[2021-03-25 03:07:38 swin_small_patch4_window7_224] INFO: number of params: 49606258 [2021-03-25 03:07:38 swin_small_patch4_window7_224] INFO: number of GFLOPs: 8.73116544 [2021-03-25 03:07:40 swin_small_patch4_window7_224] INFO: no checkpoint found in , ignoring auto resume [2021-03-25 03:07:40 swin_small_patch4_window7_224] INFO: Start training [2021-03-25 03:07:45 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 0/1251] eta: 1:50:58 lr: 0.000001 loss: 6.9417 (6.9417) grad_norm: 1.6608 (1.6608) time: 5.3222 [2021-03-25 03:07:51 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 10/1251] eta: 0:20:41 lr: 0.000001 loss: 7.0078 (6.9947) grad_norm: 1.5535 (1.5639) time: 1.0000 [2021-03-25 03:07:56 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 20/1251] eta: 0:15:49 lr: 0.000002 loss: 6.9963 (6.9949) grad_norm: 1.5386 (1.5475) time: 0.5435 [2021-03-25 03:08:01 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 30/1251] eta: 0:14:03 lr: 0.000002 loss: 6.9822 (6.9863) grad_norm: 1.5385 (1.5433) time: 0.5207 [2021-03-25 03:08:06 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 40/1251] eta: 0:13:02 lr: 0.000003 loss: 6.9500 (6.9777) grad_norm: 1.5220 (1.5318) time: 0.5155 [2021-03-25 03:08:12 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 50/1251] eta: 0:12:23 lr: 0.000003 loss: 6.9500 (6.9756) grad_norm: 1.4948 (1.5247) time: 0.5083 [2021-03-25 03:08:17 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 60/1251] eta: 0:11:57 lr: 0.000003 loss: 6.9538 (6.9726) grad_norm: 1.4822 (1.5177) time: 0.5115 [2021-03-25 03:08:22 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 70/1251] eta: 0:11:34 lr: 0.000004 loss: 6.9719 (6.9717) grad_norm: 1.4729 (1.5096) time: 0.5091 [2021-03-25 03:08:27 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 80/1251] eta: 0:11:16 lr: 0.000004 loss: 6.9546 (6.9678) grad_norm: 1.4473 (1.5018) time: 0.5042 [2021-03-25 03:08:32 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 90/1251] eta: 0:11:02 lr: 0.000005 loss: 6.9452 (6.9662) grad_norm: 1.4309 (1.4935) time: 0.5066 [2021-03-25 03:08:37 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 100/1251] eta: 0:10:48 lr: 0.000005 loss: 6.9439 (6.9630) grad_norm: 1.3722 (1.4800) time: 0.5066 [2021-03-25 03:08:42 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 110/1251] eta: 0:10:37 lr: 0.000005 loss: 6.9322 (6.9612) grad_norm: 1.3630 (1.4696) time: 0.5070 [2021-03-25 03:08:47 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 120/1251] eta: 0:10:27 lr: 0.000006 loss: 6.9440 (6.9595) grad_norm: 1.3634 (1.4603) time: 0.5089 [2021-03-25 03:08:52 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 130/1251] eta: 0:10:17 lr: 0.000006 loss: 6.9307 (6.9581) grad_norm: 1.3329 (1.4485) time: 0.5070 [2021-03-25 03:08:57 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 140/1251] eta: 0:10:08 lr: 0.000007 loss: 6.9307 (6.9557) grad_norm: 1.2873 (1.4370) time: 0.5049 [2021-03-25 03:09:02 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 150/1251] eta: 0:09:59 lr: 0.000007 loss: 6.9256 (6.9536) grad_norm: 1.2704 (1.4249) time: 0.5036 [2021-03-25 03:09:07 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 160/1251] eta: 0:09:52 lr: 0.000007 loss: 6.9298 (6.9523) grad_norm: 1.2371 (1.4119) time: 0.5082 [2021-03-25 03:09:12 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 170/1251] eta: 0:09:43 lr: 0.000008 loss: 6.9394 (6.9513) grad_norm: 1.2089 (1.3981) time: 0.5059 [2021-03-25 03:09:17 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 180/1251] eta: 0:09:36 lr: 0.000008 loss: 6.9328 (6.9502) grad_norm: 1.1756 (1.3860) time: 0.5010 [2021-03-25 03:09:22 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 190/1251] eta: 0:09:29 lr: 0.000009 loss: 6.9288 (6.9488) grad_norm: 1.1523 (1.3724) time: 0.5061 [2021-03-25 03:09:28 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 200/1251] eta: 0:09:22 lr: 0.000009 loss: 6.9087 (6.9462) grad_norm: 1.1281 (1.3603) time: 0.5078 [2021-03-25 03:09:33 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 210/1251] eta: 0:09:16 lr: 0.000009 loss: 6.9057 (6.9450) grad_norm: 1.1114 (1.3473) time: 0.5135 [2021-03-25 03:09:38 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 220/1251] eta: 0:09:09 lr: 0.000010 loss: 6.9227 (6.9437) grad_norm: 1.0800 (1.3351) time: 0.5118 [2021-03-25 03:09:43 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 230/1251] eta: 0:09:03 lr: 0.000010 loss: 6.9183 (6.9423) grad_norm: 1.0645 (1.3234) time: 0.5073 [2021-03-25 03:09:48 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 240/1251] eta: 0:08:57 lr: 0.000011 loss: 6.9030 (6.9406) grad_norm: 1.0521 (1.3114) time: 0.5114 [2021-03-25 03:09:53 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 250/1251] eta: 0:08:50 lr: 0.000011 loss: 6.9014 (6.9388) grad_norm: 1.0318 (1.3004) time: 0.5084 [2021-03-25 03:09:58 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 260/1251] eta: 0:08:44 lr: 0.000011 loss: 6.9017 (6.9373) grad_norm: 1.0166 (1.2892) time: 0.5065 [2021-03-25 03:10:03 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 270/1251] eta: 0:08:38 lr: 0.000012 loss: 6.9001 (6.9359) grad_norm: 1.0133 (1.2789) time: 0.5070 [2021-03-25 03:10:08 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 280/1251] eta: 0:08:32 lr: 0.000012 loss: 6.9006 (6.9353) grad_norm: 0.9893 (1.2682) time: 0.5067 [2021-03-25 03:10:13 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 290/1251] eta: 0:08:26 lr: 0.000013 loss: 6.9092 (6.9343) grad_norm: 0.9768 (1.2586) time: 0.5073 [2021-03-25 03:10:18 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 300/1251] eta: 0:08:20 lr: 0.000013 loss: 6.8964 (6.9332) grad_norm: 0.9649 (1.2483) time: 0.5076 [2021-03-25 03:10:23 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 310/1251] eta: 0:08:14 lr: 0.000013 loss: 6.8993 (6.9323) grad_norm: 0.9404 (1.2386) time: 0.5064 [2021-03-25 03:10:29 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 320/1251] eta: 0:08:08 lr: 0.000014 loss: 6.8968 (6.9305) grad_norm: 0.9375 (1.2293) time: 0.5078 [2021-03-25 03:10:34 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 330/1251] eta: 0:08:03 lr: 0.000014 loss: 6.8828 (6.9292) grad_norm: 0.9353 (1.2208) time: 0.5127 [2021-03-25 03:10:39 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 340/1251] eta: 0:07:57 lr: 0.000015 loss: 6.8914 (6.9280) grad_norm: 0.9336 (1.2123) time: 0.5066 [2021-03-25 03:10:44 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 350/1251] eta: 0:07:51 lr: 0.000015 loss: 6.8986 (6.9271) grad_norm: 0.9313 (1.2041) time: 0.5020 [2021-03-25 03:10:49 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 360/1251] eta: 0:07:46 lr: 0.000015 loss: 6.8854 (6.9262) grad_norm: 0.9090 (1.1957) time: 0.5052 [2021-03-25 03:10:54 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 370/1251] eta: 0:07:40 lr: 0.000016 loss: 6.8854 (6.9252) grad_norm: 0.8984 (1.1878) time: 0.5040 [2021-03-25 03:10:59 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 380/1251] eta: 0:07:34 lr: 0.000016 loss: 6.8805 (6.9238) grad_norm: 0.8943 (1.1803) time: 0.5044 [2021-03-25 03:11:04 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 390/1251] eta: 0:07:29 lr: 0.000017 loss: 6.8801 (6.9228) grad_norm: 0.9028 (1.1736) time: 0.5051 [2021-03-25 03:11:09 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 400/1251] eta: 0:07:23 lr: 0.000017 loss: 6.8748 (6.9212) grad_norm: 0.8949 (1.1668) time: 0.5033 [2021-03-25 03:11:14 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 410/1251] eta: 0:07:17 lr: 0.000017 loss: 6.8762 (6.9204) grad_norm: 0.8915 (1.1602) time: 0.5028 [2021-03-25 03:11:19 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 420/1251] eta: 0:07:12 lr: 0.000018 loss: 6.8897 (6.9195) grad_norm: 0.8832 (1.1539) time: 0.5059 [2021-03-25 03:11:24 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 430/1251] eta: 0:07:07 lr: 0.000018 loss: 6.8833 (6.9186) grad_norm: 0.8832 (1.1479) time: 0.5099 [2021-03-25 03:11:29 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 440/1251] eta: 0:07:01 lr: 0.000019 loss: 6.8834 (6.9177) grad_norm: 0.8793 (1.1416) time: 0.5028 [2021-03-25 03:11:34 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 450/1251] eta: 0:06:56 lr: 0.000019 loss: 6.8834 (6.9169) grad_norm: 0.8793 (1.1360) time: 0.5010 [2021-03-25 03:11:39 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 460/1251] eta: 0:06:50 lr: 0.000019 loss: 6.8528 (6.9155) grad_norm: 0.8912 (1.1309) time: 0.5053 [2021-03-25 03:11:44 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 470/1251] eta: 0:06:45 lr: 0.000020 loss: 6.8503 (6.9142) grad_norm: 0.8936 (1.1260) time: 0.5068 [2021-03-25 03:11:49 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 480/1251] eta: 0:06:39 lr: 0.000020 loss: 6.8563 (6.9130) grad_norm: 0.8604 (1.1206) time: 0.5089 [2021-03-25 03:11:55 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 490/1251] eta: 0:06:34 lr: 0.000021 loss: 6.8471 (6.9119) grad_norm: 0.8474 (1.1150) time: 0.5058 [2021-03-25 03:12:00 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 500/1251] eta: 0:06:29 lr: 0.000021 loss: 6.8471 (6.9107) grad_norm: 0.8537 (1.1101) time: 0.5066 [2021-03-25 03:12:05 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 510/1251] eta: 0:06:23 lr: 0.000021 loss: 6.8613 (6.9099) grad_norm: 0.8612 (1.1056) time: 0.5109 [2021-03-25 03:12:10 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 520/1251] eta: 0:06:18 lr: 0.000022 loss: 6.8613 (6.9089) grad_norm: 0.8710 (1.1014) time: 0.5111 [2021-03-25 03:12:15 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 530/1251] eta: 0:06:13 lr: 0.000022 loss: 6.8540 (6.9076) grad_norm: 0.8588 (1.0967) time: 0.5099 [2021-03-25 03:12:20 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 540/1251] eta: 0:06:07 lr: 0.000023 loss: 6.8540 (6.9066) grad_norm: 0.8447 (1.0926) time: 0.5073 [2021-03-25 03:12:25 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 550/1251] eta: 0:06:02 lr: 0.000023 loss: 6.8557 (6.9058) grad_norm: 0.8385 (1.0882) time: 0.5041 [2021-03-25 03:12:30 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 560/1251] eta: 0:05:57 lr: 0.000023 loss: 6.8729 (6.9052) grad_norm: 0.8606 (1.0856) time: 0.5067 [2021-03-25 03:12:35 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 570/1251] eta: 0:05:52 lr: 0.000024 loss: 6.8711 (6.9042) grad_norm: 0.8675 (1.0818) time: 0.5089 [2021-03-25 03:12:40 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 580/1251] eta: 0:05:46 lr: 0.000024 loss: 6.8403 (6.9032) grad_norm: 0.8375 (1.0783) time: 0.5109 [2021-03-25 03:12:46 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 590/1251] eta: 0:05:41 lr: 0.000025 loss: 6.8442 (6.9022) grad_norm: 0.8687 (1.0751) time: 0.5141 [2021-03-25 03:12:51 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 600/1251] eta: 0:05:36 lr: 0.000025 loss: 6.8424 (6.9011) grad_norm: 0.8795 (1.0725) time: 0.5098 [2021-03-25 03:12:56 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 610/1251] eta: 0:05:30 lr: 0.000025 loss: 6.8430 (6.9002) grad_norm: 0.8458 (1.0687) time: 0.5033 [2021-03-25 03:13:01 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 620/1251] eta: 0:05:25 lr: 0.000026 loss: 6.8532 (6.8994) grad_norm: 0.8414 (1.0659) time: 0.5040 [2021-03-25 03:13:06 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 630/1251] eta: 0:05:20 lr: 0.000026 loss: 6.8542 (6.8987) grad_norm: 0.9217 (1.0643) time: 0.5081 [2021-03-25 03:13:11 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 640/1251] eta: 0:05:15 lr: 0.000027 loss: 6.8564 (6.8979) grad_norm: 0.9265 (1.0627) time: 0.5050 [2021-03-25 03:13:16 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 650/1251] eta: 0:05:09 lr: 0.000027 loss: 6.8450 (6.8971) grad_norm: 0.9738 (1.0641) time: 0.5033 [2021-03-25 03:13:21 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 660/1251] eta: 0:05:04 lr: 0.000027 loss: 6.8276 (6.8956) grad_norm: 1.0394 (1.0634) time: 0.5042 [2021-03-25 03:13:26 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 670/1251] eta: 0:04:59 lr: 0.000028 loss: 6.8118 (6.8945) grad_norm: 1.0037 (1.0633) time: 0.5011 [2021-03-25 03:13:31 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 680/1251] eta: 0:04:54 lr: 0.000028 loss: 6.8357 (6.8938) grad_norm: 1.0037 (1.0639) time: 0.5021 [2021-03-25 03:13:36 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 690/1251] eta: 0:04:48 lr: 0.000029 loss: 6.8220 (6.8926) grad_norm: 1.0534 (1.0651) time: 0.5051 [2021-03-25 03:13:41 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 700/1251] eta: 0:04:43 lr: 0.000029 loss: 6.8176 (6.8914) grad_norm: 1.1049 (1.0664) time: 0.5017 [2021-03-25 03:13:46 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 710/1251] eta: 0:04:38 lr: 0.000029 loss: 6.8176 (6.8904) grad_norm: 1.1025 (1.0673) time: 0.5033 [2021-03-25 03:13:51 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 720/1251] eta: 0:04:33 lr: 0.000030 loss: 6.8205 (6.8895) grad_norm: 1.1339 (1.0685) time: 0.5076 [2021-03-25 03:13:56 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 730/1251] eta: 0:04:28 lr: 0.000030 loss: 6.8219 (6.8885) grad_norm: 1.1764 (1.0712) time: 0.5058 [2021-03-25 03:14:01 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 740/1251] eta: 0:04:22 lr: 0.000031 loss: 6.8330 (6.8878) grad_norm: 1.0669 (1.0721) time: 0.5067 [2021-03-25 03:14:06 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 750/1251] eta: 0:04:17 lr: 0.000031 loss: 6.8258 (6.8869) grad_norm: 1.0925 (1.0740) time: 0.5116 [2021-03-25 03:14:12 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 760/1251] eta: 0:04:12 lr: 0.000031 loss: 6.8186 (6.8861) grad_norm: 1.0925 (1.0750) time: 0.5151 [2021-03-25 03:14:17 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 770/1251] eta: 0:04:07 lr: 0.000032 loss: 6.8254 (6.8854) grad_norm: 1.0788 (1.0769) time: 0.5227 [2021-03-25 03:14:22 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 780/1251] eta: 0:04:02 lr: 0.000032 loss: 6.8141 (6.8846) grad_norm: 1.1406 (1.0783) time: 0.5166 [2021-03-25 03:14:27 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 790/1251] eta: 0:03:57 lr: 0.000033 loss: 6.7944 (6.8835) grad_norm: 1.1749 (1.0802) time: 0.5081 [2021-03-25 03:14:32 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 800/1251] eta: 0:03:51 lr: 0.000033 loss: 6.8013 (6.8824) grad_norm: 1.2827 (1.0849) time: 0.5082 [2021-03-25 03:14:37 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 810/1251] eta: 0:03:46 lr: 0.000033 loss: 6.7718 (6.8807) grad_norm: 1.2823 (1.0868) time: 0.5004 [2021-03-25 03:14:42 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 820/1251] eta: 0:03:41 lr: 0.000034 loss: 6.7718 (6.8799) grad_norm: 1.2823 (1.0910) time: 0.5053 [2021-03-25 03:14:47 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 830/1251] eta: 0:03:36 lr: 0.000034 loss: 6.8030 (6.8788) grad_norm: 1.3235 (1.0942) time: 0.5095 [2021-03-25 03:14:52 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 840/1251] eta: 0:03:31 lr: 0.000035 loss: 6.7889 (6.8777) grad_norm: 1.2760 (1.0980) time: 0.5067 [2021-03-25 03:14:57 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 850/1251] eta: 0:03:25 lr: 0.000035 loss: 6.7943 (6.8766) grad_norm: 1.3149 (1.1023) time: 0.5025 [2021-03-25 03:15:02 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 860/1251] eta: 0:03:20 lr: 0.000035 loss: 6.7749 (6.8753) grad_norm: 1.3234 (1.1075) time: 0.5007 [2021-03-25 03:15:07 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 870/1251] eta: 0:03:15 lr: 0.000036 loss: 6.7939 (6.8744) grad_norm: 1.4688 (1.1124) time: 0.5039 [2021-03-25 03:15:12 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 880/1251] eta: 0:03:10 lr: 0.000036 loss: 6.7759 (6.8732) grad_norm: 1.5372 (1.1165) time: 0.5048 [2021-03-25 03:15:17 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 890/1251] eta: 0:03:05 lr: 0.000037 loss: 6.7718 (6.8719) grad_norm: 1.3919 (1.1189) time: 0.5055 [2021-03-25 03:15:22 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 900/1251] eta: 0:03:00 lr: 0.000037 loss: 6.7579 (6.8707) grad_norm: 1.3398 (1.1215) time: 0.5038 [2021-03-25 03:15:27 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 910/1251] eta: 0:02:54 lr: 0.000037 loss: 6.7580 (6.8697) grad_norm: 1.3453 (1.1244) time: 0.4998 [2021-03-25 03:15:33 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 920/1251] eta: 0:02:49 lr: 0.000038 loss: 6.7629 (6.8684) grad_norm: 1.3316 (1.1260) time: 0.5037 [2021-03-25 03:15:38 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 930/1251] eta: 0:02:44 lr: 0.000038 loss: 6.7703 (6.8675) grad_norm: 1.2309 (1.1279) time: 0.5079 [2021-03-25 03:15:43 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 940/1251] eta: 0:02:39 lr: 0.000039 loss: 6.7647 (6.8660) grad_norm: 1.3750 (1.1327) time: 0.5066 [2021-03-25 03:15:48 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 950/1251] eta: 0:02:34 lr: 0.000039 loss: 6.7204 (6.8644) grad_norm: 1.5465 (1.1376) time: 0.5131 [2021-03-25 03:15:53 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 960/1251] eta: 0:02:29 lr: 0.000039 loss: 6.7279 (6.8633) grad_norm: 1.5126 (1.1412) time: 0.5147 [2021-03-25 03:15:58 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 970/1251] eta: 0:02:24 lr: 0.000040 loss: 6.7430 (6.8623) grad_norm: 1.4290 (1.1436) time: 0.5065 [2021-03-25 03:16:03 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 980/1251] eta: 0:02:18 lr: 0.000040 loss: 6.7710 (6.8615) grad_norm: 1.3472 (1.1466) time: 0.5014 [2021-03-25 03:16:08 swin_small_patch4_window7_224] INFO: Epoch: [0] [ 990/1251] eta: 0:02:13 lr: 0.000041 loss: 6.7730 (6.8602) grad_norm: 1.3781 (1.1505) time: 0.5023 [2021-03-25 03:16:13 swin_small_patch4_window7_224] INFO: Epoch: [0] [1000/1251] eta: 0:02:08 lr: 0.000041 loss: 6.7454 (6.8590) grad_norm: 1.5279 (1.1544) time: 0.5039 [2021-03-25 03:16:18 swin_small_patch4_window7_224] INFO: Epoch: [0] [1010/1251] eta: 0:02:03 lr: 0.000041 loss: 6.7803 (6.8584) grad_norm: 1.5279 (1.1589) time: 0.5031 [2021-03-25 03:16:23 swin_small_patch4_window7_224] INFO: Epoch: [0] [1020/1251] eta: 0:01:58 lr: 0.000042 loss: 6.7758 (6.8572) grad_norm: 1.4602 (1.1613) time: 0.5055 [2021-03-25 03:16:28 swin_small_patch4_window7_224] INFO: Epoch: [0] [1030/1251] eta: 0:01:53 lr: 0.000042 loss: 6.7268 (6.8561) grad_norm: 1.4182 (1.1660) time: 0.5058 [2021-03-25 03:16:33 swin_small_patch4_window7_224] INFO: Epoch: [0] [1040/1251] eta: 0:01:48 lr: 0.000043 loss: 6.7689 (6.8554) grad_norm: 1.6105 (1.1727) time: 0.5097 [2021-03-25 03:16:38 swin_small_patch4_window7_224] INFO: Epoch: [0] [1050/1251] eta: 0:01:42 lr: 0.000043 loss: 6.7629 (6.8541) grad_norm: 1.7270 (1.1775) time: 0.5123 [2021-03-25 03:16:44 swin_small_patch4_window7_224] INFO: Epoch: [0] [1060/1251] eta: 0:01:37 lr: 0.000043 loss: 6.7282 (6.8531) grad_norm: 1.6921 (1.1835) time: 0.5055 [2021-03-25 03:16:49 swin_small_patch4_window7_224] INFO: Epoch: [0] [1070/1251] eta: 0:01:32 lr: 0.000044 loss: 6.7494 (6.8520) grad_norm: 1.6921 (1.1880) time: 0.5031 [2021-03-25 03:16:54 swin_small_patch4_window7_224] INFO: Epoch: [0] [1080/1251] eta: 0:01:27 lr: 0.000044 loss: 6.7322 (6.8510) grad_norm: 1.8266 (1.1948) time: 0.5058 [2021-03-25 03:16:59 swin_small_patch4_window7_224] INFO: Epoch: [0] [1090/1251] eta: 0:01:22 lr: 0.000045 loss: 6.7230 (6.8495) grad_norm: 1.7683 (1.1997) time: 0.5063 [2021-03-25 03:17:04 swin_small_patch4_window7_224] INFO: Epoch: [0] [1100/1251] eta: 0:01:17 lr: 0.000045 loss: 6.7058 (6.8482) grad_norm: 1.6597 (1.2041) time: 0.5073 [2021-03-25 03:17:09 swin_small_patch4_window7_224] INFO: Epoch: [0] [1110/1251] eta: 0:01:12 lr: 0.000045 loss: 6.7004 (6.8469) grad_norm: 1.6147 (1.2083) time: 0.5091 [2021-03-25 03:17:14 swin_small_patch4_window7_224] INFO: Epoch: [0] [1120/1251] eta: 0:01:07 lr: 0.000046 loss: 6.7251 (6.8460) grad_norm: 1.5535 (1.2109) time: 0.5098 [2021-03-25 03:17:19 swin_small_patch4_window7_224] INFO: Epoch: [0] [1130/1251] eta: 0:01:01 lr: 0.000046 loss: 6.7251 (6.8447) grad_norm: 1.4614 (1.2148) time: 0.5087 [2021-03-25 03:17:24 swin_small_patch4_window7_224] INFO: Epoch: [0] [1140/1251] eta: 0:00:56 lr: 0.000047 loss: 6.7093 (6.8434) grad_norm: 1.4805 (1.2175) time: 0.5066 [2021-03-25 03:17:29 swin_small_patch4_window7_224] INFO: Epoch: [0] [1150/1251] eta: 0:00:51 lr: 0.000047 loss: 6.7093 (6.8422) grad_norm: 1.5848 (1.2213) time: 0.5045 [2021-03-25 03:17:34 swin_small_patch4_window7_224] INFO: Epoch: [0] [1160/1251] eta: 0:00:46 lr: 0.000047 loss: 6.7167 (6.8410) grad_norm: 1.6907 (1.2245) time: 0.4993 [2021-03-25 03:17:39 swin_small_patch4_window7_224] INFO: Epoch: [0] [1170/1251] eta: 0:00:41 lr: 0.000048 loss: 6.7167 (6.8397) grad_norm: 1.6409 (1.2293) time: 0.4998 [2021-03-25 03:17:44 swin_small_patch4_window7_224] INFO: Epoch: [0] [1180/1251] eta: 0:00:36 lr: 0.000048 loss: 6.7020 (6.8385) grad_norm: 1.7676 (1.2336) time: 0.5054 [2021-03-25 03:17:49 swin_small_patch4_window7_224] INFO: Epoch: [0] [1190/1251] eta: 0:00:31 lr: 0.000049 loss: 6.7179 (6.8376) grad_norm: 1.6435 (1.2372) time: 0.5038 [2021-03-25 03:17:54 swin_small_patch4_window7_224] INFO: Epoch: [0] [1200/1251] eta: 0:00:26 lr: 0.000049 loss: 6.7190 (6.8366) grad_norm: 1.5421 (1.2407) time: 0.5043 [2021-03-25 03:17:59 swin_small_patch4_window7_224] INFO: Epoch: [0] [1210/1251] eta: 0:00:20 lr: 0.000049 loss: 6.7446 (6.8357) grad_norm: 1.8699 (1.2473) time: 0.5046 [2021-03-25 03:18:04 swin_small_patch4_window7_224] INFO: Epoch: [0] [1220/1251] eta: 0:00:15 lr: 0.000050 loss: 6.7257 (6.8346) grad_norm: 1.8699 (1.2519) time: 0.5047 [2021-03-25 03:18:09 swin_small_patch4_window7_224] INFO: Epoch: [0] [1230/1251] eta: 0:00:10 lr: 0.000050 loss: 6.7098 (6.8336) grad_norm: 1.8317 (1.2579) time: 0.5037 [2021-03-25 03:18:14 swin_small_patch4_window7_224] INFO: Epoch: [0] [1240/1251] eta: 0:00:05 lr: 0.000051 loss: 6.6928 (6.8324) grad_norm: 1.9681 (1.2640) time: 0.4994 [2021-03-25 03:18:19 swin_small_patch4_window7_224] INFO: Epoch: [0] [1250/1251] eta: 0:00:00 lr: 0.000051 loss: 6.6793 (6.8310) grad_norm: 1.8891 (1.2699) time: 0.5012 [2021-03-25 03:18:56 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 6.3356 (6.3356) acc1: 0.0000 (0.0000) acc5: 6.2500 (6.2500) [2021-03-25 03:18:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 6.2761 (6.2554) acc1: 1.5625 (2.8409) acc5: 7.8125 (7.9545) [2021-03-25 03:18:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 6.2600 (6.2571) acc1: 3.1250 (2.8274) acc5: 7.8125 (8.0357) [2021-03-25 03:18:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 6.2673 (6.2673) acc1: 1.5625 (2.5706) acc5: 7.8125 (7.8125) [2021-03-25 03:19:00 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 6.2855 (6.2740) acc1: 1.5625 (2.5534) acc5: 7.8125 (7.5838) [2021-03-25 03:19:01 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 6.3116 (6.2785) acc1: 1.5625 (2.3680) acc5: 7.8125 (7.4880) [2021-03-25 03:19:02 swin_small_patch4_window7_224] INFO: * Acc@1 2.198 Acc@5 7.078 loss 6.283 [2021-03-25 03:19:02 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 2.2% [2021-03-25 03:19:02 swin_small_patch4_window7_224] INFO: Max accuracy: 2.20% [2021-03-25 03:19:06 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 0/1251] eta: 1:36:59 lr: 0.000051 loss: 6.6107 (6.6107) grad_norm: 1.7826 (1.7826) time: 4.6519 [2021-03-25 03:19:11 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 10/1251] eta: 0:18:13 lr: 0.000051 loss: 6.6649 (6.6716) grad_norm: 1.5427 (1.7293) time: 0.8811 [2021-03-25 03:19:16 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 20/1251] eta: 0:14:22 lr: 0.000052 loss: 6.6649 (6.6776) grad_norm: 1.5721 (1.7455) time: 0.5034 [2021-03-25 03:19:21 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 30/1251] eta: 0:13:00 lr: 0.000052 loss: 6.6876 (6.6877) grad_norm: 1.6099 (1.7175) time: 0.5057 [2021-03-25 03:19:26 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 40/1251] eta: 0:12:13 lr: 0.000053 loss: 6.7019 (6.6889) grad_norm: 1.6932 (1.7551) time: 0.5063 [2021-03-25 03:19:32 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 50/1251] eta: 0:11:45 lr: 0.000053 loss: 6.6721 (6.6926) grad_norm: 1.7948 (1.7793) time: 0.5068 [2021-03-25 03:19:37 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 60/1251] eta: 0:11:25 lr: 0.000053 loss: 6.6648 (6.6834) grad_norm: 1.4543 (1.7203) time: 0.5130 [2021-03-25 03:19:42 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 70/1251] eta: 0:11:06 lr: 0.000054 loss: 6.5829 (6.6653) grad_norm: 1.4280 (1.7026) time: 0.5064 [2021-03-25 03:19:47 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 80/1251] eta: 0:10:51 lr: 0.000054 loss: 6.6270 (6.6681) grad_norm: 1.5881 (1.7302) time: 0.4967 [2021-03-25 03:19:52 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 90/1251] eta: 0:10:40 lr: 0.000055 loss: 6.6873 (6.6734) grad_norm: 1.7792 (1.7549) time: 0.5063 [2021-03-25 03:19:57 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 100/1251] eta: 0:10:29 lr: 0.000055 loss: 6.6695 (6.6739) grad_norm: 1.9863 (1.7844) time: 0.5102 [2021-03-25 03:20:02 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 110/1251] eta: 0:10:19 lr: 0.000055 loss: 6.6530 (6.6723) grad_norm: 1.9090 (1.7842) time: 0.5028 [2021-03-25 03:20:07 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 120/1251] eta: 0:10:10 lr: 0.000056 loss: 6.6648 (6.6725) grad_norm: 1.6620 (1.7787) time: 0.5036 [2021-03-25 03:20:12 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 130/1251] eta: 0:10:02 lr: 0.000056 loss: 6.6502 (6.6713) grad_norm: 1.6609 (1.7866) time: 0.5086 [2021-03-25 03:20:17 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 140/1251] eta: 0:09:54 lr: 0.000057 loss: 6.6535 (6.6678) grad_norm: 1.7309 (1.7938) time: 0.5086 [2021-03-25 03:20:22 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 150/1251] eta: 0:09:46 lr: 0.000057 loss: 6.6737 (6.6692) grad_norm: 1.9141 (1.8144) time: 0.5030 [2021-03-25 03:20:27 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 160/1251] eta: 0:09:39 lr: 0.000057 loss: 6.6737 (6.6706) grad_norm: 1.9803 (1.8336) time: 0.5033 [2021-03-25 03:20:32 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 170/1251] eta: 0:09:32 lr: 0.000058 loss: 6.6541 (6.6701) grad_norm: 1.9351 (1.8404) time: 0.5040 [2021-03-25 03:20:37 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 180/1251] eta: 0:09:25 lr: 0.000058 loss: 6.6401 (6.6669) grad_norm: 1.7432 (1.8468) time: 0.5031 [2021-03-25 03:20:42 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 190/1251] eta: 0:09:19 lr: 0.000059 loss: 6.6002 (6.6643) grad_norm: 1.7356 (1.8473) time: 0.5069 [2021-03-25 03:20:47 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 200/1251] eta: 0:09:13 lr: 0.000059 loss: 6.6002 (6.6617) grad_norm: 1.7356 (1.8475) time: 0.5084 [2021-03-25 03:20:52 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 210/1251] eta: 0:09:06 lr: 0.000059 loss: 6.6092 (6.6601) grad_norm: 1.6671 (1.8421) time: 0.5039 [2021-03-25 03:20:57 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 220/1251] eta: 0:09:00 lr: 0.000060 loss: 6.6165 (6.6581) grad_norm: 1.8141 (1.8518) time: 0.4999 [2021-03-25 03:21:03 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 230/1251] eta: 0:08:54 lr: 0.000060 loss: 6.6058 (6.6560) grad_norm: 1.6950 (1.8395) time: 0.5033 [2021-03-25 03:21:08 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 240/1251] eta: 0:08:48 lr: 0.000061 loss: 6.5385 (6.6522) grad_norm: 1.6950 (1.8485) time: 0.5083 [2021-03-25 03:21:13 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 250/1251] eta: 0:08:42 lr: 0.000061 loss: 6.5845 (6.6504) grad_norm: 1.9056 (1.8493) time: 0.5064 [2021-03-25 03:21:18 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 260/1251] eta: 0:08:36 lr: 0.000061 loss: 6.6259 (6.6524) grad_norm: 1.7788 (1.8454) time: 0.5027 [2021-03-25 03:21:23 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 270/1251] eta: 0:08:30 lr: 0.000062 loss: 6.6624 (6.6516) grad_norm: 1.7129 (1.8418) time: 0.5046 [2021-03-25 03:21:28 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 280/1251] eta: 0:08:24 lr: 0.000062 loss: 6.6277 (6.6505) grad_norm: 1.6855 (1.8339) time: 0.5024 [2021-03-25 03:21:33 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 290/1251] eta: 0:08:18 lr: 0.000063 loss: 6.5841 (6.6491) grad_norm: 1.5086 (1.8238) time: 0.5003 [2021-03-25 03:21:38 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 300/1251] eta: 0:08:13 lr: 0.000063 loss: 6.5434 (6.6466) grad_norm: 1.5831 (1.8249) time: 0.5003 [2021-03-25 03:21:43 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 310/1251] eta: 0:08:07 lr: 0.000063 loss: 6.5635 (6.6448) grad_norm: 1.7190 (1.8270) time: 0.4994 [2021-03-25 03:21:48 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 320/1251] eta: 0:08:01 lr: 0.000064 loss: 6.5803 (6.6425) grad_norm: 1.9666 (1.8358) time: 0.5023 [2021-03-25 03:21:53 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 330/1251] eta: 0:07:56 lr: 0.000064 loss: 6.5803 (6.6405) grad_norm: 1.7655 (1.8317) time: 0.5041 [2021-03-25 03:21:58 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 340/1251] eta: 0:07:50 lr: 0.000065 loss: 6.5961 (6.6398) grad_norm: 1.5673 (1.8261) time: 0.5006 [2021-03-25 03:22:03 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 350/1251] eta: 0:07:44 lr: 0.000065 loss: 6.6111 (6.6401) grad_norm: 1.5890 (1.8222) time: 0.4988 [2021-03-25 03:22:08 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 360/1251] eta: 0:07:39 lr: 0.000065 loss: 6.6053 (6.6390) grad_norm: 1.5535 (1.8150) time: 0.5009 [2021-03-25 03:22:13 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 370/1251] eta: 0:07:33 lr: 0.000066 loss: 6.5913 (6.6371) grad_norm: 1.5294 (1.8124) time: 0.5001 [2021-03-25 03:22:18 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 380/1251] eta: 0:07:28 lr: 0.000066 loss: 6.5948 (6.6367) grad_norm: 1.8135 (1.8137) time: 0.5019 [2021-03-25 03:22:23 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 390/1251] eta: 0:07:23 lr: 0.000067 loss: 6.6125 (6.6351) grad_norm: 1.8135 (1.8110) time: 0.5031 [2021-03-25 03:22:28 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 400/1251] eta: 0:07:17 lr: 0.000067 loss: 6.5556 (6.6315) grad_norm: 1.7600 (1.8129) time: 0.5054 [2021-03-25 03:22:33 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 410/1251] eta: 0:07:12 lr: 0.000067 loss: 6.4723 (6.6285) grad_norm: 1.8251 (1.8117) time: 0.5073 [2021-03-25 03:22:38 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 420/1251] eta: 0:07:07 lr: 0.000068 loss: 6.4723 (6.6267) grad_norm: 1.7864 (1.8128) time: 0.5030 [2021-03-25 03:22:43 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 430/1251] eta: 0:07:01 lr: 0.000068 loss: 6.6351 (6.6260) grad_norm: 1.8087 (1.8135) time: 0.4999 [2021-03-25 03:22:48 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 440/1251] eta: 0:06:56 lr: 0.000069 loss: 6.6058 (6.6254) grad_norm: 1.7736 (1.8105) time: 0.4980 [2021-03-25 03:22:53 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 450/1251] eta: 0:06:50 lr: 0.000069 loss: 6.6009 (6.6253) grad_norm: 1.7536 (1.8136) time: 0.5022 [2021-03-25 03:22:58 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 460/1251] eta: 0:06:45 lr: 0.000069 loss: 6.5254 (6.6234) grad_norm: 1.7945 (1.8171) time: 0.5033 [2021-03-25 03:23:03 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 470/1251] eta: 0:06:40 lr: 0.000070 loss: 6.5171 (6.6212) grad_norm: 1.7704 (1.8136) time: 0.5026 [2021-03-25 03:23:08 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 480/1251] eta: 0:06:35 lr: 0.000070 loss: 6.6018 (6.6219) grad_norm: 1.8615 (1.8205) time: 0.5041 [2021-03-25 03:23:13 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 490/1251] eta: 0:06:29 lr: 0.000071 loss: 6.6180 (6.6201) grad_norm: 1.9856 (1.8213) time: 0.5065 [2021-03-25 03:23:18 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 500/1251] eta: 0:06:24 lr: 0.000071 loss: 6.5580 (6.6188) grad_norm: 1.9044 (1.8233) time: 0.5061 [2021-03-25 03:23:23 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 510/1251] eta: 0:06:19 lr: 0.000071 loss: 6.5686 (6.6185) grad_norm: 1.8620 (1.8251) time: 0.5005 [2021-03-25 03:23:28 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 520/1251] eta: 0:06:13 lr: 0.000072 loss: 6.6038 (6.6179) grad_norm: 1.7558 (1.8246) time: 0.4990 [2021-03-25 03:23:33 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 530/1251] eta: 0:06:08 lr: 0.000072 loss: 6.6046 (6.6180) grad_norm: 1.7730 (1.8258) time: 0.5037 [2021-03-25 03:23:39 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 540/1251] eta: 0:06:03 lr: 0.000073 loss: 6.6046 (6.6164) grad_norm: 1.7996 (1.8247) time: 0.5125 [2021-03-25 03:23:44 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 550/1251] eta: 0:05:58 lr: 0.000073 loss: 6.5815 (6.6157) grad_norm: 1.6565 (1.8233) time: 0.5168 [2021-03-25 03:23:49 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 560/1251] eta: 0:05:53 lr: 0.000073 loss: 6.5815 (6.6146) grad_norm: 1.8134 (1.8230) time: 0.5092 [2021-03-25 03:23:54 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 570/1251] eta: 0:05:48 lr: 0.000074 loss: 6.5861 (6.6140) grad_norm: 1.8123 (1.8228) time: 0.5045 [2021-03-25 03:23:59 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 580/1251] eta: 0:05:43 lr: 0.000074 loss: 6.6231 (6.6138) grad_norm: 1.7683 (1.8217) time: 0.5075 [2021-03-25 03:24:04 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 590/1251] eta: 0:05:37 lr: 0.000075 loss: 6.6023 (6.6124) grad_norm: 1.9155 (1.8257) time: 0.5061 [2021-03-25 03:24:09 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 600/1251] eta: 0:05:32 lr: 0.000075 loss: 6.4905 (6.6098) grad_norm: 1.8074 (1.8235) time: 0.5075 [2021-03-25 03:24:14 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 610/1251] eta: 0:05:27 lr: 0.000075 loss: 6.4759 (6.6087) grad_norm: 1.7167 (1.8227) time: 0.5073 [2021-03-25 03:24:19 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 620/1251] eta: 0:05:22 lr: 0.000076 loss: 6.5623 (6.6069) grad_norm: 1.8465 (1.8258) time: 0.5019 [2021-03-25 03:24:24 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 630/1251] eta: 0:05:17 lr: 0.000076 loss: 6.5933 (6.6068) grad_norm: 2.0696 (1.8297) time: 0.5028 [2021-03-25 03:24:29 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 640/1251] eta: 0:05:12 lr: 0.000077 loss: 6.5099 (6.6043) grad_norm: 2.0767 (1.8367) time: 0.5039 [2021-03-25 03:24:34 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 650/1251] eta: 0:05:06 lr: 0.000077 loss: 6.5099 (6.6042) grad_norm: 2.1205 (1.8397) time: 0.5019 [2021-03-25 03:24:39 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 660/1251] eta: 0:05:01 lr: 0.000077 loss: 6.6092 (6.6041) grad_norm: 1.7811 (1.8398) time: 0.5003 [2021-03-25 03:24:44 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 670/1251] eta: 0:04:56 lr: 0.000078 loss: 6.5391 (6.6021) grad_norm: 1.7365 (1.8397) time: 0.5020 [2021-03-25 03:24:49 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 680/1251] eta: 0:04:51 lr: 0.000078 loss: 6.4805 (6.6009) grad_norm: 1.7576 (1.8401) time: 0.5050 [2021-03-25 03:24:54 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 690/1251] eta: 0:04:46 lr: 0.000079 loss: 6.4805 (6.5994) grad_norm: 1.7724 (1.8405) time: 0.5021 [2021-03-25 03:24:59 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 700/1251] eta: 0:04:40 lr: 0.000079 loss: 6.4628 (6.5979) grad_norm: 1.9287 (1.8443) time: 0.4990 [2021-03-25 03:25:04 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 710/1251] eta: 0:04:35 lr: 0.000079 loss: 6.4734 (6.5961) grad_norm: 1.9287 (1.8462) time: 0.5039 [2021-03-25 03:25:09 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 720/1251] eta: 0:04:30 lr: 0.000080 loss: 6.4469 (6.5943) grad_norm: 1.7667 (1.8438) time: 0.5065 [2021-03-25 03:25:15 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 730/1251] eta: 0:04:25 lr: 0.000080 loss: 6.4469 (6.5934) grad_norm: 1.6371 (1.8422) time: 0.5103 [2021-03-25 03:25:20 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 740/1251] eta: 0:04:20 lr: 0.000080 loss: 6.5105 (6.5925) grad_norm: 1.7449 (1.8404) time: 0.5186 [2021-03-25 03:25:25 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 750/1251] eta: 0:04:15 lr: 0.000081 loss: 6.5026 (6.5904) grad_norm: 1.7449 (1.8395) time: 0.5146 [2021-03-25 03:25:30 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 760/1251] eta: 0:04:10 lr: 0.000081 loss: 6.5269 (6.5904) grad_norm: 1.7175 (1.8385) time: 0.5052 [2021-03-25 03:25:35 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 770/1251] eta: 0:04:05 lr: 0.000082 loss: 6.5510 (6.5894) grad_norm: 1.7868 (1.8409) time: 0.5048 [2021-03-25 03:25:40 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 780/1251] eta: 0:04:00 lr: 0.000082 loss: 6.5390 (6.5891) grad_norm: 2.0012 (1.8425) time: 0.5096 [2021-03-25 03:25:45 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 790/1251] eta: 0:03:55 lr: 0.000082 loss: 6.5716 (6.5887) grad_norm: 1.9900 (1.8447) time: 0.5129 [2021-03-25 03:25:50 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 800/1251] eta: 0:03:50 lr: 0.000083 loss: 6.5329 (6.5877) grad_norm: 1.8575 (1.8448) time: 0.5136 [2021-03-25 03:25:55 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 810/1251] eta: 0:03:44 lr: 0.000083 loss: 6.4768 (6.5863) grad_norm: 1.7591 (1.8439) time: 0.5077 [2021-03-25 03:26:00 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 820/1251] eta: 0:03:39 lr: 0.000084 loss: 6.4792 (6.5855) grad_norm: 1.7481 (1.8443) time: 0.5011 [2021-03-25 03:26:05 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 830/1251] eta: 0:03:34 lr: 0.000084 loss: 6.4988 (6.5837) grad_norm: 1.8827 (1.8458) time: 0.4990 [2021-03-25 03:26:10 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 840/1251] eta: 0:03:29 lr: 0.000084 loss: 6.5119 (6.5832) grad_norm: 1.9824 (1.8504) time: 0.4987 [2021-03-25 03:26:15 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 850/1251] eta: 0:03:24 lr: 0.000085 loss: 6.5119 (6.5816) grad_norm: 2.0177 (1.8529) time: 0.5001 [2021-03-25 03:26:20 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 860/1251] eta: 0:03:19 lr: 0.000085 loss: 6.5007 (6.5809) grad_norm: 1.6684 (1.8497) time: 0.4994 [2021-03-25 03:26:25 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 870/1251] eta: 0:03:14 lr: 0.000086 loss: 6.5221 (6.5795) grad_norm: 1.6139 (1.8486) time: 0.5004 [2021-03-25 03:26:30 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 880/1251] eta: 0:03:08 lr: 0.000086 loss: 6.4901 (6.5790) grad_norm: 1.7432 (1.8476) time: 0.5081 [2021-03-25 03:26:36 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 890/1251] eta: 0:03:03 lr: 0.000086 loss: 6.5018 (6.5788) grad_norm: 1.7432 (1.8473) time: 0.5084 [2021-03-25 03:26:41 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 900/1251] eta: 0:02:58 lr: 0.000087 loss: 6.5687 (6.5783) grad_norm: 1.7212 (1.8468) time: 0.5043 [2021-03-25 03:26:46 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 910/1251] eta: 0:02:53 lr: 0.000087 loss: 6.5229 (6.5775) grad_norm: 1.7256 (1.8465) time: 0.5055 [2021-03-25 03:26:51 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 920/1251] eta: 0:02:48 lr: 0.000088 loss: 6.5179 (6.5773) grad_norm: 1.7882 (1.8468) time: 0.5030 [2021-03-25 03:26:56 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 930/1251] eta: 0:02:43 lr: 0.000088 loss: 6.5697 (6.5765) grad_norm: 1.8634 (1.8490) time: 0.5025 [2021-03-25 03:27:01 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 940/1251] eta: 0:02:38 lr: 0.000088 loss: 6.5413 (6.5760) grad_norm: 2.0546 (1.8524) time: 0.5055 [2021-03-25 03:27:06 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 950/1251] eta: 0:02:33 lr: 0.000089 loss: 6.4713 (6.5747) grad_norm: 1.9906 (1.8521) time: 0.5000 [2021-03-25 03:27:11 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 960/1251] eta: 0:02:28 lr: 0.000089 loss: 6.4492 (6.5730) grad_norm: 1.8269 (1.8516) time: 0.5017 [2021-03-25 03:27:16 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 970/1251] eta: 0:02:22 lr: 0.000090 loss: 6.4596 (6.5721) grad_norm: 1.8094 (1.8504) time: 0.5086 [2021-03-25 03:27:21 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 980/1251] eta: 0:02:17 lr: 0.000090 loss: 6.4596 (6.5706) grad_norm: 1.6762 (1.8497) time: 0.5060 [2021-03-25 03:27:26 swin_small_patch4_window7_224] INFO: Epoch: [1] [ 990/1251] eta: 0:02:12 lr: 0.000090 loss: 6.4353 (6.5691) grad_norm: 1.7624 (1.8520) time: 0.5057 [2021-03-25 03:27:31 swin_small_patch4_window7_224] INFO: Epoch: [1] [1000/1251] eta: 0:02:07 lr: 0.000091 loss: 6.4353 (6.5678) grad_norm: 1.8181 (1.8524) time: 0.5072 [2021-03-25 03:27:36 swin_small_patch4_window7_224] INFO: Epoch: [1] [1010/1251] eta: 0:02:02 lr: 0.000091 loss: 6.4526 (6.5668) grad_norm: 1.8369 (1.8525) time: 0.5081 [2021-03-25 03:27:41 swin_small_patch4_window7_224] INFO: Epoch: [1] [1020/1251] eta: 0:01:57 lr: 0.000092 loss: 6.4934 (6.5664) grad_norm: 1.8355 (1.8521) time: 0.5063 [2021-03-25 03:27:46 swin_small_patch4_window7_224] INFO: Epoch: [1] [1030/1251] eta: 0:01:52 lr: 0.000092 loss: 6.4934 (6.5664) grad_norm: 1.8487 (1.8526) time: 0.5051 [2021-03-25 03:27:51 swin_small_patch4_window7_224] INFO: Epoch: [1] [1040/1251] eta: 0:01:47 lr: 0.000092 loss: 6.4888 (6.5655) grad_norm: 1.8487 (1.8528) time: 0.5057 [2021-03-25 03:27:56 swin_small_patch4_window7_224] INFO: Epoch: [1] [1050/1251] eta: 0:01:42 lr: 0.000093 loss: 6.4439 (6.5638) grad_norm: 1.6449 (1.8516) time: 0.5070 [2021-03-25 03:28:01 swin_small_patch4_window7_224] INFO: Epoch: [1] [1060/1251] eta: 0:01:37 lr: 0.000093 loss: 6.4439 (6.5628) grad_norm: 1.8295 (1.8542) time: 0.5043 [2021-03-25 03:28:06 swin_small_patch4_window7_224] INFO: Epoch: [1] [1070/1251] eta: 0:01:32 lr: 0.000094 loss: 6.5246 (6.5631) grad_norm: 2.0649 (1.8557) time: 0.4977 [2021-03-25 03:28:11 swin_small_patch4_window7_224] INFO: Epoch: [1] [1080/1251] eta: 0:01:26 lr: 0.000094 loss: 6.6128 (6.5630) grad_norm: 1.9124 (1.8560) time: 0.4981 [2021-03-25 03:28:17 swin_small_patch4_window7_224] INFO: Epoch: [1] [1090/1251] eta: 0:01:21 lr: 0.000094 loss: 6.4974 (6.5623) grad_norm: 1.7405 (1.8551) time: 0.5077 [2021-03-25 03:28:22 swin_small_patch4_window7_224] INFO: Epoch: [1] [1100/1251] eta: 0:01:16 lr: 0.000095 loss: 6.4473 (6.5613) grad_norm: 1.7152 (1.8551) time: 0.5107 [2021-03-25 03:28:27 swin_small_patch4_window7_224] INFO: Epoch: [1] [1110/1251] eta: 0:01:11 lr: 0.000095 loss: 6.4504 (6.5605) grad_norm: 1.8389 (1.8564) time: 0.5040 [2021-03-25 03:28:32 swin_small_patch4_window7_224] INFO: Epoch: [1] [1120/1251] eta: 0:01:06 lr: 0.000096 loss: 6.4472 (6.5597) grad_norm: 1.8930 (1.8573) time: 0.5021 [2021-03-25 03:28:37 swin_small_patch4_window7_224] INFO: Epoch: [1] [1130/1251] eta: 0:01:01 lr: 0.000096 loss: 6.4710 (6.5594) grad_norm: 1.8158 (1.8570) time: 0.5005 [2021-03-25 03:28:42 swin_small_patch4_window7_224] INFO: Epoch: [1] [1140/1251] eta: 0:00:56 lr: 0.000096 loss: 6.4660 (6.5581) grad_norm: 1.7482 (1.8565) time: 0.5048 [2021-03-25 03:28:47 swin_small_patch4_window7_224] INFO: Epoch: [1] [1150/1251] eta: 0:00:51 lr: 0.000097 loss: 6.4030 (6.5571) grad_norm: 1.7943 (1.8561) time: 0.5096 [2021-03-25 03:28:52 swin_small_patch4_window7_224] INFO: Epoch: [1] [1160/1251] eta: 0:00:46 lr: 0.000097 loss: 6.4700 (6.5562) grad_norm: 1.9877 (1.8594) time: 0.5043 [2021-03-25 03:28:57 swin_small_patch4_window7_224] INFO: Epoch: [1] [1170/1251] eta: 0:00:41 lr: 0.000098 loss: 6.4131 (6.5546) grad_norm: 2.2106 (1.8626) time: 0.5064 [2021-03-25 03:29:02 swin_small_patch4_window7_224] INFO: Epoch: [1] [1180/1251] eta: 0:00:36 lr: 0.000098 loss: 6.4199 (6.5541) grad_norm: 1.9944 (1.8623) time: 0.5086 [2021-03-25 03:29:07 swin_small_patch4_window7_224] INFO: Epoch: [1] [1190/1251] eta: 0:00:30 lr: 0.000098 loss: 6.5290 (6.5536) grad_norm: 1.7015 (1.8614) time: 0.5017 [2021-03-25 03:29:12 swin_small_patch4_window7_224] INFO: Epoch: [1] [1200/1251] eta: 0:00:25 lr: 0.000099 loss: 6.5340 (6.5529) grad_norm: 1.7073 (1.8601) time: 0.4977 [2021-03-25 03:29:17 swin_small_patch4_window7_224] INFO: Epoch: [1] [1210/1251] eta: 0:00:20 lr: 0.000099 loss: 6.4370 (6.5520) grad_norm: 1.7214 (1.8589) time: 0.4973 [2021-03-25 03:29:22 swin_small_patch4_window7_224] INFO: Epoch: [1] [1220/1251] eta: 0:00:15 lr: 0.000100 loss: 6.4370 (6.5512) grad_norm: 1.8931 (1.8615) time: 0.5022 [2021-03-25 03:29:27 swin_small_patch4_window7_224] INFO: Epoch: [1] [1230/1251] eta: 0:00:10 lr: 0.000100 loss: 6.4170 (6.5501) grad_norm: 2.1264 (1.8627) time: 0.5026 [2021-03-25 03:29:32 swin_small_patch4_window7_224] INFO: Epoch: [1] [1240/1251] eta: 0:00:05 lr: 0.000100 loss: 6.4272 (6.5495) grad_norm: 2.0429 (1.8643) time: 0.5044 [2021-03-25 03:29:37 swin_small_patch4_window7_224] INFO: Epoch: [1] [1250/1251] eta: 0:00:00 lr: 0.000101 loss: 6.4272 (6.5485) grad_norm: 1.8125 (1.8633) time: 0.5019 [2021-03-25 03:29:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 5.6422 (5.6422) acc1: 9.3750 (9.3750) acc5: 18.7500 (18.7500) [2021-03-25 03:29:43 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 5.6311 (5.6464) acc1: 6.2500 (4.8295) acc5: 12.5000 (12.7841) [2021-03-25 03:29:46 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 5.6044 (5.6290) acc1: 4.6875 (5.2083) acc5: 14.0625 (15.1042) [2021-03-25 03:29:48 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 5.6168 (5.6503) acc1: 4.6875 (5.0403) acc5: 14.0625 (14.5665) [2021-03-25 03:29:49 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 5.6037 (5.6384) acc1: 4.6875 (5.0305) acc5: 14.0625 (14.8247) [2021-03-25 03:29:50 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 5.6037 (5.6399) acc1: 4.6875 (5.1200) acc5: 14.0625 (14.9760) [2021-03-25 03:29:52 swin_small_patch4_window7_224] INFO: * Acc@1 5.082 Acc@5 15.248 loss 5.638 [2021-03-25 03:29:52 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 5.1% [2021-03-25 03:29:52 swin_small_patch4_window7_224] INFO: Max accuracy: 5.08% [2021-03-25 03:29:56 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 0/1251] eta: 1:29:46 lr: 0.000101 loss: 6.3386 (6.3386) grad_norm: 1.9003 (1.9003) time: 4.3060 [2021-03-25 03:30:01 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 10/1251] eta: 0:17:56 lr: 0.000101 loss: 6.4139 (6.3969) grad_norm: 1.8822 (1.8861) time: 0.8672 [2021-03-25 03:30:06 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 20/1251] eta: 0:14:16 lr: 0.000102 loss: 6.4553 (6.4261) grad_norm: 1.8822 (1.9587) time: 0.5154 [2021-03-25 03:30:11 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 30/1251] eta: 0:12:53 lr: 0.000102 loss: 6.4635 (6.4388) grad_norm: 1.7800 (1.9102) time: 0.5053 [2021-03-25 03:30:17 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 40/1251] eta: 0:12:11 lr: 0.000102 loss: 6.4378 (6.4297) grad_norm: 1.7779 (1.8878) time: 0.5077 [2021-03-25 03:30:22 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 50/1251] eta: 0:11:42 lr: 0.000103 loss: 6.4378 (6.4470) grad_norm: 1.7330 (1.8704) time: 0.5093 [2021-03-25 03:30:27 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 60/1251] eta: 0:11:20 lr: 0.000103 loss: 6.5883 (6.4650) grad_norm: 2.0258 (1.9338) time: 0.5050 [2021-03-25 03:30:32 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 70/1251] eta: 0:11:04 lr: 0.000104 loss: 6.5883 (6.4799) grad_norm: 2.0258 (1.9204) time: 0.5049 [2021-03-25 03:30:37 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 80/1251] eta: 0:10:51 lr: 0.000104 loss: 6.5353 (6.4853) grad_norm: 1.8524 (1.9302) time: 0.5082 [2021-03-25 03:30:42 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 90/1251] eta: 0:10:38 lr: 0.000104 loss: 6.4355 (6.4690) grad_norm: 1.8817 (1.9546) time: 0.5063 [2021-03-25 03:30:47 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 100/1251] eta: 0:10:27 lr: 0.000105 loss: 6.3957 (6.4629) grad_norm: 1.9385 (1.9608) time: 0.5032 [2021-03-25 03:30:52 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 110/1251] eta: 0:10:19 lr: 0.000105 loss: 6.3760 (6.4488) grad_norm: 1.8213 (1.9520) time: 0.5087 [2021-03-25 03:30:57 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 120/1251] eta: 0:10:09 lr: 0.000106 loss: 6.3824 (6.4482) grad_norm: 1.8213 (1.9575) time: 0.5081 [2021-03-25 03:31:02 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 130/1251] eta: 0:10:02 lr: 0.000106 loss: 6.4684 (6.4485) grad_norm: 1.9785 (1.9573) time: 0.5075 [2021-03-25 03:31:07 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 140/1251] eta: 0:09:54 lr: 0.000106 loss: 6.4769 (6.4514) grad_norm: 1.7907 (1.9405) time: 0.5117 [2021-03-25 03:31:12 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 150/1251] eta: 0:09:47 lr: 0.000107 loss: 6.4780 (6.4446) grad_norm: 1.7010 (1.9242) time: 0.5073 [2021-03-25 03:31:17 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 160/1251] eta: 0:09:40 lr: 0.000107 loss: 6.4027 (6.4446) grad_norm: 1.7469 (1.9269) time: 0.5054 [2021-03-25 03:31:22 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 170/1251] eta: 0:09:33 lr: 0.000108 loss: 6.4777 (6.4475) grad_norm: 1.8672 (1.9254) time: 0.5063 [2021-03-25 03:31:28 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 180/1251] eta: 0:09:26 lr: 0.000108 loss: 6.4822 (6.4498) grad_norm: 1.8672 (1.9254) time: 0.5110 [2021-03-25 03:31:33 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 190/1251] eta: 0:09:19 lr: 0.000108 loss: 6.4217 (6.4463) grad_norm: 1.8850 (1.9305) time: 0.5078 [2021-03-25 03:31:38 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 200/1251] eta: 0:09:13 lr: 0.000109 loss: 6.4691 (6.4502) grad_norm: 1.7935 (1.9244) time: 0.5025 [2021-03-25 03:31:43 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 210/1251] eta: 0:09:07 lr: 0.000109 loss: 6.4985 (6.4533) grad_norm: 1.7921 (1.9238) time: 0.5046 [2021-03-25 03:31:48 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 220/1251] eta: 0:09:00 lr: 0.000110 loss: 6.4894 (6.4516) grad_norm: 1.8114 (1.9190) time: 0.5023 [2021-03-25 03:31:53 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 230/1251] eta: 0:08:54 lr: 0.000110 loss: 6.4663 (6.4513) grad_norm: 1.8661 (1.9245) time: 0.5037 [2021-03-25 03:31:58 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 240/1251] eta: 0:08:48 lr: 0.000110 loss: 6.3787 (6.4420) grad_norm: 1.8177 (1.9178) time: 0.5041 [2021-03-25 03:32:03 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 250/1251] eta: 0:08:42 lr: 0.000111 loss: 6.2780 (6.4368) grad_norm: 1.8028 (1.9167) time: 0.5022 [2021-03-25 03:32:08 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 260/1251] eta: 0:08:36 lr: 0.000111 loss: 6.2858 (6.4353) grad_norm: 1.8880 (1.9178) time: 0.5037 [2021-03-25 03:32:13 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 270/1251] eta: 0:08:31 lr: 0.000112 loss: 6.4621 (6.4365) grad_norm: 1.8880 (1.9180) time: 0.5085 [2021-03-25 03:32:18 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 280/1251] eta: 0:08:25 lr: 0.000112 loss: 6.3768 (6.4322) grad_norm: 1.8069 (1.9140) time: 0.5041 [2021-03-25 03:32:23 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 290/1251] eta: 0:08:19 lr: 0.000112 loss: 6.2000 (6.4250) grad_norm: 1.7755 (1.9096) time: 0.5006 [2021-03-25 03:32:28 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 300/1251] eta: 0:08:13 lr: 0.000113 loss: 6.2293 (6.4237) grad_norm: 1.7127 (1.9015) time: 0.5018 [2021-03-25 03:32:33 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 310/1251] eta: 0:08:08 lr: 0.000113 loss: 6.4204 (6.4227) grad_norm: 1.8173 (1.9033) time: 0.5067 [2021-03-25 03:32:38 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 320/1251] eta: 0:08:02 lr: 0.000114 loss: 6.4264 (6.4222) grad_norm: 1.8642 (1.9044) time: 0.5036 [2021-03-25 03:32:43 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 330/1251] eta: 0:07:56 lr: 0.000114 loss: 6.4062 (6.4196) grad_norm: 1.8572 (1.9064) time: 0.4988 [2021-03-25 03:32:48 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 340/1251] eta: 0:07:51 lr: 0.000114 loss: 6.3563 (6.4176) grad_norm: 1.8552 (1.9046) time: 0.5039 [2021-03-25 03:32:53 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 350/1251] eta: 0:07:45 lr: 0.000115 loss: 6.3714 (6.4172) grad_norm: 1.7908 (1.9001) time: 0.5060 [2021-03-25 03:32:58 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 360/1251] eta: 0:07:40 lr: 0.000115 loss: 6.2493 (6.4092) grad_norm: 1.7908 (1.9036) time: 0.5066 [2021-03-25 03:33:03 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 370/1251] eta: 0:07:34 lr: 0.000116 loss: 6.2440 (6.4074) grad_norm: 1.8730 (1.9029) time: 0.5055 [2021-03-25 03:33:08 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 380/1251] eta: 0:07:29 lr: 0.000116 loss: 6.4323 (6.4074) grad_norm: 1.9376 (1.9044) time: 0.5060 [2021-03-25 03:33:13 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 390/1251] eta: 0:07:23 lr: 0.000116 loss: 6.3821 (6.4053) grad_norm: 1.9376 (1.9057) time: 0.5041 [2021-03-25 03:33:18 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 400/1251] eta: 0:07:18 lr: 0.000117 loss: 6.4343 (6.4059) grad_norm: 1.9193 (1.9123) time: 0.5001 [2021-03-25 03:33:23 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 410/1251] eta: 0:07:13 lr: 0.000117 loss: 6.4343 (6.4030) grad_norm: 1.9338 (1.9135) time: 0.4995 [2021-03-25 03:33:29 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 420/1251] eta: 0:07:07 lr: 0.000118 loss: 6.3266 (6.4013) grad_norm: 1.8884 (1.9110) time: 0.5021 [2021-03-25 03:33:34 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 430/1251] eta: 0:07:02 lr: 0.000118 loss: 6.3863 (6.4018) grad_norm: 1.7786 (1.9119) time: 0.5055 [2021-03-25 03:33:39 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 440/1251] eta: 0:06:56 lr: 0.000118 loss: 6.4087 (6.4011) grad_norm: 1.9881 (1.9164) time: 0.5045 [2021-03-25 03:33:44 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 450/1251] eta: 0:06:51 lr: 0.000119 loss: 6.3339 (6.3977) grad_norm: 1.9277 (1.9148) time: 0.5055 [2021-03-25 03:33:49 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 460/1251] eta: 0:06:46 lr: 0.000119 loss: 6.3008 (6.3966) grad_norm: 1.9367 (1.9188) time: 0.5081 [2021-03-25 03:33:54 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 470/1251] eta: 0:06:41 lr: 0.000120 loss: 6.3178 (6.3966) grad_norm: 1.8308 (1.9146) time: 0.5025 [2021-03-25 03:33:59 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 480/1251] eta: 0:06:35 lr: 0.000120 loss: 6.3500 (6.3950) grad_norm: 1.8044 (1.9150) time: 0.5049 [2021-03-25 03:34:04 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 490/1251] eta: 0:06:30 lr: 0.000120 loss: 6.3879 (6.3960) grad_norm: 1.9152 (1.9139) time: 0.5078 [2021-03-25 03:34:09 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 500/1251] eta: 0:06:25 lr: 0.000121 loss: 6.4029 (6.3948) grad_norm: 1.8820 (1.9123) time: 0.5026 [2021-03-25 03:34:14 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 510/1251] eta: 0:06:20 lr: 0.000121 loss: 6.3312 (6.3928) grad_norm: 1.8960 (1.9141) time: 0.5029 [2021-03-25 03:34:19 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 520/1251] eta: 0:06:14 lr: 0.000122 loss: 6.3088 (6.3920) grad_norm: 1.8850 (1.9140) time: 0.5036 [2021-03-25 03:34:24 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 530/1251] eta: 0:06:09 lr: 0.000122 loss: 6.2483 (6.3899) grad_norm: 1.8580 (1.9141) time: 0.5055 [2021-03-25 03:34:29 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 540/1251] eta: 0:06:04 lr: 0.000122 loss: 6.3304 (6.3887) grad_norm: 1.7335 (1.9111) time: 0.5108 [2021-03-25 03:34:34 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 550/1251] eta: 0:05:59 lr: 0.000123 loss: 6.3938 (6.3888) grad_norm: 1.7464 (1.9111) time: 0.5133 [2021-03-25 03:34:40 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 560/1251] eta: 0:05:54 lr: 0.000123 loss: 6.3772 (6.3874) grad_norm: 1.7786 (1.9123) time: 0.5151 [2021-03-25 03:34:45 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 570/1251] eta: 0:05:49 lr: 0.000124 loss: 6.3654 (6.3858) grad_norm: 1.7786 (1.9107) time: 0.5102 [2021-03-25 03:34:50 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 580/1251] eta: 0:05:43 lr: 0.000124 loss: 6.3556 (6.3840) grad_norm: 1.8647 (1.9110) time: 0.5014 [2021-03-25 03:34:55 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 590/1251] eta: 0:05:38 lr: 0.000124 loss: 6.3738 (6.3841) grad_norm: 1.8647 (1.9105) time: 0.4996 [2021-03-25 03:35:00 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 600/1251] eta: 0:05:33 lr: 0.000125 loss: 6.3959 (6.3834) grad_norm: 1.8397 (1.9107) time: 0.5073 [2021-03-25 03:35:05 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 610/1251] eta: 0:05:28 lr: 0.000125 loss: 6.3946 (6.3829) grad_norm: 1.8672 (1.9117) time: 0.5108 [2021-03-25 03:35:10 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 620/1251] eta: 0:05:23 lr: 0.000126 loss: 6.4069 (6.3829) grad_norm: 1.8107 (1.9102) time: 0.5048 [2021-03-25 03:35:15 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 630/1251] eta: 0:05:17 lr: 0.000126 loss: 6.4069 (6.3825) grad_norm: 1.6743 (1.9088) time: 0.5045 [2021-03-25 03:35:20 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 640/1251] eta: 0:05:12 lr: 0.000126 loss: 6.2975 (6.3799) grad_norm: 1.8122 (1.9091) time: 0.5048 [2021-03-25 03:35:25 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 650/1251] eta: 0:05:07 lr: 0.000127 loss: 6.3171 (6.3795) grad_norm: 1.8362 (1.9079) time: 0.5027 [2021-03-25 03:35:30 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 660/1251] eta: 0:05:02 lr: 0.000127 loss: 6.3486 (6.3777) grad_norm: 1.8137 (1.9071) time: 0.5032 [2021-03-25 03:35:35 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 670/1251] eta: 0:04:57 lr: 0.000128 loss: 6.3363 (6.3784) grad_norm: 1.8068 (1.9064) time: 0.5015 [2021-03-25 03:35:40 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 680/1251] eta: 0:04:51 lr: 0.000128 loss: 6.3691 (6.3782) grad_norm: 1.7617 (1.9035) time: 0.5007 [2021-03-25 03:35:45 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 690/1251] eta: 0:04:46 lr: 0.000128 loss: 6.3263 (6.3763) grad_norm: 1.7953 (1.9042) time: 0.5019 [2021-03-25 03:35:50 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 700/1251] eta: 0:04:41 lr: 0.000129 loss: 6.3455 (6.3763) grad_norm: 1.8251 (1.9021) time: 0.5038 [2021-03-25 03:35:55 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 710/1251] eta: 0:04:36 lr: 0.000129 loss: 6.4190 (6.3759) grad_norm: 1.6930 (1.8991) time: 0.5019 [2021-03-25 03:36:00 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 720/1251] eta: 0:04:31 lr: 0.000130 loss: 6.3638 (6.3749) grad_norm: 1.8231 (1.9010) time: 0.4957 [2021-03-25 03:36:05 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 730/1251] eta: 0:04:26 lr: 0.000130 loss: 6.4035 (6.3756) grad_norm: 1.9524 (1.9025) time: 0.5073 [2021-03-25 03:36:10 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 740/1251] eta: 0:04:21 lr: 0.000130 loss: 6.4852 (6.3764) grad_norm: 1.8628 (1.9006) time: 0.5234 [2021-03-25 03:36:16 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 750/1251] eta: 0:04:15 lr: 0.000131 loss: 6.3712 (6.3748) grad_norm: 1.7754 (1.9002) time: 0.5216 [2021-03-25 03:36:21 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 760/1251] eta: 0:04:10 lr: 0.000131 loss: 6.2913 (6.3738) grad_norm: 1.7754 (1.9000) time: 0.5098 [2021-03-25 03:36:26 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 770/1251] eta: 0:04:05 lr: 0.000132 loss: 6.2104 (6.3716) grad_norm: 1.8457 (1.8992) time: 0.5008 [2021-03-25 03:36:31 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 780/1251] eta: 0:04:00 lr: 0.000132 loss: 6.2071 (6.3701) grad_norm: 1.7613 (1.8978) time: 0.5026 [2021-03-25 03:36:36 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 790/1251] eta: 0:03:55 lr: 0.000132 loss: 6.2612 (6.3694) grad_norm: 1.7200 (1.8965) time: 0.5053 [2021-03-25 03:36:41 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 800/1251] eta: 0:03:50 lr: 0.000133 loss: 6.3575 (6.3683) grad_norm: 1.6560 (1.8935) time: 0.5057 [2021-03-25 03:36:46 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 810/1251] eta: 0:03:45 lr: 0.000133 loss: 6.3789 (6.3681) grad_norm: 1.7758 (1.8964) time: 0.5053 [2021-03-25 03:36:51 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 820/1251] eta: 0:03:39 lr: 0.000134 loss: 6.3335 (6.3671) grad_norm: 1.9660 (1.8971) time: 0.5014 [2021-03-25 03:36:56 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 830/1251] eta: 0:03:34 lr: 0.000134 loss: 6.2260 (6.3656) grad_norm: 1.9660 (1.8994) time: 0.5014 [2021-03-25 03:37:01 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 840/1251] eta: 0:03:29 lr: 0.000134 loss: 6.2678 (6.3644) grad_norm: 2.0510 (1.9014) time: 0.4993 [2021-03-25 03:37:06 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 850/1251] eta: 0:03:24 lr: 0.000135 loss: 6.3174 (6.3642) grad_norm: 1.9361 (1.9016) time: 0.5041 [2021-03-25 03:37:11 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 860/1251] eta: 0:03:19 lr: 0.000135 loss: 6.3515 (6.3626) grad_norm: 1.7336 (1.9001) time: 0.5161 [2021-03-25 03:37:16 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 870/1251] eta: 0:03:14 lr: 0.000136 loss: 6.1778 (6.3608) grad_norm: 1.7397 (1.8987) time: 0.5128 [2021-03-25 03:37:21 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 880/1251] eta: 0:03:09 lr: 0.000136 loss: 6.2266 (6.3609) grad_norm: 1.7885 (1.8988) time: 0.5031 [2021-03-25 03:37:26 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 890/1251] eta: 0:03:04 lr: 0.000136 loss: 6.4192 (6.3611) grad_norm: 1.8801 (1.8983) time: 0.4976 [2021-03-25 03:37:31 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 900/1251] eta: 0:02:58 lr: 0.000137 loss: 6.3603 (6.3591) grad_norm: 1.8364 (1.8983) time: 0.5036 [2021-03-25 03:37:36 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 910/1251] eta: 0:02:53 lr: 0.000137 loss: 6.2737 (6.3580) grad_norm: 1.9532 (1.9007) time: 0.5048 [2021-03-25 03:37:41 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 920/1251] eta: 0:02:48 lr: 0.000138 loss: 6.3024 (6.3580) grad_norm: 2.0652 (1.9020) time: 0.5083 [2021-03-25 03:37:47 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 930/1251] eta: 0:02:43 lr: 0.000138 loss: 6.2954 (6.3565) grad_norm: 1.8564 (1.9008) time: 0.5128 [2021-03-25 03:37:52 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 940/1251] eta: 0:02:38 lr: 0.000138 loss: 6.2702 (6.3553) grad_norm: 1.9173 (1.9022) time: 0.5097 [2021-03-25 03:37:57 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 950/1251] eta: 0:02:33 lr: 0.000139 loss: 6.2900 (6.3543) grad_norm: 1.9901 (1.9023) time: 0.5041 [2021-03-25 03:38:02 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 960/1251] eta: 0:02:28 lr: 0.000139 loss: 6.3122 (6.3538) grad_norm: 2.0104 (1.9043) time: 0.5002 [2021-03-25 03:38:07 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 970/1251] eta: 0:02:23 lr: 0.000140 loss: 6.1998 (6.3516) grad_norm: 2.0190 (1.9057) time: 0.5057 [2021-03-25 03:38:12 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 980/1251] eta: 0:02:18 lr: 0.000140 loss: 6.1904 (6.3508) grad_norm: 1.9351 (1.9056) time: 0.5078 [2021-03-25 03:38:17 swin_small_patch4_window7_224] INFO: Epoch: [2] [ 990/1251] eta: 0:02:12 lr: 0.000140 loss: 6.2638 (6.3505) grad_norm: 1.7747 (1.9037) time: 0.5033 [2021-03-25 03:38:22 swin_small_patch4_window7_224] INFO: Epoch: [2] [1000/1251] eta: 0:02:07 lr: 0.000141 loss: 6.2638 (6.3494) grad_norm: 1.7628 (1.9028) time: 0.5031 [2021-03-25 03:38:27 swin_small_patch4_window7_224] INFO: Epoch: [2] [1010/1251] eta: 0:02:02 lr: 0.000141 loss: 6.3158 (6.3480) grad_norm: 1.8761 (1.9032) time: 0.5023 [2021-03-25 03:38:32 swin_small_patch4_window7_224] INFO: Epoch: [2] [1020/1251] eta: 0:01:57 lr: 0.000142 loss: 6.2094 (6.3461) grad_norm: 1.9129 (1.9038) time: 0.4995 [2021-03-25 03:38:37 swin_small_patch4_window7_224] INFO: Epoch: [2] [1030/1251] eta: 0:01:52 lr: 0.000142 loss: 6.2286 (6.3454) grad_norm: 1.8902 (1.9038) time: 0.4993 [2021-03-25 03:38:42 swin_small_patch4_window7_224] INFO: Epoch: [2] [1040/1251] eta: 0:01:47 lr: 0.000142 loss: 6.2497 (6.3439) grad_norm: 1.8501 (1.9036) time: 0.5004 [2021-03-25 03:38:47 swin_small_patch4_window7_224] INFO: Epoch: [2] [1050/1251] eta: 0:01:42 lr: 0.000143 loss: 6.1919 (6.3425) grad_norm: 1.9305 (1.9060) time: 0.5072 [2021-03-25 03:38:52 swin_small_patch4_window7_224] INFO: Epoch: [2] [1060/1251] eta: 0:01:37 lr: 0.000143 loss: 6.1919 (6.3422) grad_norm: 1.9223 (1.9055) time: 0.5106 [2021-03-25 03:38:57 swin_small_patch4_window7_224] INFO: Epoch: [2] [1070/1251] eta: 0:01:32 lr: 0.000144 loss: 6.3442 (6.3418) grad_norm: 1.7877 (1.9049) time: 0.5083 [2021-03-25 03:39:02 swin_small_patch4_window7_224] INFO: Epoch: [2] [1080/1251] eta: 0:01:27 lr: 0.000144 loss: 6.2675 (6.3410) grad_norm: 1.8208 (1.9062) time: 0.5018 [2021-03-25 03:39:07 swin_small_patch4_window7_224] INFO: Epoch: [2] [1090/1251] eta: 0:01:21 lr: 0.000144 loss: 6.2953 (6.3411) grad_norm: 2.1077 (1.9083) time: 0.5003 [2021-03-25 03:39:12 swin_small_patch4_window7_224] INFO: Epoch: [2] [1100/1251] eta: 0:01:16 lr: 0.000145 loss: 6.3655 (6.3398) grad_norm: 1.9065 (1.9077) time: 0.5042 [2021-03-25 03:39:17 swin_small_patch4_window7_224] INFO: Epoch: [2] [1110/1251] eta: 0:01:11 lr: 0.000145 loss: 6.3528 (6.3399) grad_norm: 1.8450 (1.9088) time: 0.4998 [2021-03-25 03:39:22 swin_small_patch4_window7_224] INFO: Epoch: [2] [1120/1251] eta: 0:01:06 lr: 0.000146 loss: 6.2899 (6.3393) grad_norm: 1.9291 (1.9095) time: 0.4976 [2021-03-25 03:39:27 swin_small_patch4_window7_224] INFO: Epoch: [2] [1130/1251] eta: 0:01:01 lr: 0.000146 loss: 6.3055 (6.3394) grad_norm: 1.8997 (1.9090) time: 0.5061 [2021-03-25 03:39:32 swin_small_patch4_window7_224] INFO: Epoch: [2] [1140/1251] eta: 0:00:56 lr: 0.000146 loss: 6.3055 (6.3383) grad_norm: 1.8137 (1.9075) time: 0.5072 [2021-03-25 03:39:37 swin_small_patch4_window7_224] INFO: Epoch: [2] [1150/1251] eta: 0:00:51 lr: 0.000147 loss: 6.2213 (6.3379) grad_norm: 1.7906 (1.9078) time: 0.5036 [2021-03-25 03:39:43 swin_small_patch4_window7_224] INFO: Epoch: [2] [1160/1251] eta: 0:00:46 lr: 0.000147 loss: 6.2912 (6.3367) grad_norm: 1.8165 (1.9077) time: 0.5071 [2021-03-25 03:39:48 swin_small_patch4_window7_224] INFO: Epoch: [2] [1170/1251] eta: 0:00:41 lr: 0.000148 loss: 6.3724 (6.3363) grad_norm: 1.8395 (1.9076) time: 0.5059 [2021-03-25 03:39:52 swin_small_patch4_window7_224] INFO: Epoch: [2] [1180/1251] eta: 0:00:36 lr: 0.000148 loss: 6.3053 (6.3350) grad_norm: 1.8843 (1.9089) time: 0.4993 [2021-03-25 03:39:58 swin_small_patch4_window7_224] INFO: Epoch: [2] [1190/1251] eta: 0:00:31 lr: 0.000148 loss: 6.2235 (6.3343) grad_norm: 1.9101 (1.9101) time: 0.5024 [2021-03-25 03:40:03 swin_small_patch4_window7_224] INFO: Epoch: [2] [1200/1251] eta: 0:00:25 lr: 0.000149 loss: 6.3067 (6.3336) grad_norm: 1.8839 (1.9107) time: 0.5043 [2021-03-25 03:40:08 swin_small_patch4_window7_224] INFO: Epoch: [2] [1210/1251] eta: 0:00:20 lr: 0.000149 loss: 6.2755 (6.3327) grad_norm: 1.8920 (1.9107) time: 0.5061 [2021-03-25 03:40:13 swin_small_patch4_window7_224] INFO: Epoch: [2] [1220/1251] eta: 0:00:15 lr: 0.000150 loss: 6.2796 (6.3324) grad_norm: 1.8477 (1.9101) time: 0.5110 [2021-03-25 03:40:18 swin_small_patch4_window7_224] INFO: Epoch: [2] [1230/1251] eta: 0:00:10 lr: 0.000150 loss: 6.3140 (6.3319) grad_norm: 1.8565 (1.9110) time: 0.5056 [2021-03-25 03:40:23 swin_small_patch4_window7_224] INFO: Epoch: [2] [1240/1251] eta: 0:00:05 lr: 0.000150 loss: 6.3140 (6.3311) grad_norm: 1.8881 (1.9111) time: 0.5047 [2021-03-25 03:40:28 swin_small_patch4_window7_224] INFO: Epoch: [2] [1250/1251] eta: 0:00:00 lr: 0.000151 loss: 6.2296 (6.3297) grad_norm: 1.9729 (1.9120) time: 0.5023 [2021-03-25 03:40:32 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 5.0401 (5.0401) acc1: 12.5000 (12.5000) acc5: 21.8750 (21.8750) [2021-03-25 03:40:33 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 5.0401 (5.0177) acc1: 12.5000 (13.0682) acc5: 26.5625 (26.8466) [2021-03-25 03:40:36 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 5.0269 (5.0190) acc1: 14.0625 (13.3185) acc5: 28.1250 (28.4970) [2021-03-25 03:40:38 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 5.0535 (5.0171) acc1: 12.5000 (12.7520) acc5: 28.1250 (28.0746) [2021-03-25 03:40:39 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 5.0535 (5.0180) acc1: 10.9375 (12.2332) acc5: 29.6875 (28.2393) [2021-03-25 03:40:40 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 4.9733 (5.0150) acc1: 10.9375 (11.9040) acc5: 29.6875 (28.4160) [2021-03-25 03:40:43 swin_small_patch4_window7_224] INFO: * Acc@1 10.892 Acc@5 27.214 loss 5.016 [2021-03-25 03:40:43 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 10.9% [2021-03-25 03:40:43 swin_small_patch4_window7_224] INFO: Max accuracy: 10.89% [2021-03-25 03:40:47 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 0/1251] eta: 1:33:35 lr: 0.000151 loss: 5.9616 (5.9616) grad_norm: 1.5570 (1.5570) time: 4.4890 [2021-03-25 03:40:52 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 10/1251] eta: 0:17:53 lr: 0.000151 loss: 6.2345 (6.2133) grad_norm: 2.0149 (2.0108) time: 0.8650 [2021-03-25 03:40:57 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 20/1251] eta: 0:14:10 lr: 0.000152 loss: 6.2255 (6.1787) grad_norm: 2.0792 (2.0770) time: 0.5011 [2021-03-25 03:41:02 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 30/1251] eta: 0:12:47 lr: 0.000152 loss: 6.2027 (6.1988) grad_norm: 2.0350 (2.0375) time: 0.4983 [2021-03-25 03:41:07 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 40/1251] eta: 0:12:05 lr: 0.000152 loss: 6.2027 (6.2209) grad_norm: 1.9083 (1.9891) time: 0.5032 [2021-03-25 03:41:12 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 50/1251] eta: 0:11:37 lr: 0.000153 loss: 6.2194 (6.2218) grad_norm: 1.7908 (1.9505) time: 0.5062 [2021-03-25 03:41:17 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 60/1251] eta: 0:11:15 lr: 0.000153 loss: 6.2176 (6.1926) grad_norm: 1.7958 (1.9544) time: 0.5015 [2021-03-25 03:41:22 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 70/1251] eta: 0:10:59 lr: 0.000154 loss: 6.2261 (6.2164) grad_norm: 1.9746 (1.9633) time: 0.5019 [2021-03-25 03:41:27 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 80/1251] eta: 0:10:45 lr: 0.000154 loss: 6.3070 (6.2132) grad_norm: 1.9053 (1.9564) time: 0.5007 [2021-03-25 03:41:32 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 90/1251] eta: 0:10:33 lr: 0.000154 loss: 6.2546 (6.2011) grad_norm: 1.8902 (1.9659) time: 0.5024 [2021-03-25 03:41:37 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 100/1251] eta: 0:10:23 lr: 0.000155 loss: 6.3096 (6.2113) grad_norm: 1.9974 (1.9790) time: 0.5055 [2021-03-25 03:41:43 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 110/1251] eta: 0:10:16 lr: 0.000155 loss: 6.2817 (6.2012) grad_norm: 2.0754 (1.9923) time: 0.5145 [2021-03-25 03:41:48 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 120/1251] eta: 0:10:07 lr: 0.000156 loss: 6.1137 (6.1950) grad_norm: 2.0538 (1.9947) time: 0.5134 [2021-03-25 03:41:53 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 130/1251] eta: 0:09:59 lr: 0.000156 loss: 6.1837 (6.1814) grad_norm: 1.8625 (1.9762) time: 0.5046 [2021-03-25 03:41:58 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 140/1251] eta: 0:09:51 lr: 0.000156 loss: 6.1545 (6.1782) grad_norm: 1.7334 (1.9611) time: 0.5055 [2021-03-25 03:42:03 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 150/1251] eta: 0:09:43 lr: 0.000157 loss: 6.1956 (6.1699) grad_norm: 1.8233 (1.9623) time: 0.5001 [2021-03-25 03:42:08 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 160/1251] eta: 0:09:36 lr: 0.000157 loss: 6.2011 (6.1716) grad_norm: 1.8901 (1.9602) time: 0.4964 [2021-03-25 03:42:13 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 170/1251] eta: 0:09:29 lr: 0.000158 loss: 6.2375 (6.1742) grad_norm: 2.0302 (1.9763) time: 0.4971 [2021-03-25 03:42:18 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 180/1251] eta: 0:09:23 lr: 0.000158 loss: 6.2669 (6.1772) grad_norm: 2.0302 (1.9733) time: 0.5072 [2021-03-25 03:42:23 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 190/1251] eta: 0:09:16 lr: 0.000158 loss: 6.1999 (6.1748) grad_norm: 1.9035 (inf) time: 0.5053 [2021-03-25 03:42:28 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 200/1251] eta: 0:09:09 lr: 0.000159 loss: 6.0607 (6.1716) grad_norm: 1.7907 (inf) time: 0.4966 [2021-03-25 03:42:33 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 210/1251] eta: 0:09:03 lr: 0.000159 loss: 6.1195 (6.1738) grad_norm: 1.8410 (inf) time: 0.4982 [2021-03-25 03:42:38 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 220/1251] eta: 0:08:57 lr: 0.000160 loss: 6.2738 (6.1792) grad_norm: 1.8798 (inf) time: 0.5012 [2021-03-25 03:42:43 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 230/1251] eta: 0:08:51 lr: 0.000160 loss: 6.2668 (6.1795) grad_norm: 1.8665 (inf) time: 0.5060 [2021-03-25 03:42:48 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 240/1251] eta: 0:08:45 lr: 0.000160 loss: 6.2482 (6.1791) grad_norm: 1.8646 (inf) time: 0.5030 [2021-03-25 03:42:53 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 250/1251] eta: 0:08:39 lr: 0.000161 loss: 6.1881 (6.1772) grad_norm: 1.9150 (inf) time: 0.4988 [2021-03-25 03:42:58 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 260/1251] eta: 0:08:33 lr: 0.000161 loss: 6.1075 (6.1753) grad_norm: 2.0092 (inf) time: 0.4994 [2021-03-25 03:43:03 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 270/1251] eta: 0:08:27 lr: 0.000162 loss: 6.2610 (6.1789) grad_norm: 2.0078 (inf) time: 0.4995 [2021-03-25 03:43:08 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 280/1251] eta: 0:08:21 lr: 0.000162 loss: 6.1241 (6.1749) grad_norm: 1.8042 (inf) time: 0.5020 [2021-03-25 03:43:13 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 290/1251] eta: 0:08:16 lr: 0.000162 loss: 6.1624 (6.1806) grad_norm: 1.7803 (inf) time: 0.5017 [2021-03-25 03:43:18 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 300/1251] eta: 0:08:10 lr: 0.000163 loss: 6.3674 (6.1860) grad_norm: 1.8647 (inf) time: 0.5030 [2021-03-25 03:43:23 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 310/1251] eta: 0:08:05 lr: 0.000163 loss: 6.3674 (6.1855) grad_norm: 1.8646 (inf) time: 0.5110 [2021-03-25 03:43:28 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 320/1251] eta: 0:07:59 lr: 0.000164 loss: 6.0230 (6.1788) grad_norm: 1.8060 (inf) time: 0.5059 [2021-03-25 03:43:33 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 330/1251] eta: 0:07:54 lr: 0.000164 loss: 6.0344 (6.1741) grad_norm: 2.0192 (inf) time: 0.4962 [2021-03-25 03:43:38 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 340/1251] eta: 0:07:48 lr: 0.000164 loss: 6.0866 (6.1723) grad_norm: 2.1129 (inf) time: 0.4978 [2021-03-25 03:43:43 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 350/1251] eta: 0:07:43 lr: 0.000165 loss: 6.0972 (6.1703) grad_norm: 2.1683 (inf) time: 0.5016 [2021-03-25 03:43:48 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 360/1251] eta: 0:07:37 lr: 0.000165 loss: 6.1948 (6.1728) grad_norm: 1.8589 (inf) time: 0.5021 [2021-03-25 03:43:53 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 370/1251] eta: 0:07:32 lr: 0.000166 loss: 6.2371 (6.1735) grad_norm: 1.8589 (inf) time: 0.5020 [2021-03-25 03:43:58 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 380/1251] eta: 0:07:26 lr: 0.000166 loss: 6.1785 (6.1707) grad_norm: 2.0580 (inf) time: 0.5019 [2021-03-25 03:44:03 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 390/1251] eta: 0:07:21 lr: 0.000166 loss: 6.1489 (6.1690) grad_norm: 2.0161 (inf) time: 0.5028 [2021-03-25 03:44:08 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 400/1251] eta: 0:07:16 lr: 0.000167 loss: 6.1333 (6.1676) grad_norm: 2.0497 (inf) time: 0.5055 [2021-03-25 03:44:13 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 410/1251] eta: 0:07:10 lr: 0.000167 loss: 6.1253 (6.1687) grad_norm: 2.0505 (inf) time: 0.5025 [2021-03-25 03:44:18 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 420/1251] eta: 0:07:05 lr: 0.000168 loss: 6.2775 (6.1704) grad_norm: 1.9997 (inf) time: 0.5030 [2021-03-25 03:44:23 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 430/1251] eta: 0:07:00 lr: 0.000168 loss: 6.2437 (6.1705) grad_norm: 1.9406 (inf) time: 0.5031 [2021-03-25 03:44:28 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 440/1251] eta: 0:06:54 lr: 0.000168 loss: 6.0463 (6.1661) grad_norm: 1.9546 (inf) time: 0.4999 [2021-03-25 03:44:33 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 450/1251] eta: 0:06:49 lr: 0.000169 loss: 6.0463 (6.1657) grad_norm: 2.0829 (inf) time: 0.5028 [2021-03-25 03:44:38 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 460/1251] eta: 0:06:44 lr: 0.000169 loss: 6.2319 (6.1657) grad_norm: 1.8394 (inf) time: 0.5028 [2021-03-25 03:44:43 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 470/1251] eta: 0:06:39 lr: 0.000170 loss: 6.2379 (6.1668) grad_norm: 1.7950 (inf) time: 0.5028 [2021-03-25 03:44:48 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 480/1251] eta: 0:06:34 lr: 0.000170 loss: 6.2852 (6.1640) grad_norm: 1.9205 (inf) time: 0.5073 [2021-03-25 03:44:53 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 490/1251] eta: 0:06:28 lr: 0.000170 loss: 6.1883 (6.1643) grad_norm: 1.8662 (inf) time: 0.5055 [2021-03-25 03:44:58 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 500/1251] eta: 0:06:23 lr: 0.000171 loss: 6.1883 (6.1635) grad_norm: 1.8703 (inf) time: 0.5039 [2021-03-25 03:45:04 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 510/1251] eta: 0:06:18 lr: 0.000171 loss: 6.1494 (6.1621) grad_norm: 1.9458 (inf) time: 0.5044 [2021-03-25 03:45:09 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 520/1251] eta: 0:06:13 lr: 0.000172 loss: 6.1680 (6.1616) grad_norm: 1.7394 (inf) time: 0.5016 [2021-03-25 03:45:14 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 530/1251] eta: 0:06:07 lr: 0.000172 loss: 6.0546 (6.1578) grad_norm: 1.6651 (inf) time: 0.5016 [2021-03-25 03:45:19 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 540/1251] eta: 0:06:02 lr: 0.000172 loss: 6.0691 (6.1597) grad_norm: 1.9053 (inf) time: 0.5007 [2021-03-25 03:45:24 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 550/1251] eta: 0:05:57 lr: 0.000173 loss: 6.1301 (6.1565) grad_norm: 1.9142 (inf) time: 0.5126 [2021-03-25 03:45:29 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 560/1251] eta: 0:05:52 lr: 0.000173 loss: 6.1301 (6.1557) grad_norm: 1.7870 (inf) time: 0.5151 [2021-03-25 03:45:34 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 570/1251] eta: 0:05:47 lr: 0.000174 loss: 6.2015 (6.1566) grad_norm: 1.7675 (inf) time: 0.5022 [2021-03-25 03:45:39 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 580/1251] eta: 0:05:42 lr: 0.000174 loss: 6.1754 (6.1550) grad_norm: 1.8095 (inf) time: 0.5023 [2021-03-25 03:45:44 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 590/1251] eta: 0:05:37 lr: 0.000174 loss: 6.0365 (6.1527) grad_norm: 1.8811 (inf) time: 0.5115 [2021-03-25 03:45:49 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 600/1251] eta: 0:05:31 lr: 0.000175 loss: 6.2134 (6.1532) grad_norm: 2.0182 (inf) time: 0.5104 [2021-03-25 03:45:54 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 610/1251] eta: 0:05:26 lr: 0.000175 loss: 6.1163 (6.1514) grad_norm: 2.1463 (inf) time: 0.5058 [2021-03-25 03:45:59 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 620/1251] eta: 0:05:21 lr: 0.000176 loss: 6.2833 (6.1535) grad_norm: 2.1796 (inf) time: 0.5061 [2021-03-25 03:46:04 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 630/1251] eta: 0:05:16 lr: 0.000176 loss: 6.2138 (6.1513) grad_norm: 2.0746 (inf) time: 0.5058 [2021-03-25 03:46:09 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 640/1251] eta: 0:05:11 lr: 0.000176 loss: 6.0919 (6.1515) grad_norm: 2.0086 (inf) time: 0.5043 [2021-03-25 03:46:14 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 650/1251] eta: 0:05:06 lr: 0.000177 loss: 6.2094 (6.1525) grad_norm: 1.9429 (inf) time: 0.4995 [2021-03-25 03:46:19 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 660/1251] eta: 0:05:01 lr: 0.000177 loss: 6.1395 (6.1511) grad_norm: 1.8652 (inf) time: 0.4997 [2021-03-25 03:46:24 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 670/1251] eta: 0:04:55 lr: 0.000178 loss: 6.0957 (6.1494) grad_norm: 1.9480 (inf) time: 0.5030 [2021-03-25 03:46:29 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 680/1251] eta: 0:04:50 lr: 0.000178 loss: 6.1490 (6.1481) grad_norm: 1.9512 (inf) time: 0.5057 [2021-03-25 03:46:34 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 690/1251] eta: 0:04:45 lr: 0.000178 loss: 6.2205 (6.1489) grad_norm: 1.9678 (inf) time: 0.5020 [2021-03-25 03:46:39 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 700/1251] eta: 0:04:40 lr: 0.000179 loss: 6.2229 (6.1481) grad_norm: 1.9453 (inf) time: 0.4996 [2021-03-25 03:46:44 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 710/1251] eta: 0:04:35 lr: 0.000179 loss: 6.1120 (6.1472) grad_norm: 1.9458 (inf) time: 0.5009 [2021-03-25 03:46:50 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 720/1251] eta: 0:04:30 lr: 0.000180 loss: 6.2378 (6.1500) grad_norm: 2.1464 (inf) time: 0.5041 [2021-03-25 03:46:55 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 730/1251] eta: 0:04:25 lr: 0.000180 loss: 6.2108 (6.1497) grad_norm: 1.8549 (inf) time: 0.5078 [2021-03-25 03:47:00 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 740/1251] eta: 0:04:20 lr: 0.000180 loss: 6.0613 (6.1471) grad_norm: 1.7907 (inf) time: 0.5215 [2021-03-25 03:47:05 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 750/1251] eta: 0:04:15 lr: 0.000181 loss: 6.0613 (6.1455) grad_norm: 1.7907 (inf) time: 0.5157 [2021-03-25 03:47:10 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 760/1251] eta: 0:04:09 lr: 0.000181 loss: 6.1168 (6.1456) grad_norm: 1.8653 (inf) time: 0.4980 [2021-03-25 03:47:15 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 770/1251] eta: 0:04:04 lr: 0.000182 loss: 6.1305 (6.1455) grad_norm: 1.9216 (inf) time: 0.5005 [2021-03-25 03:47:20 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 780/1251] eta: 0:03:59 lr: 0.000182 loss: 6.1305 (6.1451) grad_norm: 2.0715 (inf) time: 0.5097 [2021-03-25 03:47:25 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 790/1251] eta: 0:03:54 lr: 0.000182 loss: 6.1301 (6.1436) grad_norm: 2.0042 (inf) time: 0.5153 [2021-03-25 03:47:30 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 800/1251] eta: 0:03:49 lr: 0.000183 loss: 6.1385 (6.1440) grad_norm: 1.7959 (inf) time: 0.5077 [2021-03-25 03:47:35 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 810/1251] eta: 0:03:44 lr: 0.000183 loss: 6.3377 (6.1451) grad_norm: 1.8932 (inf) time: 0.5048 [2021-03-25 03:47:40 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 820/1251] eta: 0:03:39 lr: 0.000184 loss: 6.2172 (6.1447) grad_norm: 1.8965 (inf) time: 0.5068 [2021-03-25 03:47:45 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 830/1251] eta: 0:03:34 lr: 0.000184 loss: 6.1802 (6.1444) grad_norm: 1.8432 (inf) time: 0.5057 [2021-03-25 03:47:51 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 840/1251] eta: 0:03:29 lr: 0.000184 loss: 6.2210 (6.1441) grad_norm: 1.8081 (inf) time: 0.5081 [2021-03-25 03:47:56 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 850/1251] eta: 0:03:24 lr: 0.000185 loss: 6.2584 (6.1441) grad_norm: 1.9299 (inf) time: 0.5132 [2021-03-25 03:48:01 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 860/1251] eta: 0:03:18 lr: 0.000185 loss: 6.0423 (6.1421) grad_norm: 1.9910 (inf) time: 0.5098 [2021-03-25 03:48:06 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 870/1251] eta: 0:03:13 lr: 0.000186 loss: 6.0418 (6.1417) grad_norm: 1.9474 (inf) time: 0.5040 [2021-03-25 03:48:11 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 880/1251] eta: 0:03:08 lr: 0.000186 loss: 6.0235 (6.1402) grad_norm: 1.9019 (inf) time: 0.5050 [2021-03-25 03:48:16 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 890/1251] eta: 0:03:03 lr: 0.000186 loss: 6.0447 (6.1402) grad_norm: 1.8671 (inf) time: 0.5062 [2021-03-25 03:48:21 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 900/1251] eta: 0:02:58 lr: 0.000187 loss: 6.0915 (6.1396) grad_norm: 1.9482 (inf) time: 0.5072 [2021-03-25 03:48:26 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 910/1251] eta: 0:02:53 lr: 0.000187 loss: 6.2022 (6.1400) grad_norm: 1.9697 (inf) time: 0.5024 [2021-03-25 03:48:31 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 920/1251] eta: 0:02:48 lr: 0.000188 loss: 6.2022 (6.1399) grad_norm: 1.9596 (inf) time: 0.4992 [2021-03-25 03:48:36 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 930/1251] eta: 0:02:43 lr: 0.000188 loss: 6.1965 (6.1402) grad_norm: 1.8460 (inf) time: 0.5043 [2021-03-25 03:48:41 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 940/1251] eta: 0:02:38 lr: 0.000188 loss: 6.2176 (6.1408) grad_norm: 1.8897 (inf) time: 0.5053 [2021-03-25 03:48:46 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 950/1251] eta: 0:02:33 lr: 0.000189 loss: 6.1859 (6.1413) grad_norm: 1.8261 (inf) time: 0.5041 [2021-03-25 03:48:51 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 960/1251] eta: 0:02:27 lr: 0.000189 loss: 6.0386 (6.1396) grad_norm: 1.8134 (inf) time: 0.5065 [2021-03-25 03:48:56 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 970/1251] eta: 0:02:22 lr: 0.000190 loss: 6.0327 (6.1398) grad_norm: 1.9673 (inf) time: 0.5082 [2021-03-25 03:49:01 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 980/1251] eta: 0:02:17 lr: 0.000190 loss: 6.0520 (6.1378) grad_norm: 2.0228 (inf) time: 0.5013 [2021-03-25 03:49:06 swin_small_patch4_window7_224] INFO: Epoch: [3] [ 990/1251] eta: 0:02:12 lr: 0.000190 loss: 6.2340 (6.1374) grad_norm: 1.9023 (inf) time: 0.4986 [2021-03-25 03:49:11 swin_small_patch4_window7_224] INFO: Epoch: [3] [1000/1251] eta: 0:02:07 lr: 0.000191 loss: 6.2340 (6.1364) grad_norm: 1.8634 (inf) time: 0.5039 [2021-03-25 03:49:16 swin_small_patch4_window7_224] INFO: Epoch: [3] [1010/1251] eta: 0:02:02 lr: 0.000191 loss: 6.0618 (6.1357) grad_norm: 2.0858 (inf) time: 0.5032 [2021-03-25 03:49:21 swin_small_patch4_window7_224] INFO: Epoch: [3] [1020/1251] eta: 0:01:57 lr: 0.000192 loss: 6.0618 (6.1336) grad_norm: 2.0858 (inf) time: 0.4986 [2021-03-25 03:49:26 swin_small_patch4_window7_224] INFO: Epoch: [3] [1030/1251] eta: 0:01:52 lr: 0.000192 loss: 6.0327 (6.1330) grad_norm: 1.9900 (inf) time: 0.4969 [2021-03-25 03:49:31 swin_small_patch4_window7_224] INFO: Epoch: [3] [1040/1251] eta: 0:01:47 lr: 0.000192 loss: 6.1385 (6.1330) grad_norm: 2.1129 (inf) time: 0.5025 [2021-03-25 03:49:37 swin_small_patch4_window7_224] INFO: Epoch: [3] [1050/1251] eta: 0:01:42 lr: 0.000193 loss: 6.1723 (6.1330) grad_norm: 2.1267 (inf) time: 0.5126 [2021-03-25 03:49:42 swin_small_patch4_window7_224] INFO: Epoch: [3] [1060/1251] eta: 0:01:37 lr: 0.000193 loss: 6.0949 (6.1319) grad_norm: 2.1143 (inf) time: 0.5095 [2021-03-25 03:49:47 swin_small_patch4_window7_224] INFO: Epoch: [3] [1070/1251] eta: 0:01:31 lr: 0.000194 loss: 5.8409 (6.1296) grad_norm: 2.1035 (inf) time: 0.5015 [2021-03-25 03:49:52 swin_small_patch4_window7_224] INFO: Epoch: [3] [1080/1251] eta: 0:01:26 lr: 0.000194 loss: 5.9783 (6.1287) grad_norm: 1.9435 (inf) time: 0.5018 [2021-03-25 03:49:57 swin_small_patch4_window7_224] INFO: Epoch: [3] [1090/1251] eta: 0:01:21 lr: 0.000194 loss: 6.0399 (6.1277) grad_norm: 1.8984 (inf) time: 0.5000 [2021-03-25 03:50:02 swin_small_patch4_window7_224] INFO: Epoch: [3] [1100/1251] eta: 0:01:16 lr: 0.000195 loss: 6.1215 (6.1257) grad_norm: 1.9517 (inf) time: 0.5024 [2021-03-25 03:50:07 swin_small_patch4_window7_224] INFO: Epoch: [3] [1110/1251] eta: 0:01:11 lr: 0.000195 loss: 5.7731 (6.1220) grad_norm: 2.0121 (inf) time: 0.4990 [2021-03-25 03:50:12 swin_small_patch4_window7_224] INFO: Epoch: [3] [1120/1251] eta: 0:01:06 lr: 0.000196 loss: 5.7852 (6.1206) grad_norm: 1.9083 (inf) time: 0.4977 [2021-03-25 03:50:17 swin_small_patch4_window7_224] INFO: Epoch: [3] [1130/1251] eta: 0:01:01 lr: 0.000196 loss: 5.9091 (6.1191) grad_norm: 1.9371 (inf) time: 0.5039 [2021-03-25 03:50:22 swin_small_patch4_window7_224] INFO: Epoch: [3] [1140/1251] eta: 0:00:56 lr: 0.000196 loss: 6.0303 (6.1184) grad_norm: 2.0915 (inf) time: 0.5061 [2021-03-25 03:50:27 swin_small_patch4_window7_224] INFO: Epoch: [3] [1150/1251] eta: 0:00:51 lr: 0.000197 loss: 5.9214 (6.1159) grad_norm: 1.9545 (inf) time: 0.5098 [2021-03-25 03:50:32 swin_small_patch4_window7_224] INFO: Epoch: [3] [1160/1251] eta: 0:00:46 lr: 0.000197 loss: 5.8790 (6.1150) grad_norm: 1.8678 (inf) time: 0.5075 [2021-03-25 03:50:37 swin_small_patch4_window7_224] INFO: Epoch: [3] [1170/1251] eta: 0:00:41 lr: 0.000198 loss: 6.0338 (6.1150) grad_norm: 1.8521 (inf) time: 0.5011 [2021-03-25 03:50:42 swin_small_patch4_window7_224] INFO: Epoch: [3] [1180/1251] eta: 0:00:36 lr: 0.000198 loss: 6.1092 (6.1153) grad_norm: 1.8568 (inf) time: 0.5008 [2021-03-25 03:50:47 swin_small_patch4_window7_224] INFO: Epoch: [3] [1190/1251] eta: 0:00:30 lr: 0.000198 loss: 6.1516 (6.1157) grad_norm: 1.8642 (inf) time: 0.5056 [2021-03-25 03:50:52 swin_small_patch4_window7_224] INFO: Epoch: [3] [1200/1251] eta: 0:00:25 lr: 0.000199 loss: 6.1464 (6.1159) grad_norm: 1.9038 (inf) time: 0.5058 [2021-03-25 03:50:57 swin_small_patch4_window7_224] INFO: Epoch: [3] [1210/1251] eta: 0:00:20 lr: 0.000199 loss: 5.9526 (6.1130) grad_norm: 1.9684 (inf) time: 0.5060 [2021-03-25 03:51:02 swin_small_patch4_window7_224] INFO: Epoch: [3] [1220/1251] eta: 0:00:15 lr: 0.000200 loss: 6.0649 (6.1127) grad_norm: 1.9288 (inf) time: 0.5043 [2021-03-25 03:51:07 swin_small_patch4_window7_224] INFO: Epoch: [3] [1230/1251] eta: 0:00:10 lr: 0.000200 loss: 6.1885 (6.1134) grad_norm: 1.9530 (inf) time: 0.5026 [2021-03-25 03:51:12 swin_small_patch4_window7_224] INFO: Epoch: [3] [1240/1251] eta: 0:00:05 lr: 0.000200 loss: 6.1235 (6.1119) grad_norm: 2.1438 (inf) time: 0.4981 [2021-03-25 03:51:17 swin_small_patch4_window7_224] INFO: Epoch: [3] [1250/1251] eta: 0:00:00 lr: 0.000201 loss: 6.0457 (6.1130) grad_norm: 1.9499 (inf) time: 0.4972 [2021-03-25 03:51:21 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:57 loss: 4.9392 (4.9392) acc1: 7.8125 (7.8125) acc5: 21.8750 (21.8750) [2021-03-25 03:51:22 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 4.4557 (4.4588) acc1: 17.1875 (18.1818) acc5: 39.0625 (39.2045) [2021-03-25 03:51:25 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 4.4128 (4.4282) acc1: 18.7500 (18.3036) acc5: 40.6250 (40.2530) [2021-03-25 03:51:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 4.4040 (4.4252) acc1: 18.7500 (18.4476) acc5: 39.0625 (39.5161) [2021-03-25 03:51:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 4.4654 (4.4383) acc1: 17.1875 (18.3689) acc5: 37.5000 (38.9863) [2021-03-25 03:51:30 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 4.5656 (4.4535) acc1: 17.1875 (17.9520) acc5: 34.3750 (38.5280) [2021-03-25 03:51:32 swin_small_patch4_window7_224] INFO: * Acc@1 17.440 Acc@5 37.576 loss 4.450 [2021-03-25 03:51:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 17.4% [2021-03-25 03:51:32 swin_small_patch4_window7_224] INFO: Max accuracy: 17.44% [2021-03-25 03:51:36 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 0/1251] eta: 1:27:17 lr: 0.000201 loss: 6.4284 (6.4284) grad_norm: 1.9001 (1.9001) time: 4.1868 [2021-03-25 03:51:41 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 10/1251] eta: 0:17:34 lr: 0.000201 loss: 6.0814 (6.0236) grad_norm: 1.8525 (1.8996) time: 0.8495 [2021-03-25 03:51:46 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 20/1251] eta: 0:14:04 lr: 0.000202 loss: 6.0107 (6.0050) grad_norm: 1.8525 (1.9263) time: 0.5113 [2021-03-25 03:51:51 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 30/1251] eta: 0:12:44 lr: 0.000202 loss: 5.8671 (5.9447) grad_norm: 1.9841 (2.0338) time: 0.5037 [2021-03-25 03:51:56 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 40/1251] eta: 0:12:02 lr: 0.000202 loss: 5.9066 (5.9527) grad_norm: 1.9951 (2.0336) time: 0.5029 [2021-03-25 03:52:01 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 50/1251] eta: 0:11:35 lr: 0.000203 loss: 5.9521 (5.9408) grad_norm: 1.8968 (2.0310) time: 0.5053 [2021-03-25 03:52:06 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 60/1251] eta: 0:11:13 lr: 0.000203 loss: 6.0799 (5.9749) grad_norm: 1.9384 (2.0423) time: 0.5025 [2021-03-25 03:52:11 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 70/1251] eta: 0:10:57 lr: 0.000204 loss: 6.0799 (5.9558) grad_norm: 1.9805 (2.0689) time: 0.5007 [2021-03-25 03:52:17 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 80/1251] eta: 0:10:45 lr: 0.000204 loss: 5.8780 (5.9492) grad_norm: 2.0239 (2.0675) time: 0.5050 [2021-03-25 03:52:22 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 90/1251] eta: 0:10:33 lr: 0.000204 loss: 5.8507 (5.9458) grad_norm: 1.9697 (2.0572) time: 0.5057 [2021-03-25 03:52:27 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 100/1251] eta: 0:10:22 lr: 0.000205 loss: 6.1148 (5.9588) grad_norm: 1.9697 (2.0579) time: 0.5020 [2021-03-25 03:52:32 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 110/1251] eta: 0:10:13 lr: 0.000205 loss: 6.1148 (5.9531) grad_norm: 1.9708 (2.0551) time: 0.5025 [2021-03-25 03:52:37 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 120/1251] eta: 0:10:05 lr: 0.000206 loss: 5.8334 (5.9501) grad_norm: 1.7386 (2.0451) time: 0.5060 [2021-03-25 03:52:42 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 130/1251] eta: 0:09:57 lr: 0.000206 loss: 5.9769 (5.9617) grad_norm: 1.7944 (2.0466) time: 0.5059 [2021-03-25 03:52:47 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 140/1251] eta: 0:09:49 lr: 0.000206 loss: 6.1025 (5.9653) grad_norm: 2.0312 (2.0598) time: 0.4998 [2021-03-25 03:52:52 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 150/1251] eta: 0:09:41 lr: 0.000207 loss: 5.9530 (5.9625) grad_norm: 2.1386 (2.0922) time: 0.4997 [2021-03-25 03:52:57 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 160/1251] eta: 0:09:34 lr: 0.000207 loss: 5.9530 (5.9700) grad_norm: 2.0195 (2.0802) time: 0.5025 [2021-03-25 03:53:02 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 170/1251] eta: 0:09:28 lr: 0.000208 loss: 5.9530 (5.9606) grad_norm: 1.8697 (2.0678) time: 0.5043 [2021-03-25 03:53:07 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 180/1251] eta: 0:09:21 lr: 0.000208 loss: 6.0493 (5.9625) grad_norm: 1.8809 (2.0670) time: 0.5056 [2021-03-25 03:53:12 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 190/1251] eta: 0:09:15 lr: 0.000208 loss: 6.0598 (5.9582) grad_norm: 1.9713 (2.0597) time: 0.5077 [2021-03-25 03:53:17 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 200/1251] eta: 0:09:09 lr: 0.000209 loss: 6.1325 (5.9639) grad_norm: 1.9332 (2.0571) time: 0.5046 [2021-03-25 03:53:22 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 210/1251] eta: 0:09:03 lr: 0.000209 loss: 6.2009 (5.9700) grad_norm: 1.9046 (2.0543) time: 0.5038 [2021-03-25 03:53:27 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 220/1251] eta: 0:08:57 lr: 0.000210 loss: 6.0262 (5.9707) grad_norm: 1.9012 (2.0539) time: 0.5126 [2021-03-25 03:53:32 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 230/1251] eta: 0:08:52 lr: 0.000210 loss: 6.0128 (5.9686) grad_norm: 1.9349 (2.0559) time: 0.5155 [2021-03-25 03:53:38 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 240/1251] eta: 0:08:46 lr: 0.000210 loss: 6.1709 (5.9731) grad_norm: 1.8598 (2.0513) time: 0.5137 [2021-03-25 03:53:43 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 250/1251] eta: 0:08:41 lr: 0.000211 loss: 6.0423 (5.9740) grad_norm: 1.9262 (2.0566) time: 0.5103 [2021-03-25 03:53:48 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 260/1251] eta: 0:08:35 lr: 0.000211 loss: 5.9907 (5.9721) grad_norm: 1.9520 (2.0504) time: 0.5066 [2021-03-25 03:53:53 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 270/1251] eta: 0:08:29 lr: 0.000212 loss: 5.8859 (5.9692) grad_norm: 1.9473 (2.0466) time: 0.5028 [2021-03-25 03:53:58 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 280/1251] eta: 0:08:23 lr: 0.000212 loss: 6.1038 (5.9738) grad_norm: 1.9523 (2.0440) time: 0.5066 [2021-03-25 03:54:03 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 290/1251] eta: 0:08:18 lr: 0.000212 loss: 6.1646 (5.9732) grad_norm: 2.0744 (2.0497) time: 0.5079 [2021-03-25 03:54:08 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 300/1251] eta: 0:08:12 lr: 0.000213 loss: 6.0891 (5.9768) grad_norm: 2.0374 (2.0497) time: 0.4997 [2021-03-25 03:54:13 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 310/1251] eta: 0:08:06 lr: 0.000213 loss: 6.0465 (5.9736) grad_norm: 1.9885 (2.0488) time: 0.5036 [2021-03-25 03:54:18 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 320/1251] eta: 0:08:01 lr: 0.000214 loss: 5.8457 (5.9698) grad_norm: 2.0072 (2.0497) time: 0.5065 [2021-03-25 03:54:23 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 330/1251] eta: 0:07:55 lr: 0.000214 loss: 5.7838 (5.9658) grad_norm: 1.9047 (2.0462) time: 0.5060 [2021-03-25 03:54:28 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 340/1251] eta: 0:07:50 lr: 0.000214 loss: 6.0157 (5.9696) grad_norm: 1.8804 (2.0452) time: 0.5032 [2021-03-25 03:54:33 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 350/1251] eta: 0:07:44 lr: 0.000215 loss: 6.1212 (5.9724) grad_norm: 1.9049 (2.0426) time: 0.5013 [2021-03-25 03:54:38 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 360/1251] eta: 0:07:39 lr: 0.000215 loss: 6.0374 (5.9707) grad_norm: 1.9248 (2.0426) time: 0.5045 [2021-03-25 03:54:43 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 370/1251] eta: 0:07:33 lr: 0.000216 loss: 5.8642 (5.9673) grad_norm: 1.9228 (2.0410) time: 0.5042 [2021-03-25 03:54:48 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 380/1251] eta: 0:07:28 lr: 0.000216 loss: 5.8218 (5.9633) grad_norm: 1.9213 (2.0382) time: 0.5036 [2021-03-25 03:54:53 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 390/1251] eta: 0:07:22 lr: 0.000216 loss: 5.9528 (5.9637) grad_norm: 1.9219 (2.0402) time: 0.5007 [2021-03-25 03:54:58 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 400/1251] eta: 0:07:17 lr: 0.000217 loss: 6.1699 (5.9686) grad_norm: 1.8976 (2.0384) time: 0.5036 [2021-03-25 03:55:03 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 410/1251] eta: 0:07:12 lr: 0.000217 loss: 6.1080 (5.9687) grad_norm: 1.8441 (2.0373) time: 0.5084 [2021-03-25 03:55:08 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 420/1251] eta: 0:07:07 lr: 0.000218 loss: 5.9600 (5.9672) grad_norm: 1.9495 (2.0343) time: 0.5078 [2021-03-25 03:55:14 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 430/1251] eta: 0:07:02 lr: 0.000218 loss: 5.9266 (5.9645) grad_norm: 1.9755 (2.0445) time: 0.5162 [2021-03-25 03:55:19 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 440/1251] eta: 0:06:56 lr: 0.000218 loss: 5.9501 (5.9643) grad_norm: 1.9860 (2.0394) time: 0.5126 [2021-03-25 03:55:24 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 450/1251] eta: 0:06:51 lr: 0.000219 loss: 5.9748 (5.9638) grad_norm: 1.9410 (2.0387) time: 0.5013 [2021-03-25 03:55:29 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 460/1251] eta: 0:06:46 lr: 0.000219 loss: 6.0747 (5.9649) grad_norm: 2.0187 (2.0389) time: 0.5009 [2021-03-25 03:55:34 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 470/1251] eta: 0:06:40 lr: 0.000220 loss: 6.0978 (5.9648) grad_norm: 1.9197 (2.0363) time: 0.5030 [2021-03-25 03:55:39 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 480/1251] eta: 0:06:35 lr: 0.000220 loss: 5.8703 (5.9620) grad_norm: 1.9237 (2.0420) time: 0.5063 [2021-03-25 03:55:44 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 490/1251] eta: 0:06:30 lr: 0.000220 loss: 5.9997 (5.9635) grad_norm: 1.8691 (2.0364) time: 0.5026 [2021-03-25 03:55:49 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 500/1251] eta: 0:06:25 lr: 0.000221 loss: 6.0494 (5.9618) grad_norm: 1.7961 (2.0331) time: 0.5030 [2021-03-25 03:55:54 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 510/1251] eta: 0:06:19 lr: 0.000221 loss: 5.7050 (5.9572) grad_norm: 1.8445 (2.0319) time: 0.5060 [2021-03-25 03:55:59 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 520/1251] eta: 0:06:14 lr: 0.000222 loss: 5.9977 (5.9588) grad_norm: 1.8422 (2.0291) time: 0.5042 [2021-03-25 03:56:04 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 530/1251] eta: 0:06:09 lr: 0.000222 loss: 6.0084 (5.9545) grad_norm: 1.8449 (2.0283) time: 0.5036 [2021-03-25 03:56:09 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 540/1251] eta: 0:06:04 lr: 0.000222 loss: 5.8741 (5.9539) grad_norm: 1.8707 (2.0269) time: 0.5024 [2021-03-25 03:56:14 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 550/1251] eta: 0:05:59 lr: 0.000223 loss: 5.9105 (5.9521) grad_norm: 1.8976 (2.0249) time: 0.5116 [2021-03-25 03:56:19 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 560/1251] eta: 0:05:53 lr: 0.000223 loss: 5.9105 (5.9521) grad_norm: 1.9925 (2.0245) time: 0.5098 [2021-03-25 03:56:24 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 570/1251] eta: 0:05:48 lr: 0.000224 loss: 5.8652 (5.9484) grad_norm: 2.0714 (2.0272) time: 0.5025 [2021-03-25 03:56:29 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 580/1251] eta: 0:05:43 lr: 0.000224 loss: 6.0624 (5.9489) grad_norm: 1.9965 (2.0249) time: 0.5080 [2021-03-25 03:56:34 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 590/1251] eta: 0:05:38 lr: 0.000224 loss: 6.1627 (5.9497) grad_norm: 2.0284 (2.0284) time: 0.5079 [2021-03-25 03:56:39 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 600/1251] eta: 0:05:33 lr: 0.000225 loss: 6.1060 (5.9478) grad_norm: 2.1623 (2.0294) time: 0.5041 [2021-03-25 03:56:45 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 610/1251] eta: 0:05:27 lr: 0.000225 loss: 5.8392 (5.9473) grad_norm: 2.0102 (2.0294) time: 0.5025 [2021-03-25 03:56:50 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 620/1251] eta: 0:05:22 lr: 0.000226 loss: 5.9275 (5.9460) grad_norm: 1.9269 (2.0326) time: 0.5033 [2021-03-25 03:56:55 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 630/1251] eta: 0:05:17 lr: 0.000226 loss: 5.9988 (5.9482) grad_norm: 1.9469 (2.0330) time: 0.5046 [2021-03-25 03:57:00 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 640/1251] eta: 0:05:12 lr: 0.000226 loss: 6.0211 (5.9468) grad_norm: 1.9771 (2.0340) time: 0.5126 [2021-03-25 03:57:05 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 650/1251] eta: 0:05:07 lr: 0.000227 loss: 5.7145 (5.9446) grad_norm: 1.9771 (2.0341) time: 0.5087 [2021-03-25 03:57:10 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 660/1251] eta: 0:05:01 lr: 0.000227 loss: 5.7849 (5.9428) grad_norm: 2.0269 (2.0362) time: 0.5000 [2021-03-25 03:57:15 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 670/1251] eta: 0:04:56 lr: 0.000228 loss: 5.7849 (5.9416) grad_norm: 2.0672 (2.0368) time: 0.5045 [2021-03-25 03:57:20 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 680/1251] eta: 0:04:51 lr: 0.000228 loss: 5.9695 (5.9416) grad_norm: 1.9783 (2.0384) time: 0.5126 [2021-03-25 03:57:25 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 690/1251] eta: 0:04:46 lr: 0.000228 loss: 5.9695 (5.9407) grad_norm: 1.8222 (2.0372) time: 0.5092 [2021-03-25 03:57:30 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 700/1251] eta: 0:04:41 lr: 0.000229 loss: 5.9560 (5.9403) grad_norm: 1.8222 (2.0364) time: 0.4991 [2021-03-25 03:57:35 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 710/1251] eta: 0:04:36 lr: 0.000229 loss: 5.9506 (5.9384) grad_norm: 2.0398 (2.0417) time: 0.5008 [2021-03-25 03:57:40 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 720/1251] eta: 0:04:31 lr: 0.000230 loss: 5.6186 (5.9348) grad_norm: 2.2170 (2.0490) time: 0.5014 [2021-03-25 03:57:45 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 730/1251] eta: 0:04:25 lr: 0.000230 loss: 5.6186 (5.9330) grad_norm: 1.9587 (2.0500) time: 0.4973 [2021-03-25 03:57:50 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 740/1251] eta: 0:04:20 lr: 0.000230 loss: 5.8576 (5.9320) grad_norm: 1.9167 (2.0515) time: 0.5120 [2021-03-25 03:57:55 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 750/1251] eta: 0:04:15 lr: 0.000231 loss: 5.8890 (5.9317) grad_norm: 1.8744 (2.0477) time: 0.5126 [2021-03-25 03:58:00 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 760/1251] eta: 0:04:10 lr: 0.000231 loss: 5.9852 (5.9324) grad_norm: 1.7720 (2.0488) time: 0.4991 [2021-03-25 03:58:05 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 770/1251] eta: 0:04:05 lr: 0.000232 loss: 5.9772 (5.9302) grad_norm: 1.9806 (2.0491) time: 0.5018 [2021-03-25 03:58:10 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 780/1251] eta: 0:04:00 lr: 0.000232 loss: 5.8508 (5.9298) grad_norm: 1.9806 (2.0502) time: 0.5036 [2021-03-25 03:58:15 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 790/1251] eta: 0:03:55 lr: 0.000232 loss: 5.8905 (5.9289) grad_norm: 2.0026 (2.0505) time: 0.4999 [2021-03-25 03:58:20 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 800/1251] eta: 0:03:49 lr: 0.000233 loss: 5.8865 (5.9280) grad_norm: 2.0739 (2.0518) time: 0.5005 [2021-03-25 03:58:25 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 810/1251] eta: 0:03:44 lr: 0.000233 loss: 5.9845 (5.9270) grad_norm: 2.1232 (2.0540) time: 0.5042 [2021-03-25 03:58:30 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 820/1251] eta: 0:03:39 lr: 0.000234 loss: 5.9977 (5.9277) grad_norm: 1.9645 (2.0531) time: 0.5047 [2021-03-25 03:58:36 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 830/1251] eta: 0:03:34 lr: 0.000234 loss: 6.0496 (5.9277) grad_norm: 1.9094 (2.0518) time: 0.5089 [2021-03-25 03:58:41 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 840/1251] eta: 0:03:29 lr: 0.000234 loss: 5.8895 (5.9266) grad_norm: 1.9094 (2.0503) time: 0.5113 [2021-03-25 03:58:46 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 850/1251] eta: 0:03:24 lr: 0.000235 loss: 5.8803 (5.9255) grad_norm: 1.9278 (2.0497) time: 0.5060 [2021-03-25 03:58:51 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 860/1251] eta: 0:03:19 lr: 0.000235 loss: 6.1264 (5.9290) grad_norm: 2.0379 (2.0500) time: 0.5112 [2021-03-25 03:58:56 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 870/1251] eta: 0:03:14 lr: 0.000236 loss: 6.1990 (5.9308) grad_norm: 1.9322 (2.0500) time: 0.5121 [2021-03-25 03:59:01 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 880/1251] eta: 0:03:09 lr: 0.000236 loss: 6.0622 (5.9313) grad_norm: 1.9322 (2.0487) time: 0.5072 [2021-03-25 03:59:06 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 890/1251] eta: 0:03:03 lr: 0.000236 loss: 5.9883 (5.9294) grad_norm: 1.7411 (2.0457) time: 0.5089 [2021-03-25 03:59:11 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 900/1251] eta: 0:02:58 lr: 0.000237 loss: 5.6375 (5.9280) grad_norm: 1.8151 (2.0472) time: 0.5032 [2021-03-25 03:59:16 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 910/1251] eta: 0:02:53 lr: 0.000237 loss: 5.9269 (5.9281) grad_norm: 1.9345 (2.0483) time: 0.5008 [2021-03-25 03:59:21 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 920/1251] eta: 0:02:48 lr: 0.000238 loss: 5.9269 (5.9278) grad_norm: 1.9345 (2.0475) time: 0.4987 [2021-03-25 03:59:26 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 930/1251] eta: 0:02:43 lr: 0.000238 loss: 5.9949 (5.9283) grad_norm: 1.8421 (2.0478) time: 0.4966 [2021-03-25 03:59:31 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 940/1251] eta: 0:02:38 lr: 0.000238 loss: 6.0273 (5.9293) grad_norm: 2.1010 (2.0513) time: 0.5011 [2021-03-25 03:59:36 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 950/1251] eta: 0:02:33 lr: 0.000239 loss: 5.9276 (5.9276) grad_norm: 2.1400 (2.0520) time: 0.5007 [2021-03-25 03:59:41 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 960/1251] eta: 0:02:28 lr: 0.000239 loss: 5.8514 (5.9257) grad_norm: 1.9778 (2.0506) time: 0.5009 [2021-03-25 03:59:46 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 970/1251] eta: 0:02:22 lr: 0.000240 loss: 6.0239 (5.9264) grad_norm: 1.9073 (2.0493) time: 0.5030 [2021-03-25 03:59:51 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 980/1251] eta: 0:02:17 lr: 0.000240 loss: 5.9849 (5.9250) grad_norm: 2.0175 (2.0509) time: 0.5042 [2021-03-25 03:59:56 swin_small_patch4_window7_224] INFO: Epoch: [4] [ 990/1251] eta: 0:02:12 lr: 0.000240 loss: 5.8328 (5.9239) grad_norm: 1.8640 (2.0480) time: 0.5027 [2021-03-25 04:00:01 swin_small_patch4_window7_224] INFO: Epoch: [4] [1000/1251] eta: 0:02:07 lr: 0.000241 loss: 5.8328 (5.9236) grad_norm: 1.7838 (2.0490) time: 0.5009 [2021-03-25 04:00:06 swin_small_patch4_window7_224] INFO: Epoch: [4] [1010/1251] eta: 0:02:02 lr: 0.000241 loss: 6.0598 (5.9241) grad_norm: 1.9506 (2.0484) time: 0.5026 [2021-03-25 04:00:11 swin_small_patch4_window7_224] INFO: Epoch: [4] [1020/1251] eta: 0:01:57 lr: 0.000242 loss: 5.8889 (5.9223) grad_norm: 1.9998 (2.0515) time: 0.5038 [2021-03-25 04:00:16 swin_small_patch4_window7_224] INFO: Epoch: [4] [1030/1251] eta: 0:01:52 lr: 0.000242 loss: 5.6108 (5.9195) grad_norm: 1.9784 (2.0505) time: 0.5032 [2021-03-25 04:00:21 swin_small_patch4_window7_224] INFO: Epoch: [4] [1040/1251] eta: 0:01:47 lr: 0.000242 loss: 5.6861 (5.9189) grad_norm: 1.9362 (2.0507) time: 0.5033 [2021-03-25 04:00:26 swin_small_patch4_window7_224] INFO: Epoch: [4] [1050/1251] eta: 0:01:42 lr: 0.000243 loss: 5.7704 (5.9175) grad_norm: 2.0841 (2.0521) time: 0.5054 [2021-03-25 04:00:32 swin_small_patch4_window7_224] INFO: Epoch: [4] [1060/1251] eta: 0:01:37 lr: 0.000243 loss: 5.8981 (5.9174) grad_norm: 1.9678 (2.0508) time: 0.5050 [2021-03-25 04:00:37 swin_small_patch4_window7_224] INFO: Epoch: [4] [1070/1251] eta: 0:01:32 lr: 0.000244 loss: 5.9628 (5.9174) grad_norm: 1.9489 (2.0493) time: 0.5053 [2021-03-25 04:00:42 swin_small_patch4_window7_224] INFO: Epoch: [4] [1080/1251] eta: 0:01:26 lr: 0.000244 loss: 5.9783 (5.9169) grad_norm: 1.9322 (2.0480) time: 0.5066 [2021-03-25 04:00:47 swin_small_patch4_window7_224] INFO: Epoch: [4] [1090/1251] eta: 0:01:21 lr: 0.000244 loss: 6.0157 (5.9170) grad_norm: 1.9322 (2.0486) time: 0.5071 [2021-03-25 04:00:52 swin_small_patch4_window7_224] INFO: Epoch: [4] [1100/1251] eta: 0:01:16 lr: 0.000245 loss: 5.7309 (5.9149) grad_norm: 1.9071 (2.0474) time: 0.5037 [2021-03-25 04:00:57 swin_small_patch4_window7_224] INFO: Epoch: [4] [1110/1251] eta: 0:01:11 lr: 0.000245 loss: 5.6215 (5.9118) grad_norm: 1.8840 (2.0472) time: 0.5000 [2021-03-25 04:01:02 swin_small_patch4_window7_224] INFO: Epoch: [4] [1120/1251] eta: 0:01:06 lr: 0.000246 loss: 5.7152 (5.9115) grad_norm: 2.0517 (2.0490) time: 0.5002 [2021-03-25 04:01:07 swin_small_patch4_window7_224] INFO: Epoch: [4] [1130/1251] eta: 0:01:01 lr: 0.000246 loss: 5.9329 (5.9111) grad_norm: 1.9849 (2.0479) time: 0.5015 [2021-03-25 04:01:12 swin_small_patch4_window7_224] INFO: Epoch: [4] [1140/1251] eta: 0:00:56 lr: 0.000246 loss: 5.6498 (5.9087) grad_norm: 1.9092 (2.0467) time: 0.4984 [2021-03-25 04:01:17 swin_small_patch4_window7_224] INFO: Epoch: [4] [1150/1251] eta: 0:00:51 lr: 0.000247 loss: 5.6007 (5.9087) grad_norm: 2.0082 (2.0482) time: 0.5001 [2021-03-25 04:01:22 swin_small_patch4_window7_224] INFO: Epoch: [4] [1160/1251] eta: 0:00:46 lr: 0.000247 loss: 5.9416 (5.9083) grad_norm: 2.0891 (2.0475) time: 0.5097 [2021-03-25 04:01:27 swin_small_patch4_window7_224] INFO: Epoch: [4] [1170/1251] eta: 0:00:41 lr: 0.000248 loss: 5.9980 (5.9088) grad_norm: 2.0008 (2.0473) time: 0.5083 [2021-03-25 04:01:32 swin_small_patch4_window7_224] INFO: Epoch: [4] [1180/1251] eta: 0:00:36 lr: 0.000248 loss: 5.9690 (5.9080) grad_norm: 1.9188 (2.0493) time: 0.5013 [2021-03-25 04:01:37 swin_small_patch4_window7_224] INFO: Epoch: [4] [1190/1251] eta: 0:00:30 lr: 0.000248 loss: 5.9834 (5.9079) grad_norm: 1.9875 (2.0496) time: 0.5025 [2021-03-25 04:01:42 swin_small_patch4_window7_224] INFO: Epoch: [4] [1200/1251] eta: 0:00:25 lr: 0.000249 loss: 6.0451 (5.9078) grad_norm: 2.0051 (2.0506) time: 0.5052 [2021-03-25 04:01:47 swin_small_patch4_window7_224] INFO: Epoch: [4] [1210/1251] eta: 0:00:20 lr: 0.000249 loss: 5.6029 (5.9043) grad_norm: 1.9232 (2.0495) time: 0.5059 [2021-03-25 04:01:52 swin_small_patch4_window7_224] INFO: Epoch: [4] [1220/1251] eta: 0:00:15 lr: 0.000250 loss: 5.6444 (5.9041) grad_norm: 1.8691 (2.0479) time: 0.5075 [2021-03-25 04:01:57 swin_small_patch4_window7_224] INFO: Epoch: [4] [1230/1251] eta: 0:00:10 lr: 0.000250 loss: 5.8207 (5.9029) grad_norm: 1.8702 (2.0475) time: 0.5092 [2021-03-25 04:02:02 swin_small_patch4_window7_224] INFO: Epoch: [4] [1240/1251] eta: 0:00:05 lr: 0.000250 loss: 5.8359 (5.9032) grad_norm: 1.9254 (2.0463) time: 0.5101 [2021-03-25 04:02:07 swin_small_patch4_window7_224] INFO: Epoch: [4] [1250/1251] eta: 0:00:00 lr: 0.000251 loss: 5.9612 (5.9040) grad_norm: 2.0580 (2.0494) time: 0.5062 [2021-03-25 04:02:10 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:20 loss: 3.6300 (3.6300) acc1: 26.5625 (26.5625) acc5: 46.8750 (46.8750) [2021-03-25 04:02:13 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 3.8903 (3.8155) acc1: 26.5625 (27.4148) acc5: 46.8750 (47.4432) [2021-03-25 04:02:17 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 3.8903 (3.8637) acc1: 25.0000 (25.6696) acc5: 46.8750 (47.1726) [2021-03-25 04:02:20 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 3.8867 (3.9009) acc1: 23.4375 (24.5968) acc5: 45.3125 (46.9254) [2021-03-25 04:02:21 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 3.9451 (3.9283) acc1: 21.8750 (24.1997) acc5: 43.7500 (46.7988) [2021-03-25 04:02:22 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.8947 (3.9286) acc1: 23.4375 (24.7040) acc5: 43.7500 (46.6240) [2021-03-25 04:02:24 swin_small_patch4_window7_224] INFO: * Acc@1 23.240 Acc@5 46.492 loss 3.926 [2021-03-25 04:02:24 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 23.2% [2021-03-25 04:02:24 swin_small_patch4_window7_224] INFO: Max accuracy: 23.24% [2021-03-25 04:02:28 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 0/1251] eta: 1:24:49 lr: 0.000251 loss: 5.8806 (5.8806) grad_norm: 1.9301 (1.9301) time: 4.0680 [2021-03-25 04:02:33 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 10/1251] eta: 0:17:38 lr: 0.000251 loss: 5.9389 (5.8681) grad_norm: 1.9336 (2.0730) time: 0.8531 [2021-03-25 04:02:38 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 20/1251] eta: 0:14:09 lr: 0.000252 loss: 6.0050 (5.8888) grad_norm: 1.9727 (2.0630) time: 0.5212 [2021-03-25 04:02:43 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 30/1251] eta: 0:12:49 lr: 0.000252 loss: 6.0050 (5.8666) grad_norm: 2.1257 (2.1385) time: 0.5080 [2021-03-25 04:02:48 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 40/1251] eta: 0:12:07 lr: 0.000252 loss: 6.0414 (5.9181) grad_norm: 2.1109 (2.0832) time: 0.5068 [2021-03-25 04:02:53 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 50/1251] eta: 0:11:41 lr: 0.000253 loss: 6.0414 (5.9251) grad_norm: 1.8640 (2.0572) time: 0.5125 [2021-03-25 04:02:58 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 60/1251] eta: 0:11:20 lr: 0.000253 loss: 5.9717 (5.9176) grad_norm: 1.9528 (2.1011) time: 0.5123 [2021-03-25 04:03:03 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 70/1251] eta: 0:11:03 lr: 0.000254 loss: 5.9415 (5.9120) grad_norm: 2.1073 (2.1170) time: 0.5040 [2021-03-25 04:03:08 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 80/1251] eta: 0:10:48 lr: 0.000254 loss: 5.8741 (5.8955) grad_norm: 1.9279 (2.0947) time: 0.5004 [2021-03-25 04:03:14 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 90/1251] eta: 0:10:37 lr: 0.000254 loss: 5.7499 (5.8865) grad_norm: 1.9279 (2.1031) time: 0.5045 [2021-03-25 04:03:19 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 100/1251] eta: 0:10:27 lr: 0.000255 loss: 5.8037 (5.8696) grad_norm: 2.0956 (2.0983) time: 0.5069 [2021-03-25 04:03:24 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 110/1251] eta: 0:10:17 lr: 0.000255 loss: 5.9732 (5.8705) grad_norm: 2.0956 (2.1089) time: 0.5035 [2021-03-25 04:03:29 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 120/1251] eta: 0:10:08 lr: 0.000256 loss: 6.0047 (5.8779) grad_norm: 2.0881 (2.1302) time: 0.5049 [2021-03-25 04:03:34 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 130/1251] eta: 0:10:01 lr: 0.000256 loss: 5.9895 (5.8708) grad_norm: 2.0413 (2.1327) time: 0.5113 [2021-03-25 04:03:39 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 140/1251] eta: 0:09:53 lr: 0.000256 loss: 5.9186 (5.8685) grad_norm: 1.8803 (2.1240) time: 0.5092 [2021-03-25 04:03:44 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 150/1251] eta: 0:09:45 lr: 0.000257 loss: 5.9186 (5.8671) grad_norm: 1.8803 (2.1105) time: 0.4996 [2021-03-25 04:03:49 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 160/1251] eta: 0:09:37 lr: 0.000257 loss: 5.8787 (5.8646) grad_norm: 1.7737 (2.0875) time: 0.4985 [2021-03-25 04:03:54 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 170/1251] eta: 0:09:31 lr: 0.000258 loss: 5.9005 (5.8683) grad_norm: 1.7227 (2.0694) time: 0.5037 [2021-03-25 04:03:59 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 180/1251] eta: 0:09:24 lr: 0.000258 loss: 5.7368 (5.8565) grad_norm: 1.9214 (2.0698) time: 0.5068 [2021-03-25 04:04:04 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 190/1251] eta: 0:09:18 lr: 0.000258 loss: 5.6717 (5.8451) grad_norm: 2.0423 (2.0820) time: 0.5112 [2021-03-25 04:04:09 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 200/1251] eta: 0:09:12 lr: 0.000259 loss: 5.7007 (5.8347) grad_norm: 2.0369 (2.0733) time: 0.5170 [2021-03-25 04:04:14 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 210/1251] eta: 0:09:07 lr: 0.000259 loss: 5.7952 (5.8308) grad_norm: 1.7840 (2.0670) time: 0.5183 [2021-03-25 04:04:19 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 220/1251] eta: 0:09:00 lr: 0.000260 loss: 5.6826 (5.8194) grad_norm: 2.0053 (2.0808) time: 0.5050 [2021-03-25 04:04:24 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 230/1251] eta: 0:08:54 lr: 0.000260 loss: 5.6100 (5.8126) grad_norm: 1.9711 (2.0726) time: 0.4975 [2021-03-25 04:04:30 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 240/1251] eta: 0:08:48 lr: 0.000260 loss: 5.8065 (5.8153) grad_norm: 1.9702 (2.0789) time: 0.5063 [2021-03-25 04:04:35 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 250/1251] eta: 0:08:42 lr: 0.000261 loss: 5.9544 (5.8093) grad_norm: 1.8948 (2.0696) time: 0.5130 [2021-03-25 04:04:40 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 260/1251] eta: 0:08:37 lr: 0.000261 loss: 5.9022 (5.8142) grad_norm: 1.8949 (2.0713) time: 0.5115 [2021-03-25 04:04:45 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 270/1251] eta: 0:08:31 lr: 0.000262 loss: 5.8752 (5.8138) grad_norm: 2.0999 (2.0723) time: 0.5065 [2021-03-25 04:04:50 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 280/1251] eta: 0:08:25 lr: 0.000262 loss: 5.7939 (5.8092) grad_norm: 1.9648 (2.0656) time: 0.4998 [2021-03-25 04:04:55 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 290/1251] eta: 0:08:19 lr: 0.000262 loss: 5.8401 (5.8126) grad_norm: 1.8452 (2.0624) time: 0.5001 [2021-03-25 04:05:00 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 300/1251] eta: 0:08:13 lr: 0.000263 loss: 5.9205 (5.8125) grad_norm: 1.9923 (2.0685) time: 0.5022 [2021-03-25 04:05:05 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 310/1251] eta: 0:08:07 lr: 0.000263 loss: 5.6136 (5.8091) grad_norm: 1.9541 (2.0644) time: 0.4998 [2021-03-25 04:05:10 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 320/1251] eta: 0:08:02 lr: 0.000264 loss: 5.6020 (5.8095) grad_norm: 1.8598 (2.0607) time: 0.5036 [2021-03-25 04:05:15 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 330/1251] eta: 0:07:56 lr: 0.000264 loss: 5.8996 (5.8056) grad_norm: 2.0247 (2.0783) time: 0.5027 [2021-03-25 04:05:20 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 340/1251] eta: 0:07:51 lr: 0.000264 loss: 5.8478 (5.8070) grad_norm: 2.1961 (2.0848) time: 0.5005 [2021-03-25 04:05:25 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 350/1251] eta: 0:07:45 lr: 0.000265 loss: 5.7282 (5.8017) grad_norm: 2.0330 (2.0812) time: 0.5030 [2021-03-25 04:05:30 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 360/1251] eta: 0:07:40 lr: 0.000265 loss: 5.7609 (5.8014) grad_norm: 1.9094 (2.0759) time: 0.5079 [2021-03-25 04:05:35 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 370/1251] eta: 0:07:34 lr: 0.000266 loss: 5.9038 (5.8051) grad_norm: 1.9094 (2.0746) time: 0.5069 [2021-03-25 04:05:40 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 380/1251] eta: 0:07:29 lr: 0.000266 loss: 5.9031 (5.8015) grad_norm: 1.8936 (2.0694) time: 0.5029 [2021-03-25 04:05:45 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 390/1251] eta: 0:07:23 lr: 0.000266 loss: 5.9027 (5.8011) grad_norm: 1.8975 (2.0675) time: 0.5032 [2021-03-25 04:05:50 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 400/1251] eta: 0:07:18 lr: 0.000267 loss: 5.8081 (5.7953) grad_norm: 1.9994 (2.0716) time: 0.5075 [2021-03-25 04:05:55 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 410/1251] eta: 0:07:13 lr: 0.000267 loss: 5.8045 (5.7963) grad_norm: 2.1009 (2.0719) time: 0.5074 [2021-03-25 04:06:00 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 420/1251] eta: 0:07:07 lr: 0.000268 loss: 5.7998 (5.7918) grad_norm: 1.8411 (2.0668) time: 0.5027 [2021-03-25 04:06:05 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 430/1251] eta: 0:07:02 lr: 0.000268 loss: 5.5372 (5.7875) grad_norm: 1.9141 (2.0643) time: 0.5030 [2021-03-25 04:06:10 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 440/1251] eta: 0:06:57 lr: 0.000268 loss: 5.6147 (5.7835) grad_norm: 1.9628 (2.0641) time: 0.5055 [2021-03-25 04:06:15 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 450/1251] eta: 0:06:51 lr: 0.000269 loss: 5.8783 (5.7861) grad_norm: 1.9635 (2.0627) time: 0.5038 [2021-03-25 04:06:20 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 460/1251] eta: 0:06:46 lr: 0.000269 loss: 5.8806 (5.7877) grad_norm: 1.8808 (2.0603) time: 0.4996 [2021-03-25 04:06:26 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 470/1251] eta: 0:06:41 lr: 0.000270 loss: 5.8806 (5.7908) grad_norm: 1.8915 (2.0594) time: 0.5037 [2021-03-25 04:06:31 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 480/1251] eta: 0:06:35 lr: 0.000270 loss: 5.8854 (5.7905) grad_norm: 1.9230 (2.0610) time: 0.5085 [2021-03-25 04:06:36 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 490/1251] eta: 0:06:30 lr: 0.000270 loss: 5.5742 (5.7856) grad_norm: 2.1987 (inf) time: 0.5035 [2021-03-25 04:06:41 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 500/1251] eta: 0:06:25 lr: 0.000271 loss: 5.5742 (5.7846) grad_norm: 1.9117 (inf) time: 0.5014 [2021-03-25 04:06:46 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 510/1251] eta: 0:06:20 lr: 0.000271 loss: 5.5009 (5.7794) grad_norm: 1.8244 (inf) time: 0.5036 [2021-03-25 04:06:51 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 520/1251] eta: 0:06:14 lr: 0.000272 loss: 5.5431 (5.7796) grad_norm: 1.8802 (inf) time: 0.5075 [2021-03-25 04:06:56 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 530/1251] eta: 0:06:09 lr: 0.000272 loss: 5.9620 (5.7800) grad_norm: 1.8054 (inf) time: 0.5107 [2021-03-25 04:07:01 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 540/1251] eta: 0:06:04 lr: 0.000272 loss: 6.0473 (5.7851) grad_norm: 1.8731 (inf) time: 0.5040 [2021-03-25 04:07:06 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 550/1251] eta: 0:05:59 lr: 0.000273 loss: 6.0008 (5.7802) grad_norm: 1.8731 (inf) time: 0.5097 [2021-03-25 04:07:11 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 560/1251] eta: 0:05:54 lr: 0.000273 loss: 5.6746 (5.7809) grad_norm: 1.9480 (inf) time: 0.5125 [2021-03-25 04:07:16 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 570/1251] eta: 0:05:48 lr: 0.000274 loss: 5.7756 (5.7807) grad_norm: 1.9875 (inf) time: 0.5067 [2021-03-25 04:07:21 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 580/1251] eta: 0:05:43 lr: 0.000274 loss: 5.7251 (5.7779) grad_norm: 1.9259 (inf) time: 0.5040 [2021-03-25 04:07:26 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 590/1251] eta: 0:05:38 lr: 0.000274 loss: 5.8284 (5.7777) grad_norm: 1.8940 (inf) time: 0.5026 [2021-03-25 04:07:31 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 600/1251] eta: 0:05:33 lr: 0.000275 loss: 5.4039 (5.7704) grad_norm: 1.9670 (inf) time: 0.5049 [2021-03-25 04:07:36 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 610/1251] eta: 0:05:28 lr: 0.000275 loss: 5.3769 (5.7665) grad_norm: 2.0183 (inf) time: 0.5014 [2021-03-25 04:07:41 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 620/1251] eta: 0:05:22 lr: 0.000276 loss: 5.7112 (5.7650) grad_norm: 1.9263 (inf) time: 0.4990 [2021-03-25 04:07:46 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 630/1251] eta: 0:05:17 lr: 0.000276 loss: 5.7112 (5.7635) grad_norm: 1.9570 (inf) time: 0.5016 [2021-03-25 04:07:51 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 640/1251] eta: 0:05:12 lr: 0.000276 loss: 5.7304 (5.7633) grad_norm: 2.2126 (inf) time: 0.5080 [2021-03-25 04:07:56 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 650/1251] eta: 0:05:07 lr: 0.000277 loss: 5.6727 (5.7589) grad_norm: 2.1857 (inf) time: 0.5070 [2021-03-25 04:08:02 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 660/1251] eta: 0:05:02 lr: 0.000277 loss: 5.6472 (5.7593) grad_norm: 2.0671 (inf) time: 0.5031 [2021-03-25 04:08:07 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 670/1251] eta: 0:04:56 lr: 0.000278 loss: 5.6624 (5.7582) grad_norm: 1.9487 (inf) time: 0.5053 [2021-03-25 04:08:12 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 680/1251] eta: 0:04:51 lr: 0.000278 loss: 5.6867 (5.7589) grad_norm: 1.9043 (inf) time: 0.5084 [2021-03-25 04:08:17 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 690/1251] eta: 0:04:46 lr: 0.000278 loss: 5.6741 (5.7544) grad_norm: 1.8959 (inf) time: 0.5058 [2021-03-25 04:08:22 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 700/1251] eta: 0:04:41 lr: 0.000279 loss: 5.5520 (5.7499) grad_norm: 1.8959 (inf) time: 0.5055 [2021-03-25 04:08:27 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 710/1251] eta: 0:04:36 lr: 0.000279 loss: 5.6498 (5.7501) grad_norm: 2.0148 (inf) time: 0.5036 [2021-03-25 04:08:32 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 720/1251] eta: 0:04:31 lr: 0.000279 loss: 5.6084 (5.7481) grad_norm: 1.9863 (inf) time: 0.5029 [2021-03-25 04:08:37 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 730/1251] eta: 0:04:26 lr: 0.000280 loss: 5.6084 (5.7469) grad_norm: 1.8940 (inf) time: 0.5042 [2021-03-25 04:08:42 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 740/1251] eta: 0:04:20 lr: 0.000280 loss: 5.6199 (5.7449) grad_norm: 1.9224 (inf) time: 0.5051 [2021-03-25 04:08:47 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 750/1251] eta: 0:04:15 lr: 0.000281 loss: 5.4396 (5.7398) grad_norm: 1.9873 (inf) time: 0.5114 [2021-03-25 04:08:52 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 760/1251] eta: 0:04:10 lr: 0.000281 loss: 5.4396 (5.7405) grad_norm: 1.9695 (inf) time: 0.5223 [2021-03-25 04:08:57 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 770/1251] eta: 0:04:05 lr: 0.000281 loss: 5.8791 (5.7385) grad_norm: 1.9214 (inf) time: 0.5184 [2021-03-25 04:09:03 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 780/1251] eta: 0:04:00 lr: 0.000282 loss: 5.7605 (5.7395) grad_norm: 1.8919 (inf) time: 0.5047 [2021-03-25 04:09:08 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 790/1251] eta: 0:03:55 lr: 0.000282 loss: 5.7964 (5.7368) grad_norm: 1.9231 (inf) time: 0.5093 [2021-03-25 04:09:13 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 800/1251] eta: 0:03:50 lr: 0.000283 loss: 5.7964 (5.7338) grad_norm: 1.9363 (inf) time: 0.5118 [2021-03-25 04:09:18 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 810/1251] eta: 0:03:45 lr: 0.000283 loss: 5.8505 (5.7360) grad_norm: 1.9411 (inf) time: 0.5051 [2021-03-25 04:09:23 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 820/1251] eta: 0:03:40 lr: 0.000283 loss: 5.8373 (5.7349) grad_norm: 1.9750 (inf) time: 0.5027 [2021-03-25 04:09:28 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 830/1251] eta: 0:03:34 lr: 0.000284 loss: 5.4967 (5.7313) grad_norm: 1.9229 (inf) time: 0.5046 [2021-03-25 04:09:33 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 840/1251] eta: 0:03:29 lr: 0.000284 loss: 5.6262 (5.7327) grad_norm: 1.9615 (inf) time: 0.5049 [2021-03-25 04:09:38 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 850/1251] eta: 0:03:24 lr: 0.000285 loss: 5.8778 (5.7330) grad_norm: 1.9615 (inf) time: 0.5036 [2021-03-25 04:09:43 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 860/1251] eta: 0:03:19 lr: 0.000285 loss: 5.7199 (5.7316) grad_norm: 1.8553 (inf) time: 0.5034 [2021-03-25 04:09:48 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 870/1251] eta: 0:03:14 lr: 0.000285 loss: 5.8046 (5.7316) grad_norm: 1.8553 (inf) time: 0.5137 [2021-03-25 04:09:53 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 880/1251] eta: 0:03:09 lr: 0.000286 loss: 5.8046 (5.7321) grad_norm: 1.8103 (inf) time: 0.5129 [2021-03-25 04:09:58 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 890/1251] eta: 0:03:04 lr: 0.000286 loss: 5.7362 (5.7308) grad_norm: 1.8408 (inf) time: 0.5034 [2021-03-25 04:10:03 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 900/1251] eta: 0:02:59 lr: 0.000287 loss: 5.8292 (5.7338) grad_norm: 1.8587 (inf) time: 0.5034 [2021-03-25 04:10:08 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 910/1251] eta: 0:02:53 lr: 0.000287 loss: 5.9044 (5.7350) grad_norm: 1.8461 (inf) time: 0.5032 [2021-03-25 04:10:13 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 920/1251] eta: 0:02:48 lr: 0.000287 loss: 5.8389 (5.7351) grad_norm: 1.8497 (inf) time: 0.5033 [2021-03-25 04:10:18 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 930/1251] eta: 0:02:43 lr: 0.000288 loss: 5.6485 (5.7320) grad_norm: 2.0054 (inf) time: 0.5058 [2021-03-25 04:10:24 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 940/1251] eta: 0:02:38 lr: 0.000288 loss: 5.5414 (5.7308) grad_norm: 2.0054 (inf) time: 0.5087 [2021-03-25 04:10:29 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 950/1251] eta: 0:02:33 lr: 0.000289 loss: 5.6734 (5.7295) grad_norm: 1.9193 (inf) time: 0.5153 [2021-03-25 04:10:34 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 960/1251] eta: 0:02:28 lr: 0.000289 loss: 5.6644 (5.7286) grad_norm: 1.9293 (inf) time: 0.5111 [2021-03-25 04:10:39 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 970/1251] eta: 0:02:23 lr: 0.000289 loss: 5.8004 (5.7293) grad_norm: 1.9157 (inf) time: 0.4985 [2021-03-25 04:10:44 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 980/1251] eta: 0:02:18 lr: 0.000290 loss: 5.7773 (5.7280) grad_norm: 1.8186 (inf) time: 0.4985 [2021-03-25 04:10:49 swin_small_patch4_window7_224] INFO: Epoch: [5] [ 990/1251] eta: 0:02:13 lr: 0.000290 loss: 5.7773 (5.7279) grad_norm: 1.8068 (inf) time: 0.5051 [2021-03-25 04:10:54 swin_small_patch4_window7_224] INFO: Epoch: [5] [1000/1251] eta: 0:02:07 lr: 0.000291 loss: 5.7947 (5.7263) grad_norm: 1.6398 (inf) time: 0.5078 [2021-03-25 04:10:59 swin_small_patch4_window7_224] INFO: Epoch: [5] [1010/1251] eta: 0:02:02 lr: 0.000291 loss: 5.8180 (5.7278) grad_norm: 1.6453 (inf) time: 0.5029 [2021-03-25 04:11:04 swin_small_patch4_window7_224] INFO: Epoch: [5] [1020/1251] eta: 0:01:57 lr: 0.000291 loss: 5.8550 (5.7275) grad_norm: 1.8149 (inf) time: 0.4979 [2021-03-25 04:11:09 swin_small_patch4_window7_224] INFO: Epoch: [5] [1030/1251] eta: 0:01:52 lr: 0.000292 loss: 5.5418 (5.7232) grad_norm: 2.0972 (inf) time: 0.5012 [2021-03-25 04:11:14 swin_small_patch4_window7_224] INFO: Epoch: [5] [1040/1251] eta: 0:01:47 lr: 0.000292 loss: 5.6401 (5.7231) grad_norm: 2.0314 (inf) time: 0.5034 [2021-03-25 04:11:19 swin_small_patch4_window7_224] INFO: Epoch: [5] [1050/1251] eta: 0:01:42 lr: 0.000293 loss: 5.7012 (5.7235) grad_norm: 1.9950 (inf) time: 0.4998 [2021-03-25 04:11:24 swin_small_patch4_window7_224] INFO: Epoch: [5] [1060/1251] eta: 0:01:37 lr: 0.000293 loss: 5.7049 (5.7244) grad_norm: 1.9878 (inf) time: 0.5015 [2021-03-25 04:11:29 swin_small_patch4_window7_224] INFO: Epoch: [5] [1070/1251] eta: 0:01:32 lr: 0.000293 loss: 5.7350 (5.7228) grad_norm: 2.0824 (inf) time: 0.5074 [2021-03-25 04:11:34 swin_small_patch4_window7_224] INFO: Epoch: [5] [1080/1251] eta: 0:01:27 lr: 0.000294 loss: 5.6444 (5.7203) grad_norm: 2.0434 (inf) time: 0.5108 [2021-03-25 04:11:39 swin_small_patch4_window7_224] INFO: Epoch: [5] [1090/1251] eta: 0:01:21 lr: 0.000294 loss: 5.6649 (5.7214) grad_norm: 1.9751 (inf) time: 0.5101 [2021-03-25 04:11:44 swin_small_patch4_window7_224] INFO: Epoch: [5] [1100/1251] eta: 0:01:16 lr: 0.000295 loss: 5.8790 (5.7221) grad_norm: 1.9195 (inf) time: 0.5093 [2021-03-25 04:11:49 swin_small_patch4_window7_224] INFO: Epoch: [5] [1110/1251] eta: 0:01:11 lr: 0.000295 loss: 5.7214 (5.7215) grad_norm: 1.9359 (inf) time: 0.5070 [2021-03-25 04:11:54 swin_small_patch4_window7_224] INFO: Epoch: [5] [1120/1251] eta: 0:01:06 lr: 0.000295 loss: 5.6915 (5.7203) grad_norm: 1.9506 (inf) time: 0.5010 [2021-03-25 04:12:00 swin_small_patch4_window7_224] INFO: Epoch: [5] [1130/1251] eta: 0:01:01 lr: 0.000296 loss: 5.7966 (5.7192) grad_norm: 1.9359 (inf) time: 0.5043 [2021-03-25 04:12:05 swin_small_patch4_window7_224] INFO: Epoch: [5] [1140/1251] eta: 0:00:56 lr: 0.000296 loss: 5.7712 (5.7186) grad_norm: 1.9446 (inf) time: 0.5089 [2021-03-25 04:12:10 swin_small_patch4_window7_224] INFO: Epoch: [5] [1150/1251] eta: 0:00:51 lr: 0.000297 loss: 5.4566 (5.7162) grad_norm: 1.7874 (inf) time: 0.5080 [2021-03-25 04:12:15 swin_small_patch4_window7_224] INFO: Epoch: [5] [1160/1251] eta: 0:00:46 lr: 0.000297 loss: 5.5076 (5.7152) grad_norm: 1.7240 (inf) time: 0.5027 [2021-03-25 04:12:20 swin_small_patch4_window7_224] INFO: Epoch: [5] [1170/1251] eta: 0:00:41 lr: 0.000297 loss: 5.7300 (5.7155) grad_norm: 1.9143 (inf) time: 0.4996 [2021-03-25 04:12:25 swin_small_patch4_window7_224] INFO: Epoch: [5] [1180/1251] eta: 0:00:36 lr: 0.000298 loss: 5.6510 (5.7141) grad_norm: 2.0044 (inf) time: 0.5059 [2021-03-25 04:12:30 swin_small_patch4_window7_224] INFO: Epoch: [5] [1190/1251] eta: 0:00:31 lr: 0.000298 loss: 5.5713 (5.7124) grad_norm: 1.9612 (inf) time: 0.5074 [2021-03-25 04:12:35 swin_small_patch4_window7_224] INFO: Epoch: [5] [1200/1251] eta: 0:00:25 lr: 0.000299 loss: 5.5713 (5.7126) grad_norm: 1.8385 (inf) time: 0.5053 [2021-03-25 04:12:40 swin_small_patch4_window7_224] INFO: Epoch: [5] [1210/1251] eta: 0:00:20 lr: 0.000299 loss: 5.7673 (5.7124) grad_norm: 1.8707 (inf) time: 0.5050 [2021-03-25 04:12:45 swin_small_patch4_window7_224] INFO: Epoch: [5] [1220/1251] eta: 0:00:15 lr: 0.000299 loss: 5.5772 (5.7121) grad_norm: 1.9170 (inf) time: 0.5037 [2021-03-25 04:12:50 swin_small_patch4_window7_224] INFO: Epoch: [5] [1230/1251] eta: 0:00:10 lr: 0.000300 loss: 5.5772 (5.7111) grad_norm: 1.9170 (inf) time: 0.5025 [2021-03-25 04:12:55 swin_small_patch4_window7_224] INFO: Epoch: [5] [1240/1251] eta: 0:00:05 lr: 0.000300 loss: 5.6021 (5.7093) grad_norm: 1.9972 (inf) time: 0.5001 [2021-03-25 04:13:00 swin_small_patch4_window7_224] INFO: Epoch: [5] [1250/1251] eta: 0:00:00 lr: 0.000301 loss: 5.6664 (5.7087) grad_norm: 1.9811 (inf) time: 0.5015 [2021-03-25 04:13:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 3.5252 (3.5252) acc1: 39.0625 (39.0625) acc5: 53.1250 (53.1250) [2021-03-25 04:13:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 3.5252 (3.5157) acc1: 28.1250 (30.3977) acc5: 53.1250 (53.8352) [2021-03-25 04:13:39 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 3.5476 (3.5491) acc1: 26.5625 (29.1667) acc5: 53.1250 (52.9762) [2021-03-25 04:13:40 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 3.4696 (3.5351) acc1: 28.1250 (28.7298) acc5: 51.5625 (52.7722) [2021-03-25 04:13:42 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 3.4696 (3.5409) acc1: 28.1250 (29.2302) acc5: 51.5625 (52.8963) [2021-03-25 04:13:42 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.5808 (3.5594) acc1: 28.1250 (28.8000) acc5: 51.5625 (52.7360) [2021-03-25 04:13:43 swin_small_patch4_window7_224] INFO: * Acc@1 28.458 Acc@5 53.274 loss 3.548 [2021-03-25 04:13:43 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 28.5% [2021-03-25 04:13:43 swin_small_patch4_window7_224] INFO: Max accuracy: 28.46% [2021-03-25 04:13:48 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 0/1251] eta: 1:30:13 lr: 0.000301 loss: 5.2148 (5.2148) grad_norm: 3.9907 (3.9907) time: 4.3270 [2021-03-25 04:13:53 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 10/1251] eta: 0:17:38 lr: 0.000301 loss: 5.6430 (5.5549) grad_norm: 1.8485 (2.1447) time: 0.8530 [2021-03-25 04:13:58 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 20/1251] eta: 0:14:12 lr: 0.000301 loss: 5.6430 (5.5168) grad_norm: 1.8320 (2.0168) time: 0.5105 [2021-03-25 04:14:03 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 30/1251] eta: 0:12:50 lr: 0.000302 loss: 5.5965 (5.4997) grad_norm: 1.8456 (1.9912) time: 0.5088 [2021-03-25 04:14:08 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 40/1251] eta: 0:12:09 lr: 0.000302 loss: 5.6821 (5.5632) grad_norm: 1.8646 (2.0103) time: 0.5072 [2021-03-25 04:14:13 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 50/1251] eta: 0:11:44 lr: 0.000303 loss: 5.6539 (5.5346) grad_norm: 2.1596 (2.0939) time: 0.5170 [2021-03-25 04:14:18 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 60/1251] eta: 0:11:22 lr: 0.000303 loss: 5.3039 (5.4964) grad_norm: 1.9536 (2.0726) time: 0.5143 [2021-03-25 04:14:24 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 70/1251] eta: 0:11:06 lr: 0.000303 loss: 5.5674 (5.5365) grad_norm: 1.9428 (2.0738) time: 0.5073 [2021-03-25 04:14:29 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 80/1251] eta: 0:10:51 lr: 0.000304 loss: 5.8014 (5.5622) grad_norm: 2.0101 (2.0664) time: 0.5040 [2021-03-25 04:14:34 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 90/1251] eta: 0:10:39 lr: 0.000304 loss: 5.7030 (5.5697) grad_norm: 1.9413 (2.0558) time: 0.5034 [2021-03-25 04:14:39 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 100/1251] eta: 0:10:27 lr: 0.000305 loss: 5.7166 (5.5765) grad_norm: 1.8332 (2.0473) time: 0.5019 [2021-03-25 04:14:44 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 110/1251] eta: 0:10:17 lr: 0.000305 loss: 5.7096 (5.5727) grad_norm: 1.9857 (2.0607) time: 0.5003 [2021-03-25 04:14:49 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 120/1251] eta: 0:10:09 lr: 0.000305 loss: 5.8122 (5.5822) grad_norm: 1.9628 (2.0515) time: 0.5073 [2021-03-25 04:14:54 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 130/1251] eta: 0:10:02 lr: 0.000306 loss: 5.8122 (5.5906) grad_norm: 1.8934 (2.0369) time: 0.5157 [2021-03-25 04:14:59 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 140/1251] eta: 0:09:54 lr: 0.000306 loss: 5.6885 (5.5919) grad_norm: 1.9746 (2.0544) time: 0.5084 [2021-03-25 04:15:04 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 150/1251] eta: 0:09:45 lr: 0.000307 loss: 5.6927 (5.5983) grad_norm: 2.0706 (2.0494) time: 0.4955 [2021-03-25 04:15:09 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 160/1251] eta: 0:09:38 lr: 0.000307 loss: 5.7806 (5.6073) grad_norm: 1.9555 (2.0505) time: 0.4961 [2021-03-25 04:15:14 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 170/1251] eta: 0:09:31 lr: 0.000307 loss: 5.6832 (5.5960) grad_norm: 1.8992 (2.0436) time: 0.4995 [2021-03-25 04:15:19 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 180/1251] eta: 0:09:24 lr: 0.000308 loss: 5.5648 (5.5912) grad_norm: 1.9005 (2.0482) time: 0.5004 [2021-03-25 04:15:24 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 190/1251] eta: 0:09:17 lr: 0.000308 loss: 5.6905 (5.5955) grad_norm: 1.8669 (2.0372) time: 0.4993 [2021-03-25 04:15:29 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 200/1251] eta: 0:09:11 lr: 0.000309 loss: 5.7918 (5.6042) grad_norm: 1.8806 (2.0428) time: 0.5073 [2021-03-25 04:15:34 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 210/1251] eta: 0:09:04 lr: 0.000309 loss: 5.7892 (5.6062) grad_norm: 2.1036 (2.0472) time: 0.5058 [2021-03-25 04:15:39 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 220/1251] eta: 0:08:58 lr: 0.000309 loss: 5.4387 (5.5870) grad_norm: 2.0809 (2.0492) time: 0.5013 [2021-03-25 04:15:44 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 230/1251] eta: 0:08:53 lr: 0.000310 loss: 5.3917 (5.5881) grad_norm: 1.8792 (2.0394) time: 0.5078 [2021-03-25 04:15:49 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 240/1251] eta: 0:08:47 lr: 0.000310 loss: 5.5979 (5.5844) grad_norm: 1.7971 (2.0329) time: 0.5094 [2021-03-25 04:15:54 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 250/1251] eta: 0:08:41 lr: 0.000311 loss: 5.4975 (5.5840) grad_norm: 1.8111 (2.0384) time: 0.5069 [2021-03-25 04:15:59 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 260/1251] eta: 0:08:35 lr: 0.000311 loss: 5.5635 (5.5837) grad_norm: 1.7653 (2.0282) time: 0.5075 [2021-03-25 04:16:04 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 270/1251] eta: 0:08:30 lr: 0.000311 loss: 5.5882 (5.5794) grad_norm: 1.8446 (2.0313) time: 0.5099 [2021-03-25 04:16:10 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 280/1251] eta: 0:08:24 lr: 0.000312 loss: 5.5860 (5.5807) grad_norm: 1.9009 (2.0433) time: 0.5093 [2021-03-25 04:16:15 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 290/1251] eta: 0:08:18 lr: 0.000312 loss: 5.6322 (5.5863) grad_norm: 1.8674 (2.0355) time: 0.5068 [2021-03-25 04:16:20 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 300/1251] eta: 0:08:13 lr: 0.000313 loss: 5.6872 (5.5856) grad_norm: 1.8864 (2.0382) time: 0.5037 [2021-03-25 04:16:25 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 310/1251] eta: 0:08:07 lr: 0.000313 loss: 5.6795 (5.5842) grad_norm: 1.9867 (2.0330) time: 0.5070 [2021-03-25 04:16:30 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 320/1251] eta: 0:08:02 lr: 0.000313 loss: 5.5612 (5.5800) grad_norm: 1.9220 (2.0350) time: 0.5109 [2021-03-25 04:16:35 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 330/1251] eta: 0:07:56 lr: 0.000314 loss: 5.5936 (5.5850) grad_norm: 2.0062 (2.0327) time: 0.5021 [2021-03-25 04:16:40 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 340/1251] eta: 0:07:51 lr: 0.000314 loss: 5.8584 (5.5826) grad_norm: 1.7937 (2.0266) time: 0.5022 [2021-03-25 04:16:45 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 350/1251] eta: 0:07:45 lr: 0.000315 loss: 5.4858 (5.5768) grad_norm: 1.7858 (2.0267) time: 0.5064 [2021-03-25 04:16:50 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 360/1251] eta: 0:07:40 lr: 0.000315 loss: 5.6919 (5.5799) grad_norm: 1.8926 (2.0256) time: 0.5030 [2021-03-25 04:16:55 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 370/1251] eta: 0:07:34 lr: 0.000315 loss: 5.6919 (5.5818) grad_norm: 1.9566 (2.0244) time: 0.5075 [2021-03-25 04:17:00 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 380/1251] eta: 0:07:29 lr: 0.000316 loss: 5.6665 (5.5806) grad_norm: 1.9566 (2.0231) time: 0.5124 [2021-03-25 04:17:05 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 390/1251] eta: 0:07:24 lr: 0.000316 loss: 5.6798 (5.5847) grad_norm: 1.8292 (2.0181) time: 0.5066 [2021-03-25 04:17:10 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 400/1251] eta: 0:07:18 lr: 0.000317 loss: 5.7787 (5.5893) grad_norm: 1.9028 (2.0182) time: 0.4998 [2021-03-25 04:17:15 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 410/1251] eta: 0:07:13 lr: 0.000317 loss: 5.5615 (5.5850) grad_norm: 1.9349 (2.0150) time: 0.5021 [2021-03-25 04:17:20 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 420/1251] eta: 0:07:07 lr: 0.000317 loss: 5.4570 (5.5846) grad_norm: 1.8849 (2.0226) time: 0.5047 [2021-03-25 04:17:25 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 430/1251] eta: 0:07:02 lr: 0.000318 loss: 5.6025 (5.5844) grad_norm: 2.0474 (2.0297) time: 0.5029 [2021-03-25 04:17:30 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 440/1251] eta: 0:06:57 lr: 0.000318 loss: 5.6322 (5.5877) grad_norm: 1.8654 (2.0277) time: 0.5031 [2021-03-25 04:17:35 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 450/1251] eta: 0:06:51 lr: 0.000319 loss: 5.6322 (5.5856) grad_norm: 1.7887 (2.0221) time: 0.5074 [2021-03-25 04:17:40 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 460/1251] eta: 0:06:46 lr: 0.000319 loss: 5.4765 (5.5833) grad_norm: 1.8602 (2.0206) time: 0.5040 [2021-03-25 04:17:46 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 470/1251] eta: 0:06:41 lr: 0.000319 loss: 5.4327 (5.5818) grad_norm: 1.9210 (2.0187) time: 0.5040 [2021-03-25 04:17:51 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 480/1251] eta: 0:06:36 lr: 0.000320 loss: 5.4327 (5.5802) grad_norm: 1.9011 (2.0170) time: 0.5089 [2021-03-25 04:17:56 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 490/1251] eta: 0:06:30 lr: 0.000320 loss: 5.4548 (5.5795) grad_norm: 1.8270 (2.0125) time: 0.5047 [2021-03-25 04:18:01 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 500/1251] eta: 0:06:25 lr: 0.000321 loss: 5.6703 (5.5799) grad_norm: 1.7051 (2.0092) time: 0.5031 [2021-03-25 04:18:06 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 510/1251] eta: 0:06:20 lr: 0.000321 loss: 5.4556 (5.5783) grad_norm: 1.8478 (2.0094) time: 0.5076 [2021-03-25 04:18:11 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 520/1251] eta: 0:06:15 lr: 0.000321 loss: 5.2817 (5.5730) grad_norm: 2.0714 (2.0172) time: 0.5127 [2021-03-25 04:18:16 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 530/1251] eta: 0:06:09 lr: 0.000322 loss: 5.5185 (5.5739) grad_norm: 2.2038 (2.0269) time: 0.5107 [2021-03-25 04:18:21 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 540/1251] eta: 0:06:04 lr: 0.000322 loss: 5.6020 (5.5715) grad_norm: 2.0556 (2.0260) time: 0.5127 [2021-03-25 04:18:26 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 550/1251] eta: 0:05:59 lr: 0.000323 loss: 5.5426 (5.5662) grad_norm: 1.9417 (2.0237) time: 0.5202 [2021-03-25 04:18:32 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 560/1251] eta: 0:05:54 lr: 0.000323 loss: 5.5579 (5.5661) grad_norm: 1.7612 (2.0205) time: 0.5170 [2021-03-25 04:18:37 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 570/1251] eta: 0:05:49 lr: 0.000323 loss: 5.7859 (5.5694) grad_norm: 1.7155 (2.0165) time: 0.5122 [2021-03-25 04:18:42 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 580/1251] eta: 0:05:44 lr: 0.000324 loss: 5.7732 (5.5697) grad_norm: 1.7580 (2.0159) time: 0.5073 [2021-03-25 04:18:47 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 590/1251] eta: 0:05:39 lr: 0.000324 loss: 5.7522 (5.5747) grad_norm: 1.9542 (2.0162) time: 0.5007 [2021-03-25 04:18:52 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 600/1251] eta: 0:05:33 lr: 0.000325 loss: 5.6066 (5.5712) grad_norm: 1.9541 (2.0141) time: 0.5084 [2021-03-25 04:18:57 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 610/1251] eta: 0:05:28 lr: 0.000325 loss: 5.2615 (5.5671) grad_norm: 1.8477 (2.0106) time: 0.5144 [2021-03-25 04:19:02 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 620/1251] eta: 0:05:23 lr: 0.000325 loss: 5.4999 (5.5683) grad_norm: 1.8477 (2.0095) time: 0.5071 [2021-03-25 04:19:07 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 630/1251] eta: 0:05:18 lr: 0.000326 loss: 5.5885 (5.5659) grad_norm: 1.8976 (2.0082) time: 0.5011 [2021-03-25 04:19:12 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 640/1251] eta: 0:05:13 lr: 0.000326 loss: 5.6222 (5.5672) grad_norm: 1.9715 (2.0086) time: 0.5046 [2021-03-25 04:19:17 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 650/1251] eta: 0:05:07 lr: 0.000327 loss: 5.7083 (5.5672) grad_norm: 2.0872 (2.0109) time: 0.5064 [2021-03-25 04:19:22 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 660/1251] eta: 0:05:02 lr: 0.000327 loss: 5.4630 (5.5646) grad_norm: 2.0047 (2.0098) time: 0.5039 [2021-03-25 04:19:27 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 670/1251] eta: 0:04:57 lr: 0.000327 loss: 5.5566 (5.5654) grad_norm: 1.9195 (2.0076) time: 0.5055 [2021-03-25 04:19:32 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 680/1251] eta: 0:04:52 lr: 0.000328 loss: 5.7190 (5.5664) grad_norm: 1.9069 (2.0072) time: 0.5046 [2021-03-25 04:19:37 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 690/1251] eta: 0:04:47 lr: 0.000328 loss: 5.6841 (5.5639) grad_norm: 1.8701 (2.0063) time: 0.5040 [2021-03-25 04:19:42 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 700/1251] eta: 0:04:42 lr: 0.000329 loss: 5.6688 (5.5644) grad_norm: 1.8641 (2.0068) time: 0.5047 [2021-03-25 04:19:47 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 710/1251] eta: 0:04:36 lr: 0.000329 loss: 5.5890 (5.5624) grad_norm: 1.8921 (2.0080) time: 0.5057 [2021-03-25 04:19:52 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 720/1251] eta: 0:04:31 lr: 0.000329 loss: 5.3927 (5.5588) grad_norm: 1.9625 (2.0103) time: 0.5040 [2021-03-25 04:19:57 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 730/1251] eta: 0:04:26 lr: 0.000330 loss: 5.3479 (5.5568) grad_norm: 1.8605 (2.0066) time: 0.5034 [2021-03-25 04:20:03 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 740/1251] eta: 0:04:21 lr: 0.000330 loss: 5.5697 (5.5569) grad_norm: 1.8130 (2.0062) time: 0.5186 [2021-03-25 04:20:08 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 750/1251] eta: 0:04:16 lr: 0.000331 loss: 5.6829 (5.5574) grad_norm: 1.9806 (2.0091) time: 0.5201 [2021-03-25 04:20:13 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 760/1251] eta: 0:04:11 lr: 0.000331 loss: 5.8038 (5.5597) grad_norm: 2.0091 (2.0075) time: 0.5044 [2021-03-25 04:20:18 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 770/1251] eta: 0:04:05 lr: 0.000331 loss: 5.7405 (5.5604) grad_norm: 1.7978 (2.0069) time: 0.4977 [2021-03-25 04:20:23 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 780/1251] eta: 0:04:00 lr: 0.000332 loss: 5.5367 (5.5603) grad_norm: 1.7883 (2.0048) time: 0.4954 [2021-03-25 04:20:28 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 790/1251] eta: 0:03:55 lr: 0.000332 loss: 5.4422 (5.5601) grad_norm: 1.7882 (2.0032) time: 0.5085 [2021-03-25 04:20:33 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 800/1251] eta: 0:03:50 lr: 0.000333 loss: 5.4244 (5.5572) grad_norm: 1.8725 (2.0023) time: 0.5117 [2021-03-25 04:20:38 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 810/1251] eta: 0:03:45 lr: 0.000333 loss: 5.4391 (5.5564) grad_norm: 1.9000 (2.0020) time: 0.5059 [2021-03-25 04:20:43 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 820/1251] eta: 0:03:40 lr: 0.000333 loss: 5.5725 (5.5569) grad_norm: 1.9101 (2.0017) time: 0.5032 [2021-03-25 04:20:48 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 830/1251] eta: 0:03:35 lr: 0.000334 loss: 5.5720 (5.5562) grad_norm: 1.9972 (2.0033) time: 0.5014 [2021-03-25 04:20:53 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 840/1251] eta: 0:03:29 lr: 0.000334 loss: 5.3094 (5.5527) grad_norm: 2.0926 (2.0062) time: 0.5065 [2021-03-25 04:20:58 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 850/1251] eta: 0:03:24 lr: 0.000335 loss: 5.5269 (5.5530) grad_norm: 1.9034 (2.0043) time: 0.5076 [2021-03-25 04:21:03 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 860/1251] eta: 0:03:19 lr: 0.000335 loss: 5.5934 (5.5528) grad_norm: 1.7311 (2.0009) time: 0.5056 [2021-03-25 04:21:09 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 870/1251] eta: 0:03:14 lr: 0.000335 loss: 5.6547 (5.5534) grad_norm: 1.8515 (2.0007) time: 0.5107 [2021-03-25 04:21:14 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 880/1251] eta: 0:03:09 lr: 0.000336 loss: 5.5403 (5.5541) grad_norm: 2.0020 (2.0016) time: 0.5087 [2021-03-25 04:21:19 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 890/1251] eta: 0:03:04 lr: 0.000336 loss: 5.5111 (5.5542) grad_norm: 1.8932 (1.9996) time: 0.5043 [2021-03-25 04:21:24 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 900/1251] eta: 0:02:59 lr: 0.000337 loss: 5.6186 (5.5541) grad_norm: 1.7694 (1.9999) time: 0.5016 [2021-03-25 04:21:29 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 910/1251] eta: 0:02:54 lr: 0.000337 loss: 5.4782 (5.5519) grad_norm: 1.7485 (1.9962) time: 0.5036 [2021-03-25 04:21:34 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 920/1251] eta: 0:02:48 lr: 0.000337 loss: 5.5723 (5.5517) grad_norm: 1.6645 (1.9936) time: 0.5085 [2021-03-25 04:21:39 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 930/1251] eta: 0:02:43 lr: 0.000338 loss: 5.5723 (5.5504) grad_norm: 1.8201 (1.9946) time: 0.5034 [2021-03-25 04:21:44 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 940/1251] eta: 0:02:38 lr: 0.000338 loss: 5.7432 (5.5523) grad_norm: 2.0231 (1.9972) time: 0.5051 [2021-03-25 04:21:49 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 950/1251] eta: 0:02:33 lr: 0.000339 loss: 5.7724 (5.5533) grad_norm: 2.0563 (1.9971) time: 0.5082 [2021-03-25 04:21:54 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 960/1251] eta: 0:02:28 lr: 0.000339 loss: 5.6768 (5.5536) grad_norm: 1.8955 (1.9952) time: 0.5042 [2021-03-25 04:21:59 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 970/1251] eta: 0:02:23 lr: 0.000339 loss: 5.4385 (5.5517) grad_norm: 1.8343 (1.9928) time: 0.5029 [2021-03-25 04:22:04 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 980/1251] eta: 0:02:18 lr: 0.000340 loss: 5.3812 (5.5503) grad_norm: 1.8784 (1.9942) time: 0.5081 [2021-03-25 04:22:09 swin_small_patch4_window7_224] INFO: Epoch: [6] [ 990/1251] eta: 0:02:13 lr: 0.000340 loss: 5.5731 (5.5531) grad_norm: 1.8187 (1.9913) time: 0.5070 [2021-03-25 04:22:14 swin_small_patch4_window7_224] INFO: Epoch: [6] [1000/1251] eta: 0:02:08 lr: 0.000341 loss: 5.8275 (5.5538) grad_norm: 1.7164 (1.9908) time: 0.5045 [2021-03-25 04:22:19 swin_small_patch4_window7_224] INFO: Epoch: [6] [1010/1251] eta: 0:02:02 lr: 0.000341 loss: 5.6855 (5.5528) grad_norm: 2.0491 (1.9915) time: 0.5039 [2021-03-25 04:22:24 swin_small_patch4_window7_224] INFO: Epoch: [6] [1020/1251] eta: 0:01:57 lr: 0.000341 loss: 5.6967 (5.5527) grad_norm: 2.0491 (1.9932) time: 0.5056 [2021-03-25 04:22:29 swin_small_patch4_window7_224] INFO: Epoch: [6] [1030/1251] eta: 0:01:52 lr: 0.000342 loss: 5.6162 (5.5528) grad_norm: 1.9233 (1.9938) time: 0.5062 [2021-03-25 04:22:34 swin_small_patch4_window7_224] INFO: Epoch: [6] [1040/1251] eta: 0:01:47 lr: 0.000342 loss: 5.5238 (5.5541) grad_norm: 1.8850 (1.9927) time: 0.5051 [2021-03-25 04:22:39 swin_small_patch4_window7_224] INFO: Epoch: [6] [1050/1251] eta: 0:01:42 lr: 0.000343 loss: 5.7017 (5.5551) grad_norm: 1.8376 (1.9925) time: 0.5056 [2021-03-25 04:22:45 swin_small_patch4_window7_224] INFO: Epoch: [6] [1060/1251] eta: 0:01:37 lr: 0.000343 loss: 5.5678 (5.5543) grad_norm: 1.8991 (1.9942) time: 0.5031 [2021-03-25 04:22:50 swin_small_patch4_window7_224] INFO: Epoch: [6] [1070/1251] eta: 0:01:32 lr: 0.000343 loss: 5.4429 (5.5523) grad_norm: 2.0665 (1.9959) time: 0.5100 [2021-03-25 04:22:55 swin_small_patch4_window7_224] INFO: Epoch: [6] [1080/1251] eta: 0:01:27 lr: 0.000344 loss: 5.5994 (5.5516) grad_norm: 2.0456 (1.9966) time: 0.5110 [2021-03-25 04:23:00 swin_small_patch4_window7_224] INFO: Epoch: [6] [1090/1251] eta: 0:01:22 lr: 0.000344 loss: 5.7810 (5.5532) grad_norm: 2.0087 (1.9961) time: 0.5022 [2021-03-25 04:23:05 swin_small_patch4_window7_224] INFO: Epoch: [6] [1100/1251] eta: 0:01:16 lr: 0.000345 loss: 5.7553 (5.5536) grad_norm: 1.9886 (1.9958) time: 0.4989 [2021-03-25 04:23:10 swin_small_patch4_window7_224] INFO: Epoch: [6] [1110/1251] eta: 0:01:11 lr: 0.000345 loss: 5.6728 (5.5542) grad_norm: 1.8085 (1.9945) time: 0.5052 [2021-03-25 04:23:15 swin_small_patch4_window7_224] INFO: Epoch: [6] [1120/1251] eta: 0:01:06 lr: 0.000345 loss: 5.6728 (5.5551) grad_norm: 1.8085 (1.9927) time: 0.5110 [2021-03-25 04:23:20 swin_small_patch4_window7_224] INFO: Epoch: [6] [1130/1251] eta: 0:01:01 lr: 0.000346 loss: 5.4137 (5.5533) grad_norm: 1.9029 (1.9936) time: 0.5093 [2021-03-25 04:23:25 swin_small_patch4_window7_224] INFO: Epoch: [6] [1140/1251] eta: 0:00:56 lr: 0.000346 loss: 5.7354 (5.5549) grad_norm: 2.0777 (1.9946) time: 0.5076 [2021-03-25 04:23:30 swin_small_patch4_window7_224] INFO: Epoch: [6] [1150/1251] eta: 0:00:51 lr: 0.000347 loss: 5.5954 (5.5532) grad_norm: 1.8590 (1.9953) time: 0.5048 [2021-03-25 04:23:35 swin_small_patch4_window7_224] INFO: Epoch: [6] [1160/1251] eta: 0:00:46 lr: 0.000347 loss: 5.4247 (5.5521) grad_norm: 2.0468 (1.9982) time: 0.5076 [2021-03-25 04:23:40 swin_small_patch4_window7_224] INFO: Epoch: [6] [1170/1251] eta: 0:00:41 lr: 0.000347 loss: 5.5145 (5.5516) grad_norm: 2.0247 (1.9980) time: 0.5105 [2021-03-25 04:23:45 swin_small_patch4_window7_224] INFO: Epoch: [6] [1180/1251] eta: 0:00:36 lr: 0.000348 loss: 5.3509 (5.5493) grad_norm: 1.7790 (1.9959) time: 0.5056 [2021-03-25 04:23:50 swin_small_patch4_window7_224] INFO: Epoch: [6] [1190/1251] eta: 0:00:31 lr: 0.000348 loss: 5.3509 (5.5479) grad_norm: 1.6646 (1.9934) time: 0.5012 [2021-03-25 04:23:55 swin_small_patch4_window7_224] INFO: Epoch: [6] [1200/1251] eta: 0:00:25 lr: 0.000349 loss: 5.5649 (5.5483) grad_norm: 1.7345 (1.9912) time: 0.5050 [2021-03-25 04:24:01 swin_small_patch4_window7_224] INFO: Epoch: [6] [1210/1251] eta: 0:00:20 lr: 0.000349 loss: 5.5529 (5.5476) grad_norm: 1.7473 (1.9901) time: 0.5071 [2021-03-25 04:24:06 swin_small_patch4_window7_224] INFO: Epoch: [6] [1220/1251] eta: 0:00:15 lr: 0.000349 loss: 5.4410 (5.5477) grad_norm: 1.8133 (1.9890) time: 0.5072 [2021-03-25 04:24:11 swin_small_patch4_window7_224] INFO: Epoch: [6] [1230/1251] eta: 0:00:10 lr: 0.000350 loss: 5.7237 (5.5483) grad_norm: 1.8507 (1.9892) time: 0.5115 [2021-03-25 04:24:16 swin_small_patch4_window7_224] INFO: Epoch: [6] [1240/1251] eta: 0:00:05 lr: 0.000350 loss: 5.5542 (5.5484) grad_norm: 1.7813 (1.9878) time: 0.5077 [2021-03-25 04:24:21 swin_small_patch4_window7_224] INFO: Epoch: [6] [1250/1251] eta: 0:00:00 lr: 0.000351 loss: 5.5712 (5.5493) grad_norm: 1.7095 (1.9862) time: 0.5015 [2021-03-25 04:24:25 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 3.6539 (3.6539) acc1: 32.8125 (32.8125) acc5: 50.0000 (50.0000) [2021-03-25 04:24:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 3.5545 (3.4097) acc1: 31.2500 (31.3920) acc5: 54.6875 (54.9716) [2021-03-25 04:24:30 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 3.2914 (3.3166) acc1: 29.6875 (31.6964) acc5: 57.8125 (57.9613) [2021-03-25 04:24:32 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 3.1631 (3.2816) acc1: 32.8125 (32.7117) acc5: 60.9375 (57.8629) [2021-03-25 04:24:34 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 3.1896 (3.2752) acc1: 34.3750 (33.2698) acc5: 56.2500 (57.5838) [2021-03-25 04:24:35 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.2005 (3.2677) acc1: 34.3750 (33.5680) acc5: 57.8125 (57.6320) [2021-03-25 04:24:36 swin_small_patch4_window7_224] INFO: * Acc@1 32.958 Acc@5 58.298 loss 3.264 [2021-03-25 04:24:36 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 33.0% [2021-03-25 04:24:36 swin_small_patch4_window7_224] INFO: Max accuracy: 32.96% [2021-03-25 04:24:40 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 0/1251] eta: 1:30:06 lr: 0.000351 loss: 5.7741 (5.7741) grad_norm: 1.6993 (1.6993) time: 4.3216 [2021-03-25 04:24:45 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 10/1251] eta: 0:17:39 lr: 0.000351 loss: 5.6773 (5.5691) grad_norm: 1.8967 (1.9511) time: 0.8539 [2021-03-25 04:24:50 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 20/1251] eta: 0:14:03 lr: 0.000351 loss: 5.6136 (5.5070) grad_norm: 1.8967 (2.0027) time: 0.5035 [2021-03-25 04:24:55 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 30/1251] eta: 0:12:45 lr: 0.000352 loss: 5.5417 (5.5097) grad_norm: 1.8686 (1.9948) time: 0.5018 [2021-03-25 04:25:00 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 40/1251] eta: 0:12:04 lr: 0.000352 loss: 5.5365 (5.5073) grad_norm: 1.8347 (1.9994) time: 0.5069 [2021-03-25 04:25:05 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 50/1251] eta: 0:11:36 lr: 0.000353 loss: 5.4920 (5.4616) grad_norm: 1.9232 (1.9800) time: 0.5068 [2021-03-25 04:25:10 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 60/1251] eta: 0:11:17 lr: 0.000353 loss: 5.2831 (5.4525) grad_norm: 2.0209 (inf) time: 0.5084 [2021-03-25 04:25:15 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 70/1251] eta: 0:11:01 lr: 0.000353 loss: 5.4960 (5.4541) grad_norm: 1.9220 (inf) time: 0.5113 [2021-03-25 04:25:20 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 80/1251] eta: 0:10:48 lr: 0.000354 loss: 5.4573 (5.4476) grad_norm: 1.8246 (inf) time: 0.5078 [2021-03-25 04:25:26 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 90/1251] eta: 0:10:38 lr: 0.000354 loss: 5.4607 (5.4512) grad_norm: 1.8307 (inf) time: 0.5143 [2021-03-25 04:25:31 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 100/1251] eta: 0:10:27 lr: 0.000355 loss: 5.5446 (5.4491) grad_norm: 1.8137 (inf) time: 0.5125 [2021-03-25 04:25:36 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 110/1251] eta: 0:10:18 lr: 0.000355 loss: 5.4704 (5.4449) grad_norm: 1.7559 (inf) time: 0.5040 [2021-03-25 04:25:41 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 120/1251] eta: 0:10:10 lr: 0.000355 loss: 5.5967 (5.4487) grad_norm: 1.7880 (inf) time: 0.5088 [2021-03-25 04:25:46 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 130/1251] eta: 0:10:01 lr: 0.000356 loss: 5.6386 (5.4515) grad_norm: 1.9282 (inf) time: 0.5060 [2021-03-25 04:25:51 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 140/1251] eta: 0:09:53 lr: 0.000356 loss: 5.5819 (5.4453) grad_norm: 2.0837 (inf) time: 0.5036 [2021-03-25 04:25:56 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 150/1251] eta: 0:09:45 lr: 0.000357 loss: 5.4196 (5.4353) grad_norm: 1.9911 (inf) time: 0.5039 [2021-03-25 04:26:01 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 160/1251] eta: 0:09:38 lr: 0.000357 loss: 5.4685 (5.4453) grad_norm: 1.9176 (inf) time: 0.5004 [2021-03-25 04:26:06 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 170/1251] eta: 0:09:31 lr: 0.000357 loss: 5.6382 (5.4507) grad_norm: 1.7719 (inf) time: 0.5047 [2021-03-25 04:26:11 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 180/1251] eta: 0:09:24 lr: 0.000358 loss: 5.7175 (5.4656) grad_norm: 1.7094 (inf) time: 0.5050 [2021-03-25 04:26:16 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 190/1251] eta: 0:09:18 lr: 0.000358 loss: 5.5960 (5.4600) grad_norm: 1.7112 (inf) time: 0.5013 [2021-03-25 04:26:21 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 200/1251] eta: 0:09:11 lr: 0.000359 loss: 5.2730 (5.4567) grad_norm: 1.7112 (inf) time: 0.5053 [2021-03-25 04:26:26 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 210/1251] eta: 0:09:05 lr: 0.000359 loss: 5.7993 (5.4782) grad_norm: 1.7128 (inf) time: 0.5072 [2021-03-25 04:26:31 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 220/1251] eta: 0:08:59 lr: 0.000359 loss: 5.7701 (5.4690) grad_norm: 1.7128 (inf) time: 0.5066 [2021-03-25 04:26:36 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 230/1251] eta: 0:08:53 lr: 0.000360 loss: 5.4747 (5.4750) grad_norm: 1.7181 (inf) time: 0.5089 [2021-03-25 04:26:42 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 240/1251] eta: 0:08:48 lr: 0.000360 loss: 5.4312 (5.4688) grad_norm: 1.7396 (inf) time: 0.5106 [2021-03-25 04:26:47 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 250/1251] eta: 0:08:42 lr: 0.000361 loss: 5.1764 (5.4533) grad_norm: 1.7627 (inf) time: 0.5149 [2021-03-25 04:26:52 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 260/1251] eta: 0:08:36 lr: 0.000361 loss: 5.2399 (5.4530) grad_norm: 1.7627 (inf) time: 0.5096 [2021-03-25 04:26:57 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 270/1251] eta: 0:08:30 lr: 0.000361 loss: 5.6417 (5.4591) grad_norm: 1.8726 (inf) time: 0.5031 [2021-03-25 04:27:02 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 280/1251] eta: 0:08:25 lr: 0.000362 loss: 5.4672 (5.4540) grad_norm: 2.2491 (inf) time: 0.5038 [2021-03-25 04:27:07 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 290/1251] eta: 0:08:19 lr: 0.000362 loss: 5.2249 (5.4453) grad_norm: 1.8743 (inf) time: 0.4996 [2021-03-25 04:27:12 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 300/1251] eta: 0:08:13 lr: 0.000363 loss: 5.0649 (5.4439) grad_norm: 1.7561 (inf) time: 0.4983 [2021-03-25 04:27:17 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 310/1251] eta: 0:08:07 lr: 0.000363 loss: 5.4905 (5.4416) grad_norm: 1.7768 (inf) time: 0.5028 [2021-03-25 04:27:22 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 320/1251] eta: 0:08:02 lr: 0.000363 loss: 5.5261 (5.4460) grad_norm: 1.7768 (inf) time: 0.5075 [2021-03-25 04:27:27 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 330/1251] eta: 0:07:56 lr: 0.000364 loss: 5.5722 (5.4435) grad_norm: 1.8271 (inf) time: 0.5021 [2021-03-25 04:27:32 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 340/1251] eta: 0:07:51 lr: 0.000364 loss: 5.4567 (5.4427) grad_norm: 1.8329 (inf) time: 0.5013 [2021-03-25 04:27:37 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 350/1251] eta: 0:07:45 lr: 0.000365 loss: 5.6003 (5.4492) grad_norm: 2.0233 (inf) time: 0.5032 [2021-03-25 04:27:42 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 360/1251] eta: 0:07:39 lr: 0.000365 loss: 5.4884 (5.4462) grad_norm: 1.7612 (inf) time: 0.5006 [2021-03-25 04:27:47 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 370/1251] eta: 0:07:34 lr: 0.000365 loss: 5.2962 (5.4421) grad_norm: 1.7449 (inf) time: 0.5002 [2021-03-25 04:27:52 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 380/1251] eta: 0:07:29 lr: 0.000366 loss: 5.2608 (5.4405) grad_norm: 1.8257 (inf) time: 0.5038 [2021-03-25 04:27:57 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 390/1251] eta: 0:07:23 lr: 0.000366 loss: 5.4831 (5.4426) grad_norm: 2.0209 (inf) time: 0.5035 [2021-03-25 04:28:02 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 400/1251] eta: 0:07:18 lr: 0.000367 loss: 5.3241 (5.4369) grad_norm: 2.0134 (inf) time: 0.5028 [2021-03-25 04:28:07 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 410/1251] eta: 0:07:12 lr: 0.000367 loss: 5.2832 (5.4392) grad_norm: 1.9516 (inf) time: 0.5056 [2021-03-25 04:28:12 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 420/1251] eta: 0:07:07 lr: 0.000367 loss: 5.4082 (5.4332) grad_norm: 1.8767 (inf) time: 0.5040 [2021-03-25 04:28:17 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 430/1251] eta: 0:07:02 lr: 0.000368 loss: 5.2268 (5.4307) grad_norm: 1.7450 (inf) time: 0.5059 [2021-03-25 04:28:22 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 440/1251] eta: 0:06:57 lr: 0.000368 loss: 5.3500 (5.4315) grad_norm: 1.7707 (inf) time: 0.5122 [2021-03-25 04:28:27 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 450/1251] eta: 0:06:51 lr: 0.000369 loss: 5.4708 (5.4294) grad_norm: 1.8970 (inf) time: 0.5104 [2021-03-25 04:28:33 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 460/1251] eta: 0:06:46 lr: 0.000369 loss: 5.5612 (5.4340) grad_norm: 1.9257 (inf) time: 0.5028 [2021-03-25 04:28:38 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 470/1251] eta: 0:06:41 lr: 0.000369 loss: 5.6428 (5.4356) grad_norm: 1.9538 (inf) time: 0.5044 [2021-03-25 04:28:43 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 480/1251] eta: 0:06:35 lr: 0.000370 loss: 5.4121 (5.4306) grad_norm: 1.9841 (inf) time: 0.5060 [2021-03-25 04:28:48 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 490/1251] eta: 0:06:30 lr: 0.000370 loss: 5.1606 (5.4269) grad_norm: 2.0893 (inf) time: 0.5026 [2021-03-25 04:28:53 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 500/1251] eta: 0:06:25 lr: 0.000371 loss: 5.2612 (5.4276) grad_norm: 1.9819 (inf) time: 0.5044 [2021-03-25 04:28:58 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 510/1251] eta: 0:06:20 lr: 0.000371 loss: 5.6025 (5.4298) grad_norm: 1.9364 (inf) time: 0.5077 [2021-03-25 04:29:03 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 520/1251] eta: 0:06:14 lr: 0.000371 loss: 5.6025 (5.4302) grad_norm: 1.8053 (inf) time: 0.5026 [2021-03-25 04:29:08 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 530/1251] eta: 0:06:09 lr: 0.000372 loss: 5.5095 (5.4303) grad_norm: 1.7137 (inf) time: 0.5038 [2021-03-25 04:29:13 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 540/1251] eta: 0:06:04 lr: 0.000372 loss: 5.3784 (5.4255) grad_norm: 1.7627 (inf) time: 0.5124 [2021-03-25 04:29:18 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 550/1251] eta: 0:05:59 lr: 0.000373 loss: 5.4254 (5.4273) grad_norm: 1.7808 (inf) time: 0.5229 [2021-03-25 04:29:23 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 560/1251] eta: 0:05:54 lr: 0.000373 loss: 5.4418 (5.4239) grad_norm: 1.7440 (inf) time: 0.5159 [2021-03-25 04:29:28 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 570/1251] eta: 0:05:48 lr: 0.000373 loss: 5.1757 (5.4223) grad_norm: 1.7250 (inf) time: 0.4983 [2021-03-25 04:29:33 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 580/1251] eta: 0:05:43 lr: 0.000374 loss: 5.2643 (5.4207) grad_norm: 1.7411 (inf) time: 0.4968 [2021-03-25 04:29:38 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 590/1251] eta: 0:05:38 lr: 0.000374 loss: 5.3781 (5.4193) grad_norm: 1.9871 (inf) time: 0.5013 [2021-03-25 04:29:43 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 600/1251] eta: 0:05:33 lr: 0.000375 loss: 5.4657 (5.4201) grad_norm: 1.9359 (inf) time: 0.5081 [2021-03-25 04:29:49 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 610/1251] eta: 0:05:28 lr: 0.000375 loss: 5.6574 (5.4256) grad_norm: 1.8460 (inf) time: 0.5083 [2021-03-25 04:29:54 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 620/1251] eta: 0:05:23 lr: 0.000375 loss: 5.5784 (5.4226) grad_norm: 1.7500 (inf) time: 0.5061 [2021-03-25 04:29:59 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 630/1251] eta: 0:05:17 lr: 0.000376 loss: 5.3773 (5.4234) grad_norm: 1.7001 (inf) time: 0.5056 [2021-03-25 04:30:04 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 640/1251] eta: 0:05:12 lr: 0.000376 loss: 5.6184 (5.4254) grad_norm: 1.7280 (inf) time: 0.5073 [2021-03-25 04:30:09 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 650/1251] eta: 0:05:07 lr: 0.000377 loss: 5.5631 (5.4252) grad_norm: 1.9130 (inf) time: 0.5100 [2021-03-25 04:30:14 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 660/1251] eta: 0:05:02 lr: 0.000377 loss: 5.6296 (5.4276) grad_norm: 1.8899 (inf) time: 0.5062 [2021-03-25 04:30:19 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 670/1251] eta: 0:04:57 lr: 0.000377 loss: 5.7165 (5.4314) grad_norm: 1.9062 (inf) time: 0.5057 [2021-03-25 04:30:24 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 680/1251] eta: 0:04:51 lr: 0.000378 loss: 5.4941 (5.4316) grad_norm: 1.9935 (inf) time: 0.5023 [2021-03-25 04:30:29 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 690/1251] eta: 0:04:46 lr: 0.000378 loss: 5.4692 (5.4322) grad_norm: 1.9206 (inf) time: 0.5014 [2021-03-25 04:30:34 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 700/1251] eta: 0:04:41 lr: 0.000379 loss: 5.3582 (5.4292) grad_norm: 1.7471 (inf) time: 0.5068 [2021-03-25 04:30:39 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 710/1251] eta: 0:04:36 lr: 0.000379 loss: 5.4416 (5.4307) grad_norm: 1.7660 (inf) time: 0.5062 [2021-03-25 04:30:44 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 720/1251] eta: 0:04:31 lr: 0.000379 loss: 5.5577 (5.4324) grad_norm: 1.7686 (inf) time: 0.5062 [2021-03-25 04:30:49 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 730/1251] eta: 0:04:26 lr: 0.000380 loss: 5.5595 (5.4355) grad_norm: 1.6729 (inf) time: 0.5119 [2021-03-25 04:30:55 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 740/1251] eta: 0:04:21 lr: 0.000380 loss: 5.5595 (5.4349) grad_norm: 1.6820 (inf) time: 0.5197 [2021-03-25 04:31:00 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 750/1251] eta: 0:04:16 lr: 0.000381 loss: 5.0268 (5.4267) grad_norm: 1.7836 (inf) time: 0.5221 [2021-03-25 04:31:05 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 760/1251] eta: 0:04:11 lr: 0.000381 loss: 5.0034 (5.4239) grad_norm: 1.8141 (inf) time: 0.5118 [2021-03-25 04:31:10 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 770/1251] eta: 0:04:05 lr: 0.000381 loss: 5.3832 (5.4256) grad_norm: 1.7505 (inf) time: 0.5031 [2021-03-25 04:31:15 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 780/1251] eta: 0:04:00 lr: 0.000382 loss: 5.5774 (5.4274) grad_norm: 1.7505 (inf) time: 0.5029 [2021-03-25 04:31:20 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 790/1251] eta: 0:03:55 lr: 0.000382 loss: 5.4347 (5.4266) grad_norm: 1.9670 (inf) time: 0.5056 [2021-03-25 04:31:25 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 800/1251] eta: 0:03:50 lr: 0.000383 loss: 5.3892 (5.4269) grad_norm: 2.0302 (inf) time: 0.5081 [2021-03-25 04:31:30 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 810/1251] eta: 0:03:45 lr: 0.000383 loss: 5.3892 (5.4255) grad_norm: 1.8179 (inf) time: 0.5100 [2021-03-25 04:31:35 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 820/1251] eta: 0:03:40 lr: 0.000383 loss: 5.3347 (5.4256) grad_norm: 1.7305 (inf) time: 0.5092 [2021-03-25 04:31:40 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 830/1251] eta: 0:03:35 lr: 0.000384 loss: 5.5443 (5.4252) grad_norm: 1.7540 (inf) time: 0.5021 [2021-03-25 04:31:45 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 840/1251] eta: 0:03:29 lr: 0.000384 loss: 5.3654 (5.4214) grad_norm: 1.6614 (inf) time: 0.5025 [2021-03-25 04:31:50 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 850/1251] eta: 0:03:24 lr: 0.000385 loss: 5.3654 (5.4213) grad_norm: 1.6742 (inf) time: 0.5064 [2021-03-25 04:31:55 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 860/1251] eta: 0:03:19 lr: 0.000385 loss: 5.3809 (5.4201) grad_norm: 1.8971 (inf) time: 0.5036 [2021-03-25 04:32:00 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 870/1251] eta: 0:03:14 lr: 0.000385 loss: 5.6086 (5.4214) grad_norm: 1.8200 (inf) time: 0.5059 [2021-03-25 04:32:05 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 880/1251] eta: 0:03:09 lr: 0.000386 loss: 5.4555 (5.4200) grad_norm: 1.8200 (inf) time: 0.5055 [2021-03-25 04:32:11 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 890/1251] eta: 0:03:04 lr: 0.000386 loss: 5.0538 (5.4164) grad_norm: 1.8540 (inf) time: 0.5016 [2021-03-25 04:32:16 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 900/1251] eta: 0:02:59 lr: 0.000387 loss: 5.2720 (5.4169) grad_norm: 1.7891 (inf) time: 0.5023 [2021-03-25 04:32:21 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 910/1251] eta: 0:02:53 lr: 0.000387 loss: 5.5209 (5.4187) grad_norm: 1.7640 (inf) time: 0.5019 [2021-03-25 04:32:26 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 920/1251] eta: 0:02:48 lr: 0.000387 loss: 5.5489 (5.4201) grad_norm: 1.8207 (inf) time: 0.5027 [2021-03-25 04:32:31 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 930/1251] eta: 0:02:43 lr: 0.000388 loss: 5.5489 (5.4224) grad_norm: 1.8384 (inf) time: 0.5024 [2021-03-25 04:32:36 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 940/1251] eta: 0:02:38 lr: 0.000388 loss: 5.5575 (5.4232) grad_norm: 1.8789 (inf) time: 0.5048 [2021-03-25 04:32:41 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 950/1251] eta: 0:02:33 lr: 0.000389 loss: 5.5575 (5.4247) grad_norm: 1.8076 (inf) time: 0.5077 [2021-03-25 04:32:46 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 960/1251] eta: 0:02:28 lr: 0.000389 loss: 5.6159 (5.4256) grad_norm: 1.8053 (inf) time: 0.5095 [2021-03-25 04:32:51 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 970/1251] eta: 0:02:23 lr: 0.000389 loss: 5.4211 (5.4221) grad_norm: 1.7733 (inf) time: 0.5070 [2021-03-25 04:32:56 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 980/1251] eta: 0:02:18 lr: 0.000390 loss: 5.3883 (5.4208) grad_norm: 1.7466 (inf) time: 0.5092 [2021-03-25 04:33:01 swin_small_patch4_window7_224] INFO: Epoch: [7] [ 990/1251] eta: 0:02:13 lr: 0.000390 loss: 5.5203 (5.4209) grad_norm: 1.8524 (inf) time: 0.5129 [2021-03-25 04:33:06 swin_small_patch4_window7_224] INFO: Epoch: [7] [1000/1251] eta: 0:02:07 lr: 0.000391 loss: 5.2227 (5.4191) grad_norm: 1.8864 (inf) time: 0.5077 [2021-03-25 04:33:11 swin_small_patch4_window7_224] INFO: Epoch: [7] [1010/1251] eta: 0:02:02 lr: 0.000391 loss: 5.2344 (5.4176) grad_norm: 1.8009 (inf) time: 0.5035 [2021-03-25 04:33:16 swin_small_patch4_window7_224] INFO: Epoch: [7] [1020/1251] eta: 0:01:57 lr: 0.000391 loss: 5.2521 (5.4163) grad_norm: 1.8081 (inf) time: 0.5079 [2021-03-25 04:33:21 swin_small_patch4_window7_224] INFO: Epoch: [7] [1030/1251] eta: 0:01:52 lr: 0.000392 loss: 5.2521 (5.4165) grad_norm: 1.7861 (inf) time: 0.5103 [2021-03-25 04:33:27 swin_small_patch4_window7_224] INFO: Epoch: [7] [1040/1251] eta: 0:01:47 lr: 0.000392 loss: 5.3526 (5.4164) grad_norm: 1.7861 (inf) time: 0.5082 [2021-03-25 04:33:32 swin_small_patch4_window7_224] INFO: Epoch: [7] [1050/1251] eta: 0:01:42 lr: 0.000393 loss: 5.3526 (5.4157) grad_norm: 1.7677 (inf) time: 0.5024 [2021-03-25 04:33:37 swin_small_patch4_window7_224] INFO: Epoch: [7] [1060/1251] eta: 0:01:37 lr: 0.000393 loss: 5.3362 (5.4145) grad_norm: 1.7925 (inf) time: 0.4989 [2021-03-25 04:33:42 swin_small_patch4_window7_224] INFO: Epoch: [7] [1070/1251] eta: 0:01:32 lr: 0.000393 loss: 5.3647 (5.4150) grad_norm: 1.8395 (inf) time: 0.5109 [2021-03-25 04:33:47 swin_small_patch4_window7_224] INFO: Epoch: [7] [1080/1251] eta: 0:01:27 lr: 0.000394 loss: 5.5475 (5.4140) grad_norm: 1.9179 (inf) time: 0.5057 [2021-03-25 04:33:52 swin_small_patch4_window7_224] INFO: Epoch: [7] [1090/1251] eta: 0:01:22 lr: 0.000394 loss: 5.3526 (5.4130) grad_norm: 1.8797 (inf) time: 0.4932 [2021-03-25 04:33:57 swin_small_patch4_window7_224] INFO: Epoch: [7] [1100/1251] eta: 0:01:16 lr: 0.000395 loss: 5.2625 (5.4104) grad_norm: 1.8049 (inf) time: 0.4998 [2021-03-25 04:34:02 swin_small_patch4_window7_224] INFO: Epoch: [7] [1110/1251] eta: 0:01:11 lr: 0.000395 loss: 5.2625 (5.4099) grad_norm: 1.7594 (inf) time: 0.5041 [2021-03-25 04:34:07 swin_small_patch4_window7_224] INFO: Epoch: [7] [1120/1251] eta: 0:01:06 lr: 0.000395 loss: 5.3817 (5.4086) grad_norm: 1.7831 (inf) time: 0.5014 [2021-03-25 04:34:12 swin_small_patch4_window7_224] INFO: Epoch: [7] [1130/1251] eta: 0:01:01 lr: 0.000396 loss: 5.4284 (5.4084) grad_norm: 1.7055 (inf) time: 0.5051 [2021-03-25 04:34:17 swin_small_patch4_window7_224] INFO: Epoch: [7] [1140/1251] eta: 0:00:56 lr: 0.000396 loss: 5.3876 (5.4075) grad_norm: 1.6885 (inf) time: 0.5080 [2021-03-25 04:34:22 swin_small_patch4_window7_224] INFO: Epoch: [7] [1150/1251] eta: 0:00:51 lr: 0.000397 loss: 5.3203 (5.4065) grad_norm: 1.8239 (inf) time: 0.5050 [2021-03-25 04:34:27 swin_small_patch4_window7_224] INFO: Epoch: [7] [1160/1251] eta: 0:00:46 lr: 0.000397 loss: 5.4791 (5.4080) grad_norm: 1.8759 (inf) time: 0.5021 [2021-03-25 04:34:32 swin_small_patch4_window7_224] INFO: Epoch: [7] [1170/1251] eta: 0:00:41 lr: 0.000397 loss: 5.4791 (5.4073) grad_norm: 1.7716 (inf) time: 0.4996 [2021-03-25 04:34:37 swin_small_patch4_window7_224] INFO: Epoch: [7] [1180/1251] eta: 0:00:36 lr: 0.000398 loss: 5.3639 (5.4058) grad_norm: 1.7399 (inf) time: 0.5043 [2021-03-25 04:34:42 swin_small_patch4_window7_224] INFO: Epoch: [7] [1190/1251] eta: 0:00:31 lr: 0.000398 loss: 5.3639 (5.4060) grad_norm: 1.7481 (inf) time: 0.5072 [2021-03-25 04:34:47 swin_small_patch4_window7_224] INFO: Epoch: [7] [1200/1251] eta: 0:00:25 lr: 0.000399 loss: 5.2925 (5.4041) grad_norm: 1.8185 (inf) time: 0.5020 [2021-03-25 04:34:52 swin_small_patch4_window7_224] INFO: Epoch: [7] [1210/1251] eta: 0:00:20 lr: 0.000399 loss: 5.1663 (5.4036) grad_norm: 1.8919 (inf) time: 0.5046 [2021-03-25 04:34:57 swin_small_patch4_window7_224] INFO: Epoch: [7] [1220/1251] eta: 0:00:15 lr: 0.000399 loss: 5.1741 (5.4019) grad_norm: 1.8833 (inf) time: 0.5071 [2021-03-25 04:35:02 swin_small_patch4_window7_224] INFO: Epoch: [7] [1230/1251] eta: 0:00:10 lr: 0.000400 loss: 5.3041 (5.4015) grad_norm: 1.7248 (inf) time: 0.5042 [2021-03-25 04:35:07 swin_small_patch4_window7_224] INFO: Epoch: [7] [1240/1251] eta: 0:00:05 lr: 0.000400 loss: 5.3041 (5.4009) grad_norm: 1.6766 (inf) time: 0.5066 [2021-03-25 04:35:12 swin_small_patch4_window7_224] INFO: Epoch: [7] [1250/1251] eta: 0:00:00 lr: 0.000401 loss: 5.4263 (5.4007) grad_norm: 1.6787 (inf) time: 0.5000 [2021-03-25 04:35:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:32 loss: 2.9889 (2.9889) acc1: 42.1875 (42.1875) acc5: 62.5000 (62.5000) [2021-03-25 04:35:19 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 2.9889 (2.9957) acc1: 35.9375 (38.0682) acc5: 62.5000 (61.6477) [2021-03-25 04:35:22 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 2.9691 (3.0109) acc1: 35.9375 (37.3512) acc5: 60.9375 (61.9048) [2021-03-25 04:35:24 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 2.9039 (2.9892) acc1: 37.5000 (37.8024) acc5: 60.9375 (62.2480) [2021-03-25 04:35:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 3.0471 (3.0014) acc1: 37.5000 (37.9954) acc5: 60.9375 (62.3476) [2021-03-25 04:35:26 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 3.0395 (2.9940) acc1: 37.5000 (37.8560) acc5: 64.0625 (62.4960) [2021-03-25 04:35:28 swin_small_patch4_window7_224] INFO: * Acc@1 37.420 Acc@5 63.378 loss 2.982 [2021-03-25 04:35:28 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 37.4% [2021-03-25 04:35:28 swin_small_patch4_window7_224] INFO: Max accuracy: 37.42% [2021-03-25 04:35:32 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 0/1251] eta: 1:23:04 lr: 0.000401 loss: 5.7312 (5.7312) grad_norm: 2.1524 (2.1524) time: 3.9848 [2021-03-25 04:35:38 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 10/1251] eta: 0:17:40 lr: 0.000401 loss: 5.7312 (5.5388) grad_norm: 1.6824 (1.8097) time: 0.8546 [2021-03-25 04:35:43 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 20/1251] eta: 0:14:12 lr: 0.000401 loss: 5.6640 (5.5643) grad_norm: 1.6130 (1.7149) time: 0.5278 [2021-03-25 04:35:48 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 30/1251] eta: 0:12:47 lr: 0.000402 loss: 5.8280 (5.5831) grad_norm: 1.6105 (1.7618) time: 0.5044 [2021-03-25 04:35:53 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 40/1251] eta: 0:12:04 lr: 0.000402 loss: 5.5630 (5.4669) grad_norm: 1.7131 (1.7860) time: 0.4987 [2021-03-25 04:35:58 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 50/1251] eta: 0:11:35 lr: 0.000403 loss: 5.4467 (5.4931) grad_norm: 1.8737 (1.8131) time: 0.5021 [2021-03-25 04:36:03 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 60/1251] eta: 0:11:15 lr: 0.000403 loss: 5.5161 (5.4832) grad_norm: 1.7416 (1.7906) time: 0.5052 [2021-03-25 04:36:08 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 70/1251] eta: 0:10:59 lr: 0.000403 loss: 5.3318 (5.4793) grad_norm: 1.6776 (1.7840) time: 0.5046 [2021-03-25 04:36:13 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 80/1251] eta: 0:10:46 lr: 0.000404 loss: 5.3295 (5.4550) grad_norm: 1.7426 (1.7912) time: 0.5036 [2021-03-25 04:36:18 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 90/1251] eta: 0:10:34 lr: 0.000404 loss: 5.4408 (5.4590) grad_norm: 1.8785 (1.7987) time: 0.5051 [2021-03-25 04:36:23 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 100/1251] eta: 0:10:24 lr: 0.000405 loss: 5.4576 (5.4416) grad_norm: 1.6749 (1.7830) time: 0.5035 [2021-03-25 04:36:28 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 110/1251] eta: 0:10:14 lr: 0.000405 loss: 5.4749 (5.4477) grad_norm: 1.6749 (1.7980) time: 0.5035 [2021-03-25 04:36:33 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 120/1251] eta: 0:10:06 lr: 0.000405 loss: 5.4749 (5.4406) grad_norm: 1.8840 (1.8082) time: 0.5047 [2021-03-25 04:36:38 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 130/1251] eta: 0:09:58 lr: 0.000406 loss: 5.4676 (5.4403) grad_norm: 1.8812 (1.8218) time: 0.5087 [2021-03-25 04:36:43 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 140/1251] eta: 0:09:51 lr: 0.000406 loss: 5.3682 (5.4135) grad_norm: 1.7951 (1.8132) time: 0.5112 [2021-03-25 04:36:48 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 150/1251] eta: 0:09:44 lr: 0.000407 loss: 4.8894 (5.4032) grad_norm: 1.7236 (1.8281) time: 0.5082 [2021-03-25 04:36:53 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 160/1251] eta: 0:09:37 lr: 0.000407 loss: 5.3190 (5.4102) grad_norm: 1.8787 (1.8380) time: 0.5040 [2021-03-25 04:36:58 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 170/1251] eta: 0:09:31 lr: 0.000407 loss: 5.4621 (5.4114) grad_norm: 1.9043 (1.8452) time: 0.5099 [2021-03-25 04:37:04 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 180/1251] eta: 0:09:25 lr: 0.000408 loss: 5.4621 (5.3985) grad_norm: 1.9043 (1.8556) time: 0.5176 [2021-03-25 04:37:09 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 190/1251] eta: 0:09:18 lr: 0.000408 loss: 5.4897 (5.4032) grad_norm: 1.8831 (1.8632) time: 0.5119 [2021-03-25 04:37:14 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 200/1251] eta: 0:09:12 lr: 0.000409 loss: 5.4445 (5.4011) grad_norm: 1.7973 (1.8633) time: 0.5105 [2021-03-25 04:37:19 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 210/1251] eta: 0:09:06 lr: 0.000409 loss: 5.3616 (5.3919) grad_norm: 1.7973 (1.8641) time: 0.5128 [2021-03-25 04:37:24 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 220/1251] eta: 0:09:00 lr: 0.000409 loss: 5.1975 (5.3772) grad_norm: 2.0032 (1.8848) time: 0.5095 [2021-03-25 04:37:29 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 230/1251] eta: 0:08:54 lr: 0.000410 loss: 5.1582 (5.3732) grad_norm: 2.0308 (1.8882) time: 0.5038 [2021-03-25 04:37:34 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 240/1251] eta: 0:08:48 lr: 0.000410 loss: 5.4513 (5.3757) grad_norm: 1.6631 (1.8831) time: 0.5029 [2021-03-25 04:37:39 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 250/1251] eta: 0:08:42 lr: 0.000411 loss: 5.6169 (5.3836) grad_norm: 1.6997 (1.8767) time: 0.5070 [2021-03-25 04:37:44 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 260/1251] eta: 0:08:36 lr: 0.000411 loss: 5.6631 (5.3865) grad_norm: 1.7556 (1.8776) time: 0.5026 [2021-03-25 04:37:49 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 270/1251] eta: 0:08:30 lr: 0.000411 loss: 5.4110 (5.3768) grad_norm: 1.8278 (1.8784) time: 0.4992 [2021-03-25 04:37:54 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 280/1251] eta: 0:08:24 lr: 0.000412 loss: 5.3347 (5.3746) grad_norm: 1.7893 (1.8756) time: 0.4998 [2021-03-25 04:37:59 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 290/1251] eta: 0:08:18 lr: 0.000412 loss: 5.3347 (5.3726) grad_norm: 1.6931 (1.8804) time: 0.5013 [2021-03-25 04:38:04 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 300/1251] eta: 0:08:13 lr: 0.000413 loss: 5.3098 (5.3792) grad_norm: 1.9203 (1.8867) time: 0.5041 [2021-03-25 04:38:09 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 310/1251] eta: 0:08:07 lr: 0.000413 loss: 5.2083 (5.3662) grad_norm: 1.9279 (1.8859) time: 0.5045 [2021-03-25 04:38:14 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 320/1251] eta: 0:08:02 lr: 0.000413 loss: 5.2083 (5.3655) grad_norm: 1.8022 (1.8852) time: 0.5089 [2021-03-25 04:38:19 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 330/1251] eta: 0:07:56 lr: 0.000414 loss: 5.3991 (5.3677) grad_norm: 1.7722 (1.8827) time: 0.5093 [2021-03-25 04:38:25 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 340/1251] eta: 0:07:51 lr: 0.000414 loss: 5.4213 (5.3664) grad_norm: 1.6601 (1.8751) time: 0.5036 [2021-03-25 04:38:30 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 350/1251] eta: 0:07:45 lr: 0.000415 loss: 5.4357 (5.3654) grad_norm: 1.6596 (1.8741) time: 0.5033 [2021-03-25 04:38:35 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 360/1251] eta: 0:07:40 lr: 0.000415 loss: 5.4273 (5.3687) grad_norm: 1.7838 (1.8888) time: 0.5112 [2021-03-25 04:38:40 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 370/1251] eta: 0:07:35 lr: 0.000415 loss: 5.2877 (5.3593) grad_norm: 1.8331 (1.8891) time: 0.5150 [2021-03-25 04:38:45 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 380/1251] eta: 0:07:29 lr: 0.000416 loss: 4.9749 (5.3548) grad_norm: 1.8331 (1.8910) time: 0.5101 [2021-03-25 04:38:50 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 390/1251] eta: 0:07:24 lr: 0.000416 loss: 5.3132 (5.3528) grad_norm: 1.7473 (1.8848) time: 0.5093 [2021-03-25 04:38:55 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 400/1251] eta: 0:07:19 lr: 0.000417 loss: 5.1351 (5.3484) grad_norm: 1.7188 (1.8862) time: 0.5099 [2021-03-25 04:39:00 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 410/1251] eta: 0:07:14 lr: 0.000417 loss: 5.1111 (5.3482) grad_norm: 1.7851 (1.8841) time: 0.5120 [2021-03-25 04:39:05 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 420/1251] eta: 0:07:08 lr: 0.000417 loss: 5.0967 (5.3434) grad_norm: 1.7466 (1.8806) time: 0.5082 [2021-03-25 04:39:10 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 430/1251] eta: 0:07:03 lr: 0.000418 loss: 5.0774 (5.3419) grad_norm: 1.6783 (1.8776) time: 0.5070 [2021-03-25 04:39:15 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 440/1251] eta: 0:06:58 lr: 0.000418 loss: 5.3549 (5.3441) grad_norm: 1.7004 (1.8764) time: 0.5083 [2021-03-25 04:39:21 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 450/1251] eta: 0:06:52 lr: 0.000419 loss: 5.2665 (5.3423) grad_norm: 1.6455 (1.8716) time: 0.5031 [2021-03-25 04:39:26 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 460/1251] eta: 0:06:47 lr: 0.000419 loss: 5.2665 (5.3406) grad_norm: 1.7137 (1.8734) time: 0.5039 [2021-03-25 04:39:31 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 470/1251] eta: 0:06:42 lr: 0.000419 loss: 5.4879 (5.3421) grad_norm: 1.9427 (1.8762) time: 0.5069 [2021-03-25 04:39:36 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 480/1251] eta: 0:06:36 lr: 0.000420 loss: 5.2850 (5.3384) grad_norm: 1.9623 (1.8807) time: 0.5064 [2021-03-25 04:39:41 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 490/1251] eta: 0:06:31 lr: 0.000420 loss: 5.4296 (5.3396) grad_norm: 1.7680 (1.8762) time: 0.5045 [2021-03-25 04:39:46 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 500/1251] eta: 0:06:26 lr: 0.000421 loss: 5.4296 (5.3417) grad_norm: 1.6453 (1.8751) time: 0.5030 [2021-03-25 04:39:51 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 510/1251] eta: 0:06:20 lr: 0.000421 loss: 5.4144 (5.3426) grad_norm: 1.6453 (1.8720) time: 0.5030 [2021-03-25 04:39:56 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 520/1251] eta: 0:06:15 lr: 0.000421 loss: 5.2319 (5.3435) grad_norm: 1.7439 (1.8773) time: 0.5068 [2021-03-25 04:40:01 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 530/1251] eta: 0:06:10 lr: 0.000422 loss: 5.0199 (5.3358) grad_norm: 1.8489 (1.8772) time: 0.5025 [2021-03-25 04:40:06 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 540/1251] eta: 0:06:05 lr: 0.000422 loss: 5.0199 (5.3372) grad_norm: 1.9466 (1.8857) time: 0.5041 [2021-03-25 04:40:11 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 550/1251] eta: 0:05:59 lr: 0.000423 loss: 5.4185 (5.3337) grad_norm: 2.0220 (1.8904) time: 0.5059 [2021-03-25 04:40:16 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 560/1251] eta: 0:05:54 lr: 0.000423 loss: 5.0076 (5.3274) grad_norm: 1.7840 (1.8874) time: 0.5020 [2021-03-25 04:40:21 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 570/1251] eta: 0:05:49 lr: 0.000423 loss: 5.0334 (5.3276) grad_norm: 1.6446 (1.8856) time: 0.5146 [2021-03-25 04:40:26 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 580/1251] eta: 0:05:44 lr: 0.000424 loss: 5.4566 (5.3269) grad_norm: 1.5969 (1.8832) time: 0.5158 [2021-03-25 04:40:31 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 590/1251] eta: 0:05:38 lr: 0.000424 loss: 5.1109 (5.3221) grad_norm: 1.6228 (1.8801) time: 0.5000 [2021-03-25 04:40:36 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 600/1251] eta: 0:05:33 lr: 0.000425 loss: 5.1109 (5.3215) grad_norm: 1.6315 (1.8776) time: 0.4972 [2021-03-25 04:40:41 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 610/1251] eta: 0:05:28 lr: 0.000425 loss: 5.1374 (5.3181) grad_norm: 1.7678 (1.8778) time: 0.5027 [2021-03-25 04:40:46 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 620/1251] eta: 0:05:23 lr: 0.000425 loss: 5.1225 (5.3157) grad_norm: 1.8159 (1.8786) time: 0.5021 [2021-03-25 04:40:51 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 630/1251] eta: 0:05:18 lr: 0.000426 loss: 5.5065 (5.3214) grad_norm: 1.7202 (1.8762) time: 0.5015 [2021-03-25 04:40:56 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 640/1251] eta: 0:05:12 lr: 0.000426 loss: 5.5538 (5.3190) grad_norm: 1.6411 (1.8744) time: 0.5070 [2021-03-25 04:41:02 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 650/1251] eta: 0:05:07 lr: 0.000427 loss: 5.1287 (5.3150) grad_norm: 1.7045 (1.8721) time: 0.5093 [2021-03-25 04:41:07 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 660/1251] eta: 0:05:02 lr: 0.000427 loss: 5.3589 (5.3151) grad_norm: 1.7045 (1.8722) time: 0.5036 [2021-03-25 04:41:12 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 670/1251] eta: 0:04:57 lr: 0.000427 loss: 5.3713 (5.3138) grad_norm: 1.8005 (1.8730) time: 0.5022 [2021-03-25 04:41:17 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 680/1251] eta: 0:04:52 lr: 0.000428 loss: 5.4389 (5.3171) grad_norm: 1.9063 (1.8758) time: 0.5081 [2021-03-25 04:41:22 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 690/1251] eta: 0:04:47 lr: 0.000428 loss: 5.4697 (5.3177) grad_norm: 1.8421 (1.8739) time: 0.5094 [2021-03-25 04:41:27 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 700/1251] eta: 0:04:41 lr: 0.000429 loss: 5.4565 (5.3178) grad_norm: 1.7340 (1.8729) time: 0.5016 [2021-03-25 04:41:32 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 710/1251] eta: 0:04:36 lr: 0.000429 loss: 5.3889 (5.3153) grad_norm: 1.8401 (1.8757) time: 0.4978 [2021-03-25 04:41:37 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 720/1251] eta: 0:04:31 lr: 0.000429 loss: 5.3545 (5.3137) grad_norm: 1.7623 (1.8739) time: 0.5002 [2021-03-25 04:41:42 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 730/1251] eta: 0:04:26 lr: 0.000430 loss: 5.4423 (5.3149) grad_norm: 1.6200 (1.8733) time: 0.5064 [2021-03-25 04:41:47 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 740/1251] eta: 0:04:21 lr: 0.000430 loss: 5.5143 (5.3149) grad_norm: 1.7975 (1.8730) time: 0.5151 [2021-03-25 04:41:52 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 750/1251] eta: 0:04:16 lr: 0.000431 loss: 5.2965 (5.3164) grad_norm: 1.7879 (1.8707) time: 0.5201 [2021-03-25 04:41:57 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 760/1251] eta: 0:04:11 lr: 0.000431 loss: 5.2786 (5.3160) grad_norm: 1.6838 (1.8705) time: 0.5180 [2021-03-25 04:42:02 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 770/1251] eta: 0:04:05 lr: 0.000431 loss: 5.2376 (5.3149) grad_norm: 1.8898 (1.8702) time: 0.5084 [2021-03-25 04:42:08 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 780/1251] eta: 0:04:00 lr: 0.000432 loss: 5.3433 (5.3149) grad_norm: 1.7556 (1.8694) time: 0.5044 [2021-03-25 04:42:13 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 790/1251] eta: 0:03:55 lr: 0.000432 loss: 5.2879 (5.3109) grad_norm: 1.7223 (1.8672) time: 0.5052 [2021-03-25 04:42:18 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 800/1251] eta: 0:03:50 lr: 0.000433 loss: 5.1177 (5.3106) grad_norm: 1.7302 (1.8672) time: 0.5022 [2021-03-25 04:42:23 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 810/1251] eta: 0:03:45 lr: 0.000433 loss: 5.3663 (5.3104) grad_norm: 1.7622 (1.8670) time: 0.5008 [2021-03-25 04:42:28 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 820/1251] eta: 0:03:40 lr: 0.000433 loss: 5.1889 (5.3078) grad_norm: 1.7601 (1.8655) time: 0.5034 [2021-03-25 04:42:33 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 830/1251] eta: 0:03:34 lr: 0.000434 loss: 5.3537 (5.3094) grad_norm: 1.6894 (1.8659) time: 0.5006 [2021-03-25 04:42:38 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 840/1251] eta: 0:03:29 lr: 0.000434 loss: 5.5711 (5.3094) grad_norm: 1.8931 (1.8697) time: 0.5092 [2021-03-25 04:42:43 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 850/1251] eta: 0:03:24 lr: 0.000435 loss: 5.4421 (5.3087) grad_norm: 1.8544 (1.8670) time: 0.5128 [2021-03-25 04:42:48 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 860/1251] eta: 0:03:19 lr: 0.000435 loss: 5.4364 (5.3095) grad_norm: 1.8173 (1.8672) time: 0.5043 [2021-03-25 04:42:53 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 870/1251] eta: 0:03:14 lr: 0.000435 loss: 5.4820 (5.3107) grad_norm: 1.8378 (1.8678) time: 0.5094 [2021-03-25 04:42:58 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 880/1251] eta: 0:03:09 lr: 0.000436 loss: 5.4703 (5.3091) grad_norm: 1.8022 (1.8672) time: 0.5062 [2021-03-25 04:43:03 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 890/1251] eta: 0:03:04 lr: 0.000436 loss: 5.2241 (5.3076) grad_norm: 1.8022 (1.8680) time: 0.5020 [2021-03-25 04:43:08 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 900/1251] eta: 0:02:59 lr: 0.000437 loss: 5.3209 (5.3080) grad_norm: 1.7599 (1.8668) time: 0.5067 [2021-03-25 04:43:13 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 910/1251] eta: 0:02:54 lr: 0.000437 loss: 5.4149 (5.3053) grad_norm: 1.6414 (1.8643) time: 0.5085 [2021-03-25 04:43:18 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 920/1251] eta: 0:02:48 lr: 0.000437 loss: 4.9534 (5.3037) grad_norm: 1.6638 (1.8650) time: 0.5079 [2021-03-25 04:43:23 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 930/1251] eta: 0:02:43 lr: 0.000438 loss: 5.0848 (5.3023) grad_norm: 1.6631 (1.8632) time: 0.5105 [2021-03-25 04:43:29 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 940/1251] eta: 0:02:38 lr: 0.000438 loss: 5.1039 (5.3028) grad_norm: 1.6909 (1.8636) time: 0.5177 [2021-03-25 04:43:34 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 950/1251] eta: 0:02:33 lr: 0.000439 loss: 5.2445 (5.3012) grad_norm: 1.7293 (1.8616) time: 0.5155 [2021-03-25 04:43:39 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 960/1251] eta: 0:02:28 lr: 0.000439 loss: 5.4353 (5.3026) grad_norm: 1.6297 (1.8604) time: 0.5066 [2021-03-25 04:43:44 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 970/1251] eta: 0:02:23 lr: 0.000439 loss: 5.4247 (5.3027) grad_norm: 1.6187 (1.8598) time: 0.5044 [2021-03-25 04:43:49 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 980/1251] eta: 0:02:18 lr: 0.000440 loss: 5.2438 (5.3006) grad_norm: 1.6533 (1.8601) time: 0.5029 [2021-03-25 04:43:54 swin_small_patch4_window7_224] INFO: Epoch: [8] [ 990/1251] eta: 0:02:13 lr: 0.000440 loss: 5.2801 (5.3002) grad_norm: 1.7136 (1.8587) time: 0.5026 [2021-03-25 04:43:59 swin_small_patch4_window7_224] INFO: Epoch: [8] [1000/1251] eta: 0:02:08 lr: 0.000441 loss: 5.4554 (5.3020) grad_norm: 1.6198 (1.8568) time: 0.5068 [2021-03-25 04:44:04 swin_small_patch4_window7_224] INFO: Epoch: [8] [1010/1251] eta: 0:02:02 lr: 0.000441 loss: 5.5220 (5.3034) grad_norm: 1.6198 (1.8562) time: 0.5047 [2021-03-25 04:44:09 swin_small_patch4_window7_224] INFO: Epoch: [8] [1020/1251] eta: 0:01:57 lr: 0.000441 loss: 5.4280 (5.3035) grad_norm: 1.7188 (1.8547) time: 0.5050 [2021-03-25 04:44:14 swin_small_patch4_window7_224] INFO: Epoch: [8] [1030/1251] eta: 0:01:52 lr: 0.000442 loss: 5.2235 (5.3023) grad_norm: 1.6636 (1.8533) time: 0.5046 [2021-03-25 04:44:19 swin_small_patch4_window7_224] INFO: Epoch: [8] [1040/1251] eta: 0:01:47 lr: 0.000442 loss: 5.3206 (5.3031) grad_norm: 1.6572 (1.8528) time: 0.5040 [2021-03-25 04:44:24 swin_small_patch4_window7_224] INFO: Epoch: [8] [1050/1251] eta: 0:01:42 lr: 0.000443 loss: 5.3053 (5.3012) grad_norm: 1.7848 (1.8540) time: 0.5124 [2021-03-25 04:44:29 swin_small_patch4_window7_224] INFO: Epoch: [8] [1060/1251] eta: 0:01:37 lr: 0.000443 loss: 5.4059 (5.3036) grad_norm: 1.8631 (1.8539) time: 0.5078 [2021-03-25 04:44:34 swin_small_patch4_window7_224] INFO: Epoch: [8] [1070/1251] eta: 0:01:32 lr: 0.000443 loss: 5.4503 (5.3027) grad_norm: 1.7397 (1.8529) time: 0.5050 [2021-03-25 04:44:40 swin_small_patch4_window7_224] INFO: Epoch: [8] [1080/1251] eta: 0:01:27 lr: 0.000444 loss: 5.1555 (5.3005) grad_norm: 1.7251 (1.8522) time: 0.5079 [2021-03-25 04:44:45 swin_small_patch4_window7_224] INFO: Epoch: [8] [1090/1251] eta: 0:01:22 lr: 0.000444 loss: 5.3633 (5.3023) grad_norm: 1.7251 (1.8503) time: 0.5065 [2021-03-25 04:44:50 swin_small_patch4_window7_224] INFO: Epoch: [8] [1100/1251] eta: 0:01:16 lr: 0.000445 loss: 5.1993 (5.2985) grad_norm: 1.7264 (1.8489) time: 0.5044 [2021-03-25 04:44:55 swin_small_patch4_window7_224] INFO: Epoch: [8] [1110/1251] eta: 0:01:11 lr: 0.000445 loss: 5.1993 (5.2983) grad_norm: 1.6570 (1.8479) time: 0.5062 [2021-03-25 04:45:00 swin_small_patch4_window7_224] INFO: Epoch: [8] [1120/1251] eta: 0:01:06 lr: 0.000445 loss: 5.3567 (5.2986) grad_norm: 1.6969 (1.8490) time: 0.5089 [2021-03-25 04:45:05 swin_small_patch4_window7_224] INFO: Epoch: [8] [1130/1251] eta: 0:01:01 lr: 0.000446 loss: 5.4182 (5.2979) grad_norm: 2.0187 (1.8507) time: 0.5041 [2021-03-25 04:45:10 swin_small_patch4_window7_224] INFO: Epoch: [8] [1140/1251] eta: 0:00:56 lr: 0.000446 loss: 5.3921 (5.2985) grad_norm: 1.9581 (1.8514) time: 0.5014 [2021-03-25 04:45:15 swin_small_patch4_window7_224] INFO: Epoch: [8] [1150/1251] eta: 0:00:51 lr: 0.000447 loss: 5.2279 (5.2981) grad_norm: 1.7408 (1.8514) time: 0.5036 [2021-03-25 04:45:20 swin_small_patch4_window7_224] INFO: Epoch: [8] [1160/1251] eta: 0:00:46 lr: 0.000447 loss: 5.2930 (5.2975) grad_norm: 1.6971 (1.8521) time: 0.5049 [2021-03-25 04:45:25 swin_small_patch4_window7_224] INFO: Epoch: [8] [1170/1251] eta: 0:00:41 lr: 0.000447 loss: 5.1900 (5.2951) grad_norm: 1.7594 (1.8524) time: 0.5054 [2021-03-25 04:45:30 swin_small_patch4_window7_224] INFO: Epoch: [8] [1180/1251] eta: 0:00:36 lr: 0.000448 loss: 5.1888 (5.2929) grad_norm: 1.8326 (1.8538) time: 0.5042 [2021-03-25 04:45:35 swin_small_patch4_window7_224] INFO: Epoch: [8] [1190/1251] eta: 0:00:31 lr: 0.000448 loss: 5.2930 (5.2923) grad_norm: 1.7572 (1.8527) time: 0.5023 [2021-03-25 04:45:40 swin_small_patch4_window7_224] INFO: Epoch: [8] [1200/1251] eta: 0:00:25 lr: 0.000449 loss: 5.2930 (5.2920) grad_norm: 1.7244 (1.8521) time: 0.5082 [2021-03-25 04:45:45 swin_small_patch4_window7_224] INFO: Epoch: [8] [1210/1251] eta: 0:00:20 lr: 0.000449 loss: 5.4271 (5.2934) grad_norm: 1.7113 (1.8523) time: 0.5065 [2021-03-25 04:45:50 swin_small_patch4_window7_224] INFO: Epoch: [8] [1220/1251] eta: 0:00:15 lr: 0.000449 loss: 5.3664 (5.2910) grad_norm: 1.8340 (1.8523) time: 0.5008 [2021-03-25 04:45:55 swin_small_patch4_window7_224] INFO: Epoch: [8] [1230/1251] eta: 0:00:10 lr: 0.000450 loss: 5.0915 (5.2910) grad_norm: 1.8247 (1.8523) time: 0.5054 [2021-03-25 04:46:00 swin_small_patch4_window7_224] INFO: Epoch: [8] [1240/1251] eta: 0:00:05 lr: 0.000450 loss: 5.2953 (5.2886) grad_norm: 1.8933 (1.8529) time: 0.5018 [2021-03-25 04:46:05 swin_small_patch4_window7_224] INFO: Epoch: [8] [1250/1251] eta: 0:00:00 lr: 0.000451 loss: 5.3220 (5.2892) grad_norm: 1.8220 (1.8515) time: 0.4921 [2021-03-25 04:46:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:44 loss: 2.5374 (2.5374) acc1: 50.0000 (50.0000) acc5: 70.3125 (70.3125) [2021-03-25 04:46:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 2.7622 (2.8287) acc1: 45.3125 (42.6136) acc5: 65.6250 (66.6193) [2021-03-25 04:46:14 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 2.8272 (2.8396) acc1: 40.6250 (40.8482) acc5: 65.6250 (65.4762) [2021-03-25 04:46:16 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.8822 (2.8578) acc1: 40.6250 (40.8770) acc5: 64.0625 (65.0706) [2021-03-25 04:46:18 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.7557 (2.8304) acc1: 43.7500 (41.5015) acc5: 67.1875 (65.6250) [2021-03-25 04:46:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.7213 (2.8208) acc1: 43.7500 (41.1520) acc5: 68.7500 (65.9840) [2021-03-25 04:46:20 swin_small_patch4_window7_224] INFO: * Acc@1 41.500 Acc@5 67.392 loss 2.795 [2021-03-25 04:46:20 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 41.5% [2021-03-25 04:46:20 swin_small_patch4_window7_224] INFO: Max accuracy: 41.50% [2021-03-25 04:46:24 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 0/1251] eta: 1:29:46 lr: 0.000451 loss: 4.5854 (4.5854) grad_norm: 1.5204 (1.5204) time: 4.3061 [2021-03-25 04:46:29 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 10/1251] eta: 0:18:00 lr: 0.000451 loss: 5.0881 (5.1142) grad_norm: 1.7065 (1.7395) time: 0.8707 [2021-03-25 04:46:34 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 20/1251] eta: 0:14:21 lr: 0.000451 loss: 5.0715 (5.0131) grad_norm: 1.7065 (1.7681) time: 0.5195 [2021-03-25 04:46:39 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 30/1251] eta: 0:12:56 lr: 0.000452 loss: 5.2988 (5.1418) grad_norm: 1.6965 (1.8702) time: 0.5066 [2021-03-25 04:46:45 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 40/1251] eta: 0:12:16 lr: 0.000452 loss: 5.3351 (5.1637) grad_norm: 1.8088 (1.8847) time: 0.5111 [2021-03-25 04:46:50 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 50/1251] eta: 0:11:47 lr: 0.000453 loss: 5.3037 (5.2048) grad_norm: 1.8088 (1.8606) time: 0.5158 [2021-03-25 04:46:55 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 60/1251] eta: 0:11:26 lr: 0.000453 loss: 5.2297 (5.1854) grad_norm: 1.7265 (1.8606) time: 0.5108 [2021-03-25 04:47:00 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 70/1251] eta: 0:11:08 lr: 0.000453 loss: 5.2968 (5.2166) grad_norm: 1.7978 (1.8520) time: 0.5081 [2021-03-25 04:47:05 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 80/1251] eta: 0:10:53 lr: 0.000454 loss: 5.3407 (5.2099) grad_norm: 1.6651 (1.8242) time: 0.5036 [2021-03-25 04:47:10 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 90/1251] eta: 0:10:40 lr: 0.000454 loss: 5.4274 (5.2283) grad_norm: 1.6328 (1.8116) time: 0.5019 [2021-03-25 04:47:15 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 100/1251] eta: 0:10:29 lr: 0.000455 loss: 5.3708 (5.2293) grad_norm: 1.8162 (1.8417) time: 0.5020 [2021-03-25 04:47:20 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 110/1251] eta: 0:10:22 lr: 0.000455 loss: 5.3016 (5.2365) grad_norm: 1.7178 (1.8187) time: 0.5187 [2021-03-25 04:47:25 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 120/1251] eta: 0:10:13 lr: 0.000455 loss: 5.3016 (5.2409) grad_norm: 1.6283 (1.8155) time: 0.5209 [2021-03-25 04:47:30 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 130/1251] eta: 0:10:06 lr: 0.000456 loss: 5.2705 (5.2281) grad_norm: 1.6283 (1.8045) time: 0.5130 [2021-03-25 04:47:35 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 140/1251] eta: 0:09:57 lr: 0.000456 loss: 5.1669 (5.2331) grad_norm: 1.7507 (1.8039) time: 0.5094 [2021-03-25 04:47:40 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 150/1251] eta: 0:09:49 lr: 0.000457 loss: 5.1535 (5.2075) grad_norm: 1.7881 (1.8014) time: 0.5002 [2021-03-25 04:47:46 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 160/1251] eta: 0:09:42 lr: 0.000457 loss: 5.2999 (5.2254) grad_norm: 1.7881 (1.8070) time: 0.5033 [2021-03-25 04:47:51 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 170/1251] eta: 0:09:34 lr: 0.000457 loss: 5.4093 (5.2209) grad_norm: 1.9068 (inf) time: 0.5034 [2021-03-25 04:47:56 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 180/1251] eta: 0:09:27 lr: 0.000458 loss: 5.1176 (5.2208) grad_norm: 1.8968 (inf) time: 0.4999 [2021-03-25 04:48:01 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 190/1251] eta: 0:09:20 lr: 0.000458 loss: 5.3724 (5.2224) grad_norm: 1.8432 (inf) time: 0.5028 [2021-03-25 04:48:06 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 200/1251] eta: 0:09:14 lr: 0.000459 loss: 5.3769 (5.2185) grad_norm: 1.8237 (inf) time: 0.5037 [2021-03-25 04:48:11 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 210/1251] eta: 0:09:07 lr: 0.000459 loss: 5.3411 (5.2179) grad_norm: 1.7452 (inf) time: 0.5026 [2021-03-25 04:48:16 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 220/1251] eta: 0:09:01 lr: 0.000459 loss: 5.4062 (5.2216) grad_norm: 1.6996 (inf) time: 0.5076 [2021-03-25 04:48:21 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 230/1251] eta: 0:08:55 lr: 0.000460 loss: 5.6162 (5.2363) grad_norm: 1.7303 (inf) time: 0.5108 [2021-03-25 04:48:26 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 240/1251] eta: 0:08:50 lr: 0.000460 loss: 5.6094 (5.2454) grad_norm: 1.6718 (inf) time: 0.5099 [2021-03-25 04:48:31 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 250/1251] eta: 0:08:44 lr: 0.000461 loss: 5.4078 (5.2517) grad_norm: 1.6844 (inf) time: 0.5081 [2021-03-25 04:48:36 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 260/1251] eta: 0:08:37 lr: 0.000461 loss: 5.3596 (5.2481) grad_norm: 1.6844 (inf) time: 0.5042 [2021-03-25 04:48:41 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 270/1251] eta: 0:08:31 lr: 0.000461 loss: 5.1067 (5.2401) grad_norm: 1.6065 (inf) time: 0.5000 [2021-03-25 04:48:46 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 280/1251] eta: 0:08:26 lr: 0.000462 loss: 5.1989 (5.2414) grad_norm: 1.7769 (inf) time: 0.5030 [2021-03-25 04:48:51 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 290/1251] eta: 0:08:20 lr: 0.000462 loss: 5.3860 (5.2432) grad_norm: 1.6971 (inf) time: 0.5098 [2021-03-25 04:48:56 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 300/1251] eta: 0:08:15 lr: 0.000463 loss: 4.9847 (5.2320) grad_norm: 1.7166 (inf) time: 0.5167 [2021-03-25 04:49:02 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 310/1251] eta: 0:08:10 lr: 0.000463 loss: 4.9847 (5.2283) grad_norm: 1.9479 (inf) time: 0.5175 [2021-03-25 04:49:07 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 320/1251] eta: 0:08:04 lr: 0.000463 loss: 5.1322 (5.2235) grad_norm: 1.9455 (inf) time: 0.5118 [2021-03-25 04:49:12 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 330/1251] eta: 0:07:58 lr: 0.000464 loss: 4.9918 (5.2170) grad_norm: 1.8460 (inf) time: 0.5050 [2021-03-25 04:49:17 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 340/1251] eta: 0:07:53 lr: 0.000464 loss: 5.0622 (5.2156) grad_norm: 1.6820 (inf) time: 0.5026 [2021-03-25 04:49:22 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 350/1251] eta: 0:07:47 lr: 0.000465 loss: 5.1919 (5.2146) grad_norm: 1.6036 (inf) time: 0.5030 [2021-03-25 04:49:27 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 360/1251] eta: 0:07:41 lr: 0.000465 loss: 5.1919 (5.2118) grad_norm: 1.6006 (inf) time: 0.5023 [2021-03-25 04:49:32 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 370/1251] eta: 0:07:36 lr: 0.000465 loss: 4.8986 (5.2007) grad_norm: 1.6664 (inf) time: 0.5010 [2021-03-25 04:49:37 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 380/1251] eta: 0:07:30 lr: 0.000466 loss: 4.8951 (5.2020) grad_norm: 1.7883 (inf) time: 0.5055 [2021-03-25 04:49:42 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 390/1251] eta: 0:07:25 lr: 0.000466 loss: 5.3276 (5.2025) grad_norm: 1.7165 (inf) time: 0.5135 [2021-03-25 04:49:47 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 400/1251] eta: 0:07:20 lr: 0.000467 loss: 5.3844 (5.2026) grad_norm: 1.7500 (inf) time: 0.5110 [2021-03-25 04:49:52 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 410/1251] eta: 0:07:14 lr: 0.000467 loss: 5.0836 (5.1999) grad_norm: 1.7500 (inf) time: 0.5068 [2021-03-25 04:49:57 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 420/1251] eta: 0:07:09 lr: 0.000467 loss: 5.4097 (5.2044) grad_norm: 1.7391 (inf) time: 0.5026 [2021-03-25 04:50:02 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 430/1251] eta: 0:07:04 lr: 0.000468 loss: 5.4097 (5.2005) grad_norm: 1.7561 (inf) time: 0.5070 [2021-03-25 04:50:07 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 440/1251] eta: 0:06:58 lr: 0.000468 loss: 5.1067 (5.1996) grad_norm: 1.8866 (inf) time: 0.5091 [2021-03-25 04:50:12 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 450/1251] eta: 0:06:53 lr: 0.000469 loss: 5.1614 (5.1972) grad_norm: 1.7905 (inf) time: 0.4992 [2021-03-25 04:50:17 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 460/1251] eta: 0:06:47 lr: 0.000469 loss: 5.1476 (5.1894) grad_norm: 1.6602 (inf) time: 0.5009 [2021-03-25 04:50:22 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 470/1251] eta: 0:06:42 lr: 0.000469 loss: 5.0182 (5.1861) grad_norm: 1.6114 (inf) time: 0.5045 [2021-03-25 04:50:27 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 480/1251] eta: 0:06:37 lr: 0.000470 loss: 5.0951 (5.1868) grad_norm: 1.8533 (inf) time: 0.5046 [2021-03-25 04:50:33 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 490/1251] eta: 0:06:31 lr: 0.000470 loss: 5.0223 (5.1802) grad_norm: 1.7565 (inf) time: 0.5072 [2021-03-25 04:50:38 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 500/1251] eta: 0:06:26 lr: 0.000471 loss: 4.9969 (5.1802) grad_norm: 1.7044 (inf) time: 0.5042 [2021-03-25 04:50:43 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 510/1251] eta: 0:06:21 lr: 0.000471 loss: 5.3832 (5.1799) grad_norm: 1.5908 (inf) time: 0.5003 [2021-03-25 04:50:48 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 520/1251] eta: 0:06:15 lr: 0.000471 loss: 5.2922 (5.1800) grad_norm: 1.5923 (inf) time: 0.4992 [2021-03-25 04:50:53 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 530/1251] eta: 0:06:10 lr: 0.000472 loss: 5.2086 (5.1790) grad_norm: 1.7444 (inf) time: 0.4975 [2021-03-25 04:50:58 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 540/1251] eta: 0:06:05 lr: 0.000472 loss: 5.1878 (5.1768) grad_norm: 1.9323 (inf) time: 0.5061 [2021-03-25 04:51:03 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 550/1251] eta: 0:06:00 lr: 0.000473 loss: 5.1897 (5.1793) grad_norm: 2.0141 (inf) time: 0.5180 [2021-03-25 04:51:08 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 560/1251] eta: 0:05:54 lr: 0.000473 loss: 5.2754 (5.1803) grad_norm: 1.7645 (inf) time: 0.5093 [2021-03-25 04:51:13 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 570/1251] eta: 0:05:49 lr: 0.000473 loss: 5.0557 (5.1773) grad_norm: 1.6679 (inf) time: 0.5036 [2021-03-25 04:51:18 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 580/1251] eta: 0:05:44 lr: 0.000474 loss: 5.0557 (5.1763) grad_norm: 1.6679 (inf) time: 0.5049 [2021-03-25 04:51:23 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 590/1251] eta: 0:05:39 lr: 0.000474 loss: 5.1750 (5.1760) grad_norm: 1.6436 (inf) time: 0.5076 [2021-03-25 04:51:28 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 600/1251] eta: 0:05:34 lr: 0.000475 loss: 5.1132 (5.1733) grad_norm: 1.6598 (inf) time: 0.5122 [2021-03-25 04:51:33 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 610/1251] eta: 0:05:28 lr: 0.000475 loss: 5.2979 (5.1733) grad_norm: 1.7930 (inf) time: 0.5071 [2021-03-25 04:51:38 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 620/1251] eta: 0:05:23 lr: 0.000475 loss: 5.3437 (5.1746) grad_norm: 1.7930 (inf) time: 0.5027 [2021-03-25 04:51:43 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 630/1251] eta: 0:05:18 lr: 0.000476 loss: 4.8395 (5.1696) grad_norm: 1.7041 (inf) time: 0.4974 [2021-03-25 04:51:48 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 640/1251] eta: 0:05:13 lr: 0.000476 loss: 5.3682 (5.1763) grad_norm: 1.6926 (inf) time: 0.4960 [2021-03-25 04:51:53 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 650/1251] eta: 0:05:07 lr: 0.000477 loss: 5.3686 (5.1764) grad_norm: 1.6448 (inf) time: 0.5033 [2021-03-25 04:51:58 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 660/1251] eta: 0:05:02 lr: 0.000477 loss: 5.2700 (5.1760) grad_norm: 1.6815 (inf) time: 0.5084 [2021-03-25 04:52:03 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 670/1251] eta: 0:04:57 lr: 0.000477 loss: 5.2949 (5.1788) grad_norm: 1.7183 (inf) time: 0.5070 [2021-03-25 04:52:09 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 680/1251] eta: 0:04:52 lr: 0.000478 loss: 5.1657 (5.1755) grad_norm: 1.8051 (inf) time: 0.5071 [2021-03-25 04:52:14 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 690/1251] eta: 0:04:47 lr: 0.000478 loss: 5.1968 (5.1773) grad_norm: 1.7060 (inf) time: 0.5072 [2021-03-25 04:52:19 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 700/1251] eta: 0:04:42 lr: 0.000478 loss: 5.3463 (5.1768) grad_norm: 1.5295 (inf) time: 0.5042 [2021-03-25 04:52:24 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 710/1251] eta: 0:04:36 lr: 0.000479 loss: 5.1722 (5.1766) grad_norm: 1.4998 (inf) time: 0.5020 [2021-03-25 04:52:29 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 720/1251] eta: 0:04:31 lr: 0.000479 loss: 5.1257 (5.1773) grad_norm: 1.7391 (inf) time: 0.5054 [2021-03-25 04:52:34 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 730/1251] eta: 0:04:26 lr: 0.000480 loss: 5.1257 (5.1748) grad_norm: 1.7596 (inf) time: 0.5168 [2021-03-25 04:52:39 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 740/1251] eta: 0:04:21 lr: 0.000480 loss: 5.2681 (5.1739) grad_norm: 1.6766 (inf) time: 0.5171 [2021-03-25 04:52:44 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 750/1251] eta: 0:04:16 lr: 0.000480 loss: 5.3301 (5.1756) grad_norm: 1.6275 (inf) time: 0.5081 [2021-03-25 04:52:49 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 760/1251] eta: 0:04:11 lr: 0.000481 loss: 5.1424 (5.1738) grad_norm: 1.5906 (inf) time: 0.5093 [2021-03-25 04:52:54 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 770/1251] eta: 0:04:06 lr: 0.000481 loss: 5.0249 (5.1737) grad_norm: 1.6187 (inf) time: 0.5135 [2021-03-25 04:52:59 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 780/1251] eta: 0:04:01 lr: 0.000482 loss: 5.2125 (5.1746) grad_norm: 1.7613 (inf) time: 0.5075 [2021-03-25 04:53:05 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 790/1251] eta: 0:03:55 lr: 0.000482 loss: 5.2152 (5.1752) grad_norm: 1.7187 (inf) time: 0.5071 [2021-03-25 04:53:10 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 800/1251] eta: 0:03:50 lr: 0.000482 loss: 5.2526 (5.1750) grad_norm: 1.6200 (inf) time: 0.5141 [2021-03-25 04:53:15 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 810/1251] eta: 0:03:45 lr: 0.000483 loss: 5.3732 (5.1777) grad_norm: 1.6745 (inf) time: 0.5077 [2021-03-25 04:53:20 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 820/1251] eta: 0:03:40 lr: 0.000483 loss: 5.3732 (5.1775) grad_norm: 1.8115 (inf) time: 0.5022 [2021-03-25 04:53:25 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 830/1251] eta: 0:03:35 lr: 0.000484 loss: 5.1220 (5.1764) grad_norm: 1.7493 (inf) time: 0.5027 [2021-03-25 04:53:30 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 840/1251] eta: 0:03:30 lr: 0.000484 loss: 4.9770 (5.1729) grad_norm: 1.6999 (inf) time: 0.5019 [2021-03-25 04:53:35 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 850/1251] eta: 0:03:25 lr: 0.000484 loss: 4.9614 (5.1707) grad_norm: 1.7802 (inf) time: 0.5126 [2021-03-25 04:53:40 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 860/1251] eta: 0:03:20 lr: 0.000485 loss: 4.9538 (5.1692) grad_norm: 1.6947 (inf) time: 0.5197 [2021-03-25 04:53:45 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 870/1251] eta: 0:03:14 lr: 0.000485 loss: 4.9538 (5.1663) grad_norm: 1.6518 (inf) time: 0.5140 [2021-03-25 04:53:50 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 880/1251] eta: 0:03:09 lr: 0.000486 loss: 4.7550 (5.1616) grad_norm: 1.6559 (inf) time: 0.5084 [2021-03-25 04:53:55 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 890/1251] eta: 0:03:04 lr: 0.000486 loss: 5.0317 (5.1621) grad_norm: 1.7202 (inf) time: 0.5082 [2021-03-25 04:54:01 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 900/1251] eta: 0:02:59 lr: 0.000486 loss: 5.0317 (5.1605) grad_norm: 1.7202 (inf) time: 0.5080 [2021-03-25 04:54:05 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 910/1251] eta: 0:02:54 lr: 0.000487 loss: 5.2435 (5.1611) grad_norm: 1.4801 (inf) time: 0.5006 [2021-03-25 04:54:10 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 920/1251] eta: 0:02:49 lr: 0.000487 loss: 5.1724 (5.1594) grad_norm: 1.5552 (inf) time: 0.4988 [2021-03-25 04:54:16 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 930/1251] eta: 0:02:44 lr: 0.000488 loss: 4.8730 (5.1556) grad_norm: 1.6457 (inf) time: 0.5012 [2021-03-25 04:54:21 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 940/1251] eta: 0:02:38 lr: 0.000488 loss: 4.8730 (5.1523) grad_norm: 1.5570 (inf) time: 0.5013 [2021-03-25 04:54:26 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 950/1251] eta: 0:02:33 lr: 0.000488 loss: 4.9736 (5.1505) grad_norm: 1.6405 (inf) time: 0.5067 [2021-03-25 04:54:31 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 960/1251] eta: 0:02:28 lr: 0.000489 loss: 5.1357 (5.1492) grad_norm: 1.6250 (inf) time: 0.5082 [2021-03-25 04:54:36 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 970/1251] eta: 0:02:23 lr: 0.000489 loss: 5.1357 (5.1501) grad_norm: 1.5137 (inf) time: 0.5033 [2021-03-25 04:54:41 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 980/1251] eta: 0:02:18 lr: 0.000490 loss: 5.3176 (5.1497) grad_norm: 1.7608 (inf) time: 0.5012 [2021-03-25 04:54:46 swin_small_patch4_window7_224] INFO: Epoch: [9] [ 990/1251] eta: 0:02:13 lr: 0.000490 loss: 5.1482 (5.1488) grad_norm: 1.9890 (inf) time: 0.5024 [2021-03-25 04:54:51 swin_small_patch4_window7_224] INFO: Epoch: [9] [1000/1251] eta: 0:02:08 lr: 0.000490 loss: 5.1482 (5.1490) grad_norm: 1.8107 (inf) time: 0.5016 [2021-03-25 04:54:56 swin_small_patch4_window7_224] INFO: Epoch: [9] [1010/1251] eta: 0:02:03 lr: 0.000491 loss: 5.1749 (5.1479) grad_norm: 1.6276 (inf) time: 0.4993 [2021-03-25 04:55:01 swin_small_patch4_window7_224] INFO: Epoch: [9] [1020/1251] eta: 0:01:57 lr: 0.000491 loss: 5.1741 (5.1466) grad_norm: 1.7788 (inf) time: 0.5041 [2021-03-25 04:55:06 swin_small_patch4_window7_224] INFO: Epoch: [9] [1030/1251] eta: 0:01:52 lr: 0.000492 loss: 5.0902 (5.1472) grad_norm: 1.6517 (inf) time: 0.5055 [2021-03-25 04:55:11 swin_small_patch4_window7_224] INFO: Epoch: [9] [1040/1251] eta: 0:01:47 lr: 0.000492 loss: 5.1284 (5.1475) grad_norm: 1.7631 (inf) time: 0.5061 [2021-03-25 04:55:16 swin_small_patch4_window7_224] INFO: Epoch: [9] [1050/1251] eta: 0:01:42 lr: 0.000492 loss: 5.1284 (5.1470) grad_norm: 1.8150 (inf) time: 0.5173 [2021-03-25 04:55:21 swin_small_patch4_window7_224] INFO: Epoch: [9] [1060/1251] eta: 0:01:37 lr: 0.000493 loss: 5.1030 (5.1466) grad_norm: 1.7468 (inf) time: 0.5212 [2021-03-25 04:55:26 swin_small_patch4_window7_224] INFO: Epoch: [9] [1070/1251] eta: 0:01:32 lr: 0.000493 loss: 5.3674 (5.1484) grad_norm: 1.5843 (inf) time: 0.5108 [2021-03-25 04:55:31 swin_small_patch4_window7_224] INFO: Epoch: [9] [1080/1251] eta: 0:01:27 lr: 0.000494 loss: 5.3413 (5.1469) grad_norm: 1.6874 (inf) time: 0.5000 [2021-03-25 04:55:36 swin_small_patch4_window7_224] INFO: Epoch: [9] [1090/1251] eta: 0:01:22 lr: 0.000494 loss: 5.2380 (5.1462) grad_norm: 1.7468 (inf) time: 0.5017 [2021-03-25 04:55:42 swin_small_patch4_window7_224] INFO: Epoch: [9] [1100/1251] eta: 0:01:17 lr: 0.000494 loss: 5.0715 (5.1445) grad_norm: 1.6013 (inf) time: 0.5069 [2021-03-25 04:55:47 swin_small_patch4_window7_224] INFO: Epoch: [9] [1110/1251] eta: 0:01:11 lr: 0.000495 loss: 4.8528 (5.1409) grad_norm: 1.8713 (inf) time: 0.5034 [2021-03-25 04:55:52 swin_small_patch4_window7_224] INFO: Epoch: [9] [1120/1251] eta: 0:01:06 lr: 0.000495 loss: 4.9269 (5.1411) grad_norm: 1.7082 (inf) time: 0.5072 [2021-03-25 04:55:57 swin_small_patch4_window7_224] INFO: Epoch: [9] [1130/1251] eta: 0:01:01 lr: 0.000496 loss: 5.2933 (5.1406) grad_norm: 1.6671 (inf) time: 0.5123 [2021-03-25 04:56:02 swin_small_patch4_window7_224] INFO: Epoch: [9] [1140/1251] eta: 0:00:56 lr: 0.000496 loss: 5.0710 (5.1382) grad_norm: 1.6908 (inf) time: 0.5061 [2021-03-25 04:56:07 swin_small_patch4_window7_224] INFO: Epoch: [9] [1150/1251] eta: 0:00:51 lr: 0.000496 loss: 5.0842 (5.1398) grad_norm: 1.5694 (inf) time: 0.5041 [2021-03-25 04:56:12 swin_small_patch4_window7_224] INFO: Epoch: [9] [1160/1251] eta: 0:00:46 lr: 0.000497 loss: 5.1539 (5.1378) grad_norm: 1.6568 (inf) time: 0.5051 [2021-03-25 04:56:17 swin_small_patch4_window7_224] INFO: Epoch: [9] [1170/1251] eta: 0:00:41 lr: 0.000497 loss: 4.7846 (5.1365) grad_norm: 1.8613 (inf) time: 0.5043 [2021-03-25 04:56:22 swin_small_patch4_window7_224] INFO: Epoch: [9] [1180/1251] eta: 0:00:36 lr: 0.000498 loss: 4.8769 (5.1341) grad_norm: 1.5701 (inf) time: 0.5039 [2021-03-25 04:56:27 swin_small_patch4_window7_224] INFO: Epoch: [9] [1190/1251] eta: 0:00:31 lr: 0.000498 loss: 4.8769 (5.1331) grad_norm: 1.5701 (inf) time: 0.4996 [2021-03-25 04:56:32 swin_small_patch4_window7_224] INFO: Epoch: [9] [1200/1251] eta: 0:00:25 lr: 0.000498 loss: 5.1217 (5.1324) grad_norm: 1.6574 (inf) time: 0.5023 [2021-03-25 04:56:37 swin_small_patch4_window7_224] INFO: Epoch: [9] [1210/1251] eta: 0:00:20 lr: 0.000499 loss: 5.2975 (5.1343) grad_norm: 1.7663 (inf) time: 0.5026 [2021-03-25 04:56:42 swin_small_patch4_window7_224] INFO: Epoch: [9] [1220/1251] eta: 0:00:15 lr: 0.000499 loss: 5.2505 (5.1329) grad_norm: 1.5993 (inf) time: 0.4969 [2021-03-25 04:56:47 swin_small_patch4_window7_224] INFO: Epoch: [9] [1230/1251] eta: 0:00:10 lr: 0.000500 loss: 4.9511 (5.1322) grad_norm: 1.6953 (inf) time: 0.5021 [2021-03-25 04:56:52 swin_small_patch4_window7_224] INFO: Epoch: [9] [1240/1251] eta: 0:00:05 lr: 0.000500 loss: 4.8643 (5.1315) grad_norm: 1.8566 (inf) time: 0.5104 [2021-03-25 04:56:57 swin_small_patch4_window7_224] INFO: Epoch: [9] [1250/1251] eta: 0:00:00 lr: 0.000500 loss: 5.2205 (5.1325) grad_norm: 1.6773 (inf) time: 0.5086 [2021-03-25 04:57:02 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:39 loss: 2.3417 (2.3417) acc1: 48.4375 (48.4375) acc5: 71.8750 (71.8750) [2021-03-25 04:57:04 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 2.5983 (2.6009) acc1: 45.3125 (45.3125) acc5: 67.1875 (67.8977) [2021-03-25 04:57:07 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 2.5443 (2.5953) acc1: 45.3125 (45.2381) acc5: 70.3125 (69.3452) [2021-03-25 04:57:09 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 2.5041 (2.5613) acc1: 45.3125 (45.7157) acc5: 71.8750 (70.2621) [2021-03-25 04:57:10 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.5565 (2.5793) acc1: 43.7500 (44.7409) acc5: 70.3125 (70.2363) [2021-03-25 04:57:11 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.6210 (2.5903) acc1: 42.1875 (44.2240) acc5: 70.3125 (70.0800) [2021-03-25 04:57:12 swin_small_patch4_window7_224] INFO: * Acc@1 44.350 Acc@5 70.284 loss 2.587 [2021-03-25 04:57:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 44.4% [2021-03-25 04:57:12 swin_small_patch4_window7_224] INFO: Max accuracy: 44.35% [2021-03-25 04:57:17 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 0/1251] eta: 1:35:50 lr: 0.000501 loss: 5.4052 (5.4052) grad_norm: 1.8527 (1.8527) time: 4.5969 [2021-03-25 04:57:22 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 10/1251] eta: 0:18:00 lr: 0.000501 loss: 5.4052 (5.4283) grad_norm: 1.8004 (1.8033) time: 0.8703 [2021-03-25 04:57:27 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 20/1251] eta: 0:14:17 lr: 0.000501 loss: 5.2614 (5.2955) grad_norm: 1.8004 (1.8176) time: 0.5017 [2021-03-25 04:57:32 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 30/1251] eta: 0:12:53 lr: 0.000502 loss: 5.1167 (5.2284) grad_norm: 1.7939 (1.8106) time: 0.5038 [2021-03-25 04:57:37 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 40/1251] eta: 0:12:07 lr: 0.000502 loss: 5.1100 (5.2205) grad_norm: 1.6595 (1.8108) time: 0.5005 [2021-03-25 04:57:42 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 50/1251] eta: 0:11:38 lr: 0.000502 loss: 5.2887 (5.1873) grad_norm: 1.6061 (1.7842) time: 0.5015 [2021-03-25 04:57:47 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 60/1251] eta: 0:11:20 lr: 0.000503 loss: 5.2054 (5.1502) grad_norm: 1.6921 (1.7686) time: 0.5097 [2021-03-25 04:57:52 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 70/1251] eta: 0:11:05 lr: 0.000503 loss: 5.2394 (5.1714) grad_norm: 1.6921 (1.7565) time: 0.5155 [2021-03-25 04:57:58 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 80/1251] eta: 0:10:52 lr: 0.000504 loss: 5.3323 (5.1848) grad_norm: 1.6005 (1.7325) time: 0.5153 [2021-03-25 04:58:03 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 90/1251] eta: 0:10:41 lr: 0.000504 loss: 5.2283 (5.1754) grad_norm: 1.6005 (1.7237) time: 0.5156 [2021-03-25 04:58:08 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 100/1251] eta: 0:10:31 lr: 0.000504 loss: 5.1901 (5.1536) grad_norm: 1.6191 (1.7132) time: 0.5118 [2021-03-25 04:58:13 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 110/1251] eta: 0:10:21 lr: 0.000505 loss: 5.1655 (5.1523) grad_norm: 1.6103 (1.7118) time: 0.5095 [2021-03-25 04:58:18 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 120/1251] eta: 0:10:12 lr: 0.000505 loss: 5.1950 (5.1533) grad_norm: 1.6103 (1.7064) time: 0.5065 [2021-03-25 04:58:23 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 130/1251] eta: 0:10:03 lr: 0.000506 loss: 5.1866 (5.1427) grad_norm: 1.6111 (1.7208) time: 0.5037 [2021-03-25 04:58:28 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 140/1251] eta: 0:09:55 lr: 0.000506 loss: 5.1866 (5.1411) grad_norm: 1.6526 (1.7201) time: 0.5010 [2021-03-25 04:58:33 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 150/1251] eta: 0:09:47 lr: 0.000506 loss: 5.2435 (5.1425) grad_norm: 1.5451 (1.7131) time: 0.5018 [2021-03-25 04:58:38 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 160/1251] eta: 0:09:40 lr: 0.000507 loss: 5.1709 (5.1455) grad_norm: 1.5368 (1.7078) time: 0.5064 [2021-03-25 04:58:43 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 170/1251] eta: 0:09:33 lr: 0.000507 loss: 5.3543 (5.1532) grad_norm: 1.6133 (1.7032) time: 0.5052 [2021-03-25 04:58:48 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 180/1251] eta: 0:09:27 lr: 0.000508 loss: 5.3912 (5.1532) grad_norm: 1.6775 (1.7108) time: 0.5156 [2021-03-25 04:58:53 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 190/1251] eta: 0:09:20 lr: 0.000508 loss: 5.2839 (5.1535) grad_norm: 1.7660 (1.7199) time: 0.5135 [2021-03-25 04:58:58 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 200/1251] eta: 0:09:14 lr: 0.000508 loss: 5.2786 (5.1491) grad_norm: 1.5529 (1.7105) time: 0.5006 [2021-03-25 04:59:03 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 210/1251] eta: 0:09:07 lr: 0.000509 loss: 5.3531 (5.1528) grad_norm: 1.5450 (1.7040) time: 0.5020 [2021-03-25 04:59:08 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 220/1251] eta: 0:09:01 lr: 0.000509 loss: 5.3531 (5.1540) grad_norm: 1.5920 (1.7054) time: 0.4996 [2021-03-25 04:59:14 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 230/1251] eta: 0:08:55 lr: 0.000510 loss: 5.2833 (5.1552) grad_norm: 1.6238 (1.7046) time: 0.5116 [2021-03-25 04:59:19 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 240/1251] eta: 0:08:49 lr: 0.000510 loss: 4.7990 (5.1375) grad_norm: 1.7066 (1.7112) time: 0.5138 [2021-03-25 04:59:24 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 250/1251] eta: 0:08:44 lr: 0.000510 loss: 4.6497 (5.1365) grad_norm: 1.7711 (1.7150) time: 0.5098 [2021-03-25 04:59:29 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 260/1251] eta: 0:08:38 lr: 0.000511 loss: 5.1170 (5.1437) grad_norm: 1.7711 (1.7199) time: 0.5146 [2021-03-25 04:59:34 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 270/1251] eta: 0:08:32 lr: 0.000511 loss: 5.1170 (5.1350) grad_norm: 1.9115 (1.7297) time: 0.5090 [2021-03-25 04:59:39 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 280/1251] eta: 0:08:26 lr: 0.000512 loss: 4.7381 (5.1266) grad_norm: 1.7515 (1.7328) time: 0.5074 [2021-03-25 04:59:44 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 290/1251] eta: 0:08:20 lr: 0.000512 loss: 4.9154 (5.1216) grad_norm: 1.6324 (1.7305) time: 0.5026 [2021-03-25 04:59:49 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 300/1251] eta: 0:08:15 lr: 0.000512 loss: 5.0570 (5.1160) grad_norm: 1.6126 (1.7331) time: 0.5032 [2021-03-25 04:59:54 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 310/1251] eta: 0:08:09 lr: 0.000513 loss: 5.2606 (5.1185) grad_norm: 1.6949 (1.7318) time: 0.5055 [2021-03-25 04:59:59 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 320/1251] eta: 0:08:03 lr: 0.000513 loss: 5.2860 (5.1193) grad_norm: 1.6446 (1.7303) time: 0.5014 [2021-03-25 05:00:04 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 330/1251] eta: 0:07:58 lr: 0.000514 loss: 5.2164 (5.1140) grad_norm: 1.6318 (1.7281) time: 0.5005 [2021-03-25 05:00:09 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 340/1251] eta: 0:07:52 lr: 0.000514 loss: 5.2203 (5.1197) grad_norm: 1.6651 (1.7295) time: 0.5045 [2021-03-25 05:00:14 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 350/1251] eta: 0:07:46 lr: 0.000514 loss: 5.0057 (5.1154) grad_norm: 1.6651 (1.7312) time: 0.5056 [2021-03-25 05:00:19 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 360/1251] eta: 0:07:41 lr: 0.000515 loss: 5.1916 (5.1218) grad_norm: 1.7418 (1.7334) time: 0.5041 [2021-03-25 05:00:24 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 370/1251] eta: 0:07:35 lr: 0.000515 loss: 5.3019 (5.1243) grad_norm: 1.8609 (1.7391) time: 0.5048 [2021-03-25 05:00:30 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 380/1251] eta: 0:07:30 lr: 0.000516 loss: 5.1267 (5.1236) grad_norm: 1.8681 (1.7401) time: 0.5029 [2021-03-25 05:00:35 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 390/1251] eta: 0:07:24 lr: 0.000516 loss: 5.3287 (5.1255) grad_norm: 1.8681 (1.7458) time: 0.5021 [2021-03-25 05:00:39 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 400/1251] eta: 0:07:19 lr: 0.000516 loss: 5.5158 (5.1304) grad_norm: 1.7615 (1.7459) time: 0.4985 [2021-03-25 05:00:45 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 410/1251] eta: 0:07:13 lr: 0.000517 loss: 5.2888 (5.1362) grad_norm: 1.7498 (1.7467) time: 0.5026 [2021-03-25 05:00:50 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 420/1251] eta: 0:07:08 lr: 0.000517 loss: 5.1491 (5.1311) grad_norm: 1.6722 (1.7439) time: 0.5164 [2021-03-25 05:00:55 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 430/1251] eta: 0:07:03 lr: 0.000518 loss: 4.9387 (5.1309) grad_norm: 1.5704 (1.7404) time: 0.5142 [2021-03-25 05:01:00 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 440/1251] eta: 0:06:58 lr: 0.000518 loss: 5.2494 (5.1300) grad_norm: 1.6614 (1.7468) time: 0.5131 [2021-03-25 05:01:05 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 450/1251] eta: 0:06:52 lr: 0.000518 loss: 5.2494 (5.1327) grad_norm: 1.7473 (1.7472) time: 0.5060 [2021-03-25 05:01:10 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 460/1251] eta: 0:06:47 lr: 0.000519 loss: 5.3176 (5.1336) grad_norm: 1.7473 (1.7552) time: 0.4968 [2021-03-25 05:01:15 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 470/1251] eta: 0:06:42 lr: 0.000519 loss: 5.0625 (5.1290) grad_norm: 1.8236 (1.7564) time: 0.5015 [2021-03-25 05:01:20 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 480/1251] eta: 0:06:36 lr: 0.000520 loss: 4.8836 (5.1216) grad_norm: 1.7176 (1.7557) time: 0.5009 [2021-03-25 05:01:25 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 490/1251] eta: 0:06:31 lr: 0.000520 loss: 4.8703 (5.1176) grad_norm: 1.6061 (1.7530) time: 0.5037 [2021-03-25 05:01:30 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 500/1251] eta: 0:06:26 lr: 0.000520 loss: 5.2775 (5.1208) grad_norm: 1.5297 (1.7469) time: 0.5114 [2021-03-25 05:01:35 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 510/1251] eta: 0:06:21 lr: 0.000521 loss: 5.4203 (5.1248) grad_norm: 1.5820 (1.7467) time: 0.5074 [2021-03-25 05:01:40 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 520/1251] eta: 0:06:15 lr: 0.000521 loss: 5.2708 (5.1237) grad_norm: 1.7712 (1.7506) time: 0.5031 [2021-03-25 05:01:45 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 530/1251] eta: 0:06:10 lr: 0.000522 loss: 5.2665 (5.1255) grad_norm: 1.6934 (1.7473) time: 0.5029 [2021-03-25 05:01:50 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 540/1251] eta: 0:06:05 lr: 0.000522 loss: 5.2953 (5.1268) grad_norm: 1.5825 (1.7471) time: 0.5006 [2021-03-25 05:01:56 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 550/1251] eta: 0:06:00 lr: 0.000522 loss: 5.0156 (5.1241) grad_norm: 1.7068 (1.7485) time: 0.5118 [2021-03-25 05:02:01 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 560/1251] eta: 0:05:54 lr: 0.000523 loss: 4.9805 (5.1214) grad_norm: 1.7068 (1.7465) time: 0.5108 [2021-03-25 05:02:06 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 570/1251] eta: 0:05:49 lr: 0.000523 loss: 5.0539 (5.1149) grad_norm: 1.5328 (1.7432) time: 0.4965 [2021-03-25 05:02:10 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 580/1251] eta: 0:05:44 lr: 0.000524 loss: 5.1474 (5.1158) grad_norm: 1.5195 (1.7394) time: 0.4957 [2021-03-25 05:02:15 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 590/1251] eta: 0:05:38 lr: 0.000524 loss: 5.4436 (5.1166) grad_norm: 1.5514 (1.7404) time: 0.4971 [2021-03-25 05:02:21 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 600/1251] eta: 0:05:33 lr: 0.000524 loss: 5.2472 (5.1176) grad_norm: 1.5931 (1.7398) time: 0.5009 [2021-03-25 05:02:26 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 610/1251] eta: 0:05:28 lr: 0.000525 loss: 5.0153 (5.1119) grad_norm: 1.5094 (1.7353) time: 0.5042 [2021-03-25 05:02:31 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 620/1251] eta: 0:05:23 lr: 0.000525 loss: 4.8249 (5.1114) grad_norm: 1.4852 (1.7316) time: 0.5030 [2021-03-25 05:02:36 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 630/1251] eta: 0:05:17 lr: 0.000526 loss: 5.0817 (5.1111) grad_norm: 1.5502 (1.7319) time: 0.5015 [2021-03-25 05:02:41 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 640/1251] eta: 0:05:12 lr: 0.000526 loss: 5.3965 (5.1148) grad_norm: 1.7070 (1.7342) time: 0.5116 [2021-03-25 05:02:46 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 650/1251] eta: 0:05:07 lr: 0.000526 loss: 5.3932 (5.1130) grad_norm: 1.6573 (1.7330) time: 0.5128 [2021-03-25 05:02:51 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 660/1251] eta: 0:05:02 lr: 0.000527 loss: 4.8469 (5.1086) grad_norm: 1.6573 (1.7337) time: 0.5012 [2021-03-25 05:02:56 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 670/1251] eta: 0:04:57 lr: 0.000527 loss: 5.1066 (5.1104) grad_norm: 1.6274 (1.7321) time: 0.5013 [2021-03-25 05:03:01 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 680/1251] eta: 0:04:52 lr: 0.000528 loss: 5.1094 (5.1077) grad_norm: 1.6038 (1.7320) time: 0.5024 [2021-03-25 05:03:06 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 690/1251] eta: 0:04:46 lr: 0.000528 loss: 5.1089 (5.1081) grad_norm: 1.7195 (1.7345) time: 0.5031 [2021-03-25 05:03:11 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 700/1251] eta: 0:04:41 lr: 0.000528 loss: 5.3828 (5.1103) grad_norm: 1.7594 (1.7329) time: 0.5064 [2021-03-25 05:03:16 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 710/1251] eta: 0:04:36 lr: 0.000529 loss: 5.3828 (5.1124) grad_norm: 1.6125 (1.7324) time: 0.5017 [2021-03-25 05:03:21 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 720/1251] eta: 0:04:31 lr: 0.000529 loss: 5.1691 (5.1119) grad_norm: 1.5749 (1.7300) time: 0.4968 [2021-03-25 05:03:26 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 730/1251] eta: 0:04:26 lr: 0.000530 loss: 4.9621 (5.1086) grad_norm: 1.5806 (1.7305) time: 0.5082 [2021-03-25 05:03:31 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 740/1251] eta: 0:04:21 lr: 0.000530 loss: 4.9048 (5.1047) grad_norm: 1.6550 (1.7293) time: 0.5197 [2021-03-25 05:03:36 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 750/1251] eta: 0:04:16 lr: 0.000530 loss: 4.8355 (5.1025) grad_norm: 1.5493 (1.7267) time: 0.5141 [2021-03-25 05:03:41 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 760/1251] eta: 0:04:10 lr: 0.000531 loss: 4.8300 (5.1001) grad_norm: 1.5353 (1.7259) time: 0.5039 [2021-03-25 05:03:47 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 770/1251] eta: 0:04:05 lr: 0.000531 loss: 4.7942 (5.0979) grad_norm: 1.7356 (1.7269) time: 0.5077 [2021-03-25 05:03:52 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 780/1251] eta: 0:04:00 lr: 0.000532 loss: 4.9406 (5.0998) grad_norm: 1.7203 (1.7279) time: 0.5123 [2021-03-25 05:03:57 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 790/1251] eta: 0:03:55 lr: 0.000532 loss: 5.1819 (5.0966) grad_norm: 1.5869 (1.7266) time: 0.5111 [2021-03-25 05:04:02 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 800/1251] eta: 0:03:50 lr: 0.000532 loss: 4.6419 (5.0915) grad_norm: 1.5719 (1.7250) time: 0.5053 [2021-03-25 05:04:07 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 810/1251] eta: 0:03:45 lr: 0.000533 loss: 4.6109 (5.0892) grad_norm: 1.7579 (1.7276) time: 0.5006 [2021-03-25 05:04:12 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 820/1251] eta: 0:03:40 lr: 0.000533 loss: 4.9515 (5.0886) grad_norm: 1.8503 (1.7295) time: 0.4992 [2021-03-25 05:04:17 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 830/1251] eta: 0:03:35 lr: 0.000534 loss: 4.9515 (5.0873) grad_norm: 1.9200 (1.7319) time: 0.5071 [2021-03-25 05:04:22 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 840/1251] eta: 0:03:29 lr: 0.000534 loss: 5.0920 (5.0879) grad_norm: 1.8705 (1.7326) time: 0.5074 [2021-03-25 05:04:27 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 850/1251] eta: 0:03:24 lr: 0.000534 loss: 4.9289 (5.0857) grad_norm: 1.7334 (1.7313) time: 0.4980 [2021-03-25 05:04:32 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 860/1251] eta: 0:03:19 lr: 0.000535 loss: 5.1883 (5.0878) grad_norm: 1.5663 (1.7299) time: 0.5045 [2021-03-25 05:04:37 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 870/1251] eta: 0:03:14 lr: 0.000535 loss: 5.3930 (5.0916) grad_norm: 1.5663 (1.7292) time: 0.5153 [2021-03-25 05:04:42 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 880/1251] eta: 0:03:09 lr: 0.000536 loss: 5.2371 (5.0910) grad_norm: 1.5994 (1.7282) time: 0.5112 [2021-03-25 05:04:47 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 890/1251] eta: 0:03:04 lr: 0.000536 loss: 4.7400 (5.0863) grad_norm: 1.6057 (1.7270) time: 0.5070 [2021-03-25 05:04:52 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 900/1251] eta: 0:02:59 lr: 0.000536 loss: 4.4408 (5.0806) grad_norm: 1.5776 (1.7264) time: 0.5091 [2021-03-25 05:04:58 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 910/1251] eta: 0:02:54 lr: 0.000537 loss: 4.7046 (5.0799) grad_norm: 1.6232 (1.7269) time: 0.5089 [2021-03-25 05:05:03 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 920/1251] eta: 0:02:48 lr: 0.000537 loss: 5.0935 (5.0798) grad_norm: 1.7652 (1.7275) time: 0.5148 [2021-03-25 05:05:08 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 930/1251] eta: 0:02:43 lr: 0.000538 loss: 5.3717 (5.0828) grad_norm: 1.5631 (1.7258) time: 0.5108 [2021-03-25 05:05:13 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 940/1251] eta: 0:02:38 lr: 0.000538 loss: 5.4194 (5.0833) grad_norm: 1.5505 (1.7261) time: 0.5054 [2021-03-25 05:05:18 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 950/1251] eta: 0:02:33 lr: 0.000538 loss: 5.0965 (5.0838) grad_norm: 1.6361 (1.7256) time: 0.5068 [2021-03-25 05:05:23 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 960/1251] eta: 0:02:28 lr: 0.000539 loss: 5.2323 (5.0849) grad_norm: 1.5681 (1.7241) time: 0.5080 [2021-03-25 05:05:28 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 970/1251] eta: 0:02:23 lr: 0.000539 loss: 5.2313 (5.0828) grad_norm: 1.5628 (1.7241) time: 0.5113 [2021-03-25 05:05:33 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 980/1251] eta: 0:02:18 lr: 0.000540 loss: 5.0037 (5.0822) grad_norm: 1.5628 (1.7220) time: 0.5089 [2021-03-25 05:05:38 swin_small_patch4_window7_224] INFO: Epoch: [10] [ 990/1251] eta: 0:02:13 lr: 0.000540 loss: 5.0794 (5.0816) grad_norm: 1.6068 (1.7224) time: 0.5113 [2021-03-25 05:05:44 swin_small_patch4_window7_224] INFO: Epoch: [10] [1000/1251] eta: 0:02:08 lr: 0.000540 loss: 4.9124 (5.0816) grad_norm: 1.7994 (1.7232) time: 0.5160 [2021-03-25 05:05:49 swin_small_patch4_window7_224] INFO: Epoch: [10] [1010/1251] eta: 0:02:02 lr: 0.000541 loss: 4.6463 (5.0764) grad_norm: 1.7363 (1.7235) time: 0.5095 [2021-03-25 05:05:54 swin_small_patch4_window7_224] INFO: Epoch: [10] [1020/1251] eta: 0:01:57 lr: 0.000541 loss: 4.8194 (5.0737) grad_norm: 1.5885 (1.7226) time: 0.5014 [2021-03-25 05:05:59 swin_small_patch4_window7_224] INFO: Epoch: [10] [1030/1251] eta: 0:01:52 lr: 0.000542 loss: 4.8922 (5.0720) grad_norm: 1.6179 (1.7230) time: 0.4984 [2021-03-25 05:06:04 swin_small_patch4_window7_224] INFO: Epoch: [10] [1040/1251] eta: 0:01:47 lr: 0.000542 loss: 5.0229 (5.0714) grad_norm: 1.6842 (1.7234) time: 0.5051 [2021-03-25 05:06:09 swin_small_patch4_window7_224] INFO: Epoch: [10] [1050/1251] eta: 0:01:42 lr: 0.000542 loss: 5.2291 (5.0710) grad_norm: 1.7491 (1.7260) time: 0.5085 [2021-03-25 05:06:14 swin_small_patch4_window7_224] INFO: Epoch: [10] [1060/1251] eta: 0:01:37 lr: 0.000543 loss: 4.8582 (5.0686) grad_norm: 1.7491 (1.7265) time: 0.5070 [2021-03-25 05:06:19 swin_small_patch4_window7_224] INFO: Epoch: [10] [1070/1251] eta: 0:01:32 lr: 0.000543 loss: 4.8582 (5.0668) grad_norm: 1.6942 (1.7260) time: 0.5052 [2021-03-25 05:06:24 swin_small_patch4_window7_224] INFO: Epoch: [10] [1080/1251] eta: 0:01:27 lr: 0.000544 loss: 5.0276 (5.0654) grad_norm: 1.5363 (1.7243) time: 0.5021 [2021-03-25 05:06:29 swin_small_patch4_window7_224] INFO: Epoch: [10] [1090/1251] eta: 0:01:22 lr: 0.000544 loss: 4.6530 (5.0618) grad_norm: 1.5278 (1.7235) time: 0.5033 [2021-03-25 05:06:34 swin_small_patch4_window7_224] INFO: Epoch: [10] [1100/1251] eta: 0:01:16 lr: 0.000544 loss: 4.9106 (5.0601) grad_norm: 1.6500 (1.7247) time: 0.5060 [2021-03-25 05:06:39 swin_small_patch4_window7_224] INFO: Epoch: [10] [1110/1251] eta: 0:01:11 lr: 0.000545 loss: 5.1632 (5.0598) grad_norm: 1.6314 (1.7234) time: 0.5128 [2021-03-25 05:06:44 swin_small_patch4_window7_224] INFO: Epoch: [10] [1120/1251] eta: 0:01:06 lr: 0.000545 loss: 5.1253 (5.0606) grad_norm: 1.5161 (1.7219) time: 0.5134 [2021-03-25 05:06:49 swin_small_patch4_window7_224] INFO: Epoch: [10] [1130/1251] eta: 0:01:01 lr: 0.000546 loss: 4.9882 (5.0566) grad_norm: 1.5877 (1.7216) time: 0.5094 [2021-03-25 05:06:54 swin_small_patch4_window7_224] INFO: Epoch: [10] [1140/1251] eta: 0:00:56 lr: 0.000546 loss: 4.5563 (5.0528) grad_norm: 1.6843 (1.7211) time: 0.5077 [2021-03-25 05:06:59 swin_small_patch4_window7_224] INFO: Epoch: [10] [1150/1251] eta: 0:00:51 lr: 0.000546 loss: 4.6402 (5.0503) grad_norm: 1.6477 (1.7196) time: 0.5082 [2021-03-25 05:07:05 swin_small_patch4_window7_224] INFO: Epoch: [10] [1160/1251] eta: 0:00:46 lr: 0.000547 loss: 5.1840 (5.0515) grad_norm: 1.6572 (1.7209) time: 0.5056 [2021-03-25 05:07:10 swin_small_patch4_window7_224] INFO: Epoch: [10] [1170/1251] eta: 0:00:41 lr: 0.000547 loss: 5.3118 (5.0525) grad_norm: 1.7556 (1.7227) time: 0.5117 [2021-03-25 05:07:15 swin_small_patch4_window7_224] INFO: Epoch: [10] [1180/1251] eta: 0:00:36 lr: 0.000548 loss: 5.2408 (5.0509) grad_norm: 1.6374 (1.7211) time: 0.5201 [2021-03-25 05:07:20 swin_small_patch4_window7_224] INFO: Epoch: [10] [1190/1251] eta: 0:00:31 lr: 0.000548 loss: 5.0059 (5.0502) grad_norm: 1.4535 (1.7192) time: 0.5077 [2021-03-25 05:07:25 swin_small_patch4_window7_224] INFO: Epoch: [10] [1200/1251] eta: 0:00:26 lr: 0.000548 loss: 5.1440 (5.0508) grad_norm: 1.4909 (1.7181) time: 0.5009 [2021-03-25 05:07:30 swin_small_patch4_window7_224] INFO: Epoch: [10] [1210/1251] eta: 0:00:20 lr: 0.000549 loss: 4.9690 (5.0505) grad_norm: 1.5182 (1.7172) time: 0.5048 [2021-03-25 05:07:35 swin_small_patch4_window7_224] INFO: Epoch: [10] [1220/1251] eta: 0:00:15 lr: 0.000549 loss: 4.9690 (5.0495) grad_norm: 1.5628 (1.7174) time: 0.5070 [2021-03-25 05:07:40 swin_small_patch4_window7_224] INFO: Epoch: [10] [1230/1251] eta: 0:00:10 lr: 0.000550 loss: 4.9745 (5.0488) grad_norm: 1.8300 (1.7180) time: 0.5029 [2021-03-25 05:07:45 swin_small_patch4_window7_224] INFO: Epoch: [10] [1240/1251] eta: 0:00:05 lr: 0.000550 loss: 5.1008 (5.0503) grad_norm: 1.5380 (1.7165) time: 0.5037 [2021-03-25 05:07:50 swin_small_patch4_window7_224] INFO: Epoch: [10] [1250/1251] eta: 0:00:00 lr: 0.000550 loss: 5.1184 (5.0503) grad_norm: 1.5242 (1.7159) time: 0.5088 [2021-03-25 05:08:31 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 2.7582 (2.7582) acc1: 40.6250 (40.6250) acc5: 68.7500 (68.7500) [2021-03-25 05:08:32 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 2.3659 (2.4179) acc1: 50.0000 (49.8580) acc5: 73.4375 (72.7273) [2021-03-25 05:08:33 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 2.3659 (2.4418) acc1: 48.4375 (47.9167) acc5: 71.8750 (72.4702) [2021-03-25 05:08:34 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 2.4324 (2.4293) acc1: 46.8750 (47.7823) acc5: 70.3125 (72.3790) [2021-03-25 05:08:35 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 2.4403 (2.4570) acc1: 46.8750 (47.2942) acc5: 70.3125 (71.9131) [2021-03-25 05:08:36 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.4730 (2.4781) acc1: 43.7500 (46.4320) acc5: 70.3125 (71.9360) [2021-03-25 05:08:37 swin_small_patch4_window7_224] INFO: * Acc@1 46.848 Acc@5 72.610 loss 2.456 [2021-03-25 05:08:37 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 46.8% [2021-03-25 05:08:37 swin_small_patch4_window7_224] INFO: Max accuracy: 46.85% [2021-03-25 05:08:42 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 0/1251] eta: 1:28:06 lr: 0.000550 loss: 5.3533 (5.3533) grad_norm: 3.0287 (3.0287) time: 4.2258 [2021-03-25 05:08:47 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 10/1251] eta: 0:17:35 lr: 0.000551 loss: 4.7822 (5.0129) grad_norm: 1.4831 (1.6897) time: 0.8509 [2021-03-25 05:08:52 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 20/1251] eta: 0:14:14 lr: 0.000551 loss: 5.2867 (5.1830) grad_norm: 1.4825 (1.6353) time: 0.5176 [2021-03-25 05:08:57 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 30/1251] eta: 0:12:50 lr: 0.000552 loss: 5.2030 (5.0547) grad_norm: 1.6178 (1.6812) time: 0.5104 [2021-03-25 05:09:02 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 40/1251] eta: 0:12:08 lr: 0.000552 loss: 4.8714 (5.0166) grad_norm: 1.6823 (1.7068) time: 0.5042 [2021-03-25 05:09:07 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 50/1251] eta: 0:11:41 lr: 0.000552 loss: 4.8714 (4.9553) grad_norm: 1.6297 (1.7434) time: 0.5112 [2021-03-25 05:09:12 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 60/1251] eta: 0:11:20 lr: 0.000553 loss: 4.9537 (4.9409) grad_norm: 1.6269 (1.7287) time: 0.5106 [2021-03-25 05:09:18 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 70/1251] eta: 0:11:06 lr: 0.000553 loss: 5.0487 (4.9299) grad_norm: 1.5801 (1.7114) time: 0.5135 [2021-03-25 05:09:23 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 80/1251] eta: 0:10:52 lr: 0.000554 loss: 5.2340 (4.9733) grad_norm: 1.6220 (1.6998) time: 0.5141 [2021-03-25 05:09:28 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 90/1251] eta: 0:10:40 lr: 0.000554 loss: 4.9976 (4.9609) grad_norm: 1.6616 (1.7111) time: 0.5084 [2021-03-25 05:09:33 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 100/1251] eta: 0:10:30 lr: 0.000554 loss: 4.9930 (4.9712) grad_norm: 1.7032 (1.7197) time: 0.5072 [2021-03-25 05:09:38 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 110/1251] eta: 0:10:21 lr: 0.000555 loss: 5.0413 (4.9783) grad_norm: 1.6470 (1.7148) time: 0.5099 [2021-03-25 05:09:43 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 120/1251] eta: 0:10:12 lr: 0.000555 loss: 4.9182 (4.9640) grad_norm: 1.6014 (1.7167) time: 0.5113 [2021-03-25 05:09:48 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 130/1251] eta: 0:10:05 lr: 0.000556 loss: 5.2342 (4.9768) grad_norm: 1.5743 (1.7255) time: 0.5172 [2021-03-25 05:09:53 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 140/1251] eta: 0:09:58 lr: 0.000556 loss: 5.1959 (4.9721) grad_norm: 1.6038 (1.7207) time: 0.5199 [2021-03-25 05:09:58 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 150/1251] eta: 0:09:50 lr: 0.000556 loss: 5.0770 (4.9783) grad_norm: 1.5957 (1.7201) time: 0.5096 [2021-03-25 05:10:04 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 160/1251] eta: 0:09:42 lr: 0.000557 loss: 4.9528 (4.9566) grad_norm: 1.5957 (1.7281) time: 0.5053 [2021-03-25 05:10:09 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 170/1251] eta: 0:09:35 lr: 0.000557 loss: 4.8882 (4.9517) grad_norm: 1.6092 (1.7278) time: 0.5056 [2021-03-25 05:10:14 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 180/1251] eta: 0:09:28 lr: 0.000558 loss: 4.9095 (4.9496) grad_norm: 1.6381 (1.7247) time: 0.5019 [2021-03-25 05:10:19 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 190/1251] eta: 0:09:21 lr: 0.000558 loss: 4.9426 (4.9357) grad_norm: 1.5582 (1.7184) time: 0.4995 [2021-03-25 05:10:24 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 200/1251] eta: 0:09:15 lr: 0.000558 loss: 4.9426 (4.9345) grad_norm: 1.4832 (1.7134) time: 0.5071 [2021-03-25 05:10:29 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 210/1251] eta: 0:09:09 lr: 0.000559 loss: 4.9730 (4.9352) grad_norm: 1.5569 (inf) time: 0.5113 [2021-03-25 05:10:34 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 220/1251] eta: 0:09:02 lr: 0.000559 loss: 5.1488 (4.9339) grad_norm: 1.5571 (inf) time: 0.5065 [2021-03-25 05:10:39 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 230/1251] eta: 0:08:56 lr: 0.000560 loss: 5.2112 (4.9485) grad_norm: 1.5567 (inf) time: 0.5034 [2021-03-25 05:10:44 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 240/1251] eta: 0:08:50 lr: 0.000560 loss: 5.2980 (4.9592) grad_norm: 1.4866 (inf) time: 0.5043 [2021-03-25 05:10:49 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 250/1251] eta: 0:08:44 lr: 0.000560 loss: 5.2593 (4.9689) grad_norm: 1.6328 (inf) time: 0.5072 [2021-03-25 05:10:54 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 260/1251] eta: 0:08:38 lr: 0.000561 loss: 5.0898 (4.9672) grad_norm: 1.5754 (inf) time: 0.5090 [2021-03-25 05:10:59 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 270/1251] eta: 0:08:32 lr: 0.000561 loss: 4.9246 (4.9661) grad_norm: 1.6312 (inf) time: 0.5074 [2021-03-25 05:11:04 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 280/1251] eta: 0:08:26 lr: 0.000562 loss: 4.9822 (4.9640) grad_norm: 1.6544 (inf) time: 0.5039 [2021-03-25 05:11:09 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 290/1251] eta: 0:08:21 lr: 0.000562 loss: 5.1406 (4.9691) grad_norm: 1.8407 (inf) time: 0.5038 [2021-03-25 05:11:14 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 300/1251] eta: 0:08:15 lr: 0.000562 loss: 4.8755 (4.9654) grad_norm: 1.6077 (inf) time: 0.5119 [2021-03-25 05:11:19 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 310/1251] eta: 0:08:09 lr: 0.000563 loss: 5.0067 (4.9759) grad_norm: 1.5422 (inf) time: 0.5071 [2021-03-25 05:11:24 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 320/1251] eta: 0:08:03 lr: 0.000563 loss: 5.1361 (4.9820) grad_norm: 1.5373 (inf) time: 0.4974 [2021-03-25 05:11:29 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 330/1251] eta: 0:07:58 lr: 0.000564 loss: 5.0492 (4.9858) grad_norm: 1.4474 (inf) time: 0.5022 [2021-03-25 05:11:34 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 340/1251] eta: 0:07:52 lr: 0.000564 loss: 5.1542 (4.9885) grad_norm: 1.5308 (inf) time: 0.5008 [2021-03-25 05:11:39 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 350/1251] eta: 0:07:47 lr: 0.000564 loss: 4.5315 (4.9773) grad_norm: 1.6282 (inf) time: 0.5026 [2021-03-25 05:11:45 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 360/1251] eta: 0:07:41 lr: 0.000565 loss: 4.5386 (4.9756) grad_norm: 1.6282 (inf) time: 0.5103 [2021-03-25 05:11:50 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 370/1251] eta: 0:07:36 lr: 0.000565 loss: 4.9841 (4.9803) grad_norm: 1.6703 (inf) time: 0.5093 [2021-03-25 05:11:55 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 380/1251] eta: 0:07:30 lr: 0.000566 loss: 5.0581 (4.9809) grad_norm: 1.6240 (inf) time: 0.5018 [2021-03-25 05:12:00 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 390/1251] eta: 0:07:25 lr: 0.000566 loss: 5.1543 (4.9846) grad_norm: 1.4959 (inf) time: 0.5026 [2021-03-25 05:12:05 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 400/1251] eta: 0:07:19 lr: 0.000566 loss: 5.1128 (4.9833) grad_norm: 1.5525 (inf) time: 0.5064 [2021-03-25 05:12:10 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 410/1251] eta: 0:07:14 lr: 0.000567 loss: 4.9398 (4.9816) grad_norm: 1.5525 (inf) time: 0.5057 [2021-03-25 05:12:15 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 420/1251] eta: 0:07:09 lr: 0.000567 loss: 4.8611 (4.9772) grad_norm: 1.5088 (inf) time: 0.5080 [2021-03-25 05:12:20 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 430/1251] eta: 0:07:03 lr: 0.000568 loss: 5.1679 (4.9833) grad_norm: 1.4576 (inf) time: 0.5078 [2021-03-25 05:12:25 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 440/1251] eta: 0:06:58 lr: 0.000568 loss: 5.1017 (4.9854) grad_norm: 1.4130 (inf) time: 0.5059 [2021-03-25 05:12:30 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 450/1251] eta: 0:06:52 lr: 0.000568 loss: 4.9220 (4.9791) grad_norm: 1.5536 (inf) time: 0.5006 [2021-03-25 05:12:35 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 460/1251] eta: 0:06:47 lr: 0.000569 loss: 4.9220 (4.9767) grad_norm: 1.5594 (inf) time: 0.5007 [2021-03-25 05:12:40 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 470/1251] eta: 0:06:42 lr: 0.000569 loss: 5.0327 (4.9732) grad_norm: 1.5616 (inf) time: 0.5033 [2021-03-25 05:12:45 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 480/1251] eta: 0:06:36 lr: 0.000570 loss: 5.0842 (4.9757) grad_norm: 1.5740 (inf) time: 0.5019 [2021-03-25 05:12:50 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 490/1251] eta: 0:06:31 lr: 0.000570 loss: 5.1063 (4.9784) grad_norm: 1.6809 (inf) time: 0.5058 [2021-03-25 05:12:55 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 500/1251] eta: 0:06:26 lr: 0.000570 loss: 5.0538 (4.9753) grad_norm: 1.5471 (inf) time: 0.5035 [2021-03-25 05:13:00 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 510/1251] eta: 0:06:20 lr: 0.000571 loss: 4.8631 (4.9739) grad_norm: 1.4703 (inf) time: 0.5033 [2021-03-25 05:13:05 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 520/1251] eta: 0:06:15 lr: 0.000571 loss: 4.7502 (4.9721) grad_norm: 1.4225 (inf) time: 0.5051 [2021-03-25 05:13:10 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 530/1251] eta: 0:06:10 lr: 0.000572 loss: 4.9723 (4.9748) grad_norm: 1.4313 (inf) time: 0.5070 [2021-03-25 05:13:16 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 540/1251] eta: 0:06:05 lr: 0.000572 loss: 4.9311 (4.9741) grad_norm: 1.6398 (inf) time: 0.5111 [2021-03-25 05:13:21 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 550/1251] eta: 0:06:00 lr: 0.000572 loss: 4.7104 (4.9687) grad_norm: 1.5181 (inf) time: 0.5242 [2021-03-25 05:13:26 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 560/1251] eta: 0:05:55 lr: 0.000573 loss: 5.0890 (4.9734) grad_norm: 1.5316 (inf) time: 0.5246 [2021-03-25 05:13:31 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 570/1251] eta: 0:05:50 lr: 0.000573 loss: 5.1466 (4.9732) grad_norm: 1.5620 (inf) time: 0.5088 [2021-03-25 05:13:36 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 580/1251] eta: 0:05:44 lr: 0.000574 loss: 5.0154 (4.9728) grad_norm: 1.5314 (inf) time: 0.5047 [2021-03-25 05:13:41 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 590/1251] eta: 0:05:39 lr: 0.000574 loss: 5.0154 (4.9721) grad_norm: 1.5115 (inf) time: 0.5016 [2021-03-25 05:13:46 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 600/1251] eta: 0:05:34 lr: 0.000574 loss: 5.0346 (4.9706) grad_norm: 1.5905 (inf) time: 0.5005 [2021-03-25 05:13:51 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 610/1251] eta: 0:05:29 lr: 0.000575 loss: 5.1839 (4.9731) grad_norm: 1.6258 (inf) time: 0.5028 [2021-03-25 05:13:56 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 620/1251] eta: 0:05:23 lr: 0.000575 loss: 5.1839 (4.9756) grad_norm: 1.5123 (inf) time: 0.5044 [2021-03-25 05:14:01 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 630/1251] eta: 0:05:18 lr: 0.000576 loss: 5.2514 (4.9769) grad_norm: 1.5123 (inf) time: 0.4997 [2021-03-25 05:14:06 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 640/1251] eta: 0:05:13 lr: 0.000576 loss: 5.3263 (4.9820) grad_norm: 1.5398 (inf) time: 0.5026 [2021-03-25 05:14:11 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 650/1251] eta: 0:05:08 lr: 0.000576 loss: 5.1797 (4.9839) grad_norm: 1.5393 (inf) time: 0.5082 [2021-03-25 05:14:16 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 660/1251] eta: 0:05:02 lr: 0.000577 loss: 5.0689 (4.9811) grad_norm: 1.4814 (inf) time: 0.5045 [2021-03-25 05:14:21 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 670/1251] eta: 0:04:57 lr: 0.000577 loss: 5.0689 (4.9853) grad_norm: 1.5052 (inf) time: 0.5023 [2021-03-25 05:14:27 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 680/1251] eta: 0:04:52 lr: 0.000578 loss: 5.0816 (4.9851) grad_norm: 1.5052 (inf) time: 0.5104 [2021-03-25 05:14:32 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 690/1251] eta: 0:04:47 lr: 0.000578 loss: 5.0816 (4.9866) grad_norm: 1.5938 (inf) time: 0.5086 [2021-03-25 05:14:37 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 700/1251] eta: 0:04:42 lr: 0.000578 loss: 5.1100 (4.9868) grad_norm: 1.6028 (inf) time: 0.5056 [2021-03-25 05:14:42 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 710/1251] eta: 0:04:37 lr: 0.000579 loss: 5.1640 (4.9906) grad_norm: 1.5783 (inf) time: 0.5039 [2021-03-25 05:14:47 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 720/1251] eta: 0:04:31 lr: 0.000579 loss: 5.0701 (4.9892) grad_norm: 1.6195 (inf) time: 0.5026 [2021-03-25 05:14:52 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 730/1251] eta: 0:04:26 lr: 0.000580 loss: 5.1688 (4.9936) grad_norm: 1.5784 (inf) time: 0.5106 [2021-03-25 05:14:57 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 740/1251] eta: 0:04:21 lr: 0.000580 loss: 5.0658 (4.9912) grad_norm: 1.4414 (inf) time: 0.5249 [2021-03-25 05:15:02 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 750/1251] eta: 0:04:16 lr: 0.000580 loss: 4.9455 (4.9883) grad_norm: 1.4342 (inf) time: 0.5241 [2021-03-25 05:15:08 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 760/1251] eta: 0:04:11 lr: 0.000581 loss: 5.0364 (4.9905) grad_norm: 1.4628 (inf) time: 0.5154 [2021-03-25 05:15:13 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 770/1251] eta: 0:04:06 lr: 0.000581 loss: 5.0364 (4.9901) grad_norm: 1.4356 (inf) time: 0.5174 [2021-03-25 05:15:18 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 780/1251] eta: 0:04:01 lr: 0.000582 loss: 4.9717 (4.9878) grad_norm: 1.4266 (inf) time: 0.5116 [2021-03-25 05:15:23 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 790/1251] eta: 0:03:56 lr: 0.000582 loss: 4.9880 (4.9891) grad_norm: 1.4772 (inf) time: 0.5050 [2021-03-25 05:15:28 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 800/1251] eta: 0:03:51 lr: 0.000582 loss: 5.0264 (4.9894) grad_norm: 1.5959 (inf) time: 0.5048 [2021-03-25 05:15:33 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 810/1251] eta: 0:03:45 lr: 0.000583 loss: 4.9942 (4.9871) grad_norm: 1.5341 (inf) time: 0.5073 [2021-03-25 05:15:38 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 820/1251] eta: 0:03:40 lr: 0.000583 loss: 5.0357 (4.9879) grad_norm: 1.5219 (inf) time: 0.5069 [2021-03-25 05:15:43 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 830/1251] eta: 0:03:35 lr: 0.000584 loss: 5.1783 (4.9884) grad_norm: 1.5219 (inf) time: 0.5058 [2021-03-25 05:15:48 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 840/1251] eta: 0:03:30 lr: 0.000584 loss: 5.2392 (4.9891) grad_norm: 1.4657 (inf) time: 0.5028 [2021-03-25 05:15:53 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 850/1251] eta: 0:03:25 lr: 0.000584 loss: 5.2678 (4.9924) grad_norm: 1.4597 (inf) time: 0.5069 [2021-03-25 05:15:58 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 860/1251] eta: 0:03:20 lr: 0.000585 loss: 5.2513 (4.9947) grad_norm: 1.4671 (inf) time: 0.5041 [2021-03-25 05:16:03 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 870/1251] eta: 0:03:14 lr: 0.000585 loss: 5.1554 (4.9952) grad_norm: 1.5462 (inf) time: 0.5066 [2021-03-25 05:16:08 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 880/1251] eta: 0:03:09 lr: 0.000586 loss: 4.9396 (4.9908) grad_norm: 1.6292 (inf) time: 0.5150 [2021-03-25 05:16:14 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 890/1251] eta: 0:03:04 lr: 0.000586 loss: 4.8336 (4.9879) grad_norm: 1.5708 (inf) time: 0.5098 [2021-03-25 05:16:19 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 900/1251] eta: 0:02:59 lr: 0.000586 loss: 5.1057 (4.9890) grad_norm: 1.5708 (inf) time: 0.5019 [2021-03-25 05:16:24 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 910/1251] eta: 0:02:54 lr: 0.000587 loss: 5.1569 (4.9884) grad_norm: 1.3803 (inf) time: 0.4989 [2021-03-25 05:16:29 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 920/1251] eta: 0:02:49 lr: 0.000587 loss: 4.9072 (4.9866) grad_norm: 1.4294 (inf) time: 0.5019 [2021-03-25 05:16:34 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 930/1251] eta: 0:02:44 lr: 0.000588 loss: 4.7530 (4.9831) grad_norm: 1.5647 (inf) time: 0.5040 [2021-03-25 05:16:39 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 940/1251] eta: 0:02:38 lr: 0.000588 loss: 4.5213 (4.9785) grad_norm: 1.5449 (inf) time: 0.5046 [2021-03-25 05:16:44 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 950/1251] eta: 0:02:33 lr: 0.000588 loss: 4.7565 (4.9778) grad_norm: 1.4627 (inf) time: 0.5093 [2021-03-25 05:16:49 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 960/1251] eta: 0:02:28 lr: 0.000589 loss: 4.7740 (4.9754) grad_norm: 1.4814 (inf) time: 0.5097 [2021-03-25 05:16:54 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 970/1251] eta: 0:02:23 lr: 0.000589 loss: 5.0224 (4.9747) grad_norm: 1.5432 (inf) time: 0.5022 [2021-03-25 05:16:59 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 980/1251] eta: 0:02:18 lr: 0.000590 loss: 5.0299 (4.9741) grad_norm: 1.5176 (inf) time: 0.4995 [2021-03-25 05:17:04 swin_small_patch4_window7_224] INFO: Epoch: [11] [ 990/1251] eta: 0:02:13 lr: 0.000590 loss: 4.9194 (4.9739) grad_norm: 1.4961 (inf) time: 0.5064 [2021-03-25 05:17:09 swin_small_patch4_window7_224] INFO: Epoch: [11] [1000/1251] eta: 0:02:08 lr: 0.000590 loss: 4.8570 (4.9708) grad_norm: 1.4290 (inf) time: 0.5096 [2021-03-25 05:17:14 swin_small_patch4_window7_224] INFO: Epoch: [11] [1010/1251] eta: 0:02:03 lr: 0.000591 loss: 4.4368 (4.9672) grad_norm: 1.4549 (inf) time: 0.5153 [2021-03-25 05:17:19 swin_small_patch4_window7_224] INFO: Epoch: [11] [1020/1251] eta: 0:01:58 lr: 0.000591 loss: 4.8147 (4.9661) grad_norm: 1.5620 (inf) time: 0.5153 [2021-03-25 05:17:24 swin_small_patch4_window7_224] INFO: Epoch: [11] [1030/1251] eta: 0:01:52 lr: 0.000592 loss: 4.9327 (4.9680) grad_norm: 1.6082 (inf) time: 0.5086 [2021-03-25 05:17:30 swin_small_patch4_window7_224] INFO: Epoch: [11] [1040/1251] eta: 0:01:47 lr: 0.000592 loss: 5.1002 (4.9693) grad_norm: 1.6589 (inf) time: 0.5088 [2021-03-25 05:17:35 swin_small_patch4_window7_224] INFO: Epoch: [11] [1050/1251] eta: 0:01:42 lr: 0.000592 loss: 4.8908 (4.9674) grad_norm: 1.5884 (inf) time: 0.5103 [2021-03-25 05:17:40 swin_small_patch4_window7_224] INFO: Epoch: [11] [1060/1251] eta: 0:01:37 lr: 0.000593 loss: 4.8574 (4.9662) grad_norm: 1.5675 (inf) time: 0.5053 [2021-03-25 05:17:45 swin_small_patch4_window7_224] INFO: Epoch: [11] [1070/1251] eta: 0:01:32 lr: 0.000593 loss: 4.9350 (4.9652) grad_norm: 1.4714 (inf) time: 0.4975 [2021-03-25 05:17:50 swin_small_patch4_window7_224] INFO: Epoch: [11] [1080/1251] eta: 0:01:27 lr: 0.000594 loss: 5.1213 (4.9662) grad_norm: 1.5506 (inf) time: 0.5035 [2021-03-25 05:17:55 swin_small_patch4_window7_224] INFO: Epoch: [11] [1090/1251] eta: 0:01:22 lr: 0.000594 loss: 5.0883 (4.9658) grad_norm: 1.5560 (inf) time: 0.5100 [2021-03-25 05:18:00 swin_small_patch4_window7_224] INFO: Epoch: [11] [1100/1251] eta: 0:01:17 lr: 0.000594 loss: 4.8986 (4.9652) grad_norm: 1.5429 (inf) time: 0.5048 [2021-03-25 05:18:05 swin_small_patch4_window7_224] INFO: Epoch: [11] [1110/1251] eta: 0:01:11 lr: 0.000595 loss: 4.8294 (4.9658) grad_norm: 1.5572 (inf) time: 0.5034 [2021-03-25 05:18:10 swin_small_patch4_window7_224] INFO: Epoch: [11] [1120/1251] eta: 0:01:06 lr: 0.000595 loss: 5.1108 (4.9664) grad_norm: 1.5870 (inf) time: 0.5021 [2021-03-25 05:18:15 swin_small_patch4_window7_224] INFO: Epoch: [11] [1130/1251] eta: 0:01:01 lr: 0.000596 loss: 5.1346 (4.9665) grad_norm: 1.5870 (inf) time: 0.5039 [2021-03-25 05:18:20 swin_small_patch4_window7_224] INFO: Epoch: [11] [1140/1251] eta: 0:00:56 lr: 0.000596 loss: 4.8850 (4.9640) grad_norm: 1.6227 (inf) time: 0.5075 [2021-03-25 05:18:25 swin_small_patch4_window7_224] INFO: Epoch: [11] [1150/1251] eta: 0:00:51 lr: 0.000596 loss: 4.9915 (4.9647) grad_norm: 1.4967 (inf) time: 0.5057 [2021-03-25 05:18:30 swin_small_patch4_window7_224] INFO: Epoch: [11] [1160/1251] eta: 0:00:46 lr: 0.000597 loss: 5.2338 (4.9657) grad_norm: 1.4367 (inf) time: 0.5072 [2021-03-25 05:18:35 swin_small_patch4_window7_224] INFO: Epoch: [11] [1170/1251] eta: 0:00:41 lr: 0.000597 loss: 4.8860 (4.9632) grad_norm: 1.5630 (inf) time: 0.5065 [2021-03-25 05:18:40 swin_small_patch4_window7_224] INFO: Epoch: [11] [1180/1251] eta: 0:00:36 lr: 0.000598 loss: 4.8350 (4.9640) grad_norm: 1.6401 (inf) time: 0.5023 [2021-03-25 05:18:45 swin_small_patch4_window7_224] INFO: Epoch: [11] [1190/1251] eta: 0:00:31 lr: 0.000598 loss: 5.0206 (4.9641) grad_norm: 1.6087 (inf) time: 0.4991 [2021-03-25 05:18:50 swin_small_patch4_window7_224] INFO: Epoch: [11] [1200/1251] eta: 0:00:26 lr: 0.000598 loss: 4.9781 (4.9634) grad_norm: 1.4237 (inf) time: 0.4986 [2021-03-25 05:18:55 swin_small_patch4_window7_224] INFO: Epoch: [11] [1210/1251] eta: 0:00:20 lr: 0.000599 loss: 4.7927 (4.9611) grad_norm: 1.5114 (inf) time: 0.5058 [2021-03-25 05:19:00 swin_small_patch4_window7_224] INFO: Epoch: [11] [1220/1251] eta: 0:00:15 lr: 0.000599 loss: 4.7927 (4.9602) grad_norm: 1.5248 (inf) time: 0.5101 [2021-03-25 05:19:05 swin_small_patch4_window7_224] INFO: Epoch: [11] [1230/1251] eta: 0:00:10 lr: 0.000600 loss: 4.9203 (4.9585) grad_norm: 1.4873 (inf) time: 0.5062 [2021-03-25 05:19:10 swin_small_patch4_window7_224] INFO: Epoch: [11] [1240/1251] eta: 0:00:05 lr: 0.000600 loss: 5.0305 (4.9592) grad_norm: 1.3715 (inf) time: 0.5023 [2021-03-25 05:19:15 swin_small_patch4_window7_224] INFO: Epoch: [11] [1250/1251] eta: 0:00:00 lr: 0.000600 loss: 5.1222 (4.9583) grad_norm: 1.4430 (inf) time: 0.4924 [2021-03-25 05:19:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:44 loss: 2.8216 (2.8216) acc1: 39.0625 (39.0625) acc5: 62.5000 (62.5000) [2021-03-25 05:19:22 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 2.4128 (2.2742) acc1: 46.8750 (48.8636) acc5: 75.0000 (75.8523) [2021-03-25 05:19:24 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 2.3213 (2.2544) acc1: 46.8750 (48.6607) acc5: 76.5625 (76.8601) [2021-03-25 05:19:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.2200 (2.2318) acc1: 51.5625 (50.2520) acc5: 78.1250 (77.5706) [2021-03-25 05:19:27 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.2653 (2.2905) acc1: 53.1250 (49.3902) acc5: 75.0000 (76.2576) [2021-03-25 05:19:28 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.3113 (2.3085) acc1: 50.0000 (49.1840) acc5: 73.4375 (75.7440) [2021-03-25 05:19:31 swin_small_patch4_window7_224] INFO: * Acc@1 49.728 Acc@5 75.190 loss 2.313 [2021-03-25 05:19:31 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 49.7% [2021-03-25 05:19:31 swin_small_patch4_window7_224] INFO: Max accuracy: 49.73% [2021-03-25 05:19:35 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 0/1251] eta: 1:26:12 lr: 0.000600 loss: 5.6529 (5.6529) grad_norm: 1.6138 (1.6138) time: 4.1344 [2021-03-25 05:19:40 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 10/1251] eta: 0:17:48 lr: 0.000601 loss: 4.9585 (4.9346) grad_norm: 1.4989 (1.5427) time: 0.8610 [2021-03-25 05:19:45 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 20/1251] eta: 0:14:09 lr: 0.000601 loss: 4.9357 (4.8300) grad_norm: 1.4989 (1.5914) time: 0.5181 [2021-03-25 05:19:50 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 30/1251] eta: 0:12:48 lr: 0.000602 loss: 5.0203 (4.8591) grad_norm: 1.5166 (1.5582) time: 0.5019 [2021-03-25 05:19:56 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 40/1251] eta: 0:12:10 lr: 0.000602 loss: 4.9539 (4.8191) grad_norm: 1.5177 (1.5747) time: 0.5110 [2021-03-25 05:20:01 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 50/1251] eta: 0:11:42 lr: 0.000602 loss: 4.8598 (4.8065) grad_norm: 1.5357 (1.6098) time: 0.5164 [2021-03-25 05:20:06 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 60/1251] eta: 0:11:25 lr: 0.000603 loss: 4.7100 (4.7784) grad_norm: 1.4295 (1.5927) time: 0.5201 [2021-03-25 05:20:11 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 70/1251] eta: 0:11:07 lr: 0.000603 loss: 4.8892 (4.8186) grad_norm: 1.4040 (1.5761) time: 0.5155 [2021-03-25 05:20:16 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 80/1251] eta: 0:10:54 lr: 0.000604 loss: 4.9532 (4.8237) grad_norm: 1.4414 (1.5741) time: 0.5091 [2021-03-25 05:20:21 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 90/1251] eta: 0:10:42 lr: 0.000604 loss: 4.9481 (4.8178) grad_norm: 1.5328 (1.5655) time: 0.5112 [2021-03-25 05:20:26 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 100/1251] eta: 0:10:31 lr: 0.000604 loss: 4.8696 (4.8187) grad_norm: 1.4981 (1.5583) time: 0.5039 [2021-03-25 05:20:31 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 110/1251] eta: 0:10:22 lr: 0.000605 loss: 5.0409 (4.8300) grad_norm: 1.4849 (1.5492) time: 0.5093 [2021-03-25 05:20:37 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 120/1251] eta: 0:10:13 lr: 0.000605 loss: 5.0225 (4.8188) grad_norm: 1.4922 (1.6001) time: 0.5110 [2021-03-25 05:20:42 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 130/1251] eta: 0:10:04 lr: 0.000606 loss: 4.6673 (4.8270) grad_norm: 1.6392 (1.6094) time: 0.5036 [2021-03-25 05:20:47 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 140/1251] eta: 0:09:57 lr: 0.000606 loss: 5.2894 (4.8613) grad_norm: 1.5640 (1.5950) time: 0.5105 [2021-03-25 05:20:52 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 150/1251] eta: 0:09:50 lr: 0.000606 loss: 5.0852 (4.8645) grad_norm: 1.4284 (1.5924) time: 0.5168 [2021-03-25 05:20:57 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 160/1251] eta: 0:09:42 lr: 0.000607 loss: 4.9084 (4.8652) grad_norm: 1.5038 (1.5896) time: 0.5093 [2021-03-25 05:21:02 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 170/1251] eta: 0:09:35 lr: 0.000607 loss: 4.8851 (4.8743) grad_norm: 1.5159 (1.5988) time: 0.5038 [2021-03-25 05:21:07 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 180/1251] eta: 0:09:28 lr: 0.000608 loss: 4.8851 (4.8665) grad_norm: 1.5113 (1.5926) time: 0.5068 [2021-03-25 05:21:12 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 190/1251] eta: 0:09:22 lr: 0.000608 loss: 4.7727 (4.8692) grad_norm: 1.5411 (1.6032) time: 0.5128 [2021-03-25 05:21:17 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 200/1251] eta: 0:09:16 lr: 0.000608 loss: 5.0538 (4.8751) grad_norm: 1.7975 (1.6166) time: 0.5168 [2021-03-25 05:21:22 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 210/1251] eta: 0:09:10 lr: 0.000609 loss: 5.0996 (4.8793) grad_norm: 1.7975 (1.6195) time: 0.5115 [2021-03-25 05:21:27 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 220/1251] eta: 0:09:03 lr: 0.000609 loss: 4.9766 (4.8837) grad_norm: 1.5724 (1.6175) time: 0.5035 [2021-03-25 05:21:32 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 230/1251] eta: 0:08:57 lr: 0.000610 loss: 4.9028 (4.8770) grad_norm: 1.5048 (1.6155) time: 0.5008 [2021-03-25 05:21:38 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 240/1251] eta: 0:08:50 lr: 0.000610 loss: 5.0276 (4.8831) grad_norm: 1.4815 (1.6097) time: 0.5017 [2021-03-25 05:21:43 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 250/1251] eta: 0:08:45 lr: 0.000610 loss: 4.9972 (4.8783) grad_norm: 1.4372 (1.6027) time: 0.5084 [2021-03-25 05:21:48 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 260/1251] eta: 0:08:39 lr: 0.000611 loss: 4.7783 (4.8809) grad_norm: 1.4397 (1.6021) time: 0.5116 [2021-03-25 05:21:53 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 270/1251] eta: 0:08:33 lr: 0.000611 loss: 5.0976 (4.8911) grad_norm: 1.4723 (1.5956) time: 0.5019 [2021-03-25 05:21:58 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 280/1251] eta: 0:08:27 lr: 0.000612 loss: 5.0984 (4.8927) grad_norm: 1.4036 (1.5913) time: 0.4999 [2021-03-25 05:22:03 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 290/1251] eta: 0:08:21 lr: 0.000612 loss: 4.8689 (4.8915) grad_norm: 1.4106 (1.5901) time: 0.5059 [2021-03-25 05:22:08 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 300/1251] eta: 0:08:16 lr: 0.000612 loss: 4.8320 (4.8897) grad_norm: 1.4816 (1.5892) time: 0.5108 [2021-03-25 05:22:13 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 310/1251] eta: 0:08:10 lr: 0.000613 loss: 4.7605 (4.8782) grad_norm: 1.5541 (1.5880) time: 0.5076 [2021-03-25 05:22:18 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 320/1251] eta: 0:08:04 lr: 0.000613 loss: 4.6933 (4.8715) grad_norm: 1.5208 (1.5901) time: 0.5023 [2021-03-25 05:22:23 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 330/1251] eta: 0:07:59 lr: 0.000614 loss: 4.6244 (4.8704) grad_norm: 1.5208 (1.5890) time: 0.5081 [2021-03-25 05:22:28 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 340/1251] eta: 0:07:53 lr: 0.000614 loss: 4.6893 (4.8738) grad_norm: 1.4644 (1.5858) time: 0.5082 [2021-03-25 05:22:33 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 350/1251] eta: 0:07:47 lr: 0.000614 loss: 5.0776 (4.8750) grad_norm: 1.4644 (1.5881) time: 0.5058 [2021-03-25 05:22:38 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 360/1251] eta: 0:07:42 lr: 0.000615 loss: 5.0345 (4.8772) grad_norm: 1.7205 (1.5896) time: 0.5027 [2021-03-25 05:22:43 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 370/1251] eta: 0:07:36 lr: 0.000615 loss: 5.1084 (4.8818) grad_norm: 1.6206 (1.5946) time: 0.5048 [2021-03-25 05:22:48 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 380/1251] eta: 0:07:31 lr: 0.000616 loss: 4.7982 (4.8686) grad_norm: 1.5065 (1.5927) time: 0.5054 [2021-03-25 05:22:53 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 390/1251] eta: 0:07:25 lr: 0.000616 loss: 4.3157 (4.8687) grad_norm: 1.7042 (1.5942) time: 0.5019 [2021-03-25 05:22:59 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 400/1251] eta: 0:07:20 lr: 0.000616 loss: 4.9501 (4.8692) grad_norm: 1.6563 (1.5943) time: 0.5103 [2021-03-25 05:23:04 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 410/1251] eta: 0:07:15 lr: 0.000617 loss: 4.9501 (4.8698) grad_norm: 1.5566 (1.5952) time: 0.5126 [2021-03-25 05:23:09 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 420/1251] eta: 0:07:09 lr: 0.000617 loss: 4.7591 (4.8632) grad_norm: 1.5221 (1.5923) time: 0.5065 [2021-03-25 05:23:14 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 430/1251] eta: 0:07:04 lr: 0.000618 loss: 4.8219 (4.8651) grad_norm: 1.4243 (1.5884) time: 0.5026 [2021-03-25 05:23:19 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 440/1251] eta: 0:06:58 lr: 0.000618 loss: 5.0784 (4.8655) grad_norm: 1.4593 (1.5879) time: 0.5004 [2021-03-25 05:23:24 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 450/1251] eta: 0:06:53 lr: 0.000618 loss: 5.0784 (4.8667) grad_norm: 1.5925 (1.5878) time: 0.5018 [2021-03-25 05:23:29 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 460/1251] eta: 0:06:48 lr: 0.000619 loss: 4.6559 (4.8565) grad_norm: 1.5461 (1.5864) time: 0.5079 [2021-03-25 05:23:34 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 470/1251] eta: 0:06:42 lr: 0.000619 loss: 4.6790 (4.8574) grad_norm: 1.5473 (1.5869) time: 0.5106 [2021-03-25 05:23:39 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 480/1251] eta: 0:06:37 lr: 0.000620 loss: 5.0462 (4.8638) grad_norm: 1.5473 (1.5875) time: 0.5045 [2021-03-25 05:23:44 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 490/1251] eta: 0:06:32 lr: 0.000620 loss: 5.1047 (4.8632) grad_norm: 1.5256 (1.5852) time: 0.5058 [2021-03-25 05:23:49 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 500/1251] eta: 0:06:26 lr: 0.000620 loss: 4.9319 (4.8635) grad_norm: 1.4949 (1.5834) time: 0.5029 [2021-03-25 05:23:54 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 510/1251] eta: 0:06:21 lr: 0.000621 loss: 5.1783 (4.8698) grad_norm: 1.4374 (1.5811) time: 0.4974 [2021-03-25 05:23:59 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 520/1251] eta: 0:06:16 lr: 0.000621 loss: 5.0303 (4.8675) grad_norm: 1.4268 (1.5800) time: 0.5009 [2021-03-25 05:24:04 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 530/1251] eta: 0:06:10 lr: 0.000622 loss: 4.8791 (4.8689) grad_norm: 1.4721 (1.5787) time: 0.5014 [2021-03-25 05:24:09 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 540/1251] eta: 0:06:05 lr: 0.000622 loss: 5.0982 (4.8693) grad_norm: 1.4835 (1.5787) time: 0.5020 [2021-03-25 05:24:14 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 550/1251] eta: 0:06:00 lr: 0.000622 loss: 5.1238 (4.8709) grad_norm: 1.5608 (1.5798) time: 0.5118 [2021-03-25 05:24:19 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 560/1251] eta: 0:05:55 lr: 0.000623 loss: 5.1856 (4.8759) grad_norm: 1.4629 (1.5767) time: 0.5160 [2021-03-25 05:24:24 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 570/1251] eta: 0:05:50 lr: 0.000623 loss: 5.1716 (4.8740) grad_norm: 1.4263 (1.5777) time: 0.5089 [2021-03-25 05:24:30 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 580/1251] eta: 0:05:44 lr: 0.000624 loss: 4.7214 (4.8706) grad_norm: 1.4263 (1.5757) time: 0.5061 [2021-03-25 05:24:35 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 590/1251] eta: 0:05:39 lr: 0.000624 loss: 4.7881 (4.8669) grad_norm: 1.3708 (1.5749) time: 0.5097 [2021-03-25 05:24:40 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 600/1251] eta: 0:05:34 lr: 0.000624 loss: 4.9771 (4.8707) grad_norm: 1.5491 (1.5770) time: 0.5134 [2021-03-25 05:24:45 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 610/1251] eta: 0:05:29 lr: 0.000625 loss: 5.0653 (4.8723) grad_norm: 1.5279 (1.5753) time: 0.5132 [2021-03-25 05:24:50 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 620/1251] eta: 0:05:24 lr: 0.000625 loss: 4.8673 (4.8746) grad_norm: 1.4837 (1.5734) time: 0.5077 [2021-03-25 05:24:55 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 630/1251] eta: 0:05:18 lr: 0.000626 loss: 4.8626 (4.8720) grad_norm: 1.4025 (1.5699) time: 0.5045 [2021-03-25 05:25:00 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 640/1251] eta: 0:05:13 lr: 0.000626 loss: 4.5605 (4.8694) grad_norm: 1.4025 (1.5698) time: 0.5064 [2021-03-25 05:25:05 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 650/1251] eta: 0:05:08 lr: 0.000626 loss: 4.8468 (4.8722) grad_norm: 1.5592 (1.5700) time: 0.5026 [2021-03-25 05:25:10 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 660/1251] eta: 0:05:03 lr: 0.000627 loss: 4.9643 (4.8723) grad_norm: 1.5821 (1.5722) time: 0.5031 [2021-03-25 05:25:15 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 670/1251] eta: 0:04:57 lr: 0.000627 loss: 4.9617 (4.8713) grad_norm: 1.5936 (1.5719) time: 0.5019 [2021-03-25 05:25:20 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 680/1251] eta: 0:04:52 lr: 0.000628 loss: 4.8279 (4.8683) grad_norm: 1.5669 (1.5718) time: 0.5010 [2021-03-25 05:25:25 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 690/1251] eta: 0:04:47 lr: 0.000628 loss: 4.9589 (4.8691) grad_norm: 1.5811 (1.5744) time: 0.5040 [2021-03-25 05:25:30 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 700/1251] eta: 0:04:42 lr: 0.000628 loss: 4.9618 (4.8682) grad_norm: 1.7257 (1.5780) time: 0.5094 [2021-03-25 05:25:35 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 710/1251] eta: 0:04:37 lr: 0.000629 loss: 4.8818 (4.8677) grad_norm: 1.5683 (1.5759) time: 0.5089 [2021-03-25 05:25:40 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 720/1251] eta: 0:04:32 lr: 0.000629 loss: 4.9042 (4.8684) grad_norm: 1.4396 (1.5774) time: 0.5020 [2021-03-25 05:25:45 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 730/1251] eta: 0:04:26 lr: 0.000630 loss: 4.9837 (4.8670) grad_norm: 1.5113 (1.5758) time: 0.5007 [2021-03-25 05:25:51 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 740/1251] eta: 0:04:21 lr: 0.000630 loss: 4.9830 (4.8682) grad_norm: 1.4356 (1.5746) time: 0.5207 [2021-03-25 05:25:56 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 750/1251] eta: 0:04:16 lr: 0.000630 loss: 4.9577 (4.8682) grad_norm: 1.4894 (1.5759) time: 0.5267 [2021-03-25 05:26:01 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 760/1251] eta: 0:04:11 lr: 0.000631 loss: 4.9396 (4.8666) grad_norm: 1.5176 (1.5756) time: 0.5066 [2021-03-25 05:26:06 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 770/1251] eta: 0:04:06 lr: 0.000631 loss: 4.8664 (4.8624) grad_norm: 1.5075 (1.5752) time: 0.4996 [2021-03-25 05:26:11 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 780/1251] eta: 0:04:01 lr: 0.000632 loss: 4.9209 (4.8651) grad_norm: 1.5075 (1.5756) time: 0.5057 [2021-03-25 05:26:16 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 790/1251] eta: 0:03:56 lr: 0.000632 loss: 5.1558 (4.8650) grad_norm: 1.4456 (1.5748) time: 0.5078 [2021-03-25 05:26:21 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 800/1251] eta: 0:03:50 lr: 0.000632 loss: 4.8941 (4.8633) grad_norm: 1.4696 (1.5735) time: 0.5092 [2021-03-25 05:26:26 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 810/1251] eta: 0:03:45 lr: 0.000633 loss: 5.1573 (4.8663) grad_norm: 1.5037 (1.5721) time: 0.5153 [2021-03-25 05:26:32 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 820/1251] eta: 0:03:40 lr: 0.000633 loss: 5.2848 (4.8694) grad_norm: 1.4745 (1.5706) time: 0.5140 [2021-03-25 05:26:37 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 830/1251] eta: 0:03:35 lr: 0.000634 loss: 5.0414 (4.8710) grad_norm: 1.4745 (1.5700) time: 0.5062 [2021-03-25 05:26:42 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 840/1251] eta: 0:03:30 lr: 0.000634 loss: 4.9726 (4.8682) grad_norm: 1.4435 (1.5689) time: 0.4981 [2021-03-25 05:26:47 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 850/1251] eta: 0:03:25 lr: 0.000634 loss: 4.9726 (4.8711) grad_norm: 1.5827 (1.5702) time: 0.5007 [2021-03-25 05:26:52 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 860/1251] eta: 0:03:20 lr: 0.000635 loss: 5.0655 (4.8714) grad_norm: 1.6260 (1.5718) time: 0.5095 [2021-03-25 05:26:57 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 870/1251] eta: 0:03:14 lr: 0.000635 loss: 5.0655 (4.8751) grad_norm: 1.5744 (1.5715) time: 0.5073 [2021-03-25 05:27:02 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 880/1251] eta: 0:03:09 lr: 0.000636 loss: 5.1859 (4.8776) grad_norm: 1.5299 (1.5709) time: 0.5033 [2021-03-25 05:27:07 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 890/1251] eta: 0:03:04 lr: 0.000636 loss: 4.9077 (4.8756) grad_norm: 1.3937 (1.5702) time: 0.5080 [2021-03-25 05:27:12 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 900/1251] eta: 0:02:59 lr: 0.000636 loss: 4.9077 (4.8769) grad_norm: 1.4487 (1.5700) time: 0.5108 [2021-03-25 05:27:17 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 910/1251] eta: 0:02:54 lr: 0.000637 loss: 4.8812 (4.8745) grad_norm: 1.4506 (1.5693) time: 0.5117 [2021-03-25 05:27:22 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 920/1251] eta: 0:02:49 lr: 0.000637 loss: 4.4513 (4.8685) grad_norm: 1.5409 (1.5699) time: 0.5098 [2021-03-25 05:27:27 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 930/1251] eta: 0:02:44 lr: 0.000638 loss: 4.7671 (4.8683) grad_norm: 1.5409 (1.5702) time: 0.5086 [2021-03-25 05:27:32 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 940/1251] eta: 0:02:39 lr: 0.000638 loss: 4.7671 (4.8654) grad_norm: 1.4205 (1.5690) time: 0.5128 [2021-03-25 05:27:38 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 950/1251] eta: 0:02:33 lr: 0.000638 loss: 4.6199 (4.8642) grad_norm: 1.5498 (1.5717) time: 0.5103 [2021-03-25 05:27:43 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 960/1251] eta: 0:02:28 lr: 0.000639 loss: 4.9292 (4.8639) grad_norm: 1.6112 (1.5714) time: 0.5038 [2021-03-25 05:27:48 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 970/1251] eta: 0:02:23 lr: 0.000639 loss: 4.8405 (4.8629) grad_norm: 1.4990 (1.5702) time: 0.5020 [2021-03-25 05:27:53 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 980/1251] eta: 0:02:18 lr: 0.000640 loss: 4.7249 (4.8610) grad_norm: 1.4356 (1.5691) time: 0.5012 [2021-03-25 05:27:58 swin_small_patch4_window7_224] INFO: Epoch: [12] [ 990/1251] eta: 0:02:13 lr: 0.000640 loss: 4.8668 (4.8633) grad_norm: 1.5090 (1.5709) time: 0.5042 [2021-03-25 05:28:03 swin_small_patch4_window7_224] INFO: Epoch: [12] [1000/1251] eta: 0:02:08 lr: 0.000640 loss: 4.9118 (4.8615) grad_norm: 1.5725 (1.5703) time: 0.5035 [2021-03-25 05:28:08 swin_small_patch4_window7_224] INFO: Epoch: [12] [1010/1251] eta: 0:02:03 lr: 0.000641 loss: 4.8880 (4.8610) grad_norm: 1.4506 (1.5696) time: 0.5004 [2021-03-25 05:28:13 swin_small_patch4_window7_224] INFO: Epoch: [12] [1020/1251] eta: 0:01:58 lr: 0.000641 loss: 4.8880 (4.8601) grad_norm: 1.3665 (1.5683) time: 0.5039 [2021-03-25 05:28:18 swin_small_patch4_window7_224] INFO: Epoch: [12] [1030/1251] eta: 0:01:52 lr: 0.000642 loss: 4.8764 (4.8597) grad_norm: 1.3869 (1.5665) time: 0.5055 [2021-03-25 05:28:23 swin_small_patch4_window7_224] INFO: Epoch: [12] [1040/1251] eta: 0:01:47 lr: 0.000642 loss: 4.9602 (4.8588) grad_norm: 1.3172 (1.5647) time: 0.5024 [2021-03-25 05:28:28 swin_small_patch4_window7_224] INFO: Epoch: [12] [1050/1251] eta: 0:01:42 lr: 0.000642 loss: 4.8267 (4.8569) grad_norm: 1.3941 (inf) time: 0.5018 [2021-03-25 05:28:33 swin_small_patch4_window7_224] INFO: Epoch: [12] [1060/1251] eta: 0:01:37 lr: 0.000643 loss: 4.8315 (4.8577) grad_norm: 1.5542 (inf) time: 0.5030 [2021-03-25 05:28:38 swin_small_patch4_window7_224] INFO: Epoch: [12] [1070/1251] eta: 0:01:32 lr: 0.000643 loss: 5.0372 (4.8590) grad_norm: 1.5482 (inf) time: 0.5044 [2021-03-25 05:28:43 swin_small_patch4_window7_224] INFO: Epoch: [12] [1080/1251] eta: 0:01:27 lr: 0.000644 loss: 4.8615 (4.8576) grad_norm: 1.5374 (inf) time: 0.5044 [2021-03-25 05:28:48 swin_small_patch4_window7_224] INFO: Epoch: [12] [1090/1251] eta: 0:01:22 lr: 0.000644 loss: 4.8615 (4.8562) grad_norm: 1.4531 (inf) time: 0.5056 [2021-03-25 05:28:53 swin_small_patch4_window7_224] INFO: Epoch: [12] [1100/1251] eta: 0:01:17 lr: 0.000644 loss: 4.7513 (4.8558) grad_norm: 1.4831 (inf) time: 0.5110 [2021-03-25 05:28:58 swin_small_patch4_window7_224] INFO: Epoch: [12] [1110/1251] eta: 0:01:11 lr: 0.000645 loss: 4.9232 (4.8564) grad_norm: 1.4436 (inf) time: 0.5167 [2021-03-25 05:29:03 swin_small_patch4_window7_224] INFO: Epoch: [12] [1120/1251] eta: 0:01:06 lr: 0.000645 loss: 4.8930 (4.8561) grad_norm: 1.4049 (inf) time: 0.5092 [2021-03-25 05:29:08 swin_small_patch4_window7_224] INFO: Epoch: [12] [1130/1251] eta: 0:01:01 lr: 0.000646 loss: 5.1001 (4.8584) grad_norm: 1.4097 (inf) time: 0.5013 [2021-03-25 05:29:14 swin_small_patch4_window7_224] INFO: Epoch: [12] [1140/1251] eta: 0:00:56 lr: 0.000646 loss: 5.1823 (4.8596) grad_norm: 1.4732 (inf) time: 0.5111 [2021-03-25 05:29:19 swin_small_patch4_window7_224] INFO: Epoch: [12] [1150/1251] eta: 0:00:51 lr: 0.000646 loss: 4.8258 (4.8597) grad_norm: 1.4947 (inf) time: 0.5108 [2021-03-25 05:29:24 swin_small_patch4_window7_224] INFO: Epoch: [12] [1160/1251] eta: 0:00:46 lr: 0.000647 loss: 4.8258 (4.8584) grad_norm: 1.4947 (inf) time: 0.5029 [2021-03-25 05:29:29 swin_small_patch4_window7_224] INFO: Epoch: [12] [1170/1251] eta: 0:00:41 lr: 0.000647 loss: 4.5075 (4.8547) grad_norm: 1.3966 (inf) time: 0.5012 [2021-03-25 05:29:34 swin_small_patch4_window7_224] INFO: Epoch: [12] [1180/1251] eta: 0:00:36 lr: 0.000648 loss: 4.6876 (4.8542) grad_norm: 1.3846 (inf) time: 0.5036 [2021-03-25 05:29:39 swin_small_patch4_window7_224] INFO: Epoch: [12] [1190/1251] eta: 0:00:31 lr: 0.000648 loss: 4.9803 (4.8555) grad_norm: 1.4170 (inf) time: 0.5029 [2021-03-25 05:29:44 swin_small_patch4_window7_224] INFO: Epoch: [12] [1200/1251] eta: 0:00:26 lr: 0.000648 loss: 4.9331 (4.8564) grad_norm: 1.5376 (inf) time: 0.5005 [2021-03-25 05:29:49 swin_small_patch4_window7_224] INFO: Epoch: [12] [1210/1251] eta: 0:00:20 lr: 0.000649 loss: 4.9331 (4.8553) grad_norm: 1.4381 (inf) time: 0.5070 [2021-03-25 05:29:54 swin_small_patch4_window7_224] INFO: Epoch: [12] [1220/1251] eta: 0:00:15 lr: 0.000649 loss: 4.9465 (4.8566) grad_norm: 1.4381 (inf) time: 0.5067 [2021-03-25 05:29:59 swin_small_patch4_window7_224] INFO: Epoch: [12] [1230/1251] eta: 0:00:10 lr: 0.000650 loss: 4.7977 (4.8529) grad_norm: 1.4812 (inf) time: 0.5012 [2021-03-25 05:30:04 swin_small_patch4_window7_224] INFO: Epoch: [12] [1240/1251] eta: 0:00:05 lr: 0.000650 loss: 4.5074 (4.8531) grad_norm: 1.5043 (inf) time: 0.5040 [2021-03-25 05:30:09 swin_small_patch4_window7_224] INFO: Epoch: [12] [1250/1251] eta: 0:00:00 lr: 0.000650 loss: 4.8107 (4.8535) grad_norm: 1.5043 (inf) time: 0.5059 [2021-03-25 05:30:13 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 1.7927 (1.7927) acc1: 57.8125 (57.8125) acc5: 85.9375 (85.9375) [2021-03-25 05:30:15 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 2.1342 (2.1475) acc1: 54.6875 (53.2670) acc5: 79.6875 (78.6932) [2021-03-25 05:30:18 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 2.0729 (2.1213) acc1: 50.0000 (51.9345) acc5: 78.1250 (77.9018) [2021-03-25 05:30:20 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.0729 (2.1329) acc1: 50.0000 (52.1169) acc5: 78.1250 (78.1754) [2021-03-25 05:30:22 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.2705 (2.1745) acc1: 48.4375 (51.3720) acc5: 75.0000 (77.4390) [2021-03-25 05:30:23 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.2793 (2.2123) acc1: 48.4375 (51.2320) acc5: 73.4375 (76.7680) [2021-03-25 05:30:25 swin_small_patch4_window7_224] INFO: * Acc@1 51.178 Acc@5 76.796 loss 2.220 [2021-03-25 05:30:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 51.2% [2021-03-25 05:30:25 swin_small_patch4_window7_224] INFO: Max accuracy: 51.18% [2021-03-25 05:30:29 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 0/1251] eta: 1:23:50 lr: 0.000650 loss: 3.6759 (3.6759) grad_norm: 1.5944 (1.5944) time: 4.0212 [2021-03-25 05:30:34 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 10/1251] eta: 0:17:32 lr: 0.000651 loss: 4.5077 (4.4762) grad_norm: 1.5906 (1.5503) time: 0.8479 [2021-03-25 05:30:39 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 20/1251] eta: 0:14:02 lr: 0.000651 loss: 4.9618 (4.7132) grad_norm: 1.5626 (1.5406) time: 0.5179 [2021-03-25 05:30:44 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 30/1251] eta: 0:12:43 lr: 0.000652 loss: 4.9618 (4.7023) grad_norm: 1.4478 (1.4951) time: 0.5027 [2021-03-25 05:30:49 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 40/1251] eta: 0:12:04 lr: 0.000652 loss: 4.6680 (4.6793) grad_norm: 1.3763 (1.4943) time: 0.5068 [2021-03-25 05:30:54 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 50/1251] eta: 0:11:35 lr: 0.000652 loss: 4.6704 (4.6879) grad_norm: 1.4450 (1.4994) time: 0.5080 [2021-03-25 05:30:59 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 60/1251] eta: 0:11:16 lr: 0.000653 loss: 4.8344 (4.7381) grad_norm: 1.4450 (1.5020) time: 0.5065 [2021-03-25 05:31:04 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 70/1251] eta: 0:11:01 lr: 0.000653 loss: 4.8344 (4.7242) grad_norm: 1.4431 (1.4851) time: 0.5108 [2021-03-25 05:31:10 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 80/1251] eta: 0:10:48 lr: 0.000654 loss: 4.7514 (4.7281) grad_norm: 1.4480 (1.4937) time: 0.5112 [2021-03-25 05:31:15 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 90/1251] eta: 0:10:37 lr: 0.000654 loss: 4.6550 (4.7116) grad_norm: 1.5055 (1.4905) time: 0.5098 [2021-03-25 05:31:20 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 100/1251] eta: 0:10:25 lr: 0.000654 loss: 4.4559 (4.7139) grad_norm: 1.3934 (1.4833) time: 0.5014 [2021-03-25 05:31:25 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 110/1251] eta: 0:10:16 lr: 0.000655 loss: 4.8195 (4.7145) grad_norm: 1.5365 (1.5559) time: 0.5001 [2021-03-25 05:31:30 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 120/1251] eta: 0:10:08 lr: 0.000655 loss: 4.5775 (4.7070) grad_norm: 1.5262 (1.5438) time: 0.5106 [2021-03-25 05:31:35 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 130/1251] eta: 0:10:01 lr: 0.000656 loss: 4.6019 (4.7124) grad_norm: 1.3402 (1.5298) time: 0.5162 [2021-03-25 05:31:40 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 140/1251] eta: 0:09:52 lr: 0.000656 loss: 4.8838 (4.7166) grad_norm: 1.3295 (1.5226) time: 0.5065 [2021-03-25 05:31:45 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 150/1251] eta: 0:09:45 lr: 0.000656 loss: 4.8838 (4.7226) grad_norm: 1.4170 (1.5167) time: 0.4979 [2021-03-25 05:31:50 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 160/1251] eta: 0:09:37 lr: 0.000657 loss: 4.5512 (4.7146) grad_norm: 1.4235 (1.5093) time: 0.5014 [2021-03-25 05:31:55 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 170/1251] eta: 0:09:30 lr: 0.000657 loss: 4.5512 (4.7144) grad_norm: 1.4235 (1.5056) time: 0.5011 [2021-03-25 05:32:00 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 180/1251] eta: 0:09:24 lr: 0.000658 loss: 4.8531 (4.7427) grad_norm: 1.4026 (1.5009) time: 0.5043 [2021-03-25 05:32:05 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 190/1251] eta: 0:09:18 lr: 0.000658 loss: 4.7820 (4.7373) grad_norm: 1.4073 (1.4983) time: 0.5107 [2021-03-25 05:32:10 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 200/1251] eta: 0:09:12 lr: 0.000658 loss: 4.6847 (4.7296) grad_norm: 1.4563 (1.4937) time: 0.5115 [2021-03-25 05:32:15 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 210/1251] eta: 0:09:06 lr: 0.000659 loss: 4.9125 (4.7435) grad_norm: 1.4444 (1.4935) time: 0.5107 [2021-03-25 05:32:20 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 220/1251] eta: 0:08:59 lr: 0.000659 loss: 4.9116 (4.7405) grad_norm: 1.5778 (1.5006) time: 0.5003 [2021-03-25 05:32:25 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 230/1251] eta: 0:08:53 lr: 0.000660 loss: 4.7969 (4.7429) grad_norm: 1.6719 (1.5053) time: 0.4979 [2021-03-25 05:32:30 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 240/1251] eta: 0:08:47 lr: 0.000660 loss: 5.0289 (4.7524) grad_norm: 1.5182 (1.5031) time: 0.5045 [2021-03-25 05:32:35 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 250/1251] eta: 0:08:41 lr: 0.000660 loss: 5.0241 (4.7607) grad_norm: 1.5182 (1.5074) time: 0.5035 [2021-03-25 05:32:40 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 260/1251] eta: 0:08:35 lr: 0.000661 loss: 4.8849 (4.7592) grad_norm: 1.4883 (1.5049) time: 0.5013 [2021-03-25 05:32:46 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 270/1251] eta: 0:08:29 lr: 0.000661 loss: 4.5435 (4.7527) grad_norm: 1.4883 (1.5087) time: 0.5059 [2021-03-25 05:32:51 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 280/1251] eta: 0:08:24 lr: 0.000662 loss: 4.6347 (4.7503) grad_norm: 1.4191 (1.5096) time: 0.5094 [2021-03-25 05:32:56 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 290/1251] eta: 0:08:18 lr: 0.000662 loss: 4.7197 (4.7420) grad_norm: 1.4021 (1.5088) time: 0.5064 [2021-03-25 05:33:01 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 300/1251] eta: 0:08:13 lr: 0.000662 loss: 4.4964 (4.7336) grad_norm: 1.4243 (1.5047) time: 0.5091 [2021-03-25 05:33:06 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 310/1251] eta: 0:08:07 lr: 0.000663 loss: 4.5757 (4.7345) grad_norm: 1.3465 (1.5011) time: 0.5082 [2021-03-25 05:33:11 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 320/1251] eta: 0:08:02 lr: 0.000663 loss: 4.9570 (4.7412) grad_norm: 1.3252 (1.4963) time: 0.5093 [2021-03-25 05:33:16 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 330/1251] eta: 0:07:56 lr: 0.000664 loss: 5.1469 (4.7509) grad_norm: 1.4701 (1.5071) time: 0.5107 [2021-03-25 05:33:21 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 340/1251] eta: 0:07:51 lr: 0.000664 loss: 4.7729 (4.7444) grad_norm: 1.5745 (1.5061) time: 0.5040 [2021-03-25 05:33:26 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 350/1251] eta: 0:07:45 lr: 0.000664 loss: 4.5695 (4.7416) grad_norm: 1.4437 (1.5071) time: 0.5014 [2021-03-25 05:33:31 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 360/1251] eta: 0:07:40 lr: 0.000665 loss: 4.8469 (4.7411) grad_norm: 1.3894 (1.5059) time: 0.5034 [2021-03-25 05:33:36 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 370/1251] eta: 0:07:34 lr: 0.000665 loss: 4.9971 (4.7501) grad_norm: 1.3423 (1.5034) time: 0.5063 [2021-03-25 05:33:41 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 380/1251] eta: 0:07:29 lr: 0.000666 loss: 5.0396 (4.7498) grad_norm: 1.4184 (1.5040) time: 0.5091 [2021-03-25 05:33:46 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 390/1251] eta: 0:07:23 lr: 0.000666 loss: 5.0170 (4.7467) grad_norm: 1.4777 (1.5050) time: 0.5021 [2021-03-25 05:33:51 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 400/1251] eta: 0:07:18 lr: 0.000666 loss: 5.0347 (4.7487) grad_norm: 1.5229 (1.5027) time: 0.5004 [2021-03-25 05:33:56 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 410/1251] eta: 0:07:12 lr: 0.000667 loss: 4.9061 (4.7418) grad_norm: 1.4246 (1.5032) time: 0.5037 [2021-03-25 05:34:01 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 420/1251] eta: 0:07:07 lr: 0.000667 loss: 4.7315 (4.7416) grad_norm: 1.5797 (1.5076) time: 0.5038 [2021-03-25 05:34:07 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 430/1251] eta: 0:07:02 lr: 0.000668 loss: 4.7315 (4.7446) grad_norm: 1.5456 (1.5071) time: 0.5077 [2021-03-25 05:34:12 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 440/1251] eta: 0:06:57 lr: 0.000668 loss: 4.9069 (4.7520) grad_norm: 1.4695 (1.5091) time: 0.5074 [2021-03-25 05:34:17 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 450/1251] eta: 0:06:51 lr: 0.000668 loss: 5.0955 (4.7571) grad_norm: 1.5442 (1.5091) time: 0.5023 [2021-03-25 05:34:22 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 460/1251] eta: 0:06:46 lr: 0.000669 loss: 4.8969 (4.7525) grad_norm: 1.4211 (1.5067) time: 0.5040 [2021-03-25 05:34:27 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 470/1251] eta: 0:06:41 lr: 0.000669 loss: 4.6649 (4.7530) grad_norm: 1.4179 (1.5054) time: 0.5065 [2021-03-25 05:34:32 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 480/1251] eta: 0:06:35 lr: 0.000670 loss: 4.7811 (4.7541) grad_norm: 1.4023 (1.5040) time: 0.5027 [2021-03-25 05:34:37 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 490/1251] eta: 0:06:30 lr: 0.000670 loss: 4.8777 (4.7593) grad_norm: 1.3876 (1.5031) time: 0.5055 [2021-03-25 05:34:42 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 500/1251] eta: 0:06:25 lr: 0.000670 loss: 5.0915 (4.7648) grad_norm: 1.4820 (1.5068) time: 0.5074 [2021-03-25 05:34:47 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 510/1251] eta: 0:06:20 lr: 0.000671 loss: 4.9780 (4.7688) grad_norm: 1.4768 (1.5055) time: 0.5027 [2021-03-25 05:34:52 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 520/1251] eta: 0:06:14 lr: 0.000671 loss: 4.9780 (4.7686) grad_norm: 1.3972 (1.5049) time: 0.5011 [2021-03-25 05:34:57 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 530/1251] eta: 0:06:09 lr: 0.000672 loss: 4.6220 (4.7619) grad_norm: 1.4770 (1.5055) time: 0.5048 [2021-03-25 05:35:02 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 540/1251] eta: 0:06:04 lr: 0.000672 loss: 4.5778 (4.7611) grad_norm: 1.4840 (1.5046) time: 0.5026 [2021-03-25 05:35:07 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 550/1251] eta: 0:05:59 lr: 0.000672 loss: 4.7197 (4.7556) grad_norm: 1.3733 (1.5024) time: 0.5067 [2021-03-25 05:35:12 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 560/1251] eta: 0:05:54 lr: 0.000673 loss: 4.6703 (4.7537) grad_norm: 1.3439 (1.5009) time: 0.5141 [2021-03-25 05:35:17 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 570/1251] eta: 0:05:48 lr: 0.000673 loss: 4.8322 (4.7578) grad_norm: 1.4231 (1.5003) time: 0.5082 [2021-03-25 05:35:22 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 580/1251] eta: 0:05:43 lr: 0.000674 loss: 4.9384 (4.7606) grad_norm: 1.4373 (1.4993) time: 0.5023 [2021-03-25 05:35:27 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 590/1251] eta: 0:05:38 lr: 0.000674 loss: 4.8758 (4.7626) grad_norm: 1.4526 (1.5006) time: 0.5025 [2021-03-25 05:35:32 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 600/1251] eta: 0:05:33 lr: 0.000674 loss: 4.6880 (4.7610) grad_norm: 1.4755 (1.5002) time: 0.5025 [2021-03-25 05:35:37 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 610/1251] eta: 0:05:27 lr: 0.000675 loss: 4.8133 (4.7621) grad_norm: 1.4230 (1.4990) time: 0.4994 [2021-03-25 05:35:42 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 620/1251] eta: 0:05:22 lr: 0.000675 loss: 4.8567 (4.7630) grad_norm: 1.4034 (1.4995) time: 0.4993 [2021-03-25 05:35:47 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 630/1251] eta: 0:05:17 lr: 0.000676 loss: 4.7567 (4.7622) grad_norm: 1.6195 (1.5020) time: 0.4994 [2021-03-25 05:35:52 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 640/1251] eta: 0:05:12 lr: 0.000676 loss: 4.7324 (4.7593) grad_norm: 1.6959 (1.5054) time: 0.5041 [2021-03-25 05:35:57 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 650/1251] eta: 0:05:07 lr: 0.000676 loss: 4.7305 (4.7550) grad_norm: 1.4784 (1.5037) time: 0.5050 [2021-03-25 05:36:02 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 660/1251] eta: 0:05:01 lr: 0.000677 loss: 4.7305 (4.7560) grad_norm: 1.4406 (1.5041) time: 0.5029 [2021-03-25 05:36:08 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 670/1251] eta: 0:04:56 lr: 0.000677 loss: 4.7203 (4.7544) grad_norm: 1.5428 (1.5056) time: 0.5142 [2021-03-25 05:36:13 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 680/1251] eta: 0:04:51 lr: 0.000678 loss: 4.7203 (4.7534) grad_norm: 1.5175 (1.5043) time: 0.5144 [2021-03-25 05:36:18 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 690/1251] eta: 0:04:46 lr: 0.000678 loss: 4.8821 (4.7549) grad_norm: 1.3731 (1.5025) time: 0.5091 [2021-03-25 05:36:23 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 700/1251] eta: 0:04:41 lr: 0.000678 loss: 4.9966 (4.7561) grad_norm: 1.4251 (1.5038) time: 0.5078 [2021-03-25 05:36:28 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 710/1251] eta: 0:04:36 lr: 0.000679 loss: 4.8326 (4.7538) grad_norm: 1.4225 (1.5028) time: 0.5077 [2021-03-25 05:36:33 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 720/1251] eta: 0:04:31 lr: 0.000679 loss: 4.8200 (4.7534) grad_norm: 1.3375 (1.5031) time: 0.5041 [2021-03-25 05:36:38 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 730/1251] eta: 0:04:26 lr: 0.000679 loss: 4.7780 (4.7524) grad_norm: 1.3510 (1.5026) time: 0.5010 [2021-03-25 05:36:43 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 740/1251] eta: 0:04:21 lr: 0.000680 loss: 4.8715 (4.7549) grad_norm: 1.4826 (1.5027) time: 0.5176 [2021-03-25 05:36:49 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 750/1251] eta: 0:04:16 lr: 0.000680 loss: 4.7769 (4.7534) grad_norm: 1.4537 (1.5022) time: 0.5256 [2021-03-25 05:36:54 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 760/1251] eta: 0:04:10 lr: 0.000681 loss: 4.5016 (4.7488) grad_norm: 1.4688 (1.5038) time: 0.5137 [2021-03-25 05:36:59 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 770/1251] eta: 0:04:05 lr: 0.000681 loss: 4.4506 (4.7465) grad_norm: 1.3587 (1.5010) time: 0.5011 [2021-03-25 05:37:04 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 780/1251] eta: 0:04:00 lr: 0.000681 loss: 4.7414 (4.7473) grad_norm: 1.3309 (1.4998) time: 0.5015 [2021-03-25 05:37:09 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 790/1251] eta: 0:03:55 lr: 0.000682 loss: 4.6363 (4.7441) grad_norm: 1.3839 (1.4987) time: 0.5070 [2021-03-25 05:37:14 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 800/1251] eta: 0:03:50 lr: 0.000682 loss: 4.6363 (4.7463) grad_norm: 1.4859 (1.5001) time: 0.5056 [2021-03-25 05:37:19 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 810/1251] eta: 0:03:45 lr: 0.000683 loss: 4.8711 (4.7444) grad_norm: 1.4830 (1.4999) time: 0.4983 [2021-03-25 05:37:24 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 820/1251] eta: 0:03:39 lr: 0.000683 loss: 4.6908 (4.7446) grad_norm: 1.4872 (1.5016) time: 0.5000 [2021-03-25 05:37:29 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 830/1251] eta: 0:03:34 lr: 0.000683 loss: 4.7516 (4.7443) grad_norm: 1.5344 (1.5029) time: 0.5097 [2021-03-25 05:37:34 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 840/1251] eta: 0:03:29 lr: 0.000684 loss: 4.9695 (4.7469) grad_norm: 1.5233 (1.5038) time: 0.5085 [2021-03-25 05:37:39 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 850/1251] eta: 0:03:24 lr: 0.000684 loss: 4.8868 (4.7456) grad_norm: 1.4731 (1.5034) time: 0.5014 [2021-03-25 05:37:44 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 860/1251] eta: 0:03:19 lr: 0.000685 loss: 4.8214 (4.7486) grad_norm: 1.4383 (1.5028) time: 0.5003 [2021-03-25 05:37:49 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 870/1251] eta: 0:03:14 lr: 0.000685 loss: 4.8820 (4.7479) grad_norm: 1.3510 (1.5010) time: 0.5073 [2021-03-25 05:37:54 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 880/1251] eta: 0:03:09 lr: 0.000685 loss: 4.8820 (4.7475) grad_norm: 1.3130 (1.4991) time: 0.5050 [2021-03-25 05:37:59 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 890/1251] eta: 0:03:04 lr: 0.000686 loss: 5.0008 (4.7488) grad_norm: 1.3130 (1.4990) time: 0.4984 [2021-03-25 05:38:04 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 900/1251] eta: 0:02:58 lr: 0.000686 loss: 5.2329 (4.7510) grad_norm: 1.4687 (1.4989) time: 0.5006 [2021-03-25 05:38:09 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 910/1251] eta: 0:02:53 lr: 0.000687 loss: 4.8621 (4.7514) grad_norm: 1.4687 (1.4986) time: 0.5026 [2021-03-25 05:38:14 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 920/1251] eta: 0:02:48 lr: 0.000687 loss: 4.6270 (4.7475) grad_norm: 1.3624 (1.4971) time: 0.5077 [2021-03-25 05:38:19 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 930/1251] eta: 0:02:43 lr: 0.000687 loss: 4.0359 (4.7428) grad_norm: 1.3283 (1.4955) time: 0.5085 [2021-03-25 05:38:24 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 940/1251] eta: 0:02:38 lr: 0.000688 loss: 4.6977 (4.7441) grad_norm: 1.3242 (1.4944) time: 0.5083 [2021-03-25 05:38:30 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 950/1251] eta: 0:02:33 lr: 0.000688 loss: 4.7569 (4.7450) grad_norm: 1.4523 (1.4938) time: 0.5092 [2021-03-25 05:38:34 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 960/1251] eta: 0:02:28 lr: 0.000689 loss: 4.7568 (4.7438) grad_norm: 1.4653 (1.4955) time: 0.5018 [2021-03-25 05:38:40 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 970/1251] eta: 0:02:23 lr: 0.000689 loss: 4.6370 (4.7416) grad_norm: 1.4594 (1.4951) time: 0.5038 [2021-03-25 05:38:45 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 980/1251] eta: 0:02:18 lr: 0.000689 loss: 4.6627 (4.7438) grad_norm: 1.4534 (1.4959) time: 0.5065 [2021-03-25 05:38:50 swin_small_patch4_window7_224] INFO: Epoch: [13] [ 990/1251] eta: 0:02:12 lr: 0.000690 loss: 4.9955 (4.7447) grad_norm: 1.4999 (1.4962) time: 0.5093 [2021-03-25 05:38:55 swin_small_patch4_window7_224] INFO: Epoch: [13] [1000/1251] eta: 0:02:07 lr: 0.000690 loss: 4.9014 (4.7471) grad_norm: 1.4021 (1.4947) time: 0.5088 [2021-03-25 05:39:00 swin_small_patch4_window7_224] INFO: Epoch: [13] [1010/1251] eta: 0:02:02 lr: 0.000691 loss: 4.7821 (4.7459) grad_norm: 1.4003 (1.4948) time: 0.5038 [2021-03-25 05:39:05 swin_small_patch4_window7_224] INFO: Epoch: [13] [1020/1251] eta: 0:01:57 lr: 0.000691 loss: 4.7280 (4.7457) grad_norm: 1.4151 (1.4939) time: 0.5103 [2021-03-25 05:39:10 swin_small_patch4_window7_224] INFO: Epoch: [13] [1030/1251] eta: 0:01:52 lr: 0.000691 loss: 4.7330 (4.7476) grad_norm: 1.3192 (1.4922) time: 0.5085 [2021-03-25 05:39:15 swin_small_patch4_window7_224] INFO: Epoch: [13] [1040/1251] eta: 0:01:47 lr: 0.000692 loss: 4.9781 (4.7493) grad_norm: 1.3192 (1.4915) time: 0.5093 [2021-03-25 05:39:20 swin_small_patch4_window7_224] INFO: Epoch: [13] [1050/1251] eta: 0:01:42 lr: 0.000692 loss: 4.9643 (4.7498) grad_norm: 1.4065 (1.4914) time: 0.5126 [2021-03-25 05:39:25 swin_small_patch4_window7_224] INFO: Epoch: [13] [1060/1251] eta: 0:01:37 lr: 0.000693 loss: 4.8891 (4.7502) grad_norm: 1.3726 (1.4898) time: 0.5088 [2021-03-25 05:39:30 swin_small_patch4_window7_224] INFO: Epoch: [13] [1070/1251] eta: 0:01:32 lr: 0.000693 loss: 4.9883 (4.7528) grad_norm: 1.2948 (1.4879) time: 0.4996 [2021-03-25 05:39:35 swin_small_patch4_window7_224] INFO: Epoch: [13] [1080/1251] eta: 0:01:27 lr: 0.000693 loss: 4.9421 (4.7493) grad_norm: 1.2780 (1.4865) time: 0.4976 [2021-03-25 05:39:40 swin_small_patch4_window7_224] INFO: Epoch: [13] [1090/1251] eta: 0:01:21 lr: 0.000694 loss: 4.6480 (4.7508) grad_norm: 1.2813 (1.4853) time: 0.5006 [2021-03-25 05:39:45 swin_small_patch4_window7_224] INFO: Epoch: [13] [1100/1251] eta: 0:01:16 lr: 0.000694 loss: 4.7251 (4.7496) grad_norm: 1.3383 (1.4856) time: 0.4975 [2021-03-25 05:39:50 swin_small_patch4_window7_224] INFO: Epoch: [13] [1110/1251] eta: 0:01:11 lr: 0.000695 loss: 4.6854 (4.7480) grad_norm: 1.4648 (1.4850) time: 0.5027 [2021-03-25 05:39:56 swin_small_patch4_window7_224] INFO: Epoch: [13] [1120/1251] eta: 0:01:06 lr: 0.000695 loss: 4.3696 (4.7447) grad_norm: 1.4778 (1.4871) time: 0.5110 [2021-03-25 05:40:01 swin_small_patch4_window7_224] INFO: Epoch: [13] [1130/1251] eta: 0:01:01 lr: 0.000695 loss: 4.7917 (4.7457) grad_norm: 1.5823 (1.4877) time: 0.5102 [2021-03-25 05:40:06 swin_small_patch4_window7_224] INFO: Epoch: [13] [1140/1251] eta: 0:00:56 lr: 0.000696 loss: 4.8352 (4.7462) grad_norm: 1.5902 (1.4888) time: 0.5032 [2021-03-25 05:40:11 swin_small_patch4_window7_224] INFO: Epoch: [13] [1150/1251] eta: 0:00:51 lr: 0.000696 loss: 4.8066 (4.7467) grad_norm: 1.4018 (1.4875) time: 0.5068 [2021-03-25 05:40:16 swin_small_patch4_window7_224] INFO: Epoch: [13] [1160/1251] eta: 0:00:46 lr: 0.000697 loss: 4.9647 (4.7492) grad_norm: 1.3288 (1.4862) time: 0.5091 [2021-03-25 05:40:21 swin_small_patch4_window7_224] INFO: Epoch: [13] [1170/1251] eta: 0:00:41 lr: 0.000697 loss: 4.9914 (4.7482) grad_norm: 1.3629 (1.4866) time: 0.5034 [2021-03-25 05:40:26 swin_small_patch4_window7_224] INFO: Epoch: [13] [1180/1251] eta: 0:00:36 lr: 0.000697 loss: 4.7136 (4.7480) grad_norm: 1.4983 (1.4872) time: 0.5025 [2021-03-25 05:40:31 swin_small_patch4_window7_224] INFO: Epoch: [13] [1190/1251] eta: 0:00:31 lr: 0.000698 loss: 4.6203 (4.7449) grad_norm: 1.4510 (1.4864) time: 0.5042 [2021-03-25 05:40:36 swin_small_patch4_window7_224] INFO: Epoch: [13] [1200/1251] eta: 0:00:25 lr: 0.000698 loss: 4.6564 (4.7430) grad_norm: 1.4385 (1.4882) time: 0.5047 [2021-03-25 05:40:41 swin_small_patch4_window7_224] INFO: Epoch: [13] [1210/1251] eta: 0:00:20 lr: 0.000699 loss: 4.7955 (4.7435) grad_norm: 1.5131 (1.4883) time: 0.5030 [2021-03-25 05:40:46 swin_small_patch4_window7_224] INFO: Epoch: [13] [1220/1251] eta: 0:00:15 lr: 0.000699 loss: 4.9075 (4.7432) grad_norm: 1.4321 (1.4877) time: 0.5038 [2021-03-25 05:40:51 swin_small_patch4_window7_224] INFO: Epoch: [13] [1230/1251] eta: 0:00:10 lr: 0.000699 loss: 4.8838 (4.7427) grad_norm: 1.4471 (1.4879) time: 0.5115 [2021-03-25 05:40:56 swin_small_patch4_window7_224] INFO: Epoch: [13] [1240/1251] eta: 0:00:05 lr: 0.000700 loss: 4.5445 (4.7385) grad_norm: 1.4566 (1.4872) time: 0.5106 [2021-03-25 05:41:01 swin_small_patch4_window7_224] INFO: Epoch: [13] [1250/1251] eta: 0:00:00 lr: 0.000700 loss: 4.6503 (4.7398) grad_norm: 1.4781 (1.4875) time: 0.4990 [2021-03-25 05:41:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:51 loss: 2.2264 (2.2264) acc1: 53.1250 (53.1250) acc5: 76.5625 (76.5625) [2021-03-25 05:41:07 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 2.1588 (2.1063) acc1: 53.1250 (53.6932) acc5: 78.1250 (77.9830) [2021-03-25 05:41:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 2.1175 (2.0714) acc1: 53.1250 (54.2411) acc5: 78.1250 (78.3482) [2021-03-25 05:41:11 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 2.0741 (2.0952) acc1: 54.6875 (53.9819) acc5: 78.1250 (78.0242) [2021-03-25 05:41:13 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.0741 (2.0750) acc1: 51.5625 (53.6204) acc5: 78.1250 (78.6966) [2021-03-25 05:41:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.0982 (2.0827) acc1: 51.5625 (53.1520) acc5: 78.1250 (78.6240) [2021-03-25 05:41:16 swin_small_patch4_window7_224] INFO: * Acc@1 53.668 Acc@5 78.700 loss 2.069 [2021-03-25 05:41:16 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 53.7% [2021-03-25 05:41:16 swin_small_patch4_window7_224] INFO: Max accuracy: 53.67% [2021-03-25 05:41:20 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 0/1251] eta: 1:28:00 lr: 0.000700 loss: 5.1386 (5.1386) grad_norm: 1.7005 (1.7005) time: 4.2207 [2021-03-25 05:41:26 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 10/1251] eta: 0:17:50 lr: 0.000701 loss: 5.1031 (4.8756) grad_norm: 1.5481 (1.4802) time: 0.8624 [2021-03-25 05:41:31 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 20/1251] eta: 0:14:11 lr: 0.000701 loss: 4.6792 (4.7180) grad_norm: 1.4034 (1.4403) time: 0.5150 [2021-03-25 05:41:36 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 30/1251] eta: 0:12:49 lr: 0.000701 loss: 4.8705 (4.7500) grad_norm: 1.4191 (1.4708) time: 0.5025 [2021-03-25 05:41:41 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 40/1251] eta: 0:12:06 lr: 0.000702 loss: 4.8169 (4.7074) grad_norm: 1.5355 (1.5048) time: 0.5042 [2021-03-25 05:41:46 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 50/1251] eta: 0:11:40 lr: 0.000702 loss: 4.6403 (4.6808) grad_norm: 1.5339 (1.5022) time: 0.5109 [2021-03-25 05:41:51 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 60/1251] eta: 0:11:18 lr: 0.000703 loss: 4.8429 (4.7277) grad_norm: 1.3613 (1.4940) time: 0.5081 [2021-03-25 05:41:56 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 70/1251] eta: 0:11:01 lr: 0.000703 loss: 4.8524 (4.7237) grad_norm: 1.3730 (1.4808) time: 0.5001 [2021-03-25 05:42:01 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 80/1251] eta: 0:10:47 lr: 0.000703 loss: 4.8864 (4.7360) grad_norm: 1.3941 (1.4734) time: 0.5006 [2021-03-25 05:42:06 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 90/1251] eta: 0:10:35 lr: 0.000704 loss: 4.9004 (4.7422) grad_norm: 1.3941 (1.4750) time: 0.5041 [2021-03-25 05:42:11 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 100/1251] eta: 0:10:26 lr: 0.000704 loss: 4.8117 (4.7406) grad_norm: 1.4149 (1.4745) time: 0.5087 [2021-03-25 05:42:16 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 110/1251] eta: 0:10:17 lr: 0.000705 loss: 4.9260 (4.7436) grad_norm: 1.4149 (1.4737) time: 0.5113 [2021-03-25 05:42:21 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 120/1251] eta: 0:10:09 lr: 0.000705 loss: 4.8297 (4.7243) grad_norm: 1.3980 (1.4722) time: 0.5110 [2021-03-25 05:42:26 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 130/1251] eta: 0:10:01 lr: 0.000705 loss: 4.8064 (4.7360) grad_norm: 1.3498 (1.4651) time: 0.5138 [2021-03-25 05:42:32 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 140/1251] eta: 0:09:54 lr: 0.000706 loss: 4.8527 (4.7359) grad_norm: 1.4013 (1.4705) time: 0.5152 [2021-03-25 05:42:37 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 150/1251] eta: 0:09:47 lr: 0.000706 loss: 4.7049 (4.7289) grad_norm: 1.3883 (1.4659) time: 0.5129 [2021-03-25 05:42:42 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 160/1251] eta: 0:09:40 lr: 0.000707 loss: 4.8708 (4.7491) grad_norm: 1.3762 (1.4672) time: 0.5058 [2021-03-25 05:42:47 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 170/1251] eta: 0:09:32 lr: 0.000707 loss: 4.8708 (4.7262) grad_norm: 1.3919 (1.4624) time: 0.5007 [2021-03-25 05:42:52 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 180/1251] eta: 0:09:26 lr: 0.000707 loss: 3.9846 (4.6913) grad_norm: 1.3764 (1.4631) time: 0.5101 [2021-03-25 05:42:57 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 190/1251] eta: 0:09:19 lr: 0.000708 loss: 4.5807 (4.7072) grad_norm: 1.4477 (1.4607) time: 0.5078 [2021-03-25 05:43:02 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 200/1251] eta: 0:09:14 lr: 0.000708 loss: 4.9768 (4.7123) grad_norm: 1.3982 (1.4583) time: 0.5115 [2021-03-25 05:43:07 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 210/1251] eta: 0:09:08 lr: 0.000709 loss: 4.6752 (4.7008) grad_norm: 1.3294 (1.4539) time: 0.5227 [2021-03-25 05:43:12 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 220/1251] eta: 0:09:02 lr: 0.000709 loss: 4.2910 (4.6977) grad_norm: 1.3294 (1.4522) time: 0.5119 [2021-03-25 05:43:17 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 230/1251] eta: 0:08:55 lr: 0.000709 loss: 4.7386 (4.7026) grad_norm: 1.4924 (1.4583) time: 0.5019 [2021-03-25 05:43:22 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 240/1251] eta: 0:08:49 lr: 0.000710 loss: 4.8491 (4.7094) grad_norm: 1.5393 (1.4657) time: 0.5038 [2021-03-25 05:43:27 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 250/1251] eta: 0:08:44 lr: 0.000710 loss: 4.8011 (4.7071) grad_norm: 1.4649 (1.4634) time: 0.5078 [2021-03-25 05:43:33 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 260/1251] eta: 0:08:38 lr: 0.000711 loss: 4.5859 (4.7068) grad_norm: 1.3646 (1.4607) time: 0.5073 [2021-03-25 05:43:38 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 270/1251] eta: 0:08:32 lr: 0.000711 loss: 4.8440 (4.7029) grad_norm: 1.3863 (1.4594) time: 0.5054 [2021-03-25 05:43:43 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 280/1251] eta: 0:08:26 lr: 0.000711 loss: 4.8533 (4.7038) grad_norm: 1.4372 (1.4626) time: 0.5049 [2021-03-25 05:43:48 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 290/1251] eta: 0:08:20 lr: 0.000712 loss: 4.7305 (4.7015) grad_norm: 1.4584 (1.4628) time: 0.5059 [2021-03-25 05:43:53 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 300/1251] eta: 0:08:15 lr: 0.000712 loss: 4.7247 (4.7040) grad_norm: 1.3959 (1.4610) time: 0.5080 [2021-03-25 05:43:58 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 310/1251] eta: 0:08:09 lr: 0.000713 loss: 4.7121 (4.6957) grad_norm: 1.3474 (1.4560) time: 0.5054 [2021-03-25 05:44:03 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 320/1251] eta: 0:08:04 lr: 0.000713 loss: 4.6032 (4.6945) grad_norm: 1.2670 (1.4519) time: 0.5118 [2021-03-25 05:44:08 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 330/1251] eta: 0:07:58 lr: 0.000713 loss: 4.8057 (4.7002) grad_norm: 1.2512 (1.4472) time: 0.5120 [2021-03-25 05:44:13 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 340/1251] eta: 0:07:52 lr: 0.000714 loss: 4.7962 (4.6951) grad_norm: 1.3024 (1.4485) time: 0.5019 [2021-03-25 05:44:18 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 350/1251] eta: 0:07:47 lr: 0.000714 loss: 4.5992 (4.6960) grad_norm: 1.4012 (1.4508) time: 0.4998 [2021-03-25 05:44:23 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 360/1251] eta: 0:07:41 lr: 0.000715 loss: 4.9689 (4.7010) grad_norm: 1.4010 (1.4480) time: 0.4991 [2021-03-25 05:44:28 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 370/1251] eta: 0:07:36 lr: 0.000715 loss: 4.9621 (4.6924) grad_norm: 1.4019 (1.4497) time: 0.5027 [2021-03-25 05:44:33 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 380/1251] eta: 0:07:30 lr: 0.000715 loss: 4.5834 (4.6937) grad_norm: 1.4008 (1.4466) time: 0.5024 [2021-03-25 05:44:38 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 390/1251] eta: 0:07:25 lr: 0.000716 loss: 4.8299 (4.6953) grad_norm: 1.4019 (1.4469) time: 0.5047 [2021-03-25 05:44:43 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 400/1251] eta: 0:07:19 lr: 0.000716 loss: 4.8702 (4.6980) grad_norm: 1.4242 (1.4467) time: 0.5090 [2021-03-25 05:44:48 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 410/1251] eta: 0:07:14 lr: 0.000717 loss: 4.9342 (4.7023) grad_norm: 1.3627 (1.4476) time: 0.5073 [2021-03-25 05:44:53 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 420/1251] eta: 0:07:08 lr: 0.000717 loss: 4.5804 (4.6987) grad_norm: 1.3589 (1.4454) time: 0.5033 [2021-03-25 05:44:58 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 430/1251] eta: 0:07:03 lr: 0.000717 loss: 4.7548 (4.7004) grad_norm: 1.3641 (1.4431) time: 0.5033 [2021-03-25 05:45:04 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 440/1251] eta: 0:06:58 lr: 0.000718 loss: 4.7548 (4.6942) grad_norm: 1.4225 (1.4482) time: 0.5116 [2021-03-25 05:45:09 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 450/1251] eta: 0:06:53 lr: 0.000718 loss: 4.5613 (4.6931) grad_norm: 1.5378 (1.4522) time: 0.5142 [2021-03-25 05:45:14 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 460/1251] eta: 0:06:47 lr: 0.000719 loss: 4.9137 (4.6999) grad_norm: 1.3973 (1.4497) time: 0.5051 [2021-03-25 05:45:19 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 470/1251] eta: 0:06:42 lr: 0.000719 loss: 4.8690 (4.6951) grad_norm: 1.3446 (1.4483) time: 0.5033 [2021-03-25 05:45:24 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 480/1251] eta: 0:06:37 lr: 0.000719 loss: 4.4323 (4.6915) grad_norm: 1.3591 (1.4459) time: 0.5051 [2021-03-25 05:45:29 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 490/1251] eta: 0:06:31 lr: 0.000720 loss: 4.9221 (4.6959) grad_norm: 1.3591 (1.4462) time: 0.5000 [2021-03-25 05:45:34 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 500/1251] eta: 0:06:26 lr: 0.000720 loss: 4.7499 (4.6934) grad_norm: 1.3711 (1.4479) time: 0.5008 [2021-03-25 05:45:39 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 510/1251] eta: 0:06:21 lr: 0.000721 loss: 4.7253 (4.6946) grad_norm: 1.4981 (1.4500) time: 0.5063 [2021-03-25 05:45:44 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 520/1251] eta: 0:06:15 lr: 0.000721 loss: 4.5830 (4.6922) grad_norm: 1.4641 (1.4476) time: 0.5061 [2021-03-25 05:45:49 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 530/1251] eta: 0:06:10 lr: 0.000721 loss: 4.7235 (4.6916) grad_norm: 1.3325 (1.4448) time: 0.4980 [2021-03-25 05:45:54 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 540/1251] eta: 0:06:05 lr: 0.000722 loss: 4.7235 (4.6868) grad_norm: 1.3869 (1.4466) time: 0.5060 [2021-03-25 05:45:59 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 550/1251] eta: 0:06:00 lr: 0.000722 loss: 4.7921 (4.6872) grad_norm: 1.4606 (1.4469) time: 0.5159 [2021-03-25 05:46:04 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 560/1251] eta: 0:05:54 lr: 0.000723 loss: 5.0028 (4.6915) grad_norm: 1.4886 (1.4482) time: 0.5081 [2021-03-25 05:46:09 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 570/1251] eta: 0:05:49 lr: 0.000723 loss: 4.8612 (4.6921) grad_norm: 1.3089 (1.4454) time: 0.5053 [2021-03-25 05:46:14 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 580/1251] eta: 0:05:44 lr: 0.000723 loss: 4.8774 (4.6969) grad_norm: 1.3313 (1.4463) time: 0.4991 [2021-03-25 05:46:19 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 590/1251] eta: 0:05:39 lr: 0.000724 loss: 5.0632 (4.7009) grad_norm: 1.3896 (1.4457) time: 0.4965 [2021-03-25 05:46:24 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 600/1251] eta: 0:05:33 lr: 0.000724 loss: 5.0060 (4.7021) grad_norm: 1.5776 (1.4504) time: 0.5034 [2021-03-25 05:46:29 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 610/1251] eta: 0:05:28 lr: 0.000725 loss: 4.8229 (4.6983) grad_norm: 1.4363 (1.4488) time: 0.5021 [2021-03-25 05:46:34 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 620/1251] eta: 0:05:23 lr: 0.000725 loss: 4.6137 (4.6957) grad_norm: 1.3742 (1.4481) time: 0.5017 [2021-03-25 05:46:39 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 630/1251] eta: 0:05:18 lr: 0.000725 loss: 4.7134 (4.6985) grad_norm: 1.3310 (1.4465) time: 0.5049 [2021-03-25 05:46:44 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 640/1251] eta: 0:05:12 lr: 0.000726 loss: 4.7134 (4.6967) grad_norm: 1.3285 (1.4451) time: 0.5039 [2021-03-25 05:46:49 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 650/1251] eta: 0:05:07 lr: 0.000726 loss: 4.6077 (4.6945) grad_norm: 1.4257 (1.4458) time: 0.5005 [2021-03-25 05:46:55 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 660/1251] eta: 0:05:02 lr: 0.000727 loss: 4.9178 (4.6976) grad_norm: 1.3644 (1.4450) time: 0.5046 [2021-03-25 05:47:00 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 670/1251] eta: 0:04:57 lr: 0.000727 loss: 5.0104 (4.6969) grad_norm: 1.3527 (1.4455) time: 0.5091 [2021-03-25 05:47:05 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 680/1251] eta: 0:04:52 lr: 0.000727 loss: 4.6417 (4.6968) grad_norm: 1.3387 (1.4442) time: 0.5069 [2021-03-25 05:47:10 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 690/1251] eta: 0:04:47 lr: 0.000728 loss: 4.8888 (4.6974) grad_norm: 1.3014 (1.4433) time: 0.5064 [2021-03-25 05:47:15 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 700/1251] eta: 0:04:41 lr: 0.000728 loss: 4.7397 (4.6994) grad_norm: 1.3561 (1.4424) time: 0.5067 [2021-03-25 05:47:20 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 710/1251] eta: 0:04:36 lr: 0.000729 loss: 4.7695 (4.7016) grad_norm: 1.3500 (1.4402) time: 0.5092 [2021-03-25 05:47:25 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 720/1251] eta: 0:04:31 lr: 0.000729 loss: 5.0949 (4.7052) grad_norm: 1.2728 (1.4384) time: 0.5067 [2021-03-25 05:47:30 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 730/1251] eta: 0:04:26 lr: 0.000729 loss: 5.1139 (4.7080) grad_norm: 1.3367 (1.4389) time: 0.5118 [2021-03-25 05:47:35 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 740/1251] eta: 0:04:21 lr: 0.000730 loss: 5.0258 (4.7109) grad_norm: 1.4022 (1.4388) time: 0.5177 [2021-03-25 05:47:41 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 750/1251] eta: 0:04:16 lr: 0.000730 loss: 4.9798 (4.7139) grad_norm: 1.3674 (1.4391) time: 0.5249 [2021-03-25 05:47:46 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 760/1251] eta: 0:04:11 lr: 0.000731 loss: 4.9674 (4.7164) grad_norm: 1.3458 (1.4388) time: 0.5227 [2021-03-25 05:47:51 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 770/1251] eta: 0:04:06 lr: 0.000731 loss: 4.8567 (4.7175) grad_norm: 1.3785 (1.4393) time: 0.5050 [2021-03-25 05:47:56 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 780/1251] eta: 0:04:00 lr: 0.000731 loss: 4.8567 (4.7151) grad_norm: 1.3206 (1.4374) time: 0.4985 [2021-03-25 05:48:01 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 790/1251] eta: 0:03:55 lr: 0.000732 loss: 4.9048 (4.7180) grad_norm: 1.3137 (1.4377) time: 0.4983 [2021-03-25 05:48:06 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 800/1251] eta: 0:03:50 lr: 0.000732 loss: 4.7208 (4.7172) grad_norm: 1.4415 (1.4371) time: 0.5063 [2021-03-25 05:48:11 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 810/1251] eta: 0:03:45 lr: 0.000733 loss: 4.8120 (4.7198) grad_norm: 1.3779 (1.4365) time: 0.5066 [2021-03-25 05:48:16 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 820/1251] eta: 0:03:40 lr: 0.000733 loss: 4.8120 (4.7176) grad_norm: 1.3212 (1.4362) time: 0.4959 [2021-03-25 05:48:21 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 830/1251] eta: 0:03:35 lr: 0.000733 loss: 4.5056 (4.7155) grad_norm: 1.3398 (1.4357) time: 0.4982 [2021-03-25 05:48:26 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 840/1251] eta: 0:03:30 lr: 0.000734 loss: 4.5056 (4.7134) grad_norm: 1.3357 (1.4345) time: 0.5072 [2021-03-25 05:48:31 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 850/1251] eta: 0:03:24 lr: 0.000734 loss: 4.6577 (4.7117) grad_norm: 1.3065 (1.4340) time: 0.5133 [2021-03-25 05:48:36 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 860/1251] eta: 0:03:19 lr: 0.000735 loss: 4.6577 (4.7108) grad_norm: 1.2631 (1.4335) time: 0.5117 [2021-03-25 05:48:41 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 870/1251] eta: 0:03:14 lr: 0.000735 loss: 4.8129 (4.7124) grad_norm: 1.4639 (1.4351) time: 0.5103 [2021-03-25 05:48:46 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 880/1251] eta: 0:03:09 lr: 0.000735 loss: 4.9569 (4.7105) grad_norm: 1.3215 (1.4339) time: 0.5132 [2021-03-25 05:48:51 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 890/1251] eta: 0:03:04 lr: 0.000736 loss: 4.7144 (4.7107) grad_norm: 1.3133 (1.4331) time: 0.5072 [2021-03-25 05:48:57 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 900/1251] eta: 0:02:59 lr: 0.000736 loss: 4.6861 (4.7110) grad_norm: 1.3614 (1.4336) time: 0.5027 [2021-03-25 05:49:02 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 910/1251] eta: 0:02:54 lr: 0.000737 loss: 4.4904 (4.7101) grad_norm: 1.4205 (1.4332) time: 0.5075 [2021-03-25 05:49:07 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 920/1251] eta: 0:02:49 lr: 0.000737 loss: 4.5291 (4.7073) grad_norm: 1.4109 (1.4336) time: 0.5086 [2021-03-25 05:49:12 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 930/1251] eta: 0:02:44 lr: 0.000737 loss: 4.5692 (4.7052) grad_norm: 1.3704 (1.4330) time: 0.5142 [2021-03-25 05:49:17 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 940/1251] eta: 0:02:38 lr: 0.000738 loss: 4.5692 (4.7029) grad_norm: 1.3500 (1.4331) time: 0.5164 [2021-03-25 05:49:22 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 950/1251] eta: 0:02:33 lr: 0.000738 loss: 4.3068 (4.7006) grad_norm: 1.3500 (1.4318) time: 0.5105 [2021-03-25 05:49:27 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 960/1251] eta: 0:02:28 lr: 0.000739 loss: 4.7348 (4.7027) grad_norm: 1.4409 (1.4330) time: 0.5095 [2021-03-25 05:49:32 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 970/1251] eta: 0:02:23 lr: 0.000739 loss: 4.9317 (4.7039) grad_norm: 1.4137 (1.4315) time: 0.5045 [2021-03-25 05:49:37 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 980/1251] eta: 0:02:18 lr: 0.000739 loss: 5.0053 (4.7049) grad_norm: 1.3123 (1.4312) time: 0.5041 [2021-03-25 05:49:42 swin_small_patch4_window7_224] INFO: Epoch: [14] [ 990/1251] eta: 0:02:13 lr: 0.000740 loss: 4.9064 (4.7056) grad_norm: 1.3076 (1.4297) time: 0.5110 [2021-03-25 05:49:47 swin_small_patch4_window7_224] INFO: Epoch: [14] [1000/1251] eta: 0:02:08 lr: 0.000740 loss: 4.9064 (4.7058) grad_norm: 1.2262 (1.4284) time: 0.5092 [2021-03-25 05:49:52 swin_small_patch4_window7_224] INFO: Epoch: [14] [1010/1251] eta: 0:02:03 lr: 0.000741 loss: 4.7918 (4.7064) grad_norm: 1.1961 (1.4261) time: 0.5010 [2021-03-25 05:49:58 swin_small_patch4_window7_224] INFO: Epoch: [14] [1020/1251] eta: 0:01:57 lr: 0.000741 loss: 4.5587 (4.7066) grad_norm: 1.2192 (1.4251) time: 0.5010 [2021-03-25 05:50:03 swin_small_patch4_window7_224] INFO: Epoch: [14] [1030/1251] eta: 0:01:52 lr: 0.000741 loss: 4.3676 (4.7021) grad_norm: 1.3445 (1.4260) time: 0.5036 [2021-03-25 05:50:08 swin_small_patch4_window7_224] INFO: Epoch: [14] [1040/1251] eta: 0:01:47 lr: 0.000742 loss: 4.6655 (4.7038) grad_norm: 1.3686 (1.4251) time: 0.5010 [2021-03-25 05:50:13 swin_small_patch4_window7_224] INFO: Epoch: [14] [1050/1251] eta: 0:01:42 lr: 0.000742 loss: 4.7440 (4.7008) grad_norm: 1.4021 (1.4256) time: 0.5046 [2021-03-25 05:50:18 swin_small_patch4_window7_224] INFO: Epoch: [14] [1060/1251] eta: 0:01:37 lr: 0.000743 loss: 4.6387 (4.7004) grad_norm: 1.4478 (1.4258) time: 0.5132 [2021-03-25 05:50:23 swin_small_patch4_window7_224] INFO: Epoch: [14] [1070/1251] eta: 0:01:32 lr: 0.000743 loss: 4.6091 (4.6992) grad_norm: 1.4287 (1.4252) time: 0.5143 [2021-03-25 05:50:28 swin_small_patch4_window7_224] INFO: Epoch: [14] [1080/1251] eta: 0:01:27 lr: 0.000743 loss: 4.5568 (4.6984) grad_norm: 1.3156 (1.4244) time: 0.5096 [2021-03-25 05:50:33 swin_small_patch4_window7_224] INFO: Epoch: [14] [1090/1251] eta: 0:01:22 lr: 0.000744 loss: 4.6955 (4.6983) grad_norm: 1.3156 (1.4239) time: 0.5054 [2021-03-25 05:50:38 swin_small_patch4_window7_224] INFO: Epoch: [14] [1100/1251] eta: 0:01:17 lr: 0.000744 loss: 4.7814 (4.6982) grad_norm: 1.4515 (1.4264) time: 0.5015 [2021-03-25 05:50:43 swin_small_patch4_window7_224] INFO: Epoch: [14] [1110/1251] eta: 0:01:11 lr: 0.000745 loss: 4.7225 (4.6953) grad_norm: 1.4099 (1.4261) time: 0.5042 [2021-03-25 05:50:48 swin_small_patch4_window7_224] INFO: Epoch: [14] [1120/1251] eta: 0:01:06 lr: 0.000745 loss: 4.4183 (4.6923) grad_norm: 1.2732 (1.4243) time: 0.5098 [2021-03-25 05:50:53 swin_small_patch4_window7_224] INFO: Epoch: [14] [1130/1251] eta: 0:01:01 lr: 0.000745 loss: 4.5852 (4.6932) grad_norm: 1.2633 (1.4237) time: 0.5039 [2021-03-25 05:50:58 swin_small_patch4_window7_224] INFO: Epoch: [14] [1140/1251] eta: 0:00:56 lr: 0.000746 loss: 4.7525 (4.6931) grad_norm: 1.4867 (1.4252) time: 0.5044 [2021-03-25 05:51:03 swin_small_patch4_window7_224] INFO: Epoch: [14] [1150/1251] eta: 0:00:51 lr: 0.000746 loss: 4.6870 (4.6922) grad_norm: 1.5043 (1.4248) time: 0.5064 [2021-03-25 05:51:08 swin_small_patch4_window7_224] INFO: Epoch: [14] [1160/1251] eta: 0:00:46 lr: 0.000747 loss: 4.5737 (4.6909) grad_norm: 1.3381 (1.4243) time: 0.5056 [2021-03-25 05:51:13 swin_small_patch4_window7_224] INFO: Epoch: [14] [1170/1251] eta: 0:00:41 lr: 0.000747 loss: 4.6210 (4.6904) grad_norm: 1.3250 (1.4245) time: 0.5061 [2021-03-25 05:51:19 swin_small_patch4_window7_224] INFO: Epoch: [14] [1180/1251] eta: 0:00:36 lr: 0.000747 loss: 4.8605 (4.6921) grad_norm: 1.4168 (1.4263) time: 0.5091 [2021-03-25 05:51:24 swin_small_patch4_window7_224] INFO: Epoch: [14] [1190/1251] eta: 0:00:31 lr: 0.000748 loss: 4.7688 (4.6911) grad_norm: 1.4835 (1.4264) time: 0.5085 [2021-03-25 05:51:29 swin_small_patch4_window7_224] INFO: Epoch: [14] [1200/1251] eta: 0:00:26 lr: 0.000748 loss: 4.2380 (4.6878) grad_norm: 1.4605 (1.4273) time: 0.4990 [2021-03-25 05:51:34 swin_small_patch4_window7_224] INFO: Epoch: [14] [1210/1251] eta: 0:00:20 lr: 0.000749 loss: 4.3774 (4.6865) grad_norm: 1.4201 (1.4260) time: 0.4982 [2021-03-25 05:51:39 swin_small_patch4_window7_224] INFO: Epoch: [14] [1220/1251] eta: 0:00:15 lr: 0.000749 loss: 4.4766 (4.6847) grad_norm: 1.2920 (1.4253) time: 0.5002 [2021-03-25 05:51:44 swin_small_patch4_window7_224] INFO: Epoch: [14] [1230/1251] eta: 0:00:10 lr: 0.000749 loss: 4.5664 (4.6846) grad_norm: 1.3214 (1.4246) time: 0.5007 [2021-03-25 05:51:49 swin_small_patch4_window7_224] INFO: Epoch: [14] [1240/1251] eta: 0:00:05 lr: 0.000750 loss: 4.5272 (4.6833) grad_norm: 1.3412 (1.4248) time: 0.5053 [2021-03-25 05:51:54 swin_small_patch4_window7_224] INFO: Epoch: [14] [1250/1251] eta: 0:00:00 lr: 0.000750 loss: 4.5597 (4.6821) grad_norm: 1.4295 (1.4248) time: 0.5113 [2021-03-25 05:51:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:25 loss: 2.1359 (2.1359) acc1: 53.1250 (53.1250) acc5: 79.6875 (79.6875) [2021-03-25 05:52:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.9973 (2.0163) acc1: 54.6875 (53.6932) acc5: 79.6875 (77.9830) [2021-03-25 05:52:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.9412 (1.9679) acc1: 57.8125 (55.8036) acc5: 78.1250 (79.0179) [2021-03-25 05:52:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.9412 (1.9968) acc1: 57.8125 (55.7964) acc5: 78.1250 (78.9315) [2021-03-25 05:52:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 2.0660 (2.0021) acc1: 54.6875 (55.7546) acc5: 79.6875 (79.2302) [2021-03-25 05:52:07 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 2.0660 (2.0101) acc1: 51.5625 (54.9760) acc5: 79.6875 (79.6800) [2021-03-25 05:52:09 swin_small_patch4_window7_224] INFO: * Acc@1 55.368 Acc@5 80.090 loss 1.999 [2021-03-25 05:52:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 55.4% [2021-03-25 05:52:09 swin_small_patch4_window7_224] INFO: Max accuracy: 55.37% [2021-03-25 05:52:13 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 0/1251] eta: 1:20:51 lr: 0.000750 loss: 4.8711 (4.8711) grad_norm: 1.3353 (1.3353) time: 3.8784 [2021-03-25 05:52:18 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 10/1251] eta: 0:17:30 lr: 0.000751 loss: 4.8711 (4.8164) grad_norm: 1.2041 (1.2578) time: 0.8464 [2021-03-25 05:52:24 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 20/1251] eta: 0:14:09 lr: 0.000751 loss: 4.7717 (4.8209) grad_norm: 1.2614 (1.3645) time: 0.5311 [2021-03-25 05:52:29 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 30/1251] eta: 0:12:48 lr: 0.000751 loss: 4.7055 (4.7632) grad_norm: 1.3005 (1.3657) time: 0.5105 [2021-03-25 05:52:34 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 40/1251] eta: 0:12:14 lr: 0.000752 loss: 4.6861 (4.7306) grad_norm: 1.2759 (1.3859) time: 0.5183 [2021-03-25 05:52:39 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 50/1251] eta: 0:11:43 lr: 0.000752 loss: 4.7099 (4.7538) grad_norm: 1.2298 (1.3563) time: 0.5180 [2021-03-25 05:52:44 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 60/1251] eta: 0:11:22 lr: 0.000753 loss: 4.6417 (4.6953) grad_norm: 1.2749 (1.3843) time: 0.5047 [2021-03-25 05:52:49 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 70/1251] eta: 0:11:06 lr: 0.000753 loss: 4.6417 (4.6515) grad_norm: 1.4060 (1.3993) time: 0.5083 [2021-03-25 05:52:54 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 80/1251] eta: 0:10:51 lr: 0.000753 loss: 4.7326 (4.6415) grad_norm: 1.4322 (1.4116) time: 0.5066 [2021-03-25 05:52:59 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 90/1251] eta: 0:10:41 lr: 0.000754 loss: 4.4437 (4.6240) grad_norm: 1.4183 (1.4037) time: 0.5119 [2021-03-25 05:53:04 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 100/1251] eta: 0:10:30 lr: 0.000754 loss: 4.7787 (4.6508) grad_norm: 1.3135 (1.4094) time: 0.5128 [2021-03-25 05:53:09 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 110/1251] eta: 0:10:20 lr: 0.000755 loss: 4.8201 (4.6376) grad_norm: 1.2718 (1.4060) time: 0.5055 [2021-03-25 05:53:14 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 120/1251] eta: 0:10:11 lr: 0.000755 loss: 4.7703 (4.6474) grad_norm: 1.2590 (1.3929) time: 0.5053 [2021-03-25 05:53:20 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 130/1251] eta: 0:10:03 lr: 0.000755 loss: 4.8085 (4.6747) grad_norm: 1.3225 (1.3966) time: 0.5093 [2021-03-25 05:53:25 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 140/1251] eta: 0:09:55 lr: 0.000756 loss: 4.7201 (4.6728) grad_norm: 1.3547 (1.3994) time: 0.5041 [2021-03-25 05:53:30 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 150/1251] eta: 0:09:47 lr: 0.000756 loss: 4.6728 (4.6611) grad_norm: 1.3294 (1.3977) time: 0.5002 [2021-03-25 05:53:35 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 160/1251] eta: 0:09:40 lr: 0.000757 loss: 4.6698 (4.6622) grad_norm: 1.3605 (1.3970) time: 0.5054 [2021-03-25 05:53:40 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 170/1251] eta: 0:09:34 lr: 0.000757 loss: 4.6843 (4.6554) grad_norm: 1.4245 (1.4055) time: 0.5128 [2021-03-25 05:53:45 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 180/1251] eta: 0:09:27 lr: 0.000757 loss: 4.5365 (4.6402) grad_norm: 1.4245 (1.4042) time: 0.5173 [2021-03-25 05:53:50 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 190/1251] eta: 0:09:21 lr: 0.000758 loss: 4.4969 (4.6255) grad_norm: 1.3054 (1.4056) time: 0.5092 [2021-03-25 05:53:55 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 200/1251] eta: 0:09:14 lr: 0.000758 loss: 4.6158 (4.6307) grad_norm: 1.3680 (1.4052) time: 0.5049 [2021-03-25 05:54:00 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 210/1251] eta: 0:09:08 lr: 0.000759 loss: 4.8316 (4.6473) grad_norm: 1.3680 (1.4054) time: 0.5042 [2021-03-25 05:54:05 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 220/1251] eta: 0:09:01 lr: 0.000759 loss: 4.8316 (4.6442) grad_norm: 1.4021 (1.4068) time: 0.5044 [2021-03-25 05:54:10 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 230/1251] eta: 0:08:56 lr: 0.000759 loss: 4.5275 (4.6414) grad_norm: 1.4021 (1.4107) time: 0.5086 [2021-03-25 05:54:15 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 240/1251] eta: 0:08:50 lr: 0.000760 loss: 4.5542 (4.6448) grad_norm: 1.2661 (1.4050) time: 0.5109 [2021-03-25 05:54:20 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 250/1251] eta: 0:08:44 lr: 0.000760 loss: 4.8794 (4.6485) grad_norm: 1.2545 (1.4028) time: 0.5062 [2021-03-25 05:54:25 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 260/1251] eta: 0:08:37 lr: 0.000761 loss: 4.7238 (4.6481) grad_norm: 1.4754 (1.4100) time: 0.5000 [2021-03-25 05:54:30 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 270/1251] eta: 0:08:31 lr: 0.000761 loss: 4.7000 (4.6422) grad_norm: 1.4754 (1.4094) time: 0.4996 [2021-03-25 05:54:35 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 280/1251] eta: 0:08:25 lr: 0.000761 loss: 4.4668 (4.6347) grad_norm: 1.3360 (1.4062) time: 0.4981 [2021-03-25 05:54:40 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 290/1251] eta: 0:08:19 lr: 0.000762 loss: 4.6732 (4.6383) grad_norm: 1.2634 (1.3998) time: 0.4976 [2021-03-25 05:54:46 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 300/1251] eta: 0:08:14 lr: 0.000762 loss: 4.7029 (4.6410) grad_norm: 1.2088 (1.3945) time: 0.5040 [2021-03-25 05:54:51 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 310/1251] eta: 0:08:08 lr: 0.000763 loss: 4.7403 (4.6446) grad_norm: 1.2560 (1.3919) time: 0.5075 [2021-03-25 05:54:55 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 320/1251] eta: 0:08:02 lr: 0.000763 loss: 4.8613 (4.6488) grad_norm: 1.3352 (1.3916) time: 0.4987 [2021-03-25 05:55:00 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 330/1251] eta: 0:07:56 lr: 0.000763 loss: 4.7323 (4.6463) grad_norm: 1.3600 (1.3919) time: 0.4963 [2021-03-25 05:55:06 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 340/1251] eta: 0:07:51 lr: 0.000764 loss: 4.7575 (4.6532) grad_norm: 1.4598 (1.3950) time: 0.5022 [2021-03-25 05:55:11 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 350/1251] eta: 0:07:45 lr: 0.000764 loss: 4.7877 (4.6543) grad_norm: 1.3877 (1.3943) time: 0.5011 [2021-03-25 05:55:16 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 360/1251] eta: 0:07:40 lr: 0.000765 loss: 4.7542 (4.6542) grad_norm: 1.2902 (1.3909) time: 0.4995 [2021-03-25 05:55:21 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 370/1251] eta: 0:07:34 lr: 0.000765 loss: 4.4706 (4.6434) grad_norm: 1.3513 (1.3924) time: 0.5035 [2021-03-25 05:55:26 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 380/1251] eta: 0:07:29 lr: 0.000765 loss: 4.3147 (4.6432) grad_norm: 1.3926 (1.3922) time: 0.5046 [2021-03-25 05:55:31 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 390/1251] eta: 0:07:24 lr: 0.000766 loss: 4.6952 (4.6386) grad_norm: 1.3951 (1.3936) time: 0.5062 [2021-03-25 05:55:36 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 400/1251] eta: 0:07:18 lr: 0.000766 loss: 4.6952 (4.6374) grad_norm: 1.4126 (1.3933) time: 0.5055 [2021-03-25 05:55:41 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 410/1251] eta: 0:07:13 lr: 0.000767 loss: 5.1172 (4.6484) grad_norm: 1.3252 (1.3916) time: 0.5017 [2021-03-25 05:55:46 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 420/1251] eta: 0:07:07 lr: 0.000767 loss: 5.1001 (4.6520) grad_norm: 1.3076 (1.3914) time: 0.5006 [2021-03-25 05:55:51 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 430/1251] eta: 0:07:02 lr: 0.000767 loss: 4.8669 (4.6528) grad_norm: 1.3076 (1.3909) time: 0.5004 [2021-03-25 05:55:56 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 440/1251] eta: 0:06:56 lr: 0.000768 loss: 4.8137 (4.6543) grad_norm: 1.2670 (1.3887) time: 0.5023 [2021-03-25 05:56:01 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 450/1251] eta: 0:06:51 lr: 0.000768 loss: 4.8137 (4.6616) grad_norm: 1.2506 (1.3871) time: 0.5052 [2021-03-25 05:56:06 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 460/1251] eta: 0:06:46 lr: 0.000769 loss: 4.9462 (4.6654) grad_norm: 1.2506 (1.3863) time: 0.5081 [2021-03-25 05:56:11 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 470/1251] eta: 0:06:41 lr: 0.000769 loss: 4.8774 (4.6685) grad_norm: 1.2620 (1.3854) time: 0.5059 [2021-03-25 05:56:16 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 480/1251] eta: 0:06:35 lr: 0.000769 loss: 4.7566 (4.6628) grad_norm: 1.2810 (1.3842) time: 0.5076 [2021-03-25 05:56:21 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 490/1251] eta: 0:06:30 lr: 0.000770 loss: 4.6526 (4.6617) grad_norm: 1.2732 (1.3842) time: 0.5087 [2021-03-25 05:56:26 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 500/1251] eta: 0:06:25 lr: 0.000770 loss: 4.5095 (4.6590) grad_norm: 1.2986 (1.3829) time: 0.5018 [2021-03-25 05:56:31 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 510/1251] eta: 0:06:20 lr: 0.000771 loss: 4.5095 (4.6547) grad_norm: 1.3746 (1.3840) time: 0.5050 [2021-03-25 05:56:36 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 520/1251] eta: 0:06:14 lr: 0.000771 loss: 4.5536 (4.6495) grad_norm: 1.3251 (1.3827) time: 0.5106 [2021-03-25 05:56:41 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 530/1251] eta: 0:06:09 lr: 0.000771 loss: 4.6977 (4.6488) grad_norm: 1.3189 (1.3832) time: 0.5085 [2021-03-25 05:56:47 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 540/1251] eta: 0:06:04 lr: 0.000772 loss: 4.5914 (4.6493) grad_norm: 1.2743 (1.3808) time: 0.5099 [2021-03-25 05:56:52 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 550/1251] eta: 0:05:59 lr: 0.000772 loss: 4.5852 (4.6466) grad_norm: 1.2743 (1.3814) time: 0.5136 [2021-03-25 05:56:57 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 560/1251] eta: 0:05:54 lr: 0.000773 loss: 4.6272 (4.6459) grad_norm: 1.3967 (1.3820) time: 0.5087 [2021-03-25 05:57:02 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 570/1251] eta: 0:05:49 lr: 0.000773 loss: 4.6560 (4.6447) grad_norm: 1.2820 (1.3797) time: 0.5086 [2021-03-25 05:57:07 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 580/1251] eta: 0:05:43 lr: 0.000773 loss: 4.7912 (4.6499) grad_norm: 1.2617 (1.3789) time: 0.5110 [2021-03-25 05:57:12 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 590/1251] eta: 0:05:38 lr: 0.000774 loss: 4.8831 (4.6474) grad_norm: 1.3033 (1.3791) time: 0.5089 [2021-03-25 05:57:17 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 600/1251] eta: 0:05:33 lr: 0.000774 loss: 4.7929 (4.6487) grad_norm: 1.3587 (1.3785) time: 0.5133 [2021-03-25 05:57:22 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 610/1251] eta: 0:05:28 lr: 0.000775 loss: 4.5715 (4.6447) grad_norm: 1.4421 (1.3801) time: 0.5079 [2021-03-25 05:57:27 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 620/1251] eta: 0:05:23 lr: 0.000775 loss: 4.3903 (4.6407) grad_norm: 1.3978 (1.3792) time: 0.4989 [2021-03-25 05:57:32 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 630/1251] eta: 0:05:17 lr: 0.000775 loss: 4.4896 (4.6352) grad_norm: 1.3304 (1.3781) time: 0.4960 [2021-03-25 05:57:37 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 640/1251] eta: 0:05:12 lr: 0.000776 loss: 4.6588 (4.6401) grad_norm: 1.3054 (1.3777) time: 0.5054 [2021-03-25 05:57:42 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 650/1251] eta: 0:05:07 lr: 0.000776 loss: 4.9859 (4.6430) grad_norm: 1.3013 (1.3772) time: 0.5139 [2021-03-25 05:57:47 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 660/1251] eta: 0:05:02 lr: 0.000777 loss: 5.0600 (4.6493) grad_norm: 1.3863 (1.3780) time: 0.5069 [2021-03-25 05:57:53 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 670/1251] eta: 0:04:57 lr: 0.000777 loss: 4.8753 (4.6470) grad_norm: 1.3974 (1.3798) time: 0.5030 [2021-03-25 05:57:58 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 680/1251] eta: 0:04:52 lr: 0.000777 loss: 4.5803 (4.6488) grad_norm: 1.3525 (1.3792) time: 0.5079 [2021-03-25 05:58:03 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 690/1251] eta: 0:04:47 lr: 0.000778 loss: 4.8555 (4.6518) grad_norm: 1.3059 (1.3796) time: 0.5076 [2021-03-25 05:58:08 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 700/1251] eta: 0:04:41 lr: 0.000778 loss: 4.7884 (4.6534) grad_norm: 1.3069 (1.3804) time: 0.5038 [2021-03-25 05:58:13 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 710/1251] eta: 0:04:36 lr: 0.000779 loss: 4.7884 (4.6534) grad_norm: 1.3434 (1.3802) time: 0.5058 [2021-03-25 05:58:18 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 720/1251] eta: 0:04:31 lr: 0.000779 loss: 4.8808 (4.6557) grad_norm: 1.4234 (1.3802) time: 0.5092 [2021-03-25 05:58:23 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 730/1251] eta: 0:04:26 lr: 0.000779 loss: 4.6847 (4.6535) grad_norm: 1.2888 (1.3793) time: 0.5136 [2021-03-25 05:58:28 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 740/1251] eta: 0:04:21 lr: 0.000780 loss: 4.5344 (4.6498) grad_norm: 1.1788 (1.3763) time: 0.5178 [2021-03-25 05:58:33 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 750/1251] eta: 0:04:16 lr: 0.000780 loss: 4.4606 (4.6482) grad_norm: 1.2985 (1.3763) time: 0.5131 [2021-03-25 05:58:38 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 760/1251] eta: 0:04:11 lr: 0.000781 loss: 4.7124 (4.6485) grad_norm: 1.3099 (1.3769) time: 0.5115 [2021-03-25 05:58:44 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 770/1251] eta: 0:04:06 lr: 0.000781 loss: 4.7773 (4.6501) grad_norm: 1.3465 (1.3768) time: 0.5122 [2021-03-25 05:58:49 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 780/1251] eta: 0:04:00 lr: 0.000781 loss: 4.9312 (4.6520) grad_norm: 1.3465 (1.3762) time: 0.5102 [2021-03-25 05:58:54 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 790/1251] eta: 0:03:55 lr: 0.000782 loss: 4.7648 (4.6486) grad_norm: 1.2888 (1.3745) time: 0.5158 [2021-03-25 05:58:59 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 800/1251] eta: 0:03:50 lr: 0.000782 loss: 4.6748 (4.6503) grad_norm: 1.2675 (1.3744) time: 0.5082 [2021-03-25 05:59:04 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 810/1251] eta: 0:03:45 lr: 0.000783 loss: 4.7946 (4.6525) grad_norm: 1.3563 (1.3742) time: 0.5008 [2021-03-25 05:59:09 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 820/1251] eta: 0:03:40 lr: 0.000783 loss: 4.7640 (4.6508) grad_norm: 1.3297 (1.3740) time: 0.5081 [2021-03-25 05:59:14 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 830/1251] eta: 0:03:35 lr: 0.000783 loss: 4.6691 (4.6527) grad_norm: 1.3271 (1.3736) time: 0.5112 [2021-03-25 05:59:19 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 840/1251] eta: 0:03:30 lr: 0.000784 loss: 4.7553 (4.6533) grad_norm: 1.3539 (1.3757) time: 0.5111 [2021-03-25 05:59:24 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 850/1251] eta: 0:03:25 lr: 0.000784 loss: 4.7200 (4.6525) grad_norm: 1.3335 (1.3744) time: 0.5107 [2021-03-25 05:59:29 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 860/1251] eta: 0:03:19 lr: 0.000785 loss: 4.6746 (4.6543) grad_norm: 1.3250 (1.3747) time: 0.5046 [2021-03-25 05:59:34 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 870/1251] eta: 0:03:14 lr: 0.000785 loss: 4.7631 (4.6535) grad_norm: 1.3905 (1.3748) time: 0.5062 [2021-03-25 05:59:39 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 880/1251] eta: 0:03:09 lr: 0.000785 loss: 4.6762 (4.6517) grad_norm: 1.3905 (1.3745) time: 0.5018 [2021-03-25 05:59:44 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 890/1251] eta: 0:03:04 lr: 0.000786 loss: 4.1580 (4.6474) grad_norm: 1.4610 (1.3763) time: 0.5001 [2021-03-25 05:59:50 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 900/1251] eta: 0:02:59 lr: 0.000786 loss: 4.2615 (4.6466) grad_norm: 1.4610 (1.3759) time: 0.5111 [2021-03-25 05:59:55 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 910/1251] eta: 0:02:54 lr: 0.000787 loss: 4.7084 (4.6456) grad_norm: 1.2629 (1.3748) time: 0.5087 [2021-03-25 06:00:00 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 920/1251] eta: 0:02:49 lr: 0.000787 loss: 4.6674 (4.6458) grad_norm: 1.2629 (1.3748) time: 0.5092 [2021-03-25 06:00:05 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 930/1251] eta: 0:02:44 lr: 0.000787 loss: 4.7292 (4.6440) grad_norm: 1.2702 (1.3739) time: 0.5155 [2021-03-25 06:00:10 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 940/1251] eta: 0:02:38 lr: 0.000788 loss: 4.7534 (4.6453) grad_norm: 1.2702 (1.3734) time: 0.5092 [2021-03-25 06:00:15 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 950/1251] eta: 0:02:33 lr: 0.000788 loss: 4.5645 (4.6419) grad_norm: 1.3639 (1.3735) time: 0.5046 [2021-03-25 06:00:20 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 960/1251] eta: 0:02:28 lr: 0.000789 loss: 4.5645 (4.6445) grad_norm: 1.2367 (1.3717) time: 0.5090 [2021-03-25 06:00:25 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 970/1251] eta: 0:02:23 lr: 0.000789 loss: 4.8681 (4.6456) grad_norm: 1.1749 (1.3699) time: 0.5106 [2021-03-25 06:00:30 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 980/1251] eta: 0:02:18 lr: 0.000789 loss: 4.7455 (4.6445) grad_norm: 1.1738 (1.3683) time: 0.5040 [2021-03-25 06:00:35 swin_small_patch4_window7_224] INFO: Epoch: [15] [ 990/1251] eta: 0:02:13 lr: 0.000790 loss: 4.5861 (4.6432) grad_norm: 1.1916 (1.3682) time: 0.4989 [2021-03-25 06:00:40 swin_small_patch4_window7_224] INFO: Epoch: [15] [1000/1251] eta: 0:02:08 lr: 0.000790 loss: 4.8446 (4.6455) grad_norm: 1.3139 (1.3680) time: 0.5023 [2021-03-25 06:00:45 swin_small_patch4_window7_224] INFO: Epoch: [15] [1010/1251] eta: 0:02:03 lr: 0.000791 loss: 4.9060 (4.6447) grad_norm: 1.3989 (1.3689) time: 0.5032 [2021-03-25 06:00:50 swin_small_patch4_window7_224] INFO: Epoch: [15] [1020/1251] eta: 0:01:57 lr: 0.000791 loss: 4.3549 (4.6427) grad_norm: 1.4672 (1.3698) time: 0.5037 [2021-03-25 06:00:55 swin_small_patch4_window7_224] INFO: Epoch: [15] [1030/1251] eta: 0:01:52 lr: 0.000791 loss: 4.5231 (4.6429) grad_norm: 1.3946 (1.3694) time: 0.5038 [2021-03-25 06:01:00 swin_small_patch4_window7_224] INFO: Epoch: [15] [1040/1251] eta: 0:01:47 lr: 0.000792 loss: 4.6891 (4.6413) grad_norm: 1.2609 (1.3686) time: 0.5022 [2021-03-25 06:01:05 swin_small_patch4_window7_224] INFO: Epoch: [15] [1050/1251] eta: 0:01:42 lr: 0.000792 loss: 4.3173 (4.6370) grad_norm: 1.2581 (1.3675) time: 0.5032 [2021-03-25 06:01:11 swin_small_patch4_window7_224] INFO: Epoch: [15] [1060/1251] eta: 0:01:37 lr: 0.000793 loss: 4.2683 (4.6344) grad_norm: 1.2619 (1.3671) time: 0.5064 [2021-03-25 06:01:16 swin_small_patch4_window7_224] INFO: Epoch: [15] [1070/1251] eta: 0:01:32 lr: 0.000793 loss: 4.6497 (4.6344) grad_norm: 1.2619 (1.3664) time: 0.5060 [2021-03-25 06:01:21 swin_small_patch4_window7_224] INFO: Epoch: [15] [1080/1251] eta: 0:01:27 lr: 0.000793 loss: 4.7531 (4.6343) grad_norm: 1.2514 (1.3667) time: 0.5036 [2021-03-25 06:01:26 swin_small_patch4_window7_224] INFO: Epoch: [15] [1090/1251] eta: 0:01:22 lr: 0.000794 loss: 4.6176 (4.6312) grad_norm: 1.3762 (1.3675) time: 0.5042 [2021-03-25 06:01:31 swin_small_patch4_window7_224] INFO: Epoch: [15] [1100/1251] eta: 0:01:17 lr: 0.000794 loss: 4.6176 (4.6327) grad_norm: 1.3596 (1.3675) time: 0.5000 [2021-03-25 06:01:36 swin_small_patch4_window7_224] INFO: Epoch: [15] [1110/1251] eta: 0:01:11 lr: 0.000795 loss: 4.7432 (4.6321) grad_norm: 1.3254 (1.3677) time: 0.5004 [2021-03-25 06:01:41 swin_small_patch4_window7_224] INFO: Epoch: [15] [1120/1251] eta: 0:01:06 lr: 0.000795 loss: 4.7432 (4.6339) grad_norm: 1.2964 (1.3672) time: 0.5131 [2021-03-25 06:01:46 swin_small_patch4_window7_224] INFO: Epoch: [15] [1130/1251] eta: 0:01:01 lr: 0.000795 loss: 5.0179 (4.6350) grad_norm: 1.2823 (1.3675) time: 0.5139 [2021-03-25 06:01:51 swin_small_patch4_window7_224] INFO: Epoch: [15] [1140/1251] eta: 0:00:56 lr: 0.000796 loss: 4.8316 (4.6341) grad_norm: 1.2823 (1.3669) time: 0.5038 [2021-03-25 06:01:56 swin_small_patch4_window7_224] INFO: Epoch: [15] [1150/1251] eta: 0:00:51 lr: 0.000796 loss: 4.7568 (4.6340) grad_norm: 1.2644 (1.3670) time: 0.5052 [2021-03-25 06:02:01 swin_small_patch4_window7_224] INFO: Epoch: [15] [1160/1251] eta: 0:00:46 lr: 0.000797 loss: 4.7568 (4.6346) grad_norm: 1.4313 (1.3684) time: 0.5072 [2021-03-25 06:02:06 swin_small_patch4_window7_224] INFO: Epoch: [15] [1170/1251] eta: 0:00:41 lr: 0.000797 loss: 4.7242 (4.6351) grad_norm: 1.3128 (1.3675) time: 0.5036 [2021-03-25 06:02:11 swin_small_patch4_window7_224] INFO: Epoch: [15] [1180/1251] eta: 0:00:36 lr: 0.000797 loss: 4.5627 (4.6333) grad_norm: 1.2411 (1.3671) time: 0.5026 [2021-03-25 06:02:16 swin_small_patch4_window7_224] INFO: Epoch: [15] [1190/1251] eta: 0:00:31 lr: 0.000798 loss: 4.6647 (4.6335) grad_norm: 1.2336 (1.3665) time: 0.5003 [2021-03-25 06:02:21 swin_small_patch4_window7_224] INFO: Epoch: [15] [1200/1251] eta: 0:00:25 lr: 0.000798 loss: 4.7568 (4.6329) grad_norm: 1.2666 (1.3659) time: 0.4970 [2021-03-25 06:02:26 swin_small_patch4_window7_224] INFO: Epoch: [15] [1210/1251] eta: 0:00:20 lr: 0.000799 loss: 4.6473 (4.6320) grad_norm: 1.3084 (1.3669) time: 0.4990 [2021-03-25 06:02:31 swin_small_patch4_window7_224] INFO: Epoch: [15] [1220/1251] eta: 0:00:15 lr: 0.000799 loss: 4.5804 (4.6307) grad_norm: 1.3414 (1.3666) time: 0.5054 [2021-03-25 06:02:36 swin_small_patch4_window7_224] INFO: Epoch: [15] [1230/1251] eta: 0:00:10 lr: 0.000799 loss: 4.6578 (4.6301) grad_norm: 1.3229 (1.3665) time: 0.5043 [2021-03-25 06:02:41 swin_small_patch4_window7_224] INFO: Epoch: [15] [1240/1251] eta: 0:00:05 lr: 0.000800 loss: 4.6410 (4.6307) grad_norm: 1.3229 (1.3661) time: 0.5057 [2021-03-25 06:02:46 swin_small_patch4_window7_224] INFO: Epoch: [15] [1250/1251] eta: 0:00:00 lr: 0.000800 loss: 4.5220 (4.6295) grad_norm: 1.3061 (1.3658) time: 0.5084 [2021-03-25 06:03:20 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:11 loss: 1.8224 (1.8224) acc1: 54.6875 (54.6875) acc5: 85.9375 (85.9375) [2021-03-25 06:03:21 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.9272 (1.8944) acc1: 59.3750 (57.9545) acc5: 81.2500 (80.6818) [2021-03-25 06:03:23 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.9483 (1.9538) acc1: 54.6875 (55.2827) acc5: 79.6875 (80.3571) [2021-03-25 06:03:24 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.9263 (1.9355) acc1: 54.6875 (56.0484) acc5: 79.6875 (80.4435) [2021-03-25 06:03:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.8698 (1.9452) acc1: 56.2500 (56.0213) acc5: 81.2500 (80.7927) [2021-03-25 06:03:26 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.8474 (1.9323) acc1: 56.2500 (56.5120) acc5: 82.8125 (81.0240) [2021-03-25 06:03:27 swin_small_patch4_window7_224] INFO: * Acc@1 56.778 Acc@5 81.060 loss 1.931 [2021-03-25 06:03:27 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 56.8% [2021-03-25 06:03:27 swin_small_patch4_window7_224] INFO: Max accuracy: 56.78% [2021-03-25 06:03:31 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 0/1251] eta: 1:24:34 lr: 0.000800 loss: 4.6225 (4.6225) grad_norm: 1.4833 (1.4833) time: 4.0560 [2021-03-25 06:03:36 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 10/1251] eta: 0:17:45 lr: 0.000801 loss: 4.6363 (4.5600) grad_norm: 1.3580 (1.3994) time: 0.8582 [2021-03-25 06:03:41 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 20/1251] eta: 0:14:09 lr: 0.000801 loss: 4.9364 (4.7242) grad_norm: 1.2643 (1.3466) time: 0.5216 [2021-03-25 06:03:46 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 30/1251] eta: 0:12:48 lr: 0.000801 loss: 4.9511 (4.7354) grad_norm: 1.2522 (1.3155) time: 0.5030 [2021-03-25 06:03:52 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 40/1251] eta: 0:12:08 lr: 0.000802 loss: 4.8743 (4.7423) grad_norm: 1.2797 (1.3532) time: 0.5088 [2021-03-25 06:03:57 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 50/1251] eta: 0:11:40 lr: 0.000802 loss: 4.8422 (4.7084) grad_norm: 1.4045 (1.3463) time: 0.5118 [2021-03-25 06:04:02 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 60/1251] eta: 0:11:20 lr: 0.000803 loss: 4.7307 (4.7211) grad_norm: 1.3506 (1.3499) time: 0.5106 [2021-03-25 06:04:07 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 70/1251] eta: 0:11:03 lr: 0.000803 loss: 4.7162 (4.6987) grad_norm: 1.3506 (1.3530) time: 0.5073 [2021-03-25 06:04:12 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 80/1251] eta: 0:10:50 lr: 0.000803 loss: 4.6915 (4.7112) grad_norm: 1.3445 (1.3554) time: 0.5078 [2021-03-25 06:04:17 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 90/1251] eta: 0:10:38 lr: 0.000804 loss: 4.8281 (4.6995) grad_norm: 1.3987 (1.3571) time: 0.5064 [2021-03-25 06:04:22 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 100/1251] eta: 0:10:29 lr: 0.000804 loss: 4.4968 (4.6665) grad_norm: 1.3656 (1.3523) time: 0.5082 [2021-03-25 06:04:27 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 110/1251] eta: 0:10:21 lr: 0.000805 loss: 4.4968 (4.6559) grad_norm: 1.3092 (1.3511) time: 0.5203 [2021-03-25 06:04:32 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 120/1251] eta: 0:10:11 lr: 0.000805 loss: 4.5609 (4.6376) grad_norm: 1.3241 (1.3529) time: 0.5119 [2021-03-25 06:04:37 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 130/1251] eta: 0:10:02 lr: 0.000805 loss: 4.5350 (4.6255) grad_norm: 1.3241 (1.3526) time: 0.4997 [2021-03-25 06:04:42 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 140/1251] eta: 0:09:54 lr: 0.000806 loss: 4.6820 (4.6325) grad_norm: 1.2915 (inf) time: 0.5004 [2021-03-25 06:04:47 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 150/1251] eta: 0:09:47 lr: 0.000806 loss: 4.6349 (4.6286) grad_norm: 1.2715 (inf) time: 0.5051 [2021-03-25 06:04:53 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 160/1251] eta: 0:09:40 lr: 0.000807 loss: 4.4307 (4.6302) grad_norm: 1.2631 (inf) time: 0.5096 [2021-03-25 06:04:58 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 170/1251] eta: 0:09:33 lr: 0.000807 loss: 4.3575 (4.6108) grad_norm: 1.2631 (inf) time: 0.5106 [2021-03-25 06:05:03 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 180/1251] eta: 0:09:27 lr: 0.000807 loss: 4.4395 (4.6093) grad_norm: 1.3012 (inf) time: 0.5134 [2021-03-25 06:05:08 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 190/1251] eta: 0:09:21 lr: 0.000808 loss: 4.5583 (4.6082) grad_norm: 1.3529 (inf) time: 0.5140 [2021-03-25 06:05:13 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 200/1251] eta: 0:09:14 lr: 0.000808 loss: 4.5547 (4.6021) grad_norm: 1.3047 (inf) time: 0.5072 [2021-03-25 06:05:18 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 210/1251] eta: 0:09:07 lr: 0.000809 loss: 4.6655 (4.6059) grad_norm: 1.2832 (inf) time: 0.5020 [2021-03-25 06:05:23 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 220/1251] eta: 0:09:01 lr: 0.000809 loss: 4.6773 (4.6022) grad_norm: 1.3274 (inf) time: 0.5045 [2021-03-25 06:05:28 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 230/1251] eta: 0:08:55 lr: 0.000809 loss: 4.9042 (4.6088) grad_norm: 1.3138 (inf) time: 0.5040 [2021-03-25 06:05:33 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 240/1251] eta: 0:08:49 lr: 0.000810 loss: 4.6817 (4.5946) grad_norm: 1.3211 (inf) time: 0.5039 [2021-03-25 06:05:38 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 250/1251] eta: 0:08:43 lr: 0.000810 loss: 4.3699 (4.5916) grad_norm: 1.3211 (inf) time: 0.5130 [2021-03-25 06:05:43 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 260/1251] eta: 0:08:38 lr: 0.000811 loss: 4.6281 (4.5914) grad_norm: 1.2491 (inf) time: 0.5110 [2021-03-25 06:05:48 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 270/1251] eta: 0:08:32 lr: 0.000811 loss: 4.7464 (4.6008) grad_norm: 1.2707 (inf) time: 0.5067 [2021-03-25 06:05:54 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 280/1251] eta: 0:08:26 lr: 0.000811 loss: 4.8401 (4.6081) grad_norm: 1.3124 (inf) time: 0.5055 [2021-03-25 06:05:59 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 290/1251] eta: 0:08:21 lr: 0.000812 loss: 4.4274 (4.5931) grad_norm: 1.2764 (inf) time: 0.5116 [2021-03-25 06:06:04 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 300/1251] eta: 0:08:15 lr: 0.000812 loss: 4.4361 (4.5960) grad_norm: 1.1930 (inf) time: 0.5123 [2021-03-25 06:06:09 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 310/1251] eta: 0:08:10 lr: 0.000813 loss: 4.5998 (4.5929) grad_norm: 1.2935 (inf) time: 0.5103 [2021-03-25 06:06:14 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 320/1251] eta: 0:08:04 lr: 0.000813 loss: 4.7883 (4.6015) grad_norm: 1.3293 (inf) time: 0.5092 [2021-03-25 06:06:19 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 330/1251] eta: 0:07:58 lr: 0.000813 loss: 4.5401 (4.5899) grad_norm: 1.3349 (inf) time: 0.5068 [2021-03-25 06:06:24 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 340/1251] eta: 0:07:52 lr: 0.000814 loss: 4.1751 (4.5881) grad_norm: 1.1752 (inf) time: 0.5023 [2021-03-25 06:06:29 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 350/1251] eta: 0:07:47 lr: 0.000814 loss: 4.3913 (4.5873) grad_norm: 1.1359 (inf) time: 0.4983 [2021-03-25 06:06:34 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 360/1251] eta: 0:07:41 lr: 0.000815 loss: 4.5699 (4.5871) grad_norm: 1.1811 (inf) time: 0.5005 [2021-03-25 06:06:39 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 370/1251] eta: 0:07:36 lr: 0.000815 loss: 4.5930 (4.5856) grad_norm: 1.2107 (inf) time: 0.5020 [2021-03-25 06:06:44 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 380/1251] eta: 0:07:30 lr: 0.000815 loss: 4.6998 (4.5893) grad_norm: 1.2442 (inf) time: 0.5089 [2021-03-25 06:06:49 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 390/1251] eta: 0:07:25 lr: 0.000816 loss: 4.7214 (4.5891) grad_norm: 1.2442 (inf) time: 0.5118 [2021-03-25 06:06:54 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 400/1251] eta: 0:07:20 lr: 0.000816 loss: 4.6521 (4.5892) grad_norm: 1.3725 (inf) time: 0.5083 [2021-03-25 06:06:59 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 410/1251] eta: 0:07:14 lr: 0.000817 loss: 4.8678 (4.5956) grad_norm: 1.3210 (inf) time: 0.5026 [2021-03-25 06:07:04 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 420/1251] eta: 0:07:09 lr: 0.000817 loss: 4.8015 (4.5957) grad_norm: 1.2580 (inf) time: 0.5026 [2021-03-25 06:07:09 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 430/1251] eta: 0:07:03 lr: 0.000817 loss: 4.3503 (4.5913) grad_norm: 1.2848 (inf) time: 0.5015 [2021-03-25 06:07:14 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 440/1251] eta: 0:06:58 lr: 0.000818 loss: 4.4951 (4.5932) grad_norm: 1.3075 (inf) time: 0.5023 [2021-03-25 06:07:20 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 450/1251] eta: 0:06:53 lr: 0.000818 loss: 4.6885 (4.5943) grad_norm: 1.2869 (inf) time: 0.5070 [2021-03-25 06:07:25 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 460/1251] eta: 0:06:47 lr: 0.000819 loss: 4.4648 (4.5947) grad_norm: 1.3305 (inf) time: 0.5053 [2021-03-25 06:07:30 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 470/1251] eta: 0:06:42 lr: 0.000819 loss: 4.7227 (4.5991) grad_norm: 1.2208 (inf) time: 0.5004 [2021-03-25 06:07:35 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 480/1251] eta: 0:06:36 lr: 0.000819 loss: 4.8048 (4.5968) grad_norm: 1.2208 (inf) time: 0.4990 [2021-03-25 06:07:40 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 490/1251] eta: 0:06:31 lr: 0.000820 loss: 4.4719 (4.5961) grad_norm: 1.3231 (inf) time: 0.5047 [2021-03-25 06:07:45 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 500/1251] eta: 0:06:26 lr: 0.000820 loss: 4.7578 (4.5969) grad_norm: 1.3243 (inf) time: 0.5094 [2021-03-25 06:07:50 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 510/1251] eta: 0:06:21 lr: 0.000821 loss: 4.7578 (4.5960) grad_norm: 1.2339 (inf) time: 0.5061 [2021-03-25 06:07:55 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 520/1251] eta: 0:06:15 lr: 0.000821 loss: 4.7080 (4.5977) grad_norm: 1.3197 (inf) time: 0.5022 [2021-03-25 06:08:00 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 530/1251] eta: 0:06:10 lr: 0.000821 loss: 4.6707 (4.5986) grad_norm: 1.4047 (inf) time: 0.4996 [2021-03-25 06:08:05 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 540/1251] eta: 0:06:04 lr: 0.000822 loss: 4.6418 (4.5934) grad_norm: 1.2099 (inf) time: 0.4953 [2021-03-25 06:08:10 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 550/1251] eta: 0:06:00 lr: 0.000822 loss: 4.6474 (4.5979) grad_norm: 1.3442 (inf) time: 0.5144 [2021-03-25 06:08:15 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 560/1251] eta: 0:05:54 lr: 0.000823 loss: 4.9394 (4.5993) grad_norm: 1.3503 (inf) time: 0.5195 [2021-03-25 06:08:20 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 570/1251] eta: 0:05:49 lr: 0.000823 loss: 4.8701 (4.6040) grad_norm: 1.3073 (inf) time: 0.5042 [2021-03-25 06:08:25 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 580/1251] eta: 0:05:44 lr: 0.000823 loss: 4.7784 (4.6012) grad_norm: 1.2924 (inf) time: 0.5030 [2021-03-25 06:08:30 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 590/1251] eta: 0:05:39 lr: 0.000824 loss: 4.6454 (4.6007) grad_norm: 1.2623 (inf) time: 0.5033 [2021-03-25 06:08:35 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 600/1251] eta: 0:05:33 lr: 0.000824 loss: 4.8113 (4.6093) grad_norm: 1.2253 (inf) time: 0.5015 [2021-03-25 06:08:40 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 610/1251] eta: 0:05:28 lr: 0.000825 loss: 4.8895 (4.6086) grad_norm: 1.2729 (inf) time: 0.5020 [2021-03-25 06:08:45 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 620/1251] eta: 0:05:23 lr: 0.000825 loss: 4.5063 (4.6065) grad_norm: 1.3569 (inf) time: 0.5121 [2021-03-25 06:08:50 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 630/1251] eta: 0:05:18 lr: 0.000825 loss: 4.5688 (4.6054) grad_norm: 1.3206 (inf) time: 0.5099 [2021-03-25 06:08:55 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 640/1251] eta: 0:05:13 lr: 0.000826 loss: 4.8293 (4.6078) grad_norm: 1.2709 (inf) time: 0.4998 [2021-03-25 06:09:00 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 650/1251] eta: 0:05:07 lr: 0.000826 loss: 4.6287 (4.6041) grad_norm: 1.3919 (inf) time: 0.4953 [2021-03-25 06:09:05 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 660/1251] eta: 0:05:02 lr: 0.000827 loss: 4.5029 (4.6049) grad_norm: 1.3919 (inf) time: 0.4988 [2021-03-25 06:09:11 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 670/1251] eta: 0:04:57 lr: 0.000827 loss: 4.5981 (4.6055) grad_norm: 1.3707 (inf) time: 0.5077 [2021-03-25 06:09:16 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 680/1251] eta: 0:04:52 lr: 0.000827 loss: 4.6198 (4.6057) grad_norm: 1.2225 (inf) time: 0.5079 [2021-03-25 06:09:21 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 690/1251] eta: 0:04:47 lr: 0.000828 loss: 4.6394 (4.6051) grad_norm: 1.1850 (inf) time: 0.5091 [2021-03-25 06:09:26 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 700/1251] eta: 0:04:41 lr: 0.000828 loss: 4.6394 (4.6041) grad_norm: 1.1966 (inf) time: 0.5049 [2021-03-25 06:09:31 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 710/1251] eta: 0:04:36 lr: 0.000829 loss: 4.7556 (4.6053) grad_norm: 1.3844 (inf) time: 0.4965 [2021-03-25 06:09:36 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 720/1251] eta: 0:04:31 lr: 0.000829 loss: 4.4548 (4.5999) grad_norm: 1.2634 (inf) time: 0.4996 [2021-03-25 06:09:41 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 730/1251] eta: 0:04:26 lr: 0.000829 loss: 4.4085 (4.6018) grad_norm: 1.2850 (inf) time: 0.5093 [2021-03-25 06:09:46 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 740/1251] eta: 0:04:21 lr: 0.000830 loss: 4.9083 (4.6031) grad_norm: 1.2850 (inf) time: 0.5252 [2021-03-25 06:09:51 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 750/1251] eta: 0:04:16 lr: 0.000830 loss: 4.6312 (4.6018) grad_norm: 1.2436 (inf) time: 0.5248 [2021-03-25 06:09:56 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 760/1251] eta: 0:04:11 lr: 0.000831 loss: 4.6497 (4.6018) grad_norm: 1.2993 (inf) time: 0.5109 [2021-03-25 06:10:01 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 770/1251] eta: 0:04:06 lr: 0.000831 loss: 4.8883 (4.6050) grad_norm: 1.2993 (inf) time: 0.5058 [2021-03-25 06:10:06 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 780/1251] eta: 0:04:00 lr: 0.000831 loss: 4.8771 (4.6012) grad_norm: 1.3539 (inf) time: 0.4986 [2021-03-25 06:10:12 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 790/1251] eta: 0:03:55 lr: 0.000832 loss: 4.3607 (4.5995) grad_norm: 1.4259 (inf) time: 0.5007 [2021-03-25 06:10:17 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 800/1251] eta: 0:03:50 lr: 0.000832 loss: 4.6590 (4.6002) grad_norm: 1.3296 (inf) time: 0.5110 [2021-03-25 06:10:22 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 810/1251] eta: 0:03:45 lr: 0.000833 loss: 4.6733 (4.6007) grad_norm: 1.1894 (inf) time: 0.5065 [2021-03-25 06:10:27 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 820/1251] eta: 0:03:40 lr: 0.000833 loss: 4.7720 (4.6042) grad_norm: 1.2275 (inf) time: 0.4994 [2021-03-25 06:10:32 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 830/1251] eta: 0:03:35 lr: 0.000833 loss: 4.8130 (4.6051) grad_norm: 1.2565 (inf) time: 0.4992 [2021-03-25 06:10:37 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 840/1251] eta: 0:03:29 lr: 0.000834 loss: 4.5557 (4.6033) grad_norm: 1.2430 (inf) time: 0.4984 [2021-03-25 06:10:42 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 850/1251] eta: 0:03:24 lr: 0.000834 loss: 4.4577 (4.5991) grad_norm: 1.2687 (inf) time: 0.5124 [2021-03-25 06:10:47 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 860/1251] eta: 0:03:19 lr: 0.000835 loss: 4.7489 (4.6004) grad_norm: 1.3118 (inf) time: 0.5148 [2021-03-25 06:10:52 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 870/1251] eta: 0:03:14 lr: 0.000835 loss: 4.5838 (4.5971) grad_norm: 1.2365 (inf) time: 0.5020 [2021-03-25 06:10:57 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 880/1251] eta: 0:03:09 lr: 0.000835 loss: 4.4915 (4.5973) grad_norm: 1.3039 (inf) time: 0.5021 [2021-03-25 06:11:02 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 890/1251] eta: 0:03:04 lr: 0.000836 loss: 4.6638 (4.5976) grad_norm: 1.3877 (inf) time: 0.5001 [2021-03-25 06:11:07 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 900/1251] eta: 0:02:59 lr: 0.000836 loss: 4.6638 (4.5972) grad_norm: 1.3113 (inf) time: 0.5049 [2021-03-25 06:11:12 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 910/1251] eta: 0:02:54 lr: 0.000837 loss: 4.6703 (4.5963) grad_norm: 1.2459 (inf) time: 0.5098 [2021-03-25 06:11:17 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 920/1251] eta: 0:02:48 lr: 0.000837 loss: 4.6903 (4.5960) grad_norm: 1.2512 (inf) time: 0.5138 [2021-03-25 06:11:22 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 930/1251] eta: 0:02:43 lr: 0.000837 loss: 4.0752 (4.5906) grad_norm: 1.3984 (inf) time: 0.5164 [2021-03-25 06:11:28 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 940/1251] eta: 0:02:38 lr: 0.000838 loss: 4.5833 (4.5938) grad_norm: 1.3326 (inf) time: 0.5110 [2021-03-25 06:11:33 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 950/1251] eta: 0:02:33 lr: 0.000838 loss: 4.8677 (4.5926) grad_norm: 1.4131 (inf) time: 0.5065 [2021-03-25 06:11:38 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 960/1251] eta: 0:02:28 lr: 0.000839 loss: 4.4178 (4.5903) grad_norm: 1.2869 (inf) time: 0.5088 [2021-03-25 06:11:43 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 970/1251] eta: 0:02:23 lr: 0.000839 loss: 4.6130 (4.5894) grad_norm: 1.2307 (inf) time: 0.5088 [2021-03-25 06:11:48 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 980/1251] eta: 0:02:18 lr: 0.000839 loss: 4.6332 (4.5902) grad_norm: 1.2154 (inf) time: 0.5049 [2021-03-25 06:11:53 swin_small_patch4_window7_224] INFO: Epoch: [16] [ 990/1251] eta: 0:02:13 lr: 0.000840 loss: 4.6710 (4.5910) grad_norm: 1.2165 (inf) time: 0.5130 [2021-03-25 06:11:58 swin_small_patch4_window7_224] INFO: Epoch: [16] [1000/1251] eta: 0:02:08 lr: 0.000840 loss: 4.6666 (4.5884) grad_norm: 1.2598 (inf) time: 0.5134 [2021-03-25 06:12:03 swin_small_patch4_window7_224] INFO: Epoch: [16] [1010/1251] eta: 0:02:02 lr: 0.000841 loss: 4.2032 (4.5856) grad_norm: 1.2106 (inf) time: 0.5031 [2021-03-25 06:12:08 swin_small_patch4_window7_224] INFO: Epoch: [16] [1020/1251] eta: 0:01:57 lr: 0.000841 loss: 4.4030 (4.5845) grad_norm: 1.2982 (inf) time: 0.5027 [2021-03-25 06:12:13 swin_small_patch4_window7_224] INFO: Epoch: [16] [1030/1251] eta: 0:01:52 lr: 0.000841 loss: 4.4638 (4.5841) grad_norm: 1.3061 (inf) time: 0.5081 [2021-03-25 06:12:18 swin_small_patch4_window7_224] INFO: Epoch: [16] [1040/1251] eta: 0:01:47 lr: 0.000842 loss: 4.4650 (4.5817) grad_norm: 1.2493 (inf) time: 0.5110 [2021-03-25 06:12:24 swin_small_patch4_window7_224] INFO: Epoch: [16] [1050/1251] eta: 0:01:42 lr: 0.000842 loss: 4.4650 (4.5824) grad_norm: 1.2659 (inf) time: 0.5158 [2021-03-25 06:12:29 swin_small_patch4_window7_224] INFO: Epoch: [16] [1060/1251] eta: 0:01:37 lr: 0.000843 loss: 4.4704 (4.5808) grad_norm: 1.3469 (inf) time: 0.5118 [2021-03-25 06:12:34 swin_small_patch4_window7_224] INFO: Epoch: [16] [1070/1251] eta: 0:01:32 lr: 0.000843 loss: 4.4704 (4.5801) grad_norm: 1.3403 (inf) time: 0.5037 [2021-03-25 06:12:39 swin_small_patch4_window7_224] INFO: Epoch: [16] [1080/1251] eta: 0:01:27 lr: 0.000843 loss: 4.5766 (4.5781) grad_norm: 1.2365 (inf) time: 0.5089 [2021-03-25 06:12:44 swin_small_patch4_window7_224] INFO: Epoch: [16] [1090/1251] eta: 0:01:22 lr: 0.000844 loss: 4.4358 (4.5760) grad_norm: 1.2930 (inf) time: 0.5116 [2021-03-25 06:12:49 swin_small_patch4_window7_224] INFO: Epoch: [16] [1100/1251] eta: 0:01:17 lr: 0.000844 loss: 4.2945 (4.5750) grad_norm: 1.3613 (inf) time: 0.5100 [2021-03-25 06:12:54 swin_small_patch4_window7_224] INFO: Epoch: [16] [1110/1251] eta: 0:01:11 lr: 0.000845 loss: 4.2945 (4.5728) grad_norm: 1.2897 (inf) time: 0.5034 [2021-03-25 06:12:59 swin_small_patch4_window7_224] INFO: Epoch: [16] [1120/1251] eta: 0:01:06 lr: 0.000845 loss: 4.2945 (4.5710) grad_norm: 1.2791 (inf) time: 0.5010 [2021-03-25 06:13:04 swin_small_patch4_window7_224] INFO: Epoch: [16] [1130/1251] eta: 0:01:01 lr: 0.000845 loss: 4.5658 (4.5720) grad_norm: 1.2224 (inf) time: 0.5046 [2021-03-25 06:13:09 swin_small_patch4_window7_224] INFO: Epoch: [16] [1140/1251] eta: 0:00:56 lr: 0.000846 loss: 4.5658 (4.5712) grad_norm: 1.3075 (inf) time: 0.5029 [2021-03-25 06:13:14 swin_small_patch4_window7_224] INFO: Epoch: [16] [1150/1251] eta: 0:00:51 lr: 0.000846 loss: 4.5056 (4.5707) grad_norm: 1.3173 (inf) time: 0.4997 [2021-03-25 06:13:19 swin_small_patch4_window7_224] INFO: Epoch: [16] [1160/1251] eta: 0:00:46 lr: 0.000847 loss: 4.4733 (4.5693) grad_norm: 1.3277 (inf) time: 0.4983 [2021-03-25 06:13:24 swin_small_patch4_window7_224] INFO: Epoch: [16] [1170/1251] eta: 0:00:41 lr: 0.000847 loss: 4.4733 (4.5699) grad_norm: 1.3432 (inf) time: 0.5028 [2021-03-25 06:13:29 swin_small_patch4_window7_224] INFO: Epoch: [16] [1180/1251] eta: 0:00:36 lr: 0.000847 loss: 4.7585 (4.5721) grad_norm: 1.1771 (inf) time: 0.5038 [2021-03-25 06:13:34 swin_small_patch4_window7_224] INFO: Epoch: [16] [1190/1251] eta: 0:00:31 lr: 0.000848 loss: 4.6158 (4.5720) grad_norm: 1.1737 (inf) time: 0.5019 [2021-03-25 06:13:39 swin_small_patch4_window7_224] INFO: Epoch: [16] [1200/1251] eta: 0:00:25 lr: 0.000848 loss: 4.6158 (4.5743) grad_norm: 1.2272 (inf) time: 0.5031 [2021-03-25 06:13:44 swin_small_patch4_window7_224] INFO: Epoch: [16] [1210/1251] eta: 0:00:20 lr: 0.000849 loss: 4.8351 (4.5741) grad_norm: 1.2289 (inf) time: 0.5053 [2021-03-25 06:13:49 swin_small_patch4_window7_224] INFO: Epoch: [16] [1220/1251] eta: 0:00:15 lr: 0.000849 loss: 4.6701 (4.5749) grad_norm: 1.3769 (inf) time: 0.5056 [2021-03-25 06:13:54 swin_small_patch4_window7_224] INFO: Epoch: [16] [1230/1251] eta: 0:00:10 lr: 0.000849 loss: 4.6239 (4.5755) grad_norm: 1.4408 (inf) time: 0.5077 [2021-03-25 06:13:59 swin_small_patch4_window7_224] INFO: Epoch: [16] [1240/1251] eta: 0:00:05 lr: 0.000850 loss: 4.5493 (4.5742) grad_norm: 1.2027 (inf) time: 0.5068 [2021-03-25 06:14:04 swin_small_patch4_window7_224] INFO: Epoch: [16] [1250/1251] eta: 0:00:00 lr: 0.000850 loss: 4.5259 (4.5736) grad_norm: 1.3539 (inf) time: 0.5032 [2021-03-25 06:14:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 1.9526 (1.9526) acc1: 62.5000 (62.5000) acc5: 75.0000 (75.0000) [2021-03-25 06:14:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.9107 (1.8274) acc1: 59.3750 (58.0966) acc5: 81.2500 (81.5341) [2021-03-25 06:14:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.8617 (1.8374) acc1: 57.8125 (57.5893) acc5: 82.8125 (81.9196) [2021-03-25 06:14:16 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.8730 (1.8878) acc1: 54.6875 (56.6028) acc5: 82.8125 (81.3508) [2021-03-25 06:14:18 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.8733 (1.8838) acc1: 54.6875 (56.8216) acc5: 82.8125 (81.9741) [2021-03-25 06:14:19 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.8281 (1.8877) acc1: 56.2500 (57.0880) acc5: 83.0189 (81.7280) [2021-03-25 06:14:20 swin_small_patch4_window7_224] INFO: * Acc@1 57.798 Acc@5 82.044 loss 1.870 [2021-03-25 06:14:20 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 57.8% [2021-03-25 06:14:20 swin_small_patch4_window7_224] INFO: Max accuracy: 57.80% [2021-03-25 06:14:24 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 0/1251] eta: 1:27:02 lr: 0.000850 loss: 4.3260 (4.3260) grad_norm: 1.2902 (1.2902) time: 4.1747 [2021-03-25 06:14:29 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 10/1251] eta: 0:17:36 lr: 0.000851 loss: 4.8334 (4.7304) grad_norm: 1.3498 (1.3232) time: 0.8514 [2021-03-25 06:14:34 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 20/1251] eta: 0:14:05 lr: 0.000851 loss: 4.8254 (4.7118) grad_norm: 1.2735 (1.2933) time: 0.5129 [2021-03-25 06:14:39 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 30/1251] eta: 0:12:52 lr: 0.000851 loss: 4.4434 (4.5555) grad_norm: 1.2187 (1.2966) time: 0.5127 [2021-03-25 06:14:45 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 40/1251] eta: 0:12:11 lr: 0.000852 loss: 4.1699 (4.4833) grad_norm: 1.2489 (1.3250) time: 0.5160 [2021-03-25 06:14:50 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 50/1251] eta: 0:11:44 lr: 0.000852 loss: 4.0720 (4.3984) grad_norm: 1.3284 (1.3377) time: 0.5143 [2021-03-25 06:14:55 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 60/1251] eta: 0:11:24 lr: 0.000853 loss: 4.0720 (4.4135) grad_norm: 1.3659 (1.3439) time: 0.5161 [2021-03-25 06:15:00 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 70/1251] eta: 0:11:06 lr: 0.000853 loss: 4.5476 (4.4338) grad_norm: 1.3171 (1.3251) time: 0.5094 [2021-03-25 06:15:05 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 80/1251] eta: 0:10:53 lr: 0.000853 loss: 4.5476 (4.4481) grad_norm: 1.1937 (1.3102) time: 0.5064 [2021-03-25 06:15:10 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 90/1251] eta: 0:10:40 lr: 0.000854 loss: 4.6717 (4.4716) grad_norm: 1.1937 (1.3040) time: 0.5054 [2021-03-25 06:15:15 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 100/1251] eta: 0:10:29 lr: 0.000854 loss: 4.6848 (4.5014) grad_norm: 1.2965 (1.3084) time: 0.5017 [2021-03-25 06:15:20 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 110/1251] eta: 0:10:19 lr: 0.000855 loss: 4.6370 (4.4930) grad_norm: 1.3779 (1.3146) time: 0.5055 [2021-03-25 06:15:25 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 120/1251] eta: 0:10:10 lr: 0.000855 loss: 4.2960 (4.4766) grad_norm: 1.3779 (1.3312) time: 0.5040 [2021-03-25 06:15:30 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 130/1251] eta: 0:10:02 lr: 0.000855 loss: 4.6309 (4.4844) grad_norm: 1.3416 (1.3336) time: 0.5039 [2021-03-25 06:15:35 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 140/1251] eta: 0:09:54 lr: 0.000856 loss: 4.3493 (4.4770) grad_norm: 1.2635 (1.3270) time: 0.5046 [2021-03-25 06:15:40 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 150/1251] eta: 0:09:47 lr: 0.000856 loss: 4.3137 (4.4620) grad_norm: 1.2766 (1.3225) time: 0.5114 [2021-03-25 06:15:45 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 160/1251] eta: 0:09:39 lr: 0.000857 loss: 4.5037 (4.4670) grad_norm: 1.2946 (1.3249) time: 0.5091 [2021-03-25 06:15:51 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 170/1251] eta: 0:09:33 lr: 0.000857 loss: 4.5309 (4.4623) grad_norm: 1.2899 (1.3214) time: 0.5038 [2021-03-25 06:15:56 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 180/1251] eta: 0:09:27 lr: 0.000857 loss: 4.5234 (4.4650) grad_norm: 1.2287 (1.3174) time: 0.5169 [2021-03-25 06:16:01 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 190/1251] eta: 0:09:20 lr: 0.000858 loss: 4.5204 (4.4623) grad_norm: 1.2340 (1.3182) time: 0.5118 [2021-03-25 06:16:06 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 200/1251] eta: 0:09:14 lr: 0.000858 loss: 4.5204 (4.4547) grad_norm: 1.3062 (1.3251) time: 0.5061 [2021-03-25 06:16:11 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 210/1251] eta: 0:09:08 lr: 0.000859 loss: 4.5794 (4.4602) grad_norm: 1.4778 (1.3296) time: 0.5075 [2021-03-25 06:16:16 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 220/1251] eta: 0:09:02 lr: 0.000859 loss: 4.4181 (4.4586) grad_norm: 1.3279 (1.3311) time: 0.5069 [2021-03-25 06:16:21 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 230/1251] eta: 0:08:55 lr: 0.000859 loss: 4.3652 (4.4596) grad_norm: 1.2917 (1.3267) time: 0.5065 [2021-03-25 06:16:26 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 240/1251] eta: 0:08:49 lr: 0.000860 loss: 4.3652 (4.4546) grad_norm: 1.2769 (1.3245) time: 0.5034 [2021-03-25 06:16:31 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 250/1251] eta: 0:08:43 lr: 0.000860 loss: 4.1509 (4.4487) grad_norm: 1.2859 (1.3240) time: 0.5030 [2021-03-25 06:16:36 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 260/1251] eta: 0:08:37 lr: 0.000861 loss: 4.6370 (4.4647) grad_norm: 1.2540 (1.3229) time: 0.5052 [2021-03-25 06:16:41 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 270/1251] eta: 0:08:32 lr: 0.000861 loss: 4.6287 (4.4544) grad_norm: 1.2227 (1.3218) time: 0.5091 [2021-03-25 06:16:47 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 280/1251] eta: 0:08:26 lr: 0.000861 loss: 3.9687 (4.4486) grad_norm: 1.1983 (1.3178) time: 0.5163 [2021-03-25 06:16:52 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 290/1251] eta: 0:08:21 lr: 0.000862 loss: 4.2310 (4.4426) grad_norm: 1.1511 (1.3132) time: 0.5140 [2021-03-25 06:16:57 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 300/1251] eta: 0:08:15 lr: 0.000862 loss: 4.3180 (4.4478) grad_norm: 1.2243 (1.3150) time: 0.5047 [2021-03-25 06:17:02 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 310/1251] eta: 0:08:09 lr: 0.000863 loss: 4.6263 (4.4552) grad_norm: 1.3440 (1.3151) time: 0.5071 [2021-03-25 06:17:07 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 320/1251] eta: 0:08:03 lr: 0.000863 loss: 4.7268 (4.4599) grad_norm: 1.2465 (1.3120) time: 0.5049 [2021-03-25 06:17:12 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 330/1251] eta: 0:07:58 lr: 0.000863 loss: 4.5450 (4.4463) grad_norm: 1.1193 (1.3080) time: 0.5024 [2021-03-25 06:17:17 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 340/1251] eta: 0:07:52 lr: 0.000864 loss: 4.2990 (4.4466) grad_norm: 1.2072 (1.3080) time: 0.5038 [2021-03-25 06:17:22 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 350/1251] eta: 0:07:47 lr: 0.000864 loss: 4.4307 (4.4364) grad_norm: 1.2191 (1.3057) time: 0.5049 [2021-03-25 06:17:27 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 360/1251] eta: 0:07:41 lr: 0.000865 loss: 4.4307 (4.4434) grad_norm: 1.2211 (1.3056) time: 0.5059 [2021-03-25 06:17:32 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 370/1251] eta: 0:07:36 lr: 0.000865 loss: 4.8850 (4.4504) grad_norm: 1.2486 (1.3045) time: 0.5070 [2021-03-25 06:17:37 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 380/1251] eta: 0:07:30 lr: 0.000865 loss: 4.8146 (4.4548) grad_norm: 1.2258 (1.3056) time: 0.5057 [2021-03-25 06:17:42 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 390/1251] eta: 0:07:25 lr: 0.000866 loss: 4.5774 (4.4547) grad_norm: 1.2714 (1.3050) time: 0.5008 [2021-03-25 06:17:47 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 400/1251] eta: 0:07:19 lr: 0.000866 loss: 4.2866 (4.4542) grad_norm: 1.2932 (1.3080) time: 0.5017 [2021-03-25 06:17:52 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 410/1251] eta: 0:07:14 lr: 0.000867 loss: 4.4899 (4.4581) grad_norm: 1.3610 (1.3098) time: 0.5075 [2021-03-25 06:17:57 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 420/1251] eta: 0:07:09 lr: 0.000867 loss: 4.5379 (4.4611) grad_norm: 1.3610 (1.3116) time: 0.5083 [2021-03-25 06:18:02 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 430/1251] eta: 0:07:03 lr: 0.000867 loss: 4.6592 (4.4636) grad_norm: 1.3037 (1.3122) time: 0.5067 [2021-03-25 06:18:07 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 440/1251] eta: 0:06:58 lr: 0.000868 loss: 4.5550 (4.4605) grad_norm: 1.3037 (1.3142) time: 0.5060 [2021-03-25 06:18:12 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 450/1251] eta: 0:06:53 lr: 0.000868 loss: 4.4857 (4.4657) grad_norm: 1.3293 (1.3147) time: 0.5043 [2021-03-25 06:18:18 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 460/1251] eta: 0:06:47 lr: 0.000869 loss: 4.7006 (4.4682) grad_norm: 1.2912 (1.3135) time: 0.5057 [2021-03-25 06:18:23 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 470/1251] eta: 0:06:42 lr: 0.000869 loss: 4.6390 (4.4697) grad_norm: 1.1697 (1.3097) time: 0.5054 [2021-03-25 06:18:28 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 480/1251] eta: 0:06:37 lr: 0.000869 loss: 4.5661 (4.4688) grad_norm: 1.1531 (1.3081) time: 0.5125 [2021-03-25 06:18:33 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 490/1251] eta: 0:06:31 lr: 0.000870 loss: 4.5597 (4.4710) grad_norm: 1.2285 (1.3071) time: 0.5104 [2021-03-25 06:18:38 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 500/1251] eta: 0:06:26 lr: 0.000870 loss: 4.8218 (4.4781) grad_norm: 1.2083 (1.3047) time: 0.5013 [2021-03-25 06:18:43 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 510/1251] eta: 0:06:21 lr: 0.000871 loss: 4.8665 (4.4748) grad_norm: 1.1518 (1.3021) time: 0.5013 [2021-03-25 06:18:48 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 520/1251] eta: 0:06:15 lr: 0.000871 loss: 4.8665 (4.4826) grad_norm: 1.1518 (1.3009) time: 0.5004 [2021-03-25 06:18:53 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 530/1251] eta: 0:06:10 lr: 0.000871 loss: 4.5163 (4.4737) grad_norm: 1.2277 (1.3008) time: 0.5009 [2021-03-25 06:18:58 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 540/1251] eta: 0:06:05 lr: 0.000872 loss: 4.5163 (4.4772) grad_norm: 1.2731 (1.2998) time: 0.5023 [2021-03-25 06:19:03 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 550/1251] eta: 0:06:00 lr: 0.000872 loss: 4.8155 (4.4834) grad_norm: 1.2949 (1.3014) time: 0.5181 [2021-03-25 06:19:08 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 560/1251] eta: 0:05:55 lr: 0.000873 loss: 4.8558 (4.4873) grad_norm: 1.4156 (1.3025) time: 0.5178 [2021-03-25 06:19:13 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 570/1251] eta: 0:05:49 lr: 0.000873 loss: 4.5540 (4.4850) grad_norm: 1.2540 (1.3013) time: 0.5049 [2021-03-25 06:19:18 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 580/1251] eta: 0:05:44 lr: 0.000873 loss: 4.5036 (4.4878) grad_norm: 1.2540 (1.2995) time: 0.5052 [2021-03-25 06:19:23 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 590/1251] eta: 0:05:39 lr: 0.000874 loss: 4.5640 (4.4841) grad_norm: 1.1415 (1.2976) time: 0.5099 [2021-03-25 06:19:29 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 600/1251] eta: 0:05:34 lr: 0.000874 loss: 4.6166 (4.4893) grad_norm: 1.2626 (1.2996) time: 0.5148 [2021-03-25 06:19:34 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 610/1251] eta: 0:05:29 lr: 0.000875 loss: 4.6982 (4.4917) grad_norm: 1.4316 (1.3030) time: 0.5116 [2021-03-25 06:19:39 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 620/1251] eta: 0:05:24 lr: 0.000875 loss: 4.5268 (4.4867) grad_norm: 1.4460 (1.3039) time: 0.5099 [2021-03-25 06:19:44 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 630/1251] eta: 0:05:18 lr: 0.000875 loss: 4.6044 (4.4930) grad_norm: 1.1954 (1.3016) time: 0.5075 [2021-03-25 06:19:49 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 640/1251] eta: 0:05:13 lr: 0.000876 loss: 4.7948 (4.4937) grad_norm: 1.1769 (1.3008) time: 0.5091 [2021-03-25 06:19:54 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 650/1251] eta: 0:05:08 lr: 0.000876 loss: 4.4206 (4.4919) grad_norm: 1.2773 (1.3004) time: 0.5050 [2021-03-25 06:19:59 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 660/1251] eta: 0:05:03 lr: 0.000877 loss: 4.8898 (4.4972) grad_norm: 1.2958 (1.3002) time: 0.5018 [2021-03-25 06:20:04 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 670/1251] eta: 0:04:57 lr: 0.000877 loss: 4.5040 (4.4954) grad_norm: 1.2972 (1.3006) time: 0.5049 [2021-03-25 06:20:09 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 680/1251] eta: 0:04:52 lr: 0.000877 loss: 4.4805 (4.4966) grad_norm: 1.3352 (1.3012) time: 0.5063 [2021-03-25 06:20:14 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 690/1251] eta: 0:04:47 lr: 0.000878 loss: 4.5306 (4.4942) grad_norm: 1.3352 (1.3028) time: 0.5064 [2021-03-25 06:20:19 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 700/1251] eta: 0:04:42 lr: 0.000878 loss: 4.2443 (4.4920) grad_norm: 1.2783 (1.3015) time: 0.5054 [2021-03-25 06:20:24 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 710/1251] eta: 0:04:37 lr: 0.000878 loss: 4.5384 (4.4959) grad_norm: 1.2489 (1.3007) time: 0.5061 [2021-03-25 06:20:29 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 720/1251] eta: 0:04:32 lr: 0.000879 loss: 4.8576 (4.5002) grad_norm: 1.2409 (1.2988) time: 0.5068 [2021-03-25 06:20:35 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 730/1251] eta: 0:04:27 lr: 0.000879 loss: 4.7936 (4.5014) grad_norm: 1.1386 (1.2982) time: 0.5134 [2021-03-25 06:20:40 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 740/1251] eta: 0:04:22 lr: 0.000880 loss: 4.8269 (4.5076) grad_norm: 1.2445 (1.2986) time: 0.5233 [2021-03-25 06:20:45 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 750/1251] eta: 0:04:16 lr: 0.000880 loss: 4.7124 (4.5067) grad_norm: 1.1606 (1.2969) time: 0.5188 [2021-03-25 06:20:50 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 760/1251] eta: 0:04:11 lr: 0.000880 loss: 4.3075 (4.5036) grad_norm: 1.1606 (1.2973) time: 0.5097 [2021-03-25 06:20:55 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 770/1251] eta: 0:04:06 lr: 0.000881 loss: 4.1105 (4.4993) grad_norm: 1.3049 (1.2982) time: 0.5109 [2021-03-25 06:21:00 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 780/1251] eta: 0:04:01 lr: 0.000881 loss: 4.5226 (4.5003) grad_norm: 1.3473 (1.2983) time: 0.5085 [2021-03-25 06:21:05 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 790/1251] eta: 0:03:56 lr: 0.000882 loss: 4.5371 (4.5004) grad_norm: 1.2817 (1.2974) time: 0.5141 [2021-03-25 06:21:10 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 800/1251] eta: 0:03:51 lr: 0.000882 loss: 4.6346 (4.5026) grad_norm: 1.2565 (1.2969) time: 0.5098 [2021-03-25 06:21:16 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 810/1251] eta: 0:03:46 lr: 0.000882 loss: 4.6661 (4.5017) grad_norm: 1.2366 (1.2967) time: 0.5100 [2021-03-25 06:21:21 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 820/1251] eta: 0:03:40 lr: 0.000883 loss: 4.3235 (4.5020) grad_norm: 1.1813 (1.2964) time: 0.5101 [2021-03-25 06:21:26 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 830/1251] eta: 0:03:35 lr: 0.000883 loss: 4.4399 (4.5023) grad_norm: 1.2268 (1.2961) time: 0.5058 [2021-03-25 06:21:31 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 840/1251] eta: 0:03:30 lr: 0.000884 loss: 4.5104 (4.5053) grad_norm: 1.2703 (1.2978) time: 0.5103 [2021-03-25 06:21:36 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 850/1251] eta: 0:03:25 lr: 0.000884 loss: 4.5104 (4.5011) grad_norm: 1.2831 (1.2967) time: 0.5100 [2021-03-25 06:21:41 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 860/1251] eta: 0:03:20 lr: 0.000884 loss: 4.2597 (4.5001) grad_norm: 1.1595 (1.2954) time: 0.5077 [2021-03-25 06:21:46 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 870/1251] eta: 0:03:15 lr: 0.000885 loss: 4.2475 (4.4990) grad_norm: 1.2004 (1.2950) time: 0.5072 [2021-03-25 06:21:51 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 880/1251] eta: 0:03:09 lr: 0.000885 loss: 4.2475 (4.4978) grad_norm: 1.2049 (1.2935) time: 0.5042 [2021-03-25 06:21:56 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 890/1251] eta: 0:03:04 lr: 0.000886 loss: 4.5979 (4.4994) grad_norm: 1.2237 (1.2936) time: 0.5040 [2021-03-25 06:22:01 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 900/1251] eta: 0:02:59 lr: 0.000886 loss: 4.4246 (4.4987) grad_norm: 1.2307 (1.2926) time: 0.5113 [2021-03-25 06:22:06 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 910/1251] eta: 0:02:54 lr: 0.000886 loss: 4.6831 (4.5004) grad_norm: 1.1307 (1.2904) time: 0.5069 [2021-03-25 06:22:11 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 920/1251] eta: 0:02:49 lr: 0.000887 loss: 4.9116 (4.5052) grad_norm: 1.1196 (1.2891) time: 0.5053 [2021-03-25 06:22:17 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 930/1251] eta: 0:02:44 lr: 0.000887 loss: 4.7725 (4.5000) grad_norm: 1.1289 (1.2879) time: 0.5145 [2021-03-25 06:22:22 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 940/1251] eta: 0:02:39 lr: 0.000888 loss: 4.1462 (4.5000) grad_norm: 1.1812 (1.2881) time: 0.5174 [2021-03-25 06:22:27 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 950/1251] eta: 0:02:34 lr: 0.000888 loss: 4.5660 (4.4993) grad_norm: 1.2523 (1.2882) time: 0.5071 [2021-03-25 06:22:32 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 960/1251] eta: 0:02:28 lr: 0.000888 loss: 4.6635 (4.5012) grad_norm: 1.3410 (1.2893) time: 0.5018 [2021-03-25 06:22:37 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 970/1251] eta: 0:02:23 lr: 0.000889 loss: 4.6215 (4.4996) grad_norm: 1.2846 (1.2883) time: 0.5048 [2021-03-25 06:22:42 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 980/1251] eta: 0:02:18 lr: 0.000889 loss: 4.4015 (4.5006) grad_norm: 1.1734 (1.2874) time: 0.5062 [2021-03-25 06:22:47 swin_small_patch4_window7_224] INFO: Epoch: [17] [ 990/1251] eta: 0:02:13 lr: 0.000890 loss: 4.7541 (4.5028) grad_norm: 1.1610 (1.2868) time: 0.5026 [2021-03-25 06:22:52 swin_small_patch4_window7_224] INFO: Epoch: [17] [1000/1251] eta: 0:02:08 lr: 0.000890 loss: 4.8139 (4.5066) grad_norm: 1.1990 (1.2866) time: 0.5052 [2021-03-25 06:22:57 swin_small_patch4_window7_224] INFO: Epoch: [17] [1010/1251] eta: 0:02:03 lr: 0.000890 loss: 4.8860 (4.5099) grad_norm: 1.2007 (1.2858) time: 0.5057 [2021-03-25 06:23:02 swin_small_patch4_window7_224] INFO: Epoch: [17] [1020/1251] eta: 0:01:58 lr: 0.000891 loss: 4.7158 (4.5086) grad_norm: 1.2054 (1.2863) time: 0.5062 [2021-03-25 06:23:07 swin_small_patch4_window7_224] INFO: Epoch: [17] [1030/1251] eta: 0:01:53 lr: 0.000891 loss: 4.3915 (4.5073) grad_norm: 1.4247 (1.2882) time: 0.5060 [2021-03-25 06:23:12 swin_small_patch4_window7_224] INFO: Epoch: [17] [1040/1251] eta: 0:01:47 lr: 0.000892 loss: 4.3369 (4.5052) grad_norm: 1.3497 (1.2888) time: 0.5006 [2021-03-25 06:23:17 swin_small_patch4_window7_224] INFO: Epoch: [17] [1050/1251] eta: 0:01:42 lr: 0.000892 loss: 4.4620 (4.5061) grad_norm: 1.2979 (1.2890) time: 0.5034 [2021-03-25 06:23:22 swin_small_patch4_window7_224] INFO: Epoch: [17] [1060/1251] eta: 0:01:37 lr: 0.000892 loss: 4.6384 (4.5077) grad_norm: 1.1946 (1.2876) time: 0.5046 [2021-03-25 06:23:27 swin_small_patch4_window7_224] INFO: Epoch: [17] [1070/1251] eta: 0:01:32 lr: 0.000893 loss: 4.8863 (4.5105) grad_norm: 1.1451 (1.2866) time: 0.5022 [2021-03-25 06:23:32 swin_small_patch4_window7_224] INFO: Epoch: [17] [1080/1251] eta: 0:01:27 lr: 0.000893 loss: 4.7921 (4.5121) grad_norm: 1.1979 (1.2868) time: 0.5016 [2021-03-25 06:23:37 swin_small_patch4_window7_224] INFO: Epoch: [17] [1090/1251] eta: 0:01:22 lr: 0.000894 loss: 4.5844 (4.5108) grad_norm: 1.2916 (1.2873) time: 0.5051 [2021-03-25 06:23:42 swin_small_patch4_window7_224] INFO: Epoch: [17] [1100/1251] eta: 0:01:17 lr: 0.000894 loss: 4.5844 (4.5124) grad_norm: 1.2009 (1.2861) time: 0.5065 [2021-03-25 06:23:48 swin_small_patch4_window7_224] INFO: Epoch: [17] [1110/1251] eta: 0:01:12 lr: 0.000894 loss: 4.7327 (4.5119) grad_norm: 1.1769 (1.2861) time: 0.5048 [2021-03-25 06:23:53 swin_small_patch4_window7_224] INFO: Epoch: [17] [1120/1251] eta: 0:01:06 lr: 0.000895 loss: 4.6019 (4.5128) grad_norm: 1.1903 (1.2852) time: 0.5037 [2021-03-25 06:23:58 swin_small_patch4_window7_224] INFO: Epoch: [17] [1130/1251] eta: 0:01:01 lr: 0.000895 loss: 4.6051 (4.5142) grad_norm: 1.1903 (1.2847) time: 0.5005 [2021-03-25 06:24:03 swin_small_patch4_window7_224] INFO: Epoch: [17] [1140/1251] eta: 0:00:56 lr: 0.000896 loss: 4.7068 (4.5128) grad_norm: 1.2506 (1.2849) time: 0.4981 [2021-03-25 06:24:08 swin_small_patch4_window7_224] INFO: Epoch: [17] [1150/1251] eta: 0:00:51 lr: 0.000896 loss: 4.7329 (4.5144) grad_norm: 1.2505 (1.2845) time: 0.4993 [2021-03-25 06:24:13 swin_small_patch4_window7_224] INFO: Epoch: [17] [1160/1251] eta: 0:00:46 lr: 0.000896 loss: 4.4061 (4.5119) grad_norm: 1.1383 (1.2838) time: 0.5066 [2021-03-25 06:24:18 swin_small_patch4_window7_224] INFO: Epoch: [17] [1170/1251] eta: 0:00:41 lr: 0.000897 loss: 4.6852 (4.5146) grad_norm: 1.1896 (1.2836) time: 0.5097 [2021-03-25 06:24:23 swin_small_patch4_window7_224] INFO: Epoch: [17] [1180/1251] eta: 0:00:36 lr: 0.000897 loss: 4.9274 (4.5180) grad_norm: 1.2610 (1.2837) time: 0.5036 [2021-03-25 06:24:28 swin_small_patch4_window7_224] INFO: Epoch: [17] [1190/1251] eta: 0:00:31 lr: 0.000898 loss: 4.7179 (4.5176) grad_norm: 1.2315 (1.2832) time: 0.4989 [2021-03-25 06:24:33 swin_small_patch4_window7_224] INFO: Epoch: [17] [1200/1251] eta: 0:00:26 lr: 0.000898 loss: 4.6730 (4.5195) grad_norm: 1.1837 (1.2827) time: 0.5002 [2021-03-25 06:24:38 swin_small_patch4_window7_224] INFO: Epoch: [17] [1210/1251] eta: 0:00:20 lr: 0.000898 loss: 4.6752 (4.5178) grad_norm: 1.2296 (1.2823) time: 0.5023 [2021-03-25 06:24:43 swin_small_patch4_window7_224] INFO: Epoch: [17] [1220/1251] eta: 0:00:15 lr: 0.000899 loss: 4.5383 (4.5171) grad_norm: 1.2343 (1.2820) time: 0.5076 [2021-03-25 06:24:48 swin_small_patch4_window7_224] INFO: Epoch: [17] [1230/1251] eta: 0:00:10 lr: 0.000899 loss: 4.3661 (4.5163) grad_norm: 1.1980 (1.2815) time: 0.5081 [2021-03-25 06:24:53 swin_small_patch4_window7_224] INFO: Epoch: [17] [1240/1251] eta: 0:00:05 lr: 0.000900 loss: 4.5488 (4.5173) grad_norm: 1.2571 (1.2819) time: 0.5049 [2021-03-25 06:24:58 swin_small_patch4_window7_224] INFO: Epoch: [17] [1250/1251] eta: 0:00:00 lr: 0.000900 loss: 4.8480 (4.5208) grad_norm: 1.2266 (1.2811) time: 0.5041 [2021-03-25 06:25:02 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 1.9394 (1.9394) acc1: 57.8125 (57.8125) acc5: 81.2500 (81.2500) [2021-03-25 06:25:05 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.9804 (1.9650) acc1: 54.6875 (56.5341) acc5: 81.2500 (81.5341) [2021-03-25 06:25:08 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.9515 (1.9240) acc1: 57.8125 (57.9613) acc5: 81.2500 (82.5149) [2021-03-25 06:25:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.8696 (1.8708) acc1: 60.9375 (59.2238) acc5: 81.2500 (82.8125) [2021-03-25 06:25:12 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.8344 (1.8718) acc1: 60.9375 (59.2988) acc5: 81.2500 (82.3933) [2021-03-25 06:25:13 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.8293 (1.8618) acc1: 60.9375 (59.2640) acc5: 81.2500 (82.5280) [2021-03-25 06:25:13 swin_small_patch4_window7_224] INFO: * Acc@1 58.926 Acc@5 82.738 loss 1.856 [2021-03-25 06:25:13 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 58.9% [2021-03-25 06:25:13 swin_small_patch4_window7_224] INFO: Max accuracy: 58.93% [2021-03-25 06:25:17 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 0/1251] eta: 1:29:52 lr: 0.000900 loss: 4.3236 (4.3236) grad_norm: 1.0595 (1.0595) time: 4.3105 [2021-03-25 06:25:23 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 10/1251] eta: 0:18:02 lr: 0.000900 loss: 4.5131 (4.5387) grad_norm: 1.2672 (1.2265) time: 0.8721 [2021-03-25 06:25:28 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 20/1251] eta: 0:14:14 lr: 0.000901 loss: 4.5029 (4.4322) grad_norm: 1.2699 (1.2756) time: 0.5131 [2021-03-25 06:25:33 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 30/1251] eta: 0:12:52 lr: 0.000901 loss: 4.3711 (4.3911) grad_norm: 1.2889 (1.2787) time: 0.5012 [2021-03-25 06:25:38 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 40/1251] eta: 0:12:07 lr: 0.000902 loss: 4.3298 (4.4087) grad_norm: 1.2005 (1.2599) time: 0.5033 [2021-03-25 06:25:43 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 50/1251] eta: 0:11:39 lr: 0.000902 loss: 4.3259 (4.3384) grad_norm: 1.1663 (1.2465) time: 0.5047 [2021-03-25 06:25:48 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 60/1251] eta: 0:11:18 lr: 0.000902 loss: 4.6387 (4.3983) grad_norm: 1.2615 (1.2731) time: 0.5057 [2021-03-25 06:25:53 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 70/1251] eta: 0:11:03 lr: 0.000903 loss: 4.6387 (4.3827) grad_norm: 1.2746 (1.2687) time: 0.5085 [2021-03-25 06:25:58 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 80/1251] eta: 0:10:50 lr: 0.000903 loss: 4.4097 (4.3819) grad_norm: 1.2506 (1.2778) time: 0.5107 [2021-03-25 06:26:03 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 90/1251] eta: 0:10:37 lr: 0.000904 loss: 4.5351 (4.4082) grad_norm: 1.3452 (1.2921) time: 0.5045 [2021-03-25 06:26:08 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 100/1251] eta: 0:10:26 lr: 0.000904 loss: 4.5351 (4.3974) grad_norm: 1.4267 (1.2910) time: 0.5024 [2021-03-25 06:26:13 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 110/1251] eta: 0:10:18 lr: 0.000904 loss: 4.6510 (4.4192) grad_norm: 1.1862 (1.2820) time: 0.5082 [2021-03-25 06:26:18 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 120/1251] eta: 0:10:09 lr: 0.000905 loss: 4.6752 (4.4351) grad_norm: 1.2190 (1.2939) time: 0.5086 [2021-03-25 06:26:23 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 130/1251] eta: 0:10:01 lr: 0.000905 loss: 4.4983 (4.4310) grad_norm: 1.2877 (1.2948) time: 0.5065 [2021-03-25 06:26:28 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 140/1251] eta: 0:09:53 lr: 0.000906 loss: 4.6176 (4.4532) grad_norm: 1.2409 (1.2933) time: 0.5075 [2021-03-25 06:26:34 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 150/1251] eta: 0:09:45 lr: 0.000906 loss: 4.7874 (4.4522) grad_norm: 1.2036 (1.2893) time: 0.5047 [2021-03-25 06:26:39 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 160/1251] eta: 0:09:38 lr: 0.000906 loss: 4.4579 (4.4372) grad_norm: 1.1957 (1.2871) time: 0.5017 [2021-03-25 06:26:44 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 170/1251] eta: 0:09:31 lr: 0.000907 loss: 4.1236 (4.4147) grad_norm: 1.2193 (1.2868) time: 0.5014 [2021-03-25 06:26:49 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 180/1251] eta: 0:09:24 lr: 0.000907 loss: 4.0055 (4.3976) grad_norm: 1.2627 (1.2873) time: 0.5032 [2021-03-25 06:26:54 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 190/1251] eta: 0:09:18 lr: 0.000908 loss: 4.0691 (4.3891) grad_norm: 1.3074 (1.2870) time: 0.5054 [2021-03-25 06:26:59 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 200/1251] eta: 0:09:12 lr: 0.000908 loss: 4.4344 (4.4038) grad_norm: 1.3455 (1.2907) time: 0.5095 [2021-03-25 06:27:04 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 210/1251] eta: 0:09:05 lr: 0.000908 loss: 4.6749 (4.4035) grad_norm: 1.3180 (1.2906) time: 0.5065 [2021-03-25 06:27:09 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 220/1251] eta: 0:08:59 lr: 0.000909 loss: 4.4537 (4.4048) grad_norm: 1.2556 (1.2894) time: 0.5000 [2021-03-25 06:27:14 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 230/1251] eta: 0:08:53 lr: 0.000909 loss: 4.5232 (4.4044) grad_norm: 1.1613 (1.2831) time: 0.5027 [2021-03-25 06:27:19 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 240/1251] eta: 0:08:47 lr: 0.000910 loss: 4.5859 (4.4089) grad_norm: 1.2574 (1.2889) time: 0.5062 [2021-03-25 06:27:24 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 250/1251] eta: 0:08:41 lr: 0.000910 loss: 4.7089 (4.4199) grad_norm: 1.3048 (1.2859) time: 0.5050 [2021-03-25 06:27:29 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 260/1251] eta: 0:08:35 lr: 0.000910 loss: 4.5270 (4.4153) grad_norm: 1.2449 (1.2835) time: 0.5051 [2021-03-25 06:27:34 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 270/1251] eta: 0:08:30 lr: 0.000911 loss: 4.5023 (4.4224) grad_norm: 1.1473 (1.2777) time: 0.5084 [2021-03-25 06:27:39 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 280/1251] eta: 0:08:24 lr: 0.000911 loss: 4.5263 (4.4282) grad_norm: 1.1473 (1.2772) time: 0.5101 [2021-03-25 06:27:44 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 290/1251] eta: 0:08:19 lr: 0.000912 loss: 4.8531 (4.4391) grad_norm: 1.1246 (1.2720) time: 0.5140 [2021-03-25 06:27:49 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 300/1251] eta: 0:08:13 lr: 0.000912 loss: 4.6863 (4.4372) grad_norm: 1.1246 (1.2690) time: 0.5122 [2021-03-25 06:27:55 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 310/1251] eta: 0:08:08 lr: 0.000912 loss: 4.1511 (4.4268) grad_norm: 1.1645 (1.2673) time: 0.5058 [2021-03-25 06:28:00 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 320/1251] eta: 0:08:02 lr: 0.000913 loss: 4.0077 (4.4263) grad_norm: 1.1558 (1.2636) time: 0.5070 [2021-03-25 06:28:05 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 330/1251] eta: 0:07:57 lr: 0.000913 loss: 4.6661 (4.4328) grad_norm: 1.1306 (1.2627) time: 0.5095 [2021-03-25 06:28:10 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 340/1251] eta: 0:07:51 lr: 0.000914 loss: 4.6978 (4.4357) grad_norm: 1.2566 (1.2638) time: 0.5080 [2021-03-25 06:28:15 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 350/1251] eta: 0:07:46 lr: 0.000914 loss: 4.5670 (4.4334) grad_norm: 1.2912 (1.2634) time: 0.5055 [2021-03-25 06:28:20 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 360/1251] eta: 0:07:40 lr: 0.000914 loss: 3.8868 (4.4144) grad_norm: 1.2219 (1.2638) time: 0.5048 [2021-03-25 06:28:25 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 370/1251] eta: 0:07:35 lr: 0.000915 loss: 4.1018 (4.4172) grad_norm: 1.2841 (1.2663) time: 0.5034 [2021-03-25 06:28:30 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 380/1251] eta: 0:07:29 lr: 0.000915 loss: 4.5994 (4.4190) grad_norm: 1.2947 (1.2677) time: 0.5047 [2021-03-25 06:28:35 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 390/1251] eta: 0:07:24 lr: 0.000916 loss: 4.6520 (4.4196) grad_norm: 1.2436 (1.2669) time: 0.5065 [2021-03-25 06:28:40 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 400/1251] eta: 0:07:19 lr: 0.000916 loss: 4.6520 (4.4228) grad_norm: 1.1805 (1.2635) time: 0.5055 [2021-03-25 06:28:45 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 410/1251] eta: 0:07:13 lr: 0.000916 loss: 4.5438 (4.4225) grad_norm: 1.1323 (1.2638) time: 0.5031 [2021-03-25 06:28:50 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 420/1251] eta: 0:07:08 lr: 0.000917 loss: 4.6814 (4.4264) grad_norm: 1.2335 (1.2653) time: 0.4990 [2021-03-25 06:28:55 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 430/1251] eta: 0:07:02 lr: 0.000917 loss: 4.7442 (4.4258) grad_norm: 1.1726 (1.2633) time: 0.4997 [2021-03-25 06:29:00 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 440/1251] eta: 0:06:57 lr: 0.000918 loss: 4.8235 (4.4310) grad_norm: 1.1642 (1.2614) time: 0.5032 [2021-03-25 06:29:05 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 450/1251] eta: 0:06:52 lr: 0.000918 loss: 4.8253 (4.4323) grad_norm: 1.1841 (1.2614) time: 0.5055 [2021-03-25 06:29:10 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 460/1251] eta: 0:06:46 lr: 0.000918 loss: 4.3710 (4.4285) grad_norm: 1.1997 (1.2604) time: 0.5064 [2021-03-25 06:29:15 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 470/1251] eta: 0:06:41 lr: 0.000919 loss: 4.2934 (4.4297) grad_norm: 1.2398 (1.2608) time: 0.5071 [2021-03-25 06:29:20 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 480/1251] eta: 0:06:36 lr: 0.000919 loss: 4.4994 (4.4285) grad_norm: 1.2170 (1.2593) time: 0.5081 [2021-03-25 06:29:25 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 490/1251] eta: 0:06:30 lr: 0.000920 loss: 4.5561 (4.4341) grad_norm: 1.1059 (inf) time: 0.5014 [2021-03-25 06:29:30 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 500/1251] eta: 0:06:25 lr: 0.000920 loss: 4.6362 (4.4370) grad_norm: 1.1472 (inf) time: 0.4988 [2021-03-25 06:29:36 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 510/1251] eta: 0:06:20 lr: 0.000920 loss: 4.3572 (4.4338) grad_norm: 1.2302 (inf) time: 0.5066 [2021-03-25 06:29:40 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 520/1251] eta: 0:06:14 lr: 0.000921 loss: 4.2726 (4.4306) grad_norm: 1.3146 (inf) time: 0.5030 [2021-03-25 06:29:46 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 530/1251] eta: 0:06:09 lr: 0.000921 loss: 4.2389 (4.4257) grad_norm: 1.2250 (inf) time: 0.5086 [2021-03-25 06:29:51 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 540/1251] eta: 0:06:04 lr: 0.000922 loss: 4.2115 (4.4258) grad_norm: 1.2250 (inf) time: 0.5162 [2021-03-25 06:29:56 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 550/1251] eta: 0:05:59 lr: 0.000922 loss: 4.5843 (4.4254) grad_norm: 1.3104 (inf) time: 0.5228 [2021-03-25 06:30:01 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 560/1251] eta: 0:05:54 lr: 0.000922 loss: 4.5575 (4.4259) grad_norm: 1.2357 (inf) time: 0.5263 [2021-03-25 06:30:06 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 570/1251] eta: 0:05:49 lr: 0.000923 loss: 4.5122 (4.4260) grad_norm: 1.1104 (inf) time: 0.5145 [2021-03-25 06:30:12 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 580/1251] eta: 0:05:44 lr: 0.000923 loss: 4.5294 (4.4254) grad_norm: 1.2803 (inf) time: 0.5097 [2021-03-25 06:30:17 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 590/1251] eta: 0:05:39 lr: 0.000924 loss: 4.6984 (4.4289) grad_norm: 1.3925 (inf) time: 0.5076 [2021-03-25 06:30:22 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 600/1251] eta: 0:05:34 lr: 0.000924 loss: 4.6055 (4.4245) grad_norm: 1.1479 (inf) time: 0.5072 [2021-03-25 06:30:27 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 610/1251] eta: 0:05:28 lr: 0.000924 loss: 4.1202 (4.4239) grad_norm: 1.0950 (inf) time: 0.5094 [2021-03-25 06:30:32 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 620/1251] eta: 0:05:23 lr: 0.000925 loss: 4.1202 (4.4212) grad_norm: 1.1306 (inf) time: 0.5126 [2021-03-25 06:30:37 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 630/1251] eta: 0:05:18 lr: 0.000925 loss: 4.6948 (4.4239) grad_norm: 1.2204 (inf) time: 0.5093 [2021-03-25 06:30:42 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 640/1251] eta: 0:05:13 lr: 0.000926 loss: 4.6942 (4.4264) grad_norm: 1.2596 (inf) time: 0.5023 [2021-03-25 06:30:47 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 650/1251] eta: 0:05:08 lr: 0.000926 loss: 4.4716 (4.4249) grad_norm: 1.2757 (inf) time: 0.5030 [2021-03-25 06:30:52 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 660/1251] eta: 0:05:02 lr: 0.000926 loss: 4.4716 (4.4255) grad_norm: 1.1758 (inf) time: 0.5007 [2021-03-25 06:30:57 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 670/1251] eta: 0:04:57 lr: 0.000927 loss: 4.4282 (4.4216) grad_norm: 1.2017 (inf) time: 0.4994 [2021-03-25 06:31:02 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 680/1251] eta: 0:04:52 lr: 0.000927 loss: 4.5479 (4.4252) grad_norm: 1.2017 (inf) time: 0.5006 [2021-03-25 06:31:07 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 690/1251] eta: 0:04:47 lr: 0.000928 loss: 4.6975 (4.4247) grad_norm: 1.1250 (inf) time: 0.5026 [2021-03-25 06:31:12 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 700/1251] eta: 0:04:42 lr: 0.000928 loss: 4.6462 (4.4237) grad_norm: 1.1168 (inf) time: 0.5054 [2021-03-25 06:31:17 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 710/1251] eta: 0:04:36 lr: 0.000928 loss: 4.6353 (4.4257) grad_norm: 1.2232 (inf) time: 0.5042 [2021-03-25 06:31:22 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 720/1251] eta: 0:04:31 lr: 0.000929 loss: 4.5858 (4.4285) grad_norm: 1.2118 (inf) time: 0.5035 [2021-03-25 06:31:27 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 730/1251] eta: 0:04:26 lr: 0.000929 loss: 4.4681 (4.4263) grad_norm: 1.1286 (inf) time: 0.5088 [2021-03-25 06:31:33 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 740/1251] eta: 0:04:21 lr: 0.000930 loss: 4.5034 (4.4281) grad_norm: 1.1427 (inf) time: 0.5330 [2021-03-25 06:31:38 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 750/1251] eta: 0:04:16 lr: 0.000930 loss: 4.6006 (4.4309) grad_norm: 1.1474 (inf) time: 0.5411 [2021-03-25 06:31:43 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 760/1251] eta: 0:04:11 lr: 0.000930 loss: 4.6006 (4.4325) grad_norm: 1.1660 (inf) time: 0.5213 [2021-03-25 06:31:48 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 770/1251] eta: 0:04:06 lr: 0.000931 loss: 4.5414 (4.4280) grad_norm: 1.1976 (inf) time: 0.5044 [2021-03-25 06:31:53 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 780/1251] eta: 0:04:01 lr: 0.000931 loss: 4.3494 (4.4271) grad_norm: 1.2367 (inf) time: 0.5046 [2021-03-25 06:31:58 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 790/1251] eta: 0:03:56 lr: 0.000932 loss: 4.4953 (4.4303) grad_norm: 1.1957 (inf) time: 0.5075 [2021-03-25 06:32:03 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 800/1251] eta: 0:03:50 lr: 0.000932 loss: 4.6583 (4.4332) grad_norm: 1.1805 (inf) time: 0.5033 [2021-03-25 06:32:09 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 810/1251] eta: 0:03:45 lr: 0.000932 loss: 4.6583 (4.4326) grad_norm: 1.1805 (inf) time: 0.5053 [2021-03-25 06:32:14 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 820/1251] eta: 0:03:40 lr: 0.000933 loss: 4.5211 (4.4321) grad_norm: 1.2850 (inf) time: 0.5055 [2021-03-25 06:32:19 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 830/1251] eta: 0:03:35 lr: 0.000933 loss: 4.6625 (4.4339) grad_norm: 1.2850 (inf) time: 0.5067 [2021-03-25 06:32:24 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 840/1251] eta: 0:03:30 lr: 0.000934 loss: 4.6183 (4.4330) grad_norm: 1.1464 (inf) time: 0.5076 [2021-03-25 06:32:29 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 850/1251] eta: 0:03:25 lr: 0.000934 loss: 4.5600 (4.4342) grad_norm: 1.2280 (inf) time: 0.5034 [2021-03-25 06:32:34 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 860/1251] eta: 0:03:20 lr: 0.000934 loss: 4.7203 (4.4325) grad_norm: 1.2393 (inf) time: 0.5030 [2021-03-25 06:32:39 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 870/1251] eta: 0:03:14 lr: 0.000935 loss: 4.5627 (4.4314) grad_norm: 1.1445 (inf) time: 0.5052 [2021-03-25 06:32:44 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 880/1251] eta: 0:03:09 lr: 0.000935 loss: 4.7434 (4.4308) grad_norm: 1.1631 (inf) time: 0.5037 [2021-03-25 06:32:49 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 890/1251] eta: 0:03:04 lr: 0.000936 loss: 4.4954 (4.4272) grad_norm: 1.1290 (inf) time: 0.5036 [2021-03-25 06:32:54 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 900/1251] eta: 0:02:59 lr: 0.000936 loss: 4.3219 (4.4249) grad_norm: 1.0659 (inf) time: 0.5057 [2021-03-25 06:32:59 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 910/1251] eta: 0:02:54 lr: 0.000936 loss: 4.3617 (4.4227) grad_norm: 1.1858 (inf) time: 0.5062 [2021-03-25 06:33:04 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 920/1251] eta: 0:02:49 lr: 0.000937 loss: 4.5366 (4.4227) grad_norm: 1.1979 (inf) time: 0.5047 [2021-03-25 06:33:09 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 930/1251] eta: 0:02:44 lr: 0.000937 loss: 4.6187 (4.4251) grad_norm: 1.1979 (inf) time: 0.5017 [2021-03-25 06:33:14 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 940/1251] eta: 0:02:38 lr: 0.000938 loss: 4.5949 (4.4262) grad_norm: 1.1323 (inf) time: 0.5004 [2021-03-25 06:33:19 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 950/1251] eta: 0:02:33 lr: 0.000938 loss: 4.6231 (4.4272) grad_norm: 1.1491 (inf) time: 0.5011 [2021-03-25 06:33:24 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 960/1251] eta: 0:02:28 lr: 0.000938 loss: 4.5064 (4.4274) grad_norm: 1.1462 (inf) time: 0.5046 [2021-03-25 06:33:29 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 970/1251] eta: 0:02:23 lr: 0.000939 loss: 4.5064 (4.4277) grad_norm: 1.1204 (inf) time: 0.5053 [2021-03-25 06:33:34 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 980/1251] eta: 0:02:18 lr: 0.000939 loss: 4.4904 (4.4244) grad_norm: 1.2813 (inf) time: 0.5061 [2021-03-25 06:33:39 swin_small_patch4_window7_224] INFO: Epoch: [18] [ 990/1251] eta: 0:02:13 lr: 0.000940 loss: 4.3552 (4.4250) grad_norm: 1.2308 (inf) time: 0.5072 [2021-03-25 06:33:44 swin_small_patch4_window7_224] INFO: Epoch: [18] [1000/1251] eta: 0:02:08 lr: 0.000940 loss: 4.7349 (4.4278) grad_norm: 1.2063 (inf) time: 0.5075 [2021-03-25 06:33:50 swin_small_patch4_window7_224] INFO: Epoch: [18] [1010/1251] eta: 0:02:03 lr: 0.000940 loss: 4.7317 (4.4261) grad_norm: 1.2113 (inf) time: 0.5089 [2021-03-25 06:33:55 swin_small_patch4_window7_224] INFO: Epoch: [18] [1020/1251] eta: 0:01:57 lr: 0.000941 loss: 4.5068 (4.4272) grad_norm: 1.1991 (inf) time: 0.5104 [2021-03-25 06:34:00 swin_small_patch4_window7_224] INFO: Epoch: [18] [1030/1251] eta: 0:01:52 lr: 0.000941 loss: 4.5659 (4.4275) grad_norm: 1.1655 (inf) time: 0.5066 [2021-03-25 06:34:05 swin_small_patch4_window7_224] INFO: Epoch: [18] [1040/1251] eta: 0:01:47 lr: 0.000942 loss: 4.4513 (4.4287) grad_norm: 1.1655 (inf) time: 0.5086 [2021-03-25 06:34:10 swin_small_patch4_window7_224] INFO: Epoch: [18] [1050/1251] eta: 0:01:42 lr: 0.000942 loss: 4.4513 (4.4305) grad_norm: 1.1719 (inf) time: 0.5145 [2021-03-25 06:34:15 swin_small_patch4_window7_224] INFO: Epoch: [18] [1060/1251] eta: 0:01:37 lr: 0.000942 loss: 4.6171 (4.4325) grad_norm: 1.1832 (inf) time: 0.5083 [2021-03-25 06:34:20 swin_small_patch4_window7_224] INFO: Epoch: [18] [1070/1251] eta: 0:01:32 lr: 0.000943 loss: 4.5669 (4.4327) grad_norm: 1.0938 (inf) time: 0.5016 [2021-03-25 06:34:25 swin_small_patch4_window7_224] INFO: Epoch: [18] [1080/1251] eta: 0:01:27 lr: 0.000943 loss: 4.6153 (4.4351) grad_norm: 1.1874 (inf) time: 0.5024 [2021-03-25 06:34:30 swin_small_patch4_window7_224] INFO: Epoch: [18] [1090/1251] eta: 0:01:22 lr: 0.000944 loss: 4.7117 (4.4368) grad_norm: 1.2914 (inf) time: 0.5100 [2021-03-25 06:34:35 swin_small_patch4_window7_224] INFO: Epoch: [18] [1100/1251] eta: 0:01:17 lr: 0.000944 loss: 4.7374 (4.4381) grad_norm: 1.2198 (inf) time: 0.5069 [2021-03-25 06:34:40 swin_small_patch4_window7_224] INFO: Epoch: [18] [1110/1251] eta: 0:01:11 lr: 0.000944 loss: 4.5424 (4.4404) grad_norm: 1.2198 (inf) time: 0.5013 [2021-03-25 06:34:45 swin_small_patch4_window7_224] INFO: Epoch: [18] [1120/1251] eta: 0:01:06 lr: 0.000945 loss: 4.5746 (4.4403) grad_norm: 1.2546 (inf) time: 0.5079 [2021-03-25 06:34:50 swin_small_patch4_window7_224] INFO: Epoch: [18] [1130/1251] eta: 0:01:01 lr: 0.000945 loss: 4.4988 (4.4390) grad_norm: 1.2436 (inf) time: 0.5113 [2021-03-25 06:34:55 swin_small_patch4_window7_224] INFO: Epoch: [18] [1140/1251] eta: 0:00:56 lr: 0.000946 loss: 4.4988 (4.4395) grad_norm: 1.2184 (inf) time: 0.5052 [2021-03-25 06:35:01 swin_small_patch4_window7_224] INFO: Epoch: [18] [1150/1251] eta: 0:00:51 lr: 0.000946 loss: 4.6668 (4.4401) grad_norm: 1.2106 (inf) time: 0.5005 [2021-03-25 06:35:06 swin_small_patch4_window7_224] INFO: Epoch: [18] [1160/1251] eta: 0:00:46 lr: 0.000946 loss: 4.7479 (4.4430) grad_norm: 1.1696 (inf) time: 0.5041 [2021-03-25 06:35:11 swin_small_patch4_window7_224] INFO: Epoch: [18] [1170/1251] eta: 0:00:41 lr: 0.000947 loss: 4.7381 (4.4412) grad_norm: 1.1190 (inf) time: 0.5077 [2021-03-25 06:35:16 swin_small_patch4_window7_224] INFO: Epoch: [18] [1180/1251] eta: 0:00:36 lr: 0.000947 loss: 4.4376 (4.4412) grad_norm: 1.1928 (inf) time: 0.5053 [2021-03-25 06:35:21 swin_small_patch4_window7_224] INFO: Epoch: [18] [1190/1251] eta: 0:00:31 lr: 0.000948 loss: 4.4398 (4.4419) grad_norm: 1.2789 (inf) time: 0.4993 [2021-03-25 06:35:26 swin_small_patch4_window7_224] INFO: Epoch: [18] [1200/1251] eta: 0:00:26 lr: 0.000948 loss: 4.5796 (4.4433) grad_norm: 1.2018 (inf) time: 0.4966 [2021-03-25 06:35:31 swin_small_patch4_window7_224] INFO: Epoch: [18] [1210/1251] eta: 0:00:20 lr: 0.000948 loss: 4.4526 (4.4408) grad_norm: 1.2018 (inf) time: 0.4974 [2021-03-25 06:35:36 swin_small_patch4_window7_224] INFO: Epoch: [18] [1220/1251] eta: 0:00:15 lr: 0.000949 loss: 4.3939 (4.4408) grad_norm: 1.2346 (inf) time: 0.5027 [2021-03-25 06:35:41 swin_small_patch4_window7_224] INFO: Epoch: [18] [1230/1251] eta: 0:00:10 lr: 0.000949 loss: 4.3535 (4.4403) grad_norm: 1.1753 (inf) time: 0.5026 [2021-03-25 06:35:46 swin_small_patch4_window7_224] INFO: Epoch: [18] [1240/1251] eta: 0:00:05 lr: 0.000950 loss: 4.2417 (4.4390) grad_norm: 1.1632 (inf) time: 0.5041 [2021-03-25 06:35:51 swin_small_patch4_window7_224] INFO: Epoch: [18] [1250/1251] eta: 0:00:00 lr: 0.000950 loss: 4.5602 (4.4411) grad_norm: 1.2546 (inf) time: 0.4979 [2021-03-25 06:35:54 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:46 loss: 2.0729 (2.0729) acc1: 50.0000 (50.0000) acc5: 79.6875 (79.6875) [2021-03-25 06:35:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.6986 (1.7769) acc1: 59.3750 (58.8068) acc5: 85.9375 (83.9489) [2021-03-25 06:35:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.7831 (1.7793) acc1: 59.3750 (59.1518) acc5: 84.3750 (83.5565) [2021-03-25 06:36:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.8399 (1.8456) acc1: 57.8125 (57.7117) acc5: 82.8125 (82.8125) [2021-03-25 06:36:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.8562 (1.8250) acc1: 56.2500 (58.1936) acc5: 82.8125 (83.0412) [2021-03-25 06:36:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.6812 (1.8031) acc1: 62.5000 (58.6240) acc5: 82.8125 (83.5520) [2021-03-25 06:36:06 swin_small_patch4_window7_224] INFO: * Acc@1 59.610 Acc@5 83.466 loss 1.784 [2021-03-25 06:36:06 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 59.6% [2021-03-25 06:36:06 swin_small_patch4_window7_224] INFO: Max accuracy: 59.61% [2021-03-25 06:36:10 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 0/1251] eta: 1:23:00 lr: 0.000950 loss: 4.0531 (4.0531) grad_norm: 1.6886 (1.6886) time: 3.9816 [2021-03-25 06:36:15 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 10/1251] eta: 0:17:19 lr: 0.000950 loss: 4.4107 (4.4050) grad_norm: 1.3239 (1.4135) time: 0.8379 [2021-03-25 06:36:20 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 20/1251] eta: 0:13:59 lr: 0.000951 loss: 4.3008 (4.2556) grad_norm: 1.2301 (1.2943) time: 0.5169 [2021-03-25 06:36:25 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 30/1251] eta: 0:12:41 lr: 0.000951 loss: 4.0158 (4.2838) grad_norm: 1.1158 (1.2423) time: 0.5059 [2021-03-25 06:36:30 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 40/1251] eta: 0:11:58 lr: 0.000952 loss: 4.2691 (4.3218) grad_norm: 1.1023 (1.2159) time: 0.5001 [2021-03-25 06:36:35 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 50/1251] eta: 0:11:29 lr: 0.000952 loss: 4.2691 (4.3126) grad_norm: 1.1066 (1.2016) time: 0.4980 [2021-03-25 06:36:40 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 60/1251] eta: 0:11:10 lr: 0.000952 loss: 4.3785 (4.3226) grad_norm: 1.2732 (1.2466) time: 0.5015 [2021-03-25 06:36:45 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 70/1251] eta: 0:10:55 lr: 0.000953 loss: 4.5202 (4.3497) grad_norm: 1.3233 (1.2580) time: 0.5068 [2021-03-25 06:36:50 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 80/1251] eta: 0:10:44 lr: 0.000953 loss: 4.4594 (4.3240) grad_norm: 1.3233 (1.2681) time: 0.5132 [2021-03-25 06:36:56 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 90/1251] eta: 0:10:34 lr: 0.000954 loss: 4.2074 (4.3437) grad_norm: 1.1850 (1.2562) time: 0.5161 [2021-03-25 06:37:01 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 100/1251] eta: 0:10:24 lr: 0.000954 loss: 4.6469 (4.3871) grad_norm: 1.1350 (1.2503) time: 0.5093 [2021-03-25 06:37:06 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 110/1251] eta: 0:10:14 lr: 0.000954 loss: 4.5315 (4.3851) grad_norm: 1.1750 (1.2544) time: 0.5026 [2021-03-25 06:37:11 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 120/1251] eta: 0:10:06 lr: 0.000955 loss: 4.5315 (4.4011) grad_norm: 1.2631 (1.2604) time: 0.5055 [2021-03-25 06:37:16 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 130/1251] eta: 0:09:58 lr: 0.000955 loss: 4.6060 (4.3996) grad_norm: 1.2876 (1.2633) time: 0.5075 [2021-03-25 06:37:21 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 140/1251] eta: 0:09:50 lr: 0.000956 loss: 4.5142 (4.3977) grad_norm: 1.2321 (1.2674) time: 0.5019 [2021-03-25 06:37:26 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 150/1251] eta: 0:09:43 lr: 0.000956 loss: 4.5142 (4.4017) grad_norm: 1.2321 (1.2734) time: 0.5013 [2021-03-25 06:37:31 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 160/1251] eta: 0:09:35 lr: 0.000956 loss: 4.4649 (4.4043) grad_norm: 1.2122 (1.2699) time: 0.5018 [2021-03-25 06:37:36 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 170/1251] eta: 0:09:29 lr: 0.000957 loss: 4.4252 (4.4054) grad_norm: 1.3210 (1.2713) time: 0.5016 [2021-03-25 06:37:41 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 180/1251] eta: 0:09:23 lr: 0.000957 loss: 4.3249 (4.3994) grad_norm: 1.3164 (1.2700) time: 0.5099 [2021-03-25 06:37:46 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 190/1251] eta: 0:09:16 lr: 0.000958 loss: 4.3509 (4.4089) grad_norm: 1.2559 (1.2733) time: 0.5054 [2021-03-25 06:37:51 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 200/1251] eta: 0:09:10 lr: 0.000958 loss: 4.6864 (4.4132) grad_norm: 1.3633 (1.2774) time: 0.5004 [2021-03-25 06:37:56 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 210/1251] eta: 0:09:04 lr: 0.000958 loss: 4.7022 (4.4143) grad_norm: 1.3539 (1.2797) time: 0.5073 [2021-03-25 06:38:01 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 220/1251] eta: 0:08:58 lr: 0.000959 loss: 4.5197 (4.4202) grad_norm: 1.2234 (1.2774) time: 0.5076 [2021-03-25 06:38:06 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 230/1251] eta: 0:08:52 lr: 0.000959 loss: 4.5652 (4.4179) grad_norm: 1.1844 (1.2714) time: 0.5077 [2021-03-25 06:38:11 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 240/1251] eta: 0:08:46 lr: 0.000960 loss: 4.7155 (4.4347) grad_norm: 1.1600 (1.2689) time: 0.5061 [2021-03-25 06:38:16 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 250/1251] eta: 0:08:40 lr: 0.000960 loss: 4.7155 (4.4355) grad_norm: 1.1140 (1.2627) time: 0.5009 [2021-03-25 06:38:21 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 260/1251] eta: 0:08:34 lr: 0.000960 loss: 4.5791 (4.4360) grad_norm: 1.0857 (1.2614) time: 0.4995 [2021-03-25 06:38:26 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 270/1251] eta: 0:08:28 lr: 0.000961 loss: 4.2786 (4.4271) grad_norm: 1.1913 (1.2614) time: 0.5043 [2021-03-25 06:38:31 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 280/1251] eta: 0:08:22 lr: 0.000961 loss: 4.2848 (4.4320) grad_norm: 1.2227 (1.2591) time: 0.5011 [2021-03-25 06:38:36 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 290/1251] eta: 0:08:17 lr: 0.000962 loss: 4.6987 (4.4330) grad_norm: 1.1717 (1.2559) time: 0.4990 [2021-03-25 06:38:42 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 300/1251] eta: 0:08:11 lr: 0.000962 loss: 4.4501 (4.4248) grad_norm: 1.1800 (1.2586) time: 0.5054 [2021-03-25 06:38:47 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 310/1251] eta: 0:08:06 lr: 0.000962 loss: 4.3333 (4.4220) grad_norm: 1.3475 (1.2627) time: 0.5084 [2021-03-25 06:38:52 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 320/1251] eta: 0:08:00 lr: 0.000963 loss: 4.5129 (4.4276) grad_norm: 1.3839 (1.2666) time: 0.5096 [2021-03-25 06:38:57 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 330/1251] eta: 0:07:55 lr: 0.000963 loss: 4.6226 (4.4374) grad_norm: 1.4161 (1.2700) time: 0.5083 [2021-03-25 06:39:02 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 340/1251] eta: 0:07:49 lr: 0.000964 loss: 4.6340 (4.4396) grad_norm: 1.2696 (1.2690) time: 0.5074 [2021-03-25 06:39:07 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 350/1251] eta: 0:07:44 lr: 0.000964 loss: 4.5652 (4.4364) grad_norm: 1.1556 (1.2658) time: 0.5079 [2021-03-25 06:39:12 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 360/1251] eta: 0:07:39 lr: 0.000964 loss: 4.2910 (4.4263) grad_norm: 1.1727 (1.2659) time: 0.5113 [2021-03-25 06:39:17 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 370/1251] eta: 0:07:34 lr: 0.000965 loss: 4.2866 (4.4293) grad_norm: 1.1727 (1.2632) time: 0.5113 [2021-03-25 06:39:22 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 380/1251] eta: 0:07:28 lr: 0.000965 loss: 4.6994 (4.4345) grad_norm: 1.2630 (1.2657) time: 0.5045 [2021-03-25 06:39:27 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 390/1251] eta: 0:07:23 lr: 0.000966 loss: 4.6994 (4.4396) grad_norm: 1.3504 (1.2662) time: 0.5050 [2021-03-25 06:39:32 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 400/1251] eta: 0:07:17 lr: 0.000966 loss: 4.6935 (4.4415) grad_norm: 1.2060 (1.2628) time: 0.5059 [2021-03-25 06:39:37 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 410/1251] eta: 0:07:12 lr: 0.000966 loss: 4.2907 (4.4365) grad_norm: 1.1281 (1.2608) time: 0.5021 [2021-03-25 06:39:42 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 420/1251] eta: 0:07:07 lr: 0.000967 loss: 4.4484 (4.4374) grad_norm: 1.2243 (1.2624) time: 0.5054 [2021-03-25 06:39:47 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 430/1251] eta: 0:07:01 lr: 0.000967 loss: 4.4853 (4.4389) grad_norm: 1.2734 (1.2615) time: 0.5049 [2021-03-25 06:39:52 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 440/1251] eta: 0:06:56 lr: 0.000968 loss: 4.5432 (4.4403) grad_norm: 1.2218 (1.2611) time: 0.5012 [2021-03-25 06:39:58 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 450/1251] eta: 0:06:51 lr: 0.000968 loss: 4.5003 (4.4381) grad_norm: 1.1756 (1.2605) time: 0.5086 [2021-03-25 06:40:03 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 460/1251] eta: 0:06:46 lr: 0.000968 loss: 4.4933 (4.4373) grad_norm: 1.2005 (1.2604) time: 0.5108 [2021-03-25 06:40:08 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 470/1251] eta: 0:06:40 lr: 0.000969 loss: 4.3479 (4.4329) grad_norm: 1.2005 (1.2598) time: 0.5041 [2021-03-25 06:40:13 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 480/1251] eta: 0:06:35 lr: 0.000969 loss: 4.5654 (4.4376) grad_norm: 1.1430 (1.2597) time: 0.5039 [2021-03-25 06:40:18 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 490/1251] eta: 0:06:30 lr: 0.000970 loss: 4.5641 (4.4348) grad_norm: 1.1293 (1.2570) time: 0.5041 [2021-03-25 06:40:23 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 500/1251] eta: 0:06:25 lr: 0.000970 loss: 4.5641 (4.4387) grad_norm: 1.1293 (1.2543) time: 0.5040 [2021-03-25 06:40:28 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 510/1251] eta: 0:06:19 lr: 0.000970 loss: 4.6843 (4.4421) grad_norm: 1.1762 (1.2542) time: 0.5047 [2021-03-25 06:40:33 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 520/1251] eta: 0:06:14 lr: 0.000971 loss: 4.4288 (4.4362) grad_norm: 1.1856 (1.2520) time: 0.5001 [2021-03-25 06:40:38 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 530/1251] eta: 0:06:09 lr: 0.000971 loss: 4.3083 (4.4369) grad_norm: 1.1837 (1.2515) time: 0.5051 [2021-03-25 06:40:43 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 540/1251] eta: 0:06:04 lr: 0.000972 loss: 4.6465 (4.4411) grad_norm: 1.2316 (1.2516) time: 0.5119 [2021-03-25 06:40:48 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 550/1251] eta: 0:05:59 lr: 0.000972 loss: 4.5915 (4.4419) grad_norm: 1.1992 (1.2496) time: 0.5204 [2021-03-25 06:40:53 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 560/1251] eta: 0:05:53 lr: 0.000972 loss: 4.4966 (4.4422) grad_norm: 1.1613 (1.2489) time: 0.5148 [2021-03-25 06:40:58 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 570/1251] eta: 0:05:48 lr: 0.000973 loss: 4.5517 (4.4463) grad_norm: 1.1310 (1.2457) time: 0.5030 [2021-03-25 06:41:04 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 580/1251] eta: 0:05:43 lr: 0.000973 loss: 4.5135 (4.4466) grad_norm: 1.0871 (1.2429) time: 0.5070 [2021-03-25 06:41:09 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 590/1251] eta: 0:05:38 lr: 0.000974 loss: 4.4369 (4.4442) grad_norm: 1.0680 (1.2406) time: 0.5074 [2021-03-25 06:41:14 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 600/1251] eta: 0:05:33 lr: 0.000974 loss: 4.2812 (4.4429) grad_norm: 1.0761 (1.2411) time: 0.5103 [2021-03-25 06:41:19 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 610/1251] eta: 0:05:28 lr: 0.000974 loss: 4.3387 (4.4418) grad_norm: 1.2484 (1.2425) time: 0.5106 [2021-03-25 06:41:24 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 620/1251] eta: 0:05:22 lr: 0.000975 loss: 4.3387 (4.4388) grad_norm: 1.2582 (1.2423) time: 0.5042 [2021-03-25 06:41:29 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 630/1251] eta: 0:05:17 lr: 0.000975 loss: 4.4598 (4.4387) grad_norm: 1.2715 (1.2437) time: 0.5081 [2021-03-25 06:41:34 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 640/1251] eta: 0:05:12 lr: 0.000976 loss: 4.5803 (4.4411) grad_norm: 1.2285 (1.2421) time: 0.5167 [2021-03-25 06:41:39 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 650/1251] eta: 0:05:07 lr: 0.000976 loss: 4.5803 (4.4406) grad_norm: 1.2285 (1.2431) time: 0.5127 [2021-03-25 06:41:44 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 660/1251] eta: 0:05:02 lr: 0.000976 loss: 4.2446 (4.4350) grad_norm: 1.2633 (1.2424) time: 0.5069 [2021-03-25 06:41:49 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 670/1251] eta: 0:04:57 lr: 0.000977 loss: 4.3834 (4.4333) grad_norm: 1.1110 (1.2400) time: 0.5062 [2021-03-25 06:41:54 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 680/1251] eta: 0:04:52 lr: 0.000977 loss: 3.9548 (4.4258) grad_norm: 1.1165 (1.2392) time: 0.5045 [2021-03-25 06:41:59 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 690/1251] eta: 0:04:46 lr: 0.000978 loss: 4.0916 (4.4263) grad_norm: 1.2393 (1.2408) time: 0.5019 [2021-03-25 06:42:04 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 700/1251] eta: 0:04:41 lr: 0.000978 loss: 4.3679 (4.4252) grad_norm: 1.2185 (1.2404) time: 0.5043 [2021-03-25 06:42:09 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 710/1251] eta: 0:04:36 lr: 0.000978 loss: 4.2920 (4.4263) grad_norm: 1.1690 (1.2406) time: 0.5026 [2021-03-25 06:42:14 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 720/1251] eta: 0:04:31 lr: 0.000979 loss: 4.5578 (4.4276) grad_norm: 1.2073 (1.2401) time: 0.5012 [2021-03-25 06:42:20 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 730/1251] eta: 0:04:26 lr: 0.000979 loss: 4.5374 (4.4270) grad_norm: 1.2222 (1.2403) time: 0.5107 [2021-03-25 06:42:25 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 740/1251] eta: 0:04:21 lr: 0.000980 loss: 4.4364 (4.4289) grad_norm: 1.2701 (1.2411) time: 0.5290 [2021-03-25 06:42:30 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 750/1251] eta: 0:04:16 lr: 0.000980 loss: 4.4260 (4.4285) grad_norm: 1.2156 (1.2407) time: 0.5293 [2021-03-25 06:42:35 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 760/1251] eta: 0:04:11 lr: 0.000980 loss: 4.4140 (4.4276) grad_norm: 1.1258 (1.2397) time: 0.5126 [2021-03-25 06:42:40 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 770/1251] eta: 0:04:05 lr: 0.000981 loss: 4.6878 (4.4331) grad_norm: 1.1074 (1.2378) time: 0.5024 [2021-03-25 06:42:45 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 780/1251] eta: 0:04:00 lr: 0.000981 loss: 4.6939 (4.4343) grad_norm: 1.0735 (1.2368) time: 0.4974 [2021-03-25 06:42:50 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 790/1251] eta: 0:03:55 lr: 0.000982 loss: 4.4181 (4.4312) grad_norm: 1.1751 (1.2370) time: 0.5036 [2021-03-25 06:42:55 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 800/1251] eta: 0:03:50 lr: 0.000982 loss: 4.3393 (4.4297) grad_norm: 1.2763 (1.2369) time: 0.5058 [2021-03-25 06:43:00 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 810/1251] eta: 0:03:45 lr: 0.000982 loss: 4.5755 (4.4330) grad_norm: 1.2944 (1.2379) time: 0.5021 [2021-03-25 06:43:06 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 820/1251] eta: 0:03:40 lr: 0.000983 loss: 4.7398 (4.4342) grad_norm: 1.2490 (1.2389) time: 0.5114 [2021-03-25 06:43:11 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 830/1251] eta: 0:03:35 lr: 0.000983 loss: 4.4422 (4.4340) grad_norm: 1.3191 (1.2409) time: 0.5221 [2021-03-25 06:43:16 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 840/1251] eta: 0:03:30 lr: 0.000984 loss: 4.3765 (4.4314) grad_norm: 1.1468 (1.2389) time: 0.5088 [2021-03-25 06:43:21 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 850/1251] eta: 0:03:24 lr: 0.000984 loss: 4.1610 (4.4300) grad_norm: 1.0952 (1.2385) time: 0.4948 [2021-03-25 06:43:26 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 860/1251] eta: 0:03:19 lr: 0.000984 loss: 4.5040 (4.4318) grad_norm: 1.1979 (1.2386) time: 0.4953 [2021-03-25 06:43:31 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 870/1251] eta: 0:03:14 lr: 0.000985 loss: 4.5040 (4.4312) grad_norm: 1.1586 (1.2372) time: 0.5031 [2021-03-25 06:43:36 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 880/1251] eta: 0:03:09 lr: 0.000985 loss: 4.4800 (4.4332) grad_norm: 1.1455 (1.2376) time: 0.5011 [2021-03-25 06:43:41 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 890/1251] eta: 0:03:04 lr: 0.000986 loss: 4.8019 (4.4346) grad_norm: 1.1794 (1.2373) time: 0.4943 [2021-03-25 06:43:46 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 900/1251] eta: 0:02:59 lr: 0.000986 loss: 4.6834 (4.4356) grad_norm: 1.1932 (1.2377) time: 0.4988 [2021-03-25 06:43:51 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 910/1251] eta: 0:02:53 lr: 0.000986 loss: 4.6808 (4.4352) grad_norm: 1.1932 (1.2380) time: 0.5031 [2021-03-25 06:43:56 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 920/1251] eta: 0:02:48 lr: 0.000987 loss: 4.4117 (4.4361) grad_norm: 1.1956 (1.2384) time: 0.5005 [2021-03-25 06:44:01 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 930/1251] eta: 0:02:43 lr: 0.000987 loss: 4.4117 (4.4365) grad_norm: 1.1956 (1.2383) time: 0.4983 [2021-03-25 06:44:06 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 940/1251] eta: 0:02:38 lr: 0.000988 loss: 4.4698 (4.4352) grad_norm: 1.1220 (1.2365) time: 0.5094 [2021-03-25 06:44:11 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 950/1251] eta: 0:02:33 lr: 0.000988 loss: 4.5727 (4.4366) grad_norm: 1.0566 (1.2348) time: 0.5052 [2021-03-25 06:44:16 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 960/1251] eta: 0:02:28 lr: 0.000988 loss: 4.6700 (4.4367) grad_norm: 1.0772 (1.2341) time: 0.4982 [2021-03-25 06:44:21 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 970/1251] eta: 0:02:23 lr: 0.000989 loss: 4.7803 (4.4425) grad_norm: 1.1182 (1.2334) time: 0.5051 [2021-03-25 06:44:26 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 980/1251] eta: 0:02:18 lr: 0.000989 loss: 4.7803 (4.4443) grad_norm: 1.1281 (1.2329) time: 0.5050 [2021-03-25 06:44:31 swin_small_patch4_window7_224] INFO: Epoch: [19] [ 990/1251] eta: 0:02:12 lr: 0.000990 loss: 4.5794 (4.4455) grad_norm: 1.1716 (1.2330) time: 0.4998 [2021-03-25 06:44:36 swin_small_patch4_window7_224] INFO: Epoch: [19] [1000/1251] eta: 0:02:07 lr: 0.000990 loss: 4.7555 (4.4474) grad_norm: 1.2063 (1.2326) time: 0.5008 [2021-03-25 06:44:41 swin_small_patch4_window7_224] INFO: Epoch: [19] [1010/1251] eta: 0:02:02 lr: 0.000990 loss: 4.7555 (4.4482) grad_norm: 1.1989 (1.2334) time: 0.5087 [2021-03-25 06:44:46 swin_small_patch4_window7_224] INFO: Epoch: [19] [1020/1251] eta: 0:01:57 lr: 0.000991 loss: 4.1260 (4.4431) grad_norm: 1.2335 (1.2340) time: 0.5065 [2021-03-25 06:44:51 swin_small_patch4_window7_224] INFO: Epoch: [19] [1030/1251] eta: 0:01:52 lr: 0.000991 loss: 4.0615 (4.4416) grad_norm: 1.2335 (1.2336) time: 0.5044 [2021-03-25 06:44:56 swin_small_patch4_window7_224] INFO: Epoch: [19] [1040/1251] eta: 0:01:47 lr: 0.000992 loss: 4.3810 (4.4405) grad_norm: 1.2411 (1.2343) time: 0.5063 [2021-03-25 06:45:01 swin_small_patch4_window7_224] INFO: Epoch: [19] [1050/1251] eta: 0:01:42 lr: 0.000992 loss: 4.5273 (4.4417) grad_norm: 1.2376 (1.2337) time: 0.5012 [2021-03-25 06:45:06 swin_small_patch4_window7_224] INFO: Epoch: [19] [1060/1251] eta: 0:01:37 lr: 0.000992 loss: 4.4123 (4.4389) grad_norm: 1.1066 (1.2329) time: 0.5038 [2021-03-25 06:45:11 swin_small_patch4_window7_224] INFO: Epoch: [19] [1070/1251] eta: 0:01:32 lr: 0.000993 loss: 3.9871 (4.4375) grad_norm: 1.1712 (1.2332) time: 0.5072 [2021-03-25 06:45:16 swin_small_patch4_window7_224] INFO: Epoch: [19] [1080/1251] eta: 0:01:27 lr: 0.000993 loss: 4.5337 (4.4392) grad_norm: 1.2069 (1.2324) time: 0.5000 [2021-03-25 06:45:21 swin_small_patch4_window7_224] INFO: Epoch: [19] [1090/1251] eta: 0:01:21 lr: 0.000994 loss: 4.5337 (4.4387) grad_norm: 1.1417 (1.2324) time: 0.4997 [2021-03-25 06:45:26 swin_small_patch4_window7_224] INFO: Epoch: [19] [1100/1251] eta: 0:01:16 lr: 0.000994 loss: 4.5377 (4.4401) grad_norm: 1.2615 (1.2342) time: 0.4969 [2021-03-25 06:45:31 swin_small_patch4_window7_224] INFO: Epoch: [19] [1110/1251] eta: 0:01:11 lr: 0.000994 loss: 4.6682 (4.4376) grad_norm: 1.2233 (1.2333) time: 0.4921 [2021-03-25 06:45:36 swin_small_patch4_window7_224] INFO: Epoch: [19] [1120/1251] eta: 0:01:06 lr: 0.000995 loss: 4.6682 (4.4392) grad_norm: 1.1956 (1.2334) time: 0.4950 [2021-03-25 06:45:41 swin_small_patch4_window7_224] INFO: Epoch: [19] [1130/1251] eta: 0:01:01 lr: 0.000995 loss: 4.6427 (4.4382) grad_norm: 1.2331 (1.2330) time: 0.5014 [2021-03-25 06:45:46 swin_small_patch4_window7_224] INFO: Epoch: [19] [1140/1251] eta: 0:00:56 lr: 0.000996 loss: 4.3521 (4.4373) grad_norm: 1.1698 (1.2324) time: 0.5033 [2021-03-25 06:45:51 swin_small_patch4_window7_224] INFO: Epoch: [19] [1150/1251] eta: 0:00:51 lr: 0.000996 loss: 4.2629 (4.4366) grad_norm: 1.2021 (1.2325) time: 0.5007 [2021-03-25 06:45:56 swin_small_patch4_window7_224] INFO: Epoch: [19] [1160/1251] eta: 0:00:46 lr: 0.000996 loss: 4.2723 (4.4348) grad_norm: 1.2074 (1.2314) time: 0.5031 [2021-03-25 06:46:01 swin_small_patch4_window7_224] INFO: Epoch: [19] [1170/1251] eta: 0:00:41 lr: 0.000997 loss: 4.5082 (4.4356) grad_norm: 1.0781 (1.2300) time: 0.5053 [2021-03-25 06:46:06 swin_small_patch4_window7_224] INFO: Epoch: [19] [1180/1251] eta: 0:00:36 lr: 0.000997 loss: 4.6936 (4.4363) grad_norm: 1.1029 (1.2310) time: 0.4993 [2021-03-25 06:46:11 swin_small_patch4_window7_224] INFO: Epoch: [19] [1190/1251] eta: 0:00:31 lr: 0.000998 loss: 4.7214 (4.4393) grad_norm: 1.2361 (1.2310) time: 0.4998 [2021-03-25 06:46:17 swin_small_patch4_window7_224] INFO: Epoch: [19] [1200/1251] eta: 0:00:25 lr: 0.000998 loss: 4.6281 (4.4385) grad_norm: 1.1554 (1.2308) time: 0.5089 [2021-03-25 06:46:21 swin_small_patch4_window7_224] INFO: Epoch: [19] [1210/1251] eta: 0:00:20 lr: 0.000998 loss: 4.6281 (4.4413) grad_norm: 1.2141 (1.2311) time: 0.5047 [2021-03-25 06:46:27 swin_small_patch4_window7_224] INFO: Epoch: [19] [1220/1251] eta: 0:00:15 lr: 0.000999 loss: 4.5744 (4.4392) grad_norm: 1.1925 (1.2304) time: 0.5019 [2021-03-25 06:46:32 swin_small_patch4_window7_224] INFO: Epoch: [19] [1230/1251] eta: 0:00:10 lr: 0.000999 loss: 4.5144 (4.4399) grad_norm: 1.0928 (1.2291) time: 0.5061 [2021-03-25 06:46:37 swin_small_patch4_window7_224] INFO: Epoch: [19] [1240/1251] eta: 0:00:05 lr: 0.001000 loss: 4.5432 (4.4397) grad_norm: 1.0648 (1.2288) time: 0.4999 [2021-03-25 06:46:42 swin_small_patch4_window7_224] INFO: Epoch: [19] [1250/1251] eta: 0:00:00 lr: 0.001000 loss: 4.5855 (4.4389) grad_norm: 1.0846 (1.2284) time: 0.4959 [2021-03-25 06:46:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:46 loss: 1.7661 (1.7661) acc1: 56.2500 (56.2500) acc5: 82.8125 (82.8125) [2021-03-25 06:46:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.7832 (1.8653) acc1: 57.8125 (57.9545) acc5: 81.2500 (82.2443) [2021-03-25 06:46:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.7034 (1.7982) acc1: 57.8125 (59.1518) acc5: 84.3750 (83.3333) [2021-03-25 06:46:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.6785 (1.7615) acc1: 60.9375 (59.6270) acc5: 84.3750 (83.8206) [2021-03-25 06:46:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.6358 (1.7503) acc1: 60.9375 (60.0991) acc5: 84.3750 (83.4604) [2021-03-25 06:46:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.7001 (1.7313) acc1: 62.5000 (60.8000) acc5: 84.3750 (83.9680) [2021-03-25 06:46:57 swin_small_patch4_window7_224] INFO: * Acc@1 60.938 Acc@5 84.208 loss 1.715 [2021-03-25 06:46:57 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 60.9% [2021-03-25 06:46:57 swin_small_patch4_window7_224] INFO: Max accuracy: 60.94% [2021-03-25 06:47:01 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 0/1251] eta: 1:30:52 lr: 0.000989 loss: 4.0054 (4.0054) grad_norm: 1.1216 (1.1216) time: 4.3583 [2021-03-25 06:47:06 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 10/1251] eta: 0:17:53 lr: 0.000989 loss: 4.2370 (4.3084) grad_norm: 1.0925 (1.0945) time: 0.8651 [2021-03-25 06:47:11 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 20/1251] eta: 0:14:12 lr: 0.000989 loss: 4.6077 (4.4117) grad_norm: 1.1397 (1.1777) time: 0.5095 [2021-03-25 06:47:16 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 30/1251] eta: 0:12:49 lr: 0.000989 loss: 4.4270 (4.3807) grad_norm: 1.2448 (1.1926) time: 0.5012 [2021-03-25 06:47:21 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 40/1251] eta: 0:12:05 lr: 0.000989 loss: 4.3542 (4.3164) grad_norm: 1.2448 (1.2108) time: 0.5015 [2021-03-25 06:47:26 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 50/1251] eta: 0:11:36 lr: 0.000989 loss: 3.9728 (4.3019) grad_norm: 1.2077 (1.2269) time: 0.5022 [2021-03-25 06:47:31 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 60/1251] eta: 0:11:14 lr: 0.000989 loss: 4.3864 (4.3173) grad_norm: 1.2077 (1.2277) time: 0.4978 [2021-03-25 06:47:36 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 70/1251] eta: 0:11:00 lr: 0.000989 loss: 4.4041 (4.3469) grad_norm: 1.2255 (1.2239) time: 0.5058 [2021-03-25 06:47:42 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 80/1251] eta: 0:10:46 lr: 0.000989 loss: 4.4298 (4.3568) grad_norm: 1.1214 (1.2093) time: 0.5109 [2021-03-25 06:47:47 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 90/1251] eta: 0:10:36 lr: 0.000989 loss: 4.4004 (4.3359) grad_norm: 1.1216 (1.2170) time: 0.5089 [2021-03-25 06:47:52 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 100/1251] eta: 0:10:26 lr: 0.000989 loss: 3.8890 (4.2913) grad_norm: 1.1749 (1.2101) time: 0.5097 [2021-03-25 06:47:57 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 110/1251] eta: 0:10:17 lr: 0.000989 loss: 4.1453 (4.3074) grad_norm: 1.1749 (1.2092) time: 0.5109 [2021-03-25 06:48:02 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 120/1251] eta: 0:10:09 lr: 0.000989 loss: 4.3398 (4.3092) grad_norm: 1.1929 (1.2105) time: 0.5146 [2021-03-25 06:48:07 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 130/1251] eta: 0:10:02 lr: 0.000989 loss: 4.1141 (4.2960) grad_norm: 1.1921 (1.2099) time: 0.5139 [2021-03-25 06:48:12 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 140/1251] eta: 0:09:54 lr: 0.000989 loss: 4.1141 (4.2919) grad_norm: 1.1962 (1.2125) time: 0.5128 [2021-03-25 06:48:17 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 150/1251] eta: 0:09:47 lr: 0.000989 loss: 4.5332 (4.3140) grad_norm: 1.1795 (1.2067) time: 0.5079 [2021-03-25 06:48:22 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 160/1251] eta: 0:09:39 lr: 0.000989 loss: 4.5864 (4.3188) grad_norm: 1.1635 (1.2066) time: 0.5034 [2021-03-25 06:48:27 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 170/1251] eta: 0:09:32 lr: 0.000989 loss: 4.1347 (4.2972) grad_norm: 1.1635 (1.2015) time: 0.5052 [2021-03-25 06:48:33 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 180/1251] eta: 0:09:26 lr: 0.000989 loss: 4.3701 (4.3119) grad_norm: 1.1018 (1.1966) time: 0.5122 [2021-03-25 06:48:38 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 190/1251] eta: 0:09:19 lr: 0.000989 loss: 4.6035 (4.3345) grad_norm: 1.1356 (1.1934) time: 0.5048 [2021-03-25 06:48:43 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 200/1251] eta: 0:09:12 lr: 0.000989 loss: 4.6311 (4.3511) grad_norm: 1.1639 (1.1903) time: 0.4969 [2021-03-25 06:48:48 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 210/1251] eta: 0:09:06 lr: 0.000989 loss: 4.6049 (4.3628) grad_norm: 1.1037 (1.1890) time: 0.5022 [2021-03-25 06:48:53 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 220/1251] eta: 0:09:00 lr: 0.000989 loss: 4.5925 (4.3689) grad_norm: 1.0850 (1.1847) time: 0.5028 [2021-03-25 06:48:58 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 230/1251] eta: 0:08:53 lr: 0.000989 loss: 4.5212 (4.3704) grad_norm: 1.1788 (1.1882) time: 0.4991 [2021-03-25 06:49:03 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 240/1251] eta: 0:08:47 lr: 0.000989 loss: 4.5025 (4.3678) grad_norm: 1.2168 (1.1885) time: 0.4981 [2021-03-25 06:49:08 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 250/1251] eta: 0:08:41 lr: 0.000989 loss: 4.3200 (4.3673) grad_norm: 1.1726 (1.1866) time: 0.5059 [2021-03-25 06:49:13 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 260/1251] eta: 0:08:35 lr: 0.000989 loss: 4.2417 (4.3678) grad_norm: 1.1726 (1.1888) time: 0.5043 [2021-03-25 06:49:18 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 270/1251] eta: 0:08:30 lr: 0.000989 loss: 4.3992 (4.3667) grad_norm: 1.2568 (1.1941) time: 0.5061 [2021-03-25 06:49:23 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 280/1251] eta: 0:08:24 lr: 0.000989 loss: 4.4287 (4.3729) grad_norm: 1.2568 (1.1955) time: 0.5084 [2021-03-25 06:49:28 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 290/1251] eta: 0:08:19 lr: 0.000989 loss: 4.4415 (4.3722) grad_norm: 1.0953 (1.1912) time: 0.5053 [2021-03-25 06:49:33 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 300/1251] eta: 0:08:13 lr: 0.000989 loss: 4.4129 (4.3735) grad_norm: 1.0953 (1.1917) time: 0.5078 [2021-03-25 06:49:38 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 310/1251] eta: 0:08:08 lr: 0.000989 loss: 4.5070 (4.3746) grad_norm: 1.2341 (1.1977) time: 0.5100 [2021-03-25 06:49:43 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 320/1251] eta: 0:08:02 lr: 0.000989 loss: 4.5182 (4.3827) grad_norm: 1.2450 (1.1999) time: 0.5152 [2021-03-25 06:49:48 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 330/1251] eta: 0:07:57 lr: 0.000989 loss: 4.5071 (4.3772) grad_norm: 1.2110 (1.1992) time: 0.5090 [2021-03-25 06:49:53 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 340/1251] eta: 0:07:51 lr: 0.000989 loss: 4.4962 (4.3825) grad_norm: 1.1692 (1.1980) time: 0.5023 [2021-03-25 06:49:58 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 350/1251] eta: 0:07:46 lr: 0.000989 loss: 4.5380 (4.3831) grad_norm: 1.1692 (1.1972) time: 0.5075 [2021-03-25 06:50:03 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 360/1251] eta: 0:07:40 lr: 0.000989 loss: 4.3959 (4.3776) grad_norm: 1.1898 (1.2010) time: 0.5055 [2021-03-25 06:50:09 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 370/1251] eta: 0:07:35 lr: 0.000989 loss: 4.3959 (4.3791) grad_norm: 1.2741 (1.2035) time: 0.5025 [2021-03-25 06:50:14 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 380/1251] eta: 0:07:29 lr: 0.000989 loss: 4.4283 (4.3806) grad_norm: 1.1289 (1.2023) time: 0.5025 [2021-03-25 06:50:19 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 390/1251] eta: 0:07:24 lr: 0.000989 loss: 4.2170 (4.3777) grad_norm: 1.1845 (1.2029) time: 0.4999 [2021-03-25 06:50:24 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 400/1251] eta: 0:07:18 lr: 0.000989 loss: 4.1901 (4.3762) grad_norm: 1.1675 (1.2017) time: 0.4995 [2021-03-25 06:50:29 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 410/1251] eta: 0:07:13 lr: 0.000989 loss: 4.2176 (4.3732) grad_norm: 1.1808 (1.2043) time: 0.5017 [2021-03-25 06:50:34 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 420/1251] eta: 0:07:07 lr: 0.000989 loss: 4.5679 (4.3853) grad_norm: 1.1783 (1.2012) time: 0.5004 [2021-03-25 06:50:39 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 430/1251] eta: 0:07:02 lr: 0.000989 loss: 4.6772 (4.3911) grad_norm: 1.0792 (1.2009) time: 0.4992 [2021-03-25 06:50:44 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 440/1251] eta: 0:06:57 lr: 0.000989 loss: 4.4623 (4.3809) grad_norm: 1.1733 (1.2026) time: 0.5045 [2021-03-25 06:50:49 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 450/1251] eta: 0:06:51 lr: 0.000989 loss: 3.9958 (4.3767) grad_norm: 1.2229 (1.2030) time: 0.5065 [2021-03-25 06:50:54 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 460/1251] eta: 0:06:46 lr: 0.000989 loss: 4.3395 (4.3809) grad_norm: 1.1886 (1.2014) time: 0.5059 [2021-03-25 06:50:59 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 470/1251] eta: 0:06:41 lr: 0.000989 loss: 4.6063 (4.3793) grad_norm: 1.0664 (1.1991) time: 0.5041 [2021-03-25 06:51:04 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 480/1251] eta: 0:06:35 lr: 0.000989 loss: 4.1309 (4.3730) grad_norm: 1.1599 (1.1998) time: 0.5018 [2021-03-25 06:51:09 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 490/1251] eta: 0:06:30 lr: 0.000989 loss: 4.1305 (4.3693) grad_norm: 1.1794 (1.1979) time: 0.4983 [2021-03-25 06:51:14 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 500/1251] eta: 0:06:25 lr: 0.000989 loss: 4.1305 (4.3652) grad_norm: 1.1729 (1.2000) time: 0.5007 [2021-03-25 06:51:19 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 510/1251] eta: 0:06:19 lr: 0.000989 loss: 4.0969 (4.3570) grad_norm: 1.1596 (1.1996) time: 0.5045 [2021-03-25 06:51:24 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 520/1251] eta: 0:06:14 lr: 0.000989 loss: 3.8773 (4.3544) grad_norm: 1.1452 (1.2000) time: 0.5042 [2021-03-25 06:51:29 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 530/1251] eta: 0:06:09 lr: 0.000989 loss: 4.3037 (4.3555) grad_norm: 1.1830 (1.2011) time: 0.5009 [2021-03-25 06:51:34 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 540/1251] eta: 0:06:04 lr: 0.000989 loss: 4.3270 (4.3527) grad_norm: 1.1780 (1.2006) time: 0.5082 [2021-03-25 06:51:39 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 550/1251] eta: 0:05:59 lr: 0.000989 loss: 4.4135 (4.3558) grad_norm: 1.1780 (1.2015) time: 0.5170 [2021-03-25 06:51:44 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 560/1251] eta: 0:05:53 lr: 0.000989 loss: 4.4135 (4.3560) grad_norm: 1.1466 (1.1998) time: 0.5108 [2021-03-25 06:51:49 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 570/1251] eta: 0:05:48 lr: 0.000989 loss: 4.5730 (4.3604) grad_norm: 1.1553 (1.2011) time: 0.5016 [2021-03-25 06:51:54 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 580/1251] eta: 0:05:43 lr: 0.000989 loss: 4.3410 (4.3594) grad_norm: 1.1765 (1.2005) time: 0.5000 [2021-03-25 06:51:59 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 590/1251] eta: 0:05:38 lr: 0.000989 loss: 4.3975 (4.3602) grad_norm: 1.0856 (1.1989) time: 0.5017 [2021-03-25 06:52:04 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 600/1251] eta: 0:05:32 lr: 0.000989 loss: 4.5120 (4.3633) grad_norm: 1.0856 (1.1986) time: 0.5002 [2021-03-25 06:52:09 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 610/1251] eta: 0:05:27 lr: 0.000989 loss: 4.5050 (4.3633) grad_norm: 1.1611 (1.1986) time: 0.4982 [2021-03-25 06:52:14 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 620/1251] eta: 0:05:22 lr: 0.000989 loss: 4.3250 (4.3603) grad_norm: 1.1194 (1.1978) time: 0.5029 [2021-03-25 06:52:19 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 630/1251] eta: 0:05:17 lr: 0.000989 loss: 4.3250 (4.3582) grad_norm: 1.1194 (1.1983) time: 0.5082 [2021-03-25 06:52:24 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 640/1251] eta: 0:05:12 lr: 0.000989 loss: 4.4893 (4.3588) grad_norm: 1.1633 (1.1976) time: 0.5051 [2021-03-25 06:52:29 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 650/1251] eta: 0:05:07 lr: 0.000989 loss: 4.4893 (4.3590) grad_norm: 1.1285 (1.1972) time: 0.5031 [2021-03-25 06:52:35 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 660/1251] eta: 0:05:01 lr: 0.000989 loss: 4.4013 (4.3575) grad_norm: 1.1422 (1.1967) time: 0.5039 [2021-03-25 06:52:40 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 670/1251] eta: 0:04:56 lr: 0.000989 loss: 4.2838 (4.3556) grad_norm: 1.0963 (1.1947) time: 0.5029 [2021-03-25 06:52:45 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 680/1251] eta: 0:04:51 lr: 0.000989 loss: 4.2521 (4.3519) grad_norm: 1.1005 (1.1937) time: 0.5008 [2021-03-25 06:52:50 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 690/1251] eta: 0:04:46 lr: 0.000989 loss: 4.4658 (4.3558) grad_norm: 1.1413 (1.1941) time: 0.5032 [2021-03-25 06:52:55 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 700/1251] eta: 0:04:41 lr: 0.000989 loss: 4.6286 (4.3585) grad_norm: 1.2235 (1.1951) time: 0.5055 [2021-03-25 06:53:00 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 710/1251] eta: 0:04:35 lr: 0.000989 loss: 4.6186 (4.3582) grad_norm: 1.1090 (1.1940) time: 0.5007 [2021-03-25 06:53:05 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 720/1251] eta: 0:04:30 lr: 0.000989 loss: 4.4845 (4.3602) grad_norm: 1.0625 (1.1930) time: 0.4969 [2021-03-25 06:53:10 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 730/1251] eta: 0:04:25 lr: 0.000989 loss: 4.3858 (4.3591) grad_norm: 1.0429 (1.1914) time: 0.5120 [2021-03-25 06:53:15 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 740/1251] eta: 0:04:20 lr: 0.000989 loss: 4.5910 (4.3618) grad_norm: 1.0801 (1.1913) time: 0.5323 [2021-03-25 06:53:20 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 750/1251] eta: 0:04:15 lr: 0.000989 loss: 4.4035 (4.3574) grad_norm: 1.1779 (1.1910) time: 0.5227 [2021-03-25 06:53:26 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 760/1251] eta: 0:04:10 lr: 0.000989 loss: 4.0472 (4.3557) grad_norm: 1.2640 (1.1944) time: 0.5208 [2021-03-25 06:53:31 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 770/1251] eta: 0:04:05 lr: 0.000989 loss: 4.3411 (4.3568) grad_norm: 1.2640 (1.1953) time: 0.5171 [2021-03-25 06:53:36 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 780/1251] eta: 0:04:00 lr: 0.000989 loss: 4.3013 (4.3567) grad_norm: 1.2170 (1.1964) time: 0.4987 [2021-03-25 06:53:41 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 790/1251] eta: 0:03:55 lr: 0.000988 loss: 4.4921 (4.3600) grad_norm: 1.1783 (1.1952) time: 0.5001 [2021-03-25 06:53:46 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 800/1251] eta: 0:03:50 lr: 0.000988 loss: 4.3359 (4.3590) grad_norm: 1.1731 (1.1959) time: 0.5009 [2021-03-25 06:53:51 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 810/1251] eta: 0:03:45 lr: 0.000988 loss: 4.3359 (4.3586) grad_norm: 1.1817 (1.1958) time: 0.5079 [2021-03-25 06:53:56 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 820/1251] eta: 0:03:39 lr: 0.000988 loss: 4.3592 (4.3591) grad_norm: 1.1464 (1.1952) time: 0.5147 [2021-03-25 06:54:01 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 830/1251] eta: 0:03:34 lr: 0.000988 loss: 4.6394 (4.3628) grad_norm: 1.1114 (1.1942) time: 0.5085 [2021-03-25 06:54:06 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 840/1251] eta: 0:03:29 lr: 0.000988 loss: 4.7003 (4.3644) grad_norm: 1.0669 (1.1936) time: 0.5036 [2021-03-25 06:54:11 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 850/1251] eta: 0:03:24 lr: 0.000988 loss: 4.7627 (4.3669) grad_norm: 1.1432 (1.1944) time: 0.5098 [2021-03-25 06:54:16 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 860/1251] eta: 0:03:19 lr: 0.000988 loss: 4.3451 (4.3627) grad_norm: 1.1966 (1.1944) time: 0.5115 [2021-03-25 06:54:21 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 870/1251] eta: 0:03:14 lr: 0.000988 loss: 4.0392 (4.3570) grad_norm: 1.1275 (1.1931) time: 0.5118 [2021-03-25 06:54:26 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 880/1251] eta: 0:03:09 lr: 0.000988 loss: 4.1187 (4.3557) grad_norm: 1.1275 (1.1927) time: 0.5061 [2021-03-25 06:54:31 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 890/1251] eta: 0:03:04 lr: 0.000988 loss: 4.2254 (4.3522) grad_norm: 1.1372 (1.1914) time: 0.4987 [2021-03-25 06:54:36 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 900/1251] eta: 0:02:59 lr: 0.000988 loss: 4.2561 (4.3529) grad_norm: 1.0929 (1.1919) time: 0.5038 [2021-03-25 06:54:42 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 910/1251] eta: 0:02:53 lr: 0.000988 loss: 4.4088 (4.3530) grad_norm: 1.0636 (1.1899) time: 0.5058 [2021-03-25 06:54:47 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 920/1251] eta: 0:02:48 lr: 0.000988 loss: 4.4088 (4.3544) grad_norm: 1.0539 (1.1895) time: 0.5079 [2021-03-25 06:54:52 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 930/1251] eta: 0:02:43 lr: 0.000988 loss: 4.2054 (4.3508) grad_norm: 1.1222 (1.1886) time: 0.5069 [2021-03-25 06:54:57 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 940/1251] eta: 0:02:38 lr: 0.000988 loss: 4.2609 (4.3516) grad_norm: 1.1243 (1.1893) time: 0.5060 [2021-03-25 06:55:02 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 950/1251] eta: 0:02:33 lr: 0.000988 loss: 4.3054 (4.3514) grad_norm: 1.2743 (1.1907) time: 0.5074 [2021-03-25 06:55:07 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 960/1251] eta: 0:02:28 lr: 0.000988 loss: 4.4086 (4.3507) grad_norm: 1.2743 (1.1904) time: 0.5044 [2021-03-25 06:55:12 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 970/1251] eta: 0:02:23 lr: 0.000988 loss: 4.1673 (4.3470) grad_norm: 1.0833 (1.1897) time: 0.5062 [2021-03-25 06:55:17 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 980/1251] eta: 0:02:18 lr: 0.000988 loss: 4.0222 (4.3449) grad_norm: 1.0560 (1.1881) time: 0.5065 [2021-03-25 06:55:22 swin_small_patch4_window7_224] INFO: Epoch: [20] [ 990/1251] eta: 0:02:13 lr: 0.000988 loss: 4.2989 (4.3455) grad_norm: 0.9941 (1.1866) time: 0.5029 [2021-03-25 06:55:27 swin_small_patch4_window7_224] INFO: Epoch: [20] [1000/1251] eta: 0:02:07 lr: 0.000988 loss: 4.3915 (4.3435) grad_norm: 1.0151 (1.1852) time: 0.5043 [2021-03-25 06:55:32 swin_small_patch4_window7_224] INFO: Epoch: [20] [1010/1251] eta: 0:02:02 lr: 0.000988 loss: 4.3370 (4.3439) grad_norm: 1.1029 (1.1857) time: 0.5062 [2021-03-25 06:55:37 swin_small_patch4_window7_224] INFO: Epoch: [20] [1020/1251] eta: 0:01:57 lr: 0.000988 loss: 4.3370 (4.3432) grad_norm: 1.1885 (1.1853) time: 0.5059 [2021-03-25 06:55:42 swin_small_patch4_window7_224] INFO: Epoch: [20] [1030/1251] eta: 0:01:52 lr: 0.000988 loss: 4.3650 (4.3428) grad_norm: 1.1483 (1.1863) time: 0.5042 [2021-03-25 06:55:47 swin_small_patch4_window7_224] INFO: Epoch: [20] [1040/1251] eta: 0:01:47 lr: 0.000988 loss: 4.3935 (4.3428) grad_norm: 1.2002 (1.1868) time: 0.5023 [2021-03-25 06:55:52 swin_small_patch4_window7_224] INFO: Epoch: [20] [1050/1251] eta: 0:01:42 lr: 0.000988 loss: 4.2555 (4.3423) grad_norm: 1.2235 (1.1884) time: 0.5073 [2021-03-25 06:55:58 swin_small_patch4_window7_224] INFO: Epoch: [20] [1060/1251] eta: 0:01:37 lr: 0.000988 loss: 4.2659 (4.3415) grad_norm: 1.1563 (1.1882) time: 0.5158 [2021-03-25 06:56:03 swin_small_patch4_window7_224] INFO: Epoch: [20] [1070/1251] eta: 0:01:32 lr: 0.000988 loss: 4.4472 (4.3437) grad_norm: 1.1474 (1.1881) time: 0.5155 [2021-03-25 06:56:08 swin_small_patch4_window7_224] INFO: Epoch: [20] [1080/1251] eta: 0:01:27 lr: 0.000988 loss: 4.5905 (4.3437) grad_norm: 1.2463 (1.1897) time: 0.5069 [2021-03-25 06:56:13 swin_small_patch4_window7_224] INFO: Epoch: [20] [1090/1251] eta: 0:01:22 lr: 0.000988 loss: 4.5776 (4.3446) grad_norm: 1.2463 (1.1898) time: 0.5065 [2021-03-25 06:56:18 swin_small_patch4_window7_224] INFO: Epoch: [20] [1100/1251] eta: 0:01:16 lr: 0.000988 loss: 4.5693 (4.3426) grad_norm: 1.1833 (1.1901) time: 0.5078 [2021-03-25 06:56:23 swin_small_patch4_window7_224] INFO: Epoch: [20] [1110/1251] eta: 0:01:11 lr: 0.000988 loss: 4.2876 (4.3425) grad_norm: 1.1024 (1.1891) time: 0.5041 [2021-03-25 06:56:28 swin_small_patch4_window7_224] INFO: Epoch: [20] [1120/1251] eta: 0:01:06 lr: 0.000988 loss: 4.4682 (4.3438) grad_norm: 1.0826 (1.1887) time: 0.5063 [2021-03-25 06:56:33 swin_small_patch4_window7_224] INFO: Epoch: [20] [1130/1251] eta: 0:01:01 lr: 0.000988 loss: 4.3544 (4.3416) grad_norm: 1.0620 (1.1880) time: 0.5035 [2021-03-25 06:56:38 swin_small_patch4_window7_224] INFO: Epoch: [20] [1140/1251] eta: 0:00:56 lr: 0.000988 loss: 4.0510 (4.3400) grad_norm: 1.0805 (1.1874) time: 0.5019 [2021-03-25 06:56:43 swin_small_patch4_window7_224] INFO: Epoch: [20] [1150/1251] eta: 0:00:51 lr: 0.000988 loss: 4.5671 (4.3423) grad_norm: 1.0938 (1.1872) time: 0.5061 [2021-03-25 06:56:48 swin_small_patch4_window7_224] INFO: Epoch: [20] [1160/1251] eta: 0:00:46 lr: 0.000988 loss: 4.6266 (4.3430) grad_norm: 1.3480 (1.1900) time: 0.5069 [2021-03-25 06:56:53 swin_small_patch4_window7_224] INFO: Epoch: [20] [1170/1251] eta: 0:00:41 lr: 0.000988 loss: 4.3415 (4.3435) grad_norm: 1.4311 (1.1909) time: 0.5066 [2021-03-25 06:56:58 swin_small_patch4_window7_224] INFO: Epoch: [20] [1180/1251] eta: 0:00:36 lr: 0.000988 loss: 4.4840 (4.3442) grad_norm: 1.2056 (1.1905) time: 0.5062 [2021-03-25 06:57:03 swin_small_patch4_window7_224] INFO: Epoch: [20] [1190/1251] eta: 0:00:31 lr: 0.000988 loss: 4.3169 (4.3424) grad_norm: 1.1061 (1.1898) time: 0.5053 [2021-03-25 06:57:08 swin_small_patch4_window7_224] INFO: Epoch: [20] [1200/1251] eta: 0:00:25 lr: 0.000988 loss: 4.3169 (4.3440) grad_norm: 1.1059 (1.1892) time: 0.5048 [2021-03-25 06:57:14 swin_small_patch4_window7_224] INFO: Epoch: [20] [1210/1251] eta: 0:00:20 lr: 0.000988 loss: 4.5469 (4.3431) grad_norm: 1.1233 (1.1894) time: 0.5064 [2021-03-25 06:57:18 swin_small_patch4_window7_224] INFO: Epoch: [20] [1220/1251] eta: 0:00:15 lr: 0.000988 loss: 4.3672 (4.3437) grad_norm: 1.1799 (1.1902) time: 0.5027 [2021-03-25 06:57:24 swin_small_patch4_window7_224] INFO: Epoch: [20] [1230/1251] eta: 0:00:10 lr: 0.000988 loss: 4.5154 (4.3449) grad_norm: 1.1745 (1.1899) time: 0.5026 [2021-03-25 06:57:29 swin_small_patch4_window7_224] INFO: Epoch: [20] [1240/1251] eta: 0:00:05 lr: 0.000988 loss: 4.8224 (4.3477) grad_norm: 1.1505 (1.1900) time: 0.5020 [2021-03-25 06:57:34 swin_small_patch4_window7_224] INFO: Epoch: [20] [1250/1251] eta: 0:00:00 lr: 0.000988 loss: 4.6949 (4.3485) grad_norm: 1.1596 (1.1901) time: 0.4986 [2021-03-25 06:58:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:03 loss: 1.8541 (1.8541) acc1: 56.2500 (56.2500) acc5: 85.9375 (85.9375) [2021-03-25 06:58:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.8373 (1.8067) acc1: 60.9375 (59.8011) acc5: 82.8125 (83.0966) [2021-03-25 06:58:12 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.8216 (1.8067) acc1: 59.3750 (59.4494) acc5: 84.3750 (84.2262) [2021-03-25 06:58:13 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.6667 (1.7300) acc1: 62.5000 (61.4919) acc5: 85.9375 (85.0302) [2021-03-25 06:58:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.6745 (1.7218) acc1: 64.0625 (61.3567) acc5: 84.3750 (84.9848) [2021-03-25 06:58:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.7573 (1.7334) acc1: 59.3750 (61.3120) acc5: 84.3750 (84.7040) [2021-03-25 06:58:16 swin_small_patch4_window7_224] INFO: * Acc@1 61.822 Acc@5 85.122 loss 1.712 [2021-03-25 06:58:16 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 61.8% [2021-03-25 06:58:16 swin_small_patch4_window7_224] INFO: Max accuracy: 61.82% [2021-03-25 06:58:21 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 0/1251] eta: 1:33:26 lr: 0.000988 loss: 3.6968 (3.6968) grad_norm: 1.0868 (1.0868) time: 4.4818 [2021-03-25 06:58:26 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 10/1251] eta: 0:17:51 lr: 0.000988 loss: 4.2988 (4.4026) grad_norm: 1.1177 (1.1649) time: 0.8631 [2021-03-25 06:58:31 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 20/1251] eta: 0:14:11 lr: 0.000988 loss: 4.6307 (4.4732) grad_norm: 1.1439 (1.1928) time: 0.5022 [2021-03-25 06:58:36 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 30/1251] eta: 0:12:50 lr: 0.000988 loss: 4.6185 (4.4688) grad_norm: 1.2065 (1.1918) time: 0.5029 [2021-03-25 06:58:41 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 40/1251] eta: 0:12:07 lr: 0.000988 loss: 4.3575 (4.3952) grad_norm: 1.1749 (1.1772) time: 0.5060 [2021-03-25 06:58:46 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 50/1251] eta: 0:11:37 lr: 0.000988 loss: 4.2672 (4.4162) grad_norm: 1.0683 (1.1640) time: 0.5033 [2021-03-25 06:58:51 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 60/1251] eta: 0:11:17 lr: 0.000988 loss: 4.5185 (4.3993) grad_norm: 1.0683 (1.1571) time: 0.5029 [2021-03-25 06:58:56 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 70/1251] eta: 0:11:02 lr: 0.000988 loss: 4.4632 (4.4229) grad_norm: 1.1908 (1.1710) time: 0.5104 [2021-03-25 06:59:01 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 80/1251] eta: 0:10:51 lr: 0.000988 loss: 4.4433 (4.4058) grad_norm: 1.2128 (1.1689) time: 0.5171 [2021-03-25 06:59:07 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 90/1251] eta: 0:10:40 lr: 0.000988 loss: 4.4615 (4.4189) grad_norm: 1.0885 (1.1638) time: 0.5207 [2021-03-25 06:59:12 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 100/1251] eta: 0:10:30 lr: 0.000988 loss: 4.4615 (4.4031) grad_norm: 1.1064 (1.1599) time: 0.5120 [2021-03-25 06:59:17 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 110/1251] eta: 0:10:20 lr: 0.000988 loss: 4.4157 (4.4036) grad_norm: 1.1064 (1.1573) time: 0.5067 [2021-03-25 06:59:22 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 120/1251] eta: 0:10:12 lr: 0.000988 loss: 4.4079 (4.4050) grad_norm: 1.0886 (1.1546) time: 0.5099 [2021-03-25 06:59:27 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 130/1251] eta: 0:10:03 lr: 0.000988 loss: 4.3620 (4.4015) grad_norm: 1.0728 (1.1489) time: 0.5096 [2021-03-25 06:59:32 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 140/1251] eta: 0:09:55 lr: 0.000988 loss: 4.3613 (4.3871) grad_norm: 1.1030 (1.1489) time: 0.5034 [2021-03-25 06:59:37 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 150/1251] eta: 0:09:47 lr: 0.000988 loss: 4.6087 (4.4083) grad_norm: 1.1387 (1.1477) time: 0.4998 [2021-03-25 06:59:42 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 160/1251] eta: 0:09:40 lr: 0.000988 loss: 4.7108 (4.4018) grad_norm: 1.1387 (1.1478) time: 0.5063 [2021-03-25 06:59:47 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 170/1251] eta: 0:09:33 lr: 0.000988 loss: 4.4422 (4.3951) grad_norm: 1.1337 (1.1450) time: 0.5091 [2021-03-25 06:59:52 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 180/1251] eta: 0:09:27 lr: 0.000988 loss: 4.4912 (4.3955) grad_norm: 1.1002 (1.1453) time: 0.5103 [2021-03-25 06:59:57 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 190/1251] eta: 0:09:21 lr: 0.000988 loss: 4.5405 (4.3985) grad_norm: 1.0383 (1.1403) time: 0.5156 [2021-03-25 07:00:02 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 200/1251] eta: 0:09:14 lr: 0.000988 loss: 4.3920 (4.3946) grad_norm: 1.0283 (1.1365) time: 0.5056 [2021-03-25 07:00:07 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 210/1251] eta: 0:09:07 lr: 0.000988 loss: 4.0194 (4.3731) grad_norm: 1.0819 (1.1391) time: 0.4965 [2021-03-25 07:00:12 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 220/1251] eta: 0:09:01 lr: 0.000988 loss: 4.2643 (4.3740) grad_norm: 1.1086 (1.1389) time: 0.5027 [2021-03-25 07:00:17 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 230/1251] eta: 0:08:55 lr: 0.000988 loss: 4.3850 (4.3747) grad_norm: 1.0679 (1.1365) time: 0.5032 [2021-03-25 07:00:22 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 240/1251] eta: 0:08:48 lr: 0.000988 loss: 4.2795 (4.3668) grad_norm: 1.0679 (1.1378) time: 0.5012 [2021-03-25 07:00:27 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 250/1251] eta: 0:08:42 lr: 0.000988 loss: 4.2403 (4.3668) grad_norm: 1.0605 (1.1357) time: 0.5017 [2021-03-25 07:00:33 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 260/1251] eta: 0:08:37 lr: 0.000988 loss: 4.2403 (4.3652) grad_norm: 1.1166 (1.1365) time: 0.5109 [2021-03-25 07:00:38 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 270/1251] eta: 0:08:31 lr: 0.000988 loss: 4.6027 (4.3822) grad_norm: 1.1864 (1.1427) time: 0.5092 [2021-03-25 07:00:43 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 280/1251] eta: 0:08:25 lr: 0.000988 loss: 4.5405 (4.3819) grad_norm: 1.1864 (1.1419) time: 0.5013 [2021-03-25 07:00:48 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 290/1251] eta: 0:08:19 lr: 0.000988 loss: 4.2794 (4.3765) grad_norm: 1.1174 (1.1436) time: 0.5046 [2021-03-25 07:00:53 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 300/1251] eta: 0:08:14 lr: 0.000988 loss: 4.3597 (4.3844) grad_norm: 1.1225 (1.1435) time: 0.5094 [2021-03-25 07:00:58 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 310/1251] eta: 0:08:09 lr: 0.000988 loss: 4.3597 (4.3799) grad_norm: 1.1308 (1.1439) time: 0.5127 [2021-03-25 07:01:03 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 320/1251] eta: 0:08:03 lr: 0.000988 loss: 4.2892 (4.3777) grad_norm: 1.1530 (1.1447) time: 0.5046 [2021-03-25 07:01:08 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 330/1251] eta: 0:07:57 lr: 0.000988 loss: 4.2790 (4.3695) grad_norm: 1.1486 (1.1449) time: 0.5033 [2021-03-25 07:01:13 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 340/1251] eta: 0:07:52 lr: 0.000988 loss: 4.2755 (4.3667) grad_norm: 1.1343 (1.1433) time: 0.5052 [2021-03-25 07:01:18 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 350/1251] eta: 0:07:46 lr: 0.000988 loss: 4.1304 (4.3577) grad_norm: 1.1343 (1.1429) time: 0.5030 [2021-03-25 07:01:23 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 360/1251] eta: 0:07:40 lr: 0.000988 loss: 4.1304 (4.3550) grad_norm: 1.0510 (1.1412) time: 0.5034 [2021-03-25 07:01:28 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 370/1251] eta: 0:07:35 lr: 0.000988 loss: 3.9286 (4.3415) grad_norm: 1.0628 (1.1391) time: 0.4998 [2021-03-25 07:01:33 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 380/1251] eta: 0:07:30 lr: 0.000988 loss: 4.1613 (4.3471) grad_norm: 1.1028 (1.1405) time: 0.5052 [2021-03-25 07:01:38 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 390/1251] eta: 0:07:24 lr: 0.000988 loss: 4.5420 (4.3560) grad_norm: 1.1780 (1.1420) time: 0.5081 [2021-03-25 07:01:43 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 400/1251] eta: 0:07:19 lr: 0.000988 loss: 4.6115 (4.3563) grad_norm: 1.2129 (1.1436) time: 0.5045 [2021-03-25 07:01:48 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 410/1251] eta: 0:07:13 lr: 0.000988 loss: 4.4471 (4.3609) grad_norm: 1.1330 (1.1437) time: 0.5033 [2021-03-25 07:01:53 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 420/1251] eta: 0:07:08 lr: 0.000988 loss: 4.4075 (4.3599) grad_norm: 1.0624 (1.1421) time: 0.5028 [2021-03-25 07:01:58 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 430/1251] eta: 0:07:03 lr: 0.000988 loss: 4.1305 (4.3602) grad_norm: 1.0546 (1.1420) time: 0.5057 [2021-03-25 07:02:04 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 440/1251] eta: 0:06:57 lr: 0.000988 loss: 4.5504 (4.3630) grad_norm: 1.0658 (1.1429) time: 0.5090 [2021-03-25 07:02:09 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 450/1251] eta: 0:06:52 lr: 0.000988 loss: 4.5504 (4.3653) grad_norm: 1.0658 (1.1435) time: 0.5138 [2021-03-25 07:02:14 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 460/1251] eta: 0:06:47 lr: 0.000988 loss: 4.3818 (4.3658) grad_norm: 1.1688 (1.1456) time: 0.5141 [2021-03-25 07:02:19 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 470/1251] eta: 0:06:42 lr: 0.000988 loss: 4.1245 (4.3625) grad_norm: 1.1782 (1.1473) time: 0.5105 [2021-03-25 07:02:24 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 480/1251] eta: 0:06:36 lr: 0.000988 loss: 4.2130 (4.3597) grad_norm: 1.1782 (1.1482) time: 0.5062 [2021-03-25 07:02:29 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 490/1251] eta: 0:06:31 lr: 0.000988 loss: 4.0124 (4.3497) grad_norm: 1.1796 (1.1487) time: 0.4999 [2021-03-25 07:02:34 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 500/1251] eta: 0:06:26 lr: 0.000988 loss: 4.1786 (4.3508) grad_norm: 1.1719 (1.1476) time: 0.4997 [2021-03-25 07:02:39 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 510/1251] eta: 0:06:20 lr: 0.000988 loss: 4.4024 (4.3498) grad_norm: 1.0603 (1.1458) time: 0.5022 [2021-03-25 07:02:44 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 520/1251] eta: 0:06:15 lr: 0.000988 loss: 4.2530 (4.3491) grad_norm: 1.1381 (1.1478) time: 0.5053 [2021-03-25 07:02:49 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 530/1251] eta: 0:06:10 lr: 0.000988 loss: 4.3089 (4.3500) grad_norm: 1.1601 (1.1476) time: 0.5104 [2021-03-25 07:02:54 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 540/1251] eta: 0:06:05 lr: 0.000988 loss: 4.5237 (4.3519) grad_norm: 1.1231 (1.1491) time: 0.5095 [2021-03-25 07:03:00 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 550/1251] eta: 0:06:00 lr: 0.000988 loss: 4.4566 (4.3501) grad_norm: 1.1385 (1.1509) time: 0.5145 [2021-03-25 07:03:05 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 560/1251] eta: 0:05:55 lr: 0.000988 loss: 4.4372 (4.3498) grad_norm: 1.1385 (1.1507) time: 0.5197 [2021-03-25 07:03:10 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 570/1251] eta: 0:05:49 lr: 0.000988 loss: 4.2131 (4.3447) grad_norm: 1.1100 (1.1524) time: 0.5132 [2021-03-25 07:03:15 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 580/1251] eta: 0:05:44 lr: 0.000988 loss: 4.3163 (4.3468) grad_norm: 1.1310 (1.1521) time: 0.5078 [2021-03-25 07:03:20 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 590/1251] eta: 0:05:39 lr: 0.000988 loss: 4.4953 (4.3505) grad_norm: 1.1310 (1.1514) time: 0.5139 [2021-03-25 07:03:25 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 600/1251] eta: 0:05:34 lr: 0.000988 loss: 4.4554 (4.3512) grad_norm: 1.1210 (1.1519) time: 0.5143 [2021-03-25 07:03:30 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 610/1251] eta: 0:05:29 lr: 0.000988 loss: 4.4462 (4.3540) grad_norm: 1.1158 (1.1509) time: 0.5056 [2021-03-25 07:03:35 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 620/1251] eta: 0:05:23 lr: 0.000988 loss: 4.4462 (4.3518) grad_norm: 1.1195 (1.1521) time: 0.5042 [2021-03-25 07:03:40 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 630/1251] eta: 0:05:18 lr: 0.000988 loss: 4.3901 (4.3532) grad_norm: 1.0611 (1.1504) time: 0.5076 [2021-03-25 07:03:45 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 640/1251] eta: 0:05:13 lr: 0.000987 loss: 4.2320 (4.3506) grad_norm: 1.0611 (1.1500) time: 0.5061 [2021-03-25 07:03:50 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 650/1251] eta: 0:05:08 lr: 0.000987 loss: 4.2320 (4.3501) grad_norm: 1.1641 (1.1515) time: 0.5021 [2021-03-25 07:03:55 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 660/1251] eta: 0:05:03 lr: 0.000987 loss: 4.3642 (4.3460) grad_norm: 1.0657 (1.1491) time: 0.5041 [2021-03-25 07:04:01 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 670/1251] eta: 0:04:57 lr: 0.000987 loss: 4.3628 (4.3456) grad_norm: 1.0031 (1.1481) time: 0.5093 [2021-03-25 07:04:06 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 680/1251] eta: 0:04:52 lr: 0.000987 loss: 4.5356 (4.3482) grad_norm: 1.1214 (1.1475) time: 0.5084 [2021-03-25 07:04:11 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 690/1251] eta: 0:04:47 lr: 0.000987 loss: 4.6805 (4.3494) grad_norm: 1.1214 (1.1483) time: 0.5057 [2021-03-25 07:04:16 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 700/1251] eta: 0:04:42 lr: 0.000987 loss: 4.4678 (4.3489) grad_norm: 1.1085 (1.1490) time: 0.5030 [2021-03-25 07:04:21 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 710/1251] eta: 0:04:37 lr: 0.000987 loss: 4.3481 (4.3467) grad_norm: 1.0458 (1.1475) time: 0.5091 [2021-03-25 07:04:26 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 720/1251] eta: 0:04:32 lr: 0.000987 loss: 4.1409 (4.3465) grad_norm: 1.0458 (1.1482) time: 0.5090 [2021-03-25 07:04:31 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 730/1251] eta: 0:04:27 lr: 0.000987 loss: 4.3320 (4.3475) grad_norm: 1.1301 (1.1474) time: 0.5095 [2021-03-25 07:04:36 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 740/1251] eta: 0:04:21 lr: 0.000987 loss: 4.4671 (4.3460) grad_norm: 1.1630 (inf) time: 0.5218 [2021-03-25 07:04:41 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 750/1251] eta: 0:04:16 lr: 0.000987 loss: 4.3690 (4.3450) grad_norm: 1.1608 (inf) time: 0.5121 [2021-03-25 07:04:46 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 760/1251] eta: 0:04:11 lr: 0.000987 loss: 4.3778 (4.3455) grad_norm: 1.1306 (inf) time: 0.5006 [2021-03-25 07:04:51 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 770/1251] eta: 0:04:06 lr: 0.000987 loss: 4.4394 (4.3435) grad_norm: 1.0833 (inf) time: 0.5029 [2021-03-25 07:04:56 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 780/1251] eta: 0:04:01 lr: 0.000987 loss: 4.4294 (4.3448) grad_norm: 1.1005 (inf) time: 0.5038 [2021-03-25 07:05:02 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 790/1251] eta: 0:03:56 lr: 0.000987 loss: 4.4128 (4.3413) grad_norm: 1.2736 (inf) time: 0.5085 [2021-03-25 07:05:07 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 800/1251] eta: 0:03:50 lr: 0.000987 loss: 4.1581 (4.3402) grad_norm: 1.1990 (inf) time: 0.5096 [2021-03-25 07:05:12 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 810/1251] eta: 0:03:45 lr: 0.000987 loss: 4.5346 (4.3407) grad_norm: 1.1130 (inf) time: 0.5096 [2021-03-25 07:05:17 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 820/1251] eta: 0:03:40 lr: 0.000987 loss: 4.7123 (4.3463) grad_norm: 1.0757 (inf) time: 0.5068 [2021-03-25 07:05:22 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 830/1251] eta: 0:03:35 lr: 0.000987 loss: 4.5086 (4.3456) grad_norm: 1.0987 (inf) time: 0.5119 [2021-03-25 07:05:27 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 840/1251] eta: 0:03:30 lr: 0.000987 loss: 4.3762 (4.3482) grad_norm: 1.1385 (inf) time: 0.5135 [2021-03-25 07:05:32 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 850/1251] eta: 0:03:25 lr: 0.000987 loss: 4.5379 (4.3493) grad_norm: 1.2066 (inf) time: 0.5047 [2021-03-25 07:05:37 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 860/1251] eta: 0:03:20 lr: 0.000987 loss: 4.6111 (4.3483) grad_norm: 1.2013 (inf) time: 0.5068 [2021-03-25 07:05:42 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 870/1251] eta: 0:03:14 lr: 0.000987 loss: 4.4679 (4.3487) grad_norm: 1.0994 (inf) time: 0.5032 [2021-03-25 07:05:47 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 880/1251] eta: 0:03:09 lr: 0.000987 loss: 4.3569 (4.3489) grad_norm: 1.1075 (inf) time: 0.4995 [2021-03-25 07:05:52 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 890/1251] eta: 0:03:04 lr: 0.000987 loss: 4.3413 (4.3499) grad_norm: 1.0022 (inf) time: 0.5043 [2021-03-25 07:05:57 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 900/1251] eta: 0:02:59 lr: 0.000987 loss: 4.2814 (4.3471) grad_norm: 1.0597 (inf) time: 0.5031 [2021-03-25 07:06:02 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 910/1251] eta: 0:02:54 lr: 0.000987 loss: 4.0771 (4.3458) grad_norm: 1.1040 (inf) time: 0.5014 [2021-03-25 07:06:07 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 920/1251] eta: 0:02:49 lr: 0.000987 loss: 4.3857 (4.3445) grad_norm: 1.0690 (inf) time: 0.5075 [2021-03-25 07:06:12 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 930/1251] eta: 0:02:44 lr: 0.000987 loss: 4.5073 (4.3460) grad_norm: 1.0358 (inf) time: 0.5105 [2021-03-25 07:06:18 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 940/1251] eta: 0:02:39 lr: 0.000987 loss: 4.5073 (4.3420) grad_norm: 1.0804 (inf) time: 0.5142 [2021-03-25 07:06:23 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 950/1251] eta: 0:02:33 lr: 0.000987 loss: 3.9727 (4.3396) grad_norm: 1.0686 (inf) time: 0.5117 [2021-03-25 07:06:28 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 960/1251] eta: 0:02:28 lr: 0.000987 loss: 4.0202 (4.3364) grad_norm: 1.0686 (inf) time: 0.5032 [2021-03-25 07:06:33 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 970/1251] eta: 0:02:23 lr: 0.000987 loss: 4.2517 (4.3371) grad_norm: 1.2133 (inf) time: 0.5025 [2021-03-25 07:06:38 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 980/1251] eta: 0:02:18 lr: 0.000987 loss: 4.2990 (4.3353) grad_norm: 1.1123 (inf) time: 0.5103 [2021-03-25 07:06:43 swin_small_patch4_window7_224] INFO: Epoch: [21] [ 990/1251] eta: 0:02:13 lr: 0.000987 loss: 4.5525 (4.3376) grad_norm: 1.0767 (inf) time: 0.5083 [2021-03-25 07:06:48 swin_small_patch4_window7_224] INFO: Epoch: [21] [1000/1251] eta: 0:02:08 lr: 0.000987 loss: 4.5442 (4.3387) grad_norm: 1.0329 (inf) time: 0.5051 [2021-03-25 07:06:53 swin_small_patch4_window7_224] INFO: Epoch: [21] [1010/1251] eta: 0:02:03 lr: 0.000987 loss: 4.4653 (4.3371) grad_norm: 1.1135 (inf) time: 0.5097 [2021-03-25 07:06:58 swin_small_patch4_window7_224] INFO: Epoch: [21] [1020/1251] eta: 0:01:58 lr: 0.000987 loss: 4.4653 (4.3378) grad_norm: 1.1771 (inf) time: 0.5057 [2021-03-25 07:07:03 swin_small_patch4_window7_224] INFO: Epoch: [21] [1030/1251] eta: 0:01:52 lr: 0.000987 loss: 4.2712 (4.3347) grad_norm: 1.1949 (inf) time: 0.5028 [2021-03-25 07:07:08 swin_small_patch4_window7_224] INFO: Epoch: [21] [1040/1251] eta: 0:01:47 lr: 0.000987 loss: 4.1431 (4.3319) grad_norm: 1.1792 (inf) time: 0.5026 [2021-03-25 07:07:13 swin_small_patch4_window7_224] INFO: Epoch: [21] [1050/1251] eta: 0:01:42 lr: 0.000987 loss: 4.3774 (4.3341) grad_norm: 1.1041 (inf) time: 0.5055 [2021-03-25 07:07:18 swin_small_patch4_window7_224] INFO: Epoch: [21] [1060/1251] eta: 0:01:37 lr: 0.000987 loss: 4.7020 (4.3352) grad_norm: 1.0775 (inf) time: 0.5081 [2021-03-25 07:07:23 swin_small_patch4_window7_224] INFO: Epoch: [21] [1070/1251] eta: 0:01:32 lr: 0.000987 loss: 4.0714 (4.3310) grad_norm: 1.1247 (inf) time: 0.5046 [2021-03-25 07:07:28 swin_small_patch4_window7_224] INFO: Epoch: [21] [1080/1251] eta: 0:01:27 lr: 0.000987 loss: 3.9347 (4.3303) grad_norm: 1.1508 (inf) time: 0.5022 [2021-03-25 07:07:33 swin_small_patch4_window7_224] INFO: Epoch: [21] [1090/1251] eta: 0:01:22 lr: 0.000987 loss: 4.6612 (4.3307) grad_norm: 1.1275 (inf) time: 0.5002 [2021-03-25 07:07:38 swin_small_patch4_window7_224] INFO: Epoch: [21] [1100/1251] eta: 0:01:17 lr: 0.000987 loss: 4.2813 (4.3294) grad_norm: 1.1029 (inf) time: 0.5008 [2021-03-25 07:07:43 swin_small_patch4_window7_224] INFO: Epoch: [21] [1110/1251] eta: 0:01:11 lr: 0.000987 loss: 4.1848 (4.3301) grad_norm: 1.0763 (inf) time: 0.5041 [2021-03-25 07:07:48 swin_small_patch4_window7_224] INFO: Epoch: [21] [1120/1251] eta: 0:01:06 lr: 0.000987 loss: 4.6053 (4.3321) grad_norm: 1.1074 (inf) time: 0.4983 [2021-03-25 07:07:53 swin_small_patch4_window7_224] INFO: Epoch: [21] [1130/1251] eta: 0:01:01 lr: 0.000987 loss: 4.4226 (4.3324) grad_norm: 1.1464 (inf) time: 0.4993 [2021-03-25 07:07:59 swin_small_patch4_window7_224] INFO: Epoch: [21] [1140/1251] eta: 0:00:56 lr: 0.000987 loss: 4.3909 (4.3314) grad_norm: 1.1466 (inf) time: 0.5083 [2021-03-25 07:08:04 swin_small_patch4_window7_224] INFO: Epoch: [21] [1150/1251] eta: 0:00:51 lr: 0.000987 loss: 4.3241 (4.3305) grad_norm: 1.1576 (inf) time: 0.5057 [2021-03-25 07:08:09 swin_small_patch4_window7_224] INFO: Epoch: [21] [1160/1251] eta: 0:00:46 lr: 0.000987 loss: 4.3139 (4.3289) grad_norm: 1.1331 (inf) time: 0.5066 [2021-03-25 07:08:14 swin_small_patch4_window7_224] INFO: Epoch: [21] [1170/1251] eta: 0:00:41 lr: 0.000987 loss: 4.3147 (4.3298) grad_norm: 1.1299 (inf) time: 0.5039 [2021-03-25 07:08:19 swin_small_patch4_window7_224] INFO: Epoch: [21] [1180/1251] eta: 0:00:36 lr: 0.000987 loss: 4.3302 (4.3283) grad_norm: 1.2089 (inf) time: 0.5003 [2021-03-25 07:08:24 swin_small_patch4_window7_224] INFO: Epoch: [21] [1190/1251] eta: 0:00:31 lr: 0.000987 loss: 4.3302 (4.3272) grad_norm: 1.1878 (inf) time: 0.5091 [2021-03-25 07:08:29 swin_small_patch4_window7_224] INFO: Epoch: [21] [1200/1251] eta: 0:00:26 lr: 0.000987 loss: 4.0553 (4.3252) grad_norm: 1.0982 (inf) time: 0.5098 [2021-03-25 07:08:34 swin_small_patch4_window7_224] INFO: Epoch: [21] [1210/1251] eta: 0:00:20 lr: 0.000987 loss: 4.2987 (4.3269) grad_norm: 1.1456 (inf) time: 0.4995 [2021-03-25 07:08:39 swin_small_patch4_window7_224] INFO: Epoch: [21] [1220/1251] eta: 0:00:15 lr: 0.000987 loss: 4.5540 (4.3274) grad_norm: 1.1509 (inf) time: 0.4979 [2021-03-25 07:08:44 swin_small_patch4_window7_224] INFO: Epoch: [21] [1230/1251] eta: 0:00:10 lr: 0.000987 loss: 4.5011 (4.3261) grad_norm: 1.1000 (inf) time: 0.4971 [2021-03-25 07:08:49 swin_small_patch4_window7_224] INFO: Epoch: [21] [1240/1251] eta: 0:00:05 lr: 0.000987 loss: 4.0861 (4.3248) grad_norm: 1.1000 (inf) time: 0.4947 [2021-03-25 07:08:54 swin_small_patch4_window7_224] INFO: Epoch: [21] [1250/1251] eta: 0:00:00 lr: 0.000987 loss: 3.9637 (4.3221) grad_norm: 1.1328 (inf) time: 0.4989 [2021-03-25 07:08:58 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 1.8589 (1.8589) acc1: 54.6875 (54.6875) acc5: 82.8125 (82.8125) [2021-03-25 07:09:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.5694 (1.5856) acc1: 62.5000 (62.3580) acc5: 85.9375 (86.5057) [2021-03-25 07:09:03 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.5683 (1.5904) acc1: 62.5000 (62.6488) acc5: 85.9375 (85.2679) [2021-03-25 07:09:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.5530 (1.6007) acc1: 60.9375 (61.9960) acc5: 84.3750 (85.2319) [2021-03-25 07:09:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.5857 (1.6023) acc1: 62.5000 (62.3857) acc5: 84.3750 (85.4421) [2021-03-25 07:09:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.6178 (1.5933) acc1: 62.5000 (62.4000) acc5: 84.3750 (85.6960) [2021-03-25 07:09:10 swin_small_patch4_window7_224] INFO: * Acc@1 62.862 Acc@5 85.760 loss 1.591 [2021-03-25 07:09:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 62.9% [2021-03-25 07:09:10 swin_small_patch4_window7_224] INFO: Max accuracy: 62.86% [2021-03-25 07:09:14 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 0/1251] eta: 1:28:05 lr: 0.000987 loss: 4.9448 (4.9448) grad_norm: 1.1416 (1.1416) time: 4.2252 [2021-03-25 07:09:19 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 10/1251] eta: 0:17:48 lr: 0.000987 loss: 4.5439 (4.4622) grad_norm: 1.1326 (1.1486) time: 0.8610 [2021-03-25 07:09:24 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 20/1251] eta: 0:14:08 lr: 0.000987 loss: 4.5464 (4.4959) grad_norm: 1.1067 (1.1436) time: 0.5128 [2021-03-25 07:09:29 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 30/1251] eta: 0:12:51 lr: 0.000987 loss: 4.6364 (4.4504) grad_norm: 1.0926 (1.1431) time: 0.5057 [2021-03-25 07:09:34 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 40/1251] eta: 0:12:09 lr: 0.000987 loss: 4.6055 (4.4136) grad_norm: 1.0405 (1.1115) time: 0.5103 [2021-03-25 07:09:39 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 50/1251] eta: 0:11:39 lr: 0.000987 loss: 4.0898 (4.3170) grad_norm: 1.0642 (1.1044) time: 0.5067 [2021-03-25 07:09:45 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 60/1251] eta: 0:11:19 lr: 0.000987 loss: 4.0894 (4.2977) grad_norm: 1.0747 (1.0963) time: 0.5045 [2021-03-25 07:09:50 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 70/1251] eta: 0:11:01 lr: 0.000987 loss: 4.3856 (4.2839) grad_norm: 1.1241 (1.1105) time: 0.5018 [2021-03-25 07:09:55 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 80/1251] eta: 0:10:47 lr: 0.000987 loss: 4.4106 (4.2722) grad_norm: 1.1430 (1.1220) time: 0.5001 [2021-03-25 07:10:00 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 90/1251] eta: 0:10:35 lr: 0.000987 loss: 4.4072 (4.2659) grad_norm: 1.1543 (1.1338) time: 0.5025 [2021-03-25 07:10:05 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 100/1251] eta: 0:10:25 lr: 0.000987 loss: 3.9740 (4.2437) grad_norm: 1.1368 (1.1337) time: 0.5033 [2021-03-25 07:10:10 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 110/1251] eta: 0:10:15 lr: 0.000987 loss: 4.2244 (4.2555) grad_norm: 1.0040 (1.1205) time: 0.5059 [2021-03-25 07:10:15 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 120/1251] eta: 0:10:08 lr: 0.000987 loss: 4.2793 (4.2435) grad_norm: 1.0092 (1.1349) time: 0.5133 [2021-03-25 07:10:20 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 130/1251] eta: 0:10:01 lr: 0.000987 loss: 4.0402 (4.2373) grad_norm: 1.1620 (1.1377) time: 0.5207 [2021-03-25 07:10:25 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 140/1251] eta: 0:09:53 lr: 0.000987 loss: 4.5234 (4.2601) grad_norm: 1.1308 (1.1445) time: 0.5122 [2021-03-25 07:10:30 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 150/1251] eta: 0:09:45 lr: 0.000987 loss: 4.5778 (4.2662) grad_norm: 1.1525 (1.1445) time: 0.4991 [2021-03-25 07:10:35 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 160/1251] eta: 0:09:38 lr: 0.000987 loss: 4.2280 (4.2487) grad_norm: 1.1525 (1.1424) time: 0.4985 [2021-03-25 07:10:40 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 170/1251] eta: 0:09:31 lr: 0.000987 loss: 4.2280 (4.2538) grad_norm: 1.0400 (1.1352) time: 0.5058 [2021-03-25 07:10:45 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 180/1251] eta: 0:09:25 lr: 0.000987 loss: 4.4795 (4.2629) grad_norm: 1.0509 (1.1358) time: 0.5122 [2021-03-25 07:10:50 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 190/1251] eta: 0:09:18 lr: 0.000987 loss: 4.4098 (4.2496) grad_norm: 1.1144 (1.1370) time: 0.5068 [2021-03-25 07:10:55 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 200/1251] eta: 0:09:12 lr: 0.000987 loss: 4.3443 (4.2620) grad_norm: 1.1075 (1.1374) time: 0.5019 [2021-03-25 07:11:00 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 210/1251] eta: 0:09:05 lr: 0.000987 loss: 4.4348 (4.2629) grad_norm: 1.0405 (1.1338) time: 0.5037 [2021-03-25 07:11:05 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 220/1251] eta: 0:08:59 lr: 0.000987 loss: 4.2353 (4.2556) grad_norm: 1.1028 (1.1368) time: 0.5009 [2021-03-25 07:11:11 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 230/1251] eta: 0:08:53 lr: 0.000987 loss: 4.2353 (4.2540) grad_norm: 1.2589 (1.1456) time: 0.5064 [2021-03-25 07:11:16 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 240/1251] eta: 0:08:47 lr: 0.000987 loss: 4.3422 (4.2528) grad_norm: 1.1653 (1.1459) time: 0.5100 [2021-03-25 07:11:21 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 250/1251] eta: 0:08:41 lr: 0.000987 loss: 4.2844 (4.2559) grad_norm: 1.0870 (1.1463) time: 0.5029 [2021-03-25 07:11:26 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 260/1251] eta: 0:08:35 lr: 0.000987 loss: 4.2923 (4.2573) grad_norm: 1.0956 (inf) time: 0.5009 [2021-03-25 07:11:31 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 270/1251] eta: 0:08:29 lr: 0.000987 loss: 4.1599 (4.2519) grad_norm: 1.1439 (inf) time: 0.4998 [2021-03-25 07:11:36 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 280/1251] eta: 0:08:23 lr: 0.000987 loss: 4.4380 (4.2630) grad_norm: 1.1954 (inf) time: 0.4993 [2021-03-25 07:11:41 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 290/1251] eta: 0:08:18 lr: 0.000987 loss: 4.5255 (4.2663) grad_norm: 1.0697 (inf) time: 0.5035 [2021-03-25 07:11:46 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 300/1251] eta: 0:08:12 lr: 0.000987 loss: 4.4121 (4.2697) grad_norm: 0.9884 (inf) time: 0.5095 [2021-03-25 07:11:51 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 310/1251] eta: 0:08:07 lr: 0.000987 loss: 4.3643 (4.2700) grad_norm: 1.0051 (inf) time: 0.5126 [2021-03-25 07:11:56 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 320/1251] eta: 0:08:02 lr: 0.000987 loss: 4.3754 (4.2736) grad_norm: 1.1049 (inf) time: 0.5093 [2021-03-25 07:12:01 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 330/1251] eta: 0:07:56 lr: 0.000987 loss: 4.4758 (4.2818) grad_norm: 1.2149 (inf) time: 0.5028 [2021-03-25 07:12:06 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 340/1251] eta: 0:07:51 lr: 0.000987 loss: 4.5407 (4.2806) grad_norm: 1.1242 (inf) time: 0.5070 [2021-03-25 07:12:11 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 350/1251] eta: 0:07:45 lr: 0.000987 loss: 4.5798 (4.2875) grad_norm: 1.1242 (inf) time: 0.5084 [2021-03-25 07:12:16 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 360/1251] eta: 0:07:39 lr: 0.000987 loss: 4.5798 (4.2876) grad_norm: 1.1844 (inf) time: 0.5005 [2021-03-25 07:12:21 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 370/1251] eta: 0:07:34 lr: 0.000987 loss: 4.3359 (4.2854) grad_norm: 1.1658 (inf) time: 0.5026 [2021-03-25 07:12:26 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 380/1251] eta: 0:07:28 lr: 0.000987 loss: 4.3198 (4.2815) grad_norm: 1.0953 (inf) time: 0.5021 [2021-03-25 07:12:31 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 390/1251] eta: 0:07:23 lr: 0.000987 loss: 4.2182 (4.2779) grad_norm: 1.0948 (inf) time: 0.5031 [2021-03-25 07:12:36 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 400/1251] eta: 0:07:18 lr: 0.000987 loss: 4.3343 (4.2810) grad_norm: 1.1285 (inf) time: 0.5046 [2021-03-25 07:12:41 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 410/1251] eta: 0:07:12 lr: 0.000987 loss: 4.3983 (4.2841) grad_norm: 1.1910 (inf) time: 0.5011 [2021-03-25 07:12:46 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 420/1251] eta: 0:07:07 lr: 0.000987 loss: 4.3198 (4.2763) grad_norm: 1.0832 (inf) time: 0.5006 [2021-03-25 07:12:52 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 430/1251] eta: 0:07:02 lr: 0.000987 loss: 4.0542 (4.2773) grad_norm: 1.1121 (inf) time: 0.5086 [2021-03-25 07:12:56 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 440/1251] eta: 0:06:56 lr: 0.000987 loss: 4.4189 (4.2768) grad_norm: 1.1766 (inf) time: 0.5076 [2021-03-25 07:13:01 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 450/1251] eta: 0:06:51 lr: 0.000986 loss: 4.4952 (4.2821) grad_norm: 1.0927 (inf) time: 0.4984 [2021-03-25 07:13:07 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 460/1251] eta: 0:06:46 lr: 0.000986 loss: 4.5890 (4.2788) grad_norm: 1.0927 (inf) time: 0.5014 [2021-03-25 07:13:12 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 470/1251] eta: 0:06:40 lr: 0.000986 loss: 4.1464 (4.2808) grad_norm: 1.0603 (inf) time: 0.5065 [2021-03-25 07:13:17 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 480/1251] eta: 0:06:35 lr: 0.000986 loss: 4.2737 (4.2837) grad_norm: 1.0978 (inf) time: 0.5071 [2021-03-25 07:13:22 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 490/1251] eta: 0:06:30 lr: 0.000986 loss: 4.2737 (4.2808) grad_norm: 1.1564 (inf) time: 0.5023 [2021-03-25 07:13:27 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 500/1251] eta: 0:06:25 lr: 0.000986 loss: 4.3437 (4.2813) grad_norm: 1.1617 (inf) time: 0.5014 [2021-03-25 07:13:32 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 510/1251] eta: 0:06:19 lr: 0.000986 loss: 4.2269 (4.2809) grad_norm: 1.2818 (inf) time: 0.5027 [2021-03-25 07:13:37 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 520/1251] eta: 0:06:14 lr: 0.000986 loss: 4.4796 (4.2835) grad_norm: 1.1724 (inf) time: 0.5100 [2021-03-25 07:13:42 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 530/1251] eta: 0:06:09 lr: 0.000986 loss: 4.4796 (4.2814) grad_norm: 1.0370 (inf) time: 0.5096 [2021-03-25 07:13:47 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 540/1251] eta: 0:06:04 lr: 0.000986 loss: 4.0627 (4.2762) grad_norm: 1.0602 (inf) time: 0.5026 [2021-03-25 07:13:52 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 550/1251] eta: 0:05:59 lr: 0.000986 loss: 3.9591 (4.2716) grad_norm: 1.0610 (inf) time: 0.5182 [2021-03-25 07:13:57 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 560/1251] eta: 0:05:54 lr: 0.000986 loss: 4.4314 (4.2767) grad_norm: 1.0776 (inf) time: 0.5199 [2021-03-25 07:14:02 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 570/1251] eta: 0:05:48 lr: 0.000986 loss: 4.6099 (4.2818) grad_norm: 1.1024 (inf) time: 0.5061 [2021-03-25 07:14:07 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 580/1251] eta: 0:05:43 lr: 0.000986 loss: 4.2693 (4.2735) grad_norm: 1.1860 (inf) time: 0.5051 [2021-03-25 07:14:13 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 590/1251] eta: 0:05:38 lr: 0.000986 loss: 4.2531 (4.2788) grad_norm: 1.0856 (inf) time: 0.5064 [2021-03-25 07:14:18 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 600/1251] eta: 0:05:33 lr: 0.000986 loss: 4.4561 (4.2775) grad_norm: 1.0565 (inf) time: 0.5092 [2021-03-25 07:14:23 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 610/1251] eta: 0:05:28 lr: 0.000986 loss: 3.9834 (4.2719) grad_norm: 0.9777 (inf) time: 0.5084 [2021-03-25 07:14:28 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 620/1251] eta: 0:05:23 lr: 0.000986 loss: 3.8765 (4.2695) grad_norm: 1.1412 (inf) time: 0.5061 [2021-03-25 07:14:33 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 630/1251] eta: 0:05:17 lr: 0.000986 loss: 4.5064 (4.2745) grad_norm: 1.1412 (inf) time: 0.5028 [2021-03-25 07:14:38 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 640/1251] eta: 0:05:12 lr: 0.000986 loss: 4.5292 (4.2724) grad_norm: 1.1125 (inf) time: 0.5038 [2021-03-25 07:14:43 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 650/1251] eta: 0:05:07 lr: 0.000986 loss: 4.4223 (4.2744) grad_norm: 1.1559 (inf) time: 0.5064 [2021-03-25 07:14:48 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 660/1251] eta: 0:05:02 lr: 0.000986 loss: 4.3241 (4.2743) grad_norm: 1.1930 (inf) time: 0.5031 [2021-03-25 07:14:53 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 670/1251] eta: 0:04:57 lr: 0.000986 loss: 4.1746 (4.2696) grad_norm: 1.1855 (inf) time: 0.5024 [2021-03-25 07:14:58 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 680/1251] eta: 0:04:51 lr: 0.000986 loss: 4.3433 (4.2714) grad_norm: 1.1847 (inf) time: 0.5065 [2021-03-25 07:15:03 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 690/1251] eta: 0:04:46 lr: 0.000986 loss: 4.3634 (4.2673) grad_norm: 1.1389 (inf) time: 0.5142 [2021-03-25 07:15:08 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 700/1251] eta: 0:04:41 lr: 0.000986 loss: 4.0180 (4.2665) grad_norm: 1.0982 (inf) time: 0.5137 [2021-03-25 07:15:13 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 710/1251] eta: 0:04:36 lr: 0.000986 loss: 4.3441 (4.2685) grad_norm: 1.0934 (inf) time: 0.5102 [2021-03-25 07:15:19 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 720/1251] eta: 0:04:31 lr: 0.000986 loss: 4.3441 (4.2628) grad_norm: 1.1050 (inf) time: 0.5137 [2021-03-25 07:15:24 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 730/1251] eta: 0:04:26 lr: 0.000986 loss: 4.2445 (4.2650) grad_norm: 1.1050 (inf) time: 0.5193 [2021-03-25 07:15:29 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 740/1251] eta: 0:04:21 lr: 0.000986 loss: 4.5997 (4.2697) grad_norm: 1.0770 (inf) time: 0.5227 [2021-03-25 07:15:34 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 750/1251] eta: 0:04:16 lr: 0.000986 loss: 4.5511 (4.2697) grad_norm: 1.1539 (inf) time: 0.5157 [2021-03-25 07:15:39 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 760/1251] eta: 0:04:11 lr: 0.000986 loss: 4.2063 (4.2684) grad_norm: 1.1801 (inf) time: 0.5093 [2021-03-25 07:15:44 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 770/1251] eta: 0:04:06 lr: 0.000986 loss: 4.1568 (4.2689) grad_norm: 1.0997 (inf) time: 0.5061 [2021-03-25 07:15:49 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 780/1251] eta: 0:04:00 lr: 0.000986 loss: 4.3335 (4.2682) grad_norm: 1.0738 (inf) time: 0.5046 [2021-03-25 07:15:54 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 790/1251] eta: 0:03:55 lr: 0.000986 loss: 4.6496 (4.2722) grad_norm: 1.0502 (inf) time: 0.5058 [2021-03-25 07:15:59 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 800/1251] eta: 0:03:50 lr: 0.000986 loss: 4.4671 (4.2718) grad_norm: 1.0415 (inf) time: 0.5032 [2021-03-25 07:16:04 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 810/1251] eta: 0:03:45 lr: 0.000986 loss: 4.1958 (4.2699) grad_norm: 1.1032 (inf) time: 0.5023 [2021-03-25 07:16:09 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 820/1251] eta: 0:03:40 lr: 0.000986 loss: 4.1972 (4.2685) grad_norm: 1.1046 (inf) time: 0.5044 [2021-03-25 07:16:15 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 830/1251] eta: 0:03:35 lr: 0.000986 loss: 4.1095 (4.2650) grad_norm: 1.0595 (inf) time: 0.5029 [2021-03-25 07:16:20 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 840/1251] eta: 0:03:30 lr: 0.000986 loss: 4.2881 (4.2688) grad_norm: 1.0290 (inf) time: 0.5069 [2021-03-25 07:16:25 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 850/1251] eta: 0:03:24 lr: 0.000986 loss: 4.5848 (4.2688) grad_norm: 1.0563 (inf) time: 0.5110 [2021-03-25 07:16:30 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 860/1251] eta: 0:03:19 lr: 0.000986 loss: 4.3763 (4.2685) grad_norm: 1.0574 (inf) time: 0.5066 [2021-03-25 07:16:35 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 870/1251] eta: 0:03:14 lr: 0.000986 loss: 4.1536 (4.2659) grad_norm: 1.1320 (inf) time: 0.5072 [2021-03-25 07:16:40 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 880/1251] eta: 0:03:09 lr: 0.000986 loss: 4.1903 (4.2661) grad_norm: 1.1670 (inf) time: 0.5074 [2021-03-25 07:16:45 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 890/1251] eta: 0:03:04 lr: 0.000986 loss: 4.1903 (4.2656) grad_norm: 1.1804 (inf) time: 0.5132 [2021-03-25 07:16:50 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 900/1251] eta: 0:02:59 lr: 0.000986 loss: 4.3543 (4.2655) grad_norm: 1.1852 (inf) time: 0.5101 [2021-03-25 07:16:55 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 910/1251] eta: 0:02:54 lr: 0.000986 loss: 4.3223 (4.2649) grad_norm: 1.1852 (inf) time: 0.5054 [2021-03-25 07:17:00 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 920/1251] eta: 0:02:49 lr: 0.000986 loss: 4.0422 (4.2627) grad_norm: 1.1014 (inf) time: 0.5112 [2021-03-25 07:17:05 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 930/1251] eta: 0:02:43 lr: 0.000986 loss: 4.1722 (4.2630) grad_norm: 1.1014 (inf) time: 0.5083 [2021-03-25 07:17:11 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 940/1251] eta: 0:02:38 lr: 0.000986 loss: 4.4494 (4.2636) grad_norm: 1.1055 (inf) time: 0.5115 [2021-03-25 07:17:16 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 950/1251] eta: 0:02:33 lr: 0.000986 loss: 4.4575 (4.2636) grad_norm: 1.0487 (inf) time: 0.5147 [2021-03-25 07:17:21 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 960/1251] eta: 0:02:28 lr: 0.000986 loss: 4.1345 (4.2607) grad_norm: 1.0836 (inf) time: 0.5103 [2021-03-25 07:17:26 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 970/1251] eta: 0:02:23 lr: 0.000986 loss: 4.1041 (4.2600) grad_norm: 1.0710 (inf) time: 0.5054 [2021-03-25 07:17:31 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 980/1251] eta: 0:02:18 lr: 0.000986 loss: 4.2755 (4.2596) grad_norm: 1.0177 (inf) time: 0.5051 [2021-03-25 07:17:36 swin_small_patch4_window7_224] INFO: Epoch: [22] [ 990/1251] eta: 0:02:13 lr: 0.000986 loss: 4.4881 (4.2614) grad_norm: 1.0750 (inf) time: 0.5052 [2021-03-25 07:17:41 swin_small_patch4_window7_224] INFO: Epoch: [22] [1000/1251] eta: 0:02:08 lr: 0.000986 loss: 4.2287 (4.2601) grad_norm: 1.0750 (inf) time: 0.5049 [2021-03-25 07:17:46 swin_small_patch4_window7_224] INFO: Epoch: [22] [1010/1251] eta: 0:02:03 lr: 0.000986 loss: 4.0165 (4.2586) grad_norm: 1.1148 (inf) time: 0.5105 [2021-03-25 07:17:51 swin_small_patch4_window7_224] INFO: Epoch: [22] [1020/1251] eta: 0:01:57 lr: 0.000986 loss: 4.2926 (4.2598) grad_norm: 1.0817 (inf) time: 0.5101 [2021-03-25 07:17:56 swin_small_patch4_window7_224] INFO: Epoch: [22] [1030/1251] eta: 0:01:52 lr: 0.000986 loss: 4.3435 (4.2599) grad_norm: 1.0337 (inf) time: 0.5051 [2021-03-25 07:18:01 swin_small_patch4_window7_224] INFO: Epoch: [22] [1040/1251] eta: 0:01:47 lr: 0.000986 loss: 4.5380 (4.2629) grad_norm: 1.1129 (inf) time: 0.5069 [2021-03-25 07:18:06 swin_small_patch4_window7_224] INFO: Epoch: [22] [1050/1251] eta: 0:01:42 lr: 0.000986 loss: 4.5267 (4.2612) grad_norm: 1.1129 (inf) time: 0.5111 [2021-03-25 07:18:12 swin_small_patch4_window7_224] INFO: Epoch: [22] [1060/1251] eta: 0:01:37 lr: 0.000986 loss: 4.4517 (4.2625) grad_norm: 1.0667 (inf) time: 0.5166 [2021-03-25 07:18:17 swin_small_patch4_window7_224] INFO: Epoch: [22] [1070/1251] eta: 0:01:32 lr: 0.000986 loss: 4.4830 (4.2633) grad_norm: 1.0699 (inf) time: 0.5171 [2021-03-25 07:18:22 swin_small_patch4_window7_224] INFO: Epoch: [22] [1080/1251] eta: 0:01:27 lr: 0.000986 loss: 4.5055 (4.2647) grad_norm: 1.1701 (inf) time: 0.5087 [2021-03-25 07:18:27 swin_small_patch4_window7_224] INFO: Epoch: [22] [1090/1251] eta: 0:01:22 lr: 0.000986 loss: 4.4688 (4.2663) grad_norm: 1.1728 (inf) time: 0.5011 [2021-03-25 07:18:32 swin_small_patch4_window7_224] INFO: Epoch: [22] [1100/1251] eta: 0:01:17 lr: 0.000986 loss: 4.4975 (4.2693) grad_norm: 1.0975 (inf) time: 0.5012 [2021-03-25 07:18:37 swin_small_patch4_window7_224] INFO: Epoch: [22] [1110/1251] eta: 0:01:11 lr: 0.000986 loss: 4.4975 (4.2685) grad_norm: 1.0833 (inf) time: 0.5054 [2021-03-25 07:18:42 swin_small_patch4_window7_224] INFO: Epoch: [22] [1120/1251] eta: 0:01:06 lr: 0.000986 loss: 4.3644 (4.2676) grad_norm: 1.1123 (inf) time: 0.5101 [2021-03-25 07:18:47 swin_small_patch4_window7_224] INFO: Epoch: [22] [1130/1251] eta: 0:01:01 lr: 0.000986 loss: 4.2916 (4.2670) grad_norm: 1.1484 (inf) time: 0.5022 [2021-03-25 07:18:52 swin_small_patch4_window7_224] INFO: Epoch: [22] [1140/1251] eta: 0:00:56 lr: 0.000986 loss: 4.2688 (4.2687) grad_norm: 1.2111 (inf) time: 0.4971 [2021-03-25 07:18:57 swin_small_patch4_window7_224] INFO: Epoch: [22] [1150/1251] eta: 0:00:51 lr: 0.000986 loss: 4.2688 (4.2677) grad_norm: 1.0668 (inf) time: 0.5061 [2021-03-25 07:19:02 swin_small_patch4_window7_224] INFO: Epoch: [22] [1160/1251] eta: 0:00:46 lr: 0.000986 loss: 4.3351 (4.2683) grad_norm: 1.0731 (inf) time: 0.5067 [2021-03-25 07:19:07 swin_small_patch4_window7_224] INFO: Epoch: [22] [1170/1251] eta: 0:00:41 lr: 0.000986 loss: 4.5339 (4.2702) grad_norm: 1.0865 (inf) time: 0.5057 [2021-03-25 07:19:12 swin_small_patch4_window7_224] INFO: Epoch: [22] [1180/1251] eta: 0:00:36 lr: 0.000986 loss: 4.4824 (4.2707) grad_norm: 1.1082 (inf) time: 0.5046 [2021-03-25 07:19:17 swin_small_patch4_window7_224] INFO: Epoch: [22] [1190/1251] eta: 0:00:31 lr: 0.000986 loss: 4.3901 (4.2705) grad_norm: 1.1082 (inf) time: 0.5023 [2021-03-25 07:19:22 swin_small_patch4_window7_224] INFO: Epoch: [22] [1200/1251] eta: 0:00:26 lr: 0.000986 loss: 4.3712 (4.2710) grad_norm: 1.0882 (inf) time: 0.5008 [2021-03-25 07:19:27 swin_small_patch4_window7_224] INFO: Epoch: [22] [1210/1251] eta: 0:00:20 lr: 0.000986 loss: 4.3665 (4.2723) grad_norm: 1.0882 (inf) time: 0.5002 [2021-03-25 07:19:32 swin_small_patch4_window7_224] INFO: Epoch: [22] [1220/1251] eta: 0:00:15 lr: 0.000986 loss: 4.1022 (4.2704) grad_norm: 1.0572 (inf) time: 0.5056 [2021-03-25 07:19:37 swin_small_patch4_window7_224] INFO: Epoch: [22] [1230/1251] eta: 0:00:10 lr: 0.000986 loss: 4.1022 (4.2713) grad_norm: 1.0865 (inf) time: 0.5055 [2021-03-25 07:19:42 swin_small_patch4_window7_224] INFO: Epoch: [22] [1240/1251] eta: 0:00:05 lr: 0.000986 loss: 4.4243 (4.2704) grad_norm: 1.1059 (inf) time: 0.5030 [2021-03-25 07:19:48 swin_small_patch4_window7_224] INFO: Epoch: [22] [1250/1251] eta: 0:00:00 lr: 0.000986 loss: 4.2484 (4.2675) grad_norm: 1.0980 (inf) time: 0.5064 [2021-03-25 07:19:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:37 loss: 1.4353 (1.4353) acc1: 70.3125 (70.3125) acc5: 84.3750 (84.3750) [2021-03-25 07:19:55 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.6389 (1.5613) acc1: 67.1875 (65.9091) acc5: 84.3750 (86.3636) [2021-03-25 07:19:57 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.6829 (1.6298) acc1: 62.5000 (63.6905) acc5: 85.9375 (85.8631) [2021-03-25 07:19:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.6772 (1.6506) acc1: 60.9375 (62.6008) acc5: 85.9375 (85.3327) [2021-03-25 07:20:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.6210 (1.6418) acc1: 62.5000 (62.8430) acc5: 87.5000 (85.7851) [2021-03-25 07:20:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.6106 (1.6426) acc1: 64.0625 (63.3600) acc5: 87.5000 (85.6960) [2021-03-25 07:20:03 swin_small_patch4_window7_224] INFO: * Acc@1 63.592 Acc@5 86.364 loss 1.598 [2021-03-25 07:20:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 63.6% [2021-03-25 07:20:03 swin_small_patch4_window7_224] INFO: Max accuracy: 63.59% [2021-03-25 07:20:07 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 0/1251] eta: 1:35:39 lr: 0.000986 loss: 3.5781 (3.5781) grad_norm: 1.4558 (1.4558) time: 4.5882 [2021-03-25 07:20:13 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 10/1251] eta: 0:18:18 lr: 0.000986 loss: 4.1250 (3.9947) grad_norm: 1.2017 (1.1917) time: 0.8854 [2021-03-25 07:20:18 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 20/1251] eta: 0:14:32 lr: 0.000986 loss: 4.2879 (4.1963) grad_norm: 1.1658 (1.1855) time: 0.5151 [2021-03-25 07:20:23 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 30/1251] eta: 0:13:04 lr: 0.000986 loss: 4.5682 (4.1840) grad_norm: 1.1750 (1.2048) time: 0.5093 [2021-03-25 07:20:28 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 40/1251] eta: 0:12:25 lr: 0.000986 loss: 4.2155 (4.1652) grad_norm: 1.1142 (1.1622) time: 0.5181 [2021-03-25 07:20:33 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 50/1251] eta: 0:11:57 lr: 0.000986 loss: 4.2358 (4.1690) grad_norm: 0.9996 (1.1504) time: 0.5269 [2021-03-25 07:20:38 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 60/1251] eta: 0:11:31 lr: 0.000986 loss: 4.2698 (4.1680) grad_norm: 1.0697 (1.1449) time: 0.5091 [2021-03-25 07:20:43 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 70/1251] eta: 0:11:14 lr: 0.000986 loss: 4.2285 (4.1520) grad_norm: 1.0959 (1.1424) time: 0.5051 [2021-03-25 07:20:49 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 80/1251] eta: 0:11:01 lr: 0.000986 loss: 4.0801 (4.1792) grad_norm: 1.0959 (1.1354) time: 0.5156 [2021-03-25 07:20:54 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 90/1251] eta: 0:10:50 lr: 0.000986 loss: 4.5065 (4.2021) grad_norm: 1.0305 (1.1203) time: 0.5218 [2021-03-25 07:20:59 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 100/1251] eta: 0:10:38 lr: 0.000986 loss: 4.5342 (4.2292) grad_norm: 1.0578 (1.1209) time: 0.5154 [2021-03-25 07:21:04 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 110/1251] eta: 0:10:29 lr: 0.000986 loss: 4.4349 (4.2281) grad_norm: 1.1095 (1.1245) time: 0.5099 [2021-03-25 07:21:09 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 120/1251] eta: 0:10:19 lr: 0.000986 loss: 3.9086 (4.2014) grad_norm: 1.0489 (1.1171) time: 0.5102 [2021-03-25 07:21:14 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 130/1251] eta: 0:10:09 lr: 0.000986 loss: 3.8021 (4.1840) grad_norm: 1.0945 (1.1190) time: 0.5005 [2021-03-25 07:21:19 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 140/1251] eta: 0:10:01 lr: 0.000986 loss: 4.0191 (4.1735) grad_norm: 1.1467 (1.1224) time: 0.5038 [2021-03-25 07:21:24 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 150/1251] eta: 0:09:53 lr: 0.000986 loss: 4.0731 (4.1566) grad_norm: 1.1314 (1.1226) time: 0.5093 [2021-03-25 07:21:29 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 160/1251] eta: 0:09:45 lr: 0.000986 loss: 3.9996 (4.1598) grad_norm: 1.0496 (1.1183) time: 0.5039 [2021-03-25 07:21:34 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 170/1251] eta: 0:09:38 lr: 0.000986 loss: 4.2475 (4.1629) grad_norm: 1.1265 (1.1282) time: 0.5084 [2021-03-25 07:21:40 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 180/1251] eta: 0:09:32 lr: 0.000986 loss: 4.2598 (4.1556) grad_norm: 1.1613 (1.1277) time: 0.5179 [2021-03-25 07:21:45 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 190/1251] eta: 0:09:25 lr: 0.000986 loss: 4.4723 (4.1747) grad_norm: 1.1023 (1.1259) time: 0.5131 [2021-03-25 07:21:50 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 200/1251] eta: 0:09:18 lr: 0.000986 loss: 4.4872 (4.1805) grad_norm: 1.0923 (1.1265) time: 0.5023 [2021-03-25 07:21:55 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 210/1251] eta: 0:09:11 lr: 0.000986 loss: 4.3949 (4.1879) grad_norm: 1.1350 (1.1315) time: 0.4988 [2021-03-25 07:22:00 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 220/1251] eta: 0:09:05 lr: 0.000985 loss: 4.5144 (4.1924) grad_norm: 1.1350 (1.1331) time: 0.5012 [2021-03-25 07:22:05 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 230/1251] eta: 0:08:59 lr: 0.000985 loss: 4.3229 (4.1949) grad_norm: 1.0821 (1.1313) time: 0.5081 [2021-03-25 07:22:10 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 240/1251] eta: 0:08:53 lr: 0.000985 loss: 4.3229 (4.1955) grad_norm: 1.0905 (1.1327) time: 0.5117 [2021-03-25 07:22:15 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 250/1251] eta: 0:08:47 lr: 0.000985 loss: 4.3379 (4.1990) grad_norm: 1.0362 (1.1298) time: 0.5099 [2021-03-25 07:22:20 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 260/1251] eta: 0:08:41 lr: 0.000985 loss: 4.3379 (4.2037) grad_norm: 1.0362 (1.1274) time: 0.5091 [2021-03-25 07:22:25 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 270/1251] eta: 0:08:34 lr: 0.000985 loss: 4.3156 (4.2012) grad_norm: 1.0408 (1.1243) time: 0.5018 [2021-03-25 07:22:30 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 280/1251] eta: 0:08:28 lr: 0.000985 loss: 4.3084 (4.2002) grad_norm: 1.0498 (1.1263) time: 0.5004 [2021-03-25 07:22:35 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 290/1251] eta: 0:08:22 lr: 0.000985 loss: 4.3969 (4.2079) grad_norm: 1.1049 (1.1249) time: 0.5059 [2021-03-25 07:22:40 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 300/1251] eta: 0:08:17 lr: 0.000985 loss: 4.4903 (4.1994) grad_norm: 1.0592 (1.1221) time: 0.5059 [2021-03-25 07:22:45 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 310/1251] eta: 0:08:11 lr: 0.000985 loss: 4.4043 (4.2093) grad_norm: 1.0804 (1.1243) time: 0.5058 [2021-03-25 07:22:50 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 320/1251] eta: 0:08:05 lr: 0.000985 loss: 4.4945 (4.2108) grad_norm: 1.0880 (1.1223) time: 0.5037 [2021-03-25 07:22:55 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 330/1251] eta: 0:07:59 lr: 0.000985 loss: 4.3100 (4.2098) grad_norm: 1.0848 (1.1213) time: 0.5008 [2021-03-25 07:23:00 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 340/1251] eta: 0:07:54 lr: 0.000985 loss: 4.3137 (4.2151) grad_norm: 1.0767 (1.1204) time: 0.5018 [2021-03-25 07:23:05 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 350/1251] eta: 0:07:48 lr: 0.000985 loss: 4.2429 (4.2088) grad_norm: 1.0190 (1.1171) time: 0.5054 [2021-03-25 07:23:10 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 360/1251] eta: 0:07:42 lr: 0.000985 loss: 4.2256 (4.2081) grad_norm: 1.0071 (1.1146) time: 0.5043 [2021-03-25 07:23:16 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 370/1251] eta: 0:07:37 lr: 0.000985 loss: 4.3463 (4.2142) grad_norm: 1.0225 (1.1148) time: 0.5055 [2021-03-25 07:23:20 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 380/1251] eta: 0:07:31 lr: 0.000985 loss: 4.5680 (4.2214) grad_norm: 1.0702 (1.1149) time: 0.5023 [2021-03-25 07:23:26 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 390/1251] eta: 0:07:26 lr: 0.000985 loss: 4.5983 (4.2259) grad_norm: 1.1020 (1.1145) time: 0.5020 [2021-03-25 07:23:31 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 400/1251] eta: 0:07:20 lr: 0.000985 loss: 4.3411 (4.2231) grad_norm: 1.0666 (1.1127) time: 0.5056 [2021-03-25 07:23:36 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 410/1251] eta: 0:07:15 lr: 0.000985 loss: 4.1021 (4.2214) grad_norm: 1.0271 (1.1103) time: 0.5024 [2021-03-25 07:23:41 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 420/1251] eta: 0:07:09 lr: 0.000985 loss: 4.0523 (4.2156) grad_norm: 1.0495 (1.1120) time: 0.5025 [2021-03-25 07:23:46 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 430/1251] eta: 0:07:04 lr: 0.000985 loss: 4.1835 (4.2157) grad_norm: 1.2078 (1.1159) time: 0.5034 [2021-03-25 07:23:51 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 440/1251] eta: 0:06:59 lr: 0.000985 loss: 4.3751 (4.2120) grad_norm: 1.1612 (1.1150) time: 0.5041 [2021-03-25 07:23:56 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 450/1251] eta: 0:06:53 lr: 0.000985 loss: 4.2447 (4.2097) grad_norm: 1.0102 (1.1130) time: 0.5053 [2021-03-25 07:24:01 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 460/1251] eta: 0:06:48 lr: 0.000985 loss: 4.1626 (4.2111) grad_norm: 1.0784 (1.1126) time: 0.5024 [2021-03-25 07:24:06 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 470/1251] eta: 0:06:42 lr: 0.000985 loss: 4.2066 (4.2080) grad_norm: 1.0866 (1.1138) time: 0.5019 [2021-03-25 07:24:11 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 480/1251] eta: 0:06:37 lr: 0.000985 loss: 4.3762 (4.2109) grad_norm: 1.1322 (1.1150) time: 0.5021 [2021-03-25 07:24:16 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 490/1251] eta: 0:06:32 lr: 0.000985 loss: 4.3115 (4.2079) grad_norm: 1.1071 (1.1147) time: 0.5010 [2021-03-25 07:24:21 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 500/1251] eta: 0:06:26 lr: 0.000985 loss: 4.2588 (4.2108) grad_norm: 1.0413 (1.1131) time: 0.5089 [2021-03-25 07:24:26 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 510/1251] eta: 0:06:21 lr: 0.000985 loss: 4.3217 (4.2164) grad_norm: 1.0134 (1.1129) time: 0.5095 [2021-03-25 07:24:31 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 520/1251] eta: 0:06:16 lr: 0.000985 loss: 4.5886 (4.2237) grad_norm: 1.1237 (1.1146) time: 0.5015 [2021-03-25 07:24:36 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 530/1251] eta: 0:06:10 lr: 0.000985 loss: 4.4654 (4.2228) grad_norm: 1.0830 (1.1132) time: 0.5003 [2021-03-25 07:24:41 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 540/1251] eta: 0:06:05 lr: 0.000985 loss: 4.2696 (4.2234) grad_norm: 1.0414 (1.1127) time: 0.5016 [2021-03-25 07:24:46 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 550/1251] eta: 0:06:00 lr: 0.000985 loss: 4.1624 (4.2224) grad_norm: 1.0466 (1.1116) time: 0.5148 [2021-03-25 07:24:51 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 560/1251] eta: 0:05:55 lr: 0.000985 loss: 4.3933 (4.2273) grad_norm: 1.0354 (1.1106) time: 0.5131 [2021-03-25 07:24:56 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 570/1251] eta: 0:05:49 lr: 0.000985 loss: 4.6349 (4.2362) grad_norm: 0.9960 (1.1102) time: 0.4997 [2021-03-25 07:25:01 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 580/1251] eta: 0:05:44 lr: 0.000985 loss: 4.6714 (4.2383) grad_norm: 1.0965 (1.1116) time: 0.5014 [2021-03-25 07:25:07 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 590/1251] eta: 0:05:39 lr: 0.000985 loss: 4.2278 (4.2355) grad_norm: 1.0793 (1.1104) time: 0.5111 [2021-03-25 07:25:12 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 600/1251] eta: 0:05:34 lr: 0.000985 loss: 4.1953 (4.2372) grad_norm: 1.0061 (1.1110) time: 0.5147 [2021-03-25 07:25:17 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 610/1251] eta: 0:05:29 lr: 0.000985 loss: 4.1092 (4.2329) grad_norm: 1.1706 (1.1120) time: 0.5049 [2021-03-25 07:25:22 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 620/1251] eta: 0:05:23 lr: 0.000985 loss: 4.1755 (4.2337) grad_norm: 1.1469 (1.1134) time: 0.5015 [2021-03-25 07:25:27 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 630/1251] eta: 0:05:18 lr: 0.000985 loss: 4.2993 (4.2341) grad_norm: 1.0393 (1.1122) time: 0.5064 [2021-03-25 07:25:32 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 640/1251] eta: 0:05:13 lr: 0.000985 loss: 4.3356 (4.2357) grad_norm: 1.0127 (1.1109) time: 0.5129 [2021-03-25 07:25:37 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 650/1251] eta: 0:05:08 lr: 0.000985 loss: 4.3250 (4.2346) grad_norm: 1.0467 (1.1104) time: 0.5113 [2021-03-25 07:25:42 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 660/1251] eta: 0:05:03 lr: 0.000985 loss: 4.2356 (4.2319) grad_norm: 1.0997 (1.1112) time: 0.5063 [2021-03-25 07:25:47 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 670/1251] eta: 0:04:58 lr: 0.000985 loss: 4.2356 (4.2302) grad_norm: 1.0892 (1.1111) time: 0.5053 [2021-03-25 07:25:52 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 680/1251] eta: 0:04:52 lr: 0.000985 loss: 4.1642 (4.2289) grad_norm: 1.0521 (1.1114) time: 0.5020 [2021-03-25 07:25:57 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 690/1251] eta: 0:04:47 lr: 0.000985 loss: 4.3881 (4.2309) grad_norm: 1.0882 (1.1129) time: 0.5009 [2021-03-25 07:26:02 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 700/1251] eta: 0:04:42 lr: 0.000985 loss: 4.4333 (4.2301) grad_norm: 1.1617 (1.1136) time: 0.5071 [2021-03-25 07:26:07 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 710/1251] eta: 0:04:37 lr: 0.000985 loss: 4.4090 (4.2344) grad_norm: 1.1895 (1.1159) time: 0.5064 [2021-03-25 07:26:12 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 720/1251] eta: 0:04:32 lr: 0.000985 loss: 4.4480 (4.2350) grad_norm: 1.1649 (1.1161) time: 0.5067 [2021-03-25 07:26:17 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 730/1251] eta: 0:04:26 lr: 0.000985 loss: 4.5620 (4.2372) grad_norm: 1.1191 (1.1169) time: 0.5067 [2021-03-25 07:26:23 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 740/1251] eta: 0:04:22 lr: 0.000985 loss: 4.4542 (4.2397) grad_norm: 1.1180 (1.1169) time: 0.5236 [2021-03-25 07:26:28 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 750/1251] eta: 0:04:16 lr: 0.000985 loss: 4.2833 (4.2340) grad_norm: 1.0907 (1.1177) time: 0.5262 [2021-03-25 07:26:33 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 760/1251] eta: 0:04:11 lr: 0.000985 loss: 3.8330 (4.2302) grad_norm: 1.0822 (1.1178) time: 0.5043 [2021-03-25 07:26:38 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 770/1251] eta: 0:04:06 lr: 0.000985 loss: 4.2161 (4.2320) grad_norm: 1.1341 (1.1176) time: 0.5063 [2021-03-25 07:26:43 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 780/1251] eta: 0:04:01 lr: 0.000985 loss: 4.1896 (4.2284) grad_norm: 1.1499 (1.1206) time: 0.5135 [2021-03-25 07:26:48 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 790/1251] eta: 0:03:56 lr: 0.000985 loss: 4.3181 (4.2312) grad_norm: 1.1499 (1.1208) time: 0.5174 [2021-03-25 07:26:54 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 800/1251] eta: 0:03:51 lr: 0.000985 loss: 4.5512 (4.2337) grad_norm: 1.1274 (1.1207) time: 0.5118 [2021-03-25 07:26:59 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 810/1251] eta: 0:03:46 lr: 0.000985 loss: 4.4821 (4.2340) grad_norm: 1.1274 (1.1210) time: 0.5048 [2021-03-25 07:27:04 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 820/1251] eta: 0:03:40 lr: 0.000985 loss: 4.3240 (4.2310) grad_norm: 1.0984 (1.1216) time: 0.5052 [2021-03-25 07:27:09 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 830/1251] eta: 0:03:35 lr: 0.000985 loss: 3.9639 (4.2298) grad_norm: 1.1304 (1.1218) time: 0.5094 [2021-03-25 07:27:14 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 840/1251] eta: 0:03:30 lr: 0.000985 loss: 4.0584 (4.2267) grad_norm: 1.1104 (1.1212) time: 0.5137 [2021-03-25 07:27:19 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 850/1251] eta: 0:03:25 lr: 0.000985 loss: 3.9041 (4.2257) grad_norm: 1.0705 (1.1211) time: 0.5085 [2021-03-25 07:27:24 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 860/1251] eta: 0:03:20 lr: 0.000985 loss: 4.2487 (4.2273) grad_norm: 1.0702 (1.1206) time: 0.5030 [2021-03-25 07:27:29 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 870/1251] eta: 0:03:15 lr: 0.000985 loss: 4.2487 (4.2275) grad_norm: 1.1208 (1.1216) time: 0.5031 [2021-03-25 07:27:34 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 880/1251] eta: 0:03:09 lr: 0.000985 loss: 4.4963 (4.2301) grad_norm: 1.1625 (1.1225) time: 0.5064 [2021-03-25 07:27:39 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 890/1251] eta: 0:03:04 lr: 0.000985 loss: 4.4963 (4.2289) grad_norm: 1.0917 (1.1225) time: 0.5115 [2021-03-25 07:27:44 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 900/1251] eta: 0:02:59 lr: 0.000985 loss: 4.3725 (4.2314) grad_norm: 1.0730 (1.1226) time: 0.5108 [2021-03-25 07:27:49 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 910/1251] eta: 0:02:54 lr: 0.000985 loss: 4.4093 (4.2341) grad_norm: 0.9824 (1.1211) time: 0.5079 [2021-03-25 07:27:54 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 920/1251] eta: 0:02:49 lr: 0.000985 loss: 4.4815 (4.2362) grad_norm: 0.9689 (1.1202) time: 0.5053 [2021-03-25 07:28:00 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 930/1251] eta: 0:02:44 lr: 0.000985 loss: 4.4162 (4.2359) grad_norm: 0.9406 (1.1187) time: 0.5118 [2021-03-25 07:28:05 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 940/1251] eta: 0:02:39 lr: 0.000985 loss: 4.3575 (4.2336) grad_norm: 0.9648 (1.1178) time: 0.5130 [2021-03-25 07:28:10 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 950/1251] eta: 0:02:34 lr: 0.000985 loss: 4.3594 (4.2355) grad_norm: 1.0198 (1.1177) time: 0.5054 [2021-03-25 07:28:15 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 960/1251] eta: 0:02:28 lr: 0.000985 loss: 4.1997 (4.2321) grad_norm: 1.0584 (1.1178) time: 0.5029 [2021-03-25 07:28:20 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 970/1251] eta: 0:02:23 lr: 0.000985 loss: 3.9587 (4.2302) grad_norm: 1.1031 (1.1185) time: 0.5023 [2021-03-25 07:28:25 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 980/1251] eta: 0:02:18 lr: 0.000985 loss: 4.2854 (4.2299) grad_norm: 1.0972 (1.1183) time: 0.5037 [2021-03-25 07:28:30 swin_small_patch4_window7_224] INFO: Epoch: [23] [ 990/1251] eta: 0:02:13 lr: 0.000985 loss: 4.0108 (4.2263) grad_norm: 1.0334 (1.1176) time: 0.5063 [2021-03-25 07:28:35 swin_small_patch4_window7_224] INFO: Epoch: [23] [1000/1251] eta: 0:02:08 lr: 0.000985 loss: 4.1158 (4.2257) grad_norm: 1.1370 (1.1184) time: 0.5079 [2021-03-25 07:28:40 swin_small_patch4_window7_224] INFO: Epoch: [23] [1010/1251] eta: 0:02:03 lr: 0.000985 loss: 4.1284 (4.2242) grad_norm: 1.1370 (1.1183) time: 0.5002 [2021-03-25 07:28:45 swin_small_patch4_window7_224] INFO: Epoch: [23] [1020/1251] eta: 0:01:58 lr: 0.000985 loss: 4.2030 (4.2247) grad_norm: 1.0390 (1.1172) time: 0.4983 [2021-03-25 07:28:50 swin_small_patch4_window7_224] INFO: Epoch: [23] [1030/1251] eta: 0:01:52 lr: 0.000985 loss: 4.2914 (4.2258) grad_norm: 1.0340 (1.1163) time: 0.5049 [2021-03-25 07:28:55 swin_small_patch4_window7_224] INFO: Epoch: [23] [1040/1251] eta: 0:01:47 lr: 0.000985 loss: 4.4091 (4.2278) grad_norm: 1.0410 (1.1163) time: 0.5124 [2021-03-25 07:29:00 swin_small_patch4_window7_224] INFO: Epoch: [23] [1050/1251] eta: 0:01:42 lr: 0.000985 loss: 4.3765 (4.2277) grad_norm: 1.0702 (1.1159) time: 0.5053 [2021-03-25 07:29:05 swin_small_patch4_window7_224] INFO: Epoch: [23] [1060/1251] eta: 0:01:37 lr: 0.000985 loss: 4.3288 (4.2283) grad_norm: 1.0615 (1.1155) time: 0.5036 [2021-03-25 07:29:10 swin_small_patch4_window7_224] INFO: Epoch: [23] [1070/1251] eta: 0:01:32 lr: 0.000985 loss: 4.4540 (4.2268) grad_norm: 1.0615 (1.1151) time: 0.5081 [2021-03-25 07:29:15 swin_small_patch4_window7_224] INFO: Epoch: [23] [1080/1251] eta: 0:01:27 lr: 0.000985 loss: 4.3003 (4.2271) grad_norm: 1.0210 (1.1139) time: 0.5002 [2021-03-25 07:29:20 swin_small_patch4_window7_224] INFO: Epoch: [23] [1090/1251] eta: 0:01:22 lr: 0.000985 loss: 4.2982 (4.2267) grad_norm: 1.0210 (1.1131) time: 0.5026 [2021-03-25 07:29:25 swin_small_patch4_window7_224] INFO: Epoch: [23] [1100/1251] eta: 0:01:17 lr: 0.000985 loss: 4.2571 (4.2285) grad_norm: 1.0360 (1.1128) time: 0.5017 [2021-03-25 07:29:30 swin_small_patch4_window7_224] INFO: Epoch: [23] [1110/1251] eta: 0:01:12 lr: 0.000985 loss: 4.1522 (4.2257) grad_norm: 1.1040 (1.1135) time: 0.5021 [2021-03-25 07:29:35 swin_small_patch4_window7_224] INFO: Epoch: [23] [1120/1251] eta: 0:01:06 lr: 0.000985 loss: 3.8469 (4.2238) grad_norm: 1.1121 (1.1136) time: 0.5061 [2021-03-25 07:29:40 swin_small_patch4_window7_224] INFO: Epoch: [23] [1130/1251] eta: 0:01:01 lr: 0.000985 loss: 4.2350 (4.2239) grad_norm: 1.0630 (1.1135) time: 0.5033 [2021-03-25 07:29:46 swin_small_patch4_window7_224] INFO: Epoch: [23] [1140/1251] eta: 0:00:56 lr: 0.000985 loss: 4.3198 (4.2233) grad_norm: 1.0630 (1.1128) time: 0.5049 [2021-03-25 07:29:51 swin_small_patch4_window7_224] INFO: Epoch: [23] [1150/1251] eta: 0:00:51 lr: 0.000985 loss: 4.2870 (4.2215) grad_norm: 1.0660 (1.1124) time: 0.5052 [2021-03-25 07:29:56 swin_small_patch4_window7_224] INFO: Epoch: [23] [1160/1251] eta: 0:00:46 lr: 0.000985 loss: 4.0946 (4.2205) grad_norm: 1.0786 (1.1125) time: 0.5033 [2021-03-25 07:30:01 swin_small_patch4_window7_224] INFO: Epoch: [23] [1170/1251] eta: 0:00:41 lr: 0.000985 loss: 4.1694 (4.2222) grad_norm: 1.0896 (1.1125) time: 0.5014 [2021-03-25 07:30:06 swin_small_patch4_window7_224] INFO: Epoch: [23] [1180/1251] eta: 0:00:36 lr: 0.000985 loss: 4.5366 (4.2245) grad_norm: 1.0896 (1.1125) time: 0.5030 [2021-03-25 07:30:11 swin_small_patch4_window7_224] INFO: Epoch: [23] [1190/1251] eta: 0:00:31 lr: 0.000985 loss: 4.5509 (4.2254) grad_norm: 1.1220 (1.1126) time: 0.5087 [2021-03-25 07:30:16 swin_small_patch4_window7_224] INFO: Epoch: [23] [1200/1251] eta: 0:00:26 lr: 0.000985 loss: 4.6710 (4.2264) grad_norm: 1.1248 (1.1130) time: 0.5074 [2021-03-25 07:30:21 swin_small_patch4_window7_224] INFO: Epoch: [23] [1210/1251] eta: 0:00:20 lr: 0.000984 loss: 4.4072 (4.2253) grad_norm: 1.1540 (1.1140) time: 0.5022 [2021-03-25 07:30:26 swin_small_patch4_window7_224] INFO: Epoch: [23] [1220/1251] eta: 0:00:15 lr: 0.000984 loss: 4.4277 (4.2280) grad_norm: 1.1360 (1.1138) time: 0.5008 [2021-03-25 07:30:31 swin_small_patch4_window7_224] INFO: Epoch: [23] [1230/1251] eta: 0:00:10 lr: 0.000984 loss: 4.4606 (4.2282) grad_norm: 1.0862 (1.1141) time: 0.5002 [2021-03-25 07:30:36 swin_small_patch4_window7_224] INFO: Epoch: [23] [1240/1251] eta: 0:00:05 lr: 0.000984 loss: 4.2441 (4.2274) grad_norm: 1.1036 (1.1138) time: 0.5058 [2021-03-25 07:30:41 swin_small_patch4_window7_224] INFO: Epoch: [23] [1250/1251] eta: 0:00:00 lr: 0.000984 loss: 4.1791 (4.2270) grad_norm: 1.0838 (1.1137) time: 0.5073 [2021-03-25 07:30:46 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:29 loss: 1.6209 (1.6209) acc1: 59.3750 (59.3750) acc5: 87.5000 (87.5000) [2021-03-25 07:30:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.7376 (1.6881) acc1: 60.9375 (61.5057) acc5: 84.3750 (84.9432) [2021-03-25 07:30:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.5704 (1.6465) acc1: 65.6250 (62.7976) acc5: 85.9375 (85.7887) [2021-03-25 07:30:53 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.4816 (1.6127) acc1: 65.6250 (62.8528) acc5: 89.0625 (86.1895) [2021-03-25 07:30:55 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.4844 (1.5723) acc1: 65.6250 (63.9863) acc5: 87.5000 (86.6235) [2021-03-25 07:30:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4844 (1.5776) acc1: 65.6250 (64.1920) acc5: 86.7925 (86.4640) [2021-03-25 07:30:57 swin_small_patch4_window7_224] INFO: * Acc@1 64.588 Acc@5 86.840 loss 1.559 [2021-03-25 07:30:57 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 64.6% [2021-03-25 07:30:57 swin_small_patch4_window7_224] INFO: Max accuracy: 64.59% [2021-03-25 07:31:01 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 0/1251] eta: 1:22:11 lr: 0.000984 loss: 4.7585 (4.7585) grad_norm: 1.2906 (1.2906) time: 3.9421 [2021-03-25 07:31:06 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 10/1251] eta: 0:17:39 lr: 0.000984 loss: 4.1186 (4.0480) grad_norm: 1.0182 (1.0449) time: 0.8538 [2021-03-25 07:31:11 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 20/1251] eta: 0:14:12 lr: 0.000984 loss: 4.0865 (4.0941) grad_norm: 1.0379 (1.1113) time: 0.5303 [2021-03-25 07:31:16 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 30/1251] eta: 0:12:49 lr: 0.000984 loss: 4.3862 (4.1808) grad_norm: 1.0753 (1.0817) time: 0.5068 [2021-03-25 07:31:22 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 40/1251] eta: 0:12:11 lr: 0.000984 loss: 4.2739 (4.1843) grad_norm: 1.0239 (1.0749) time: 0.5104 [2021-03-25 07:31:27 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 50/1251] eta: 0:11:40 lr: 0.000984 loss: 4.2491 (4.2008) grad_norm: 1.0334 (1.0724) time: 0.5112 [2021-03-25 07:31:32 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 60/1251] eta: 0:11:19 lr: 0.000984 loss: 4.4157 (4.1650) grad_norm: 1.0334 (1.0649) time: 0.5031 [2021-03-25 07:31:37 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 70/1251] eta: 0:11:04 lr: 0.000984 loss: 4.2877 (4.1632) grad_norm: 1.0436 (1.0911) time: 0.5090 [2021-03-25 07:31:42 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 80/1251] eta: 0:10:50 lr: 0.000984 loss: 4.3506 (4.2103) grad_norm: 1.0466 (1.0827) time: 0.5089 [2021-03-25 07:31:47 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 90/1251] eta: 0:10:37 lr: 0.000984 loss: 4.4917 (4.2242) grad_norm: 0.9763 (1.0757) time: 0.5038 [2021-03-25 07:31:52 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 100/1251] eta: 0:10:27 lr: 0.000984 loss: 4.4917 (4.2414) grad_norm: 0.9879 (1.0726) time: 0.5028 [2021-03-25 07:31:57 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 110/1251] eta: 0:10:17 lr: 0.000984 loss: 4.5295 (4.2703) grad_norm: 1.0443 (1.0737) time: 0.5041 [2021-03-25 07:32:02 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 120/1251] eta: 0:10:08 lr: 0.000984 loss: 4.3975 (4.2492) grad_norm: 1.1075 (1.0808) time: 0.5047 [2021-03-25 07:32:07 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 130/1251] eta: 0:10:00 lr: 0.000984 loss: 4.4091 (4.2601) grad_norm: 0.9924 (1.0736) time: 0.5060 [2021-03-25 07:32:12 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 140/1251] eta: 0:09:52 lr: 0.000984 loss: 4.4363 (4.2391) grad_norm: 0.9951 (1.0786) time: 0.5036 [2021-03-25 07:32:17 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 150/1251] eta: 0:09:45 lr: 0.000984 loss: 4.2416 (4.2450) grad_norm: 1.0951 (1.0797) time: 0.5029 [2021-03-25 07:32:22 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 160/1251] eta: 0:09:38 lr: 0.000984 loss: 4.3147 (4.2399) grad_norm: 1.1194 (1.0853) time: 0.5051 [2021-03-25 07:32:27 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 170/1251] eta: 0:09:31 lr: 0.000984 loss: 4.2946 (4.2483) grad_norm: 1.1319 (1.0892) time: 0.5031 [2021-03-25 07:32:32 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 180/1251] eta: 0:09:25 lr: 0.000984 loss: 4.3172 (4.2514) grad_norm: 1.1274 (1.0882) time: 0.5102 [2021-03-25 07:32:38 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 190/1251] eta: 0:09:19 lr: 0.000984 loss: 4.1975 (4.2487) grad_norm: 1.0602 (1.0872) time: 0.5177 [2021-03-25 07:32:43 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 200/1251] eta: 0:09:12 lr: 0.000984 loss: 3.8139 (4.2258) grad_norm: 1.0777 (1.0902) time: 0.5114 [2021-03-25 07:32:48 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 210/1251] eta: 0:09:06 lr: 0.000984 loss: 3.8632 (4.2141) grad_norm: 1.0869 (1.0890) time: 0.5060 [2021-03-25 07:32:53 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 220/1251] eta: 0:09:00 lr: 0.000984 loss: 4.0082 (4.2124) grad_norm: 1.0592 (1.0889) time: 0.5015 [2021-03-25 07:32:58 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 230/1251] eta: 0:08:54 lr: 0.000984 loss: 4.4254 (4.2291) grad_norm: 1.0957 (1.0903) time: 0.5029 [2021-03-25 07:33:03 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 240/1251] eta: 0:08:48 lr: 0.000984 loss: 4.3793 (4.2315) grad_norm: 1.0671 (1.0894) time: 0.5061 [2021-03-25 07:33:08 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 250/1251] eta: 0:08:41 lr: 0.000984 loss: 4.2978 (4.2315) grad_norm: 1.0111 (1.0867) time: 0.5005 [2021-03-25 07:33:13 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 260/1251] eta: 0:08:35 lr: 0.000984 loss: 4.4241 (4.2268) grad_norm: 1.0525 (1.0894) time: 0.4990 [2021-03-25 07:33:18 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 270/1251] eta: 0:08:30 lr: 0.000984 loss: 4.1599 (4.2253) grad_norm: 1.0414 (1.0866) time: 0.5029 [2021-03-25 07:33:23 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 280/1251] eta: 0:08:24 lr: 0.000984 loss: 4.5069 (4.2341) grad_norm: 1.0151 (1.0856) time: 0.5039 [2021-03-25 07:33:28 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 290/1251] eta: 0:08:18 lr: 0.000984 loss: 4.3838 (4.2317) grad_norm: 1.0678 (1.0888) time: 0.4988 [2021-03-25 07:33:33 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 300/1251] eta: 0:08:12 lr: 0.000984 loss: 4.2689 (4.2342) grad_norm: 1.0872 (1.0901) time: 0.5000 [2021-03-25 07:33:38 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 310/1251] eta: 0:08:07 lr: 0.000984 loss: 4.3089 (4.2341) grad_norm: 1.0872 (1.0915) time: 0.5056 [2021-03-25 07:33:43 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 320/1251] eta: 0:08:01 lr: 0.000984 loss: 4.2543 (4.2315) grad_norm: 1.0418 (1.0887) time: 0.5067 [2021-03-25 07:33:48 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 330/1251] eta: 0:07:56 lr: 0.000984 loss: 4.1221 (4.2273) grad_norm: 1.0114 (1.0897) time: 0.5067 [2021-03-25 07:33:53 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 340/1251] eta: 0:07:50 lr: 0.000984 loss: 4.4384 (4.2297) grad_norm: 1.0748 (1.0894) time: 0.5041 [2021-03-25 07:33:58 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 350/1251] eta: 0:07:45 lr: 0.000984 loss: 4.1956 (4.2297) grad_norm: 1.1238 (1.0909) time: 0.5074 [2021-03-25 07:34:03 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 360/1251] eta: 0:07:39 lr: 0.000984 loss: 4.1956 (4.2325) grad_norm: 1.1238 (1.0920) time: 0.5044 [2021-03-25 07:34:08 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 370/1251] eta: 0:07:34 lr: 0.000984 loss: 4.4141 (4.2313) grad_norm: 1.0806 (1.0917) time: 0.5037 [2021-03-25 07:34:13 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 380/1251] eta: 0:07:28 lr: 0.000984 loss: 4.2443 (4.2246) grad_norm: 1.0104 (1.0907) time: 0.5064 [2021-03-25 07:34:18 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 390/1251] eta: 0:07:23 lr: 0.000984 loss: 3.7188 (4.2188) grad_norm: 1.0941 (1.0930) time: 0.5018 [2021-03-25 07:34:23 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 400/1251] eta: 0:07:18 lr: 0.000984 loss: 4.1944 (4.2231) grad_norm: 1.2181 (1.0951) time: 0.5059 [2021-03-25 07:34:28 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 410/1251] eta: 0:07:12 lr: 0.000984 loss: 4.4507 (4.2270) grad_norm: 1.1484 (1.0969) time: 0.5065 [2021-03-25 07:34:34 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 420/1251] eta: 0:07:07 lr: 0.000984 loss: 4.3368 (4.2283) grad_norm: 1.1484 (1.0971) time: 0.5076 [2021-03-25 07:34:39 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 430/1251] eta: 0:07:02 lr: 0.000984 loss: 4.2910 (4.2229) grad_norm: 1.0160 (1.0945) time: 0.5100 [2021-03-25 07:34:44 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 440/1251] eta: 0:06:57 lr: 0.000984 loss: 4.2739 (4.2236) grad_norm: 0.9808 (1.0933) time: 0.5050 [2021-03-25 07:34:49 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 450/1251] eta: 0:06:51 lr: 0.000984 loss: 4.3105 (4.2224) grad_norm: 1.0555 (1.0921) time: 0.5024 [2021-03-25 07:34:54 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 460/1251] eta: 0:06:46 lr: 0.000984 loss: 4.3105 (4.2284) grad_norm: 1.0555 (1.0904) time: 0.5046 [2021-03-25 07:34:59 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 470/1251] eta: 0:06:41 lr: 0.000984 loss: 4.4329 (4.2283) grad_norm: 1.0647 (1.0910) time: 0.5083 [2021-03-25 07:35:04 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 480/1251] eta: 0:06:35 lr: 0.000984 loss: 4.2294 (4.2266) grad_norm: 1.0922 (1.0915) time: 0.5066 [2021-03-25 07:35:09 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 490/1251] eta: 0:06:30 lr: 0.000984 loss: 3.8618 (4.2202) grad_norm: 1.0336 (1.0901) time: 0.5036 [2021-03-25 07:35:14 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 500/1251] eta: 0:06:25 lr: 0.000984 loss: 3.7877 (4.2134) grad_norm: 1.0336 (1.0909) time: 0.5024 [2021-03-25 07:35:19 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 510/1251] eta: 0:06:20 lr: 0.000984 loss: 3.7310 (4.2059) grad_norm: 1.0653 (1.0920) time: 0.5020 [2021-03-25 07:35:24 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 520/1251] eta: 0:06:14 lr: 0.000984 loss: 3.9400 (4.2065) grad_norm: 1.0635 (1.0913) time: 0.5039 [2021-03-25 07:35:29 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 530/1251] eta: 0:06:09 lr: 0.000984 loss: 4.2135 (4.2060) grad_norm: 1.0602 (1.0906) time: 0.5040 [2021-03-25 07:35:34 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 540/1251] eta: 0:06:04 lr: 0.000984 loss: 4.0746 (4.2002) grad_norm: 1.0394 (1.0906) time: 0.5088 [2021-03-25 07:35:39 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 550/1251] eta: 0:05:59 lr: 0.000984 loss: 3.9150 (4.1952) grad_norm: 1.0544 (1.0911) time: 0.5184 [2021-03-25 07:35:45 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 560/1251] eta: 0:05:54 lr: 0.000984 loss: 4.0607 (4.1946) grad_norm: 1.0993 (1.0912) time: 0.5180 [2021-03-25 07:35:50 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 570/1251] eta: 0:05:49 lr: 0.000984 loss: 4.2450 (4.1959) grad_norm: 1.0734 (1.0904) time: 0.5129 [2021-03-25 07:35:55 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 580/1251] eta: 0:05:44 lr: 0.000984 loss: 4.1813 (4.1922) grad_norm: 1.0048 (1.0883) time: 0.5108 [2021-03-25 07:36:00 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 590/1251] eta: 0:05:39 lr: 0.000984 loss: 4.1636 (4.1936) grad_norm: 1.0031 (1.0884) time: 0.5189 [2021-03-25 07:36:05 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 600/1251] eta: 0:05:33 lr: 0.000984 loss: 4.2957 (4.1944) grad_norm: 1.0186 (1.0882) time: 0.5202 [2021-03-25 07:36:10 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 610/1251] eta: 0:05:28 lr: 0.000984 loss: 4.2077 (4.1909) grad_norm: 1.0186 (1.0871) time: 0.5101 [2021-03-25 07:36:15 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 620/1251] eta: 0:05:23 lr: 0.000984 loss: 4.2287 (4.1926) grad_norm: 1.1143 (1.0899) time: 0.5122 [2021-03-25 07:36:20 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 630/1251] eta: 0:05:18 lr: 0.000984 loss: 4.2535 (4.1957) grad_norm: 1.1486 (1.0906) time: 0.5082 [2021-03-25 07:36:26 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 640/1251] eta: 0:05:13 lr: 0.000984 loss: 4.4361 (4.1995) grad_norm: 1.0805 (1.0921) time: 0.5037 [2021-03-25 07:36:31 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 650/1251] eta: 0:05:08 lr: 0.000984 loss: 4.3682 (4.1968) grad_norm: 1.1066 (1.0918) time: 0.5060 [2021-03-25 07:36:36 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 660/1251] eta: 0:05:02 lr: 0.000984 loss: 4.0091 (4.1925) grad_norm: 1.0423 (1.0911) time: 0.5057 [2021-03-25 07:36:41 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 670/1251] eta: 0:04:57 lr: 0.000984 loss: 4.0801 (4.1925) grad_norm: 1.0330 (1.0912) time: 0.5027 [2021-03-25 07:36:46 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 680/1251] eta: 0:04:52 lr: 0.000984 loss: 4.2935 (4.1914) grad_norm: 1.0501 (1.0919) time: 0.5040 [2021-03-25 07:36:51 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 690/1251] eta: 0:04:47 lr: 0.000984 loss: 4.2014 (4.1916) grad_norm: 1.0502 (1.0917) time: 0.5088 [2021-03-25 07:36:56 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 700/1251] eta: 0:04:42 lr: 0.000984 loss: 4.2366 (4.1919) grad_norm: 1.0951 (1.0928) time: 0.5067 [2021-03-25 07:37:01 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 710/1251] eta: 0:04:36 lr: 0.000984 loss: 4.2366 (4.1916) grad_norm: 1.0952 (1.0920) time: 0.5042 [2021-03-25 07:37:06 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 720/1251] eta: 0:04:31 lr: 0.000984 loss: 4.1047 (4.1893) grad_norm: 0.9825 (1.0911) time: 0.5027 [2021-03-25 07:37:11 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 730/1251] eta: 0:04:26 lr: 0.000984 loss: 4.1047 (4.1907) grad_norm: 1.0378 (1.0911) time: 0.5039 [2021-03-25 07:37:16 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 740/1251] eta: 0:04:21 lr: 0.000984 loss: 4.5741 (4.1923) grad_norm: 1.1731 (1.0932) time: 0.5246 [2021-03-25 07:37:22 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 750/1251] eta: 0:04:16 lr: 0.000984 loss: 4.4524 (4.1958) grad_norm: 1.1389 (1.0938) time: 0.5295 [2021-03-25 07:37:27 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 760/1251] eta: 0:04:11 lr: 0.000984 loss: 4.3996 (4.1969) grad_norm: 1.0558 (1.0933) time: 0.5149 [2021-03-25 07:37:32 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 770/1251] eta: 0:04:06 lr: 0.000984 loss: 4.3129 (4.1998) grad_norm: 1.0241 (1.0929) time: 0.5027 [2021-03-25 07:37:37 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 780/1251] eta: 0:04:01 lr: 0.000984 loss: 4.3484 (4.2008) grad_norm: 1.0168 (1.0928) time: 0.5100 [2021-03-25 07:37:42 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 790/1251] eta: 0:03:56 lr: 0.000984 loss: 4.3648 (4.2058) grad_norm: 0.9867 (1.0910) time: 0.5191 [2021-03-25 07:37:47 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 800/1251] eta: 0:03:50 lr: 0.000984 loss: 4.4933 (4.2092) grad_norm: 0.9849 (1.0908) time: 0.5081 [2021-03-25 07:37:52 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 810/1251] eta: 0:03:45 lr: 0.000984 loss: 4.5430 (4.2105) grad_norm: 1.0057 (1.0900) time: 0.5079 [2021-03-25 07:37:57 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 820/1251] eta: 0:03:40 lr: 0.000984 loss: 4.1891 (4.2103) grad_norm: 1.0265 (1.0899) time: 0.5068 [2021-03-25 07:38:02 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 830/1251] eta: 0:03:35 lr: 0.000984 loss: 4.1845 (4.2095) grad_norm: 1.0850 (1.0903) time: 0.5037 [2021-03-25 07:38:07 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 840/1251] eta: 0:03:30 lr: 0.000984 loss: 4.3173 (4.2121) grad_norm: 1.0831 (1.0902) time: 0.5015 [2021-03-25 07:38:12 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 850/1251] eta: 0:03:25 lr: 0.000984 loss: 4.4362 (4.2149) grad_norm: 1.0050 (1.0892) time: 0.5008 [2021-03-25 07:38:17 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 860/1251] eta: 0:03:19 lr: 0.000984 loss: 4.4362 (4.2157) grad_norm: 1.0025 (1.0883) time: 0.5004 [2021-03-25 07:38:22 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 870/1251] eta: 0:03:14 lr: 0.000984 loss: 4.2214 (4.2141) grad_norm: 1.0113 (1.0878) time: 0.5059 [2021-03-25 07:38:27 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 880/1251] eta: 0:03:09 lr: 0.000984 loss: 4.2903 (4.2135) grad_norm: 1.0744 (1.0888) time: 0.5078 [2021-03-25 07:38:33 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 890/1251] eta: 0:03:04 lr: 0.000984 loss: 4.3323 (4.2147) grad_norm: 1.1348 (1.0891) time: 0.5081 [2021-03-25 07:38:38 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 900/1251] eta: 0:02:59 lr: 0.000984 loss: 4.1710 (4.2131) grad_norm: 1.0763 (1.0896) time: 0.5078 [2021-03-25 07:38:43 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 910/1251] eta: 0:02:54 lr: 0.000983 loss: 4.3479 (4.2164) grad_norm: 1.1046 (1.0900) time: 0.5035 [2021-03-25 07:38:48 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 920/1251] eta: 0:02:49 lr: 0.000983 loss: 4.3481 (4.2119) grad_norm: 1.0994 (1.0908) time: 0.5096 [2021-03-25 07:38:53 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 930/1251] eta: 0:02:44 lr: 0.000983 loss: 4.1727 (4.2089) grad_norm: 1.1684 (1.0924) time: 0.5153 [2021-03-25 07:38:58 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 940/1251] eta: 0:02:39 lr: 0.000983 loss: 4.2795 (4.2092) grad_norm: 1.1684 (1.0930) time: 0.5166 [2021-03-25 07:39:03 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 950/1251] eta: 0:02:33 lr: 0.000983 loss: 4.1100 (4.2072) grad_norm: 1.1355 (1.0935) time: 0.5177 [2021-03-25 07:39:08 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 960/1251] eta: 0:02:28 lr: 0.000983 loss: 4.0973 (4.2070) grad_norm: 1.1355 (1.0937) time: 0.5077 [2021-03-25 07:39:13 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 970/1251] eta: 0:02:23 lr: 0.000983 loss: 4.0973 (4.2055) grad_norm: 1.0614 (1.0935) time: 0.5057 [2021-03-25 07:39:18 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 980/1251] eta: 0:02:18 lr: 0.000983 loss: 4.1110 (4.2055) grad_norm: 1.1009 (1.0937) time: 0.5106 [2021-03-25 07:39:24 swin_small_patch4_window7_224] INFO: Epoch: [24] [ 990/1251] eta: 0:02:13 lr: 0.000983 loss: 4.2886 (4.2065) grad_norm: 1.1009 (1.0936) time: 0.5054 [2021-03-25 07:39:29 swin_small_patch4_window7_224] INFO: Epoch: [24] [1000/1251] eta: 0:02:08 lr: 0.000983 loss: 4.2886 (4.2046) grad_norm: 1.0029 (1.0930) time: 0.5045 [2021-03-25 07:39:34 swin_small_patch4_window7_224] INFO: Epoch: [24] [1010/1251] eta: 0:02:03 lr: 0.000983 loss: 4.1463 (4.2051) grad_norm: 1.0027 (1.0923) time: 0.5052 [2021-03-25 07:39:39 swin_small_patch4_window7_224] INFO: Epoch: [24] [1020/1251] eta: 0:01:58 lr: 0.000983 loss: 4.3823 (4.2075) grad_norm: 1.0642 (1.0922) time: 0.5047 [2021-03-25 07:39:44 swin_small_patch4_window7_224] INFO: Epoch: [24] [1030/1251] eta: 0:01:52 lr: 0.000983 loss: 4.5617 (4.2094) grad_norm: 1.0552 (1.0920) time: 0.5046 [2021-03-25 07:39:49 swin_small_patch4_window7_224] INFO: Epoch: [24] [1040/1251] eta: 0:01:47 lr: 0.000983 loss: 4.4809 (4.2105) grad_norm: 1.0670 (1.0924) time: 0.5019 [2021-03-25 07:39:54 swin_small_patch4_window7_224] INFO: Epoch: [24] [1050/1251] eta: 0:01:42 lr: 0.000983 loss: 4.3421 (4.2101) grad_norm: 1.1354 (1.0926) time: 0.5034 [2021-03-25 07:39:59 swin_small_patch4_window7_224] INFO: Epoch: [24] [1060/1251] eta: 0:01:37 lr: 0.000983 loss: 4.3558 (4.2124) grad_norm: 1.0859 (1.0926) time: 0.5092 [2021-03-25 07:40:04 swin_small_patch4_window7_224] INFO: Epoch: [24] [1070/1251] eta: 0:01:32 lr: 0.000983 loss: 4.3558 (4.2144) grad_norm: 1.0739 (1.0923) time: 0.5078 [2021-03-25 07:40:09 swin_small_patch4_window7_224] INFO: Epoch: [24] [1080/1251] eta: 0:01:27 lr: 0.000983 loss: 4.3979 (4.2154) grad_norm: 1.0293 (1.0918) time: 0.5029 [2021-03-25 07:40:14 swin_small_patch4_window7_224] INFO: Epoch: [24] [1090/1251] eta: 0:01:22 lr: 0.000983 loss: 4.3979 (4.2165) grad_norm: 1.0352 (1.0919) time: 0.5057 [2021-03-25 07:40:19 swin_small_patch4_window7_224] INFO: Epoch: [24] [1100/1251] eta: 0:01:17 lr: 0.000983 loss: 4.3792 (4.2167) grad_norm: 1.0352 (1.0920) time: 0.5093 [2021-03-25 07:40:24 swin_small_patch4_window7_224] INFO: Epoch: [24] [1110/1251] eta: 0:01:11 lr: 0.000983 loss: 4.4835 (4.2202) grad_norm: 1.0688 (1.0922) time: 0.5024 [2021-03-25 07:40:29 swin_small_patch4_window7_224] INFO: Epoch: [24] [1120/1251] eta: 0:01:06 lr: 0.000983 loss: 4.6065 (4.2221) grad_norm: 1.0436 (1.0919) time: 0.5006 [2021-03-25 07:40:34 swin_small_patch4_window7_224] INFO: Epoch: [24] [1130/1251] eta: 0:01:01 lr: 0.000983 loss: 4.4906 (4.2222) grad_norm: 1.0436 (1.0916) time: 0.4989 [2021-03-25 07:40:39 swin_small_patch4_window7_224] INFO: Epoch: [24] [1140/1251] eta: 0:00:56 lr: 0.000983 loss: 4.2103 (4.2213) grad_norm: 1.0447 (1.0915) time: 0.4987 [2021-03-25 07:40:44 swin_small_patch4_window7_224] INFO: Epoch: [24] [1150/1251] eta: 0:00:51 lr: 0.000983 loss: 4.2103 (4.2217) grad_norm: 1.0129 (1.0916) time: 0.5078 [2021-03-25 07:40:49 swin_small_patch4_window7_224] INFO: Epoch: [24] [1160/1251] eta: 0:00:46 lr: 0.000983 loss: 4.1925 (4.2193) grad_norm: 0.9523 (1.0905) time: 0.5095 [2021-03-25 07:40:54 swin_small_patch4_window7_224] INFO: Epoch: [24] [1170/1251] eta: 0:00:41 lr: 0.000983 loss: 4.0886 (4.2176) grad_norm: 0.9500 (1.0906) time: 0.5054 [2021-03-25 07:40:59 swin_small_patch4_window7_224] INFO: Epoch: [24] [1180/1251] eta: 0:00:36 lr: 0.000983 loss: 4.1154 (4.2151) grad_norm: 1.0606 (1.0904) time: 0.5037 [2021-03-25 07:41:05 swin_small_patch4_window7_224] INFO: Epoch: [24] [1190/1251] eta: 0:00:31 lr: 0.000983 loss: 4.1154 (4.2142) grad_norm: 1.0596 (1.0901) time: 0.5074 [2021-03-25 07:41:10 swin_small_patch4_window7_224] INFO: Epoch: [24] [1200/1251] eta: 0:00:26 lr: 0.000983 loss: 4.0417 (4.2125) grad_norm: 1.0992 (1.0908) time: 0.5088 [2021-03-25 07:41:15 swin_small_patch4_window7_224] INFO: Epoch: [24] [1210/1251] eta: 0:00:20 lr: 0.000983 loss: 4.2810 (4.2131) grad_norm: 1.0711 (1.0905) time: 0.5056 [2021-03-25 07:41:20 swin_small_patch4_window7_224] INFO: Epoch: [24] [1220/1251] eta: 0:00:15 lr: 0.000983 loss: 4.4431 (4.2133) grad_norm: 1.0276 (1.0897) time: 0.5020 [2021-03-25 07:41:25 swin_small_patch4_window7_224] INFO: Epoch: [24] [1230/1251] eta: 0:00:10 lr: 0.000983 loss: 4.3259 (4.2135) grad_norm: 0.9964 (1.0891) time: 0.5031 [2021-03-25 07:41:30 swin_small_patch4_window7_224] INFO: Epoch: [24] [1240/1251] eta: 0:00:05 lr: 0.000983 loss: 4.4250 (4.2148) grad_norm: 0.9779 (1.0883) time: 0.5084 [2021-03-25 07:41:35 swin_small_patch4_window7_224] INFO: Epoch: [24] [1250/1251] eta: 0:00:00 lr: 0.000983 loss: 4.2366 (4.2134) grad_norm: 0.9994 (1.0880) time: 0.4999 [2021-03-25 07:41:40 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:47 loss: 1.8152 (1.8152) acc1: 59.3750 (59.3750) acc5: 82.8125 (82.8125) [2021-03-25 07:41:42 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.5722 (1.5488) acc1: 62.5000 (62.9261) acc5: 85.9375 (86.6477) [2021-03-25 07:41:44 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.5618 (1.5606) acc1: 64.0625 (64.3601) acc5: 85.9375 (86.2351) [2021-03-25 07:41:46 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.4742 (1.5382) acc1: 67.1875 (64.8690) acc5: 85.9375 (86.6935) [2021-03-25 07:41:48 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.4237 (1.5133) acc1: 64.0625 (64.5579) acc5: 87.5000 (87.1189) [2021-03-25 07:41:49 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4237 (1.5132) acc1: 64.0625 (64.7680) acc5: 87.5000 (86.9120) [2021-03-25 07:41:50 swin_small_patch4_window7_224] INFO: * Acc@1 65.230 Acc@5 87.296 loss 1.493 [2021-03-25 07:41:50 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 65.2% [2021-03-25 07:41:50 swin_small_patch4_window7_224] INFO: Max accuracy: 65.23% [2021-03-25 07:41:55 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 0/1251] eta: 1:25:07 lr: 0.000983 loss: 5.1421 (5.1421) grad_norm: 1.2374 (1.2374) time: 4.0830 [2021-03-25 07:42:00 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 10/1251] eta: 0:17:51 lr: 0.000983 loss: 4.5475 (4.4745) grad_norm: 1.1063 (1.0965) time: 0.8637 [2021-03-25 07:42:05 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 20/1251] eta: 0:14:16 lr: 0.000983 loss: 4.1664 (4.2424) grad_norm: 1.0949 (1.0941) time: 0.5264 [2021-03-25 07:42:10 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 30/1251] eta: 0:12:53 lr: 0.000983 loss: 3.8810 (4.1192) grad_norm: 1.1261 (1.1050) time: 0.5070 [2021-03-25 07:42:15 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 40/1251] eta: 0:12:12 lr: 0.000983 loss: 3.9503 (4.1352) grad_norm: 1.1261 (1.1147) time: 0.5099 [2021-03-25 07:42:20 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 50/1251] eta: 0:11:45 lr: 0.000983 loss: 3.9503 (4.0523) grad_norm: 1.0897 (1.0947) time: 0.5169 [2021-03-25 07:42:25 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 60/1251] eta: 0:11:23 lr: 0.000983 loss: 4.2279 (4.1356) grad_norm: 1.0248 (1.0939) time: 0.5107 [2021-03-25 07:42:31 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 70/1251] eta: 0:11:06 lr: 0.000983 loss: 4.3969 (4.1448) grad_norm: 1.0320 (1.0917) time: 0.5049 [2021-03-25 07:42:36 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 80/1251] eta: 0:10:52 lr: 0.000983 loss: 4.3565 (4.1535) grad_norm: 1.0320 (1.0856) time: 0.5061 [2021-03-25 07:42:41 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 90/1251] eta: 0:10:40 lr: 0.000983 loss: 4.4031 (4.1744) grad_norm: 1.0313 (1.0886) time: 0.5082 [2021-03-25 07:42:46 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 100/1251] eta: 0:10:30 lr: 0.000983 loss: 4.2479 (4.1753) grad_norm: 1.0313 (1.0823) time: 0.5094 [2021-03-25 07:42:51 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 110/1251] eta: 0:10:22 lr: 0.000983 loss: 4.2094 (4.1682) grad_norm: 1.0924 (1.0924) time: 0.5145 [2021-03-25 07:42:56 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 120/1251] eta: 0:10:12 lr: 0.000983 loss: 4.1083 (4.1702) grad_norm: 1.1400 (1.0954) time: 0.5120 [2021-03-25 07:43:01 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 130/1251] eta: 0:10:05 lr: 0.000983 loss: 4.1152 (4.1521) grad_norm: 1.1324 (1.0989) time: 0.5099 [2021-03-25 07:43:06 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 140/1251] eta: 0:09:57 lr: 0.000983 loss: 4.1152 (4.1463) grad_norm: 1.0364 (1.0949) time: 0.5118 [2021-03-25 07:43:11 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 150/1251] eta: 0:09:49 lr: 0.000983 loss: 4.2208 (4.1628) grad_norm: 0.9770 (1.0941) time: 0.5047 [2021-03-25 07:43:16 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 160/1251] eta: 0:09:42 lr: 0.000983 loss: 4.5291 (4.1720) grad_norm: 1.1051 (1.0932) time: 0.5062 [2021-03-25 07:43:22 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 170/1251] eta: 0:09:35 lr: 0.000983 loss: 4.2219 (4.1622) grad_norm: 1.0212 (1.0917) time: 0.5111 [2021-03-25 07:43:27 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 180/1251] eta: 0:09:28 lr: 0.000983 loss: 4.2042 (4.1579) grad_norm: 1.0032 (1.0893) time: 0.5114 [2021-03-25 07:43:32 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 190/1251] eta: 0:09:22 lr: 0.000983 loss: 4.2508 (4.1699) grad_norm: 1.0599 (1.0906) time: 0.5089 [2021-03-25 07:43:37 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 200/1251] eta: 0:09:16 lr: 0.000983 loss: 4.4150 (4.1807) grad_norm: 0.9777 (1.0851) time: 0.5160 [2021-03-25 07:43:42 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 210/1251] eta: 0:09:10 lr: 0.000983 loss: 4.3118 (4.1760) grad_norm: 1.0485 (1.0873) time: 0.5164 [2021-03-25 07:43:47 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 220/1251] eta: 0:09:03 lr: 0.000983 loss: 4.2934 (4.1754) grad_norm: 1.1645 (1.0896) time: 0.5053 [2021-03-25 07:43:52 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 230/1251] eta: 0:08:57 lr: 0.000983 loss: 4.3646 (4.1809) grad_norm: 1.1178 (1.0904) time: 0.5012 [2021-03-25 07:43:57 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 240/1251] eta: 0:08:51 lr: 0.000983 loss: 4.4351 (4.1844) grad_norm: 1.0897 (1.0911) time: 0.5032 [2021-03-25 07:44:02 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 250/1251] eta: 0:08:45 lr: 0.000983 loss: 4.3608 (4.1897) grad_norm: 1.0072 (1.0886) time: 0.5072 [2021-03-25 07:44:07 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 260/1251] eta: 0:08:39 lr: 0.000983 loss: 4.2301 (4.1855) grad_norm: 1.0323 (1.0893) time: 0.5050 [2021-03-25 07:44:12 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 270/1251] eta: 0:08:33 lr: 0.000983 loss: 3.8432 (4.1672) grad_norm: 1.1021 (1.0909) time: 0.5039 [2021-03-25 07:44:17 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 280/1251] eta: 0:08:27 lr: 0.000983 loss: 3.4846 (4.1595) grad_norm: 1.0805 (1.0901) time: 0.5029 [2021-03-25 07:44:22 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 290/1251] eta: 0:08:21 lr: 0.000983 loss: 4.1661 (4.1568) grad_norm: 1.1317 (1.0935) time: 0.5007 [2021-03-25 07:44:27 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 300/1251] eta: 0:08:15 lr: 0.000983 loss: 4.3480 (4.1636) grad_norm: 1.1347 (1.0947) time: 0.5053 [2021-03-25 07:44:32 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 310/1251] eta: 0:08:09 lr: 0.000983 loss: 4.3717 (4.1656) grad_norm: 1.1058 (1.0952) time: 0.5045 [2021-03-25 07:44:37 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 320/1251] eta: 0:08:04 lr: 0.000983 loss: 4.3717 (4.1710) grad_norm: 1.1382 (1.0968) time: 0.5019 [2021-03-25 07:44:43 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 330/1251] eta: 0:07:58 lr: 0.000983 loss: 4.2706 (4.1669) grad_norm: 1.1382 (1.0961) time: 0.5075 [2021-03-25 07:44:48 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 340/1251] eta: 0:07:52 lr: 0.000983 loss: 4.1756 (4.1667) grad_norm: 1.0269 (1.0943) time: 0.5034 [2021-03-25 07:44:53 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 350/1251] eta: 0:07:47 lr: 0.000983 loss: 4.1756 (4.1650) grad_norm: 1.0269 (1.0968) time: 0.5036 [2021-03-25 07:44:58 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 360/1251] eta: 0:07:41 lr: 0.000983 loss: 4.1020 (4.1594) grad_norm: 1.1667 (1.0979) time: 0.5048 [2021-03-25 07:45:03 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 370/1251] eta: 0:07:36 lr: 0.000983 loss: 4.1020 (4.1562) grad_norm: 1.0180 (1.0953) time: 0.5030 [2021-03-25 07:45:08 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 380/1251] eta: 0:07:31 lr: 0.000983 loss: 4.2060 (4.1590) grad_norm: 1.0581 (1.0948) time: 0.5103 [2021-03-25 07:45:13 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 390/1251] eta: 0:07:25 lr: 0.000983 loss: 4.3199 (4.1614) grad_norm: 1.1236 (1.0974) time: 0.5071 [2021-03-25 07:45:18 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 400/1251] eta: 0:07:19 lr: 0.000983 loss: 4.3199 (4.1671) grad_norm: 1.1818 (1.0993) time: 0.4984 [2021-03-25 07:45:23 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 410/1251] eta: 0:07:14 lr: 0.000983 loss: 4.3457 (4.1661) grad_norm: 1.1955 (1.1014) time: 0.5015 [2021-03-25 07:45:28 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 420/1251] eta: 0:07:09 lr: 0.000983 loss: 3.8706 (4.1615) grad_norm: 1.1091 (1.1012) time: 0.5032 [2021-03-25 07:45:33 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 430/1251] eta: 0:07:03 lr: 0.000983 loss: 4.3890 (4.1672) grad_norm: 1.0473 (1.0996) time: 0.5019 [2021-03-25 07:45:38 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 440/1251] eta: 0:06:58 lr: 0.000983 loss: 4.4111 (4.1708) grad_norm: 1.0974 (1.1030) time: 0.5015 [2021-03-25 07:45:43 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 450/1251] eta: 0:06:52 lr: 0.000983 loss: 4.2483 (4.1713) grad_norm: 1.1258 (1.1027) time: 0.5030 [2021-03-25 07:45:48 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 460/1251] eta: 0:06:47 lr: 0.000983 loss: 4.0499 (4.1622) grad_norm: 0.9993 (1.1014) time: 0.5063 [2021-03-25 07:45:53 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 470/1251] eta: 0:06:42 lr: 0.000983 loss: 4.0380 (4.1634) grad_norm: 1.0305 (1.1012) time: 0.5084 [2021-03-25 07:45:58 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 480/1251] eta: 0:06:36 lr: 0.000983 loss: 4.1961 (4.1662) grad_norm: 1.1339 (1.1029) time: 0.5074 [2021-03-25 07:46:03 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 490/1251] eta: 0:06:31 lr: 0.000983 loss: 4.3755 (4.1711) grad_norm: 1.1614 (1.1058) time: 0.5044 [2021-03-25 07:46:08 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 500/1251] eta: 0:06:26 lr: 0.000983 loss: 4.3755 (4.1746) grad_norm: 1.1334 (1.1048) time: 0.5060 [2021-03-25 07:46:13 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 510/1251] eta: 0:06:21 lr: 0.000983 loss: 4.3919 (4.1775) grad_norm: 0.9733 (1.1024) time: 0.5034 [2021-03-25 07:46:18 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 520/1251] eta: 0:06:15 lr: 0.000983 loss: 4.4811 (4.1829) grad_norm: 1.0129 (inf) time: 0.5030 [2021-03-25 07:46:23 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 530/1251] eta: 0:06:10 lr: 0.000983 loss: 4.3512 (4.1817) grad_norm: 1.0129 (inf) time: 0.5042 [2021-03-25 07:46:29 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 540/1251] eta: 0:06:05 lr: 0.000983 loss: 4.1304 (4.1815) grad_norm: 0.9783 (inf) time: 0.5107 [2021-03-25 07:46:34 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 550/1251] eta: 0:06:00 lr: 0.000983 loss: 4.1189 (4.1798) grad_norm: 1.0130 (inf) time: 0.5272 [2021-03-25 07:46:39 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 560/1251] eta: 0:05:55 lr: 0.000983 loss: 4.1101 (4.1783) grad_norm: 1.0254 (inf) time: 0.5212 [2021-03-25 07:46:44 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 570/1251] eta: 0:05:50 lr: 0.000983 loss: 4.2143 (4.1781) grad_norm: 1.0680 (inf) time: 0.5074 [2021-03-25 07:46:49 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 580/1251] eta: 0:05:44 lr: 0.000983 loss: 4.0608 (4.1734) grad_norm: 1.1197 (inf) time: 0.5035 [2021-03-25 07:46:54 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 590/1251] eta: 0:05:39 lr: 0.000982 loss: 4.1602 (4.1739) grad_norm: 1.1347 (inf) time: 0.5062 [2021-03-25 07:46:59 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 600/1251] eta: 0:05:34 lr: 0.000982 loss: 4.3402 (4.1755) grad_norm: 1.1595 (inf) time: 0.5139 [2021-03-25 07:47:04 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 610/1251] eta: 0:05:29 lr: 0.000982 loss: 4.2324 (4.1731) grad_norm: 1.0653 (inf) time: 0.5060 [2021-03-25 07:47:09 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 620/1251] eta: 0:05:23 lr: 0.000982 loss: 4.0040 (4.1706) grad_norm: 1.0598 (inf) time: 0.4993 [2021-03-25 07:47:14 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 630/1251] eta: 0:05:18 lr: 0.000982 loss: 4.0200 (4.1710) grad_norm: 1.0699 (inf) time: 0.4997 [2021-03-25 07:47:19 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 640/1251] eta: 0:05:13 lr: 0.000982 loss: 4.3307 (4.1721) grad_norm: 1.0528 (inf) time: 0.5019 [2021-03-25 07:47:24 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 650/1251] eta: 0:05:08 lr: 0.000982 loss: 4.3996 (4.1748) grad_norm: 1.0460 (inf) time: 0.5026 [2021-03-25 07:47:30 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 660/1251] eta: 0:05:03 lr: 0.000982 loss: 4.2176 (4.1753) grad_norm: 1.0460 (inf) time: 0.5051 [2021-03-25 07:47:35 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 670/1251] eta: 0:04:57 lr: 0.000982 loss: 4.2157 (4.1750) grad_norm: 1.1123 (inf) time: 0.5074 [2021-03-25 07:47:40 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 680/1251] eta: 0:04:52 lr: 0.000982 loss: 4.3107 (4.1775) grad_norm: 0.9893 (inf) time: 0.5075 [2021-03-25 07:47:45 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 690/1251] eta: 0:04:47 lr: 0.000982 loss: 4.1138 (4.1729) grad_norm: 0.9497 (inf) time: 0.5035 [2021-03-25 07:47:50 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 700/1251] eta: 0:04:42 lr: 0.000982 loss: 4.1138 (4.1722) grad_norm: 0.9878 (inf) time: 0.5046 [2021-03-25 07:47:55 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 710/1251] eta: 0:04:37 lr: 0.000982 loss: 4.0414 (4.1677) grad_norm: 1.0827 (inf) time: 0.5113 [2021-03-25 07:48:00 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 720/1251] eta: 0:04:32 lr: 0.000982 loss: 3.9644 (4.1677) grad_norm: 1.1064 (inf) time: 0.5093 [2021-03-25 07:48:05 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 730/1251] eta: 0:04:26 lr: 0.000982 loss: 4.2182 (4.1668) grad_norm: 1.1064 (inf) time: 0.5133 [2021-03-25 07:48:10 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 740/1251] eta: 0:04:21 lr: 0.000982 loss: 3.9719 (4.1644) grad_norm: 1.1004 (inf) time: 0.5271 [2021-03-25 07:48:16 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 750/1251] eta: 0:04:16 lr: 0.000982 loss: 3.9719 (4.1640) grad_norm: 1.0564 (inf) time: 0.5315 [2021-03-25 07:48:21 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 760/1251] eta: 0:04:11 lr: 0.000982 loss: 3.9358 (4.1631) grad_norm: 1.1224 (inf) time: 0.5181 [2021-03-25 07:48:26 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 770/1251] eta: 0:04:06 lr: 0.000982 loss: 3.9432 (4.1607) grad_norm: 1.1359 (inf) time: 0.5108 [2021-03-25 07:48:31 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 780/1251] eta: 0:04:01 lr: 0.000982 loss: 4.0293 (4.1589) grad_norm: 1.0668 (inf) time: 0.5069 [2021-03-25 07:48:36 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 790/1251] eta: 0:03:56 lr: 0.000982 loss: 4.0996 (4.1604) grad_norm: 1.0668 (inf) time: 0.5085 [2021-03-25 07:48:41 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 800/1251] eta: 0:03:51 lr: 0.000982 loss: 4.3073 (4.1609) grad_norm: 1.0864 (inf) time: 0.5095 [2021-03-25 07:48:46 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 810/1251] eta: 0:03:46 lr: 0.000982 loss: 4.3567 (4.1611) grad_norm: 1.1154 (inf) time: 0.5040 [2021-03-25 07:48:51 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 820/1251] eta: 0:03:40 lr: 0.000982 loss: 4.3938 (4.1605) grad_norm: 1.0026 (inf) time: 0.5043 [2021-03-25 07:48:56 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 830/1251] eta: 0:03:35 lr: 0.000982 loss: 4.3385 (4.1622) grad_norm: 1.0026 (inf) time: 0.5077 [2021-03-25 07:49:01 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 840/1251] eta: 0:03:30 lr: 0.000982 loss: 4.2167 (4.1633) grad_norm: 1.0753 (inf) time: 0.5058 [2021-03-25 07:49:07 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 850/1251] eta: 0:03:25 lr: 0.000982 loss: 4.2956 (4.1649) grad_norm: 1.0769 (inf) time: 0.5080 [2021-03-25 07:49:12 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 860/1251] eta: 0:03:20 lr: 0.000982 loss: 4.2586 (4.1633) grad_norm: 1.0017 (inf) time: 0.5067 [2021-03-25 07:49:17 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 870/1251] eta: 0:03:15 lr: 0.000982 loss: 4.2223 (4.1642) grad_norm: 0.9702 (inf) time: 0.5024 [2021-03-25 07:49:22 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 880/1251] eta: 0:03:09 lr: 0.000982 loss: 4.5276 (4.1672) grad_norm: 0.9702 (inf) time: 0.5115 [2021-03-25 07:49:27 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 890/1251] eta: 0:03:04 lr: 0.000982 loss: 4.4473 (4.1685) grad_norm: 1.0206 (inf) time: 0.5108 [2021-03-25 07:49:32 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 900/1251] eta: 0:02:59 lr: 0.000982 loss: 4.2499 (4.1695) grad_norm: 1.0460 (inf) time: 0.5074 [2021-03-25 07:49:37 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 910/1251] eta: 0:02:54 lr: 0.000982 loss: 4.2499 (4.1704) grad_norm: 1.0255 (inf) time: 0.5016 [2021-03-25 07:49:42 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 920/1251] eta: 0:02:49 lr: 0.000982 loss: 4.4197 (4.1705) grad_norm: 1.0678 (inf) time: 0.4977 [2021-03-25 07:49:47 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 930/1251] eta: 0:02:44 lr: 0.000982 loss: 4.4197 (4.1707) grad_norm: 1.1225 (inf) time: 0.5022 [2021-03-25 07:49:52 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 940/1251] eta: 0:02:39 lr: 0.000982 loss: 4.2924 (4.1729) grad_norm: 1.1617 (inf) time: 0.5132 [2021-03-25 07:49:57 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 950/1251] eta: 0:02:34 lr: 0.000982 loss: 4.2765 (4.1727) grad_norm: 1.0951 (inf) time: 0.5129 [2021-03-25 07:50:02 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 960/1251] eta: 0:02:28 lr: 0.000982 loss: 4.2765 (4.1724) grad_norm: 1.1242 (inf) time: 0.5043 [2021-03-25 07:50:07 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 970/1251] eta: 0:02:23 lr: 0.000982 loss: 4.4247 (4.1747) grad_norm: 1.1527 (inf) time: 0.5105 [2021-03-25 07:50:12 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 980/1251] eta: 0:02:18 lr: 0.000982 loss: 4.2241 (4.1740) grad_norm: 1.1307 (inf) time: 0.5131 [2021-03-25 07:50:18 swin_small_patch4_window7_224] INFO: Epoch: [25] [ 990/1251] eta: 0:02:13 lr: 0.000982 loss: 4.2241 (4.1745) grad_norm: 1.1307 (inf) time: 0.5110 [2021-03-25 07:50:23 swin_small_patch4_window7_224] INFO: Epoch: [25] [1000/1251] eta: 0:02:08 lr: 0.000982 loss: 4.2786 (4.1746) grad_norm: 1.1782 (inf) time: 0.5070 [2021-03-25 07:50:28 swin_small_patch4_window7_224] INFO: Epoch: [25] [1010/1251] eta: 0:02:03 lr: 0.000982 loss: 4.5719 (4.1740) grad_norm: 1.0726 (inf) time: 0.4984 [2021-03-25 07:50:33 swin_small_patch4_window7_224] INFO: Epoch: [25] [1020/1251] eta: 0:01:58 lr: 0.000982 loss: 4.2520 (4.1734) grad_norm: 0.9903 (inf) time: 0.5017 [2021-03-25 07:50:38 swin_small_patch4_window7_224] INFO: Epoch: [25] [1030/1251] eta: 0:01:52 lr: 0.000982 loss: 4.2520 (4.1749) grad_norm: 1.0325 (inf) time: 0.5089 [2021-03-25 07:50:43 swin_small_patch4_window7_224] INFO: Epoch: [25] [1040/1251] eta: 0:01:47 lr: 0.000982 loss: 4.4038 (4.1770) grad_norm: 1.0666 (nan) time: 0.5114 [2021-03-25 07:50:48 swin_small_patch4_window7_224] INFO: Epoch: [25] [1050/1251] eta: 0:01:42 lr: 0.000982 loss: 4.3241 (4.1768) grad_norm: 1.0425 (nan) time: 0.5104 [2021-03-25 07:50:53 swin_small_patch4_window7_224] INFO: Epoch: [25] [1060/1251] eta: 0:01:37 lr: 0.000982 loss: 4.3934 (4.1791) grad_norm: 1.0208 (nan) time: 0.5039 [2021-03-25 07:50:58 swin_small_patch4_window7_224] INFO: Epoch: [25] [1070/1251] eta: 0:01:32 lr: 0.000982 loss: 4.4394 (4.1806) grad_norm: 1.0152 (nan) time: 0.5098 [2021-03-25 07:51:03 swin_small_patch4_window7_224] INFO: Epoch: [25] [1080/1251] eta: 0:01:27 lr: 0.000982 loss: 4.2982 (4.1805) grad_norm: 0.9894 (nan) time: 0.5111 [2021-03-25 07:51:08 swin_small_patch4_window7_224] INFO: Epoch: [25] [1090/1251] eta: 0:01:22 lr: 0.000982 loss: 3.9993 (4.1776) grad_norm: 0.9696 (nan) time: 0.5044 [2021-03-25 07:51:13 swin_small_patch4_window7_224] INFO: Epoch: [25] [1100/1251] eta: 0:01:17 lr: 0.000982 loss: 3.7484 (4.1761) grad_norm: 1.0338 (nan) time: 0.5049 [2021-03-25 07:51:18 swin_small_patch4_window7_224] INFO: Epoch: [25] [1110/1251] eta: 0:01:12 lr: 0.000982 loss: 4.2193 (4.1761) grad_norm: 1.0999 (nan) time: 0.5051 [2021-03-25 07:51:23 swin_small_patch4_window7_224] INFO: Epoch: [25] [1120/1251] eta: 0:01:06 lr: 0.000982 loss: 4.2978 (4.1766) grad_norm: 1.0999 (nan) time: 0.5042 [2021-03-25 07:51:28 swin_small_patch4_window7_224] INFO: Epoch: [25] [1130/1251] eta: 0:01:01 lr: 0.000982 loss: 4.3341 (4.1764) grad_norm: 1.1008 (nan) time: 0.5029 [2021-03-25 07:51:33 swin_small_patch4_window7_224] INFO: Epoch: [25] [1140/1251] eta: 0:00:56 lr: 0.000982 loss: 4.2920 (4.1758) grad_norm: 1.1008 (nan) time: 0.5042 [2021-03-25 07:51:39 swin_small_patch4_window7_224] INFO: Epoch: [25] [1150/1251] eta: 0:00:51 lr: 0.000982 loss: 4.3070 (4.1769) grad_norm: 1.0520 (nan) time: 0.5064 [2021-03-25 07:51:44 swin_small_patch4_window7_224] INFO: Epoch: [25] [1160/1251] eta: 0:00:46 lr: 0.000982 loss: 4.4325 (4.1761) grad_norm: 1.0138 (nan) time: 0.5060 [2021-03-25 07:51:49 swin_small_patch4_window7_224] INFO: Epoch: [25] [1170/1251] eta: 0:00:41 lr: 0.000982 loss: 4.4103 (4.1784) grad_norm: 0.9917 (nan) time: 0.5069 [2021-03-25 07:51:54 swin_small_patch4_window7_224] INFO: Epoch: [25] [1180/1251] eta: 0:00:36 lr: 0.000982 loss: 3.9944 (4.1748) grad_norm: 0.9993 (nan) time: 0.5051 [2021-03-25 07:51:59 swin_small_patch4_window7_224] INFO: Epoch: [25] [1190/1251] eta: 0:00:31 lr: 0.000982 loss: 3.9611 (4.1758) grad_norm: 0.9926 (nan) time: 0.5072 [2021-03-25 07:52:04 swin_small_patch4_window7_224] INFO: Epoch: [25] [1200/1251] eta: 0:00:26 lr: 0.000982 loss: 4.3190 (4.1761) grad_norm: 0.9847 (nan) time: 0.5094 [2021-03-25 07:52:09 swin_small_patch4_window7_224] INFO: Epoch: [25] [1210/1251] eta: 0:00:20 lr: 0.000982 loss: 4.3037 (4.1747) grad_norm: 0.9902 (nan) time: 0.5005 [2021-03-25 07:52:14 swin_small_patch4_window7_224] INFO: Epoch: [25] [1220/1251] eta: 0:00:15 lr: 0.000982 loss: 3.8060 (4.1738) grad_norm: 1.0060 (nan) time: 0.4990 [2021-03-25 07:52:19 swin_small_patch4_window7_224] INFO: Epoch: [25] [1230/1251] eta: 0:00:10 lr: 0.000982 loss: 4.1005 (4.1731) grad_norm: 1.0776 (nan) time: 0.5033 [2021-03-25 07:52:24 swin_small_patch4_window7_224] INFO: Epoch: [25] [1240/1251] eta: 0:00:05 lr: 0.000982 loss: 3.8847 (4.1706) grad_norm: 1.0988 (nan) time: 0.5046 [2021-03-25 07:52:29 swin_small_patch4_window7_224] INFO: Epoch: [25] [1250/1251] eta: 0:00:00 lr: 0.000982 loss: 3.9857 (4.1710) grad_norm: 1.1264 (nan) time: 0.5021 [2021-03-25 07:53:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 1.7375 (1.7375) acc1: 56.2500 (56.2500) acc5: 85.9375 (85.9375) [2021-03-25 07:53:05 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.4639 (1.4674) acc1: 65.6250 (63.9205) acc5: 85.9375 (87.6420) [2021-03-25 07:53:06 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.4639 (1.4988) acc1: 65.6250 (64.2113) acc5: 85.9375 (86.9792) [2021-03-25 07:53:07 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.5403 (1.5307) acc1: 64.0625 (64.0121) acc5: 85.9375 (86.5927) [2021-03-25 07:53:08 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.4723 (1.5136) acc1: 64.0625 (64.7104) acc5: 87.5000 (86.6616) [2021-03-25 07:53:09 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4150 (1.5020) acc1: 65.6250 (65.0240) acc5: 85.9375 (86.6240) [2021-03-25 07:53:12 swin_small_patch4_window7_224] INFO: * Acc@1 65.688 Acc@5 87.500 loss 1.476 [2021-03-25 07:53:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 65.7% [2021-03-25 07:53:12 swin_small_patch4_window7_224] INFO: Max accuracy: 65.69% [2021-03-25 07:53:16 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 0/1251] eta: 1:24:22 lr: 0.000982 loss: 4.2585 (4.2585) grad_norm: 0.9940 (0.9940) time: 4.0464 [2021-03-25 07:53:21 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 10/1251] eta: 0:17:41 lr: 0.000982 loss: 4.0391 (3.9175) grad_norm: 1.1212 (1.1331) time: 0.8554 [2021-03-25 07:53:26 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 20/1251] eta: 0:14:04 lr: 0.000982 loss: 4.0254 (4.0310) grad_norm: 1.0876 (1.0971) time: 0.5178 [2021-03-25 07:53:31 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 30/1251] eta: 0:12:43 lr: 0.000982 loss: 4.0209 (3.9702) grad_norm: 1.0705 (1.0848) time: 0.4987 [2021-03-25 07:53:36 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 40/1251] eta: 0:12:02 lr: 0.000982 loss: 4.2515 (4.0835) grad_norm: 1.0777 (1.0965) time: 0.5029 [2021-03-25 07:53:41 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 50/1251] eta: 0:11:37 lr: 0.000982 loss: 4.3743 (4.1084) grad_norm: 1.0559 (1.0819) time: 0.5119 [2021-03-25 07:53:46 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 60/1251] eta: 0:11:17 lr: 0.000982 loss: 4.2949 (4.1171) grad_norm: 1.0101 (1.0734) time: 0.5120 [2021-03-25 07:53:51 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 70/1251] eta: 0:11:02 lr: 0.000982 loss: 4.2949 (4.1126) grad_norm: 0.9953 (1.0633) time: 0.5094 [2021-03-25 07:53:56 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 80/1251] eta: 0:10:47 lr: 0.000982 loss: 4.2456 (4.1142) grad_norm: 0.9922 (1.0638) time: 0.5058 [2021-03-25 07:54:02 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 90/1251] eta: 0:10:37 lr: 0.000982 loss: 4.0246 (4.1132) grad_norm: 1.1397 (1.0745) time: 0.5081 [2021-03-25 07:54:07 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 100/1251] eta: 0:10:29 lr: 0.000982 loss: 3.9484 (4.0988) grad_norm: 1.0477 (1.0668) time: 0.5199 [2021-03-25 07:54:12 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 110/1251] eta: 0:10:18 lr: 0.000982 loss: 4.2178 (4.1136) grad_norm: 0.9781 (1.0588) time: 0.5124 [2021-03-25 07:54:17 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 120/1251] eta: 0:10:10 lr: 0.000982 loss: 4.3998 (4.1188) grad_norm: 0.9512 (1.0511) time: 0.5063 [2021-03-25 07:54:22 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 130/1251] eta: 0:10:03 lr: 0.000982 loss: 4.1864 (4.1106) grad_norm: 0.9880 (1.0615) time: 0.5126 [2021-03-25 07:54:27 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 140/1251] eta: 0:09:54 lr: 0.000982 loss: 4.0989 (4.1050) grad_norm: 1.0274 (1.0567) time: 0.5025 [2021-03-25 07:54:32 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 150/1251] eta: 0:09:46 lr: 0.000982 loss: 4.0989 (4.1043) grad_norm: 1.0690 (1.0595) time: 0.4979 [2021-03-25 07:54:37 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 160/1251] eta: 0:09:38 lr: 0.000982 loss: 4.1107 (4.1141) grad_norm: 1.0336 (1.0558) time: 0.5008 [2021-03-25 07:54:42 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 170/1251] eta: 0:09:31 lr: 0.000982 loss: 4.1819 (4.0993) grad_norm: 0.9976 (1.0558) time: 0.5014 [2021-03-25 07:54:47 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 180/1251] eta: 0:09:25 lr: 0.000982 loss: 3.8143 (4.0804) grad_norm: 0.9909 (1.0548) time: 0.5117 [2021-03-25 07:54:52 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 190/1251] eta: 0:09:20 lr: 0.000982 loss: 4.1008 (4.0928) grad_norm: 1.0749 (1.0569) time: 0.5179 [2021-03-25 07:54:57 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 200/1251] eta: 0:09:13 lr: 0.000982 loss: 4.3116 (4.1005) grad_norm: 1.0895 (1.0605) time: 0.5088 [2021-03-25 07:55:02 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 210/1251] eta: 0:09:06 lr: 0.000982 loss: 4.3116 (4.1153) grad_norm: 1.1018 (1.0618) time: 0.4998 [2021-03-25 07:55:07 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 220/1251] eta: 0:09:00 lr: 0.000982 loss: 4.2473 (4.1050) grad_norm: 1.0429 (1.0626) time: 0.5008 [2021-03-25 07:55:13 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 230/1251] eta: 0:08:54 lr: 0.000982 loss: 4.0138 (4.0983) grad_norm: 1.0237 (1.0596) time: 0.5082 [2021-03-25 07:55:18 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 240/1251] eta: 0:08:48 lr: 0.000981 loss: 4.1905 (4.1011) grad_norm: 0.9525 (1.0567) time: 0.5086 [2021-03-25 07:55:23 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 250/1251] eta: 0:08:43 lr: 0.000981 loss: 4.3482 (4.1089) grad_norm: 1.0026 (1.0564) time: 0.5087 [2021-03-25 07:55:28 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 260/1251] eta: 0:08:36 lr: 0.000981 loss: 4.3637 (4.1111) grad_norm: 1.0571 (1.0580) time: 0.5074 [2021-03-25 07:55:33 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 270/1251] eta: 0:08:30 lr: 0.000981 loss: 4.1634 (4.1146) grad_norm: 1.1207 (1.0668) time: 0.4991 [2021-03-25 07:55:38 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 280/1251] eta: 0:08:25 lr: 0.000981 loss: 4.1208 (4.1087) grad_norm: 1.2399 (1.0737) time: 0.5007 [2021-03-25 07:55:43 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 290/1251] eta: 0:08:19 lr: 0.000981 loss: 4.4256 (4.1205) grad_norm: 1.1267 (1.0756) time: 0.5035 [2021-03-25 07:55:48 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 300/1251] eta: 0:08:13 lr: 0.000981 loss: 4.5547 (4.1317) grad_norm: 1.0106 (1.0729) time: 0.5013 [2021-03-25 07:55:53 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 310/1251] eta: 0:08:07 lr: 0.000981 loss: 4.5547 (4.1385) grad_norm: 0.9880 (1.0727) time: 0.4990 [2021-03-25 07:55:58 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 320/1251] eta: 0:08:02 lr: 0.000981 loss: 4.3689 (4.1391) grad_norm: 1.0308 (1.0724) time: 0.5059 [2021-03-25 07:56:03 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 330/1251] eta: 0:07:56 lr: 0.000981 loss: 4.5724 (4.1512) grad_norm: 1.0549 (1.0738) time: 0.5040 [2021-03-25 07:56:08 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 340/1251] eta: 0:07:50 lr: 0.000981 loss: 4.5609 (4.1507) grad_norm: 1.0943 (1.0747) time: 0.4993 [2021-03-25 07:56:13 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 350/1251] eta: 0:07:45 lr: 0.000981 loss: 4.2002 (4.1421) grad_norm: 1.0430 (1.0749) time: 0.5056 [2021-03-25 07:56:18 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 360/1251] eta: 0:07:39 lr: 0.000981 loss: 3.9220 (4.1354) grad_norm: 1.0016 (1.0727) time: 0.5018 [2021-03-25 07:56:23 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 370/1251] eta: 0:07:34 lr: 0.000981 loss: 3.9199 (4.1282) grad_norm: 1.0514 (1.0754) time: 0.5013 [2021-03-25 07:56:28 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 380/1251] eta: 0:07:29 lr: 0.000981 loss: 3.7991 (4.1239) grad_norm: 1.0658 (1.0741) time: 0.5058 [2021-03-25 07:56:33 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 390/1251] eta: 0:07:23 lr: 0.000981 loss: 4.1542 (4.1264) grad_norm: 1.0252 (1.0730) time: 0.5020 [2021-03-25 07:56:38 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 400/1251] eta: 0:07:18 lr: 0.000981 loss: 4.2670 (4.1255) grad_norm: 1.0223 (1.0741) time: 0.5002 [2021-03-25 07:56:43 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 410/1251] eta: 0:07:12 lr: 0.000981 loss: 4.2830 (4.1268) grad_norm: 1.0456 (1.0740) time: 0.5055 [2021-03-25 07:56:48 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 420/1251] eta: 0:07:07 lr: 0.000981 loss: 4.3094 (4.1265) grad_norm: 1.0416 (1.0734) time: 0.5102 [2021-03-25 07:56:53 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 430/1251] eta: 0:07:02 lr: 0.000981 loss: 3.7811 (4.1232) grad_norm: 1.0239 (1.0740) time: 0.5091 [2021-03-25 07:56:58 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 440/1251] eta: 0:06:56 lr: 0.000981 loss: 3.7181 (4.1205) grad_norm: 1.1328 (1.0770) time: 0.5014 [2021-03-25 07:57:03 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 450/1251] eta: 0:06:51 lr: 0.000981 loss: 4.1744 (4.1220) grad_norm: 1.1492 (1.0798) time: 0.5000 [2021-03-25 07:57:09 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 460/1251] eta: 0:06:46 lr: 0.000981 loss: 3.8632 (4.1148) grad_norm: 1.0686 (1.0783) time: 0.5058 [2021-03-25 07:57:14 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 470/1251] eta: 0:06:41 lr: 0.000981 loss: 4.0101 (4.1151) grad_norm: 0.9887 (1.0768) time: 0.5079 [2021-03-25 07:57:19 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 480/1251] eta: 0:06:35 lr: 0.000981 loss: 4.1415 (4.1158) grad_norm: 0.9887 (1.0767) time: 0.5072 [2021-03-25 07:57:24 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 490/1251] eta: 0:06:30 lr: 0.000981 loss: 4.1415 (4.1151) grad_norm: 0.9962 (1.0760) time: 0.5078 [2021-03-25 07:57:29 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 500/1251] eta: 0:06:25 lr: 0.000981 loss: 4.2584 (4.1196) grad_norm: 0.9668 (1.0748) time: 0.5031 [2021-03-25 07:57:34 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 510/1251] eta: 0:06:20 lr: 0.000981 loss: 4.2629 (4.1184) grad_norm: 0.9936 (1.0744) time: 0.5013 [2021-03-25 07:57:39 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 520/1251] eta: 0:06:14 lr: 0.000981 loss: 4.2284 (4.1219) grad_norm: 1.0314 (1.0759) time: 0.4967 [2021-03-25 07:57:44 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 530/1251] eta: 0:06:09 lr: 0.000981 loss: 4.2284 (4.1270) grad_norm: 1.0716 (1.0759) time: 0.5002 [2021-03-25 07:57:49 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 540/1251] eta: 0:06:04 lr: 0.000981 loss: 4.3732 (4.1299) grad_norm: 1.0416 (1.0751) time: 0.5105 [2021-03-25 07:57:54 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 550/1251] eta: 0:05:59 lr: 0.000981 loss: 4.2566 (4.1272) grad_norm: 1.0036 (1.0739) time: 0.5178 [2021-03-25 07:57:59 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 560/1251] eta: 0:05:53 lr: 0.000981 loss: 4.2701 (4.1296) grad_norm: 1.0713 (1.0745) time: 0.5100 [2021-03-25 07:58:04 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 570/1251] eta: 0:05:48 lr: 0.000981 loss: 4.2701 (4.1300) grad_norm: 1.0713 (1.0754) time: 0.4979 [2021-03-25 07:58:09 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 580/1251] eta: 0:05:43 lr: 0.000981 loss: 4.1551 (4.1303) grad_norm: 1.0131 (1.0741) time: 0.5050 [2021-03-25 07:58:14 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 590/1251] eta: 0:05:38 lr: 0.000981 loss: 4.3846 (4.1333) grad_norm: 1.0294 (1.0746) time: 0.5102 [2021-03-25 07:58:19 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 600/1251] eta: 0:05:33 lr: 0.000981 loss: 4.2984 (4.1347) grad_norm: 1.0323 (1.0747) time: 0.5151 [2021-03-25 07:58:25 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 610/1251] eta: 0:05:28 lr: 0.000981 loss: 4.0847 (4.1341) grad_norm: 1.0348 (1.0742) time: 0.5113 [2021-03-25 07:58:30 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 620/1251] eta: 0:05:22 lr: 0.000981 loss: 3.8766 (4.1276) grad_norm: 1.0521 (1.0736) time: 0.5045 [2021-03-25 07:58:35 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 630/1251] eta: 0:05:17 lr: 0.000981 loss: 4.0608 (4.1263) grad_norm: 1.1072 (1.0749) time: 0.5049 [2021-03-25 07:58:40 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 640/1251] eta: 0:05:12 lr: 0.000981 loss: 4.0990 (4.1271) grad_norm: 1.0281 (1.0738) time: 0.5053 [2021-03-25 07:58:45 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 650/1251] eta: 0:05:07 lr: 0.000981 loss: 4.1705 (4.1254) grad_norm: 0.9984 (1.0739) time: 0.5065 [2021-03-25 07:58:50 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 660/1251] eta: 0:05:02 lr: 0.000981 loss: 4.1849 (4.1255) grad_norm: 1.1023 (1.0762) time: 0.5032 [2021-03-25 07:58:55 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 670/1251] eta: 0:04:57 lr: 0.000981 loss: 4.1422 (4.1259) grad_norm: 1.1131 (1.0763) time: 0.5033 [2021-03-25 07:59:00 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 680/1251] eta: 0:04:51 lr: 0.000981 loss: 4.1490 (4.1261) grad_norm: 1.0893 (1.0768) time: 0.5039 [2021-03-25 07:59:05 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 690/1251] eta: 0:04:46 lr: 0.000981 loss: 4.1490 (4.1228) grad_norm: 1.0607 (1.0762) time: 0.5013 [2021-03-25 07:59:10 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 700/1251] eta: 0:04:41 lr: 0.000981 loss: 3.9816 (4.1225) grad_norm: 1.0327 (1.0760) time: 0.5024 [2021-03-25 07:59:15 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 710/1251] eta: 0:04:36 lr: 0.000981 loss: 4.2714 (4.1235) grad_norm: 0.9962 (1.0752) time: 0.5024 [2021-03-25 07:59:20 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 720/1251] eta: 0:04:31 lr: 0.000981 loss: 4.2899 (4.1275) grad_norm: 1.0112 (1.0745) time: 0.5036 [2021-03-25 07:59:25 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 730/1251] eta: 0:04:26 lr: 0.000981 loss: 3.9951 (4.1221) grad_norm: 1.0132 (1.0739) time: 0.5100 [2021-03-25 07:59:30 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 740/1251] eta: 0:04:21 lr: 0.000981 loss: 3.8922 (4.1236) grad_norm: 1.0408 (1.0751) time: 0.5224 [2021-03-25 07:59:35 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 750/1251] eta: 0:04:15 lr: 0.000981 loss: 3.9272 (4.1214) grad_norm: 1.0817 (1.0754) time: 0.5144 [2021-03-25 07:59:41 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 760/1251] eta: 0:04:10 lr: 0.000981 loss: 4.0108 (4.1231) grad_norm: 1.0497 (1.0750) time: 0.5056 [2021-03-25 07:59:46 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 770/1251] eta: 0:04:05 lr: 0.000981 loss: 4.0580 (4.1228) grad_norm: 0.9597 (1.0747) time: 0.5076 [2021-03-25 07:59:51 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 780/1251] eta: 0:04:00 lr: 0.000981 loss: 4.3279 (4.1249) grad_norm: 1.1355 (1.0769) time: 0.5041 [2021-03-25 07:59:56 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 790/1251] eta: 0:03:55 lr: 0.000981 loss: 4.3279 (4.1264) grad_norm: 1.0704 (1.0762) time: 0.5096 [2021-03-25 08:00:01 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 800/1251] eta: 0:03:50 lr: 0.000981 loss: 4.2681 (4.1287) grad_norm: 0.9941 (1.0748) time: 0.5115 [2021-03-25 08:00:06 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 810/1251] eta: 0:03:45 lr: 0.000981 loss: 4.3395 (4.1299) grad_norm: 0.9941 (1.0742) time: 0.5069 [2021-03-25 08:00:11 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 820/1251] eta: 0:03:40 lr: 0.000981 loss: 4.1058 (4.1286) grad_norm: 0.9826 (1.0730) time: 0.5037 [2021-03-25 08:00:16 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 830/1251] eta: 0:03:34 lr: 0.000981 loss: 4.0228 (4.1299) grad_norm: 0.9826 (1.0744) time: 0.5006 [2021-03-25 08:00:21 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 840/1251] eta: 0:03:29 lr: 0.000981 loss: 3.8295 (4.1269) grad_norm: 1.1564 (1.0759) time: 0.5053 [2021-03-25 08:00:26 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 850/1251] eta: 0:03:24 lr: 0.000981 loss: 3.9938 (4.1281) grad_norm: 1.1571 (1.0780) time: 0.5096 [2021-03-25 08:00:31 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 860/1251] eta: 0:03:19 lr: 0.000981 loss: 4.3434 (4.1307) grad_norm: 1.0711 (1.0773) time: 0.5073 [2021-03-25 08:00:36 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 870/1251] eta: 0:03:14 lr: 0.000981 loss: 4.2860 (4.1291) grad_norm: 0.9895 (1.0768) time: 0.5100 [2021-03-25 08:00:41 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 880/1251] eta: 0:03:09 lr: 0.000981 loss: 4.0800 (4.1278) grad_norm: 0.9895 (1.0760) time: 0.5128 [2021-03-25 08:00:46 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 890/1251] eta: 0:03:04 lr: 0.000981 loss: 3.9455 (4.1246) grad_norm: 0.9769 (1.0747) time: 0.5039 [2021-03-25 08:00:51 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 900/1251] eta: 0:02:59 lr: 0.000981 loss: 4.2120 (4.1240) grad_norm: 0.9963 (1.0750) time: 0.5021 [2021-03-25 08:00:57 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 910/1251] eta: 0:02:53 lr: 0.000981 loss: 4.1605 (4.1199) grad_norm: 1.0449 (1.0741) time: 0.5057 [2021-03-25 08:01:02 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 920/1251] eta: 0:02:48 lr: 0.000981 loss: 4.1124 (4.1211) grad_norm: 0.9837 (1.0735) time: 0.5056 [2021-03-25 08:01:07 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 930/1251] eta: 0:02:43 lr: 0.000981 loss: 4.0644 (4.1208) grad_norm: 0.9704 (1.0731) time: 0.5116 [2021-03-25 08:01:12 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 940/1251] eta: 0:02:38 lr: 0.000981 loss: 4.0352 (4.1224) grad_norm: 1.0549 (1.0735) time: 0.5104 [2021-03-25 08:01:17 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 950/1251] eta: 0:02:33 lr: 0.000981 loss: 4.4679 (4.1275) grad_norm: 1.0549 (1.0734) time: 0.5080 [2021-03-25 08:01:22 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 960/1251] eta: 0:02:28 lr: 0.000981 loss: 4.4114 (4.1284) grad_norm: 1.0697 (1.0738) time: 0.5060 [2021-03-25 08:01:27 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 970/1251] eta: 0:02:23 lr: 0.000981 loss: 4.2888 (4.1290) grad_norm: 1.0152 (1.0728) time: 0.5006 [2021-03-25 08:01:32 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 980/1251] eta: 0:02:18 lr: 0.000981 loss: 4.2346 (4.1307) grad_norm: 1.0137 (1.0725) time: 0.5020 [2021-03-25 08:01:37 swin_small_patch4_window7_224] INFO: Epoch: [26] [ 990/1251] eta: 0:02:13 lr: 0.000981 loss: 4.3725 (4.1345) grad_norm: 1.0436 (1.0726) time: 0.5046 [2021-03-25 08:01:42 swin_small_patch4_window7_224] INFO: Epoch: [26] [1000/1251] eta: 0:02:07 lr: 0.000981 loss: 4.3676 (4.1345) grad_norm: 1.0374 (1.0721) time: 0.5056 [2021-03-25 08:01:47 swin_small_patch4_window7_224] INFO: Epoch: [26] [1010/1251] eta: 0:02:02 lr: 0.000981 loss: 4.3482 (4.1363) grad_norm: 0.9979 (1.0719) time: 0.5021 [2021-03-25 08:01:52 swin_small_patch4_window7_224] INFO: Epoch: [26] [1020/1251] eta: 0:01:57 lr: 0.000981 loss: 4.3863 (4.1376) grad_norm: 1.0699 (1.0729) time: 0.4986 [2021-03-25 08:01:57 swin_small_patch4_window7_224] INFO: Epoch: [26] [1030/1251] eta: 0:01:52 lr: 0.000981 loss: 4.3175 (4.1368) grad_norm: 1.0552 (1.0727) time: 0.5035 [2021-03-25 08:02:02 swin_small_patch4_window7_224] INFO: Epoch: [26] [1040/1251] eta: 0:01:47 lr: 0.000981 loss: 4.0871 (4.1371) grad_norm: 1.0489 (1.0726) time: 0.5062 [2021-03-25 08:02:07 swin_small_patch4_window7_224] INFO: Epoch: [26] [1050/1251] eta: 0:01:42 lr: 0.000981 loss: 4.1039 (4.1380) grad_norm: 1.0291 (1.0720) time: 0.5027 [2021-03-25 08:02:12 swin_small_patch4_window7_224] INFO: Epoch: [26] [1060/1251] eta: 0:01:37 lr: 0.000981 loss: 4.0521 (4.1376) grad_norm: 1.0181 (1.0721) time: 0.5041 [2021-03-25 08:02:17 swin_small_patch4_window7_224] INFO: Epoch: [26] [1070/1251] eta: 0:01:32 lr: 0.000981 loss: 4.3422 (4.1392) grad_norm: 1.1224 (1.0731) time: 0.5089 [2021-03-25 08:02:22 swin_small_patch4_window7_224] INFO: Epoch: [26] [1080/1251] eta: 0:01:27 lr: 0.000981 loss: 4.3422 (4.1395) grad_norm: 1.1530 (1.0734) time: 0.5072 [2021-03-25 08:02:27 swin_small_patch4_window7_224] INFO: Epoch: [26] [1090/1251] eta: 0:01:21 lr: 0.000981 loss: 4.2243 (4.1422) grad_norm: 1.0150 (1.0732) time: 0.5030 [2021-03-25 08:02:32 swin_small_patch4_window7_224] INFO: Epoch: [26] [1100/1251] eta: 0:01:16 lr: 0.000981 loss: 4.2243 (4.1413) grad_norm: 1.0311 (1.0737) time: 0.4984 [2021-03-25 08:02:37 swin_small_patch4_window7_224] INFO: Epoch: [26] [1110/1251] eta: 0:01:11 lr: 0.000981 loss: 4.1319 (4.1408) grad_norm: 1.0210 (1.0732) time: 0.4985 [2021-03-25 08:02:42 swin_small_patch4_window7_224] INFO: Epoch: [26] [1120/1251] eta: 0:01:06 lr: 0.000980 loss: 3.8837 (4.1367) grad_norm: 1.0077 (1.0733) time: 0.5044 [2021-03-25 08:02:48 swin_small_patch4_window7_224] INFO: Epoch: [26] [1130/1251] eta: 0:01:01 lr: 0.000980 loss: 3.8091 (4.1358) grad_norm: 1.0614 (1.0735) time: 0.5059 [2021-03-25 08:02:53 swin_small_patch4_window7_224] INFO: Epoch: [26] [1140/1251] eta: 0:00:56 lr: 0.000980 loss: 3.8091 (4.1336) grad_norm: 1.0391 (1.0739) time: 0.5091 [2021-03-25 08:02:58 swin_small_patch4_window7_224] INFO: Epoch: [26] [1150/1251] eta: 0:00:51 lr: 0.000980 loss: 4.0932 (4.1338) grad_norm: 1.0547 (1.0737) time: 0.5073 [2021-03-25 08:03:03 swin_small_patch4_window7_224] INFO: Epoch: [26] [1160/1251] eta: 0:00:46 lr: 0.000980 loss: 4.2096 (4.1326) grad_norm: 1.0547 (1.0739) time: 0.5033 [2021-03-25 08:03:08 swin_small_patch4_window7_224] INFO: Epoch: [26] [1170/1251] eta: 0:00:41 lr: 0.000980 loss: 3.9393 (4.1313) grad_norm: 1.0664 (1.0741) time: 0.5090 [2021-03-25 08:03:13 swin_small_patch4_window7_224] INFO: Epoch: [26] [1180/1251] eta: 0:00:36 lr: 0.000980 loss: 3.9451 (4.1318) grad_norm: 1.1129 (1.0747) time: 0.5090 [2021-03-25 08:03:18 swin_small_patch4_window7_224] INFO: Epoch: [26] [1190/1251] eta: 0:00:31 lr: 0.000980 loss: 4.2754 (4.1317) grad_norm: 1.0819 (1.0746) time: 0.5039 [2021-03-25 08:03:23 swin_small_patch4_window7_224] INFO: Epoch: [26] [1200/1251] eta: 0:00:25 lr: 0.000980 loss: 4.0236 (4.1277) grad_norm: 1.0202 (1.0743) time: 0.5017 [2021-03-25 08:03:28 swin_small_patch4_window7_224] INFO: Epoch: [26] [1210/1251] eta: 0:00:20 lr: 0.000980 loss: 3.9426 (4.1284) grad_norm: 1.0906 (1.0748) time: 0.4999 [2021-03-25 08:03:33 swin_small_patch4_window7_224] INFO: Epoch: [26] [1220/1251] eta: 0:00:15 lr: 0.000980 loss: 4.5308 (4.1312) grad_norm: 1.1201 (1.0748) time: 0.5023 [2021-03-25 08:03:38 swin_small_patch4_window7_224] INFO: Epoch: [26] [1230/1251] eta: 0:00:10 lr: 0.000980 loss: 4.2930 (4.1290) grad_norm: 1.0636 (1.0749) time: 0.4993 [2021-03-25 08:03:43 swin_small_patch4_window7_224] INFO: Epoch: [26] [1240/1251] eta: 0:00:05 lr: 0.000980 loss: 3.9046 (4.1272) grad_norm: 1.0635 (1.0748) time: 0.4984 [2021-03-25 08:03:48 swin_small_patch4_window7_224] INFO: Epoch: [26] [1250/1251] eta: 0:00:00 lr: 0.000980 loss: 4.0606 (4.1275) grad_norm: 1.0579 (1.0751) time: 0.5035 [2021-03-25 08:03:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 1.5277 (1.5277) acc1: 59.3750 (59.3750) acc5: 85.9375 (85.9375) [2021-03-25 08:03:55 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.4801 (1.4898) acc1: 67.1875 (65.1989) acc5: 85.9375 (86.6477) [2021-03-25 08:03:57 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.4182 (1.4398) acc1: 67.1875 (66.5179) acc5: 89.0625 (87.8720) [2021-03-25 08:03:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.4205 (1.4607) acc1: 65.6250 (65.8266) acc5: 89.0625 (87.7016) [2021-03-25 08:04:00 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.5216 (1.4746) acc1: 64.0625 (65.5869) acc5: 87.5000 (87.6143) [2021-03-25 08:04:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.5022 (1.4729) acc1: 64.0625 (65.6000) acc5: 87.5000 (87.6160) [2021-03-25 08:04:03 swin_small_patch4_window7_224] INFO: * Acc@1 66.424 Acc@5 88.038 loss 1.458 [2021-03-25 08:04:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 66.4% [2021-03-25 08:04:03 swin_small_patch4_window7_224] INFO: Max accuracy: 66.42% [2021-03-25 08:04:07 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 0/1251] eta: 1:23:11 lr: 0.000980 loss: 4.5414 (4.5414) grad_norm: 0.9989 (0.9989) time: 3.9899 [2021-03-25 08:04:13 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 10/1251] eta: 0:17:45 lr: 0.000980 loss: 3.7113 (3.7508) grad_norm: 0.9416 (0.9650) time: 0.8582 [2021-03-25 08:04:18 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 20/1251] eta: 0:14:05 lr: 0.000980 loss: 3.9788 (3.8916) grad_norm: 0.9688 (1.0108) time: 0.5216 [2021-03-25 08:04:23 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 30/1251] eta: 0:12:46 lr: 0.000980 loss: 4.3826 (4.0632) grad_norm: 1.0448 (1.0227) time: 0.5011 [2021-03-25 08:04:28 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 40/1251] eta: 0:12:05 lr: 0.000980 loss: 4.3661 (4.0863) grad_norm: 0.9666 (1.0027) time: 0.5079 [2021-03-25 08:04:33 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 50/1251] eta: 0:11:36 lr: 0.000980 loss: 3.9385 (4.0616) grad_norm: 0.9644 (0.9989) time: 0.5064 [2021-03-25 08:04:38 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 60/1251] eta: 0:11:17 lr: 0.000980 loss: 4.1486 (4.0690) grad_norm: 1.0681 (1.0345) time: 0.5049 [2021-03-25 08:04:43 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 70/1251] eta: 0:10:59 lr: 0.000980 loss: 4.1762 (4.0824) grad_norm: 1.1685 (1.0808) time: 0.5034 [2021-03-25 08:04:48 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 80/1251] eta: 0:10:46 lr: 0.000980 loss: 4.2716 (4.1095) grad_norm: 1.0962 (1.0751) time: 0.5030 [2021-03-25 08:04:53 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 90/1251] eta: 0:10:36 lr: 0.000980 loss: 4.4084 (4.1438) grad_norm: 0.9939 (1.0666) time: 0.5105 [2021-03-25 08:04:58 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 100/1251] eta: 0:10:25 lr: 0.000980 loss: 4.3255 (4.1591) grad_norm: 0.9939 (1.0641) time: 0.5075 [2021-03-25 08:05:03 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 110/1251] eta: 0:10:17 lr: 0.000980 loss: 4.2653 (4.1543) grad_norm: 1.0252 (1.0646) time: 0.5088 [2021-03-25 08:05:08 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 120/1251] eta: 0:10:08 lr: 0.000980 loss: 4.1584 (4.1515) grad_norm: 1.0394 (1.0647) time: 0.5121 [2021-03-25 08:05:13 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 130/1251] eta: 0:10:01 lr: 0.000980 loss: 4.0674 (4.1286) grad_norm: 1.0889 (1.0683) time: 0.5115 [2021-03-25 08:05:18 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 140/1251] eta: 0:09:53 lr: 0.000980 loss: 3.8301 (4.1103) grad_norm: 1.0478 (1.0650) time: 0.5087 [2021-03-25 08:05:24 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 150/1251] eta: 0:09:46 lr: 0.000980 loss: 3.9588 (4.1112) grad_norm: 1.0478 (1.0650) time: 0.5074 [2021-03-25 08:05:29 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 160/1251] eta: 0:09:39 lr: 0.000980 loss: 4.0991 (4.1143) grad_norm: 1.0767 (1.0669) time: 0.5132 [2021-03-25 08:05:34 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 170/1251] eta: 0:09:32 lr: 0.000980 loss: 4.1440 (4.0996) grad_norm: 1.1035 (1.0753) time: 0.5102 [2021-03-25 08:05:39 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 180/1251] eta: 0:09:26 lr: 0.000980 loss: 3.3849 (4.0697) grad_norm: 1.0818 (1.0757) time: 0.5104 [2021-03-25 08:05:44 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 190/1251] eta: 0:09:20 lr: 0.000980 loss: 3.7537 (4.0777) grad_norm: 1.0709 (1.0761) time: 0.5146 [2021-03-25 08:05:49 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 200/1251] eta: 0:09:14 lr: 0.000980 loss: 4.1761 (4.0814) grad_norm: 1.0937 (1.0783) time: 0.5117 [2021-03-25 08:05:54 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 210/1251] eta: 0:09:07 lr: 0.000980 loss: 4.0785 (4.0721) grad_norm: 0.9854 (1.0744) time: 0.5071 [2021-03-25 08:05:59 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 220/1251] eta: 0:09:01 lr: 0.000980 loss: 3.9274 (4.0602) grad_norm: 1.0046 (1.0730) time: 0.5028 [2021-03-25 08:06:04 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 230/1251] eta: 0:08:54 lr: 0.000980 loss: 4.1551 (4.0652) grad_norm: 1.0515 (1.0753) time: 0.4989 [2021-03-25 08:06:09 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 240/1251] eta: 0:08:48 lr: 0.000980 loss: 4.2169 (4.0614) grad_norm: 1.0515 (1.0725) time: 0.5014 [2021-03-25 08:06:14 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 250/1251] eta: 0:08:43 lr: 0.000980 loss: 4.0664 (4.0630) grad_norm: 0.9930 (1.0699) time: 0.5080 [2021-03-25 08:06:19 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 260/1251] eta: 0:08:37 lr: 0.000980 loss: 4.0664 (4.0661) grad_norm: 1.0346 (1.0702) time: 0.5059 [2021-03-25 08:06:24 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 270/1251] eta: 0:08:30 lr: 0.000980 loss: 4.3016 (4.0693) grad_norm: 1.0716 (1.0730) time: 0.4983 [2021-03-25 08:06:29 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 280/1251] eta: 0:08:25 lr: 0.000980 loss: 3.9847 (4.0660) grad_norm: 1.0952 (1.0739) time: 0.5002 [2021-03-25 08:06:35 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 290/1251] eta: 0:08:19 lr: 0.000980 loss: 4.1314 (4.0777) grad_norm: 1.0285 (1.0718) time: 0.5076 [2021-03-25 08:06:40 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 300/1251] eta: 0:08:14 lr: 0.000980 loss: 4.3165 (4.0825) grad_norm: 1.0044 (1.0705) time: 0.5092 [2021-03-25 08:06:45 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 310/1251] eta: 0:08:08 lr: 0.000980 loss: 4.0463 (4.0770) grad_norm: 1.0209 (1.0714) time: 0.5101 [2021-03-25 08:06:50 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 320/1251] eta: 0:08:02 lr: 0.000980 loss: 4.2114 (4.0869) grad_norm: 1.0176 (1.0724) time: 0.5013 [2021-03-25 08:06:55 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 330/1251] eta: 0:07:57 lr: 0.000980 loss: 4.3301 (4.0787) grad_norm: 1.0032 (1.0722) time: 0.4972 [2021-03-25 08:07:00 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 340/1251] eta: 0:07:51 lr: 0.000980 loss: 4.0638 (4.0750) grad_norm: 0.9757 (1.0694) time: 0.5025 [2021-03-25 08:07:05 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 350/1251] eta: 0:07:45 lr: 0.000980 loss: 4.1222 (4.0752) grad_norm: 0.9608 (1.0671) time: 0.5016 [2021-03-25 08:07:10 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 360/1251] eta: 0:07:40 lr: 0.000980 loss: 4.2574 (4.0790) grad_norm: 0.9653 (1.0653) time: 0.4991 [2021-03-25 08:07:15 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 370/1251] eta: 0:07:34 lr: 0.000980 loss: 4.0770 (4.0738) grad_norm: 1.0067 (1.0646) time: 0.4999 [2021-03-25 08:07:20 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 380/1251] eta: 0:07:29 lr: 0.000980 loss: 3.9747 (4.0745) grad_norm: 1.0567 (1.0643) time: 0.5067 [2021-03-25 08:07:25 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 390/1251] eta: 0:07:24 lr: 0.000980 loss: 4.4154 (4.0792) grad_norm: 0.9875 (1.0623) time: 0.5072 [2021-03-25 08:07:30 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 400/1251] eta: 0:07:18 lr: 0.000980 loss: 3.9862 (4.0708) grad_norm: 1.0258 (1.0639) time: 0.5017 [2021-03-25 08:07:35 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 410/1251] eta: 0:07:13 lr: 0.000980 loss: 4.2511 (4.0796) grad_norm: 1.0574 (1.0632) time: 0.5021 [2021-03-25 08:07:40 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 420/1251] eta: 0:07:07 lr: 0.000980 loss: 4.2511 (4.0719) grad_norm: 0.9985 (1.0632) time: 0.5029 [2021-03-25 08:07:45 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 430/1251] eta: 0:07:02 lr: 0.000980 loss: 3.9542 (4.0650) grad_norm: 1.0079 (1.0625) time: 0.5025 [2021-03-25 08:07:50 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 440/1251] eta: 0:06:56 lr: 0.000980 loss: 3.9556 (4.0629) grad_norm: 1.0191 (1.0626) time: 0.5020 [2021-03-25 08:07:55 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 450/1251] eta: 0:06:51 lr: 0.000980 loss: 3.7906 (4.0544) grad_norm: 1.0335 (1.0625) time: 0.4999 [2021-03-25 08:08:00 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 460/1251] eta: 0:06:46 lr: 0.000980 loss: 4.0832 (4.0603) grad_norm: 1.0077 (1.0615) time: 0.5015 [2021-03-25 08:08:05 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 470/1251] eta: 0:06:40 lr: 0.000980 loss: 4.3813 (4.0602) grad_norm: 1.0484 (1.0622) time: 0.4997 [2021-03-25 08:08:10 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 480/1251] eta: 0:06:35 lr: 0.000980 loss: 4.2219 (4.0592) grad_norm: 1.0656 (1.0634) time: 0.5005 [2021-03-25 08:08:15 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 490/1251] eta: 0:06:30 lr: 0.000980 loss: 4.1325 (4.0589) grad_norm: 0.9983 (1.0628) time: 0.5030 [2021-03-25 08:08:20 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 500/1251] eta: 0:06:24 lr: 0.000980 loss: 4.2234 (4.0641) grad_norm: 1.0045 (1.0624) time: 0.5010 [2021-03-25 08:08:25 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 510/1251] eta: 0:06:19 lr: 0.000980 loss: 4.3186 (4.0687) grad_norm: 1.0326 (1.0626) time: 0.5013 [2021-03-25 08:08:30 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 520/1251] eta: 0:06:14 lr: 0.000980 loss: 4.1357 (4.0667) grad_norm: 1.0644 (1.0646) time: 0.5041 [2021-03-25 08:08:35 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 530/1251] eta: 0:06:09 lr: 0.000980 loss: 4.1794 (4.0715) grad_norm: 1.0447 (1.0647) time: 0.5122 [2021-03-25 08:08:40 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 540/1251] eta: 0:06:04 lr: 0.000980 loss: 4.3107 (4.0719) grad_norm: 1.0042 (1.0628) time: 0.5109 [2021-03-25 08:08:46 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 550/1251] eta: 0:05:59 lr: 0.000980 loss: 4.4076 (4.0777) grad_norm: 0.9667 (1.0624) time: 0.5141 [2021-03-25 08:08:51 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 560/1251] eta: 0:05:53 lr: 0.000980 loss: 4.2657 (4.0760) grad_norm: 0.9894 (1.0613) time: 0.5142 [2021-03-25 08:08:56 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 570/1251] eta: 0:05:48 lr: 0.000980 loss: 3.6909 (4.0681) grad_norm: 1.0350 (1.0611) time: 0.5038 [2021-03-25 08:09:01 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 580/1251] eta: 0:05:43 lr: 0.000980 loss: 3.9359 (4.0702) grad_norm: 1.0616 (1.0619) time: 0.5080 [2021-03-25 08:09:06 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 590/1251] eta: 0:05:38 lr: 0.000980 loss: 4.3776 (4.0757) grad_norm: 1.0683 (1.0624) time: 0.5148 [2021-03-25 08:09:11 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 600/1251] eta: 0:05:33 lr: 0.000980 loss: 4.3871 (4.0807) grad_norm: 1.0237 (1.0613) time: 0.5132 [2021-03-25 08:09:16 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 610/1251] eta: 0:05:28 lr: 0.000980 loss: 4.3871 (4.0834) grad_norm: 0.9884 (1.0605) time: 0.5073 [2021-03-25 08:09:21 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 620/1251] eta: 0:05:23 lr: 0.000980 loss: 4.1482 (4.0846) grad_norm: 0.9782 (1.0600) time: 0.5068 [2021-03-25 08:09:26 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 630/1251] eta: 0:05:17 lr: 0.000980 loss: 4.2264 (4.0854) grad_norm: 1.0605 (1.0604) time: 0.5068 [2021-03-25 08:09:31 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 640/1251] eta: 0:05:12 lr: 0.000980 loss: 4.0370 (4.0834) grad_norm: 1.0738 (1.0610) time: 0.5082 [2021-03-25 08:09:36 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 650/1251] eta: 0:05:07 lr: 0.000980 loss: 3.9822 (4.0821) grad_norm: 1.0448 (1.0619) time: 0.5085 [2021-03-25 08:09:42 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 660/1251] eta: 0:05:02 lr: 0.000980 loss: 3.9822 (4.0816) grad_norm: 1.0704 (1.0621) time: 0.5072 [2021-03-25 08:09:47 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 670/1251] eta: 0:04:57 lr: 0.000980 loss: 4.3540 (4.0846) grad_norm: 1.0803 (1.0637) time: 0.5092 [2021-03-25 08:09:52 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 680/1251] eta: 0:04:52 lr: 0.000980 loss: 4.2097 (4.0849) grad_norm: 1.0803 (1.0641) time: 0.5123 [2021-03-25 08:09:57 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 690/1251] eta: 0:04:47 lr: 0.000980 loss: 4.0127 (4.0836) grad_norm: 1.0205 (1.0633) time: 0.5109 [2021-03-25 08:10:02 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 700/1251] eta: 0:04:41 lr: 0.000980 loss: 4.1601 (4.0829) grad_norm: 1.0280 (1.0636) time: 0.4992 [2021-03-25 08:10:07 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 710/1251] eta: 0:04:36 lr: 0.000980 loss: 4.3327 (4.0872) grad_norm: 1.0795 (1.0639) time: 0.4987 [2021-03-25 08:10:12 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 720/1251] eta: 0:04:31 lr: 0.000980 loss: 4.3580 (4.0873) grad_norm: 1.0588 (1.0643) time: 0.5053 [2021-03-25 08:10:17 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 730/1251] eta: 0:04:26 lr: 0.000979 loss: 4.1215 (4.0873) grad_norm: 1.0259 (1.0641) time: 0.5112 [2021-03-25 08:10:22 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 740/1251] eta: 0:04:21 lr: 0.000979 loss: 4.1322 (4.0878) grad_norm: 0.9684 (1.0628) time: 0.5288 [2021-03-25 08:10:27 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 750/1251] eta: 0:04:16 lr: 0.000979 loss: 4.1141 (4.0869) grad_norm: 0.9873 (1.0631) time: 0.5216 [2021-03-25 08:10:33 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 760/1251] eta: 0:04:11 lr: 0.000979 loss: 4.0018 (4.0867) grad_norm: 0.9873 (1.0616) time: 0.5049 [2021-03-25 08:10:38 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 770/1251] eta: 0:04:05 lr: 0.000979 loss: 4.0697 (4.0848) grad_norm: 0.9523 (1.0602) time: 0.5020 [2021-03-25 08:10:43 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 780/1251] eta: 0:04:00 lr: 0.000979 loss: 4.1444 (4.0858) grad_norm: 0.9523 (1.0591) time: 0.5025 [2021-03-25 08:10:48 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 790/1251] eta: 0:03:55 lr: 0.000979 loss: 4.0700 (4.0841) grad_norm: 1.0114 (1.0598) time: 0.5055 [2021-03-25 08:10:53 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 800/1251] eta: 0:03:50 lr: 0.000979 loss: 4.0612 (4.0854) grad_norm: 1.0750 (1.0600) time: 0.5011 [2021-03-25 08:10:58 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 810/1251] eta: 0:03:45 lr: 0.000979 loss: 4.1334 (4.0863) grad_norm: 1.0499 (1.0591) time: 0.5055 [2021-03-25 08:11:03 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 820/1251] eta: 0:03:40 lr: 0.000979 loss: 4.0037 (4.0823) grad_norm: 0.9328 (1.0577) time: 0.5073 [2021-03-25 08:11:08 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 830/1251] eta: 0:03:35 lr: 0.000979 loss: 4.0037 (4.0826) grad_norm: 0.9363 (1.0578) time: 0.5101 [2021-03-25 08:11:13 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 840/1251] eta: 0:03:29 lr: 0.000979 loss: 4.0239 (4.0803) grad_norm: 1.1393 (1.0594) time: 0.5113 [2021-03-25 08:11:18 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 850/1251] eta: 0:03:24 lr: 0.000979 loss: 3.9301 (4.0784) grad_norm: 1.1421 (inf) time: 0.5041 [2021-03-25 08:11:23 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 860/1251] eta: 0:03:19 lr: 0.000979 loss: 3.7354 (4.0771) grad_norm: 1.0155 (inf) time: 0.5086 [2021-03-25 08:11:28 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 870/1251] eta: 0:03:14 lr: 0.000979 loss: 3.7354 (4.0736) grad_norm: 0.9814 (inf) time: 0.5141 [2021-03-25 08:11:33 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 880/1251] eta: 0:03:09 lr: 0.000979 loss: 4.0344 (4.0727) grad_norm: 1.0042 (inf) time: 0.5112 [2021-03-25 08:11:38 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 890/1251] eta: 0:03:04 lr: 0.000979 loss: 4.1888 (4.0745) grad_norm: 1.0427 (inf) time: 0.5074 [2021-03-25 08:11:43 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 900/1251] eta: 0:02:59 lr: 0.000979 loss: 4.1737 (4.0719) grad_norm: 0.9979 (inf) time: 0.5046 [2021-03-25 08:11:48 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 910/1251] eta: 0:02:54 lr: 0.000979 loss: 4.2630 (4.0744) grad_norm: 0.9585 (inf) time: 0.4995 [2021-03-25 08:11:54 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 920/1251] eta: 0:02:49 lr: 0.000979 loss: 4.3951 (4.0792) grad_norm: 1.1044 (inf) time: 0.5044 [2021-03-25 08:11:59 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 930/1251] eta: 0:02:43 lr: 0.000979 loss: 4.5174 (4.0840) grad_norm: 1.1436 (inf) time: 0.5043 [2021-03-25 08:12:03 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 940/1251] eta: 0:02:38 lr: 0.000979 loss: 4.4010 (4.0852) grad_norm: 1.0931 (inf) time: 0.4949 [2021-03-25 08:12:09 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 950/1251] eta: 0:02:33 lr: 0.000979 loss: 4.2517 (4.0853) grad_norm: 1.0426 (inf) time: 0.4970 [2021-03-25 08:12:13 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 960/1251] eta: 0:02:28 lr: 0.000979 loss: 4.2490 (4.0846) grad_norm: 1.0650 (inf) time: 0.5001 [2021-03-25 08:12:19 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 970/1251] eta: 0:02:23 lr: 0.000979 loss: 3.9585 (4.0839) grad_norm: 1.1951 (inf) time: 0.5000 [2021-03-25 08:12:23 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 980/1251] eta: 0:02:18 lr: 0.000979 loss: 4.1131 (4.0857) grad_norm: 1.0623 (inf) time: 0.4995 [2021-03-25 08:12:29 swin_small_patch4_window7_224] INFO: Epoch: [27] [ 990/1251] eta: 0:02:13 lr: 0.000979 loss: 4.3723 (4.0873) grad_norm: 0.9985 (inf) time: 0.5026 [2021-03-25 08:12:34 swin_small_patch4_window7_224] INFO: Epoch: [27] [1000/1251] eta: 0:02:07 lr: 0.000979 loss: 4.3723 (4.0894) grad_norm: 0.9953 (inf) time: 0.5085 [2021-03-25 08:12:39 swin_small_patch4_window7_224] INFO: Epoch: [27] [1010/1251] eta: 0:02:02 lr: 0.000979 loss: 4.2934 (4.0880) grad_norm: 0.9279 (inf) time: 0.5077 [2021-03-25 08:12:44 swin_small_patch4_window7_224] INFO: Epoch: [27] [1020/1251] eta: 0:01:57 lr: 0.000979 loss: 4.2282 (4.0883) grad_norm: 0.9709 (inf) time: 0.5078 [2021-03-25 08:12:49 swin_small_patch4_window7_224] INFO: Epoch: [27] [1030/1251] eta: 0:01:52 lr: 0.000979 loss: 4.2282 (4.0863) grad_norm: 1.0537 (inf) time: 0.5084 [2021-03-25 08:12:54 swin_small_patch4_window7_224] INFO: Epoch: [27] [1040/1251] eta: 0:01:47 lr: 0.000979 loss: 4.1170 (4.0857) grad_norm: 1.0233 (inf) time: 0.5064 [2021-03-25 08:12:59 swin_small_patch4_window7_224] INFO: Epoch: [27] [1050/1251] eta: 0:01:42 lr: 0.000979 loss: 4.0987 (4.0845) grad_norm: 1.0123 (inf) time: 0.5133 [2021-03-25 08:13:04 swin_small_patch4_window7_224] INFO: Epoch: [27] [1060/1251] eta: 0:01:37 lr: 0.000979 loss: 4.2397 (4.0877) grad_norm: 1.0280 (inf) time: 0.5064 [2021-03-25 08:13:09 swin_small_patch4_window7_224] INFO: Epoch: [27] [1070/1251] eta: 0:01:32 lr: 0.000979 loss: 4.2397 (4.0871) grad_norm: 1.0122 (inf) time: 0.4968 [2021-03-25 08:13:14 swin_small_patch4_window7_224] INFO: Epoch: [27] [1080/1251] eta: 0:01:27 lr: 0.000979 loss: 4.1793 (4.0881) grad_norm: 0.9502 (inf) time: 0.5027 [2021-03-25 08:13:19 swin_small_patch4_window7_224] INFO: Epoch: [27] [1090/1251] eta: 0:01:22 lr: 0.000979 loss: 4.2550 (4.0889) grad_norm: 0.9502 (inf) time: 0.5034 [2021-03-25 08:13:24 swin_small_patch4_window7_224] INFO: Epoch: [27] [1100/1251] eta: 0:01:16 lr: 0.000979 loss: 4.2619 (4.0914) grad_norm: 0.9927 (inf) time: 0.5035 [2021-03-25 08:13:29 swin_small_patch4_window7_224] INFO: Epoch: [27] [1110/1251] eta: 0:01:11 lr: 0.000979 loss: 4.2457 (4.0907) grad_norm: 1.0201 (inf) time: 0.5069 [2021-03-25 08:13:34 swin_small_patch4_window7_224] INFO: Epoch: [27] [1120/1251] eta: 0:01:06 lr: 0.000979 loss: 3.9223 (4.0901) grad_norm: 1.0797 (inf) time: 0.5100 [2021-03-25 08:13:39 swin_small_patch4_window7_224] INFO: Epoch: [27] [1130/1251] eta: 0:01:01 lr: 0.000979 loss: 4.1417 (4.0901) grad_norm: 1.0544 (inf) time: 0.5086 [2021-03-25 08:13:45 swin_small_patch4_window7_224] INFO: Epoch: [27] [1140/1251] eta: 0:00:56 lr: 0.000979 loss: 3.9791 (4.0896) grad_norm: 1.0636 (inf) time: 0.5059 [2021-03-25 08:13:50 swin_small_patch4_window7_224] INFO: Epoch: [27] [1150/1251] eta: 0:00:51 lr: 0.000979 loss: 3.9752 (4.0901) grad_norm: 1.0776 (inf) time: 0.5011 [2021-03-25 08:13:54 swin_small_patch4_window7_224] INFO: Epoch: [27] [1160/1251] eta: 0:00:46 lr: 0.000979 loss: 4.0727 (4.0897) grad_norm: 1.0406 (inf) time: 0.4976 [2021-03-25 08:14:00 swin_small_patch4_window7_224] INFO: Epoch: [27] [1170/1251] eta: 0:00:41 lr: 0.000979 loss: 4.2603 (4.0916) grad_norm: 1.0135 (inf) time: 0.5022 [2021-03-25 08:14:05 swin_small_patch4_window7_224] INFO: Epoch: [27] [1180/1251] eta: 0:00:36 lr: 0.000979 loss: 4.3537 (4.0934) grad_norm: 1.0044 (inf) time: 0.5043 [2021-03-25 08:14:10 swin_small_patch4_window7_224] INFO: Epoch: [27] [1190/1251] eta: 0:00:31 lr: 0.000979 loss: 4.4250 (4.0956) grad_norm: 1.0537 (inf) time: 0.5026 [2021-03-25 08:14:15 swin_small_patch4_window7_224] INFO: Epoch: [27] [1200/1251] eta: 0:00:25 lr: 0.000979 loss: 4.1408 (4.0949) grad_norm: 1.0537 (inf) time: 0.5053 [2021-03-25 08:14:20 swin_small_patch4_window7_224] INFO: Epoch: [27] [1210/1251] eta: 0:00:20 lr: 0.000979 loss: 4.0111 (4.0923) grad_norm: 1.0503 (inf) time: 0.5035 [2021-03-25 08:14:25 swin_small_patch4_window7_224] INFO: Epoch: [27] [1220/1251] eta: 0:00:15 lr: 0.000979 loss: 4.1700 (4.0932) grad_norm: 1.0355 (inf) time: 0.5063 [2021-03-25 08:14:30 swin_small_patch4_window7_224] INFO: Epoch: [27] [1230/1251] eta: 0:00:10 lr: 0.000979 loss: 4.2871 (4.0933) grad_norm: 0.9972 (inf) time: 0.5100 [2021-03-25 08:14:35 swin_small_patch4_window7_224] INFO: Epoch: [27] [1240/1251] eta: 0:00:05 lr: 0.000979 loss: 3.8287 (4.0918) grad_norm: 1.0014 (inf) time: 0.5024 [2021-03-25 08:14:40 swin_small_patch4_window7_224] INFO: Epoch: [27] [1250/1251] eta: 0:00:00 lr: 0.000979 loss: 3.8025 (4.0907) grad_norm: 1.0132 (inf) time: 0.5019 [2021-03-25 08:14:43 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:22 loss: 1.5114 (1.5114) acc1: 68.7500 (68.7500) acc5: 84.3750 (84.3750) [2021-03-25 08:14:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.4607 (1.4862) acc1: 67.1875 (66.3352) acc5: 87.5000 (86.2216) [2021-03-25 08:14:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.4607 (1.4744) acc1: 65.6250 (66.5923) acc5: 87.5000 (86.7560) [2021-03-25 08:14:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.5510 (1.4788) acc1: 64.0625 (66.0786) acc5: 87.5000 (86.7944) [2021-03-25 08:14:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.4204 (1.4591) acc1: 65.6250 (66.2348) acc5: 89.0625 (87.4619) [2021-03-25 08:14:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3833 (1.4590) acc1: 65.6250 (66.1440) acc5: 88.6792 (87.5520) [2021-03-25 08:14:56 swin_small_patch4_window7_224] INFO: * Acc@1 67.074 Acc@5 88.376 loss 1.441 [2021-03-25 08:14:56 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 67.1% [2021-03-25 08:14:56 swin_small_patch4_window7_224] INFO: Max accuracy: 67.07% [2021-03-25 08:15:00 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 0/1251] eta: 1:24:07 lr: 0.000979 loss: 4.3615 (4.3615) grad_norm: 1.1929 (1.1929) time: 4.0350 [2021-03-25 08:15:05 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 10/1251] eta: 0:17:46 lr: 0.000979 loss: 4.3615 (4.2888) grad_norm: 1.1948 (1.2518) time: 0.8590 [2021-03-25 08:15:10 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 20/1251] eta: 0:14:16 lr: 0.000979 loss: 3.9624 (4.0327) grad_norm: 1.1189 (1.1900) time: 0.5286 [2021-03-25 08:15:15 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 30/1251] eta: 0:12:53 lr: 0.000979 loss: 3.7833 (4.0328) grad_norm: 1.0559 (1.1682) time: 0.5090 [2021-03-25 08:15:21 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 40/1251] eta: 0:12:14 lr: 0.000979 loss: 4.2364 (4.0587) grad_norm: 1.0695 (1.1347) time: 0.5128 [2021-03-25 08:15:26 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 50/1251] eta: 0:11:43 lr: 0.000979 loss: 4.1839 (4.0162) grad_norm: 0.9355 (1.1068) time: 0.5116 [2021-03-25 08:15:31 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 60/1251] eta: 0:11:22 lr: 0.000979 loss: 4.1839 (4.0409) grad_norm: 0.9943 (1.1016) time: 0.5034 [2021-03-25 08:15:36 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 70/1251] eta: 0:11:03 lr: 0.000979 loss: 4.1885 (4.0445) grad_norm: 1.0977 (1.1008) time: 0.5017 [2021-03-25 08:15:41 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 80/1251] eta: 0:10:49 lr: 0.000979 loss: 3.9937 (4.0256) grad_norm: 1.0623 (1.0949) time: 0.5008 [2021-03-25 08:15:46 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 90/1251] eta: 0:10:37 lr: 0.000979 loss: 4.1936 (4.0705) grad_norm: 1.0368 (1.0884) time: 0.5046 [2021-03-25 08:15:51 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 100/1251] eta: 0:10:27 lr: 0.000979 loss: 4.4605 (4.0966) grad_norm: 1.0645 (1.0867) time: 0.5057 [2021-03-25 08:15:56 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 110/1251] eta: 0:10:18 lr: 0.000979 loss: 4.4605 (4.1194) grad_norm: 1.0536 (1.0825) time: 0.5113 [2021-03-25 08:16:01 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 120/1251] eta: 0:10:10 lr: 0.000979 loss: 4.2706 (4.1089) grad_norm: 1.0279 (1.0797) time: 0.5116 [2021-03-25 08:16:06 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 130/1251] eta: 0:10:01 lr: 0.000979 loss: 4.0139 (4.1013) grad_norm: 1.0135 (1.0791) time: 0.5050 [2021-03-25 08:16:11 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 140/1251] eta: 0:09:53 lr: 0.000979 loss: 4.2933 (4.1232) grad_norm: 1.0466 (1.0778) time: 0.5039 [2021-03-25 08:16:16 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 150/1251] eta: 0:09:46 lr: 0.000979 loss: 4.4566 (4.1333) grad_norm: 1.0466 (1.0800) time: 0.5036 [2021-03-25 08:16:21 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 160/1251] eta: 0:09:38 lr: 0.000979 loss: 4.4100 (4.1533) grad_norm: 0.9541 (1.0712) time: 0.5023 [2021-03-25 08:16:26 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 170/1251] eta: 0:09:31 lr: 0.000979 loss: 4.2659 (4.1537) grad_norm: 0.9541 (1.0674) time: 0.5048 [2021-03-25 08:16:31 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 180/1251] eta: 0:09:25 lr: 0.000979 loss: 4.1571 (4.1597) grad_norm: 0.9680 (1.0618) time: 0.5093 [2021-03-25 08:16:37 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 190/1251] eta: 0:09:19 lr: 0.000979 loss: 4.1261 (4.1557) grad_norm: 0.9572 (1.0600) time: 0.5139 [2021-03-25 08:16:42 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 200/1251] eta: 0:09:13 lr: 0.000979 loss: 4.1261 (4.1504) grad_norm: 0.9778 (1.0577) time: 0.5134 [2021-03-25 08:16:47 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 210/1251] eta: 0:09:07 lr: 0.000979 loss: 4.0377 (4.1449) grad_norm: 0.9778 (1.0540) time: 0.5126 [2021-03-25 08:16:52 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 220/1251] eta: 0:09:01 lr: 0.000979 loss: 4.3010 (4.1587) grad_norm: 1.0216 (1.0537) time: 0.5131 [2021-03-25 08:16:57 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 230/1251] eta: 0:08:56 lr: 0.000979 loss: 4.3680 (4.1631) grad_norm: 1.0464 (1.0543) time: 0.5133 [2021-03-25 08:17:02 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 240/1251] eta: 0:08:50 lr: 0.000979 loss: 4.2763 (4.1578) grad_norm: 1.0544 (1.0567) time: 0.5119 [2021-03-25 08:17:07 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 250/1251] eta: 0:08:44 lr: 0.000979 loss: 3.9343 (4.1414) grad_norm: 1.0304 (1.0568) time: 0.5084 [2021-03-25 08:17:12 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 260/1251] eta: 0:08:38 lr: 0.000979 loss: 3.8516 (4.1289) grad_norm: 1.0221 (1.0568) time: 0.5074 [2021-03-25 08:17:18 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 270/1251] eta: 0:08:32 lr: 0.000979 loss: 3.7911 (4.1236) grad_norm: 0.9797 (1.0561) time: 0.5100 [2021-03-25 08:17:23 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 280/1251] eta: 0:08:27 lr: 0.000979 loss: 4.0480 (4.1217) grad_norm: 1.0164 (1.0575) time: 0.5121 [2021-03-25 08:17:28 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 290/1251] eta: 0:08:21 lr: 0.000979 loss: 4.0795 (4.1182) grad_norm: 1.0335 (1.0569) time: 0.5116 [2021-03-25 08:17:33 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 300/1251] eta: 0:08:15 lr: 0.000979 loss: 4.0795 (4.1197) grad_norm: 1.0391 (1.0565) time: 0.5101 [2021-03-25 08:17:38 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 310/1251] eta: 0:08:10 lr: 0.000979 loss: 4.0887 (4.1166) grad_norm: 1.0562 (1.0573) time: 0.5098 [2021-03-25 08:17:43 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 320/1251] eta: 0:08:04 lr: 0.000978 loss: 4.0239 (4.1151) grad_norm: 1.0544 (1.0591) time: 0.5102 [2021-03-25 08:17:48 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 330/1251] eta: 0:07:59 lr: 0.000978 loss: 4.0146 (4.1042) grad_norm: 1.1227 (1.0616) time: 0.5066 [2021-03-25 08:17:53 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 340/1251] eta: 0:07:53 lr: 0.000978 loss: 4.0146 (4.1032) grad_norm: 1.0947 (1.0616) time: 0.5057 [2021-03-25 08:17:58 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 350/1251] eta: 0:07:47 lr: 0.000978 loss: 3.9953 (4.0964) grad_norm: 1.0240 (1.0603) time: 0.5005 [2021-03-25 08:18:03 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 360/1251] eta: 0:07:42 lr: 0.000978 loss: 3.9523 (4.0970) grad_norm: 0.9843 (1.0582) time: 0.4984 [2021-03-25 08:18:08 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 370/1251] eta: 0:07:36 lr: 0.000978 loss: 3.7312 (4.0842) grad_norm: 0.9694 (1.0562) time: 0.5048 [2021-03-25 08:18:13 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 380/1251] eta: 0:07:31 lr: 0.000978 loss: 3.7312 (4.0779) grad_norm: 0.9850 (1.0550) time: 0.5071 [2021-03-25 08:18:18 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 390/1251] eta: 0:07:25 lr: 0.000978 loss: 3.8505 (4.0782) grad_norm: 1.0227 (1.0557) time: 0.5072 [2021-03-25 08:18:23 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 400/1251] eta: 0:07:20 lr: 0.000978 loss: 4.1334 (4.0801) grad_norm: 1.0618 (1.0564) time: 0.5041 [2021-03-25 08:18:28 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 410/1251] eta: 0:07:14 lr: 0.000978 loss: 4.1334 (4.0833) grad_norm: 0.9849 (1.0550) time: 0.5036 [2021-03-25 08:18:34 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 420/1251] eta: 0:07:09 lr: 0.000978 loss: 4.1331 (4.0773) grad_norm: 1.0147 (1.0567) time: 0.5076 [2021-03-25 08:18:39 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 430/1251] eta: 0:07:04 lr: 0.000978 loss: 3.9930 (4.0731) grad_norm: 1.0196 (1.0554) time: 0.5101 [2021-03-25 08:18:44 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 440/1251] eta: 0:06:58 lr: 0.000978 loss: 4.1363 (4.0791) grad_norm: 1.0005 (1.0552) time: 0.5076 [2021-03-25 08:18:49 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 450/1251] eta: 0:06:53 lr: 0.000978 loss: 4.2461 (4.0793) grad_norm: 1.0395 (1.0555) time: 0.5002 [2021-03-25 08:18:54 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 460/1251] eta: 0:06:47 lr: 0.000978 loss: 4.2335 (4.0799) grad_norm: 1.0241 (1.0560) time: 0.5000 [2021-03-25 08:18:59 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 470/1251] eta: 0:06:42 lr: 0.000978 loss: 4.3749 (4.0801) grad_norm: 1.0744 (1.0579) time: 0.5024 [2021-03-25 08:19:04 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 480/1251] eta: 0:06:37 lr: 0.000978 loss: 4.3310 (4.0786) grad_norm: 1.1280 (1.0606) time: 0.4990 [2021-03-25 08:19:09 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 490/1251] eta: 0:06:31 lr: 0.000978 loss: 4.3310 (4.0836) grad_norm: 1.1108 (1.0611) time: 0.5012 [2021-03-25 08:19:14 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 500/1251] eta: 0:06:26 lr: 0.000978 loss: 4.2387 (4.0802) grad_norm: 1.0356 (1.0602) time: 0.5043 [2021-03-25 08:19:19 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 510/1251] eta: 0:06:21 lr: 0.000978 loss: 3.7458 (4.0728) grad_norm: 1.0087 (1.0598) time: 0.5005 [2021-03-25 08:19:24 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 520/1251] eta: 0:06:15 lr: 0.000978 loss: 3.9461 (4.0724) grad_norm: 0.9669 (1.0573) time: 0.5006 [2021-03-25 08:19:29 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 530/1251] eta: 0:06:10 lr: 0.000978 loss: 4.2229 (4.0728) grad_norm: 0.9875 (1.0570) time: 0.5093 [2021-03-25 08:19:34 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 540/1251] eta: 0:06:05 lr: 0.000978 loss: 4.2546 (4.0740) grad_norm: 1.0487 (1.0567) time: 0.5099 [2021-03-25 08:19:39 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 550/1251] eta: 0:06:00 lr: 0.000978 loss: 4.0968 (4.0749) grad_norm: 1.0541 (1.0563) time: 0.5230 [2021-03-25 08:19:45 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 560/1251] eta: 0:05:55 lr: 0.000978 loss: 4.2467 (4.0751) grad_norm: 1.0087 (1.0564) time: 0.5326 [2021-03-25 08:19:50 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 570/1251] eta: 0:05:50 lr: 0.000978 loss: 4.3824 (4.0781) grad_norm: 1.0012 (1.0553) time: 0.5116 [2021-03-25 08:19:55 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 580/1251] eta: 0:05:45 lr: 0.000978 loss: 4.4469 (4.0845) grad_norm: 1.0012 (1.0546) time: 0.5023 [2021-03-25 08:20:00 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 590/1251] eta: 0:05:39 lr: 0.000978 loss: 4.3548 (4.0808) grad_norm: 1.0076 (1.0540) time: 0.5088 [2021-03-25 08:20:05 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 600/1251] eta: 0:05:34 lr: 0.000978 loss: 4.3548 (4.0871) grad_norm: 1.0280 (1.0538) time: 0.5144 [2021-03-25 08:20:10 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 610/1251] eta: 0:05:29 lr: 0.000978 loss: 4.3809 (4.0860) grad_norm: 1.0625 (1.0547) time: 0.5111 [2021-03-25 08:20:15 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 620/1251] eta: 0:05:24 lr: 0.000978 loss: 3.8431 (4.0791) grad_norm: 1.0617 (1.0539) time: 0.5051 [2021-03-25 08:20:20 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 630/1251] eta: 0:05:19 lr: 0.000978 loss: 4.0058 (4.0800) grad_norm: 0.9871 (1.0537) time: 0.5049 [2021-03-25 08:20:25 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 640/1251] eta: 0:05:13 lr: 0.000978 loss: 4.0058 (4.0764) grad_norm: 0.9972 (1.0541) time: 0.5050 [2021-03-25 08:20:30 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 650/1251] eta: 0:05:08 lr: 0.000978 loss: 3.7872 (4.0757) grad_norm: 1.0135 (1.0540) time: 0.5068 [2021-03-25 08:20:35 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 660/1251] eta: 0:05:03 lr: 0.000978 loss: 4.2160 (4.0736) grad_norm: 0.9854 (1.0529) time: 0.5071 [2021-03-25 08:20:40 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 670/1251] eta: 0:04:58 lr: 0.000978 loss: 4.2436 (4.0740) grad_norm: 0.9795 (1.0522) time: 0.5042 [2021-03-25 08:20:45 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 680/1251] eta: 0:04:53 lr: 0.000978 loss: 4.2757 (4.0743) grad_norm: 0.9755 (1.0509) time: 0.5058 [2021-03-25 08:20:50 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 690/1251] eta: 0:04:47 lr: 0.000978 loss: 3.7392 (4.0667) grad_norm: 0.9873 (1.0517) time: 0.5065 [2021-03-25 08:20:55 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 700/1251] eta: 0:04:42 lr: 0.000978 loss: 3.7617 (4.0688) grad_norm: 1.0358 (1.0511) time: 0.5031 [2021-03-25 08:21:01 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 710/1251] eta: 0:04:37 lr: 0.000978 loss: 4.0437 (4.0647) grad_norm: 1.0358 (1.0520) time: 0.5050 [2021-03-25 08:21:06 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 720/1251] eta: 0:04:32 lr: 0.000978 loss: 4.1905 (4.0663) grad_norm: 1.0556 (1.0518) time: 0.5093 [2021-03-25 08:21:11 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 730/1251] eta: 0:04:27 lr: 0.000978 loss: 4.2604 (4.0706) grad_norm: 1.0445 (1.0513) time: 0.5157 [2021-03-25 08:21:16 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 740/1251] eta: 0:04:22 lr: 0.000978 loss: 3.9717 (4.0626) grad_norm: 1.0235 (1.0517) time: 0.5292 [2021-03-25 08:21:22 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 750/1251] eta: 0:04:17 lr: 0.000978 loss: 3.6518 (4.0615) grad_norm: 1.0167 (1.0512) time: 0.5329 [2021-03-25 08:21:27 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 760/1251] eta: 0:04:12 lr: 0.000978 loss: 4.1023 (4.0639) grad_norm: 0.9941 (1.0509) time: 0.5197 [2021-03-25 08:21:32 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 770/1251] eta: 0:04:06 lr: 0.000978 loss: 4.2335 (4.0670) grad_norm: 1.0099 (1.0506) time: 0.5065 [2021-03-25 08:21:37 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 780/1251] eta: 0:04:01 lr: 0.000978 loss: 4.2335 (4.0664) grad_norm: 1.0337 (1.0506) time: 0.5010 [2021-03-25 08:21:42 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 790/1251] eta: 0:03:56 lr: 0.000978 loss: 3.9619 (4.0654) grad_norm: 1.0375 (1.0502) time: 0.5078 [2021-03-25 08:21:47 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 800/1251] eta: 0:03:51 lr: 0.000978 loss: 4.1724 (4.0686) grad_norm: 0.9635 (1.0493) time: 0.5107 [2021-03-25 08:21:52 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 810/1251] eta: 0:03:46 lr: 0.000978 loss: 4.1874 (4.0679) grad_norm: 0.9829 (1.0492) time: 0.5080 [2021-03-25 08:21:57 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 820/1251] eta: 0:03:41 lr: 0.000978 loss: 4.1874 (4.0681) grad_norm: 1.1001 (1.0509) time: 0.5091 [2021-03-25 08:22:02 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 830/1251] eta: 0:03:35 lr: 0.000978 loss: 4.1140 (4.0638) grad_norm: 1.0795 (1.0507) time: 0.5041 [2021-03-25 08:22:07 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 840/1251] eta: 0:03:30 lr: 0.000978 loss: 3.7271 (4.0610) grad_norm: 1.0020 (1.0500) time: 0.5036 [2021-03-25 08:22:12 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 850/1251] eta: 0:03:25 lr: 0.000978 loss: 3.8447 (4.0612) grad_norm: 1.0207 (1.0497) time: 0.5094 [2021-03-25 08:22:17 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 860/1251] eta: 0:03:20 lr: 0.000978 loss: 4.0197 (4.0591) grad_norm: 1.0303 (1.0502) time: 0.5087 [2021-03-25 08:22:22 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 870/1251] eta: 0:03:15 lr: 0.000978 loss: 3.8031 (4.0564) grad_norm: 1.0216 (1.0502) time: 0.5054 [2021-03-25 08:22:27 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 880/1251] eta: 0:03:10 lr: 0.000978 loss: 4.1873 (4.0581) grad_norm: 1.0110 (1.0503) time: 0.5057 [2021-03-25 08:22:33 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 890/1251] eta: 0:03:04 lr: 0.000978 loss: 4.0688 (4.0565) grad_norm: 0.9968 (1.0497) time: 0.5058 [2021-03-25 08:22:37 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 900/1251] eta: 0:02:59 lr: 0.000978 loss: 4.0688 (4.0576) grad_norm: 0.9734 (1.0493) time: 0.5004 [2021-03-25 08:22:43 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 910/1251] eta: 0:02:54 lr: 0.000978 loss: 4.3022 (4.0588) grad_norm: 0.9733 (1.0482) time: 0.4997 [2021-03-25 08:22:48 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 920/1251] eta: 0:02:49 lr: 0.000978 loss: 4.1471 (4.0603) grad_norm: 1.0151 (1.0489) time: 0.5066 [2021-03-25 08:22:53 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 930/1251] eta: 0:02:44 lr: 0.000978 loss: 4.3001 (4.0622) grad_norm: 1.0763 (1.0491) time: 0.5111 [2021-03-25 08:22:58 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 940/1251] eta: 0:02:39 lr: 0.000978 loss: 4.3012 (4.0607) grad_norm: 1.0136 (1.0487) time: 0.5138 [2021-03-25 08:23:03 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 950/1251] eta: 0:02:34 lr: 0.000978 loss: 3.5987 (4.0551) grad_norm: 1.0377 (1.0492) time: 0.5072 [2021-03-25 08:23:08 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 960/1251] eta: 0:02:28 lr: 0.000978 loss: 3.6443 (4.0536) grad_norm: 1.0315 (1.0493) time: 0.5031 [2021-03-25 08:23:13 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 970/1251] eta: 0:02:23 lr: 0.000978 loss: 3.8688 (4.0518) grad_norm: 1.0315 (1.0501) time: 0.5116 [2021-03-25 08:23:18 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 980/1251] eta: 0:02:18 lr: 0.000978 loss: 3.9641 (4.0514) grad_norm: 1.0358 (1.0499) time: 0.5142 [2021-03-25 08:23:23 swin_small_patch4_window7_224] INFO: Epoch: [28] [ 990/1251] eta: 0:02:13 lr: 0.000978 loss: 3.9889 (4.0513) grad_norm: 1.0358 (1.0499) time: 0.5082 [2021-03-25 08:23:28 swin_small_patch4_window7_224] INFO: Epoch: [28] [1000/1251] eta: 0:02:08 lr: 0.000978 loss: 4.0676 (4.0515) grad_norm: 1.0638 (1.0498) time: 0.5029 [2021-03-25 08:23:33 swin_small_patch4_window7_224] INFO: Epoch: [28] [1010/1251] eta: 0:02:03 lr: 0.000978 loss: 4.1768 (4.0513) grad_norm: 1.0407 (1.0495) time: 0.5053 [2021-03-25 08:23:38 swin_small_patch4_window7_224] INFO: Epoch: [28] [1020/1251] eta: 0:01:58 lr: 0.000978 loss: 4.2134 (4.0539) grad_norm: 0.9767 (1.0486) time: 0.5091 [2021-03-25 08:23:44 swin_small_patch4_window7_224] INFO: Epoch: [28] [1030/1251] eta: 0:01:53 lr: 0.000978 loss: 3.9921 (4.0514) grad_norm: 0.9041 (1.0476) time: 0.5100 [2021-03-25 08:23:49 swin_small_patch4_window7_224] INFO: Epoch: [28] [1040/1251] eta: 0:01:47 lr: 0.000978 loss: 3.9019 (4.0524) grad_norm: 0.9475 (1.0474) time: 0.5124 [2021-03-25 08:23:54 swin_small_patch4_window7_224] INFO: Epoch: [28] [1050/1251] eta: 0:01:42 lr: 0.000978 loss: 4.0577 (4.0510) grad_norm: 0.9603 (1.0471) time: 0.5146 [2021-03-25 08:23:59 swin_small_patch4_window7_224] INFO: Epoch: [28] [1060/1251] eta: 0:01:37 lr: 0.000978 loss: 3.8407 (4.0500) grad_norm: 0.9779 (1.0469) time: 0.5077 [2021-03-25 08:24:04 swin_small_patch4_window7_224] INFO: Epoch: [28] [1070/1251] eta: 0:01:32 lr: 0.000978 loss: 3.9212 (4.0494) grad_norm: 1.0464 (1.0480) time: 0.4991 [2021-03-25 08:24:09 swin_small_patch4_window7_224] INFO: Epoch: [28] [1080/1251] eta: 0:01:27 lr: 0.000978 loss: 4.1645 (4.0493) grad_norm: 1.0230 (1.0470) time: 0.5016 [2021-03-25 08:24:14 swin_small_patch4_window7_224] INFO: Epoch: [28] [1090/1251] eta: 0:01:22 lr: 0.000978 loss: 4.0685 (4.0481) grad_norm: 0.9465 (1.0465) time: 0.4986 [2021-03-25 08:24:19 swin_small_patch4_window7_224] INFO: Epoch: [28] [1100/1251] eta: 0:01:17 lr: 0.000978 loss: 3.9531 (4.0462) grad_norm: 0.9879 (1.0464) time: 0.4969 [2021-03-25 08:24:24 swin_small_patch4_window7_224] INFO: Epoch: [28] [1110/1251] eta: 0:01:12 lr: 0.000978 loss: 4.0294 (4.0468) grad_norm: 1.0044 (1.0467) time: 0.5043 [2021-03-25 08:24:29 swin_small_patch4_window7_224] INFO: Epoch: [28] [1120/1251] eta: 0:01:06 lr: 0.000978 loss: 4.1184 (4.0458) grad_norm: 1.0737 (1.0475) time: 0.5064 [2021-03-25 08:24:34 swin_small_patch4_window7_224] INFO: Epoch: [28] [1130/1251] eta: 0:01:01 lr: 0.000977 loss: 4.2824 (4.0479) grad_norm: 1.0737 (1.0473) time: 0.5033 [2021-03-25 08:24:39 swin_small_patch4_window7_224] INFO: Epoch: [28] [1140/1251] eta: 0:00:56 lr: 0.000977 loss: 4.2128 (4.0473) grad_norm: 1.0568 (1.0472) time: 0.5023 [2021-03-25 08:24:44 swin_small_patch4_window7_224] INFO: Epoch: [28] [1150/1251] eta: 0:00:51 lr: 0.000977 loss: 4.1461 (4.0486) grad_norm: 1.0630 (1.0483) time: 0.5070 [2021-03-25 08:24:49 swin_small_patch4_window7_224] INFO: Epoch: [28] [1160/1251] eta: 0:00:46 lr: 0.000977 loss: 3.9919 (4.0481) grad_norm: 1.0293 (1.0483) time: 0.5101 [2021-03-25 08:24:54 swin_small_patch4_window7_224] INFO: Epoch: [28] [1170/1251] eta: 0:00:41 lr: 0.000977 loss: 4.0100 (4.0482) grad_norm: 1.0267 (1.0486) time: 0.5136 [2021-03-25 08:24:59 swin_small_patch4_window7_224] INFO: Epoch: [28] [1180/1251] eta: 0:00:36 lr: 0.000977 loss: 4.1032 (4.0479) grad_norm: 1.0237 (1.0483) time: 0.5101 [2021-03-25 08:25:04 swin_small_patch4_window7_224] INFO: Epoch: [28] [1190/1251] eta: 0:00:31 lr: 0.000977 loss: 3.9492 (4.0475) grad_norm: 1.0344 (1.0488) time: 0.5025 [2021-03-25 08:25:10 swin_small_patch4_window7_224] INFO: Epoch: [28] [1200/1251] eta: 0:00:26 lr: 0.000977 loss: 3.9116 (4.0463) grad_norm: 1.0465 (1.0491) time: 0.5048 [2021-03-25 08:25:15 swin_small_patch4_window7_224] INFO: Epoch: [28] [1210/1251] eta: 0:00:20 lr: 0.000977 loss: 3.9170 (4.0457) grad_norm: 0.9978 (1.0491) time: 0.5054 [2021-03-25 08:25:20 swin_small_patch4_window7_224] INFO: Epoch: [28] [1220/1251] eta: 0:00:15 lr: 0.000977 loss: 4.0393 (4.0468) grad_norm: 1.0427 (1.0494) time: 0.5043 [2021-03-25 08:25:25 swin_small_patch4_window7_224] INFO: Epoch: [28] [1230/1251] eta: 0:00:10 lr: 0.000977 loss: 4.2633 (4.0469) grad_norm: 1.0293 (1.0491) time: 0.5027 [2021-03-25 08:25:30 swin_small_patch4_window7_224] INFO: Epoch: [28] [1240/1251] eta: 0:00:05 lr: 0.000977 loss: 4.2953 (4.0488) grad_norm: 1.0732 (1.0505) time: 0.5002 [2021-03-25 08:25:35 swin_small_patch4_window7_224] INFO: Epoch: [28] [1250/1251] eta: 0:00:00 lr: 0.000977 loss: 4.3771 (4.0516) grad_norm: 1.1214 (1.0504) time: 0.5032 [2021-03-25 08:25:43 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:25 loss: 1.3667 (1.3667) acc1: 65.6250 (65.6250) acc5: 92.1875 (92.1875) [2021-03-25 08:25:45 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.5678 (1.4985) acc1: 65.6250 (64.6307) acc5: 90.6250 (88.4943) [2021-03-25 08:25:47 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.5095 (1.4624) acc1: 67.1875 (66.5923) acc5: 87.5000 (88.4673) [2021-03-25 08:25:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3603 (1.4300) acc1: 68.7500 (66.9859) acc5: 89.0625 (88.4577) [2021-03-25 08:25:51 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.4131 (1.4245) acc1: 67.1875 (66.8445) acc5: 87.5000 (88.1098) [2021-03-25 08:25:52 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4009 (1.4072) acc1: 67.9245 (67.4880) acc5: 87.5000 (88.3520) [2021-03-25 08:25:54 swin_small_patch4_window7_224] INFO: * Acc@1 67.818 Acc@5 88.734 loss 1.388 [2021-03-25 08:25:54 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 67.8% [2021-03-25 08:25:54 swin_small_patch4_window7_224] INFO: Max accuracy: 67.82% [2021-03-25 08:25:58 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 0/1251] eta: 1:27:56 lr: 0.000977 loss: 4.3267 (4.3267) grad_norm: 1.0298 (1.0298) time: 4.2181 [2021-03-25 08:26:03 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 10/1251] eta: 0:17:27 lr: 0.000977 loss: 4.1582 (4.2069) grad_norm: 0.9605 (0.9309) time: 0.8442 [2021-03-25 08:26:08 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 20/1251] eta: 0:13:56 lr: 0.000977 loss: 4.0358 (3.9682) grad_norm: 0.9955 (1.0054) time: 0.5026 [2021-03-25 08:26:14 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 30/1251] eta: 0:12:42 lr: 0.000977 loss: 3.9901 (3.9973) grad_norm: 1.0299 (1.0111) time: 0.5042 [2021-03-25 08:26:19 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 40/1251] eta: 0:12:02 lr: 0.000977 loss: 4.0617 (3.9818) grad_norm: 1.0094 (1.0074) time: 0.5099 [2021-03-25 08:26:24 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 50/1251] eta: 0:11:36 lr: 0.000977 loss: 3.9938 (3.9697) grad_norm: 1.0094 (1.0175) time: 0.5098 [2021-03-25 08:26:29 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 60/1251] eta: 0:11:17 lr: 0.000977 loss: 3.6956 (3.9298) grad_norm: 0.9771 (1.0167) time: 0.5104 [2021-03-25 08:26:34 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 70/1251] eta: 0:10:59 lr: 0.000977 loss: 3.6786 (3.9154) grad_norm: 0.9994 (1.0211) time: 0.5050 [2021-03-25 08:26:39 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 80/1251] eta: 0:10:46 lr: 0.000977 loss: 4.0746 (3.9500) grad_norm: 1.0240 (1.0220) time: 0.5036 [2021-03-25 08:26:44 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 90/1251] eta: 0:10:35 lr: 0.000977 loss: 4.1041 (3.9647) grad_norm: 1.0240 (1.0266) time: 0.5058 [2021-03-25 08:26:49 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 100/1251] eta: 0:10:24 lr: 0.000977 loss: 4.1477 (3.9746) grad_norm: 1.0332 (1.0340) time: 0.5043 [2021-03-25 08:26:54 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 110/1251] eta: 0:10:15 lr: 0.000977 loss: 4.0928 (3.9570) grad_norm: 1.0398 (1.0390) time: 0.5070 [2021-03-25 08:26:59 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 120/1251] eta: 0:10:06 lr: 0.000977 loss: 4.0928 (3.9827) grad_norm: 1.0223 (1.0360) time: 0.5027 [2021-03-25 08:27:04 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 130/1251] eta: 0:09:59 lr: 0.000977 loss: 4.2289 (3.9892) grad_norm: 0.9760 (1.0331) time: 0.5083 [2021-03-25 08:27:09 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 140/1251] eta: 0:09:51 lr: 0.000977 loss: 4.0486 (3.9731) grad_norm: 0.9752 (1.0326) time: 0.5116 [2021-03-25 08:27:14 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 150/1251] eta: 0:09:44 lr: 0.000977 loss: 3.9633 (3.9666) grad_norm: 0.9348 (1.0262) time: 0.5064 [2021-03-25 08:27:19 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 160/1251] eta: 0:09:37 lr: 0.000977 loss: 4.2780 (3.9980) grad_norm: 0.9254 (1.0247) time: 0.5054 [2021-03-25 08:27:25 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 170/1251] eta: 0:09:31 lr: 0.000977 loss: 4.2625 (3.9995) grad_norm: 1.0720 (1.0277) time: 0.5068 [2021-03-25 08:27:30 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 180/1251] eta: 0:09:25 lr: 0.000977 loss: 4.0271 (3.9989) grad_norm: 1.0832 (1.0317) time: 0.5151 [2021-03-25 08:27:35 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 190/1251] eta: 0:09:18 lr: 0.000977 loss: 3.9382 (3.9920) grad_norm: 1.1074 (1.0365) time: 0.5097 [2021-03-25 08:27:40 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 200/1251] eta: 0:09:12 lr: 0.000977 loss: 3.7640 (3.9773) grad_norm: 1.1315 (1.0403) time: 0.5103 [2021-03-25 08:27:45 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 210/1251] eta: 0:09:06 lr: 0.000977 loss: 4.1505 (3.9843) grad_norm: 1.0642 (1.0396) time: 0.5126 [2021-03-25 08:27:50 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 220/1251] eta: 0:09:00 lr: 0.000977 loss: 4.3964 (3.9913) grad_norm: 1.0996 (1.0435) time: 0.5054 [2021-03-25 08:27:55 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 230/1251] eta: 0:08:54 lr: 0.000977 loss: 4.3177 (4.0001) grad_norm: 1.1129 (1.0465) time: 0.5089 [2021-03-25 08:28:00 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 240/1251] eta: 0:08:48 lr: 0.000977 loss: 4.3177 (4.0107) grad_norm: 1.0469 (1.0463) time: 0.5087 [2021-03-25 08:28:05 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 250/1251] eta: 0:08:42 lr: 0.000977 loss: 4.1181 (4.0124) grad_norm: 1.0601 (1.0499) time: 0.5077 [2021-03-25 08:28:10 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 260/1251] eta: 0:08:37 lr: 0.000977 loss: 4.1181 (4.0107) grad_norm: 1.0709 (1.0527) time: 0.5093 [2021-03-25 08:28:15 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 270/1251] eta: 0:08:31 lr: 0.000977 loss: 4.1968 (4.0122) grad_norm: 1.1404 (1.0565) time: 0.5034 [2021-03-25 08:28:21 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 280/1251] eta: 0:08:25 lr: 0.000977 loss: 4.0952 (4.0094) grad_norm: 1.1267 (1.0590) time: 0.5015 [2021-03-25 08:28:26 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 290/1251] eta: 0:08:19 lr: 0.000977 loss: 3.8806 (4.0049) grad_norm: 1.0308 (1.0574) time: 0.5069 [2021-03-25 08:28:31 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 300/1251] eta: 0:08:14 lr: 0.000977 loss: 3.7849 (4.0047) grad_norm: 1.0059 (1.0591) time: 0.5087 [2021-03-25 08:28:36 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 310/1251] eta: 0:08:08 lr: 0.000977 loss: 4.2216 (4.0126) grad_norm: 1.0019 (1.0600) time: 0.5046 [2021-03-25 08:28:41 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 320/1251] eta: 0:08:02 lr: 0.000977 loss: 4.2308 (4.0164) grad_norm: 1.0687 (1.0618) time: 0.5037 [2021-03-25 08:28:46 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 330/1251] eta: 0:07:57 lr: 0.000977 loss: 4.2659 (4.0194) grad_norm: 1.0471 (1.0613) time: 0.5068 [2021-03-25 08:28:51 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 340/1251] eta: 0:07:51 lr: 0.000977 loss: 4.2420 (4.0169) grad_norm: 1.0400 (1.0597) time: 0.5083 [2021-03-25 08:28:56 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 350/1251] eta: 0:07:46 lr: 0.000977 loss: 3.9300 (4.0147) grad_norm: 0.9436 (1.0574) time: 0.5025 [2021-03-25 08:29:01 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 360/1251] eta: 0:07:40 lr: 0.000977 loss: 3.9799 (4.0214) grad_norm: 0.9399 (1.0565) time: 0.4997 [2021-03-25 08:29:06 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 370/1251] eta: 0:07:35 lr: 0.000977 loss: 4.3023 (4.0203) grad_norm: 0.9601 (1.0549) time: 0.5039 [2021-03-25 08:29:11 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 380/1251] eta: 0:07:29 lr: 0.000977 loss: 4.1865 (4.0261) grad_norm: 0.9936 (1.0582) time: 0.5071 [2021-03-25 08:29:16 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 390/1251] eta: 0:07:24 lr: 0.000977 loss: 4.2344 (4.0318) grad_norm: 1.0026 (1.0564) time: 0.5065 [2021-03-25 08:29:21 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 400/1251] eta: 0:07:19 lr: 0.000977 loss: 4.1167 (4.0267) grad_norm: 1.0008 (1.0557) time: 0.5053 [2021-03-25 08:29:26 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 410/1251] eta: 0:07:13 lr: 0.000977 loss: 4.0016 (4.0248) grad_norm: 1.0728 (1.0585) time: 0.5072 [2021-03-25 08:29:31 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 420/1251] eta: 0:07:08 lr: 0.000977 loss: 3.8166 (4.0197) grad_norm: 1.0894 (1.0584) time: 0.5102 [2021-03-25 08:29:36 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 430/1251] eta: 0:07:03 lr: 0.000977 loss: 3.9479 (4.0212) grad_norm: 0.9899 (1.0574) time: 0.5087 [2021-03-25 08:29:42 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 440/1251] eta: 0:06:57 lr: 0.000977 loss: 4.1005 (4.0202) grad_norm: 0.9807 (1.0576) time: 0.5077 [2021-03-25 08:29:47 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 450/1251] eta: 0:06:52 lr: 0.000977 loss: 4.0622 (4.0199) grad_norm: 1.0209 (1.0577) time: 0.5088 [2021-03-25 08:29:52 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 460/1251] eta: 0:06:47 lr: 0.000977 loss: 4.1769 (4.0188) grad_norm: 1.0903 (1.0591) time: 0.5071 [2021-03-25 08:29:57 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 470/1251] eta: 0:06:42 lr: 0.000977 loss: 4.2315 (4.0190) grad_norm: 1.0903 (1.0598) time: 0.5092 [2021-03-25 08:30:02 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 480/1251] eta: 0:06:36 lr: 0.000977 loss: 4.2835 (4.0287) grad_norm: 1.0362 (1.0595) time: 0.5090 [2021-03-25 08:30:07 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 490/1251] eta: 0:06:31 lr: 0.000977 loss: 4.3367 (4.0312) grad_norm: 0.9848 (1.0606) time: 0.5044 [2021-03-25 08:30:12 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 500/1251] eta: 0:06:26 lr: 0.000977 loss: 3.9753 (4.0278) grad_norm: 0.9803 (1.0603) time: 0.5067 [2021-03-25 08:30:17 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 510/1251] eta: 0:06:21 lr: 0.000977 loss: 3.8951 (4.0262) grad_norm: 1.0489 (1.0610) time: 0.5100 [2021-03-25 08:30:22 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 520/1251] eta: 0:06:15 lr: 0.000977 loss: 3.8721 (4.0220) grad_norm: 0.9817 (1.0590) time: 0.5095 [2021-03-25 08:30:27 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 530/1251] eta: 0:06:10 lr: 0.000977 loss: 3.8458 (4.0206) grad_norm: 0.9766 (1.0589) time: 0.5033 [2021-03-25 08:30:32 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 540/1251] eta: 0:06:05 lr: 0.000977 loss: 3.9521 (4.0170) grad_norm: 1.0640 (1.0591) time: 0.4987 [2021-03-25 08:30:37 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 550/1251] eta: 0:06:00 lr: 0.000977 loss: 3.9903 (4.0180) grad_norm: 1.0266 (1.0586) time: 0.5129 [2021-03-25 08:30:42 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 560/1251] eta: 0:05:54 lr: 0.000977 loss: 4.0974 (4.0169) grad_norm: 1.0052 (1.0583) time: 0.5145 [2021-03-25 08:30:47 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 570/1251] eta: 0:05:49 lr: 0.000977 loss: 4.1945 (4.0182) grad_norm: 0.9407 (1.0558) time: 0.5014 [2021-03-25 08:30:53 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 580/1251] eta: 0:05:44 lr: 0.000977 loss: 4.1697 (4.0166) grad_norm: 0.9120 (1.0539) time: 0.5046 [2021-03-25 08:30:58 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 590/1251] eta: 0:05:39 lr: 0.000977 loss: 4.1697 (4.0188) grad_norm: 0.9991 (1.0537) time: 0.5155 [2021-03-25 08:31:03 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 600/1251] eta: 0:05:34 lr: 0.000977 loss: 4.0558 (4.0163) grad_norm: 1.0136 (1.0529) time: 0.5137 [2021-03-25 08:31:08 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 610/1251] eta: 0:05:28 lr: 0.000977 loss: 4.0871 (4.0197) grad_norm: 0.9864 (1.0524) time: 0.5066 [2021-03-25 08:31:13 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 620/1251] eta: 0:05:23 lr: 0.000977 loss: 4.2609 (4.0188) grad_norm: 1.0074 (1.0528) time: 0.5058 [2021-03-25 08:31:18 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 630/1251] eta: 0:05:18 lr: 0.000977 loss: 4.1546 (4.0191) grad_norm: 0.9872 (1.0514) time: 0.5058 [2021-03-25 08:31:23 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 640/1251] eta: 0:05:13 lr: 0.000977 loss: 4.2547 (4.0200) grad_norm: 0.9265 (1.0510) time: 0.5079 [2021-03-25 08:31:28 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 650/1251] eta: 0:05:08 lr: 0.000977 loss: 4.2180 (4.0217) grad_norm: 1.0263 (1.0511) time: 0.5097 [2021-03-25 08:31:33 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 660/1251] eta: 0:05:03 lr: 0.000977 loss: 4.2661 (4.0250) grad_norm: 1.0420 (1.0504) time: 0.5090 [2021-03-25 08:31:38 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 670/1251] eta: 0:04:57 lr: 0.000977 loss: 4.0826 (4.0213) grad_norm: 0.9686 (1.0490) time: 0.5023 [2021-03-25 08:31:43 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 680/1251] eta: 0:04:52 lr: 0.000976 loss: 4.0826 (4.0245) grad_norm: 0.9686 (1.0483) time: 0.5070 [2021-03-25 08:31:49 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 690/1251] eta: 0:04:47 lr: 0.000976 loss: 4.3391 (4.0274) grad_norm: 0.9859 (1.0476) time: 0.5118 [2021-03-25 08:31:54 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 700/1251] eta: 0:04:42 lr: 0.000976 loss: 4.3025 (4.0281) grad_norm: 0.9754 (1.0475) time: 0.5061 [2021-03-25 08:31:59 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 710/1251] eta: 0:04:37 lr: 0.000976 loss: 4.1545 (4.0314) grad_norm: 1.0031 (1.0473) time: 0.5034 [2021-03-25 08:32:04 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 720/1251] eta: 0:04:31 lr: 0.000976 loss: 4.2370 (4.0331) grad_norm: 1.0410 (1.0473) time: 0.5023 [2021-03-25 08:32:09 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 730/1251] eta: 0:04:26 lr: 0.000976 loss: 4.2024 (4.0320) grad_norm: 1.0183 (1.0483) time: 0.5110 [2021-03-25 08:32:14 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 740/1251] eta: 0:04:21 lr: 0.000976 loss: 4.0010 (4.0303) grad_norm: 0.9990 (1.0478) time: 0.5259 [2021-03-25 08:32:19 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 750/1251] eta: 0:04:16 lr: 0.000976 loss: 3.9010 (4.0278) grad_norm: 1.0039 (1.0476) time: 0.5261 [2021-03-25 08:32:24 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 760/1251] eta: 0:04:11 lr: 0.000976 loss: 3.9378 (4.0294) grad_norm: 1.0452 (1.0474) time: 0.5083 [2021-03-25 08:32:29 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 770/1251] eta: 0:04:06 lr: 0.000976 loss: 4.0845 (4.0281) grad_norm: 1.0715 (1.0483) time: 0.5037 [2021-03-25 08:32:35 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 780/1251] eta: 0:04:01 lr: 0.000976 loss: 4.0845 (4.0296) grad_norm: 1.0503 (1.0483) time: 0.5156 [2021-03-25 08:32:40 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 790/1251] eta: 0:03:56 lr: 0.000976 loss: 4.1150 (4.0272) grad_norm: 0.9858 (1.0479) time: 0.5234 [2021-03-25 08:32:45 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 800/1251] eta: 0:03:51 lr: 0.000976 loss: 4.1160 (4.0278) grad_norm: 1.0259 (1.0488) time: 0.5147 [2021-03-25 08:32:50 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 810/1251] eta: 0:03:46 lr: 0.000976 loss: 4.0317 (4.0279) grad_norm: 1.0357 (1.0489) time: 0.5059 [2021-03-25 08:32:55 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 820/1251] eta: 0:03:40 lr: 0.000976 loss: 3.8577 (4.0288) grad_norm: 1.0564 (1.0496) time: 0.5078 [2021-03-25 08:33:00 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 830/1251] eta: 0:03:35 lr: 0.000976 loss: 4.1480 (4.0285) grad_norm: 1.0851 (1.0507) time: 0.5073 [2021-03-25 08:33:05 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 840/1251] eta: 0:03:30 lr: 0.000976 loss: 4.0696 (4.0287) grad_norm: 0.9976 (1.0505) time: 0.5051 [2021-03-25 08:33:10 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 850/1251] eta: 0:03:25 lr: 0.000976 loss: 3.9622 (4.0271) grad_norm: 0.9660 (1.0496) time: 0.5056 [2021-03-25 08:33:15 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 860/1251] eta: 0:03:20 lr: 0.000976 loss: 4.2772 (4.0289) grad_norm: 0.9683 (1.0486) time: 0.5029 [2021-03-25 08:33:20 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 870/1251] eta: 0:03:15 lr: 0.000976 loss: 4.1987 (4.0275) grad_norm: 0.9758 (1.0485) time: 0.5083 [2021-03-25 08:33:25 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 880/1251] eta: 0:03:09 lr: 0.000976 loss: 4.0082 (4.0274) grad_norm: 1.0006 (1.0481) time: 0.5077 [2021-03-25 08:33:30 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 890/1251] eta: 0:03:04 lr: 0.000976 loss: 4.0959 (4.0283) grad_norm: 0.9827 (1.0480) time: 0.4994 [2021-03-25 08:33:35 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 900/1251] eta: 0:02:59 lr: 0.000976 loss: 4.1727 (4.0306) grad_norm: 1.0150 (1.0481) time: 0.5018 [2021-03-25 08:33:41 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 910/1251] eta: 0:02:54 lr: 0.000976 loss: 4.1324 (4.0286) grad_norm: 1.0751 (1.0494) time: 0.5060 [2021-03-25 08:33:46 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 920/1251] eta: 0:02:49 lr: 0.000976 loss: 3.7920 (4.0255) grad_norm: 1.0881 (1.0500) time: 0.5126 [2021-03-25 08:33:51 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 930/1251] eta: 0:02:44 lr: 0.000976 loss: 3.7814 (4.0225) grad_norm: 1.0446 (1.0499) time: 0.5148 [2021-03-25 08:33:56 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 940/1251] eta: 0:02:39 lr: 0.000976 loss: 3.9255 (4.0236) grad_norm: 1.0261 (1.0506) time: 0.5176 [2021-03-25 08:34:01 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 950/1251] eta: 0:02:34 lr: 0.000976 loss: 4.1510 (4.0228) grad_norm: 1.0382 (1.0514) time: 0.5147 [2021-03-25 08:34:06 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 960/1251] eta: 0:02:28 lr: 0.000976 loss: 4.0737 (4.0258) grad_norm: 1.0308 (1.0513) time: 0.5082 [2021-03-25 08:34:11 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 970/1251] eta: 0:02:23 lr: 0.000976 loss: 4.0028 (4.0250) grad_norm: 1.0606 (1.0523) time: 0.5051 [2021-03-25 08:34:16 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 980/1251] eta: 0:02:18 lr: 0.000976 loss: 3.9948 (4.0242) grad_norm: 1.0715 (1.0522) time: 0.5041 [2021-03-25 08:34:21 swin_small_patch4_window7_224] INFO: Epoch: [29] [ 990/1251] eta: 0:02:13 lr: 0.000976 loss: 4.1163 (4.0249) grad_norm: 1.0661 (1.0523) time: 0.5066 [2021-03-25 08:34:26 swin_small_patch4_window7_224] INFO: Epoch: [29] [1000/1251] eta: 0:02:08 lr: 0.000976 loss: 4.3219 (4.0268) grad_norm: 1.0398 (1.0518) time: 0.5073 [2021-03-25 08:34:32 swin_small_patch4_window7_224] INFO: Epoch: [29] [1010/1251] eta: 0:02:03 lr: 0.000976 loss: 4.2435 (4.0282) grad_norm: 0.9935 (1.0511) time: 0.5059 [2021-03-25 08:34:37 swin_small_patch4_window7_224] INFO: Epoch: [29] [1020/1251] eta: 0:01:58 lr: 0.000976 loss: 4.0413 (4.0272) grad_norm: 0.9769 (1.0507) time: 0.5056 [2021-03-25 08:34:42 swin_small_patch4_window7_224] INFO: Epoch: [29] [1030/1251] eta: 0:01:53 lr: 0.000976 loss: 4.0362 (4.0306) grad_norm: 0.9656 (1.0500) time: 0.5060 [2021-03-25 08:34:47 swin_small_patch4_window7_224] INFO: Epoch: [29] [1040/1251] eta: 0:01:47 lr: 0.000976 loss: 4.3885 (4.0307) grad_norm: 0.9676 (1.0495) time: 0.5053 [2021-03-25 08:34:52 swin_small_patch4_window7_224] INFO: Epoch: [29] [1050/1251] eta: 0:01:42 lr: 0.000976 loss: 4.1956 (4.0323) grad_norm: 0.9796 (1.0491) time: 0.5072 [2021-03-25 08:34:57 swin_small_patch4_window7_224] INFO: Epoch: [29] [1060/1251] eta: 0:01:37 lr: 0.000976 loss: 3.8210 (4.0295) grad_norm: 1.0414 (1.0487) time: 0.5083 [2021-03-25 08:35:02 swin_small_patch4_window7_224] INFO: Epoch: [29] [1070/1251] eta: 0:01:32 lr: 0.000976 loss: 3.7970 (4.0315) grad_norm: 1.0739 (1.0491) time: 0.5074 [2021-03-25 08:35:07 swin_small_patch4_window7_224] INFO: Epoch: [29] [1080/1251] eta: 0:01:27 lr: 0.000976 loss: 4.1625 (4.0316) grad_norm: 0.9793 (1.0482) time: 0.5042 [2021-03-25 08:35:12 swin_small_patch4_window7_224] INFO: Epoch: [29] [1090/1251] eta: 0:01:22 lr: 0.000976 loss: 3.9039 (4.0305) grad_norm: 0.9484 (1.0478) time: 0.5005 [2021-03-25 08:35:17 swin_small_patch4_window7_224] INFO: Epoch: [29] [1100/1251] eta: 0:01:17 lr: 0.000976 loss: 3.8798 (4.0293) grad_norm: 0.9842 (1.0475) time: 0.5054 [2021-03-25 08:35:22 swin_small_patch4_window7_224] INFO: Epoch: [29] [1110/1251] eta: 0:01:12 lr: 0.000976 loss: 4.0582 (4.0312) grad_norm: 0.9842 (1.0481) time: 0.5071 [2021-03-25 08:35:27 swin_small_patch4_window7_224] INFO: Epoch: [29] [1120/1251] eta: 0:01:06 lr: 0.000976 loss: 4.1820 (4.0319) grad_norm: 1.0475 (1.0476) time: 0.5068 [2021-03-25 08:35:32 swin_small_patch4_window7_224] INFO: Epoch: [29] [1130/1251] eta: 0:01:01 lr: 0.000976 loss: 4.1479 (4.0317) grad_norm: 1.0020 (1.0479) time: 0.5074 [2021-03-25 08:35:37 swin_small_patch4_window7_224] INFO: Epoch: [29] [1140/1251] eta: 0:00:56 lr: 0.000976 loss: 4.0429 (4.0324) grad_norm: 1.0709 (1.0486) time: 0.5060 [2021-03-25 08:35:42 swin_small_patch4_window7_224] INFO: Epoch: [29] [1150/1251] eta: 0:00:51 lr: 0.000976 loss: 4.1087 (4.0316) grad_norm: 1.1048 (1.0491) time: 0.5083 [2021-03-25 08:35:47 swin_small_patch4_window7_224] INFO: Epoch: [29] [1160/1251] eta: 0:00:46 lr: 0.000976 loss: 3.9372 (4.0313) grad_norm: 1.0901 (1.0504) time: 0.5034 [2021-03-25 08:35:53 swin_small_patch4_window7_224] INFO: Epoch: [29] [1170/1251] eta: 0:00:41 lr: 0.000976 loss: 4.0467 (4.0310) grad_norm: 1.0901 (1.0509) time: 0.5076 [2021-03-25 08:35:58 swin_small_patch4_window7_224] INFO: Epoch: [29] [1180/1251] eta: 0:00:36 lr: 0.000976 loss: 4.0865 (4.0304) grad_norm: 1.0138 (1.0502) time: 0.5107 [2021-03-25 08:36:03 swin_small_patch4_window7_224] INFO: Epoch: [29] [1190/1251] eta: 0:00:31 lr: 0.000976 loss: 4.0210 (4.0303) grad_norm: 1.0124 (1.0510) time: 0.5028 [2021-03-25 08:36:08 swin_small_patch4_window7_224] INFO: Epoch: [29] [1200/1251] eta: 0:00:26 lr: 0.000976 loss: 4.0210 (4.0295) grad_norm: 1.1865 (1.0519) time: 0.4990 [2021-03-25 08:36:13 swin_small_patch4_window7_224] INFO: Epoch: [29] [1210/1251] eta: 0:00:20 lr: 0.000976 loss: 4.0175 (4.0295) grad_norm: 1.0562 (1.0515) time: 0.5039 [2021-03-25 08:36:18 swin_small_patch4_window7_224] INFO: Epoch: [29] [1220/1251] eta: 0:00:15 lr: 0.000976 loss: 3.9670 (4.0281) grad_norm: 0.9807 (1.0510) time: 0.5109 [2021-03-25 08:36:23 swin_small_patch4_window7_224] INFO: Epoch: [29] [1230/1251] eta: 0:00:10 lr: 0.000976 loss: 3.8740 (4.0276) grad_norm: 0.9807 (1.0507) time: 0.5101 [2021-03-25 08:36:28 swin_small_patch4_window7_224] INFO: Epoch: [29] [1240/1251] eta: 0:00:05 lr: 0.000976 loss: 4.0505 (4.0278) grad_norm: 1.0222 (1.0508) time: 0.5084 [2021-03-25 08:36:33 swin_small_patch4_window7_224] INFO: Epoch: [29] [1250/1251] eta: 0:00:00 lr: 0.000976 loss: 3.9694 (4.0274) grad_norm: 1.0734 (1.0511) time: 0.5060 [2021-03-25 08:36:36 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:20 loss: 1.3726 (1.3726) acc1: 64.0625 (64.0625) acc5: 92.1875 (92.1875) [2021-03-25 08:36:40 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.5350 (1.4570) acc1: 64.0625 (65.4830) acc5: 87.5000 (88.3523) [2021-03-25 08:36:42 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.5350 (1.4784) acc1: 62.5000 (65.6250) acc5: 87.5000 (88.0208) [2021-03-25 08:36:44 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.4470 (1.4357) acc1: 67.1875 (67.3387) acc5: 89.0625 (88.7097) [2021-03-25 08:36:46 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.4255 (1.4365) acc1: 67.1875 (67.0732) acc5: 89.0625 (88.6814) [2021-03-25 08:36:47 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4479 (1.4397) acc1: 65.6250 (66.9760) acc5: 89.0625 (88.7040) [2021-03-25 08:36:49 swin_small_patch4_window7_224] INFO: * Acc@1 67.720 Acc@5 88.778 loss 1.422 [2021-03-25 08:36:49 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 67.7% [2021-03-25 08:36:49 swin_small_patch4_window7_224] INFO: Max accuracy: 67.82% [2021-03-25 08:36:53 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 0/1251] eta: 1:30:51 lr: 0.000976 loss: 4.5176 (4.5176) grad_norm: 1.0132 (1.0132) time: 4.3575 [2021-03-25 08:36:58 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 10/1251] eta: 0:17:35 lr: 0.000976 loss: 4.4949 (4.1951) grad_norm: 1.0505 (1.0316) time: 0.8509 [2021-03-25 08:37:03 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 20/1251] eta: 0:14:05 lr: 0.000976 loss: 3.7588 (4.0403) grad_norm: 1.0452 (1.0248) time: 0.5033 [2021-03-25 08:37:08 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 30/1251] eta: 0:12:44 lr: 0.000976 loss: 3.9309 (4.0371) grad_norm: 1.0437 (1.0420) time: 0.5021 [2021-03-25 08:37:14 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 40/1251] eta: 0:12:09 lr: 0.000976 loss: 4.0118 (4.0339) grad_norm: 1.0467 (1.0364) time: 0.5142 [2021-03-25 08:37:19 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 50/1251] eta: 0:11:41 lr: 0.000976 loss: 4.1387 (4.0668) grad_norm: 1.0599 (1.0551) time: 0.5196 [2021-03-25 08:37:24 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 60/1251] eta: 0:11:20 lr: 0.000976 loss: 4.2580 (4.0712) grad_norm: 1.0578 (1.0586) time: 0.5086 [2021-03-25 08:37:29 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 70/1251] eta: 0:11:03 lr: 0.000976 loss: 4.1168 (4.0111) grad_norm: 1.0417 (1.0639) time: 0.5048 [2021-03-25 08:37:34 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 80/1251] eta: 0:10:49 lr: 0.000976 loss: 4.1387 (4.0313) grad_norm: 1.0635 (1.0665) time: 0.5032 [2021-03-25 08:37:39 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 90/1251] eta: 0:10:38 lr: 0.000976 loss: 4.1387 (4.0056) grad_norm: 1.0324 (1.0614) time: 0.5078 [2021-03-25 08:37:44 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 100/1251] eta: 0:10:28 lr: 0.000976 loss: 3.7886 (3.9992) grad_norm: 1.0850 (1.0641) time: 0.5086 [2021-03-25 08:37:49 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 110/1251] eta: 0:10:18 lr: 0.000976 loss: 4.1749 (4.0238) grad_norm: 1.0452 (1.0612) time: 0.5062 [2021-03-25 08:37:54 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 120/1251] eta: 0:10:08 lr: 0.000976 loss: 4.3196 (4.0377) grad_norm: 0.9799 (1.0539) time: 0.5014 [2021-03-25 08:37:59 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 130/1251] eta: 0:10:01 lr: 0.000976 loss: 4.1949 (4.0389) grad_norm: 0.9388 (1.0450) time: 0.5061 [2021-03-25 08:38:04 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 140/1251] eta: 0:09:54 lr: 0.000976 loss: 4.1396 (4.0390) grad_norm: 0.9669 (1.0474) time: 0.5143 [2021-03-25 08:38:09 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 150/1251] eta: 0:09:47 lr: 0.000976 loss: 3.8387 (4.0219) grad_norm: 0.9877 (1.0434) time: 0.5113 [2021-03-25 08:38:15 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 160/1251] eta: 0:09:40 lr: 0.000976 loss: 4.0023 (4.0358) grad_norm: 0.9912 (1.0478) time: 0.5087 [2021-03-25 08:38:20 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 170/1251] eta: 0:09:33 lr: 0.000976 loss: 4.1331 (4.0390) grad_norm: 1.0203 (1.0557) time: 0.5083 [2021-03-25 08:38:25 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 180/1251] eta: 0:09:27 lr: 0.000976 loss: 4.1331 (4.0410) grad_norm: 1.1522 (1.0595) time: 0.5122 [2021-03-25 08:38:30 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 190/1251] eta: 0:09:20 lr: 0.000976 loss: 4.3344 (4.0540) grad_norm: 1.1330 (1.0599) time: 0.5141 [2021-03-25 08:38:35 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 200/1251] eta: 0:09:14 lr: 0.000976 loss: 4.2528 (4.0545) grad_norm: 0.9890 (1.0554) time: 0.5092 [2021-03-25 08:38:40 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 210/1251] eta: 0:09:07 lr: 0.000976 loss: 3.9084 (4.0477) grad_norm: 0.9890 (1.0571) time: 0.5026 [2021-03-25 08:38:45 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 220/1251] eta: 0:09:01 lr: 0.000975 loss: 3.5776 (4.0256) grad_norm: 0.9971 (1.0527) time: 0.5028 [2021-03-25 08:38:50 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 230/1251] eta: 0:08:55 lr: 0.000975 loss: 3.8785 (4.0232) grad_norm: 0.9582 (1.0476) time: 0.5036 [2021-03-25 08:38:55 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 240/1251] eta: 0:08:49 lr: 0.000975 loss: 3.8827 (4.0241) grad_norm: 0.9870 (1.0477) time: 0.5030 [2021-03-25 08:39:00 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 250/1251] eta: 0:08:43 lr: 0.000975 loss: 3.7516 (4.0280) grad_norm: 1.0383 (1.0465) time: 0.5119 [2021-03-25 08:39:05 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 260/1251] eta: 0:08:38 lr: 0.000975 loss: 3.7516 (4.0210) grad_norm: 1.0196 (1.0451) time: 0.5144 [2021-03-25 08:39:10 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 270/1251] eta: 0:08:32 lr: 0.000975 loss: 4.1138 (4.0307) grad_norm: 1.0067 (1.0437) time: 0.5072 [2021-03-25 08:39:16 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 280/1251] eta: 0:08:26 lr: 0.000975 loss: 4.0930 (4.0219) grad_norm: 0.9983 (1.0423) time: 0.5059 [2021-03-25 08:39:21 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 290/1251] eta: 0:08:20 lr: 0.000975 loss: 3.7546 (4.0172) grad_norm: 1.0498 (1.0440) time: 0.5037 [2021-03-25 08:39:26 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 300/1251] eta: 0:08:14 lr: 0.000975 loss: 3.9382 (4.0144) grad_norm: 1.0607 (1.0464) time: 0.5032 [2021-03-25 08:39:31 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 310/1251] eta: 0:08:09 lr: 0.000975 loss: 3.9382 (4.0111) grad_norm: 1.0088 (1.0440) time: 0.5081 [2021-03-25 08:39:36 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 320/1251] eta: 0:08:04 lr: 0.000975 loss: 4.0742 (4.0115) grad_norm: 1.0115 (1.0442) time: 0.5152 [2021-03-25 08:39:41 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 330/1251] eta: 0:07:58 lr: 0.000975 loss: 4.1676 (4.0165) grad_norm: 1.0162 (1.0424) time: 0.5126 [2021-03-25 08:39:46 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 340/1251] eta: 0:07:52 lr: 0.000975 loss: 4.1648 (4.0148) grad_norm: 0.9009 (1.0400) time: 0.4998 [2021-03-25 08:39:51 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 350/1251] eta: 0:07:47 lr: 0.000975 loss: 4.2340 (4.0200) grad_norm: 0.9023 (1.0384) time: 0.4996 [2021-03-25 08:39:56 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 360/1251] eta: 0:07:41 lr: 0.000975 loss: 4.2309 (4.0214) grad_norm: 0.9674 (1.0380) time: 0.5017 [2021-03-25 08:40:01 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 370/1251] eta: 0:07:35 lr: 0.000975 loss: 4.0995 (4.0140) grad_norm: 1.0383 (1.0401) time: 0.5029 [2021-03-25 08:40:06 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 380/1251] eta: 0:07:30 lr: 0.000975 loss: 4.1498 (4.0149) grad_norm: 1.0511 (1.0413) time: 0.5055 [2021-03-25 08:40:11 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 390/1251] eta: 0:07:25 lr: 0.000975 loss: 4.1021 (4.0148) grad_norm: 1.0514 (1.0420) time: 0.5064 [2021-03-25 08:40:16 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 400/1251] eta: 0:07:19 lr: 0.000975 loss: 4.2593 (4.0181) grad_norm: 0.9870 (1.0403) time: 0.5062 [2021-03-25 08:40:21 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 410/1251] eta: 0:07:14 lr: 0.000975 loss: 4.0045 (4.0104) grad_norm: 0.9730 (1.0387) time: 0.5032 [2021-03-25 08:40:26 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 420/1251] eta: 0:07:08 lr: 0.000975 loss: 3.7426 (4.0024) grad_norm: 0.9778 (1.0381) time: 0.5057 [2021-03-25 08:40:31 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 430/1251] eta: 0:07:03 lr: 0.000975 loss: 4.0845 (4.0051) grad_norm: 0.9933 (1.0371) time: 0.5072 [2021-03-25 08:40:36 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 440/1251] eta: 0:06:58 lr: 0.000975 loss: 4.1789 (4.0047) grad_norm: 0.9745 (1.0356) time: 0.5047 [2021-03-25 08:40:41 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 450/1251] eta: 0:06:52 lr: 0.000975 loss: 3.9804 (4.0007) grad_norm: 0.9684 (1.0344) time: 0.4994 [2021-03-25 08:40:46 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 460/1251] eta: 0:06:47 lr: 0.000975 loss: 3.9753 (3.9986) grad_norm: 0.9685 (1.0339) time: 0.5012 [2021-03-25 08:40:51 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 470/1251] eta: 0:06:42 lr: 0.000975 loss: 4.0000 (3.9998) grad_norm: 0.9984 (1.0337) time: 0.5056 [2021-03-25 08:40:57 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 480/1251] eta: 0:06:36 lr: 0.000975 loss: 4.0000 (3.9967) grad_norm: 1.0415 (1.0349) time: 0.5043 [2021-03-25 08:41:02 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 490/1251] eta: 0:06:31 lr: 0.000975 loss: 3.8581 (3.9947) grad_norm: 1.0297 (1.0352) time: 0.5046 [2021-03-25 08:41:07 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 500/1251] eta: 0:06:26 lr: 0.000975 loss: 3.8581 (3.9936) grad_norm: 0.9821 (1.0352) time: 0.5060 [2021-03-25 08:41:12 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 510/1251] eta: 0:06:20 lr: 0.000975 loss: 4.0240 (3.9913) grad_norm: 1.0321 (1.0380) time: 0.5063 [2021-03-25 08:41:17 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 520/1251] eta: 0:06:15 lr: 0.000975 loss: 4.0247 (3.9910) grad_norm: 1.0581 (1.0377) time: 0.5022 [2021-03-25 08:41:22 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 530/1251] eta: 0:06:10 lr: 0.000975 loss: 3.9436 (3.9893) grad_norm: 1.0483 (1.0385) time: 0.4999 [2021-03-25 08:41:27 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 540/1251] eta: 0:06:05 lr: 0.000975 loss: 3.7401 (3.9857) grad_norm: 1.0531 (1.0397) time: 0.5075 [2021-03-25 08:41:32 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 550/1251] eta: 0:06:00 lr: 0.000975 loss: 3.7401 (3.9838) grad_norm: 1.0575 (1.0412) time: 0.5198 [2021-03-25 08:41:37 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 560/1251] eta: 0:05:54 lr: 0.000975 loss: 4.0734 (3.9859) grad_norm: 1.0575 (1.0412) time: 0.5170 [2021-03-25 08:41:42 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 570/1251] eta: 0:05:49 lr: 0.000975 loss: 4.1562 (3.9925) grad_norm: 0.9617 (1.0405) time: 0.5104 [2021-03-25 08:41:47 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 580/1251] eta: 0:05:44 lr: 0.000975 loss: 4.1853 (3.9952) grad_norm: 0.9567 (1.0393) time: 0.5068 [2021-03-25 08:41:53 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 590/1251] eta: 0:05:39 lr: 0.000975 loss: 4.1856 (3.9970) grad_norm: 0.9695 (1.0385) time: 0.5104 [2021-03-25 08:41:58 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 600/1251] eta: 0:05:34 lr: 0.000975 loss: 4.2820 (3.9978) grad_norm: 0.9724 (1.0382) time: 0.5134 [2021-03-25 08:42:03 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 610/1251] eta: 0:05:28 lr: 0.000975 loss: 4.2618 (3.9999) grad_norm: 0.9786 (1.0382) time: 0.5032 [2021-03-25 08:42:08 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 620/1251] eta: 0:05:23 lr: 0.000975 loss: 4.3501 (4.0021) grad_norm: 0.9901 (1.0373) time: 0.5059 [2021-03-25 08:42:13 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 630/1251] eta: 0:05:18 lr: 0.000975 loss: 4.2759 (4.0033) grad_norm: 0.9939 (1.0367) time: 0.5095 [2021-03-25 08:42:18 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 640/1251] eta: 0:05:13 lr: 0.000975 loss: 4.1671 (4.0057) grad_norm: 1.0118 (1.0362) time: 0.5038 [2021-03-25 08:42:23 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 650/1251] eta: 0:05:08 lr: 0.000975 loss: 4.0312 (4.0023) grad_norm: 0.9944 (1.0362) time: 0.5047 [2021-03-25 08:42:28 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 660/1251] eta: 0:05:02 lr: 0.000975 loss: 4.0312 (4.0044) grad_norm: 0.9670 (1.0353) time: 0.5045 [2021-03-25 08:42:33 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 670/1251] eta: 0:04:57 lr: 0.000975 loss: 4.0138 (4.0028) grad_norm: 0.9529 (1.0347) time: 0.5002 [2021-03-25 08:42:38 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 680/1251] eta: 0:04:52 lr: 0.000975 loss: 4.0927 (4.0064) grad_norm: 0.9891 (1.0339) time: 0.5030 [2021-03-25 08:42:43 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 690/1251] eta: 0:04:47 lr: 0.000975 loss: 4.1303 (4.0075) grad_norm: 1.0470 (1.0352) time: 0.5065 [2021-03-25 08:42:48 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 700/1251] eta: 0:04:42 lr: 0.000975 loss: 4.0872 (4.0051) grad_norm: 0.9902 (1.0335) time: 0.5053 [2021-03-25 08:42:53 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 710/1251] eta: 0:04:37 lr: 0.000975 loss: 4.1037 (4.0087) grad_norm: 0.9783 (1.0338) time: 0.5066 [2021-03-25 08:42:58 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 720/1251] eta: 0:04:31 lr: 0.000975 loss: 4.1369 (4.0068) grad_norm: 1.0148 (1.0327) time: 0.5045 [2021-03-25 08:43:03 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 730/1251] eta: 0:04:26 lr: 0.000975 loss: 4.1421 (4.0121) grad_norm: 0.9547 (1.0329) time: 0.5134 [2021-03-25 08:43:09 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 740/1251] eta: 0:04:21 lr: 0.000975 loss: 4.3427 (4.0143) grad_norm: 1.0465 (1.0340) time: 0.5293 [2021-03-25 08:43:14 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 750/1251] eta: 0:04:16 lr: 0.000975 loss: 4.3610 (4.0162) grad_norm: 1.0908 (1.0351) time: 0.5208 [2021-03-25 08:43:19 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 760/1251] eta: 0:04:11 lr: 0.000975 loss: 4.2131 (4.0184) grad_norm: 1.0477 (1.0349) time: 0.5040 [2021-03-25 08:43:24 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 770/1251] eta: 0:04:06 lr: 0.000975 loss: 4.1585 (4.0178) grad_norm: 1.0215 (1.0349) time: 0.5014 [2021-03-25 08:43:29 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 780/1251] eta: 0:04:01 lr: 0.000975 loss: 3.6979 (4.0121) grad_norm: 0.9980 (1.0345) time: 0.5078 [2021-03-25 08:43:34 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 790/1251] eta: 0:03:56 lr: 0.000975 loss: 3.8621 (4.0110) grad_norm: 0.9527 (1.0341) time: 0.5156 [2021-03-25 08:43:39 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 800/1251] eta: 0:03:51 lr: 0.000975 loss: 3.9548 (4.0096) grad_norm: 1.0150 (1.0343) time: 0.5205 [2021-03-25 08:43:44 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 810/1251] eta: 0:03:45 lr: 0.000975 loss: 4.0925 (4.0099) grad_norm: 0.9727 (1.0334) time: 0.5122 [2021-03-25 08:43:50 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 820/1251] eta: 0:03:40 lr: 0.000975 loss: 4.0925 (4.0076) grad_norm: 0.9523 (1.0324) time: 0.5060 [2021-03-25 08:43:55 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 830/1251] eta: 0:03:35 lr: 0.000975 loss: 4.0710 (4.0096) grad_norm: 0.9653 (1.0317) time: 0.5082 [2021-03-25 08:44:00 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 840/1251] eta: 0:03:30 lr: 0.000975 loss: 4.1632 (4.0110) grad_norm: 0.9843 (1.0312) time: 0.5045 [2021-03-25 08:44:05 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 850/1251] eta: 0:03:25 lr: 0.000975 loss: 4.1160 (4.0098) grad_norm: 1.0404 (1.0324) time: 0.5058 [2021-03-25 08:44:10 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 860/1251] eta: 0:03:20 lr: 0.000975 loss: 4.2761 (4.0125) grad_norm: 1.0923 (1.0326) time: 0.5044 [2021-03-25 08:44:15 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 870/1251] eta: 0:03:15 lr: 0.000975 loss: 4.1498 (4.0077) grad_norm: 0.9784 (1.0314) time: 0.5092 [2021-03-25 08:44:20 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 880/1251] eta: 0:03:09 lr: 0.000975 loss: 3.7029 (4.0071) grad_norm: 0.9751 (1.0314) time: 0.5161 [2021-03-25 08:44:25 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 890/1251] eta: 0:03:04 lr: 0.000975 loss: 3.9272 (4.0066) grad_norm: 1.0442 (1.0314) time: 0.5050 [2021-03-25 08:44:30 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 900/1251] eta: 0:02:59 lr: 0.000975 loss: 4.3040 (4.0103) grad_norm: 1.0093 (1.0309) time: 0.4991 [2021-03-25 08:44:35 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 910/1251] eta: 0:02:54 lr: 0.000975 loss: 4.2836 (4.0103) grad_norm: 0.9701 (1.0307) time: 0.5061 [2021-03-25 08:44:40 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 920/1251] eta: 0:02:49 lr: 0.000975 loss: 3.9405 (4.0078) grad_norm: 0.9397 (1.0297) time: 0.5100 [2021-03-25 08:44:45 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 930/1251] eta: 0:02:44 lr: 0.000975 loss: 3.9701 (4.0066) grad_norm: 0.9122 (1.0287) time: 0.5084 [2021-03-25 08:44:50 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 940/1251] eta: 0:02:39 lr: 0.000975 loss: 4.0186 (4.0066) grad_norm: 0.9407 (1.0283) time: 0.5090 [2021-03-25 08:44:56 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 950/1251] eta: 0:02:33 lr: 0.000975 loss: 4.0671 (4.0079) grad_norm: 0.9407 (1.0276) time: 0.5121 [2021-03-25 08:45:01 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 960/1251] eta: 0:02:28 lr: 0.000975 loss: 4.1331 (4.0074) grad_norm: 0.9603 (1.0271) time: 0.5123 [2021-03-25 08:45:06 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 970/1251] eta: 0:02:23 lr: 0.000975 loss: 3.7275 (4.0047) grad_norm: 0.9620 (1.0272) time: 0.5075 [2021-03-25 08:45:11 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 980/1251] eta: 0:02:18 lr: 0.000975 loss: 3.9165 (4.0052) grad_norm: 1.0378 (1.0275) time: 0.5058 [2021-03-25 08:45:16 swin_small_patch4_window7_224] INFO: Epoch: [30] [ 990/1251] eta: 0:02:13 lr: 0.000974 loss: 4.3412 (4.0078) grad_norm: 1.1176 (1.0291) time: 0.5112 [2021-03-25 08:45:21 swin_small_patch4_window7_224] INFO: Epoch: [30] [1000/1251] eta: 0:02:08 lr: 0.000974 loss: 4.3223 (4.0090) grad_norm: 1.1364 (1.0298) time: 0.5083 [2021-03-25 08:45:26 swin_small_patch4_window7_224] INFO: Epoch: [30] [1010/1251] eta: 0:02:03 lr: 0.000974 loss: 3.9270 (4.0070) grad_norm: 1.0942 (1.0306) time: 0.5036 [2021-03-25 08:45:31 swin_small_patch4_window7_224] INFO: Epoch: [30] [1020/1251] eta: 0:01:58 lr: 0.000974 loss: 3.5242 (4.0043) grad_norm: 0.9797 (inf) time: 0.5017 [2021-03-25 08:45:36 swin_small_patch4_window7_224] INFO: Epoch: [30] [1030/1251] eta: 0:01:52 lr: 0.000974 loss: 3.7603 (4.0037) grad_norm: 0.9549 (inf) time: 0.5013 [2021-03-25 08:45:41 swin_small_patch4_window7_224] INFO: Epoch: [30] [1040/1251] eta: 0:01:47 lr: 0.000974 loss: 4.0539 (4.0039) grad_norm: 0.9806 (inf) time: 0.5069 [2021-03-25 08:45:46 swin_small_patch4_window7_224] INFO: Epoch: [30] [1050/1251] eta: 0:01:42 lr: 0.000974 loss: 4.1651 (4.0056) grad_norm: 1.0465 (inf) time: 0.5138 [2021-03-25 08:45:51 swin_small_patch4_window7_224] INFO: Epoch: [30] [1060/1251] eta: 0:01:37 lr: 0.000974 loss: 4.3120 (4.0055) grad_norm: 1.0389 (inf) time: 0.5108 [2021-03-25 08:45:56 swin_small_patch4_window7_224] INFO: Epoch: [30] [1070/1251] eta: 0:01:32 lr: 0.000974 loss: 3.9913 (4.0042) grad_norm: 0.9630 (inf) time: 0.5072 [2021-03-25 08:46:01 swin_small_patch4_window7_224] INFO: Epoch: [30] [1080/1251] eta: 0:01:27 lr: 0.000974 loss: 3.9345 (4.0044) grad_norm: 0.9819 (inf) time: 0.5036 [2021-03-25 08:46:07 swin_small_patch4_window7_224] INFO: Epoch: [30] [1090/1251] eta: 0:01:22 lr: 0.000974 loss: 4.0740 (4.0047) grad_norm: 0.9915 (inf) time: 0.4999 [2021-03-25 08:46:12 swin_small_patch4_window7_224] INFO: Epoch: [30] [1100/1251] eta: 0:01:17 lr: 0.000974 loss: 3.9361 (4.0013) grad_norm: 0.9401 (inf) time: 0.5050 [2021-03-25 08:46:17 swin_small_patch4_window7_224] INFO: Epoch: [30] [1110/1251] eta: 0:01:12 lr: 0.000974 loss: 3.7215 (4.0004) grad_norm: 0.9828 (inf) time: 0.5093 [2021-03-25 08:46:22 swin_small_patch4_window7_224] INFO: Epoch: [30] [1120/1251] eta: 0:01:06 lr: 0.000974 loss: 3.7985 (3.9986) grad_norm: 1.0162 (inf) time: 0.5111 [2021-03-25 08:46:27 swin_small_patch4_window7_224] INFO: Epoch: [30] [1130/1251] eta: 0:01:01 lr: 0.000974 loss: 3.7985 (3.9973) grad_norm: 1.0161 (inf) time: 0.5037 [2021-03-25 08:46:32 swin_small_patch4_window7_224] INFO: Epoch: [30] [1140/1251] eta: 0:00:56 lr: 0.000974 loss: 3.9643 (3.9965) grad_norm: 1.0669 (inf) time: 0.5040 [2021-03-25 08:46:37 swin_small_patch4_window7_224] INFO: Epoch: [30] [1150/1251] eta: 0:00:51 lr: 0.000974 loss: 3.9643 (3.9970) grad_norm: 1.0504 (inf) time: 0.5066 [2021-03-25 08:46:42 swin_small_patch4_window7_224] INFO: Epoch: [30] [1160/1251] eta: 0:00:46 lr: 0.000974 loss: 3.9975 (3.9974) grad_norm: 1.0140 (inf) time: 0.5027 [2021-03-25 08:46:47 swin_small_patch4_window7_224] INFO: Epoch: [30] [1170/1251] eta: 0:00:41 lr: 0.000974 loss: 3.9912 (3.9965) grad_norm: 1.0491 (inf) time: 0.5026 [2021-03-25 08:46:52 swin_small_patch4_window7_224] INFO: Epoch: [30] [1180/1251] eta: 0:00:36 lr: 0.000974 loss: 3.9896 (3.9982) grad_norm: 0.9982 (inf) time: 0.5054 [2021-03-25 08:46:57 swin_small_patch4_window7_224] INFO: Epoch: [30] [1190/1251] eta: 0:00:31 lr: 0.000974 loss: 4.2029 (3.9977) grad_norm: 0.9884 (inf) time: 0.5061 [2021-03-25 08:47:02 swin_small_patch4_window7_224] INFO: Epoch: [30] [1200/1251] eta: 0:00:26 lr: 0.000974 loss: 4.2563 (3.9987) grad_norm: 0.9943 (inf) time: 0.5016 [2021-03-25 08:47:07 swin_small_patch4_window7_224] INFO: Epoch: [30] [1210/1251] eta: 0:00:20 lr: 0.000974 loss: 4.2862 (4.0006) grad_norm: 0.9645 (inf) time: 0.5001 [2021-03-25 08:47:12 swin_small_patch4_window7_224] INFO: Epoch: [30] [1220/1251] eta: 0:00:15 lr: 0.000974 loss: 4.2093 (4.0006) grad_norm: 0.9630 (inf) time: 0.5063 [2021-03-25 08:47:17 swin_small_patch4_window7_224] INFO: Epoch: [30] [1230/1251] eta: 0:00:10 lr: 0.000974 loss: 4.0096 (3.9985) grad_norm: 1.0309 (inf) time: 0.5063 [2021-03-25 08:47:22 swin_small_patch4_window7_224] INFO: Epoch: [30] [1240/1251] eta: 0:00:05 lr: 0.000974 loss: 3.6362 (3.9965) grad_norm: 1.0534 (inf) time: 0.5023 [2021-03-25 08:47:27 swin_small_patch4_window7_224] INFO: Epoch: [30] [1250/1251] eta: 0:00:00 lr: 0.000974 loss: 3.9752 (3.9966) grad_norm: 1.0348 (inf) time: 0.5014 [2021-03-25 08:48:03 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 1.1540 (1.1540) acc1: 67.1875 (67.1875) acc5: 92.1875 (92.1875) [2021-03-25 08:48:04 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.2306 (1.3346) acc1: 70.3125 (69.8864) acc5: 87.5000 (88.6364) [2021-03-25 08:48:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.3501 (1.3634) acc1: 68.7500 (68.3036) acc5: 87.5000 (88.3185) [2021-03-25 08:48:06 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.3045 (1.3714) acc1: 67.1875 (67.5403) acc5: 89.0625 (88.3569) [2021-03-25 08:48:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.3045 (1.3858) acc1: 67.1875 (67.4162) acc5: 89.0625 (88.5671) [2021-03-25 08:48:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3912 (1.3769) acc1: 67.1875 (67.8080) acc5: 87.5000 (88.6400) [2021-03-25 08:48:10 swin_small_patch4_window7_224] INFO: * Acc@1 68.322 Acc@5 89.076 loss 1.363 [2021-03-25 08:48:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 68.3% [2021-03-25 08:48:10 swin_small_patch4_window7_224] INFO: Max accuracy: 68.32% [2021-03-25 08:48:14 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 0/1251] eta: 1:18:50 lr: 0.000974 loss: 3.0732 (3.0732) grad_norm: 1.0925 (1.0925) time: 3.7816 [2021-03-25 08:48:19 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 10/1251] eta: 0:17:20 lr: 0.000974 loss: 4.2250 (4.0943) grad_norm: 1.0472 (1.0461) time: 0.8388 [2021-03-25 08:48:24 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 20/1251] eta: 0:14:00 lr: 0.000974 loss: 4.2250 (4.0727) grad_norm: 0.9676 (1.0166) time: 0.5278 [2021-03-25 08:48:29 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 30/1251] eta: 0:12:43 lr: 0.000974 loss: 4.1429 (3.9731) grad_norm: 1.0009 (1.0387) time: 0.5081 [2021-03-25 08:48:34 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 40/1251] eta: 0:12:02 lr: 0.000974 loss: 3.5205 (3.8760) grad_norm: 0.9813 (1.0224) time: 0.5060 [2021-03-25 08:48:40 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 50/1251] eta: 0:11:36 lr: 0.000974 loss: 3.3767 (3.8391) grad_norm: 0.9703 (1.0294) time: 0.5101 [2021-03-25 08:48:45 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 60/1251] eta: 0:11:17 lr: 0.000974 loss: 3.6778 (3.8361) grad_norm: 1.0058 (1.0281) time: 0.5116 [2021-03-25 08:48:50 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 70/1251] eta: 0:11:00 lr: 0.000974 loss: 3.7132 (3.8167) grad_norm: 1.0029 (1.0197) time: 0.5072 [2021-03-25 08:48:55 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 80/1251] eta: 0:10:49 lr: 0.000974 loss: 3.7137 (3.8237) grad_norm: 1.0111 (1.0275) time: 0.5107 [2021-03-25 08:49:00 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 90/1251] eta: 0:10:38 lr: 0.000974 loss: 3.9269 (3.8553) grad_norm: 1.0574 (1.0312) time: 0.5139 [2021-03-25 08:49:05 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 100/1251] eta: 0:10:27 lr: 0.000974 loss: 4.1853 (3.8958) grad_norm: 1.0977 (1.0412) time: 0.5097 [2021-03-25 08:49:10 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 110/1251] eta: 0:10:19 lr: 0.000974 loss: 4.2130 (3.9280) grad_norm: 1.0557 (1.0334) time: 0.5112 [2021-03-25 08:49:15 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 120/1251] eta: 0:10:10 lr: 0.000974 loss: 4.3630 (3.9616) grad_norm: 1.0006 (1.0384) time: 0.5113 [2021-03-25 08:49:20 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 130/1251] eta: 0:10:01 lr: 0.000974 loss: 4.2588 (3.9719) grad_norm: 1.0202 (1.0351) time: 0.5026 [2021-03-25 08:49:25 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 140/1251] eta: 0:09:53 lr: 0.000974 loss: 4.0948 (3.9642) grad_norm: 1.0052 (1.0410) time: 0.5002 [2021-03-25 08:49:30 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 150/1251] eta: 0:09:45 lr: 0.000974 loss: 3.8288 (3.9629) grad_norm: 1.0538 (1.0426) time: 0.5007 [2021-03-25 08:49:35 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 160/1251] eta: 0:09:38 lr: 0.000974 loss: 3.7534 (3.9513) grad_norm: 1.0660 (1.0470) time: 0.5014 [2021-03-25 08:49:40 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 170/1251] eta: 0:09:32 lr: 0.000974 loss: 3.9650 (3.9694) grad_norm: 1.0648 (1.0455) time: 0.5092 [2021-03-25 08:49:46 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 180/1251] eta: 0:09:26 lr: 0.000974 loss: 4.2221 (3.9818) grad_norm: 0.9846 (1.0442) time: 0.5218 [2021-03-25 08:49:51 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 190/1251] eta: 0:09:21 lr: 0.000974 loss: 4.1364 (3.9690) grad_norm: 0.9846 (1.0465) time: 0.5263 [2021-03-25 08:49:56 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 200/1251] eta: 0:09:15 lr: 0.000974 loss: 4.0023 (3.9834) grad_norm: 0.9730 (1.0440) time: 0.5176 [2021-03-25 08:50:01 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 210/1251] eta: 0:09:08 lr: 0.000974 loss: 4.1419 (3.9891) grad_norm: 1.0147 (1.0490) time: 0.5092 [2021-03-25 08:50:06 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 220/1251] eta: 0:09:02 lr: 0.000974 loss: 3.8690 (3.9807) grad_norm: 1.0616 (1.0479) time: 0.5084 [2021-03-25 08:50:11 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 230/1251] eta: 0:08:56 lr: 0.000974 loss: 3.7423 (3.9699) grad_norm: 1.0266 (1.0484) time: 0.5104 [2021-03-25 08:50:16 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 240/1251] eta: 0:08:50 lr: 0.000974 loss: 3.8476 (3.9641) grad_norm: 1.0469 (1.0499) time: 0.5063 [2021-03-25 08:50:22 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 250/1251] eta: 0:08:44 lr: 0.000974 loss: 3.8476 (3.9646) grad_norm: 1.0457 (1.0499) time: 0.5070 [2021-03-25 08:50:27 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 260/1251] eta: 0:08:38 lr: 0.000974 loss: 3.8559 (3.9591) grad_norm: 1.0237 (1.0474) time: 0.5096 [2021-03-25 08:50:32 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 270/1251] eta: 0:08:32 lr: 0.000974 loss: 4.0940 (3.9715) grad_norm: 0.9693 (1.0458) time: 0.5050 [2021-03-25 08:50:37 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 280/1251] eta: 0:08:26 lr: 0.000974 loss: 4.4290 (3.9761) grad_norm: 0.9911 (1.0460) time: 0.5018 [2021-03-25 08:50:42 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 290/1251] eta: 0:08:21 lr: 0.000974 loss: 4.2410 (3.9781) grad_norm: 1.0718 (1.0501) time: 0.5034 [2021-03-25 08:50:47 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 300/1251] eta: 0:08:15 lr: 0.000974 loss: 4.2571 (3.9885) grad_norm: 1.1068 (1.0512) time: 0.5051 [2021-03-25 08:50:52 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 310/1251] eta: 0:08:10 lr: 0.000974 loss: 4.1757 (3.9926) grad_norm: 0.9887 (1.0489) time: 0.5138 [2021-03-25 08:50:57 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 320/1251] eta: 0:08:04 lr: 0.000974 loss: 4.0483 (3.9879) grad_norm: 0.9643 (1.0471) time: 0.5095 [2021-03-25 08:51:02 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 330/1251] eta: 0:07:58 lr: 0.000974 loss: 4.2684 (3.9963) grad_norm: 0.9629 (1.0449) time: 0.5038 [2021-03-25 08:51:07 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 340/1251] eta: 0:07:53 lr: 0.000974 loss: 4.2770 (3.9980) grad_norm: 0.9582 (1.0436) time: 0.5082 [2021-03-25 08:51:12 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 350/1251] eta: 0:07:47 lr: 0.000974 loss: 4.0743 (3.9958) grad_norm: 0.9582 (1.0439) time: 0.5082 [2021-03-25 08:51:17 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 360/1251] eta: 0:07:42 lr: 0.000974 loss: 3.8763 (3.9927) grad_norm: 1.0412 (1.0457) time: 0.5071 [2021-03-25 08:51:22 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 370/1251] eta: 0:07:37 lr: 0.000974 loss: 3.8505 (3.9852) grad_norm: 1.0324 (1.0451) time: 0.5134 [2021-03-25 08:51:28 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 380/1251] eta: 0:07:31 lr: 0.000974 loss: 4.0271 (3.9848) grad_norm: 0.9554 (1.0431) time: 0.5186 [2021-03-25 08:51:33 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 390/1251] eta: 0:07:26 lr: 0.000974 loss: 4.0115 (3.9805) grad_norm: 0.9219 (1.0403) time: 0.5094 [2021-03-25 08:51:38 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 400/1251] eta: 0:07:20 lr: 0.000974 loss: 4.1021 (3.9929) grad_norm: 0.9369 (1.0384) time: 0.5032 [2021-03-25 08:51:43 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 410/1251] eta: 0:07:15 lr: 0.000974 loss: 4.2743 (3.9917) grad_norm: 0.9570 (1.0366) time: 0.5049 [2021-03-25 08:51:48 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 420/1251] eta: 0:07:09 lr: 0.000974 loss: 4.0537 (3.9963) grad_norm: 0.9485 (1.0351) time: 0.5053 [2021-03-25 08:51:53 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 430/1251] eta: 0:07:04 lr: 0.000974 loss: 4.1775 (3.9967) grad_norm: 1.0117 (1.0364) time: 0.5036 [2021-03-25 08:51:58 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 440/1251] eta: 0:06:59 lr: 0.000974 loss: 4.1380 (3.9958) grad_norm: 1.0149 (1.0364) time: 0.5047 [2021-03-25 08:52:03 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 450/1251] eta: 0:06:53 lr: 0.000974 loss: 4.2058 (3.9964) grad_norm: 1.0993 (1.0382) time: 0.5024 [2021-03-25 08:52:08 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 460/1251] eta: 0:06:48 lr: 0.000974 loss: 4.0668 (3.9953) grad_norm: 0.9950 (1.0371) time: 0.5040 [2021-03-25 08:52:13 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 470/1251] eta: 0:06:43 lr: 0.000974 loss: 4.0651 (3.9939) grad_norm: 0.9813 (1.0368) time: 0.5083 [2021-03-25 08:52:18 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 480/1251] eta: 0:06:37 lr: 0.000974 loss: 4.1487 (3.9965) grad_norm: 1.0489 (1.0386) time: 0.5079 [2021-03-25 08:52:23 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 490/1251] eta: 0:06:32 lr: 0.000973 loss: 3.9997 (3.9911) grad_norm: 0.9952 (1.0372) time: 0.5092 [2021-03-25 08:52:28 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 500/1251] eta: 0:06:27 lr: 0.000973 loss: 3.8482 (3.9927) grad_norm: 0.9690 (1.0370) time: 0.5090 [2021-03-25 08:52:33 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 510/1251] eta: 0:06:21 lr: 0.000973 loss: 3.8686 (3.9903) grad_norm: 0.9844 (1.0376) time: 0.5068 [2021-03-25 08:52:38 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 520/1251] eta: 0:06:16 lr: 0.000973 loss: 3.8686 (3.9885) grad_norm: 1.0289 (1.0374) time: 0.5046 [2021-03-25 08:52:43 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 530/1251] eta: 0:06:11 lr: 0.000973 loss: 3.9682 (3.9884) grad_norm: 1.0020 (1.0372) time: 0.5010 [2021-03-25 08:52:49 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 540/1251] eta: 0:06:06 lr: 0.000973 loss: 4.0216 (3.9907) grad_norm: 1.0386 (1.0392) time: 0.5085 [2021-03-25 08:52:54 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 550/1251] eta: 0:06:01 lr: 0.000973 loss: 3.9075 (3.9838) grad_norm: 1.0133 (1.0384) time: 0.5217 [2021-03-25 08:52:59 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 560/1251] eta: 0:05:55 lr: 0.000973 loss: 3.4952 (3.9814) grad_norm: 1.0073 (1.0382) time: 0.5157 [2021-03-25 08:53:04 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 570/1251] eta: 0:05:50 lr: 0.000973 loss: 3.9066 (3.9841) grad_norm: 1.0073 (1.0377) time: 0.5053 [2021-03-25 08:53:09 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 580/1251] eta: 0:05:45 lr: 0.000973 loss: 3.9725 (3.9852) grad_norm: 0.9744 (1.0364) time: 0.5082 [2021-03-25 08:53:14 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 590/1251] eta: 0:05:40 lr: 0.000973 loss: 3.9725 (3.9853) grad_norm: 0.9806 (1.0356) time: 0.5118 [2021-03-25 08:53:19 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 600/1251] eta: 0:05:34 lr: 0.000973 loss: 4.0618 (3.9845) grad_norm: 0.9899 (1.0347) time: 0.5072 [2021-03-25 08:53:24 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 610/1251] eta: 0:05:29 lr: 0.000973 loss: 4.0618 (3.9846) grad_norm: 0.9776 (1.0342) time: 0.5072 [2021-03-25 08:53:29 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 620/1251] eta: 0:05:24 lr: 0.000973 loss: 4.3067 (3.9910) grad_norm: 1.0247 (1.0350) time: 0.5054 [2021-03-25 08:53:34 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 630/1251] eta: 0:05:19 lr: 0.000973 loss: 4.3085 (3.9920) grad_norm: 1.0318 (1.0362) time: 0.5033 [2021-03-25 08:53:40 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 640/1251] eta: 0:05:14 lr: 0.000973 loss: 4.0891 (3.9929) grad_norm: 1.1422 (1.0381) time: 0.5122 [2021-03-25 08:53:45 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 650/1251] eta: 0:05:08 lr: 0.000973 loss: 4.0513 (3.9939) grad_norm: 1.0685 (1.0380) time: 0.5134 [2021-03-25 08:53:50 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 660/1251] eta: 0:05:03 lr: 0.000973 loss: 4.0449 (3.9940) grad_norm: 1.0065 (1.0370) time: 0.5077 [2021-03-25 08:53:55 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 670/1251] eta: 0:04:58 lr: 0.000973 loss: 4.2107 (3.9963) grad_norm: 1.0114 (1.0368) time: 0.5054 [2021-03-25 08:54:00 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 680/1251] eta: 0:04:53 lr: 0.000973 loss: 4.2107 (3.9974) grad_norm: 1.0197 (1.0369) time: 0.5064 [2021-03-25 08:54:05 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 690/1251] eta: 0:04:48 lr: 0.000973 loss: 4.3077 (4.0000) grad_norm: 1.0493 (1.0381) time: 0.5041 [2021-03-25 08:54:10 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 700/1251] eta: 0:04:42 lr: 0.000973 loss: 4.2988 (4.0030) grad_norm: 1.0023 (1.0373) time: 0.5065 [2021-03-25 08:54:15 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 710/1251] eta: 0:04:37 lr: 0.000973 loss: 4.1710 (4.0004) grad_norm: 0.9904 (1.0367) time: 0.5058 [2021-03-25 08:54:20 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 720/1251] eta: 0:04:32 lr: 0.000973 loss: 3.9970 (4.0027) grad_norm: 0.9775 (1.0361) time: 0.5010 [2021-03-25 08:54:25 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 730/1251] eta: 0:04:27 lr: 0.000973 loss: 4.2188 (4.0029) grad_norm: 0.9775 (1.0375) time: 0.5106 [2021-03-25 08:54:31 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 740/1251] eta: 0:04:22 lr: 0.000973 loss: 4.2469 (4.0069) grad_norm: 1.0431 (1.0374) time: 0.5275 [2021-03-25 08:54:36 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 750/1251] eta: 0:04:17 lr: 0.000973 loss: 4.2469 (4.0076) grad_norm: 1.0270 (1.0374) time: 0.5218 [2021-03-25 08:54:41 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 760/1251] eta: 0:04:12 lr: 0.000973 loss: 3.7599 (4.0049) grad_norm: 0.9843 (1.0372) time: 0.5071 [2021-03-25 08:54:46 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 770/1251] eta: 0:04:06 lr: 0.000973 loss: 3.6499 (4.0007) grad_norm: 1.0088 (1.0380) time: 0.5017 [2021-03-25 08:54:51 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 780/1251] eta: 0:04:01 lr: 0.000973 loss: 3.7564 (3.9988) grad_norm: 1.0329 (1.0378) time: 0.4981 [2021-03-25 08:54:56 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 790/1251] eta: 0:03:56 lr: 0.000973 loss: 4.0461 (3.9985) grad_norm: 0.9587 (1.0374) time: 0.4994 [2021-03-25 08:55:01 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 800/1251] eta: 0:03:51 lr: 0.000973 loss: 4.2056 (4.0025) grad_norm: 0.9587 (1.0370) time: 0.5067 [2021-03-25 08:55:06 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 810/1251] eta: 0:03:46 lr: 0.000973 loss: 4.3002 (4.0055) grad_norm: 1.0276 (1.0380) time: 0.5085 [2021-03-25 08:55:11 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 820/1251] eta: 0:03:40 lr: 0.000973 loss: 4.2736 (4.0078) grad_norm: 1.0452 (1.0383) time: 0.5029 [2021-03-25 08:55:16 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 830/1251] eta: 0:03:35 lr: 0.000973 loss: 4.0565 (4.0063) grad_norm: 1.0725 (1.0395) time: 0.5055 [2021-03-25 08:55:21 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 840/1251] eta: 0:03:30 lr: 0.000973 loss: 3.9342 (4.0069) grad_norm: 1.0725 (1.0394) time: 0.5065 [2021-03-25 08:55:26 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 850/1251] eta: 0:03:25 lr: 0.000973 loss: 3.9966 (4.0071) grad_norm: 0.9699 (1.0388) time: 0.5097 [2021-03-25 08:55:31 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 860/1251] eta: 0:03:20 lr: 0.000973 loss: 3.9966 (4.0046) grad_norm: 0.9459 (1.0376) time: 0.5129 [2021-03-25 08:55:36 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 870/1251] eta: 0:03:15 lr: 0.000973 loss: 4.1728 (4.0067) grad_norm: 0.9735 (1.0380) time: 0.5100 [2021-03-25 08:55:41 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 880/1251] eta: 0:03:10 lr: 0.000973 loss: 3.9578 (4.0057) grad_norm: 1.0617 (1.0378) time: 0.5056 [2021-03-25 08:55:46 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 890/1251] eta: 0:03:04 lr: 0.000973 loss: 3.9578 (4.0037) grad_norm: 0.9955 (1.0376) time: 0.5031 [2021-03-25 08:55:52 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 900/1251] eta: 0:02:59 lr: 0.000973 loss: 4.1814 (4.0056) grad_norm: 1.0032 (1.0371) time: 0.5063 [2021-03-25 08:55:57 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 910/1251] eta: 0:02:54 lr: 0.000973 loss: 4.2258 (4.0079) grad_norm: 1.0032 (1.0373) time: 0.5083 [2021-03-25 08:56:02 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 920/1251] eta: 0:02:49 lr: 0.000973 loss: 4.2258 (4.0080) grad_norm: 1.0486 (1.0375) time: 0.5104 [2021-03-25 08:56:07 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 930/1251] eta: 0:02:44 lr: 0.000973 loss: 3.9456 (4.0066) grad_norm: 1.0496 (1.0378) time: 0.5166 [2021-03-25 08:56:12 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 940/1251] eta: 0:02:39 lr: 0.000973 loss: 4.0987 (4.0070) grad_norm: 1.0332 (1.0379) time: 0.5191 [2021-03-25 08:56:17 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 950/1251] eta: 0:02:34 lr: 0.000973 loss: 4.0403 (4.0076) grad_norm: 1.0414 (1.0387) time: 0.5070 [2021-03-25 08:56:22 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 960/1251] eta: 0:02:29 lr: 0.000973 loss: 4.0709 (4.0083) grad_norm: 1.0692 (1.0388) time: 0.5015 [2021-03-25 08:56:27 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 970/1251] eta: 0:02:23 lr: 0.000973 loss: 4.2018 (4.0083) grad_norm: 0.9816 (1.0384) time: 0.5038 [2021-03-25 08:56:32 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 980/1251] eta: 0:02:18 lr: 0.000973 loss: 4.1658 (4.0091) grad_norm: 0.9421 (1.0378) time: 0.5006 [2021-03-25 08:56:37 swin_small_patch4_window7_224] INFO: Epoch: [31] [ 990/1251] eta: 0:02:13 lr: 0.000973 loss: 4.0177 (4.0070) grad_norm: 0.9544 (1.0377) time: 0.5049 [2021-03-25 08:56:42 swin_small_patch4_window7_224] INFO: Epoch: [31] [1000/1251] eta: 0:02:08 lr: 0.000973 loss: 3.7992 (4.0040) grad_norm: 1.0150 (1.0373) time: 0.5096 [2021-03-25 08:56:47 swin_small_patch4_window7_224] INFO: Epoch: [31] [1010/1251] eta: 0:02:03 lr: 0.000973 loss: 3.7992 (4.0024) grad_norm: 1.0150 (1.0377) time: 0.5087 [2021-03-25 08:56:52 swin_small_patch4_window7_224] INFO: Epoch: [31] [1020/1251] eta: 0:01:58 lr: 0.000973 loss: 4.0197 (4.0016) grad_norm: 1.0726 (1.0389) time: 0.5040 [2021-03-25 08:56:58 swin_small_patch4_window7_224] INFO: Epoch: [31] [1030/1251] eta: 0:01:53 lr: 0.000973 loss: 4.0274 (4.0018) grad_norm: 1.0726 (1.0394) time: 0.5037 [2021-03-25 08:57:03 swin_small_patch4_window7_224] INFO: Epoch: [31] [1040/1251] eta: 0:01:47 lr: 0.000973 loss: 4.2779 (4.0037) grad_norm: 1.1383 (1.0407) time: 0.5060 [2021-03-25 08:57:08 swin_small_patch4_window7_224] INFO: Epoch: [31] [1050/1251] eta: 0:01:42 lr: 0.000973 loss: 4.1385 (4.0039) grad_norm: 1.1283 (1.0410) time: 0.5104 [2021-03-25 08:57:13 swin_small_patch4_window7_224] INFO: Epoch: [31] [1060/1251] eta: 0:01:37 lr: 0.000973 loss: 4.1131 (4.0023) grad_norm: 1.0456 (1.0411) time: 0.5103 [2021-03-25 08:57:18 swin_small_patch4_window7_224] INFO: Epoch: [31] [1070/1251] eta: 0:01:32 lr: 0.000973 loss: 3.9927 (4.0012) grad_norm: 1.0383 (1.0411) time: 0.5046 [2021-03-25 08:57:23 swin_small_patch4_window7_224] INFO: Epoch: [31] [1080/1251] eta: 0:01:27 lr: 0.000973 loss: 4.0518 (4.0024) grad_norm: 0.9784 (1.0408) time: 0.5033 [2021-03-25 08:57:28 swin_small_patch4_window7_224] INFO: Epoch: [31] [1090/1251] eta: 0:01:22 lr: 0.000973 loss: 4.1727 (4.0025) grad_norm: 0.9458 (1.0405) time: 0.5068 [2021-03-25 08:57:33 swin_small_patch4_window7_224] INFO: Epoch: [31] [1100/1251] eta: 0:01:17 lr: 0.000973 loss: 3.9718 (4.0007) grad_norm: 0.9330 (1.0397) time: 0.5168 [2021-03-25 08:57:38 swin_small_patch4_window7_224] INFO: Epoch: [31] [1110/1251] eta: 0:01:12 lr: 0.000973 loss: 3.8322 (3.9991) grad_norm: 1.0352 (1.0405) time: 0.5126 [2021-03-25 08:57:43 swin_small_patch4_window7_224] INFO: Epoch: [31] [1120/1251] eta: 0:01:06 lr: 0.000973 loss: 3.8913 (3.9994) grad_norm: 1.0354 (1.0403) time: 0.5114 [2021-03-25 08:57:48 swin_small_patch4_window7_224] INFO: Epoch: [31] [1130/1251] eta: 0:01:01 lr: 0.000973 loss: 4.2038 (3.9992) grad_norm: 0.9635 (1.0397) time: 0.5133 [2021-03-25 08:57:54 swin_small_patch4_window7_224] INFO: Epoch: [31] [1140/1251] eta: 0:00:56 lr: 0.000973 loss: 4.1675 (4.0003) grad_norm: 0.9635 (1.0395) time: 0.5051 [2021-03-25 08:57:59 swin_small_patch4_window7_224] INFO: Epoch: [31] [1150/1251] eta: 0:00:51 lr: 0.000973 loss: 3.8620 (3.9982) grad_norm: 1.0200 (1.0402) time: 0.5016 [2021-03-25 08:58:04 swin_small_patch4_window7_224] INFO: Epoch: [31] [1160/1251] eta: 0:00:46 lr: 0.000973 loss: 3.9011 (4.0010) grad_norm: 1.0836 (1.0403) time: 0.5044 [2021-03-25 08:58:09 swin_small_patch4_window7_224] INFO: Epoch: [31] [1170/1251] eta: 0:00:41 lr: 0.000973 loss: 4.2197 (4.0007) grad_norm: 1.0304 (1.0400) time: 0.5072 [2021-03-25 08:58:14 swin_small_patch4_window7_224] INFO: Epoch: [31] [1180/1251] eta: 0:00:36 lr: 0.000973 loss: 3.6116 (3.9977) grad_norm: 1.0069 (1.0400) time: 0.5012 [2021-03-25 08:58:19 swin_small_patch4_window7_224] INFO: Epoch: [31] [1190/1251] eta: 0:00:31 lr: 0.000973 loss: 3.6448 (3.9978) grad_norm: 1.0799 (1.0405) time: 0.4987 [2021-03-25 08:58:24 swin_small_patch4_window7_224] INFO: Epoch: [31] [1200/1251] eta: 0:00:26 lr: 0.000973 loss: 4.0912 (3.9980) grad_norm: 1.0387 (1.0397) time: 0.5033 [2021-03-25 08:58:29 swin_small_patch4_window7_224] INFO: Epoch: [31] [1210/1251] eta: 0:00:20 lr: 0.000973 loss: 4.1836 (4.0011) grad_norm: 0.9503 (1.0395) time: 0.5050 [2021-03-25 08:58:34 swin_small_patch4_window7_224] INFO: Epoch: [31] [1220/1251] eta: 0:00:15 lr: 0.000973 loss: 4.2495 (4.0002) grad_norm: 0.9608 (1.0391) time: 0.5034 [2021-03-25 08:58:39 swin_small_patch4_window7_224] INFO: Epoch: [31] [1230/1251] eta: 0:00:10 lr: 0.000972 loss: 4.2495 (4.0006) grad_norm: 1.0174 (1.0388) time: 0.5069 [2021-03-25 08:58:44 swin_small_patch4_window7_224] INFO: Epoch: [31] [1240/1251] eta: 0:00:05 lr: 0.000972 loss: 3.9146 (3.9992) grad_norm: 1.0174 (1.0384) time: 0.5101 [2021-03-25 08:58:49 swin_small_patch4_window7_224] INFO: Epoch: [31] [1250/1251] eta: 0:00:00 lr: 0.000972 loss: 3.6073 (3.9974) grad_norm: 1.0043 (1.0380) time: 0.5085 [2021-03-25 08:58:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:13 loss: 1.8370 (1.8370) acc1: 62.5000 (62.5000) acc5: 87.5000 (87.5000) [2021-03-25 08:58:56 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.3894 (1.3766) acc1: 68.7500 (69.0341) acc5: 89.0625 (89.0625) [2021-03-25 08:58:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.3141 (1.3450) acc1: 68.7500 (68.3036) acc5: 89.0625 (89.0625) [2021-03-25 08:59:00 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3042 (1.3363) acc1: 68.7500 (68.5988) acc5: 89.0625 (89.6673) [2021-03-25 08:59:02 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3975 (1.3685) acc1: 67.1875 (67.9878) acc5: 89.0625 (88.7957) [2021-03-25 08:59:03 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3451 (1.3606) acc1: 66.0377 (68.0640) acc5: 87.5000 (88.8960) [2021-03-25 08:59:06 swin_small_patch4_window7_224] INFO: * Acc@1 68.766 Acc@5 89.360 loss 1.336 [2021-03-25 08:59:06 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 68.8% [2021-03-25 08:59:06 swin_small_patch4_window7_224] INFO: Max accuracy: 68.77% [2021-03-25 08:59:10 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 0/1251] eta: 1:27:08 lr: 0.000972 loss: 3.7567 (3.7567) grad_norm: 0.9968 (0.9968) time: 4.1797 [2021-03-25 08:59:15 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 10/1251] eta: 0:17:28 lr: 0.000972 loss: 4.1083 (3.7607) grad_norm: 1.0061 (1.0312) time: 0.8451 [2021-03-25 08:59:21 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 20/1251] eta: 0:14:05 lr: 0.000972 loss: 4.1083 (3.9115) grad_norm: 0.9872 (1.0212) time: 0.5125 [2021-03-25 08:59:26 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 30/1251] eta: 0:12:49 lr: 0.000972 loss: 3.9060 (3.8887) grad_norm: 0.9491 (1.0259) time: 0.5123 [2021-03-25 08:59:31 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 40/1251] eta: 0:12:10 lr: 0.000972 loss: 4.0595 (3.9496) grad_norm: 0.9492 (1.0134) time: 0.5143 [2021-03-25 08:59:36 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 50/1251] eta: 0:11:41 lr: 0.000972 loss: 4.2025 (3.9721) grad_norm: 1.0064 (1.0191) time: 0.5133 [2021-03-25 08:59:41 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 60/1251] eta: 0:11:21 lr: 0.000972 loss: 4.2025 (3.9823) grad_norm: 1.0185 (1.0229) time: 0.5099 [2021-03-25 08:59:46 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 70/1251] eta: 0:11:05 lr: 0.000972 loss: 4.0196 (3.9412) grad_norm: 0.9946 (1.0237) time: 0.5092 [2021-03-25 08:59:51 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 80/1251] eta: 0:10:52 lr: 0.000972 loss: 3.8722 (3.9511) grad_norm: 0.9921 (1.0247) time: 0.5119 [2021-03-25 08:59:56 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 90/1251] eta: 0:10:40 lr: 0.000972 loss: 3.8679 (3.9230) grad_norm: 0.9761 (1.0171) time: 0.5096 [2021-03-25 09:00:01 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 100/1251] eta: 0:10:29 lr: 0.000972 loss: 3.9171 (3.9377) grad_norm: 0.9529 (1.0174) time: 0.5045 [2021-03-25 09:00:07 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 110/1251] eta: 0:10:21 lr: 0.000972 loss: 4.2062 (3.9581) grad_norm: 1.0044 (1.0187) time: 0.5160 [2021-03-25 09:00:12 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 120/1251] eta: 0:10:12 lr: 0.000972 loss: 4.2126 (3.9674) grad_norm: 1.0407 (1.0247) time: 0.5158 [2021-03-25 09:00:17 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 130/1251] eta: 0:10:04 lr: 0.000972 loss: 4.1878 (3.9652) grad_norm: 1.0345 (1.0288) time: 0.5093 [2021-03-25 09:00:22 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 140/1251] eta: 0:09:56 lr: 0.000972 loss: 4.1468 (3.9699) grad_norm: 1.0079 (1.0335) time: 0.5103 [2021-03-25 09:00:27 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 150/1251] eta: 0:09:49 lr: 0.000972 loss: 3.9873 (3.9690) grad_norm: 1.1137 (1.0384) time: 0.5047 [2021-03-25 09:00:32 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 160/1251] eta: 0:09:41 lr: 0.000972 loss: 3.7242 (3.9582) grad_norm: 0.9826 (1.0335) time: 0.4991 [2021-03-25 09:00:37 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 170/1251] eta: 0:09:33 lr: 0.000972 loss: 3.9531 (3.9619) grad_norm: 0.9776 (1.0309) time: 0.4990 [2021-03-25 09:00:42 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 180/1251] eta: 0:09:27 lr: 0.000972 loss: 3.9570 (3.9560) grad_norm: 0.9693 (1.0274) time: 0.5063 [2021-03-25 09:00:47 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 190/1251] eta: 0:09:21 lr: 0.000972 loss: 4.0054 (3.9633) grad_norm: 0.9693 (1.0254) time: 0.5124 [2021-03-25 09:00:52 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 200/1251] eta: 0:09:14 lr: 0.000972 loss: 4.0054 (3.9700) grad_norm: 0.9934 (1.0239) time: 0.5115 [2021-03-25 09:00:57 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 210/1251] eta: 0:09:08 lr: 0.000972 loss: 3.8656 (3.9520) grad_norm: 0.9536 (1.0205) time: 0.5110 [2021-03-25 09:01:02 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 220/1251] eta: 0:09:02 lr: 0.000972 loss: 3.7554 (3.9507) grad_norm: 0.9776 (1.0212) time: 0.5085 [2021-03-25 09:01:07 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 230/1251] eta: 0:08:55 lr: 0.000972 loss: 4.2194 (3.9645) grad_norm: 0.9776 (1.0228) time: 0.4997 [2021-03-25 09:01:13 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 240/1251] eta: 0:08:49 lr: 0.000972 loss: 4.2468 (3.9749) grad_norm: 1.0165 (1.0256) time: 0.5012 [2021-03-25 09:01:17 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 250/1251] eta: 0:08:43 lr: 0.000972 loss: 4.0459 (3.9804) grad_norm: 1.0078 (1.0238) time: 0.5018 [2021-03-25 09:01:23 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 260/1251] eta: 0:08:37 lr: 0.000972 loss: 4.2104 (3.9989) grad_norm: 1.0006 (1.0250) time: 0.5011 [2021-03-25 09:01:28 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 270/1251] eta: 0:08:31 lr: 0.000972 loss: 4.3034 (4.0051) grad_norm: 1.0699 (1.0308) time: 0.5036 [2021-03-25 09:01:33 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 280/1251] eta: 0:08:25 lr: 0.000972 loss: 4.3034 (4.0047) grad_norm: 1.1025 (1.0345) time: 0.5041 [2021-03-25 09:01:38 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 290/1251] eta: 0:08:20 lr: 0.000972 loss: 4.0124 (4.0009) grad_norm: 1.0292 (1.0349) time: 0.5100 [2021-03-25 09:01:43 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 300/1251] eta: 0:08:15 lr: 0.000972 loss: 3.9336 (3.9964) grad_norm: 0.9763 (1.0348) time: 0.5136 [2021-03-25 09:01:48 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 310/1251] eta: 0:08:09 lr: 0.000972 loss: 3.9691 (3.9925) grad_norm: 0.9636 (1.0317) time: 0.5115 [2021-03-25 09:01:53 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 320/1251] eta: 0:08:03 lr: 0.000972 loss: 3.8831 (3.9847) grad_norm: 0.9548 (1.0302) time: 0.5065 [2021-03-25 09:01:58 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 330/1251] eta: 0:07:58 lr: 0.000972 loss: 3.8831 (3.9823) grad_norm: 0.9079 (1.0259) time: 0.5091 [2021-03-25 09:02:03 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 340/1251] eta: 0:07:52 lr: 0.000972 loss: 4.0057 (3.9833) grad_norm: 0.9069 (1.0234) time: 0.5076 [2021-03-25 09:02:08 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 350/1251] eta: 0:07:47 lr: 0.000972 loss: 4.2339 (3.9914) grad_norm: 0.9495 (1.0227) time: 0.5024 [2021-03-25 09:02:13 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 360/1251] eta: 0:07:41 lr: 0.000972 loss: 4.1591 (3.9899) grad_norm: 1.0174 (1.0238) time: 0.5053 [2021-03-25 09:02:18 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 370/1251] eta: 0:07:36 lr: 0.000972 loss: 4.0977 (3.9868) grad_norm: 1.0174 (1.0239) time: 0.5079 [2021-03-25 09:02:23 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 380/1251] eta: 0:07:30 lr: 0.000972 loss: 3.9108 (3.9871) grad_norm: 1.0047 (1.0254) time: 0.5076 [2021-03-25 09:02:29 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 390/1251] eta: 0:07:25 lr: 0.000972 loss: 4.0737 (3.9872) grad_norm: 1.0047 (1.0263) time: 0.5083 [2021-03-25 09:02:34 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 400/1251] eta: 0:07:20 lr: 0.000972 loss: 3.8863 (3.9826) grad_norm: 1.0314 (1.0269) time: 0.5062 [2021-03-25 09:02:39 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 410/1251] eta: 0:07:14 lr: 0.000972 loss: 3.8863 (3.9779) grad_norm: 1.0199 (1.0261) time: 0.5037 [2021-03-25 09:02:44 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 420/1251] eta: 0:07:09 lr: 0.000972 loss: 4.0733 (3.9844) grad_norm: 1.0114 (1.0268) time: 0.5049 [2021-03-25 09:02:49 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 430/1251] eta: 0:07:03 lr: 0.000972 loss: 4.1886 (3.9872) grad_norm: 1.0689 (1.0278) time: 0.5055 [2021-03-25 09:02:54 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 440/1251] eta: 0:06:58 lr: 0.000972 loss: 4.1837 (3.9919) grad_norm: 1.0617 (1.0282) time: 0.5027 [2021-03-25 09:02:59 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 450/1251] eta: 0:06:53 lr: 0.000972 loss: 4.0600 (3.9977) grad_norm: 1.0508 (1.0298) time: 0.5047 [2021-03-25 09:03:04 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 460/1251] eta: 0:06:47 lr: 0.000972 loss: 4.0034 (3.9989) grad_norm: 1.0424 (1.0297) time: 0.5077 [2021-03-25 09:03:09 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 470/1251] eta: 0:06:42 lr: 0.000972 loss: 3.9620 (4.0011) grad_norm: 1.0127 (1.0287) time: 0.5099 [2021-03-25 09:03:14 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 480/1251] eta: 0:06:37 lr: 0.000972 loss: 3.9760 (4.0011) grad_norm: 1.0108 (1.0289) time: 0.5151 [2021-03-25 09:03:19 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 490/1251] eta: 0:06:32 lr: 0.000972 loss: 4.1374 (4.0047) grad_norm: 1.0045 (1.0289) time: 0.5099 [2021-03-25 09:03:24 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 500/1251] eta: 0:06:26 lr: 0.000972 loss: 4.1374 (4.0051) grad_norm: 0.9815 (1.0280) time: 0.5017 [2021-03-25 09:03:29 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 510/1251] eta: 0:06:21 lr: 0.000972 loss: 3.8785 (3.9959) grad_norm: 0.9899 (1.0280) time: 0.5004 [2021-03-25 09:03:34 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 520/1251] eta: 0:06:16 lr: 0.000972 loss: 3.6205 (3.9921) grad_norm: 1.0172 (1.0283) time: 0.5085 [2021-03-25 09:03:40 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 530/1251] eta: 0:06:11 lr: 0.000972 loss: 3.6602 (3.9882) grad_norm: 1.0115 (1.0277) time: 0.5121 [2021-03-25 09:03:45 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 540/1251] eta: 0:06:05 lr: 0.000972 loss: 3.7310 (3.9913) grad_norm: 1.0101 (1.0280) time: 0.5103 [2021-03-25 09:03:50 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 550/1251] eta: 0:06:00 lr: 0.000972 loss: 4.0874 (3.9916) grad_norm: 1.0252 (1.0287) time: 0.5111 [2021-03-25 09:03:55 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 560/1251] eta: 0:05:55 lr: 0.000972 loss: 4.0611 (3.9908) grad_norm: 1.0113 (1.0282) time: 0.5057 [2021-03-25 09:04:00 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 570/1251] eta: 0:05:50 lr: 0.000972 loss: 4.0302 (3.9895) grad_norm: 0.9906 (1.0278) time: 0.5039 [2021-03-25 09:04:05 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 580/1251] eta: 0:05:44 lr: 0.000972 loss: 3.8828 (3.9844) grad_norm: 0.9826 (1.0291) time: 0.5085 [2021-03-25 09:04:10 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 590/1251] eta: 0:05:39 lr: 0.000972 loss: 4.1322 (3.9851) grad_norm: 1.0183 (1.0291) time: 0.5040 [2021-03-25 09:04:15 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 600/1251] eta: 0:05:34 lr: 0.000972 loss: 3.9515 (3.9797) grad_norm: 1.0183 (1.0296) time: 0.5060 [2021-03-25 09:04:20 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 610/1251] eta: 0:05:29 lr: 0.000972 loss: 3.9993 (3.9843) grad_norm: 1.0317 (1.0302) time: 0.5063 [2021-03-25 09:04:25 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 620/1251] eta: 0:05:24 lr: 0.000972 loss: 4.1652 (3.9830) grad_norm: 1.0161 (1.0304) time: 0.5053 [2021-03-25 09:04:30 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 630/1251] eta: 0:05:18 lr: 0.000972 loss: 3.9355 (3.9839) grad_norm: 1.0161 (1.0309) time: 0.5072 [2021-03-25 09:04:35 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 640/1251] eta: 0:05:13 lr: 0.000972 loss: 4.1712 (3.9856) grad_norm: 1.0449 (1.0316) time: 0.5078 [2021-03-25 09:04:40 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 650/1251] eta: 0:05:08 lr: 0.000972 loss: 3.9702 (3.9817) grad_norm: 1.1097 (1.0330) time: 0.5100 [2021-03-25 09:04:45 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 660/1251] eta: 0:05:03 lr: 0.000972 loss: 3.8305 (3.9777) grad_norm: 1.1191 (1.0340) time: 0.5041 [2021-03-25 09:04:50 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 670/1251] eta: 0:04:57 lr: 0.000972 loss: 4.0355 (3.9785) grad_norm: 1.0100 (1.0330) time: 0.5007 [2021-03-25 09:04:55 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 680/1251] eta: 0:04:52 lr: 0.000972 loss: 4.0355 (3.9763) grad_norm: 0.9788 (1.0325) time: 0.4994 [2021-03-25 09:05:01 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 690/1251] eta: 0:04:47 lr: 0.000972 loss: 4.1395 (3.9813) grad_norm: 0.9905 (1.0330) time: 0.5055 [2021-03-25 09:05:06 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 700/1251] eta: 0:04:42 lr: 0.000972 loss: 4.1395 (3.9812) grad_norm: 1.0622 (1.0337) time: 0.5075 [2021-03-25 09:05:11 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 710/1251] eta: 0:04:37 lr: 0.000971 loss: 3.7919 (3.9773) grad_norm: 1.0538 (1.0334) time: 0.5085 [2021-03-25 09:05:16 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 720/1251] eta: 0:04:32 lr: 0.000971 loss: 3.9874 (3.9778) grad_norm: 0.9584 (1.0334) time: 0.5130 [2021-03-25 09:05:21 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 730/1251] eta: 0:04:27 lr: 0.000971 loss: 4.0219 (3.9768) grad_norm: 1.0987 (1.0352) time: 0.5173 [2021-03-25 09:05:26 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 740/1251] eta: 0:04:22 lr: 0.000971 loss: 3.8882 (3.9749) grad_norm: 1.0442 (1.0348) time: 0.5224 [2021-03-25 09:05:31 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 750/1251] eta: 0:04:16 lr: 0.000971 loss: 3.8326 (3.9731) grad_norm: 0.9787 (1.0338) time: 0.5125 [2021-03-25 09:05:36 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 760/1251] eta: 0:04:11 lr: 0.000971 loss: 3.9014 (3.9698) grad_norm: 0.9847 (1.0342) time: 0.5055 [2021-03-25 09:05:41 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 770/1251] eta: 0:04:06 lr: 0.000971 loss: 3.9455 (3.9687) grad_norm: 1.0049 (1.0340) time: 0.5085 [2021-03-25 09:05:46 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 780/1251] eta: 0:04:01 lr: 0.000971 loss: 4.0687 (3.9699) grad_norm: 1.0091 (1.0342) time: 0.5054 [2021-03-25 09:05:52 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 790/1251] eta: 0:03:56 lr: 0.000971 loss: 3.9497 (3.9685) grad_norm: 1.0091 (1.0343) time: 0.5058 [2021-03-25 09:05:57 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 800/1251] eta: 0:03:51 lr: 0.000971 loss: 3.7536 (3.9654) grad_norm: 1.0400 (1.0348) time: 0.5065 [2021-03-25 09:06:02 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 810/1251] eta: 0:03:45 lr: 0.000971 loss: 3.8014 (3.9633) grad_norm: 1.0136 (1.0344) time: 0.5077 [2021-03-25 09:06:07 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 820/1251] eta: 0:03:40 lr: 0.000971 loss: 3.8462 (3.9612) grad_norm: 1.0136 (1.0358) time: 0.5065 [2021-03-25 09:06:12 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 830/1251] eta: 0:03:35 lr: 0.000971 loss: 4.0137 (3.9646) grad_norm: 1.0032 (1.0358) time: 0.5043 [2021-03-25 09:06:17 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 840/1251] eta: 0:03:30 lr: 0.000971 loss: 4.2921 (3.9654) grad_norm: 1.0296 (1.0366) time: 0.5030 [2021-03-25 09:06:22 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 850/1251] eta: 0:03:25 lr: 0.000971 loss: 3.9578 (3.9658) grad_norm: 1.0574 (1.0367) time: 0.5075 [2021-03-25 09:06:27 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 860/1251] eta: 0:03:20 lr: 0.000971 loss: 3.8471 (3.9630) grad_norm: 0.9790 (1.0360) time: 0.5127 [2021-03-25 09:06:32 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 870/1251] eta: 0:03:15 lr: 0.000971 loss: 3.9835 (3.9663) grad_norm: 0.9766 (1.0358) time: 0.5087 [2021-03-25 09:06:37 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 880/1251] eta: 0:03:09 lr: 0.000971 loss: 4.2592 (3.9634) grad_norm: 0.9766 (1.0355) time: 0.5044 [2021-03-25 09:06:42 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 890/1251] eta: 0:03:04 lr: 0.000971 loss: 3.7355 (3.9624) grad_norm: 0.9398 (1.0344) time: 0.5022 [2021-03-25 09:06:47 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 900/1251] eta: 0:02:59 lr: 0.000971 loss: 3.7786 (3.9615) grad_norm: 0.9659 (1.0346) time: 0.5053 [2021-03-25 09:06:52 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 910/1251] eta: 0:02:54 lr: 0.000971 loss: 3.6990 (3.9596) grad_norm: 1.0086 (1.0348) time: 0.5040 [2021-03-25 09:06:57 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 920/1251] eta: 0:02:49 lr: 0.000971 loss: 3.9495 (3.9593) grad_norm: 1.0513 (1.0356) time: 0.5022 [2021-03-25 09:07:02 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 930/1251] eta: 0:02:44 lr: 0.000971 loss: 3.9826 (3.9597) grad_norm: 1.0951 (1.0366) time: 0.5103 [2021-03-25 09:07:08 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 940/1251] eta: 0:02:39 lr: 0.000971 loss: 3.9826 (3.9597) grad_norm: 1.0529 (1.0364) time: 0.5133 [2021-03-25 09:07:13 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 950/1251] eta: 0:02:33 lr: 0.000971 loss: 3.9796 (3.9614) grad_norm: 0.9621 (1.0354) time: 0.5102 [2021-03-25 09:07:18 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 960/1251] eta: 0:02:28 lr: 0.000971 loss: 3.9796 (3.9636) grad_norm: 0.9395 (1.0346) time: 0.5079 [2021-03-25 09:07:23 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 970/1251] eta: 0:02:23 lr: 0.000971 loss: 4.1138 (3.9634) grad_norm: 0.9612 (1.0343) time: 0.5028 [2021-03-25 09:07:28 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 980/1251] eta: 0:02:18 lr: 0.000971 loss: 4.2306 (3.9656) grad_norm: 0.9982 (1.0343) time: 0.5043 [2021-03-25 09:07:33 swin_small_patch4_window7_224] INFO: Epoch: [32] [ 990/1251] eta: 0:02:13 lr: 0.000971 loss: 4.1704 (3.9659) grad_norm: 1.0068 (1.0339) time: 0.5070 [2021-03-25 09:07:38 swin_small_patch4_window7_224] INFO: Epoch: [32] [1000/1251] eta: 0:02:08 lr: 0.000971 loss: 4.1120 (3.9678) grad_norm: 1.0068 (1.0342) time: 0.5061 [2021-03-25 09:07:43 swin_small_patch4_window7_224] INFO: Epoch: [32] [1010/1251] eta: 0:02:03 lr: 0.000971 loss: 4.0499 (3.9667) grad_norm: 0.9795 (1.0335) time: 0.5022 [2021-03-25 09:07:48 swin_small_patch4_window7_224] INFO: Epoch: [32] [1020/1251] eta: 0:01:58 lr: 0.000971 loss: 4.0356 (3.9675) grad_norm: 1.0893 (1.0346) time: 0.5066 [2021-03-25 09:07:53 swin_small_patch4_window7_224] INFO: Epoch: [32] [1030/1251] eta: 0:01:52 lr: 0.000971 loss: 4.1142 (3.9672) grad_norm: 1.1069 (1.0347) time: 0.5160 [2021-03-25 09:07:59 swin_small_patch4_window7_224] INFO: Epoch: [32] [1040/1251] eta: 0:01:47 lr: 0.000971 loss: 4.0614 (3.9689) grad_norm: 1.0267 (1.0343) time: 0.5202 [2021-03-25 09:08:04 swin_small_patch4_window7_224] INFO: Epoch: [32] [1050/1251] eta: 0:01:42 lr: 0.000971 loss: 4.1669 (3.9700) grad_norm: 0.9778 (1.0337) time: 0.5140 [2021-03-25 09:08:09 swin_small_patch4_window7_224] INFO: Epoch: [32] [1060/1251] eta: 0:01:37 lr: 0.000971 loss: 4.2858 (3.9708) grad_norm: 1.0244 (1.0342) time: 0.5006 [2021-03-25 09:08:14 swin_small_patch4_window7_224] INFO: Epoch: [32] [1070/1251] eta: 0:01:32 lr: 0.000971 loss: 4.0572 (3.9718) grad_norm: 1.0484 (1.0343) time: 0.4971 [2021-03-25 09:08:19 swin_small_patch4_window7_224] INFO: Epoch: [32] [1080/1251] eta: 0:01:27 lr: 0.000971 loss: 4.1057 (3.9733) grad_norm: 0.9939 (1.0342) time: 0.5017 [2021-03-25 09:08:24 swin_small_patch4_window7_224] INFO: Epoch: [32] [1090/1251] eta: 0:01:22 lr: 0.000971 loss: 4.3908 (3.9741) grad_norm: 1.0281 (1.0348) time: 0.5028 [2021-03-25 09:08:29 swin_small_patch4_window7_224] INFO: Epoch: [32] [1100/1251] eta: 0:01:17 lr: 0.000971 loss: 4.1706 (3.9753) grad_norm: 1.0281 (1.0346) time: 0.5042 [2021-03-25 09:08:34 swin_small_patch4_window7_224] INFO: Epoch: [32] [1110/1251] eta: 0:01:11 lr: 0.000971 loss: 4.2089 (3.9784) grad_norm: 0.9837 (1.0342) time: 0.5028 [2021-03-25 09:08:39 swin_small_patch4_window7_224] INFO: Epoch: [32] [1120/1251] eta: 0:01:06 lr: 0.000971 loss: 4.3946 (3.9804) grad_norm: 0.9493 (1.0338) time: 0.4978 [2021-03-25 09:08:44 swin_small_patch4_window7_224] INFO: Epoch: [32] [1130/1251] eta: 0:01:01 lr: 0.000971 loss: 4.0546 (3.9787) grad_norm: 1.0320 (1.0340) time: 0.5050 [2021-03-25 09:08:49 swin_small_patch4_window7_224] INFO: Epoch: [32] [1140/1251] eta: 0:00:56 lr: 0.000971 loss: 3.9930 (3.9779) grad_norm: 1.0320 (1.0342) time: 0.5096 [2021-03-25 09:08:54 swin_small_patch4_window7_224] INFO: Epoch: [32] [1150/1251] eta: 0:00:51 lr: 0.000971 loss: 3.9555 (3.9778) grad_norm: 1.0172 (1.0346) time: 0.5064 [2021-03-25 09:08:59 swin_small_patch4_window7_224] INFO: Epoch: [32] [1160/1251] eta: 0:00:46 lr: 0.000971 loss: 3.9344 (3.9773) grad_norm: 1.0699 (1.0354) time: 0.5099 [2021-03-25 09:09:04 swin_small_patch4_window7_224] INFO: Epoch: [32] [1170/1251] eta: 0:00:41 lr: 0.000971 loss: 3.9830 (3.9772) grad_norm: 1.0350 (1.0351) time: 0.5059 [2021-03-25 09:09:09 swin_small_patch4_window7_224] INFO: Epoch: [32] [1180/1251] eta: 0:00:36 lr: 0.000971 loss: 3.9830 (3.9777) grad_norm: 1.0139 (1.0348) time: 0.4976 [2021-03-25 09:09:14 swin_small_patch4_window7_224] INFO: Epoch: [32] [1190/1251] eta: 0:00:31 lr: 0.000971 loss: 3.9022 (3.9771) grad_norm: 0.9817 (1.0342) time: 0.5030 [2021-03-25 09:09:19 swin_small_patch4_window7_224] INFO: Epoch: [32] [1200/1251] eta: 0:00:26 lr: 0.000971 loss: 3.7335 (3.9760) grad_norm: 0.9658 (1.0339) time: 0.5046 [2021-03-25 09:09:24 swin_small_patch4_window7_224] INFO: Epoch: [32] [1210/1251] eta: 0:00:20 lr: 0.000971 loss: 3.6923 (3.9727) grad_norm: 0.9661 (1.0338) time: 0.5041 [2021-03-25 09:09:29 swin_small_patch4_window7_224] INFO: Epoch: [32] [1220/1251] eta: 0:00:15 lr: 0.000971 loss: 3.9027 (3.9732) grad_norm: 0.9697 (1.0336) time: 0.5117 [2021-03-25 09:09:34 swin_small_patch4_window7_224] INFO: Epoch: [32] [1230/1251] eta: 0:00:10 lr: 0.000971 loss: 4.1847 (3.9725) grad_norm: 1.0398 (1.0338) time: 0.5070 [2021-03-25 09:09:39 swin_small_patch4_window7_224] INFO: Epoch: [32] [1240/1251] eta: 0:00:05 lr: 0.000971 loss: 4.1112 (3.9736) grad_norm: 1.0407 (1.0338) time: 0.5044 [2021-03-25 09:09:45 swin_small_patch4_window7_224] INFO: Epoch: [32] [1250/1251] eta: 0:00:00 lr: 0.000971 loss: 4.1112 (3.9754) grad_norm: 1.0879 (1.0347) time: 0.5117 [2021-03-25 09:09:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 1.3143 (1.3143) acc1: 65.6250 (65.6250) acc5: 85.9375 (85.9375) [2021-03-25 09:09:51 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.3143 (1.3191) acc1: 68.7500 (69.3182) acc5: 92.1875 (90.6250) [2021-03-25 09:09:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.2880 (1.3312) acc1: 68.7500 (69.5685) acc5: 89.0625 (90.0298) [2021-03-25 09:09:55 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.3987 (1.3613) acc1: 67.1875 (68.2964) acc5: 89.0625 (89.3145) [2021-03-25 09:09:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3987 (1.3515) acc1: 65.6250 (68.4451) acc5: 89.0625 (89.5579) [2021-03-25 09:09:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.4083 (1.3640) acc1: 65.6250 (68.0320) acc5: 89.0625 (89.4080) [2021-03-25 09:10:00 swin_small_patch4_window7_224] INFO: * Acc@1 69.128 Acc@5 89.670 loss 1.349 [2021-03-25 09:10:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 69.1% [2021-03-25 09:10:00 swin_small_patch4_window7_224] INFO: Max accuracy: 69.13% [2021-03-25 09:10:05 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 0/1251] eta: 1:32:37 lr: 0.000971 loss: 4.5525 (4.5525) grad_norm: 1.1564 (1.1564) time: 4.4421 [2021-03-25 09:10:10 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 10/1251] eta: 0:18:01 lr: 0.000971 loss: 4.3279 (4.0332) grad_norm: 1.0116 (1.0253) time: 0.8716 [2021-03-25 09:10:15 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 20/1251] eta: 0:14:24 lr: 0.000971 loss: 4.1771 (4.0471) grad_norm: 1.0116 (1.0536) time: 0.5157 [2021-03-25 09:10:20 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 30/1251] eta: 0:13:02 lr: 0.000971 loss: 4.0092 (4.0026) grad_norm: 1.0513 (1.0611) time: 0.5137 [2021-03-25 09:10:25 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 40/1251] eta: 0:12:15 lr: 0.000971 loss: 3.9487 (3.9515) grad_norm: 1.1072 (1.0835) time: 0.5074 [2021-03-25 09:10:31 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 50/1251] eta: 0:11:48 lr: 0.000971 loss: 3.9487 (3.9381) grad_norm: 1.1072 (1.0824) time: 0.5113 [2021-03-25 09:10:36 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 60/1251] eta: 0:11:25 lr: 0.000971 loss: 4.0592 (3.9037) grad_norm: 1.0569 (1.0722) time: 0.5108 [2021-03-25 09:10:41 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 70/1251] eta: 0:11:06 lr: 0.000971 loss: 4.0749 (3.9204) grad_norm: 0.9936 (1.0703) time: 0.4993 [2021-03-25 09:10:46 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 80/1251] eta: 0:10:52 lr: 0.000971 loss: 4.1200 (3.9443) grad_norm: 1.0000 (1.0640) time: 0.5019 [2021-03-25 09:10:51 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 90/1251] eta: 0:10:40 lr: 0.000971 loss: 4.1678 (3.9542) grad_norm: 1.0043 (1.0714) time: 0.5052 [2021-03-25 09:10:56 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 100/1251] eta: 0:10:29 lr: 0.000971 loss: 4.1082 (3.9759) grad_norm: 1.0696 (1.0676) time: 0.5050 [2021-03-25 09:11:01 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 110/1251] eta: 0:10:20 lr: 0.000971 loss: 4.0816 (3.9776) grad_norm: 1.0344 (1.0705) time: 0.5096 [2021-03-25 09:11:06 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 120/1251] eta: 0:10:11 lr: 0.000971 loss: 3.8539 (3.9661) grad_norm: 1.0562 (1.0746) time: 0.5106 [2021-03-25 09:11:11 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 130/1251] eta: 0:10:03 lr: 0.000971 loss: 3.8539 (3.9715) grad_norm: 1.0669 (1.0761) time: 0.5093 [2021-03-25 09:11:16 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 140/1251] eta: 0:09:55 lr: 0.000971 loss: 3.8241 (3.9492) grad_norm: 1.0349 (1.0725) time: 0.5074 [2021-03-25 09:11:21 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 150/1251] eta: 0:09:48 lr: 0.000971 loss: 3.7551 (3.9484) grad_norm: 1.0420 (1.0731) time: 0.5108 [2021-03-25 09:11:26 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 160/1251] eta: 0:09:41 lr: 0.000971 loss: 4.0276 (3.9523) grad_norm: 1.0636 (1.0747) time: 0.5062 [2021-03-25 09:11:31 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 170/1251] eta: 0:09:34 lr: 0.000970 loss: 4.1938 (3.9452) grad_norm: 1.0850 (1.0775) time: 0.5056 [2021-03-25 09:11:36 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 180/1251] eta: 0:09:27 lr: 0.000970 loss: 3.9193 (3.9293) grad_norm: 0.9775 (1.0732) time: 0.5097 [2021-03-25 09:11:42 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 190/1251] eta: 0:09:21 lr: 0.000970 loss: 3.8522 (3.9205) grad_norm: 0.9775 (1.0706) time: 0.5107 [2021-03-25 09:11:47 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 200/1251] eta: 0:09:15 lr: 0.000970 loss: 3.9132 (3.9205) grad_norm: 0.9960 (1.0669) time: 0.5145 [2021-03-25 09:11:52 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 210/1251] eta: 0:09:08 lr: 0.000970 loss: 3.9230 (3.9188) grad_norm: 0.9942 (1.0659) time: 0.5065 [2021-03-25 09:11:57 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 220/1251] eta: 0:09:02 lr: 0.000970 loss: 3.8750 (3.9036) grad_norm: 0.9942 (1.0649) time: 0.4989 [2021-03-25 09:12:02 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 230/1251] eta: 0:08:56 lr: 0.000970 loss: 3.9186 (3.9149) grad_norm: 0.9896 (1.0629) time: 0.5080 [2021-03-25 09:12:07 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 240/1251] eta: 0:08:50 lr: 0.000970 loss: 4.1717 (3.9155) grad_norm: 0.9390 (1.0576) time: 0.5166 [2021-03-25 09:12:12 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 250/1251] eta: 0:08:44 lr: 0.000970 loss: 4.1151 (3.9184) grad_norm: 0.9739 (1.0611) time: 0.5110 [2021-03-25 09:12:17 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 260/1251] eta: 0:08:38 lr: 0.000970 loss: 4.0891 (3.9159) grad_norm: 1.0492 (1.0579) time: 0.5051 [2021-03-25 09:12:22 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 270/1251] eta: 0:08:32 lr: 0.000970 loss: 4.0068 (3.9147) grad_norm: 0.9193 (1.0549) time: 0.5023 [2021-03-25 09:12:27 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 280/1251] eta: 0:08:26 lr: 0.000970 loss: 4.0982 (3.9275) grad_norm: 0.9276 (1.0528) time: 0.4980 [2021-03-25 09:12:32 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 290/1251] eta: 0:08:20 lr: 0.000970 loss: 4.1727 (3.9305) grad_norm: 0.9756 (1.0525) time: 0.4966 [2021-03-25 09:12:37 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 300/1251] eta: 0:08:14 lr: 0.000970 loss: 4.1727 (3.9398) grad_norm: 0.9883 (1.0530) time: 0.5023 [2021-03-25 09:12:42 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 310/1251] eta: 0:08:09 lr: 0.000970 loss: 4.0263 (3.9383) grad_norm: 0.9870 (1.0497) time: 0.5126 [2021-03-25 09:12:47 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 320/1251] eta: 0:08:04 lr: 0.000970 loss: 3.9385 (3.9339) grad_norm: 0.9602 (1.0490) time: 0.5140 [2021-03-25 09:12:53 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 330/1251] eta: 0:07:58 lr: 0.000970 loss: 3.7728 (3.9227) grad_norm: 0.9961 (1.0490) time: 0.5058 [2021-03-25 09:12:58 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 340/1251] eta: 0:07:53 lr: 0.000970 loss: 3.8105 (3.9268) grad_norm: 0.9856 (1.0471) time: 0.5084 [2021-03-25 09:13:03 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 350/1251] eta: 0:07:47 lr: 0.000970 loss: 3.9619 (3.9238) grad_norm: 0.9788 (1.0466) time: 0.5090 [2021-03-25 09:13:08 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 360/1251] eta: 0:07:42 lr: 0.000970 loss: 3.5511 (3.9156) grad_norm: 0.9959 (1.0474) time: 0.5052 [2021-03-25 09:13:13 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 370/1251] eta: 0:07:36 lr: 0.000970 loss: 3.6647 (3.9155) grad_norm: 1.0374 (1.0481) time: 0.5055 [2021-03-25 09:13:18 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 380/1251] eta: 0:07:30 lr: 0.000970 loss: 4.0327 (3.9163) grad_norm: 1.0507 (1.0485) time: 0.5016 [2021-03-25 09:13:23 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 390/1251] eta: 0:07:25 lr: 0.000970 loss: 4.1401 (3.9164) grad_norm: 1.1144 (1.0501) time: 0.5051 [2021-03-25 09:13:28 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 400/1251] eta: 0:07:20 lr: 0.000970 loss: 3.9775 (3.9131) grad_norm: 1.0667 (1.0495) time: 0.5067 [2021-03-25 09:13:33 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 410/1251] eta: 0:07:14 lr: 0.000970 loss: 3.9657 (3.9153) grad_norm: 0.9482 (1.0477) time: 0.5011 [2021-03-25 09:13:38 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 420/1251] eta: 0:07:09 lr: 0.000970 loss: 3.7545 (3.9125) grad_norm: 0.9460 (1.0457) time: 0.5015 [2021-03-25 09:13:43 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 430/1251] eta: 0:07:03 lr: 0.000970 loss: 3.7545 (3.9132) grad_norm: 0.9796 (1.0457) time: 0.5057 [2021-03-25 09:13:48 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 440/1251] eta: 0:06:58 lr: 0.000970 loss: 3.6376 (3.9088) grad_norm: 1.0705 (1.0458) time: 0.5050 [2021-03-25 09:13:53 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 450/1251] eta: 0:06:53 lr: 0.000970 loss: 3.8992 (3.9097) grad_norm: 1.0317 (1.0459) time: 0.5042 [2021-03-25 09:13:58 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 460/1251] eta: 0:06:47 lr: 0.000970 loss: 4.0234 (3.9103) grad_norm: 1.0074 (1.0448) time: 0.5076 [2021-03-25 09:14:03 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 470/1251] eta: 0:06:42 lr: 0.000970 loss: 3.8308 (3.9019) grad_norm: 0.9846 (1.0432) time: 0.5066 [2021-03-25 09:14:08 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 480/1251] eta: 0:06:37 lr: 0.000970 loss: 3.8930 (3.9061) grad_norm: 0.9284 (1.0411) time: 0.5028 [2021-03-25 09:14:13 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 490/1251] eta: 0:06:31 lr: 0.000970 loss: 3.9726 (3.9007) grad_norm: 0.9570 (1.0412) time: 0.5021 [2021-03-25 09:14:18 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 500/1251] eta: 0:06:26 lr: 0.000970 loss: 3.9630 (3.9020) grad_norm: 1.0030 (1.0407) time: 0.5048 [2021-03-25 09:14:23 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 510/1251] eta: 0:06:21 lr: 0.000970 loss: 4.0647 (3.9055) grad_norm: 0.9755 (1.0409) time: 0.5050 [2021-03-25 09:14:28 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 520/1251] eta: 0:06:15 lr: 0.000970 loss: 3.9912 (3.9049) grad_norm: 1.0317 (1.0404) time: 0.5014 [2021-03-25 09:14:33 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 530/1251] eta: 0:06:10 lr: 0.000970 loss: 4.0228 (3.9084) grad_norm: 1.0317 (1.0414) time: 0.5016 [2021-03-25 09:14:39 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 540/1251] eta: 0:06:05 lr: 0.000970 loss: 3.9880 (3.9072) grad_norm: 1.0252 (1.0408) time: 0.5107 [2021-03-25 09:14:44 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 550/1251] eta: 0:06:00 lr: 0.000970 loss: 3.6864 (3.9041) grad_norm: 0.9790 (1.0396) time: 0.5177 [2021-03-25 09:14:49 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 560/1251] eta: 0:05:55 lr: 0.000970 loss: 3.5083 (3.8994) grad_norm: 0.9910 (1.0401) time: 0.5162 [2021-03-25 09:14:54 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 570/1251] eta: 0:05:49 lr: 0.000970 loss: 3.8991 (3.9002) grad_norm: 1.0040 (1.0405) time: 0.5113 [2021-03-25 09:14:59 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 580/1251] eta: 0:05:44 lr: 0.000970 loss: 4.0626 (3.8971) grad_norm: 1.0019 (1.0391) time: 0.5053 [2021-03-25 09:15:04 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 590/1251] eta: 0:05:39 lr: 0.000970 loss: 4.0358 (3.8986) grad_norm: 0.9634 (1.0385) time: 0.5026 [2021-03-25 09:15:09 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 600/1251] eta: 0:05:34 lr: 0.000970 loss: 4.0358 (3.9005) grad_norm: 1.0124 (1.0401) time: 0.5056 [2021-03-25 09:15:14 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 610/1251] eta: 0:05:29 lr: 0.000970 loss: 3.9617 (3.8997) grad_norm: 1.0124 (1.0396) time: 0.5109 [2021-03-25 09:15:19 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 620/1251] eta: 0:05:23 lr: 0.000970 loss: 3.9961 (3.9018) grad_norm: 0.9711 (1.0387) time: 0.5113 [2021-03-25 09:15:24 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 630/1251] eta: 0:05:18 lr: 0.000970 loss: 4.2475 (3.9093) grad_norm: 0.9559 (1.0380) time: 0.5035 [2021-03-25 09:15:29 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 640/1251] eta: 0:05:13 lr: 0.000970 loss: 4.1045 (3.9051) grad_norm: 0.9703 (1.0377) time: 0.5001 [2021-03-25 09:15:34 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 650/1251] eta: 0:05:08 lr: 0.000970 loss: 3.7930 (3.9051) grad_norm: 1.0076 (1.0371) time: 0.5039 [2021-03-25 09:15:40 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 660/1251] eta: 0:05:03 lr: 0.000970 loss: 3.9877 (3.9061) grad_norm: 1.0229 (1.0379) time: 0.5100 [2021-03-25 09:15:45 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 670/1251] eta: 0:04:57 lr: 0.000970 loss: 4.0075 (3.9110) grad_norm: 1.0349 (1.0384) time: 0.5102 [2021-03-25 09:15:50 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 680/1251] eta: 0:04:52 lr: 0.000970 loss: 4.2099 (3.9155) grad_norm: 1.0123 (1.0380) time: 0.5065 [2021-03-25 09:15:55 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 690/1251] eta: 0:04:47 lr: 0.000970 loss: 4.1033 (3.9135) grad_norm: 0.9906 (1.0380) time: 0.5048 [2021-03-25 09:16:00 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 700/1251] eta: 0:04:42 lr: 0.000970 loss: 4.0438 (3.9161) grad_norm: 1.0069 (1.0374) time: 0.5083 [2021-03-25 09:16:05 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 710/1251] eta: 0:04:37 lr: 0.000970 loss: 4.1577 (3.9184) grad_norm: 1.0069 (1.0366) time: 0.5095 [2021-03-25 09:16:10 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 720/1251] eta: 0:04:32 lr: 0.000970 loss: 4.2065 (3.9208) grad_norm: 0.9774 (1.0361) time: 0.5094 [2021-03-25 09:16:15 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 730/1251] eta: 0:04:27 lr: 0.000970 loss: 4.1051 (3.9209) grad_norm: 1.0197 (1.0364) time: 0.5166 [2021-03-25 09:16:21 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 740/1251] eta: 0:04:21 lr: 0.000970 loss: 4.0409 (3.9196) grad_norm: 1.0458 (1.0372) time: 0.5207 [2021-03-25 09:16:26 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 750/1251] eta: 0:04:16 lr: 0.000970 loss: 4.1244 (3.9222) grad_norm: 0.9859 (1.0361) time: 0.5155 [2021-03-25 09:16:31 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 760/1251] eta: 0:04:11 lr: 0.000970 loss: 4.1839 (3.9242) grad_norm: 0.9486 (1.0354) time: 0.5108 [2021-03-25 09:16:36 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 770/1251] eta: 0:04:06 lr: 0.000970 loss: 4.1268 (3.9262) grad_norm: 0.9486 (1.0348) time: 0.5103 [2021-03-25 09:16:41 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 780/1251] eta: 0:04:01 lr: 0.000970 loss: 4.2786 (3.9282) grad_norm: 0.9754 (1.0346) time: 0.5068 [2021-03-25 09:16:46 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 790/1251] eta: 0:03:56 lr: 0.000970 loss: 4.2736 (3.9301) grad_norm: 1.0082 (1.0353) time: 0.5057 [2021-03-25 09:16:51 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 800/1251] eta: 0:03:51 lr: 0.000970 loss: 3.9029 (3.9284) grad_norm: 0.9915 (1.0346) time: 0.5079 [2021-03-25 09:16:56 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 810/1251] eta: 0:03:45 lr: 0.000970 loss: 3.9029 (3.9264) grad_norm: 0.9885 (1.0346) time: 0.5063 [2021-03-25 09:17:01 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 820/1251] eta: 0:03:40 lr: 0.000970 loss: 4.0678 (3.9277) grad_norm: 0.9936 (1.0346) time: 0.5032 [2021-03-25 09:17:06 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 830/1251] eta: 0:03:35 lr: 0.000970 loss: 4.0013 (3.9272) grad_norm: 0.9936 (1.0341) time: 0.5024 [2021-03-25 09:17:11 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 840/1251] eta: 0:03:30 lr: 0.000970 loss: 4.0013 (3.9292) grad_norm: 1.0076 (1.0342) time: 0.5015 [2021-03-25 09:17:16 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 850/1251] eta: 0:03:25 lr: 0.000970 loss: 3.9299 (3.9262) grad_norm: 1.0145 (1.0343) time: 0.5057 [2021-03-25 09:17:21 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 860/1251] eta: 0:03:20 lr: 0.000970 loss: 3.7975 (3.9284) grad_norm: 1.0236 (1.0348) time: 0.5157 [2021-03-25 09:17:27 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 870/1251] eta: 0:03:15 lr: 0.000970 loss: 3.9375 (3.9281) grad_norm: 1.0289 (1.0350) time: 0.5132 [2021-03-25 09:17:32 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 880/1251] eta: 0:03:09 lr: 0.000969 loss: 3.8978 (3.9248) grad_norm: 1.0518 (1.0359) time: 0.5033 [2021-03-25 09:17:37 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 890/1251] eta: 0:03:04 lr: 0.000969 loss: 4.1467 (3.9265) grad_norm: 1.0250 (1.0356) time: 0.5091 [2021-03-25 09:17:42 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 900/1251] eta: 0:02:59 lr: 0.000969 loss: 4.1467 (3.9278) grad_norm: 1.0118 (1.0353) time: 0.5106 [2021-03-25 09:17:47 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 910/1251] eta: 0:02:54 lr: 0.000969 loss: 4.0767 (3.9287) grad_norm: 0.9900 (1.0353) time: 0.5094 [2021-03-25 09:17:52 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 920/1251] eta: 0:02:49 lr: 0.000969 loss: 4.2388 (3.9320) grad_norm: 1.0349 (1.0356) time: 0.5112 [2021-03-25 09:17:57 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 930/1251] eta: 0:02:44 lr: 0.000969 loss: 4.0682 (3.9323) grad_norm: 1.0158 (1.0348) time: 0.5122 [2021-03-25 09:18:02 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 940/1251] eta: 0:02:39 lr: 0.000969 loss: 3.9847 (3.9333) grad_norm: 1.0013 (1.0350) time: 0.5121 [2021-03-25 09:18:07 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 950/1251] eta: 0:02:33 lr: 0.000969 loss: 4.1665 (3.9359) grad_norm: 1.0130 (1.0353) time: 0.5028 [2021-03-25 09:18:12 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 960/1251] eta: 0:02:28 lr: 0.000969 loss: 4.0828 (3.9350) grad_norm: 0.9896 (1.0344) time: 0.5025 [2021-03-25 09:18:17 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 970/1251] eta: 0:02:23 lr: 0.000969 loss: 3.9726 (3.9358) grad_norm: 0.9650 (1.0344) time: 0.5083 [2021-03-25 09:18:22 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 980/1251] eta: 0:02:18 lr: 0.000969 loss: 4.2381 (3.9375) grad_norm: 1.0128 (1.0343) time: 0.5077 [2021-03-25 09:18:27 swin_small_patch4_window7_224] INFO: Epoch: [33] [ 990/1251] eta: 0:02:13 lr: 0.000969 loss: 4.1468 (3.9347) grad_norm: 1.0128 (1.0337) time: 0.5011 [2021-03-25 09:18:32 swin_small_patch4_window7_224] INFO: Epoch: [33] [1000/1251] eta: 0:02:08 lr: 0.000969 loss: 3.9717 (3.9346) grad_norm: 0.9685 (1.0336) time: 0.5018 [2021-03-25 09:18:37 swin_small_patch4_window7_224] INFO: Epoch: [33] [1010/1251] eta: 0:02:03 lr: 0.000969 loss: 3.9678 (3.9321) grad_norm: 1.0125 (1.0341) time: 0.5027 [2021-03-25 09:18:42 swin_small_patch4_window7_224] INFO: Epoch: [33] [1020/1251] eta: 0:01:58 lr: 0.000969 loss: 3.9678 (3.9341) grad_norm: 0.9833 (1.0342) time: 0.4987 [2021-03-25 09:18:47 swin_small_patch4_window7_224] INFO: Epoch: [33] [1030/1251] eta: 0:01:52 lr: 0.000969 loss: 4.0999 (3.9348) grad_norm: 0.9860 (1.0340) time: 0.5014 [2021-03-25 09:18:52 swin_small_patch4_window7_224] INFO: Epoch: [33] [1040/1251] eta: 0:01:47 lr: 0.000969 loss: 4.0450 (3.9369) grad_norm: 0.9727 (1.0332) time: 0.5009 [2021-03-25 09:18:58 swin_small_patch4_window7_224] INFO: Epoch: [33] [1050/1251] eta: 0:01:42 lr: 0.000969 loss: 4.1005 (3.9380) grad_norm: 0.9161 (1.0322) time: 0.5126 [2021-03-25 09:19:03 swin_small_patch4_window7_224] INFO: Epoch: [33] [1060/1251] eta: 0:01:37 lr: 0.000969 loss: 4.1005 (3.9382) grad_norm: 0.9015 (1.0309) time: 0.5111 [2021-03-25 09:19:08 swin_small_patch4_window7_224] INFO: Epoch: [33] [1070/1251] eta: 0:01:32 lr: 0.000969 loss: 3.9181 (3.9363) grad_norm: 0.9421 (1.0314) time: 0.5018 [2021-03-25 09:19:13 swin_small_patch4_window7_224] INFO: Epoch: [33] [1080/1251] eta: 0:01:27 lr: 0.000969 loss: 3.9181 (3.9362) grad_norm: 1.0209 (1.0316) time: 0.5095 [2021-03-25 09:19:18 swin_small_patch4_window7_224] INFO: Epoch: [33] [1090/1251] eta: 0:01:22 lr: 0.000969 loss: 3.9367 (3.9348) grad_norm: 0.9784 (1.0317) time: 0.5065 [2021-03-25 09:19:23 swin_small_patch4_window7_224] INFO: Epoch: [33] [1100/1251] eta: 0:01:17 lr: 0.000969 loss: 3.7079 (3.9331) grad_norm: 1.0738 (1.0325) time: 0.5039 [2021-03-25 09:19:28 swin_small_patch4_window7_224] INFO: Epoch: [33] [1110/1251] eta: 0:01:11 lr: 0.000969 loss: 4.1219 (3.9354) grad_norm: 1.0614 (1.0327) time: 0.5038 [2021-03-25 09:19:33 swin_small_patch4_window7_224] INFO: Epoch: [33] [1120/1251] eta: 0:01:06 lr: 0.000969 loss: 4.3143 (3.9366) grad_norm: 1.0037 (1.0326) time: 0.5060 [2021-03-25 09:19:38 swin_small_patch4_window7_224] INFO: Epoch: [33] [1130/1251] eta: 0:01:01 lr: 0.000969 loss: 3.9006 (3.9363) grad_norm: 0.9919 (1.0324) time: 0.5073 [2021-03-25 09:19:43 swin_small_patch4_window7_224] INFO: Epoch: [33] [1140/1251] eta: 0:00:56 lr: 0.000969 loss: 3.9006 (3.9356) grad_norm: 0.9687 (1.0318) time: 0.5032 [2021-03-25 09:19:48 swin_small_patch4_window7_224] INFO: Epoch: [33] [1150/1251] eta: 0:00:51 lr: 0.000969 loss: 4.0449 (3.9370) grad_norm: 0.9701 (1.0313) time: 0.5004 [2021-03-25 09:19:53 swin_small_patch4_window7_224] INFO: Epoch: [33] [1160/1251] eta: 0:00:46 lr: 0.000969 loss: 4.1165 (3.9361) grad_norm: 0.9845 (1.0314) time: 0.4994 [2021-03-25 09:19:58 swin_small_patch4_window7_224] INFO: Epoch: [33] [1170/1251] eta: 0:00:41 lr: 0.000969 loss: 4.0357 (3.9367) grad_norm: 1.0462 (1.0316) time: 0.5042 [2021-03-25 09:20:03 swin_small_patch4_window7_224] INFO: Epoch: [33] [1180/1251] eta: 0:00:36 lr: 0.000969 loss: 3.9995 (3.9363) grad_norm: 1.1027 (1.0326) time: 0.5017 [2021-03-25 09:20:08 swin_small_patch4_window7_224] INFO: Epoch: [33] [1190/1251] eta: 0:00:31 lr: 0.000969 loss: 3.9995 (3.9365) grad_norm: 1.1211 (1.0336) time: 0.4961 [2021-03-25 09:20:13 swin_small_patch4_window7_224] INFO: Epoch: [33] [1200/1251] eta: 0:00:26 lr: 0.000969 loss: 4.0478 (3.9375) grad_norm: 1.0746 (1.0333) time: 0.5009 [2021-03-25 09:20:18 swin_small_patch4_window7_224] INFO: Epoch: [33] [1210/1251] eta: 0:00:20 lr: 0.000969 loss: 3.9424 (3.9361) grad_norm: 0.9891 (1.0332) time: 0.5014 [2021-03-25 09:20:23 swin_small_patch4_window7_224] INFO: Epoch: [33] [1220/1251] eta: 0:00:15 lr: 0.000969 loss: 4.3094 (3.9397) grad_norm: 0.9951 (1.0331) time: 0.5053 [2021-03-25 09:20:28 swin_small_patch4_window7_224] INFO: Epoch: [33] [1230/1251] eta: 0:00:10 lr: 0.000969 loss: 4.3205 (3.9409) grad_norm: 0.9614 (1.0324) time: 0.5118 [2021-03-25 09:20:34 swin_small_patch4_window7_224] INFO: Epoch: [33] [1240/1251] eta: 0:00:05 lr: 0.000969 loss: 4.1004 (3.9411) grad_norm: 0.9760 (1.0325) time: 0.5099 [2021-03-25 09:20:39 swin_small_patch4_window7_224] INFO: Epoch: [33] [1250/1251] eta: 0:00:00 lr: 0.000969 loss: 3.9060 (3.9415) grad_norm: 1.0303 (1.0323) time: 0.5091 [2021-03-25 09:20:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 1.4487 (1.4487) acc1: 60.9375 (60.9375) acc5: 89.0625 (89.0625) [2021-03-25 09:20:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.4487 (1.4633) acc1: 62.5000 (65.3409) acc5: 89.0625 (88.3523) [2021-03-25 09:20:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.3523 (1.3714) acc1: 68.7500 (68.0804) acc5: 89.0625 (88.9881) [2021-03-25 09:20:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.2816 (1.3529) acc1: 68.7500 (68.5484) acc5: 89.0625 (89.2137) [2021-03-25 09:20:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3809 (1.3650) acc1: 67.1875 (67.9116) acc5: 89.0625 (89.2149) [2021-03-25 09:20:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3220 (1.3496) acc1: 67.1875 (68.2560) acc5: 89.0625 (89.3440) [2021-03-25 09:20:56 swin_small_patch4_window7_224] INFO: * Acc@1 69.210 Acc@5 89.708 loss 1.324 [2021-03-25 09:20:56 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 69.2% [2021-03-25 09:20:56 swin_small_patch4_window7_224] INFO: Max accuracy: 69.21% [2021-03-25 09:21:00 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 0/1251] eta: 1:21:55 lr: 0.000969 loss: 4.2741 (4.2741) grad_norm: 0.8754 (0.8754) time: 3.9294 [2021-03-25 09:21:05 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 10/1251] eta: 0:17:27 lr: 0.000969 loss: 4.2741 (4.0553) grad_norm: 1.0813 (1.1304) time: 0.8437 [2021-03-25 09:21:11 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 20/1251] eta: 0:13:59 lr: 0.000969 loss: 3.9057 (3.9309) grad_norm: 1.0160 (1.0623) time: 0.5198 [2021-03-25 09:21:16 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 30/1251] eta: 0:12:42 lr: 0.000969 loss: 3.6435 (3.7375) grad_norm: 0.9840 (inf) time: 0.5044 [2021-03-25 09:21:21 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 40/1251] eta: 0:12:03 lr: 0.000969 loss: 3.6992 (3.8083) grad_norm: 1.0270 (inf) time: 0.5093 [2021-03-25 09:21:26 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 50/1251] eta: 0:11:36 lr: 0.000969 loss: 3.9574 (3.8216) grad_norm: 1.0228 (inf) time: 0.5111 [2021-03-25 09:21:31 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 60/1251] eta: 0:11:17 lr: 0.000969 loss: 3.9860 (3.8442) grad_norm: 0.9701 (inf) time: 0.5087 [2021-03-25 09:21:36 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 70/1251] eta: 0:11:01 lr: 0.000969 loss: 4.0235 (3.8116) grad_norm: 0.9880 (inf) time: 0.5099 [2021-03-25 09:21:41 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 80/1251] eta: 0:10:48 lr: 0.000969 loss: 3.7155 (3.8091) grad_norm: 1.0340 (inf) time: 0.5074 [2021-03-25 09:21:46 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 90/1251] eta: 0:10:37 lr: 0.000969 loss: 3.7986 (3.8124) grad_norm: 1.0287 (inf) time: 0.5105 [2021-03-25 09:21:51 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 100/1251] eta: 0:10:28 lr: 0.000969 loss: 4.2680 (3.8441) grad_norm: 1.0201 (inf) time: 0.5177 [2021-03-25 09:21:56 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 110/1251] eta: 0:10:18 lr: 0.000969 loss: 4.3405 (3.8719) grad_norm: 0.9886 (inf) time: 0.5102 [2021-03-25 09:22:02 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 120/1251] eta: 0:10:10 lr: 0.000969 loss: 4.1188 (3.8801) grad_norm: 1.0242 (inf) time: 0.5043 [2021-03-25 09:22:07 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 130/1251] eta: 0:10:02 lr: 0.000969 loss: 4.1498 (3.8698) grad_norm: 0.9514 (inf) time: 0.5105 [2021-03-25 09:22:12 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 140/1251] eta: 0:09:54 lr: 0.000969 loss: 4.0252 (3.8643) grad_norm: 0.9548 (inf) time: 0.5094 [2021-03-25 09:22:17 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 150/1251] eta: 0:09:46 lr: 0.000969 loss: 3.8490 (3.8627) grad_norm: 1.0160 (inf) time: 0.5016 [2021-03-25 09:22:22 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 160/1251] eta: 0:09:39 lr: 0.000969 loss: 3.5431 (3.8458) grad_norm: 0.9725 (inf) time: 0.5025 [2021-03-25 09:22:27 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 170/1251] eta: 0:09:32 lr: 0.000969 loss: 3.7948 (3.8533) grad_norm: 1.0228 (inf) time: 0.5072 [2021-03-25 09:22:32 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 180/1251] eta: 0:09:26 lr: 0.000969 loss: 3.9152 (3.8589) grad_norm: 1.0445 (inf) time: 0.5148 [2021-03-25 09:22:37 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 190/1251] eta: 0:09:20 lr: 0.000969 loss: 3.9571 (3.8543) grad_norm: 1.0390 (inf) time: 0.5119 [2021-03-25 09:22:42 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 200/1251] eta: 0:09:13 lr: 0.000969 loss: 4.0901 (3.8715) grad_norm: 1.0285 (inf) time: 0.5013 [2021-03-25 09:22:47 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 210/1251] eta: 0:09:07 lr: 0.000969 loss: 4.0614 (3.8805) grad_norm: 1.0024 (inf) time: 0.5044 [2021-03-25 09:22:52 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 220/1251] eta: 0:09:00 lr: 0.000969 loss: 3.9692 (3.8750) grad_norm: 1.0081 (inf) time: 0.5061 [2021-03-25 09:22:57 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 230/1251] eta: 0:08:54 lr: 0.000969 loss: 3.9785 (3.8804) grad_norm: 1.0316 (inf) time: 0.5059 [2021-03-25 09:23:02 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 240/1251] eta: 0:08:49 lr: 0.000969 loss: 3.9934 (3.8798) grad_norm: 1.0288 (inf) time: 0.5089 [2021-03-25 09:23:07 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 250/1251] eta: 0:08:43 lr: 0.000969 loss: 3.8913 (3.8755) grad_norm: 0.9468 (inf) time: 0.5083 [2021-03-25 09:23:13 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 260/1251] eta: 0:08:37 lr: 0.000969 loss: 3.9461 (3.8815) grad_norm: 0.9404 (inf) time: 0.5059 [2021-03-25 09:23:18 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 270/1251] eta: 0:08:31 lr: 0.000969 loss: 4.0923 (3.8915) grad_norm: 0.9684 (inf) time: 0.5061 [2021-03-25 09:23:23 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 280/1251] eta: 0:08:25 lr: 0.000969 loss: 3.9297 (3.8845) grad_norm: 0.9718 (inf) time: 0.5083 [2021-03-25 09:23:28 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 290/1251] eta: 0:08:20 lr: 0.000969 loss: 3.9501 (3.8883) grad_norm: 0.9895 (inf) time: 0.5121 [2021-03-25 09:23:33 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 300/1251] eta: 0:08:14 lr: 0.000969 loss: 4.0628 (3.8850) grad_norm: 0.9496 (inf) time: 0.5103 [2021-03-25 09:23:38 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 310/1251] eta: 0:08:09 lr: 0.000969 loss: 4.0296 (3.8878) grad_norm: 0.9386 (inf) time: 0.5073 [2021-03-25 09:23:43 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 320/1251] eta: 0:08:03 lr: 0.000968 loss: 4.0103 (3.8859) grad_norm: 0.9580 (inf) time: 0.5111 [2021-03-25 09:23:48 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 330/1251] eta: 0:07:58 lr: 0.000968 loss: 4.2358 (3.8951) grad_norm: 0.9942 (inf) time: 0.5104 [2021-03-25 09:23:53 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 340/1251] eta: 0:07:52 lr: 0.000968 loss: 4.3093 (3.9053) grad_norm: 1.0007 (inf) time: 0.5032 [2021-03-25 09:23:58 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 350/1251] eta: 0:07:47 lr: 0.000968 loss: 4.2320 (3.9067) grad_norm: 1.1214 (inf) time: 0.5014 [2021-03-25 09:24:03 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 360/1251] eta: 0:07:41 lr: 0.000968 loss: 3.6966 (3.8987) grad_norm: 1.0810 (inf) time: 0.5041 [2021-03-25 09:24:08 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 370/1251] eta: 0:07:36 lr: 0.000968 loss: 3.8177 (3.9018) grad_norm: 1.0253 (inf) time: 0.5067 [2021-03-25 09:24:13 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 380/1251] eta: 0:07:30 lr: 0.000968 loss: 4.1277 (3.9059) grad_norm: 1.0210 (inf) time: 0.5071 [2021-03-25 09:24:18 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 390/1251] eta: 0:07:25 lr: 0.000968 loss: 3.9536 (3.9016) grad_norm: 0.9233 (inf) time: 0.5061 [2021-03-25 09:24:24 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 400/1251] eta: 0:07:19 lr: 0.000968 loss: 3.5808 (3.8996) grad_norm: 0.9697 (inf) time: 0.5060 [2021-03-25 09:24:29 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 410/1251] eta: 0:07:14 lr: 0.000968 loss: 3.5551 (3.8917) grad_norm: 1.0385 (inf) time: 0.5006 [2021-03-25 09:24:33 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 420/1251] eta: 0:07:08 lr: 0.000968 loss: 3.7534 (3.8946) grad_norm: 1.0017 (inf) time: 0.4974 [2021-03-25 09:24:39 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 430/1251] eta: 0:07:03 lr: 0.000968 loss: 4.0419 (3.8931) grad_norm: 1.0172 (inf) time: 0.5046 [2021-03-25 09:24:44 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 440/1251] eta: 0:06:58 lr: 0.000968 loss: 3.8977 (3.8916) grad_norm: 1.0875 (inf) time: 0.5133 [2021-03-25 09:24:49 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 450/1251] eta: 0:06:53 lr: 0.000968 loss: 3.9039 (3.8926) grad_norm: 1.0763 (inf) time: 0.5120 [2021-03-25 09:24:54 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 460/1251] eta: 0:06:47 lr: 0.000968 loss: 3.9039 (3.8861) grad_norm: 0.9924 (inf) time: 0.5026 [2021-03-25 09:24:59 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 470/1251] eta: 0:06:42 lr: 0.000968 loss: 3.8893 (3.8914) grad_norm: 1.0112 (inf) time: 0.5031 [2021-03-25 09:25:04 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 480/1251] eta: 0:06:36 lr: 0.000968 loss: 4.0029 (3.8949) grad_norm: 1.0143 (inf) time: 0.5055 [2021-03-25 09:25:09 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 490/1251] eta: 0:06:31 lr: 0.000968 loss: 4.0029 (3.8914) grad_norm: 1.0510 (inf) time: 0.5004 [2021-03-25 09:25:14 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 500/1251] eta: 0:06:26 lr: 0.000968 loss: 4.1382 (3.8982) grad_norm: 1.0722 (inf) time: 0.5002 [2021-03-25 09:25:19 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 510/1251] eta: 0:06:20 lr: 0.000968 loss: 4.1908 (3.9003) grad_norm: 0.9894 (inf) time: 0.4997 [2021-03-25 09:25:24 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 520/1251] eta: 0:06:15 lr: 0.000968 loss: 4.0088 (3.9025) grad_norm: 0.9894 (inf) time: 0.5028 [2021-03-25 09:25:29 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 530/1251] eta: 0:06:10 lr: 0.000968 loss: 4.0088 (3.9047) grad_norm: 1.0397 (inf) time: 0.5056 [2021-03-25 09:25:34 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 540/1251] eta: 0:06:05 lr: 0.000968 loss: 3.9484 (3.9054) grad_norm: 0.9913 (inf) time: 0.5073 [2021-03-25 09:25:39 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 550/1251] eta: 0:06:00 lr: 0.000968 loss: 4.0224 (3.9096) grad_norm: 0.9691 (inf) time: 0.5188 [2021-03-25 09:25:45 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 560/1251] eta: 0:05:55 lr: 0.000968 loss: 4.1325 (3.9130) grad_norm: 0.9882 (inf) time: 0.5210 [2021-03-25 09:25:50 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 570/1251] eta: 0:05:49 lr: 0.000968 loss: 4.2338 (3.9147) grad_norm: 1.0122 (inf) time: 0.5103 [2021-03-25 09:25:55 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 580/1251] eta: 0:05:44 lr: 0.000968 loss: 4.1199 (3.9162) grad_norm: 0.9907 (inf) time: 0.5059 [2021-03-25 09:26:00 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 590/1251] eta: 0:05:39 lr: 0.000968 loss: 4.0465 (3.9162) grad_norm: 0.9632 (inf) time: 0.5115 [2021-03-25 09:26:05 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 600/1251] eta: 0:05:34 lr: 0.000968 loss: 3.7426 (3.9122) grad_norm: 0.9753 (inf) time: 0.5064 [2021-03-25 09:26:10 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 610/1251] eta: 0:05:28 lr: 0.000968 loss: 3.8742 (3.9127) grad_norm: 1.0168 (inf) time: 0.5011 [2021-03-25 09:26:15 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 620/1251] eta: 0:05:23 lr: 0.000968 loss: 3.9329 (3.9115) grad_norm: 1.0281 (inf) time: 0.5064 [2021-03-25 09:26:20 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 630/1251] eta: 0:05:18 lr: 0.000968 loss: 4.0072 (3.9131) grad_norm: 1.0046 (inf) time: 0.5086 [2021-03-25 09:26:25 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 640/1251] eta: 0:05:13 lr: 0.000968 loss: 4.0703 (3.9142) grad_norm: 1.0068 (inf) time: 0.5105 [2021-03-25 09:26:30 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 650/1251] eta: 0:05:08 lr: 0.000968 loss: 4.0884 (3.9206) grad_norm: 1.0092 (inf) time: 0.5069 [2021-03-25 09:26:35 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 660/1251] eta: 0:05:03 lr: 0.000968 loss: 4.1142 (3.9207) grad_norm: 0.9537 (inf) time: 0.5030 [2021-03-25 09:26:40 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 670/1251] eta: 0:04:57 lr: 0.000968 loss: 4.0063 (3.9211) grad_norm: 0.9074 (inf) time: 0.5044 [2021-03-25 09:26:45 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 680/1251] eta: 0:04:52 lr: 0.000968 loss: 4.0666 (3.9240) grad_norm: 1.0319 (inf) time: 0.5023 [2021-03-25 09:26:50 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 690/1251] eta: 0:04:47 lr: 0.000968 loss: 4.1345 (3.9248) grad_norm: 1.0632 (inf) time: 0.5036 [2021-03-25 09:26:55 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 700/1251] eta: 0:04:42 lr: 0.000968 loss: 4.0392 (3.9258) grad_norm: 1.0013 (inf) time: 0.5058 [2021-03-25 09:27:00 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 710/1251] eta: 0:04:37 lr: 0.000968 loss: 4.1359 (3.9286) grad_norm: 0.9797 (inf) time: 0.5038 [2021-03-25 09:27:05 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 720/1251] eta: 0:04:31 lr: 0.000968 loss: 4.1359 (3.9318) grad_norm: 0.9840 (inf) time: 0.5020 [2021-03-25 09:27:11 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 730/1251] eta: 0:04:26 lr: 0.000968 loss: 4.0921 (3.9298) grad_norm: 0.9940 (inf) time: 0.5041 [2021-03-25 09:27:16 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 740/1251] eta: 0:04:21 lr: 0.000968 loss: 4.0045 (3.9313) grad_norm: 0.9592 (inf) time: 0.5216 [2021-03-25 09:27:21 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 750/1251] eta: 0:04:16 lr: 0.000968 loss: 4.1833 (3.9342) grad_norm: 1.0625 (inf) time: 0.5231 [2021-03-25 09:27:26 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 760/1251] eta: 0:04:11 lr: 0.000968 loss: 4.1833 (3.9359) grad_norm: 1.0138 (inf) time: 0.5042 [2021-03-25 09:27:31 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 770/1251] eta: 0:04:06 lr: 0.000968 loss: 3.8612 (3.9310) grad_norm: 0.9322 (inf) time: 0.4939 [2021-03-25 09:27:36 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 780/1251] eta: 0:04:01 lr: 0.000968 loss: 3.9930 (3.9321) grad_norm: 0.9322 (inf) time: 0.5055 [2021-03-25 09:27:41 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 790/1251] eta: 0:03:55 lr: 0.000968 loss: 4.1690 (3.9309) grad_norm: 1.0321 (inf) time: 0.5176 [2021-03-25 09:27:46 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 800/1251] eta: 0:03:50 lr: 0.000968 loss: 3.9949 (3.9322) grad_norm: 1.0499 (inf) time: 0.5095 [2021-03-25 09:27:51 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 810/1251] eta: 0:03:45 lr: 0.000968 loss: 4.0470 (3.9347) grad_norm: 0.9839 (inf) time: 0.5007 [2021-03-25 09:27:56 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 820/1251] eta: 0:03:40 lr: 0.000968 loss: 4.0424 (3.9332) grad_norm: 0.9839 (inf) time: 0.5008 [2021-03-25 09:28:01 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 830/1251] eta: 0:03:35 lr: 0.000968 loss: 3.9407 (3.9332) grad_norm: 0.9915 (inf) time: 0.5065 [2021-03-25 09:28:06 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 840/1251] eta: 0:03:30 lr: 0.000968 loss: 4.1706 (3.9356) grad_norm: 1.0327 (inf) time: 0.5053 [2021-03-25 09:28:11 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 850/1251] eta: 0:03:25 lr: 0.000968 loss: 4.2165 (3.9354) grad_norm: 0.9840 (inf) time: 0.5041 [2021-03-25 09:28:17 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 860/1251] eta: 0:03:19 lr: 0.000968 loss: 3.9296 (3.9328) grad_norm: 0.9840 (inf) time: 0.5080 [2021-03-25 09:28:22 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 870/1251] eta: 0:03:14 lr: 0.000968 loss: 3.9327 (3.9340) grad_norm: 0.9926 (inf) time: 0.5145 [2021-03-25 09:28:27 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 880/1251] eta: 0:03:09 lr: 0.000968 loss: 3.9327 (3.9349) grad_norm: 0.9744 (inf) time: 0.5153 [2021-03-25 09:28:32 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 890/1251] eta: 0:03:04 lr: 0.000968 loss: 4.0784 (3.9369) grad_norm: 1.0026 (inf) time: 0.5070 [2021-03-25 09:28:37 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 900/1251] eta: 0:02:59 lr: 0.000968 loss: 4.0508 (3.9368) grad_norm: 1.0036 (inf) time: 0.5033 [2021-03-25 09:28:42 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 910/1251] eta: 0:02:54 lr: 0.000968 loss: 3.9941 (3.9369) grad_norm: 1.0400 (inf) time: 0.5083 [2021-03-25 09:28:47 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 920/1251] eta: 0:02:49 lr: 0.000968 loss: 4.0024 (3.9379) grad_norm: 0.9762 (inf) time: 0.5082 [2021-03-25 09:28:52 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 930/1251] eta: 0:02:44 lr: 0.000968 loss: 4.0832 (3.9375) grad_norm: 0.9728 (inf) time: 0.5085 [2021-03-25 09:28:57 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 940/1251] eta: 0:02:38 lr: 0.000968 loss: 3.9455 (3.9368) grad_norm: 0.9518 (inf) time: 0.5087 [2021-03-25 09:29:02 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 950/1251] eta: 0:02:33 lr: 0.000968 loss: 3.8159 (3.9353) grad_norm: 0.9549 (inf) time: 0.4985 [2021-03-25 09:29:07 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 960/1251] eta: 0:02:28 lr: 0.000968 loss: 3.7750 (3.9317) grad_norm: 1.0251 (inf) time: 0.4990 [2021-03-25 09:29:12 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 970/1251] eta: 0:02:23 lr: 0.000968 loss: 3.6194 (3.9307) grad_norm: 0.9753 (inf) time: 0.5060 [2021-03-25 09:29:17 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 980/1251] eta: 0:02:18 lr: 0.000968 loss: 3.6740 (3.9299) grad_norm: 0.9500 (inf) time: 0.5074 [2021-03-25 09:29:22 swin_small_patch4_window7_224] INFO: Epoch: [34] [ 990/1251] eta: 0:02:13 lr: 0.000968 loss: 4.1017 (3.9310) grad_norm: 0.9618 (inf) time: 0.5046 [2021-03-25 09:29:27 swin_small_patch4_window7_224] INFO: Epoch: [34] [1000/1251] eta: 0:02:08 lr: 0.000967 loss: 3.9516 (3.9279) grad_norm: 0.9964 (inf) time: 0.5015 [2021-03-25 09:29:32 swin_small_patch4_window7_224] INFO: Epoch: [34] [1010/1251] eta: 0:02:03 lr: 0.000967 loss: 3.6689 (3.9271) grad_norm: 1.0068 (inf) time: 0.5011 [2021-03-25 09:29:38 swin_small_patch4_window7_224] INFO: Epoch: [34] [1020/1251] eta: 0:01:57 lr: 0.000967 loss: 4.0067 (3.9289) grad_norm: 1.0434 (inf) time: 0.5039 [2021-03-25 09:29:43 swin_small_patch4_window7_224] INFO: Epoch: [34] [1030/1251] eta: 0:01:52 lr: 0.000967 loss: 4.0067 (3.9287) grad_norm: 1.0015 (inf) time: 0.5053 [2021-03-25 09:29:48 swin_small_patch4_window7_224] INFO: Epoch: [34] [1040/1251] eta: 0:01:47 lr: 0.000967 loss: 3.6812 (3.9272) grad_norm: 0.9676 (inf) time: 0.5080 [2021-03-25 09:29:53 swin_small_patch4_window7_224] INFO: Epoch: [34] [1050/1251] eta: 0:01:42 lr: 0.000967 loss: 3.6353 (3.9241) grad_norm: 0.9628 (inf) time: 0.5099 [2021-03-25 09:29:58 swin_small_patch4_window7_224] INFO: Epoch: [34] [1060/1251] eta: 0:01:37 lr: 0.000967 loss: 4.0240 (3.9246) grad_norm: 0.9705 (inf) time: 0.5147 [2021-03-25 09:30:03 swin_small_patch4_window7_224] INFO: Epoch: [34] [1070/1251] eta: 0:01:32 lr: 0.000967 loss: 4.1919 (3.9269) grad_norm: 0.9855 (inf) time: 0.5149 [2021-03-25 09:30:08 swin_small_patch4_window7_224] INFO: Epoch: [34] [1080/1251] eta: 0:01:27 lr: 0.000967 loss: 4.1919 (3.9270) grad_norm: 0.9609 (inf) time: 0.5068 [2021-03-25 09:30:13 swin_small_patch4_window7_224] INFO: Epoch: [34] [1090/1251] eta: 0:01:22 lr: 0.000967 loss: 3.8449 (3.9252) grad_norm: 0.9021 (inf) time: 0.5079 [2021-03-25 09:30:18 swin_small_patch4_window7_224] INFO: Epoch: [34] [1100/1251] eta: 0:01:17 lr: 0.000967 loss: 4.0917 (3.9263) grad_norm: 0.9481 (inf) time: 0.5033 [2021-03-25 09:30:23 swin_small_patch4_window7_224] INFO: Epoch: [34] [1110/1251] eta: 0:01:11 lr: 0.000967 loss: 3.9779 (3.9247) grad_norm: 0.9743 (inf) time: 0.5084 [2021-03-25 09:30:28 swin_small_patch4_window7_224] INFO: Epoch: [34] [1120/1251] eta: 0:01:06 lr: 0.000967 loss: 3.9779 (3.9262) grad_norm: 0.9282 (inf) time: 0.5112 [2021-03-25 09:30:33 swin_small_patch4_window7_224] INFO: Epoch: [34] [1130/1251] eta: 0:01:01 lr: 0.000967 loss: 3.9211 (3.9250) grad_norm: 0.9781 (inf) time: 0.5041 [2021-03-25 09:30:39 swin_small_patch4_window7_224] INFO: Epoch: [34] [1140/1251] eta: 0:00:56 lr: 0.000967 loss: 3.9562 (3.9261) grad_norm: 1.0341 (inf) time: 0.5067 [2021-03-25 09:30:44 swin_small_patch4_window7_224] INFO: Epoch: [34] [1150/1251] eta: 0:00:51 lr: 0.000967 loss: 4.1138 (3.9270) grad_norm: 0.9806 (inf) time: 0.5074 [2021-03-25 09:30:49 swin_small_patch4_window7_224] INFO: Epoch: [34] [1160/1251] eta: 0:00:46 lr: 0.000967 loss: 4.0831 (3.9288) grad_norm: 0.9608 (inf) time: 0.4990 [2021-03-25 09:30:54 swin_small_patch4_window7_224] INFO: Epoch: [34] [1170/1251] eta: 0:00:41 lr: 0.000967 loss: 4.0365 (3.9281) grad_norm: 0.9537 (inf) time: 0.5007 [2021-03-25 09:30:59 swin_small_patch4_window7_224] INFO: Epoch: [34] [1180/1251] eta: 0:00:36 lr: 0.000967 loss: 3.9720 (3.9284) grad_norm: 0.9378 (inf) time: 0.5080 [2021-03-25 09:31:04 swin_small_patch4_window7_224] INFO: Epoch: [34] [1190/1251] eta: 0:00:31 lr: 0.000967 loss: 4.1289 (3.9298) grad_norm: 0.9713 (inf) time: 0.5028 [2021-03-25 09:31:09 swin_small_patch4_window7_224] INFO: Epoch: [34] [1200/1251] eta: 0:00:26 lr: 0.000967 loss: 4.1266 (3.9261) grad_norm: 1.0000 (inf) time: 0.5045 [2021-03-25 09:31:14 swin_small_patch4_window7_224] INFO: Epoch: [34] [1210/1251] eta: 0:00:20 lr: 0.000967 loss: 3.8238 (3.9276) grad_norm: 1.0201 (inf) time: 0.5025 [2021-03-25 09:31:19 swin_small_patch4_window7_224] INFO: Epoch: [34] [1220/1251] eta: 0:00:15 lr: 0.000967 loss: 4.0991 (3.9278) grad_norm: 1.0140 (inf) time: 0.4997 [2021-03-25 09:31:24 swin_small_patch4_window7_224] INFO: Epoch: [34] [1230/1251] eta: 0:00:10 lr: 0.000967 loss: 3.9756 (3.9267) grad_norm: 1.0140 (inf) time: 0.5015 [2021-03-25 09:31:29 swin_small_patch4_window7_224] INFO: Epoch: [34] [1240/1251] eta: 0:00:05 lr: 0.000967 loss: 3.7396 (3.9241) grad_norm: 0.9922 (inf) time: 0.5032 [2021-03-25 09:31:34 swin_small_patch4_window7_224] INFO: Epoch: [34] [1250/1251] eta: 0:00:00 lr: 0.000967 loss: 3.9431 (3.9244) grad_norm: 0.9298 (inf) time: 0.5072 [2021-03-25 09:31:39 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:18 loss: 1.3373 (1.3373) acc1: 62.5000 (62.5000) acc5: 92.1875 (92.1875) [2021-03-25 09:31:41 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.4285 (1.4083) acc1: 67.1875 (66.4773) acc5: 87.5000 (88.2102) [2021-03-25 09:31:44 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.3100 (1.3390) acc1: 67.1875 (67.9315) acc5: 89.0625 (88.6161) [2021-03-25 09:31:47 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.2283 (1.3379) acc1: 68.7500 (68.0948) acc5: 90.6250 (88.9617) [2021-03-25 09:31:48 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3026 (1.3338) acc1: 67.1875 (68.2546) acc5: 89.0625 (88.8720) [2021-03-25 09:31:49 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2371 (1.3095) acc1: 70.3125 (68.6400) acc5: 90.6250 (89.4400) [2021-03-25 09:31:50 swin_small_patch4_window7_224] INFO: * Acc@1 69.738 Acc@5 90.062 loss 1.292 [2021-03-25 09:31:50 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 69.7% [2021-03-25 09:31:50 swin_small_patch4_window7_224] INFO: Max accuracy: 69.74% [2021-03-25 09:31:55 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 0/1251] eta: 1:35:19 lr: 0.000967 loss: 4.3871 (4.3871) grad_norm: 1.1865 (1.1865) time: 4.5721 [2021-03-25 09:32:00 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 10/1251] eta: 0:18:09 lr: 0.000967 loss: 4.1459 (3.8507) grad_norm: 0.9932 (1.0475) time: 0.8776 [2021-03-25 09:32:05 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 20/1251] eta: 0:14:30 lr: 0.000967 loss: 3.9864 (3.7885) grad_norm: 0.9932 (1.0493) time: 0.5138 [2021-03-25 09:32:10 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 30/1251] eta: 0:13:01 lr: 0.000967 loss: 3.8839 (3.8293) grad_norm: 1.0211 (1.0676) time: 0.5096 [2021-03-25 09:32:15 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 40/1251] eta: 0:12:16 lr: 0.000967 loss: 3.9799 (3.8869) grad_norm: 1.0670 (1.0819) time: 0.5036 [2021-03-25 09:32:20 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 50/1251] eta: 0:11:45 lr: 0.000967 loss: 3.9988 (3.8841) grad_norm: 1.0417 (1.0666) time: 0.5059 [2021-03-25 09:32:25 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 60/1251] eta: 0:11:25 lr: 0.000967 loss: 3.9180 (3.9129) grad_norm: 0.9823 (1.0489) time: 0.5086 [2021-03-25 09:32:31 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 70/1251] eta: 0:11:07 lr: 0.000967 loss: 4.0035 (3.9188) grad_norm: 1.0127 (1.0471) time: 0.5090 [2021-03-25 09:32:36 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 80/1251] eta: 0:10:53 lr: 0.000967 loss: 3.9002 (3.8878) grad_norm: 1.0121 (1.0325) time: 0.5069 [2021-03-25 09:32:41 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 90/1251] eta: 0:10:39 lr: 0.000967 loss: 3.8964 (3.8915) grad_norm: 0.9716 (1.0283) time: 0.5010 [2021-03-25 09:32:46 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 100/1251] eta: 0:10:29 lr: 0.000967 loss: 3.9373 (3.8881) grad_norm: 0.9716 (1.0230) time: 0.5006 [2021-03-25 09:32:51 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 110/1251] eta: 0:10:21 lr: 0.000967 loss: 3.6342 (3.8704) grad_norm: 0.9880 (1.0219) time: 0.5137 [2021-03-25 09:32:56 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 120/1251] eta: 0:10:12 lr: 0.000967 loss: 4.0708 (3.8885) grad_norm: 0.9890 (1.0189) time: 0.5163 [2021-03-25 09:33:01 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 130/1251] eta: 0:10:06 lr: 0.000967 loss: 4.1389 (3.8867) grad_norm: 0.9768 (1.0178) time: 0.5197 [2021-03-25 09:33:06 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 140/1251] eta: 0:09:58 lr: 0.000967 loss: 4.1401 (3.9020) grad_norm: 0.9906 (1.0238) time: 0.5169 [2021-03-25 09:33:11 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 150/1251] eta: 0:09:50 lr: 0.000967 loss: 4.1177 (3.9095) grad_norm: 1.1036 (1.0336) time: 0.5076 [2021-03-25 09:33:16 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 160/1251] eta: 0:09:42 lr: 0.000967 loss: 3.9112 (3.9012) grad_norm: 1.0993 (1.0376) time: 0.5013 [2021-03-25 09:33:21 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 170/1251] eta: 0:09:35 lr: 0.000967 loss: 3.7996 (3.9029) grad_norm: 1.0099 (1.0347) time: 0.5005 [2021-03-25 09:33:27 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 180/1251] eta: 0:09:28 lr: 0.000967 loss: 4.0206 (3.8962) grad_norm: 0.9900 (1.0318) time: 0.5111 [2021-03-25 09:33:32 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 190/1251] eta: 0:09:22 lr: 0.000967 loss: 4.1593 (3.9120) grad_norm: 0.9914 (1.0319) time: 0.5137 [2021-03-25 09:33:37 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 200/1251] eta: 0:09:16 lr: 0.000967 loss: 4.1855 (3.9065) grad_norm: 1.0070 (1.0321) time: 0.5106 [2021-03-25 09:33:42 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 210/1251] eta: 0:09:09 lr: 0.000967 loss: 3.8927 (3.9127) grad_norm: 0.9924 (1.0300) time: 0.5088 [2021-03-25 09:33:47 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 220/1251] eta: 0:09:03 lr: 0.000967 loss: 3.9610 (3.9190) grad_norm: 1.0173 (1.0334) time: 0.5108 [2021-03-25 09:33:52 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 230/1251] eta: 0:08:57 lr: 0.000967 loss: 3.8422 (3.9092) grad_norm: 1.0948 (1.0359) time: 0.5129 [2021-03-25 09:33:57 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 240/1251] eta: 0:08:51 lr: 0.000967 loss: 3.7283 (3.9030) grad_norm: 1.0233 (1.0336) time: 0.5072 [2021-03-25 09:34:02 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 250/1251] eta: 0:08:46 lr: 0.000967 loss: 3.9353 (3.9129) grad_norm: 0.9547 (1.0301) time: 0.5110 [2021-03-25 09:34:07 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 260/1251] eta: 0:08:39 lr: 0.000967 loss: 3.9353 (3.9148) grad_norm: 0.9547 (1.0303) time: 0.5104 [2021-03-25 09:34:12 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 270/1251] eta: 0:08:33 lr: 0.000967 loss: 4.0185 (3.9254) grad_norm: 0.9762 (1.0294) time: 0.4987 [2021-03-25 09:34:17 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 280/1251] eta: 0:08:27 lr: 0.000967 loss: 4.0892 (3.9232) grad_norm: 0.9762 (1.0291) time: 0.4990 [2021-03-25 09:34:22 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 290/1251] eta: 0:08:21 lr: 0.000967 loss: 3.9515 (3.9273) grad_norm: 0.9953 (1.0275) time: 0.5002 [2021-03-25 09:34:27 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 300/1251] eta: 0:08:15 lr: 0.000967 loss: 3.9515 (3.9252) grad_norm: 1.0057 (1.0274) time: 0.5029 [2021-03-25 09:34:33 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 310/1251] eta: 0:08:10 lr: 0.000967 loss: 3.8655 (3.9206) grad_norm: 1.0021 (1.0269) time: 0.5089 [2021-03-25 09:34:38 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 320/1251] eta: 0:08:04 lr: 0.000967 loss: 4.0120 (3.9205) grad_norm: 0.9656 (1.0265) time: 0.5067 [2021-03-25 09:34:43 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 330/1251] eta: 0:07:59 lr: 0.000967 loss: 4.0307 (3.9285) grad_norm: 0.9710 (1.0258) time: 0.5060 [2021-03-25 09:34:48 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 340/1251] eta: 0:07:53 lr: 0.000967 loss: 4.2078 (3.9368) grad_norm: 0.9868 (1.0263) time: 0.5024 [2021-03-25 09:34:53 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 350/1251] eta: 0:07:47 lr: 0.000967 loss: 4.1508 (3.9338) grad_norm: 0.9623 (1.0253) time: 0.4984 [2021-03-25 09:34:58 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 360/1251] eta: 0:07:42 lr: 0.000967 loss: 3.9988 (3.9366) grad_norm: 1.0144 (1.0260) time: 0.5030 [2021-03-25 09:35:03 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 370/1251] eta: 0:07:36 lr: 0.000967 loss: 4.1698 (3.9413) grad_norm: 1.0144 (1.0253) time: 0.5054 [2021-03-25 09:35:08 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 380/1251] eta: 0:07:31 lr: 0.000967 loss: 4.1768 (3.9444) grad_norm: 0.9668 (1.0250) time: 0.5073 [2021-03-25 09:35:13 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 390/1251] eta: 0:07:25 lr: 0.000967 loss: 4.1395 (3.9457) grad_norm: 0.9472 (1.0258) time: 0.5030 [2021-03-25 09:35:18 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 400/1251] eta: 0:07:20 lr: 0.000967 loss: 4.1522 (3.9468) grad_norm: 1.0452 (1.0279) time: 0.5033 [2021-03-25 09:35:23 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 410/1251] eta: 0:07:14 lr: 0.000967 loss: 4.1711 (3.9516) grad_norm: 1.0046 (1.0265) time: 0.5043 [2021-03-25 09:35:28 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 420/1251] eta: 0:07:09 lr: 0.000966 loss: 4.1388 (3.9523) grad_norm: 0.9639 (1.0257) time: 0.5064 [2021-03-25 09:35:33 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 430/1251] eta: 0:07:03 lr: 0.000966 loss: 3.9886 (3.9471) grad_norm: 0.9653 (1.0263) time: 0.5071 [2021-03-25 09:35:38 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 440/1251] eta: 0:06:58 lr: 0.000966 loss: 3.9886 (3.9478) grad_norm: 1.0827 (1.0285) time: 0.5103 [2021-03-25 09:35:43 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 450/1251] eta: 0:06:53 lr: 0.000966 loss: 3.9363 (3.9478) grad_norm: 1.1080 (1.0299) time: 0.5119 [2021-03-25 09:35:48 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 460/1251] eta: 0:06:48 lr: 0.000966 loss: 3.9363 (3.9475) grad_norm: 1.0000 (1.0303) time: 0.5050 [2021-03-25 09:35:53 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 470/1251] eta: 0:06:42 lr: 0.000966 loss: 4.0332 (3.9507) grad_norm: 0.9410 (1.0283) time: 0.5042 [2021-03-25 09:35:58 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 480/1251] eta: 0:06:37 lr: 0.000966 loss: 3.9745 (3.9485) grad_norm: 0.9467 (1.0289) time: 0.5001 [2021-03-25 09:36:03 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 490/1251] eta: 0:06:32 lr: 0.000966 loss: 3.9051 (3.9489) grad_norm: 1.0820 (1.0308) time: 0.5047 [2021-03-25 09:36:09 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 500/1251] eta: 0:06:26 lr: 0.000966 loss: 4.0416 (3.9456) grad_norm: 1.0820 (1.0321) time: 0.5090 [2021-03-25 09:36:14 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 510/1251] eta: 0:06:21 lr: 0.000966 loss: 4.0385 (3.9433) grad_norm: 1.0733 (1.0332) time: 0.5077 [2021-03-25 09:36:19 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 520/1251] eta: 0:06:16 lr: 0.000966 loss: 4.0385 (3.9456) grad_norm: 1.0054 (1.0325) time: 0.5047 [2021-03-25 09:36:24 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 530/1251] eta: 0:06:10 lr: 0.000966 loss: 4.0152 (3.9444) grad_norm: 0.9719 (1.0313) time: 0.4993 [2021-03-25 09:36:29 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 540/1251] eta: 0:06:05 lr: 0.000966 loss: 3.8694 (3.9428) grad_norm: 0.9427 (1.0314) time: 0.5073 [2021-03-25 09:36:34 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 550/1251] eta: 0:06:00 lr: 0.000966 loss: 3.8694 (3.9411) grad_norm: 0.9643 (1.0303) time: 0.5194 [2021-03-25 09:36:39 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 560/1251] eta: 0:05:55 lr: 0.000966 loss: 3.9161 (3.9399) grad_norm: 0.9754 (1.0298) time: 0.5095 [2021-03-25 09:36:44 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 570/1251] eta: 0:05:50 lr: 0.000966 loss: 4.1018 (3.9428) grad_norm: 1.0069 (1.0300) time: 0.5034 [2021-03-25 09:36:49 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 580/1251] eta: 0:05:44 lr: 0.000966 loss: 4.1695 (3.9472) grad_norm: 1.0256 (1.0297) time: 0.5084 [2021-03-25 09:36:54 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 590/1251] eta: 0:05:39 lr: 0.000966 loss: 4.0772 (3.9466) grad_norm: 1.0659 (1.0314) time: 0.5048 [2021-03-25 09:36:59 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 600/1251] eta: 0:05:34 lr: 0.000966 loss: 3.9625 (3.9479) grad_norm: 1.0659 (1.0308) time: 0.5043 [2021-03-25 09:37:04 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 610/1251] eta: 0:05:29 lr: 0.000966 loss: 3.9625 (3.9490) grad_norm: 0.9976 (1.0308) time: 0.5021 [2021-03-25 09:37:09 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 620/1251] eta: 0:05:23 lr: 0.000966 loss: 3.9472 (3.9478) grad_norm: 0.9606 (1.0293) time: 0.4997 [2021-03-25 09:37:14 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 630/1251] eta: 0:05:18 lr: 0.000966 loss: 3.7297 (3.9415) grad_norm: 0.9320 (1.0284) time: 0.4987 [2021-03-25 09:37:19 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 640/1251] eta: 0:05:13 lr: 0.000966 loss: 3.7152 (3.9395) grad_norm: 0.9320 (1.0273) time: 0.5001 [2021-03-25 09:37:24 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 650/1251] eta: 0:05:08 lr: 0.000966 loss: 4.1456 (3.9397) grad_norm: 0.9369 (1.0277) time: 0.5016 [2021-03-25 09:37:29 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 660/1251] eta: 0:05:02 lr: 0.000966 loss: 3.8981 (3.9371) grad_norm: 1.0116 (1.0279) time: 0.5033 [2021-03-25 09:37:34 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 670/1251] eta: 0:04:57 lr: 0.000966 loss: 3.8981 (3.9343) grad_norm: 1.0075 (1.0274) time: 0.5044 [2021-03-25 09:37:39 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 680/1251] eta: 0:04:52 lr: 0.000966 loss: 3.9979 (3.9370) grad_norm: 0.9618 (1.0265) time: 0.5075 [2021-03-25 09:37:44 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 690/1251] eta: 0:04:47 lr: 0.000966 loss: 4.0540 (3.9364) grad_norm: 1.0755 (1.0288) time: 0.5082 [2021-03-25 09:37:50 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 700/1251] eta: 0:04:42 lr: 0.000966 loss: 3.8358 (3.9335) grad_norm: 1.1677 (1.0300) time: 0.5046 [2021-03-25 09:37:55 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 710/1251] eta: 0:04:37 lr: 0.000966 loss: 4.2129 (3.9355) grad_norm: 1.0415 (1.0292) time: 0.5055 [2021-03-25 09:38:00 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 720/1251] eta: 0:04:31 lr: 0.000966 loss: 4.0378 (3.9333) grad_norm: 0.9686 (1.0286) time: 0.5011 [2021-03-25 09:38:05 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 730/1251] eta: 0:04:26 lr: 0.000966 loss: 3.8921 (3.9314) grad_norm: 0.9506 (1.0281) time: 0.5019 [2021-03-25 09:38:10 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 740/1251] eta: 0:04:21 lr: 0.000966 loss: 3.7673 (3.9275) grad_norm: 0.9307 (1.0271) time: 0.5263 [2021-03-25 09:38:15 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 750/1251] eta: 0:04:16 lr: 0.000966 loss: 3.4349 (3.9233) grad_norm: 1.0562 (1.0292) time: 0.5238 [2021-03-25 09:38:20 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 760/1251] eta: 0:04:11 lr: 0.000966 loss: 3.9740 (3.9261) grad_norm: 1.0907 (1.0294) time: 0.5048 [2021-03-25 09:38:25 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 770/1251] eta: 0:04:06 lr: 0.000966 loss: 4.0261 (3.9233) grad_norm: 1.0139 (1.0300) time: 0.5053 [2021-03-25 09:38:30 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 780/1251] eta: 0:04:01 lr: 0.000966 loss: 3.9543 (3.9263) grad_norm: 1.0229 (1.0308) time: 0.5043 [2021-03-25 09:38:35 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 790/1251] eta: 0:03:55 lr: 0.000966 loss: 4.0531 (3.9250) grad_norm: 0.9933 (1.0302) time: 0.5014 [2021-03-25 09:38:40 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 800/1251] eta: 0:03:50 lr: 0.000966 loss: 4.1371 (3.9282) grad_norm: 1.0440 (1.0311) time: 0.5018 [2021-03-25 09:38:45 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 810/1251] eta: 0:03:45 lr: 0.000966 loss: 3.9644 (3.9287) grad_norm: 1.0383 (1.0304) time: 0.5026 [2021-03-25 09:38:50 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 820/1251] eta: 0:03:40 lr: 0.000966 loss: 3.9795 (3.9303) grad_norm: 1.0187 (1.0316) time: 0.5026 [2021-03-25 09:38:55 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 830/1251] eta: 0:03:35 lr: 0.000966 loss: 4.0064 (3.9299) grad_norm: 1.0562 (1.0320) time: 0.5047 [2021-03-25 09:39:00 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 840/1251] eta: 0:03:30 lr: 0.000966 loss: 4.0064 (3.9298) grad_norm: 1.0562 (1.0320) time: 0.5054 [2021-03-25 09:39:06 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 850/1251] eta: 0:03:25 lr: 0.000966 loss: 4.0266 (3.9287) grad_norm: 1.0307 (1.0323) time: 0.5147 [2021-03-25 09:39:11 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 860/1251] eta: 0:03:19 lr: 0.000966 loss: 4.0988 (3.9318) grad_norm: 1.0426 (1.0328) time: 0.5174 [2021-03-25 09:39:16 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 870/1251] eta: 0:03:14 lr: 0.000966 loss: 4.1041 (3.9328) grad_norm: 1.0487 (1.0330) time: 0.5164 [2021-03-25 09:39:21 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 880/1251] eta: 0:03:09 lr: 0.000966 loss: 4.0437 (3.9313) grad_norm: 1.0587 (1.0335) time: 0.5165 [2021-03-25 09:39:26 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 890/1251] eta: 0:03:04 lr: 0.000966 loss: 3.8935 (3.9290) grad_norm: 0.9957 (1.0326) time: 0.5108 [2021-03-25 09:39:31 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 900/1251] eta: 0:02:59 lr: 0.000966 loss: 3.9399 (3.9292) grad_norm: 0.9739 (1.0330) time: 0.5065 [2021-03-25 09:39:36 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 910/1251] eta: 0:02:54 lr: 0.000966 loss: 3.9517 (3.9284) grad_norm: 1.0716 (1.0339) time: 0.5052 [2021-03-25 09:39:41 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 920/1251] eta: 0:02:49 lr: 0.000966 loss: 4.1996 (3.9300) grad_norm: 1.0716 (1.0349) time: 0.5029 [2021-03-25 09:39:46 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 930/1251] eta: 0:02:44 lr: 0.000966 loss: 4.0839 (3.9312) grad_norm: 1.0092 (1.0349) time: 0.5048 [2021-03-25 09:39:52 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 940/1251] eta: 0:02:39 lr: 0.000966 loss: 4.0803 (3.9334) grad_norm: 0.9762 (1.0346) time: 0.5138 [2021-03-25 09:39:57 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 950/1251] eta: 0:02:33 lr: 0.000966 loss: 4.0856 (3.9347) grad_norm: 0.9442 (1.0339) time: 0.5110 [2021-03-25 09:40:02 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 960/1251] eta: 0:02:28 lr: 0.000966 loss: 4.0683 (3.9346) grad_norm: 0.9389 (1.0339) time: 0.5076 [2021-03-25 09:40:07 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 970/1251] eta: 0:02:23 lr: 0.000966 loss: 4.1353 (3.9340) grad_norm: 1.0420 (1.0337) time: 0.5130 [2021-03-25 09:40:12 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 980/1251] eta: 0:02:18 lr: 0.000966 loss: 3.8511 (3.9331) grad_norm: 1.0102 (1.0343) time: 0.5105 [2021-03-25 09:40:17 swin_small_patch4_window7_224] INFO: Epoch: [35] [ 990/1251] eta: 0:02:13 lr: 0.000966 loss: 4.0062 (3.9340) grad_norm: 0.9781 (1.0341) time: 0.5076 [2021-03-25 09:40:22 swin_small_patch4_window7_224] INFO: Epoch: [35] [1000/1251] eta: 0:02:08 lr: 0.000966 loss: 4.1085 (3.9353) grad_norm: 1.0204 (1.0349) time: 0.5124 [2021-03-25 09:40:27 swin_small_patch4_window7_224] INFO: Epoch: [35] [1010/1251] eta: 0:02:03 lr: 0.000966 loss: 4.0825 (3.9351) grad_norm: 1.0635 (1.0354) time: 0.5054 [2021-03-25 09:40:32 swin_small_patch4_window7_224] INFO: Epoch: [35] [1020/1251] eta: 0:01:58 lr: 0.000966 loss: 4.0825 (3.9368) grad_norm: 1.0113 (1.0347) time: 0.4964 [2021-03-25 09:40:37 swin_small_patch4_window7_224] INFO: Epoch: [35] [1030/1251] eta: 0:01:52 lr: 0.000966 loss: 3.8735 (3.9332) grad_norm: 0.9508 (1.0343) time: 0.4992 [2021-03-25 09:40:42 swin_small_patch4_window7_224] INFO: Epoch: [35] [1040/1251] eta: 0:01:47 lr: 0.000966 loss: 3.6894 (3.9312) grad_norm: 0.9668 (1.0340) time: 0.5021 [2021-03-25 09:40:47 swin_small_patch4_window7_224] INFO: Epoch: [35] [1050/1251] eta: 0:01:42 lr: 0.000966 loss: 3.9603 (3.9319) grad_norm: 1.0273 (1.0345) time: 0.5120 [2021-03-25 09:40:52 swin_small_patch4_window7_224] INFO: Epoch: [35] [1060/1251] eta: 0:01:37 lr: 0.000966 loss: 3.8684 (3.9294) grad_norm: 1.0859 (1.0350) time: 0.5105 [2021-03-25 09:40:57 swin_small_patch4_window7_224] INFO: Epoch: [35] [1070/1251] eta: 0:01:32 lr: 0.000966 loss: 3.6944 (3.9293) grad_norm: 1.0151 (1.0344) time: 0.5020 [2021-03-25 09:41:03 swin_small_patch4_window7_224] INFO: Epoch: [35] [1080/1251] eta: 0:01:27 lr: 0.000965 loss: 3.7730 (3.9266) grad_norm: 0.9616 (1.0338) time: 0.5057 [2021-03-25 09:41:08 swin_small_patch4_window7_224] INFO: Epoch: [35] [1090/1251] eta: 0:01:22 lr: 0.000965 loss: 3.7730 (3.9253) grad_norm: 0.9740 (1.0338) time: 0.5085 [2021-03-25 09:41:13 swin_small_patch4_window7_224] INFO: Epoch: [35] [1100/1251] eta: 0:01:17 lr: 0.000965 loss: 3.9835 (3.9269) grad_norm: 1.0095 (1.0334) time: 0.5072 [2021-03-25 09:41:18 swin_small_patch4_window7_224] INFO: Epoch: [35] [1110/1251] eta: 0:01:11 lr: 0.000965 loss: 4.0787 (3.9272) grad_norm: 0.9858 (1.0331) time: 0.5049 [2021-03-25 09:41:23 swin_small_patch4_window7_224] INFO: Epoch: [35] [1120/1251] eta: 0:01:06 lr: 0.000965 loss: 3.9661 (3.9252) grad_norm: 0.9359 (1.0325) time: 0.5065 [2021-03-25 09:41:28 swin_small_patch4_window7_224] INFO: Epoch: [35] [1130/1251] eta: 0:01:01 lr: 0.000965 loss: 3.8959 (3.9250) grad_norm: 0.9446 (1.0328) time: 0.5031 [2021-03-25 09:41:33 swin_small_patch4_window7_224] INFO: Epoch: [35] [1140/1251] eta: 0:00:56 lr: 0.000965 loss: 3.9827 (3.9248) grad_norm: 0.9809 (1.0321) time: 0.5054 [2021-03-25 09:41:38 swin_small_patch4_window7_224] INFO: Epoch: [35] [1150/1251] eta: 0:00:51 lr: 0.000965 loss: 4.0578 (3.9245) grad_norm: 0.9809 (1.0323) time: 0.5073 [2021-03-25 09:41:43 swin_small_patch4_window7_224] INFO: Epoch: [35] [1160/1251] eta: 0:00:46 lr: 0.000965 loss: 4.0578 (3.9256) grad_norm: 0.9698 (1.0318) time: 0.5054 [2021-03-25 09:41:48 swin_small_patch4_window7_224] INFO: Epoch: [35] [1170/1251] eta: 0:00:41 lr: 0.000965 loss: 4.1197 (3.9274) grad_norm: 0.9871 (1.0321) time: 0.5041 [2021-03-25 09:41:53 swin_small_patch4_window7_224] INFO: Epoch: [35] [1180/1251] eta: 0:00:36 lr: 0.000965 loss: 3.9643 (3.9253) grad_norm: 1.0032 (1.0315) time: 0.5041 [2021-03-25 09:41:58 swin_small_patch4_window7_224] INFO: Epoch: [35] [1190/1251] eta: 0:00:31 lr: 0.000965 loss: 4.0137 (3.9267) grad_norm: 0.9230 (1.0307) time: 0.5064 [2021-03-25 09:42:03 swin_small_patch4_window7_224] INFO: Epoch: [35] [1200/1251] eta: 0:00:26 lr: 0.000965 loss: 3.9793 (3.9231) grad_norm: 0.9229 (1.0304) time: 0.5054 [2021-03-25 09:42:08 swin_small_patch4_window7_224] INFO: Epoch: [35] [1210/1251] eta: 0:00:20 lr: 0.000965 loss: 3.6541 (3.9230) grad_norm: 0.9809 (1.0301) time: 0.5090 [2021-03-25 09:42:13 swin_small_patch4_window7_224] INFO: Epoch: [35] [1220/1251] eta: 0:00:15 lr: 0.000965 loss: 3.9273 (3.9255) grad_norm: 1.0081 (1.0303) time: 0.5043 [2021-03-25 09:42:18 swin_small_patch4_window7_224] INFO: Epoch: [35] [1230/1251] eta: 0:00:10 lr: 0.000965 loss: 4.2219 (3.9257) grad_norm: 1.0394 (1.0302) time: 0.5048 [2021-03-25 09:42:24 swin_small_patch4_window7_224] INFO: Epoch: [35] [1240/1251] eta: 0:00:05 lr: 0.000965 loss: 3.9557 (3.9253) grad_norm: 0.9507 (1.0297) time: 0.5102 [2021-03-25 09:42:29 swin_small_patch4_window7_224] INFO: Epoch: [35] [1250/1251] eta: 0:00:00 lr: 0.000965 loss: 4.0703 (3.9264) grad_norm: 1.0014 (1.0300) time: 0.5099 [2021-03-25 09:43:08 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.0014 (1.0014) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-25 09:43:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.2357 (1.2295) acc1: 73.4375 (72.7273) acc5: 89.0625 (90.1989) [2021-03-25 09:43:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.3124 (1.2915) acc1: 70.3125 (71.1310) acc5: 89.0625 (89.3601) [2021-03-25 09:43:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.2543 (1.2886) acc1: 68.7500 (70.2117) acc5: 89.0625 (89.6169) [2021-03-25 09:43:13 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2543 (1.3067) acc1: 68.7500 (69.7790) acc5: 90.6250 (89.7866) [2021-03-25 09:43:14 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3715 (1.3189) acc1: 67.1875 (69.3760) acc5: 89.0625 (89.5680) [2021-03-25 09:43:17 swin_small_patch4_window7_224] INFO: * Acc@1 70.024 Acc@5 90.098 loss 1.287 [2021-03-25 09:43:17 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.0% [2021-03-25 09:43:17 swin_small_patch4_window7_224] INFO: Max accuracy: 70.02% [2021-03-25 09:43:21 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 0/1251] eta: 1:28:49 lr: 0.000965 loss: 4.3172 (4.3172) grad_norm: 1.0609 (1.0609) time: 4.2605 [2021-03-25 09:43:26 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 10/1251] eta: 0:17:44 lr: 0.000965 loss: 3.8463 (3.8619) grad_norm: 1.0700 (1.1035) time: 0.8575 [2021-03-25 09:43:31 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 20/1251] eta: 0:14:09 lr: 0.000965 loss: 3.8463 (3.8723) grad_norm: 1.0043 (1.0507) time: 0.5113 [2021-03-25 09:43:36 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 30/1251] eta: 0:12:48 lr: 0.000965 loss: 3.7607 (3.8851) grad_norm: 1.0043 (1.0408) time: 0.5045 [2021-03-25 09:43:41 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 40/1251] eta: 0:12:08 lr: 0.000965 loss: 3.8440 (3.9244) grad_norm: 0.9993 (1.0219) time: 0.5087 [2021-03-25 09:43:47 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 50/1251] eta: 0:11:44 lr: 0.000965 loss: 4.2462 (3.9952) grad_norm: 0.9835 (1.0149) time: 0.5199 [2021-03-25 09:43:52 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 60/1251] eta: 0:11:23 lr: 0.000965 loss: 4.0765 (3.9978) grad_norm: 0.9874 (1.0128) time: 0.5177 [2021-03-25 09:43:57 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 70/1251] eta: 0:11:05 lr: 0.000965 loss: 3.9736 (3.9951) grad_norm: 1.0191 (1.0129) time: 0.5051 [2021-03-25 09:44:02 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 80/1251] eta: 0:10:53 lr: 0.000965 loss: 4.0626 (3.9853) grad_norm: 0.9862 (1.0180) time: 0.5091 [2021-03-25 09:44:07 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 90/1251] eta: 0:10:39 lr: 0.000965 loss: 3.9696 (3.9772) grad_norm: 1.0039 (1.0195) time: 0.5048 [2021-03-25 09:44:12 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 100/1251] eta: 0:10:28 lr: 0.000965 loss: 3.9769 (3.9862) grad_norm: 1.0039 (1.0191) time: 0.4975 [2021-03-25 09:44:17 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 110/1251] eta: 0:10:20 lr: 0.000965 loss: 4.1025 (3.9805) grad_norm: 1.0035 (1.0179) time: 0.5108 [2021-03-25 09:44:22 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 120/1251] eta: 0:10:10 lr: 0.000965 loss: 3.8577 (3.9591) grad_norm: 0.9989 (1.0216) time: 0.5076 [2021-03-25 09:44:27 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 130/1251] eta: 0:10:02 lr: 0.000965 loss: 3.9938 (3.9677) grad_norm: 0.9835 (1.0236) time: 0.5032 [2021-03-25 09:44:32 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 140/1251] eta: 0:09:55 lr: 0.000965 loss: 4.0213 (3.9658) grad_norm: 1.0502 (1.0330) time: 0.5139 [2021-03-25 09:44:37 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 150/1251] eta: 0:09:47 lr: 0.000965 loss: 3.9972 (3.9796) grad_norm: 1.0865 (1.0348) time: 0.5110 [2021-03-25 09:44:43 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 160/1251] eta: 0:09:40 lr: 0.000965 loss: 3.9507 (3.9560) grad_norm: 1.0057 (1.0350) time: 0.5066 [2021-03-25 09:44:48 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 170/1251] eta: 0:09:33 lr: 0.000965 loss: 3.8395 (3.9584) grad_norm: 0.9941 (1.0368) time: 0.5055 [2021-03-25 09:44:53 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 180/1251] eta: 0:09:27 lr: 0.000965 loss: 4.0993 (3.9555) grad_norm: 0.9637 (1.0323) time: 0.5067 [2021-03-25 09:44:58 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 190/1251] eta: 0:09:19 lr: 0.000965 loss: 3.9272 (3.9529) grad_norm: 0.9226 (1.0306) time: 0.5035 [2021-03-25 09:45:03 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 200/1251] eta: 0:09:13 lr: 0.000965 loss: 3.9455 (3.9502) grad_norm: 0.9627 (1.0262) time: 0.4998 [2021-03-25 09:45:08 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 210/1251] eta: 0:09:06 lr: 0.000965 loss: 3.8971 (3.9409) grad_norm: 0.9686 (1.0246) time: 0.5008 [2021-03-25 09:45:13 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 220/1251] eta: 0:09:00 lr: 0.000965 loss: 3.7882 (3.9353) grad_norm: 0.9198 (1.0197) time: 0.4970 [2021-03-25 09:45:18 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 230/1251] eta: 0:08:54 lr: 0.000965 loss: 4.0430 (3.9330) grad_norm: 0.9559 (1.0246) time: 0.5073 [2021-03-25 09:45:23 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 240/1251] eta: 0:08:48 lr: 0.000965 loss: 4.0065 (3.9297) grad_norm: 1.0644 (1.0270) time: 0.5120 [2021-03-25 09:45:28 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 250/1251] eta: 0:08:42 lr: 0.000965 loss: 4.1372 (3.9368) grad_norm: 0.9906 (1.0251) time: 0.5071 [2021-03-25 09:45:33 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 260/1251] eta: 0:08:36 lr: 0.000965 loss: 4.1575 (3.9376) grad_norm: 0.9593 (1.0235) time: 0.5060 [2021-03-25 09:45:38 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 270/1251] eta: 0:08:31 lr: 0.000965 loss: 4.0013 (3.9455) grad_norm: 0.9518 (1.0225) time: 0.5053 [2021-03-25 09:45:43 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 280/1251] eta: 0:08:25 lr: 0.000965 loss: 4.2672 (3.9504) grad_norm: 0.9985 (1.0215) time: 0.5077 [2021-03-25 09:45:48 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 290/1251] eta: 0:08:19 lr: 0.000965 loss: 3.9912 (3.9404) grad_norm: 0.9985 (1.0211) time: 0.5075 [2021-03-25 09:45:53 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 300/1251] eta: 0:08:14 lr: 0.000965 loss: 3.8236 (3.9312) grad_norm: 1.0297 (1.0219) time: 0.5090 [2021-03-25 09:45:58 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 310/1251] eta: 0:08:08 lr: 0.000965 loss: 3.9771 (3.9304) grad_norm: 0.9705 (1.0190) time: 0.5047 [2021-03-25 09:46:03 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 320/1251] eta: 0:08:02 lr: 0.000965 loss: 3.6697 (3.9146) grad_norm: 0.9307 (1.0189) time: 0.4999 [2021-03-25 09:46:08 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 330/1251] eta: 0:07:57 lr: 0.000965 loss: 3.5577 (3.9163) grad_norm: 0.9746 (1.0192) time: 0.5069 [2021-03-25 09:46:13 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 340/1251] eta: 0:07:51 lr: 0.000965 loss: 3.8432 (3.9105) grad_norm: 1.0381 (1.0223) time: 0.5071 [2021-03-25 09:46:19 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 350/1251] eta: 0:07:46 lr: 0.000965 loss: 3.8564 (3.9130) grad_norm: 1.0574 (1.0224) time: 0.5034 [2021-03-25 09:46:24 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 360/1251] eta: 0:07:40 lr: 0.000965 loss: 3.9701 (3.9157) grad_norm: 0.9706 (1.0225) time: 0.5032 [2021-03-25 09:46:29 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 370/1251] eta: 0:07:35 lr: 0.000965 loss: 3.9820 (3.9173) grad_norm: 1.0198 (1.0237) time: 0.5023 [2021-03-25 09:46:34 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 380/1251] eta: 0:07:29 lr: 0.000965 loss: 4.0245 (3.9159) grad_norm: 1.0198 (1.0234) time: 0.5057 [2021-03-25 09:46:39 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 390/1251] eta: 0:07:24 lr: 0.000965 loss: 4.2607 (3.9219) grad_norm: 1.0186 (1.0234) time: 0.5091 [2021-03-25 09:46:44 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 400/1251] eta: 0:07:19 lr: 0.000965 loss: 4.1265 (3.9207) grad_norm: 0.9864 (1.0227) time: 0.5050 [2021-03-25 09:46:49 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 410/1251] eta: 0:07:13 lr: 0.000965 loss: 3.8783 (3.9189) grad_norm: 0.9488 (1.0228) time: 0.5044 [2021-03-25 09:46:54 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 420/1251] eta: 0:07:08 lr: 0.000965 loss: 3.8114 (3.9191) grad_norm: 1.0014 (1.0225) time: 0.5034 [2021-03-25 09:46:59 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 430/1251] eta: 0:07:02 lr: 0.000965 loss: 3.9787 (3.9183) grad_norm: 0.9883 (1.0223) time: 0.5040 [2021-03-25 09:47:04 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 440/1251] eta: 0:06:57 lr: 0.000965 loss: 3.8814 (3.9135) grad_norm: 0.9461 (1.0206) time: 0.5105 [2021-03-25 09:47:09 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 450/1251] eta: 0:06:52 lr: 0.000965 loss: 3.9041 (3.9188) grad_norm: 0.9360 (1.0197) time: 0.5085 [2021-03-25 09:47:14 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 460/1251] eta: 0:06:47 lr: 0.000965 loss: 4.1025 (3.9153) grad_norm: 0.9360 (1.0174) time: 0.5064 [2021-03-25 09:47:19 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 470/1251] eta: 0:06:41 lr: 0.000965 loss: 3.8656 (3.9141) grad_norm: 0.9061 (1.0158) time: 0.5054 [2021-03-25 09:47:24 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 480/1251] eta: 0:06:36 lr: 0.000965 loss: 3.5426 (3.9070) grad_norm: 0.9523 (1.0156) time: 0.5015 [2021-03-25 09:47:29 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 490/1251] eta: 0:06:31 lr: 0.000964 loss: 3.5426 (3.9075) grad_norm: 0.9929 (1.0167) time: 0.5070 [2021-03-25 09:47:34 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 500/1251] eta: 0:06:26 lr: 0.000964 loss: 3.4655 (3.8963) grad_norm: 1.0209 (1.0170) time: 0.5093 [2021-03-25 09:47:39 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 510/1251] eta: 0:06:20 lr: 0.000964 loss: 3.7105 (3.8987) grad_norm: 0.9984 (1.0161) time: 0.5040 [2021-03-25 09:47:45 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 520/1251] eta: 0:06:15 lr: 0.000964 loss: 4.0466 (3.9009) grad_norm: 0.9394 (1.0152) time: 0.5116 [2021-03-25 09:47:50 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 530/1251] eta: 0:06:10 lr: 0.000964 loss: 4.1082 (3.8997) grad_norm: 1.0085 (1.0169) time: 0.5118 [2021-03-25 09:47:55 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 540/1251] eta: 0:06:05 lr: 0.000964 loss: 3.8272 (3.8957) grad_norm: 1.1108 (1.0184) time: 0.5052 [2021-03-25 09:48:00 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 550/1251] eta: 0:06:00 lr: 0.000964 loss: 3.7806 (3.8944) grad_norm: 1.0019 (1.0178) time: 0.5121 [2021-03-25 09:48:05 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 560/1251] eta: 0:05:54 lr: 0.000964 loss: 3.9786 (3.8973) grad_norm: 0.9315 (1.0164) time: 0.5144 [2021-03-25 09:48:10 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 570/1251] eta: 0:05:49 lr: 0.000964 loss: 4.0800 (3.8973) grad_norm: 0.9291 (1.0160) time: 0.5126 [2021-03-25 09:48:15 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 580/1251] eta: 0:05:44 lr: 0.000964 loss: 4.0272 (3.8969) grad_norm: 1.0046 (1.0162) time: 0.5043 [2021-03-25 09:48:20 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 590/1251] eta: 0:05:39 lr: 0.000964 loss: 3.8361 (3.8932) grad_norm: 0.9411 (1.0152) time: 0.4996 [2021-03-25 09:48:25 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 600/1251] eta: 0:05:33 lr: 0.000964 loss: 3.6519 (3.8929) grad_norm: 0.9305 (1.0148) time: 0.5056 [2021-03-25 09:48:30 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 610/1251] eta: 0:05:28 lr: 0.000964 loss: 3.9323 (3.8891) grad_norm: 0.9644 (1.0136) time: 0.5067 [2021-03-25 09:48:35 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 620/1251] eta: 0:05:23 lr: 0.000964 loss: 3.7397 (3.8876) grad_norm: 0.9172 (1.0126) time: 0.5024 [2021-03-25 09:48:40 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 630/1251] eta: 0:05:18 lr: 0.000964 loss: 3.7397 (3.8874) grad_norm: 0.9629 (1.0136) time: 0.5041 [2021-03-25 09:48:46 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 640/1251] eta: 0:05:13 lr: 0.000964 loss: 4.1472 (3.8932) grad_norm: 1.0323 (1.0137) time: 0.5108 [2021-03-25 09:48:51 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 650/1251] eta: 0:05:08 lr: 0.000964 loss: 4.1493 (3.8966) grad_norm: 0.9702 (1.0142) time: 0.5077 [2021-03-25 09:48:56 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 660/1251] eta: 0:05:02 lr: 0.000964 loss: 4.1493 (3.8987) grad_norm: 0.9481 (1.0136) time: 0.5097 [2021-03-25 09:49:01 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 670/1251] eta: 0:04:57 lr: 0.000964 loss: 4.1137 (3.8970) grad_norm: 0.9994 (1.0139) time: 0.5075 [2021-03-25 09:49:06 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 680/1251] eta: 0:04:52 lr: 0.000964 loss: 3.8050 (3.8968) grad_norm: 1.0343 (1.0139) time: 0.5009 [2021-03-25 09:49:11 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 690/1251] eta: 0:04:47 lr: 0.000964 loss: 4.1349 (3.9024) grad_norm: 1.0343 (1.0149) time: 0.5068 [2021-03-25 09:49:16 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 700/1251] eta: 0:04:42 lr: 0.000964 loss: 3.9590 (3.8991) grad_norm: 1.0199 (1.0147) time: 0.5094 [2021-03-25 09:49:21 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 710/1251] eta: 0:04:37 lr: 0.000964 loss: 3.8547 (3.9000) grad_norm: 0.9767 (1.0143) time: 0.5132 [2021-03-25 09:49:26 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 720/1251] eta: 0:04:31 lr: 0.000964 loss: 3.8372 (3.8962) grad_norm: 1.0415 (1.0153) time: 0.5121 [2021-03-25 09:49:31 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 730/1251] eta: 0:04:26 lr: 0.000964 loss: 3.9131 (3.8979) grad_norm: 1.0435 (1.0152) time: 0.4996 [2021-03-25 09:49:36 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 740/1251] eta: 0:04:21 lr: 0.000964 loss: 4.0665 (3.8988) grad_norm: 0.9907 (1.0149) time: 0.5023 [2021-03-25 09:49:41 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 750/1251] eta: 0:04:16 lr: 0.000964 loss: 4.0316 (3.8997) grad_norm: 0.9843 (1.0150) time: 0.5074 [2021-03-25 09:49:46 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 760/1251] eta: 0:04:11 lr: 0.000964 loss: 3.9445 (3.8993) grad_norm: 0.9843 (1.0148) time: 0.5076 [2021-03-25 09:49:51 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 770/1251] eta: 0:04:06 lr: 0.000964 loss: 3.4845 (3.8942) grad_norm: 0.9634 (1.0145) time: 0.5085 [2021-03-25 09:49:57 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 780/1251] eta: 0:04:01 lr: 0.000964 loss: 3.6566 (3.8960) grad_norm: 0.9634 (1.0144) time: 0.5094 [2021-03-25 09:50:02 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 790/1251] eta: 0:03:55 lr: 0.000964 loss: 4.1544 (3.8976) grad_norm: 1.0440 (1.0150) time: 0.5133 [2021-03-25 09:50:07 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 800/1251] eta: 0:03:50 lr: 0.000964 loss: 3.9703 (3.8982) grad_norm: 0.9815 (1.0138) time: 0.5153 [2021-03-25 09:50:12 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 810/1251] eta: 0:03:45 lr: 0.000964 loss: 3.7492 (3.8966) grad_norm: 0.9115 (1.0131) time: 0.5072 [2021-03-25 09:50:17 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 820/1251] eta: 0:03:40 lr: 0.000964 loss: 3.6838 (3.8935) grad_norm: 0.9449 (1.0124) time: 0.5011 [2021-03-25 09:50:22 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 830/1251] eta: 0:03:35 lr: 0.000964 loss: 3.6143 (3.8886) grad_norm: 1.0141 (1.0140) time: 0.5108 [2021-03-25 09:50:27 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 840/1251] eta: 0:03:30 lr: 0.000964 loss: 3.6143 (3.8865) grad_norm: 1.0967 (1.0151) time: 0.5142 [2021-03-25 09:50:32 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 850/1251] eta: 0:03:25 lr: 0.000964 loss: 4.0131 (3.8876) grad_norm: 1.0303 (1.0150) time: 0.5057 [2021-03-25 09:50:37 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 860/1251] eta: 0:03:19 lr: 0.000964 loss: 4.0167 (3.8875) grad_norm: 0.9629 (1.0147) time: 0.5019 [2021-03-25 09:50:42 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 870/1251] eta: 0:03:14 lr: 0.000964 loss: 3.9161 (3.8869) grad_norm: 1.0415 (1.0161) time: 0.5058 [2021-03-25 09:50:47 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 880/1251] eta: 0:03:09 lr: 0.000964 loss: 3.9198 (3.8877) grad_norm: 1.0030 (1.0158) time: 0.5123 [2021-03-25 09:50:52 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 890/1251] eta: 0:03:04 lr: 0.000964 loss: 4.1570 (3.8878) grad_norm: 0.9931 (1.0159) time: 0.5079 [2021-03-25 09:50:57 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 900/1251] eta: 0:02:59 lr: 0.000964 loss: 4.1379 (3.8881) grad_norm: 1.0520 (1.0167) time: 0.4957 [2021-03-25 09:51:02 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 910/1251] eta: 0:02:54 lr: 0.000964 loss: 4.2016 (3.8917) grad_norm: 1.0059 (1.0166) time: 0.4979 [2021-03-25 09:51:07 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 920/1251] eta: 0:02:49 lr: 0.000964 loss: 4.1711 (3.8927) grad_norm: 0.9754 (1.0166) time: 0.5039 [2021-03-25 09:51:13 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 930/1251] eta: 0:02:43 lr: 0.000964 loss: 4.0402 (3.8933) grad_norm: 0.9981 (1.0166) time: 0.5021 [2021-03-25 09:51:18 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 940/1251] eta: 0:02:38 lr: 0.000964 loss: 3.9947 (3.8933) grad_norm: 1.0337 (1.0170) time: 0.5022 [2021-03-25 09:51:23 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 950/1251] eta: 0:02:33 lr: 0.000964 loss: 4.0570 (3.8930) grad_norm: 1.0337 (1.0174) time: 0.5055 [2021-03-25 09:51:28 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 960/1251] eta: 0:02:28 lr: 0.000964 loss: 4.0213 (3.8935) grad_norm: 1.0212 (1.0181) time: 0.5083 [2021-03-25 09:51:33 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 970/1251] eta: 0:02:23 lr: 0.000964 loss: 4.0764 (3.8952) grad_norm: 1.0390 (1.0184) time: 0.5158 [2021-03-25 09:51:38 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 980/1251] eta: 0:02:18 lr: 0.000964 loss: 4.0764 (3.8939) grad_norm: 1.0780 (1.0199) time: 0.5175 [2021-03-25 09:51:43 swin_small_patch4_window7_224] INFO: Epoch: [36] [ 990/1251] eta: 0:02:13 lr: 0.000964 loss: 4.0249 (3.8952) grad_norm: 1.1081 (1.0201) time: 0.5121 [2021-03-25 09:51:48 swin_small_patch4_window7_224] INFO: Epoch: [36] [1000/1251] eta: 0:02:08 lr: 0.000964 loss: 4.0249 (3.8951) grad_norm: 1.0193 (1.0203) time: 0.5028 [2021-03-25 09:51:53 swin_small_patch4_window7_224] INFO: Epoch: [36] [1010/1251] eta: 0:02:03 lr: 0.000964 loss: 3.7804 (3.8939) grad_norm: 0.9992 (1.0202) time: 0.4969 [2021-03-25 09:51:58 swin_small_patch4_window7_224] INFO: Epoch: [36] [1020/1251] eta: 0:01:57 lr: 0.000964 loss: 3.8634 (3.8935) grad_norm: 0.9938 (1.0202) time: 0.5046 [2021-03-25 09:52:03 swin_small_patch4_window7_224] INFO: Epoch: [36] [1030/1251] eta: 0:01:52 lr: 0.000964 loss: 3.8738 (3.8948) grad_norm: 0.9598 (1.0195) time: 0.5030 [2021-03-25 09:52:08 swin_small_patch4_window7_224] INFO: Epoch: [36] [1040/1251] eta: 0:01:47 lr: 0.000964 loss: 3.9440 (3.8939) grad_norm: 0.9505 (1.0191) time: 0.5004 [2021-03-25 09:52:13 swin_small_patch4_window7_224] INFO: Epoch: [36] [1050/1251] eta: 0:01:42 lr: 0.000964 loss: 3.9759 (3.8939) grad_norm: 1.0141 (1.0199) time: 0.5103 [2021-03-25 09:52:18 swin_small_patch4_window7_224] INFO: Epoch: [36] [1060/1251] eta: 0:01:37 lr: 0.000964 loss: 4.1375 (3.8941) grad_norm: 1.0653 (1.0202) time: 0.5089 [2021-03-25 09:52:23 swin_small_patch4_window7_224] INFO: Epoch: [36] [1070/1251] eta: 0:01:32 lr: 0.000964 loss: 4.0909 (3.8943) grad_norm: 1.0289 (1.0205) time: 0.5037 [2021-03-25 09:52:29 swin_small_patch4_window7_224] INFO: Epoch: [36] [1080/1251] eta: 0:01:27 lr: 0.000964 loss: 4.1521 (3.8952) grad_norm: 0.9860 (1.0197) time: 0.5093 [2021-03-25 09:52:34 swin_small_patch4_window7_224] INFO: Epoch: [36] [1090/1251] eta: 0:01:22 lr: 0.000964 loss: 4.2403 (3.8962) grad_norm: 0.9860 (1.0202) time: 0.5124 [2021-03-25 09:52:39 swin_small_patch4_window7_224] INFO: Epoch: [36] [1100/1251] eta: 0:01:17 lr: 0.000964 loss: 4.0024 (3.8958) grad_norm: 0.9725 (1.0194) time: 0.5086 [2021-03-25 09:52:44 swin_small_patch4_window7_224] INFO: Epoch: [36] [1110/1251] eta: 0:01:11 lr: 0.000964 loss: 4.0289 (3.8982) grad_norm: 0.9452 (1.0194) time: 0.5081 [2021-03-25 09:52:49 swin_small_patch4_window7_224] INFO: Epoch: [36] [1120/1251] eta: 0:01:06 lr: 0.000964 loss: 4.0985 (3.8979) grad_norm: 0.9677 (1.0191) time: 0.5026 [2021-03-25 09:52:54 swin_small_patch4_window7_224] INFO: Epoch: [36] [1130/1251] eta: 0:01:01 lr: 0.000963 loss: 4.0951 (3.8989) grad_norm: 0.9813 (1.0198) time: 0.4976 [2021-03-25 09:52:59 swin_small_patch4_window7_224] INFO: Epoch: [36] [1140/1251] eta: 0:00:56 lr: 0.000963 loss: 4.0951 (3.9005) grad_norm: 0.9563 (1.0194) time: 0.5006 [2021-03-25 09:53:04 swin_small_patch4_window7_224] INFO: Epoch: [36] [1150/1251] eta: 0:00:51 lr: 0.000963 loss: 4.0137 (3.8998) grad_norm: 0.9563 (1.0191) time: 0.5019 [2021-03-25 09:53:09 swin_small_patch4_window7_224] INFO: Epoch: [36] [1160/1251] eta: 0:00:46 lr: 0.000963 loss: 4.1654 (3.9031) grad_norm: 0.9850 (1.0192) time: 0.5015 [2021-03-25 09:53:14 swin_small_patch4_window7_224] INFO: Epoch: [36] [1170/1251] eta: 0:00:41 lr: 0.000963 loss: 4.1134 (3.9019) grad_norm: 1.0211 (1.0191) time: 0.5018 [2021-03-25 09:53:19 swin_small_patch4_window7_224] INFO: Epoch: [36] [1180/1251] eta: 0:00:36 lr: 0.000963 loss: 3.9533 (3.9028) grad_norm: 1.0302 (1.0194) time: 0.4983 [2021-03-25 09:53:24 swin_small_patch4_window7_224] INFO: Epoch: [36] [1190/1251] eta: 0:00:31 lr: 0.000963 loss: 4.2516 (3.9028) grad_norm: 0.9966 (1.0193) time: 0.4986 [2021-03-25 09:53:29 swin_small_patch4_window7_224] INFO: Epoch: [36] [1200/1251] eta: 0:00:25 lr: 0.000963 loss: 3.8926 (3.9019) grad_norm: 0.9966 (1.0193) time: 0.5051 [2021-03-25 09:53:34 swin_small_patch4_window7_224] INFO: Epoch: [36] [1210/1251] eta: 0:00:20 lr: 0.000963 loss: 3.7907 (3.8998) grad_norm: 1.0035 (1.0192) time: 0.5051 [2021-03-25 09:53:39 swin_small_patch4_window7_224] INFO: Epoch: [36] [1220/1251] eta: 0:00:15 lr: 0.000963 loss: 3.9069 (3.9007) grad_norm: 0.9508 (1.0187) time: 0.5044 [2021-03-25 09:53:44 swin_small_patch4_window7_224] INFO: Epoch: [36] [1230/1251] eta: 0:00:10 lr: 0.000963 loss: 3.9156 (3.9002) grad_norm: 0.9456 (1.0185) time: 0.5030 [2021-03-25 09:53:49 swin_small_patch4_window7_224] INFO: Epoch: [36] [1240/1251] eta: 0:00:05 lr: 0.000963 loss: 3.9754 (3.8996) grad_norm: 1.0228 (1.0186) time: 0.5045 [2021-03-25 09:53:54 swin_small_patch4_window7_224] INFO: Epoch: [36] [1250/1251] eta: 0:00:00 lr: 0.000963 loss: 3.9983 (3.9002) grad_norm: 1.0317 (1.0183) time: 0.4972 [2021-03-25 09:53:58 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:26 loss: 1.4877 (1.4877) acc1: 73.4375 (73.4375) acc5: 84.3750 (84.3750) [2021-03-25 09:54:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.3196 (1.3550) acc1: 71.8750 (70.3125) acc5: 89.0625 (88.7784) [2021-03-25 09:54:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.2722 (1.2974) acc1: 70.3125 (70.7589) acc5: 89.0625 (89.8810) [2021-03-25 09:54:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1678 (1.2782) acc1: 70.3125 (70.8165) acc5: 92.1875 (90.5746) [2021-03-25 09:54:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2733 (1.3161) acc1: 68.7500 (69.4360) acc5: 90.6250 (90.0152) [2021-03-25 09:54:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3811 (1.3123) acc1: 67.1875 (69.4400) acc5: 87.5000 (90.1440) [2021-03-25 09:54:09 swin_small_patch4_window7_224] INFO: * Acc@1 70.182 Acc@5 90.248 loss 1.290 [2021-03-25 09:54:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.2% [2021-03-25 09:54:09 swin_small_patch4_window7_224] INFO: Max accuracy: 70.18% [2021-03-25 09:54:13 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 0/1251] eta: 1:25:21 lr: 0.000963 loss: 3.9713 (3.9713) grad_norm: 0.8892 (0.8892) time: 4.0940 [2021-03-25 09:54:19 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 10/1251] eta: 0:17:46 lr: 0.000963 loss: 4.0310 (4.1039) grad_norm: 1.0657 (1.0734) time: 0.8595 [2021-03-25 09:54:24 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 20/1251] eta: 0:14:14 lr: 0.000963 loss: 3.6690 (3.8637) grad_norm: 1.0666 (1.1001) time: 0.5245 [2021-03-25 09:54:29 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 30/1251] eta: 0:12:59 lr: 0.000963 loss: 3.7872 (3.9602) grad_norm: 1.0121 (1.0798) time: 0.5165 [2021-03-25 09:54:34 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 40/1251] eta: 0:12:12 lr: 0.000963 loss: 3.9741 (3.9167) grad_norm: 0.9816 (1.0489) time: 0.5104 [2021-03-25 09:54:39 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 50/1251] eta: 0:11:41 lr: 0.000963 loss: 4.1010 (3.9778) grad_norm: 1.0384 (1.0527) time: 0.4993 [2021-03-25 09:54:44 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 60/1251] eta: 0:11:21 lr: 0.000963 loss: 4.1456 (3.9682) grad_norm: 1.0430 (1.0433) time: 0.5056 [2021-03-25 09:54:49 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 70/1251] eta: 0:11:04 lr: 0.000963 loss: 3.8807 (3.9277) grad_norm: 0.9611 (1.0293) time: 0.5104 [2021-03-25 09:54:54 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 80/1251] eta: 0:10:51 lr: 0.000963 loss: 4.1588 (3.9725) grad_norm: 0.9544 (1.0311) time: 0.5088 [2021-03-25 09:54:59 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 90/1251] eta: 0:10:39 lr: 0.000963 loss: 4.1588 (3.9645) grad_norm: 0.9608 (1.0275) time: 0.5080 [2021-03-25 09:55:04 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 100/1251] eta: 0:10:29 lr: 0.000963 loss: 4.0205 (3.9578) grad_norm: 0.9862 (1.0276) time: 0.5058 [2021-03-25 09:55:09 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 110/1251] eta: 0:10:19 lr: 0.000963 loss: 4.0205 (3.9542) grad_norm: 1.0066 (1.0271) time: 0.5042 [2021-03-25 09:55:14 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 120/1251] eta: 0:10:09 lr: 0.000963 loss: 4.1425 (3.9595) grad_norm: 0.9220 (1.0167) time: 0.5000 [2021-03-25 09:55:20 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 130/1251] eta: 0:10:01 lr: 0.000963 loss: 4.1425 (3.9664) grad_norm: 0.9220 (1.0195) time: 0.5016 [2021-03-25 09:55:25 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 140/1251] eta: 0:09:53 lr: 0.000963 loss: 4.0137 (3.9580) grad_norm: 0.9903 (1.0179) time: 0.5071 [2021-03-25 09:55:30 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 150/1251] eta: 0:09:46 lr: 0.000963 loss: 3.7940 (3.9356) grad_norm: 0.9744 (1.0148) time: 0.5076 [2021-03-25 09:55:35 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 160/1251] eta: 0:09:39 lr: 0.000963 loss: 3.7018 (3.9256) grad_norm: 0.9640 (1.0124) time: 0.5072 [2021-03-25 09:55:40 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 170/1251] eta: 0:09:32 lr: 0.000963 loss: 3.9337 (3.9349) grad_norm: 0.9762 (1.0102) time: 0.5096 [2021-03-25 09:55:45 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 180/1251] eta: 0:09:26 lr: 0.000963 loss: 3.8505 (3.9277) grad_norm: 0.9722 (1.0067) time: 0.5112 [2021-03-25 09:55:50 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 190/1251] eta: 0:09:19 lr: 0.000963 loss: 3.8505 (3.9219) grad_norm: 1.0028 (1.0159) time: 0.5070 [2021-03-25 09:55:55 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 200/1251] eta: 0:09:13 lr: 0.000963 loss: 3.9396 (3.9119) grad_norm: 1.1496 (1.0200) time: 0.5123 [2021-03-25 09:56:00 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 210/1251] eta: 0:09:08 lr: 0.000963 loss: 3.8808 (3.9038) grad_norm: 1.0187 (1.0179) time: 0.5175 [2021-03-25 09:56:05 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 220/1251] eta: 0:09:02 lr: 0.000963 loss: 3.6217 (3.9038) grad_norm: 0.9855 (1.0181) time: 0.5138 [2021-03-25 09:56:11 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 230/1251] eta: 0:08:56 lr: 0.000963 loss: 4.0771 (3.8992) grad_norm: 1.0599 (1.0205) time: 0.5106 [2021-03-25 09:56:16 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 240/1251] eta: 0:08:50 lr: 0.000963 loss: 4.0593 (3.8982) grad_norm: 1.0639 (1.0247) time: 0.5068 [2021-03-25 09:56:21 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 250/1251] eta: 0:08:43 lr: 0.000963 loss: 4.0593 (3.8961) grad_norm: 1.0976 (1.0280) time: 0.5039 [2021-03-25 09:56:26 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 260/1251] eta: 0:08:37 lr: 0.000963 loss: 4.0593 (3.8935) grad_norm: 0.9860 (1.0258) time: 0.5011 [2021-03-25 09:56:31 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 270/1251] eta: 0:08:32 lr: 0.000963 loss: 3.8786 (3.8915) grad_norm: 0.9361 (1.0237) time: 0.5035 [2021-03-25 09:56:36 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 280/1251] eta: 0:08:26 lr: 0.000963 loss: 3.9840 (3.8954) grad_norm: 0.9361 (1.0244) time: 0.5040 [2021-03-25 09:56:41 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 290/1251] eta: 0:08:20 lr: 0.000963 loss: 4.2957 (3.9021) grad_norm: 1.0112 (1.0263) time: 0.5030 [2021-03-25 09:56:46 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 300/1251] eta: 0:08:14 lr: 0.000963 loss: 4.0618 (3.8972) grad_norm: 1.0112 (1.0264) time: 0.5064 [2021-03-25 09:56:51 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 310/1251] eta: 0:08:09 lr: 0.000963 loss: 3.9664 (3.9024) grad_norm: 0.9845 (1.0260) time: 0.5054 [2021-03-25 09:56:56 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 320/1251] eta: 0:08:03 lr: 0.000963 loss: 4.1873 (3.9027) grad_norm: 0.9845 (1.0248) time: 0.5012 [2021-03-25 09:57:01 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 330/1251] eta: 0:07:57 lr: 0.000963 loss: 4.0722 (3.8957) grad_norm: 0.9482 (1.0232) time: 0.5055 [2021-03-25 09:57:06 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 340/1251] eta: 0:07:52 lr: 0.000963 loss: 3.7354 (3.8929) grad_norm: 0.9871 (1.0260) time: 0.5087 [2021-03-25 09:57:11 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 350/1251] eta: 0:07:47 lr: 0.000963 loss: 3.8184 (3.8979) grad_norm: 0.9807 (1.0242) time: 0.5113 [2021-03-25 09:57:16 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 360/1251] eta: 0:07:41 lr: 0.000963 loss: 4.0705 (3.8992) grad_norm: 0.9796 (1.0253) time: 0.5085 [2021-03-25 09:57:21 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 370/1251] eta: 0:07:35 lr: 0.000963 loss: 4.0346 (3.8969) grad_norm: 1.0207 (1.0253) time: 0.4990 [2021-03-25 09:57:26 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 380/1251] eta: 0:07:30 lr: 0.000963 loss: 3.9417 (3.8911) grad_norm: 0.9789 (1.0248) time: 0.4967 [2021-03-25 09:57:31 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 390/1251] eta: 0:07:24 lr: 0.000963 loss: 3.9417 (3.8935) grad_norm: 0.9895 (1.0246) time: 0.5013 [2021-03-25 09:57:36 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 400/1251] eta: 0:07:19 lr: 0.000963 loss: 4.0002 (3.8897) grad_norm: 1.0157 (1.0270) time: 0.5035 [2021-03-25 09:57:41 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 410/1251] eta: 0:07:13 lr: 0.000963 loss: 3.8991 (3.8875) grad_norm: 1.0439 (1.0265) time: 0.5061 [2021-03-25 09:57:46 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 420/1251] eta: 0:07:08 lr: 0.000963 loss: 3.5333 (3.8777) grad_norm: 1.0229 (1.0270) time: 0.5080 [2021-03-25 09:57:52 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 430/1251] eta: 0:07:03 lr: 0.000963 loss: 3.5904 (3.8796) grad_norm: 1.0328 (1.0280) time: 0.5066 [2021-03-25 09:57:57 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 440/1251] eta: 0:06:57 lr: 0.000963 loss: 4.0028 (3.8794) grad_norm: 1.0768 (1.0302) time: 0.5058 [2021-03-25 09:58:02 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 450/1251] eta: 0:06:52 lr: 0.000963 loss: 3.9386 (3.8757) grad_norm: 1.0352 (1.0301) time: 0.5062 [2021-03-25 09:58:07 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 460/1251] eta: 0:06:47 lr: 0.000963 loss: 3.5250 (3.8659) grad_norm: 0.9943 (1.0289) time: 0.5077 [2021-03-25 09:58:12 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 470/1251] eta: 0:06:42 lr: 0.000963 loss: 3.3777 (3.8613) grad_norm: 0.9759 (1.0285) time: 0.5063 [2021-03-25 09:58:17 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 480/1251] eta: 0:06:36 lr: 0.000963 loss: 4.0732 (3.8690) grad_norm: 1.0008 (1.0290) time: 0.5099 [2021-03-25 09:58:22 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 490/1251] eta: 0:06:31 lr: 0.000963 loss: 4.2881 (3.8750) grad_norm: 0.9939 (1.0279) time: 0.5106 [2021-03-25 09:58:27 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 500/1251] eta: 0:06:26 lr: 0.000963 loss: 4.1932 (3.8782) grad_norm: 0.9882 (1.0278) time: 0.5037 [2021-03-25 09:58:32 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 510/1251] eta: 0:06:20 lr: 0.000963 loss: 4.1616 (3.8814) grad_norm: 1.0450 (1.0279) time: 0.4979 [2021-03-25 09:58:37 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 520/1251] eta: 0:06:15 lr: 0.000962 loss: 3.9106 (3.8776) grad_norm: 1.0611 (1.0284) time: 0.5000 [2021-03-25 09:58:42 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 530/1251] eta: 0:06:10 lr: 0.000962 loss: 3.9106 (3.8803) grad_norm: 1.0112 (1.0280) time: 0.5043 [2021-03-25 09:58:47 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 540/1251] eta: 0:06:05 lr: 0.000962 loss: 4.2299 (3.8842) grad_norm: 1.0016 (1.0282) time: 0.5096 [2021-03-25 09:58:52 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 550/1251] eta: 0:06:00 lr: 0.000962 loss: 4.1689 (3.8864) grad_norm: 1.0112 (1.0274) time: 0.5174 [2021-03-25 09:58:57 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 560/1251] eta: 0:05:54 lr: 0.000962 loss: 3.9616 (3.8848) grad_norm: 1.0326 (1.0281) time: 0.5110 [2021-03-25 09:59:03 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 570/1251] eta: 0:05:49 lr: 0.000962 loss: 3.9616 (3.8836) grad_norm: 1.0757 (1.0284) time: 0.5081 [2021-03-25 09:59:08 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 580/1251] eta: 0:05:44 lr: 0.000962 loss: 3.9763 (3.8821) grad_norm: 0.9540 (1.0271) time: 0.5110 [2021-03-25 09:59:13 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 590/1251] eta: 0:05:39 lr: 0.000962 loss: 3.7870 (3.8782) grad_norm: 0.9420 (1.0267) time: 0.5053 [2021-03-25 09:59:18 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 600/1251] eta: 0:05:34 lr: 0.000962 loss: 4.1325 (3.8815) grad_norm: 0.9420 (1.0252) time: 0.5038 [2021-03-25 09:59:23 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 610/1251] eta: 0:05:28 lr: 0.000962 loss: 4.1403 (3.8798) grad_norm: 0.9364 (1.0247) time: 0.5095 [2021-03-25 09:59:28 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 620/1251] eta: 0:05:23 lr: 0.000962 loss: 3.7312 (3.8789) grad_norm: 0.9385 (1.0237) time: 0.5097 [2021-03-25 09:59:33 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 630/1251] eta: 0:05:18 lr: 0.000962 loss: 3.7245 (3.8737) grad_norm: 0.9429 (1.0238) time: 0.5072 [2021-03-25 09:59:38 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 640/1251] eta: 0:05:13 lr: 0.000962 loss: 4.0942 (3.8778) grad_norm: 0.9429 (1.0229) time: 0.5096 [2021-03-25 09:59:43 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 650/1251] eta: 0:05:08 lr: 0.000962 loss: 4.1970 (3.8815) grad_norm: 0.9680 (1.0230) time: 0.5058 [2021-03-25 09:59:48 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 660/1251] eta: 0:05:03 lr: 0.000962 loss: 4.1714 (3.8855) grad_norm: 1.0069 (1.0238) time: 0.5074 [2021-03-25 09:59:53 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 670/1251] eta: 0:04:57 lr: 0.000962 loss: 3.9791 (3.8860) grad_norm: 0.9706 (1.0224) time: 0.5171 [2021-03-25 09:59:58 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 680/1251] eta: 0:04:52 lr: 0.000962 loss: 3.9736 (3.8891) grad_norm: 0.9424 (1.0217) time: 0.5115 [2021-03-25 10:00:04 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 690/1251] eta: 0:04:47 lr: 0.000962 loss: 3.8943 (3.8873) grad_norm: 0.9864 (1.0223) time: 0.5074 [2021-03-25 10:00:09 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 700/1251] eta: 0:04:42 lr: 0.000962 loss: 3.7307 (3.8847) grad_norm: 1.0263 (1.0222) time: 0.5092 [2021-03-25 10:00:14 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 710/1251] eta: 0:04:37 lr: 0.000962 loss: 3.8477 (3.8870) grad_norm: 1.0026 (1.0226) time: 0.5007 [2021-03-25 10:00:19 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 720/1251] eta: 0:04:32 lr: 0.000962 loss: 4.1436 (3.8914) grad_norm: 1.0230 (1.0231) time: 0.5026 [2021-03-25 10:00:24 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 730/1251] eta: 0:04:27 lr: 0.000962 loss: 4.1554 (3.8923) grad_norm: 1.0230 (1.0237) time: 0.5211 [2021-03-25 10:00:29 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 740/1251] eta: 0:04:21 lr: 0.000962 loss: 4.2700 (3.8948) grad_norm: 0.9701 (1.0231) time: 0.5266 [2021-03-25 10:00:34 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 750/1251] eta: 0:04:16 lr: 0.000962 loss: 4.0152 (3.8958) grad_norm: 0.9565 (1.0220) time: 0.5179 [2021-03-25 10:00:40 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 760/1251] eta: 0:04:11 lr: 0.000962 loss: 3.9208 (3.8964) grad_norm: 0.9565 (1.0219) time: 0.5166 [2021-03-25 10:00:45 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 770/1251] eta: 0:04:06 lr: 0.000962 loss: 3.6508 (3.8930) grad_norm: 0.9832 (1.0213) time: 0.5169 [2021-03-25 10:00:50 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 780/1251] eta: 0:04:01 lr: 0.000962 loss: 3.4989 (3.8875) grad_norm: 0.9916 (1.0212) time: 0.5070 [2021-03-25 10:00:55 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 790/1251] eta: 0:03:56 lr: 0.000962 loss: 3.7308 (3.8865) grad_norm: 1.0173 (1.0213) time: 0.5080 [2021-03-25 10:01:00 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 800/1251] eta: 0:03:51 lr: 0.000962 loss: 4.0225 (3.8895) grad_norm: 0.9756 (1.0204) time: 0.5131 [2021-03-25 10:01:05 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 810/1251] eta: 0:03:46 lr: 0.000962 loss: 4.0225 (3.8879) grad_norm: 0.9196 (1.0195) time: 0.5060 [2021-03-25 10:01:10 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 820/1251] eta: 0:03:40 lr: 0.000962 loss: 3.8667 (3.8891) grad_norm: 0.9311 (1.0182) time: 0.5017 [2021-03-25 10:01:15 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 830/1251] eta: 0:03:35 lr: 0.000962 loss: 3.9710 (3.8884) grad_norm: 0.9572 (1.0185) time: 0.5035 [2021-03-25 10:01:20 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 840/1251] eta: 0:03:30 lr: 0.000962 loss: 3.5581 (3.8831) grad_norm: 1.0526 (1.0190) time: 0.5059 [2021-03-25 10:01:25 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 850/1251] eta: 0:03:25 lr: 0.000962 loss: 3.8072 (3.8837) grad_norm: 1.0453 (1.0188) time: 0.5062 [2021-03-25 10:01:30 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 860/1251] eta: 0:03:20 lr: 0.000962 loss: 4.0075 (3.8832) grad_norm: 0.9945 (inf) time: 0.5032 [2021-03-25 10:01:35 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 870/1251] eta: 0:03:15 lr: 0.000962 loss: 3.9074 (3.8830) grad_norm: 0.9578 (inf) time: 0.4989 [2021-03-25 10:01:40 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 880/1251] eta: 0:03:09 lr: 0.000962 loss: 3.9162 (3.8834) grad_norm: 0.9525 (inf) time: 0.5008 [2021-03-25 10:01:45 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 890/1251] eta: 0:03:04 lr: 0.000962 loss: 3.9718 (3.8835) grad_norm: 0.9424 (inf) time: 0.5064 [2021-03-25 10:01:50 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 900/1251] eta: 0:02:59 lr: 0.000962 loss: 3.9541 (3.8846) grad_norm: 0.9338 (inf) time: 0.5105 [2021-03-25 10:01:55 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 910/1251] eta: 0:02:54 lr: 0.000962 loss: 3.9019 (3.8807) grad_norm: 1.0099 (inf) time: 0.5056 [2021-03-25 10:02:01 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 920/1251] eta: 0:02:49 lr: 0.000962 loss: 3.5731 (3.8794) grad_norm: 1.0204 (inf) time: 0.5093 [2021-03-25 10:02:06 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 930/1251] eta: 0:02:44 lr: 0.000962 loss: 3.9980 (3.8803) grad_norm: 0.9827 (inf) time: 0.5165 [2021-03-25 10:02:11 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 940/1251] eta: 0:02:39 lr: 0.000962 loss: 4.0723 (3.8837) grad_norm: 0.9827 (inf) time: 0.5122 [2021-03-25 10:02:16 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 950/1251] eta: 0:02:34 lr: 0.000962 loss: 4.0374 (3.8836) grad_norm: 0.9829 (inf) time: 0.5189 [2021-03-25 10:02:21 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 960/1251] eta: 0:02:28 lr: 0.000962 loss: 3.8006 (3.8818) grad_norm: 0.9883 (inf) time: 0.5150 [2021-03-25 10:02:26 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 970/1251] eta: 0:02:23 lr: 0.000962 loss: 3.9445 (3.8827) grad_norm: 0.9952 (inf) time: 0.5026 [2021-03-25 10:02:31 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 980/1251] eta: 0:02:18 lr: 0.000962 loss: 4.1610 (3.8840) grad_norm: 1.0108 (inf) time: 0.5063 [2021-03-25 10:02:36 swin_small_patch4_window7_224] INFO: Epoch: [37] [ 990/1251] eta: 0:02:13 lr: 0.000962 loss: 4.0408 (3.8848) grad_norm: 1.0323 (inf) time: 0.5080 [2021-03-25 10:02:41 swin_small_patch4_window7_224] INFO: Epoch: [37] [1000/1251] eta: 0:02:08 lr: 0.000962 loss: 3.9978 (3.8858) grad_norm: 1.0333 (inf) time: 0.5043 [2021-03-25 10:02:46 swin_small_patch4_window7_224] INFO: Epoch: [37] [1010/1251] eta: 0:02:03 lr: 0.000962 loss: 3.7691 (3.8836) grad_norm: 1.0248 (inf) time: 0.5000 [2021-03-25 10:02:51 swin_small_patch4_window7_224] INFO: Epoch: [37] [1020/1251] eta: 0:01:58 lr: 0.000962 loss: 3.8440 (3.8844) grad_norm: 1.0490 (inf) time: 0.5006 [2021-03-25 10:02:56 swin_small_patch4_window7_224] INFO: Epoch: [37] [1030/1251] eta: 0:01:52 lr: 0.000962 loss: 3.9919 (3.8848) grad_norm: 1.0490 (inf) time: 0.5028 [2021-03-25 10:03:01 swin_small_patch4_window7_224] INFO: Epoch: [37] [1040/1251] eta: 0:01:47 lr: 0.000962 loss: 4.0334 (3.8861) grad_norm: 1.0791 (inf) time: 0.5012 [2021-03-25 10:03:07 swin_small_patch4_window7_224] INFO: Epoch: [37] [1050/1251] eta: 0:01:42 lr: 0.000962 loss: 4.0619 (3.8857) grad_norm: 1.0419 (inf) time: 0.5032 [2021-03-25 10:03:12 swin_small_patch4_window7_224] INFO: Epoch: [37] [1060/1251] eta: 0:01:37 lr: 0.000962 loss: 4.1513 (3.8872) grad_norm: 1.0086 (inf) time: 0.5060 [2021-03-25 10:03:17 swin_small_patch4_window7_224] INFO: Epoch: [37] [1070/1251] eta: 0:01:32 lr: 0.000962 loss: 4.1957 (3.8900) grad_norm: 1.0086 (inf) time: 0.5079 [2021-03-25 10:03:22 swin_small_patch4_window7_224] INFO: Epoch: [37] [1080/1251] eta: 0:01:27 lr: 0.000962 loss: 4.1036 (3.8910) grad_norm: 0.9620 (inf) time: 0.5105 [2021-03-25 10:03:27 swin_small_patch4_window7_224] INFO: Epoch: [37] [1090/1251] eta: 0:01:22 lr: 0.000962 loss: 3.9079 (3.8896) grad_norm: 0.9989 (inf) time: 0.5114 [2021-03-25 10:03:32 swin_small_patch4_window7_224] INFO: Epoch: [37] [1100/1251] eta: 0:01:17 lr: 0.000962 loss: 3.6530 (3.8892) grad_norm: 0.9656 (inf) time: 0.5095 [2021-03-25 10:03:37 swin_small_patch4_window7_224] INFO: Epoch: [37] [1110/1251] eta: 0:01:12 lr: 0.000962 loss: 3.9795 (3.8903) grad_norm: 0.9645 (inf) time: 0.5015 [2021-03-25 10:03:42 swin_small_patch4_window7_224] INFO: Epoch: [37] [1120/1251] eta: 0:01:06 lr: 0.000962 loss: 4.0009 (3.8900) grad_norm: 1.0061 (inf) time: 0.5008 [2021-03-25 10:03:47 swin_small_patch4_window7_224] INFO: Epoch: [37] [1130/1251] eta: 0:01:01 lr: 0.000962 loss: 4.0009 (3.8929) grad_norm: 0.9918 (inf) time: 0.5032 [2021-03-25 10:03:52 swin_small_patch4_window7_224] INFO: Epoch: [37] [1140/1251] eta: 0:00:56 lr: 0.000962 loss: 4.0119 (3.8923) grad_norm: 0.9918 (inf) time: 0.5086 [2021-03-25 10:03:57 swin_small_patch4_window7_224] INFO: Epoch: [37] [1150/1251] eta: 0:00:51 lr: 0.000961 loss: 4.0119 (3.8938) grad_norm: 1.0265 (inf) time: 0.5073 [2021-03-25 10:04:02 swin_small_patch4_window7_224] INFO: Epoch: [37] [1160/1251] eta: 0:00:46 lr: 0.000961 loss: 4.1255 (3.8941) grad_norm: 1.0617 (inf) time: 0.4986 [2021-03-25 10:04:07 swin_small_patch4_window7_224] INFO: Epoch: [37] [1170/1251] eta: 0:00:41 lr: 0.000961 loss: 3.7321 (3.8919) grad_norm: 1.0144 (inf) time: 0.4988 [2021-03-25 10:04:12 swin_small_patch4_window7_224] INFO: Epoch: [37] [1180/1251] eta: 0:00:36 lr: 0.000961 loss: 4.0275 (3.8931) grad_norm: 1.0065 (inf) time: 0.5030 [2021-03-25 10:04:17 swin_small_patch4_window7_224] INFO: Epoch: [37] [1190/1251] eta: 0:00:31 lr: 0.000961 loss: 4.2910 (3.8965) grad_norm: 0.9534 (inf) time: 0.5020 [2021-03-25 10:04:22 swin_small_patch4_window7_224] INFO: Epoch: [37] [1200/1251] eta: 0:00:26 lr: 0.000961 loss: 4.3034 (3.8962) grad_norm: 0.9442 (inf) time: 0.5013 [2021-03-25 10:04:27 swin_small_patch4_window7_224] INFO: Epoch: [37] [1210/1251] eta: 0:00:20 lr: 0.000961 loss: 3.7923 (3.8958) grad_norm: 0.9670 (inf) time: 0.5018 [2021-03-25 10:04:32 swin_small_patch4_window7_224] INFO: Epoch: [37] [1220/1251] eta: 0:00:15 lr: 0.000961 loss: 4.0097 (3.8953) grad_norm: 0.9497 (inf) time: 0.5001 [2021-03-25 10:04:37 swin_small_patch4_window7_224] INFO: Epoch: [37] [1230/1251] eta: 0:00:10 lr: 0.000961 loss: 3.9133 (3.8947) grad_norm: 0.9497 (inf) time: 0.5032 [2021-03-25 10:04:42 swin_small_patch4_window7_224] INFO: Epoch: [37] [1240/1251] eta: 0:00:05 lr: 0.000961 loss: 3.9991 (3.8962) grad_norm: 0.9604 (inf) time: 0.5058 [2021-03-25 10:04:47 swin_small_patch4_window7_224] INFO: Epoch: [37] [1250/1251] eta: 0:00:00 lr: 0.000961 loss: 4.0570 (3.8968) grad_norm: 0.9410 (inf) time: 0.5033 [2021-03-25 10:04:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:08 loss: 1.1190 (1.1190) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-25 10:04:54 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.2897 (1.2928) acc1: 68.7500 (69.8864) acc5: 92.1875 (90.1989) [2021-03-25 10:04:57 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.2232 (1.2506) acc1: 71.8750 (71.3542) acc5: 92.1875 (90.4018) [2021-03-25 10:04:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2934 (1.2887) acc1: 71.8750 (71.2198) acc5: 90.6250 (90.3226) [2021-03-25 10:05:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3666 (1.2903) acc1: 67.1875 (71.0366) acc5: 89.0625 (90.2820) [2021-03-25 10:05:01 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3910 (1.3067) acc1: 67.1875 (70.5280) acc5: 89.0625 (90.0800) [2021-03-25 10:05:03 swin_small_patch4_window7_224] INFO: * Acc@1 70.684 Acc@5 90.528 loss 1.274 [2021-03-25 10:05:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.7% [2021-03-25 10:05:03 swin_small_patch4_window7_224] INFO: Max accuracy: 70.68% [2021-03-25 10:05:07 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 0/1251] eta: 1:23:48 lr: 0.000961 loss: 4.1968 (4.1968) grad_norm: 1.0376 (1.0376) time: 4.0198 [2021-03-25 10:05:13 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 10/1251] eta: 0:17:48 lr: 0.000961 loss: 3.8133 (3.7663) grad_norm: 0.9852 (0.9856) time: 0.8613 [2021-03-25 10:05:18 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 20/1251] eta: 0:14:15 lr: 0.000961 loss: 3.9017 (3.9003) grad_norm: 0.9349 (0.9891) time: 0.5290 [2021-03-25 10:05:23 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 30/1251] eta: 0:12:52 lr: 0.000961 loss: 4.0599 (3.8864) grad_norm: 0.9622 (1.0203) time: 0.5069 [2021-03-25 10:05:28 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 40/1251] eta: 0:12:09 lr: 0.000961 loss: 4.0080 (3.8467) grad_norm: 1.0190 (1.0246) time: 0.5043 [2021-03-25 10:05:33 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 50/1251] eta: 0:11:44 lr: 0.000961 loss: 3.8515 (3.8147) grad_norm: 1.0190 (1.0203) time: 0.5160 [2021-03-25 10:05:38 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 60/1251] eta: 0:11:23 lr: 0.000961 loss: 3.8920 (3.8535) grad_norm: 1.0021 (1.0194) time: 0.5158 [2021-03-25 10:05:43 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 70/1251] eta: 0:11:06 lr: 0.000961 loss: 3.8920 (3.8765) grad_norm: 0.9624 (1.0134) time: 0.5062 [2021-03-25 10:05:48 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 80/1251] eta: 0:10:52 lr: 0.000961 loss: 3.7663 (3.8493) grad_norm: 0.9758 (1.0148) time: 0.5059 [2021-03-25 10:05:54 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 90/1251] eta: 0:10:39 lr: 0.000961 loss: 3.7019 (3.8461) grad_norm: 1.0005 (1.0121) time: 0.5035 [2021-03-25 10:05:59 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 100/1251] eta: 0:10:29 lr: 0.000961 loss: 3.8156 (3.8460) grad_norm: 0.9978 (1.0138) time: 0.5071 [2021-03-25 10:06:04 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 110/1251] eta: 0:10:22 lr: 0.000961 loss: 3.9107 (3.8669) grad_norm: 1.0090 (1.0140) time: 0.5198 [2021-03-25 10:06:09 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 120/1251] eta: 0:10:12 lr: 0.000961 loss: 4.0178 (3.8609) grad_norm: 0.9802 (1.0117) time: 0.5146 [2021-03-25 10:06:14 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 130/1251] eta: 0:10:04 lr: 0.000961 loss: 3.9889 (3.8740) grad_norm: 0.9802 (1.0121) time: 0.5052 [2021-03-25 10:06:19 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 140/1251] eta: 0:09:56 lr: 0.000961 loss: 4.0758 (3.8720) grad_norm: 1.0093 (1.0150) time: 0.5100 [2021-03-25 10:06:24 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 150/1251] eta: 0:09:49 lr: 0.000961 loss: 4.0006 (3.8745) grad_norm: 0.9603 (1.0122) time: 0.5109 [2021-03-25 10:06:29 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 160/1251] eta: 0:09:42 lr: 0.000961 loss: 3.8783 (3.8751) grad_norm: 0.9193 (1.0131) time: 0.5098 [2021-03-25 10:06:34 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 170/1251] eta: 0:09:35 lr: 0.000961 loss: 4.0169 (3.8818) grad_norm: 0.9935 (1.0146) time: 0.5074 [2021-03-25 10:06:39 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 180/1251] eta: 0:09:28 lr: 0.000961 loss: 4.1234 (3.8931) grad_norm: 1.0001 (1.0148) time: 0.5031 [2021-03-25 10:06:45 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 190/1251] eta: 0:09:21 lr: 0.000961 loss: 4.1140 (3.8902) grad_norm: 1.0788 (1.0211) time: 0.5066 [2021-03-25 10:06:50 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 200/1251] eta: 0:09:15 lr: 0.000961 loss: 3.9236 (3.8885) grad_norm: 1.1082 (1.0255) time: 0.5142 [2021-03-25 10:06:55 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 210/1251] eta: 0:09:09 lr: 0.000961 loss: 3.9236 (3.8955) grad_norm: 1.0609 (1.0263) time: 0.5130 [2021-03-25 10:07:00 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 220/1251] eta: 0:09:03 lr: 0.000961 loss: 3.9779 (3.9002) grad_norm: 1.0080 (1.0262) time: 0.5068 [2021-03-25 10:07:05 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 230/1251] eta: 0:08:56 lr: 0.000961 loss: 3.9399 (3.8951) grad_norm: 0.9985 (1.0245) time: 0.5014 [2021-03-25 10:07:10 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 240/1251] eta: 0:08:50 lr: 0.000961 loss: 3.9939 (3.9045) grad_norm: 0.9911 (1.0230) time: 0.5030 [2021-03-25 10:07:15 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 250/1251] eta: 0:08:44 lr: 0.000961 loss: 4.0359 (3.9126) grad_norm: 1.0149 (1.0235) time: 0.5086 [2021-03-25 10:07:20 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 260/1251] eta: 0:08:38 lr: 0.000961 loss: 4.1980 (3.9269) grad_norm: 1.0473 (1.0251) time: 0.5048 [2021-03-25 10:07:25 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 270/1251] eta: 0:08:32 lr: 0.000961 loss: 4.1673 (3.9230) grad_norm: 1.0006 (1.0248) time: 0.5052 [2021-03-25 10:07:30 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 280/1251] eta: 0:08:26 lr: 0.000961 loss: 3.7554 (3.9205) grad_norm: 0.9503 (1.0216) time: 0.5026 [2021-03-25 10:07:35 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 290/1251] eta: 0:08:20 lr: 0.000961 loss: 3.9419 (3.9242) grad_norm: 0.9356 (1.0195) time: 0.4988 [2021-03-25 10:07:40 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 300/1251] eta: 0:08:15 lr: 0.000961 loss: 3.8931 (3.9173) grad_norm: 0.8957 (1.0155) time: 0.5138 [2021-03-25 10:07:45 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 310/1251] eta: 0:08:10 lr: 0.000961 loss: 3.9296 (3.9163) grad_norm: 0.9312 (1.0142) time: 0.5201 [2021-03-25 10:07:50 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 320/1251] eta: 0:08:04 lr: 0.000961 loss: 3.9581 (3.9131) grad_norm: 1.0011 (1.0157) time: 0.5083 [2021-03-25 10:07:56 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 330/1251] eta: 0:07:59 lr: 0.000961 loss: 4.1115 (3.9207) grad_norm: 1.0258 (1.0157) time: 0.5078 [2021-03-25 10:08:01 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 340/1251] eta: 0:07:53 lr: 0.000961 loss: 4.2906 (3.9241) grad_norm: 0.9824 (1.0179) time: 0.5068 [2021-03-25 10:08:06 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 350/1251] eta: 0:07:47 lr: 0.000961 loss: 4.0385 (3.9191) grad_norm: 0.9850 (1.0178) time: 0.5002 [2021-03-25 10:08:11 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 360/1251] eta: 0:07:42 lr: 0.000961 loss: 3.9904 (3.9219) grad_norm: 0.9455 (1.0170) time: 0.5045 [2021-03-25 10:08:16 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 370/1251] eta: 0:07:36 lr: 0.000961 loss: 3.9904 (3.9241) grad_norm: 0.9784 (1.0172) time: 0.5078 [2021-03-25 10:08:21 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 380/1251] eta: 0:07:31 lr: 0.000961 loss: 4.0167 (3.9228) grad_norm: 0.9865 (1.0160) time: 0.5073 [2021-03-25 10:08:26 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 390/1251] eta: 0:07:25 lr: 0.000961 loss: 3.8599 (3.9181) grad_norm: 0.9565 (1.0138) time: 0.5043 [2021-03-25 10:08:31 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 400/1251] eta: 0:07:20 lr: 0.000961 loss: 3.9329 (3.9186) grad_norm: 0.9883 (1.0164) time: 0.5049 [2021-03-25 10:08:36 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 410/1251] eta: 0:07:14 lr: 0.000961 loss: 3.9674 (3.9167) grad_norm: 1.0327 (1.0169) time: 0.5050 [2021-03-25 10:08:41 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 420/1251] eta: 0:07:09 lr: 0.000961 loss: 3.8540 (3.9157) grad_norm: 0.9931 (1.0169) time: 0.5047 [2021-03-25 10:08:46 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 430/1251] eta: 0:07:04 lr: 0.000961 loss: 3.8509 (3.9119) grad_norm: 0.9569 (1.0160) time: 0.5080 [2021-03-25 10:08:51 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 440/1251] eta: 0:06:58 lr: 0.000961 loss: 3.5877 (3.9047) grad_norm: 0.9530 (1.0148) time: 0.5064 [2021-03-25 10:08:56 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 450/1251] eta: 0:06:53 lr: 0.000961 loss: 3.8396 (3.9075) grad_norm: 0.9311 (1.0146) time: 0.5088 [2021-03-25 10:09:01 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 460/1251] eta: 0:06:48 lr: 0.000961 loss: 4.0634 (3.9103) grad_norm: 0.9252 (1.0137) time: 0.5083 [2021-03-25 10:09:06 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 470/1251] eta: 0:06:42 lr: 0.000961 loss: 4.1845 (3.9142) grad_norm: 0.9299 (1.0118) time: 0.5044 [2021-03-25 10:09:12 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 480/1251] eta: 0:06:37 lr: 0.000961 loss: 4.2001 (3.9196) grad_norm: 0.9640 (1.0115) time: 0.5076 [2021-03-25 10:09:17 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 490/1251] eta: 0:06:32 lr: 0.000961 loss: 3.8657 (3.9127) grad_norm: 0.9390 (1.0109) time: 0.5063 [2021-03-25 10:09:22 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 500/1251] eta: 0:06:27 lr: 0.000961 loss: 3.8816 (3.9160) grad_norm: 1.0011 (1.0133) time: 0.5049 [2021-03-25 10:09:27 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 510/1251] eta: 0:06:21 lr: 0.000960 loss: 3.9355 (3.9164) grad_norm: 1.0990 (1.0146) time: 0.5102 [2021-03-25 10:09:32 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 520/1251] eta: 0:06:16 lr: 0.000960 loss: 3.9355 (3.9139) grad_norm: 1.0444 (1.0151) time: 0.5066 [2021-03-25 10:09:37 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 530/1251] eta: 0:06:11 lr: 0.000960 loss: 4.0266 (3.9134) grad_norm: 1.0182 (1.0162) time: 0.5013 [2021-03-25 10:09:42 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 540/1251] eta: 0:06:05 lr: 0.000960 loss: 3.9714 (3.9098) grad_norm: 1.0182 (1.0163) time: 0.5048 [2021-03-25 10:09:47 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 550/1251] eta: 0:06:01 lr: 0.000960 loss: 3.6592 (3.9080) grad_norm: 0.9689 (1.0152) time: 0.5208 [2021-03-25 10:09:52 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 560/1251] eta: 0:05:55 lr: 0.000960 loss: 3.6006 (3.9013) grad_norm: 0.9277 (1.0141) time: 0.5195 [2021-03-25 10:09:57 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 570/1251] eta: 0:05:50 lr: 0.000960 loss: 3.7658 (3.9007) grad_norm: 0.9334 (1.0138) time: 0.5109 [2021-03-25 10:10:03 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 580/1251] eta: 0:05:45 lr: 0.000960 loss: 3.7069 (3.8985) grad_norm: 0.9896 (1.0142) time: 0.5132 [2021-03-25 10:10:08 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 590/1251] eta: 0:05:40 lr: 0.000960 loss: 3.7732 (3.9012) grad_norm: 0.9531 (1.0127) time: 0.5108 [2021-03-25 10:10:13 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 600/1251] eta: 0:05:35 lr: 0.000960 loss: 3.9090 (3.8991) grad_norm: 0.9846 (1.0126) time: 0.5171 [2021-03-25 10:10:18 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 610/1251] eta: 0:05:29 lr: 0.000960 loss: 3.8314 (3.8957) grad_norm: 0.9915 (1.0126) time: 0.5109 [2021-03-25 10:10:23 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 620/1251] eta: 0:05:24 lr: 0.000960 loss: 3.9068 (3.9004) grad_norm: 1.0278 (1.0136) time: 0.5009 [2021-03-25 10:10:28 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 630/1251] eta: 0:05:19 lr: 0.000960 loss: 4.0838 (3.9015) grad_norm: 1.0071 (1.0135) time: 0.5049 [2021-03-25 10:10:33 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 640/1251] eta: 0:05:14 lr: 0.000960 loss: 3.8054 (3.8966) grad_norm: 0.9890 (1.0132) time: 0.5078 [2021-03-25 10:10:38 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 650/1251] eta: 0:05:08 lr: 0.000960 loss: 3.9601 (3.8991) grad_norm: 1.0220 (1.0142) time: 0.5075 [2021-03-25 10:10:43 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 660/1251] eta: 0:05:03 lr: 0.000960 loss: 3.9888 (3.8926) grad_norm: 0.9934 (1.0136) time: 0.5063 [2021-03-25 10:10:48 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 670/1251] eta: 0:04:58 lr: 0.000960 loss: 3.7405 (3.8947) grad_norm: 0.9550 (1.0136) time: 0.5067 [2021-03-25 10:10:53 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 680/1251] eta: 0:04:53 lr: 0.000960 loss: 4.2262 (3.8988) grad_norm: 0.9896 (1.0140) time: 0.5076 [2021-03-25 10:10:58 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 690/1251] eta: 0:04:48 lr: 0.000960 loss: 4.1728 (3.9009) grad_norm: 1.0027 (1.0147) time: 0.5031 [2021-03-25 10:11:03 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 700/1251] eta: 0:04:42 lr: 0.000960 loss: 4.1728 (3.9057) grad_norm: 0.9607 (1.0146) time: 0.5044 [2021-03-25 10:11:08 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 710/1251] eta: 0:04:37 lr: 0.000960 loss: 4.0920 (3.9078) grad_norm: 0.9613 (1.0154) time: 0.5034 [2021-03-25 10:11:14 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 720/1251] eta: 0:04:32 lr: 0.000960 loss: 3.9859 (3.9069) grad_norm: 1.0577 (1.0162) time: 0.5046 [2021-03-25 10:11:19 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 730/1251] eta: 0:04:27 lr: 0.000960 loss: 3.8643 (3.9042) grad_norm: 1.0831 (1.0169) time: 0.5152 [2021-03-25 10:11:24 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 740/1251] eta: 0:04:22 lr: 0.000960 loss: 3.8643 (3.9038) grad_norm: 1.0753 (1.0171) time: 0.5216 [2021-03-25 10:11:29 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 750/1251] eta: 0:04:17 lr: 0.000960 loss: 4.1424 (3.9092) grad_norm: 1.0101 (1.0174) time: 0.5156 [2021-03-25 10:11:34 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 760/1251] eta: 0:04:12 lr: 0.000960 loss: 4.1360 (3.9062) grad_norm: 0.9963 (1.0169) time: 0.5123 [2021-03-25 10:11:39 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 770/1251] eta: 0:04:06 lr: 0.000960 loss: 3.5463 (3.9024) grad_norm: 0.9717 (1.0165) time: 0.5097 [2021-03-25 10:11:44 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 780/1251] eta: 0:04:01 lr: 0.000960 loss: 3.5463 (3.8983) grad_norm: 0.9515 (1.0155) time: 0.5023 [2021-03-25 10:11:49 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 790/1251] eta: 0:03:56 lr: 0.000960 loss: 3.7099 (3.8972) grad_norm: 0.9538 (1.0153) time: 0.5084 [2021-03-25 10:11:55 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 800/1251] eta: 0:03:51 lr: 0.000960 loss: 4.0078 (3.9012) grad_norm: 0.9538 (1.0146) time: 0.5188 [2021-03-25 10:12:00 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 810/1251] eta: 0:03:46 lr: 0.000960 loss: 4.0041 (3.8987) grad_norm: 0.9523 (1.0143) time: 0.5118 [2021-03-25 10:12:05 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 820/1251] eta: 0:03:41 lr: 0.000960 loss: 3.9472 (3.8983) grad_norm: 1.0046 (1.0144) time: 0.5005 [2021-03-25 10:12:10 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 830/1251] eta: 0:03:35 lr: 0.000960 loss: 4.0591 (3.9002) grad_norm: 1.0261 (1.0151) time: 0.5046 [2021-03-25 10:12:15 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 840/1251] eta: 0:03:30 lr: 0.000960 loss: 4.0591 (3.9017) grad_norm: 1.0206 (1.0148) time: 0.5110 [2021-03-25 10:12:20 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 850/1251] eta: 0:03:25 lr: 0.000960 loss: 4.0394 (3.9010) grad_norm: 0.9861 (1.0144) time: 0.5119 [2021-03-25 10:12:25 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 860/1251] eta: 0:03:20 lr: 0.000960 loss: 4.3132 (3.9067) grad_norm: 0.9915 (1.0148) time: 0.5115 [2021-03-25 10:12:30 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 870/1251] eta: 0:03:15 lr: 0.000960 loss: 4.3132 (3.9061) grad_norm: 0.9932 (1.0145) time: 0.5053 [2021-03-25 10:12:35 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 880/1251] eta: 0:03:10 lr: 0.000960 loss: 3.8854 (3.9044) grad_norm: 0.9880 (1.0148) time: 0.5044 [2021-03-25 10:12:40 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 890/1251] eta: 0:03:05 lr: 0.000960 loss: 3.9083 (3.9022) grad_norm: 0.9880 (1.0147) time: 0.5057 [2021-03-25 10:12:45 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 900/1251] eta: 0:02:59 lr: 0.000960 loss: 4.0969 (3.9068) grad_norm: 0.9588 (1.0144) time: 0.5001 [2021-03-25 10:12:50 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 910/1251] eta: 0:02:54 lr: 0.000960 loss: 4.0841 (3.9077) grad_norm: 0.9354 (1.0139) time: 0.5019 [2021-03-25 10:12:55 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 920/1251] eta: 0:02:49 lr: 0.000960 loss: 3.9293 (3.9068) grad_norm: 0.9469 (1.0135) time: 0.5051 [2021-03-25 10:13:00 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 930/1251] eta: 0:02:44 lr: 0.000960 loss: 3.9293 (3.9060) grad_norm: 1.0329 (1.0146) time: 0.5032 [2021-03-25 10:13:05 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 940/1251] eta: 0:02:39 lr: 0.000960 loss: 3.9582 (3.9057) grad_norm: 1.0383 (1.0144) time: 0.5026 [2021-03-25 10:13:11 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 950/1251] eta: 0:02:34 lr: 0.000960 loss: 4.1831 (3.9068) grad_norm: 0.9963 (1.0151) time: 0.5101 [2021-03-25 10:13:16 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 960/1251] eta: 0:02:29 lr: 0.000960 loss: 3.7881 (3.9064) grad_norm: 1.0101 (1.0156) time: 0.5139 [2021-03-25 10:13:21 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 970/1251] eta: 0:02:23 lr: 0.000960 loss: 3.9237 (3.9068) grad_norm: 0.9980 (1.0153) time: 0.5069 [2021-03-25 10:13:26 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 980/1251] eta: 0:02:18 lr: 0.000960 loss: 3.9529 (3.9073) grad_norm: 1.0011 (1.0157) time: 0.5041 [2021-03-25 10:13:31 swin_small_patch4_window7_224] INFO: Epoch: [38] [ 990/1251] eta: 0:02:13 lr: 0.000960 loss: 3.8042 (3.9038) grad_norm: 1.0058 (1.0155) time: 0.5021 [2021-03-25 10:13:36 swin_small_patch4_window7_224] INFO: Epoch: [38] [1000/1251] eta: 0:02:08 lr: 0.000960 loss: 3.6616 (3.9040) grad_norm: 0.9753 (1.0151) time: 0.5018 [2021-03-25 10:13:41 swin_small_patch4_window7_224] INFO: Epoch: [38] [1010/1251] eta: 0:02:03 lr: 0.000960 loss: 3.6616 (3.8999) grad_norm: 0.9695 (1.0152) time: 0.5057 [2021-03-25 10:13:46 swin_small_patch4_window7_224] INFO: Epoch: [38] [1020/1251] eta: 0:01:58 lr: 0.000960 loss: 3.8477 (3.9012) grad_norm: 0.9787 (1.0152) time: 0.5050 [2021-03-25 10:13:51 swin_small_patch4_window7_224] INFO: Epoch: [38] [1030/1251] eta: 0:01:53 lr: 0.000960 loss: 4.1104 (3.9006) grad_norm: 1.0054 (1.0164) time: 0.5047 [2021-03-25 10:13:56 swin_small_patch4_window7_224] INFO: Epoch: [38] [1040/1251] eta: 0:01:47 lr: 0.000960 loss: 4.1104 (3.9009) grad_norm: 1.0743 (1.0179) time: 0.5034 [2021-03-25 10:14:01 swin_small_patch4_window7_224] INFO: Epoch: [38] [1050/1251] eta: 0:01:42 lr: 0.000960 loss: 4.2507 (3.9018) grad_norm: 1.1420 (1.0184) time: 0.5084 [2021-03-25 10:14:06 swin_small_patch4_window7_224] INFO: Epoch: [38] [1060/1251] eta: 0:01:37 lr: 0.000960 loss: 4.0851 (3.9010) grad_norm: 0.9665 (1.0181) time: 0.5109 [2021-03-25 10:14:11 swin_small_patch4_window7_224] INFO: Epoch: [38] [1070/1251] eta: 0:01:32 lr: 0.000960 loss: 3.8428 (3.9017) grad_norm: 0.9544 (1.0182) time: 0.5082 [2021-03-25 10:14:16 swin_small_patch4_window7_224] INFO: Epoch: [38] [1080/1251] eta: 0:01:27 lr: 0.000960 loss: 3.9696 (3.9014) grad_norm: 0.9491 (1.0177) time: 0.5076 [2021-03-25 10:14:21 swin_small_patch4_window7_224] INFO: Epoch: [38] [1090/1251] eta: 0:01:22 lr: 0.000960 loss: 4.0348 (3.9024) grad_norm: 0.9273 (1.0172) time: 0.5071 [2021-03-25 10:14:27 swin_small_patch4_window7_224] INFO: Epoch: [38] [1100/1251] eta: 0:01:17 lr: 0.000960 loss: 3.7056 (3.8992) grad_norm: 0.9611 (1.0174) time: 0.5102 [2021-03-25 10:14:32 swin_small_patch4_window7_224] INFO: Epoch: [38] [1110/1251] eta: 0:01:12 lr: 0.000960 loss: 3.6759 (3.9003) grad_norm: 0.9681 (1.0174) time: 0.5106 [2021-03-25 10:14:37 swin_small_patch4_window7_224] INFO: Epoch: [38] [1120/1251] eta: 0:01:06 lr: 0.000960 loss: 3.7871 (3.8967) grad_norm: 0.9744 (1.0173) time: 0.5044 [2021-03-25 10:14:42 swin_small_patch4_window7_224] INFO: Epoch: [38] [1130/1251] eta: 0:01:01 lr: 0.000959 loss: 3.7871 (3.8952) grad_norm: 1.0135 (1.0174) time: 0.5057 [2021-03-25 10:14:47 swin_small_patch4_window7_224] INFO: Epoch: [38] [1140/1251] eta: 0:00:56 lr: 0.000959 loss: 3.9818 (3.8962) grad_norm: 0.9438 (1.0170) time: 0.5086 [2021-03-25 10:14:52 swin_small_patch4_window7_224] INFO: Epoch: [38] [1150/1251] eta: 0:00:51 lr: 0.000959 loss: 4.0611 (3.8981) grad_norm: 0.9032 (1.0163) time: 0.5033 [2021-03-25 10:14:57 swin_small_patch4_window7_224] INFO: Epoch: [38] [1160/1251] eta: 0:00:46 lr: 0.000959 loss: 3.8463 (3.8976) grad_norm: 0.9818 (1.0163) time: 0.5010 [2021-03-25 10:15:02 swin_small_patch4_window7_224] INFO: Epoch: [38] [1170/1251] eta: 0:00:41 lr: 0.000959 loss: 3.8463 (3.8976) grad_norm: 1.0141 (1.0163) time: 0.5032 [2021-03-25 10:15:07 swin_small_patch4_window7_224] INFO: Epoch: [38] [1180/1251] eta: 0:00:36 lr: 0.000959 loss: 3.7499 (3.8945) grad_norm: 1.0287 (1.0174) time: 0.5027 [2021-03-25 10:15:12 swin_small_patch4_window7_224] INFO: Epoch: [38] [1190/1251] eta: 0:00:31 lr: 0.000959 loss: 3.7611 (3.8939) grad_norm: 1.0837 (1.0173) time: 0.5029 [2021-03-25 10:15:17 swin_small_patch4_window7_224] INFO: Epoch: [38] [1200/1251] eta: 0:00:26 lr: 0.000959 loss: 3.8218 (3.8930) grad_norm: 0.9788 (1.0171) time: 0.5038 [2021-03-25 10:15:22 swin_small_patch4_window7_224] INFO: Epoch: [38] [1210/1251] eta: 0:00:20 lr: 0.000959 loss: 4.0931 (3.8935) grad_norm: 0.9385 (1.0164) time: 0.4996 [2021-03-25 10:15:27 swin_small_patch4_window7_224] INFO: Epoch: [38] [1220/1251] eta: 0:00:15 lr: 0.000959 loss: 4.1363 (3.8945) grad_norm: 0.9385 (1.0164) time: 0.4969 [2021-03-25 10:15:32 swin_small_patch4_window7_224] INFO: Epoch: [38] [1230/1251] eta: 0:00:10 lr: 0.000959 loss: 4.0459 (3.8952) grad_norm: 0.9707 (1.0163) time: 0.5010 [2021-03-25 10:15:37 swin_small_patch4_window7_224] INFO: Epoch: [38] [1240/1251] eta: 0:00:05 lr: 0.000959 loss: 3.9618 (3.8951) grad_norm: 0.9991 (1.0165) time: 0.5045 [2021-03-25 10:15:42 swin_small_patch4_window7_224] INFO: Epoch: [38] [1250/1251] eta: 0:00:00 lr: 0.000959 loss: 3.9188 (3.8933) grad_norm: 1.1105 (1.0175) time: 0.5028 [2021-03-25 10:15:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 1.0021 (1.0021) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-25 10:15:50 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 1.2006 (1.1974) acc1: 71.8750 (72.7273) acc5: 90.6250 (91.6193) [2021-03-25 10:15:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.2104 (1.2449) acc1: 71.8750 (71.6518) acc5: 90.6250 (91.3690) [2021-03-25 10:15:55 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.3184 (1.2667) acc1: 70.3125 (71.5222) acc5: 90.6250 (90.8770) [2021-03-25 10:15:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3226 (1.2947) acc1: 67.1875 (70.4268) acc5: 89.0625 (90.4345) [2021-03-25 10:15:57 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3226 (1.3002) acc1: 67.1875 (70.4320) acc5: 89.0625 (90.4320) [2021-03-25 10:15:59 swin_small_patch4_window7_224] INFO: * Acc@1 70.898 Acc@5 90.614 loss 1.265 [2021-03-25 10:15:59 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.9% [2021-03-25 10:15:59 swin_small_patch4_window7_224] INFO: Max accuracy: 70.90% [2021-03-25 10:16:03 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 0/1251] eta: 1:19:01 lr: 0.000959 loss: 3.8139 (3.8139) grad_norm: 1.0718 (1.0718) time: 3.7904 [2021-03-25 10:16:08 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 10/1251] eta: 0:17:39 lr: 0.000959 loss: 3.9021 (3.9284) grad_norm: 1.0718 (1.1371) time: 0.8537 [2021-03-25 10:16:14 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 20/1251] eta: 0:14:13 lr: 0.000959 loss: 3.9993 (4.0001) grad_norm: 1.0549 (1.1000) time: 0.5382 [2021-03-25 10:16:19 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 30/1251] eta: 0:12:52 lr: 0.000959 loss: 3.9537 (3.9428) grad_norm: 1.0108 (1.0719) time: 0.5111 [2021-03-25 10:16:24 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 40/1251] eta: 0:12:08 lr: 0.000959 loss: 3.7656 (3.8356) grad_norm: 0.9520 (1.0519) time: 0.5048 [2021-03-25 10:16:29 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 50/1251] eta: 0:11:40 lr: 0.000959 loss: 3.8002 (3.8169) grad_norm: 1.0348 (1.0686) time: 0.5063 [2021-03-25 10:16:34 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 60/1251] eta: 0:11:18 lr: 0.000959 loss: 4.0159 (3.8173) grad_norm: 0.9910 (1.0612) time: 0.5062 [2021-03-25 10:16:39 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 70/1251] eta: 0:11:02 lr: 0.000959 loss: 4.0171 (3.8242) grad_norm: 0.9795 (1.0594) time: 0.5044 [2021-03-25 10:16:44 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 80/1251] eta: 0:10:49 lr: 0.000959 loss: 3.7655 (3.8145) grad_norm: 0.9813 (1.0487) time: 0.5093 [2021-03-25 10:16:49 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 90/1251] eta: 0:10:39 lr: 0.000959 loss: 4.1599 (3.8473) grad_norm: 0.9592 (1.0389) time: 0.5139 [2021-03-25 10:16:54 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 100/1251] eta: 0:10:28 lr: 0.000959 loss: 4.1039 (3.8685) grad_norm: 0.9582 (1.0379) time: 0.5100 [2021-03-25 10:16:59 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 110/1251] eta: 0:10:18 lr: 0.000959 loss: 4.0664 (3.8847) grad_norm: 0.9582 (1.0334) time: 0.5044 [2021-03-25 10:17:04 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 120/1251] eta: 0:10:10 lr: 0.000959 loss: 3.9560 (3.8885) grad_norm: 0.9359 (1.0260) time: 0.5062 [2021-03-25 10:17:09 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 130/1251] eta: 0:10:01 lr: 0.000959 loss: 4.0317 (3.9189) grad_norm: 0.9643 (1.0271) time: 0.5056 [2021-03-25 10:17:14 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 140/1251] eta: 0:09:53 lr: 0.000959 loss: 4.0069 (3.9204) grad_norm: 1.0163 (1.0289) time: 0.5004 [2021-03-25 10:17:19 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 150/1251] eta: 0:09:45 lr: 0.000959 loss: 3.8815 (3.9222) grad_norm: 0.9991 (1.0295) time: 0.4996 [2021-03-25 10:17:24 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 160/1251] eta: 0:09:38 lr: 0.000959 loss: 3.8815 (3.9131) grad_norm: 0.9696 (1.0312) time: 0.5008 [2021-03-25 10:17:30 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 170/1251] eta: 0:09:31 lr: 0.000959 loss: 3.6566 (3.9040) grad_norm: 0.9958 (1.0310) time: 0.5060 [2021-03-25 10:17:34 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 180/1251] eta: 0:09:24 lr: 0.000959 loss: 3.9314 (3.9043) grad_norm: 1.0306 (1.0318) time: 0.5050 [2021-03-25 10:17:39 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 190/1251] eta: 0:09:17 lr: 0.000959 loss: 3.9971 (3.9104) grad_norm: 1.0306 (1.0329) time: 0.4988 [2021-03-25 10:17:45 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 200/1251] eta: 0:09:11 lr: 0.000959 loss: 4.1340 (3.9085) grad_norm: 1.0159 (1.0336) time: 0.5047 [2021-03-25 10:17:50 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 210/1251] eta: 0:09:05 lr: 0.000959 loss: 3.8733 (3.8996) grad_norm: 1.0129 (1.0334) time: 0.5122 [2021-03-25 10:17:55 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 220/1251] eta: 0:08:59 lr: 0.000959 loss: 3.9575 (3.9086) grad_norm: 1.0304 (1.0353) time: 0.5124 [2021-03-25 10:18:00 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 230/1251] eta: 0:08:54 lr: 0.000959 loss: 3.9727 (3.9048) grad_norm: 1.0504 (1.0353) time: 0.5099 [2021-03-25 10:18:05 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 240/1251] eta: 0:08:48 lr: 0.000959 loss: 3.8676 (3.9030) grad_norm: 1.0210 (1.0334) time: 0.5083 [2021-03-25 10:18:10 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 250/1251] eta: 0:08:42 lr: 0.000959 loss: 3.7921 (3.8918) grad_norm: 0.9779 (1.0318) time: 0.5064 [2021-03-25 10:18:15 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 260/1251] eta: 0:08:36 lr: 0.000959 loss: 3.7272 (3.8971) grad_norm: 0.9936 (1.0313) time: 0.5039 [2021-03-25 10:18:20 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 270/1251] eta: 0:08:30 lr: 0.000959 loss: 4.2315 (3.8985) grad_norm: 0.9910 (1.0292) time: 0.5030 [2021-03-25 10:18:25 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 280/1251] eta: 0:08:24 lr: 0.000959 loss: 3.9955 (3.8957) grad_norm: 1.0075 (1.0314) time: 0.5009 [2021-03-25 10:18:30 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 290/1251] eta: 0:08:18 lr: 0.000959 loss: 3.7158 (3.8909) grad_norm: 1.0280 (1.0302) time: 0.5014 [2021-03-25 10:18:35 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 300/1251] eta: 0:08:13 lr: 0.000959 loss: 3.8560 (3.8949) grad_norm: 1.0001 (1.0294) time: 0.5062 [2021-03-25 10:18:40 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 310/1251] eta: 0:08:07 lr: 0.000959 loss: 3.9196 (3.8948) grad_norm: 0.9739 (1.0276) time: 0.5068 [2021-03-25 10:18:45 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 320/1251] eta: 0:08:02 lr: 0.000959 loss: 4.0325 (3.9008) grad_norm: 0.9693 (1.0259) time: 0.5070 [2021-03-25 10:18:50 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 330/1251] eta: 0:07:56 lr: 0.000959 loss: 4.0864 (3.8991) grad_norm: 0.9701 (1.0254) time: 0.5060 [2021-03-25 10:18:55 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 340/1251] eta: 0:07:51 lr: 0.000959 loss: 3.9962 (3.8984) grad_norm: 1.0153 (1.0261) time: 0.5050 [2021-03-25 10:19:01 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 350/1251] eta: 0:07:45 lr: 0.000959 loss: 3.9966 (3.8984) grad_norm: 1.0443 (1.0267) time: 0.5046 [2021-03-25 10:19:06 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 360/1251] eta: 0:07:40 lr: 0.000959 loss: 3.9236 (3.8878) grad_norm: 1.0701 (1.0283) time: 0.5040 [2021-03-25 10:19:11 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 370/1251] eta: 0:07:34 lr: 0.000959 loss: 3.9516 (3.8907) grad_norm: 1.0921 (1.0295) time: 0.5080 [2021-03-25 10:19:16 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 380/1251] eta: 0:07:29 lr: 0.000959 loss: 4.1533 (3.8960) grad_norm: 1.0921 (1.0305) time: 0.5068 [2021-03-25 10:19:21 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 390/1251] eta: 0:07:24 lr: 0.000959 loss: 4.0079 (3.8941) grad_norm: 1.0292 (1.0311) time: 0.5065 [2021-03-25 10:19:26 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 400/1251] eta: 0:07:18 lr: 0.000959 loss: 4.0199 (3.8973) grad_norm: 0.9894 (1.0306) time: 0.5093 [2021-03-25 10:19:31 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 410/1251] eta: 0:07:13 lr: 0.000959 loss: 4.0237 (3.8987) grad_norm: 0.9804 (1.0297) time: 0.5070 [2021-03-25 10:19:36 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 420/1251] eta: 0:07:07 lr: 0.000959 loss: 4.0237 (3.8998) grad_norm: 0.9539 (1.0281) time: 0.5011 [2021-03-25 10:19:41 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 430/1251] eta: 0:07:02 lr: 0.000959 loss: 4.0369 (3.9040) grad_norm: 0.9545 (1.0281) time: 0.5032 [2021-03-25 10:19:46 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 440/1251] eta: 0:06:57 lr: 0.000959 loss: 4.0212 (3.9034) grad_norm: 0.9903 (1.0271) time: 0.5072 [2021-03-25 10:19:51 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 450/1251] eta: 0:06:52 lr: 0.000959 loss: 3.8159 (3.8982) grad_norm: 0.9942 (1.0283) time: 0.5068 [2021-03-25 10:19:56 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 460/1251] eta: 0:06:46 lr: 0.000959 loss: 3.6179 (3.8913) grad_norm: 1.0414 (1.0297) time: 0.5061 [2021-03-25 10:20:01 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 470/1251] eta: 0:06:41 lr: 0.000959 loss: 3.9302 (3.8953) grad_norm: 1.0098 (1.0295) time: 0.5012 [2021-03-25 10:20:06 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 480/1251] eta: 0:06:36 lr: 0.000958 loss: 4.0699 (3.9000) grad_norm: 0.9493 (1.0304) time: 0.5024 [2021-03-25 10:20:11 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 490/1251] eta: 0:06:30 lr: 0.000958 loss: 4.0699 (3.9027) grad_norm: 1.0290 (1.0314) time: 0.5063 [2021-03-25 10:20:16 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 500/1251] eta: 0:06:25 lr: 0.000958 loss: 3.9453 (3.8971) grad_norm: 1.0628 (1.0327) time: 0.5065 [2021-03-25 10:20:21 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 510/1251] eta: 0:06:20 lr: 0.000958 loss: 3.9453 (3.8985) grad_norm: 1.0639 (1.0336) time: 0.5062 [2021-03-25 10:20:27 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 520/1251] eta: 0:06:15 lr: 0.000958 loss: 4.0533 (3.9026) grad_norm: 1.0789 (1.0342) time: 0.5096 [2021-03-25 10:20:32 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 530/1251] eta: 0:06:09 lr: 0.000958 loss: 3.9288 (3.8972) grad_norm: 1.0213 (1.0332) time: 0.5094 [2021-03-25 10:20:37 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 540/1251] eta: 0:06:04 lr: 0.000958 loss: 3.8218 (3.8936) grad_norm: 0.9696 (1.0332) time: 0.5041 [2021-03-25 10:20:42 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 550/1251] eta: 0:05:59 lr: 0.000958 loss: 3.9038 (3.8928) grad_norm: 1.0045 (1.0328) time: 0.5208 [2021-03-25 10:20:47 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 560/1251] eta: 0:05:54 lr: 0.000958 loss: 4.0440 (3.8928) grad_norm: 1.0420 (1.0336) time: 0.5248 [2021-03-25 10:20:52 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 570/1251] eta: 0:05:49 lr: 0.000958 loss: 4.1745 (3.8972) grad_norm: 1.0289 (1.0339) time: 0.5100 [2021-03-25 10:20:57 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 580/1251] eta: 0:05:44 lr: 0.000958 loss: 4.1335 (3.8993) grad_norm: 1.0086 (1.0341) time: 0.5075 [2021-03-25 10:21:02 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 590/1251] eta: 0:05:39 lr: 0.000958 loss: 4.1335 (3.9005) grad_norm: 0.9866 (1.0333) time: 0.5043 [2021-03-25 10:21:07 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 600/1251] eta: 0:05:33 lr: 0.000958 loss: 4.1233 (3.9040) grad_norm: 1.0235 (1.0335) time: 0.5081 [2021-03-25 10:21:13 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 610/1251] eta: 0:05:28 lr: 0.000958 loss: 4.1304 (3.9103) grad_norm: 1.0276 (1.0341) time: 0.5090 [2021-03-25 10:21:18 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 620/1251] eta: 0:05:23 lr: 0.000958 loss: 4.1304 (3.9090) grad_norm: 1.0222 (1.0346) time: 0.5033 [2021-03-25 10:21:23 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 630/1251] eta: 0:05:18 lr: 0.000958 loss: 4.0390 (3.9097) grad_norm: 0.9695 (1.0334) time: 0.5067 [2021-03-25 10:21:28 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 640/1251] eta: 0:05:13 lr: 0.000958 loss: 3.8433 (3.9061) grad_norm: 0.9285 (1.0322) time: 0.5107 [2021-03-25 10:21:33 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 650/1251] eta: 0:05:08 lr: 0.000958 loss: 3.7619 (3.9046) grad_norm: 0.9285 (1.0315) time: 0.5122 [2021-03-25 10:21:38 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 660/1251] eta: 0:05:02 lr: 0.000958 loss: 3.7619 (3.9026) grad_norm: 0.9216 (1.0311) time: 0.5103 [2021-03-25 10:21:43 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 670/1251] eta: 0:04:57 lr: 0.000958 loss: 4.0204 (3.9053) grad_norm: 0.9168 (1.0301) time: 0.5033 [2021-03-25 10:21:48 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 680/1251] eta: 0:04:52 lr: 0.000958 loss: 3.9771 (3.9021) grad_norm: 0.9742 (1.0306) time: 0.5031 [2021-03-25 10:21:53 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 690/1251] eta: 0:04:47 lr: 0.000958 loss: 3.8045 (3.8978) grad_norm: 1.0515 (1.0309) time: 0.5024 [2021-03-25 10:21:58 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 700/1251] eta: 0:04:42 lr: 0.000958 loss: 3.6680 (3.8918) grad_norm: 0.9741 (1.0296) time: 0.5003 [2021-03-25 10:22:03 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 710/1251] eta: 0:04:36 lr: 0.000958 loss: 3.6680 (3.8932) grad_norm: 0.9438 (1.0289) time: 0.5075 [2021-03-25 10:22:08 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 720/1251] eta: 0:04:31 lr: 0.000958 loss: 3.8112 (3.8915) grad_norm: 0.9719 (1.0283) time: 0.5173 [2021-03-25 10:22:13 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 730/1251] eta: 0:04:26 lr: 0.000958 loss: 3.9556 (3.8927) grad_norm: 0.9639 (1.0282) time: 0.5115 [2021-03-25 10:22:19 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 740/1251] eta: 0:04:21 lr: 0.000958 loss: 3.9556 (3.8893) grad_norm: 0.9731 (1.0278) time: 0.5265 [2021-03-25 10:22:24 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 750/1251] eta: 0:04:16 lr: 0.000958 loss: 3.6396 (3.8878) grad_norm: 1.0045 (1.0277) time: 0.5273 [2021-03-25 10:22:29 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 760/1251] eta: 0:04:11 lr: 0.000958 loss: 3.9669 (3.8862) grad_norm: 1.0255 (1.0279) time: 0.5085 [2021-03-25 10:22:34 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 770/1251] eta: 0:04:06 lr: 0.000958 loss: 4.0870 (3.8873) grad_norm: 0.9770 (1.0272) time: 0.5077 [2021-03-25 10:22:39 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 780/1251] eta: 0:04:01 lr: 0.000958 loss: 4.0480 (3.8854) grad_norm: 0.9495 (1.0259) time: 0.5003 [2021-03-25 10:22:44 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 790/1251] eta: 0:03:55 lr: 0.000958 loss: 3.8122 (3.8827) grad_norm: 0.9202 (1.0247) time: 0.4984 [2021-03-25 10:22:49 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 800/1251] eta: 0:03:50 lr: 0.000958 loss: 4.0358 (3.8840) grad_norm: 0.9202 (1.0236) time: 0.5064 [2021-03-25 10:22:54 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 810/1251] eta: 0:03:45 lr: 0.000958 loss: 3.8755 (3.8826) grad_norm: 0.9787 (1.0235) time: 0.5091 [2021-03-25 10:22:59 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 820/1251] eta: 0:03:40 lr: 0.000958 loss: 3.8669 (3.8826) grad_norm: 0.9787 (1.0227) time: 0.5037 [2021-03-25 10:23:04 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 830/1251] eta: 0:03:35 lr: 0.000958 loss: 3.7906 (3.8804) grad_norm: 0.9757 (1.0227) time: 0.5016 [2021-03-25 10:23:09 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 840/1251] eta: 0:03:30 lr: 0.000958 loss: 3.7906 (3.8808) grad_norm: 0.9799 (1.0222) time: 0.5050 [2021-03-25 10:23:15 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 850/1251] eta: 0:03:25 lr: 0.000958 loss: 3.8221 (3.8794) grad_norm: 1.0101 (1.0236) time: 0.5094 [2021-03-25 10:23:20 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 860/1251] eta: 0:03:19 lr: 0.000958 loss: 4.1422 (3.8819) grad_norm: 1.1149 (1.0244) time: 0.5074 [2021-03-25 10:23:25 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 870/1251] eta: 0:03:14 lr: 0.000958 loss: 4.1422 (3.8801) grad_norm: 0.9606 (1.0232) time: 0.5052 [2021-03-25 10:23:30 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 880/1251] eta: 0:03:09 lr: 0.000958 loss: 3.7777 (3.8785) grad_norm: 0.9435 (1.0234) time: 0.5025 [2021-03-25 10:23:35 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 890/1251] eta: 0:03:04 lr: 0.000958 loss: 3.8762 (3.8793) grad_norm: 0.9693 (1.0231) time: 0.5040 [2021-03-25 10:23:40 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 900/1251] eta: 0:02:59 lr: 0.000958 loss: 4.1101 (3.8820) grad_norm: 0.9772 (1.0230) time: 0.5066 [2021-03-25 10:23:45 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 910/1251] eta: 0:02:54 lr: 0.000958 loss: 4.0868 (3.8797) grad_norm: 1.0081 (1.0229) time: 0.5109 [2021-03-25 10:23:50 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 920/1251] eta: 0:02:49 lr: 0.000958 loss: 3.5446 (3.8760) grad_norm: 0.9935 (1.0231) time: 0.5119 [2021-03-25 10:23:55 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 930/1251] eta: 0:02:44 lr: 0.000958 loss: 3.5446 (3.8755) grad_norm: 0.9899 (1.0228) time: 0.5009 [2021-03-25 10:24:00 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 940/1251] eta: 0:02:38 lr: 0.000958 loss: 3.8358 (3.8749) grad_norm: 0.9591 (1.0220) time: 0.4952 [2021-03-25 10:24:05 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 950/1251] eta: 0:02:33 lr: 0.000958 loss: 4.0128 (3.8778) grad_norm: 0.9569 (1.0218) time: 0.5053 [2021-03-25 10:24:10 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 960/1251] eta: 0:02:28 lr: 0.000958 loss: 4.0021 (3.8770) grad_norm: 1.0603 (1.0222) time: 0.5111 [2021-03-25 10:24:15 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 970/1251] eta: 0:02:23 lr: 0.000958 loss: 3.7005 (3.8753) grad_norm: 1.0603 (1.0225) time: 0.5071 [2021-03-25 10:24:20 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 980/1251] eta: 0:02:18 lr: 0.000958 loss: 3.7583 (3.8759) grad_norm: 1.0556 (1.0232) time: 0.5073 [2021-03-25 10:24:25 swin_small_patch4_window7_224] INFO: Epoch: [39] [ 990/1251] eta: 0:02:13 lr: 0.000958 loss: 4.1101 (3.8759) grad_norm: 1.0184 (1.0225) time: 0.5092 [2021-03-25 10:24:30 swin_small_patch4_window7_224] INFO: Epoch: [39] [1000/1251] eta: 0:02:08 lr: 0.000958 loss: 3.9387 (3.8750) grad_norm: 1.0085 (1.0232) time: 0.5084 [2021-03-25 10:24:36 swin_small_patch4_window7_224] INFO: Epoch: [39] [1010/1251] eta: 0:02:03 lr: 0.000958 loss: 3.8799 (3.8740) grad_norm: 1.0031 (1.0227) time: 0.5088 [2021-03-25 10:24:41 swin_small_patch4_window7_224] INFO: Epoch: [39] [1020/1251] eta: 0:01:57 lr: 0.000958 loss: 3.9163 (3.8751) grad_norm: 1.0525 (1.0229) time: 0.5067 [2021-03-25 10:24:46 swin_small_patch4_window7_224] INFO: Epoch: [39] [1030/1251] eta: 0:01:52 lr: 0.000958 loss: 4.1575 (3.8785) grad_norm: 1.0530 (1.0228) time: 0.5031 [2021-03-25 10:24:51 swin_small_patch4_window7_224] INFO: Epoch: [39] [1040/1251] eta: 0:01:47 lr: 0.000958 loss: 4.0554 (3.8785) grad_norm: 0.9854 (1.0228) time: 0.5041 [2021-03-25 10:24:56 swin_small_patch4_window7_224] INFO: Epoch: [39] [1050/1251] eta: 0:01:42 lr: 0.000958 loss: 3.9043 (3.8776) grad_norm: 1.0464 (1.0234) time: 0.5041 [2021-03-25 10:25:01 swin_small_patch4_window7_224] INFO: Epoch: [39] [1060/1251] eta: 0:01:37 lr: 0.000958 loss: 3.9043 (3.8771) grad_norm: 1.0094 (1.0234) time: 0.5046 [2021-03-25 10:25:06 swin_small_patch4_window7_224] INFO: Epoch: [39] [1070/1251] eta: 0:01:32 lr: 0.000958 loss: 3.8613 (3.8753) grad_norm: 0.9980 (1.0234) time: 0.5062 [2021-03-25 10:25:11 swin_small_patch4_window7_224] INFO: Epoch: [39] [1080/1251] eta: 0:01:27 lr: 0.000957 loss: 3.9158 (3.8783) grad_norm: 0.9932 (1.0229) time: 0.5024 [2021-03-25 10:25:16 swin_small_patch4_window7_224] INFO: Epoch: [39] [1090/1251] eta: 0:01:22 lr: 0.000957 loss: 4.1040 (3.8801) grad_norm: 1.0529 (1.0235) time: 0.4990 [2021-03-25 10:25:21 swin_small_patch4_window7_224] INFO: Epoch: [39] [1100/1251] eta: 0:01:17 lr: 0.000957 loss: 3.9389 (3.8805) grad_norm: 1.0396 (1.0236) time: 0.5059 [2021-03-25 10:25:26 swin_small_patch4_window7_224] INFO: Epoch: [39] [1110/1251] eta: 0:01:11 lr: 0.000957 loss: 4.1433 (3.8823) grad_norm: 1.0087 (1.0234) time: 0.5037 [2021-03-25 10:25:31 swin_small_patch4_window7_224] INFO: Epoch: [39] [1120/1251] eta: 0:01:06 lr: 0.000957 loss: 3.9607 (3.8822) grad_norm: 1.0084 (1.0231) time: 0.5013 [2021-03-25 10:25:36 swin_small_patch4_window7_224] INFO: Epoch: [39] [1130/1251] eta: 0:01:01 lr: 0.000957 loss: 3.8678 (3.8819) grad_norm: 0.9793 (1.0232) time: 0.5067 [2021-03-25 10:25:41 swin_small_patch4_window7_224] INFO: Epoch: [39] [1140/1251] eta: 0:00:56 lr: 0.000957 loss: 3.8578 (3.8817) grad_norm: 1.0219 (1.0232) time: 0.5048 [2021-03-25 10:25:46 swin_small_patch4_window7_224] INFO: Epoch: [39] [1150/1251] eta: 0:00:51 lr: 0.000957 loss: 4.0120 (3.8842) grad_norm: 0.9605 (1.0227) time: 0.5054 [2021-03-25 10:25:51 swin_small_patch4_window7_224] INFO: Epoch: [39] [1160/1251] eta: 0:00:46 lr: 0.000957 loss: 4.2739 (3.8861) grad_norm: 0.9857 (1.0230) time: 0.5014 [2021-03-25 10:25:56 swin_small_patch4_window7_224] INFO: Epoch: [39] [1170/1251] eta: 0:00:41 lr: 0.000957 loss: 3.9659 (3.8835) grad_norm: 0.9918 (1.0234) time: 0.5028 [2021-03-25 10:26:01 swin_small_patch4_window7_224] INFO: Epoch: [39] [1180/1251] eta: 0:00:36 lr: 0.000957 loss: 3.5350 (3.8817) grad_norm: 0.9752 (1.0228) time: 0.5090 [2021-03-25 10:26:06 swin_small_patch4_window7_224] INFO: Epoch: [39] [1190/1251] eta: 0:00:31 lr: 0.000957 loss: 4.0688 (3.8843) grad_norm: 1.0464 (1.0235) time: 0.5072 [2021-03-25 10:26:11 swin_small_patch4_window7_224] INFO: Epoch: [39] [1200/1251] eta: 0:00:25 lr: 0.000957 loss: 4.0718 (3.8851) grad_norm: 1.0734 (1.0236) time: 0.5043 [2021-03-25 10:26:16 swin_small_patch4_window7_224] INFO: Epoch: [39] [1210/1251] eta: 0:00:20 lr: 0.000957 loss: 3.9617 (3.8831) grad_norm: 1.0655 (1.0240) time: 0.5041 [2021-03-25 10:26:22 swin_small_patch4_window7_224] INFO: Epoch: [39] [1220/1251] eta: 0:00:15 lr: 0.000957 loss: 3.7123 (3.8814) grad_norm: 1.0655 (1.0243) time: 0.5072 [2021-03-25 10:26:27 swin_small_patch4_window7_224] INFO: Epoch: [39] [1230/1251] eta: 0:00:10 lr: 0.000957 loss: 3.6971 (3.8806) grad_norm: 0.9951 (1.0238) time: 0.5064 [2021-03-25 10:26:32 swin_small_patch4_window7_224] INFO: Epoch: [39] [1240/1251] eta: 0:00:05 lr: 0.000957 loss: 3.7922 (3.8797) grad_norm: 0.9827 (1.0235) time: 0.5040 [2021-03-25 10:26:37 swin_small_patch4_window7_224] INFO: Epoch: [39] [1250/1251] eta: 0:00:00 lr: 0.000957 loss: 3.7922 (3.8766) grad_norm: 0.9761 (1.0235) time: 0.5065 [2021-03-25 10:26:40 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.4474 (1.4474) acc1: 65.6250 (65.6250) acc5: 92.1875 (92.1875) [2021-03-25 10:26:43 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.3107 (1.2307) acc1: 71.8750 (72.3011) acc5: 92.1875 (92.0455) [2021-03-25 10:26:45 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.2297 (1.2188) acc1: 70.3125 (71.5030) acc5: 92.1875 (92.2619) [2021-03-25 10:26:48 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2297 (1.2333) acc1: 70.3125 (71.1190) acc5: 90.6250 (91.6835) [2021-03-25 10:26:50 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2981 (1.2728) acc1: 68.7500 (70.1982) acc5: 89.0625 (91.0061) [2021-03-25 10:26:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.3646 (1.2706) acc1: 68.7500 (70.5280) acc5: 89.0625 (90.8480) [2021-03-25 10:26:53 swin_small_patch4_window7_224] INFO: * Acc@1 70.734 Acc@5 90.776 loss 1.254 [2021-03-25 10:26:53 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.7% [2021-03-25 10:26:53 swin_small_patch4_window7_224] INFO: Max accuracy: 70.90% [2021-03-25 10:26:57 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 0/1251] eta: 1:28:18 lr: 0.000957 loss: 2.8157 (2.8157) grad_norm: 1.0216 (1.0216) time: 4.2354 [2021-03-25 10:27:03 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 10/1251] eta: 0:18:03 lr: 0.000957 loss: 3.8603 (3.7374) grad_norm: 0.9293 (0.9524) time: 0.8727 [2021-03-25 10:27:08 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 20/1251] eta: 0:14:19 lr: 0.000957 loss: 3.9433 (3.8348) grad_norm: 0.9293 (0.9897) time: 0.5211 [2021-03-25 10:27:13 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 30/1251] eta: 0:12:57 lr: 0.000957 loss: 4.1032 (3.9274) grad_norm: 0.9684 (0.9996) time: 0.5069 [2021-03-25 10:27:18 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 40/1251] eta: 0:12:14 lr: 0.000957 loss: 3.9617 (3.9150) grad_norm: 1.0253 (1.0331) time: 0.5105 [2021-03-25 10:27:23 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 50/1251] eta: 0:11:45 lr: 0.000957 loss: 3.9617 (3.9031) grad_norm: 1.1001 (1.0441) time: 0.5105 [2021-03-25 10:27:28 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 60/1251] eta: 0:11:23 lr: 0.000957 loss: 3.8787 (3.8716) grad_norm: 1.0487 (1.0366) time: 0.5059 [2021-03-25 10:27:33 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 70/1251] eta: 0:11:05 lr: 0.000957 loss: 3.6140 (3.8113) grad_norm: 0.9624 (1.0322) time: 0.5033 [2021-03-25 10:27:38 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 80/1251] eta: 0:10:51 lr: 0.000957 loss: 3.7605 (3.8427) grad_norm: 1.0256 (1.0371) time: 0.5043 [2021-03-25 10:27:43 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 90/1251] eta: 0:10:38 lr: 0.000957 loss: 3.7605 (3.8090) grad_norm: 1.0641 (1.0343) time: 0.5033 [2021-03-25 10:27:48 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 100/1251] eta: 0:10:27 lr: 0.000957 loss: 3.5073 (3.8188) grad_norm: 1.0345 (1.0359) time: 0.5016 [2021-03-25 10:27:53 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 110/1251] eta: 0:10:18 lr: 0.000957 loss: 3.9692 (3.7979) grad_norm: 1.0278 (1.0359) time: 0.5044 [2021-03-25 10:27:58 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 120/1251] eta: 0:10:09 lr: 0.000957 loss: 4.0044 (3.8088) grad_norm: 0.9637 (1.0307) time: 0.5077 [2021-03-25 10:28:04 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 130/1251] eta: 0:10:01 lr: 0.000957 loss: 4.0574 (3.8132) grad_norm: 0.9450 (1.0313) time: 0.5088 [2021-03-25 10:28:09 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 140/1251] eta: 0:09:54 lr: 0.000957 loss: 3.9778 (3.8183) grad_norm: 1.0519 (1.0340) time: 0.5092 [2021-03-25 10:28:14 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 150/1251] eta: 0:09:47 lr: 0.000957 loss: 3.8172 (3.8266) grad_norm: 1.0651 (1.0396) time: 0.5090 [2021-03-25 10:28:19 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 160/1251] eta: 0:09:39 lr: 0.000957 loss: 3.8564 (3.8197) grad_norm: 1.0626 (1.0430) time: 0.5051 [2021-03-25 10:28:24 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 170/1251] eta: 0:09:33 lr: 0.000957 loss: 3.8849 (3.8266) grad_norm: 1.0418 (1.0398) time: 0.5095 [2021-03-25 10:28:29 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 180/1251] eta: 0:09:27 lr: 0.000957 loss: 3.8849 (3.8237) grad_norm: 0.9744 (1.0362) time: 0.5151 [2021-03-25 10:28:34 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 190/1251] eta: 0:09:20 lr: 0.000957 loss: 3.8618 (3.8214) grad_norm: 0.9689 (1.0336) time: 0.5098 [2021-03-25 10:28:39 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 200/1251] eta: 0:09:14 lr: 0.000957 loss: 3.9016 (3.8109) grad_norm: 0.9564 (1.0308) time: 0.5093 [2021-03-25 10:28:44 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 210/1251] eta: 0:09:07 lr: 0.000957 loss: 4.0073 (3.8155) grad_norm: 0.9740 (1.0306) time: 0.5050 [2021-03-25 10:28:49 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 220/1251] eta: 0:09:01 lr: 0.000957 loss: 3.9384 (3.8153) grad_norm: 0.9951 (1.0293) time: 0.5052 [2021-03-25 10:28:54 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 230/1251] eta: 0:08:55 lr: 0.000957 loss: 3.9384 (3.8213) grad_norm: 1.0419 (1.0315) time: 0.5054 [2021-03-25 10:28:59 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 240/1251] eta: 0:08:49 lr: 0.000957 loss: 4.0382 (3.8257) grad_norm: 0.9775 (1.0285) time: 0.5013 [2021-03-25 10:29:04 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 250/1251] eta: 0:08:43 lr: 0.000957 loss: 4.0515 (3.8337) grad_norm: 0.9363 (1.0254) time: 0.5058 [2021-03-25 10:29:10 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 260/1251] eta: 0:08:37 lr: 0.000957 loss: 3.9694 (3.8332) grad_norm: 0.9462 (1.0228) time: 0.5094 [2021-03-25 10:29:15 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 270/1251] eta: 0:08:31 lr: 0.000957 loss: 3.7580 (3.8256) grad_norm: 0.9398 (1.0200) time: 0.5063 [2021-03-25 10:29:20 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 280/1251] eta: 0:08:26 lr: 0.000957 loss: 3.4397 (3.8207) grad_norm: 0.9264 (1.0182) time: 0.5066 [2021-03-25 10:29:25 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 290/1251] eta: 0:08:20 lr: 0.000957 loss: 3.6538 (3.8241) grad_norm: 0.9561 (1.0166) time: 0.5100 [2021-03-25 10:29:30 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 300/1251] eta: 0:08:14 lr: 0.000957 loss: 4.0741 (3.8271) grad_norm: 0.9832 (1.0190) time: 0.5026 [2021-03-25 10:29:35 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 310/1251] eta: 0:08:08 lr: 0.000957 loss: 4.0741 (3.8377) grad_norm: 1.0129 (1.0204) time: 0.5000 [2021-03-25 10:29:40 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 320/1251] eta: 0:08:03 lr: 0.000957 loss: 3.9612 (3.8287) grad_norm: 0.9793 (1.0190) time: 0.5034 [2021-03-25 10:29:45 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 330/1251] eta: 0:07:57 lr: 0.000957 loss: 3.7753 (3.8298) grad_norm: 0.9793 (1.0198) time: 0.5080 [2021-03-25 10:29:50 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 340/1251] eta: 0:07:52 lr: 0.000957 loss: 4.0326 (3.8359) grad_norm: 1.0082 (1.0197) time: 0.5123 [2021-03-25 10:29:55 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 350/1251] eta: 0:07:46 lr: 0.000957 loss: 3.9007 (3.8330) grad_norm: 1.0047 (1.0196) time: 0.5083 [2021-03-25 10:30:00 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 360/1251] eta: 0:07:41 lr: 0.000957 loss: 3.9563 (3.8455) grad_norm: 0.9956 (1.0191) time: 0.5082 [2021-03-25 10:30:05 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 370/1251] eta: 0:07:36 lr: 0.000957 loss: 4.3322 (3.8550) grad_norm: 0.9638 (1.0181) time: 0.5147 [2021-03-25 10:30:10 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 380/1251] eta: 0:07:30 lr: 0.000957 loss: 4.1899 (3.8601) grad_norm: 0.9356 (1.0160) time: 0.5095 [2021-03-25 10:30:15 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 390/1251] eta: 0:07:25 lr: 0.000957 loss: 3.8941 (3.8623) grad_norm: 0.9305 (1.0153) time: 0.5017 [2021-03-25 10:30:20 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 400/1251] eta: 0:07:19 lr: 0.000957 loss: 4.0539 (3.8640) grad_norm: 1.0045 (1.0175) time: 0.4996 [2021-03-25 10:30:25 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 410/1251] eta: 0:07:14 lr: 0.000957 loss: 4.1027 (3.8633) grad_norm: 1.0603 (1.0202) time: 0.4983 [2021-03-25 10:30:30 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 420/1251] eta: 0:07:08 lr: 0.000956 loss: 4.1027 (3.8673) grad_norm: 0.9787 (1.0186) time: 0.4992 [2021-03-25 10:30:35 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 430/1251] eta: 0:07:03 lr: 0.000956 loss: 4.0925 (3.8708) grad_norm: 0.9769 (1.0184) time: 0.5025 [2021-03-25 10:30:40 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 440/1251] eta: 0:06:57 lr: 0.000956 loss: 4.0609 (3.8705) grad_norm: 1.0213 (1.0195) time: 0.5005 [2021-03-25 10:30:45 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 450/1251] eta: 0:06:52 lr: 0.000956 loss: 3.6928 (3.8602) grad_norm: 1.0234 (1.0184) time: 0.4971 [2021-03-25 10:30:51 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 460/1251] eta: 0:06:47 lr: 0.000956 loss: 3.7283 (3.8622) grad_norm: 0.9420 (1.0189) time: 0.5036 [2021-03-25 10:30:56 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 470/1251] eta: 0:06:41 lr: 0.000956 loss: 3.8331 (3.8603) grad_norm: 1.0035 (1.0173) time: 0.5085 [2021-03-25 10:31:01 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 480/1251] eta: 0:06:36 lr: 0.000956 loss: 3.8331 (3.8597) grad_norm: 0.9779 (inf) time: 0.5047 [2021-03-25 10:31:06 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 490/1251] eta: 0:06:31 lr: 0.000956 loss: 3.7755 (3.8569) grad_norm: 1.0281 (inf) time: 0.5003 [2021-03-25 10:31:11 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 500/1251] eta: 0:06:25 lr: 0.000956 loss: 3.9812 (3.8618) grad_norm: 1.0535 (inf) time: 0.5025 [2021-03-25 10:31:16 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 510/1251] eta: 0:06:20 lr: 0.000956 loss: 4.0674 (3.8637) grad_norm: 0.9953 (inf) time: 0.5058 [2021-03-25 10:31:21 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 520/1251] eta: 0:06:15 lr: 0.000956 loss: 4.0456 (3.8638) grad_norm: 0.9807 (inf) time: 0.5095 [2021-03-25 10:31:26 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 530/1251] eta: 0:06:10 lr: 0.000956 loss: 3.9754 (3.8668) grad_norm: 0.9908 (inf) time: 0.5070 [2021-03-25 10:31:31 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 540/1251] eta: 0:06:05 lr: 0.000956 loss: 3.9754 (3.8639) grad_norm: 0.9908 (inf) time: 0.5091 [2021-03-25 10:31:36 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 550/1251] eta: 0:06:00 lr: 0.000956 loss: 3.9908 (3.8657) grad_norm: 0.9745 (inf) time: 0.5235 [2021-03-25 10:31:42 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 560/1251] eta: 0:05:55 lr: 0.000956 loss: 3.6695 (3.8598) grad_norm: 0.9847 (inf) time: 0.5225 [2021-03-25 10:31:47 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 570/1251] eta: 0:05:49 lr: 0.000956 loss: 3.6563 (3.8612) grad_norm: 1.0033 (inf) time: 0.5100 [2021-03-25 10:31:52 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 580/1251] eta: 0:05:44 lr: 0.000956 loss: 3.7751 (3.8536) grad_norm: 0.9955 (inf) time: 0.5074 [2021-03-25 10:31:57 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 590/1251] eta: 0:05:39 lr: 0.000956 loss: 3.4164 (3.8459) grad_norm: 1.1252 (inf) time: 0.5111 [2021-03-25 10:32:02 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 600/1251] eta: 0:05:34 lr: 0.000956 loss: 3.5898 (3.8507) grad_norm: 1.0982 (inf) time: 0.5110 [2021-03-25 10:32:07 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 610/1251] eta: 0:05:29 lr: 0.000956 loss: 4.0597 (3.8495) grad_norm: 0.9791 (inf) time: 0.5079 [2021-03-25 10:32:12 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 620/1251] eta: 0:05:23 lr: 0.000956 loss: 3.6791 (3.8465) grad_norm: 0.9791 (inf) time: 0.5019 [2021-03-25 10:32:17 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 630/1251] eta: 0:05:18 lr: 0.000956 loss: 3.7568 (3.8487) grad_norm: 1.0012 (inf) time: 0.4994 [2021-03-25 10:32:22 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 640/1251] eta: 0:05:13 lr: 0.000956 loss: 3.9646 (3.8483) grad_norm: 0.9393 (inf) time: 0.5032 [2021-03-25 10:32:27 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 650/1251] eta: 0:05:08 lr: 0.000956 loss: 4.0409 (3.8525) grad_norm: 0.9130 (inf) time: 0.5050 [2021-03-25 10:32:32 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 660/1251] eta: 0:05:02 lr: 0.000956 loss: 4.1022 (3.8547) grad_norm: 0.9801 (inf) time: 0.5027 [2021-03-25 10:32:37 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 670/1251] eta: 0:04:57 lr: 0.000956 loss: 3.9229 (3.8531) grad_norm: 1.0111 (inf) time: 0.5061 [2021-03-25 10:32:42 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 680/1251] eta: 0:04:52 lr: 0.000956 loss: 4.0312 (3.8580) grad_norm: 0.9419 (inf) time: 0.5059 [2021-03-25 10:32:47 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 690/1251] eta: 0:04:47 lr: 0.000956 loss: 4.1065 (3.8605) grad_norm: 0.9263 (inf) time: 0.5018 [2021-03-25 10:32:52 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 700/1251] eta: 0:04:42 lr: 0.000956 loss: 4.0467 (3.8621) grad_norm: 1.0135 (inf) time: 0.5035 [2021-03-25 10:32:57 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 710/1251] eta: 0:04:36 lr: 0.000956 loss: 3.9229 (3.8585) grad_norm: 1.0146 (inf) time: 0.5048 [2021-03-25 10:33:02 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 720/1251] eta: 0:04:31 lr: 0.000956 loss: 3.7933 (3.8575) grad_norm: 0.9620 (inf) time: 0.5080 [2021-03-25 10:33:07 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 730/1251] eta: 0:04:26 lr: 0.000956 loss: 3.9917 (3.8578) grad_norm: 0.9603 (inf) time: 0.5070 [2021-03-25 10:33:13 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 740/1251] eta: 0:04:21 lr: 0.000956 loss: 3.8874 (3.8544) grad_norm: 0.9937 (inf) time: 0.5252 [2021-03-25 10:33:18 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 750/1251] eta: 0:04:16 lr: 0.000956 loss: 3.5138 (3.8522) grad_norm: 1.0283 (inf) time: 0.5327 [2021-03-25 10:33:23 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 760/1251] eta: 0:04:11 lr: 0.000956 loss: 3.8152 (3.8501) grad_norm: 0.9761 (inf) time: 0.5168 [2021-03-25 10:33:28 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 770/1251] eta: 0:04:06 lr: 0.000956 loss: 4.0793 (3.8513) grad_norm: 0.9247 (inf) time: 0.5106 [2021-03-25 10:33:34 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 780/1251] eta: 0:04:01 lr: 0.000956 loss: 4.0641 (3.8490) grad_norm: 0.9604 (inf) time: 0.5145 [2021-03-25 10:33:39 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 790/1251] eta: 0:03:56 lr: 0.000956 loss: 4.0641 (3.8529) grad_norm: 0.9990 (inf) time: 0.5091 [2021-03-25 10:33:44 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 800/1251] eta: 0:03:50 lr: 0.000956 loss: 4.1474 (3.8517) grad_norm: 0.9871 (inf) time: 0.5001 [2021-03-25 10:33:49 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 810/1251] eta: 0:03:45 lr: 0.000956 loss: 4.0889 (3.8541) grad_norm: 0.9288 (inf) time: 0.5000 [2021-03-25 10:33:54 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 820/1251] eta: 0:03:40 lr: 0.000956 loss: 4.0889 (3.8549) grad_norm: 0.9790 (inf) time: 0.5017 [2021-03-25 10:33:59 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 830/1251] eta: 0:03:35 lr: 0.000956 loss: 3.9827 (3.8568) grad_norm: 1.0042 (inf) time: 0.5051 [2021-03-25 10:34:04 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 840/1251] eta: 0:03:30 lr: 0.000956 loss: 3.9827 (3.8594) grad_norm: 0.9606 (inf) time: 0.5070 [2021-03-25 10:34:09 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 850/1251] eta: 0:03:25 lr: 0.000956 loss: 4.0784 (3.8589) grad_norm: 0.9606 (inf) time: 0.5056 [2021-03-25 10:34:14 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 860/1251] eta: 0:03:20 lr: 0.000956 loss: 4.0919 (3.8616) grad_norm: 1.0004 (inf) time: 0.5031 [2021-03-25 10:34:19 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 870/1251] eta: 0:03:14 lr: 0.000956 loss: 4.0696 (3.8621) grad_norm: 0.9928 (inf) time: 0.5017 [2021-03-25 10:34:24 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 880/1251] eta: 0:03:09 lr: 0.000956 loss: 3.9269 (3.8639) grad_norm: 0.9268 (inf) time: 0.5007 [2021-03-25 10:34:29 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 890/1251] eta: 0:03:04 lr: 0.000956 loss: 3.9046 (3.8633) grad_norm: 0.9992 (inf) time: 0.5028 [2021-03-25 10:34:34 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 900/1251] eta: 0:02:59 lr: 0.000956 loss: 3.9782 (3.8643) grad_norm: 1.0114 (inf) time: 0.5041 [2021-03-25 10:34:39 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 910/1251] eta: 0:02:54 lr: 0.000956 loss: 4.0094 (3.8657) grad_norm: 0.9748 (inf) time: 0.5079 [2021-03-25 10:34:44 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 920/1251] eta: 0:02:49 lr: 0.000956 loss: 3.9829 (3.8655) grad_norm: 1.0200 (inf) time: 0.5085 [2021-03-25 10:34:49 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 930/1251] eta: 0:02:44 lr: 0.000956 loss: 3.8695 (3.8644) grad_norm: 1.0607 (inf) time: 0.5081 [2021-03-25 10:34:54 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 940/1251] eta: 0:02:38 lr: 0.000956 loss: 4.0301 (3.8659) grad_norm: 1.0208 (inf) time: 0.5069 [2021-03-25 10:34:59 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 950/1251] eta: 0:02:33 lr: 0.000956 loss: 3.9719 (3.8625) grad_norm: 0.9643 (inf) time: 0.5107 [2021-03-25 10:35:05 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 960/1251] eta: 0:02:28 lr: 0.000956 loss: 3.6265 (3.8608) grad_norm: 0.9335 (inf) time: 0.5183 [2021-03-25 10:35:10 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 970/1251] eta: 0:02:23 lr: 0.000956 loss: 3.7607 (3.8598) grad_norm: 0.9434 (inf) time: 0.5114 [2021-03-25 10:35:15 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 980/1251] eta: 0:02:18 lr: 0.000956 loss: 3.9651 (3.8618) grad_norm: 0.9507 (inf) time: 0.5020 [2021-03-25 10:35:20 swin_small_patch4_window7_224] INFO: Epoch: [40] [ 990/1251] eta: 0:02:13 lr: 0.000956 loss: 3.9651 (3.8616) grad_norm: 0.9441 (inf) time: 0.5026 [2021-03-25 10:35:25 swin_small_patch4_window7_224] INFO: Epoch: [40] [1000/1251] eta: 0:02:08 lr: 0.000956 loss: 4.0401 (3.8646) grad_norm: 0.9815 (inf) time: 0.5028 [2021-03-25 10:35:30 swin_small_patch4_window7_224] INFO: Epoch: [40] [1010/1251] eta: 0:02:03 lr: 0.000955 loss: 4.0858 (3.8662) grad_norm: 1.0373 (inf) time: 0.5002 [2021-03-25 10:35:35 swin_small_patch4_window7_224] INFO: Epoch: [40] [1020/1251] eta: 0:01:57 lr: 0.000955 loss: 4.0145 (3.8676) grad_norm: 1.1134 (inf) time: 0.4993 [2021-03-25 10:35:40 swin_small_patch4_window7_224] INFO: Epoch: [40] [1030/1251] eta: 0:01:52 lr: 0.000955 loss: 3.9801 (3.8670) grad_norm: 1.0129 (inf) time: 0.5038 [2021-03-25 10:35:45 swin_small_patch4_window7_224] INFO: Epoch: [40] [1040/1251] eta: 0:01:47 lr: 0.000955 loss: 3.7974 (3.8657) grad_norm: 0.9665 (inf) time: 0.5060 [2021-03-25 10:35:50 swin_small_patch4_window7_224] INFO: Epoch: [40] [1050/1251] eta: 0:01:42 lr: 0.000955 loss: 3.9707 (3.8666) grad_norm: 0.9684 (inf) time: 0.5012 [2021-03-25 10:35:55 swin_small_patch4_window7_224] INFO: Epoch: [40] [1060/1251] eta: 0:01:37 lr: 0.000955 loss: 3.9707 (3.8669) grad_norm: 0.9717 (inf) time: 0.4989 [2021-03-25 10:36:00 swin_small_patch4_window7_224] INFO: Epoch: [40] [1070/1251] eta: 0:01:32 lr: 0.000955 loss: 3.9248 (3.8675) grad_norm: 1.0076 (inf) time: 0.5098 [2021-03-25 10:36:05 swin_small_patch4_window7_224] INFO: Epoch: [40] [1080/1251] eta: 0:01:27 lr: 0.000955 loss: 3.9569 (3.8671) grad_norm: 0.9798 (inf) time: 0.5097 [2021-03-25 10:36:10 swin_small_patch4_window7_224] INFO: Epoch: [40] [1090/1251] eta: 0:01:22 lr: 0.000955 loss: 3.9288 (3.8633) grad_norm: 0.9665 (inf) time: 0.5014 [2021-03-25 10:36:15 swin_small_patch4_window7_224] INFO: Epoch: [40] [1100/1251] eta: 0:01:17 lr: 0.000955 loss: 3.7387 (3.8615) grad_norm: 0.9711 (inf) time: 0.5010 [2021-03-25 10:36:20 swin_small_patch4_window7_224] INFO: Epoch: [40] [1110/1251] eta: 0:01:11 lr: 0.000955 loss: 3.9800 (3.8609) grad_norm: 0.9729 (inf) time: 0.5066 [2021-03-25 10:36:25 swin_small_patch4_window7_224] INFO: Epoch: [40] [1120/1251] eta: 0:01:06 lr: 0.000955 loss: 4.0116 (3.8611) grad_norm: 0.9729 (inf) time: 0.5086 [2021-03-25 10:36:30 swin_small_patch4_window7_224] INFO: Epoch: [40] [1130/1251] eta: 0:01:01 lr: 0.000955 loss: 3.9841 (3.8632) grad_norm: 0.9773 (inf) time: 0.5048 [2021-03-25 10:36:35 swin_small_patch4_window7_224] INFO: Epoch: [40] [1140/1251] eta: 0:00:56 lr: 0.000955 loss: 3.9302 (3.8614) grad_norm: 1.0168 (inf) time: 0.5061 [2021-03-25 10:36:40 swin_small_patch4_window7_224] INFO: Epoch: [40] [1150/1251] eta: 0:00:51 lr: 0.000955 loss: 3.9134 (3.8619) grad_norm: 1.0536 (inf) time: 0.5025 [2021-03-25 10:36:45 swin_small_patch4_window7_224] INFO: Epoch: [40] [1160/1251] eta: 0:00:46 lr: 0.000955 loss: 3.9818 (3.8629) grad_norm: 1.0522 (inf) time: 0.5006 [2021-03-25 10:36:50 swin_small_patch4_window7_224] INFO: Epoch: [40] [1170/1251] eta: 0:00:41 lr: 0.000955 loss: 3.7282 (3.8600) grad_norm: 0.9872 (inf) time: 0.5045 [2021-03-25 10:36:55 swin_small_patch4_window7_224] INFO: Epoch: [40] [1180/1251] eta: 0:00:36 lr: 0.000955 loss: 3.4527 (3.8583) grad_norm: 0.9661 (inf) time: 0.5027 [2021-03-25 10:37:01 swin_small_patch4_window7_224] INFO: Epoch: [40] [1190/1251] eta: 0:00:31 lr: 0.000955 loss: 3.4099 (3.8552) grad_norm: 0.9950 (inf) time: 0.5058 [2021-03-25 10:37:06 swin_small_patch4_window7_224] INFO: Epoch: [40] [1200/1251] eta: 0:00:25 lr: 0.000955 loss: 3.7693 (3.8549) grad_norm: 1.0066 (inf) time: 0.5083 [2021-03-25 10:37:11 swin_small_patch4_window7_224] INFO: Epoch: [40] [1210/1251] eta: 0:00:20 lr: 0.000955 loss: 3.6009 (3.8513) grad_norm: 1.0174 (inf) time: 0.5065 [2021-03-25 10:37:16 swin_small_patch4_window7_224] INFO: Epoch: [40] [1220/1251] eta: 0:00:15 lr: 0.000955 loss: 3.8358 (3.8515) grad_norm: 1.0225 (inf) time: 0.5030 [2021-03-25 10:37:21 swin_small_patch4_window7_224] INFO: Epoch: [40] [1230/1251] eta: 0:00:10 lr: 0.000955 loss: 3.9174 (3.8522) grad_norm: 0.9718 (inf) time: 0.4996 [2021-03-25 10:37:26 swin_small_patch4_window7_224] INFO: Epoch: [40] [1240/1251] eta: 0:00:05 lr: 0.000955 loss: 3.8450 (3.8518) grad_norm: 0.9494 (inf) time: 0.4996 [2021-03-25 10:37:31 swin_small_patch4_window7_224] INFO: Epoch: [40] [1250/1251] eta: 0:00:00 lr: 0.000955 loss: 3.9580 (3.8513) grad_norm: 0.9864 (inf) time: 0.4975 [2021-03-25 10:38:11 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 1.0984 (1.0984) acc1: 67.1875 (67.1875) acc5: 90.6250 (90.6250) [2021-03-25 10:38:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.2474 (1.2606) acc1: 70.3125 (70.8807) acc5: 90.6250 (90.0568) [2021-03-25 10:38:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.2715 (1.2799) acc1: 70.3125 (70.6101) acc5: 89.0625 (89.9554) [2021-03-25 10:38:14 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.2362 (1.2495) acc1: 71.8750 (71.2198) acc5: 89.0625 (90.7762) [2021-03-25 10:38:15 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2362 (1.2831) acc1: 70.3125 (70.3887) acc5: 92.1875 (90.2058) [2021-03-25 10:38:16 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2805 (1.2818) acc1: 67.9245 (70.0480) acc5: 89.0625 (90.4000) [2021-03-25 10:38:19 swin_small_patch4_window7_224] INFO: * Acc@1 70.906 Acc@5 90.738 loss 1.257 [2021-03-25 10:38:19 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 70.9% [2021-03-25 10:38:19 swin_small_patch4_window7_224] INFO: Max accuracy: 70.91% [2021-03-25 10:38:23 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 0/1251] eta: 1:22:58 lr: 0.000955 loss: 4.1363 (4.1363) grad_norm: 1.0561 (1.0561) time: 3.9796 [2021-03-25 10:38:28 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 10/1251] eta: 0:17:35 lr: 0.000955 loss: 4.1363 (4.0273) grad_norm: 0.9727 (0.9718) time: 0.8503 [2021-03-25 10:38:33 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 20/1251] eta: 0:14:08 lr: 0.000955 loss: 3.9737 (3.9607) grad_norm: 0.9651 (0.9945) time: 0.5250 [2021-03-25 10:38:38 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 30/1251] eta: 0:12:52 lr: 0.000955 loss: 3.3926 (3.7101) grad_norm: 1.0142 (1.0104) time: 0.5126 [2021-03-25 10:38:43 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 40/1251] eta: 0:12:12 lr: 0.000955 loss: 3.3876 (3.7449) grad_norm: 1.0425 (1.0178) time: 0.5158 [2021-03-25 10:38:49 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 50/1251] eta: 0:11:42 lr: 0.000955 loss: 4.0204 (3.7886) grad_norm: 1.0587 (1.0220) time: 0.5112 [2021-03-25 10:38:54 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 60/1251] eta: 0:11:26 lr: 0.000955 loss: 3.8365 (3.7872) grad_norm: 1.0423 (1.0295) time: 0.5183 [2021-03-25 10:38:59 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 70/1251] eta: 0:11:09 lr: 0.000955 loss: 3.8095 (3.8230) grad_norm: 1.0033 (1.0338) time: 0.5211 [2021-03-25 10:39:04 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 80/1251] eta: 0:10:55 lr: 0.000955 loss: 3.9174 (3.8210) grad_norm: 1.0193 (1.0403) time: 0.5099 [2021-03-25 10:39:09 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 90/1251] eta: 0:10:44 lr: 0.000955 loss: 3.8066 (3.8010) grad_norm: 1.0424 (1.0433) time: 0.5124 [2021-03-25 10:39:14 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 100/1251] eta: 0:10:31 lr: 0.000955 loss: 3.8066 (3.8109) grad_norm: 0.9810 (1.0411) time: 0.5043 [2021-03-25 10:39:19 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 110/1251] eta: 0:10:22 lr: 0.000955 loss: 4.0314 (3.8222) grad_norm: 0.9997 (1.0418) time: 0.5009 [2021-03-25 10:39:24 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 120/1251] eta: 0:10:13 lr: 0.000955 loss: 3.7658 (3.8155) grad_norm: 0.9997 (1.0406) time: 0.5077 [2021-03-25 10:39:29 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 130/1251] eta: 0:10:04 lr: 0.000955 loss: 3.9381 (3.8374) grad_norm: 0.9689 (1.0356) time: 0.5047 [2021-03-25 10:39:34 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 140/1251] eta: 0:09:55 lr: 0.000955 loss: 4.1290 (3.8428) grad_norm: 0.9382 (1.0272) time: 0.5011 [2021-03-25 10:39:39 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 150/1251] eta: 0:09:47 lr: 0.000955 loss: 4.0347 (3.8473) grad_norm: 0.8988 (1.0193) time: 0.5009 [2021-03-25 10:39:44 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 160/1251] eta: 0:09:40 lr: 0.000955 loss: 3.8668 (3.8415) grad_norm: 0.8716 (1.0148) time: 0.5007 [2021-03-25 10:39:49 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 170/1251] eta: 0:09:33 lr: 0.000955 loss: 3.6816 (3.8255) grad_norm: 1.0213 (1.0162) time: 0.5026 [2021-03-25 10:39:55 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 180/1251] eta: 0:09:27 lr: 0.000955 loss: 3.7728 (3.8317) grad_norm: 1.0001 (1.0139) time: 0.5150 [2021-03-25 10:40:00 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 190/1251] eta: 0:09:21 lr: 0.000955 loss: 3.7034 (3.8181) grad_norm: 0.9634 (1.0149) time: 0.5155 [2021-03-25 10:40:05 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 200/1251] eta: 0:09:14 lr: 0.000955 loss: 3.5278 (3.8153) grad_norm: 1.0128 (1.0189) time: 0.5081 [2021-03-25 10:40:10 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 210/1251] eta: 0:09:08 lr: 0.000955 loss: 4.0047 (3.8257) grad_norm: 1.0382 (1.0213) time: 0.5074 [2021-03-25 10:40:15 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 220/1251] eta: 0:09:02 lr: 0.000955 loss: 4.0622 (3.8329) grad_norm: 1.0234 (1.0207) time: 0.5042 [2021-03-25 10:40:20 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 230/1251] eta: 0:08:55 lr: 0.000955 loss: 4.1017 (3.8358) grad_norm: 1.0365 (1.0235) time: 0.5054 [2021-03-25 10:40:25 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 240/1251] eta: 0:08:49 lr: 0.000955 loss: 4.0128 (3.8439) grad_norm: 1.0488 (1.0278) time: 0.5037 [2021-03-25 10:40:30 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 250/1251] eta: 0:08:43 lr: 0.000955 loss: 4.2748 (3.8549) grad_norm: 1.0410 (1.0280) time: 0.5056 [2021-03-25 10:40:35 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 260/1251] eta: 0:08:38 lr: 0.000955 loss: 3.9564 (3.8417) grad_norm: 1.0176 (1.0290) time: 0.5084 [2021-03-25 10:40:40 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 270/1251] eta: 0:08:31 lr: 0.000955 loss: 3.9564 (3.8478) grad_norm: 0.9891 (1.0272) time: 0.5032 [2021-03-25 10:40:45 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 280/1251] eta: 0:08:26 lr: 0.000955 loss: 3.7780 (3.8370) grad_norm: 0.9799 (1.0248) time: 0.5017 [2021-03-25 10:40:50 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 290/1251] eta: 0:08:20 lr: 0.000955 loss: 3.7292 (3.8394) grad_norm: 0.9799 (1.0247) time: 0.5032 [2021-03-25 10:40:55 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 300/1251] eta: 0:08:14 lr: 0.000955 loss: 4.0794 (3.8432) grad_norm: 0.9396 (1.0221) time: 0.5051 [2021-03-25 10:41:00 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 310/1251] eta: 0:08:09 lr: 0.000955 loss: 4.0284 (3.8459) grad_norm: 0.9912 (1.0227) time: 0.5117 [2021-03-25 10:41:06 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 320/1251] eta: 0:08:03 lr: 0.000955 loss: 4.2123 (3.8572) grad_norm: 1.0296 (1.0236) time: 0.5104 [2021-03-25 10:41:11 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 330/1251] eta: 0:07:57 lr: 0.000955 loss: 4.1665 (3.8514) grad_norm: 1.0077 (1.0237) time: 0.5028 [2021-03-25 10:41:16 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 340/1251] eta: 0:07:52 lr: 0.000954 loss: 3.9178 (3.8511) grad_norm: 1.0077 (1.0229) time: 0.5030 [2021-03-25 10:41:21 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 350/1251] eta: 0:07:46 lr: 0.000954 loss: 4.2055 (3.8616) grad_norm: 0.9827 (1.0212) time: 0.5061 [2021-03-25 10:41:26 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 360/1251] eta: 0:07:41 lr: 0.000954 loss: 4.1840 (3.8564) grad_norm: 0.9075 (1.0191) time: 0.5058 [2021-03-25 10:41:31 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 370/1251] eta: 0:07:35 lr: 0.000954 loss: 3.6488 (3.8483) grad_norm: 0.9795 (1.0185) time: 0.5003 [2021-03-25 10:41:36 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 380/1251] eta: 0:07:30 lr: 0.000954 loss: 3.8263 (3.8519) grad_norm: 0.9999 (1.0189) time: 0.5009 [2021-03-25 10:41:41 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 390/1251] eta: 0:07:24 lr: 0.000954 loss: 4.0734 (3.8546) grad_norm: 1.0837 (1.0219) time: 0.5021 [2021-03-25 10:41:46 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 400/1251] eta: 0:07:19 lr: 0.000954 loss: 4.0731 (3.8532) grad_norm: 1.0574 (1.0230) time: 0.5020 [2021-03-25 10:41:51 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 410/1251] eta: 0:07:14 lr: 0.000954 loss: 3.6668 (3.8447) grad_norm: 1.0047 (1.0231) time: 0.5080 [2021-03-25 10:41:56 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 420/1251] eta: 0:07:08 lr: 0.000954 loss: 3.6543 (3.8443) grad_norm: 0.9303 (1.0209) time: 0.5063 [2021-03-25 10:42:01 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 430/1251] eta: 0:07:03 lr: 0.000954 loss: 3.7990 (3.8426) grad_norm: 0.9130 (1.0194) time: 0.5021 [2021-03-25 10:42:06 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 440/1251] eta: 0:06:57 lr: 0.000954 loss: 3.7226 (3.8395) grad_norm: 0.9410 (1.0187) time: 0.5052 [2021-03-25 10:42:11 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 450/1251] eta: 0:06:52 lr: 0.000954 loss: 3.8216 (3.8430) grad_norm: 0.9718 (1.0192) time: 0.5068 [2021-03-25 10:42:16 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 460/1251] eta: 0:06:47 lr: 0.000954 loss: 4.1436 (3.8497) grad_norm: 1.0323 (1.0206) time: 0.5046 [2021-03-25 10:42:21 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 470/1251] eta: 0:06:41 lr: 0.000954 loss: 3.8929 (3.8438) grad_norm: 1.0225 (1.0208) time: 0.5054 [2021-03-25 10:42:26 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 480/1251] eta: 0:06:36 lr: 0.000954 loss: 3.4813 (3.8362) grad_norm: 0.9516 (1.0199) time: 0.5031 [2021-03-25 10:42:31 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 490/1251] eta: 0:06:31 lr: 0.000954 loss: 3.6719 (3.8344) grad_norm: 0.9509 (1.0204) time: 0.5036 [2021-03-25 10:42:36 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 500/1251] eta: 0:06:25 lr: 0.000954 loss: 3.7160 (3.8326) grad_norm: 1.0154 (1.0203) time: 0.5026 [2021-03-25 10:42:41 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 510/1251] eta: 0:06:20 lr: 0.000954 loss: 3.6405 (3.8287) grad_norm: 1.0362 (1.0210) time: 0.5006 [2021-03-25 10:42:46 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 520/1251] eta: 0:06:15 lr: 0.000954 loss: 3.8682 (3.8296) grad_norm: 1.0811 (1.0227) time: 0.5042 [2021-03-25 10:42:51 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 530/1251] eta: 0:06:10 lr: 0.000954 loss: 3.9005 (3.8290) grad_norm: 1.0417 (1.0231) time: 0.5034 [2021-03-25 10:42:57 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 540/1251] eta: 0:06:05 lr: 0.000954 loss: 3.7792 (3.8289) grad_norm: 1.0417 (1.0245) time: 0.5119 [2021-03-25 10:43:02 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 550/1251] eta: 0:06:00 lr: 0.000954 loss: 3.8380 (3.8285) grad_norm: 1.0310 (1.0236) time: 0.5246 [2021-03-25 10:43:07 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 560/1251] eta: 0:05:54 lr: 0.000954 loss: 4.0115 (3.8315) grad_norm: 0.9668 (1.0225) time: 0.5131 [2021-03-25 10:43:12 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 570/1251] eta: 0:05:49 lr: 0.000954 loss: 3.8186 (3.8299) grad_norm: 0.9875 (1.0226) time: 0.5001 [2021-03-25 10:43:17 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 580/1251] eta: 0:05:44 lr: 0.000954 loss: 3.7975 (3.8294) grad_norm: 0.9500 (1.0211) time: 0.5028 [2021-03-25 10:43:22 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 590/1251] eta: 0:05:39 lr: 0.000954 loss: 3.6842 (3.8277) grad_norm: 0.9190 (1.0206) time: 0.5105 [2021-03-25 10:43:27 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 600/1251] eta: 0:05:33 lr: 0.000954 loss: 4.0180 (3.8334) grad_norm: 1.0397 (1.0214) time: 0.5089 [2021-03-25 10:43:32 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 610/1251] eta: 0:05:28 lr: 0.000954 loss: 4.1668 (3.8359) grad_norm: 1.0156 (1.0209) time: 0.5078 [2021-03-25 10:43:37 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 620/1251] eta: 0:05:23 lr: 0.000954 loss: 3.8725 (3.8347) grad_norm: 0.9873 (1.0202) time: 0.5107 [2021-03-25 10:43:42 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 630/1251] eta: 0:05:18 lr: 0.000954 loss: 4.0088 (3.8371) grad_norm: 0.9520 (1.0194) time: 0.5081 [2021-03-25 10:43:47 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 640/1251] eta: 0:05:13 lr: 0.000954 loss: 4.0506 (3.8393) grad_norm: 0.9284 (1.0181) time: 0.5060 [2021-03-25 10:43:52 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 650/1251] eta: 0:05:08 lr: 0.000954 loss: 3.9674 (3.8407) grad_norm: 0.9211 (1.0180) time: 0.5043 [2021-03-25 10:43:57 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 660/1251] eta: 0:05:02 lr: 0.000954 loss: 3.9674 (3.8404) grad_norm: 0.9719 (1.0177) time: 0.5014 [2021-03-25 10:44:02 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 670/1251] eta: 0:04:57 lr: 0.000954 loss: 3.9258 (3.8406) grad_norm: 0.9874 (1.0180) time: 0.4994 [2021-03-25 10:44:07 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 680/1251] eta: 0:04:52 lr: 0.000954 loss: 3.8426 (3.8405) grad_norm: 0.9718 (1.0172) time: 0.5012 [2021-03-25 10:44:13 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 690/1251] eta: 0:04:47 lr: 0.000954 loss: 3.8459 (3.8417) grad_norm: 0.9479 (1.0167) time: 0.5051 [2021-03-25 10:44:18 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 700/1251] eta: 0:04:42 lr: 0.000954 loss: 3.7955 (3.8395) grad_norm: 0.9141 (1.0154) time: 0.5064 [2021-03-25 10:44:23 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 710/1251] eta: 0:04:36 lr: 0.000954 loss: 3.7530 (3.8406) grad_norm: 0.9141 (1.0148) time: 0.5034 [2021-03-25 10:44:28 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 720/1251] eta: 0:04:31 lr: 0.000954 loss: 4.0058 (3.8418) grad_norm: 0.9457 (1.0149) time: 0.5013 [2021-03-25 10:44:33 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 730/1251] eta: 0:04:26 lr: 0.000954 loss: 3.9964 (3.8424) grad_norm: 1.0302 (1.0155) time: 0.5138 [2021-03-25 10:44:38 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 740/1251] eta: 0:04:21 lr: 0.000954 loss: 3.8844 (3.8419) grad_norm: 1.0383 (1.0151) time: 0.5307 [2021-03-25 10:44:43 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 750/1251] eta: 0:04:16 lr: 0.000954 loss: 3.9432 (3.8449) grad_norm: 0.9651 (1.0157) time: 0.5199 [2021-03-25 10:44:48 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 760/1251] eta: 0:04:11 lr: 0.000954 loss: 3.9432 (3.8417) grad_norm: 0.9967 (1.0162) time: 0.5081 [2021-03-25 10:44:53 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 770/1251] eta: 0:04:06 lr: 0.000954 loss: 3.8140 (3.8428) grad_norm: 0.9967 (1.0158) time: 0.5047 [2021-03-25 10:44:59 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 780/1251] eta: 0:04:01 lr: 0.000954 loss: 3.9577 (3.8399) grad_norm: 0.9221 (1.0146) time: 0.5103 [2021-03-25 10:45:04 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 790/1251] eta: 0:03:55 lr: 0.000954 loss: 3.9577 (3.8426) grad_norm: 0.9182 (1.0139) time: 0.5167 [2021-03-25 10:45:09 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 800/1251] eta: 0:03:50 lr: 0.000954 loss: 3.8805 (3.8408) grad_norm: 0.9937 (1.0139) time: 0.5156 [2021-03-25 10:45:14 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 810/1251] eta: 0:03:45 lr: 0.000954 loss: 3.9226 (3.8415) grad_norm: 1.0568 (1.0151) time: 0.5114 [2021-03-25 10:45:19 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 820/1251] eta: 0:03:40 lr: 0.000954 loss: 3.9226 (3.8429) grad_norm: 1.0608 (1.0155) time: 0.5030 [2021-03-25 10:45:24 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 830/1251] eta: 0:03:35 lr: 0.000954 loss: 4.0748 (3.8461) grad_norm: 1.0486 (1.0160) time: 0.5034 [2021-03-25 10:45:29 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 840/1251] eta: 0:03:30 lr: 0.000954 loss: 4.1620 (3.8498) grad_norm: 1.0714 (1.0165) time: 0.5050 [2021-03-25 10:45:34 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 850/1251] eta: 0:03:25 lr: 0.000954 loss: 4.0405 (3.8520) grad_norm: 0.9857 (1.0160) time: 0.5051 [2021-03-25 10:45:39 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 860/1251] eta: 0:03:19 lr: 0.000954 loss: 4.0249 (3.8524) grad_norm: 0.9857 (1.0158) time: 0.5035 [2021-03-25 10:45:44 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 870/1251] eta: 0:03:14 lr: 0.000954 loss: 3.9649 (3.8544) grad_norm: 0.9398 (1.0149) time: 0.4973 [2021-03-25 10:45:49 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 880/1251] eta: 0:03:09 lr: 0.000954 loss: 3.9649 (3.8564) grad_norm: 0.9350 (1.0147) time: 0.4991 [2021-03-25 10:45:54 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 890/1251] eta: 0:03:04 lr: 0.000954 loss: 3.9465 (3.8570) grad_norm: 0.9825 (1.0153) time: 0.5041 [2021-03-25 10:45:59 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 900/1251] eta: 0:02:59 lr: 0.000954 loss: 3.8068 (3.8553) grad_norm: 0.9409 (1.0141) time: 0.5040 [2021-03-25 10:46:04 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 910/1251] eta: 0:02:54 lr: 0.000953 loss: 3.9018 (3.8539) grad_norm: 0.9302 (1.0141) time: 0.5024 [2021-03-25 10:46:09 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 920/1251] eta: 0:02:49 lr: 0.000953 loss: 3.8933 (3.8534) grad_norm: 1.0337 (1.0147) time: 0.5036 [2021-03-25 10:46:14 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 930/1251] eta: 0:02:43 lr: 0.000953 loss: 4.0838 (3.8553) grad_norm: 1.0428 (1.0150) time: 0.5116 [2021-03-25 10:46:20 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 940/1251] eta: 0:02:38 lr: 0.000953 loss: 4.1383 (3.8599) grad_norm: 1.0428 (1.0159) time: 0.5107 [2021-03-25 10:46:25 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 950/1251] eta: 0:02:33 lr: 0.000953 loss: 3.9450 (3.8595) grad_norm: 1.0339 (1.0158) time: 0.5051 [2021-03-25 10:46:30 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 960/1251] eta: 0:02:28 lr: 0.000953 loss: 4.0086 (3.8631) grad_norm: 1.0014 (1.0158) time: 0.5078 [2021-03-25 10:46:35 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 970/1251] eta: 0:02:23 lr: 0.000953 loss: 4.0592 (3.8616) grad_norm: 1.0055 (1.0158) time: 0.5101 [2021-03-25 10:46:40 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 980/1251] eta: 0:02:18 lr: 0.000953 loss: 3.7239 (3.8602) grad_norm: 0.9806 (1.0150) time: 0.5040 [2021-03-25 10:46:45 swin_small_patch4_window7_224] INFO: Epoch: [41] [ 990/1251] eta: 0:02:13 lr: 0.000953 loss: 3.8573 (3.8583) grad_norm: 0.9806 (1.0149) time: 0.5045 [2021-03-25 10:46:50 swin_small_patch4_window7_224] INFO: Epoch: [41] [1000/1251] eta: 0:02:08 lr: 0.000953 loss: 3.7646 (3.8574) grad_norm: 1.0502 (1.0154) time: 0.5097 [2021-03-25 10:46:55 swin_small_patch4_window7_224] INFO: Epoch: [41] [1010/1251] eta: 0:02:03 lr: 0.000953 loss: 3.8012 (3.8581) grad_norm: 1.0173 (1.0155) time: 0.5061 [2021-03-25 10:47:00 swin_small_patch4_window7_224] INFO: Epoch: [41] [1020/1251] eta: 0:01:57 lr: 0.000953 loss: 4.1763 (3.8615) grad_norm: 0.9328 (1.0146) time: 0.5026 [2021-03-25 10:47:05 swin_small_patch4_window7_224] INFO: Epoch: [41] [1030/1251] eta: 0:01:52 lr: 0.000953 loss: 4.0722 (3.8617) grad_norm: 0.9274 (1.0138) time: 0.5012 [2021-03-25 10:47:10 swin_small_patch4_window7_224] INFO: Epoch: [41] [1040/1251] eta: 0:01:47 lr: 0.000953 loss: 3.8954 (3.8613) grad_norm: 0.9806 (1.0144) time: 0.5023 [2021-03-25 10:47:15 swin_small_patch4_window7_224] INFO: Epoch: [41] [1050/1251] eta: 0:01:42 lr: 0.000953 loss: 3.8137 (3.8582) grad_norm: 1.0801 (1.0151) time: 0.5078 [2021-03-25 10:47:20 swin_small_patch4_window7_224] INFO: Epoch: [41] [1060/1251] eta: 0:01:37 lr: 0.000953 loss: 3.6822 (3.8564) grad_norm: 1.0723 (1.0154) time: 0.5100 [2021-03-25 10:47:25 swin_small_patch4_window7_224] INFO: Epoch: [41] [1070/1251] eta: 0:01:32 lr: 0.000953 loss: 3.7292 (3.8562) grad_norm: 1.0229 (1.0156) time: 0.5119 [2021-03-25 10:47:30 swin_small_patch4_window7_224] INFO: Epoch: [41] [1080/1251] eta: 0:01:27 lr: 0.000953 loss: 4.0075 (3.8587) grad_norm: 0.9708 (1.0149) time: 0.5087 [2021-03-25 10:47:35 swin_small_patch4_window7_224] INFO: Epoch: [41] [1090/1251] eta: 0:01:22 lr: 0.000953 loss: 4.0548 (3.8594) grad_norm: 0.9510 (1.0143) time: 0.5005 [2021-03-25 10:47:40 swin_small_patch4_window7_224] INFO: Epoch: [41] [1100/1251] eta: 0:01:17 lr: 0.000953 loss: 4.0869 (3.8612) grad_norm: 0.9935 (1.0144) time: 0.5004 [2021-03-25 10:47:45 swin_small_patch4_window7_224] INFO: Epoch: [41] [1110/1251] eta: 0:01:11 lr: 0.000953 loss: 4.1035 (3.8609) grad_norm: 1.0121 (1.0145) time: 0.5020 [2021-03-25 10:47:51 swin_small_patch4_window7_224] INFO: Epoch: [41] [1120/1251] eta: 0:01:06 lr: 0.000953 loss: 4.0683 (3.8625) grad_norm: 1.0234 (1.0148) time: 0.5082 [2021-03-25 10:47:56 swin_small_patch4_window7_224] INFO: Epoch: [41] [1130/1251] eta: 0:01:01 lr: 0.000953 loss: 4.0683 (3.8629) grad_norm: 1.0148 (1.0148) time: 0.5079 [2021-03-25 10:48:01 swin_small_patch4_window7_224] INFO: Epoch: [41] [1140/1251] eta: 0:00:56 lr: 0.000953 loss: 3.8964 (3.8626) grad_norm: 0.9303 (1.0145) time: 0.5048 [2021-03-25 10:48:06 swin_small_patch4_window7_224] INFO: Epoch: [41] [1150/1251] eta: 0:00:51 lr: 0.000953 loss: 3.8937 (3.8630) grad_norm: 0.9479 (1.0143) time: 0.5057 [2021-03-25 10:48:11 swin_small_patch4_window7_224] INFO: Epoch: [41] [1160/1251] eta: 0:00:46 lr: 0.000953 loss: 3.9151 (3.8630) grad_norm: 0.9798 (1.0140) time: 0.5035 [2021-03-25 10:48:16 swin_small_patch4_window7_224] INFO: Epoch: [41] [1170/1251] eta: 0:00:41 lr: 0.000953 loss: 4.0079 (3.8641) grad_norm: 0.9521 (1.0140) time: 0.5017 [2021-03-25 10:48:21 swin_small_patch4_window7_224] INFO: Epoch: [41] [1180/1251] eta: 0:00:36 lr: 0.000953 loss: 4.0270 (3.8658) grad_norm: 0.9467 (1.0137) time: 0.5080 [2021-03-25 10:48:26 swin_small_patch4_window7_224] INFO: Epoch: [41] [1190/1251] eta: 0:00:31 lr: 0.000953 loss: 4.0270 (3.8649) grad_norm: 0.9948 (1.0136) time: 0.5096 [2021-03-25 10:48:31 swin_small_patch4_window7_224] INFO: Epoch: [41] [1200/1251] eta: 0:00:25 lr: 0.000953 loss: 3.7439 (3.8626) grad_norm: 1.0240 (1.0139) time: 0.5016 [2021-03-25 10:48:36 swin_small_patch4_window7_224] INFO: Epoch: [41] [1210/1251] eta: 0:00:20 lr: 0.000953 loss: 3.5961 (3.8617) grad_norm: 1.0672 (1.0147) time: 0.4990 [2021-03-25 10:48:41 swin_small_patch4_window7_224] INFO: Epoch: [41] [1220/1251] eta: 0:00:15 lr: 0.000953 loss: 3.6515 (3.8619) grad_norm: 1.0521 (1.0151) time: 0.5023 [2021-03-25 10:48:46 swin_small_patch4_window7_224] INFO: Epoch: [41] [1230/1251] eta: 0:00:10 lr: 0.000953 loss: 3.8768 (3.8614) grad_norm: 0.9936 (1.0146) time: 0.5090 [2021-03-25 10:48:51 swin_small_patch4_window7_224] INFO: Epoch: [41] [1240/1251] eta: 0:00:05 lr: 0.000953 loss: 3.9951 (3.8619) grad_norm: 0.9487 (1.0142) time: 0.5066 [2021-03-25 10:48:56 swin_small_patch4_window7_224] INFO: Epoch: [41] [1250/1251] eta: 0:00:00 lr: 0.000953 loss: 4.0006 (3.8626) grad_norm: 0.9111 (1.0134) time: 0.5043 [2021-03-25 10:49:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:35 loss: 1.1850 (1.1850) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.7500) [2021-03-25 10:49:03 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.2355 (1.2634) acc1: 68.7500 (69.4602) acc5: 92.1875 (91.0511) [2021-03-25 10:49:06 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.2355 (1.2460) acc1: 68.7500 (70.2381) acc5: 90.6250 (90.9226) [2021-03-25 10:49:08 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1999 (1.2298) acc1: 70.3125 (70.4637) acc5: 90.6250 (90.9274) [2021-03-25 10:49:10 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2850 (1.2463) acc1: 70.3125 (70.1982) acc5: 90.6250 (90.6250) [2021-03-25 10:49:11 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2850 (1.2515) acc1: 70.3125 (70.2720) acc5: 90.6250 (90.6240) [2021-03-25 10:49:13 swin_small_patch4_window7_224] INFO: * Acc@1 71.330 Acc@5 90.990 loss 1.224 [2021-03-25 10:49:13 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.3% [2021-03-25 10:49:13 swin_small_patch4_window7_224] INFO: Max accuracy: 71.33% [2021-03-25 10:49:17 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 0/1251] eta: 1:34:23 lr: 0.000953 loss: 3.8035 (3.8035) grad_norm: 1.0378 (1.0378) time: 4.5273 [2021-03-25 10:49:22 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 10/1251] eta: 0:18:15 lr: 0.000953 loss: 4.0456 (4.0418) grad_norm: 1.0771 (1.0631) time: 0.8830 [2021-03-25 10:49:28 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 20/1251] eta: 0:14:27 lr: 0.000953 loss: 4.1469 (4.0795) grad_norm: 1.0385 (1.0527) time: 0.5139 [2021-03-25 10:49:33 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 30/1251] eta: 0:13:01 lr: 0.000953 loss: 4.0283 (3.9962) grad_norm: 0.9860 (1.0450) time: 0.5070 [2021-03-25 10:49:38 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 40/1251] eta: 0:12:17 lr: 0.000953 loss: 4.0351 (4.0395) grad_norm: 0.9437 (1.0256) time: 0.5090 [2021-03-25 10:49:43 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 50/1251] eta: 0:11:47 lr: 0.000953 loss: 4.0862 (3.9883) grad_norm: 0.9182 (1.0085) time: 0.5093 [2021-03-25 10:49:48 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 60/1251] eta: 0:11:25 lr: 0.000953 loss: 3.8920 (3.9458) grad_norm: 0.9458 (1.0121) time: 0.5060 [2021-03-25 10:49:53 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 70/1251] eta: 0:11:07 lr: 0.000953 loss: 4.1143 (3.9591) grad_norm: 1.0151 (1.0149) time: 0.5041 [2021-03-25 10:49:58 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 80/1251] eta: 0:10:52 lr: 0.000953 loss: 3.8909 (3.9315) grad_norm: 1.0003 (1.0188) time: 0.5018 [2021-03-25 10:50:03 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 90/1251] eta: 0:10:40 lr: 0.000953 loss: 3.7637 (3.9010) grad_norm: 0.9937 (1.0174) time: 0.5026 [2021-03-25 10:50:08 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 100/1251] eta: 0:10:28 lr: 0.000953 loss: 3.7800 (3.9120) grad_norm: 1.0251 (1.0411) time: 0.4983 [2021-03-25 10:50:13 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 110/1251] eta: 0:10:19 lr: 0.000953 loss: 3.9752 (3.8857) grad_norm: 1.0016 (1.0384) time: 0.5057 [2021-03-25 10:50:18 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 120/1251] eta: 0:10:10 lr: 0.000953 loss: 3.3414 (3.8361) grad_norm: 0.9518 (1.0347) time: 0.5108 [2021-03-25 10:50:23 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 130/1251] eta: 0:10:03 lr: 0.000953 loss: 3.4444 (3.8189) grad_norm: 0.9890 (1.0333) time: 0.5108 [2021-03-25 10:50:28 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 140/1251] eta: 0:09:54 lr: 0.000953 loss: 3.8123 (3.8174) grad_norm: 0.9867 (1.0312) time: 0.5088 [2021-03-25 10:50:33 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 150/1251] eta: 0:09:47 lr: 0.000953 loss: 4.1005 (3.8294) grad_norm: 0.9648 (1.0272) time: 0.5024 [2021-03-25 10:50:38 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 160/1251] eta: 0:09:40 lr: 0.000953 loss: 4.0101 (3.8329) grad_norm: 0.9541 (1.0263) time: 0.5072 [2021-03-25 10:50:43 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 170/1251] eta: 0:09:33 lr: 0.000953 loss: 3.8753 (3.8296) grad_norm: 1.0109 (1.0301) time: 0.5054 [2021-03-25 10:50:49 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 180/1251] eta: 0:09:26 lr: 0.000953 loss: 4.0222 (3.8490) grad_norm: 1.0109 (1.0275) time: 0.5085 [2021-03-25 10:50:54 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 190/1251] eta: 0:09:20 lr: 0.000953 loss: 4.1107 (3.8499) grad_norm: 0.9902 (1.0282) time: 0.5144 [2021-03-25 10:50:59 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 200/1251] eta: 0:09:14 lr: 0.000953 loss: 3.9804 (3.8368) grad_norm: 1.0147 (1.0289) time: 0.5080 [2021-03-25 10:51:04 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 210/1251] eta: 0:09:08 lr: 0.000953 loss: 3.9251 (3.8408) grad_norm: 1.0147 (1.0290) time: 0.5064 [2021-03-25 10:51:09 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 220/1251] eta: 0:09:02 lr: 0.000953 loss: 3.9861 (3.8496) grad_norm: 0.9935 (1.0293) time: 0.5134 [2021-03-25 10:51:14 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 230/1251] eta: 0:08:56 lr: 0.000952 loss: 3.9466 (3.8414) grad_norm: 0.9354 (1.0258) time: 0.5108 [2021-03-25 10:51:19 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 240/1251] eta: 0:08:49 lr: 0.000952 loss: 3.5314 (3.8278) grad_norm: 1.0249 (inf) time: 0.5026 [2021-03-25 10:51:24 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 250/1251] eta: 0:08:43 lr: 0.000952 loss: 3.3326 (3.8247) grad_norm: 1.1188 (inf) time: 0.4986 [2021-03-25 10:51:29 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 260/1251] eta: 0:08:37 lr: 0.000952 loss: 3.6718 (3.8178) grad_norm: 1.0818 (inf) time: 0.4970 [2021-03-25 10:51:34 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 270/1251] eta: 0:08:31 lr: 0.000952 loss: 3.6486 (3.8206) grad_norm: 1.0492 (inf) time: 0.4981 [2021-03-25 10:51:39 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 280/1251] eta: 0:08:25 lr: 0.000952 loss: 3.5992 (3.8112) grad_norm: 0.9482 (inf) time: 0.5009 [2021-03-25 10:51:44 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 290/1251] eta: 0:08:19 lr: 0.000952 loss: 3.8091 (3.8125) grad_norm: 0.9441 (inf) time: 0.5048 [2021-03-25 10:51:49 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 300/1251] eta: 0:08:13 lr: 0.000952 loss: 3.8231 (3.8055) grad_norm: 0.9514 (inf) time: 0.5009 [2021-03-25 10:51:54 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 310/1251] eta: 0:08:08 lr: 0.000952 loss: 3.7193 (3.8041) grad_norm: 0.9671 (inf) time: 0.5031 [2021-03-25 10:51:59 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 320/1251] eta: 0:08:02 lr: 0.000952 loss: 3.8843 (3.8081) grad_norm: 1.0224 (inf) time: 0.5083 [2021-03-25 10:52:04 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 330/1251] eta: 0:07:56 lr: 0.000952 loss: 3.9854 (3.8114) grad_norm: 0.9729 (inf) time: 0.5024 [2021-03-25 10:52:09 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 340/1251] eta: 0:07:51 lr: 0.000952 loss: 3.9961 (3.8139) grad_norm: 0.9866 (inf) time: 0.4978 [2021-03-25 10:52:14 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 350/1251] eta: 0:07:45 lr: 0.000952 loss: 3.9580 (3.8163) grad_norm: 0.9860 (inf) time: 0.4992 [2021-03-25 10:52:19 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 360/1251] eta: 0:07:40 lr: 0.000952 loss: 3.7679 (3.8082) grad_norm: 0.9860 (inf) time: 0.5033 [2021-03-25 10:52:24 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 370/1251] eta: 0:07:34 lr: 0.000952 loss: 3.5188 (3.8036) grad_norm: 1.0240 (inf) time: 0.4982 [2021-03-25 10:52:29 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 380/1251] eta: 0:07:29 lr: 0.000952 loss: 3.8092 (3.8065) grad_norm: 1.0296 (inf) time: 0.5029 [2021-03-25 10:52:34 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 390/1251] eta: 0:07:23 lr: 0.000952 loss: 3.9177 (3.8101) grad_norm: 1.0262 (inf) time: 0.5097 [2021-03-25 10:52:39 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 400/1251] eta: 0:07:18 lr: 0.000952 loss: 3.9098 (3.8134) grad_norm: 1.0173 (inf) time: 0.5037 [2021-03-25 10:52:44 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 410/1251] eta: 0:07:13 lr: 0.000952 loss: 4.0341 (3.8137) grad_norm: 1.0173 (inf) time: 0.5028 [2021-03-25 10:52:49 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 420/1251] eta: 0:07:07 lr: 0.000952 loss: 3.9290 (3.8074) grad_norm: 0.9602 (inf) time: 0.4999 [2021-03-25 10:52:54 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 430/1251] eta: 0:07:02 lr: 0.000952 loss: 3.6504 (3.8039) grad_norm: 0.9691 (inf) time: 0.4985 [2021-03-25 10:52:59 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 440/1251] eta: 0:06:56 lr: 0.000952 loss: 4.0143 (3.8089) grad_norm: 1.0141 (inf) time: 0.5034 [2021-03-25 10:53:05 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 450/1251] eta: 0:06:51 lr: 0.000952 loss: 4.0826 (3.8076) grad_norm: 1.0491 (inf) time: 0.5035 [2021-03-25 10:53:10 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 460/1251] eta: 0:06:46 lr: 0.000952 loss: 4.0077 (3.8080) grad_norm: 1.0701 (inf) time: 0.5054 [2021-03-25 10:53:15 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 470/1251] eta: 0:06:40 lr: 0.000952 loss: 3.5949 (3.8064) grad_norm: 1.0854 (inf) time: 0.5041 [2021-03-25 10:53:20 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 480/1251] eta: 0:06:35 lr: 0.000952 loss: 3.8664 (3.8082) grad_norm: 1.0426 (inf) time: 0.5004 [2021-03-25 10:53:25 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 490/1251] eta: 0:06:30 lr: 0.000952 loss: 3.9090 (3.8122) grad_norm: 1.0127 (inf) time: 0.5035 [2021-03-25 10:53:30 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 500/1251] eta: 0:06:25 lr: 0.000952 loss: 3.9599 (3.8125) grad_norm: 1.0187 (inf) time: 0.5056 [2021-03-25 10:53:35 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 510/1251] eta: 0:06:19 lr: 0.000952 loss: 3.9490 (3.8081) grad_norm: 0.9600 (inf) time: 0.5043 [2021-03-25 10:53:40 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 520/1251] eta: 0:06:14 lr: 0.000952 loss: 4.1261 (3.8157) grad_norm: 0.9807 (inf) time: 0.5070 [2021-03-25 10:53:45 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 530/1251] eta: 0:06:09 lr: 0.000952 loss: 4.0787 (3.8138) grad_norm: 1.0045 (inf) time: 0.5090 [2021-03-25 10:53:50 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 540/1251] eta: 0:06:04 lr: 0.000952 loss: 3.6864 (3.8126) grad_norm: 0.9965 (inf) time: 0.5111 [2021-03-25 10:53:55 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 550/1251] eta: 0:05:59 lr: 0.000952 loss: 3.6864 (3.8095) grad_norm: 1.0510 (inf) time: 0.5208 [2021-03-25 10:54:00 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 560/1251] eta: 0:05:54 lr: 0.000952 loss: 3.9460 (3.8133) grad_norm: 0.9660 (inf) time: 0.5194 [2021-03-25 10:54:06 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 570/1251] eta: 0:05:49 lr: 0.000952 loss: 3.9681 (3.8120) grad_norm: 0.9830 (inf) time: 0.5080 [2021-03-25 10:54:11 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 580/1251] eta: 0:05:43 lr: 0.000952 loss: 3.9681 (3.8185) grad_norm: 1.0235 (inf) time: 0.5073 [2021-03-25 10:54:16 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 590/1251] eta: 0:05:38 lr: 0.000952 loss: 3.9420 (3.8153) grad_norm: 0.9804 (inf) time: 0.5065 [2021-03-25 10:54:21 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 600/1251] eta: 0:05:33 lr: 0.000952 loss: 3.7095 (3.8135) grad_norm: 0.9726 (inf) time: 0.5012 [2021-03-25 10:54:26 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 610/1251] eta: 0:05:28 lr: 0.000952 loss: 3.7212 (3.8151) grad_norm: 0.9692 (inf) time: 0.5046 [2021-03-25 10:54:31 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 620/1251] eta: 0:05:23 lr: 0.000952 loss: 4.1162 (3.8206) grad_norm: 0.9936 (inf) time: 0.5057 [2021-03-25 10:54:36 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 630/1251] eta: 0:05:17 lr: 0.000952 loss: 4.0349 (3.8145) grad_norm: 0.9883 (inf) time: 0.5039 [2021-03-25 10:54:41 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 640/1251] eta: 0:05:12 lr: 0.000952 loss: 3.8311 (3.8133) grad_norm: 0.9871 (inf) time: 0.5051 [2021-03-25 10:54:46 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 650/1251] eta: 0:05:07 lr: 0.000952 loss: 4.0020 (3.8162) grad_norm: 0.9953 (inf) time: 0.5056 [2021-03-25 10:54:51 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 660/1251] eta: 0:05:02 lr: 0.000952 loss: 3.9566 (3.8120) grad_norm: 1.0077 (inf) time: 0.5040 [2021-03-25 10:54:56 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 670/1251] eta: 0:04:57 lr: 0.000952 loss: 3.6278 (3.8082) grad_norm: 1.0219 (inf) time: 0.5010 [2021-03-25 10:55:01 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 680/1251] eta: 0:04:51 lr: 0.000952 loss: 3.8772 (3.8097) grad_norm: 1.0412 (inf) time: 0.5013 [2021-03-25 10:55:06 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 690/1251] eta: 0:04:46 lr: 0.000952 loss: 3.8980 (3.8096) grad_norm: 0.9365 (inf) time: 0.5039 [2021-03-25 10:55:11 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 700/1251] eta: 0:04:41 lr: 0.000952 loss: 3.7895 (3.8068) grad_norm: 0.9341 (inf) time: 0.5064 [2021-03-25 10:55:16 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 710/1251] eta: 0:04:36 lr: 0.000952 loss: 3.9080 (3.8069) grad_norm: 0.9747 (inf) time: 0.5121 [2021-03-25 10:55:21 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 720/1251] eta: 0:04:31 lr: 0.000952 loss: 3.9080 (3.8062) grad_norm: 0.9876 (inf) time: 0.5107 [2021-03-25 10:55:27 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 730/1251] eta: 0:04:26 lr: 0.000952 loss: 3.6018 (3.8043) grad_norm: 1.0467 (inf) time: 0.5167 [2021-03-25 10:55:32 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 740/1251] eta: 0:04:21 lr: 0.000952 loss: 3.9935 (3.8083) grad_norm: 1.0455 (inf) time: 0.5302 [2021-03-25 10:55:37 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 750/1251] eta: 0:04:16 lr: 0.000952 loss: 4.1125 (3.8099) grad_norm: 0.9833 (inf) time: 0.5232 [2021-03-25 10:55:42 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 760/1251] eta: 0:04:11 lr: 0.000952 loss: 3.9365 (3.8104) grad_norm: 0.9528 (inf) time: 0.5088 [2021-03-25 10:55:47 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 770/1251] eta: 0:04:06 lr: 0.000952 loss: 3.9210 (3.8110) grad_norm: 0.9746 (inf) time: 0.5062 [2021-03-25 10:55:52 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 780/1251] eta: 0:04:00 lr: 0.000952 loss: 3.7343 (3.8072) grad_norm: 0.9806 (inf) time: 0.5099 [2021-03-25 10:55:57 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 790/1251] eta: 0:03:55 lr: 0.000951 loss: 3.6812 (3.8052) grad_norm: 0.9904 (inf) time: 0.5071 [2021-03-25 10:56:02 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 800/1251] eta: 0:03:50 lr: 0.000951 loss: 3.9117 (3.8061) grad_norm: 1.0174 (inf) time: 0.5071 [2021-03-25 10:56:08 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 810/1251] eta: 0:03:45 lr: 0.000951 loss: 3.8992 (3.8066) grad_norm: 1.0338 (inf) time: 0.5064 [2021-03-25 10:56:13 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 820/1251] eta: 0:03:40 lr: 0.000951 loss: 3.8780 (3.8086) grad_norm: 1.0330 (inf) time: 0.5057 [2021-03-25 10:56:18 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 830/1251] eta: 0:03:35 lr: 0.000951 loss: 3.9752 (3.8096) grad_norm: 0.9900 (inf) time: 0.5026 [2021-03-25 10:56:23 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 840/1251] eta: 0:03:29 lr: 0.000951 loss: 3.5950 (3.8051) grad_norm: 0.9929 (inf) time: 0.4974 [2021-03-25 10:56:28 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 850/1251] eta: 0:03:24 lr: 0.000951 loss: 3.4463 (3.8037) grad_norm: 1.0054 (inf) time: 0.5029 [2021-03-25 10:56:33 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 860/1251] eta: 0:03:19 lr: 0.000951 loss: 3.7093 (3.8046) grad_norm: 1.0106 (inf) time: 0.5070 [2021-03-25 10:56:38 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 870/1251] eta: 0:03:14 lr: 0.000951 loss: 3.9509 (3.8056) grad_norm: 1.0594 (inf) time: 0.5083 [2021-03-25 10:56:43 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 880/1251] eta: 0:03:09 lr: 0.000951 loss: 3.9509 (3.8060) grad_norm: 0.9317 (inf) time: 0.5029 [2021-03-25 10:56:48 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 890/1251] eta: 0:03:04 lr: 0.000951 loss: 3.8429 (3.8067) grad_norm: 0.9382 (inf) time: 0.4975 [2021-03-25 10:56:53 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 900/1251] eta: 0:02:59 lr: 0.000951 loss: 3.9445 (3.8074) grad_norm: 0.9670 (inf) time: 0.4986 [2021-03-25 10:56:58 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 910/1251] eta: 0:02:54 lr: 0.000951 loss: 4.0672 (3.8080) grad_norm: 0.9938 (inf) time: 0.5011 [2021-03-25 10:57:03 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 920/1251] eta: 0:02:48 lr: 0.000951 loss: 3.7297 (3.8069) grad_norm: 1.0336 (inf) time: 0.5115 [2021-03-25 10:57:08 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 930/1251] eta: 0:02:43 lr: 0.000951 loss: 3.6638 (3.8074) grad_norm: 0.9894 (inf) time: 0.5183 [2021-03-25 10:57:13 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 940/1251] eta: 0:02:38 lr: 0.000951 loss: 3.6638 (3.8042) grad_norm: 0.9846 (inf) time: 0.5097 [2021-03-25 10:57:18 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 950/1251] eta: 0:02:33 lr: 0.000951 loss: 3.7954 (3.8071) grad_norm: 0.9338 (inf) time: 0.4998 [2021-03-25 10:57:23 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 960/1251] eta: 0:02:28 lr: 0.000951 loss: 4.1331 (3.8079) grad_norm: 0.9421 (inf) time: 0.5018 [2021-03-25 10:57:28 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 970/1251] eta: 0:02:23 lr: 0.000951 loss: 3.8424 (3.8064) grad_norm: 0.9950 (inf) time: 0.5038 [2021-03-25 10:57:33 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 980/1251] eta: 0:02:18 lr: 0.000951 loss: 3.7440 (3.8068) grad_norm: 1.0105 (inf) time: 0.5010 [2021-03-25 10:57:38 swin_small_patch4_window7_224] INFO: Epoch: [42] [ 990/1251] eta: 0:02:13 lr: 0.000951 loss: 4.0952 (3.8092) grad_norm: 0.9919 (inf) time: 0.4994 [2021-03-25 10:57:43 swin_small_patch4_window7_224] INFO: Epoch: [42] [1000/1251] eta: 0:02:07 lr: 0.000951 loss: 3.8478 (3.8079) grad_norm: 0.9072 (inf) time: 0.5013 [2021-03-25 10:57:48 swin_small_patch4_window7_224] INFO: Epoch: [42] [1010/1251] eta: 0:02:02 lr: 0.000951 loss: 3.8478 (3.8090) grad_norm: 0.9087 (inf) time: 0.5043 [2021-03-25 10:57:53 swin_small_patch4_window7_224] INFO: Epoch: [42] [1020/1251] eta: 0:01:57 lr: 0.000951 loss: 3.8537 (3.8074) grad_norm: 0.9483 (inf) time: 0.5062 [2021-03-25 10:57:58 swin_small_patch4_window7_224] INFO: Epoch: [42] [1030/1251] eta: 0:01:52 lr: 0.000951 loss: 3.8027 (3.8086) grad_norm: 1.0210 (inf) time: 0.5077 [2021-03-25 10:58:03 swin_small_patch4_window7_224] INFO: Epoch: [42] [1040/1251] eta: 0:01:47 lr: 0.000951 loss: 3.9612 (3.8086) grad_norm: 1.0220 (inf) time: 0.5052 [2021-03-25 10:58:09 swin_small_patch4_window7_224] INFO: Epoch: [42] [1050/1251] eta: 0:01:42 lr: 0.000951 loss: 3.9897 (3.8119) grad_norm: 0.9704 (inf) time: 0.5137 [2021-03-25 10:58:14 swin_small_patch4_window7_224] INFO: Epoch: [42] [1060/1251] eta: 0:01:37 lr: 0.000951 loss: 3.9112 (3.8128) grad_norm: 0.9772 (inf) time: 0.5134 [2021-03-25 10:58:19 swin_small_patch4_window7_224] INFO: Epoch: [42] [1070/1251] eta: 0:01:32 lr: 0.000951 loss: 3.7461 (3.8120) grad_norm: 0.9883 (inf) time: 0.5094 [2021-03-25 10:58:24 swin_small_patch4_window7_224] INFO: Epoch: [42] [1080/1251] eta: 0:01:27 lr: 0.000951 loss: 3.6666 (3.8108) grad_norm: 1.0169 (inf) time: 0.5088 [2021-03-25 10:58:29 swin_small_patch4_window7_224] INFO: Epoch: [42] [1090/1251] eta: 0:01:22 lr: 0.000951 loss: 3.6222 (3.8115) grad_norm: 0.9698 (inf) time: 0.5057 [2021-03-25 10:58:34 swin_small_patch4_window7_224] INFO: Epoch: [42] [1100/1251] eta: 0:01:16 lr: 0.000951 loss: 3.5283 (3.8079) grad_norm: 0.9679 (inf) time: 0.5074 [2021-03-25 10:58:39 swin_small_patch4_window7_224] INFO: Epoch: [42] [1110/1251] eta: 0:01:11 lr: 0.000951 loss: 3.5283 (3.8086) grad_norm: 0.9496 (inf) time: 0.5042 [2021-03-25 10:58:44 swin_small_patch4_window7_224] INFO: Epoch: [42] [1120/1251] eta: 0:01:06 lr: 0.000951 loss: 3.4933 (3.8059) grad_norm: 0.9496 (inf) time: 0.5105 [2021-03-25 10:58:49 swin_small_patch4_window7_224] INFO: Epoch: [42] [1130/1251] eta: 0:01:01 lr: 0.000951 loss: 3.6033 (3.8032) grad_norm: 0.9837 (inf) time: 0.5075 [2021-03-25 10:58:54 swin_small_patch4_window7_224] INFO: Epoch: [42] [1140/1251] eta: 0:00:56 lr: 0.000951 loss: 3.6475 (3.8038) grad_norm: 1.0222 (inf) time: 0.5000 [2021-03-25 10:58:59 swin_small_patch4_window7_224] INFO: Epoch: [42] [1150/1251] eta: 0:00:51 lr: 0.000951 loss: 4.0126 (3.8058) grad_norm: 0.9831 (inf) time: 0.5058 [2021-03-25 10:59:04 swin_small_patch4_window7_224] INFO: Epoch: [42] [1160/1251] eta: 0:00:46 lr: 0.000951 loss: 4.0720 (3.8070) grad_norm: 0.9567 (inf) time: 0.5059 [2021-03-25 10:59:09 swin_small_patch4_window7_224] INFO: Epoch: [42] [1170/1251] eta: 0:00:41 lr: 0.000951 loss: 3.9107 (3.8067) grad_norm: 0.9649 (inf) time: 0.5039 [2021-03-25 10:59:14 swin_small_patch4_window7_224] INFO: Epoch: [42] [1180/1251] eta: 0:00:36 lr: 0.000951 loss: 3.7905 (3.8054) grad_norm: 0.9857 (inf) time: 0.5015 [2021-03-25 10:59:20 swin_small_patch4_window7_224] INFO: Epoch: [42] [1190/1251] eta: 0:00:31 lr: 0.000951 loss: 3.9056 (3.8065) grad_norm: 0.9695 (inf) time: 0.5013 [2021-03-25 10:59:25 swin_small_patch4_window7_224] INFO: Epoch: [42] [1200/1251] eta: 0:00:25 lr: 0.000951 loss: 4.0502 (3.8079) grad_norm: 1.0129 (inf) time: 0.5071 [2021-03-25 10:59:30 swin_small_patch4_window7_224] INFO: Epoch: [42] [1210/1251] eta: 0:00:20 lr: 0.000951 loss: 3.9536 (3.8071) grad_norm: 1.0188 (inf) time: 0.5057 [2021-03-25 10:59:35 swin_small_patch4_window7_224] INFO: Epoch: [42] [1220/1251] eta: 0:00:15 lr: 0.000951 loss: 3.9514 (3.8081) grad_norm: 0.9794 (inf) time: 0.5004 [2021-03-25 10:59:40 swin_small_patch4_window7_224] INFO: Epoch: [42] [1230/1251] eta: 0:00:10 lr: 0.000951 loss: 3.7899 (3.8070) grad_norm: 0.9729 (inf) time: 0.5022 [2021-03-25 10:59:45 swin_small_patch4_window7_224] INFO: Epoch: [42] [1240/1251] eta: 0:00:05 lr: 0.000951 loss: 3.7899 (3.8069) grad_norm: 0.9847 (inf) time: 0.5027 [2021-03-25 10:59:50 swin_small_patch4_window7_224] INFO: Epoch: [42] [1250/1251] eta: 0:00:00 lr: 0.000951 loss: 3.7900 (3.8061) grad_norm: 1.0417 (inf) time: 0.5013 [2021-03-25 10:59:56 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:40 loss: 0.8658 (0.8658) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-25 10:59:58 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.2246 (1.2184) acc1: 71.8750 (70.5966) acc5: 90.6250 (91.7614) [2021-03-25 11:00:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.2453 (1.2388) acc1: 70.3125 (70.1637) acc5: 90.6250 (90.5506) [2021-03-25 11:00:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2331 (1.2245) acc1: 70.3125 (70.4133) acc5: 89.0625 (90.7762) [2021-03-25 11:00:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1205 (1.2124) acc1: 71.8750 (71.2271) acc5: 90.6250 (90.9299) [2021-03-25 11:00:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2331 (1.2287) acc1: 73.4375 (71.0400) acc5: 90.6250 (90.7520) [2021-03-25 11:00:08 swin_small_patch4_window7_224] INFO: * Acc@1 71.318 Acc@5 91.114 loss 1.205 [2021-03-25 11:00:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.3% [2021-03-25 11:00:08 swin_small_patch4_window7_224] INFO: Max accuracy: 71.33% [2021-03-25 11:00:12 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 0/1251] eta: 1:31:54 lr: 0.000951 loss: 4.0062 (4.0062) grad_norm: 0.9061 (0.9061) time: 4.4084 [2021-03-25 11:00:17 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 10/1251] eta: 0:17:43 lr: 0.000951 loss: 4.0062 (3.8494) grad_norm: 0.9669 (0.9802) time: 0.8569 [2021-03-25 11:00:22 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 20/1251] eta: 0:14:04 lr: 0.000951 loss: 3.8266 (3.7758) grad_norm: 0.9981 (inf) time: 0.4996 [2021-03-25 11:00:27 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 30/1251] eta: 0:12:46 lr: 0.000951 loss: 3.8570 (3.9349) grad_norm: 0.9981 (inf) time: 0.5013 [2021-03-25 11:00:32 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 40/1251] eta: 0:12:10 lr: 0.000951 loss: 4.0191 (3.9072) grad_norm: 0.9861 (inf) time: 0.5159 [2021-03-25 11:00:37 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 50/1251] eta: 0:11:41 lr: 0.000951 loss: 3.8959 (3.8867) grad_norm: 0.9609 (inf) time: 0.5162 [2021-03-25 11:00:42 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 60/1251] eta: 0:11:20 lr: 0.000951 loss: 3.8276 (3.8802) grad_norm: 1.0125 (inf) time: 0.5055 [2021-03-25 11:00:48 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 70/1251] eta: 0:11:04 lr: 0.000951 loss: 3.9646 (3.8581) grad_norm: 1.0532 (inf) time: 0.5074 [2021-03-25 11:00:53 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 80/1251] eta: 0:10:50 lr: 0.000951 loss: 3.8622 (3.8444) grad_norm: 1.0092 (inf) time: 0.5098 [2021-03-25 11:00:58 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 90/1251] eta: 0:10:39 lr: 0.000950 loss: 3.8622 (3.8499) grad_norm: 0.9811 (inf) time: 0.5117 [2021-03-25 11:01:03 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 100/1251] eta: 0:10:29 lr: 0.000950 loss: 3.9635 (3.8538) grad_norm: 1.0146 (inf) time: 0.5092 [2021-03-25 11:01:08 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 110/1251] eta: 0:10:20 lr: 0.000950 loss: 3.9635 (3.8561) grad_norm: 0.9349 (inf) time: 0.5099 [2021-03-25 11:01:13 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 120/1251] eta: 0:10:10 lr: 0.000950 loss: 3.7296 (3.8514) grad_norm: 0.9359 (inf) time: 0.5079 [2021-03-25 11:01:18 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 130/1251] eta: 0:10:02 lr: 0.000950 loss: 3.7533 (3.8435) grad_norm: 0.9461 (inf) time: 0.5011 [2021-03-25 11:01:23 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 140/1251] eta: 0:09:54 lr: 0.000950 loss: 3.8285 (3.8441) grad_norm: 0.9858 (inf) time: 0.5039 [2021-03-25 11:01:28 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 150/1251] eta: 0:09:47 lr: 0.000950 loss: 4.0004 (3.8586) grad_norm: 0.9986 (inf) time: 0.5078 [2021-03-25 11:01:33 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 160/1251] eta: 0:09:40 lr: 0.000950 loss: 3.9969 (3.8497) grad_norm: 0.9986 (inf) time: 0.5081 [2021-03-25 11:01:38 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 170/1251] eta: 0:09:33 lr: 0.000950 loss: 3.6002 (3.8434) grad_norm: 0.9793 (inf) time: 0.5111 [2021-03-25 11:01:44 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 180/1251] eta: 0:09:27 lr: 0.000950 loss: 3.6002 (3.8302) grad_norm: 1.0650 (inf) time: 0.5164 [2021-03-25 11:01:49 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 190/1251] eta: 0:09:20 lr: 0.000950 loss: 3.5937 (3.8204) grad_norm: 1.0106 (inf) time: 0.5068 [2021-03-25 11:01:54 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 200/1251] eta: 0:09:14 lr: 0.000950 loss: 3.9542 (3.8210) grad_norm: 0.9913 (inf) time: 0.5037 [2021-03-25 11:01:59 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 210/1251] eta: 0:09:08 lr: 0.000950 loss: 4.0124 (3.8093) grad_norm: 0.9878 (inf) time: 0.5127 [2021-03-25 11:02:04 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 220/1251] eta: 0:09:02 lr: 0.000950 loss: 3.7884 (3.7998) grad_norm: 0.9809 (inf) time: 0.5139 [2021-03-25 11:02:09 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 230/1251] eta: 0:08:56 lr: 0.000950 loss: 3.7042 (3.7963) grad_norm: 1.0098 (inf) time: 0.5121 [2021-03-25 11:02:14 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 240/1251] eta: 0:08:50 lr: 0.000950 loss: 4.0014 (3.8145) grad_norm: 1.0447 (inf) time: 0.5143 [2021-03-25 11:02:19 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 250/1251] eta: 0:08:45 lr: 0.000950 loss: 3.9890 (3.8144) grad_norm: 1.0066 (inf) time: 0.5128 [2021-03-25 11:02:24 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 260/1251] eta: 0:08:39 lr: 0.000950 loss: 3.7661 (3.8134) grad_norm: 0.9563 (inf) time: 0.5078 [2021-03-25 11:02:29 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 270/1251] eta: 0:08:33 lr: 0.000950 loss: 3.8912 (3.8226) grad_norm: 0.9745 (inf) time: 0.5037 [2021-03-25 11:02:34 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 280/1251] eta: 0:08:27 lr: 0.000950 loss: 3.9323 (3.8231) grad_norm: 0.9724 (inf) time: 0.5029 [2021-03-25 11:02:40 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 290/1251] eta: 0:08:21 lr: 0.000950 loss: 3.9213 (3.8251) grad_norm: 0.9504 (inf) time: 0.5066 [2021-03-25 11:02:45 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 300/1251] eta: 0:08:15 lr: 0.000950 loss: 4.0219 (3.8346) grad_norm: 1.0326 (inf) time: 0.5097 [2021-03-25 11:02:50 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 310/1251] eta: 0:08:10 lr: 0.000950 loss: 3.8021 (3.8219) grad_norm: 0.9904 (inf) time: 0.5175 [2021-03-25 11:02:55 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 320/1251] eta: 0:08:05 lr: 0.000950 loss: 3.4932 (3.8204) grad_norm: 0.9551 (inf) time: 0.5140 [2021-03-25 11:03:00 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 330/1251] eta: 0:07:59 lr: 0.000950 loss: 3.4932 (3.8072) grad_norm: 0.8966 (inf) time: 0.5081 [2021-03-25 11:03:05 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 340/1251] eta: 0:07:54 lr: 0.000950 loss: 3.4579 (3.8062) grad_norm: 0.9255 (inf) time: 0.5099 [2021-03-25 11:03:10 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 350/1251] eta: 0:07:48 lr: 0.000950 loss: 3.9831 (3.8116) grad_norm: 0.9531 (inf) time: 0.5067 [2021-03-25 11:03:15 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 360/1251] eta: 0:07:43 lr: 0.000950 loss: 3.9798 (3.8121) grad_norm: 0.9452 (inf) time: 0.5082 [2021-03-25 11:03:20 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 370/1251] eta: 0:07:37 lr: 0.000950 loss: 3.6686 (3.8074) grad_norm: 0.9301 (inf) time: 0.5087 [2021-03-25 11:03:25 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 380/1251] eta: 0:07:32 lr: 0.000950 loss: 3.7972 (3.8074) grad_norm: 0.9358 (inf) time: 0.5061 [2021-03-25 11:03:31 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 390/1251] eta: 0:07:26 lr: 0.000950 loss: 3.8290 (3.8082) grad_norm: 0.9934 (inf) time: 0.5071 [2021-03-25 11:03:36 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 400/1251] eta: 0:07:21 lr: 0.000950 loss: 4.1152 (3.8139) grad_norm: 0.9670 (inf) time: 0.5053 [2021-03-25 11:03:41 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 410/1251] eta: 0:07:15 lr: 0.000950 loss: 4.1564 (3.8199) grad_norm: 0.9883 (inf) time: 0.5045 [2021-03-25 11:03:46 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 420/1251] eta: 0:07:10 lr: 0.000950 loss: 3.9383 (3.8181) grad_norm: 1.0068 (inf) time: 0.5043 [2021-03-25 11:03:51 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 430/1251] eta: 0:07:05 lr: 0.000950 loss: 3.9383 (3.8210) grad_norm: 1.0199 (inf) time: 0.5145 [2021-03-25 11:03:56 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 440/1251] eta: 0:06:59 lr: 0.000950 loss: 4.1113 (3.8227) grad_norm: 0.9781 (inf) time: 0.5159 [2021-03-25 11:04:01 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 450/1251] eta: 0:06:54 lr: 0.000950 loss: 4.0112 (3.8237) grad_norm: 0.9622 (inf) time: 0.5052 [2021-03-25 11:04:06 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 460/1251] eta: 0:06:48 lr: 0.000950 loss: 3.8069 (3.8227) grad_norm: 0.9975 (inf) time: 0.5021 [2021-03-25 11:04:11 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 470/1251] eta: 0:06:43 lr: 0.000950 loss: 3.9859 (3.8284) grad_norm: 0.9709 (inf) time: 0.4998 [2021-03-25 11:04:16 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 480/1251] eta: 0:06:38 lr: 0.000950 loss: 4.1551 (3.8308) grad_norm: 0.9709 (inf) time: 0.5036 [2021-03-25 11:04:21 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 490/1251] eta: 0:06:32 lr: 0.000950 loss: 4.1441 (3.8344) grad_norm: 1.0253 (inf) time: 0.5090 [2021-03-25 11:04:26 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 500/1251] eta: 0:06:27 lr: 0.000950 loss: 3.8611 (3.8304) grad_norm: 1.0216 (inf) time: 0.5146 [2021-03-25 11:04:31 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 510/1251] eta: 0:06:22 lr: 0.000950 loss: 3.8043 (3.8281) grad_norm: 0.9319 (inf) time: 0.5065 [2021-03-25 11:04:36 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 520/1251] eta: 0:06:16 lr: 0.000950 loss: 3.8738 (3.8268) grad_norm: 0.9410 (inf) time: 0.4987 [2021-03-25 11:04:41 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 530/1251] eta: 0:06:11 lr: 0.000950 loss: 3.8738 (3.8265) grad_norm: 0.9501 (inf) time: 0.5079 [2021-03-25 11:04:47 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 540/1251] eta: 0:06:06 lr: 0.000950 loss: 3.7985 (3.8238) grad_norm: 0.9576 (inf) time: 0.5092 [2021-03-25 11:04:52 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 550/1251] eta: 0:06:01 lr: 0.000950 loss: 4.0401 (3.8245) grad_norm: 0.9892 (inf) time: 0.5172 [2021-03-25 11:04:57 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 560/1251] eta: 0:05:56 lr: 0.000950 loss: 3.4868 (3.8174) grad_norm: 0.9941 (inf) time: 0.5199 [2021-03-25 11:05:02 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 570/1251] eta: 0:05:50 lr: 0.000950 loss: 3.7006 (3.8167) grad_norm: 0.9968 (inf) time: 0.5064 [2021-03-25 11:05:07 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 580/1251] eta: 0:05:45 lr: 0.000950 loss: 3.7443 (3.8105) grad_norm: 1.0186 (inf) time: 0.5019 [2021-03-25 11:05:12 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 590/1251] eta: 0:05:40 lr: 0.000950 loss: 3.7760 (3.8146) grad_norm: 0.9785 (inf) time: 0.5111 [2021-03-25 11:05:17 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 600/1251] eta: 0:05:35 lr: 0.000950 loss: 4.0950 (3.8168) grad_norm: 0.9818 (inf) time: 0.5147 [2021-03-25 11:05:22 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 610/1251] eta: 0:05:30 lr: 0.000950 loss: 3.7931 (3.8117) grad_norm: 1.0051 (inf) time: 0.5069 [2021-03-25 11:05:27 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 620/1251] eta: 0:05:24 lr: 0.000950 loss: 3.4693 (3.8059) grad_norm: 0.9512 (inf) time: 0.5001 [2021-03-25 11:05:32 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 630/1251] eta: 0:05:19 lr: 0.000950 loss: 3.6203 (3.8045) grad_norm: 0.9962 (inf) time: 0.4970 [2021-03-25 11:05:37 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 640/1251] eta: 0:05:14 lr: 0.000949 loss: 3.8586 (3.8080) grad_norm: 1.0341 (inf) time: 0.5074 [2021-03-25 11:05:42 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 650/1251] eta: 0:05:09 lr: 0.000949 loss: 3.8346 (3.8074) grad_norm: 1.0319 (inf) time: 0.5108 [2021-03-25 11:05:47 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 660/1251] eta: 0:05:03 lr: 0.000949 loss: 3.5374 (3.8042) grad_norm: 0.9443 (inf) time: 0.5011 [2021-03-25 11:05:52 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 670/1251] eta: 0:04:58 lr: 0.000949 loss: 3.8208 (3.8050) grad_norm: 0.9443 (inf) time: 0.4989 [2021-03-25 11:05:58 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 680/1251] eta: 0:04:53 lr: 0.000949 loss: 4.0300 (3.8067) grad_norm: 0.9443 (inf) time: 0.5075 [2021-03-25 11:06:03 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 690/1251] eta: 0:04:48 lr: 0.000949 loss: 3.9562 (3.8080) grad_norm: 0.9504 (inf) time: 0.5089 [2021-03-25 11:06:08 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 700/1251] eta: 0:04:42 lr: 0.000949 loss: 3.8292 (3.8069) grad_norm: 0.9933 (inf) time: 0.5043 [2021-03-25 11:06:13 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 710/1251] eta: 0:04:37 lr: 0.000949 loss: 3.9249 (3.8104) grad_norm: 0.9667 (inf) time: 0.5090 [2021-03-25 11:06:18 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 720/1251] eta: 0:04:32 lr: 0.000949 loss: 3.8727 (3.8079) grad_norm: 0.9809 (inf) time: 0.5080 [2021-03-25 11:06:23 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 730/1251] eta: 0:04:27 lr: 0.000949 loss: 3.8028 (3.8084) grad_norm: 0.9939 (inf) time: 0.5125 [2021-03-25 11:06:28 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 740/1251] eta: 0:04:22 lr: 0.000949 loss: 3.8093 (3.8059) grad_norm: 1.0873 (inf) time: 0.5196 [2021-03-25 11:06:33 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 750/1251] eta: 0:04:17 lr: 0.000949 loss: 3.8093 (3.8063) grad_norm: 1.0292 (inf) time: 0.5080 [2021-03-25 11:06:38 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 760/1251] eta: 0:04:11 lr: 0.000949 loss: 3.8847 (3.8059) grad_norm: 1.0333 (inf) time: 0.5030 [2021-03-25 11:06:43 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 770/1251] eta: 0:04:06 lr: 0.000949 loss: 3.9260 (3.8083) grad_norm: 1.0896 (inf) time: 0.5050 [2021-03-25 11:06:48 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 780/1251] eta: 0:04:01 lr: 0.000949 loss: 4.0607 (3.8113) grad_norm: 1.0376 (inf) time: 0.5055 [2021-03-25 11:06:54 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 790/1251] eta: 0:03:56 lr: 0.000949 loss: 4.1342 (3.8133) grad_norm: 0.9802 (inf) time: 0.5126 [2021-03-25 11:06:59 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 800/1251] eta: 0:03:51 lr: 0.000949 loss: 4.0018 (3.8148) grad_norm: 0.9714 (inf) time: 0.5130 [2021-03-25 11:07:04 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 810/1251] eta: 0:03:46 lr: 0.000949 loss: 3.9577 (3.8153) grad_norm: 0.9802 (inf) time: 0.5026 [2021-03-25 11:07:09 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 820/1251] eta: 0:03:40 lr: 0.000949 loss: 3.6723 (3.8120) grad_norm: 1.0529 (inf) time: 0.4958 [2021-03-25 11:07:14 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 830/1251] eta: 0:03:35 lr: 0.000949 loss: 3.8202 (3.8135) grad_norm: 1.0816 (inf) time: 0.5070 [2021-03-25 11:07:19 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 840/1251] eta: 0:03:30 lr: 0.000949 loss: 4.0369 (3.8158) grad_norm: 1.0483 (inf) time: 0.5136 [2021-03-25 11:07:24 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 850/1251] eta: 0:03:25 lr: 0.000949 loss: 3.7606 (3.8133) grad_norm: 1.0905 (inf) time: 0.5047 [2021-03-25 11:07:29 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 860/1251] eta: 0:03:20 lr: 0.000949 loss: 3.5756 (3.8105) grad_norm: 1.0087 (inf) time: 0.5045 [2021-03-25 11:07:34 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 870/1251] eta: 0:03:15 lr: 0.000949 loss: 3.8309 (3.8111) grad_norm: 0.9672 (inf) time: 0.5074 [2021-03-25 11:07:39 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 880/1251] eta: 0:03:10 lr: 0.000949 loss: 3.8929 (3.8101) grad_norm: 0.9521 (inf) time: 0.5075 [2021-03-25 11:07:44 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 890/1251] eta: 0:03:04 lr: 0.000949 loss: 3.8362 (3.8113) grad_norm: 0.9337 (inf) time: 0.5058 [2021-03-25 11:07:49 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 900/1251] eta: 0:02:59 lr: 0.000949 loss: 3.8362 (3.8102) grad_norm: 0.9337 (inf) time: 0.5066 [2021-03-25 11:07:54 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 910/1251] eta: 0:02:54 lr: 0.000949 loss: 3.3347 (3.8059) grad_norm: 0.9564 (inf) time: 0.5040 [2021-03-25 11:07:59 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 920/1251] eta: 0:02:49 lr: 0.000949 loss: 3.3550 (3.8040) grad_norm: 0.9706 (inf) time: 0.5040 [2021-03-25 11:08:05 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 930/1251] eta: 0:02:44 lr: 0.000949 loss: 3.7399 (3.8047) grad_norm: 0.9743 (inf) time: 0.5128 [2021-03-25 11:08:10 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 940/1251] eta: 0:02:39 lr: 0.000949 loss: 3.6129 (3.8008) grad_norm: 1.0581 (inf) time: 0.5086 [2021-03-25 11:08:15 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 950/1251] eta: 0:02:34 lr: 0.000949 loss: 3.4406 (3.7988) grad_norm: 0.9740 (inf) time: 0.5020 [2021-03-25 11:08:20 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 960/1251] eta: 0:02:28 lr: 0.000949 loss: 3.5685 (3.7994) grad_norm: 0.9740 (inf) time: 0.5027 [2021-03-25 11:08:25 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 970/1251] eta: 0:02:23 lr: 0.000949 loss: 3.7264 (3.7983) grad_norm: 1.0041 (inf) time: 0.5094 [2021-03-25 11:08:30 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 980/1251] eta: 0:02:18 lr: 0.000949 loss: 3.8432 (3.7990) grad_norm: 1.0259 (inf) time: 0.5110 [2021-03-25 11:08:35 swin_small_patch4_window7_224] INFO: Epoch: [43] [ 990/1251] eta: 0:02:13 lr: 0.000949 loss: 3.8432 (3.7988) grad_norm: 0.9972 (inf) time: 0.5029 [2021-03-25 11:08:40 swin_small_patch4_window7_224] INFO: Epoch: [43] [1000/1251] eta: 0:02:08 lr: 0.000949 loss: 3.8086 (3.7976) grad_norm: 1.0092 (inf) time: 0.5045 [2021-03-25 11:08:45 swin_small_patch4_window7_224] INFO: Epoch: [43] [1010/1251] eta: 0:02:03 lr: 0.000949 loss: 3.8516 (3.7982) grad_norm: 1.0562 (inf) time: 0.5080 [2021-03-25 11:08:50 swin_small_patch4_window7_224] INFO: Epoch: [43] [1020/1251] eta: 0:01:58 lr: 0.000949 loss: 3.8516 (3.7987) grad_norm: 1.0024 (inf) time: 0.5029 [2021-03-25 11:08:55 swin_small_patch4_window7_224] INFO: Epoch: [43] [1030/1251] eta: 0:01:53 lr: 0.000949 loss: 3.8530 (3.7990) grad_norm: 0.9979 (inf) time: 0.5011 [2021-03-25 11:09:00 swin_small_patch4_window7_224] INFO: Epoch: [43] [1040/1251] eta: 0:01:47 lr: 0.000949 loss: 3.8716 (3.7994) grad_norm: 1.0282 (inf) time: 0.5031 [2021-03-25 11:09:05 swin_small_patch4_window7_224] INFO: Epoch: [43] [1050/1251] eta: 0:01:42 lr: 0.000949 loss: 3.8144 (3.7972) grad_norm: 1.0050 (inf) time: 0.5160 [2021-03-25 11:09:10 swin_small_patch4_window7_224] INFO: Epoch: [43] [1060/1251] eta: 0:01:37 lr: 0.000949 loss: 3.9416 (3.7976) grad_norm: 0.9668 (inf) time: 0.5174 [2021-03-25 11:09:15 swin_small_patch4_window7_224] INFO: Epoch: [43] [1070/1251] eta: 0:01:32 lr: 0.000949 loss: 3.9416 (3.7979) grad_norm: 0.9635 (inf) time: 0.5085 [2021-03-25 11:09:21 swin_small_patch4_window7_224] INFO: Epoch: [43] [1080/1251] eta: 0:01:27 lr: 0.000949 loss: 4.0345 (3.8004) grad_norm: 0.9403 (inf) time: 0.5075 [2021-03-25 11:09:26 swin_small_patch4_window7_224] INFO: Epoch: [43] [1090/1251] eta: 0:01:22 lr: 0.000949 loss: 4.0345 (3.8020) grad_norm: 0.9268 (inf) time: 0.5075 [2021-03-25 11:09:31 swin_small_patch4_window7_224] INFO: Epoch: [43] [1100/1251] eta: 0:01:17 lr: 0.000949 loss: 3.8956 (3.8012) grad_norm: 0.9473 (inf) time: 0.5068 [2021-03-25 11:09:36 swin_small_patch4_window7_224] INFO: Epoch: [43] [1110/1251] eta: 0:01:12 lr: 0.000949 loss: 3.8831 (3.8031) grad_norm: 1.0044 (inf) time: 0.5074 [2021-03-25 11:09:41 swin_small_patch4_window7_224] INFO: Epoch: [43] [1120/1251] eta: 0:01:06 lr: 0.000949 loss: 3.8868 (3.8039) grad_norm: 1.0103 (inf) time: 0.5084 [2021-03-25 11:09:46 swin_small_patch4_window7_224] INFO: Epoch: [43] [1130/1251] eta: 0:01:01 lr: 0.000949 loss: 3.7656 (3.8036) grad_norm: 1.0061 (inf) time: 0.5016 [2021-03-25 11:09:51 swin_small_patch4_window7_224] INFO: Epoch: [43] [1140/1251] eta: 0:00:56 lr: 0.000949 loss: 3.7656 (3.8037) grad_norm: 0.9895 (inf) time: 0.4977 [2021-03-25 11:09:56 swin_small_patch4_window7_224] INFO: Epoch: [43] [1150/1251] eta: 0:00:51 lr: 0.000949 loss: 4.1321 (3.8065) grad_norm: 0.9812 (inf) time: 0.5006 [2021-03-25 11:10:01 swin_small_patch4_window7_224] INFO: Epoch: [43] [1160/1251] eta: 0:00:46 lr: 0.000949 loss: 3.9588 (3.8034) grad_norm: 0.9789 (inf) time: 0.5086 [2021-03-25 11:10:06 swin_small_patch4_window7_224] INFO: Epoch: [43] [1170/1251] eta: 0:00:41 lr: 0.000949 loss: 3.7862 (3.8037) grad_norm: 0.9662 (inf) time: 0.5169 [2021-03-25 11:10:11 swin_small_patch4_window7_224] INFO: Epoch: [43] [1180/1251] eta: 0:00:36 lr: 0.000949 loss: 3.7862 (3.8012) grad_norm: 0.9670 (inf) time: 0.5166 [2021-03-25 11:10:16 swin_small_patch4_window7_224] INFO: Epoch: [43] [1190/1251] eta: 0:00:31 lr: 0.000948 loss: 3.8576 (3.8026) grad_norm: 1.0090 (inf) time: 0.5105 [2021-03-25 11:10:21 swin_small_patch4_window7_224] INFO: Epoch: [43] [1200/1251] eta: 0:00:26 lr: 0.000948 loss: 3.8576 (3.8009) grad_norm: 1.0090 (inf) time: 0.5050 [2021-03-25 11:10:26 swin_small_patch4_window7_224] INFO: Epoch: [43] [1210/1251] eta: 0:00:20 lr: 0.000948 loss: 3.8408 (3.8022) grad_norm: 0.9451 (inf) time: 0.5026 [2021-03-25 11:10:31 swin_small_patch4_window7_224] INFO: Epoch: [43] [1220/1251] eta: 0:00:15 lr: 0.000948 loss: 3.7054 (3.8005) grad_norm: 0.9835 (inf) time: 0.5021 [2021-03-25 11:10:37 swin_small_patch4_window7_224] INFO: Epoch: [43] [1230/1251] eta: 0:00:10 lr: 0.000948 loss: 3.5700 (3.8003) grad_norm: 0.9829 (inf) time: 0.5028 [2021-03-25 11:10:42 swin_small_patch4_window7_224] INFO: Epoch: [43] [1240/1251] eta: 0:00:05 lr: 0.000948 loss: 3.9378 (3.8016) grad_norm: 0.9716 (inf) time: 0.5068 [2021-03-25 11:10:47 swin_small_patch4_window7_224] INFO: Epoch: [43] [1250/1251] eta: 0:00:00 lr: 0.000948 loss: 3.9194 (3.8004) grad_norm: 0.9792 (inf) time: 0.5098 [2021-03-25 11:10:51 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 1.4999 (1.4999) acc1: 64.0625 (64.0625) acc5: 92.1875 (92.1875) [2021-03-25 11:10:54 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.2773 (1.2862) acc1: 71.8750 (71.0227) acc5: 90.6250 (90.4830) [2021-03-25 11:10:57 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.2773 (1.3035) acc1: 70.3125 (70.0893) acc5: 90.6250 (90.2530) [2021-03-25 11:10:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.3671 (1.3162) acc1: 68.7500 (69.8589) acc5: 90.6250 (90.7762) [2021-03-25 11:11:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.3430 (1.3051) acc1: 70.3125 (70.3887) acc5: 90.6250 (90.8918) [2021-03-25 11:11:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1967 (1.2845) acc1: 71.8750 (70.8800) acc5: 92.1875 (91.1360) [2021-03-25 11:11:04 swin_small_patch4_window7_224] INFO: * Acc@1 71.502 Acc@5 90.940 loss 1.261 [2021-03-25 11:11:04 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.5% [2021-03-25 11:11:04 swin_small_patch4_window7_224] INFO: Max accuracy: 71.50% [2021-03-25 11:11:08 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 0/1251] eta: 1:30:39 lr: 0.000948 loss: 3.9414 (3.9414) grad_norm: 1.1104 (1.1104) time: 4.3478 [2021-03-25 11:11:13 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 10/1251] eta: 0:17:47 lr: 0.000948 loss: 3.8657 (3.7607) grad_norm: 0.9554 (0.9635) time: 0.8605 [2021-03-25 11:11:18 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 20/1251] eta: 0:14:13 lr: 0.000948 loss: 3.8655 (3.8187) grad_norm: 0.9554 (0.9915) time: 0.5108 [2021-03-25 11:11:23 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 30/1251] eta: 0:12:50 lr: 0.000948 loss: 4.0790 (3.9483) grad_norm: 0.9483 (0.9881) time: 0.5042 [2021-03-25 11:11:29 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 40/1251] eta: 0:12:08 lr: 0.000948 loss: 3.9147 (3.8088) grad_norm: 0.9565 (0.9946) time: 0.5051 [2021-03-25 11:11:34 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 50/1251] eta: 0:11:41 lr: 0.000948 loss: 3.7470 (3.8515) grad_norm: 0.9712 (0.9898) time: 0.5129 [2021-03-25 11:11:39 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 60/1251] eta: 0:11:20 lr: 0.000948 loss: 3.9266 (3.8413) grad_norm: 0.9759 (0.9921) time: 0.5084 [2021-03-25 11:11:44 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 70/1251] eta: 0:11:04 lr: 0.000948 loss: 3.8382 (3.8271) grad_norm: 0.9622 (0.9881) time: 0.5059 [2021-03-25 11:11:49 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 80/1251] eta: 0:10:49 lr: 0.000948 loss: 3.9274 (3.8305) grad_norm: 0.9554 (0.9848) time: 0.5054 [2021-03-25 11:11:54 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 90/1251] eta: 0:10:39 lr: 0.000948 loss: 3.8010 (3.7876) grad_norm: 0.9032 (0.9780) time: 0.5100 [2021-03-25 11:11:59 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 100/1251] eta: 0:10:29 lr: 0.000948 loss: 3.7503 (3.8031) grad_norm: 0.9578 (0.9860) time: 0.5134 [2021-03-25 11:12:04 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 110/1251] eta: 0:10:21 lr: 0.000948 loss: 3.9298 (3.7837) grad_norm: 0.9994 (0.9871) time: 0.5152 [2021-03-25 11:12:09 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 120/1251] eta: 0:10:12 lr: 0.000948 loss: 3.7946 (3.7793) grad_norm: 1.0031 (0.9902) time: 0.5154 [2021-03-25 11:12:15 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 130/1251] eta: 0:10:05 lr: 0.000948 loss: 3.8201 (3.7960) grad_norm: 0.9818 (0.9859) time: 0.5152 [2021-03-25 11:12:20 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 140/1251] eta: 0:09:57 lr: 0.000948 loss: 3.8201 (3.7666) grad_norm: 0.9859 (0.9904) time: 0.5134 [2021-03-25 11:12:25 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 150/1251] eta: 0:09:49 lr: 0.000948 loss: 3.8881 (3.7761) grad_norm: 0.9628 (0.9843) time: 0.5079 [2021-03-25 11:12:30 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 160/1251] eta: 0:09:42 lr: 0.000948 loss: 3.9934 (3.7908) grad_norm: 0.8983 (0.9811) time: 0.5078 [2021-03-25 11:12:35 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 170/1251] eta: 0:09:35 lr: 0.000948 loss: 3.9934 (3.7859) grad_norm: 1.0032 (0.9855) time: 0.5050 [2021-03-25 11:12:40 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 180/1251] eta: 0:09:28 lr: 0.000948 loss: 3.7917 (3.7905) grad_norm: 1.1061 (1.0002) time: 0.5090 [2021-03-25 11:12:45 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 190/1251] eta: 0:09:22 lr: 0.000948 loss: 3.8874 (3.7940) grad_norm: 1.0802 (1.0016) time: 0.5101 [2021-03-25 11:12:50 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 200/1251] eta: 0:09:15 lr: 0.000948 loss: 3.7900 (3.7791) grad_norm: 0.9717 (0.9995) time: 0.5066 [2021-03-25 11:12:55 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 210/1251] eta: 0:09:09 lr: 0.000948 loss: 3.7900 (3.7880) grad_norm: 0.9290 (1.0005) time: 0.5095 [2021-03-25 11:13:00 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 220/1251] eta: 0:09:03 lr: 0.000948 loss: 3.8641 (3.7770) grad_norm: 0.9312 (1.0005) time: 0.5091 [2021-03-25 11:13:05 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 230/1251] eta: 0:08:56 lr: 0.000948 loss: 3.6999 (3.7761) grad_norm: 1.0324 (1.0031) time: 0.5031 [2021-03-25 11:13:10 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 240/1251] eta: 0:08:50 lr: 0.000948 loss: 3.9596 (3.7764) grad_norm: 1.0345 (1.0039) time: 0.5017 [2021-03-25 11:13:15 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 250/1251] eta: 0:08:44 lr: 0.000948 loss: 3.5467 (3.7709) grad_norm: 0.9618 (1.0010) time: 0.5051 [2021-03-25 11:13:20 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 260/1251] eta: 0:08:38 lr: 0.000948 loss: 3.7354 (3.7757) grad_norm: 0.8923 (0.9974) time: 0.5029 [2021-03-25 11:13:25 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 270/1251] eta: 0:08:32 lr: 0.000948 loss: 3.8302 (3.7764) grad_norm: 0.9114 (0.9960) time: 0.5000 [2021-03-25 11:13:31 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 280/1251] eta: 0:08:26 lr: 0.000948 loss: 3.8802 (3.7788) grad_norm: 1.0049 (1.0003) time: 0.5053 [2021-03-25 11:13:36 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 290/1251] eta: 0:08:20 lr: 0.000948 loss: 3.9732 (3.7863) grad_norm: 1.0347 (1.0018) time: 0.5046 [2021-03-25 11:13:41 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 300/1251] eta: 0:08:15 lr: 0.000948 loss: 4.0051 (3.7904) grad_norm: 1.0323 (1.0038) time: 0.5048 [2021-03-25 11:13:46 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 310/1251] eta: 0:08:09 lr: 0.000948 loss: 4.0447 (3.7907) grad_norm: 1.0638 (1.0064) time: 0.5072 [2021-03-25 11:13:51 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 320/1251] eta: 0:08:03 lr: 0.000948 loss: 4.0374 (3.7938) grad_norm: 1.1097 (1.0088) time: 0.5054 [2021-03-25 11:13:56 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 330/1251] eta: 0:07:58 lr: 0.000948 loss: 3.9164 (3.8029) grad_norm: 1.0084 (1.0080) time: 0.5053 [2021-03-25 11:14:01 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 340/1251] eta: 0:07:52 lr: 0.000948 loss: 3.8418 (3.7969) grad_norm: 0.9811 (1.0083) time: 0.5060 [2021-03-25 11:14:06 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 350/1251] eta: 0:07:47 lr: 0.000948 loss: 3.6721 (3.7985) grad_norm: 1.0244 (1.0102) time: 0.5059 [2021-03-25 11:14:11 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 360/1251] eta: 0:07:41 lr: 0.000948 loss: 3.6799 (3.7922) grad_norm: 1.0682 (1.0143) time: 0.5045 [2021-03-25 11:14:16 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 370/1251] eta: 0:07:36 lr: 0.000948 loss: 3.6799 (3.7954) grad_norm: 1.0862 (1.0155) time: 0.5033 [2021-03-25 11:14:21 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 380/1251] eta: 0:07:30 lr: 0.000948 loss: 3.9305 (3.8005) grad_norm: 1.0258 (1.0155) time: 0.5037 [2021-03-25 11:14:26 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 390/1251] eta: 0:07:25 lr: 0.000948 loss: 4.1476 (3.8031) grad_norm: 0.9786 (1.0143) time: 0.5045 [2021-03-25 11:14:31 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 400/1251] eta: 0:07:19 lr: 0.000948 loss: 4.0401 (3.8063) grad_norm: 0.9481 (1.0142) time: 0.5053 [2021-03-25 11:14:36 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 410/1251] eta: 0:07:14 lr: 0.000948 loss: 4.0401 (3.8090) grad_norm: 1.0094 (1.0147) time: 0.5041 [2021-03-25 11:14:41 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 420/1251] eta: 0:07:08 lr: 0.000948 loss: 3.9800 (3.8068) grad_norm: 1.0062 (1.0145) time: 0.5037 [2021-03-25 11:14:46 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 430/1251] eta: 0:07:03 lr: 0.000948 loss: 3.9945 (3.8085) grad_norm: 0.9911 (1.0143) time: 0.5022 [2021-03-25 11:14:51 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 440/1251] eta: 0:06:58 lr: 0.000948 loss: 4.0400 (3.8138) grad_norm: 0.9618 (1.0139) time: 0.5014 [2021-03-25 11:14:56 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 450/1251] eta: 0:06:52 lr: 0.000948 loss: 3.9319 (3.8120) grad_norm: 0.9923 (1.0137) time: 0.5048 [2021-03-25 11:15:01 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 460/1251] eta: 0:06:47 lr: 0.000948 loss: 3.7206 (3.8050) grad_norm: 1.0156 (1.0145) time: 0.5049 [2021-03-25 11:15:06 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 470/1251] eta: 0:06:42 lr: 0.000948 loss: 3.8953 (3.8103) grad_norm: 0.9983 (1.0129) time: 0.5051 [2021-03-25 11:15:11 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 480/1251] eta: 0:06:36 lr: 0.000947 loss: 3.9481 (3.8115) grad_norm: 0.9392 (1.0115) time: 0.5036 [2021-03-25 11:15:16 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 490/1251] eta: 0:06:31 lr: 0.000947 loss: 3.9720 (3.8112) grad_norm: 0.9564 (1.0124) time: 0.5014 [2021-03-25 11:15:22 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 500/1251] eta: 0:06:26 lr: 0.000947 loss: 4.0155 (3.8084) grad_norm: 0.9820 (1.0119) time: 0.5044 [2021-03-25 11:15:27 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 510/1251] eta: 0:06:20 lr: 0.000947 loss: 3.8260 (3.8087) grad_norm: 0.9365 (1.0114) time: 0.5050 [2021-03-25 11:15:32 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 520/1251] eta: 0:06:15 lr: 0.000947 loss: 4.0931 (3.8154) grad_norm: 0.9521 (1.0109) time: 0.4995 [2021-03-25 11:15:37 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 530/1251] eta: 0:06:10 lr: 0.000947 loss: 4.1318 (3.8142) grad_norm: 0.9593 (1.0134) time: 0.5009 [2021-03-25 11:15:42 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 540/1251] eta: 0:06:05 lr: 0.000947 loss: 3.8292 (3.8159) grad_norm: 1.0093 (1.0132) time: 0.5133 [2021-03-25 11:15:47 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 550/1251] eta: 0:06:00 lr: 0.000947 loss: 3.9030 (3.8146) grad_norm: 0.9899 (1.0133) time: 0.5225 [2021-03-25 11:15:52 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 560/1251] eta: 0:05:54 lr: 0.000947 loss: 3.9465 (3.8157) grad_norm: 0.9988 (1.0147) time: 0.5137 [2021-03-25 11:15:57 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 570/1251] eta: 0:05:49 lr: 0.000947 loss: 3.8281 (3.8151) grad_norm: 0.9939 (1.0144) time: 0.5025 [2021-03-25 11:16:02 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 580/1251] eta: 0:05:44 lr: 0.000947 loss: 3.7942 (3.8149) grad_norm: 0.9681 (1.0153) time: 0.5013 [2021-03-25 11:16:07 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 590/1251] eta: 0:05:39 lr: 0.000947 loss: 3.8018 (3.8169) grad_norm: 1.0094 (1.0167) time: 0.5067 [2021-03-25 11:16:12 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 600/1251] eta: 0:05:33 lr: 0.000947 loss: 3.8675 (3.8156) grad_norm: 1.0078 (1.0170) time: 0.5087 [2021-03-25 11:16:17 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 610/1251] eta: 0:05:28 lr: 0.000947 loss: 3.5336 (3.8112) grad_norm: 0.9684 (1.0161) time: 0.5026 [2021-03-25 11:16:22 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 620/1251] eta: 0:05:23 lr: 0.000947 loss: 3.7535 (3.8100) grad_norm: 0.9133 (1.0147) time: 0.5083 [2021-03-25 11:16:27 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 630/1251] eta: 0:05:18 lr: 0.000947 loss: 3.8966 (3.8081) grad_norm: 0.9168 (1.0144) time: 0.5069 [2021-03-25 11:16:33 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 640/1251] eta: 0:05:13 lr: 0.000947 loss: 3.8013 (3.8067) grad_norm: 0.9464 (1.0142) time: 0.5045 [2021-03-25 11:16:38 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 650/1251] eta: 0:05:08 lr: 0.000947 loss: 3.9789 (3.8089) grad_norm: 0.9979 (1.0147) time: 0.5085 [2021-03-25 11:16:43 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 660/1251] eta: 0:05:02 lr: 0.000947 loss: 3.9993 (3.8124) grad_norm: 1.0259 (1.0153) time: 0.5067 [2021-03-25 11:16:48 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 670/1251] eta: 0:04:57 lr: 0.000947 loss: 3.6569 (3.8079) grad_norm: 1.0255 (1.0149) time: 0.5047 [2021-03-25 11:16:53 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 680/1251] eta: 0:04:52 lr: 0.000947 loss: 3.5877 (3.8067) grad_norm: 0.9622 (1.0139) time: 0.5104 [2021-03-25 11:16:58 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 690/1251] eta: 0:04:47 lr: 0.000947 loss: 3.6696 (3.8056) grad_norm: 0.9095 (1.0131) time: 0.5131 [2021-03-25 11:17:03 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 700/1251] eta: 0:04:42 lr: 0.000947 loss: 3.6644 (3.8043) grad_norm: 1.0085 (1.0146) time: 0.5041 [2021-03-25 11:17:08 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 710/1251] eta: 0:04:37 lr: 0.000947 loss: 4.0681 (3.8084) grad_norm: 1.0580 (1.0154) time: 0.5072 [2021-03-25 11:17:13 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 720/1251] eta: 0:04:31 lr: 0.000947 loss: 3.9912 (3.8038) grad_norm: 1.0413 (1.0153) time: 0.5098 [2021-03-25 11:17:18 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 730/1251] eta: 0:04:26 lr: 0.000947 loss: 3.5993 (3.8015) grad_norm: 0.9835 (1.0148) time: 0.5122 [2021-03-25 11:17:24 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 740/1251] eta: 0:04:21 lr: 0.000947 loss: 4.0201 (3.8013) grad_norm: 0.9974 (1.0149) time: 0.5234 [2021-03-25 11:17:29 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 750/1251] eta: 0:04:16 lr: 0.000947 loss: 4.0201 (3.8029) grad_norm: 1.0315 (1.0162) time: 0.5170 [2021-03-25 11:17:34 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 760/1251] eta: 0:04:11 lr: 0.000947 loss: 3.8220 (3.8004) grad_norm: 1.0697 (1.0181) time: 0.5075 [2021-03-25 11:17:39 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 770/1251] eta: 0:04:06 lr: 0.000947 loss: 3.7888 (3.8005) grad_norm: 1.0009 (1.0179) time: 0.5092 [2021-03-25 11:17:44 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 780/1251] eta: 0:04:01 lr: 0.000947 loss: 3.6899 (3.7976) grad_norm: 0.9687 (1.0177) time: 0.5062 [2021-03-25 11:17:49 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 790/1251] eta: 0:03:56 lr: 0.000947 loss: 3.6206 (3.7963) grad_norm: 0.9974 (1.0179) time: 0.5097 [2021-03-25 11:17:54 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 800/1251] eta: 0:03:50 lr: 0.000947 loss: 3.7316 (3.7965) grad_norm: 1.0238 (1.0184) time: 0.5116 [2021-03-25 11:17:59 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 810/1251] eta: 0:03:45 lr: 0.000947 loss: 3.7316 (3.7935) grad_norm: 1.1111 (1.0201) time: 0.5059 [2021-03-25 11:18:04 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 820/1251] eta: 0:03:40 lr: 0.000947 loss: 4.0444 (3.7987) grad_norm: 1.1197 (1.0200) time: 0.5027 [2021-03-25 11:18:09 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 830/1251] eta: 0:03:35 lr: 0.000947 loss: 4.0444 (3.7979) grad_norm: 0.9733 (1.0203) time: 0.5039 [2021-03-25 11:18:14 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 840/1251] eta: 0:03:30 lr: 0.000947 loss: 3.6525 (3.7945) grad_norm: 0.9879 (1.0212) time: 0.5050 [2021-03-25 11:18:19 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 850/1251] eta: 0:03:25 lr: 0.000947 loss: 3.6075 (3.7941) grad_norm: 0.9931 (1.0215) time: 0.5088 [2021-03-25 11:18:25 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 860/1251] eta: 0:03:20 lr: 0.000947 loss: 3.5517 (3.7901) grad_norm: 1.0696 (1.0218) time: 0.5117 [2021-03-25 11:18:30 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 870/1251] eta: 0:03:14 lr: 0.000947 loss: 3.9922 (3.7918) grad_norm: 1.0746 (1.0222) time: 0.5122 [2021-03-25 11:18:35 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 880/1251] eta: 0:03:09 lr: 0.000947 loss: 4.0016 (3.7916) grad_norm: 1.0073 (1.0220) time: 0.5191 [2021-03-25 11:18:40 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 890/1251] eta: 0:03:04 lr: 0.000947 loss: 4.0062 (3.7962) grad_norm: 0.9666 (1.0211) time: 0.5138 [2021-03-25 11:18:45 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 900/1251] eta: 0:02:59 lr: 0.000947 loss: 3.9258 (3.7952) grad_norm: 0.9533 (1.0209) time: 0.5086 [2021-03-25 11:18:50 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 910/1251] eta: 0:02:54 lr: 0.000947 loss: 3.7218 (3.7973) grad_norm: 0.9915 (1.0207) time: 0.5078 [2021-03-25 11:18:55 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 920/1251] eta: 0:02:49 lr: 0.000947 loss: 4.0235 (3.7993) grad_norm: 1.0073 (1.0211) time: 0.5063 [2021-03-25 11:19:00 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 930/1251] eta: 0:02:44 lr: 0.000947 loss: 4.0235 (3.7986) grad_norm: 1.0366 (1.0213) time: 0.5070 [2021-03-25 11:19:05 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 940/1251] eta: 0:02:39 lr: 0.000947 loss: 3.7953 (3.7990) grad_norm: 1.0962 (1.0216) time: 0.5075 [2021-03-25 11:19:11 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 950/1251] eta: 0:02:33 lr: 0.000947 loss: 3.7953 (3.7994) grad_norm: 1.0427 (1.0219) time: 0.5132 [2021-03-25 11:19:16 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 960/1251] eta: 0:02:28 lr: 0.000947 loss: 3.7658 (3.7981) grad_norm: 0.9419 (1.0213) time: 0.5095 [2021-03-25 11:19:21 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 970/1251] eta: 0:02:23 lr: 0.000947 loss: 3.8550 (3.7994) grad_norm: 0.9761 (1.0224) time: 0.5053 [2021-03-25 11:19:26 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 980/1251] eta: 0:02:18 lr: 0.000947 loss: 3.9200 (3.7993) grad_norm: 1.0099 (1.0224) time: 0.5035 [2021-03-25 11:19:31 swin_small_patch4_window7_224] INFO: Epoch: [44] [ 990/1251] eta: 0:02:13 lr: 0.000947 loss: 3.7506 (3.7993) grad_norm: 0.9864 (1.0220) time: 0.4988 [2021-03-25 11:19:36 swin_small_patch4_window7_224] INFO: Epoch: [44] [1000/1251] eta: 0:02:08 lr: 0.000947 loss: 3.8041 (3.7998) grad_norm: 0.9971 (1.0218) time: 0.4993 [2021-03-25 11:19:41 swin_small_patch4_window7_224] INFO: Epoch: [44] [1010/1251] eta: 0:02:03 lr: 0.000947 loss: 3.8859 (3.8010) grad_norm: 0.9983 (1.0211) time: 0.5027 [2021-03-25 11:19:46 swin_small_patch4_window7_224] INFO: Epoch: [44] [1020/1251] eta: 0:01:58 lr: 0.000946 loss: 4.0388 (3.8028) grad_norm: 0.9536 (1.0207) time: 0.5014 [2021-03-25 11:19:51 swin_small_patch4_window7_224] INFO: Epoch: [44] [1030/1251] eta: 0:01:52 lr: 0.000946 loss: 3.9373 (3.8015) grad_norm: 0.9536 (1.0203) time: 0.5025 [2021-03-25 11:19:56 swin_small_patch4_window7_224] INFO: Epoch: [44] [1040/1251] eta: 0:01:47 lr: 0.000946 loss: 3.5820 (3.7999) grad_norm: 1.0107 (1.0205) time: 0.5148 [2021-03-25 11:20:01 swin_small_patch4_window7_224] INFO: Epoch: [44] [1050/1251] eta: 0:01:42 lr: 0.000946 loss: 3.5689 (3.7978) grad_norm: 1.0218 (1.0206) time: 0.5136 [2021-03-25 11:20:06 swin_small_patch4_window7_224] INFO: Epoch: [44] [1060/1251] eta: 0:01:37 lr: 0.000946 loss: 3.7163 (3.7990) grad_norm: 0.9549 (1.0199) time: 0.5074 [2021-03-25 11:20:11 swin_small_patch4_window7_224] INFO: Epoch: [44] [1070/1251] eta: 0:01:32 lr: 0.000946 loss: 3.9039 (3.7998) grad_norm: 0.9714 (1.0201) time: 0.5091 [2021-03-25 11:20:16 swin_small_patch4_window7_224] INFO: Epoch: [44] [1080/1251] eta: 0:01:27 lr: 0.000946 loss: 3.6965 (3.7972) grad_norm: 1.0397 (1.0199) time: 0.5073 [2021-03-25 11:20:21 swin_small_patch4_window7_224] INFO: Epoch: [44] [1090/1251] eta: 0:01:22 lr: 0.000946 loss: 3.4782 (3.7967) grad_norm: 0.9600 (1.0194) time: 0.5058 [2021-03-25 11:20:26 swin_small_patch4_window7_224] INFO: Epoch: [44] [1100/1251] eta: 0:01:17 lr: 0.000946 loss: 3.7483 (3.7968) grad_norm: 0.9806 (1.0192) time: 0.5075 [2021-03-25 11:20:31 swin_small_patch4_window7_224] INFO: Epoch: [44] [1110/1251] eta: 0:01:12 lr: 0.000946 loss: 3.6635 (3.7957) grad_norm: 0.9906 (1.0192) time: 0.5051 [2021-03-25 11:20:36 swin_small_patch4_window7_224] INFO: Epoch: [44] [1120/1251] eta: 0:01:06 lr: 0.000946 loss: 3.6439 (3.7935) grad_norm: 1.0268 (1.0196) time: 0.4979 [2021-03-25 11:20:41 swin_small_patch4_window7_224] INFO: Epoch: [44] [1130/1251] eta: 0:01:01 lr: 0.000946 loss: 3.8014 (3.7934) grad_norm: 1.0063 (1.0197) time: 0.4979 [2021-03-25 11:20:46 swin_small_patch4_window7_224] INFO: Epoch: [44] [1140/1251] eta: 0:00:56 lr: 0.000946 loss: 3.8014 (3.7915) grad_norm: 0.9784 (1.0201) time: 0.5030 [2021-03-25 11:20:52 swin_small_patch4_window7_224] INFO: Epoch: [44] [1150/1251] eta: 0:00:51 lr: 0.000946 loss: 3.8796 (3.7940) grad_norm: 1.0012 (1.0201) time: 0.5059 [2021-03-25 11:20:57 swin_small_patch4_window7_224] INFO: Epoch: [44] [1160/1251] eta: 0:00:46 lr: 0.000946 loss: 3.9388 (3.7926) grad_norm: 0.9967 (1.0197) time: 0.5092 [2021-03-25 11:21:02 swin_small_patch4_window7_224] INFO: Epoch: [44] [1170/1251] eta: 0:00:41 lr: 0.000946 loss: 3.9388 (3.7935) grad_norm: 0.9739 (1.0193) time: 0.5103 [2021-03-25 11:21:07 swin_small_patch4_window7_224] INFO: Epoch: [44] [1180/1251] eta: 0:00:36 lr: 0.000946 loss: 4.0431 (3.7928) grad_norm: 1.0109 (1.0196) time: 0.5022 [2021-03-25 11:21:12 swin_small_patch4_window7_224] INFO: Epoch: [44] [1190/1251] eta: 0:00:31 lr: 0.000946 loss: 3.8789 (3.7924) grad_norm: 1.0109 (1.0195) time: 0.5005 [2021-03-25 11:21:17 swin_small_patch4_window7_224] INFO: Epoch: [44] [1200/1251] eta: 0:00:26 lr: 0.000946 loss: 3.9307 (3.7939) grad_norm: 0.9245 (1.0191) time: 0.5030 [2021-03-25 11:21:22 swin_small_patch4_window7_224] INFO: Epoch: [44] [1210/1251] eta: 0:00:20 lr: 0.000946 loss: 3.9307 (3.7939) grad_norm: 0.9740 (1.0192) time: 0.5035 [2021-03-25 11:21:27 swin_small_patch4_window7_224] INFO: Epoch: [44] [1220/1251] eta: 0:00:15 lr: 0.000946 loss: 3.8251 (3.7929) grad_norm: 1.0180 (1.0189) time: 0.5047 [2021-03-25 11:21:32 swin_small_patch4_window7_224] INFO: Epoch: [44] [1230/1251] eta: 0:00:10 lr: 0.000946 loss: 3.9065 (3.7951) grad_norm: 1.0186 (1.0191) time: 0.5053 [2021-03-25 11:21:37 swin_small_patch4_window7_224] INFO: Epoch: [44] [1240/1251] eta: 0:00:05 lr: 0.000946 loss: 3.9879 (3.7963) grad_norm: 1.0857 (1.0197) time: 0.4991 [2021-03-25 11:21:42 swin_small_patch4_window7_224] INFO: Epoch: [44] [1250/1251] eta: 0:00:00 lr: 0.000946 loss: 3.8700 (3.7956) grad_norm: 1.0096 (1.0192) time: 0.4994 [2021-03-25 11:21:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 1.0530 (1.0530) acc1: 71.8750 (71.8750) acc5: 89.0625 (89.0625) [2021-03-25 11:21:49 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1047 (1.1662) acc1: 71.8750 (71.7330) acc5: 90.6250 (91.9034) [2021-03-25 11:21:52 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1742 (1.1995) acc1: 70.3125 (70.6845) acc5: 92.1875 (91.9643) [2021-03-25 11:21:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1966 (1.2117) acc1: 70.3125 (70.8165) acc5: 90.6250 (91.4819) [2021-03-25 11:21:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1795 (1.2149) acc1: 71.8750 (70.8841) acc5: 90.6250 (91.3491) [2021-03-25 11:21:57 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1554 (1.2168) acc1: 71.8750 (71.0400) acc5: 90.6250 (91.2000) [2021-03-25 11:21:59 swin_small_patch4_window7_224] INFO: * Acc@1 71.930 Acc@5 91.268 loss 1.198 [2021-03-25 11:21:59 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 71.9% [2021-03-25 11:21:59 swin_small_patch4_window7_224] INFO: Max accuracy: 71.93% [2021-03-25 11:22:03 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 0/1251] eta: 1:22:21 lr: 0.000946 loss: 4.6563 (4.6563) grad_norm: 0.8959 (0.8959) time: 3.9503 [2021-03-25 11:22:09 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 10/1251] eta: 0:17:34 lr: 0.000946 loss: 3.7239 (3.8837) grad_norm: 1.0773 (1.0927) time: 0.8500 [2021-03-25 11:22:14 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 20/1251] eta: 0:14:04 lr: 0.000946 loss: 4.0740 (4.0512) grad_norm: 1.0366 (1.0444) time: 0.5232 [2021-03-25 11:22:19 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 30/1251] eta: 0:12:47 lr: 0.000946 loss: 4.1788 (4.0556) grad_norm: 0.9616 (1.0094) time: 0.5068 [2021-03-25 11:22:24 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 40/1251] eta: 0:12:06 lr: 0.000946 loss: 3.9294 (4.0069) grad_norm: 0.9760 (1.0252) time: 0.5100 [2021-03-25 11:22:29 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 50/1251] eta: 0:11:41 lr: 0.000946 loss: 3.6611 (3.9182) grad_norm: 0.9760 (1.0220) time: 0.5158 [2021-03-25 11:22:34 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 60/1251] eta: 0:11:20 lr: 0.000946 loss: 3.8260 (3.9305) grad_norm: 0.9521 (1.0164) time: 0.5109 [2021-03-25 11:22:39 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 70/1251] eta: 0:11:04 lr: 0.000946 loss: 3.8426 (3.9208) grad_norm: 0.9729 (1.0206) time: 0.5070 [2021-03-25 11:22:44 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 80/1251] eta: 0:10:50 lr: 0.000946 loss: 3.8623 (3.9207) grad_norm: 0.9982 (1.0193) time: 0.5087 [2021-03-25 11:22:49 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 90/1251] eta: 0:10:40 lr: 0.000946 loss: 4.1233 (3.9500) grad_norm: 1.0075 (1.0197) time: 0.5115 [2021-03-25 11:22:55 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 100/1251] eta: 0:10:29 lr: 0.000946 loss: 4.0331 (3.9289) grad_norm: 1.0192 (1.0188) time: 0.5134 [2021-03-25 11:23:00 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 110/1251] eta: 0:10:19 lr: 0.000946 loss: 3.9114 (3.9348) grad_norm: 1.0298 (1.0201) time: 0.5057 [2021-03-25 11:23:05 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 120/1251] eta: 0:10:10 lr: 0.000946 loss: 3.9717 (3.9117) grad_norm: 1.0282 (1.0206) time: 0.5037 [2021-03-25 11:23:10 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 130/1251] eta: 0:10:01 lr: 0.000946 loss: 4.0610 (3.9245) grad_norm: 0.9946 (1.0159) time: 0.5017 [2021-03-25 11:23:15 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 140/1251] eta: 0:09:54 lr: 0.000946 loss: 3.9435 (3.9064) grad_norm: 0.9610 (1.0111) time: 0.5062 [2021-03-25 11:23:20 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 150/1251] eta: 0:09:47 lr: 0.000946 loss: 3.7188 (3.8946) grad_norm: 0.8958 (1.0039) time: 0.5134 [2021-03-25 11:23:25 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 160/1251] eta: 0:09:40 lr: 0.000946 loss: 3.8523 (3.8772) grad_norm: 0.9048 (1.0006) time: 0.5105 [2021-03-25 11:23:30 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 170/1251] eta: 0:09:33 lr: 0.000946 loss: 3.8720 (3.8686) grad_norm: 0.9325 (1.0015) time: 0.5068 [2021-03-25 11:23:35 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 180/1251] eta: 0:09:27 lr: 0.000946 loss: 3.9640 (3.8649) grad_norm: 0.9751 (1.0020) time: 0.5111 [2021-03-25 11:23:40 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 190/1251] eta: 0:09:20 lr: 0.000946 loss: 3.9640 (3.8735) grad_norm: 0.9751 (1.0030) time: 0.5077 [2021-03-25 11:23:45 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 200/1251] eta: 0:09:13 lr: 0.000946 loss: 3.9828 (3.8614) grad_norm: 1.0769 (1.0115) time: 0.4995 [2021-03-25 11:23:50 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 210/1251] eta: 0:09:07 lr: 0.000946 loss: 3.9828 (3.8637) grad_norm: 1.0845 (1.0134) time: 0.5063 [2021-03-25 11:23:55 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 220/1251] eta: 0:09:01 lr: 0.000946 loss: 4.0307 (3.8653) grad_norm: 1.0018 (1.0111) time: 0.5062 [2021-03-25 11:24:01 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 230/1251] eta: 0:08:55 lr: 0.000946 loss: 4.0307 (3.8708) grad_norm: 0.9627 (1.0110) time: 0.5091 [2021-03-25 11:24:06 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 240/1251] eta: 0:08:49 lr: 0.000946 loss: 3.8187 (3.8533) grad_norm: 1.0163 (1.0107) time: 0.5130 [2021-03-25 11:24:11 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 250/1251] eta: 0:08:44 lr: 0.000946 loss: 3.9351 (3.8503) grad_norm: 1.0196 (1.0121) time: 0.5105 [2021-03-25 11:24:16 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 260/1251] eta: 0:08:37 lr: 0.000946 loss: 3.9351 (3.8495) grad_norm: 0.9703 (1.0101) time: 0.5057 [2021-03-25 11:24:21 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 270/1251] eta: 0:08:31 lr: 0.000946 loss: 3.6978 (3.8433) grad_norm: 0.9558 (1.0101) time: 0.5018 [2021-03-25 11:24:26 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 280/1251] eta: 0:08:26 lr: 0.000946 loss: 3.5671 (3.8339) grad_norm: 1.0329 (1.0130) time: 0.5104 [2021-03-25 11:24:31 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 290/1251] eta: 0:08:20 lr: 0.000946 loss: 3.8998 (3.8285) grad_norm: 1.0591 (1.0159) time: 0.5108 [2021-03-25 11:24:36 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 300/1251] eta: 0:08:14 lr: 0.000945 loss: 3.9906 (3.8265) grad_norm: 1.0156 (1.0165) time: 0.5033 [2021-03-25 11:24:41 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 310/1251] eta: 0:08:09 lr: 0.000945 loss: 4.0006 (3.8291) grad_norm: 1.0150 (1.0193) time: 0.5012 [2021-03-25 11:24:46 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 320/1251] eta: 0:08:03 lr: 0.000945 loss: 3.9457 (3.8293) grad_norm: 1.0607 (1.0205) time: 0.5071 [2021-03-25 11:24:51 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 330/1251] eta: 0:07:58 lr: 0.000945 loss: 3.9457 (3.8281) grad_norm: 1.0004 (1.0198) time: 0.5110 [2021-03-25 11:24:56 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 340/1251] eta: 0:07:52 lr: 0.000945 loss: 3.9192 (3.8264) grad_norm: 0.9997 (1.0187) time: 0.5058 [2021-03-25 11:25:01 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 350/1251] eta: 0:07:47 lr: 0.000945 loss: 3.9736 (3.8250) grad_norm: 0.9851 (1.0180) time: 0.5024 [2021-03-25 11:25:06 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 360/1251] eta: 0:07:41 lr: 0.000945 loss: 3.8956 (3.8240) grad_norm: 0.9591 (1.0165) time: 0.5049 [2021-03-25 11:25:11 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 370/1251] eta: 0:07:35 lr: 0.000945 loss: 3.8311 (3.8197) grad_norm: 0.9647 (1.0160) time: 0.5025 [2021-03-25 11:25:16 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 380/1251] eta: 0:07:30 lr: 0.000945 loss: 3.8311 (3.8228) grad_norm: 1.0424 (1.0192) time: 0.5021 [2021-03-25 11:25:21 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 390/1251] eta: 0:07:24 lr: 0.000945 loss: 3.9701 (3.8249) grad_norm: 1.0534 (1.0202) time: 0.5019 [2021-03-25 11:25:26 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 400/1251] eta: 0:07:19 lr: 0.000945 loss: 3.9286 (3.8254) grad_norm: 1.0534 (1.0212) time: 0.4963 [2021-03-25 11:25:31 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 410/1251] eta: 0:07:13 lr: 0.000945 loss: 3.8558 (3.8198) grad_norm: 0.9911 (1.0211) time: 0.5002 [2021-03-25 11:25:37 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 420/1251] eta: 0:07:08 lr: 0.000945 loss: 3.7273 (3.8182) grad_norm: 0.9751 (1.0194) time: 0.5115 [2021-03-25 11:25:42 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 430/1251] eta: 0:07:03 lr: 0.000945 loss: 3.7582 (3.8175) grad_norm: 0.9572 (1.0184) time: 0.5104 [2021-03-25 11:25:47 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 440/1251] eta: 0:06:58 lr: 0.000945 loss: 3.6869 (3.8130) grad_norm: 0.9909 (1.0202) time: 0.5078 [2021-03-25 11:25:52 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 450/1251] eta: 0:06:52 lr: 0.000945 loss: 3.7673 (3.8117) grad_norm: 1.0224 (1.0203) time: 0.5082 [2021-03-25 11:25:57 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 460/1251] eta: 0:06:47 lr: 0.000945 loss: 3.8714 (3.8055) grad_norm: 0.9967 (1.0194) time: 0.5062 [2021-03-25 11:26:02 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 470/1251] eta: 0:06:42 lr: 0.000945 loss: 3.8832 (3.8076) grad_norm: 0.9502 (1.0196) time: 0.5060 [2021-03-25 11:26:07 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 480/1251] eta: 0:06:36 lr: 0.000945 loss: 4.0070 (3.8103) grad_norm: 1.0137 (1.0200) time: 0.5072 [2021-03-25 11:26:12 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 490/1251] eta: 0:06:31 lr: 0.000945 loss: 4.0070 (3.8125) grad_norm: 1.0582 (1.0212) time: 0.5071 [2021-03-25 11:26:17 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 500/1251] eta: 0:06:26 lr: 0.000945 loss: 3.9799 (3.8121) grad_norm: 0.9933 (1.0210) time: 0.5000 [2021-03-25 11:26:22 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 510/1251] eta: 0:06:20 lr: 0.000945 loss: 3.8827 (3.8126) grad_norm: 0.9740 (1.0207) time: 0.5028 [2021-03-25 11:26:27 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 520/1251] eta: 0:06:15 lr: 0.000945 loss: 3.8724 (3.8103) grad_norm: 0.9783 (1.0214) time: 0.5081 [2021-03-25 11:26:32 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 530/1251] eta: 0:06:10 lr: 0.000945 loss: 4.0381 (3.8127) grad_norm: 1.0048 (1.0227) time: 0.5056 [2021-03-25 11:26:37 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 540/1251] eta: 0:06:05 lr: 0.000945 loss: 4.0572 (3.8149) grad_norm: 0.9953 (1.0212) time: 0.5012 [2021-03-25 11:26:42 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 550/1251] eta: 0:06:00 lr: 0.000945 loss: 4.0350 (3.8192) grad_norm: 0.9691 (1.0209) time: 0.5124 [2021-03-25 11:26:48 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 560/1251] eta: 0:05:54 lr: 0.000945 loss: 3.9466 (3.8173) grad_norm: 0.9698 (1.0201) time: 0.5167 [2021-03-25 11:26:53 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 570/1251] eta: 0:05:49 lr: 0.000945 loss: 3.7149 (3.8150) grad_norm: 0.9837 (1.0201) time: 0.5065 [2021-03-25 11:26:58 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 580/1251] eta: 0:05:44 lr: 0.000945 loss: 3.7023 (3.8126) grad_norm: 0.9914 (1.0198) time: 0.5040 [2021-03-25 11:27:03 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 590/1251] eta: 0:05:39 lr: 0.000945 loss: 3.9749 (3.8139) grad_norm: 0.9585 (1.0187) time: 0.5045 [2021-03-25 11:27:08 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 600/1251] eta: 0:05:34 lr: 0.000945 loss: 3.8244 (3.8110) grad_norm: 0.9703 (1.0183) time: 0.5108 [2021-03-25 11:27:13 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 610/1251] eta: 0:05:28 lr: 0.000945 loss: 3.8244 (3.8117) grad_norm: 0.9703 (1.0179) time: 0.5101 [2021-03-25 11:27:18 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 620/1251] eta: 0:05:23 lr: 0.000945 loss: 3.9172 (3.8136) grad_norm: 0.9986 (1.0185) time: 0.5060 [2021-03-25 11:27:23 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 630/1251] eta: 0:05:18 lr: 0.000945 loss: 3.8695 (3.8141) grad_norm: 1.0219 (1.0185) time: 0.5032 [2021-03-25 11:27:28 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 640/1251] eta: 0:05:13 lr: 0.000945 loss: 3.8441 (3.8130) grad_norm: 1.0383 (1.0208) time: 0.5036 [2021-03-25 11:27:33 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 650/1251] eta: 0:05:08 lr: 0.000945 loss: 3.8447 (3.8136) grad_norm: 1.0954 (1.0227) time: 0.5057 [2021-03-25 11:27:38 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 660/1251] eta: 0:05:02 lr: 0.000945 loss: 3.8447 (3.8108) grad_norm: 1.0559 (1.0231) time: 0.5055 [2021-03-25 11:27:43 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 670/1251] eta: 0:04:57 lr: 0.000945 loss: 4.0231 (3.8116) grad_norm: 1.0356 (1.0232) time: 0.5096 [2021-03-25 11:27:48 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 680/1251] eta: 0:04:52 lr: 0.000945 loss: 4.1038 (3.8109) grad_norm: 1.0419 (1.0239) time: 0.5066 [2021-03-25 11:27:53 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 690/1251] eta: 0:04:47 lr: 0.000945 loss: 3.9395 (3.8128) grad_norm: 0.9938 (1.0230) time: 0.5058 [2021-03-25 11:27:58 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 700/1251] eta: 0:04:42 lr: 0.000945 loss: 3.8954 (3.8121) grad_norm: 0.9747 (1.0236) time: 0.5063 [2021-03-25 11:28:04 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 710/1251] eta: 0:04:37 lr: 0.000945 loss: 3.7511 (3.8086) grad_norm: 1.0334 (1.0245) time: 0.5051 [2021-03-25 11:28:09 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 720/1251] eta: 0:04:31 lr: 0.000945 loss: 3.7745 (3.8088) grad_norm: 0.9519 (1.0236) time: 0.5054 [2021-03-25 11:28:14 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 730/1251] eta: 0:04:26 lr: 0.000945 loss: 3.8678 (3.8071) grad_norm: 0.9438 (1.0236) time: 0.5068 [2021-03-25 11:28:19 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 740/1251] eta: 0:04:21 lr: 0.000945 loss: 3.7826 (3.8038) grad_norm: 0.9951 (1.0228) time: 0.5188 [2021-03-25 11:28:24 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 750/1251] eta: 0:04:16 lr: 0.000945 loss: 3.7826 (3.8050) grad_norm: 0.9853 (1.0225) time: 0.5179 [2021-03-25 11:28:29 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 760/1251] eta: 0:04:11 lr: 0.000945 loss: 4.0229 (3.8085) grad_norm: 0.9583 (1.0223) time: 0.5134 [2021-03-25 11:28:34 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 770/1251] eta: 0:04:06 lr: 0.000945 loss: 4.0938 (3.8122) grad_norm: 1.0054 (1.0229) time: 0.5158 [2021-03-25 11:28:39 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 780/1251] eta: 0:04:01 lr: 0.000945 loss: 3.9570 (3.8079) grad_norm: 1.0520 (1.0233) time: 0.5072 [2021-03-25 11:28:45 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 790/1251] eta: 0:03:56 lr: 0.000945 loss: 3.4880 (3.8049) grad_norm: 1.0182 (1.0239) time: 0.5148 [2021-03-25 11:28:50 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 800/1251] eta: 0:03:51 lr: 0.000945 loss: 3.8121 (3.8067) grad_norm: 0.9835 (1.0242) time: 0.5199 [2021-03-25 11:28:55 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 810/1251] eta: 0:03:45 lr: 0.000945 loss: 3.9308 (3.8084) grad_norm: 0.9585 (1.0235) time: 0.5040 [2021-03-25 11:29:00 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 820/1251] eta: 0:03:40 lr: 0.000944 loss: 3.9130 (3.8087) grad_norm: 0.9912 (1.0237) time: 0.5010 [2021-03-25 11:29:05 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 830/1251] eta: 0:03:35 lr: 0.000944 loss: 3.9208 (3.8114) grad_norm: 0.9705 (1.0228) time: 0.5025 [2021-03-25 11:29:10 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 840/1251] eta: 0:03:30 lr: 0.000944 loss: 3.8758 (3.8091) grad_norm: 0.9539 (1.0221) time: 0.5074 [2021-03-25 11:29:15 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 850/1251] eta: 0:03:25 lr: 0.000944 loss: 3.7515 (3.8085) grad_norm: 0.9265 (1.0211) time: 0.5073 [2021-03-25 11:29:20 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 860/1251] eta: 0:03:20 lr: 0.000944 loss: 3.9597 (3.8094) grad_norm: 0.9404 (1.0212) time: 0.5032 [2021-03-25 11:29:25 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 870/1251] eta: 0:03:14 lr: 0.000944 loss: 3.9472 (3.8098) grad_norm: 0.9825 (1.0208) time: 0.5038 [2021-03-25 11:29:30 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 880/1251] eta: 0:03:09 lr: 0.000944 loss: 3.8079 (3.8087) grad_norm: 0.9600 (1.0206) time: 0.5011 [2021-03-25 11:29:35 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 890/1251] eta: 0:03:04 lr: 0.000944 loss: 3.4579 (3.8043) grad_norm: 0.9681 (1.0205) time: 0.5057 [2021-03-25 11:29:40 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 900/1251] eta: 0:02:59 lr: 0.000944 loss: 3.5025 (3.8043) grad_norm: 0.9681 (1.0203) time: 0.5069 [2021-03-25 11:29:45 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 910/1251] eta: 0:02:54 lr: 0.000944 loss: 3.8333 (3.8052) grad_norm: 0.9679 (1.0201) time: 0.5031 [2021-03-25 11:29:50 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 920/1251] eta: 0:02:49 lr: 0.000944 loss: 3.7708 (3.8034) grad_norm: 0.9679 (1.0194) time: 0.5061 [2021-03-25 11:29:55 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 930/1251] eta: 0:02:44 lr: 0.000944 loss: 3.7187 (3.8028) grad_norm: 0.9652 (1.0192) time: 0.5073 [2021-03-25 11:30:00 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 940/1251] eta: 0:02:38 lr: 0.000944 loss: 3.7888 (3.8006) grad_norm: 0.9946 (1.0194) time: 0.5088 [2021-03-25 11:30:05 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 950/1251] eta: 0:02:33 lr: 0.000944 loss: 3.8120 (3.7992) grad_norm: 0.9946 (1.0194) time: 0.5058 [2021-03-25 11:30:10 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 960/1251] eta: 0:02:28 lr: 0.000944 loss: 3.5560 (3.7982) grad_norm: 0.9370 (1.0192) time: 0.4999 [2021-03-25 11:30:16 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 970/1251] eta: 0:02:23 lr: 0.000944 loss: 3.9815 (3.7991) grad_norm: 0.9547 (1.0189) time: 0.5028 [2021-03-25 11:30:21 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 980/1251] eta: 0:02:18 lr: 0.000944 loss: 4.0120 (3.7983) grad_norm: 0.9905 (1.0194) time: 0.5042 [2021-03-25 11:30:26 swin_small_patch4_window7_224] INFO: Epoch: [45] [ 990/1251] eta: 0:02:13 lr: 0.000944 loss: 3.8390 (3.7981) grad_norm: 1.0524 (1.0194) time: 0.5065 [2021-03-25 11:30:31 swin_small_patch4_window7_224] INFO: Epoch: [45] [1000/1251] eta: 0:02:08 lr: 0.000944 loss: 3.8434 (3.7976) grad_norm: 0.9814 (1.0191) time: 0.5106 [2021-03-25 11:30:36 swin_small_patch4_window7_224] INFO: Epoch: [45] [1010/1251] eta: 0:02:03 lr: 0.000944 loss: 3.8162 (3.7979) grad_norm: 0.9861 (1.0194) time: 0.5070 [2021-03-25 11:30:41 swin_small_patch4_window7_224] INFO: Epoch: [45] [1020/1251] eta: 0:01:57 lr: 0.000944 loss: 3.8939 (3.7993) grad_norm: 0.9803 (1.0192) time: 0.5070 [2021-03-25 11:30:46 swin_small_patch4_window7_224] INFO: Epoch: [45] [1030/1251] eta: 0:01:52 lr: 0.000944 loss: 4.0101 (3.8019) grad_norm: 0.9832 (1.0201) time: 0.5078 [2021-03-25 11:30:51 swin_small_patch4_window7_224] INFO: Epoch: [45] [1040/1251] eta: 0:01:47 lr: 0.000944 loss: 3.9466 (3.8012) grad_norm: 1.0471 (1.0201) time: 0.5006 [2021-03-25 11:30:56 swin_small_patch4_window7_224] INFO: Epoch: [45] [1050/1251] eta: 0:01:42 lr: 0.000944 loss: 3.9256 (3.8029) grad_norm: 0.9728 (1.0195) time: 0.4973 [2021-03-25 11:31:01 swin_small_patch4_window7_224] INFO: Epoch: [45] [1060/1251] eta: 0:01:37 lr: 0.000944 loss: 3.7889 (3.8001) grad_norm: 0.9728 (1.0197) time: 0.5016 [2021-03-25 11:31:06 swin_small_patch4_window7_224] INFO: Epoch: [45] [1070/1251] eta: 0:01:32 lr: 0.000944 loss: 3.6850 (3.8002) grad_norm: 1.0466 (1.0204) time: 0.5082 [2021-03-25 11:31:11 swin_small_patch4_window7_224] INFO: Epoch: [45] [1080/1251] eta: 0:01:27 lr: 0.000944 loss: 3.8816 (3.7994) grad_norm: 1.0389 (1.0206) time: 0.5056 [2021-03-25 11:31:16 swin_small_patch4_window7_224] INFO: Epoch: [45] [1090/1251] eta: 0:01:22 lr: 0.000944 loss: 3.8946 (3.8001) grad_norm: 0.9886 (1.0206) time: 0.5032 [2021-03-25 11:31:21 swin_small_patch4_window7_224] INFO: Epoch: [45] [1100/1251] eta: 0:01:17 lr: 0.000944 loss: 3.8946 (3.7981) grad_norm: 0.9600 (1.0207) time: 0.5101 [2021-03-25 11:31:26 swin_small_patch4_window7_224] INFO: Epoch: [45] [1110/1251] eta: 0:01:11 lr: 0.000944 loss: 3.7154 (3.7975) grad_norm: 1.0063 (1.0204) time: 0.5088 [2021-03-25 11:31:31 swin_small_patch4_window7_224] INFO: Epoch: [45] [1120/1251] eta: 0:01:06 lr: 0.000944 loss: 4.0164 (3.7999) grad_norm: 1.0085 (1.0203) time: 0.5054 [2021-03-25 11:31:36 swin_small_patch4_window7_224] INFO: Epoch: [45] [1130/1251] eta: 0:01:01 lr: 0.000944 loss: 3.9904 (3.7979) grad_norm: 1.0101 (1.0203) time: 0.5033 [2021-03-25 11:31:41 swin_small_patch4_window7_224] INFO: Epoch: [45] [1140/1251] eta: 0:00:56 lr: 0.000944 loss: 3.6312 (3.7965) grad_norm: 0.9997 (1.0204) time: 0.5052 [2021-03-25 11:31:47 swin_small_patch4_window7_224] INFO: Epoch: [45] [1150/1251] eta: 0:00:51 lr: 0.000944 loss: 3.7080 (3.7949) grad_norm: 0.9706 (1.0202) time: 0.5089 [2021-03-25 11:31:52 swin_small_patch4_window7_224] INFO: Epoch: [45] [1160/1251] eta: 0:00:46 lr: 0.000944 loss: 3.7811 (3.7951) grad_norm: 1.0012 (1.0202) time: 0.5124 [2021-03-25 11:31:57 swin_small_patch4_window7_224] INFO: Epoch: [45] [1170/1251] eta: 0:00:41 lr: 0.000944 loss: 3.6238 (3.7920) grad_norm: 1.0104 (1.0198) time: 0.5105 [2021-03-25 11:32:02 swin_small_patch4_window7_224] INFO: Epoch: [45] [1180/1251] eta: 0:00:36 lr: 0.000944 loss: 3.5338 (3.7907) grad_norm: 0.9779 (1.0198) time: 0.5031 [2021-03-25 11:32:07 swin_small_patch4_window7_224] INFO: Epoch: [45] [1190/1251] eta: 0:00:31 lr: 0.000944 loss: 3.7882 (3.7898) grad_norm: 1.0041 (1.0196) time: 0.5074 [2021-03-25 11:32:12 swin_small_patch4_window7_224] INFO: Epoch: [45] [1200/1251] eta: 0:00:26 lr: 0.000944 loss: 3.7469 (3.7880) grad_norm: 1.0033 (1.0198) time: 0.5109 [2021-03-25 11:32:17 swin_small_patch4_window7_224] INFO: Epoch: [45] [1210/1251] eta: 0:00:20 lr: 0.000944 loss: 3.4830 (3.7866) grad_norm: 1.0514 (1.0204) time: 0.5093 [2021-03-25 11:32:22 swin_small_patch4_window7_224] INFO: Epoch: [45] [1220/1251] eta: 0:00:15 lr: 0.000944 loss: 4.0376 (3.7880) grad_norm: 1.0383 (1.0202) time: 0.5053 [2021-03-25 11:32:27 swin_small_patch4_window7_224] INFO: Epoch: [45] [1230/1251] eta: 0:00:10 lr: 0.000944 loss: 4.0582 (3.7875) grad_norm: 0.9881 (1.0202) time: 0.5016 [2021-03-25 11:32:32 swin_small_patch4_window7_224] INFO: Epoch: [45] [1240/1251] eta: 0:00:05 lr: 0.000944 loss: 3.7694 (3.7894) grad_norm: 0.9874 (1.0204) time: 0.5008 [2021-03-25 11:32:37 swin_small_patch4_window7_224] INFO: Epoch: [45] [1250/1251] eta: 0:00:00 lr: 0.000944 loss: 3.8975 (3.7901) grad_norm: 1.0438 (1.0204) time: 0.5016 [2021-03-25 11:33:15 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.8191 (0.8191) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-25 11:33:16 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.0857 (1.0734) acc1: 71.8750 (74.1477) acc5: 92.1875 (93.0398) [2021-03-25 11:33:17 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.1628 (1.1484) acc1: 71.8750 (72.8423) acc5: 92.1875 (91.6667) [2021-03-25 11:33:18 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.2151 (1.1869) acc1: 70.3125 (72.1270) acc5: 90.6250 (91.3810) [2021-03-25 11:33:19 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2922 (1.2107) acc1: 70.3125 (71.5701) acc5: 90.6250 (91.1204) [2021-03-25 11:33:20 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2620 (1.2076) acc1: 68.7500 (71.2640) acc5: 90.6250 (91.1040) [2021-03-25 11:33:23 swin_small_patch4_window7_224] INFO: * Acc@1 72.044 Acc@5 91.262 loss 1.188 [2021-03-25 11:33:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.0% [2021-03-25 11:33:23 swin_small_patch4_window7_224] INFO: Max accuracy: 72.04% [2021-03-25 11:33:27 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 0/1251] eta: 1:25:49 lr: 0.000944 loss: 2.9142 (2.9142) grad_norm: 1.0647 (1.0647) time: 4.1166 [2021-03-25 11:33:33 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 10/1251] eta: 0:17:39 lr: 0.000944 loss: 3.9283 (3.6523) grad_norm: 1.0647 (1.0383) time: 0.8537 [2021-03-25 11:33:38 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 20/1251] eta: 0:14:06 lr: 0.000944 loss: 3.9194 (3.6500) grad_norm: 0.9915 (1.0258) time: 0.5164 [2021-03-25 11:33:43 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 30/1251] eta: 0:12:47 lr: 0.000944 loss: 3.9149 (3.7320) grad_norm: 1.0470 (1.0449) time: 0.5051 [2021-03-25 11:33:48 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 40/1251] eta: 0:12:08 lr: 0.000944 loss: 3.9508 (3.7960) grad_norm: 1.0470 (1.0420) time: 0.5111 [2021-03-25 11:33:53 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 50/1251] eta: 0:11:41 lr: 0.000944 loss: 3.9318 (3.8122) grad_norm: 1.0347 (1.0544) time: 0.5138 [2021-03-25 11:33:58 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 60/1251] eta: 0:11:20 lr: 0.000944 loss: 3.9721 (3.8465) grad_norm: 1.0133 (1.0370) time: 0.5098 [2021-03-25 11:34:03 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 70/1251] eta: 0:11:06 lr: 0.000944 loss: 3.9893 (3.8715) grad_norm: 0.9666 (1.0311) time: 0.5139 [2021-03-25 11:34:08 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 80/1251] eta: 0:10:51 lr: 0.000944 loss: 3.8362 (3.8585) grad_norm: 0.9770 (1.0248) time: 0.5100 [2021-03-25 11:34:13 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 90/1251] eta: 0:10:39 lr: 0.000943 loss: 3.9322 (3.8802) grad_norm: 0.9707 (1.0169) time: 0.5041 [2021-03-25 11:34:18 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 100/1251] eta: 0:10:28 lr: 0.000943 loss: 3.9322 (3.8570) grad_norm: 0.9707 (1.0186) time: 0.5041 [2021-03-25 11:34:23 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 110/1251] eta: 0:10:19 lr: 0.000943 loss: 3.8569 (3.8259) grad_norm: 0.9853 (1.0176) time: 0.5060 [2021-03-25 11:34:28 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 120/1251] eta: 0:10:10 lr: 0.000943 loss: 3.8569 (3.8211) grad_norm: 0.9726 (1.0147) time: 0.5062 [2021-03-25 11:34:34 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 130/1251] eta: 0:10:02 lr: 0.000943 loss: 3.8152 (3.8199) grad_norm: 1.0492 (1.0266) time: 0.5062 [2021-03-25 11:34:39 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 140/1251] eta: 0:09:54 lr: 0.000943 loss: 3.9315 (3.8321) grad_norm: 1.0492 (1.0276) time: 0.5065 [2021-03-25 11:34:44 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 150/1251] eta: 0:09:46 lr: 0.000943 loss: 4.0242 (3.8436) grad_norm: 0.9373 (1.0238) time: 0.5020 [2021-03-25 11:34:49 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 160/1251] eta: 0:09:39 lr: 0.000943 loss: 3.9160 (3.8376) grad_norm: 0.9802 (1.0224) time: 0.5069 [2021-03-25 11:34:54 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 170/1251] eta: 0:09:32 lr: 0.000943 loss: 3.8062 (3.8261) grad_norm: 0.9802 (1.0190) time: 0.5087 [2021-03-25 11:34:59 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 180/1251] eta: 0:09:26 lr: 0.000943 loss: 3.7523 (3.8206) grad_norm: 0.9664 (1.0216) time: 0.5087 [2021-03-25 11:35:04 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 190/1251] eta: 0:09:20 lr: 0.000943 loss: 3.8193 (3.8193) grad_norm: 0.9783 (1.0226) time: 0.5114 [2021-03-25 11:35:09 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 200/1251] eta: 0:09:14 lr: 0.000943 loss: 3.9827 (3.8236) grad_norm: 0.9542 (1.0211) time: 0.5194 [2021-03-25 11:35:14 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 210/1251] eta: 0:09:08 lr: 0.000943 loss: 3.7165 (3.8102) grad_norm: 1.0200 (1.0231) time: 0.5193 [2021-03-25 11:35:19 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 220/1251] eta: 0:09:02 lr: 0.000943 loss: 3.7229 (3.8203) grad_norm: 1.0464 (1.0260) time: 0.5043 [2021-03-25 11:35:24 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 230/1251] eta: 0:08:55 lr: 0.000943 loss: 4.0488 (3.8216) grad_norm: 1.0049 (1.0241) time: 0.4998 [2021-03-25 11:35:29 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 240/1251] eta: 0:08:49 lr: 0.000943 loss: 3.7044 (3.8194) grad_norm: 0.9805 (1.0235) time: 0.5006 [2021-03-25 11:35:34 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 250/1251] eta: 0:08:43 lr: 0.000943 loss: 3.9271 (3.8251) grad_norm: 0.9735 (1.0242) time: 0.4987 [2021-03-25 11:35:39 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 260/1251] eta: 0:08:37 lr: 0.000943 loss: 4.0049 (3.8263) grad_norm: 0.9735 (1.0227) time: 0.5006 [2021-03-25 11:35:45 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 270/1251] eta: 0:08:31 lr: 0.000943 loss: 3.7645 (3.8174) grad_norm: 0.9975 (1.0221) time: 0.5091 [2021-03-25 11:35:50 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 280/1251] eta: 0:08:25 lr: 0.000943 loss: 3.5639 (3.8117) grad_norm: 0.9975 (1.0210) time: 0.5103 [2021-03-25 11:35:55 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 290/1251] eta: 0:08:20 lr: 0.000943 loss: 3.9182 (3.8113) grad_norm: 0.9730 (1.0200) time: 0.5068 [2021-03-25 11:36:00 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 300/1251] eta: 0:08:14 lr: 0.000943 loss: 3.9838 (3.8121) grad_norm: 1.0456 (1.0220) time: 0.5073 [2021-03-25 11:36:05 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 310/1251] eta: 0:08:08 lr: 0.000943 loss: 3.5603 (3.7990) grad_norm: 1.0476 (1.0220) time: 0.5005 [2021-03-25 11:36:10 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 320/1251] eta: 0:08:03 lr: 0.000943 loss: 3.5263 (3.7925) grad_norm: 1.0229 (1.0213) time: 0.5018 [2021-03-25 11:36:15 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 330/1251] eta: 0:07:57 lr: 0.000943 loss: 3.4750 (3.7828) grad_norm: 0.9696 (1.0198) time: 0.5068 [2021-03-25 11:36:20 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 340/1251] eta: 0:07:51 lr: 0.000943 loss: 3.7298 (3.7817) grad_norm: 0.9891 (1.0195) time: 0.5031 [2021-03-25 11:36:25 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 350/1251] eta: 0:07:46 lr: 0.000943 loss: 3.7408 (3.7800) grad_norm: 1.0224 (1.0187) time: 0.5060 [2021-03-25 11:36:30 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 360/1251] eta: 0:07:41 lr: 0.000943 loss: 3.6190 (3.7761) grad_norm: 1.0141 (1.0203) time: 0.5091 [2021-03-25 11:36:35 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 370/1251] eta: 0:07:35 lr: 0.000943 loss: 3.4736 (3.7733) grad_norm: 0.9999 (1.0203) time: 0.5065 [2021-03-25 11:36:40 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 380/1251] eta: 0:07:30 lr: 0.000943 loss: 3.7041 (3.7756) grad_norm: 0.9962 (1.0192) time: 0.5035 [2021-03-25 11:36:45 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 390/1251] eta: 0:07:24 lr: 0.000943 loss: 3.7571 (3.7722) grad_norm: 0.9633 (1.0190) time: 0.5037 [2021-03-25 11:36:50 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 400/1251] eta: 0:07:19 lr: 0.000943 loss: 3.9114 (3.7802) grad_norm: 1.0379 (1.0224) time: 0.5097 [2021-03-25 11:36:55 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 410/1251] eta: 0:07:14 lr: 0.000943 loss: 3.8972 (3.7794) grad_norm: 1.0681 (1.0233) time: 0.5075 [2021-03-25 11:37:00 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 420/1251] eta: 0:07:08 lr: 0.000943 loss: 3.7435 (3.7797) grad_norm: 1.0067 (1.0233) time: 0.5047 [2021-03-25 11:37:05 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 430/1251] eta: 0:07:03 lr: 0.000943 loss: 3.9416 (3.7807) grad_norm: 1.0153 (1.0241) time: 0.5074 [2021-03-25 11:37:11 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 440/1251] eta: 0:06:57 lr: 0.000943 loss: 3.7526 (3.7778) grad_norm: 1.0169 (1.0239) time: 0.5042 [2021-03-25 11:37:16 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 450/1251] eta: 0:06:52 lr: 0.000943 loss: 3.6690 (3.7778) grad_norm: 0.9598 (1.0223) time: 0.5031 [2021-03-25 11:37:21 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 460/1251] eta: 0:06:47 lr: 0.000943 loss: 3.5759 (3.7750) grad_norm: 0.9625 (1.0232) time: 0.5075 [2021-03-25 11:37:26 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 470/1251] eta: 0:06:42 lr: 0.000943 loss: 3.6510 (3.7751) grad_norm: 1.0219 (1.0236) time: 0.5106 [2021-03-25 11:37:31 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 480/1251] eta: 0:06:36 lr: 0.000943 loss: 3.6841 (3.7728) grad_norm: 1.0187 (1.0244) time: 0.5033 [2021-03-25 11:37:36 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 490/1251] eta: 0:06:31 lr: 0.000943 loss: 3.8774 (3.7766) grad_norm: 1.0282 (1.0254) time: 0.4962 [2021-03-25 11:37:41 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 500/1251] eta: 0:06:25 lr: 0.000943 loss: 4.0916 (3.7836) grad_norm: 1.0577 (1.0261) time: 0.4964 [2021-03-25 11:37:46 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 510/1251] eta: 0:06:20 lr: 0.000943 loss: 4.0147 (3.7852) grad_norm: 1.0767 (1.0285) time: 0.4974 [2021-03-25 11:37:51 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 520/1251] eta: 0:06:15 lr: 0.000943 loss: 4.0147 (3.7888) grad_norm: 1.0732 (1.0287) time: 0.4991 [2021-03-25 11:37:56 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 530/1251] eta: 0:06:09 lr: 0.000943 loss: 3.9898 (3.7929) grad_norm: 0.9869 (1.0283) time: 0.5028 [2021-03-25 11:38:01 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 540/1251] eta: 0:06:04 lr: 0.000943 loss: 3.8175 (3.7886) grad_norm: 1.0141 (1.0287) time: 0.5104 [2021-03-25 11:38:06 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 550/1251] eta: 0:06:00 lr: 0.000943 loss: 3.5749 (3.7893) grad_norm: 1.0654 (1.0293) time: 0.5266 [2021-03-25 11:38:11 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 560/1251] eta: 0:05:54 lr: 0.000943 loss: 3.9464 (3.7931) grad_norm: 1.0408 (1.0285) time: 0.5223 [2021-03-25 11:38:16 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 570/1251] eta: 0:05:49 lr: 0.000943 loss: 4.0001 (3.7957) grad_norm: 1.0169 (1.0289) time: 0.5063 [2021-03-25 11:38:22 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 580/1251] eta: 0:05:44 lr: 0.000943 loss: 3.7693 (3.7962) grad_norm: 0.9812 (1.0279) time: 0.5101 [2021-03-25 11:38:27 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 590/1251] eta: 0:05:39 lr: 0.000943 loss: 3.7693 (3.7945) grad_norm: 0.9707 (1.0276) time: 0.5128 [2021-03-25 11:38:32 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 600/1251] eta: 0:05:34 lr: 0.000943 loss: 3.5976 (3.7913) grad_norm: 0.9893 (1.0272) time: 0.5048 [2021-03-25 11:38:37 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 610/1251] eta: 0:05:28 lr: 0.000942 loss: 3.4078 (3.7863) grad_norm: 1.0147 (1.0278) time: 0.5035 [2021-03-25 11:38:42 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 620/1251] eta: 0:05:23 lr: 0.000942 loss: 3.6516 (3.7859) grad_norm: 1.0141 (1.0280) time: 0.5111 [2021-03-25 11:38:47 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 630/1251] eta: 0:05:18 lr: 0.000942 loss: 3.6516 (3.7828) grad_norm: 0.9613 (1.0273) time: 0.5099 [2021-03-25 11:38:52 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 640/1251] eta: 0:05:13 lr: 0.000942 loss: 3.7860 (3.7871) grad_norm: 0.9269 (1.0269) time: 0.4996 [2021-03-25 11:38:57 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 650/1251] eta: 0:05:07 lr: 0.000942 loss: 3.9777 (3.7842) grad_norm: 0.9579 (1.0252) time: 0.4981 [2021-03-25 11:39:02 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 660/1251] eta: 0:05:02 lr: 0.000942 loss: 4.0920 (3.7877) grad_norm: 0.9563 (1.0243) time: 0.5030 [2021-03-25 11:39:07 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 670/1251] eta: 0:04:57 lr: 0.000942 loss: 3.9688 (3.7854) grad_norm: 0.9817 (1.0247) time: 0.5043 [2021-03-25 11:39:12 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 680/1251] eta: 0:04:52 lr: 0.000942 loss: 3.5384 (3.7845) grad_norm: 1.0406 (1.0252) time: 0.5058 [2021-03-25 11:39:17 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 690/1251] eta: 0:04:47 lr: 0.000942 loss: 3.8349 (3.7855) grad_norm: 1.0282 (1.0251) time: 0.5014 [2021-03-25 11:39:22 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 700/1251] eta: 0:04:42 lr: 0.000942 loss: 3.6575 (3.7818) grad_norm: 0.9580 (1.0247) time: 0.5015 [2021-03-25 11:39:27 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 710/1251] eta: 0:04:36 lr: 0.000942 loss: 3.6575 (3.7834) grad_norm: 0.9428 (1.0243) time: 0.5056 [2021-03-25 11:39:32 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 720/1251] eta: 0:04:31 lr: 0.000942 loss: 3.9793 (3.7848) grad_norm: 0.9689 (1.0240) time: 0.5044 [2021-03-25 11:39:37 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 730/1251] eta: 0:04:26 lr: 0.000942 loss: 3.9793 (3.7853) grad_norm: 1.0047 (1.0245) time: 0.5117 [2021-03-25 11:39:43 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 740/1251] eta: 0:04:21 lr: 0.000942 loss: 4.0288 (3.7860) grad_norm: 1.1393 (1.0262) time: 0.5337 [2021-03-25 11:39:48 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 750/1251] eta: 0:04:16 lr: 0.000942 loss: 3.8025 (3.7815) grad_norm: 1.1454 (1.0271) time: 0.5283 [2021-03-25 11:39:53 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 760/1251] eta: 0:04:11 lr: 0.000942 loss: 3.8025 (3.7820) grad_norm: 1.1289 (1.0282) time: 0.5093 [2021-03-25 11:39:58 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 770/1251] eta: 0:04:06 lr: 0.000942 loss: 3.8958 (3.7849) grad_norm: 1.0734 (1.0284) time: 0.5094 [2021-03-25 11:40:03 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 780/1251] eta: 0:04:01 lr: 0.000942 loss: 3.8730 (3.7857) grad_norm: 1.0283 (1.0284) time: 0.5077 [2021-03-25 11:40:08 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 790/1251] eta: 0:03:56 lr: 0.000942 loss: 3.9739 (3.7888) grad_norm: 0.9391 (1.0279) time: 0.5092 [2021-03-25 11:40:13 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 800/1251] eta: 0:03:50 lr: 0.000942 loss: 3.9475 (3.7871) grad_norm: 0.9988 (1.0288) time: 0.5115 [2021-03-25 11:40:18 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 810/1251] eta: 0:03:45 lr: 0.000942 loss: 3.4674 (3.7830) grad_norm: 1.0378 (1.0285) time: 0.5085 [2021-03-25 11:40:24 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 820/1251] eta: 0:03:40 lr: 0.000942 loss: 3.5795 (3.7821) grad_norm: 0.9565 (1.0278) time: 0.5117 [2021-03-25 11:40:29 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 830/1251] eta: 0:03:35 lr: 0.000942 loss: 3.5795 (3.7785) grad_norm: 0.9565 (1.0274) time: 0.5072 [2021-03-25 11:40:34 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 840/1251] eta: 0:03:30 lr: 0.000942 loss: 3.5731 (3.7801) grad_norm: 0.9724 (1.0271) time: 0.5027 [2021-03-25 11:40:39 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 850/1251] eta: 0:03:25 lr: 0.000942 loss: 3.8036 (3.7759) grad_norm: 1.0129 (1.0269) time: 0.5051 [2021-03-25 11:40:44 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 860/1251] eta: 0:03:20 lr: 0.000942 loss: 3.4331 (3.7744) grad_norm: 0.9915 (1.0266) time: 0.5039 [2021-03-25 11:40:49 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 870/1251] eta: 0:03:14 lr: 0.000942 loss: 3.7311 (3.7732) grad_norm: 0.9909 (1.0266) time: 0.5082 [2021-03-25 11:40:54 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 880/1251] eta: 0:03:09 lr: 0.000942 loss: 3.7060 (3.7711) grad_norm: 0.9647 (1.0262) time: 0.5101 [2021-03-25 11:40:59 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 890/1251] eta: 0:03:04 lr: 0.000942 loss: 3.7914 (3.7777) grad_norm: 0.9694 (1.0259) time: 0.5041 [2021-03-25 11:41:04 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 900/1251] eta: 0:02:59 lr: 0.000942 loss: 4.0025 (3.7783) grad_norm: 0.9487 (1.0248) time: 0.5008 [2021-03-25 11:41:09 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 910/1251] eta: 0:02:54 lr: 0.000942 loss: 3.8170 (3.7767) grad_norm: 0.9157 (1.0242) time: 0.5023 [2021-03-25 11:41:14 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 920/1251] eta: 0:02:49 lr: 0.000942 loss: 3.8170 (3.7790) grad_norm: 1.0183 (1.0251) time: 0.5081 [2021-03-25 11:41:19 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 930/1251] eta: 0:02:44 lr: 0.000942 loss: 3.8055 (3.7807) grad_norm: 1.0129 (1.0247) time: 0.5137 [2021-03-25 11:41:25 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 940/1251] eta: 0:02:39 lr: 0.000942 loss: 3.7762 (3.7800) grad_norm: 0.9705 (1.0241) time: 0.5187 [2021-03-25 11:41:30 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 950/1251] eta: 0:02:33 lr: 0.000942 loss: 3.9757 (3.7824) grad_norm: 0.9330 (1.0238) time: 0.5150 [2021-03-25 11:41:35 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 960/1251] eta: 0:02:28 lr: 0.000942 loss: 3.9915 (3.7854) grad_norm: 0.9732 (1.0237) time: 0.5062 [2021-03-25 11:41:40 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 970/1251] eta: 0:02:23 lr: 0.000942 loss: 3.9216 (3.7835) grad_norm: 0.9647 (1.0233) time: 0.5044 [2021-03-25 11:41:45 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 980/1251] eta: 0:02:18 lr: 0.000942 loss: 3.6407 (3.7827) grad_norm: 0.9624 (1.0232) time: 0.5043 [2021-03-25 11:41:50 swin_small_patch4_window7_224] INFO: Epoch: [46] [ 990/1251] eta: 0:02:13 lr: 0.000942 loss: 3.9233 (3.7826) grad_norm: 0.9858 (1.0231) time: 0.5070 [2021-03-25 11:41:55 swin_small_patch4_window7_224] INFO: Epoch: [46] [1000/1251] eta: 0:02:08 lr: 0.000942 loss: 3.8380 (3.7807) grad_norm: 1.0024 (1.0230) time: 0.5038 [2021-03-25 11:42:00 swin_small_patch4_window7_224] INFO: Epoch: [46] [1010/1251] eta: 0:02:03 lr: 0.000942 loss: 3.6531 (3.7792) grad_norm: 1.0288 (1.0237) time: 0.5105 [2021-03-25 11:42:05 swin_small_patch4_window7_224] INFO: Epoch: [46] [1020/1251] eta: 0:01:58 lr: 0.000942 loss: 3.6531 (3.7773) grad_norm: 1.0288 (1.0234) time: 0.5106 [2021-03-25 11:42:10 swin_small_patch4_window7_224] INFO: Epoch: [46] [1030/1251] eta: 0:01:52 lr: 0.000942 loss: 3.8226 (3.7774) grad_norm: 1.0626 (1.0245) time: 0.5012 [2021-03-25 11:42:15 swin_small_patch4_window7_224] INFO: Epoch: [46] [1040/1251] eta: 0:01:47 lr: 0.000942 loss: 3.9277 (3.7777) grad_norm: 1.0740 (1.0257) time: 0.5029 [2021-03-25 11:42:20 swin_small_patch4_window7_224] INFO: Epoch: [46] [1050/1251] eta: 0:01:42 lr: 0.000942 loss: 3.8790 (3.7768) grad_norm: 1.0356 (1.0256) time: 0.5025 [2021-03-25 11:42:25 swin_small_patch4_window7_224] INFO: Epoch: [46] [1060/1251] eta: 0:01:37 lr: 0.000942 loss: 3.6285 (3.7751) grad_norm: 1.0519 (1.0261) time: 0.5047 [2021-03-25 11:42:30 swin_small_patch4_window7_224] INFO: Epoch: [46] [1070/1251] eta: 0:01:32 lr: 0.000942 loss: 3.9429 (3.7755) grad_norm: 1.0574 (1.0259) time: 0.5021 [2021-03-25 11:42:35 swin_small_patch4_window7_224] INFO: Epoch: [46] [1080/1251] eta: 0:01:27 lr: 0.000942 loss: 3.7587 (3.7728) grad_norm: 0.9677 (1.0251) time: 0.5000 [2021-03-25 11:42:40 swin_small_patch4_window7_224] INFO: Epoch: [46] [1090/1251] eta: 0:01:22 lr: 0.000942 loss: 3.6969 (3.7731) grad_norm: 0.9314 (1.0240) time: 0.5086 [2021-03-25 11:42:45 swin_small_patch4_window7_224] INFO: Epoch: [46] [1100/1251] eta: 0:01:17 lr: 0.000942 loss: 3.8106 (3.7723) grad_norm: 0.9212 (1.0233) time: 0.5056 [2021-03-25 11:42:50 swin_small_patch4_window7_224] INFO: Epoch: [46] [1110/1251] eta: 0:01:11 lr: 0.000942 loss: 3.9246 (3.7725) grad_norm: 0.9766 (1.0234) time: 0.5036 [2021-03-25 11:42:56 swin_small_patch4_window7_224] INFO: Epoch: [46] [1120/1251] eta: 0:01:06 lr: 0.000942 loss: 3.9246 (3.7724) grad_norm: 1.0459 (1.0241) time: 0.5103 [2021-03-25 11:43:01 swin_small_patch4_window7_224] INFO: Epoch: [46] [1130/1251] eta: 0:01:01 lr: 0.000941 loss: 3.9734 (3.7754) grad_norm: 1.0459 (1.0244) time: 0.5114 [2021-03-25 11:43:06 swin_small_patch4_window7_224] INFO: Epoch: [46] [1140/1251] eta: 0:00:56 lr: 0.000941 loss: 3.9960 (3.7759) grad_norm: 1.0449 (1.0250) time: 0.5117 [2021-03-25 11:43:11 swin_small_patch4_window7_224] INFO: Epoch: [46] [1150/1251] eta: 0:00:51 lr: 0.000941 loss: 3.9482 (3.7760) grad_norm: 1.0268 (1.0249) time: 0.5098 [2021-03-25 11:43:16 swin_small_patch4_window7_224] INFO: Epoch: [46] [1160/1251] eta: 0:00:46 lr: 0.000941 loss: 3.9532 (3.7779) grad_norm: 1.0431 (1.0255) time: 0.5035 [2021-03-25 11:43:21 swin_small_patch4_window7_224] INFO: Epoch: [46] [1170/1251] eta: 0:00:41 lr: 0.000941 loss: 3.8436 (3.7777) grad_norm: 1.0431 (1.0253) time: 0.4993 [2021-03-25 11:43:26 swin_small_patch4_window7_224] INFO: Epoch: [46] [1180/1251] eta: 0:00:36 lr: 0.000941 loss: 3.7878 (3.7769) grad_norm: 0.9576 (1.0245) time: 0.5010 [2021-03-25 11:43:31 swin_small_patch4_window7_224] INFO: Epoch: [46] [1190/1251] eta: 0:00:31 lr: 0.000941 loss: 3.6420 (3.7752) grad_norm: 0.9576 (1.0242) time: 0.5035 [2021-03-25 11:43:36 swin_small_patch4_window7_224] INFO: Epoch: [46] [1200/1251] eta: 0:00:26 lr: 0.000941 loss: 3.6872 (3.7762) grad_norm: 0.9719 (1.0240) time: 0.5027 [2021-03-25 11:43:41 swin_small_patch4_window7_224] INFO: Epoch: [46] [1210/1251] eta: 0:00:20 lr: 0.000941 loss: 4.1080 (3.7778) grad_norm: 0.9783 (1.0242) time: 0.5038 [2021-03-25 11:43:46 swin_small_patch4_window7_224] INFO: Epoch: [46] [1220/1251] eta: 0:00:15 lr: 0.000941 loss: 3.9977 (3.7784) grad_norm: 0.9648 (1.0233) time: 0.5027 [2021-03-25 11:43:51 swin_small_patch4_window7_224] INFO: Epoch: [46] [1230/1251] eta: 0:00:10 lr: 0.000941 loss: 3.9432 (3.7787) grad_norm: 0.9081 (1.0227) time: 0.5035 [2021-03-25 11:43:56 swin_small_patch4_window7_224] INFO: Epoch: [46] [1240/1251] eta: 0:00:05 lr: 0.000941 loss: 3.7968 (3.7803) grad_norm: 0.9948 (1.0229) time: 0.5061 [2021-03-25 11:44:01 swin_small_patch4_window7_224] INFO: Epoch: [46] [1250/1251] eta: 0:00:00 lr: 0.000941 loss: 4.0643 (3.7819) grad_norm: 1.1052 (1.0242) time: 0.5031 [2021-03-25 11:44:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:36 loss: 1.3489 (1.3489) acc1: 57.8125 (57.8125) acc5: 90.6250 (90.6250) [2021-03-25 11:44:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.2087 (1.2155) acc1: 71.8750 (69.4602) acc5: 90.6250 (91.1932) [2021-03-25 11:44:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1863 (1.2125) acc1: 70.3125 (70.0149) acc5: 92.1875 (91.5923) [2021-03-25 11:44:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2429 (1.2215) acc1: 70.3125 (70.6653) acc5: 90.6250 (90.9274) [2021-03-25 11:44:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1640 (1.2104) acc1: 73.4375 (71.1890) acc5: 90.6250 (90.9680) [2021-03-25 11:44:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1870 (1.2113) acc1: 73.4375 (71.0400) acc5: 90.6250 (90.9440) [2021-03-25 11:44:18 swin_small_patch4_window7_224] INFO: * Acc@1 72.376 Acc@5 91.378 loss 1.179 [2021-03-25 11:44:18 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.4% [2021-03-25 11:44:18 swin_small_patch4_window7_224] INFO: Max accuracy: 72.38% [2021-03-25 11:44:22 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 0/1251] eta: 1:22:27 lr: 0.000941 loss: 3.9760 (3.9760) grad_norm: 0.9482 (0.9482) time: 3.9551 [2021-03-25 11:44:28 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 10/1251] eta: 0:18:00 lr: 0.000941 loss: 4.1386 (3.9332) grad_norm: 1.0777 (1.0210) time: 0.8703 [2021-03-25 11:44:33 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 20/1251] eta: 0:14:20 lr: 0.000941 loss: 3.6424 (3.7194) grad_norm: 1.0777 (1.0404) time: 0.5361 [2021-03-25 11:44:38 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 30/1251] eta: 0:12:59 lr: 0.000941 loss: 3.6424 (3.7187) grad_norm: 1.0061 (1.0221) time: 0.5111 [2021-03-25 11:44:43 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 40/1251] eta: 0:12:12 lr: 0.000941 loss: 3.6283 (3.6800) grad_norm: 1.0139 (1.0294) time: 0.5065 [2021-03-25 11:44:48 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 50/1251] eta: 0:11:42 lr: 0.000941 loss: 3.8005 (3.7088) grad_norm: 0.9975 (1.0114) time: 0.5015 [2021-03-25 11:44:53 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 60/1251] eta: 0:11:22 lr: 0.000941 loss: 3.8213 (3.7153) grad_norm: 0.9242 (1.0016) time: 0.5062 [2021-03-25 11:44:58 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 70/1251] eta: 0:11:04 lr: 0.000941 loss: 3.9541 (3.7518) grad_norm: 0.9572 (0.9983) time: 0.5056 [2021-03-25 11:45:03 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 80/1251] eta: 0:10:49 lr: 0.000941 loss: 3.7915 (3.7537) grad_norm: 0.9887 (1.0011) time: 0.5007 [2021-03-25 11:45:08 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 90/1251] eta: 0:10:37 lr: 0.000941 loss: 3.8648 (3.7675) grad_norm: 1.0887 (1.0143) time: 0.4997 [2021-03-25 11:45:13 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 100/1251] eta: 0:10:26 lr: 0.000941 loss: 3.7782 (3.7547) grad_norm: 1.0887 (1.0216) time: 0.5006 [2021-03-25 11:45:18 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 110/1251] eta: 0:10:18 lr: 0.000941 loss: 3.7395 (3.7491) grad_norm: 0.9876 (1.0168) time: 0.5099 [2021-03-25 11:45:23 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 120/1251] eta: 0:10:09 lr: 0.000941 loss: 3.5783 (3.7265) grad_norm: 0.9595 (1.0146) time: 0.5108 [2021-03-25 11:45:28 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 130/1251] eta: 0:10:01 lr: 0.000941 loss: 3.7206 (3.7465) grad_norm: 0.9939 (1.0118) time: 0.5089 [2021-03-25 11:45:33 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 140/1251] eta: 0:09:53 lr: 0.000941 loss: 3.9009 (3.7365) grad_norm: 1.0030 (1.0135) time: 0.5073 [2021-03-25 11:45:38 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 150/1251] eta: 0:09:45 lr: 0.000941 loss: 3.6628 (3.7251) grad_norm: 0.9836 (1.0090) time: 0.4991 [2021-03-25 11:45:43 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 160/1251] eta: 0:09:38 lr: 0.000941 loss: 3.8023 (3.7502) grad_norm: 0.9789 (1.0091) time: 0.5005 [2021-03-25 11:45:49 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 170/1251] eta: 0:09:31 lr: 0.000941 loss: 4.0318 (3.7628) grad_norm: 1.0290 (1.0137) time: 0.5077 [2021-03-25 11:45:54 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 180/1251] eta: 0:09:25 lr: 0.000941 loss: 3.7927 (3.7544) grad_norm: 1.0534 (1.0142) time: 0.5100 [2021-03-25 11:45:59 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 190/1251] eta: 0:09:19 lr: 0.000941 loss: 3.8157 (3.7679) grad_norm: 0.9717 (1.0131) time: 0.5128 [2021-03-25 11:46:04 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 200/1251] eta: 0:09:13 lr: 0.000941 loss: 3.9092 (3.7672) grad_norm: 0.9628 (1.0148) time: 0.5163 [2021-03-25 11:46:09 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 210/1251] eta: 0:09:07 lr: 0.000941 loss: 3.6302 (3.7520) grad_norm: 0.9918 (1.0162) time: 0.5139 [2021-03-25 11:46:14 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 220/1251] eta: 0:09:01 lr: 0.000941 loss: 3.6302 (3.7544) grad_norm: 0.9142 (1.0112) time: 0.5079 [2021-03-25 11:46:19 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 230/1251] eta: 0:08:55 lr: 0.000941 loss: 3.5692 (3.7474) grad_norm: 0.9124 (1.0091) time: 0.5069 [2021-03-25 11:46:24 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 240/1251] eta: 0:08:49 lr: 0.000941 loss: 3.6775 (3.7479) grad_norm: 1.0011 (1.0102) time: 0.5078 [2021-03-25 11:46:29 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 250/1251] eta: 0:08:43 lr: 0.000941 loss: 3.7892 (3.7555) grad_norm: 1.0037 (1.0108) time: 0.5014 [2021-03-25 11:46:34 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 260/1251] eta: 0:08:37 lr: 0.000941 loss: 3.7139 (3.7440) grad_norm: 1.0164 (1.0116) time: 0.5034 [2021-03-25 11:46:39 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 270/1251] eta: 0:08:31 lr: 0.000941 loss: 3.6913 (3.7429) grad_norm: 1.0424 (1.0127) time: 0.5076 [2021-03-25 11:46:44 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 280/1251] eta: 0:08:25 lr: 0.000941 loss: 3.8851 (3.7557) grad_norm: 1.0422 (1.0129) time: 0.5032 [2021-03-25 11:46:49 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 290/1251] eta: 0:08:19 lr: 0.000941 loss: 4.0025 (3.7577) grad_norm: 1.0027 (1.0127) time: 0.5011 [2021-03-25 11:46:55 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 300/1251] eta: 0:08:14 lr: 0.000941 loss: 3.8295 (3.7594) grad_norm: 1.0255 (1.0137) time: 0.5082 [2021-03-25 11:47:00 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 310/1251] eta: 0:08:08 lr: 0.000941 loss: 3.7107 (3.7562) grad_norm: 0.9767 (1.0131) time: 0.5117 [2021-03-25 11:47:05 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 320/1251] eta: 0:08:03 lr: 0.000941 loss: 3.8828 (3.7674) grad_norm: 0.9868 (1.0129) time: 0.5141 [2021-03-25 11:47:10 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 330/1251] eta: 0:07:57 lr: 0.000941 loss: 4.0953 (3.7743) grad_norm: 0.9528 (1.0115) time: 0.5110 [2021-03-25 11:47:15 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 340/1251] eta: 0:07:52 lr: 0.000941 loss: 3.9120 (3.7740) grad_norm: 0.9328 (1.0110) time: 0.5017 [2021-03-25 11:47:20 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 350/1251] eta: 0:07:46 lr: 0.000941 loss: 3.7599 (3.7730) grad_norm: 1.0272 (1.0126) time: 0.5045 [2021-03-25 11:47:25 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 360/1251] eta: 0:07:41 lr: 0.000941 loss: 3.7599 (3.7761) grad_norm: 0.9840 (1.0122) time: 0.5032 [2021-03-25 11:47:30 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 370/1251] eta: 0:07:35 lr: 0.000941 loss: 3.8414 (3.7732) grad_norm: 0.9840 (1.0115) time: 0.5020 [2021-03-25 11:47:35 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 380/1251] eta: 0:07:30 lr: 0.000940 loss: 3.7126 (3.7733) grad_norm: 1.0045 (1.0127) time: 0.5061 [2021-03-25 11:47:40 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 390/1251] eta: 0:07:24 lr: 0.000940 loss: 3.4739 (3.7622) grad_norm: 1.0573 (1.0142) time: 0.5051 [2021-03-25 11:47:45 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 400/1251] eta: 0:07:19 lr: 0.000940 loss: 3.7746 (3.7661) grad_norm: 1.1109 (1.0157) time: 0.5027 [2021-03-25 11:47:50 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 410/1251] eta: 0:07:13 lr: 0.000940 loss: 4.1159 (3.7695) grad_norm: 1.0669 (1.0160) time: 0.5008 [2021-03-25 11:47:55 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 420/1251] eta: 0:07:08 lr: 0.000940 loss: 4.0430 (3.7757) grad_norm: 1.0582 (1.0169) time: 0.5045 [2021-03-25 11:48:00 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 430/1251] eta: 0:07:03 lr: 0.000940 loss: 3.9908 (3.7801) grad_norm: 0.9992 (1.0161) time: 0.5083 [2021-03-25 11:48:05 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 440/1251] eta: 0:06:58 lr: 0.000940 loss: 3.9104 (3.7799) grad_norm: 0.9992 (1.0176) time: 0.5095 [2021-03-25 11:48:11 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 450/1251] eta: 0:06:52 lr: 0.000940 loss: 3.8649 (3.7776) grad_norm: 1.0553 (1.0182) time: 0.5088 [2021-03-25 11:48:15 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 460/1251] eta: 0:06:47 lr: 0.000940 loss: 3.5931 (3.7724) grad_norm: 1.0367 (1.0195) time: 0.5015 [2021-03-25 11:48:21 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 470/1251] eta: 0:06:41 lr: 0.000940 loss: 3.6685 (3.7735) grad_norm: 0.9944 (1.0190) time: 0.5015 [2021-03-25 11:48:26 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 480/1251] eta: 0:06:36 lr: 0.000940 loss: 3.4564 (3.7677) grad_norm: 0.9441 (1.0174) time: 0.5010 [2021-03-25 11:48:31 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 490/1251] eta: 0:06:31 lr: 0.000940 loss: 3.4153 (3.7622) grad_norm: 0.9782 (1.0172) time: 0.5050 [2021-03-25 11:48:36 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 500/1251] eta: 0:06:26 lr: 0.000940 loss: 3.7065 (3.7621) grad_norm: 1.0196 (1.0167) time: 0.5092 [2021-03-25 11:48:41 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 510/1251] eta: 0:06:20 lr: 0.000940 loss: 3.9834 (3.7672) grad_norm: 0.9580 (1.0156) time: 0.5008 [2021-03-25 11:48:46 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 520/1251] eta: 0:06:15 lr: 0.000940 loss: 3.9834 (3.7651) grad_norm: 0.9580 (1.0162) time: 0.4999 [2021-03-25 11:48:51 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 530/1251] eta: 0:06:10 lr: 0.000940 loss: 3.7820 (3.7656) grad_norm: 1.0150 (1.0161) time: 0.5037 [2021-03-25 11:48:56 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 540/1251] eta: 0:06:04 lr: 0.000940 loss: 3.7712 (3.7660) grad_norm: 1.0150 (1.0172) time: 0.5071 [2021-03-25 11:49:01 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 550/1251] eta: 0:06:00 lr: 0.000940 loss: 3.9469 (3.7703) grad_norm: 1.0285 (1.0172) time: 0.5216 [2021-03-25 11:49:06 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 560/1251] eta: 0:05:54 lr: 0.000940 loss: 3.9873 (3.7752) grad_norm: 1.0048 (1.0166) time: 0.5235 [2021-03-25 11:49:11 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 570/1251] eta: 0:05:49 lr: 0.000940 loss: 4.0310 (3.7787) grad_norm: 0.9815 (1.0169) time: 0.5078 [2021-03-25 11:49:16 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 580/1251] eta: 0:05:44 lr: 0.000940 loss: 3.9710 (3.7775) grad_norm: 0.9815 (1.0162) time: 0.5026 [2021-03-25 11:49:21 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 590/1251] eta: 0:05:39 lr: 0.000940 loss: 3.9952 (3.7788) grad_norm: 0.9757 (1.0153) time: 0.5044 [2021-03-25 11:49:26 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 600/1251] eta: 0:05:33 lr: 0.000940 loss: 4.0593 (3.7806) grad_norm: 0.9758 (1.0154) time: 0.5018 [2021-03-25 11:49:31 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 610/1251] eta: 0:05:28 lr: 0.000940 loss: 3.9938 (3.7818) grad_norm: 1.0016 (1.0153) time: 0.4972 [2021-03-25 11:49:36 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 620/1251] eta: 0:05:23 lr: 0.000940 loss: 3.9606 (3.7833) grad_norm: 0.9779 (1.0143) time: 0.4973 [2021-03-25 11:49:41 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 630/1251] eta: 0:05:18 lr: 0.000940 loss: 3.9606 (3.7848) grad_norm: 0.9212 (1.0146) time: 0.5002 [2021-03-25 11:49:46 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 640/1251] eta: 0:05:12 lr: 0.000940 loss: 3.7709 (3.7843) grad_norm: 0.9685 (1.0144) time: 0.5064 [2021-03-25 11:49:51 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 650/1251] eta: 0:05:07 lr: 0.000940 loss: 3.7709 (3.7853) grad_norm: 0.9685 (1.0144) time: 0.5056 [2021-03-25 11:49:57 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 660/1251] eta: 0:05:02 lr: 0.000940 loss: 3.7665 (3.7794) grad_norm: 0.9804 (1.0134) time: 0.5067 [2021-03-25 11:50:02 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 670/1251] eta: 0:04:57 lr: 0.000940 loss: 3.7783 (3.7767) grad_norm: 0.9684 (1.0139) time: 0.5065 [2021-03-25 11:50:07 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 680/1251] eta: 0:04:52 lr: 0.000940 loss: 3.7518 (3.7740) grad_norm: 1.0487 (1.0143) time: 0.5007 [2021-03-25 11:50:12 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 690/1251] eta: 0:04:47 lr: 0.000940 loss: 3.7513 (3.7745) grad_norm: 1.0219 (1.0147) time: 0.5078 [2021-03-25 11:50:17 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 700/1251] eta: 0:04:41 lr: 0.000940 loss: 3.8768 (3.7763) grad_norm: 1.0827 (1.0154) time: 0.5049 [2021-03-25 11:50:22 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 710/1251] eta: 0:04:36 lr: 0.000940 loss: 4.0044 (3.7791) grad_norm: 1.0094 (1.0152) time: 0.4996 [2021-03-25 11:50:27 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 720/1251] eta: 0:04:31 lr: 0.000940 loss: 4.0260 (3.7831) grad_norm: 0.9889 (1.0152) time: 0.5061 [2021-03-25 11:50:32 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 730/1251] eta: 0:04:26 lr: 0.000940 loss: 3.9922 (3.7852) grad_norm: 0.9808 (1.0151) time: 0.5128 [2021-03-25 11:50:38 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 740/1251] eta: 0:04:21 lr: 0.000940 loss: 3.7890 (3.7844) grad_norm: 1.0020 (1.0152) time: 0.5339 [2021-03-25 11:50:43 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 750/1251] eta: 0:04:16 lr: 0.000940 loss: 3.7134 (3.7820) grad_norm: 1.0237 (1.0151) time: 0.5460 [2021-03-25 11:50:48 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 760/1251] eta: 0:04:11 lr: 0.000940 loss: 4.0424 (3.7869) grad_norm: 1.0217 (1.0164) time: 0.5264 [2021-03-25 11:50:53 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 770/1251] eta: 0:04:06 lr: 0.000940 loss: 4.0424 (3.7856) grad_norm: 1.0152 (1.0166) time: 0.5051 [2021-03-25 11:50:58 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 780/1251] eta: 0:04:01 lr: 0.000940 loss: 3.9133 (3.7865) grad_norm: 0.9901 (1.0164) time: 0.5064 [2021-03-25 11:51:03 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 790/1251] eta: 0:03:56 lr: 0.000940 loss: 3.8835 (3.7851) grad_norm: 0.9753 (1.0161) time: 0.5107 [2021-03-25 11:51:08 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 800/1251] eta: 0:03:50 lr: 0.000940 loss: 3.8835 (3.7889) grad_norm: 0.9886 (1.0173) time: 0.5050 [2021-03-25 11:51:13 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 810/1251] eta: 0:03:45 lr: 0.000940 loss: 4.1414 (3.7893) grad_norm: 1.0344 (1.0176) time: 0.5011 [2021-03-25 11:51:18 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 820/1251] eta: 0:03:40 lr: 0.000940 loss: 3.7912 (3.7878) grad_norm: 1.0016 (1.0182) time: 0.5000 [2021-03-25 11:51:23 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 830/1251] eta: 0:03:35 lr: 0.000940 loss: 3.8702 (3.7905) grad_norm: 1.0203 (1.0185) time: 0.5003 [2021-03-25 11:51:28 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 840/1251] eta: 0:03:30 lr: 0.000940 loss: 3.9440 (3.7910) grad_norm: 0.9997 (1.0177) time: 0.4996 [2021-03-25 11:51:33 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 850/1251] eta: 0:03:25 lr: 0.000940 loss: 3.8549 (3.7903) grad_norm: 0.9622 (1.0176) time: 0.5072 [2021-03-25 11:51:39 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 860/1251] eta: 0:03:19 lr: 0.000940 loss: 3.7526 (3.7861) grad_norm: 1.0017 (1.0180) time: 0.5144 [2021-03-25 11:51:44 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 870/1251] eta: 0:03:14 lr: 0.000940 loss: 3.5443 (3.7852) grad_norm: 1.0175 (1.0177) time: 0.5124 [2021-03-25 11:51:49 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 880/1251] eta: 0:03:09 lr: 0.000940 loss: 3.7774 (3.7849) grad_norm: 0.9969 (1.0183) time: 0.5055 [2021-03-25 11:51:54 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 890/1251] eta: 0:03:04 lr: 0.000939 loss: 3.7062 (3.7815) grad_norm: 1.0177 (1.0185) time: 0.5000 [2021-03-25 11:51:59 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 900/1251] eta: 0:02:59 lr: 0.000939 loss: 3.5063 (3.7775) grad_norm: 1.0177 (1.0186) time: 0.5046 [2021-03-25 11:52:04 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 910/1251] eta: 0:02:54 lr: 0.000939 loss: 3.3065 (3.7768) grad_norm: 1.0180 (1.0181) time: 0.5066 [2021-03-25 11:52:09 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 920/1251] eta: 0:02:49 lr: 0.000939 loss: 3.6764 (3.7772) grad_norm: 0.9606 (1.0179) time: 0.5093 [2021-03-25 11:52:14 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 930/1251] eta: 0:02:44 lr: 0.000939 loss: 3.7523 (3.7755) grad_norm: 0.9606 (1.0179) time: 0.5089 [2021-03-25 11:52:19 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 940/1251] eta: 0:02:38 lr: 0.000939 loss: 3.2308 (3.7713) grad_norm: 0.9506 (1.0171) time: 0.5103 [2021-03-25 11:52:24 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 950/1251] eta: 0:02:33 lr: 0.000939 loss: 4.0298 (3.7743) grad_norm: 0.9907 (1.0173) time: 0.5172 [2021-03-25 11:52:29 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 960/1251] eta: 0:02:28 lr: 0.000939 loss: 4.0726 (3.7739) grad_norm: 1.0081 (1.0168) time: 0.5097 [2021-03-25 11:52:34 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 970/1251] eta: 0:02:23 lr: 0.000939 loss: 3.7059 (3.7715) grad_norm: 0.9678 (1.0167) time: 0.5043 [2021-03-25 11:52:40 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 980/1251] eta: 0:02:18 lr: 0.000939 loss: 3.4427 (3.7695) grad_norm: 0.9671 (1.0164) time: 0.5057 [2021-03-25 11:52:45 swin_small_patch4_window7_224] INFO: Epoch: [47] [ 990/1251] eta: 0:02:13 lr: 0.000939 loss: 3.3837 (3.7681) grad_norm: 1.0373 (1.0170) time: 0.5049 [2021-03-25 11:52:50 swin_small_patch4_window7_224] INFO: Epoch: [47] [1000/1251] eta: 0:02:08 lr: 0.000939 loss: 3.6987 (3.7689) grad_norm: 1.0586 (1.0177) time: 0.5024 [2021-03-25 11:52:55 swin_small_patch4_window7_224] INFO: Epoch: [47] [1010/1251] eta: 0:02:03 lr: 0.000939 loss: 3.9860 (3.7719) grad_norm: 0.9976 (1.0178) time: 0.5043 [2021-03-25 11:53:00 swin_small_patch4_window7_224] INFO: Epoch: [47] [1020/1251] eta: 0:01:57 lr: 0.000939 loss: 3.9860 (3.7728) grad_norm: 0.9861 (1.0176) time: 0.5083 [2021-03-25 11:53:05 swin_small_patch4_window7_224] INFO: Epoch: [47] [1030/1251] eta: 0:01:52 lr: 0.000939 loss: 3.8847 (3.7735) grad_norm: 0.9790 (1.0171) time: 0.5049 [2021-03-25 11:53:10 swin_small_patch4_window7_224] INFO: Epoch: [47] [1040/1251] eta: 0:01:47 lr: 0.000939 loss: 3.9656 (3.7734) grad_norm: 0.9551 (1.0164) time: 0.5063 [2021-03-25 11:53:15 swin_small_patch4_window7_224] INFO: Epoch: [47] [1050/1251] eta: 0:01:42 lr: 0.000939 loss: 3.6374 (3.7693) grad_norm: 0.9574 (1.0165) time: 0.5100 [2021-03-25 11:53:20 swin_small_patch4_window7_224] INFO: Epoch: [47] [1060/1251] eta: 0:01:37 lr: 0.000939 loss: 3.6374 (3.7702) grad_norm: 0.9712 (inf) time: 0.5053 [2021-03-25 11:53:25 swin_small_patch4_window7_224] INFO: Epoch: [47] [1070/1251] eta: 0:01:32 lr: 0.000939 loss: 4.0834 (3.7730) grad_norm: 1.0149 (inf) time: 0.5068 [2021-03-25 11:53:30 swin_small_patch4_window7_224] INFO: Epoch: [47] [1080/1251] eta: 0:01:27 lr: 0.000939 loss: 4.0141 (3.7734) grad_norm: 0.9503 (inf) time: 0.5097 [2021-03-25 11:53:35 swin_small_patch4_window7_224] INFO: Epoch: [47] [1090/1251] eta: 0:01:22 lr: 0.000939 loss: 3.7708 (3.7721) grad_norm: 0.9822 (inf) time: 0.5065 [2021-03-25 11:53:40 swin_small_patch4_window7_224] INFO: Epoch: [47] [1100/1251] eta: 0:01:17 lr: 0.000939 loss: 3.7591 (3.7728) grad_norm: 0.9660 (inf) time: 0.5058 [2021-03-25 11:53:45 swin_small_patch4_window7_224] INFO: Epoch: [47] [1110/1251] eta: 0:01:11 lr: 0.000939 loss: 3.7111 (3.7711) grad_norm: 0.9385 (inf) time: 0.5077 [2021-03-25 11:53:50 swin_small_patch4_window7_224] INFO: Epoch: [47] [1120/1251] eta: 0:01:06 lr: 0.000939 loss: 3.5415 (3.7689) grad_norm: 0.9849 (inf) time: 0.5040 [2021-03-25 11:53:55 swin_small_patch4_window7_224] INFO: Epoch: [47] [1130/1251] eta: 0:01:01 lr: 0.000939 loss: 3.5650 (3.7694) grad_norm: 1.0027 (inf) time: 0.5013 [2021-03-25 11:54:01 swin_small_patch4_window7_224] INFO: Epoch: [47] [1140/1251] eta: 0:00:56 lr: 0.000939 loss: 3.6181 (3.7688) grad_norm: 0.9773 (inf) time: 0.5071 [2021-03-25 11:54:06 swin_small_patch4_window7_224] INFO: Epoch: [47] [1150/1251] eta: 0:00:51 lr: 0.000939 loss: 3.7979 (3.7705) grad_norm: 0.9940 (inf) time: 0.5123 [2021-03-25 11:54:11 swin_small_patch4_window7_224] INFO: Epoch: [47] [1160/1251] eta: 0:00:46 lr: 0.000939 loss: 3.9853 (3.7708) grad_norm: 0.9940 (inf) time: 0.5112 [2021-03-25 11:54:16 swin_small_patch4_window7_224] INFO: Epoch: [47] [1170/1251] eta: 0:00:41 lr: 0.000939 loss: 4.0065 (3.7728) grad_norm: 1.0148 (inf) time: 0.5087 [2021-03-25 11:54:21 swin_small_patch4_window7_224] INFO: Epoch: [47] [1180/1251] eta: 0:00:36 lr: 0.000939 loss: 4.0092 (3.7750) grad_norm: 1.0442 (inf) time: 0.5055 [2021-03-25 11:54:26 swin_small_patch4_window7_224] INFO: Epoch: [47] [1190/1251] eta: 0:00:31 lr: 0.000939 loss: 3.8097 (3.7724) grad_norm: 1.0123 (inf) time: 0.5051 [2021-03-25 11:54:31 swin_small_patch4_window7_224] INFO: Epoch: [47] [1200/1251] eta: 0:00:26 lr: 0.000939 loss: 3.9566 (3.7750) grad_norm: 0.9977 (inf) time: 0.5081 [2021-03-25 11:54:36 swin_small_patch4_window7_224] INFO: Epoch: [47] [1210/1251] eta: 0:00:20 lr: 0.000939 loss: 4.0269 (3.7729) grad_norm: 0.9951 (inf) time: 0.5094 [2021-03-25 11:54:41 swin_small_patch4_window7_224] INFO: Epoch: [47] [1220/1251] eta: 0:00:15 lr: 0.000939 loss: 3.8624 (3.7740) grad_norm: 0.9663 (inf) time: 0.5090 [2021-03-25 11:54:46 swin_small_patch4_window7_224] INFO: Epoch: [47] [1230/1251] eta: 0:00:10 lr: 0.000939 loss: 3.8733 (3.7738) grad_norm: 0.9801 (inf) time: 0.5020 [2021-03-25 11:54:51 swin_small_patch4_window7_224] INFO: Epoch: [47] [1240/1251] eta: 0:00:05 lr: 0.000939 loss: 3.8631 (3.7741) grad_norm: 1.0075 (inf) time: 0.5025 [2021-03-25 11:54:56 swin_small_patch4_window7_224] INFO: Epoch: [47] [1250/1251] eta: 0:00:00 lr: 0.000939 loss: 3.9980 (3.7768) grad_norm: 0.9904 (inf) time: 0.5022 [2021-03-25 11:55:02 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:37 loss: 0.8528 (0.8528) acc1: 73.4375 (73.4375) acc5: 98.4375 (98.4375) [2021-03-25 11:55:03 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.3205 (1.1671) acc1: 70.3125 (72.3011) acc5: 92.1875 (91.9034) [2021-03-25 11:55:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0735 (1.1345) acc1: 70.3125 (72.9911) acc5: 92.1875 (92.3363) [2021-03-25 11:55:08 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1055 (1.1644) acc1: 71.8750 (72.4798) acc5: 92.1875 (91.9355) [2021-03-25 11:55:10 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1806 (1.1874) acc1: 71.8750 (72.2180) acc5: 89.0625 (91.1204) [2021-03-25 11:55:11 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2454 (1.1972) acc1: 70.3125 (71.9360) acc5: 90.6250 (91.1360) [2021-03-25 11:55:14 swin_small_patch4_window7_224] INFO: * Acc@1 72.104 Acc@5 91.454 loss 1.178 [2021-03-25 11:55:14 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.1% [2021-03-25 11:55:14 swin_small_patch4_window7_224] INFO: Max accuracy: 72.38% [2021-03-25 11:55:17 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 0/1251] eta: 1:19:32 lr: 0.000939 loss: 4.3033 (4.3033) grad_norm: 0.8614 (0.8614) time: 3.8146 [2021-03-25 11:55:23 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 10/1251] eta: 0:17:08 lr: 0.000939 loss: 4.2251 (4.0398) grad_norm: 1.0102 (0.9840) time: 0.8286 [2021-03-25 11:55:28 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 20/1251] eta: 0:13:52 lr: 0.000939 loss: 3.8537 (3.8620) grad_norm: 1.0138 (0.9954) time: 0.5196 [2021-03-25 11:55:33 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 30/1251] eta: 0:12:37 lr: 0.000939 loss: 3.5608 (3.7512) grad_norm: 1.0176 (1.0206) time: 0.5058 [2021-03-25 11:55:38 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 40/1251] eta: 0:11:55 lr: 0.000939 loss: 3.8871 (3.7941) grad_norm: 1.0767 (1.0408) time: 0.5013 [2021-03-25 11:55:43 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 50/1251] eta: 0:11:29 lr: 0.000939 loss: 3.9178 (3.7942) grad_norm: 1.0578 (1.0484) time: 0.5024 [2021-03-25 11:55:48 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 60/1251] eta: 0:11:09 lr: 0.000939 loss: 3.8482 (3.7803) grad_norm: 1.0419 (1.0495) time: 0.5033 [2021-03-25 11:55:53 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 70/1251] eta: 0:10:53 lr: 0.000939 loss: 3.8060 (3.7863) grad_norm: 1.0419 (1.0522) time: 0.5017 [2021-03-25 11:55:58 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 80/1251] eta: 0:10:41 lr: 0.000939 loss: 3.7211 (3.7797) grad_norm: 1.0179 (1.0464) time: 0.5037 [2021-03-25 11:56:03 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 90/1251] eta: 0:10:30 lr: 0.000939 loss: 3.7896 (3.7792) grad_norm: 0.9831 (1.0374) time: 0.5060 [2021-03-25 11:56:08 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 100/1251] eta: 0:10:20 lr: 0.000939 loss: 3.8014 (3.7824) grad_norm: 0.9717 (1.0307) time: 0.5017 [2021-03-25 11:56:13 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 110/1251] eta: 0:10:11 lr: 0.000939 loss: 3.8014 (3.7955) grad_norm: 0.9563 (1.0293) time: 0.5013 [2021-03-25 11:56:18 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 120/1251] eta: 0:10:03 lr: 0.000939 loss: 3.7939 (3.7869) grad_norm: 1.0324 (1.0392) time: 0.5093 [2021-03-25 11:56:23 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 130/1251] eta: 0:09:56 lr: 0.000939 loss: 3.9250 (3.7755) grad_norm: 1.0335 (1.0375) time: 0.5100 [2021-03-25 11:56:28 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 140/1251] eta: 0:09:48 lr: 0.000938 loss: 3.9008 (3.7829) grad_norm: 0.9955 (1.0355) time: 0.5078 [2021-03-25 11:56:33 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 150/1251] eta: 0:09:41 lr: 0.000938 loss: 3.7947 (3.7592) grad_norm: 0.9886 (1.0324) time: 0.5079 [2021-03-25 11:56:38 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 160/1251] eta: 0:09:34 lr: 0.000938 loss: 3.7581 (3.7761) grad_norm: 1.0041 (1.0321) time: 0.5019 [2021-03-25 11:56:43 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 170/1251] eta: 0:09:27 lr: 0.000938 loss: 3.9614 (3.7909) grad_norm: 0.9941 (1.0277) time: 0.5013 [2021-03-25 11:56:49 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 180/1251] eta: 0:09:22 lr: 0.000938 loss: 3.8655 (3.7832) grad_norm: 0.9832 (1.0289) time: 0.5123 [2021-03-25 11:56:54 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 190/1251] eta: 0:09:16 lr: 0.000938 loss: 3.7946 (3.7907) grad_norm: 1.0385 (1.0323) time: 0.5177 [2021-03-25 11:56:59 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 200/1251] eta: 0:09:10 lr: 0.000938 loss: 3.8212 (3.7881) grad_norm: 1.0273 (1.0310) time: 0.5127 [2021-03-25 11:57:04 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 210/1251] eta: 0:09:04 lr: 0.000938 loss: 3.8072 (3.7795) grad_norm: 0.9598 (1.0306) time: 0.5090 [2021-03-25 11:57:09 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 220/1251] eta: 0:08:58 lr: 0.000938 loss: 3.7044 (3.7699) grad_norm: 0.9886 (1.0292) time: 0.5089 [2021-03-25 11:57:14 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 230/1251] eta: 0:08:53 lr: 0.000938 loss: 3.7314 (3.7692) grad_norm: 0.9616 (1.0262) time: 0.5106 [2021-03-25 11:57:19 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 240/1251] eta: 0:08:47 lr: 0.000938 loss: 3.6707 (3.7613) grad_norm: 0.9666 (1.0251) time: 0.5101 [2021-03-25 11:57:24 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 250/1251] eta: 0:08:41 lr: 0.000938 loss: 3.8368 (3.7724) grad_norm: 0.9965 (1.0273) time: 0.5074 [2021-03-25 11:57:29 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 260/1251] eta: 0:08:35 lr: 0.000938 loss: 3.9771 (3.7625) grad_norm: 1.1126 (1.0322) time: 0.5082 [2021-03-25 11:57:34 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 270/1251] eta: 0:08:30 lr: 0.000938 loss: 3.5968 (3.7567) grad_norm: 1.0119 (1.0308) time: 0.5088 [2021-03-25 11:57:39 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 280/1251] eta: 0:08:24 lr: 0.000938 loss: 3.7620 (3.7563) grad_norm: 0.9770 (1.0301) time: 0.5036 [2021-03-25 11:57:45 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 290/1251] eta: 0:08:18 lr: 0.000938 loss: 3.6974 (3.7484) grad_norm: 1.0107 (1.0330) time: 0.5042 [2021-03-25 11:57:50 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 300/1251] eta: 0:08:13 lr: 0.000938 loss: 3.7729 (3.7540) grad_norm: 1.0213 (1.0323) time: 0.5094 [2021-03-25 11:57:55 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 310/1251] eta: 0:08:07 lr: 0.000938 loss: 3.9141 (3.7545) grad_norm: 0.9916 (1.0302) time: 0.5130 [2021-03-25 11:58:00 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 320/1251] eta: 0:08:02 lr: 0.000938 loss: 3.8976 (3.7533) grad_norm: 0.9260 (1.0266) time: 0.5086 [2021-03-25 11:58:05 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 330/1251] eta: 0:07:56 lr: 0.000938 loss: 3.6313 (3.7456) grad_norm: 0.9552 (1.0256) time: 0.5082 [2021-03-25 11:58:10 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 340/1251] eta: 0:07:51 lr: 0.000938 loss: 3.6724 (3.7524) grad_norm: 0.9783 (1.0250) time: 0.5098 [2021-03-25 11:58:15 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 350/1251] eta: 0:07:45 lr: 0.000938 loss: 4.0875 (3.7556) grad_norm: 0.9783 (1.0248) time: 0.4999 [2021-03-25 11:58:20 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 360/1251] eta: 0:07:40 lr: 0.000938 loss: 3.9580 (3.7563) grad_norm: 0.9793 (1.0242) time: 0.5024 [2021-03-25 11:58:25 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 370/1251] eta: 0:07:34 lr: 0.000938 loss: 3.7571 (3.7532) grad_norm: 0.9558 (1.0227) time: 0.5076 [2021-03-25 11:58:30 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 380/1251] eta: 0:07:29 lr: 0.000938 loss: 3.7458 (3.7497) grad_norm: 0.9867 (1.0240) time: 0.5056 [2021-03-25 11:58:35 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 390/1251] eta: 0:07:24 lr: 0.000938 loss: 3.9371 (3.7594) grad_norm: 1.0292 (1.0243) time: 0.5075 [2021-03-25 11:58:40 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 400/1251] eta: 0:07:18 lr: 0.000938 loss: 4.0074 (3.7603) grad_norm: 0.9755 (1.0245) time: 0.5086 [2021-03-25 11:58:45 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 410/1251] eta: 0:07:13 lr: 0.000938 loss: 3.8233 (3.7595) grad_norm: 0.9697 (1.0240) time: 0.5073 [2021-03-25 11:58:51 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 420/1251] eta: 0:07:08 lr: 0.000938 loss: 4.0324 (3.7632) grad_norm: 0.9697 (1.0233) time: 0.5086 [2021-03-25 11:58:56 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 430/1251] eta: 0:07:02 lr: 0.000938 loss: 3.9157 (3.7597) grad_norm: 1.0359 (1.0244) time: 0.5050 [2021-03-25 11:59:01 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 440/1251] eta: 0:06:57 lr: 0.000938 loss: 3.6311 (3.7583) grad_norm: 1.0481 (1.0247) time: 0.4994 [2021-03-25 11:59:06 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 450/1251] eta: 0:06:52 lr: 0.000938 loss: 3.5911 (3.7581) grad_norm: 1.0751 (1.0258) time: 0.5081 [2021-03-25 11:59:11 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 460/1251] eta: 0:06:47 lr: 0.000938 loss: 3.5170 (3.7528) grad_norm: 1.0393 (1.0254) time: 0.5126 [2021-03-25 11:59:16 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 470/1251] eta: 0:06:41 lr: 0.000938 loss: 3.7681 (3.7570) grad_norm: 1.0278 (1.0253) time: 0.5084 [2021-03-25 11:59:21 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 480/1251] eta: 0:06:36 lr: 0.000938 loss: 4.0010 (3.7608) grad_norm: 1.0278 (1.0252) time: 0.5049 [2021-03-25 11:59:26 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 490/1251] eta: 0:06:31 lr: 0.000938 loss: 4.0193 (3.7654) grad_norm: 1.0052 (1.0249) time: 0.5057 [2021-03-25 11:59:31 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 500/1251] eta: 0:06:25 lr: 0.000938 loss: 3.9474 (3.7717) grad_norm: 1.0005 (1.0247) time: 0.5054 [2021-03-25 11:59:36 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 510/1251] eta: 0:06:20 lr: 0.000938 loss: 4.0098 (3.7729) grad_norm: 0.9380 (1.0229) time: 0.4991 [2021-03-25 11:59:41 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 520/1251] eta: 0:06:15 lr: 0.000938 loss: 3.8499 (3.7673) grad_norm: 0.9857 (1.0238) time: 0.5060 [2021-03-25 11:59:46 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 530/1251] eta: 0:06:10 lr: 0.000938 loss: 3.5246 (3.7663) grad_norm: 1.0392 (1.0241) time: 0.5060 [2021-03-25 11:59:51 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 540/1251] eta: 0:06:04 lr: 0.000938 loss: 3.7153 (3.7709) grad_norm: 1.0343 (1.0243) time: 0.5048 [2021-03-25 11:59:57 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 550/1251] eta: 0:05:59 lr: 0.000938 loss: 4.0117 (3.7701) grad_norm: 0.9979 (1.0233) time: 0.5204 [2021-03-25 12:00:02 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 560/1251] eta: 0:05:54 lr: 0.000938 loss: 3.4850 (3.7678) grad_norm: 0.9559 (1.0231) time: 0.5182 [2021-03-25 12:00:07 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 570/1251] eta: 0:05:49 lr: 0.000938 loss: 3.7465 (3.7707) grad_norm: 0.9969 (1.0230) time: 0.5032 [2021-03-25 12:00:12 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 580/1251] eta: 0:05:44 lr: 0.000938 loss: 3.7465 (3.7667) grad_norm: 1.0154 (1.0231) time: 0.5043 [2021-03-25 12:00:17 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 590/1251] eta: 0:05:39 lr: 0.000938 loss: 3.6738 (3.7712) grad_norm: 1.0675 (1.0233) time: 0.5082 [2021-03-25 12:00:22 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 600/1251] eta: 0:05:33 lr: 0.000938 loss: 3.9868 (3.7727) grad_norm: 0.9814 (1.0225) time: 0.5061 [2021-03-25 12:00:27 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 610/1251] eta: 0:05:28 lr: 0.000938 loss: 3.9271 (3.7744) grad_norm: 0.9840 (1.0229) time: 0.5078 [2021-03-25 12:00:32 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 620/1251] eta: 0:05:23 lr: 0.000938 loss: 3.8675 (3.7746) grad_norm: 0.9873 (1.0218) time: 0.5079 [2021-03-25 12:00:37 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 630/1251] eta: 0:05:18 lr: 0.000938 loss: 3.7901 (3.7768) grad_norm: 0.9873 (1.0213) time: 0.5073 [2021-03-25 12:00:42 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 640/1251] eta: 0:05:13 lr: 0.000937 loss: 3.7901 (3.7793) grad_norm: 0.9907 (1.0211) time: 0.5110 [2021-03-25 12:00:47 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 650/1251] eta: 0:05:07 lr: 0.000937 loss: 3.8693 (3.7795) grad_norm: 0.9786 (1.0208) time: 0.5067 [2021-03-25 12:00:52 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 660/1251] eta: 0:05:02 lr: 0.000937 loss: 3.6284 (3.7753) grad_norm: 1.0147 (1.0207) time: 0.5029 [2021-03-25 12:00:57 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 670/1251] eta: 0:04:57 lr: 0.000937 loss: 3.8911 (3.7760) grad_norm: 0.9937 (1.0202) time: 0.5061 [2021-03-25 12:01:02 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 680/1251] eta: 0:04:52 lr: 0.000937 loss: 3.9489 (3.7768) grad_norm: 0.9863 (1.0198) time: 0.5107 [2021-03-25 12:01:07 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 690/1251] eta: 0:04:47 lr: 0.000937 loss: 3.9742 (3.7790) grad_norm: 0.9863 (1.0193) time: 0.5052 [2021-03-25 12:01:12 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 700/1251] eta: 0:04:42 lr: 0.000937 loss: 3.9742 (3.7816) grad_norm: 0.9954 (1.0201) time: 0.5003 [2021-03-25 12:01:18 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 710/1251] eta: 0:04:36 lr: 0.000937 loss: 3.9758 (3.7856) grad_norm: 1.0452 (1.0212) time: 0.5059 [2021-03-25 12:01:23 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 720/1251] eta: 0:04:31 lr: 0.000937 loss: 3.7637 (3.7790) grad_norm: 1.0129 (1.0204) time: 0.5051 [2021-03-25 12:01:28 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 730/1251] eta: 0:04:26 lr: 0.000937 loss: 3.5688 (3.7779) grad_norm: 0.9633 (1.0206) time: 0.5085 [2021-03-25 12:01:33 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 740/1251] eta: 0:04:21 lr: 0.000937 loss: 3.6869 (3.7775) grad_norm: 1.0677 (1.0216) time: 0.5283 [2021-03-25 12:01:38 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 750/1251] eta: 0:04:16 lr: 0.000937 loss: 4.0202 (3.7800) grad_norm: 1.0609 (1.0216) time: 0.5223 [2021-03-25 12:01:43 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 760/1251] eta: 0:04:11 lr: 0.000937 loss: 4.0081 (3.7806) grad_norm: 0.9839 (1.0218) time: 0.5025 [2021-03-25 12:01:48 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 770/1251] eta: 0:04:06 lr: 0.000937 loss: 3.8827 (3.7792) grad_norm: 1.0635 (1.0231) time: 0.5048 [2021-03-25 12:01:53 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 780/1251] eta: 0:04:01 lr: 0.000937 loss: 3.9413 (3.7826) grad_norm: 1.0388 (1.0230) time: 0.5070 [2021-03-25 12:01:59 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 790/1251] eta: 0:03:55 lr: 0.000937 loss: 4.0648 (3.7873) grad_norm: 0.9552 (1.0221) time: 0.5118 [2021-03-25 12:02:04 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 800/1251] eta: 0:03:50 lr: 0.000937 loss: 4.0973 (3.7887) grad_norm: 0.9440 (1.0212) time: 0.5122 [2021-03-25 12:02:09 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 810/1251] eta: 0:03:45 lr: 0.000937 loss: 3.7988 (3.7838) grad_norm: 0.9759 (1.0218) time: 0.5076 [2021-03-25 12:02:14 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 820/1251] eta: 0:03:40 lr: 0.000937 loss: 3.4685 (3.7811) grad_norm: 1.0332 (1.0215) time: 0.5081 [2021-03-25 12:02:19 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 830/1251] eta: 0:03:35 lr: 0.000937 loss: 3.5686 (3.7814) grad_norm: 0.9650 (1.0211) time: 0.5104 [2021-03-25 12:02:24 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 840/1251] eta: 0:03:30 lr: 0.000937 loss: 3.8133 (3.7811) grad_norm: 0.9568 (1.0206) time: 0.5103 [2021-03-25 12:02:29 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 850/1251] eta: 0:03:25 lr: 0.000937 loss: 3.7841 (3.7788) grad_norm: 0.9609 (1.0202) time: 0.5071 [2021-03-25 12:02:34 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 860/1251] eta: 0:03:20 lr: 0.000937 loss: 3.8583 (3.7812) grad_norm: 0.9487 (1.0195) time: 0.5066 [2021-03-25 12:02:39 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 870/1251] eta: 0:03:14 lr: 0.000937 loss: 3.8827 (3.7817) grad_norm: 0.9321 (1.0189) time: 0.5024 [2021-03-25 12:02:44 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 880/1251] eta: 0:03:09 lr: 0.000937 loss: 3.8712 (3.7833) grad_norm: 0.9699 (1.0187) time: 0.5019 [2021-03-25 12:02:49 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 890/1251] eta: 0:03:04 lr: 0.000937 loss: 3.4910 (3.7792) grad_norm: 1.0109 (1.0189) time: 0.5029 [2021-03-25 12:02:54 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 900/1251] eta: 0:02:59 lr: 0.000937 loss: 3.4910 (3.7781) grad_norm: 1.0074 (1.0193) time: 0.5026 [2021-03-25 12:02:59 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 910/1251] eta: 0:02:54 lr: 0.000937 loss: 3.7776 (3.7783) grad_norm: 0.9654 (1.0188) time: 0.5024 [2021-03-25 12:03:04 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 920/1251] eta: 0:02:49 lr: 0.000937 loss: 3.9298 (3.7777) grad_norm: 0.9484 (1.0177) time: 0.4993 [2021-03-25 12:03:09 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 930/1251] eta: 0:02:44 lr: 0.000937 loss: 4.0119 (3.7801) grad_norm: 0.9467 (1.0178) time: 0.5084 [2021-03-25 12:03:15 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 940/1251] eta: 0:02:38 lr: 0.000937 loss: 4.0340 (3.7833) grad_norm: 0.9664 (1.0179) time: 0.5223 [2021-03-25 12:03:20 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 950/1251] eta: 0:02:33 lr: 0.000937 loss: 4.0005 (3.7826) grad_norm: 0.9561 (1.0170) time: 0.5147 [2021-03-25 12:03:25 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 960/1251] eta: 0:02:28 lr: 0.000937 loss: 3.6484 (3.7807) grad_norm: 0.9569 (1.0171) time: 0.5038 [2021-03-25 12:03:30 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 970/1251] eta: 0:02:23 lr: 0.000937 loss: 3.5125 (3.7789) grad_norm: 0.9687 (1.0166) time: 0.5065 [2021-03-25 12:03:35 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 980/1251] eta: 0:02:18 lr: 0.000937 loss: 3.5590 (3.7782) grad_norm: 0.9631 (1.0168) time: 0.5055 [2021-03-25 12:03:40 swin_small_patch4_window7_224] INFO: Epoch: [48] [ 990/1251] eta: 0:02:13 lr: 0.000937 loss: 3.9169 (3.7828) grad_norm: 0.9929 (1.0165) time: 0.5074 [2021-03-25 12:03:45 swin_small_patch4_window7_224] INFO: Epoch: [48] [1000/1251] eta: 0:02:08 lr: 0.000937 loss: 3.8910 (3.7806) grad_norm: 0.9867 (1.0161) time: 0.5109 [2021-03-25 12:03:50 swin_small_patch4_window7_224] INFO: Epoch: [48] [1010/1251] eta: 0:02:03 lr: 0.000937 loss: 3.6878 (3.7811) grad_norm: 0.9638 (1.0156) time: 0.5103 [2021-03-25 12:03:55 swin_small_patch4_window7_224] INFO: Epoch: [48] [1020/1251] eta: 0:01:58 lr: 0.000937 loss: 3.6491 (3.7788) grad_norm: 0.9284 (1.0151) time: 0.5097 [2021-03-25 12:04:00 swin_small_patch4_window7_224] INFO: Epoch: [48] [1030/1251] eta: 0:01:52 lr: 0.000937 loss: 3.4833 (3.7778) grad_norm: 0.9945 (1.0154) time: 0.5067 [2021-03-25 12:04:05 swin_small_patch4_window7_224] INFO: Epoch: [48] [1040/1251] eta: 0:01:47 lr: 0.000937 loss: 3.5773 (3.7772) grad_norm: 1.0209 (1.0159) time: 0.5015 [2021-03-25 12:04:10 swin_small_patch4_window7_224] INFO: Epoch: [48] [1050/1251] eta: 0:01:42 lr: 0.000937 loss: 3.6762 (3.7754) grad_norm: 1.0209 (1.0161) time: 0.5037 [2021-03-25 12:04:16 swin_small_patch4_window7_224] INFO: Epoch: [48] [1060/1251] eta: 0:01:37 lr: 0.000937 loss: 3.7243 (3.7753) grad_norm: 1.0120 (1.0160) time: 0.5112 [2021-03-25 12:04:21 swin_small_patch4_window7_224] INFO: Epoch: [48] [1070/1251] eta: 0:01:32 lr: 0.000937 loss: 3.8432 (3.7768) grad_norm: 0.9876 (1.0159) time: 0.5146 [2021-03-25 12:04:26 swin_small_patch4_window7_224] INFO: Epoch: [48] [1080/1251] eta: 0:01:27 lr: 0.000937 loss: 3.8431 (3.7758) grad_norm: 0.9862 (1.0158) time: 0.5106 [2021-03-25 12:04:31 swin_small_patch4_window7_224] INFO: Epoch: [48] [1090/1251] eta: 0:01:22 lr: 0.000937 loss: 3.5926 (3.7750) grad_norm: 0.9719 (1.0153) time: 0.5053 [2021-03-25 12:04:36 swin_small_patch4_window7_224] INFO: Epoch: [48] [1100/1251] eta: 0:01:17 lr: 0.000937 loss: 3.8351 (3.7769) grad_norm: 0.9863 (1.0165) time: 0.5076 [2021-03-25 12:04:41 swin_small_patch4_window7_224] INFO: Epoch: [48] [1110/1251] eta: 0:01:11 lr: 0.000937 loss: 3.9258 (3.7771) grad_norm: 1.0080 (1.0161) time: 0.5058 [2021-03-25 12:04:46 swin_small_patch4_window7_224] INFO: Epoch: [48] [1120/1251] eta: 0:01:06 lr: 0.000937 loss: 3.7253 (3.7740) grad_norm: 1.0191 (1.0166) time: 0.5021 [2021-03-25 12:04:51 swin_small_patch4_window7_224] INFO: Epoch: [48] [1130/1251] eta: 0:01:01 lr: 0.000936 loss: 3.8213 (3.7744) grad_norm: 1.0479 (1.0177) time: 0.5040 [2021-03-25 12:04:56 swin_small_patch4_window7_224] INFO: Epoch: [48] [1140/1251] eta: 0:00:56 lr: 0.000936 loss: 3.9267 (3.7732) grad_norm: 1.0811 (1.0187) time: 0.5004 [2021-03-25 12:05:01 swin_small_patch4_window7_224] INFO: Epoch: [48] [1150/1251] eta: 0:00:51 lr: 0.000936 loss: 3.5270 (3.7718) grad_norm: 1.1285 (1.0200) time: 0.5007 [2021-03-25 12:05:06 swin_small_patch4_window7_224] INFO: Epoch: [48] [1160/1251] eta: 0:00:46 lr: 0.000936 loss: 3.6748 (3.7715) grad_norm: 1.1041 (1.0196) time: 0.5098 [2021-03-25 12:05:11 swin_small_patch4_window7_224] INFO: Epoch: [48] [1170/1251] eta: 0:00:41 lr: 0.000936 loss: 3.8694 (3.7728) grad_norm: 1.0078 (1.0198) time: 0.5137 [2021-03-25 12:05:16 swin_small_patch4_window7_224] INFO: Epoch: [48] [1180/1251] eta: 0:00:36 lr: 0.000936 loss: 4.0276 (3.7738) grad_norm: 1.0125 (1.0198) time: 0.5070 [2021-03-25 12:05:21 swin_small_patch4_window7_224] INFO: Epoch: [48] [1190/1251] eta: 0:00:31 lr: 0.000936 loss: 3.8604 (3.7743) grad_norm: 0.9905 (1.0194) time: 0.5081 [2021-03-25 12:05:26 swin_small_patch4_window7_224] INFO: Epoch: [48] [1200/1251] eta: 0:00:26 lr: 0.000936 loss: 3.7852 (3.7744) grad_norm: 0.9642 (1.0189) time: 0.5071 [2021-03-25 12:05:31 swin_small_patch4_window7_224] INFO: Epoch: [48] [1210/1251] eta: 0:00:20 lr: 0.000936 loss: 3.6380 (3.7738) grad_norm: 0.9413 (1.0184) time: 0.4985 [2021-03-25 12:05:37 swin_small_patch4_window7_224] INFO: Epoch: [48] [1220/1251] eta: 0:00:15 lr: 0.000936 loss: 3.8438 (3.7749) grad_norm: 0.9200 (1.0181) time: 0.5024 [2021-03-25 12:05:42 swin_small_patch4_window7_224] INFO: Epoch: [48] [1230/1251] eta: 0:00:10 lr: 0.000936 loss: 4.0216 (3.7767) grad_norm: 0.9564 (1.0180) time: 0.5055 [2021-03-25 12:05:47 swin_small_patch4_window7_224] INFO: Epoch: [48] [1240/1251] eta: 0:00:05 lr: 0.000936 loss: 3.4542 (3.7732) grad_norm: 0.9872 (1.0180) time: 0.5063 [2021-03-25 12:05:52 swin_small_patch4_window7_224] INFO: Epoch: [48] [1250/1251] eta: 0:00:00 lr: 0.000936 loss: 3.4542 (3.7730) grad_norm: 0.9864 (1.0182) time: 0.5075 [2021-03-25 12:05:58 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:20 loss: 1.5179 (1.5179) acc1: 59.3750 (59.3750) acc5: 89.0625 (89.0625) [2021-03-25 12:06:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1361 (1.1918) acc1: 67.1875 (69.6023) acc5: 92.1875 (91.7614) [2021-03-25 12:06:03 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0975 (1.1348) acc1: 70.3125 (71.1310) acc5: 92.1875 (92.2619) [2021-03-25 12:06:06 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1197 (1.1775) acc1: 71.8750 (71.0181) acc5: 92.1875 (91.4315) [2021-03-25 12:06:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1583 (1.1632) acc1: 71.8750 (71.3034) acc5: 90.6250 (91.5777) [2021-03-25 12:06:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1286 (1.1703) acc1: 71.8750 (71.2640) acc5: 92.1875 (91.3920) [2021-03-25 12:06:12 swin_small_patch4_window7_224] INFO: * Acc@1 72.220 Acc@5 91.450 loss 1.158 [2021-03-25 12:06:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.2% [2021-03-25 12:06:12 swin_small_patch4_window7_224] INFO: Max accuracy: 72.38% [2021-03-25 12:06:16 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 0/1251] eta: 1:28:40 lr: 0.000936 loss: 3.8628 (3.8628) grad_norm: 1.1210 (1.1210) time: 4.2530 [2021-03-25 12:06:21 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 10/1251] eta: 0:17:48 lr: 0.000936 loss: 3.9603 (3.8856) grad_norm: 1.0927 (1.0897) time: 0.8609 [2021-03-25 12:06:26 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 20/1251] eta: 0:14:11 lr: 0.000936 loss: 3.9112 (3.7520) grad_norm: 1.0740 (1.1157) time: 0.5139 [2021-03-25 12:06:31 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 30/1251] eta: 0:12:51 lr: 0.000936 loss: 3.6125 (3.7427) grad_norm: 1.0490 (1.1112) time: 0.5064 [2021-03-25 12:06:36 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 40/1251] eta: 0:12:11 lr: 0.000936 loss: 3.6125 (3.7470) grad_norm: 0.9851 (1.0848) time: 0.5121 [2021-03-25 12:06:42 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 50/1251] eta: 0:11:45 lr: 0.000936 loss: 4.1224 (3.8008) grad_norm: 0.9594 (1.0614) time: 0.5175 [2021-03-25 12:06:47 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 60/1251] eta: 0:11:22 lr: 0.000936 loss: 3.7818 (3.7334) grad_norm: 0.9594 (1.0487) time: 0.5086 [2021-03-25 12:06:51 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 70/1251] eta: 0:11:03 lr: 0.000936 loss: 3.7405 (3.7491) grad_norm: 0.9594 (1.0403) time: 0.4978 [2021-03-25 12:06:57 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 80/1251] eta: 0:10:49 lr: 0.000936 loss: 3.7383 (3.7252) grad_norm: 1.0114 (1.0499) time: 0.4994 [2021-03-25 12:07:02 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 90/1251] eta: 0:10:39 lr: 0.000936 loss: 3.8225 (3.7177) grad_norm: 1.0879 (1.0521) time: 0.5129 [2021-03-25 12:07:07 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 100/1251] eta: 0:10:29 lr: 0.000936 loss: 3.8387 (3.7040) grad_norm: 0.9488 (1.0420) time: 0.5133 [2021-03-25 12:07:12 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 110/1251] eta: 0:10:19 lr: 0.000936 loss: 3.8612 (3.7028) grad_norm: 0.9644 (1.0374) time: 0.5067 [2021-03-25 12:07:17 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 120/1251] eta: 0:10:11 lr: 0.000936 loss: 3.6378 (3.7003) grad_norm: 1.0100 (1.0413) time: 0.5109 [2021-03-25 12:07:22 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 130/1251] eta: 0:10:03 lr: 0.000936 loss: 3.5958 (3.6901) grad_norm: 1.0404 (1.0433) time: 0.5110 [2021-03-25 12:07:27 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 140/1251] eta: 0:09:55 lr: 0.000936 loss: 3.5775 (3.6931) grad_norm: 1.0273 (1.0394) time: 0.5073 [2021-03-25 12:07:32 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 150/1251] eta: 0:09:48 lr: 0.000936 loss: 3.7809 (3.6900) grad_norm: 0.9901 (1.0445) time: 0.5074 [2021-03-25 12:07:37 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 160/1251] eta: 0:09:40 lr: 0.000936 loss: 3.7980 (3.6991) grad_norm: 1.0226 (1.0466) time: 0.5023 [2021-03-25 12:07:42 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 170/1251] eta: 0:09:33 lr: 0.000936 loss: 3.7396 (3.6806) grad_norm: 0.9405 (1.0409) time: 0.4999 [2021-03-25 12:07:47 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 180/1251] eta: 0:09:26 lr: 0.000936 loss: 3.6094 (3.6903) grad_norm: 0.9897 (1.0416) time: 0.5063 [2021-03-25 12:07:52 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 190/1251] eta: 0:09:20 lr: 0.000936 loss: 3.9523 (3.6901) grad_norm: 1.0081 (1.0381) time: 0.5105 [2021-03-25 12:07:58 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 200/1251] eta: 0:09:14 lr: 0.000936 loss: 3.5482 (3.6873) grad_norm: 1.0194 (1.0392) time: 0.5112 [2021-03-25 12:08:03 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 210/1251] eta: 0:09:07 lr: 0.000936 loss: 3.5194 (3.6710) grad_norm: 1.0430 (1.0403) time: 0.5058 [2021-03-25 12:08:08 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 220/1251] eta: 0:09:01 lr: 0.000936 loss: 3.8328 (3.6798) grad_norm: 1.0418 (1.0411) time: 0.5019 [2021-03-25 12:08:13 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 230/1251] eta: 0:08:55 lr: 0.000936 loss: 3.9157 (3.6905) grad_norm: 1.0800 (1.0426) time: 0.5050 [2021-03-25 12:08:18 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 240/1251] eta: 0:08:49 lr: 0.000936 loss: 3.9471 (3.6960) grad_norm: 1.0651 (1.0431) time: 0.5066 [2021-03-25 12:08:23 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 250/1251] eta: 0:08:43 lr: 0.000936 loss: 3.9129 (3.6969) grad_norm: 1.0675 (1.0460) time: 0.5038 [2021-03-25 12:08:28 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 260/1251] eta: 0:08:36 lr: 0.000936 loss: 3.8390 (3.6982) grad_norm: 1.0622 (1.0456) time: 0.5004 [2021-03-25 12:08:33 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 270/1251] eta: 0:08:31 lr: 0.000936 loss: 3.8020 (3.7006) grad_norm: 1.0372 (1.0474) time: 0.5014 [2021-03-25 12:08:38 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 280/1251] eta: 0:08:25 lr: 0.000936 loss: 3.8020 (3.7045) grad_norm: 1.0442 (1.0472) time: 0.5029 [2021-03-25 12:08:43 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 290/1251] eta: 0:08:19 lr: 0.000936 loss: 3.8076 (3.7046) grad_norm: 1.0422 (1.0460) time: 0.5007 [2021-03-25 12:08:48 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 300/1251] eta: 0:08:13 lr: 0.000936 loss: 3.7760 (3.7006) grad_norm: 0.9883 (1.0429) time: 0.5004 [2021-03-25 12:08:53 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 310/1251] eta: 0:08:07 lr: 0.000936 loss: 3.8285 (3.7034) grad_norm: 0.9499 (1.0423) time: 0.5001 [2021-03-25 12:08:58 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 320/1251] eta: 0:08:02 lr: 0.000936 loss: 3.7020 (3.6999) grad_norm: 1.0134 (1.0423) time: 0.5069 [2021-03-25 12:09:03 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 330/1251] eta: 0:07:56 lr: 0.000936 loss: 3.7415 (3.7041) grad_norm: 1.0121 (1.0394) time: 0.5093 [2021-03-25 12:09:08 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 340/1251] eta: 0:07:51 lr: 0.000936 loss: 3.8567 (3.7019) grad_norm: 1.0078 (1.0392) time: 0.5059 [2021-03-25 12:09:13 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 350/1251] eta: 0:07:46 lr: 0.000936 loss: 3.7087 (3.6992) grad_norm: 1.0248 (1.0388) time: 0.5112 [2021-03-25 12:09:18 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 360/1251] eta: 0:07:40 lr: 0.000936 loss: 3.6947 (3.7025) grad_norm: 0.9817 (1.0366) time: 0.5123 [2021-03-25 12:09:23 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 370/1251] eta: 0:07:35 lr: 0.000935 loss: 3.8968 (3.7096) grad_norm: 0.9604 (1.0357) time: 0.5041 [2021-03-25 12:09:28 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 380/1251] eta: 0:07:29 lr: 0.000935 loss: 3.9844 (3.7130) grad_norm: 0.9581 (1.0340) time: 0.5050 [2021-03-25 12:09:33 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 390/1251] eta: 0:07:24 lr: 0.000935 loss: 3.5648 (3.7087) grad_norm: 1.0120 (1.0363) time: 0.5057 [2021-03-25 12:09:38 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 400/1251] eta: 0:07:18 lr: 0.000935 loss: 3.9194 (3.7204) grad_norm: 1.0863 (1.0378) time: 0.4994 [2021-03-25 12:09:44 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 410/1251] eta: 0:07:13 lr: 0.000935 loss: 4.0064 (3.7204) grad_norm: 1.0211 (1.0369) time: 0.5041 [2021-03-25 12:09:49 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 420/1251] eta: 0:07:08 lr: 0.000935 loss: 3.9240 (3.7218) grad_norm: 0.9641 (1.0354) time: 0.5088 [2021-03-25 12:09:54 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 430/1251] eta: 0:07:02 lr: 0.000935 loss: 4.0039 (3.7226) grad_norm: 0.9651 (1.0349) time: 0.5006 [2021-03-25 12:09:59 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 440/1251] eta: 0:06:57 lr: 0.000935 loss: 4.0164 (3.7291) grad_norm: 1.0262 (1.0380) time: 0.5002 [2021-03-25 12:10:04 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 450/1251] eta: 0:06:52 lr: 0.000935 loss: 3.8694 (3.7320) grad_norm: 1.0150 (1.0363) time: 0.5053 [2021-03-25 12:10:09 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 460/1251] eta: 0:06:46 lr: 0.000935 loss: 3.7826 (3.7319) grad_norm: 0.9596 (1.0350) time: 0.5084 [2021-03-25 12:10:14 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 470/1251] eta: 0:06:41 lr: 0.000935 loss: 3.7814 (3.7287) grad_norm: 0.9549 (1.0335) time: 0.5074 [2021-03-25 12:10:19 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 480/1251] eta: 0:06:36 lr: 0.000935 loss: 3.7801 (3.7291) grad_norm: 0.9616 (1.0336) time: 0.5043 [2021-03-25 12:10:24 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 490/1251] eta: 0:06:30 lr: 0.000935 loss: 3.8823 (3.7339) grad_norm: 0.9846 (1.0332) time: 0.5049 [2021-03-25 12:10:29 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 500/1251] eta: 0:06:25 lr: 0.000935 loss: 3.8823 (3.7262) grad_norm: 0.9770 (1.0328) time: 0.5071 [2021-03-25 12:10:34 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 510/1251] eta: 0:06:20 lr: 0.000935 loss: 3.7133 (3.7278) grad_norm: 0.9718 (1.0317) time: 0.5050 [2021-03-25 12:10:39 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 520/1251] eta: 0:06:15 lr: 0.000935 loss: 3.9678 (3.7318) grad_norm: 0.9707 (1.0304) time: 0.5036 [2021-03-25 12:10:44 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 530/1251] eta: 0:06:10 lr: 0.000935 loss: 3.9678 (3.7283) grad_norm: 0.9491 (1.0293) time: 0.5072 [2021-03-25 12:10:49 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 540/1251] eta: 0:06:04 lr: 0.000935 loss: 3.7587 (3.7279) grad_norm: 0.9703 (1.0283) time: 0.5131 [2021-03-25 12:10:55 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 550/1251] eta: 0:05:59 lr: 0.000935 loss: 3.6035 (3.7262) grad_norm: 1.0176 (1.0300) time: 0.5160 [2021-03-25 12:11:00 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 560/1251] eta: 0:05:54 lr: 0.000935 loss: 3.5843 (3.7230) grad_norm: 1.0845 (inf) time: 0.5074 [2021-03-25 12:11:05 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 570/1251] eta: 0:05:49 lr: 0.000935 loss: 3.9021 (3.7272) grad_norm: 1.0514 (inf) time: 0.5054 [2021-03-25 12:11:10 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 580/1251] eta: 0:05:44 lr: 0.000935 loss: 3.9021 (3.7286) grad_norm: 1.0470 (inf) time: 0.5066 [2021-03-25 12:11:15 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 590/1251] eta: 0:05:39 lr: 0.000935 loss: 3.8161 (3.7303) grad_norm: 1.0188 (inf) time: 0.5104 [2021-03-25 12:11:20 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 600/1251] eta: 0:05:33 lr: 0.000935 loss: 3.8852 (3.7323) grad_norm: 1.0391 (inf) time: 0.5144 [2021-03-25 12:11:25 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 610/1251] eta: 0:05:28 lr: 0.000935 loss: 3.8592 (3.7340) grad_norm: 1.0344 (inf) time: 0.5058 [2021-03-25 12:11:30 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 620/1251] eta: 0:05:23 lr: 0.000935 loss: 3.8212 (3.7372) grad_norm: 0.9739 (inf) time: 0.5009 [2021-03-25 12:11:35 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 630/1251] eta: 0:05:18 lr: 0.000935 loss: 3.9779 (3.7392) grad_norm: 0.9808 (inf) time: 0.5075 [2021-03-25 12:11:40 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 640/1251] eta: 0:05:13 lr: 0.000935 loss: 3.9920 (3.7423) grad_norm: 0.9823 (inf) time: 0.5087 [2021-03-25 12:11:45 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 650/1251] eta: 0:05:07 lr: 0.000935 loss: 4.0527 (3.7452) grad_norm: 0.9396 (inf) time: 0.5058 [2021-03-25 12:11:50 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 660/1251] eta: 0:05:02 lr: 0.000935 loss: 3.8943 (3.7422) grad_norm: 1.0028 (inf) time: 0.5073 [2021-03-25 12:11:55 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 670/1251] eta: 0:04:57 lr: 0.000935 loss: 3.6354 (3.7426) grad_norm: 1.0298 (inf) time: 0.5055 [2021-03-25 12:12:00 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 680/1251] eta: 0:04:52 lr: 0.000935 loss: 3.7238 (3.7394) grad_norm: 1.0326 (inf) time: 0.5065 [2021-03-25 12:12:06 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 690/1251] eta: 0:04:47 lr: 0.000935 loss: 3.6270 (3.7369) grad_norm: 0.9823 (inf) time: 0.5152 [2021-03-25 12:12:11 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 700/1251] eta: 0:04:42 lr: 0.000935 loss: 3.7749 (3.7392) grad_norm: 1.0083 (inf) time: 0.5130 [2021-03-25 12:12:16 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 710/1251] eta: 0:04:37 lr: 0.000935 loss: 3.7749 (3.7380) grad_norm: 0.9985 (inf) time: 0.5078 [2021-03-25 12:12:21 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 720/1251] eta: 0:04:31 lr: 0.000935 loss: 3.8256 (3.7392) grad_norm: 0.9662 (inf) time: 0.5121 [2021-03-25 12:12:26 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 730/1251] eta: 0:04:26 lr: 0.000935 loss: 3.8742 (3.7415) grad_norm: 0.9822 (inf) time: 0.5144 [2021-03-25 12:12:31 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 740/1251] eta: 0:04:21 lr: 0.000935 loss: 3.7576 (3.7413) grad_norm: 0.9512 (inf) time: 0.5230 [2021-03-25 12:12:37 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 750/1251] eta: 0:04:16 lr: 0.000935 loss: 3.9820 (3.7425) grad_norm: 1.0041 (inf) time: 0.5234 [2021-03-25 12:12:42 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 760/1251] eta: 0:04:11 lr: 0.000935 loss: 4.0139 (3.7440) grad_norm: 1.0238 (inf) time: 0.5125 [2021-03-25 12:12:47 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 770/1251] eta: 0:04:06 lr: 0.000935 loss: 3.8401 (3.7431) grad_norm: 1.0238 (inf) time: 0.5097 [2021-03-25 12:12:52 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 780/1251] eta: 0:04:01 lr: 0.000935 loss: 3.7176 (3.7408) grad_norm: 0.9740 (inf) time: 0.5141 [2021-03-25 12:12:57 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 790/1251] eta: 0:03:56 lr: 0.000935 loss: 3.8321 (3.7421) grad_norm: 1.0341 (inf) time: 0.5209 [2021-03-25 12:13:02 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 800/1251] eta: 0:03:51 lr: 0.000935 loss: 3.7708 (3.7395) grad_norm: 1.0542 (inf) time: 0.5141 [2021-03-25 12:13:07 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 810/1251] eta: 0:03:45 lr: 0.000935 loss: 3.4967 (3.7361) grad_norm: 1.0363 (inf) time: 0.5064 [2021-03-25 12:13:12 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 820/1251] eta: 0:03:40 lr: 0.000935 loss: 3.6456 (3.7358) grad_norm: 1.0258 (inf) time: 0.5034 [2021-03-25 12:13:17 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 830/1251] eta: 0:03:35 lr: 0.000935 loss: 3.7398 (3.7343) grad_norm: 1.0055 (inf) time: 0.5023 [2021-03-25 12:13:22 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 840/1251] eta: 0:03:30 lr: 0.000935 loss: 3.6606 (3.7344) grad_norm: 1.0035 (inf) time: 0.5083 [2021-03-25 12:13:27 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 850/1251] eta: 0:03:25 lr: 0.000935 loss: 3.7012 (3.7351) grad_norm: 1.0436 (inf) time: 0.5057 [2021-03-25 12:13:33 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 860/1251] eta: 0:03:20 lr: 0.000934 loss: 3.7012 (3.7352) grad_norm: 0.9830 (inf) time: 0.5052 [2021-03-25 12:13:38 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 870/1251] eta: 0:03:15 lr: 0.000934 loss: 3.8437 (3.7358) grad_norm: 0.9609 (inf) time: 0.5129 [2021-03-25 12:13:43 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 880/1251] eta: 0:03:09 lr: 0.000934 loss: 3.9523 (3.7387) grad_norm: 0.9685 (inf) time: 0.5148 [2021-03-25 12:13:48 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 890/1251] eta: 0:03:04 lr: 0.000934 loss: 3.9213 (3.7396) grad_norm: 1.0369 (inf) time: 0.5110 [2021-03-25 12:13:53 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 900/1251] eta: 0:02:59 lr: 0.000934 loss: 3.7856 (3.7393) grad_norm: 1.1189 (inf) time: 0.5075 [2021-03-25 12:13:58 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 910/1251] eta: 0:02:54 lr: 0.000934 loss: 3.8628 (3.7401) grad_norm: 1.0716 (inf) time: 0.5102 [2021-03-25 12:14:03 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 920/1251] eta: 0:02:49 lr: 0.000934 loss: 3.8712 (3.7390) grad_norm: 0.9951 (inf) time: 0.5070 [2021-03-25 12:14:08 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 930/1251] eta: 0:02:44 lr: 0.000934 loss: 3.8374 (3.7387) grad_norm: 1.0006 (inf) time: 0.5093 [2021-03-25 12:14:13 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 940/1251] eta: 0:02:39 lr: 0.000934 loss: 3.4905 (3.7357) grad_norm: 1.0730 (inf) time: 0.5143 [2021-03-25 12:14:18 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 950/1251] eta: 0:02:34 lr: 0.000934 loss: 3.5814 (3.7373) grad_norm: 0.9995 (inf) time: 0.5062 [2021-03-25 12:14:24 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 960/1251] eta: 0:02:28 lr: 0.000934 loss: 3.7025 (3.7360) grad_norm: 0.9375 (inf) time: 0.5046 [2021-03-25 12:14:29 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 970/1251] eta: 0:02:23 lr: 0.000934 loss: 3.8905 (3.7364) grad_norm: 0.9767 (inf) time: 0.5047 [2021-03-25 12:14:34 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 980/1251] eta: 0:02:18 lr: 0.000934 loss: 3.7088 (3.7346) grad_norm: 0.9951 (inf) time: 0.4993 [2021-03-25 12:14:39 swin_small_patch4_window7_224] INFO: Epoch: [49] [ 990/1251] eta: 0:02:13 lr: 0.000934 loss: 3.8093 (3.7364) grad_norm: 1.0723 (inf) time: 0.5031 [2021-03-25 12:14:44 swin_small_patch4_window7_224] INFO: Epoch: [49] [1000/1251] eta: 0:02:08 lr: 0.000934 loss: 4.1140 (3.7392) grad_norm: 1.0984 (inf) time: 0.5079 [2021-03-25 12:14:49 swin_small_patch4_window7_224] INFO: Epoch: [49] [1010/1251] eta: 0:02:03 lr: 0.000934 loss: 4.0110 (3.7384) grad_norm: 1.0058 (inf) time: 0.5108 [2021-03-25 12:14:54 swin_small_patch4_window7_224] INFO: Epoch: [49] [1020/1251] eta: 0:01:58 lr: 0.000934 loss: 3.7233 (3.7386) grad_norm: 0.9600 (inf) time: 0.5066 [2021-03-25 12:14:59 swin_small_patch4_window7_224] INFO: Epoch: [49] [1030/1251] eta: 0:01:53 lr: 0.000934 loss: 3.7422 (3.7391) grad_norm: 1.0033 (inf) time: 0.5051 [2021-03-25 12:15:04 swin_small_patch4_window7_224] INFO: Epoch: [49] [1040/1251] eta: 0:01:47 lr: 0.000934 loss: 4.0359 (3.7402) grad_norm: 1.0372 (inf) time: 0.5096 [2021-03-25 12:15:09 swin_small_patch4_window7_224] INFO: Epoch: [49] [1050/1251] eta: 0:01:42 lr: 0.000934 loss: 4.0074 (3.7395) grad_norm: 1.0177 (inf) time: 0.5059 [2021-03-25 12:15:14 swin_small_patch4_window7_224] INFO: Epoch: [49] [1060/1251] eta: 0:01:37 lr: 0.000934 loss: 3.7774 (3.7404) grad_norm: 1.0136 (inf) time: 0.5076 [2021-03-25 12:15:19 swin_small_patch4_window7_224] INFO: Epoch: [49] [1070/1251] eta: 0:01:32 lr: 0.000934 loss: 3.9701 (3.7427) grad_norm: 1.0114 (inf) time: 0.5064 [2021-03-25 12:15:24 swin_small_patch4_window7_224] INFO: Epoch: [49] [1080/1251] eta: 0:01:27 lr: 0.000934 loss: 3.5465 (3.7380) grad_norm: 0.9912 (inf) time: 0.5055 [2021-03-25 12:15:29 swin_small_patch4_window7_224] INFO: Epoch: [49] [1090/1251] eta: 0:01:22 lr: 0.000934 loss: 3.4286 (3.7385) grad_norm: 0.9411 (inf) time: 0.5109 [2021-03-25 12:15:34 swin_small_patch4_window7_224] INFO: Epoch: [49] [1100/1251] eta: 0:01:17 lr: 0.000934 loss: 3.8461 (3.7392) grad_norm: 0.9638 (inf) time: 0.5076 [2021-03-25 12:15:40 swin_small_patch4_window7_224] INFO: Epoch: [49] [1110/1251] eta: 0:01:12 lr: 0.000934 loss: 3.7642 (3.7402) grad_norm: 0.9638 (inf) time: 0.5046 [2021-03-25 12:15:45 swin_small_patch4_window7_224] INFO: Epoch: [49] [1120/1251] eta: 0:01:06 lr: 0.000934 loss: 3.5638 (3.7377) grad_norm: 0.9339 (inf) time: 0.5086 [2021-03-25 12:15:50 swin_small_patch4_window7_224] INFO: Epoch: [49] [1130/1251] eta: 0:01:01 lr: 0.000934 loss: 3.5638 (3.7372) grad_norm: 0.9304 (inf) time: 0.5065 [2021-03-25 12:15:55 swin_small_patch4_window7_224] INFO: Epoch: [49] [1140/1251] eta: 0:00:56 lr: 0.000934 loss: 3.7842 (3.7383) grad_norm: 0.9465 (inf) time: 0.5066 [2021-03-25 12:16:00 swin_small_patch4_window7_224] INFO: Epoch: [49] [1150/1251] eta: 0:00:51 lr: 0.000934 loss: 3.8851 (3.7397) grad_norm: 0.9996 (inf) time: 0.5060 [2021-03-25 12:16:05 swin_small_patch4_window7_224] INFO: Epoch: [49] [1160/1251] eta: 0:00:46 lr: 0.000934 loss: 3.7939 (3.7402) grad_norm: 0.9953 (inf) time: 0.5010 [2021-03-25 12:16:10 swin_small_patch4_window7_224] INFO: Epoch: [49] [1170/1251] eta: 0:00:41 lr: 0.000934 loss: 3.7569 (3.7392) grad_norm: 0.9932 (inf) time: 0.5031 [2021-03-25 12:16:15 swin_small_patch4_window7_224] INFO: Epoch: [49] [1180/1251] eta: 0:00:36 lr: 0.000934 loss: 3.7497 (3.7375) grad_norm: 0.9735 (inf) time: 0.5060 [2021-03-25 12:16:20 swin_small_patch4_window7_224] INFO: Epoch: [49] [1190/1251] eta: 0:00:31 lr: 0.000934 loss: 3.7137 (3.7374) grad_norm: 0.9735 (inf) time: 0.5043 [2021-03-25 12:16:25 swin_small_patch4_window7_224] INFO: Epoch: [49] [1200/1251] eta: 0:00:26 lr: 0.000934 loss: 3.7137 (3.7366) grad_norm: 1.0149 (inf) time: 0.5020 [2021-03-25 12:16:30 swin_small_patch4_window7_224] INFO: Epoch: [49] [1210/1251] eta: 0:00:20 lr: 0.000934 loss: 3.9641 (3.7390) grad_norm: 1.0786 (inf) time: 0.5042 [2021-03-25 12:16:35 swin_small_patch4_window7_224] INFO: Epoch: [49] [1220/1251] eta: 0:00:15 lr: 0.000934 loss: 3.6975 (3.7348) grad_norm: 1.0581 (inf) time: 0.5054 [2021-03-25 12:16:40 swin_small_patch4_window7_224] INFO: Epoch: [49] [1230/1251] eta: 0:00:10 lr: 0.000934 loss: 3.3735 (3.7352) grad_norm: 1.0581 (inf) time: 0.5005 [2021-03-25 12:16:45 swin_small_patch4_window7_224] INFO: Epoch: [49] [1240/1251] eta: 0:00:05 lr: 0.000934 loss: 3.8302 (3.7373) grad_norm: 1.0167 (inf) time: 0.5021 [2021-03-25 12:16:50 swin_small_patch4_window7_224] INFO: Epoch: [49] [1250/1251] eta: 0:00:00 lr: 0.000934 loss: 4.0202 (3.7393) grad_norm: 1.0469 (inf) time: 0.5074 [2021-03-25 12:16:55 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:15 loss: 1.1003 (1.1003) acc1: 73.4375 (73.4375) acc5: 90.6250 (90.6250) [2021-03-25 12:16:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1970 (1.1510) acc1: 71.8750 (73.2955) acc5: 92.1875 (93.4659) [2021-03-25 12:17:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1970 (1.1914) acc1: 71.8750 (72.6935) acc5: 92.1875 (92.2619) [2021-03-25 12:17:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1334 (1.2167) acc1: 71.8750 (71.8246) acc5: 92.1875 (91.5323) [2021-03-25 12:17:04 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1722 (1.2219) acc1: 71.8750 (71.7988) acc5: 90.6250 (91.4253) [2021-03-25 12:17:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1332 (1.2027) acc1: 71.8750 (72.2240) acc5: 90.6250 (91.6480) [2021-03-25 12:17:08 swin_small_patch4_window7_224] INFO: * Acc@1 72.430 Acc@5 91.734 loss 1.171 [2021-03-25 12:17:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.4% [2021-03-25 12:17:08 swin_small_patch4_window7_224] INFO: Max accuracy: 72.43% [2021-03-25 12:17:12 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 0/1251] eta: 1:24:58 lr: 0.000934 loss: 3.2024 (3.2024) grad_norm: 0.9936 (0.9936) time: 4.0753 [2021-03-25 12:17:17 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 10/1251] eta: 0:17:23 lr: 0.000934 loss: 3.4487 (3.6332) grad_norm: 0.9817 (0.9822) time: 0.8409 [2021-03-25 12:17:22 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 20/1251] eta: 0:14:03 lr: 0.000934 loss: 3.6100 (3.7084) grad_norm: 1.0232 (1.0251) time: 0.5159 [2021-03-25 12:17:27 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 30/1251] eta: 0:12:51 lr: 0.000934 loss: 3.7982 (3.7295) grad_norm: 1.0232 (1.0155) time: 0.5164 [2021-03-25 12:17:32 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 40/1251] eta: 0:12:11 lr: 0.000934 loss: 3.6471 (3.6947) grad_norm: 1.0031 (1.0301) time: 0.5189 [2021-03-25 12:17:37 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 50/1251] eta: 0:11:42 lr: 0.000934 loss: 3.6471 (3.6756) grad_norm: 1.0414 (1.0377) time: 0.5121 [2021-03-25 12:17:43 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 60/1251] eta: 0:11:22 lr: 0.000934 loss: 3.8380 (3.7298) grad_norm: 1.0601 (1.0405) time: 0.5103 [2021-03-25 12:17:48 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 70/1251] eta: 0:11:05 lr: 0.000934 loss: 3.7690 (3.7188) grad_norm: 1.0569 (1.0472) time: 0.5090 [2021-03-25 12:17:53 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 80/1251] eta: 0:10:51 lr: 0.000934 loss: 3.5323 (3.7022) grad_norm: 1.0815 (1.0495) time: 0.5042 [2021-03-25 12:17:58 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 90/1251] eta: 0:10:39 lr: 0.000933 loss: 3.7590 (3.7116) grad_norm: 1.0070 (1.0432) time: 0.5060 [2021-03-25 12:18:03 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 100/1251] eta: 0:10:27 lr: 0.000933 loss: 3.7590 (3.6797) grad_norm: 0.9808 (1.0408) time: 0.5014 [2021-03-25 12:18:08 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 110/1251] eta: 0:10:19 lr: 0.000933 loss: 3.8034 (3.7065) grad_norm: 1.0321 (1.0481) time: 0.5050 [2021-03-25 12:18:13 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 120/1251] eta: 0:10:11 lr: 0.000933 loss: 4.0356 (3.7309) grad_norm: 0.9911 (1.0395) time: 0.5170 [2021-03-25 12:18:18 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 130/1251] eta: 0:10:03 lr: 0.000933 loss: 3.7968 (3.7117) grad_norm: 0.9395 (1.0343) time: 0.5141 [2021-03-25 12:18:23 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 140/1251] eta: 0:09:55 lr: 0.000933 loss: 3.7968 (3.7398) grad_norm: 1.0283 (1.0393) time: 0.5078 [2021-03-25 12:18:28 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 150/1251] eta: 0:09:47 lr: 0.000933 loss: 3.9306 (3.7321) grad_norm: 1.0746 (1.0422) time: 0.5068 [2021-03-25 12:18:33 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 160/1251] eta: 0:09:40 lr: 0.000933 loss: 3.8006 (3.7280) grad_norm: 1.0662 (1.0424) time: 0.5048 [2021-03-25 12:18:38 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 170/1251] eta: 0:09:33 lr: 0.000933 loss: 3.8677 (3.7392) grad_norm: 1.0457 (1.0407) time: 0.5034 [2021-03-25 12:18:44 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 180/1251] eta: 0:09:27 lr: 0.000933 loss: 3.7760 (3.7366) grad_norm: 0.9757 (1.0386) time: 0.5129 [2021-03-25 12:18:49 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 190/1251] eta: 0:09:21 lr: 0.000933 loss: 3.8277 (3.7490) grad_norm: 0.9765 (1.0362) time: 0.5194 [2021-03-25 12:18:54 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 200/1251] eta: 0:09:15 lr: 0.000933 loss: 3.8504 (3.7395) grad_norm: 0.9779 (1.0349) time: 0.5113 [2021-03-25 12:18:59 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 210/1251] eta: 0:09:08 lr: 0.000933 loss: 3.6419 (3.7357) grad_norm: 0.9910 (1.0361) time: 0.5081 [2021-03-25 12:19:04 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 220/1251] eta: 0:09:02 lr: 0.000933 loss: 3.8505 (3.7375) grad_norm: 1.0805 (1.0420) time: 0.5089 [2021-03-25 12:19:09 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 230/1251] eta: 0:08:56 lr: 0.000933 loss: 3.7440 (3.7337) grad_norm: 1.0805 (1.0421) time: 0.5069 [2021-03-25 12:19:14 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 240/1251] eta: 0:08:50 lr: 0.000933 loss: 3.7958 (3.7442) grad_norm: 1.0234 (1.0420) time: 0.5079 [2021-03-25 12:19:19 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 250/1251] eta: 0:08:44 lr: 0.000933 loss: 3.8055 (3.7357) grad_norm: 1.0233 (1.0413) time: 0.5104 [2021-03-25 12:19:24 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 260/1251] eta: 0:08:38 lr: 0.000933 loss: 3.7265 (3.7414) grad_norm: 1.0076 (1.0406) time: 0.5061 [2021-03-25 12:19:29 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 270/1251] eta: 0:08:32 lr: 0.000933 loss: 3.9840 (3.7449) grad_norm: 1.0218 (1.0411) time: 0.5040 [2021-03-25 12:19:34 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 280/1251] eta: 0:08:27 lr: 0.000933 loss: 3.9648 (3.7450) grad_norm: 1.0140 (1.0395) time: 0.5081 [2021-03-25 12:19:39 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 290/1251] eta: 0:08:21 lr: 0.000933 loss: 3.8334 (3.7418) grad_norm: 1.0301 (1.0409) time: 0.5066 [2021-03-25 12:19:45 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 300/1251] eta: 0:08:15 lr: 0.000933 loss: 3.3114 (3.7292) grad_norm: 1.0565 (1.0427) time: 0.5082 [2021-03-25 12:19:50 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 310/1251] eta: 0:08:10 lr: 0.000933 loss: 3.8182 (3.7412) grad_norm: 1.0647 (1.0449) time: 0.5148 [2021-03-25 12:19:55 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 320/1251] eta: 0:08:05 lr: 0.000933 loss: 4.0437 (3.7449) grad_norm: 1.0487 (1.0454) time: 0.5199 [2021-03-25 12:20:00 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 330/1251] eta: 0:07:59 lr: 0.000933 loss: 3.9939 (3.7529) grad_norm: 0.9942 (1.0444) time: 0.5100 [2021-03-25 12:20:05 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 340/1251] eta: 0:07:53 lr: 0.000933 loss: 3.9309 (3.7513) grad_norm: 0.9683 (1.0434) time: 0.4951 [2021-03-25 12:20:10 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 350/1251] eta: 0:07:47 lr: 0.000933 loss: 4.0310 (3.7640) grad_norm: 1.0181 (1.0436) time: 0.4999 [2021-03-25 12:20:15 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 360/1251] eta: 0:07:42 lr: 0.000933 loss: 4.0310 (3.7666) grad_norm: 1.0378 (1.0436) time: 0.5086 [2021-03-25 12:20:20 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 370/1251] eta: 0:07:37 lr: 0.000933 loss: 3.8147 (3.7616) grad_norm: 1.0115 (1.0431) time: 0.5103 [2021-03-25 12:20:25 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 380/1251] eta: 0:07:31 lr: 0.000933 loss: 3.7744 (3.7645) grad_norm: 1.0532 (1.0452) time: 0.5050 [2021-03-25 12:20:30 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 390/1251] eta: 0:07:26 lr: 0.000933 loss: 3.7795 (3.7620) grad_norm: 1.0856 (1.0456) time: 0.5054 [2021-03-25 12:20:35 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 400/1251] eta: 0:07:20 lr: 0.000933 loss: 3.9413 (3.7639) grad_norm: 1.0050 (1.0441) time: 0.5041 [2021-03-25 12:20:40 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 410/1251] eta: 0:07:15 lr: 0.000933 loss: 3.8194 (3.7595) grad_norm: 0.9714 (1.0434) time: 0.5040 [2021-03-25 12:20:45 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 420/1251] eta: 0:07:09 lr: 0.000933 loss: 3.8194 (3.7644) grad_norm: 1.0138 (1.0439) time: 0.5056 [2021-03-25 12:20:50 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 430/1251] eta: 0:07:04 lr: 0.000933 loss: 4.0515 (3.7720) grad_norm: 1.0133 (1.0423) time: 0.5002 [2021-03-25 12:20:56 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 440/1251] eta: 0:06:59 lr: 0.000933 loss: 4.0515 (3.7681) grad_norm: 0.9815 (1.0408) time: 0.5067 [2021-03-25 12:21:01 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 450/1251] eta: 0:06:53 lr: 0.000933 loss: 3.8884 (3.7656) grad_norm: 0.9784 (1.0402) time: 0.5123 [2021-03-25 12:21:06 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 460/1251] eta: 0:06:48 lr: 0.000933 loss: 3.8038 (3.7650) grad_norm: 0.9916 (1.0398) time: 0.5066 [2021-03-25 12:21:11 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 470/1251] eta: 0:06:43 lr: 0.000933 loss: 3.8802 (3.7644) grad_norm: 1.0027 (1.0404) time: 0.5073 [2021-03-25 12:21:16 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 480/1251] eta: 0:06:37 lr: 0.000933 loss: 3.9081 (3.7613) grad_norm: 1.0027 (1.0393) time: 0.5061 [2021-03-25 12:21:21 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 490/1251] eta: 0:06:32 lr: 0.000933 loss: 3.6491 (3.7568) grad_norm: 1.0215 (1.0389) time: 0.5017 [2021-03-25 12:21:26 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 500/1251] eta: 0:06:26 lr: 0.000933 loss: 3.6909 (3.7603) grad_norm: 1.0292 (1.0387) time: 0.4995 [2021-03-25 12:21:31 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 510/1251] eta: 0:06:21 lr: 0.000933 loss: 3.7725 (3.7605) grad_norm: 1.0331 (1.0391) time: 0.4996 [2021-03-25 12:21:36 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 520/1251] eta: 0:06:16 lr: 0.000933 loss: 3.7725 (3.7564) grad_norm: 1.0740 (1.0400) time: 0.5013 [2021-03-25 12:21:41 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 530/1251] eta: 0:06:10 lr: 0.000933 loss: 3.8221 (3.7592) grad_norm: 1.0468 (1.0393) time: 0.5010 [2021-03-25 12:21:46 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 540/1251] eta: 0:06:05 lr: 0.000933 loss: 3.8913 (3.7619) grad_norm: 1.0002 (1.0393) time: 0.5055 [2021-03-25 12:21:51 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 550/1251] eta: 0:06:00 lr: 0.000933 loss: 3.8630 (3.7650) grad_norm: 0.9776 (1.0374) time: 0.5175 [2021-03-25 12:21:56 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 560/1251] eta: 0:05:55 lr: 0.000933 loss: 3.7303 (3.7626) grad_norm: 0.9743 (1.0376) time: 0.5155 [2021-03-25 12:22:01 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 570/1251] eta: 0:05:50 lr: 0.000932 loss: 3.7665 (3.7662) grad_norm: 1.0109 (1.0371) time: 0.5018 [2021-03-25 12:22:06 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 580/1251] eta: 0:05:44 lr: 0.000932 loss: 3.8708 (3.7679) grad_norm: 1.0049 (1.0375) time: 0.5033 [2021-03-25 12:22:11 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 590/1251] eta: 0:05:39 lr: 0.000932 loss: 3.6636 (3.7661) grad_norm: 1.0007 (1.0370) time: 0.5115 [2021-03-25 12:22:17 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 600/1251] eta: 0:05:34 lr: 0.000932 loss: 3.6019 (3.7634) grad_norm: 0.9909 (1.0364) time: 0.5145 [2021-03-25 12:22:22 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 610/1251] eta: 0:05:29 lr: 0.000932 loss: 3.6327 (3.7604) grad_norm: 0.9846 (1.0359) time: 0.5056 [2021-03-25 12:22:27 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 620/1251] eta: 0:05:24 lr: 0.000932 loss: 3.7573 (3.7603) grad_norm: 0.9659 (1.0348) time: 0.4993 [2021-03-25 12:22:32 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 630/1251] eta: 0:05:18 lr: 0.000932 loss: 3.9193 (3.7605) grad_norm: 0.9489 (1.0338) time: 0.4984 [2021-03-25 12:22:37 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 640/1251] eta: 0:05:13 lr: 0.000932 loss: 3.8669 (3.7599) grad_norm: 0.9743 (1.0329) time: 0.4971 [2021-03-25 12:22:42 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 650/1251] eta: 0:05:08 lr: 0.000932 loss: 3.3644 (3.7562) grad_norm: 0.9743 (1.0327) time: 0.4989 [2021-03-25 12:22:47 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 660/1251] eta: 0:05:02 lr: 0.000932 loss: 3.7738 (3.7577) grad_norm: 0.9562 (1.0323) time: 0.5010 [2021-03-25 12:22:52 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 670/1251] eta: 0:04:57 lr: 0.000932 loss: 3.7748 (3.7572) grad_norm: 0.9669 (1.0327) time: 0.5042 [2021-03-25 12:22:57 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 680/1251] eta: 0:04:52 lr: 0.000932 loss: 3.8365 (3.7586) grad_norm: 1.0151 (1.0329) time: 0.5028 [2021-03-25 12:23:02 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 690/1251] eta: 0:04:47 lr: 0.000932 loss: 3.8365 (3.7599) grad_norm: 1.0068 (1.0323) time: 0.5059 [2021-03-25 12:23:07 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 700/1251] eta: 0:04:42 lr: 0.000932 loss: 3.8064 (3.7573) grad_norm: 1.0068 (1.0323) time: 0.5066 [2021-03-25 12:23:12 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 710/1251] eta: 0:04:37 lr: 0.000932 loss: 3.8595 (3.7600) grad_norm: 1.0601 (1.0337) time: 0.5026 [2021-03-25 12:23:17 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 720/1251] eta: 0:04:31 lr: 0.000932 loss: 4.0737 (3.7656) grad_norm: 1.0231 (1.0334) time: 0.5056 [2021-03-25 12:23:22 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 730/1251] eta: 0:04:26 lr: 0.000932 loss: 4.0317 (3.7644) grad_norm: 0.9827 (1.0327) time: 0.5115 [2021-03-25 12:23:27 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 740/1251] eta: 0:04:21 lr: 0.000932 loss: 3.6272 (3.7639) grad_norm: 0.9914 (1.0325) time: 0.5281 [2021-03-25 12:23:32 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 750/1251] eta: 0:04:16 lr: 0.000932 loss: 3.7091 (3.7609) grad_norm: 1.0202 (1.0331) time: 0.5229 [2021-03-25 12:23:38 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 760/1251] eta: 0:04:11 lr: 0.000932 loss: 3.8707 (3.7639) grad_norm: 1.0069 (1.0327) time: 0.5061 [2021-03-25 12:23:43 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 770/1251] eta: 0:04:06 lr: 0.000932 loss: 3.9393 (3.7648) grad_norm: 0.9851 (1.0313) time: 0.5101 [2021-03-25 12:23:48 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 780/1251] eta: 0:04:01 lr: 0.000932 loss: 4.0317 (3.7681) grad_norm: 0.9484 (1.0318) time: 0.5143 [2021-03-25 12:23:53 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 790/1251] eta: 0:03:56 lr: 0.000932 loss: 4.1470 (3.7727) grad_norm: 1.0191 (1.0321) time: 0.5109 [2021-03-25 12:23:58 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 800/1251] eta: 0:03:50 lr: 0.000932 loss: 3.9711 (3.7717) grad_norm: 1.0086 (1.0322) time: 0.5044 [2021-03-25 12:24:03 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 810/1251] eta: 0:03:45 lr: 0.000932 loss: 3.7108 (3.7706) grad_norm: 0.9935 (1.0315) time: 0.5081 [2021-03-25 12:24:08 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 820/1251] eta: 0:03:40 lr: 0.000932 loss: 3.8029 (3.7731) grad_norm: 0.9839 (1.0309) time: 0.5088 [2021-03-25 12:24:13 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 830/1251] eta: 0:03:35 lr: 0.000932 loss: 3.8551 (3.7728) grad_norm: 0.9451 (1.0298) time: 0.5021 [2021-03-25 12:24:18 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 840/1251] eta: 0:03:30 lr: 0.000932 loss: 3.7515 (3.7732) grad_norm: 0.9451 (1.0295) time: 0.4994 [2021-03-25 12:24:23 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 850/1251] eta: 0:03:25 lr: 0.000932 loss: 3.8756 (3.7730) grad_norm: 0.9713 (1.0292) time: 0.5017 [2021-03-25 12:24:28 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 860/1251] eta: 0:03:20 lr: 0.000932 loss: 3.8756 (3.7723) grad_norm: 0.9976 (1.0293) time: 0.5126 [2021-03-25 12:24:33 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 870/1251] eta: 0:03:14 lr: 0.000932 loss: 3.8584 (3.7728) grad_norm: 0.9896 (1.0288) time: 0.5103 [2021-03-25 12:24:38 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 880/1251] eta: 0:03:09 lr: 0.000932 loss: 3.9098 (3.7737) grad_norm: 0.9894 (1.0290) time: 0.5034 [2021-03-25 12:24:43 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 890/1251] eta: 0:03:04 lr: 0.000932 loss: 3.9365 (3.7746) grad_norm: 1.0105 (1.0291) time: 0.5057 [2021-03-25 12:24:48 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 900/1251] eta: 0:02:59 lr: 0.000932 loss: 3.9527 (3.7762) grad_norm: 0.9926 (1.0286) time: 0.5030 [2021-03-25 12:24:54 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 910/1251] eta: 0:02:54 lr: 0.000932 loss: 3.6954 (3.7746) grad_norm: 0.9880 (1.0287) time: 0.5063 [2021-03-25 12:24:59 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 920/1251] eta: 0:02:49 lr: 0.000932 loss: 3.6635 (3.7733) grad_norm: 1.0805 (1.0297) time: 0.5088 [2021-03-25 12:25:04 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 930/1251] eta: 0:02:44 lr: 0.000932 loss: 3.8056 (3.7730) grad_norm: 1.0707 (1.0301) time: 0.5057 [2021-03-25 12:25:09 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 940/1251] eta: 0:02:38 lr: 0.000932 loss: 3.8056 (3.7732) grad_norm: 0.9707 (1.0299) time: 0.5064 [2021-03-25 12:25:14 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 950/1251] eta: 0:02:33 lr: 0.000932 loss: 3.8991 (3.7734) grad_norm: 0.9477 (1.0301) time: 0.5083 [2021-03-25 12:25:19 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 960/1251] eta: 0:02:28 lr: 0.000932 loss: 3.9250 (3.7749) grad_norm: 1.0081 (1.0302) time: 0.5102 [2021-03-25 12:25:24 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 970/1251] eta: 0:02:23 lr: 0.000932 loss: 3.9250 (3.7725) grad_norm: 1.0113 (1.0303) time: 0.5058 [2021-03-25 12:25:29 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 980/1251] eta: 0:02:18 lr: 0.000932 loss: 3.6438 (3.7710) grad_norm: 1.0079 (1.0303) time: 0.5018 [2021-03-25 12:25:34 swin_small_patch4_window7_224] INFO: Epoch: [50] [ 990/1251] eta: 0:02:13 lr: 0.000932 loss: 3.8360 (3.7720) grad_norm: 1.0106 (1.0303) time: 0.5044 [2021-03-25 12:25:39 swin_small_patch4_window7_224] INFO: Epoch: [50] [1000/1251] eta: 0:02:08 lr: 0.000932 loss: 3.8514 (3.7712) grad_norm: 1.0106 (1.0302) time: 0.5122 [2021-03-25 12:25:44 swin_small_patch4_window7_224] INFO: Epoch: [50] [1010/1251] eta: 0:02:03 lr: 0.000932 loss: 3.7528 (3.7715) grad_norm: 0.9920 (1.0309) time: 0.5088 [2021-03-25 12:25:49 swin_small_patch4_window7_224] INFO: Epoch: [50] [1020/1251] eta: 0:01:58 lr: 0.000932 loss: 3.7528 (3.7722) grad_norm: 1.0012 (1.0307) time: 0.5056 [2021-03-25 12:25:55 swin_small_patch4_window7_224] INFO: Epoch: [50] [1030/1251] eta: 0:01:52 lr: 0.000932 loss: 3.8856 (3.7707) grad_norm: 1.0010 (1.0304) time: 0.5108 [2021-03-25 12:26:00 swin_small_patch4_window7_224] INFO: Epoch: [50] [1040/1251] eta: 0:01:47 lr: 0.000932 loss: 3.7298 (3.7701) grad_norm: 0.9883 (1.0297) time: 0.5046 [2021-03-25 12:26:05 swin_small_patch4_window7_224] INFO: Epoch: [50] [1050/1251] eta: 0:01:42 lr: 0.000931 loss: 3.7320 (3.7677) grad_norm: 1.0114 (1.0298) time: 0.5148 [2021-03-25 12:26:10 swin_small_patch4_window7_224] INFO: Epoch: [50] [1060/1251] eta: 0:01:37 lr: 0.000931 loss: 3.7450 (3.7665) grad_norm: 1.0174 (1.0293) time: 0.5241 [2021-03-25 12:26:15 swin_small_patch4_window7_224] INFO: Epoch: [50] [1070/1251] eta: 0:01:32 lr: 0.000931 loss: 3.7775 (3.7664) grad_norm: 0.9671 (1.0288) time: 0.5143 [2021-03-25 12:26:20 swin_small_patch4_window7_224] INFO: Epoch: [50] [1080/1251] eta: 0:01:27 lr: 0.000931 loss: 3.7419 (3.7654) grad_norm: 0.9458 (1.0283) time: 0.5025 [2021-03-25 12:26:25 swin_small_patch4_window7_224] INFO: Epoch: [50] [1090/1251] eta: 0:01:22 lr: 0.000931 loss: 3.8562 (3.7662) grad_norm: 0.9742 (1.0281) time: 0.5017 [2021-03-25 12:26:30 swin_small_patch4_window7_224] INFO: Epoch: [50] [1100/1251] eta: 0:01:17 lr: 0.000931 loss: 3.8562 (3.7653) grad_norm: 0.9659 (1.0276) time: 0.5074 [2021-03-25 12:26:35 swin_small_patch4_window7_224] INFO: Epoch: [50] [1110/1251] eta: 0:01:12 lr: 0.000931 loss: 3.7408 (3.7650) grad_norm: 0.9541 (1.0274) time: 0.5042 [2021-03-25 12:26:40 swin_small_patch4_window7_224] INFO: Epoch: [50] [1120/1251] eta: 0:01:06 lr: 0.000931 loss: 4.0863 (3.7690) grad_norm: 0.9655 (1.0275) time: 0.5062 [2021-03-25 12:26:45 swin_small_patch4_window7_224] INFO: Epoch: [50] [1130/1251] eta: 0:01:01 lr: 0.000931 loss: 3.9872 (3.7689) grad_norm: 0.9847 (1.0274) time: 0.5081 [2021-03-25 12:26:50 swin_small_patch4_window7_224] INFO: Epoch: [50] [1140/1251] eta: 0:00:56 lr: 0.000931 loss: 3.7865 (3.7692) grad_norm: 0.9859 (1.0273) time: 0.5052 [2021-03-25 12:26:55 swin_small_patch4_window7_224] INFO: Epoch: [50] [1150/1251] eta: 0:00:51 lr: 0.000931 loss: 3.8844 (3.7682) grad_norm: 0.9660 (1.0268) time: 0.4993 [2021-03-25 12:27:00 swin_small_patch4_window7_224] INFO: Epoch: [50] [1160/1251] eta: 0:00:46 lr: 0.000931 loss: 3.8133 (3.7667) grad_norm: 0.9714 (1.0267) time: 0.4973 [2021-03-25 12:27:05 swin_small_patch4_window7_224] INFO: Epoch: [50] [1170/1251] eta: 0:00:41 lr: 0.000931 loss: 3.8133 (3.7666) grad_norm: 1.0269 (1.0268) time: 0.5042 [2021-03-25 12:27:11 swin_small_patch4_window7_224] INFO: Epoch: [50] [1180/1251] eta: 0:00:36 lr: 0.000931 loss: 3.8194 (3.7670) grad_norm: 1.0546 (1.0277) time: 0.5077 [2021-03-25 12:27:16 swin_small_patch4_window7_224] INFO: Epoch: [50] [1190/1251] eta: 0:00:31 lr: 0.000931 loss: 3.7963 (3.7679) grad_norm: 1.0322 (1.0273) time: 0.5065 [2021-03-25 12:27:21 swin_small_patch4_window7_224] INFO: Epoch: [50] [1200/1251] eta: 0:00:26 lr: 0.000931 loss: 3.7233 (3.7671) grad_norm: 0.9928 (1.0269) time: 0.5014 [2021-03-25 12:27:26 swin_small_patch4_window7_224] INFO: Epoch: [50] [1210/1251] eta: 0:00:20 lr: 0.000931 loss: 3.8996 (3.7682) grad_norm: 1.0051 (1.0270) time: 0.5020 [2021-03-25 12:27:31 swin_small_patch4_window7_224] INFO: Epoch: [50] [1220/1251] eta: 0:00:15 lr: 0.000931 loss: 3.9388 (3.7682) grad_norm: 1.0118 (1.0269) time: 0.5045 [2021-03-25 12:27:36 swin_small_patch4_window7_224] INFO: Epoch: [50] [1230/1251] eta: 0:00:10 lr: 0.000931 loss: 3.8756 (3.7668) grad_norm: 1.0209 (1.0269) time: 0.5018 [2021-03-25 12:27:41 swin_small_patch4_window7_224] INFO: Epoch: [50] [1240/1251] eta: 0:00:05 lr: 0.000931 loss: 3.9369 (3.7685) grad_norm: 1.0208 (1.0272) time: 0.5073 [2021-03-25 12:27:46 swin_small_patch4_window7_224] INFO: Epoch: [50] [1250/1251] eta: 0:00:00 lr: 0.000931 loss: 3.9711 (3.7681) grad_norm: 0.9687 (1.0269) time: 0.5093 [2021-03-25 12:28:26 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 1.1975 (1.1975) acc1: 75.0000 (75.0000) acc5: 90.6250 (90.6250) [2021-03-25 12:28:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.2154 (1.1927) acc1: 71.8750 (72.3011) acc5: 90.6250 (91.7614) [2021-03-25 12:28:28 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.1199 (1.1516) acc1: 71.8750 (73.1399) acc5: 92.1875 (92.3363) [2021-03-25 12:28:29 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.1610 (1.1946) acc1: 73.4375 (72.5302) acc5: 90.6250 (91.3810) [2021-03-25 12:28:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2102 (1.1750) acc1: 71.8750 (72.6372) acc5: 90.6250 (91.6540) [2021-03-25 12:28:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2102 (1.1768) acc1: 71.8750 (72.6080) acc5: 92.1875 (91.5520) [2021-03-25 12:28:34 swin_small_patch4_window7_224] INFO: * Acc@1 72.750 Acc@5 91.792 loss 1.156 [2021-03-25 12:28:34 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.8% [2021-03-25 12:28:34 swin_small_patch4_window7_224] INFO: Max accuracy: 72.75% [2021-03-25 12:28:38 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 0/1251] eta: 1:26:50 lr: 0.000931 loss: 2.0831 (2.0831) grad_norm: 1.1607 (1.1607) time: 4.1651 [2021-03-25 12:28:44 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 10/1251] eta: 0:17:37 lr: 0.000931 loss: 3.7328 (3.7240) grad_norm: 0.9784 (1.0442) time: 0.8524 [2021-03-25 12:28:49 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 20/1251] eta: 0:14:05 lr: 0.000931 loss: 3.8831 (3.6975) grad_norm: 0.9755 (1.0303) time: 0.5129 [2021-03-25 12:28:54 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 30/1251] eta: 0:12:47 lr: 0.000931 loss: 3.8992 (3.7301) grad_norm: 1.0288 (1.0534) time: 0.5060 [2021-03-25 12:28:59 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 40/1251] eta: 0:12:04 lr: 0.000931 loss: 3.7520 (3.7067) grad_norm: 1.0524 (1.0550) time: 0.5061 [2021-03-25 12:29:04 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 50/1251] eta: 0:11:38 lr: 0.000931 loss: 3.9110 (3.7711) grad_norm: 1.0003 (1.0402) time: 0.5072 [2021-03-25 12:29:09 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 60/1251] eta: 0:11:16 lr: 0.000931 loss: 3.8510 (3.7279) grad_norm: 1.0003 (1.0451) time: 0.5051 [2021-03-25 12:29:14 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 70/1251] eta: 0:11:00 lr: 0.000931 loss: 3.8510 (3.7554) grad_norm: 1.0820 (1.0475) time: 0.5028 [2021-03-25 12:29:19 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 80/1251] eta: 0:10:46 lr: 0.000931 loss: 3.9324 (3.7778) grad_norm: 1.0372 (1.0501) time: 0.5045 [2021-03-25 12:29:24 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 90/1251] eta: 0:10:38 lr: 0.000931 loss: 3.8576 (3.7902) grad_norm: 1.0746 (1.0653) time: 0.5175 [2021-03-25 12:29:29 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 100/1251] eta: 0:10:27 lr: 0.000931 loss: 3.8207 (3.8040) grad_norm: 1.0294 (1.0587) time: 0.5158 [2021-03-25 12:29:34 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 110/1251] eta: 0:10:18 lr: 0.000931 loss: 3.8489 (3.8065) grad_norm: 0.9853 (1.0542) time: 0.5085 [2021-03-25 12:29:40 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 120/1251] eta: 0:10:11 lr: 0.000931 loss: 3.8655 (3.8039) grad_norm: 1.0140 (1.0522) time: 0.5182 [2021-03-25 12:29:45 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 130/1251] eta: 0:10:03 lr: 0.000931 loss: 3.9483 (3.8166) grad_norm: 1.0140 (1.0518) time: 0.5140 [2021-03-25 12:29:50 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 140/1251] eta: 0:09:56 lr: 0.000931 loss: 3.7527 (3.7942) grad_norm: 1.0582 (1.0591) time: 0.5123 [2021-03-25 12:29:55 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 150/1251] eta: 0:09:49 lr: 0.000931 loss: 3.4305 (3.7728) grad_norm: 1.0591 (1.0596) time: 0.5156 [2021-03-25 12:30:00 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 160/1251] eta: 0:09:41 lr: 0.000931 loss: 3.7137 (3.7801) grad_norm: 0.9962 (1.0568) time: 0.5088 [2021-03-25 12:30:05 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 170/1251] eta: 0:09:34 lr: 0.000931 loss: 3.8268 (3.7713) grad_norm: 1.0011 (1.0535) time: 0.5042 [2021-03-25 12:30:10 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 180/1251] eta: 0:09:28 lr: 0.000931 loss: 3.8268 (3.7687) grad_norm: 0.9671 (1.0488) time: 0.5108 [2021-03-25 12:30:15 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 190/1251] eta: 0:09:22 lr: 0.000931 loss: 3.7752 (3.7699) grad_norm: 0.9486 (1.0435) time: 0.5192 [2021-03-25 12:30:20 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 200/1251] eta: 0:09:15 lr: 0.000931 loss: 3.7263 (3.7756) grad_norm: 0.9346 (1.0393) time: 0.5109 [2021-03-25 12:30:25 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 210/1251] eta: 0:09:08 lr: 0.000931 loss: 3.9703 (3.7791) grad_norm: 0.9800 (1.0389) time: 0.4998 [2021-03-25 12:30:30 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 220/1251] eta: 0:09:02 lr: 0.000931 loss: 3.9703 (3.7852) grad_norm: 1.0543 (1.0409) time: 0.5018 [2021-03-25 12:30:36 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 230/1251] eta: 0:08:56 lr: 0.000931 loss: 3.8604 (3.7765) grad_norm: 1.0431 (1.0430) time: 0.5087 [2021-03-25 12:30:41 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 240/1251] eta: 0:08:50 lr: 0.000931 loss: 3.6446 (3.7692) grad_norm: 0.9494 (1.0392) time: 0.5073 [2021-03-25 12:30:46 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 250/1251] eta: 0:08:44 lr: 0.000931 loss: 3.6391 (3.7613) grad_norm: 0.9471 (1.0355) time: 0.5007 [2021-03-25 12:30:51 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 260/1251] eta: 0:08:38 lr: 0.000931 loss: 3.7044 (3.7702) grad_norm: 0.9772 (1.0365) time: 0.5054 [2021-03-25 12:30:56 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 270/1251] eta: 0:08:32 lr: 0.000930 loss: 3.9511 (3.7728) grad_norm: 1.0117 (1.0360) time: 0.5037 [2021-03-25 12:31:01 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 280/1251] eta: 0:08:26 lr: 0.000930 loss: 3.9511 (3.7728) grad_norm: 0.9676 (1.0332) time: 0.4980 [2021-03-25 12:31:06 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 290/1251] eta: 0:08:20 lr: 0.000930 loss: 3.7321 (3.7626) grad_norm: 0.9602 (1.0323) time: 0.5019 [2021-03-25 12:31:11 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 300/1251] eta: 0:08:14 lr: 0.000930 loss: 3.7321 (3.7643) grad_norm: 0.9685 (1.0302) time: 0.5035 [2021-03-25 12:31:16 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 310/1251] eta: 0:08:09 lr: 0.000930 loss: 3.7643 (3.7563) grad_norm: 0.9979 (1.0313) time: 0.5063 [2021-03-25 12:31:21 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 320/1251] eta: 0:08:03 lr: 0.000930 loss: 3.6439 (3.7519) grad_norm: 0.9900 (1.0295) time: 0.5072 [2021-03-25 12:31:26 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 330/1251] eta: 0:07:58 lr: 0.000930 loss: 3.4680 (3.7474) grad_norm: 0.9900 (1.0298) time: 0.5098 [2021-03-25 12:31:31 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 340/1251] eta: 0:07:52 lr: 0.000930 loss: 3.4081 (3.7459) grad_norm: 1.0241 (1.0301) time: 0.5082 [2021-03-25 12:31:36 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 350/1251] eta: 0:07:47 lr: 0.000930 loss: 3.6103 (3.7448) grad_norm: 0.9923 (1.0291) time: 0.5056 [2021-03-25 12:31:41 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 360/1251] eta: 0:07:41 lr: 0.000930 loss: 3.5722 (3.7346) grad_norm: 0.9779 (1.0286) time: 0.5085 [2021-03-25 12:31:46 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 370/1251] eta: 0:07:36 lr: 0.000930 loss: 3.5840 (3.7389) grad_norm: 1.0090 (1.0275) time: 0.5042 [2021-03-25 12:31:51 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 380/1251] eta: 0:07:30 lr: 0.000930 loss: 4.0437 (3.7489) grad_norm: 1.0504 (1.0294) time: 0.5100 [2021-03-25 12:31:56 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 390/1251] eta: 0:07:25 lr: 0.000930 loss: 4.0437 (3.7444) grad_norm: 1.0754 (1.0318) time: 0.5076 [2021-03-25 12:32:02 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 400/1251] eta: 0:07:19 lr: 0.000930 loss: 3.7215 (3.7395) grad_norm: 1.0337 (1.0318) time: 0.5031 [2021-03-25 12:32:07 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 410/1251] eta: 0:07:14 lr: 0.000930 loss: 3.7759 (3.7378) grad_norm: 1.0209 (1.0321) time: 0.5065 [2021-03-25 12:32:12 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 420/1251] eta: 0:07:09 lr: 0.000930 loss: 3.8066 (3.7410) grad_norm: 1.0178 (1.0318) time: 0.5039 [2021-03-25 12:32:17 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 430/1251] eta: 0:07:03 lr: 0.000930 loss: 3.9399 (3.7465) grad_norm: 1.0161 (1.0321) time: 0.5064 [2021-03-25 12:32:22 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 440/1251] eta: 0:06:58 lr: 0.000930 loss: 3.8147 (3.7446) grad_norm: 1.0161 (1.0328) time: 0.5029 [2021-03-25 12:32:27 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 450/1251] eta: 0:06:52 lr: 0.000930 loss: 3.7192 (3.7458) grad_norm: 1.0139 (1.0325) time: 0.4977 [2021-03-25 12:32:32 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 460/1251] eta: 0:06:47 lr: 0.000930 loss: 3.6944 (3.7387) grad_norm: 0.9574 (1.0314) time: 0.5060 [2021-03-25 12:32:37 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 470/1251] eta: 0:06:42 lr: 0.000930 loss: 3.6627 (3.7372) grad_norm: 0.9369 (1.0296) time: 0.5133 [2021-03-25 12:32:42 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 480/1251] eta: 0:06:37 lr: 0.000930 loss: 3.7624 (3.7380) grad_norm: 1.0193 (1.0307) time: 0.5097 [2021-03-25 12:32:47 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 490/1251] eta: 0:06:31 lr: 0.000930 loss: 3.7624 (3.7373) grad_norm: 1.0550 (1.0314) time: 0.5058 [2021-03-25 12:32:52 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 500/1251] eta: 0:06:26 lr: 0.000930 loss: 4.0072 (3.7436) grad_norm: 1.0537 (1.0324) time: 0.5016 [2021-03-25 12:32:57 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 510/1251] eta: 0:06:21 lr: 0.000930 loss: 4.1342 (3.7457) grad_norm: 1.0427 (1.0321) time: 0.5012 [2021-03-25 12:33:02 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 520/1251] eta: 0:06:15 lr: 0.000930 loss: 3.7067 (3.7424) grad_norm: 0.9856 (1.0322) time: 0.5019 [2021-03-25 12:33:07 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 530/1251] eta: 0:06:10 lr: 0.000930 loss: 3.7007 (3.7444) grad_norm: 0.9937 (1.0324) time: 0.4995 [2021-03-25 12:33:12 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 540/1251] eta: 0:06:05 lr: 0.000930 loss: 3.6374 (3.7428) grad_norm: 0.9678 (1.0308) time: 0.5030 [2021-03-25 12:33:17 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 550/1251] eta: 0:06:00 lr: 0.000930 loss: 3.5930 (3.7416) grad_norm: 0.9626 (1.0310) time: 0.5176 [2021-03-25 12:33:22 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 560/1251] eta: 0:05:54 lr: 0.000930 loss: 3.6036 (3.7410) grad_norm: 0.9318 (1.0294) time: 0.5134 [2021-03-25 12:33:27 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 570/1251] eta: 0:05:49 lr: 0.000930 loss: 3.6576 (3.7409) grad_norm: 0.9318 (1.0288) time: 0.4960 [2021-03-25 12:33:32 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 580/1251] eta: 0:05:44 lr: 0.000930 loss: 3.8969 (3.7416) grad_norm: 1.0309 (1.0292) time: 0.4999 [2021-03-25 12:33:37 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 590/1251] eta: 0:05:39 lr: 0.000930 loss: 3.8969 (3.7439) grad_norm: 1.0315 (1.0290) time: 0.5054 [2021-03-25 12:33:43 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 600/1251] eta: 0:05:33 lr: 0.000930 loss: 3.6536 (3.7396) grad_norm: 1.0405 (1.0296) time: 0.5050 [2021-03-25 12:33:48 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 610/1251] eta: 0:05:28 lr: 0.000930 loss: 3.6536 (3.7421) grad_norm: 1.0231 (1.0295) time: 0.5022 [2021-03-25 12:33:53 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 620/1251] eta: 0:05:23 lr: 0.000930 loss: 4.0241 (3.7452) grad_norm: 0.9855 (1.0286) time: 0.5015 [2021-03-25 12:33:58 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 630/1251] eta: 0:05:18 lr: 0.000930 loss: 3.5936 (3.7396) grad_norm: 0.9777 (1.0274) time: 0.5075 [2021-03-25 12:34:03 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 640/1251] eta: 0:05:13 lr: 0.000930 loss: 3.4938 (3.7367) grad_norm: 0.9771 (1.0267) time: 0.5138 [2021-03-25 12:34:08 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 650/1251] eta: 0:05:07 lr: 0.000930 loss: 3.8453 (3.7380) grad_norm: 1.0028 (1.0264) time: 0.5073 [2021-03-25 12:34:13 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 660/1251] eta: 0:05:02 lr: 0.000930 loss: 3.9359 (3.7396) grad_norm: 1.0179 (1.0272) time: 0.4990 [2021-03-25 12:34:18 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 670/1251] eta: 0:04:57 lr: 0.000930 loss: 3.9359 (3.7426) grad_norm: 1.0033 (1.0259) time: 0.5000 [2021-03-25 12:34:23 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 680/1251] eta: 0:04:52 lr: 0.000930 loss: 3.9777 (3.7426) grad_norm: 1.0059 (1.0267) time: 0.5044 [2021-03-25 12:34:28 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 690/1251] eta: 0:04:47 lr: 0.000930 loss: 3.9560 (3.7434) grad_norm: 1.1119 (1.0285) time: 0.5044 [2021-03-25 12:34:33 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 700/1251] eta: 0:04:41 lr: 0.000930 loss: 3.7699 (3.7429) grad_norm: 1.0850 (1.0286) time: 0.4990 [2021-03-25 12:34:38 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 710/1251] eta: 0:04:36 lr: 0.000930 loss: 3.4375 (3.7399) grad_norm: 1.0132 (1.0283) time: 0.4975 [2021-03-25 12:34:43 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 720/1251] eta: 0:04:31 lr: 0.000930 loss: 3.6062 (3.7396) grad_norm: 1.0021 (1.0285) time: 0.4999 [2021-03-25 12:34:48 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 730/1251] eta: 0:04:26 lr: 0.000930 loss: 3.6530 (3.7354) grad_norm: 1.0021 (1.0281) time: 0.5083 [2021-03-25 12:34:53 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 740/1251] eta: 0:04:21 lr: 0.000929 loss: 3.5842 (3.7332) grad_norm: 1.0478 (1.0299) time: 0.5287 [2021-03-25 12:34:59 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 750/1251] eta: 0:04:16 lr: 0.000929 loss: 3.6569 (3.7319) grad_norm: 1.0560 (1.0299) time: 0.5256 [2021-03-25 12:35:04 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 760/1251] eta: 0:04:11 lr: 0.000929 loss: 3.7302 (3.7308) grad_norm: 1.0463 (1.0302) time: 0.5101 [2021-03-25 12:35:09 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 770/1251] eta: 0:04:06 lr: 0.000929 loss: 3.7631 (3.7290) grad_norm: 1.0676 (1.0305) time: 0.5105 [2021-03-25 12:35:14 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 780/1251] eta: 0:04:00 lr: 0.000929 loss: 3.9569 (3.7341) grad_norm: 0.9768 (1.0298) time: 0.5102 [2021-03-25 12:35:19 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 790/1251] eta: 0:03:55 lr: 0.000929 loss: 3.9225 (3.7320) grad_norm: 0.9813 (1.0300) time: 0.5098 [2021-03-25 12:35:24 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 800/1251] eta: 0:03:50 lr: 0.000929 loss: 3.6714 (3.7348) grad_norm: 1.0471 (1.0302) time: 0.5033 [2021-03-25 12:35:29 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 810/1251] eta: 0:03:45 lr: 0.000929 loss: 4.0782 (3.7384) grad_norm: 1.0471 (1.0303) time: 0.5025 [2021-03-25 12:35:34 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 820/1251] eta: 0:03:40 lr: 0.000929 loss: 4.0782 (3.7392) grad_norm: 0.9816 (1.0304) time: 0.5098 [2021-03-25 12:35:39 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 830/1251] eta: 0:03:35 lr: 0.000929 loss: 3.8679 (3.7396) grad_norm: 0.9654 (1.0295) time: 0.5175 [2021-03-25 12:35:44 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 840/1251] eta: 0:03:30 lr: 0.000929 loss: 3.7141 (3.7404) grad_norm: 0.9863 (inf) time: 0.5122 [2021-03-25 12:35:50 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 850/1251] eta: 0:03:25 lr: 0.000929 loss: 3.7239 (3.7392) grad_norm: 0.9912 (inf) time: 0.5061 [2021-03-25 12:35:55 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 860/1251] eta: 0:03:19 lr: 0.000929 loss: 3.6746 (3.7380) grad_norm: 0.9971 (inf) time: 0.5073 [2021-03-25 12:36:00 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 870/1251] eta: 0:03:14 lr: 0.000929 loss: 3.5562 (3.7346) grad_norm: 0.9971 (inf) time: 0.5032 [2021-03-25 12:36:05 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 880/1251] eta: 0:03:09 lr: 0.000929 loss: 3.6045 (3.7340) grad_norm: 0.9686 (inf) time: 0.5050 [2021-03-25 12:36:10 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 890/1251] eta: 0:03:04 lr: 0.000929 loss: 3.7879 (3.7360) grad_norm: 0.9909 (inf) time: 0.5032 [2021-03-25 12:36:15 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 900/1251] eta: 0:02:59 lr: 0.000929 loss: 3.9038 (3.7342) grad_norm: 0.9161 (inf) time: 0.5077 [2021-03-25 12:36:20 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 910/1251] eta: 0:02:54 lr: 0.000929 loss: 3.8209 (3.7356) grad_norm: 0.9133 (inf) time: 0.5102 [2021-03-25 12:36:25 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 920/1251] eta: 0:02:49 lr: 0.000929 loss: 3.6435 (3.7309) grad_norm: 0.9419 (inf) time: 0.5048 [2021-03-25 12:36:30 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 930/1251] eta: 0:02:44 lr: 0.000929 loss: 3.3480 (3.7308) grad_norm: 0.9949 (inf) time: 0.5184 [2021-03-25 12:36:35 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 940/1251] eta: 0:02:38 lr: 0.000929 loss: 3.6788 (3.7323) grad_norm: 1.0461 (inf) time: 0.5165 [2021-03-25 12:36:40 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 950/1251] eta: 0:02:33 lr: 0.000929 loss: 4.0029 (3.7331) grad_norm: 1.0006 (inf) time: 0.5044 [2021-03-25 12:36:45 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 960/1251] eta: 0:02:28 lr: 0.000929 loss: 3.8373 (3.7317) grad_norm: 0.9556 (inf) time: 0.5046 [2021-03-25 12:36:50 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 970/1251] eta: 0:02:23 lr: 0.000929 loss: 3.7821 (3.7315) grad_norm: 1.0336 (inf) time: 0.4993 [2021-03-25 12:36:55 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 980/1251] eta: 0:02:18 lr: 0.000929 loss: 3.5673 (3.7300) grad_norm: 1.0206 (inf) time: 0.5009 [2021-03-25 12:37:00 swin_small_patch4_window7_224] INFO: Epoch: [51] [ 990/1251] eta: 0:02:13 lr: 0.000929 loss: 3.7724 (3.7308) grad_norm: 1.0148 (inf) time: 0.5075 [2021-03-25 12:37:06 swin_small_patch4_window7_224] INFO: Epoch: [51] [1000/1251] eta: 0:02:08 lr: 0.000929 loss: 3.7724 (3.7261) grad_norm: 0.9967 (inf) time: 0.5088 [2021-03-25 12:37:11 swin_small_patch4_window7_224] INFO: Epoch: [51] [1010/1251] eta: 0:02:03 lr: 0.000929 loss: 3.5438 (3.7260) grad_norm: 0.9680 (inf) time: 0.5075 [2021-03-25 12:37:16 swin_small_patch4_window7_224] INFO: Epoch: [51] [1020/1251] eta: 0:01:57 lr: 0.000929 loss: 3.8865 (3.7259) grad_norm: 1.0654 (inf) time: 0.5093 [2021-03-25 12:37:21 swin_small_patch4_window7_224] INFO: Epoch: [51] [1030/1251] eta: 0:01:52 lr: 0.000929 loss: 3.5597 (3.7228) grad_norm: 1.0472 (inf) time: 0.5106 [2021-03-25 12:37:26 swin_small_patch4_window7_224] INFO: Epoch: [51] [1040/1251] eta: 0:01:47 lr: 0.000929 loss: 3.5309 (3.7215) grad_norm: 1.0155 (inf) time: 0.5137 [2021-03-25 12:37:31 swin_small_patch4_window7_224] INFO: Epoch: [51] [1050/1251] eta: 0:01:42 lr: 0.000929 loss: 3.6069 (3.7212) grad_norm: 0.9869 (inf) time: 0.5130 [2021-03-25 12:37:36 swin_small_patch4_window7_224] INFO: Epoch: [51] [1060/1251] eta: 0:01:37 lr: 0.000929 loss: 3.6374 (3.7220) grad_norm: 0.9955 (inf) time: 0.5077 [2021-03-25 12:37:41 swin_small_patch4_window7_224] INFO: Epoch: [51] [1070/1251] eta: 0:01:32 lr: 0.000929 loss: 3.8391 (3.7231) grad_norm: 1.0588 (inf) time: 0.5085 [2021-03-25 12:37:46 swin_small_patch4_window7_224] INFO: Epoch: [51] [1080/1251] eta: 0:01:27 lr: 0.000929 loss: 3.8859 (3.7234) grad_norm: 0.9834 (inf) time: 0.5086 [2021-03-25 12:37:51 swin_small_patch4_window7_224] INFO: Epoch: [51] [1090/1251] eta: 0:01:22 lr: 0.000929 loss: 3.8985 (3.7240) grad_norm: 0.9553 (inf) time: 0.5067 [2021-03-25 12:37:56 swin_small_patch4_window7_224] INFO: Epoch: [51] [1100/1251] eta: 0:01:17 lr: 0.000929 loss: 3.8430 (3.7259) grad_norm: 0.9553 (inf) time: 0.5062 [2021-03-25 12:38:01 swin_small_patch4_window7_224] INFO: Epoch: [51] [1110/1251] eta: 0:01:11 lr: 0.000929 loss: 3.8430 (3.7268) grad_norm: 0.9598 (inf) time: 0.5039 [2021-03-25 12:38:06 swin_small_patch4_window7_224] INFO: Epoch: [51] [1120/1251] eta: 0:01:06 lr: 0.000929 loss: 3.9081 (3.7264) grad_norm: 1.0146 (inf) time: 0.5007 [2021-03-25 12:38:12 swin_small_patch4_window7_224] INFO: Epoch: [51] [1130/1251] eta: 0:01:01 lr: 0.000929 loss: 3.9712 (3.7284) grad_norm: 1.0352 (inf) time: 0.5049 [2021-03-25 12:38:17 swin_small_patch4_window7_224] INFO: Epoch: [51] [1140/1251] eta: 0:00:56 lr: 0.000929 loss: 3.8260 (3.7262) grad_norm: 1.0063 (inf) time: 0.5092 [2021-03-25 12:38:22 swin_small_patch4_window7_224] INFO: Epoch: [51] [1150/1251] eta: 0:00:51 lr: 0.000929 loss: 3.8771 (3.7279) grad_norm: 1.0339 (inf) time: 0.5086 [2021-03-25 12:38:27 swin_small_patch4_window7_224] INFO: Epoch: [51] [1160/1251] eta: 0:00:46 lr: 0.000929 loss: 3.9099 (3.7268) grad_norm: 1.0355 (inf) time: 0.5060 [2021-03-25 12:38:32 swin_small_patch4_window7_224] INFO: Epoch: [51] [1170/1251] eta: 0:00:41 lr: 0.000929 loss: 3.5675 (3.7249) grad_norm: 0.9645 (inf) time: 0.5106 [2021-03-25 12:38:37 swin_small_patch4_window7_224] INFO: Epoch: [51] [1180/1251] eta: 0:00:36 lr: 0.000929 loss: 3.8328 (3.7271) grad_norm: 0.9425 (inf) time: 0.5088 [2021-03-25 12:38:42 swin_small_patch4_window7_224] INFO: Epoch: [51] [1190/1251] eta: 0:00:31 lr: 0.000929 loss: 3.9510 (3.7270) grad_norm: 0.9742 (inf) time: 0.5007 [2021-03-25 12:38:47 swin_small_patch4_window7_224] INFO: Epoch: [51] [1200/1251] eta: 0:00:26 lr: 0.000929 loss: 3.7968 (3.7261) grad_norm: 0.9803 (inf) time: 0.5019 [2021-03-25 12:38:52 swin_small_patch4_window7_224] INFO: Epoch: [51] [1210/1251] eta: 0:00:20 lr: 0.000928 loss: 3.7177 (3.7249) grad_norm: 0.9803 (inf) time: 0.5036 [2021-03-25 12:38:57 swin_small_patch4_window7_224] INFO: Epoch: [51] [1220/1251] eta: 0:00:15 lr: 0.000928 loss: 3.7789 (3.7261) grad_norm: 1.0075 (inf) time: 0.5076 [2021-03-25 12:39:02 swin_small_patch4_window7_224] INFO: Epoch: [51] [1230/1251] eta: 0:00:10 lr: 0.000928 loss: 3.8979 (3.7270) grad_norm: 1.0761 (inf) time: 0.5059 [2021-03-25 12:39:07 swin_small_patch4_window7_224] INFO: Epoch: [51] [1240/1251] eta: 0:00:05 lr: 0.000928 loss: 4.0115 (3.7267) grad_norm: 1.0284 (inf) time: 0.5029 [2021-03-25 12:39:12 swin_small_patch4_window7_224] INFO: Epoch: [51] [1250/1251] eta: 0:00:00 lr: 0.000928 loss: 4.0115 (3.7285) grad_norm: 1.0284 (inf) time: 0.5001 [2021-03-25 12:39:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:19 loss: 1.3004 (1.3004) acc1: 70.3125 (70.3125) acc5: 90.6250 (90.6250) [2021-03-25 12:39:20 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.2060 (1.2467) acc1: 71.8750 (71.3068) acc5: 90.6250 (90.0568) [2021-03-25 12:39:22 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1809 (1.2259) acc1: 71.8750 (71.5774) acc5: 92.1875 (90.9970) [2021-03-25 12:39:24 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1809 (1.2062) acc1: 71.8750 (72.5806) acc5: 92.1875 (91.5827) [2021-03-25 12:39:26 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1605 (1.2044) acc1: 71.8750 (72.1037) acc5: 92.1875 (91.6159) [2021-03-25 12:39:27 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1693 (1.2033) acc1: 70.3125 (71.7760) acc5: 90.6250 (91.6800) [2021-03-25 12:39:30 swin_small_patch4_window7_224] INFO: * Acc@1 72.682 Acc@5 91.576 loss 1.176 [2021-03-25 12:39:30 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.7% [2021-03-25 12:39:30 swin_small_patch4_window7_224] INFO: Max accuracy: 72.75% [2021-03-25 12:39:34 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 0/1251] eta: 1:25:54 lr: 0.000928 loss: 3.3569 (3.3569) grad_norm: 1.0948 (1.0948) time: 4.1199 [2021-03-25 12:39:39 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 10/1251] eta: 0:17:55 lr: 0.000928 loss: 3.6505 (3.7971) grad_norm: 1.0186 (1.0433) time: 0.8667 [2021-03-25 12:39:44 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 20/1251] eta: 0:14:20 lr: 0.000928 loss: 3.6627 (3.7438) grad_norm: 0.9975 (1.0138) time: 0.5277 [2021-03-25 12:39:49 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 30/1251] eta: 0:12:55 lr: 0.000928 loss: 3.7286 (3.7153) grad_norm: 0.9904 (1.0072) time: 0.5073 [2021-03-25 12:39:54 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 40/1251] eta: 0:12:12 lr: 0.000928 loss: 3.8928 (3.7845) grad_norm: 0.9716 (1.0052) time: 0.5062 [2021-03-25 12:39:59 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 50/1251] eta: 0:11:44 lr: 0.000928 loss: 3.8928 (3.7323) grad_norm: 0.9278 (1.0016) time: 0.5113 [2021-03-25 12:40:05 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 60/1251] eta: 0:11:23 lr: 0.000928 loss: 3.9976 (3.7877) grad_norm: 0.9384 (0.9983) time: 0.5097 [2021-03-25 12:40:10 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 70/1251] eta: 0:11:05 lr: 0.000928 loss: 4.1785 (3.7872) grad_norm: 0.9662 (0.9957) time: 0.5050 [2021-03-25 12:40:15 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 80/1251] eta: 0:10:52 lr: 0.000928 loss: 3.3761 (3.7342) grad_norm: 1.0085 (1.0059) time: 0.5068 [2021-03-25 12:40:20 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 90/1251] eta: 0:10:41 lr: 0.000928 loss: 3.5123 (3.7180) grad_norm: 0.9855 (1.0007) time: 0.5144 [2021-03-25 12:40:25 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 100/1251] eta: 0:10:31 lr: 0.000928 loss: 3.5571 (3.7007) grad_norm: 0.9399 (1.0034) time: 0.5124 [2021-03-25 12:40:30 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 110/1251] eta: 0:10:23 lr: 0.000928 loss: 3.6988 (3.7120) grad_norm: 0.9590 (1.0003) time: 0.5176 [2021-03-25 12:40:35 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 120/1251] eta: 0:10:14 lr: 0.000928 loss: 3.7721 (3.7104) grad_norm: 0.9611 (1.0100) time: 0.5181 [2021-03-25 12:40:41 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 130/1251] eta: 0:10:07 lr: 0.000928 loss: 3.9059 (3.7238) grad_norm: 1.0269 (1.0131) time: 0.5168 [2021-03-25 12:40:46 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 140/1251] eta: 0:09:59 lr: 0.000928 loss: 4.0601 (3.7500) grad_norm: 1.0299 (1.0192) time: 0.5154 [2021-03-25 12:40:51 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 150/1251] eta: 0:09:51 lr: 0.000928 loss: 4.1163 (3.7727) grad_norm: 1.0299 (1.0190) time: 0.5086 [2021-03-25 12:40:56 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 160/1251] eta: 0:09:43 lr: 0.000928 loss: 4.0241 (3.7807) grad_norm: 0.9872 (1.0161) time: 0.5022 [2021-03-25 12:41:01 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 170/1251] eta: 0:09:36 lr: 0.000928 loss: 3.7829 (3.7648) grad_norm: 0.9868 (1.0155) time: 0.4993 [2021-03-25 12:41:06 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 180/1251] eta: 0:09:29 lr: 0.000928 loss: 3.7863 (3.7653) grad_norm: 1.0079 (1.0182) time: 0.5037 [2021-03-25 12:41:11 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 190/1251] eta: 0:09:22 lr: 0.000928 loss: 3.9255 (3.7633) grad_norm: 1.0592 (1.0200) time: 0.5089 [2021-03-25 12:41:16 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 200/1251] eta: 0:09:16 lr: 0.000928 loss: 3.8407 (3.7610) grad_norm: 1.0592 (1.0230) time: 0.5091 [2021-03-25 12:41:21 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 210/1251] eta: 0:09:09 lr: 0.000928 loss: 3.7716 (3.7587) grad_norm: 1.0165 (1.0204) time: 0.5066 [2021-03-25 12:41:26 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 220/1251] eta: 0:09:03 lr: 0.000928 loss: 3.8110 (3.7696) grad_norm: 0.9621 (1.0199) time: 0.5080 [2021-03-25 12:41:31 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 230/1251] eta: 0:08:57 lr: 0.000928 loss: 3.8950 (3.7745) grad_norm: 0.9975 (1.0201) time: 0.5024 [2021-03-25 12:41:36 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 240/1251] eta: 0:08:50 lr: 0.000928 loss: 3.8937 (3.7673) grad_norm: 1.0062 (1.0209) time: 0.4997 [2021-03-25 12:41:41 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 250/1251] eta: 0:08:44 lr: 0.000928 loss: 3.8536 (3.7569) grad_norm: 1.0145 (1.0229) time: 0.5059 [2021-03-25 12:41:46 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 260/1251] eta: 0:08:38 lr: 0.000928 loss: 3.7520 (3.7566) grad_norm: 1.0688 (1.0249) time: 0.5078 [2021-03-25 12:41:51 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 270/1251] eta: 0:08:33 lr: 0.000928 loss: 3.8468 (3.7549) grad_norm: 1.0557 (1.0272) time: 0.5094 [2021-03-25 12:41:56 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 280/1251] eta: 0:08:27 lr: 0.000928 loss: 3.6865 (3.7484) grad_norm: 0.9992 (1.0258) time: 0.5107 [2021-03-25 12:42:02 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 290/1251] eta: 0:08:21 lr: 0.000928 loss: 3.5576 (3.7394) grad_norm: 0.9992 (1.0257) time: 0.5066 [2021-03-25 12:42:07 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 300/1251] eta: 0:08:16 lr: 0.000928 loss: 3.8216 (3.7396) grad_norm: 1.0398 (1.0269) time: 0.5152 [2021-03-25 12:42:12 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 310/1251] eta: 0:08:11 lr: 0.000928 loss: 3.8887 (3.7337) grad_norm: 1.0355 (1.0281) time: 0.5184 [2021-03-25 12:42:17 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 320/1251] eta: 0:08:05 lr: 0.000928 loss: 3.5642 (3.7263) grad_norm: 1.0324 (1.0294) time: 0.5072 [2021-03-25 12:42:22 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 330/1251] eta: 0:07:59 lr: 0.000928 loss: 3.8446 (3.7282) grad_norm: 1.0056 (1.0280) time: 0.5034 [2021-03-25 12:42:27 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 340/1251] eta: 0:07:53 lr: 0.000928 loss: 3.8564 (3.7311) grad_norm: 0.9715 (1.0276) time: 0.5032 [2021-03-25 12:42:32 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 350/1251] eta: 0:07:48 lr: 0.000928 loss: 3.8564 (3.7365) grad_norm: 0.9799 (1.0264) time: 0.5018 [2021-03-25 12:42:37 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 360/1251] eta: 0:07:42 lr: 0.000928 loss: 3.8845 (3.7367) grad_norm: 1.0114 (1.0269) time: 0.5074 [2021-03-25 12:42:42 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 370/1251] eta: 0:07:37 lr: 0.000928 loss: 3.8137 (3.7415) grad_norm: 1.0484 (1.0274) time: 0.5100 [2021-03-25 12:42:47 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 380/1251] eta: 0:07:31 lr: 0.000928 loss: 3.9750 (3.7469) grad_norm: 1.0883 (1.0287) time: 0.5055 [2021-03-25 12:42:52 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 390/1251] eta: 0:07:26 lr: 0.000928 loss: 3.9367 (3.7511) grad_norm: 0.9711 (1.0274) time: 0.5012 [2021-03-25 12:42:57 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 400/1251] eta: 0:07:20 lr: 0.000928 loss: 3.8345 (3.7553) grad_norm: 0.9549 (1.0259) time: 0.5041 [2021-03-25 12:43:02 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 410/1251] eta: 0:07:15 lr: 0.000928 loss: 3.9586 (3.7575) grad_norm: 0.9765 (1.0260) time: 0.5028 [2021-03-25 12:43:07 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 420/1251] eta: 0:07:09 lr: 0.000928 loss: 3.8215 (3.7559) grad_norm: 1.0053 (1.0249) time: 0.4985 [2021-03-25 12:43:12 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 430/1251] eta: 0:07:04 lr: 0.000927 loss: 3.8057 (3.7566) grad_norm: 0.9763 (1.0239) time: 0.5048 [2021-03-25 12:43:18 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 440/1251] eta: 0:06:59 lr: 0.000927 loss: 3.8057 (3.7569) grad_norm: 1.0499 (1.0257) time: 0.5124 [2021-03-25 12:43:23 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 450/1251] eta: 0:06:53 lr: 0.000927 loss: 3.9706 (3.7604) grad_norm: 1.0470 (1.0245) time: 0.5107 [2021-03-25 12:43:28 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 460/1251] eta: 0:06:48 lr: 0.000927 loss: 3.9929 (3.7622) grad_norm: 0.9798 (1.0249) time: 0.5039 [2021-03-25 12:43:33 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 470/1251] eta: 0:06:43 lr: 0.000927 loss: 3.9060 (3.7619) grad_norm: 1.0235 (1.0261) time: 0.5065 [2021-03-25 12:43:38 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 480/1251] eta: 0:06:37 lr: 0.000927 loss: 3.9638 (3.7679) grad_norm: 1.0167 (1.0266) time: 0.5067 [2021-03-25 12:43:43 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 490/1251] eta: 0:06:32 lr: 0.000927 loss: 3.9975 (3.7699) grad_norm: 0.9749 (1.0259) time: 0.5036 [2021-03-25 12:43:48 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 500/1251] eta: 0:06:27 lr: 0.000927 loss: 3.9975 (3.7729) grad_norm: 0.9826 (1.0273) time: 0.5051 [2021-03-25 12:43:53 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 510/1251] eta: 0:06:21 lr: 0.000927 loss: 3.9899 (3.7736) grad_norm: 1.0256 (1.0271) time: 0.5045 [2021-03-25 12:43:58 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 520/1251] eta: 0:06:16 lr: 0.000927 loss: 3.9113 (3.7781) grad_norm: 1.0132 (1.0282) time: 0.5050 [2021-03-25 12:44:03 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 530/1251] eta: 0:06:11 lr: 0.000927 loss: 3.9025 (3.7781) grad_norm: 1.0024 (1.0282) time: 0.5057 [2021-03-25 12:44:08 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 540/1251] eta: 0:06:06 lr: 0.000927 loss: 3.6273 (3.7746) grad_norm: 1.0021 (1.0286) time: 0.5072 [2021-03-25 12:44:13 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 550/1251] eta: 0:06:01 lr: 0.000927 loss: 3.4918 (3.7714) grad_norm: 1.0030 (1.0294) time: 0.5190 [2021-03-25 12:44:18 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 560/1251] eta: 0:05:55 lr: 0.000927 loss: 3.8112 (3.7732) grad_norm: 0.9805 (1.0286) time: 0.5177 [2021-03-25 12:44:24 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 570/1251] eta: 0:05:50 lr: 0.000927 loss: 3.7315 (3.7692) grad_norm: 0.9391 (1.0278) time: 0.5083 [2021-03-25 12:44:29 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 580/1251] eta: 0:05:45 lr: 0.000927 loss: 3.6181 (3.7693) grad_norm: 0.9622 (1.0270) time: 0.5065 [2021-03-25 12:44:34 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 590/1251] eta: 0:05:40 lr: 0.000927 loss: 4.0164 (3.7696) grad_norm: 0.9650 (1.0267) time: 0.5051 [2021-03-25 12:44:39 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 600/1251] eta: 0:05:34 lr: 0.000927 loss: 3.5856 (3.7665) grad_norm: 0.9745 (1.0265) time: 0.5009 [2021-03-25 12:44:44 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 610/1251] eta: 0:05:29 lr: 0.000927 loss: 3.5856 (3.7620) grad_norm: 1.0570 (1.0283) time: 0.5023 [2021-03-25 12:44:49 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 620/1251] eta: 0:05:24 lr: 0.000927 loss: 3.8976 (3.7647) grad_norm: 1.0249 (1.0271) time: 0.4987 [2021-03-25 12:44:54 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 630/1251] eta: 0:05:18 lr: 0.000927 loss: 3.8274 (3.7625) grad_norm: 0.9264 (1.0262) time: 0.4958 [2021-03-25 12:44:59 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 640/1251] eta: 0:05:13 lr: 0.000927 loss: 3.5994 (3.7595) grad_norm: 1.0458 (1.0275) time: 0.5101 [2021-03-25 12:45:04 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 650/1251] eta: 0:05:08 lr: 0.000927 loss: 3.8550 (3.7609) grad_norm: 1.0501 (1.0275) time: 0.5149 [2021-03-25 12:45:09 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 660/1251] eta: 0:05:03 lr: 0.000927 loss: 3.8726 (3.7576) grad_norm: 0.9968 (1.0272) time: 0.5119 [2021-03-25 12:45:14 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 670/1251] eta: 0:04:58 lr: 0.000927 loss: 3.7082 (3.7576) grad_norm: 0.9884 (1.0261) time: 0.5108 [2021-03-25 12:45:19 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 680/1251] eta: 0:04:53 lr: 0.000927 loss: 3.7082 (3.7545) grad_norm: 0.9693 (1.0257) time: 0.5139 [2021-03-25 12:45:24 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 690/1251] eta: 0:04:47 lr: 0.000927 loss: 3.5230 (3.7533) grad_norm: 0.9629 (1.0250) time: 0.5089 [2021-03-25 12:45:30 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 700/1251] eta: 0:04:42 lr: 0.000927 loss: 3.7289 (3.7515) grad_norm: 0.9281 (1.0236) time: 0.5082 [2021-03-25 12:45:35 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 710/1251] eta: 0:04:37 lr: 0.000927 loss: 3.7302 (3.7533) grad_norm: 0.9281 (1.0235) time: 0.5083 [2021-03-25 12:45:40 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 720/1251] eta: 0:04:32 lr: 0.000927 loss: 4.0327 (3.7571) grad_norm: 1.1022 (1.0248) time: 0.5037 [2021-03-25 12:45:45 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 730/1251] eta: 0:04:27 lr: 0.000927 loss: 3.8252 (3.7520) grad_norm: 1.1507 (1.0264) time: 0.5089 [2021-03-25 12:45:50 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 740/1251] eta: 0:04:22 lr: 0.000927 loss: 3.8252 (3.7564) grad_norm: 1.0576 (1.0263) time: 0.5250 [2021-03-25 12:45:55 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 750/1251] eta: 0:04:17 lr: 0.000927 loss: 3.8952 (3.7557) grad_norm: 0.9833 (1.0258) time: 0.5209 [2021-03-25 12:46:00 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 760/1251] eta: 0:04:12 lr: 0.000927 loss: 3.6889 (3.7544) grad_norm: 0.9849 (1.0257) time: 0.5132 [2021-03-25 12:46:05 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 770/1251] eta: 0:04:06 lr: 0.000927 loss: 3.5543 (3.7499) grad_norm: 0.9945 (1.0254) time: 0.5152 [2021-03-25 12:46:10 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 780/1251] eta: 0:04:01 lr: 0.000927 loss: 3.3691 (3.7462) grad_norm: 0.9953 (1.0257) time: 0.5058 [2021-03-25 12:46:16 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 790/1251] eta: 0:03:56 lr: 0.000927 loss: 3.6228 (3.7453) grad_norm: 1.0452 (1.0267) time: 0.5037 [2021-03-25 12:46:20 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 800/1251] eta: 0:03:51 lr: 0.000927 loss: 3.8027 (3.7466) grad_norm: 1.0790 (1.0271) time: 0.5012 [2021-03-25 12:46:26 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 810/1251] eta: 0:03:46 lr: 0.000927 loss: 3.7856 (3.7468) grad_norm: 1.0790 (1.0279) time: 0.5026 [2021-03-25 12:46:31 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 820/1251] eta: 0:03:40 lr: 0.000927 loss: 3.7856 (3.7468) grad_norm: 1.0092 (1.0277) time: 0.5042 [2021-03-25 12:46:36 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 830/1251] eta: 0:03:35 lr: 0.000927 loss: 3.8749 (3.7480) grad_norm: 0.9770 (1.0277) time: 0.5121 [2021-03-25 12:46:41 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 840/1251] eta: 0:03:30 lr: 0.000927 loss: 3.6549 (3.7458) grad_norm: 1.0030 (1.0286) time: 0.5147 [2021-03-25 12:46:46 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 850/1251] eta: 0:03:25 lr: 0.000927 loss: 3.6060 (3.7457) grad_norm: 1.0142 (1.0282) time: 0.5069 [2021-03-25 12:46:51 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 860/1251] eta: 0:03:20 lr: 0.000927 loss: 3.8868 (3.7478) grad_norm: 0.9168 (1.0270) time: 0.5081 [2021-03-25 12:46:56 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 870/1251] eta: 0:03:15 lr: 0.000927 loss: 3.9541 (3.7488) grad_norm: 0.9487 (1.0267) time: 0.5057 [2021-03-25 12:47:01 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 880/1251] eta: 0:03:10 lr: 0.000927 loss: 3.6979 (3.7479) grad_norm: 0.9487 (1.0256) time: 0.5019 [2021-03-25 12:47:06 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 890/1251] eta: 0:03:04 lr: 0.000926 loss: 3.8481 (3.7503) grad_norm: 0.9538 (1.0250) time: 0.5067 [2021-03-25 12:47:11 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 900/1251] eta: 0:02:59 lr: 0.000926 loss: 3.9207 (3.7489) grad_norm: 0.9807 (1.0247) time: 0.5078 [2021-03-25 12:47:16 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 910/1251] eta: 0:02:54 lr: 0.000926 loss: 3.6654 (3.7471) grad_norm: 0.9807 (1.0239) time: 0.5051 [2021-03-25 12:47:21 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 920/1251] eta: 0:02:49 lr: 0.000926 loss: 3.6566 (3.7461) grad_norm: 0.9861 (1.0244) time: 0.5080 [2021-03-25 12:47:26 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 930/1251] eta: 0:02:44 lr: 0.000926 loss: 3.4038 (3.7415) grad_norm: 0.9965 (1.0244) time: 0.5095 [2021-03-25 12:47:32 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 940/1251] eta: 0:02:39 lr: 0.000926 loss: 3.7294 (3.7442) grad_norm: 0.9746 (1.0242) time: 0.5094 [2021-03-25 12:47:37 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 950/1251] eta: 0:02:34 lr: 0.000926 loss: 3.9047 (3.7435) grad_norm: 0.9743 (1.0238) time: 0.5130 [2021-03-25 12:47:42 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 960/1251] eta: 0:02:28 lr: 0.000926 loss: 3.8368 (3.7438) grad_norm: 0.9902 (1.0235) time: 0.5053 [2021-03-25 12:47:47 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 970/1251] eta: 0:02:23 lr: 0.000926 loss: 3.9070 (3.7419) grad_norm: 0.9703 (1.0227) time: 0.4972 [2021-03-25 12:47:52 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 980/1251] eta: 0:02:18 lr: 0.000926 loss: 3.8991 (3.7435) grad_norm: 0.9465 (1.0221) time: 0.5038 [2021-03-25 12:47:57 swin_small_patch4_window7_224] INFO: Epoch: [52] [ 990/1251] eta: 0:02:13 lr: 0.000926 loss: 3.8695 (3.7433) grad_norm: 0.9794 (1.0222) time: 0.5084 [2021-03-25 12:48:02 swin_small_patch4_window7_224] INFO: Epoch: [52] [1000/1251] eta: 0:02:08 lr: 0.000926 loss: 3.9093 (3.7452) grad_norm: 1.0075 (1.0224) time: 0.5116 [2021-03-25 12:48:07 swin_small_patch4_window7_224] INFO: Epoch: [52] [1010/1251] eta: 0:02:03 lr: 0.000926 loss: 3.8285 (3.7431) grad_norm: 0.9661 (1.0217) time: 0.5114 [2021-03-25 12:48:12 swin_small_patch4_window7_224] INFO: Epoch: [52] [1020/1251] eta: 0:01:58 lr: 0.000926 loss: 3.7407 (3.7427) grad_norm: 0.9661 (1.0218) time: 0.5103 [2021-03-25 12:48:17 swin_small_patch4_window7_224] INFO: Epoch: [52] [1030/1251] eta: 0:01:53 lr: 0.000926 loss: 3.8981 (3.7455) grad_norm: 1.0373 (1.0221) time: 0.5089 [2021-03-25 12:48:22 swin_small_patch4_window7_224] INFO: Epoch: [52] [1040/1251] eta: 0:01:47 lr: 0.000926 loss: 3.8981 (3.7455) grad_norm: 1.0234 (1.0226) time: 0.5005 [2021-03-25 12:48:27 swin_small_patch4_window7_224] INFO: Epoch: [52] [1050/1251] eta: 0:01:42 lr: 0.000926 loss: 3.8551 (3.7467) grad_norm: 1.0602 (1.0234) time: 0.5020 [2021-03-25 12:48:32 swin_small_patch4_window7_224] INFO: Epoch: [52] [1060/1251] eta: 0:01:37 lr: 0.000926 loss: 3.9122 (3.7486) grad_norm: 1.0389 (1.0231) time: 0.5082 [2021-03-25 12:48:37 swin_small_patch4_window7_224] INFO: Epoch: [52] [1070/1251] eta: 0:01:32 lr: 0.000926 loss: 3.7732 (3.7472) grad_norm: 0.9591 (1.0227) time: 0.5075 [2021-03-25 12:48:42 swin_small_patch4_window7_224] INFO: Epoch: [52] [1080/1251] eta: 0:01:27 lr: 0.000926 loss: 3.7732 (3.7500) grad_norm: 1.0201 (1.0234) time: 0.5032 [2021-03-25 12:48:48 swin_small_patch4_window7_224] INFO: Epoch: [52] [1090/1251] eta: 0:01:22 lr: 0.000926 loss: 3.9851 (3.7505) grad_norm: 1.0628 (1.0243) time: 0.5039 [2021-03-25 12:48:53 swin_small_patch4_window7_224] INFO: Epoch: [52] [1100/1251] eta: 0:01:17 lr: 0.000926 loss: 3.7163 (3.7499) grad_norm: 1.0547 (1.0245) time: 0.5080 [2021-03-25 12:48:58 swin_small_patch4_window7_224] INFO: Epoch: [52] [1110/1251] eta: 0:01:12 lr: 0.000926 loss: 3.8144 (3.7518) grad_norm: 1.0456 (1.0250) time: 0.5059 [2021-03-25 12:49:03 swin_small_patch4_window7_224] INFO: Epoch: [52] [1120/1251] eta: 0:01:06 lr: 0.000926 loss: 3.8089 (3.7511) grad_norm: 1.0127 (1.0245) time: 0.5055 [2021-03-25 12:49:08 swin_small_patch4_window7_224] INFO: Epoch: [52] [1130/1251] eta: 0:01:01 lr: 0.000926 loss: 3.6889 (3.7503) grad_norm: 0.9950 (1.0246) time: 0.5036 [2021-03-25 12:49:13 swin_small_patch4_window7_224] INFO: Epoch: [52] [1140/1251] eta: 0:00:56 lr: 0.000926 loss: 3.6983 (3.7496) grad_norm: 1.0130 (1.0242) time: 0.4999 [2021-03-25 12:49:18 swin_small_patch4_window7_224] INFO: Epoch: [52] [1150/1251] eta: 0:00:51 lr: 0.000926 loss: 3.8271 (3.7507) grad_norm: 1.0130 (1.0240) time: 0.5027 [2021-03-25 12:49:23 swin_small_patch4_window7_224] INFO: Epoch: [52] [1160/1251] eta: 0:00:46 lr: 0.000926 loss: 3.8415 (3.7504) grad_norm: 1.0069 (1.0244) time: 0.5066 [2021-03-25 12:49:28 swin_small_patch4_window7_224] INFO: Epoch: [52] [1170/1251] eta: 0:00:41 lr: 0.000926 loss: 3.2479 (3.7457) grad_norm: 1.0249 (1.0244) time: 0.5033 [2021-03-25 12:49:33 swin_small_patch4_window7_224] INFO: Epoch: [52] [1180/1251] eta: 0:00:36 lr: 0.000926 loss: 3.8312 (3.7496) grad_norm: 0.9660 (1.0239) time: 0.4999 [2021-03-25 12:49:38 swin_small_patch4_window7_224] INFO: Epoch: [52] [1190/1251] eta: 0:00:31 lr: 0.000926 loss: 4.2190 (3.7517) grad_norm: 0.9723 (1.0242) time: 0.4989 [2021-03-25 12:49:43 swin_small_patch4_window7_224] INFO: Epoch: [52] [1200/1251] eta: 0:00:26 lr: 0.000926 loss: 3.9208 (3.7506) grad_norm: 1.0071 (1.0239) time: 0.5026 [2021-03-25 12:49:48 swin_small_patch4_window7_224] INFO: Epoch: [52] [1210/1251] eta: 0:00:20 lr: 0.000926 loss: 3.8556 (3.7505) grad_norm: 0.9933 (1.0240) time: 0.5131 [2021-03-25 12:49:53 swin_small_patch4_window7_224] INFO: Epoch: [52] [1220/1251] eta: 0:00:15 lr: 0.000926 loss: 3.7494 (3.7487) grad_norm: 0.9222 (1.0239) time: 0.5079 [2021-03-25 12:49:58 swin_small_patch4_window7_224] INFO: Epoch: [52] [1230/1251] eta: 0:00:10 lr: 0.000926 loss: 3.4576 (3.7471) grad_norm: 0.9905 (1.0238) time: 0.4980 [2021-03-25 12:50:03 swin_small_patch4_window7_224] INFO: Epoch: [52] [1240/1251] eta: 0:00:05 lr: 0.000926 loss: 3.5392 (3.7474) grad_norm: 0.9924 (1.0236) time: 0.5022 [2021-03-25 12:50:08 swin_small_patch4_window7_224] INFO: Epoch: [52] [1250/1251] eta: 0:00:00 lr: 0.000926 loss: 3.9280 (3.7480) grad_norm: 0.9924 (1.0235) time: 0.5066 [2021-03-25 12:50:13 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 1.1226 (1.1226) acc1: 75.0000 (75.0000) acc5: 92.1875 (92.1875) [2021-03-25 12:50:15 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1604 (1.1932) acc1: 75.0000 (72.3011) acc5: 92.1875 (91.7614) [2021-03-25 12:50:17 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1794 (1.2024) acc1: 71.8750 (72.1726) acc5: 90.6250 (91.0714) [2021-03-25 12:50:19 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2617 (1.2190) acc1: 68.7500 (71.5222) acc5: 90.6250 (90.9274) [2021-03-25 12:50:22 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1605 (1.1970) acc1: 71.8750 (72.1418) acc5: 92.1875 (91.2729) [2021-03-25 12:50:23 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1222 (1.1861) acc1: 71.8750 (72.2560) acc5: 90.6250 (91.2320) [2021-03-25 12:50:25 swin_small_patch4_window7_224] INFO: * Acc@1 72.996 Acc@5 91.872 loss 1.167 [2021-03-25 12:50:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.0% [2021-03-25 12:50:25 swin_small_patch4_window7_224] INFO: Max accuracy: 73.00% [2021-03-25 12:50:29 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 0/1251] eta: 1:19:52 lr: 0.000926 loss: 4.0914 (4.0914) grad_norm: 0.8480 (0.8480) time: 3.8311 [2021-03-25 12:50:34 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 10/1251] eta: 0:17:28 lr: 0.000926 loss: 3.5532 (3.4636) grad_norm: 1.0399 (1.0214) time: 0.8451 [2021-03-25 12:50:39 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 20/1251] eta: 0:14:00 lr: 0.000926 loss: 3.4271 (3.4156) grad_norm: 0.9764 (0.9956) time: 0.5251 [2021-03-25 12:50:44 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 30/1251] eta: 0:12:43 lr: 0.000926 loss: 3.5288 (3.5288) grad_norm: 0.9507 (0.9936) time: 0.5048 [2021-03-25 12:50:49 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 40/1251] eta: 0:12:07 lr: 0.000926 loss: 3.7861 (3.5798) grad_norm: 0.9643 (0.9903) time: 0.5144 [2021-03-25 12:50:54 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 50/1251] eta: 0:11:38 lr: 0.000926 loss: 3.8151 (3.6202) grad_norm: 1.0016 (0.9933) time: 0.5127 [2021-03-25 12:50:59 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 60/1251] eta: 0:11:15 lr: 0.000926 loss: 3.9475 (3.6476) grad_norm: 1.0025 (1.0042) time: 0.4981 [2021-03-25 12:51:05 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 70/1251] eta: 0:11:00 lr: 0.000926 loss: 4.0523 (3.6990) grad_norm: 1.0386 (1.0182) time: 0.5041 [2021-03-25 12:51:10 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 80/1251] eta: 0:10:48 lr: 0.000926 loss: 3.9210 (3.6727) grad_norm: 1.0210 (1.0113) time: 0.5122 [2021-03-25 12:51:15 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 90/1251] eta: 0:10:35 lr: 0.000926 loss: 3.7356 (3.6809) grad_norm: 0.9596 (1.0074) time: 0.5056 [2021-03-25 12:51:20 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 100/1251] eta: 0:10:25 lr: 0.000925 loss: 3.8276 (3.6964) grad_norm: 1.0003 (1.0125) time: 0.5041 [2021-03-25 12:51:25 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 110/1251] eta: 0:10:16 lr: 0.000925 loss: 3.7819 (3.7015) grad_norm: 1.0173 (1.0170) time: 0.5058 [2021-03-25 12:51:30 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 120/1251] eta: 0:10:07 lr: 0.000925 loss: 3.7819 (3.6975) grad_norm: 0.9899 (1.0160) time: 0.5067 [2021-03-25 12:51:35 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 130/1251] eta: 0:10:01 lr: 0.000925 loss: 3.8882 (3.7091) grad_norm: 1.0343 (1.0200) time: 0.5168 [2021-03-25 12:51:40 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 140/1251] eta: 0:09:54 lr: 0.000925 loss: 3.7511 (3.7012) grad_norm: 1.0442 (1.0227) time: 0.5192 [2021-03-25 12:51:45 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 150/1251] eta: 0:09:46 lr: 0.000925 loss: 3.5257 (3.6781) grad_norm: 1.0151 (1.0248) time: 0.5100 [2021-03-25 12:51:50 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 160/1251] eta: 0:09:39 lr: 0.000925 loss: 3.7944 (3.6936) grad_norm: 1.0053 (1.0267) time: 0.5064 [2021-03-25 12:51:55 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 170/1251] eta: 0:09:32 lr: 0.000925 loss: 4.0240 (3.6943) grad_norm: 1.0063 (1.0287) time: 0.5058 [2021-03-25 12:52:01 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 180/1251] eta: 0:09:26 lr: 0.000925 loss: 3.6985 (3.6978) grad_norm: 1.0050 (1.0283) time: 0.5112 [2021-03-25 12:52:06 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 190/1251] eta: 0:09:19 lr: 0.000925 loss: 3.6376 (3.6931) grad_norm: 1.0043 (1.0316) time: 0.5092 [2021-03-25 12:52:11 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 200/1251] eta: 0:09:14 lr: 0.000925 loss: 3.7500 (3.6961) grad_norm: 1.0307 (1.0312) time: 0.5107 [2021-03-25 12:52:16 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 210/1251] eta: 0:09:07 lr: 0.000925 loss: 3.8451 (3.6981) grad_norm: 0.9899 (1.0303) time: 0.5097 [2021-03-25 12:52:21 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 220/1251] eta: 0:09:01 lr: 0.000925 loss: 3.8555 (3.7085) grad_norm: 0.9634 (1.0243) time: 0.5018 [2021-03-25 12:52:26 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 230/1251] eta: 0:08:55 lr: 0.000925 loss: 3.8555 (3.7061) grad_norm: 0.9778 (1.0246) time: 0.5041 [2021-03-25 12:52:31 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 240/1251] eta: 0:08:49 lr: 0.000925 loss: 3.5590 (3.7049) grad_norm: 1.0116 (1.0239) time: 0.5150 [2021-03-25 12:52:36 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 250/1251] eta: 0:08:43 lr: 0.000925 loss: 3.6208 (3.7041) grad_norm: 0.9750 (1.0229) time: 0.5145 [2021-03-25 12:52:41 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 260/1251] eta: 0:08:38 lr: 0.000925 loss: 3.7738 (3.7096) grad_norm: 0.9429 (1.0215) time: 0.5071 [2021-03-25 12:52:46 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 270/1251] eta: 0:08:32 lr: 0.000925 loss: 3.7738 (3.7084) grad_norm: 0.9440 (1.0214) time: 0.5074 [2021-03-25 12:52:51 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 280/1251] eta: 0:08:26 lr: 0.000925 loss: 3.8724 (3.7158) grad_norm: 1.0499 (1.0248) time: 0.5015 [2021-03-25 12:52:56 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 290/1251] eta: 0:08:20 lr: 0.000925 loss: 3.7617 (3.7093) grad_norm: 1.0499 (1.0253) time: 0.4982 [2021-03-25 12:53:01 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 300/1251] eta: 0:08:14 lr: 0.000925 loss: 3.6324 (3.7046) grad_norm: 0.9761 (1.0242) time: 0.4990 [2021-03-25 12:53:06 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 310/1251] eta: 0:08:08 lr: 0.000925 loss: 3.6043 (3.7062) grad_norm: 0.9810 (1.0273) time: 0.5019 [2021-03-25 12:53:11 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 320/1251] eta: 0:08:03 lr: 0.000925 loss: 3.4156 (3.6923) grad_norm: 1.1030 (1.0297) time: 0.5031 [2021-03-25 12:53:16 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 330/1251] eta: 0:07:57 lr: 0.000925 loss: 3.6130 (3.6973) grad_norm: 1.0027 (1.0292) time: 0.5047 [2021-03-25 12:53:22 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 340/1251] eta: 0:07:51 lr: 0.000925 loss: 3.8000 (3.6920) grad_norm: 0.9910 (1.0279) time: 0.5061 [2021-03-25 12:53:27 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 350/1251] eta: 0:07:46 lr: 0.000925 loss: 3.5738 (3.6931) grad_norm: 1.0063 (1.0281) time: 0.5044 [2021-03-25 12:53:32 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 360/1251] eta: 0:07:40 lr: 0.000925 loss: 4.0597 (3.6983) grad_norm: 1.0063 (1.0270) time: 0.5011 [2021-03-25 12:53:37 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 370/1251] eta: 0:07:35 lr: 0.000925 loss: 3.8933 (3.6981) grad_norm: 0.9866 (1.0279) time: 0.5033 [2021-03-25 12:53:42 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 380/1251] eta: 0:07:29 lr: 0.000925 loss: 3.8526 (3.7002) grad_norm: 1.0215 (1.0284) time: 0.5067 [2021-03-25 12:53:47 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 390/1251] eta: 0:07:24 lr: 0.000925 loss: 3.8526 (3.6989) grad_norm: 1.0280 (1.0277) time: 0.5063 [2021-03-25 12:53:52 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 400/1251] eta: 0:07:19 lr: 0.000925 loss: 3.8043 (3.6985) grad_norm: 0.9744 (1.0272) time: 0.5064 [2021-03-25 12:53:57 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 410/1251] eta: 0:07:13 lr: 0.000925 loss: 3.8043 (3.7000) grad_norm: 1.0042 (1.0279) time: 0.5074 [2021-03-25 12:54:02 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 420/1251] eta: 0:07:08 lr: 0.000925 loss: 3.9136 (3.7049) grad_norm: 1.0844 (1.0321) time: 0.5025 [2021-03-25 12:54:07 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 430/1251] eta: 0:07:03 lr: 0.000925 loss: 3.8463 (3.7024) grad_norm: 1.0760 (1.0323) time: 0.5019 [2021-03-25 12:54:12 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 440/1251] eta: 0:06:57 lr: 0.000925 loss: 3.8463 (3.7007) grad_norm: 1.0050 (1.0321) time: 0.5067 [2021-03-25 12:54:17 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 450/1251] eta: 0:06:52 lr: 0.000925 loss: 3.9372 (3.7052) grad_norm: 0.9687 (1.0297) time: 0.5099 [2021-03-25 12:54:22 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 460/1251] eta: 0:06:47 lr: 0.000925 loss: 3.7925 (3.7035) grad_norm: 0.9122 (1.0281) time: 0.5100 [2021-03-25 12:54:27 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 470/1251] eta: 0:06:41 lr: 0.000925 loss: 3.7371 (3.7063) grad_norm: 0.9829 (1.0282) time: 0.5082 [2021-03-25 12:54:32 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 480/1251] eta: 0:06:36 lr: 0.000925 loss: 3.7371 (3.7033) grad_norm: 0.9903 (1.0271) time: 0.5081 [2021-03-25 12:54:37 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 490/1251] eta: 0:06:31 lr: 0.000925 loss: 3.7746 (3.7066) grad_norm: 0.9759 (1.0267) time: 0.5065 [2021-03-25 12:54:42 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 500/1251] eta: 0:06:26 lr: 0.000925 loss: 3.7386 (3.7062) grad_norm: 1.0064 (1.0275) time: 0.5012 [2021-03-25 12:54:48 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 510/1251] eta: 0:06:20 lr: 0.000925 loss: 3.7386 (3.7086) grad_norm: 1.0479 (1.0281) time: 0.5037 [2021-03-25 12:54:53 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 520/1251] eta: 0:06:15 lr: 0.000925 loss: 3.8049 (3.7091) grad_norm: 1.0332 (1.0277) time: 0.5144 [2021-03-25 12:54:58 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 530/1251] eta: 0:06:10 lr: 0.000925 loss: 4.0402 (3.7139) grad_norm: 1.0007 (1.0270) time: 0.5089 [2021-03-25 12:55:03 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 540/1251] eta: 0:06:05 lr: 0.000925 loss: 4.0402 (3.7154) grad_norm: 1.0086 (1.0272) time: 0.5020 [2021-03-25 12:55:08 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 550/1251] eta: 0:06:00 lr: 0.000924 loss: 4.1232 (3.7251) grad_norm: 0.9891 (1.0273) time: 0.5117 [2021-03-25 12:55:13 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 560/1251] eta: 0:05:55 lr: 0.000924 loss: 3.8435 (3.7241) grad_norm: 0.9891 (1.0277) time: 0.5190 [2021-03-25 12:55:18 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 570/1251] eta: 0:05:49 lr: 0.000924 loss: 3.6872 (3.7193) grad_norm: 0.9544 (1.0263) time: 0.5134 [2021-03-25 12:55:23 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 580/1251] eta: 0:05:44 lr: 0.000924 loss: 3.8197 (3.7186) grad_norm: 0.9640 (1.0266) time: 0.5059 [2021-03-25 12:55:28 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 590/1251] eta: 0:05:39 lr: 0.000924 loss: 3.8800 (3.7181) grad_norm: 0.9866 (1.0248) time: 0.5059 [2021-03-25 12:55:34 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 600/1251] eta: 0:05:34 lr: 0.000924 loss: 3.8800 (3.7135) grad_norm: 0.9365 (1.0246) time: 0.5106 [2021-03-25 12:55:38 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 610/1251] eta: 0:05:28 lr: 0.000924 loss: 3.6712 (3.7143) grad_norm: 0.9990 (1.0257) time: 0.5058 [2021-03-25 12:55:44 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 620/1251] eta: 0:05:23 lr: 0.000924 loss: 3.8956 (3.7165) grad_norm: 1.0375 (1.0267) time: 0.5038 [2021-03-25 12:55:49 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 630/1251] eta: 0:05:18 lr: 0.000924 loss: 3.8956 (3.7174) grad_norm: 1.0428 (1.0265) time: 0.5082 [2021-03-25 12:55:54 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 640/1251] eta: 0:05:13 lr: 0.000924 loss: 3.8292 (3.7169) grad_norm: 0.9899 (1.0260) time: 0.5091 [2021-03-25 12:55:59 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 650/1251] eta: 0:05:08 lr: 0.000924 loss: 3.9271 (3.7220) grad_norm: 0.9250 (1.0245) time: 0.5105 [2021-03-25 12:56:04 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 660/1251] eta: 0:05:03 lr: 0.000924 loss: 3.9271 (3.7178) grad_norm: 0.9255 (1.0233) time: 0.5083 [2021-03-25 12:56:09 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 670/1251] eta: 0:04:57 lr: 0.000924 loss: 3.8653 (3.7200) grad_norm: 1.0049 (1.0240) time: 0.5051 [2021-03-25 12:56:14 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 680/1251] eta: 0:04:52 lr: 0.000924 loss: 3.6704 (3.7172) grad_norm: 1.0445 (1.0242) time: 0.5103 [2021-03-25 12:56:19 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 690/1251] eta: 0:04:47 lr: 0.000924 loss: 3.6293 (3.7176) grad_norm: 0.9680 (1.0229) time: 0.5114 [2021-03-25 12:56:24 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 700/1251] eta: 0:04:42 lr: 0.000924 loss: 3.8673 (3.7179) grad_norm: 1.0018 (1.0231) time: 0.5018 [2021-03-25 12:56:29 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 710/1251] eta: 0:04:37 lr: 0.000924 loss: 3.6469 (3.7161) grad_norm: 1.0436 (1.0239) time: 0.5032 [2021-03-25 12:56:34 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 720/1251] eta: 0:04:32 lr: 0.000924 loss: 3.6469 (3.7159) grad_norm: 1.0593 (1.0244) time: 0.5066 [2021-03-25 12:56:39 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 730/1251] eta: 0:04:26 lr: 0.000924 loss: 3.7114 (3.7148) grad_norm: 1.0481 (1.0244) time: 0.5084 [2021-03-25 12:56:45 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 740/1251] eta: 0:04:21 lr: 0.000924 loss: 3.7114 (3.7167) grad_norm: 1.0121 (1.0245) time: 0.5170 [2021-03-25 12:56:50 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 750/1251] eta: 0:04:16 lr: 0.000924 loss: 3.8416 (3.7145) grad_norm: 0.9766 (1.0231) time: 0.5243 [2021-03-25 12:56:55 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 760/1251] eta: 0:04:11 lr: 0.000924 loss: 3.8416 (3.7140) grad_norm: 0.8874 (1.0221) time: 0.5187 [2021-03-25 12:57:00 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 770/1251] eta: 0:04:06 lr: 0.000924 loss: 4.0056 (3.7179) grad_norm: 0.9663 (1.0226) time: 0.5037 [2021-03-25 12:57:05 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 780/1251] eta: 0:04:01 lr: 0.000924 loss: 3.6866 (3.7144) grad_norm: 0.9936 (1.0226) time: 0.5017 [2021-03-25 12:57:10 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 790/1251] eta: 0:03:56 lr: 0.000924 loss: 3.6861 (3.7144) grad_norm: 0.9821 (1.0223) time: 0.5082 [2021-03-25 12:57:15 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 800/1251] eta: 0:03:50 lr: 0.000924 loss: 3.7651 (3.7123) grad_norm: 0.9670 (1.0215) time: 0.5044 [2021-03-25 12:57:20 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 810/1251] eta: 0:03:45 lr: 0.000924 loss: 3.4024 (3.7079) grad_norm: 1.0019 (1.0218) time: 0.5003 [2021-03-25 12:57:25 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 820/1251] eta: 0:03:40 lr: 0.000924 loss: 3.4402 (3.7066) grad_norm: 1.0332 (1.0229) time: 0.5069 [2021-03-25 12:57:30 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 830/1251] eta: 0:03:35 lr: 0.000924 loss: 3.5932 (3.7053) grad_norm: 1.0174 (1.0225) time: 0.5107 [2021-03-25 12:57:35 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 840/1251] eta: 0:03:30 lr: 0.000924 loss: 3.5075 (3.7021) grad_norm: 0.9904 (1.0222) time: 0.5017 [2021-03-25 12:57:40 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 850/1251] eta: 0:03:25 lr: 0.000924 loss: 3.5015 (3.7027) grad_norm: 0.9904 (1.0220) time: 0.4948 [2021-03-25 12:57:45 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 860/1251] eta: 0:03:19 lr: 0.000924 loss: 3.6647 (3.7018) grad_norm: 0.9998 (1.0219) time: 0.4954 [2021-03-25 12:57:50 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 870/1251] eta: 0:03:14 lr: 0.000924 loss: 3.7471 (3.7051) grad_norm: 0.9839 (1.0221) time: 0.5052 [2021-03-25 12:57:56 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 880/1251] eta: 0:03:09 lr: 0.000924 loss: 3.9015 (3.7084) grad_norm: 0.9702 (1.0213) time: 0.5128 [2021-03-25 12:58:01 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 890/1251] eta: 0:03:04 lr: 0.000924 loss: 3.8733 (3.7078) grad_norm: 0.9653 (1.0214) time: 0.5126 [2021-03-25 12:58:06 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 900/1251] eta: 0:02:59 lr: 0.000924 loss: 3.5667 (3.7053) grad_norm: 0.9895 (1.0214) time: 0.5109 [2021-03-25 12:58:11 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 910/1251] eta: 0:02:54 lr: 0.000924 loss: 3.5427 (3.7045) grad_norm: 0.9772 (1.0207) time: 0.5044 [2021-03-25 12:58:16 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 920/1251] eta: 0:02:49 lr: 0.000924 loss: 3.7627 (3.7059) grad_norm: 0.9559 (1.0207) time: 0.4998 [2021-03-25 12:58:21 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 930/1251] eta: 0:02:44 lr: 0.000924 loss: 3.7627 (3.7054) grad_norm: 0.9783 (1.0207) time: 0.5023 [2021-03-25 12:58:26 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 940/1251] eta: 0:02:38 lr: 0.000924 loss: 3.5291 (3.7030) grad_norm: 0.9758 (1.0201) time: 0.5067 [2021-03-25 12:58:31 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 950/1251] eta: 0:02:33 lr: 0.000924 loss: 3.5291 (3.7004) grad_norm: 0.9332 (1.0190) time: 0.5060 [2021-03-25 12:58:36 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 960/1251] eta: 0:02:28 lr: 0.000924 loss: 3.5150 (3.6984) grad_norm: 0.9555 (1.0195) time: 0.5016 [2021-03-25 12:58:41 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 970/1251] eta: 0:02:23 lr: 0.000924 loss: 3.9480 (3.6997) grad_norm: 1.0203 (1.0193) time: 0.4972 [2021-03-25 12:58:46 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 980/1251] eta: 0:02:18 lr: 0.000924 loss: 3.8571 (3.6998) grad_norm: 0.9773 (1.0188) time: 0.5083 [2021-03-25 12:58:51 swin_small_patch4_window7_224] INFO: Epoch: [53] [ 990/1251] eta: 0:02:13 lr: 0.000924 loss: 3.9233 (3.7023) grad_norm: 0.9881 (1.0190) time: 0.5134 [2021-03-25 12:58:56 swin_small_patch4_window7_224] INFO: Epoch: [53] [1000/1251] eta: 0:02:08 lr: 0.000923 loss: 3.9034 (3.7014) grad_norm: 0.9558 (1.0183) time: 0.5086 [2021-03-25 12:59:01 swin_small_patch4_window7_224] INFO: Epoch: [53] [1010/1251] eta: 0:02:03 lr: 0.000923 loss: 3.6423 (3.7012) grad_norm: 0.9707 (1.0186) time: 0.5067 [2021-03-25 12:59:06 swin_small_patch4_window7_224] INFO: Epoch: [53] [1020/1251] eta: 0:01:57 lr: 0.000923 loss: 3.6423 (3.6984) grad_norm: 0.9961 (1.0187) time: 0.5009 [2021-03-25 12:59:11 swin_small_patch4_window7_224] INFO: Epoch: [53] [1030/1251] eta: 0:01:52 lr: 0.000923 loss: 3.5392 (3.6982) grad_norm: 1.0061 (1.0186) time: 0.4993 [2021-03-25 12:59:16 swin_small_patch4_window7_224] INFO: Epoch: [53] [1040/1251] eta: 0:01:47 lr: 0.000923 loss: 3.8093 (3.7001) grad_norm: 0.9855 (1.0185) time: 0.5009 [2021-03-25 12:59:21 swin_small_patch4_window7_224] INFO: Epoch: [53] [1050/1251] eta: 0:01:42 lr: 0.000923 loss: 3.9564 (3.7009) grad_norm: 1.0366 (1.0193) time: 0.5027 [2021-03-25 12:59:26 swin_small_patch4_window7_224] INFO: Epoch: [53] [1060/1251] eta: 0:01:37 lr: 0.000923 loss: 3.8109 (3.7011) grad_norm: 1.0713 (1.0196) time: 0.5001 [2021-03-25 12:59:31 swin_small_patch4_window7_224] INFO: Epoch: [53] [1070/1251] eta: 0:01:32 lr: 0.000923 loss: 3.7472 (3.6999) grad_norm: 1.0722 (1.0204) time: 0.5001 [2021-03-25 12:59:36 swin_small_patch4_window7_224] INFO: Epoch: [53] [1080/1251] eta: 0:01:27 lr: 0.000923 loss: 3.5906 (3.6990) grad_norm: 1.0990 (1.0212) time: 0.5080 [2021-03-25 12:59:42 swin_small_patch4_window7_224] INFO: Epoch: [53] [1090/1251] eta: 0:01:22 lr: 0.000923 loss: 3.7725 (3.7007) grad_norm: 1.0961 (1.0222) time: 0.5098 [2021-03-25 12:59:47 swin_small_patch4_window7_224] INFO: Epoch: [53] [1100/1251] eta: 0:01:17 lr: 0.000923 loss: 3.7065 (3.6985) grad_norm: 1.0745 (1.0227) time: 0.5062 [2021-03-25 12:59:52 swin_small_patch4_window7_224] INFO: Epoch: [53] [1110/1251] eta: 0:01:11 lr: 0.000923 loss: 3.6879 (3.7002) grad_norm: 1.0556 (1.0227) time: 0.5061 [2021-03-25 12:59:57 swin_small_patch4_window7_224] INFO: Epoch: [53] [1120/1251] eta: 0:01:06 lr: 0.000923 loss: 3.8828 (3.7009) grad_norm: 1.0585 (1.0234) time: 0.5048 [2021-03-25 13:00:02 swin_small_patch4_window7_224] INFO: Epoch: [53] [1130/1251] eta: 0:01:01 lr: 0.000923 loss: 3.7868 (3.7003) grad_norm: 1.0281 (1.0230) time: 0.5082 [2021-03-25 13:00:07 swin_small_patch4_window7_224] INFO: Epoch: [53] [1140/1251] eta: 0:00:56 lr: 0.000923 loss: 3.8701 (3.7010) grad_norm: 0.9467 (1.0227) time: 0.5124 [2021-03-25 13:00:12 swin_small_patch4_window7_224] INFO: Epoch: [53] [1150/1251] eta: 0:00:51 lr: 0.000923 loss: 3.6792 (3.6986) grad_norm: 0.9803 (1.0222) time: 0.5101 [2021-03-25 13:00:17 swin_small_patch4_window7_224] INFO: Epoch: [53] [1160/1251] eta: 0:00:46 lr: 0.000923 loss: 3.2819 (3.6986) grad_norm: 0.9826 (1.0220) time: 0.5041 [2021-03-25 13:00:22 swin_small_patch4_window7_224] INFO: Epoch: [53] [1170/1251] eta: 0:00:41 lr: 0.000923 loss: 3.9770 (3.7005) grad_norm: 0.9826 (1.0218) time: 0.5071 [2021-03-25 13:00:27 swin_small_patch4_window7_224] INFO: Epoch: [53] [1180/1251] eta: 0:00:36 lr: 0.000923 loss: 4.0354 (3.7007) grad_norm: 1.0520 (1.0226) time: 0.5120 [2021-03-25 13:00:32 swin_small_patch4_window7_224] INFO: Epoch: [53] [1190/1251] eta: 0:00:31 lr: 0.000923 loss: 3.8297 (3.7001) grad_norm: 1.0936 (1.0232) time: 0.5105 [2021-03-25 13:00:37 swin_small_patch4_window7_224] INFO: Epoch: [53] [1200/1251] eta: 0:00:26 lr: 0.000923 loss: 3.9230 (3.7026) grad_norm: 1.0414 (1.0231) time: 0.5091 [2021-03-25 13:00:43 swin_small_patch4_window7_224] INFO: Epoch: [53] [1210/1251] eta: 0:00:20 lr: 0.000923 loss: 3.9720 (3.7026) grad_norm: 0.9921 (1.0226) time: 0.5106 [2021-03-25 13:00:48 swin_small_patch4_window7_224] INFO: Epoch: [53] [1220/1251] eta: 0:00:15 lr: 0.000923 loss: 3.6564 (3.7008) grad_norm: 0.9508 (1.0223) time: 0.5138 [2021-03-25 13:00:53 swin_small_patch4_window7_224] INFO: Epoch: [53] [1230/1251] eta: 0:00:10 lr: 0.000923 loss: 3.2635 (3.6975) grad_norm: 0.9929 (1.0228) time: 0.5098 [2021-03-25 13:00:58 swin_small_patch4_window7_224] INFO: Epoch: [53] [1240/1251] eta: 0:00:05 lr: 0.000923 loss: 3.3973 (3.6975) grad_norm: 1.0441 (1.0230) time: 0.5076 [2021-03-25 13:01:03 swin_small_patch4_window7_224] INFO: Epoch: [53] [1250/1251] eta: 0:00:00 lr: 0.000923 loss: 3.4400 (3.6948) grad_norm: 1.0441 (1.0232) time: 0.5070 [2021-03-25 13:01:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 1.2497 (1.2497) acc1: 65.6250 (65.6250) acc5: 92.1875 (92.1875) [2021-03-25 13:01:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.2497 (1.1858) acc1: 71.8750 (71.3068) acc5: 92.1875 (91.9034) [2021-03-25 13:01:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.2261 (1.1945) acc1: 71.8750 (70.8333) acc5: 92.1875 (91.8899) [2021-03-25 13:01:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1612 (1.1909) acc1: 71.8750 (71.7742) acc5: 92.1875 (91.9355) [2021-03-25 13:01:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1752 (1.2028) acc1: 73.4375 (71.7988) acc5: 90.6250 (91.4634) [2021-03-25 13:01:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1605 (1.1912) acc1: 75.0000 (72.4480) acc5: 90.6250 (91.4560) [2021-03-25 13:01:20 swin_small_patch4_window7_224] INFO: * Acc@1 72.946 Acc@5 91.722 loss 1.167 [2021-03-25 13:01:20 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 72.9% [2021-03-25 13:01:20 swin_small_patch4_window7_224] INFO: Max accuracy: 73.00% [2021-03-25 13:01:24 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 0/1251] eta: 1:24:20 lr: 0.000923 loss: 2.8170 (2.8170) grad_norm: 0.9409 (0.9409) time: 4.0452 [2021-03-25 13:01:29 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 10/1251] eta: 0:17:31 lr: 0.000923 loss: 3.8473 (3.8688) grad_norm: 1.0666 (1.0840) time: 0.8474 [2021-03-25 13:01:35 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 20/1251] eta: 0:14:05 lr: 0.000923 loss: 3.9381 (3.9084) grad_norm: 1.0125 (1.0604) time: 0.5185 [2021-03-25 13:01:40 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 30/1251] eta: 0:12:46 lr: 0.000923 loss: 3.9236 (3.8183) grad_norm: 1.0550 (1.0655) time: 0.5071 [2021-03-25 13:01:45 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 40/1251] eta: 0:12:06 lr: 0.000923 loss: 3.8824 (3.8033) grad_norm: 1.0534 (1.0533) time: 0.5097 [2021-03-25 13:01:50 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 50/1251] eta: 0:11:39 lr: 0.000923 loss: 3.9661 (3.7859) grad_norm: 1.0250 (1.0431) time: 0.5130 [2021-03-25 13:01:55 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 60/1251] eta: 0:11:20 lr: 0.000923 loss: 3.8854 (3.7874) grad_norm: 1.0303 (1.0468) time: 0.5110 [2021-03-25 13:02:00 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 70/1251] eta: 0:11:05 lr: 0.000923 loss: 3.8854 (3.7899) grad_norm: 1.0303 (1.0464) time: 0.5128 [2021-03-25 13:02:05 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 80/1251] eta: 0:10:51 lr: 0.000923 loss: 3.8417 (3.7535) grad_norm: 0.9949 (1.0449) time: 0.5108 [2021-03-25 13:02:10 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 90/1251] eta: 0:10:39 lr: 0.000923 loss: 3.8417 (3.7697) grad_norm: 0.9727 (1.0386) time: 0.5085 [2021-03-25 13:02:15 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 100/1251] eta: 0:10:29 lr: 0.000923 loss: 3.9750 (3.7506) grad_norm: 0.9600 (1.0367) time: 0.5094 [2021-03-25 13:02:20 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 110/1251] eta: 0:10:20 lr: 0.000923 loss: 3.9474 (3.7614) grad_norm: 0.9553 (1.0331) time: 0.5116 [2021-03-25 13:02:26 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 120/1251] eta: 0:10:11 lr: 0.000923 loss: 3.9353 (3.7723) grad_norm: 0.9633 (1.0305) time: 0.5087 [2021-03-25 13:02:31 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 130/1251] eta: 0:10:03 lr: 0.000923 loss: 3.8301 (3.7701) grad_norm: 0.9821 (1.0280) time: 0.5051 [2021-03-25 13:02:36 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 140/1251] eta: 0:09:55 lr: 0.000923 loss: 3.8352 (3.7609) grad_norm: 0.9803 (1.0235) time: 0.5108 [2021-03-25 13:02:41 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 150/1251] eta: 0:09:47 lr: 0.000923 loss: 3.8479 (3.7662) grad_norm: 0.9778 (1.0239) time: 0.5041 [2021-03-25 13:02:46 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 160/1251] eta: 0:09:40 lr: 0.000923 loss: 3.8330 (3.7532) grad_norm: 0.9682 (1.0211) time: 0.5001 [2021-03-25 13:02:51 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 170/1251] eta: 0:09:32 lr: 0.000923 loss: 3.6069 (3.7353) grad_norm: 0.9630 (1.0232) time: 0.5032 [2021-03-25 13:02:56 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 180/1251] eta: 0:09:26 lr: 0.000923 loss: 3.7034 (3.7434) grad_norm: 1.0986 (1.0340) time: 0.5033 [2021-03-25 13:03:01 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 190/1251] eta: 0:09:20 lr: 0.000923 loss: 3.7801 (3.7366) grad_norm: 1.1192 (1.0355) time: 0.5128 [2021-03-25 13:03:06 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 200/1251] eta: 0:09:13 lr: 0.000922 loss: 3.7801 (3.7453) grad_norm: 1.0629 (1.0386) time: 0.5127 [2021-03-25 13:03:11 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 210/1251] eta: 0:09:07 lr: 0.000922 loss: 3.8368 (3.7408) grad_norm: 1.0693 (1.0397) time: 0.5068 [2021-03-25 13:03:16 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 220/1251] eta: 0:09:01 lr: 0.000922 loss: 3.5691 (3.7286) grad_norm: 1.0922 (1.0425) time: 0.5094 [2021-03-25 13:03:21 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 230/1251] eta: 0:08:55 lr: 0.000922 loss: 3.4717 (3.7216) grad_norm: 1.0937 (1.0437) time: 0.5050 [2021-03-25 13:03:26 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 240/1251] eta: 0:08:49 lr: 0.000922 loss: 3.6919 (3.7172) grad_norm: 1.0534 (1.0439) time: 0.5016 [2021-03-25 13:03:31 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 250/1251] eta: 0:08:43 lr: 0.000922 loss: 3.9184 (3.7295) grad_norm: 1.0398 (1.0455) time: 0.5057 [2021-03-25 13:03:36 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 260/1251] eta: 0:08:37 lr: 0.000922 loss: 3.9521 (3.7336) grad_norm: 1.1086 (1.0479) time: 0.5096 [2021-03-25 13:03:42 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 270/1251] eta: 0:08:32 lr: 0.000922 loss: 3.7189 (3.7318) grad_norm: 1.0237 (1.0471) time: 0.5104 [2021-03-25 13:03:47 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 280/1251] eta: 0:08:26 lr: 0.000922 loss: 3.6882 (3.7306) grad_norm: 1.0237 (1.0496) time: 0.5052 [2021-03-25 13:03:52 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 290/1251] eta: 0:08:20 lr: 0.000922 loss: 3.5046 (3.7251) grad_norm: 1.0444 (1.0494) time: 0.5001 [2021-03-25 13:03:57 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 300/1251] eta: 0:08:14 lr: 0.000922 loss: 3.4420 (3.7139) grad_norm: 1.0444 (inf) time: 0.4992 [2021-03-25 13:04:02 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 310/1251] eta: 0:08:08 lr: 0.000922 loss: 3.3597 (3.7089) grad_norm: 1.0170 (inf) time: 0.5073 [2021-03-25 13:04:07 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 320/1251] eta: 0:08:03 lr: 0.000922 loss: 3.6991 (3.7059) grad_norm: 0.9960 (inf) time: 0.5090 [2021-03-25 13:04:12 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 330/1251] eta: 0:07:57 lr: 0.000922 loss: 3.8014 (3.7119) grad_norm: 1.0502 (inf) time: 0.5042 [2021-03-25 13:04:17 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 340/1251] eta: 0:07:52 lr: 0.000922 loss: 3.8014 (3.7173) grad_norm: 1.0089 (inf) time: 0.5027 [2021-03-25 13:04:22 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 350/1251] eta: 0:07:46 lr: 0.000922 loss: 3.9182 (3.7237) grad_norm: 0.9929 (inf) time: 0.5026 [2021-03-25 13:04:27 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 360/1251] eta: 0:07:40 lr: 0.000922 loss: 3.7854 (3.7211) grad_norm: 1.0352 (inf) time: 0.5033 [2021-03-25 13:04:32 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 370/1251] eta: 0:07:35 lr: 0.000922 loss: 3.7747 (3.7210) grad_norm: 1.0203 (inf) time: 0.5040 [2021-03-25 13:04:37 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 380/1251] eta: 0:07:30 lr: 0.000922 loss: 3.7141 (3.7161) grad_norm: 0.9891 (inf) time: 0.5089 [2021-03-25 13:04:42 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 390/1251] eta: 0:07:24 lr: 0.000922 loss: 3.5139 (3.7165) grad_norm: 0.9858 (inf) time: 0.5068 [2021-03-25 13:04:47 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 400/1251] eta: 0:07:19 lr: 0.000922 loss: 3.7145 (3.7161) grad_norm: 1.0207 (inf) time: 0.5028 [2021-03-25 13:04:52 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 410/1251] eta: 0:07:13 lr: 0.000922 loss: 3.7283 (3.7154) grad_norm: 1.0054 (inf) time: 0.5052 [2021-03-25 13:04:57 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 420/1251] eta: 0:07:08 lr: 0.000922 loss: 3.7283 (3.7122) grad_norm: 0.9936 (inf) time: 0.5068 [2021-03-25 13:05:02 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 430/1251] eta: 0:07:03 lr: 0.000922 loss: 3.8998 (3.7178) grad_norm: 0.9727 (inf) time: 0.5071 [2021-03-25 13:05:07 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 440/1251] eta: 0:06:57 lr: 0.000922 loss: 3.6437 (3.7109) grad_norm: 1.0274 (inf) time: 0.5040 [2021-03-25 13:05:12 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 450/1251] eta: 0:06:52 lr: 0.000922 loss: 3.6437 (3.7138) grad_norm: 1.0355 (inf) time: 0.4993 [2021-03-25 13:05:18 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 460/1251] eta: 0:06:47 lr: 0.000922 loss: 3.8953 (3.7143) grad_norm: 1.0099 (inf) time: 0.5082 [2021-03-25 13:05:23 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 470/1251] eta: 0:06:41 lr: 0.000922 loss: 3.7499 (3.7118) grad_norm: 1.0010 (inf) time: 0.5093 [2021-03-25 13:05:28 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 480/1251] eta: 0:06:36 lr: 0.000922 loss: 3.7054 (3.7173) grad_norm: 1.0010 (inf) time: 0.4998 [2021-03-25 13:05:33 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 490/1251] eta: 0:06:31 lr: 0.000922 loss: 3.6173 (3.7157) grad_norm: 1.0443 (inf) time: 0.5054 [2021-03-25 13:05:38 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 500/1251] eta: 0:06:26 lr: 0.000922 loss: 3.4728 (3.7125) grad_norm: 1.0443 (inf) time: 0.5083 [2021-03-25 13:05:43 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 510/1251] eta: 0:06:20 lr: 0.000922 loss: 3.7719 (3.7130) grad_norm: 0.9977 (inf) time: 0.5044 [2021-03-25 13:05:48 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 520/1251] eta: 0:06:15 lr: 0.000922 loss: 3.8410 (3.7126) grad_norm: 0.9389 (inf) time: 0.5054 [2021-03-25 13:05:53 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 530/1251] eta: 0:06:10 lr: 0.000922 loss: 3.5967 (3.7072) grad_norm: 0.9640 (inf) time: 0.5060 [2021-03-25 13:05:58 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 540/1251] eta: 0:06:04 lr: 0.000922 loss: 3.6087 (3.7073) grad_norm: 0.9805 (inf) time: 0.5018 [2021-03-25 13:06:03 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 550/1251] eta: 0:05:59 lr: 0.000922 loss: 3.9011 (3.7138) grad_norm: 0.9805 (inf) time: 0.5129 [2021-03-25 13:06:08 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 560/1251] eta: 0:05:54 lr: 0.000922 loss: 3.9353 (3.7166) grad_norm: 1.0318 (inf) time: 0.5155 [2021-03-25 13:06:13 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 570/1251] eta: 0:05:49 lr: 0.000922 loss: 3.4666 (3.7092) grad_norm: 1.0414 (inf) time: 0.5088 [2021-03-25 13:06:18 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 580/1251] eta: 0:05:44 lr: 0.000922 loss: 3.5709 (3.7167) grad_norm: 1.0244 (inf) time: 0.5117 [2021-03-25 13:06:24 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 590/1251] eta: 0:05:39 lr: 0.000922 loss: 3.8989 (3.7152) grad_norm: 1.0597 (inf) time: 0.5136 [2021-03-25 13:06:29 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 600/1251] eta: 0:05:34 lr: 0.000922 loss: 3.6654 (3.7162) grad_norm: 1.0451 (inf) time: 0.5109 [2021-03-25 13:06:34 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 610/1251] eta: 0:05:28 lr: 0.000922 loss: 3.7065 (3.7138) grad_norm: 1.0409 (inf) time: 0.5078 [2021-03-25 13:06:39 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 620/1251] eta: 0:05:23 lr: 0.000922 loss: 3.8533 (3.7184) grad_norm: 1.0206 (inf) time: 0.5061 [2021-03-25 13:06:44 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 630/1251] eta: 0:05:18 lr: 0.000922 loss: 4.0033 (3.7249) grad_norm: 1.0137 (inf) time: 0.5077 [2021-03-25 13:06:49 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 640/1251] eta: 0:05:13 lr: 0.000922 loss: 3.9020 (3.7232) grad_norm: 1.0291 (inf) time: 0.5072 [2021-03-25 13:06:54 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 650/1251] eta: 0:05:08 lr: 0.000921 loss: 3.7037 (3.7242) grad_norm: 1.0554 (inf) time: 0.5021 [2021-03-25 13:06:59 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 660/1251] eta: 0:05:02 lr: 0.000921 loss: 3.8336 (3.7245) grad_norm: 1.0548 (inf) time: 0.5057 [2021-03-25 13:07:04 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 670/1251] eta: 0:04:57 lr: 0.000921 loss: 3.9151 (3.7275) grad_norm: 1.0414 (inf) time: 0.5071 [2021-03-25 13:07:09 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 680/1251] eta: 0:04:52 lr: 0.000921 loss: 3.8243 (3.7278) grad_norm: 0.9813 (inf) time: 0.5133 [2021-03-25 13:07:14 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 690/1251] eta: 0:04:47 lr: 0.000921 loss: 3.8491 (3.7288) grad_norm: 0.9813 (inf) time: 0.5151 [2021-03-25 13:07:19 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 700/1251] eta: 0:04:42 lr: 0.000921 loss: 3.9501 (3.7297) grad_norm: 0.9850 (inf) time: 0.5087 [2021-03-25 13:07:24 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 710/1251] eta: 0:04:37 lr: 0.000921 loss: 3.9178 (3.7304) grad_norm: 0.9776 (inf) time: 0.5060 [2021-03-25 13:07:30 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 720/1251] eta: 0:04:32 lr: 0.000921 loss: 3.8049 (3.7305) grad_norm: 1.0095 (inf) time: 0.5081 [2021-03-25 13:07:35 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 730/1251] eta: 0:04:26 lr: 0.000921 loss: 3.5948 (3.7265) grad_norm: 1.0187 (inf) time: 0.5108 [2021-03-25 13:07:40 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 740/1251] eta: 0:04:21 lr: 0.000921 loss: 3.5604 (3.7250) grad_norm: 1.0285 (inf) time: 0.5240 [2021-03-25 13:07:45 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 750/1251] eta: 0:04:16 lr: 0.000921 loss: 4.1518 (3.7289) grad_norm: 1.0312 (inf) time: 0.5255 [2021-03-25 13:07:50 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 760/1251] eta: 0:04:11 lr: 0.000921 loss: 4.0479 (3.7311) grad_norm: 1.0164 (inf) time: 0.5039 [2021-03-25 13:07:55 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 770/1251] eta: 0:04:06 lr: 0.000921 loss: 4.0079 (3.7325) grad_norm: 1.0025 (inf) time: 0.5028 [2021-03-25 13:08:00 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 780/1251] eta: 0:04:01 lr: 0.000921 loss: 3.9833 (3.7347) grad_norm: 1.0364 (inf) time: 0.5119 [2021-03-25 13:08:05 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 790/1251] eta: 0:03:56 lr: 0.000921 loss: 3.9099 (3.7360) grad_norm: 1.0634 (inf) time: 0.5048 [2021-03-25 13:08:10 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 800/1251] eta: 0:03:50 lr: 0.000921 loss: 3.9099 (3.7374) grad_norm: 0.9966 (inf) time: 0.5014 [2021-03-25 13:08:16 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 810/1251] eta: 0:03:45 lr: 0.000921 loss: 4.0259 (3.7404) grad_norm: 1.0036 (inf) time: 0.5125 [2021-03-25 13:08:21 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 820/1251] eta: 0:03:40 lr: 0.000921 loss: 3.9513 (3.7424) grad_norm: 1.0358 (inf) time: 0.5112 [2021-03-25 13:08:26 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 830/1251] eta: 0:03:35 lr: 0.000921 loss: 3.8572 (3.7423) grad_norm: 1.0122 (inf) time: 0.5048 [2021-03-25 13:08:31 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 840/1251] eta: 0:03:30 lr: 0.000921 loss: 3.6651 (3.7398) grad_norm: 0.9780 (inf) time: 0.5025 [2021-03-25 13:08:36 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 850/1251] eta: 0:03:25 lr: 0.000921 loss: 3.8753 (3.7422) grad_norm: 0.9954 (inf) time: 0.5028 [2021-03-25 13:08:41 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 860/1251] eta: 0:03:20 lr: 0.000921 loss: 3.9124 (3.7421) grad_norm: 0.9823 (inf) time: 0.5046 [2021-03-25 13:08:46 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 870/1251] eta: 0:03:14 lr: 0.000921 loss: 3.6315 (3.7404) grad_norm: 0.9933 (inf) time: 0.5072 [2021-03-25 13:08:51 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 880/1251] eta: 0:03:09 lr: 0.000921 loss: 3.7831 (3.7443) grad_norm: 1.0024 (inf) time: 0.5096 [2021-03-25 13:08:56 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 890/1251] eta: 0:03:04 lr: 0.000921 loss: 4.2132 (3.7497) grad_norm: 0.9986 (inf) time: 0.5038 [2021-03-25 13:09:01 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 900/1251] eta: 0:02:59 lr: 0.000921 loss: 4.0467 (3.7474) grad_norm: 0.9717 (inf) time: 0.5035 [2021-03-25 13:09:06 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 910/1251] eta: 0:02:54 lr: 0.000921 loss: 3.9859 (3.7503) grad_norm: 0.9863 (inf) time: 0.5072 [2021-03-25 13:09:11 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 920/1251] eta: 0:02:49 lr: 0.000921 loss: 3.9680 (3.7490) grad_norm: 0.9863 (inf) time: 0.5044 [2021-03-25 13:09:16 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 930/1251] eta: 0:02:44 lr: 0.000921 loss: 3.8039 (3.7477) grad_norm: 0.9643 (inf) time: 0.5069 [2021-03-25 13:09:21 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 940/1251] eta: 0:02:39 lr: 0.000921 loss: 3.9136 (3.7488) grad_norm: 0.9760 (inf) time: 0.5122 [2021-03-25 13:09:26 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 950/1251] eta: 0:02:33 lr: 0.000921 loss: 3.9289 (3.7466) grad_norm: 0.9760 (inf) time: 0.5090 [2021-03-25 13:09:32 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 960/1251] eta: 0:02:28 lr: 0.000921 loss: 3.6956 (3.7444) grad_norm: 0.9677 (inf) time: 0.5069 [2021-03-25 13:09:37 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 970/1251] eta: 0:02:23 lr: 0.000921 loss: 3.7744 (3.7434) grad_norm: 0.9546 (inf) time: 0.5082 [2021-03-25 13:09:42 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 980/1251] eta: 0:02:18 lr: 0.000921 loss: 3.9310 (3.7448) grad_norm: 0.9729 (inf) time: 0.5048 [2021-03-25 13:09:47 swin_small_patch4_window7_224] INFO: Epoch: [54] [ 990/1251] eta: 0:02:13 lr: 0.000921 loss: 3.9455 (3.7469) grad_norm: 0.9866 (inf) time: 0.5029 [2021-03-25 13:09:52 swin_small_patch4_window7_224] INFO: Epoch: [54] [1000/1251] eta: 0:02:08 lr: 0.000921 loss: 3.9455 (3.7470) grad_norm: 1.0055 (inf) time: 0.5043 [2021-03-25 13:09:57 swin_small_patch4_window7_224] INFO: Epoch: [54] [1010/1251] eta: 0:02:03 lr: 0.000921 loss: 3.7454 (3.7488) grad_norm: 1.0055 (inf) time: 0.5087 [2021-03-25 13:10:02 swin_small_patch4_window7_224] INFO: Epoch: [54] [1020/1251] eta: 0:01:58 lr: 0.000921 loss: 3.9744 (3.7492) grad_norm: 1.0152 (inf) time: 0.5132 [2021-03-25 13:10:07 swin_small_patch4_window7_224] INFO: Epoch: [54] [1030/1251] eta: 0:01:52 lr: 0.000921 loss: 3.7961 (3.7484) grad_norm: 1.0503 (inf) time: 0.5079 [2021-03-25 13:10:12 swin_small_patch4_window7_224] INFO: Epoch: [54] [1040/1251] eta: 0:01:47 lr: 0.000921 loss: 3.8330 (3.7492) grad_norm: 1.0503 (inf) time: 0.5040 [2021-03-25 13:10:17 swin_small_patch4_window7_224] INFO: Epoch: [54] [1050/1251] eta: 0:01:42 lr: 0.000921 loss: 3.7914 (3.7480) grad_norm: 1.0485 (inf) time: 0.5115 [2021-03-25 13:10:22 swin_small_patch4_window7_224] INFO: Epoch: [54] [1060/1251] eta: 0:01:37 lr: 0.000921 loss: 3.6659 (3.7468) grad_norm: 1.0502 (inf) time: 0.5104 [2021-03-25 13:10:27 swin_small_patch4_window7_224] INFO: Epoch: [54] [1070/1251] eta: 0:01:32 lr: 0.000921 loss: 3.8612 (3.7489) grad_norm: 1.0621 (inf) time: 0.5023 [2021-03-25 13:10:32 swin_small_patch4_window7_224] INFO: Epoch: [54] [1080/1251] eta: 0:01:27 lr: 0.000921 loss: 3.9065 (3.7482) grad_norm: 1.0621 (inf) time: 0.5005 [2021-03-25 13:10:37 swin_small_patch4_window7_224] INFO: Epoch: [54] [1090/1251] eta: 0:01:22 lr: 0.000921 loss: 3.8853 (3.7481) grad_norm: 1.0705 (inf) time: 0.5021 [2021-03-25 13:10:42 swin_small_patch4_window7_224] INFO: Epoch: [54] [1100/1251] eta: 0:01:17 lr: 0.000920 loss: 3.9290 (3.7489) grad_norm: 0.9706 (inf) time: 0.5043 [2021-03-25 13:10:47 swin_small_patch4_window7_224] INFO: Epoch: [54] [1110/1251] eta: 0:01:11 lr: 0.000920 loss: 4.0061 (3.7497) grad_norm: 0.9311 (inf) time: 0.5010 [2021-03-25 13:10:52 swin_small_patch4_window7_224] INFO: Epoch: [54] [1120/1251] eta: 0:01:06 lr: 0.000920 loss: 3.9633 (3.7497) grad_norm: 0.9544 (inf) time: 0.4996 [2021-03-25 13:10:57 swin_small_patch4_window7_224] INFO: Epoch: [54] [1130/1251] eta: 0:01:01 lr: 0.000920 loss: 3.5823 (3.7464) grad_norm: 0.9544 (inf) time: 0.5034 [2021-03-25 13:11:03 swin_small_patch4_window7_224] INFO: Epoch: [54] [1140/1251] eta: 0:00:56 lr: 0.000920 loss: 3.5415 (3.7450) grad_norm: 0.9770 (inf) time: 0.5043 [2021-03-25 13:11:08 swin_small_patch4_window7_224] INFO: Epoch: [54] [1150/1251] eta: 0:00:51 lr: 0.000920 loss: 3.4264 (3.7428) grad_norm: 1.0334 (inf) time: 0.5053 [2021-03-25 13:11:13 swin_small_patch4_window7_224] INFO: Epoch: [54] [1160/1251] eta: 0:00:46 lr: 0.000920 loss: 3.8660 (3.7435) grad_norm: 1.0334 (inf) time: 0.5065 [2021-03-25 13:11:18 swin_small_patch4_window7_224] INFO: Epoch: [54] [1170/1251] eta: 0:00:41 lr: 0.000920 loss: 4.0698 (3.7468) grad_norm: 1.0063 (inf) time: 0.5058 [2021-03-25 13:11:23 swin_small_patch4_window7_224] INFO: Epoch: [54] [1180/1251] eta: 0:00:36 lr: 0.000920 loss: 3.9372 (3.7445) grad_norm: 1.0121 (inf) time: 0.5039 [2021-03-25 13:11:28 swin_small_patch4_window7_224] INFO: Epoch: [54] [1190/1251] eta: 0:00:31 lr: 0.000920 loss: 3.6216 (3.7446) grad_norm: 0.9805 (inf) time: 0.5052 [2021-03-25 13:11:33 swin_small_patch4_window7_224] INFO: Epoch: [54] [1200/1251] eta: 0:00:26 lr: 0.000920 loss: 3.8225 (3.7452) grad_norm: 0.9537 (inf) time: 0.5120 [2021-03-25 13:11:38 swin_small_patch4_window7_224] INFO: Epoch: [54] [1210/1251] eta: 0:00:20 lr: 0.000920 loss: 3.5956 (3.7420) grad_norm: 1.0248 (inf) time: 0.5116 [2021-03-25 13:11:43 swin_small_patch4_window7_224] INFO: Epoch: [54] [1220/1251] eta: 0:00:15 lr: 0.000920 loss: 3.4200 (3.7408) grad_norm: 0.9881 (inf) time: 0.5081 [2021-03-25 13:11:48 swin_small_patch4_window7_224] INFO: Epoch: [54] [1230/1251] eta: 0:00:10 lr: 0.000920 loss: 3.6862 (3.7403) grad_norm: 0.9578 (inf) time: 0.5034 [2021-03-25 13:11:53 swin_small_patch4_window7_224] INFO: Epoch: [54] [1240/1251] eta: 0:00:05 lr: 0.000920 loss: 3.8940 (3.7403) grad_norm: 0.9677 (inf) time: 0.5043 [2021-03-25 13:11:58 swin_small_patch4_window7_224] INFO: Epoch: [54] [1250/1251] eta: 0:00:00 lr: 0.000920 loss: 3.9741 (3.7409) grad_norm: 0.9677 (inf) time: 0.5040 [2021-03-25 13:12:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:35 loss: 0.9550 (0.9550) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-25 13:12:07 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 1.2750 (1.2154) acc1: 70.3125 (70.5966) acc5: 93.7500 (91.9034) [2021-03-25 13:12:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 1.2223 (1.2024) acc1: 70.3125 (71.2054) acc5: 90.6250 (92.3363) [2021-03-25 13:12:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1762 (1.2035) acc1: 71.8750 (71.6230) acc5: 92.1875 (91.9859) [2021-03-25 13:12:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1526 (1.1975) acc1: 71.8750 (71.6845) acc5: 92.1875 (92.0732) [2021-03-25 13:12:14 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1324 (1.1851) acc1: 70.3125 (72.1280) acc5: 92.1875 (92.0640) [2021-03-25 13:12:16 swin_small_patch4_window7_224] INFO: * Acc@1 73.012 Acc@5 91.956 loss 1.156 [2021-03-25 13:12:16 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.0% [2021-03-25 13:12:16 swin_small_patch4_window7_224] INFO: Max accuracy: 73.01% [2021-03-25 13:12:20 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 0/1251] eta: 1:30:42 lr: 0.000920 loss: 3.6245 (3.6245) grad_norm: 0.8515 (0.8515) time: 4.3501 [2021-03-25 13:12:25 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 10/1251] eta: 0:17:48 lr: 0.000920 loss: 3.8019 (3.6492) grad_norm: 0.9772 (0.9664) time: 0.8609 [2021-03-25 13:12:30 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 20/1251] eta: 0:14:09 lr: 0.000920 loss: 3.8019 (3.6805) grad_norm: 1.0025 (1.0142) time: 0.5069 [2021-03-25 13:12:35 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 30/1251] eta: 0:12:50 lr: 0.000920 loss: 3.8532 (3.7522) grad_norm: 1.0160 (1.0108) time: 0.5045 [2021-03-25 13:12:41 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 40/1251] eta: 0:12:09 lr: 0.000920 loss: 3.7336 (3.7042) grad_norm: 1.0392 (1.0180) time: 0.5104 [2021-03-25 13:12:46 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 50/1251] eta: 0:11:42 lr: 0.000920 loss: 3.6469 (3.6763) grad_norm: 1.0367 (1.0198) time: 0.5144 [2021-03-25 13:12:51 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 60/1251] eta: 0:11:22 lr: 0.000920 loss: 3.5481 (3.6460) grad_norm: 1.0139 (1.0161) time: 0.5128 [2021-03-25 13:12:56 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 70/1251] eta: 0:11:04 lr: 0.000920 loss: 3.5857 (3.6312) grad_norm: 1.0176 (1.0321) time: 0.5048 [2021-03-25 13:13:01 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 80/1251] eta: 0:10:51 lr: 0.000920 loss: 3.6923 (3.6418) grad_norm: 1.0664 (1.0366) time: 0.5063 [2021-03-25 13:13:06 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 90/1251] eta: 0:10:39 lr: 0.000920 loss: 3.7916 (3.6702) grad_norm: 1.0593 (1.0436) time: 0.5106 [2021-03-25 13:13:11 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 100/1251] eta: 0:10:29 lr: 0.000920 loss: 3.8405 (3.6515) grad_norm: 1.0200 (1.0388) time: 0.5065 [2021-03-25 13:13:16 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 110/1251] eta: 0:10:21 lr: 0.000920 loss: 3.6210 (3.6463) grad_norm: 0.9636 (1.0383) time: 0.5137 [2021-03-25 13:13:21 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 120/1251] eta: 0:10:11 lr: 0.000920 loss: 3.7571 (3.6591) grad_norm: 1.0004 (1.0354) time: 0.5106 [2021-03-25 13:13:26 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 130/1251] eta: 0:10:03 lr: 0.000920 loss: 4.0157 (3.6758) grad_norm: 1.0004 (1.0358) time: 0.5048 [2021-03-25 13:13:32 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 140/1251] eta: 0:09:56 lr: 0.000920 loss: 4.0158 (3.6959) grad_norm: 1.0207 (1.0367) time: 0.5125 [2021-03-25 13:13:37 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 150/1251] eta: 0:09:48 lr: 0.000920 loss: 3.9351 (3.6836) grad_norm: 1.0528 (1.0389) time: 0.5090 [2021-03-25 13:13:42 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 160/1251] eta: 0:09:41 lr: 0.000920 loss: 3.8313 (3.6947) grad_norm: 1.0148 (1.0377) time: 0.5055 [2021-03-25 13:13:47 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 170/1251] eta: 0:09:34 lr: 0.000920 loss: 3.9652 (3.6983) grad_norm: 0.9854 (1.0394) time: 0.5084 [2021-03-25 13:13:52 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 180/1251] eta: 0:09:27 lr: 0.000920 loss: 3.8709 (3.7035) grad_norm: 1.0035 (1.0375) time: 0.5101 [2021-03-25 13:13:57 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 190/1251] eta: 0:09:20 lr: 0.000920 loss: 3.8709 (3.7058) grad_norm: 1.0035 (1.0376) time: 0.5046 [2021-03-25 13:14:02 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 200/1251] eta: 0:09:14 lr: 0.000920 loss: 3.9789 (3.7155) grad_norm: 1.0240 (1.0353) time: 0.5077 [2021-03-25 13:14:07 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 210/1251] eta: 0:09:08 lr: 0.000920 loss: 3.8083 (3.7082) grad_norm: 1.0240 (1.0366) time: 0.5116 [2021-03-25 13:14:12 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 220/1251] eta: 0:09:02 lr: 0.000920 loss: 3.8624 (3.7142) grad_norm: 1.0624 (1.0358) time: 0.5068 [2021-03-25 13:14:17 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 230/1251] eta: 0:08:56 lr: 0.000920 loss: 3.7142 (3.7082) grad_norm: 1.0456 (1.0366) time: 0.5067 [2021-03-25 13:14:22 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 240/1251] eta: 0:08:50 lr: 0.000920 loss: 3.3085 (3.6976) grad_norm: 1.0284 (1.0362) time: 0.5093 [2021-03-25 13:14:27 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 250/1251] eta: 0:08:44 lr: 0.000920 loss: 3.8860 (3.7113) grad_norm: 1.0390 (1.0383) time: 0.5056 [2021-03-25 13:14:32 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 260/1251] eta: 0:08:38 lr: 0.000920 loss: 3.9888 (3.7184) grad_norm: 1.0247 (1.0382) time: 0.5023 [2021-03-25 13:14:37 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 270/1251] eta: 0:08:32 lr: 0.000920 loss: 3.6749 (3.7070) grad_norm: 1.0066 (1.0367) time: 0.5041 [2021-03-25 13:14:43 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 280/1251] eta: 0:08:26 lr: 0.000920 loss: 3.4732 (3.6992) grad_norm: 0.9774 (1.0360) time: 0.5038 [2021-03-25 13:14:48 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 290/1251] eta: 0:08:20 lr: 0.000919 loss: 3.4189 (3.6905) grad_norm: 0.9699 (1.0330) time: 0.5057 [2021-03-25 13:14:53 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 300/1251] eta: 0:08:15 lr: 0.000919 loss: 3.4189 (3.6861) grad_norm: 0.9758 (1.0341) time: 0.5062 [2021-03-25 13:14:58 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 310/1251] eta: 0:08:09 lr: 0.000919 loss: 3.6068 (3.6900) grad_norm: 1.0723 (1.0379) time: 0.5048 [2021-03-25 13:15:03 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 320/1251] eta: 0:08:03 lr: 0.000919 loss: 3.5875 (3.6847) grad_norm: 1.0728 (1.0371) time: 0.5061 [2021-03-25 13:15:08 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 330/1251] eta: 0:07:58 lr: 0.000919 loss: 3.6567 (3.6871) grad_norm: 0.9627 (1.0362) time: 0.5076 [2021-03-25 13:15:13 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 340/1251] eta: 0:07:52 lr: 0.000919 loss: 3.7986 (3.6835) grad_norm: 0.9763 (1.0382) time: 0.5093 [2021-03-25 13:15:18 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 350/1251] eta: 0:07:47 lr: 0.000919 loss: 3.6251 (3.6821) grad_norm: 0.9984 (1.0382) time: 0.5121 [2021-03-25 13:15:23 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 360/1251] eta: 0:07:41 lr: 0.000919 loss: 3.8066 (3.6835) grad_norm: 0.9697 (1.0361) time: 0.5070 [2021-03-25 13:15:28 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 370/1251] eta: 0:07:36 lr: 0.000919 loss: 3.7203 (3.6851) grad_norm: 0.9656 (1.0357) time: 0.5045 [2021-03-25 13:15:33 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 380/1251] eta: 0:07:31 lr: 0.000919 loss: 3.7130 (3.6860) grad_norm: 1.0151 (1.0359) time: 0.5064 [2021-03-25 13:15:38 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 390/1251] eta: 0:07:25 lr: 0.000919 loss: 3.6718 (3.6792) grad_norm: 0.9855 (1.0334) time: 0.5063 [2021-03-25 13:15:43 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 400/1251] eta: 0:07:20 lr: 0.000919 loss: 3.6718 (3.6827) grad_norm: 0.9581 (1.0319) time: 0.5100 [2021-03-25 13:15:49 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 410/1251] eta: 0:07:14 lr: 0.000919 loss: 3.8789 (3.6906) grad_norm: 0.9921 (1.0320) time: 0.5089 [2021-03-25 13:15:54 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 420/1251] eta: 0:07:09 lr: 0.000919 loss: 3.9715 (3.6936) grad_norm: 1.0342 (1.0320) time: 0.5029 [2021-03-25 13:15:58 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 430/1251] eta: 0:07:03 lr: 0.000919 loss: 3.8800 (3.6910) grad_norm: 1.0518 (1.0351) time: 0.4984 [2021-03-25 13:16:03 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 440/1251] eta: 0:06:58 lr: 0.000919 loss: 3.7259 (3.6874) grad_norm: 1.1123 (1.0362) time: 0.4984 [2021-03-25 13:16:08 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 450/1251] eta: 0:06:52 lr: 0.000919 loss: 3.6706 (3.6855) grad_norm: 1.0212 (1.0368) time: 0.4996 [2021-03-25 13:16:13 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 460/1251] eta: 0:06:47 lr: 0.000919 loss: 3.7018 (3.6856) grad_norm: 0.9973 (1.0363) time: 0.4972 [2021-03-25 13:16:18 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 470/1251] eta: 0:06:42 lr: 0.000919 loss: 3.6902 (3.6830) grad_norm: 0.9973 (1.0357) time: 0.4980 [2021-03-25 13:16:24 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 480/1251] eta: 0:06:36 lr: 0.000919 loss: 3.7987 (3.6823) grad_norm: 1.0329 (1.0354) time: 0.5039 [2021-03-25 13:16:28 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 490/1251] eta: 0:06:31 lr: 0.000919 loss: 3.8040 (3.6821) grad_norm: 1.0173 (1.0350) time: 0.5015 [2021-03-25 13:16:34 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 500/1251] eta: 0:06:26 lr: 0.000919 loss: 3.7151 (3.6832) grad_norm: 1.0100 (1.0346) time: 0.5022 [2021-03-25 13:16:39 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 510/1251] eta: 0:06:20 lr: 0.000919 loss: 3.7151 (3.6847) grad_norm: 0.9777 (1.0338) time: 0.5053 [2021-03-25 13:16:44 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 520/1251] eta: 0:06:15 lr: 0.000919 loss: 3.7602 (3.6863) grad_norm: 0.9437 (1.0326) time: 0.5020 [2021-03-25 13:16:49 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 530/1251] eta: 0:06:10 lr: 0.000919 loss: 3.7602 (3.6872) grad_norm: 0.9697 (1.0324) time: 0.5093 [2021-03-25 13:16:54 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 540/1251] eta: 0:06:05 lr: 0.000919 loss: 3.7299 (3.6888) grad_norm: 0.9920 (1.0323) time: 0.5104 [2021-03-25 13:16:59 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 550/1251] eta: 0:06:00 lr: 0.000919 loss: 3.7617 (3.6898) grad_norm: 0.9580 (1.0325) time: 0.5222 [2021-03-25 13:17:04 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 560/1251] eta: 0:05:55 lr: 0.000919 loss: 3.8738 (3.6915) grad_norm: 0.9755 (1.0320) time: 0.5204 [2021-03-25 13:17:09 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 570/1251] eta: 0:05:49 lr: 0.000919 loss: 3.7283 (3.6925) grad_norm: 1.0203 (1.0330) time: 0.5047 [2021-03-25 13:17:14 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 580/1251] eta: 0:05:44 lr: 0.000919 loss: 3.7899 (3.6943) grad_norm: 1.0771 (1.0339) time: 0.5112 [2021-03-25 13:17:20 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 590/1251] eta: 0:05:39 lr: 0.000919 loss: 3.7899 (3.6940) grad_norm: 1.0584 (1.0343) time: 0.5160 [2021-03-25 13:17:25 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 600/1251] eta: 0:05:34 lr: 0.000919 loss: 3.5740 (3.6913) grad_norm: 1.0299 (1.0344) time: 0.5125 [2021-03-25 13:17:30 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 610/1251] eta: 0:05:29 lr: 0.000919 loss: 3.5274 (3.6897) grad_norm: 1.0705 (1.0357) time: 0.5064 [2021-03-25 13:17:35 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 620/1251] eta: 0:05:23 lr: 0.000919 loss: 3.7980 (3.6924) grad_norm: 1.0800 (1.0366) time: 0.5008 [2021-03-25 13:17:40 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 630/1251] eta: 0:05:18 lr: 0.000919 loss: 3.9648 (3.6958) grad_norm: 1.0885 (1.0379) time: 0.4992 [2021-03-25 13:17:45 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 640/1251] eta: 0:05:13 lr: 0.000919 loss: 3.9099 (3.6992) grad_norm: 1.0297 (1.0371) time: 0.5077 [2021-03-25 13:17:50 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 650/1251] eta: 0:05:08 lr: 0.000919 loss: 3.8785 (3.7003) grad_norm: 0.9719 (1.0368) time: 0.5125 [2021-03-25 13:17:55 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 660/1251] eta: 0:05:03 lr: 0.000919 loss: 3.8084 (3.6998) grad_norm: 0.9619 (1.0356) time: 0.5103 [2021-03-25 13:18:00 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 670/1251] eta: 0:04:58 lr: 0.000919 loss: 3.7231 (3.6947) grad_norm: 0.9809 (1.0357) time: 0.5101 [2021-03-25 13:18:05 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 680/1251] eta: 0:04:52 lr: 0.000919 loss: 3.6455 (3.6970) grad_norm: 1.0769 (1.0368) time: 0.5092 [2021-03-25 13:18:10 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 690/1251] eta: 0:04:47 lr: 0.000919 loss: 3.8027 (3.6960) grad_norm: 1.0725 (1.0378) time: 0.5090 [2021-03-25 13:18:15 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 700/1251] eta: 0:04:42 lr: 0.000919 loss: 3.6938 (3.6938) grad_norm: 1.0510 (1.0371) time: 0.5070 [2021-03-25 13:18:21 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 710/1251] eta: 0:04:37 lr: 0.000919 loss: 3.6209 (3.6927) grad_norm: 0.9551 (1.0362) time: 0.5059 [2021-03-25 13:18:26 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 720/1251] eta: 0:04:32 lr: 0.000919 loss: 3.6314 (3.6912) grad_norm: 0.9761 (1.0359) time: 0.5067 [2021-03-25 13:18:31 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 730/1251] eta: 0:04:26 lr: 0.000918 loss: 3.8405 (3.6952) grad_norm: 1.0112 (1.0363) time: 0.5054 [2021-03-25 13:18:36 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 740/1251] eta: 0:04:22 lr: 0.000918 loss: 3.9284 (3.6968) grad_norm: 1.0184 (1.0358) time: 0.5212 [2021-03-25 13:18:41 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 750/1251] eta: 0:04:16 lr: 0.000918 loss: 3.9205 (3.6957) grad_norm: 1.0184 (1.0361) time: 0.5232 [2021-03-25 13:18:46 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 760/1251] eta: 0:04:11 lr: 0.000918 loss: 3.6711 (3.6961) grad_norm: 1.0376 (1.0363) time: 0.5071 [2021-03-25 13:18:51 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 770/1251] eta: 0:04:06 lr: 0.000918 loss: 3.5165 (3.6932) grad_norm: 1.0376 (1.0364) time: 0.5109 [2021-03-25 13:18:57 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 780/1251] eta: 0:04:01 lr: 0.000918 loss: 3.5165 (3.6908) grad_norm: 0.9683 (1.0356) time: 0.5191 [2021-03-25 13:19:02 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 790/1251] eta: 0:03:56 lr: 0.000918 loss: 3.6224 (3.6908) grad_norm: 0.9538 (1.0354) time: 0.5136 [2021-03-25 13:19:07 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 800/1251] eta: 0:03:51 lr: 0.000918 loss: 3.5075 (3.6889) grad_norm: 0.9891 (1.0349) time: 0.5081 [2021-03-25 13:19:12 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 810/1251] eta: 0:03:46 lr: 0.000918 loss: 3.8294 (3.6904) grad_norm: 1.0054 (1.0355) time: 0.5040 [2021-03-25 13:19:17 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 820/1251] eta: 0:03:40 lr: 0.000918 loss: 3.7464 (3.6882) grad_norm: 1.0681 (1.0359) time: 0.5012 [2021-03-25 13:19:22 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 830/1251] eta: 0:03:35 lr: 0.000918 loss: 3.5763 (3.6865) grad_norm: 1.0271 (1.0357) time: 0.5108 [2021-03-25 13:19:27 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 840/1251] eta: 0:03:30 lr: 0.000918 loss: 3.6412 (3.6850) grad_norm: 0.9801 (1.0352) time: 0.5097 [2021-03-25 13:19:32 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 850/1251] eta: 0:03:25 lr: 0.000918 loss: 3.6844 (3.6833) grad_norm: 1.0053 (1.0354) time: 0.5011 [2021-03-25 13:19:37 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 860/1251] eta: 0:03:20 lr: 0.000918 loss: 3.6980 (3.6845) grad_norm: 1.0298 (1.0355) time: 0.5034 [2021-03-25 13:19:42 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 870/1251] eta: 0:03:15 lr: 0.000918 loss: 3.8084 (3.6834) grad_norm: 0.9994 (1.0351) time: 0.5061 [2021-03-25 13:19:47 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 880/1251] eta: 0:03:10 lr: 0.000918 loss: 3.8084 (3.6866) grad_norm: 0.9994 (1.0350) time: 0.5139 [2021-03-25 13:19:52 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 890/1251] eta: 0:03:04 lr: 0.000918 loss: 3.9442 (3.6867) grad_norm: 1.0208 (1.0354) time: 0.5162 [2021-03-25 13:19:57 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 900/1251] eta: 0:02:59 lr: 0.000918 loss: 3.8413 (3.6881) grad_norm: 0.9953 (1.0354) time: 0.5100 [2021-03-25 13:20:02 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 910/1251] eta: 0:02:54 lr: 0.000918 loss: 3.7487 (3.6896) grad_norm: 1.0178 (1.0357) time: 0.5051 [2021-03-25 13:20:08 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 920/1251] eta: 0:02:49 lr: 0.000918 loss: 3.6108 (3.6868) grad_norm: 1.0178 (1.0353) time: 0.5022 [2021-03-25 13:20:13 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 930/1251] eta: 0:02:44 lr: 0.000918 loss: 3.6794 (3.6896) grad_norm: 1.0100 (1.0355) time: 0.5078 [2021-03-25 13:20:18 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 940/1251] eta: 0:02:39 lr: 0.000918 loss: 4.0403 (3.6925) grad_norm: 0.9860 (1.0349) time: 0.5135 [2021-03-25 13:20:23 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 950/1251] eta: 0:02:34 lr: 0.000918 loss: 3.9428 (3.6930) grad_norm: 0.9737 (1.0348) time: 0.5104 [2021-03-25 13:20:28 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 960/1251] eta: 0:02:28 lr: 0.000918 loss: 3.9659 (3.6965) grad_norm: 1.0346 (1.0349) time: 0.5054 [2021-03-25 13:20:33 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 970/1251] eta: 0:02:23 lr: 0.000918 loss: 3.8162 (3.6957) grad_norm: 1.0339 (1.0350) time: 0.5021 [2021-03-25 13:20:38 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 980/1251] eta: 0:02:18 lr: 0.000918 loss: 3.7085 (3.6937) grad_norm: 1.0202 (1.0352) time: 0.5015 [2021-03-25 13:20:43 swin_small_patch4_window7_224] INFO: Epoch: [55] [ 990/1251] eta: 0:02:13 lr: 0.000918 loss: 3.8919 (3.6957) grad_norm: 1.0618 (1.0360) time: 0.4999 [2021-03-25 13:20:48 swin_small_patch4_window7_224] INFO: Epoch: [55] [1000/1251] eta: 0:02:08 lr: 0.000918 loss: 3.9240 (3.6976) grad_norm: 1.0174 (1.0354) time: 0.5021 [2021-03-25 13:20:53 swin_small_patch4_window7_224] INFO: Epoch: [55] [1010/1251] eta: 0:02:03 lr: 0.000918 loss: 3.7405 (3.6952) grad_norm: 0.9710 (1.0352) time: 0.5082 [2021-03-25 13:20:58 swin_small_patch4_window7_224] INFO: Epoch: [55] [1020/1251] eta: 0:01:58 lr: 0.000918 loss: 3.4623 (3.6943) grad_norm: 0.9710 (1.0350) time: 0.5064 [2021-03-25 13:21:03 swin_small_patch4_window7_224] INFO: Epoch: [55] [1030/1251] eta: 0:01:52 lr: 0.000918 loss: 3.8514 (3.6949) grad_norm: 0.9702 (1.0346) time: 0.5021 [2021-03-25 13:21:08 swin_small_patch4_window7_224] INFO: Epoch: [55] [1040/1251] eta: 0:01:47 lr: 0.000918 loss: 3.9148 (3.6958) grad_norm: 1.0346 (1.0352) time: 0.5034 [2021-03-25 13:21:13 swin_small_patch4_window7_224] INFO: Epoch: [55] [1050/1251] eta: 0:01:42 lr: 0.000918 loss: 3.7325 (3.6946) grad_norm: 1.0748 (1.0356) time: 0.5058 [2021-03-25 13:21:18 swin_small_patch4_window7_224] INFO: Epoch: [55] [1060/1251] eta: 0:01:37 lr: 0.000918 loss: 3.6921 (3.6947) grad_norm: 0.9855 (1.0351) time: 0.5049 [2021-03-25 13:21:23 swin_small_patch4_window7_224] INFO: Epoch: [55] [1070/1251] eta: 0:01:32 lr: 0.000918 loss: 3.5355 (3.6894) grad_norm: 0.9622 (1.0354) time: 0.5098 [2021-03-25 13:21:28 swin_small_patch4_window7_224] INFO: Epoch: [55] [1080/1251] eta: 0:01:27 lr: 0.000918 loss: 3.2687 (3.6897) grad_norm: 1.0038 (1.0356) time: 0.5094 [2021-03-25 13:21:34 swin_small_patch4_window7_224] INFO: Epoch: [55] [1090/1251] eta: 0:01:22 lr: 0.000918 loss: 3.9088 (3.6904) grad_norm: 1.0190 (1.0358) time: 0.5054 [2021-03-25 13:21:39 swin_small_patch4_window7_224] INFO: Epoch: [55] [1100/1251] eta: 0:01:17 lr: 0.000918 loss: 3.7560 (3.6908) grad_norm: 1.0650 (1.0363) time: 0.5031 [2021-03-25 13:21:44 swin_small_patch4_window7_224] INFO: Epoch: [55] [1110/1251] eta: 0:01:12 lr: 0.000918 loss: 3.7940 (3.6919) grad_norm: 1.0650 (1.0361) time: 0.5015 [2021-03-25 13:21:49 swin_small_patch4_window7_224] INFO: Epoch: [55] [1120/1251] eta: 0:01:06 lr: 0.000918 loss: 3.8465 (3.6915) grad_norm: 1.0043 (1.0359) time: 0.5071 [2021-03-25 13:21:54 swin_small_patch4_window7_224] INFO: Epoch: [55] [1130/1251] eta: 0:01:01 lr: 0.000918 loss: 3.9649 (3.6938) grad_norm: 1.0070 (1.0358) time: 0.5078 [2021-03-25 13:21:59 swin_small_patch4_window7_224] INFO: Epoch: [55] [1140/1251] eta: 0:00:56 lr: 0.000918 loss: 3.9734 (3.6941) grad_norm: 0.9598 (1.0354) time: 0.5074 [2021-03-25 13:22:04 swin_small_patch4_window7_224] INFO: Epoch: [55] [1150/1251] eta: 0:00:51 lr: 0.000918 loss: 3.7721 (3.6943) grad_norm: 1.0294 (1.0354) time: 0.5086 [2021-03-25 13:22:09 swin_small_patch4_window7_224] INFO: Epoch: [55] [1160/1251] eta: 0:00:46 lr: 0.000918 loss: 3.7128 (3.6924) grad_norm: 1.0445 (1.0358) time: 0.5055 [2021-03-25 13:22:14 swin_small_patch4_window7_224] INFO: Epoch: [55] [1170/1251] eta: 0:00:41 lr: 0.000917 loss: 3.6819 (3.6923) grad_norm: 1.0122 (1.0354) time: 0.5057 [2021-03-25 13:22:19 swin_small_patch4_window7_224] INFO: Epoch: [55] [1180/1251] eta: 0:00:36 lr: 0.000917 loss: 3.6521 (3.6901) grad_norm: 0.9977 (1.0351) time: 0.5020 [2021-03-25 13:22:24 swin_small_patch4_window7_224] INFO: Epoch: [55] [1190/1251] eta: 0:00:31 lr: 0.000917 loss: 3.5406 (3.6887) grad_norm: 0.9604 (1.0344) time: 0.4993 [2021-03-25 13:22:29 swin_small_patch4_window7_224] INFO: Epoch: [55] [1200/1251] eta: 0:00:26 lr: 0.000917 loss: 3.2859 (3.6857) grad_norm: 0.9391 (1.0339) time: 0.5014 [2021-03-25 13:22:34 swin_small_patch4_window7_224] INFO: Epoch: [55] [1210/1251] eta: 0:00:20 lr: 0.000917 loss: 3.8231 (3.6870) grad_norm: 0.9814 (1.0343) time: 0.5042 [2021-03-25 13:22:39 swin_small_patch4_window7_224] INFO: Epoch: [55] [1220/1251] eta: 0:00:15 lr: 0.000917 loss: 3.8231 (3.6850) grad_norm: 1.0382 (1.0341) time: 0.5052 [2021-03-25 13:22:44 swin_small_patch4_window7_224] INFO: Epoch: [55] [1230/1251] eta: 0:00:10 lr: 0.000917 loss: 3.5740 (3.6835) grad_norm: 0.9486 (1.0339) time: 0.5040 [2021-03-25 13:22:49 swin_small_patch4_window7_224] INFO: Epoch: [55] [1240/1251] eta: 0:00:05 lr: 0.000917 loss: 3.6029 (3.6829) grad_norm: 0.9437 (1.0335) time: 0.5061 [2021-03-25 13:22:54 swin_small_patch4_window7_224] INFO: Epoch: [55] [1250/1251] eta: 0:00:00 lr: 0.000917 loss: 3.6936 (3.6830) grad_norm: 1.0242 (1.0339) time: 0.5051 [2021-03-25 13:23:29 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 1.1073 (1.1073) acc1: 64.0625 (64.0625) acc5: 92.1875 (92.1875) [2021-03-25 13:23:30 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.1456 (1.1387) acc1: 71.8750 (71.1648) acc5: 93.7500 (92.8977) [2021-03-25 13:23:31 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.1448 (1.1319) acc1: 71.8750 (72.6190) acc5: 92.1875 (92.3363) [2021-03-25 13:23:32 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.1428 (1.1375) acc1: 71.8750 (72.5302) acc5: 92.1875 (92.0867) [2021-03-25 13:23:33 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2026 (1.1566) acc1: 70.3125 (72.1418) acc5: 90.6250 (91.8445) [2021-03-25 13:23:34 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.2026 (1.1604) acc1: 70.3125 (72.1920) acc5: 90.6250 (91.5840) [2021-03-25 13:23:37 swin_small_patch4_window7_224] INFO: * Acc@1 73.014 Acc@5 91.932 loss 1.140 [2021-03-25 13:23:37 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.0% [2021-03-25 13:23:37 swin_small_patch4_window7_224] INFO: Max accuracy: 73.01% [2021-03-25 13:23:41 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 0/1251] eta: 1:29:08 lr: 0.000917 loss: 3.5356 (3.5356) grad_norm: 0.9191 (0.9191) time: 4.2753 [2021-03-25 13:23:46 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 10/1251] eta: 0:18:06 lr: 0.000917 loss: 3.5122 (3.4315) grad_norm: 1.0653 (1.0283) time: 0.8758 [2021-03-25 13:23:51 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 20/1251] eta: 0:14:15 lr: 0.000917 loss: 3.8514 (3.7551) grad_norm: 1.0088 (1.0013) time: 0.5160 [2021-03-25 13:23:57 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 30/1251] eta: 0:13:01 lr: 0.000917 loss: 3.9307 (3.7150) grad_norm: 0.9500 (0.9985) time: 0.5107 [2021-03-25 13:24:02 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 40/1251] eta: 0:12:14 lr: 0.000917 loss: 3.7171 (3.6709) grad_norm: 0.9507 (0.9883) time: 0.5128 [2021-03-25 13:24:07 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 50/1251] eta: 0:11:46 lr: 0.000917 loss: 3.6242 (3.6376) grad_norm: 0.9507 (0.9883) time: 0.5075 [2021-03-25 13:24:12 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 60/1251] eta: 0:11:23 lr: 0.000917 loss: 3.7026 (3.6694) grad_norm: 1.0042 (1.0087) time: 0.5086 [2021-03-25 13:24:17 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 70/1251] eta: 0:11:06 lr: 0.000917 loss: 3.8405 (3.6788) grad_norm: 1.0286 (1.0216) time: 0.5045 [2021-03-25 13:24:22 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 80/1251] eta: 0:10:53 lr: 0.000917 loss: 3.6730 (3.6618) grad_norm: 1.0659 (1.0274) time: 0.5076 [2021-03-25 13:24:27 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 90/1251] eta: 0:10:40 lr: 0.000917 loss: 3.6053 (3.6693) grad_norm: 0.9955 (inf) time: 0.5063 [2021-03-25 13:24:32 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 100/1251] eta: 0:10:30 lr: 0.000917 loss: 3.8520 (3.6898) grad_norm: 0.9663 (inf) time: 0.5059 [2021-03-25 13:24:37 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 110/1251] eta: 0:10:21 lr: 0.000917 loss: 3.9477 (3.7081) grad_norm: 0.9835 (inf) time: 0.5126 [2021-03-25 13:24:42 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 120/1251] eta: 0:10:12 lr: 0.000917 loss: 3.6952 (3.6838) grad_norm: 1.0011 (inf) time: 0.5128 [2021-03-25 13:24:47 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 130/1251] eta: 0:10:03 lr: 0.000917 loss: 3.6952 (3.6921) grad_norm: 1.0015 (inf) time: 0.5058 [2021-03-25 13:24:52 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 140/1251] eta: 0:09:56 lr: 0.000917 loss: 3.9136 (3.7020) grad_norm: 1.0175 (inf) time: 0.5053 [2021-03-25 13:24:57 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 150/1251] eta: 0:09:48 lr: 0.000917 loss: 3.9136 (3.7233) grad_norm: 0.9442 (inf) time: 0.5074 [2021-03-25 13:25:02 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 160/1251] eta: 0:09:40 lr: 0.000917 loss: 3.8100 (3.7039) grad_norm: 0.9442 (inf) time: 0.5030 [2021-03-25 13:25:08 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 170/1251] eta: 0:09:33 lr: 0.000917 loss: 3.6582 (3.6960) grad_norm: 0.9639 (inf) time: 0.5032 [2021-03-25 13:25:13 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 180/1251] eta: 0:09:27 lr: 0.000917 loss: 3.6167 (3.7025) grad_norm: 0.9726 (inf) time: 0.5087 [2021-03-25 13:25:18 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 190/1251] eta: 0:09:21 lr: 0.000917 loss: 3.8520 (3.7056) grad_norm: 0.9731 (inf) time: 0.5134 [2021-03-25 13:25:23 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 200/1251] eta: 0:09:15 lr: 0.000917 loss: 3.6504 (3.6939) grad_norm: 1.0148 (inf) time: 0.5176 [2021-03-25 13:25:28 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 210/1251] eta: 0:09:08 lr: 0.000917 loss: 3.7683 (3.6991) grad_norm: 1.0148 (inf) time: 0.5075 [2021-03-25 13:25:33 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 220/1251] eta: 0:09:02 lr: 0.000917 loss: 3.9619 (3.7004) grad_norm: 1.0199 (inf) time: 0.5037 [2021-03-25 13:25:38 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 230/1251] eta: 0:08:56 lr: 0.000917 loss: 3.8277 (3.6969) grad_norm: 1.0484 (inf) time: 0.5120 [2021-03-25 13:25:43 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 240/1251] eta: 0:08:50 lr: 0.000917 loss: 3.8277 (3.7012) grad_norm: 1.0650 (inf) time: 0.5087 [2021-03-25 13:25:48 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 250/1251] eta: 0:08:44 lr: 0.000917 loss: 3.6613 (3.6913) grad_norm: 1.0584 (inf) time: 0.5043 [2021-03-25 13:25:53 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 260/1251] eta: 0:08:38 lr: 0.000917 loss: 3.2797 (3.6856) grad_norm: 0.9909 (inf) time: 0.5040 [2021-03-25 13:25:58 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 270/1251] eta: 0:08:32 lr: 0.000917 loss: 3.6567 (3.6815) grad_norm: 0.9933 (inf) time: 0.5044 [2021-03-25 13:26:03 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 280/1251] eta: 0:08:26 lr: 0.000917 loss: 3.8162 (3.6911) grad_norm: 0.9996 (inf) time: 0.5052 [2021-03-25 13:26:08 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 290/1251] eta: 0:08:21 lr: 0.000917 loss: 3.9071 (3.6977) grad_norm: 0.9901 (inf) time: 0.5055 [2021-03-25 13:26:14 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 300/1251] eta: 0:08:15 lr: 0.000917 loss: 3.8767 (3.6994) grad_norm: 1.0193 (inf) time: 0.5046 [2021-03-25 13:26:19 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 310/1251] eta: 0:08:09 lr: 0.000917 loss: 3.6158 (3.6915) grad_norm: 1.0109 (inf) time: 0.5058 [2021-03-25 13:26:24 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 320/1251] eta: 0:08:04 lr: 0.000917 loss: 3.6158 (3.6973) grad_norm: 0.9943 (inf) time: 0.5109 [2021-03-25 13:26:29 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 330/1251] eta: 0:07:59 lr: 0.000917 loss: 4.1188 (3.7088) grad_norm: 1.0012 (inf) time: 0.5169 [2021-03-25 13:26:34 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 340/1251] eta: 0:07:53 lr: 0.000917 loss: 3.9976 (3.7132) grad_norm: 0.9976 (inf) time: 0.5126 [2021-03-25 13:26:39 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 350/1251] eta: 0:07:47 lr: 0.000916 loss: 3.8682 (3.7160) grad_norm: 1.0365 (inf) time: 0.5060 [2021-03-25 13:26:44 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 360/1251] eta: 0:07:42 lr: 0.000916 loss: 3.8682 (3.7188) grad_norm: 1.0405 (inf) time: 0.5045 [2021-03-25 13:26:49 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 370/1251] eta: 0:07:36 lr: 0.000916 loss: 3.8378 (3.7191) grad_norm: 1.0043 (inf) time: 0.5043 [2021-03-25 13:26:54 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 380/1251] eta: 0:07:31 lr: 0.000916 loss: 3.7515 (3.7183) grad_norm: 1.0140 (inf) time: 0.5031 [2021-03-25 13:26:59 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 390/1251] eta: 0:07:25 lr: 0.000916 loss: 3.7515 (3.7208) grad_norm: 1.0140 (inf) time: 0.5071 [2021-03-25 13:27:04 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 400/1251] eta: 0:07:20 lr: 0.000916 loss: 3.9060 (3.7204) grad_norm: 1.0527 (inf) time: 0.5071 [2021-03-25 13:27:09 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 410/1251] eta: 0:07:15 lr: 0.000916 loss: 3.8967 (3.7192) grad_norm: 1.0723 (inf) time: 0.5044 [2021-03-25 13:27:14 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 420/1251] eta: 0:07:09 lr: 0.000916 loss: 3.5632 (3.7125) grad_norm: 1.0083 (inf) time: 0.5058 [2021-03-25 13:27:19 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 430/1251] eta: 0:07:04 lr: 0.000916 loss: 3.8067 (3.7153) grad_norm: 0.9806 (inf) time: 0.5036 [2021-03-25 13:27:25 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 440/1251] eta: 0:06:58 lr: 0.000916 loss: 3.8411 (3.7127) grad_norm: 0.9871 (inf) time: 0.5060 [2021-03-25 13:27:30 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 450/1251] eta: 0:06:53 lr: 0.000916 loss: 3.7349 (3.7149) grad_norm: 0.9839 (inf) time: 0.5032 [2021-03-25 13:27:34 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 460/1251] eta: 0:06:47 lr: 0.000916 loss: 3.8544 (3.7180) grad_norm: 0.9883 (inf) time: 0.4959 [2021-03-25 13:27:40 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 470/1251] eta: 0:06:42 lr: 0.000916 loss: 3.8414 (3.7174) grad_norm: 1.1023 (inf) time: 0.5005 [2021-03-25 13:27:45 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 480/1251] eta: 0:06:37 lr: 0.000916 loss: 3.8674 (3.7226) grad_norm: 1.0616 (inf) time: 0.5088 [2021-03-25 13:27:50 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 490/1251] eta: 0:06:31 lr: 0.000916 loss: 3.9277 (3.7225) grad_norm: 1.0628 (inf) time: 0.5060 [2021-03-25 13:27:55 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 500/1251] eta: 0:06:26 lr: 0.000916 loss: 3.7994 (3.7240) grad_norm: 1.0864 (inf) time: 0.5023 [2021-03-25 13:28:00 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 510/1251] eta: 0:06:21 lr: 0.000916 loss: 3.9039 (3.7248) grad_norm: 1.0241 (inf) time: 0.5024 [2021-03-25 13:28:05 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 520/1251] eta: 0:06:16 lr: 0.000916 loss: 3.7613 (3.7248) grad_norm: 1.0056 (inf) time: 0.5146 [2021-03-25 13:28:10 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 530/1251] eta: 0:06:11 lr: 0.000916 loss: 3.7613 (3.7229) grad_norm: 1.0102 (inf) time: 0.5175 [2021-03-25 13:28:15 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 540/1251] eta: 0:06:05 lr: 0.000916 loss: 3.8467 (3.7233) grad_norm: 1.0364 (inf) time: 0.5103 [2021-03-25 13:28:20 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 550/1251] eta: 0:06:00 lr: 0.000916 loss: 4.0239 (3.7271) grad_norm: 1.0441 (inf) time: 0.5160 [2021-03-25 13:28:26 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 560/1251] eta: 0:05:55 lr: 0.000916 loss: 3.7518 (3.7247) grad_norm: 1.0094 (inf) time: 0.5198 [2021-03-25 13:28:31 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 570/1251] eta: 0:05:50 lr: 0.000916 loss: 3.7422 (3.7234) grad_norm: 1.0306 (inf) time: 0.5091 [2021-03-25 13:28:36 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 580/1251] eta: 0:05:45 lr: 0.000916 loss: 3.7895 (3.7287) grad_norm: 1.0013 (inf) time: 0.5087 [2021-03-25 13:28:41 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 590/1251] eta: 0:05:39 lr: 0.000916 loss: 3.9093 (3.7246) grad_norm: 1.0105 (inf) time: 0.5085 [2021-03-25 13:28:46 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 600/1251] eta: 0:05:34 lr: 0.000916 loss: 3.8712 (3.7266) grad_norm: 1.0745 (inf) time: 0.5043 [2021-03-25 13:28:51 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 610/1251] eta: 0:05:29 lr: 0.000916 loss: 3.8712 (3.7300) grad_norm: 1.0745 (inf) time: 0.5051 [2021-03-25 13:28:56 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 620/1251] eta: 0:05:24 lr: 0.000916 loss: 3.7729 (3.7315) grad_norm: 0.9640 (inf) time: 0.5029 [2021-03-25 13:29:01 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 630/1251] eta: 0:05:18 lr: 0.000916 loss: 3.7525 (3.7313) grad_norm: 0.9554 (inf) time: 0.5035 [2021-03-25 13:29:06 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 640/1251] eta: 0:05:13 lr: 0.000916 loss: 3.8355 (3.7308) grad_norm: 0.9780 (inf) time: 0.5020 [2021-03-25 13:29:11 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 650/1251] eta: 0:05:08 lr: 0.000916 loss: 3.8627 (3.7335) grad_norm: 1.0281 (inf) time: 0.5075 [2021-03-25 13:29:16 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 660/1251] eta: 0:05:03 lr: 0.000916 loss: 3.8627 (3.7319) grad_norm: 1.0334 (inf) time: 0.5089 [2021-03-25 13:29:21 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 670/1251] eta: 0:04:58 lr: 0.000916 loss: 3.8207 (3.7326) grad_norm: 1.0414 (inf) time: 0.5053 [2021-03-25 13:29:26 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 680/1251] eta: 0:04:52 lr: 0.000916 loss: 3.8207 (3.7333) grad_norm: 1.0589 (inf) time: 0.5031 [2021-03-25 13:29:31 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 690/1251] eta: 0:04:47 lr: 0.000916 loss: 3.7890 (3.7316) grad_norm: 1.0398 (inf) time: 0.5001 [2021-03-25 13:29:36 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 700/1251] eta: 0:04:42 lr: 0.000916 loss: 3.4479 (3.7272) grad_norm: 0.9775 (inf) time: 0.5007 [2021-03-25 13:29:41 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 710/1251] eta: 0:04:37 lr: 0.000916 loss: 3.6314 (3.7293) grad_norm: 0.9223 (inf) time: 0.5068 [2021-03-25 13:29:46 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 720/1251] eta: 0:04:32 lr: 0.000916 loss: 3.9136 (3.7267) grad_norm: 0.9483 (inf) time: 0.5093 [2021-03-25 13:29:52 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 730/1251] eta: 0:04:27 lr: 0.000916 loss: 3.6108 (3.7267) grad_norm: 0.9258 (inf) time: 0.5137 [2021-03-25 13:29:57 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 740/1251] eta: 0:04:22 lr: 0.000916 loss: 3.5304 (3.7199) grad_norm: 0.9654 (inf) time: 0.5257 [2021-03-25 13:30:02 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 750/1251] eta: 0:04:16 lr: 0.000916 loss: 3.3807 (3.7198) grad_norm: 1.0360 (inf) time: 0.5159 [2021-03-25 13:30:07 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 760/1251] eta: 0:04:11 lr: 0.000916 loss: 3.6439 (3.7177) grad_norm: 1.0360 (inf) time: 0.5093 [2021-03-25 13:30:12 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 770/1251] eta: 0:04:06 lr: 0.000916 loss: 3.8511 (3.7191) grad_norm: 1.0575 (inf) time: 0.5179 [2021-03-25 13:30:17 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 780/1251] eta: 0:04:01 lr: 0.000915 loss: 3.8511 (3.7177) grad_norm: 1.0167 (inf) time: 0.5081 [2021-03-25 13:30:22 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 790/1251] eta: 0:03:56 lr: 0.000915 loss: 3.5340 (3.7160) grad_norm: 0.9572 (inf) time: 0.5051 [2021-03-25 13:30:27 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 800/1251] eta: 0:03:51 lr: 0.000915 loss: 3.9491 (3.7189) grad_norm: 1.0231 (inf) time: 0.5083 [2021-03-25 13:30:32 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 810/1251] eta: 0:03:46 lr: 0.000915 loss: 4.0680 (3.7214) grad_norm: 1.0176 (inf) time: 0.5025 [2021-03-25 13:30:38 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 820/1251] eta: 0:03:40 lr: 0.000915 loss: 3.8210 (3.7188) grad_norm: 0.9499 (inf) time: 0.5027 [2021-03-25 13:30:43 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 830/1251] eta: 0:03:35 lr: 0.000915 loss: 3.4549 (3.7164) grad_norm: 0.9617 (inf) time: 0.5071 [2021-03-25 13:30:48 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 840/1251] eta: 0:03:30 lr: 0.000915 loss: 3.7271 (3.7159) grad_norm: 0.9798 (inf) time: 0.5119 [2021-03-25 13:30:53 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 850/1251] eta: 0:03:25 lr: 0.000915 loss: 3.8916 (3.7154) grad_norm: 1.0154 (inf) time: 0.5063 [2021-03-25 13:30:58 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 860/1251] eta: 0:03:20 lr: 0.000915 loss: 4.0319 (3.7192) grad_norm: 1.0263 (inf) time: 0.5061 [2021-03-25 13:31:03 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 870/1251] eta: 0:03:15 lr: 0.000915 loss: 3.8545 (3.7171) grad_norm: 1.0759 (inf) time: 0.5094 [2021-03-25 13:31:08 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 880/1251] eta: 0:03:09 lr: 0.000915 loss: 3.5473 (3.7126) grad_norm: 1.0688 (inf) time: 0.5044 [2021-03-25 13:31:13 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 890/1251] eta: 0:03:04 lr: 0.000915 loss: 3.7363 (3.7159) grad_norm: 1.0159 (inf) time: 0.5039 [2021-03-25 13:31:18 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 900/1251] eta: 0:02:59 lr: 0.000915 loss: 4.0229 (3.7179) grad_norm: 1.0087 (inf) time: 0.5046 [2021-03-25 13:31:23 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 910/1251] eta: 0:02:54 lr: 0.000915 loss: 3.9642 (3.7228) grad_norm: 1.0265 (inf) time: 0.5018 [2021-03-25 13:31:28 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 920/1251] eta: 0:02:49 lr: 0.000915 loss: 3.9276 (3.7227) grad_norm: 0.9854 (inf) time: 0.5040 [2021-03-25 13:31:33 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 930/1251] eta: 0:02:44 lr: 0.000915 loss: 3.7758 (3.7229) grad_norm: 0.9881 (inf) time: 0.5125 [2021-03-25 13:31:38 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 940/1251] eta: 0:02:39 lr: 0.000915 loss: 3.6637 (3.7220) grad_norm: 0.9881 (inf) time: 0.5132 [2021-03-25 13:31:44 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 950/1251] eta: 0:02:34 lr: 0.000915 loss: 3.6350 (3.7196) grad_norm: 0.9882 (inf) time: 0.5131 [2021-03-25 13:31:49 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 960/1251] eta: 0:02:28 lr: 0.000915 loss: 3.8102 (3.7211) grad_norm: 0.9882 (inf) time: 0.5116 [2021-03-25 13:31:54 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 970/1251] eta: 0:02:23 lr: 0.000915 loss: 3.8345 (3.7230) grad_norm: 1.0291 (inf) time: 0.5089 [2021-03-25 13:31:59 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 980/1251] eta: 0:02:18 lr: 0.000915 loss: 3.8345 (3.7244) grad_norm: 1.0339 (inf) time: 0.5094 [2021-03-25 13:32:04 swin_small_patch4_window7_224] INFO: Epoch: [56] [ 990/1251] eta: 0:02:13 lr: 0.000915 loss: 3.9533 (3.7268) grad_norm: 1.0318 (inf) time: 0.5037 [2021-03-25 13:32:09 swin_small_patch4_window7_224] INFO: Epoch: [56] [1000/1251] eta: 0:02:08 lr: 0.000915 loss: 4.0153 (3.7296) grad_norm: 1.0166 (inf) time: 0.5019 [2021-03-25 13:32:14 swin_small_patch4_window7_224] INFO: Epoch: [56] [1010/1251] eta: 0:02:03 lr: 0.000915 loss: 3.8512 (3.7267) grad_norm: 0.9963 (inf) time: 0.5052 [2021-03-25 13:32:19 swin_small_patch4_window7_224] INFO: Epoch: [56] [1020/1251] eta: 0:01:58 lr: 0.000915 loss: 3.5563 (3.7239) grad_norm: 0.9622 (inf) time: 0.5014 [2021-03-25 13:32:24 swin_small_patch4_window7_224] INFO: Epoch: [56] [1030/1251] eta: 0:01:52 lr: 0.000915 loss: 3.6632 (3.7212) grad_norm: 0.9835 (inf) time: 0.4971 [2021-03-25 13:32:29 swin_small_patch4_window7_224] INFO: Epoch: [56] [1040/1251] eta: 0:01:47 lr: 0.000915 loss: 3.6082 (3.7211) grad_norm: 0.9575 (inf) time: 0.4990 [2021-03-25 13:32:34 swin_small_patch4_window7_224] INFO: Epoch: [56] [1050/1251] eta: 0:01:42 lr: 0.000915 loss: 3.5804 (3.7189) grad_norm: 0.9658 (inf) time: 0.5085 [2021-03-25 13:32:39 swin_small_patch4_window7_224] INFO: Epoch: [56] [1060/1251] eta: 0:01:37 lr: 0.000915 loss: 3.5804 (3.7182) grad_norm: 1.0360 (inf) time: 0.5067 [2021-03-25 13:32:44 swin_small_patch4_window7_224] INFO: Epoch: [56] [1070/1251] eta: 0:01:32 lr: 0.000915 loss: 3.7769 (3.7197) grad_norm: 1.0398 (inf) time: 0.5038 [2021-03-25 13:32:49 swin_small_patch4_window7_224] INFO: Epoch: [56] [1080/1251] eta: 0:01:27 lr: 0.000915 loss: 4.0288 (3.7203) grad_norm: 1.0398 (inf) time: 0.5083 [2021-03-25 13:32:54 swin_small_patch4_window7_224] INFO: Epoch: [56] [1090/1251] eta: 0:01:22 lr: 0.000915 loss: 3.7270 (3.7193) grad_norm: 1.0373 (inf) time: 0.5076 [2021-03-25 13:32:59 swin_small_patch4_window7_224] INFO: Epoch: [56] [1100/1251] eta: 0:01:17 lr: 0.000915 loss: 3.7710 (3.7203) grad_norm: 1.0628 (inf) time: 0.5079 [2021-03-25 13:33:04 swin_small_patch4_window7_224] INFO: Epoch: [56] [1110/1251] eta: 0:01:12 lr: 0.000915 loss: 3.8353 (3.7213) grad_norm: 1.0839 (inf) time: 0.5071 [2021-03-25 13:33:09 swin_small_patch4_window7_224] INFO: Epoch: [56] [1120/1251] eta: 0:01:06 lr: 0.000915 loss: 3.7589 (3.7214) grad_norm: 1.0811 (inf) time: 0.5063 [2021-03-25 13:33:15 swin_small_patch4_window7_224] INFO: Epoch: [56] [1130/1251] eta: 0:01:01 lr: 0.000915 loss: 3.7485 (3.7229) grad_norm: 1.0384 (inf) time: 0.5055 [2021-03-25 13:33:20 swin_small_patch4_window7_224] INFO: Epoch: [56] [1140/1251] eta: 0:00:56 lr: 0.000915 loss: 3.6430 (3.7204) grad_norm: 1.0384 (inf) time: 0.5003 [2021-03-25 13:33:25 swin_small_patch4_window7_224] INFO: Epoch: [56] [1150/1251] eta: 0:00:51 lr: 0.000915 loss: 3.7524 (3.7205) grad_norm: 0.9807 (inf) time: 0.4990 [2021-03-25 13:33:30 swin_small_patch4_window7_224] INFO: Epoch: [56] [1160/1251] eta: 0:00:46 lr: 0.000915 loss: 3.7892 (3.7202) grad_norm: 0.9491 (inf) time: 0.5011 [2021-03-25 13:33:35 swin_small_patch4_window7_224] INFO: Epoch: [56] [1170/1251] eta: 0:00:41 lr: 0.000915 loss: 3.5264 (3.7194) grad_norm: 0.9346 (inf) time: 0.5014 [2021-03-25 13:33:40 swin_small_patch4_window7_224] INFO: Epoch: [56] [1180/1251] eta: 0:00:36 lr: 0.000915 loss: 3.8969 (3.7209) grad_norm: 0.9719 (inf) time: 0.5031 [2021-03-25 13:33:45 swin_small_patch4_window7_224] INFO: Epoch: [56] [1190/1251] eta: 0:00:31 lr: 0.000915 loss: 3.9844 (3.7239) grad_norm: 1.0007 (inf) time: 0.5052 [2021-03-25 13:33:50 swin_small_patch4_window7_224] INFO: Epoch: [56] [1200/1251] eta: 0:00:26 lr: 0.000915 loss: 3.9176 (3.7223) grad_norm: 1.0475 (inf) time: 0.5085 [2021-03-25 13:33:55 swin_small_patch4_window7_224] INFO: Epoch: [56] [1210/1251] eta: 0:00:20 lr: 0.000915 loss: 3.8720 (3.7227) grad_norm: 1.0184 (inf) time: 0.5092 [2021-03-25 13:34:00 swin_small_patch4_window7_224] INFO: Epoch: [56] [1220/1251] eta: 0:00:15 lr: 0.000914 loss: 4.0531 (3.7247) grad_norm: 1.0066 (inf) time: 0.5021 [2021-03-25 13:34:05 swin_small_patch4_window7_224] INFO: Epoch: [56] [1230/1251] eta: 0:00:10 lr: 0.000914 loss: 3.7897 (3.7234) grad_norm: 1.0066 (inf) time: 0.5022 [2021-03-25 13:34:10 swin_small_patch4_window7_224] INFO: Epoch: [56] [1240/1251] eta: 0:00:05 lr: 0.000914 loss: 3.6112 (3.7233) grad_norm: 1.0303 (inf) time: 0.5051 [2021-03-25 13:34:15 swin_small_patch4_window7_224] INFO: Epoch: [56] [1250/1251] eta: 0:00:00 lr: 0.000914 loss: 3.7972 (3.7239) grad_norm: 1.0100 (inf) time: 0.5011 [2021-03-25 13:34:20 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:28 loss: 1.2581 (1.2581) acc1: 70.3125 (70.3125) acc5: 89.0625 (89.0625) [2021-03-25 13:34:22 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1327 (1.1380) acc1: 75.0000 (73.7216) acc5: 92.1875 (92.6136) [2021-03-25 13:34:25 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.1284 (1.1789) acc1: 75.0000 (73.5863) acc5: 92.1875 (92.1131) [2021-03-25 13:34:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.2498 (1.2106) acc1: 71.8750 (72.4798) acc5: 90.6250 (91.6331) [2021-03-25 13:34:29 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.2449 (1.2122) acc1: 68.7500 (72.1037) acc5: 90.6250 (91.7683) [2021-03-25 13:34:30 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1962 (1.1970) acc1: 71.8750 (72.3840) acc5: 90.6250 (91.7120) [2021-03-25 13:34:32 swin_small_patch4_window7_224] INFO: * Acc@1 73.188 Acc@5 91.942 loss 1.152 [2021-03-25 13:34:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.2% [2021-03-25 13:34:32 swin_small_patch4_window7_224] INFO: Max accuracy: 73.19% [2021-03-25 13:34:36 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 0/1251] eta: 1:26:22 lr: 0.000914 loss: 2.7547 (2.7547) grad_norm: 0.8628 (0.8628) time: 4.1426 [2021-03-25 13:34:41 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 10/1251] eta: 0:17:45 lr: 0.000914 loss: 4.1694 (3.9234) grad_norm: 1.0197 (1.0099) time: 0.8586 [2021-03-25 13:34:46 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 20/1251] eta: 0:14:08 lr: 0.000914 loss: 3.5843 (3.6030) grad_norm: 1.0141 (0.9970) time: 0.5162 [2021-03-25 13:34:51 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 30/1251] eta: 0:12:50 lr: 0.000914 loss: 3.3501 (3.5892) grad_norm: 1.0035 (0.9878) time: 0.5062 [2021-03-25 13:34:57 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 40/1251] eta: 0:12:08 lr: 0.000914 loss: 3.4073 (3.6209) grad_norm: 1.0248 (1.0113) time: 0.5099 [2021-03-25 13:35:02 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 50/1251] eta: 0:11:39 lr: 0.000914 loss: 3.6073 (3.5907) grad_norm: 1.0696 (1.0308) time: 0.5077 [2021-03-25 13:35:07 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 60/1251] eta: 0:11:18 lr: 0.000914 loss: 3.6808 (3.6237) grad_norm: 1.0986 (1.0421) time: 0.5050 [2021-03-25 13:35:12 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 70/1251] eta: 0:11:01 lr: 0.000914 loss: 3.6664 (3.6130) grad_norm: 1.0446 (1.0401) time: 0.5013 [2021-03-25 13:35:17 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 80/1251] eta: 0:10:48 lr: 0.000914 loss: 3.6690 (3.6375) grad_norm: 1.0184 (1.0452) time: 0.5041 [2021-03-25 13:35:22 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 90/1251] eta: 0:10:36 lr: 0.000914 loss: 3.8199 (3.6541) grad_norm: 1.0022 (1.0410) time: 0.5063 [2021-03-25 13:35:27 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 100/1251] eta: 0:10:26 lr: 0.000914 loss: 3.8199 (3.6583) grad_norm: 1.0067 (1.0458) time: 0.5053 [2021-03-25 13:35:32 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 110/1251] eta: 0:10:16 lr: 0.000914 loss: 3.8810 (3.6604) grad_norm: 1.0546 (1.0396) time: 0.5062 [2021-03-25 13:35:37 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 120/1251] eta: 0:10:08 lr: 0.000914 loss: 3.7947 (3.6437) grad_norm: 0.9894 (1.0416) time: 0.5051 [2021-03-25 13:35:42 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 130/1251] eta: 0:09:59 lr: 0.000914 loss: 3.5092 (3.6508) grad_norm: 0.9975 (1.0382) time: 0.5058 [2021-03-25 13:35:47 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 140/1251] eta: 0:09:52 lr: 0.000914 loss: 3.9046 (3.6653) grad_norm: 0.9975 (1.0389) time: 0.5081 [2021-03-25 13:35:52 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 150/1251] eta: 0:09:44 lr: 0.000914 loss: 3.8645 (3.6732) grad_norm: 0.9979 (1.0390) time: 0.5034 [2021-03-25 13:35:57 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 160/1251] eta: 0:09:36 lr: 0.000914 loss: 3.8205 (3.6747) grad_norm: 1.0490 (1.0432) time: 0.4963 [2021-03-25 13:36:02 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 170/1251] eta: 0:09:30 lr: 0.000914 loss: 3.7340 (3.6740) grad_norm: 1.0490 (1.0472) time: 0.5039 [2021-03-25 13:36:07 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 180/1251] eta: 0:09:24 lr: 0.000914 loss: 3.8492 (3.6793) grad_norm: 1.0065 (1.0427) time: 0.5118 [2021-03-25 13:36:13 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 190/1251] eta: 0:09:19 lr: 0.000914 loss: 3.9475 (3.6815) grad_norm: 0.9365 (1.0412) time: 0.5206 [2021-03-25 13:36:18 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 200/1251] eta: 0:09:12 lr: 0.000914 loss: 3.8145 (3.6764) grad_norm: 0.9788 (1.0396) time: 0.5129 [2021-03-25 13:36:23 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 210/1251] eta: 0:09:06 lr: 0.000914 loss: 3.6995 (3.6640) grad_norm: 1.0060 (1.0386) time: 0.5039 [2021-03-25 13:36:28 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 220/1251] eta: 0:09:00 lr: 0.000914 loss: 3.3671 (3.6546) grad_norm: 1.0281 (1.0407) time: 0.5106 [2021-03-25 13:36:33 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 230/1251] eta: 0:08:54 lr: 0.000914 loss: 3.4215 (3.6528) grad_norm: 1.0216 (1.0394) time: 0.5055 [2021-03-25 13:36:38 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 240/1251] eta: 0:08:48 lr: 0.000914 loss: 3.6364 (3.6501) grad_norm: 1.0011 (1.0372) time: 0.5036 [2021-03-25 13:36:43 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 250/1251] eta: 0:08:42 lr: 0.000914 loss: 3.6652 (3.6499) grad_norm: 1.0081 (1.0375) time: 0.5036 [2021-03-25 13:36:48 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 260/1251] eta: 0:08:36 lr: 0.000914 loss: 3.6652 (3.6523) grad_norm: 1.0099 (1.0368) time: 0.5026 [2021-03-25 13:36:53 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 270/1251] eta: 0:08:30 lr: 0.000914 loss: 3.6594 (3.6551) grad_norm: 0.9511 (1.0337) time: 0.5030 [2021-03-25 13:36:58 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 280/1251] eta: 0:08:24 lr: 0.000914 loss: 3.8235 (3.6540) grad_norm: 1.0107 (1.0386) time: 0.5010 [2021-03-25 13:37:03 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 290/1251] eta: 0:08:18 lr: 0.000914 loss: 3.7630 (3.6516) grad_norm: 1.0668 (1.0388) time: 0.5015 [2021-03-25 13:37:08 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 300/1251] eta: 0:08:13 lr: 0.000914 loss: 3.4788 (3.6482) grad_norm: 1.0302 (1.0397) time: 0.5025 [2021-03-25 13:37:13 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 310/1251] eta: 0:08:07 lr: 0.000914 loss: 3.5182 (3.6531) grad_norm: 0.9985 (1.0378) time: 0.5059 [2021-03-25 13:37:18 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 320/1251] eta: 0:08:01 lr: 0.000914 loss: 4.0681 (3.6616) grad_norm: 0.9660 (1.0379) time: 0.5069 [2021-03-25 13:37:23 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 330/1251] eta: 0:07:56 lr: 0.000914 loss: 3.9900 (3.6635) grad_norm: 1.0570 (1.0389) time: 0.5091 [2021-03-25 13:37:28 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 340/1251] eta: 0:07:51 lr: 0.000914 loss: 3.6092 (3.6563) grad_norm: 1.0570 (1.0379) time: 0.5121 [2021-03-25 13:37:33 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 350/1251] eta: 0:07:45 lr: 0.000914 loss: 3.5527 (3.6600) grad_norm: 0.9712 (1.0353) time: 0.5015 [2021-03-25 13:37:38 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 360/1251] eta: 0:07:40 lr: 0.000914 loss: 3.8583 (3.6623) grad_norm: 0.9569 (1.0337) time: 0.4999 [2021-03-25 13:37:43 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 370/1251] eta: 0:07:34 lr: 0.000914 loss: 3.8839 (3.6632) grad_norm: 0.9569 (1.0315) time: 0.5052 [2021-03-25 13:37:48 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 380/1251] eta: 0:07:29 lr: 0.000914 loss: 3.8869 (3.6659) grad_norm: 0.9133 (1.0287) time: 0.5021 [2021-03-25 13:37:53 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 390/1251] eta: 0:07:23 lr: 0.000913 loss: 3.9048 (3.6725) grad_norm: 0.9979 (1.0302) time: 0.5022 [2021-03-25 13:37:58 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 400/1251] eta: 0:07:18 lr: 0.000913 loss: 4.0098 (3.6790) grad_norm: 1.0195 (1.0308) time: 0.5008 [2021-03-25 13:38:04 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 410/1251] eta: 0:07:12 lr: 0.000913 loss: 3.6260 (3.6739) grad_norm: 0.9766 (1.0294) time: 0.5034 [2021-03-25 13:38:09 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 420/1251] eta: 0:07:07 lr: 0.000913 loss: 3.4357 (3.6746) grad_norm: 1.0536 (1.0320) time: 0.5054 [2021-03-25 13:38:14 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 430/1251] eta: 0:07:02 lr: 0.000913 loss: 3.8240 (3.6731) grad_norm: 1.0897 (1.0323) time: 0.4989 [2021-03-25 13:38:19 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 440/1251] eta: 0:06:56 lr: 0.000913 loss: 3.8730 (3.6737) grad_norm: 1.0715 (1.0342) time: 0.5015 [2021-03-25 13:38:24 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 450/1251] eta: 0:06:51 lr: 0.000913 loss: 3.8839 (3.6801) grad_norm: 1.1286 (1.0364) time: 0.5045 [2021-03-25 13:38:29 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 460/1251] eta: 0:06:46 lr: 0.000913 loss: 3.7118 (3.6794) grad_norm: 1.0487 (1.0370) time: 0.5033 [2021-03-25 13:38:34 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 470/1251] eta: 0:06:40 lr: 0.000913 loss: 3.6924 (3.6832) grad_norm: 1.0092 (1.0369) time: 0.5017 [2021-03-25 13:38:39 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 480/1251] eta: 0:06:35 lr: 0.000913 loss: 3.6141 (3.6769) grad_norm: 1.0135 (1.0368) time: 0.5031 [2021-03-25 13:38:44 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 490/1251] eta: 0:06:30 lr: 0.000913 loss: 3.5785 (3.6758) grad_norm: 1.0379 (1.0372) time: 0.5071 [2021-03-25 13:38:49 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 500/1251] eta: 0:06:24 lr: 0.000913 loss: 3.5785 (3.6721) grad_norm: 1.0420 (1.0370) time: 0.5036 [2021-03-25 13:38:54 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 510/1251] eta: 0:06:19 lr: 0.000913 loss: 3.6546 (3.6719) grad_norm: 0.9798 (1.0366) time: 0.5034 [2021-03-25 13:38:59 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 520/1251] eta: 0:06:14 lr: 0.000913 loss: 3.8494 (3.6746) grad_norm: 0.9699 (1.0351) time: 0.5070 [2021-03-25 13:39:04 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 530/1251] eta: 0:06:09 lr: 0.000913 loss: 3.8706 (3.6765) grad_norm: 0.9997 (1.0367) time: 0.5044 [2021-03-25 13:39:09 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 540/1251] eta: 0:06:04 lr: 0.000913 loss: 3.7577 (3.6775) grad_norm: 1.0898 (1.0375) time: 0.5040 [2021-03-25 13:39:14 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 550/1251] eta: 0:05:59 lr: 0.000913 loss: 3.7577 (3.6776) grad_norm: 1.0584 (1.0379) time: 0.5158 [2021-03-25 13:39:19 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 560/1251] eta: 0:05:53 lr: 0.000913 loss: 3.8223 (3.6772) grad_norm: 1.0055 (1.0374) time: 0.5147 [2021-03-25 13:39:24 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 570/1251] eta: 0:05:48 lr: 0.000913 loss: 3.7924 (3.6755) grad_norm: 0.9922 (1.0377) time: 0.5060 [2021-03-25 13:39:29 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 580/1251] eta: 0:05:43 lr: 0.000913 loss: 3.5753 (3.6700) grad_norm: 1.0030 (1.0377) time: 0.5051 [2021-03-25 13:39:35 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 590/1251] eta: 0:05:38 lr: 0.000913 loss: 3.6680 (3.6691) grad_norm: 1.0030 (1.0373) time: 0.5120 [2021-03-25 13:39:40 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 600/1251] eta: 0:05:33 lr: 0.000913 loss: 3.5197 (3.6660) grad_norm: 1.0339 (1.0390) time: 0.5168 [2021-03-25 13:39:45 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 610/1251] eta: 0:05:28 lr: 0.000913 loss: 3.5270 (3.6655) grad_norm: 1.0590 (1.0397) time: 0.5126 [2021-03-25 13:39:50 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 620/1251] eta: 0:05:23 lr: 0.000913 loss: 3.5335 (3.6592) grad_norm: 0.9995 (1.0391) time: 0.5071 [2021-03-25 13:39:55 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 630/1251] eta: 0:05:17 lr: 0.000913 loss: 3.7555 (3.6617) grad_norm: 0.9602 (1.0384) time: 0.5024 [2021-03-25 13:40:00 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 640/1251] eta: 0:05:12 lr: 0.000913 loss: 3.7986 (3.6613) grad_norm: 0.9713 (1.0371) time: 0.5035 [2021-03-25 13:40:05 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 650/1251] eta: 0:05:07 lr: 0.000913 loss: 3.7233 (3.6636) grad_norm: 0.9827 (1.0366) time: 0.5033 [2021-03-25 13:40:10 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 660/1251] eta: 0:05:02 lr: 0.000913 loss: 3.8175 (3.6647) grad_norm: 1.0283 (1.0371) time: 0.5031 [2021-03-25 13:40:15 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 670/1251] eta: 0:04:57 lr: 0.000913 loss: 3.8914 (3.6665) grad_norm: 1.0283 (1.0372) time: 0.5023 [2021-03-25 13:40:20 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 680/1251] eta: 0:04:51 lr: 0.000913 loss: 3.9882 (3.6702) grad_norm: 0.9739 (1.0364) time: 0.4987 [2021-03-25 13:40:25 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 690/1251] eta: 0:04:46 lr: 0.000913 loss: 3.7259 (3.6708) grad_norm: 0.9833 (1.0359) time: 0.5012 [2021-03-25 13:40:30 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 700/1251] eta: 0:04:41 lr: 0.000913 loss: 3.8525 (3.6744) grad_norm: 1.0273 (1.0369) time: 0.5033 [2021-03-25 13:40:35 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 710/1251] eta: 0:04:36 lr: 0.000913 loss: 4.0470 (3.6781) grad_norm: 1.0433 (1.0369) time: 0.4987 [2021-03-25 13:40:40 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 720/1251] eta: 0:04:31 lr: 0.000913 loss: 3.7048 (3.6776) grad_norm: 0.9914 (1.0364) time: 0.5046 [2021-03-25 13:40:45 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 730/1251] eta: 0:04:26 lr: 0.000913 loss: 3.6461 (3.6764) grad_norm: 1.0250 (1.0365) time: 0.5137 [2021-03-25 13:40:51 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 740/1251] eta: 0:04:21 lr: 0.000913 loss: 3.6461 (3.6748) grad_norm: 0.9809 (1.0356) time: 0.5362 [2021-03-25 13:40:56 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 750/1251] eta: 0:04:16 lr: 0.000913 loss: 3.5751 (3.6723) grad_norm: 0.9674 (1.0353) time: 0.5317 [2021-03-25 13:41:01 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 760/1251] eta: 0:04:11 lr: 0.000913 loss: 3.5028 (3.6716) grad_norm: 0.9468 (1.0347) time: 0.5067 [2021-03-25 13:41:06 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 770/1251] eta: 0:04:05 lr: 0.000913 loss: 3.7793 (3.6725) grad_norm: 0.9571 (1.0347) time: 0.5070 [2021-03-25 13:41:11 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 780/1251] eta: 0:04:00 lr: 0.000913 loss: 3.8420 (3.6748) grad_norm: 0.9779 (1.0343) time: 0.5087 [2021-03-25 13:41:16 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 790/1251] eta: 0:03:55 lr: 0.000913 loss: 3.8639 (3.6761) grad_norm: 0.9527 (1.0338) time: 0.5088 [2021-03-25 13:41:21 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 800/1251] eta: 0:03:50 lr: 0.000913 loss: 3.6399 (3.6746) grad_norm: 1.0120 (1.0340) time: 0.5058 [2021-03-25 13:41:26 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 810/1251] eta: 0:03:45 lr: 0.000913 loss: 3.9042 (3.6776) grad_norm: 1.0594 (1.0343) time: 0.5025 [2021-03-25 13:41:31 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 820/1251] eta: 0:03:40 lr: 0.000912 loss: 3.9507 (3.6783) grad_norm: 1.0429 (1.0345) time: 0.5073 [2021-03-25 13:41:37 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 830/1251] eta: 0:03:35 lr: 0.000912 loss: 3.7262 (3.6752) grad_norm: 1.0982 (1.0363) time: 0.5111 [2021-03-25 13:41:42 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 840/1251] eta: 0:03:29 lr: 0.000912 loss: 3.4442 (3.6761) grad_norm: 1.0752 (1.0357) time: 0.5068 [2021-03-25 13:41:47 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 850/1251] eta: 0:03:24 lr: 0.000912 loss: 3.6966 (3.6756) grad_norm: 0.9487 (1.0348) time: 0.5016 [2021-03-25 13:41:52 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 860/1251] eta: 0:03:19 lr: 0.000912 loss: 3.5466 (3.6744) grad_norm: 1.0059 (1.0350) time: 0.5014 [2021-03-25 13:41:57 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 870/1251] eta: 0:03:14 lr: 0.000912 loss: 3.5065 (3.6726) grad_norm: 1.0246 (1.0353) time: 0.5035 [2021-03-25 13:42:02 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 880/1251] eta: 0:03:09 lr: 0.000912 loss: 3.6246 (3.6723) grad_norm: 1.0144 (1.0353) time: 0.5090 [2021-03-25 13:42:07 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 890/1251] eta: 0:03:04 lr: 0.000912 loss: 3.6246 (3.6691) grad_norm: 1.0251 (1.0353) time: 0.5089 [2021-03-25 13:42:12 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 900/1251] eta: 0:02:59 lr: 0.000912 loss: 3.5187 (3.6686) grad_norm: 1.0627 (1.0360) time: 0.5019 [2021-03-25 13:42:17 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 910/1251] eta: 0:02:54 lr: 0.000912 loss: 3.8541 (3.6717) grad_norm: 1.0617 (1.0360) time: 0.5109 [2021-03-25 13:42:22 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 920/1251] eta: 0:02:48 lr: 0.000912 loss: 3.9824 (3.6730) grad_norm: 1.0220 (1.0358) time: 0.5106 [2021-03-25 13:42:27 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 930/1251] eta: 0:02:43 lr: 0.000912 loss: 4.0679 (3.6746) grad_norm: 1.0042 (1.0356) time: 0.5188 [2021-03-25 13:42:32 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 940/1251] eta: 0:02:38 lr: 0.000912 loss: 4.0679 (3.6761) grad_norm: 1.0482 (1.0354) time: 0.5167 [2021-03-25 13:42:38 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 950/1251] eta: 0:02:33 lr: 0.000912 loss: 3.9490 (3.6775) grad_norm: 1.0546 (1.0362) time: 0.5036 [2021-03-25 13:42:43 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 960/1251] eta: 0:02:28 lr: 0.000912 loss: 3.9773 (3.6776) grad_norm: 1.0669 (1.0359) time: 0.5107 [2021-03-25 13:42:48 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 970/1251] eta: 0:02:23 lr: 0.000912 loss: 3.9010 (3.6789) grad_norm: 1.0758 (1.0366) time: 0.5090 [2021-03-25 13:42:53 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 980/1251] eta: 0:02:18 lr: 0.000912 loss: 3.9063 (3.6817) grad_norm: 1.0369 (1.0363) time: 0.5002 [2021-03-25 13:42:58 swin_small_patch4_window7_224] INFO: Epoch: [57] [ 990/1251] eta: 0:02:13 lr: 0.000912 loss: 3.8158 (3.6808) grad_norm: 0.9895 (1.0364) time: 0.5022 [2021-03-25 13:43:03 swin_small_patch4_window7_224] INFO: Epoch: [57] [1000/1251] eta: 0:02:08 lr: 0.000912 loss: 3.7665 (3.6826) grad_norm: 1.0187 (1.0361) time: 0.5075 [2021-03-25 13:43:08 swin_small_patch4_window7_224] INFO: Epoch: [57] [1010/1251] eta: 0:02:02 lr: 0.000912 loss: 3.7750 (3.6840) grad_norm: 0.9766 (1.0356) time: 0.5055 [2021-03-25 13:43:13 swin_small_patch4_window7_224] INFO: Epoch: [57] [1020/1251] eta: 0:01:57 lr: 0.000912 loss: 3.5619 (3.6815) grad_norm: 0.9731 (1.0353) time: 0.5074 [2021-03-25 13:43:18 swin_small_patch4_window7_224] INFO: Epoch: [57] [1030/1251] eta: 0:01:52 lr: 0.000912 loss: 3.4581 (3.6796) grad_norm: 0.9837 (1.0347) time: 0.5062 [2021-03-25 13:43:23 swin_small_patch4_window7_224] INFO: Epoch: [57] [1040/1251] eta: 0:01:47 lr: 0.000912 loss: 3.5193 (3.6805) grad_norm: 0.9837 (1.0348) time: 0.5054 [2021-03-25 13:43:28 swin_small_patch4_window7_224] INFO: Epoch: [57] [1050/1251] eta: 0:01:42 lr: 0.000912 loss: 3.5465 (3.6778) grad_norm: 1.0486 (1.0355) time: 0.5042 [2021-03-25 13:43:33 swin_small_patch4_window7_224] INFO: Epoch: [57] [1060/1251] eta: 0:01:37 lr: 0.000912 loss: 3.2208 (3.6752) grad_norm: 1.0115 (1.0348) time: 0.5041 [2021-03-25 13:43:38 swin_small_patch4_window7_224] INFO: Epoch: [57] [1070/1251] eta: 0:01:32 lr: 0.000912 loss: 3.6807 (3.6762) grad_norm: 0.9636 (1.0346) time: 0.5087 [2021-03-25 13:43:43 swin_small_patch4_window7_224] INFO: Epoch: [57] [1080/1251] eta: 0:01:27 lr: 0.000912 loss: 3.8791 (3.6778) grad_norm: 0.9796 (1.0342) time: 0.5083 [2021-03-25 13:43:48 swin_small_patch4_window7_224] INFO: Epoch: [57] [1090/1251] eta: 0:01:22 lr: 0.000912 loss: 3.8791 (3.6781) grad_norm: 0.9907 (1.0338) time: 0.5073 [2021-03-25 13:43:54 swin_small_patch4_window7_224] INFO: Epoch: [57] [1100/1251] eta: 0:01:17 lr: 0.000912 loss: 3.8776 (3.6790) grad_norm: 0.9907 (1.0339) time: 0.5096 [2021-03-25 13:43:59 swin_small_patch4_window7_224] INFO: Epoch: [57] [1110/1251] eta: 0:01:11 lr: 0.000912 loss: 3.8808 (3.6803) grad_norm: 1.0283 (1.0339) time: 0.5070 [2021-03-25 13:44:04 swin_small_patch4_window7_224] INFO: Epoch: [57] [1120/1251] eta: 0:01:06 lr: 0.000912 loss: 3.5495 (3.6775) grad_norm: 1.0526 (1.0340) time: 0.5032 [2021-03-25 13:44:09 swin_small_patch4_window7_224] INFO: Epoch: [57] [1130/1251] eta: 0:01:01 lr: 0.000912 loss: 3.4693 (3.6761) grad_norm: 1.0212 (1.0338) time: 0.5046 [2021-03-25 13:44:14 swin_small_patch4_window7_224] INFO: Epoch: [57] [1140/1251] eta: 0:00:56 lr: 0.000912 loss: 3.7720 (3.6776) grad_norm: 0.9828 (1.0334) time: 0.5064 [2021-03-25 13:44:19 swin_small_patch4_window7_224] INFO: Epoch: [57] [1150/1251] eta: 0:00:51 lr: 0.000912 loss: 4.0404 (3.6798) grad_norm: 0.9828 (1.0331) time: 0.5075 [2021-03-25 13:44:24 swin_small_patch4_window7_224] INFO: Epoch: [57] [1160/1251] eta: 0:00:46 lr: 0.000912 loss: 4.0309 (3.6810) grad_norm: 1.0210 (1.0338) time: 0.5039 [2021-03-25 13:44:29 swin_small_patch4_window7_224] INFO: Epoch: [57] [1170/1251] eta: 0:00:41 lr: 0.000912 loss: 3.5994 (3.6807) grad_norm: 1.0880 (1.0348) time: 0.5029 [2021-03-25 13:44:34 swin_small_patch4_window7_224] INFO: Epoch: [57] [1180/1251] eta: 0:00:36 lr: 0.000912 loss: 3.5252 (3.6795) grad_norm: 1.0535 (1.0348) time: 0.5047 [2021-03-25 13:44:39 swin_small_patch4_window7_224] INFO: Epoch: [57] [1190/1251] eta: 0:00:31 lr: 0.000912 loss: 3.4764 (3.6789) grad_norm: 1.0037 (1.0348) time: 0.5063 [2021-03-25 13:44:44 swin_small_patch4_window7_224] INFO: Epoch: [57] [1200/1251] eta: 0:00:25 lr: 0.000912 loss: 3.8510 (3.6802) grad_norm: 1.0056 (1.0353) time: 0.5080 [2021-03-25 13:44:49 swin_small_patch4_window7_224] INFO: Epoch: [57] [1210/1251] eta: 0:00:20 lr: 0.000912 loss: 3.6819 (3.6765) grad_norm: 1.0056 (1.0351) time: 0.5038 [2021-03-25 13:44:54 swin_small_patch4_window7_224] INFO: Epoch: [57] [1220/1251] eta: 0:00:15 lr: 0.000912 loss: 3.4730 (3.6746) grad_norm: 1.0160 (1.0355) time: 0.5045 [2021-03-25 13:44:59 swin_small_patch4_window7_224] INFO: Epoch: [57] [1230/1251] eta: 0:00:10 lr: 0.000912 loss: 3.5745 (3.6733) grad_norm: 1.1093 (1.0365) time: 0.5031 [2021-03-25 13:45:04 swin_small_patch4_window7_224] INFO: Epoch: [57] [1240/1251] eta: 0:00:05 lr: 0.000911 loss: 3.7055 (3.6742) grad_norm: 1.0828 (1.0367) time: 0.5015 [2021-03-25 13:45:09 swin_small_patch4_window7_224] INFO: Epoch: [57] [1250/1251] eta: 0:00:00 lr: 0.000911 loss: 3.7870 (3.6748) grad_norm: 1.0054 (1.0368) time: 0.5038 [2021-03-25 13:45:14 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:26 loss: 1.5825 (1.5825) acc1: 60.9375 (60.9375) acc5: 85.9375 (85.9375) [2021-03-25 13:45:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.0767 (1.1223) acc1: 76.5625 (73.2955) acc5: 92.1875 (92.6136) [2021-03-25 13:45:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0767 (1.1599) acc1: 75.0000 (72.9167) acc5: 92.1875 (92.1131) [2021-03-25 13:45:21 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1534 (1.1726) acc1: 70.3125 (72.3790) acc5: 92.1875 (91.9355) [2021-03-25 13:45:23 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1358 (1.1686) acc1: 70.3125 (72.5229) acc5: 92.1875 (91.7302) [2021-03-25 13:45:24 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1662 (1.1692) acc1: 71.8750 (72.6400) acc5: 92.1875 (91.8080) [2021-03-25 13:45:28 swin_small_patch4_window7_224] INFO: * Acc@1 73.164 Acc@5 92.006 loss 1.147 [2021-03-25 13:45:28 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.2% [2021-03-25 13:45:28 swin_small_patch4_window7_224] INFO: Max accuracy: 73.19% [2021-03-25 13:45:32 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 0/1251] eta: 1:27:34 lr: 0.000911 loss: 3.9866 (3.9866) grad_norm: 1.0967 (1.0967) time: 4.2005 [2021-03-25 13:45:37 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 10/1251] eta: 0:17:45 lr: 0.000911 loss: 3.4787 (3.3411) grad_norm: 1.0688 (1.0511) time: 0.8588 [2021-03-25 13:45:42 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 20/1251] eta: 0:14:07 lr: 0.000911 loss: 3.4587 (3.4967) grad_norm: 0.9895 (1.0105) time: 0.5131 [2021-03-25 13:45:47 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 30/1251] eta: 0:12:46 lr: 0.000911 loss: 3.5124 (3.4955) grad_norm: 0.9716 (1.0120) time: 0.5008 [2021-03-25 13:45:53 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 40/1251] eta: 0:12:12 lr: 0.000911 loss: 3.7948 (3.5066) grad_norm: 0.9595 (1.0000) time: 0.5162 [2021-03-25 13:45:58 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 50/1251] eta: 0:11:41 lr: 0.000911 loss: 3.6716 (3.5418) grad_norm: 0.9901 (1.0092) time: 0.5154 [2021-03-25 13:46:03 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 60/1251] eta: 0:11:19 lr: 0.000911 loss: 3.6613 (3.5312) grad_norm: 1.0439 (1.0171) time: 0.5019 [2021-03-25 13:46:08 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 70/1251] eta: 0:11:02 lr: 0.000911 loss: 3.6305 (3.5594) grad_norm: 1.1012 (1.0287) time: 0.5024 [2021-03-25 13:46:13 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 80/1251] eta: 0:10:49 lr: 0.000911 loss: 3.9393 (3.6101) grad_norm: 1.0401 (1.0321) time: 0.5066 [2021-03-25 13:46:18 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 90/1251] eta: 0:10:37 lr: 0.000911 loss: 4.0960 (3.6569) grad_norm: 1.0309 (1.0339) time: 0.5072 [2021-03-25 13:46:23 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 100/1251] eta: 0:10:27 lr: 0.000911 loss: 3.8373 (3.6577) grad_norm: 0.9876 (1.0350) time: 0.5035 [2021-03-25 13:46:28 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 110/1251] eta: 0:10:18 lr: 0.000911 loss: 3.7359 (3.6548) grad_norm: 1.0155 (1.0355) time: 0.5081 [2021-03-25 13:46:33 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 120/1251] eta: 0:10:09 lr: 0.000911 loss: 3.5780 (3.6364) grad_norm: 1.0155 (1.0321) time: 0.5110 [2021-03-25 13:46:38 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 130/1251] eta: 0:10:01 lr: 0.000911 loss: 3.6213 (3.6426) grad_norm: 0.9977 (1.0299) time: 0.5096 [2021-03-25 13:46:43 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 140/1251] eta: 0:09:53 lr: 0.000911 loss: 3.8677 (3.6405) grad_norm: 0.9908 (1.0256) time: 0.5045 [2021-03-25 13:46:48 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 150/1251] eta: 0:09:45 lr: 0.000911 loss: 3.8118 (3.6467) grad_norm: 1.0167 (1.0284) time: 0.5012 [2021-03-25 13:46:53 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 160/1251] eta: 0:09:38 lr: 0.000911 loss: 3.8118 (3.6523) grad_norm: 1.1188 (1.0356) time: 0.5009 [2021-03-25 13:46:58 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 170/1251] eta: 0:09:31 lr: 0.000911 loss: 3.7896 (3.6586) grad_norm: 1.1105 (1.0401) time: 0.5022 [2021-03-25 13:47:03 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 180/1251] eta: 0:09:25 lr: 0.000911 loss: 3.7741 (3.6597) grad_norm: 1.0264 (1.0383) time: 0.5086 [2021-03-25 13:47:08 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 190/1251] eta: 0:09:18 lr: 0.000911 loss: 3.7741 (3.6636) grad_norm: 1.0264 (1.0395) time: 0.5045 [2021-03-25 13:47:13 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 200/1251] eta: 0:09:11 lr: 0.000911 loss: 3.7725 (3.6620) grad_norm: 0.9921 (1.0375) time: 0.5012 [2021-03-25 13:47:19 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 210/1251] eta: 0:09:05 lr: 0.000911 loss: 3.7725 (3.6678) grad_norm: 0.9836 (1.0377) time: 0.5087 [2021-03-25 13:47:24 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 220/1251] eta: 0:08:59 lr: 0.000911 loss: 3.8109 (3.6652) grad_norm: 0.9865 (1.0358) time: 0.5062 [2021-03-25 13:47:29 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 230/1251] eta: 0:08:53 lr: 0.000911 loss: 3.6969 (3.6600) grad_norm: 0.9866 (1.0365) time: 0.5004 [2021-03-25 13:47:34 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 240/1251] eta: 0:08:47 lr: 0.000911 loss: 3.8408 (3.6623) grad_norm: 1.0307 (1.0377) time: 0.5024 [2021-03-25 13:47:39 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 250/1251] eta: 0:08:41 lr: 0.000911 loss: 3.4693 (3.6572) grad_norm: 1.0748 (1.0433) time: 0.5057 [2021-03-25 13:47:44 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 260/1251] eta: 0:08:35 lr: 0.000911 loss: 3.7254 (3.6651) grad_norm: 1.0614 (1.0424) time: 0.5085 [2021-03-25 13:47:49 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 270/1251] eta: 0:08:30 lr: 0.000911 loss: 3.8675 (3.6639) grad_norm: 1.0584 (1.0435) time: 0.5073 [2021-03-25 13:47:54 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 280/1251] eta: 0:08:24 lr: 0.000911 loss: 3.8852 (3.6729) grad_norm: 1.0584 (1.0440) time: 0.5025 [2021-03-25 13:47:59 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 290/1251] eta: 0:08:18 lr: 0.000911 loss: 3.7933 (3.6728) grad_norm: 1.0074 (1.0435) time: 0.5054 [2021-03-25 13:48:04 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 300/1251] eta: 0:08:13 lr: 0.000911 loss: 3.6491 (3.6719) grad_norm: 0.9901 (1.0415) time: 0.5058 [2021-03-25 13:48:09 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 310/1251] eta: 0:08:07 lr: 0.000911 loss: 3.8899 (3.6692) grad_norm: 1.0195 (1.0430) time: 0.5091 [2021-03-25 13:48:14 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 320/1251] eta: 0:08:02 lr: 0.000911 loss: 3.8899 (3.6703) grad_norm: 1.0482 (1.0422) time: 0.5080 [2021-03-25 13:48:19 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 330/1251] eta: 0:07:56 lr: 0.000911 loss: 3.9279 (3.6793) grad_norm: 1.0567 (1.0442) time: 0.4970 [2021-03-25 13:48:24 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 340/1251] eta: 0:07:50 lr: 0.000911 loss: 4.0546 (3.6846) grad_norm: 1.0036 (1.0426) time: 0.4996 [2021-03-25 13:48:29 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 350/1251] eta: 0:07:45 lr: 0.000911 loss: 3.8364 (3.6844) grad_norm: 0.9920 (1.0415) time: 0.5037 [2021-03-25 13:48:34 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 360/1251] eta: 0:07:39 lr: 0.000911 loss: 3.8411 (3.6874) grad_norm: 1.0114 (1.0421) time: 0.4993 [2021-03-25 13:48:39 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 370/1251] eta: 0:07:34 lr: 0.000911 loss: 3.8541 (3.6854) grad_norm: 0.9491 (1.0403) time: 0.4986 [2021-03-25 13:48:44 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 380/1251] eta: 0:07:28 lr: 0.000911 loss: 3.6483 (3.6815) grad_norm: 0.9668 (1.0391) time: 0.4993 [2021-03-25 13:48:49 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 390/1251] eta: 0:07:22 lr: 0.000911 loss: 3.6281 (3.6851) grad_norm: 1.0307 (1.0382) time: 0.4977 [2021-03-25 13:48:54 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 400/1251] eta: 0:07:17 lr: 0.000911 loss: 4.0030 (3.6886) grad_norm: 1.0383 (1.0392) time: 0.5019 [2021-03-25 13:48:59 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 410/1251] eta: 0:07:12 lr: 0.000910 loss: 3.6696 (3.6894) grad_norm: 1.1338 (1.0397) time: 0.5079 [2021-03-25 13:49:04 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 420/1251] eta: 0:07:07 lr: 0.000910 loss: 3.8007 (3.6930) grad_norm: 1.0663 (1.0415) time: 0.5078 [2021-03-25 13:49:09 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 430/1251] eta: 0:07:01 lr: 0.000910 loss: 4.0008 (3.6996) grad_norm: 1.0796 (1.0422) time: 0.5070 [2021-03-25 13:49:14 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 440/1251] eta: 0:06:56 lr: 0.000910 loss: 3.9327 (3.7042) grad_norm: 1.0545 (1.0415) time: 0.5047 [2021-03-25 13:49:20 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 450/1251] eta: 0:06:51 lr: 0.000910 loss: 3.8063 (3.7051) grad_norm: 0.9705 (1.0398) time: 0.5083 [2021-03-25 13:49:25 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 460/1251] eta: 0:06:46 lr: 0.000910 loss: 3.6820 (3.7026) grad_norm: 1.0027 (1.0414) time: 0.5127 [2021-03-25 13:49:30 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 470/1251] eta: 0:06:40 lr: 0.000910 loss: 3.6519 (3.7014) grad_norm: 1.1484 (1.0435) time: 0.5095 [2021-03-25 13:49:35 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 480/1251] eta: 0:06:35 lr: 0.000910 loss: 3.7347 (3.7078) grad_norm: 1.0787 (1.0444) time: 0.5051 [2021-03-25 13:49:40 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 490/1251] eta: 0:06:30 lr: 0.000910 loss: 3.6915 (3.7021) grad_norm: 1.0522 (1.0464) time: 0.5024 [2021-03-25 13:49:45 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 500/1251] eta: 0:06:25 lr: 0.000910 loss: 3.3370 (3.6967) grad_norm: 1.0522 (1.0464) time: 0.5042 [2021-03-25 13:49:50 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 510/1251] eta: 0:06:19 lr: 0.000910 loss: 3.8486 (3.7031) grad_norm: 1.0907 (1.0474) time: 0.5076 [2021-03-25 13:49:55 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 520/1251] eta: 0:06:14 lr: 0.000910 loss: 3.9510 (3.7038) grad_norm: 1.0502 (1.0468) time: 0.5056 [2021-03-25 13:50:00 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 530/1251] eta: 0:06:09 lr: 0.000910 loss: 3.8310 (3.7054) grad_norm: 1.0508 (1.0475) time: 0.5053 [2021-03-25 13:50:05 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 540/1251] eta: 0:06:04 lr: 0.000910 loss: 3.9341 (3.7121) grad_norm: 1.0508 (1.0467) time: 0.5076 [2021-03-25 13:50:10 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 550/1251] eta: 0:05:59 lr: 0.000910 loss: 3.8528 (3.7077) grad_norm: 1.0467 (1.0479) time: 0.5208 [2021-03-25 13:50:16 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 560/1251] eta: 0:05:54 lr: 0.000910 loss: 3.6982 (3.7070) grad_norm: 1.0307 (1.0470) time: 0.5254 [2021-03-25 13:50:21 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 570/1251] eta: 0:05:49 lr: 0.000910 loss: 3.8807 (3.7116) grad_norm: 0.9842 (1.0464) time: 0.5094 [2021-03-25 13:50:26 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 580/1251] eta: 0:05:43 lr: 0.000910 loss: 4.1959 (3.7192) grad_norm: 0.9821 (1.0460) time: 0.5043 [2021-03-25 13:50:31 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 590/1251] eta: 0:05:38 lr: 0.000910 loss: 3.9742 (3.7184) grad_norm: 1.0325 (1.0471) time: 0.5176 [2021-03-25 13:50:36 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 600/1251] eta: 0:05:33 lr: 0.000910 loss: 3.9143 (3.7189) grad_norm: 1.0325 (1.0470) time: 0.5144 [2021-03-25 13:50:41 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 610/1251] eta: 0:05:28 lr: 0.000910 loss: 3.7344 (3.7171) grad_norm: 1.0062 (1.0467) time: 0.5024 [2021-03-25 13:50:46 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 620/1251] eta: 0:05:23 lr: 0.000910 loss: 3.6772 (3.7179) grad_norm: 0.9881 (1.0464) time: 0.5030 [2021-03-25 13:50:51 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 630/1251] eta: 0:05:18 lr: 0.000910 loss: 3.8550 (3.7167) grad_norm: 1.0313 (1.0465) time: 0.5048 [2021-03-25 13:50:56 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 640/1251] eta: 0:05:12 lr: 0.000910 loss: 3.9042 (3.7186) grad_norm: 1.0321 (1.0460) time: 0.5082 [2021-03-25 13:51:01 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 650/1251] eta: 0:05:07 lr: 0.000910 loss: 3.9127 (3.7207) grad_norm: 1.0323 (1.0463) time: 0.5014 [2021-03-25 13:51:06 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 660/1251] eta: 0:05:02 lr: 0.000910 loss: 3.8621 (3.7207) grad_norm: 1.0637 (1.0469) time: 0.5033 [2021-03-25 13:51:11 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 670/1251] eta: 0:04:57 lr: 0.000910 loss: 3.8358 (3.7223) grad_norm: 1.0354 (1.0477) time: 0.5061 [2021-03-25 13:51:16 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 680/1251] eta: 0:04:52 lr: 0.000910 loss: 3.8358 (3.7218) grad_norm: 1.0274 (1.0481) time: 0.5036 [2021-03-25 13:51:21 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 690/1251] eta: 0:04:46 lr: 0.000910 loss: 3.5799 (3.7185) grad_norm: 0.9782 (1.0468) time: 0.5002 [2021-03-25 13:51:26 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 700/1251] eta: 0:04:41 lr: 0.000910 loss: 3.6352 (3.7184) grad_norm: 0.9411 (1.0461) time: 0.5001 [2021-03-25 13:51:31 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 710/1251] eta: 0:04:36 lr: 0.000910 loss: 3.7717 (3.7207) grad_norm: 1.0513 (1.0471) time: 0.5071 [2021-03-25 13:51:37 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 720/1251] eta: 0:04:31 lr: 0.000910 loss: 3.8679 (3.7218) grad_norm: 1.0876 (1.0472) time: 0.5068 [2021-03-25 13:51:42 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 730/1251] eta: 0:04:26 lr: 0.000910 loss: 3.7873 (3.7225) grad_norm: 1.0289 (1.0471) time: 0.5108 [2021-03-25 13:51:47 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 740/1251] eta: 0:04:21 lr: 0.000910 loss: 3.6157 (3.7189) grad_norm: 1.0289 (1.0473) time: 0.5241 [2021-03-25 13:51:52 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 750/1251] eta: 0:04:16 lr: 0.000910 loss: 3.6899 (3.7195) grad_norm: 1.0110 (1.0464) time: 0.5295 [2021-03-25 13:51:57 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 760/1251] eta: 0:04:11 lr: 0.000910 loss: 3.6899 (3.7180) grad_norm: 1.0110 (1.0466) time: 0.5166 [2021-03-25 13:52:02 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 770/1251] eta: 0:04:06 lr: 0.000910 loss: 3.6598 (3.7164) grad_norm: 1.0264 (1.0467) time: 0.5049 [2021-03-25 13:52:08 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 780/1251] eta: 0:04:00 lr: 0.000910 loss: 3.7548 (3.7156) grad_norm: 1.0225 (1.0467) time: 0.5074 [2021-03-25 13:52:13 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 790/1251] eta: 0:03:55 lr: 0.000910 loss: 3.6815 (3.7146) grad_norm: 0.9559 (1.0458) time: 0.5161 [2021-03-25 13:52:18 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 800/1251] eta: 0:03:50 lr: 0.000910 loss: 3.6815 (3.7138) grad_norm: 0.9868 (1.0452) time: 0.5118 [2021-03-25 13:52:23 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 810/1251] eta: 0:03:45 lr: 0.000910 loss: 3.8080 (3.7141) grad_norm: 0.9920 (1.0452) time: 0.5072 [2021-03-25 13:52:28 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 820/1251] eta: 0:03:40 lr: 0.000910 loss: 3.7938 (3.7136) grad_norm: 1.0069 (1.0455) time: 0.5111 [2021-03-25 13:52:33 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 830/1251] eta: 0:03:35 lr: 0.000909 loss: 3.6557 (3.7129) grad_norm: 1.0827 (1.0460) time: 0.5059 [2021-03-25 13:52:38 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 840/1251] eta: 0:03:30 lr: 0.000909 loss: 3.7397 (3.7136) grad_norm: 1.0827 (1.0463) time: 0.5045 [2021-03-25 13:52:43 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 850/1251] eta: 0:03:25 lr: 0.000909 loss: 3.7403 (3.7117) grad_norm: 0.9878 (1.0454) time: 0.5054 [2021-03-25 13:52:48 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 860/1251] eta: 0:03:19 lr: 0.000909 loss: 3.7403 (3.7124) grad_norm: 0.9798 (1.0454) time: 0.5020 [2021-03-25 13:52:53 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 870/1251] eta: 0:03:14 lr: 0.000909 loss: 3.7159 (3.7116) grad_norm: 0.9831 (1.0449) time: 0.5033 [2021-03-25 13:52:58 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 880/1251] eta: 0:03:09 lr: 0.000909 loss: 3.8002 (3.7129) grad_norm: 0.9964 (1.0446) time: 0.5030 [2021-03-25 13:53:03 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 890/1251] eta: 0:03:04 lr: 0.000909 loss: 3.6702 (3.7118) grad_norm: 1.0354 (1.0451) time: 0.4996 [2021-03-25 13:53:08 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 900/1251] eta: 0:02:59 lr: 0.000909 loss: 3.6937 (3.7129) grad_norm: 1.0165 (1.0445) time: 0.4993 [2021-03-25 13:53:13 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 910/1251] eta: 0:02:54 lr: 0.000909 loss: 3.6405 (3.7098) grad_norm: 1.0024 (1.0448) time: 0.5000 [2021-03-25 13:53:18 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 920/1251] eta: 0:02:48 lr: 0.000909 loss: 3.7481 (3.7118) grad_norm: 1.0704 (1.0454) time: 0.4991 [2021-03-25 13:53:23 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 930/1251] eta: 0:02:43 lr: 0.000909 loss: 3.9789 (3.7138) grad_norm: 1.0375 (1.0456) time: 0.5014 [2021-03-25 13:53:28 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 940/1251] eta: 0:02:38 lr: 0.000909 loss: 3.8955 (3.7142) grad_norm: 1.0505 (1.0462) time: 0.5139 [2021-03-25 13:53:33 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 950/1251] eta: 0:02:33 lr: 0.000909 loss: 3.8147 (3.7126) grad_norm: 1.0360 (1.0451) time: 0.5136 [2021-03-25 13:53:39 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 960/1251] eta: 0:02:28 lr: 0.000909 loss: 3.6336 (3.7114) grad_norm: 0.9170 (1.0445) time: 0.5049 [2021-03-25 13:53:44 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 970/1251] eta: 0:02:23 lr: 0.000909 loss: 3.6355 (3.7113) grad_norm: 0.9830 (1.0443) time: 0.5031 [2021-03-25 13:53:49 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 980/1251] eta: 0:02:18 lr: 0.000909 loss: 3.8610 (3.7116) grad_norm: 1.0150 (1.0444) time: 0.4993 [2021-03-25 13:53:54 swin_small_patch4_window7_224] INFO: Epoch: [58] [ 990/1251] eta: 0:02:13 lr: 0.000909 loss: 3.8483 (3.7096) grad_norm: 1.0475 (1.0444) time: 0.5022 [2021-03-25 13:53:59 swin_small_patch4_window7_224] INFO: Epoch: [58] [1000/1251] eta: 0:02:08 lr: 0.000909 loss: 3.5845 (3.7069) grad_norm: 1.0364 (1.0445) time: 0.5055 [2021-03-25 13:54:04 swin_small_patch4_window7_224] INFO: Epoch: [58] [1010/1251] eta: 0:02:02 lr: 0.000909 loss: 3.6288 (3.7070) grad_norm: 0.9982 (1.0444) time: 0.5062 [2021-03-25 13:54:09 swin_small_patch4_window7_224] INFO: Epoch: [58] [1020/1251] eta: 0:01:57 lr: 0.000909 loss: 3.7350 (3.7072) grad_norm: 0.9894 (1.0441) time: 0.5067 [2021-03-25 13:54:14 swin_small_patch4_window7_224] INFO: Epoch: [58] [1030/1251] eta: 0:01:52 lr: 0.000909 loss: 3.7350 (3.7068) grad_norm: 0.9998 (1.0439) time: 0.5046 [2021-03-25 13:54:19 swin_small_patch4_window7_224] INFO: Epoch: [58] [1040/1251] eta: 0:01:47 lr: 0.000909 loss: 3.6976 (3.7050) grad_norm: 1.0263 (1.0446) time: 0.5060 [2021-03-25 13:54:24 swin_small_patch4_window7_224] INFO: Epoch: [58] [1050/1251] eta: 0:01:42 lr: 0.000909 loss: 3.8916 (3.7064) grad_norm: 1.0663 (1.0449) time: 0.5161 [2021-03-25 13:54:29 swin_small_patch4_window7_224] INFO: Epoch: [58] [1060/1251] eta: 0:01:37 lr: 0.000909 loss: 3.8026 (3.7048) grad_norm: 1.0583 (1.0448) time: 0.5146 [2021-03-25 13:54:34 swin_small_patch4_window7_224] INFO: Epoch: [58] [1070/1251] eta: 0:01:32 lr: 0.000909 loss: 3.8026 (3.7069) grad_norm: 0.9908 (1.0440) time: 0.5031 [2021-03-25 13:54:39 swin_small_patch4_window7_224] INFO: Epoch: [58] [1080/1251] eta: 0:01:27 lr: 0.000909 loss: 4.0053 (3.7081) grad_norm: 0.9658 (1.0444) time: 0.5015 [2021-03-25 13:54:44 swin_small_patch4_window7_224] INFO: Epoch: [58] [1090/1251] eta: 0:01:22 lr: 0.000909 loss: 3.9012 (3.7072) grad_norm: 0.9894 (1.0438) time: 0.5027 [2021-03-25 13:54:49 swin_small_patch4_window7_224] INFO: Epoch: [58] [1100/1251] eta: 0:01:16 lr: 0.000909 loss: 3.4081 (3.7040) grad_norm: 0.9148 (1.0430) time: 0.5087 [2021-03-25 13:54:54 swin_small_patch4_window7_224] INFO: Epoch: [58] [1110/1251] eta: 0:01:11 lr: 0.000909 loss: 3.4668 (3.7034) grad_norm: 0.9333 (1.0426) time: 0.5077 [2021-03-25 13:54:59 swin_small_patch4_window7_224] INFO: Epoch: [58] [1120/1251] eta: 0:01:06 lr: 0.000909 loss: 3.9396 (3.7051) grad_norm: 0.9887 (1.0427) time: 0.5022 [2021-03-25 13:55:04 swin_small_patch4_window7_224] INFO: Epoch: [58] [1130/1251] eta: 0:01:01 lr: 0.000909 loss: 3.7584 (3.7035) grad_norm: 1.0016 (1.0428) time: 0.5035 [2021-03-25 13:55:10 swin_small_patch4_window7_224] INFO: Epoch: [58] [1140/1251] eta: 0:00:56 lr: 0.000909 loss: 3.4037 (3.7011) grad_norm: 1.0517 (1.0434) time: 0.5049 [2021-03-25 13:55:15 swin_small_patch4_window7_224] INFO: Epoch: [58] [1150/1251] eta: 0:00:51 lr: 0.000909 loss: 3.6444 (3.6998) grad_norm: 1.0517 (1.0435) time: 0.5098 [2021-03-25 13:55:20 swin_small_patch4_window7_224] INFO: Epoch: [58] [1160/1251] eta: 0:00:46 lr: 0.000909 loss: 3.5692 (3.6969) grad_norm: 1.0113 (1.0433) time: 0.5089 [2021-03-25 13:55:25 swin_small_patch4_window7_224] INFO: Epoch: [58] [1170/1251] eta: 0:00:41 lr: 0.000909 loss: 3.5963 (3.6972) grad_norm: 1.0113 (1.0431) time: 0.5039 [2021-03-25 13:55:30 swin_small_patch4_window7_224] INFO: Epoch: [58] [1180/1251] eta: 0:00:36 lr: 0.000909 loss: 3.9552 (3.6984) grad_norm: 1.0192 (1.0433) time: 0.5044 [2021-03-25 13:55:35 swin_small_patch4_window7_224] INFO: Epoch: [58] [1190/1251] eta: 0:00:31 lr: 0.000909 loss: 3.9273 (3.6984) grad_norm: 1.0479 (1.0435) time: 0.5064 [2021-03-25 13:55:40 swin_small_patch4_window7_224] INFO: Epoch: [58] [1200/1251] eta: 0:00:25 lr: 0.000909 loss: 3.7822 (3.6982) grad_norm: 1.0452 (1.0433) time: 0.5077 [2021-03-25 13:55:45 swin_small_patch4_window7_224] INFO: Epoch: [58] [1210/1251] eta: 0:00:20 lr: 0.000909 loss: 3.8374 (3.6983) grad_norm: 0.9695 (1.0434) time: 0.5052 [2021-03-25 13:55:50 swin_small_patch4_window7_224] INFO: Epoch: [58] [1220/1251] eta: 0:00:15 lr: 0.000909 loss: 3.7205 (3.6974) grad_norm: 0.9740 (1.0433) time: 0.5005 [2021-03-25 13:55:55 swin_small_patch4_window7_224] INFO: Epoch: [58] [1230/1251] eta: 0:00:10 lr: 0.000909 loss: 3.7133 (3.6976) grad_norm: 1.0399 (1.0433) time: 0.5007 [2021-03-25 13:56:00 swin_small_patch4_window7_224] INFO: Epoch: [58] [1240/1251] eta: 0:00:05 lr: 0.000909 loss: 3.8716 (3.6988) grad_norm: 1.0407 (1.0433) time: 0.5058 [2021-03-25 13:56:05 swin_small_patch4_window7_224] INFO: Epoch: [58] [1250/1251] eta: 0:00:00 lr: 0.000908 loss: 3.8374 (3.6984) grad_norm: 1.0530 (1.0441) time: 0.5049 [2021-03-25 13:56:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 1.1312 (1.1312) acc1: 70.3125 (70.3125) acc5: 95.3125 (95.3125) [2021-03-25 13:56:13 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1964 (1.1971) acc1: 68.7500 (71.0227) acc5: 92.1875 (91.6193) [2021-03-25 13:56:14 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1365 (1.1658) acc1: 70.3125 (71.4286) acc5: 92.1875 (92.1131) [2021-03-25 13:56:17 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1365 (1.1710) acc1: 71.8750 (71.8246) acc5: 90.6250 (91.7339) [2021-03-25 13:56:19 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1412 (1.1735) acc1: 71.8750 (72.1799) acc5: 92.1875 (91.9207) [2021-03-25 13:56:20 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0881 (1.1715) acc1: 71.8750 (72.2880) acc5: 92.1875 (92.1280) [2021-03-25 13:56:22 swin_small_patch4_window7_224] INFO: * Acc@1 73.276 Acc@5 92.196 loss 1.146 [2021-03-25 13:56:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.3% [2021-03-25 13:56:22 swin_small_patch4_window7_224] INFO: Max accuracy: 73.28% [2021-03-25 13:56:27 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 0/1251] eta: 1:27:51 lr: 0.000908 loss: 4.1302 (4.1302) grad_norm: 1.4006 (1.4006) time: 4.2141 [2021-03-25 13:56:32 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 10/1251] eta: 0:17:35 lr: 0.000908 loss: 3.9116 (3.7675) grad_norm: 1.0622 (1.0891) time: 0.8503 [2021-03-25 13:56:37 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 20/1251] eta: 0:14:02 lr: 0.000908 loss: 3.5909 (3.6405) grad_norm: 1.0158 (1.0436) time: 0.5083 [2021-03-25 13:56:42 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 30/1251] eta: 0:12:44 lr: 0.000908 loss: 3.4535 (3.6981) grad_norm: 0.9969 (1.0195) time: 0.5023 [2021-03-25 13:56:47 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 40/1251] eta: 0:12:01 lr: 0.000908 loss: 3.9103 (3.7133) grad_norm: 0.9969 (1.0232) time: 0.5031 [2021-03-25 13:56:52 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 50/1251] eta: 0:11:34 lr: 0.000908 loss: 3.7363 (3.6696) grad_norm: 1.0230 (1.0301) time: 0.5052 [2021-03-25 13:56:57 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 60/1251] eta: 0:11:13 lr: 0.000908 loss: 3.6368 (3.6365) grad_norm: 0.9655 (1.0179) time: 0.5018 [2021-03-25 13:57:02 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 70/1251] eta: 0:10:56 lr: 0.000908 loss: 3.6129 (3.6078) grad_norm: 0.9656 (1.0211) time: 0.4996 [2021-03-25 13:57:07 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 80/1251] eta: 0:10:44 lr: 0.000908 loss: 3.5180 (3.5794) grad_norm: 1.0432 (inf) time: 0.5051 [2021-03-25 13:57:12 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 90/1251] eta: 0:10:32 lr: 0.000908 loss: 3.6199 (3.5748) grad_norm: 0.9867 (inf) time: 0.5051 [2021-03-25 13:57:17 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 100/1251] eta: 0:10:22 lr: 0.000908 loss: 3.6902 (3.5991) grad_norm: 0.9867 (inf) time: 0.5036 [2021-03-25 13:57:22 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 110/1251] eta: 0:10:13 lr: 0.000908 loss: 3.9434 (3.6342) grad_norm: 1.0135 (inf) time: 0.5028 [2021-03-25 13:57:27 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 120/1251] eta: 0:10:04 lr: 0.000908 loss: 3.7751 (3.6384) grad_norm: 1.0267 (inf) time: 0.5018 [2021-03-25 13:57:32 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 130/1251] eta: 0:09:57 lr: 0.000908 loss: 3.6065 (3.6198) grad_norm: 1.0251 (inf) time: 0.5074 [2021-03-25 13:57:38 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 140/1251] eta: 0:09:50 lr: 0.000908 loss: 3.4571 (3.6013) grad_norm: 1.0328 (inf) time: 0.5136 [2021-03-25 13:57:42 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 150/1251] eta: 0:09:42 lr: 0.000908 loss: 3.5264 (3.5963) grad_norm: 1.0224 (inf) time: 0.5066 [2021-03-25 13:57:48 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 160/1251] eta: 0:09:35 lr: 0.000908 loss: 3.7092 (3.6172) grad_norm: 1.0224 (inf) time: 0.5007 [2021-03-25 13:57:52 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 170/1251] eta: 0:09:28 lr: 0.000908 loss: 3.7272 (3.6281) grad_norm: 1.0572 (inf) time: 0.4996 [2021-03-25 13:57:58 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 180/1251] eta: 0:09:22 lr: 0.000908 loss: 3.6583 (3.6317) grad_norm: 0.9641 (inf) time: 0.5045 [2021-03-25 13:58:03 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 190/1251] eta: 0:09:16 lr: 0.000908 loss: 3.6771 (3.6486) grad_norm: 0.9549 (inf) time: 0.5131 [2021-03-25 13:58:08 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 200/1251] eta: 0:09:10 lr: 0.000908 loss: 3.8047 (3.6511) grad_norm: 1.0011 (inf) time: 0.5127 [2021-03-25 13:58:13 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 210/1251] eta: 0:09:04 lr: 0.000908 loss: 3.6659 (3.6536) grad_norm: 1.0700 (inf) time: 0.5065 [2021-03-25 13:58:18 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 220/1251] eta: 0:08:58 lr: 0.000908 loss: 3.8314 (3.6693) grad_norm: 1.0928 (inf) time: 0.5047 [2021-03-25 13:58:23 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 230/1251] eta: 0:08:52 lr: 0.000908 loss: 3.8701 (3.6669) grad_norm: 1.0555 (inf) time: 0.5101 [2021-03-25 13:58:28 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 240/1251] eta: 0:08:47 lr: 0.000908 loss: 3.6352 (3.6670) grad_norm: 1.0210 (inf) time: 0.5107 [2021-03-25 13:58:33 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 250/1251] eta: 0:08:41 lr: 0.000908 loss: 3.6831 (3.6653) grad_norm: 1.0053 (inf) time: 0.5119 [2021-03-25 13:58:38 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 260/1251] eta: 0:08:35 lr: 0.000908 loss: 3.6060 (3.6633) grad_norm: 0.9991 (inf) time: 0.5086 [2021-03-25 13:58:43 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 270/1251] eta: 0:08:29 lr: 0.000908 loss: 3.7825 (3.6721) grad_norm: 1.0233 (inf) time: 0.5022 [2021-03-25 13:58:48 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 280/1251] eta: 0:08:23 lr: 0.000908 loss: 3.7870 (3.6662) grad_norm: 1.0360 (inf) time: 0.4976 [2021-03-25 13:58:53 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 290/1251] eta: 0:08:17 lr: 0.000908 loss: 3.4369 (3.6657) grad_norm: 1.0021 (inf) time: 0.4974 [2021-03-25 13:58:58 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 300/1251] eta: 0:08:12 lr: 0.000908 loss: 3.6305 (3.6724) grad_norm: 0.9984 (inf) time: 0.4996 [2021-03-25 13:59:03 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 310/1251] eta: 0:08:06 lr: 0.000908 loss: 4.0590 (3.6865) grad_norm: 0.9907 (inf) time: 0.4978 [2021-03-25 13:59:08 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 320/1251] eta: 0:08:00 lr: 0.000908 loss: 4.0057 (3.6900) grad_norm: 0.9532 (inf) time: 0.5049 [2021-03-25 13:59:14 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 330/1251] eta: 0:07:55 lr: 0.000908 loss: 3.6293 (3.6843) grad_norm: 0.9992 (inf) time: 0.5160 [2021-03-25 13:59:19 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 340/1251] eta: 0:07:50 lr: 0.000908 loss: 3.5896 (3.6835) grad_norm: 1.0069 (inf) time: 0.5082 [2021-03-25 13:59:24 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 350/1251] eta: 0:07:44 lr: 0.000908 loss: 3.7877 (3.6837) grad_norm: 0.9281 (inf) time: 0.5012 [2021-03-25 13:59:29 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 360/1251] eta: 0:07:39 lr: 0.000908 loss: 3.7277 (3.6882) grad_norm: 0.9671 (inf) time: 0.5006 [2021-03-25 13:59:34 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 370/1251] eta: 0:07:33 lr: 0.000908 loss: 3.6925 (3.6845) grad_norm: 0.9912 (inf) time: 0.5005 [2021-03-25 13:59:39 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 380/1251] eta: 0:07:28 lr: 0.000908 loss: 3.6925 (3.6841) grad_norm: 1.0452 (inf) time: 0.5004 [2021-03-25 13:59:44 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 390/1251] eta: 0:07:22 lr: 0.000908 loss: 3.7628 (3.6870) grad_norm: 1.0001 (inf) time: 0.4963 [2021-03-25 13:59:49 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 400/1251] eta: 0:07:17 lr: 0.000908 loss: 3.4396 (3.6791) grad_norm: 0.9803 (inf) time: 0.4989 [2021-03-25 13:59:54 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 410/1251] eta: 0:07:11 lr: 0.000908 loss: 3.3234 (3.6727) grad_norm: 1.0518 (inf) time: 0.4990 [2021-03-25 13:59:59 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 420/1251] eta: 0:07:06 lr: 0.000907 loss: 3.4755 (3.6715) grad_norm: 0.9653 (inf) time: 0.4966 [2021-03-25 14:00:04 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 430/1251] eta: 0:07:01 lr: 0.000907 loss: 3.6276 (3.6669) grad_norm: 0.9463 (inf) time: 0.5067 [2021-03-25 14:00:09 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 440/1251] eta: 0:06:55 lr: 0.000907 loss: 3.6779 (3.6700) grad_norm: 0.9463 (inf) time: 0.5101 [2021-03-25 14:00:14 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 450/1251] eta: 0:06:50 lr: 0.000907 loss: 3.5955 (3.6628) grad_norm: 0.9393 (inf) time: 0.5081 [2021-03-25 14:00:19 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 460/1251] eta: 0:06:45 lr: 0.000907 loss: 3.6225 (3.6715) grad_norm: 0.9714 (inf) time: 0.5021 [2021-03-25 14:00:24 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 470/1251] eta: 0:06:39 lr: 0.000907 loss: 4.0433 (3.6762) grad_norm: 0.9857 (inf) time: 0.4975 [2021-03-25 14:00:29 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 480/1251] eta: 0:06:34 lr: 0.000907 loss: 3.8700 (3.6730) grad_norm: 1.0599 (inf) time: 0.5097 [2021-03-25 14:00:34 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 490/1251] eta: 0:06:29 lr: 0.000907 loss: 3.7177 (3.6741) grad_norm: 1.0605 (inf) time: 0.5109 [2021-03-25 14:00:39 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 500/1251] eta: 0:06:24 lr: 0.000907 loss: 3.6913 (3.6718) grad_norm: 1.0667 (inf) time: 0.5049 [2021-03-25 14:00:44 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 510/1251] eta: 0:06:19 lr: 0.000907 loss: 3.6754 (3.6728) grad_norm: 1.0851 (inf) time: 0.5054 [2021-03-25 14:00:49 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 520/1251] eta: 0:06:13 lr: 0.000907 loss: 3.8574 (3.6760) grad_norm: 1.0492 (inf) time: 0.5039 [2021-03-25 14:00:54 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 530/1251] eta: 0:06:08 lr: 0.000907 loss: 3.8340 (3.6777) grad_norm: 0.9898 (inf) time: 0.5015 [2021-03-25 14:00:59 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 540/1251] eta: 0:06:03 lr: 0.000907 loss: 3.8490 (3.6800) grad_norm: 1.0150 (inf) time: 0.5013 [2021-03-25 14:01:05 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 550/1251] eta: 0:05:58 lr: 0.000907 loss: 4.0299 (3.6861) grad_norm: 0.9767 (inf) time: 0.5181 [2021-03-25 14:01:10 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 560/1251] eta: 0:05:53 lr: 0.000907 loss: 3.8509 (3.6855) grad_norm: 0.9767 (inf) time: 0.5212 [2021-03-25 14:01:15 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 570/1251] eta: 0:05:48 lr: 0.000907 loss: 3.6555 (3.6817) grad_norm: 1.0240 (inf) time: 0.4990 [2021-03-25 14:01:20 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 580/1251] eta: 0:05:42 lr: 0.000907 loss: 3.6612 (3.6834) grad_norm: 0.9800 (inf) time: 0.4973 [2021-03-25 14:01:25 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 590/1251] eta: 0:05:37 lr: 0.000907 loss: 3.9359 (3.6868) grad_norm: 0.9935 (inf) time: 0.5051 [2021-03-25 14:01:30 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 600/1251] eta: 0:05:32 lr: 0.000907 loss: 3.7330 (3.6846) grad_norm: 1.0046 (inf) time: 0.5043 [2021-03-25 14:01:35 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 610/1251] eta: 0:05:27 lr: 0.000907 loss: 3.6666 (3.6823) grad_norm: 1.0156 (inf) time: 0.4998 [2021-03-25 14:01:40 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 620/1251] eta: 0:05:22 lr: 0.000907 loss: 3.6059 (3.6831) grad_norm: 1.0105 (inf) time: 0.4984 [2021-03-25 14:01:45 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 630/1251] eta: 0:05:16 lr: 0.000907 loss: 3.6500 (3.6819) grad_norm: 0.9839 (inf) time: 0.5027 [2021-03-25 14:01:50 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 640/1251] eta: 0:05:11 lr: 0.000907 loss: 3.7434 (3.6795) grad_norm: 0.9839 (inf) time: 0.5023 [2021-03-25 14:01:55 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 650/1251] eta: 0:05:06 lr: 0.000907 loss: 3.7223 (3.6796) grad_norm: 0.9934 (inf) time: 0.5015 [2021-03-25 14:02:00 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 660/1251] eta: 0:05:01 lr: 0.000907 loss: 3.9110 (3.6868) grad_norm: 1.0190 (inf) time: 0.5038 [2021-03-25 14:02:05 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 670/1251] eta: 0:04:56 lr: 0.000907 loss: 3.8613 (3.6873) grad_norm: 1.0057 (inf) time: 0.5011 [2021-03-25 14:02:10 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 680/1251] eta: 0:04:51 lr: 0.000907 loss: 3.7174 (3.6859) grad_norm: 1.0309 (inf) time: 0.5020 [2021-03-25 14:02:15 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 690/1251] eta: 0:04:45 lr: 0.000907 loss: 3.5609 (3.6877) grad_norm: 1.0070 (inf) time: 0.5072 [2021-03-25 14:02:20 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 700/1251] eta: 0:04:40 lr: 0.000907 loss: 3.8588 (3.6881) grad_norm: 1.0070 (inf) time: 0.5068 [2021-03-25 14:02:25 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 710/1251] eta: 0:04:35 lr: 0.000907 loss: 3.8241 (3.6857) grad_norm: 1.0668 (inf) time: 0.5013 [2021-03-25 14:02:30 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 720/1251] eta: 0:04:30 lr: 0.000907 loss: 3.5073 (3.6823) grad_norm: 1.0509 (inf) time: 0.4999 [2021-03-25 14:02:35 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 730/1251] eta: 0:04:25 lr: 0.000907 loss: 3.6057 (3.6833) grad_norm: 1.0333 (inf) time: 0.5041 [2021-03-25 14:02:40 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 740/1251] eta: 0:04:20 lr: 0.000907 loss: 3.4919 (3.6783) grad_norm: 1.0022 (inf) time: 0.5251 [2021-03-25 14:02:45 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 750/1251] eta: 0:04:15 lr: 0.000907 loss: 3.4832 (3.6791) grad_norm: 0.9657 (inf) time: 0.5243 [2021-03-25 14:02:51 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 760/1251] eta: 0:04:10 lr: 0.000907 loss: 3.7870 (3.6802) grad_norm: 0.9886 (inf) time: 0.5064 [2021-03-25 14:02:56 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 770/1251] eta: 0:04:05 lr: 0.000907 loss: 3.7870 (3.6805) grad_norm: 0.9886 (inf) time: 0.5038 [2021-03-25 14:03:01 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 780/1251] eta: 0:03:59 lr: 0.000907 loss: 3.8179 (3.6812) grad_norm: 0.9525 (inf) time: 0.4966 [2021-03-25 14:03:05 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 790/1251] eta: 0:03:54 lr: 0.000907 loss: 3.8841 (3.6840) grad_norm: 1.0117 (inf) time: 0.4946 [2021-03-25 14:03:10 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 800/1251] eta: 0:03:49 lr: 0.000907 loss: 3.9370 (3.6871) grad_norm: 1.0575 (inf) time: 0.4987 [2021-03-25 14:03:16 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 810/1251] eta: 0:03:44 lr: 0.000907 loss: 3.9315 (3.6859) grad_norm: 1.0581 (inf) time: 0.5051 [2021-03-25 14:03:21 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 820/1251] eta: 0:03:39 lr: 0.000907 loss: 3.5321 (3.6832) grad_norm: 1.0840 (inf) time: 0.5100 [2021-03-25 14:03:26 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 830/1251] eta: 0:03:34 lr: 0.000906 loss: 3.7862 (3.6894) grad_norm: 1.0932 (inf) time: 0.5102 [2021-03-25 14:03:31 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 840/1251] eta: 0:03:29 lr: 0.000906 loss: 3.9797 (3.6904) grad_norm: 1.0755 (inf) time: 0.5080 [2021-03-25 14:03:36 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 850/1251] eta: 0:03:24 lr: 0.000906 loss: 3.9413 (3.6921) grad_norm: 1.0315 (inf) time: 0.5035 [2021-03-25 14:03:41 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 860/1251] eta: 0:03:18 lr: 0.000906 loss: 3.8923 (3.6940) grad_norm: 0.9893 (inf) time: 0.5006 [2021-03-25 14:03:46 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 870/1251] eta: 0:03:13 lr: 0.000906 loss: 3.7145 (3.6942) grad_norm: 0.9997 (inf) time: 0.5035 [2021-03-25 14:03:51 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 880/1251] eta: 0:03:08 lr: 0.000906 loss: 3.8242 (3.6959) grad_norm: 0.9930 (inf) time: 0.5076 [2021-03-25 14:03:56 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 890/1251] eta: 0:03:03 lr: 0.000906 loss: 3.7390 (3.6966) grad_norm: 0.9930 (inf) time: 0.5101 [2021-03-25 14:04:01 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 900/1251] eta: 0:02:58 lr: 0.000906 loss: 3.7329 (3.6972) grad_norm: 1.0876 (inf) time: 0.5084 [2021-03-25 14:04:06 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 910/1251] eta: 0:02:53 lr: 0.000906 loss: 3.8113 (3.6980) grad_norm: 1.0260 (inf) time: 0.5036 [2021-03-25 14:04:11 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 920/1251] eta: 0:02:48 lr: 0.000906 loss: 3.8249 (3.6992) grad_norm: 1.0065 (inf) time: 0.5045 [2021-03-25 14:04:16 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 930/1251] eta: 0:02:43 lr: 0.000906 loss: 3.8249 (3.7018) grad_norm: 0.9925 (inf) time: 0.5088 [2021-03-25 14:04:21 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 940/1251] eta: 0:02:38 lr: 0.000906 loss: 3.8661 (3.7025) grad_norm: 0.9753 (inf) time: 0.5100 [2021-03-25 14:04:26 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 950/1251] eta: 0:02:33 lr: 0.000906 loss: 3.8661 (3.7028) grad_norm: 0.9873 (inf) time: 0.5046 [2021-03-25 14:04:32 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 960/1251] eta: 0:02:28 lr: 0.000906 loss: 3.8060 (3.7032) grad_norm: 0.9644 (inf) time: 0.5009 [2021-03-25 14:04:37 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 970/1251] eta: 0:02:22 lr: 0.000906 loss: 3.7053 (3.7009) grad_norm: 0.9644 (inf) time: 0.5059 [2021-03-25 14:04:42 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 980/1251] eta: 0:02:17 lr: 0.000906 loss: 3.6627 (3.7013) grad_norm: 1.0684 (inf) time: 0.5101 [2021-03-25 14:04:47 swin_small_patch4_window7_224] INFO: Epoch: [59] [ 990/1251] eta: 0:02:12 lr: 0.000906 loss: 3.8796 (3.7039) grad_norm: 1.0018 (inf) time: 0.5108 [2021-03-25 14:04:52 swin_small_patch4_window7_224] INFO: Epoch: [59] [1000/1251] eta: 0:02:07 lr: 0.000906 loss: 3.9823 (3.7050) grad_norm: 1.0018 (inf) time: 0.5059 [2021-03-25 14:04:57 swin_small_patch4_window7_224] INFO: Epoch: [59] [1010/1251] eta: 0:02:02 lr: 0.000906 loss: 3.7980 (3.7035) grad_norm: 1.0165 (inf) time: 0.5044 [2021-03-25 14:05:02 swin_small_patch4_window7_224] INFO: Epoch: [59] [1020/1251] eta: 0:01:57 lr: 0.000906 loss: 3.6460 (3.7031) grad_norm: 1.0165 (inf) time: 0.5014 [2021-03-25 14:05:07 swin_small_patch4_window7_224] INFO: Epoch: [59] [1030/1251] eta: 0:01:52 lr: 0.000906 loss: 3.8087 (3.7028) grad_norm: 1.1113 (inf) time: 0.4986 [2021-03-25 14:05:12 swin_small_patch4_window7_224] INFO: Epoch: [59] [1040/1251] eta: 0:01:47 lr: 0.000906 loss: 3.8145 (3.7038) grad_norm: 1.1113 (inf) time: 0.5054 [2021-03-25 14:05:17 swin_small_patch4_window7_224] INFO: Epoch: [59] [1050/1251] eta: 0:01:42 lr: 0.000906 loss: 3.8407 (3.7054) grad_norm: 1.0150 (inf) time: 0.5048 [2021-03-25 14:05:22 swin_small_patch4_window7_224] INFO: Epoch: [59] [1060/1251] eta: 0:01:37 lr: 0.000906 loss: 3.8407 (3.7059) grad_norm: 1.0119 (inf) time: 0.5015 [2021-03-25 14:05:27 swin_small_patch4_window7_224] INFO: Epoch: [59] [1070/1251] eta: 0:01:32 lr: 0.000906 loss: 3.8112 (3.7039) grad_norm: 1.0119 (inf) time: 0.5074 [2021-03-25 14:05:32 swin_small_patch4_window7_224] INFO: Epoch: [59] [1080/1251] eta: 0:01:26 lr: 0.000906 loss: 3.6728 (3.7049) grad_norm: 1.0703 (inf) time: 0.5067 [2021-03-25 14:05:37 swin_small_patch4_window7_224] INFO: Epoch: [59] [1090/1251] eta: 0:01:21 lr: 0.000906 loss: 3.6728 (3.7046) grad_norm: 1.0977 (inf) time: 0.5004 [2021-03-25 14:05:42 swin_small_patch4_window7_224] INFO: Epoch: [59] [1100/1251] eta: 0:01:16 lr: 0.000906 loss: 3.8698 (3.7073) grad_norm: 1.0296 (inf) time: 0.5040 [2021-03-25 14:05:47 swin_small_patch4_window7_224] INFO: Epoch: [59] [1110/1251] eta: 0:01:11 lr: 0.000906 loss: 3.6002 (3.7043) grad_norm: 0.9981 (inf) time: 0.5052 [2021-03-25 14:05:52 swin_small_patch4_window7_224] INFO: Epoch: [59] [1120/1251] eta: 0:01:06 lr: 0.000906 loss: 3.5800 (3.7050) grad_norm: 1.0139 (inf) time: 0.5040 [2021-03-25 14:05:57 swin_small_patch4_window7_224] INFO: Epoch: [59] [1130/1251] eta: 0:01:01 lr: 0.000906 loss: 4.0006 (3.7051) grad_norm: 0.9923 (inf) time: 0.5060 [2021-03-25 14:06:02 swin_small_patch4_window7_224] INFO: Epoch: [59] [1140/1251] eta: 0:00:56 lr: 0.000906 loss: 3.9781 (3.7057) grad_norm: 0.9923 (inf) time: 0.5029 [2021-03-25 14:06:07 swin_small_patch4_window7_224] INFO: Epoch: [59] [1150/1251] eta: 0:00:51 lr: 0.000906 loss: 3.7764 (3.7057) grad_norm: 1.0273 (inf) time: 0.5022 [2021-03-25 14:06:12 swin_small_patch4_window7_224] INFO: Epoch: [59] [1160/1251] eta: 0:00:46 lr: 0.000906 loss: 3.5981 (3.7036) grad_norm: 0.9614 (inf) time: 0.5049 [2021-03-25 14:06:18 swin_small_patch4_window7_224] INFO: Epoch: [59] [1170/1251] eta: 0:00:41 lr: 0.000906 loss: 3.5978 (3.7036) grad_norm: 0.9766 (inf) time: 0.5101 [2021-03-25 14:06:23 swin_small_patch4_window7_224] INFO: Epoch: [59] [1180/1251] eta: 0:00:36 lr: 0.000906 loss: 3.8253 (3.7044) grad_norm: 1.0000 (inf) time: 0.5171 [2021-03-25 14:06:28 swin_small_patch4_window7_224] INFO: Epoch: [59] [1190/1251] eta: 0:00:30 lr: 0.000906 loss: 3.7451 (3.7031) grad_norm: 0.9677 (inf) time: 0.5134 [2021-03-25 14:06:33 swin_small_patch4_window7_224] INFO: Epoch: [59] [1200/1251] eta: 0:00:25 lr: 0.000906 loss: 3.5172 (3.7017) grad_norm: 0.9677 (inf) time: 0.5072 [2021-03-25 14:06:38 swin_small_patch4_window7_224] INFO: Epoch: [59] [1210/1251] eta: 0:00:20 lr: 0.000906 loss: 3.5865 (3.7013) grad_norm: 0.9831 (inf) time: 0.5042 [2021-03-25 14:06:43 swin_small_patch4_window7_224] INFO: Epoch: [59] [1220/1251] eta: 0:00:15 lr: 0.000906 loss: 3.7342 (3.7025) grad_norm: 0.9635 (inf) time: 0.5033 [2021-03-25 14:06:48 swin_small_patch4_window7_224] INFO: Epoch: [59] [1230/1251] eta: 0:00:10 lr: 0.000906 loss: 3.7342 (3.7022) grad_norm: 0.9855 (inf) time: 0.5017 [2021-03-25 14:06:53 swin_small_patch4_window7_224] INFO: Epoch: [59] [1240/1251] eta: 0:00:05 lr: 0.000905 loss: 3.9860 (3.7042) grad_norm: 1.0157 (inf) time: 0.5053 [2021-03-25 14:06:58 swin_small_patch4_window7_224] INFO: Epoch: [59] [1250/1251] eta: 0:00:00 lr: 0.000905 loss: 3.9907 (3.7044) grad_norm: 0.9952 (inf) time: 0.5038 [2021-03-25 14:07:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:18 loss: 1.0664 (1.0664) acc1: 70.3125 (70.3125) acc5: 93.7500 (93.7500) [2021-03-25 14:07:06 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.2191 (1.1744) acc1: 71.8750 (72.0170) acc5: 92.1875 (91.9034) [2021-03-25 14:07:08 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.2191 (1.1945) acc1: 71.8750 (71.7262) acc5: 90.6250 (91.4435) [2021-03-25 14:07:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1207 (1.1486) acc1: 71.8750 (72.6815) acc5: 92.1875 (91.6331) [2021-03-25 14:07:12 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0885 (1.1515) acc1: 75.0000 (73.1707) acc5: 92.1875 (91.3491) [2021-03-25 14:07:13 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1770 (1.1529) acc1: 71.8750 (72.8320) acc5: 90.6250 (91.5200) [2021-03-25 14:07:16 swin_small_patch4_window7_224] INFO: * Acc@1 73.520 Acc@5 92.060 loss 1.131 [2021-03-25 14:07:16 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.5% [2021-03-25 14:07:16 swin_small_patch4_window7_224] INFO: Max accuracy: 73.52% [2021-03-25 14:07:20 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 0/1251] eta: 1:22:55 lr: 0.000905 loss: 3.6363 (3.6363) grad_norm: 1.0345 (1.0345) time: 3.9772 [2021-03-25 14:07:25 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 10/1251] eta: 0:17:37 lr: 0.000905 loss: 3.5210 (3.5067) grad_norm: 0.9594 (0.9965) time: 0.8519 [2021-03-25 14:07:30 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 20/1251] eta: 0:14:03 lr: 0.000905 loss: 3.2694 (3.4027) grad_norm: 1.0262 (1.0280) time: 0.5208 [2021-03-25 14:07:35 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 30/1251] eta: 0:12:44 lr: 0.000905 loss: 3.3261 (3.5370) grad_norm: 1.0262 (1.0190) time: 0.5025 [2021-03-25 14:07:40 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 40/1251] eta: 0:12:05 lr: 0.000905 loss: 3.7723 (3.5719) grad_norm: 1.0185 (1.0374) time: 0.5082 [2021-03-25 14:07:45 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 50/1251] eta: 0:11:41 lr: 0.000905 loss: 3.8147 (3.6350) grad_norm: 1.0443 (1.0493) time: 0.5177 [2021-03-25 14:07:51 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 60/1251] eta: 0:11:21 lr: 0.000905 loss: 3.9128 (3.6360) grad_norm: 1.0921 (1.0520) time: 0.5168 [2021-03-25 14:07:56 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 70/1251] eta: 0:11:05 lr: 0.000905 loss: 3.7210 (3.6306) grad_norm: 1.0569 (1.0418) time: 0.5118 [2021-03-25 14:08:01 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 80/1251] eta: 0:10:51 lr: 0.000905 loss: 3.8060 (3.6511) grad_norm: 1.0043 (1.0544) time: 0.5077 [2021-03-25 14:08:06 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 90/1251] eta: 0:10:38 lr: 0.000905 loss: 3.8060 (3.6532) grad_norm: 0.9747 (1.0444) time: 0.5015 [2021-03-25 14:08:11 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 100/1251] eta: 0:10:27 lr: 0.000905 loss: 3.6116 (3.6374) grad_norm: 0.9996 (1.0434) time: 0.5002 [2021-03-25 14:08:16 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 110/1251] eta: 0:10:18 lr: 0.000905 loss: 3.6631 (3.6444) grad_norm: 1.0588 (1.0425) time: 0.5042 [2021-03-25 14:08:21 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 120/1251] eta: 0:10:11 lr: 0.000905 loss: 3.7556 (3.6537) grad_norm: 0.9823 (1.0383) time: 0.5165 [2021-03-25 14:08:26 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 130/1251] eta: 0:10:04 lr: 0.000905 loss: 3.7490 (3.6458) grad_norm: 0.9776 (1.0363) time: 0.5276 [2021-03-25 14:08:31 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 140/1251] eta: 0:09:56 lr: 0.000905 loss: 3.7541 (3.6635) grad_norm: 1.0204 (1.0393) time: 0.5180 [2021-03-25 14:08:36 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 150/1251] eta: 0:09:48 lr: 0.000905 loss: 3.7541 (3.6519) grad_norm: 1.0193 (1.0375) time: 0.5031 [2021-03-25 14:08:41 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 160/1251] eta: 0:09:40 lr: 0.000905 loss: 3.4976 (3.6432) grad_norm: 1.0193 (1.0385) time: 0.4995 [2021-03-25 14:08:46 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 170/1251] eta: 0:09:34 lr: 0.000905 loss: 3.9911 (3.6701) grad_norm: 1.0436 (1.0409) time: 0.5030 [2021-03-25 14:08:52 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 180/1251] eta: 0:09:27 lr: 0.000905 loss: 3.8865 (3.6554) grad_norm: 1.0326 (1.0421) time: 0.5108 [2021-03-25 14:08:57 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 190/1251] eta: 0:09:22 lr: 0.000905 loss: 3.6383 (3.6616) grad_norm: 0.9908 (1.0377) time: 0.5190 [2021-03-25 14:09:02 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 200/1251] eta: 0:09:15 lr: 0.000905 loss: 3.8723 (3.6634) grad_norm: 0.9793 (1.0393) time: 0.5163 [2021-03-25 14:09:07 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 210/1251] eta: 0:09:08 lr: 0.000905 loss: 3.6433 (3.6584) grad_norm: 1.0370 (1.0382) time: 0.5039 [2021-03-25 14:09:12 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 220/1251] eta: 0:09:02 lr: 0.000905 loss: 3.6876 (3.6649) grad_norm: 1.0449 (1.0400) time: 0.5020 [2021-03-25 14:09:17 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 230/1251] eta: 0:08:56 lr: 0.000905 loss: 3.7826 (3.6673) grad_norm: 1.0926 (1.0419) time: 0.5046 [2021-03-25 14:09:22 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 240/1251] eta: 0:08:50 lr: 0.000905 loss: 3.7160 (3.6696) grad_norm: 1.0629 (1.0416) time: 0.5014 [2021-03-25 14:09:27 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 250/1251] eta: 0:08:44 lr: 0.000905 loss: 3.8824 (3.6740) grad_norm: 1.0537 (1.0431) time: 0.5022 [2021-03-25 14:09:32 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 260/1251] eta: 0:08:38 lr: 0.000905 loss: 3.7070 (3.6696) grad_norm: 1.0067 (1.0425) time: 0.5061 [2021-03-25 14:09:37 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 270/1251] eta: 0:08:32 lr: 0.000905 loss: 3.6287 (3.6742) grad_norm: 0.9886 (1.0434) time: 0.5041 [2021-03-25 14:09:42 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 280/1251] eta: 0:08:26 lr: 0.000905 loss: 3.7640 (3.6782) grad_norm: 1.0164 (1.0423) time: 0.5016 [2021-03-25 14:09:47 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 290/1251] eta: 0:08:20 lr: 0.000905 loss: 3.8038 (3.6742) grad_norm: 1.0202 (1.0411) time: 0.5061 [2021-03-25 14:09:52 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 300/1251] eta: 0:08:14 lr: 0.000905 loss: 3.7229 (3.6702) grad_norm: 0.9839 (1.0412) time: 0.5066 [2021-03-25 14:09:57 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 310/1251] eta: 0:08:09 lr: 0.000905 loss: 3.6368 (3.6674) grad_norm: 0.9829 (1.0395) time: 0.5070 [2021-03-25 14:10:03 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 320/1251] eta: 0:08:03 lr: 0.000905 loss: 3.9111 (3.6647) grad_norm: 0.9735 (1.0402) time: 0.5100 [2021-03-25 14:10:08 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 330/1251] eta: 0:07:58 lr: 0.000905 loss: 3.5177 (3.6553) grad_norm: 1.0493 (1.0410) time: 0.5039 [2021-03-25 14:10:13 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 340/1251] eta: 0:07:52 lr: 0.000905 loss: 3.6019 (3.6589) grad_norm: 1.0633 (1.0426) time: 0.5039 [2021-03-25 14:10:18 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 350/1251] eta: 0:07:46 lr: 0.000905 loss: 3.8302 (3.6635) grad_norm: 1.0315 (1.0437) time: 0.5021 [2021-03-25 14:10:23 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 360/1251] eta: 0:07:41 lr: 0.000905 loss: 3.8565 (3.6676) grad_norm: 1.0315 (1.0441) time: 0.5000 [2021-03-25 14:10:28 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 370/1251] eta: 0:07:35 lr: 0.000905 loss: 3.7825 (3.6689) grad_norm: 1.0251 (1.0447) time: 0.5040 [2021-03-25 14:10:33 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 380/1251] eta: 0:07:30 lr: 0.000905 loss: 3.7825 (3.6722) grad_norm: 1.0493 (1.0458) time: 0.5040 [2021-03-25 14:10:38 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 390/1251] eta: 0:07:25 lr: 0.000905 loss: 3.7911 (3.6704) grad_norm: 1.0603 (1.0473) time: 0.5075 [2021-03-25 14:10:43 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 400/1251] eta: 0:07:19 lr: 0.000904 loss: 3.8495 (3.6742) grad_norm: 1.0603 (1.0476) time: 0.5114 [2021-03-25 14:10:48 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 410/1251] eta: 0:07:14 lr: 0.000904 loss: 3.8495 (3.6755) grad_norm: 0.9856 (1.0466) time: 0.5082 [2021-03-25 14:10:53 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 420/1251] eta: 0:07:08 lr: 0.000904 loss: 3.6464 (3.6710) grad_norm: 0.9856 (1.0451) time: 0.5052 [2021-03-25 14:10:58 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 430/1251] eta: 0:07:03 lr: 0.000904 loss: 3.4322 (3.6700) grad_norm: 1.0072 (1.0442) time: 0.5021 [2021-03-25 14:11:03 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 440/1251] eta: 0:06:58 lr: 0.000904 loss: 3.6692 (3.6681) grad_norm: 1.0434 (1.0447) time: 0.5081 [2021-03-25 14:11:08 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 450/1251] eta: 0:06:52 lr: 0.000904 loss: 3.8704 (3.6701) grad_norm: 1.0475 (1.0449) time: 0.5088 [2021-03-25 14:11:13 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 460/1251] eta: 0:06:47 lr: 0.000904 loss: 3.9427 (3.6739) grad_norm: 1.0174 (1.0444) time: 0.5025 [2021-03-25 14:11:18 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 470/1251] eta: 0:06:42 lr: 0.000904 loss: 3.8027 (3.6740) grad_norm: 1.0174 (1.0437) time: 0.5060 [2021-03-25 14:11:23 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 480/1251] eta: 0:06:36 lr: 0.000904 loss: 3.7841 (3.6754) grad_norm: 1.0112 (1.0436) time: 0.5030 [2021-03-25 14:11:28 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 490/1251] eta: 0:06:31 lr: 0.000904 loss: 3.7536 (3.6737) grad_norm: 1.0047 (1.0433) time: 0.5061 [2021-03-25 14:11:33 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 500/1251] eta: 0:06:26 lr: 0.000904 loss: 3.6411 (3.6732) grad_norm: 1.0267 (1.0434) time: 0.5079 [2021-03-25 14:11:38 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 510/1251] eta: 0:06:21 lr: 0.000904 loss: 3.7230 (3.6757) grad_norm: 1.0682 (1.0439) time: 0.5023 [2021-03-25 14:11:43 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 520/1251] eta: 0:06:15 lr: 0.000904 loss: 3.7942 (3.6784) grad_norm: 1.0817 (1.0441) time: 0.4978 [2021-03-25 14:11:48 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 530/1251] eta: 0:06:10 lr: 0.000904 loss: 3.8848 (3.6829) grad_norm: 1.0817 (1.0451) time: 0.4956 [2021-03-25 14:11:53 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 540/1251] eta: 0:06:04 lr: 0.000904 loss: 3.9391 (3.6823) grad_norm: 1.1332 (1.0476) time: 0.5007 [2021-03-25 14:11:59 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 550/1251] eta: 0:05:59 lr: 0.000904 loss: 3.8843 (3.6861) grad_norm: 1.0736 (1.0476) time: 0.5094 [2021-03-25 14:12:04 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 560/1251] eta: 0:05:54 lr: 0.000904 loss: 3.7811 (3.6882) grad_norm: 1.0189 (1.0481) time: 0.5072 [2021-03-25 14:12:09 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 570/1251] eta: 0:05:49 lr: 0.000904 loss: 3.7752 (3.6892) grad_norm: 0.9981 (1.0473) time: 0.5012 [2021-03-25 14:12:14 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 580/1251] eta: 0:05:44 lr: 0.000904 loss: 3.5839 (3.6888) grad_norm: 1.0051 (1.0469) time: 0.5012 [2021-03-25 14:12:19 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 590/1251] eta: 0:05:38 lr: 0.000904 loss: 3.5839 (3.6900) grad_norm: 1.0059 (1.0474) time: 0.5031 [2021-03-25 14:12:24 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 600/1251] eta: 0:05:33 lr: 0.000904 loss: 3.7163 (3.6906) grad_norm: 1.0082 (1.0479) time: 0.5063 [2021-03-25 14:12:29 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 610/1251] eta: 0:05:28 lr: 0.000904 loss: 3.7163 (3.6926) grad_norm: 1.0303 (1.0474) time: 0.5090 [2021-03-25 14:12:34 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 620/1251] eta: 0:05:23 lr: 0.000904 loss: 4.0672 (3.6949) grad_norm: 1.0472 (1.0475) time: 0.5064 [2021-03-25 14:12:39 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 630/1251] eta: 0:05:18 lr: 0.000904 loss: 3.8404 (3.6948) grad_norm: 1.0069 (1.0461) time: 0.5019 [2021-03-25 14:12:44 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 640/1251] eta: 0:05:12 lr: 0.000904 loss: 3.8404 (3.6976) grad_norm: 0.9889 (1.0470) time: 0.5018 [2021-03-25 14:12:49 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 650/1251] eta: 0:05:07 lr: 0.000904 loss: 3.9571 (3.6988) grad_norm: 1.0673 (1.0478) time: 0.5064 [2021-03-25 14:12:54 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 660/1251] eta: 0:05:02 lr: 0.000904 loss: 3.7667 (3.6996) grad_norm: 1.0032 (1.0469) time: 0.5047 [2021-03-25 14:12:59 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 670/1251] eta: 0:04:57 lr: 0.000904 loss: 3.7480 (3.6986) grad_norm: 0.9593 (1.0463) time: 0.4998 [2021-03-25 14:13:04 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 680/1251] eta: 0:04:52 lr: 0.000904 loss: 3.7465 (3.7011) grad_norm: 0.9929 (1.0460) time: 0.5049 [2021-03-25 14:13:09 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 690/1251] eta: 0:04:46 lr: 0.000904 loss: 3.6906 (3.6987) grad_norm: 1.0156 (1.0466) time: 0.5086 [2021-03-25 14:13:14 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 700/1251] eta: 0:04:41 lr: 0.000904 loss: 3.7613 (3.6997) grad_norm: 1.0101 (1.0458) time: 0.5058 [2021-03-25 14:13:19 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 710/1251] eta: 0:04:36 lr: 0.000904 loss: 3.8304 (3.6992) grad_norm: 0.9816 (1.0451) time: 0.5038 [2021-03-25 14:13:24 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 720/1251] eta: 0:04:31 lr: 0.000904 loss: 3.8515 (3.7011) grad_norm: 0.9817 (1.0443) time: 0.5060 [2021-03-25 14:13:29 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 730/1251] eta: 0:04:26 lr: 0.000904 loss: 3.8473 (3.7004) grad_norm: 1.0097 (1.0444) time: 0.5065 [2021-03-25 14:13:35 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 740/1251] eta: 0:04:21 lr: 0.000904 loss: 3.7263 (3.7015) grad_norm: 1.0097 (1.0441) time: 0.5139 [2021-03-25 14:13:40 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 750/1251] eta: 0:04:16 lr: 0.000904 loss: 3.7263 (3.6990) grad_norm: 0.9742 (1.0434) time: 0.5107 [2021-03-25 14:13:45 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 760/1251] eta: 0:04:10 lr: 0.000904 loss: 3.3640 (3.6948) grad_norm: 0.9579 (1.0430) time: 0.5056 [2021-03-25 14:13:50 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 770/1251] eta: 0:04:05 lr: 0.000904 loss: 3.5791 (3.6960) grad_norm: 0.9803 (1.0431) time: 0.5100 [2021-03-25 14:13:55 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 780/1251] eta: 0:04:00 lr: 0.000904 loss: 3.9455 (3.6967) grad_norm: 1.0562 (1.0430) time: 0.5051 [2021-03-25 14:14:00 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 790/1251] eta: 0:03:55 lr: 0.000904 loss: 3.8636 (3.6982) grad_norm: 1.0399 (1.0431) time: 0.5086 [2021-03-25 14:14:05 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 800/1251] eta: 0:03:50 lr: 0.000904 loss: 3.8478 (3.6985) grad_norm: 1.0461 (1.0434) time: 0.5135 [2021-03-25 14:14:10 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 810/1251] eta: 0:03:45 lr: 0.000903 loss: 3.6164 (3.6965) grad_norm: 0.9854 (1.0428) time: 0.5104 [2021-03-25 14:14:15 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 820/1251] eta: 0:03:40 lr: 0.000903 loss: 3.7089 (3.6985) grad_norm: 0.9616 (1.0416) time: 0.5076 [2021-03-25 14:14:20 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 830/1251] eta: 0:03:35 lr: 0.000903 loss: 3.6087 (3.6957) grad_norm: 0.9249 (1.0412) time: 0.5060 [2021-03-25 14:14:25 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 840/1251] eta: 0:03:29 lr: 0.000903 loss: 3.6087 (3.6955) grad_norm: 0.9428 (1.0397) time: 0.5066 [2021-03-25 14:14:30 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 850/1251] eta: 0:03:24 lr: 0.000903 loss: 3.8116 (3.6972) grad_norm: 0.9443 (1.0394) time: 0.5029 [2021-03-25 14:14:35 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 860/1251] eta: 0:03:19 lr: 0.000903 loss: 3.8456 (3.6981) grad_norm: 1.0409 (1.0400) time: 0.5025 [2021-03-25 14:14:41 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 870/1251] eta: 0:03:14 lr: 0.000903 loss: 3.6425 (3.6956) grad_norm: 1.0417 (1.0395) time: 0.5149 [2021-03-25 14:14:46 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 880/1251] eta: 0:03:09 lr: 0.000903 loss: 3.6425 (3.6953) grad_norm: 1.0289 (1.0401) time: 0.5132 [2021-03-25 14:14:51 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 890/1251] eta: 0:03:04 lr: 0.000903 loss: 3.8648 (3.6955) grad_norm: 1.0690 (1.0408) time: 0.5041 [2021-03-25 14:14:56 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 900/1251] eta: 0:02:59 lr: 0.000903 loss: 3.6572 (3.6926) grad_norm: 1.0406 (1.0406) time: 0.5057 [2021-03-25 14:15:01 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 910/1251] eta: 0:02:54 lr: 0.000903 loss: 3.6272 (3.6920) grad_norm: 1.0766 (1.0415) time: 0.5028 [2021-03-25 14:15:06 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 920/1251] eta: 0:02:48 lr: 0.000903 loss: 3.7241 (3.6913) grad_norm: 1.1154 (1.0424) time: 0.5062 [2021-03-25 14:15:11 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 930/1251] eta: 0:02:43 lr: 0.000903 loss: 3.7717 (3.6892) grad_norm: 1.0693 (1.0431) time: 0.5203 [2021-03-25 14:15:16 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 940/1251] eta: 0:02:38 lr: 0.000903 loss: 3.7665 (3.6892) grad_norm: 1.0599 (1.0431) time: 0.5186 [2021-03-25 14:15:21 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 950/1251] eta: 0:02:33 lr: 0.000903 loss: 3.6430 (3.6885) grad_norm: 0.9446 (1.0419) time: 0.5103 [2021-03-25 14:15:27 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 960/1251] eta: 0:02:28 lr: 0.000903 loss: 3.7396 (3.6872) grad_norm: 0.9443 (1.0414) time: 0.5073 [2021-03-25 14:15:32 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 970/1251] eta: 0:02:23 lr: 0.000903 loss: 3.9108 (3.6893) grad_norm: 0.9877 (1.0410) time: 0.5025 [2021-03-25 14:15:37 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 980/1251] eta: 0:02:18 lr: 0.000903 loss: 3.7123 (3.6865) grad_norm: 0.9749 (1.0406) time: 0.4991 [2021-03-25 14:15:42 swin_small_patch4_window7_224] INFO: Epoch: [60] [ 990/1251] eta: 0:02:13 lr: 0.000903 loss: 3.7123 (3.6877) grad_norm: 0.9662 (1.0401) time: 0.5039 [2021-03-25 14:15:47 swin_small_patch4_window7_224] INFO: Epoch: [60] [1000/1251] eta: 0:02:08 lr: 0.000903 loss: 3.8048 (3.6873) grad_norm: 1.0008 (1.0403) time: 0.5090 [2021-03-25 14:15:52 swin_small_patch4_window7_224] INFO: Epoch: [60] [1010/1251] eta: 0:02:02 lr: 0.000903 loss: 3.8476 (3.6894) grad_norm: 1.0282 (1.0409) time: 0.5076 [2021-03-25 14:15:57 swin_small_patch4_window7_224] INFO: Epoch: [60] [1020/1251] eta: 0:01:57 lr: 0.000903 loss: 3.8245 (3.6893) grad_norm: 1.0452 (1.0411) time: 0.5036 [2021-03-25 14:16:02 swin_small_patch4_window7_224] INFO: Epoch: [60] [1030/1251] eta: 0:01:52 lr: 0.000903 loss: 3.8115 (3.6905) grad_norm: 1.0566 (1.0417) time: 0.4986 [2021-03-25 14:16:07 swin_small_patch4_window7_224] INFO: Epoch: [60] [1040/1251] eta: 0:01:47 lr: 0.000903 loss: 3.8601 (3.6906) grad_norm: 0.9940 (1.0413) time: 0.4950 [2021-03-25 14:16:12 swin_small_patch4_window7_224] INFO: Epoch: [60] [1050/1251] eta: 0:01:42 lr: 0.000903 loss: 3.8630 (3.6913) grad_norm: 0.9775 (1.0411) time: 0.4997 [2021-03-25 14:16:17 swin_small_patch4_window7_224] INFO: Epoch: [60] [1060/1251] eta: 0:01:37 lr: 0.000903 loss: 3.9091 (3.6934) grad_norm: 1.0313 (1.0413) time: 0.5049 [2021-03-25 14:16:22 swin_small_patch4_window7_224] INFO: Epoch: [60] [1070/1251] eta: 0:01:32 lr: 0.000903 loss: 3.9462 (3.6943) grad_norm: 1.0723 (1.0419) time: 0.5127 [2021-03-25 14:16:27 swin_small_patch4_window7_224] INFO: Epoch: [60] [1080/1251] eta: 0:01:27 lr: 0.000903 loss: 4.0288 (3.6968) grad_norm: 1.0789 (1.0420) time: 0.5086 [2021-03-25 14:16:32 swin_small_patch4_window7_224] INFO: Epoch: [60] [1090/1251] eta: 0:01:22 lr: 0.000903 loss: 3.7906 (3.6953) grad_norm: 1.0085 (1.0420) time: 0.4983 [2021-03-25 14:16:37 swin_small_patch4_window7_224] INFO: Epoch: [60] [1100/1251] eta: 0:01:16 lr: 0.000903 loss: 3.5649 (3.6935) grad_norm: 0.9865 (1.0416) time: 0.5034 [2021-03-25 14:16:42 swin_small_patch4_window7_224] INFO: Epoch: [60] [1110/1251] eta: 0:01:11 lr: 0.000903 loss: 3.8123 (3.6942) grad_norm: 0.9530 (1.0411) time: 0.5065 [2021-03-25 14:16:47 swin_small_patch4_window7_224] INFO: Epoch: [60] [1120/1251] eta: 0:01:06 lr: 0.000903 loss: 3.8108 (3.6926) grad_norm: 1.0362 (1.0416) time: 0.5118 [2021-03-25 14:16:52 swin_small_patch4_window7_224] INFO: Epoch: [60] [1130/1251] eta: 0:01:01 lr: 0.000903 loss: 3.6428 (3.6922) grad_norm: 1.0362 (1.0416) time: 0.5058 [2021-03-25 14:16:57 swin_small_patch4_window7_224] INFO: Epoch: [60] [1140/1251] eta: 0:00:56 lr: 0.000903 loss: 3.7964 (3.6929) grad_norm: 0.9829 (1.0411) time: 0.4980 [2021-03-25 14:17:02 swin_small_patch4_window7_224] INFO: Epoch: [60] [1150/1251] eta: 0:00:51 lr: 0.000903 loss: 3.6158 (3.6895) grad_norm: 0.9883 (1.0411) time: 0.5012 [2021-03-25 14:17:07 swin_small_patch4_window7_224] INFO: Epoch: [60] [1160/1251] eta: 0:00:46 lr: 0.000903 loss: 3.8053 (3.6914) grad_norm: 1.0006 (1.0408) time: 0.4993 [2021-03-25 14:17:12 swin_small_patch4_window7_224] INFO: Epoch: [60] [1170/1251] eta: 0:00:41 lr: 0.000903 loss: 3.8508 (3.6926) grad_norm: 1.0430 (1.0412) time: 0.5007 [2021-03-25 14:17:17 swin_small_patch4_window7_224] INFO: Epoch: [60] [1180/1251] eta: 0:00:36 lr: 0.000903 loss: 3.5724 (3.6929) grad_norm: 1.0537 (1.0418) time: 0.5069 [2021-03-25 14:17:22 swin_small_patch4_window7_224] INFO: Epoch: [60] [1190/1251] eta: 0:00:31 lr: 0.000903 loss: 3.5724 (3.6924) grad_norm: 1.0244 (1.0419) time: 0.5088 [2021-03-25 14:17:27 swin_small_patch4_window7_224] INFO: Epoch: [60] [1200/1251] eta: 0:00:25 lr: 0.000903 loss: 3.9690 (3.6925) grad_norm: 0.9820 (1.0412) time: 0.5049 [2021-03-25 14:17:33 swin_small_patch4_window7_224] INFO: Epoch: [60] [1210/1251] eta: 0:00:20 lr: 0.000902 loss: 3.7441 (3.6917) grad_norm: 0.9538 (1.0406) time: 0.5075 [2021-03-25 14:17:38 swin_small_patch4_window7_224] INFO: Epoch: [60] [1220/1251] eta: 0:00:15 lr: 0.000902 loss: 3.7736 (3.6932) grad_norm: 0.9538 (1.0401) time: 0.5108 [2021-03-25 14:17:43 swin_small_patch4_window7_224] INFO: Epoch: [60] [1230/1251] eta: 0:00:10 lr: 0.000902 loss: 3.8556 (3.6929) grad_norm: 0.9987 (1.0400) time: 0.5048 [2021-03-25 14:17:48 swin_small_patch4_window7_224] INFO: Epoch: [60] [1240/1251] eta: 0:00:05 lr: 0.000902 loss: 3.6102 (3.6916) grad_norm: 0.9987 (1.0395) time: 0.5022 [2021-03-25 14:17:53 swin_small_patch4_window7_224] INFO: Epoch: [60] [1250/1251] eta: 0:00:00 lr: 0.000902 loss: 3.7472 (3.6920) grad_norm: 0.9651 (1.0391) time: 0.5017 [2021-03-25 14:18:40 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 1.1962 (1.1962) acc1: 67.1875 (67.1875) acc5: 92.1875 (92.1875) [2021-03-25 14:18:41 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.1551 (1.1157) acc1: 78.1250 (74.1477) acc5: 92.1875 (92.1875) [2021-03-25 14:18:42 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.1551 (1.1453) acc1: 73.4375 (74.3304) acc5: 92.1875 (91.7411) [2021-03-25 14:18:43 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.2260 (1.1655) acc1: 71.8750 (73.2863) acc5: 90.6250 (91.3810) [2021-03-25 14:18:44 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.2084 (1.1697) acc1: 71.8750 (73.3994) acc5: 90.6250 (91.5015) [2021-03-25 14:18:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1070 (1.1526) acc1: 73.4375 (73.4400) acc5: 92.1875 (91.8080) [2021-03-25 14:18:51 swin_small_patch4_window7_224] INFO: * Acc@1 73.898 Acc@5 92.274 loss 1.124 [2021-03-25 14:18:51 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.9% [2021-03-25 14:18:51 swin_small_patch4_window7_224] INFO: Max accuracy: 73.90% [2021-03-25 14:18:55 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 0/1251] eta: 1:25:36 lr: 0.000902 loss: 4.6858 (4.6858) grad_norm: 1.0630 (1.0630) time: 4.1055 [2021-03-25 14:19:00 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 10/1251] eta: 0:17:35 lr: 0.000902 loss: 3.7742 (3.4787) grad_norm: 1.0630 (1.0772) time: 0.8503 [2021-03-25 14:19:05 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 20/1251] eta: 0:14:00 lr: 0.000902 loss: 3.5472 (3.5389) grad_norm: 1.0327 (1.0477) time: 0.5120 [2021-03-25 14:19:10 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 30/1251] eta: 0:12:42 lr: 0.000902 loss: 3.5057 (3.5519) grad_norm: 1.0560 (1.0450) time: 0.5006 [2021-03-25 14:19:16 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 40/1251] eta: 0:12:04 lr: 0.000902 loss: 3.7707 (3.5996) grad_norm: 1.0560 (1.0433) time: 0.5098 [2021-03-25 14:19:21 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 50/1251] eta: 0:11:37 lr: 0.000902 loss: 3.7707 (3.5928) grad_norm: 1.0515 (1.0410) time: 0.5126 [2021-03-25 14:19:26 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 60/1251] eta: 0:11:17 lr: 0.000902 loss: 3.4475 (3.5921) grad_norm: 1.0448 (1.0507) time: 0.5090 [2021-03-25 14:19:31 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 70/1251] eta: 0:11:02 lr: 0.000902 loss: 3.4348 (3.5762) grad_norm: 1.0448 (1.0520) time: 0.5105 [2021-03-25 14:19:36 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 80/1251] eta: 0:10:49 lr: 0.000902 loss: 3.4797 (3.5695) grad_norm: 1.0244 (1.0485) time: 0.5097 [2021-03-25 14:19:41 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 90/1251] eta: 0:10:37 lr: 0.000902 loss: 3.7007 (3.6156) grad_norm: 1.0244 (1.0496) time: 0.5074 [2021-03-25 14:19:46 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 100/1251] eta: 0:10:27 lr: 0.000902 loss: 4.0901 (3.6496) grad_norm: 1.0925 (1.0586) time: 0.5066 [2021-03-25 14:19:51 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 110/1251] eta: 0:10:18 lr: 0.000902 loss: 3.7703 (3.6361) grad_norm: 1.1216 (1.0659) time: 0.5095 [2021-03-25 14:19:56 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 120/1251] eta: 0:10:10 lr: 0.000902 loss: 3.6670 (3.6574) grad_norm: 1.0201 (1.0595) time: 0.5112 [2021-03-25 14:20:02 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 130/1251] eta: 0:10:04 lr: 0.000902 loss: 3.7332 (3.6565) grad_norm: 0.9777 (1.0554) time: 0.5224 [2021-03-25 14:20:07 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 140/1251] eta: 0:09:56 lr: 0.000902 loss: 3.6911 (3.6629) grad_norm: 0.9996 (1.0523) time: 0.5199 [2021-03-25 14:20:12 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 150/1251] eta: 0:09:48 lr: 0.000902 loss: 3.6406 (3.6525) grad_norm: 0.9879 (1.0482) time: 0.5076 [2021-03-25 14:20:17 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 160/1251] eta: 0:09:41 lr: 0.000902 loss: 3.2950 (3.6323) grad_norm: 0.9867 (1.0487) time: 0.5040 [2021-03-25 14:20:22 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 170/1251] eta: 0:09:34 lr: 0.000902 loss: 3.7060 (3.6357) grad_norm: 1.0221 (1.0495) time: 0.5033 [2021-03-25 14:20:27 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 180/1251] eta: 0:09:27 lr: 0.000902 loss: 3.8319 (3.6297) grad_norm: 1.0712 (1.0522) time: 0.5072 [2021-03-25 14:20:32 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 190/1251] eta: 0:09:20 lr: 0.000902 loss: 3.6146 (3.6279) grad_norm: 1.0993 (1.0542) time: 0.5044 [2021-03-25 14:20:37 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 200/1251] eta: 0:09:14 lr: 0.000902 loss: 3.8085 (3.6396) grad_norm: 1.0993 (1.0553) time: 0.5103 [2021-03-25 14:20:42 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 210/1251] eta: 0:09:08 lr: 0.000902 loss: 3.8217 (3.6413) grad_norm: 1.0150 (1.0532) time: 0.5104 [2021-03-25 14:20:47 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 220/1251] eta: 0:09:01 lr: 0.000902 loss: 3.7571 (3.6372) grad_norm: 0.9949 (1.0531) time: 0.5036 [2021-03-25 14:20:52 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 230/1251] eta: 0:08:55 lr: 0.000902 loss: 3.8994 (3.6586) grad_norm: 1.0609 (1.0533) time: 0.5019 [2021-03-25 14:20:57 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 240/1251] eta: 0:08:49 lr: 0.000902 loss: 4.1718 (3.6630) grad_norm: 1.0515 (1.0541) time: 0.5072 [2021-03-25 14:21:03 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 250/1251] eta: 0:08:44 lr: 0.000902 loss: 3.8935 (3.6608) grad_norm: 1.0194 (1.0516) time: 0.5174 [2021-03-25 14:21:08 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 260/1251] eta: 0:08:38 lr: 0.000902 loss: 3.6179 (3.6514) grad_norm: 1.0041 (1.0524) time: 0.5185 [2021-03-25 14:21:13 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 270/1251] eta: 0:08:33 lr: 0.000902 loss: 3.5595 (3.6548) grad_norm: 1.0606 (1.0550) time: 0.5108 [2021-03-25 14:21:18 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 280/1251] eta: 0:08:27 lr: 0.000902 loss: 3.9118 (3.6608) grad_norm: 1.0489 (1.0549) time: 0.5048 [2021-03-25 14:21:23 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 290/1251] eta: 0:08:21 lr: 0.000902 loss: 3.8359 (3.6646) grad_norm: 1.0942 (1.0568) time: 0.5022 [2021-03-25 14:21:28 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 300/1251] eta: 0:08:15 lr: 0.000902 loss: 3.7822 (3.6650) grad_norm: 1.1159 (1.0600) time: 0.5024 [2021-03-25 14:21:33 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 310/1251] eta: 0:08:09 lr: 0.000902 loss: 3.6699 (3.6641) grad_norm: 1.1076 (1.0621) time: 0.5056 [2021-03-25 14:21:38 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 320/1251] eta: 0:08:04 lr: 0.000902 loss: 3.8476 (3.6721) grad_norm: 1.0111 (1.0606) time: 0.5118 [2021-03-25 14:21:43 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 330/1251] eta: 0:07:58 lr: 0.000902 loss: 3.8989 (3.6690) grad_norm: 0.9894 (1.0591) time: 0.5107 [2021-03-25 14:21:48 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 340/1251] eta: 0:07:53 lr: 0.000902 loss: 3.6903 (3.6672) grad_norm: 1.0136 (1.0602) time: 0.5026 [2021-03-25 14:21:53 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 350/1251] eta: 0:07:47 lr: 0.000902 loss: 3.7427 (3.6661) grad_norm: 1.0449 (1.0605) time: 0.4988 [2021-03-25 14:21:58 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 360/1251] eta: 0:07:41 lr: 0.000902 loss: 3.6945 (3.6638) grad_norm: 1.0455 (1.0625) time: 0.5007 [2021-03-25 14:22:03 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 370/1251] eta: 0:07:36 lr: 0.000901 loss: 3.7308 (3.6703) grad_norm: 1.0424 (1.0622) time: 0.5023 [2021-03-25 14:22:08 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 380/1251] eta: 0:07:30 lr: 0.000901 loss: 3.8182 (3.6741) grad_norm: 1.0127 (1.0618) time: 0.5003 [2021-03-25 14:22:13 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 390/1251] eta: 0:07:25 lr: 0.000901 loss: 3.7696 (3.6716) grad_norm: 1.0022 (1.0613) time: 0.5066 [2021-03-25 14:22:18 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 400/1251] eta: 0:07:19 lr: 0.000901 loss: 3.6557 (3.6712) grad_norm: 1.0787 (1.0635) time: 0.5043 [2021-03-25 14:22:23 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 410/1251] eta: 0:07:14 lr: 0.000901 loss: 3.6152 (3.6687) grad_norm: 1.0787 (1.0622) time: 0.4966 [2021-03-25 14:22:28 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 420/1251] eta: 0:07:08 lr: 0.000901 loss: 3.5682 (3.6685) grad_norm: 1.0228 (1.0620) time: 0.5023 [2021-03-25 14:22:34 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 430/1251] eta: 0:07:03 lr: 0.000901 loss: 3.7185 (3.6661) grad_norm: 1.0487 (1.0622) time: 0.5089 [2021-03-25 14:22:39 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 440/1251] eta: 0:06:58 lr: 0.000901 loss: 3.7185 (3.6675) grad_norm: 1.0216 (1.0617) time: 0.5109 [2021-03-25 14:22:44 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 450/1251] eta: 0:06:53 lr: 0.000901 loss: 3.7089 (3.6671) grad_norm: 1.0103 (1.0614) time: 0.5089 [2021-03-25 14:22:49 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 460/1251] eta: 0:06:47 lr: 0.000901 loss: 3.7254 (3.6689) grad_norm: 1.0568 (1.0620) time: 0.4973 [2021-03-25 14:22:54 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 470/1251] eta: 0:06:41 lr: 0.000901 loss: 3.7883 (3.6711) grad_norm: 1.0209 (1.0606) time: 0.4947 [2021-03-25 14:22:59 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 480/1251] eta: 0:06:36 lr: 0.000901 loss: 3.7322 (3.6685) grad_norm: 1.0209 (1.0619) time: 0.5036 [2021-03-25 14:23:04 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 490/1251] eta: 0:06:31 lr: 0.000901 loss: 3.7736 (3.6690) grad_norm: 1.0112 (1.0596) time: 0.5078 [2021-03-25 14:23:09 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 500/1251] eta: 0:06:26 lr: 0.000901 loss: 3.8490 (3.6702) grad_norm: 0.9546 (1.0586) time: 0.5088 [2021-03-25 14:23:14 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 510/1251] eta: 0:06:20 lr: 0.000901 loss: 3.7487 (3.6703) grad_norm: 0.9680 (1.0584) time: 0.5066 [2021-03-25 14:23:19 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 520/1251] eta: 0:06:15 lr: 0.000901 loss: 3.8241 (3.6756) grad_norm: 1.0352 (1.0591) time: 0.5070 [2021-03-25 14:23:24 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 530/1251] eta: 0:06:10 lr: 0.000901 loss: 3.8460 (3.6763) grad_norm: 1.0352 (1.0580) time: 0.5113 [2021-03-25 14:23:29 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 540/1251] eta: 0:06:05 lr: 0.000901 loss: 3.7363 (3.6748) grad_norm: 1.0251 (1.0573) time: 0.5036 [2021-03-25 14:23:34 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 550/1251] eta: 0:06:00 lr: 0.000901 loss: 3.7655 (3.6792) grad_norm: 1.0069 (1.0562) time: 0.5106 [2021-03-25 14:23:39 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 560/1251] eta: 0:05:55 lr: 0.000901 loss: 3.9561 (3.6809) grad_norm: 1.0071 (1.0562) time: 0.5178 [2021-03-25 14:23:44 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 570/1251] eta: 0:05:49 lr: 0.000901 loss: 3.8853 (3.6821) grad_norm: 1.0303 (1.0554) time: 0.5043 [2021-03-25 14:23:49 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 580/1251] eta: 0:05:44 lr: 0.000901 loss: 3.8853 (3.6838) grad_norm: 1.0500 (1.0564) time: 0.4994 [2021-03-25 14:23:55 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 590/1251] eta: 0:05:39 lr: 0.000901 loss: 3.7438 (3.6850) grad_norm: 1.0442 (1.0561) time: 0.5039 [2021-03-25 14:24:00 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 600/1251] eta: 0:05:34 lr: 0.000901 loss: 3.7008 (3.6829) grad_norm: 1.0041 (1.0550) time: 0.5068 [2021-03-25 14:24:05 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 610/1251] eta: 0:05:28 lr: 0.000901 loss: 3.6969 (3.6815) grad_norm: 0.9929 (1.0544) time: 0.5060 [2021-03-25 14:24:10 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 620/1251] eta: 0:05:23 lr: 0.000901 loss: 3.5720 (3.6810) grad_norm: 1.0076 (1.0539) time: 0.5038 [2021-03-25 14:24:15 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 630/1251] eta: 0:05:18 lr: 0.000901 loss: 3.5720 (3.6805) grad_norm: 1.0053 (1.0533) time: 0.5019 [2021-03-25 14:24:20 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 640/1251] eta: 0:05:13 lr: 0.000901 loss: 3.6406 (3.6789) grad_norm: 1.0276 (1.0537) time: 0.5007 [2021-03-25 14:24:25 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 650/1251] eta: 0:05:07 lr: 0.000901 loss: 3.5972 (3.6772) grad_norm: 1.0627 (1.0549) time: 0.5004 [2021-03-25 14:24:30 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 660/1251] eta: 0:05:02 lr: 0.000901 loss: 3.5972 (3.6762) grad_norm: 1.1571 (1.0571) time: 0.5013 [2021-03-25 14:24:35 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 670/1251] eta: 0:04:57 lr: 0.000901 loss: 3.5609 (3.6727) grad_norm: 1.0698 (1.0564) time: 0.4980 [2021-03-25 14:24:40 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 680/1251] eta: 0:04:52 lr: 0.000901 loss: 3.5609 (3.6734) grad_norm: 0.9937 (1.0557) time: 0.4972 [2021-03-25 14:24:45 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 690/1251] eta: 0:04:47 lr: 0.000901 loss: 3.5983 (3.6711) grad_norm: 0.9937 (1.0553) time: 0.5053 [2021-03-25 14:24:50 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 700/1251] eta: 0:04:41 lr: 0.000901 loss: 3.5983 (3.6706) grad_norm: 1.0816 (1.0563) time: 0.5100 [2021-03-25 14:24:55 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 710/1251] eta: 0:04:36 lr: 0.000901 loss: 3.6195 (3.6707) grad_norm: 1.0820 (1.0566) time: 0.5026 [2021-03-25 14:25:00 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 720/1251] eta: 0:04:31 lr: 0.000901 loss: 3.6982 (3.6701) grad_norm: 1.0500 (1.0568) time: 0.5023 [2021-03-25 14:25:05 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 730/1251] eta: 0:04:26 lr: 0.000901 loss: 3.7998 (3.6702) grad_norm: 1.0150 (1.0558) time: 0.5010 [2021-03-25 14:25:10 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 740/1251] eta: 0:04:21 lr: 0.000901 loss: 3.7399 (3.6698) grad_norm: 0.9970 (1.0558) time: 0.5092 [2021-03-25 14:25:15 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 750/1251] eta: 0:04:16 lr: 0.000901 loss: 3.7380 (3.6671) grad_norm: 0.9970 (1.0555) time: 0.5136 [2021-03-25 14:25:20 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 760/1251] eta: 0:04:10 lr: 0.000901 loss: 4.0158 (3.6723) grad_norm: 0.9456 (1.0553) time: 0.5038 [2021-03-25 14:25:25 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 770/1251] eta: 0:04:05 lr: 0.000900 loss: 4.0201 (3.6732) grad_norm: 1.0171 (1.0549) time: 0.4995 [2021-03-25 14:25:30 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 780/1251] eta: 0:04:00 lr: 0.000900 loss: 3.8112 (3.6734) grad_norm: 1.0164 (1.0544) time: 0.4956 [2021-03-25 14:25:35 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 790/1251] eta: 0:03:55 lr: 0.000900 loss: 3.8070 (3.6743) grad_norm: 0.9821 (1.0540) time: 0.5032 [2021-03-25 14:25:40 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 800/1251] eta: 0:03:50 lr: 0.000900 loss: 3.7523 (3.6719) grad_norm: 1.0294 (1.0544) time: 0.5078 [2021-03-25 14:25:45 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 810/1251] eta: 0:03:45 lr: 0.000900 loss: 3.7312 (3.6739) grad_norm: 1.0684 (1.0546) time: 0.5060 [2021-03-25 14:25:50 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 820/1251] eta: 0:03:40 lr: 0.000900 loss: 3.7312 (3.6727) grad_norm: 1.0159 (1.0539) time: 0.5045 [2021-03-25 14:25:55 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 830/1251] eta: 0:03:34 lr: 0.000900 loss: 3.7550 (3.6734) grad_norm: 0.9340 (1.0526) time: 0.5055 [2021-03-25 14:26:00 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 840/1251] eta: 0:03:29 lr: 0.000900 loss: 3.8490 (3.6749) grad_norm: 0.9788 (1.0525) time: 0.5061 [2021-03-25 14:26:06 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 850/1251] eta: 0:03:24 lr: 0.000900 loss: 3.8943 (3.6760) grad_norm: 1.0324 (1.0527) time: 0.5070 [2021-03-25 14:26:11 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 860/1251] eta: 0:03:19 lr: 0.000900 loss: 3.9478 (3.6808) grad_norm: 1.0324 (1.0526) time: 0.5083 [2021-03-25 14:26:16 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 870/1251] eta: 0:03:14 lr: 0.000900 loss: 3.9343 (3.6819) grad_norm: 0.9898 (1.0518) time: 0.5030 [2021-03-25 14:26:21 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 880/1251] eta: 0:03:09 lr: 0.000900 loss: 3.7778 (3.6822) grad_norm: 1.0367 (1.0521) time: 0.5085 [2021-03-25 14:26:26 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 890/1251] eta: 0:03:04 lr: 0.000900 loss: 3.7576 (3.6830) grad_norm: 1.0883 (1.0532) time: 0.5079 [2021-03-25 14:26:31 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 900/1251] eta: 0:02:59 lr: 0.000900 loss: 4.0143 (3.6862) grad_norm: 1.0883 (1.0533) time: 0.4994 [2021-03-25 14:26:36 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 910/1251] eta: 0:02:53 lr: 0.000900 loss: 3.7667 (3.6843) grad_norm: 1.0554 (1.0538) time: 0.5003 [2021-03-25 14:26:41 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 920/1251] eta: 0:02:48 lr: 0.000900 loss: 3.7949 (3.6894) grad_norm: 1.0680 (1.0543) time: 0.4998 [2021-03-25 14:26:46 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 930/1251] eta: 0:02:43 lr: 0.000900 loss: 3.8238 (3.6880) grad_norm: 1.0795 (1.0545) time: 0.4991 [2021-03-25 14:26:51 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 940/1251] eta: 0:02:38 lr: 0.000900 loss: 3.7512 (3.6876) grad_norm: 1.0005 (1.0535) time: 0.5064 [2021-03-25 14:26:56 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 950/1251] eta: 0:02:33 lr: 0.000900 loss: 3.7121 (3.6861) grad_norm: 0.9935 (1.0532) time: 0.5090 [2021-03-25 14:27:01 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 960/1251] eta: 0:02:28 lr: 0.000900 loss: 3.7481 (3.6879) grad_norm: 1.0033 (1.0534) time: 0.5014 [2021-03-25 14:27:06 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 970/1251] eta: 0:02:23 lr: 0.000900 loss: 3.7940 (3.6873) grad_norm: 1.1008 (1.0545) time: 0.5008 [2021-03-25 14:27:11 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 980/1251] eta: 0:02:18 lr: 0.000900 loss: 3.6944 (3.6863) grad_norm: 1.1283 (1.0550) time: 0.5034 [2021-03-25 14:27:16 swin_small_patch4_window7_224] INFO: Epoch: [61] [ 990/1251] eta: 0:02:12 lr: 0.000900 loss: 3.9836 (3.6876) grad_norm: 0.9889 (1.0543) time: 0.5104 [2021-03-25 14:27:21 swin_small_patch4_window7_224] INFO: Epoch: [61] [1000/1251] eta: 0:02:07 lr: 0.000900 loss: 3.7925 (3.6855) grad_norm: 0.9896 (1.0537) time: 0.5171 [2021-03-25 14:27:26 swin_small_patch4_window7_224] INFO: Epoch: [61] [1010/1251] eta: 0:02:02 lr: 0.000900 loss: 3.5031 (3.6870) grad_norm: 1.0080 (1.0534) time: 0.5098 [2021-03-25 14:27:31 swin_small_patch4_window7_224] INFO: Epoch: [61] [1020/1251] eta: 0:01:57 lr: 0.000900 loss: 4.0202 (3.6887) grad_norm: 1.0124 (1.0535) time: 0.5051 [2021-03-25 14:27:36 swin_small_patch4_window7_224] INFO: Epoch: [61] [1030/1251] eta: 0:01:52 lr: 0.000900 loss: 3.8697 (3.6892) grad_norm: 0.9915 (1.0529) time: 0.5027 [2021-03-25 14:27:42 swin_small_patch4_window7_224] INFO: Epoch: [61] [1040/1251] eta: 0:01:47 lr: 0.000900 loss: 3.8381 (3.6906) grad_norm: 1.0140 (1.0529) time: 0.5039 [2021-03-25 14:27:47 swin_small_patch4_window7_224] INFO: Epoch: [61] [1050/1251] eta: 0:01:42 lr: 0.000900 loss: 3.8475 (3.6915) grad_norm: 1.0100 (1.0519) time: 0.5085 [2021-03-25 14:27:52 swin_small_patch4_window7_224] INFO: Epoch: [61] [1060/1251] eta: 0:01:37 lr: 0.000900 loss: 3.8228 (3.6899) grad_norm: 0.9638 (1.0520) time: 0.5030 [2021-03-25 14:27:57 swin_small_patch4_window7_224] INFO: Epoch: [61] [1070/1251] eta: 0:01:32 lr: 0.000900 loss: 3.5769 (3.6892) grad_norm: 1.0176 (1.0521) time: 0.5020 [2021-03-25 14:28:02 swin_small_patch4_window7_224] INFO: Epoch: [61] [1080/1251] eta: 0:01:27 lr: 0.000900 loss: 3.6085 (3.6899) grad_norm: 0.9952 (1.0517) time: 0.5041 [2021-03-25 14:28:07 swin_small_patch4_window7_224] INFO: Epoch: [61] [1090/1251] eta: 0:01:21 lr: 0.000900 loss: 3.8386 (3.6910) grad_norm: 0.9725 (1.0512) time: 0.5047 [2021-03-25 14:28:12 swin_small_patch4_window7_224] INFO: Epoch: [61] [1100/1251] eta: 0:01:16 lr: 0.000900 loss: 3.9190 (3.6933) grad_norm: 0.9725 (1.0508) time: 0.5068 [2021-03-25 14:28:17 swin_small_patch4_window7_224] INFO: Epoch: [61] [1110/1251] eta: 0:01:11 lr: 0.000900 loss: 4.0649 (3.6951) grad_norm: 1.0533 (1.0510) time: 0.5119 [2021-03-25 14:28:22 swin_small_patch4_window7_224] INFO: Epoch: [61] [1120/1251] eta: 0:01:06 lr: 0.000900 loss: 3.8607 (3.6933) grad_norm: 1.0495 (1.0506) time: 0.5072 [2021-03-25 14:28:27 swin_small_patch4_window7_224] INFO: Epoch: [61] [1130/1251] eta: 0:01:01 lr: 0.000900 loss: 3.3545 (3.6894) grad_norm: 1.0370 (inf) time: 0.4971 [2021-03-25 14:28:32 swin_small_patch4_window7_224] INFO: Epoch: [61] [1140/1251] eta: 0:00:56 lr: 0.000900 loss: 3.5633 (3.6900) grad_norm: 0.9988 (inf) time: 0.5015 [2021-03-25 14:28:37 swin_small_patch4_window7_224] INFO: Epoch: [61] [1150/1251] eta: 0:00:51 lr: 0.000900 loss: 3.7675 (3.6903) grad_norm: 1.0286 (inf) time: 0.5053 [2021-03-25 14:28:42 swin_small_patch4_window7_224] INFO: Epoch: [61] [1160/1251] eta: 0:00:46 lr: 0.000900 loss: 3.7050 (3.6909) grad_norm: 1.0286 (inf) time: 0.5015 [2021-03-25 14:28:47 swin_small_patch4_window7_224] INFO: Epoch: [61] [1170/1251] eta: 0:00:41 lr: 0.000899 loss: 3.8015 (3.6924) grad_norm: 1.0252 (inf) time: 0.5030 [2021-03-25 14:28:52 swin_small_patch4_window7_224] INFO: Epoch: [61] [1180/1251] eta: 0:00:36 lr: 0.000899 loss: 3.7636 (3.6924) grad_norm: 1.0496 (inf) time: 0.5039 [2021-03-25 14:28:57 swin_small_patch4_window7_224] INFO: Epoch: [61] [1190/1251] eta: 0:00:31 lr: 0.000899 loss: 3.6307 (3.6929) grad_norm: 1.0143 (inf) time: 0.5089 [2021-03-25 14:29:02 swin_small_patch4_window7_224] INFO: Epoch: [61] [1200/1251] eta: 0:00:25 lr: 0.000899 loss: 3.6699 (3.6917) grad_norm: 1.0028 (inf) time: 0.5079 [2021-03-25 14:29:07 swin_small_patch4_window7_224] INFO: Epoch: [61] [1210/1251] eta: 0:00:20 lr: 0.000899 loss: 3.6699 (3.6906) grad_norm: 1.0011 (inf) time: 0.5015 [2021-03-25 14:29:12 swin_small_patch4_window7_224] INFO: Epoch: [61] [1220/1251] eta: 0:00:15 lr: 0.000899 loss: 3.4672 (3.6894) grad_norm: 1.0055 (inf) time: 0.5028 [2021-03-25 14:29:17 swin_small_patch4_window7_224] INFO: Epoch: [61] [1230/1251] eta: 0:00:10 lr: 0.000899 loss: 3.4731 (3.6888) grad_norm: 1.0118 (inf) time: 0.5039 [2021-03-25 14:29:22 swin_small_patch4_window7_224] INFO: Epoch: [61] [1240/1251] eta: 0:00:05 lr: 0.000899 loss: 3.4731 (3.6884) grad_norm: 1.0687 (inf) time: 0.5043 [2021-03-25 14:29:27 swin_small_patch4_window7_224] INFO: Epoch: [61] [1250/1251] eta: 0:00:00 lr: 0.000899 loss: 3.4679 (3.6876) grad_norm: 1.0231 (inf) time: 0.4997 [2021-03-25 14:29:34 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:35 loss: 1.5185 (1.5185) acc1: 70.3125 (70.3125) acc5: 92.1875 (92.1875) [2021-03-25 14:29:36 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1923 (1.1878) acc1: 70.3125 (72.4432) acc5: 92.1875 (91.7614) [2021-03-25 14:29:38 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0796 (1.1352) acc1: 70.3125 (72.3958) acc5: 92.1875 (92.8571) [2021-03-25 14:29:40 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1030 (1.1431) acc1: 70.3125 (71.8246) acc5: 92.1875 (92.5403) [2021-03-25 14:29:43 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1033 (1.1290) acc1: 71.8750 (72.5229) acc5: 93.7500 (92.8735) [2021-03-25 14:29:44 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1201 (1.1344) acc1: 71.8750 (72.5760) acc5: 92.1875 (92.5760) [2021-03-25 14:29:46 swin_small_patch4_window7_224] INFO: * Acc@1 73.934 Acc@5 92.248 loss 1.109 [2021-03-25 14:29:46 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.9% [2021-03-25 14:29:46 swin_small_patch4_window7_224] INFO: Max accuracy: 73.93% [2021-03-25 14:29:51 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 0/1251] eta: 1:25:56 lr: 0.000899 loss: 3.8765 (3.8765) grad_norm: 0.9529 (0.9529) time: 4.1220 [2021-03-25 14:29:56 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 10/1251] eta: 0:17:19 lr: 0.000899 loss: 3.9543 (3.6845) grad_norm: 0.9529 (0.9577) time: 0.8374 [2021-03-25 14:30:01 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 20/1251] eta: 0:13:50 lr: 0.000899 loss: 3.8632 (3.5929) grad_norm: 0.9585 (0.9773) time: 0.5019 [2021-03-25 14:30:06 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 30/1251] eta: 0:12:35 lr: 0.000899 loss: 3.8632 (3.6934) grad_norm: 0.9726 (0.9748) time: 0.4980 [2021-03-25 14:30:11 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 40/1251] eta: 0:11:55 lr: 0.000899 loss: 3.8220 (3.6702) grad_norm: 0.9873 (0.9849) time: 0.5025 [2021-03-25 14:30:16 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 50/1251] eta: 0:11:29 lr: 0.000899 loss: 3.8229 (3.6959) grad_norm: 1.0143 (0.9968) time: 0.5053 [2021-03-25 14:30:21 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 60/1251] eta: 0:11:10 lr: 0.000899 loss: 3.9887 (3.7086) grad_norm: 1.0658 (1.0077) time: 0.5052 [2021-03-25 14:30:26 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 70/1251] eta: 0:10:57 lr: 0.000899 loss: 3.6692 (3.6825) grad_norm: 1.0008 (1.0032) time: 0.5116 [2021-03-25 14:30:31 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 80/1251] eta: 0:10:44 lr: 0.000899 loss: 3.5163 (3.6433) grad_norm: 0.9764 (0.9996) time: 0.5133 [2021-03-25 14:30:36 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 90/1251] eta: 0:10:35 lr: 0.000899 loss: 3.6692 (3.6454) grad_norm: 0.9725 (0.9983) time: 0.5140 [2021-03-25 14:30:41 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 100/1251] eta: 0:10:24 lr: 0.000899 loss: 3.6482 (3.6328) grad_norm: 0.9966 (0.9989) time: 0.5094 [2021-03-25 14:30:46 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 110/1251] eta: 0:10:14 lr: 0.000899 loss: 3.5843 (3.6298) grad_norm: 1.0001 (1.0048) time: 0.5011 [2021-03-25 14:30:51 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 120/1251] eta: 0:10:06 lr: 0.000899 loss: 3.6310 (3.6336) grad_norm: 1.0278 (1.0085) time: 0.5043 [2021-03-25 14:30:56 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 130/1251] eta: 0:09:59 lr: 0.000899 loss: 3.4998 (3.6168) grad_norm: 1.0401 (1.0115) time: 0.5100 [2021-03-25 14:31:01 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 140/1251] eta: 0:09:51 lr: 0.000899 loss: 3.4302 (3.6106) grad_norm: 1.0553 (1.0138) time: 0.5088 [2021-03-25 14:31:07 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 150/1251] eta: 0:09:43 lr: 0.000899 loss: 3.6200 (3.6035) grad_norm: 1.0825 (1.0220) time: 0.5040 [2021-03-25 14:31:12 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 160/1251] eta: 0:09:36 lr: 0.000899 loss: 3.4504 (3.5946) grad_norm: 1.1061 (1.0266) time: 0.5051 [2021-03-25 14:31:17 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 170/1251] eta: 0:09:29 lr: 0.000899 loss: 3.4005 (3.5901) grad_norm: 1.1185 (1.0305) time: 0.5015 [2021-03-25 14:31:22 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 180/1251] eta: 0:09:23 lr: 0.000899 loss: 3.6625 (3.5897) grad_norm: 1.0730 (1.0337) time: 0.5047 [2021-03-25 14:31:27 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 190/1251] eta: 0:09:17 lr: 0.000899 loss: 3.5827 (3.5860) grad_norm: 1.0780 (1.0376) time: 0.5094 [2021-03-25 14:31:32 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 200/1251] eta: 0:09:10 lr: 0.000899 loss: 3.5827 (3.5915) grad_norm: 1.0852 (1.0380) time: 0.5040 [2021-03-25 14:31:37 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 210/1251] eta: 0:09:04 lr: 0.000899 loss: 3.8160 (3.6077) grad_norm: 0.9899 (1.0362) time: 0.4980 [2021-03-25 14:31:42 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 220/1251] eta: 0:08:58 lr: 0.000899 loss: 3.9261 (3.6019) grad_norm: 0.9717 (1.0328) time: 0.5008 [2021-03-25 14:31:47 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 230/1251] eta: 0:08:52 lr: 0.000899 loss: 3.7253 (3.6035) grad_norm: 1.0177 (1.0336) time: 0.5090 [2021-03-25 14:31:52 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 240/1251] eta: 0:08:46 lr: 0.000899 loss: 3.8192 (3.6106) grad_norm: 1.0008 (1.0316) time: 0.5043 [2021-03-25 14:31:57 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 250/1251] eta: 0:08:40 lr: 0.000899 loss: 3.6612 (3.6055) grad_norm: 1.0201 (1.0328) time: 0.4986 [2021-03-25 14:32:02 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 260/1251] eta: 0:08:34 lr: 0.000899 loss: 3.5156 (3.6068) grad_norm: 1.0368 (1.0327) time: 0.5048 [2021-03-25 14:32:07 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 270/1251] eta: 0:08:28 lr: 0.000899 loss: 3.3819 (3.5996) grad_norm: 1.0739 (1.0346) time: 0.5050 [2021-03-25 14:32:12 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 280/1251] eta: 0:08:22 lr: 0.000899 loss: 3.5904 (3.6021) grad_norm: 1.0739 (1.0360) time: 0.5022 [2021-03-25 14:32:17 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 290/1251] eta: 0:08:17 lr: 0.000899 loss: 3.7365 (3.6047) grad_norm: 0.9709 (1.0333) time: 0.5026 [2021-03-25 14:32:22 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 300/1251] eta: 0:08:11 lr: 0.000899 loss: 3.5532 (3.6072) grad_norm: 0.9448 (1.0321) time: 0.5026 [2021-03-25 14:32:27 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 310/1251] eta: 0:08:06 lr: 0.000899 loss: 3.8535 (3.6152) grad_norm: 0.9732 (1.0334) time: 0.5035 [2021-03-25 14:32:32 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 320/1251] eta: 0:08:00 lr: 0.000898 loss: 3.8042 (3.6158) grad_norm: 1.0050 (1.0324) time: 0.5058 [2021-03-25 14:32:37 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 330/1251] eta: 0:07:54 lr: 0.000898 loss: 3.7906 (3.6169) grad_norm: 1.0093 (1.0333) time: 0.4998 [2021-03-25 14:32:42 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 340/1251] eta: 0:07:49 lr: 0.000898 loss: 3.7797 (3.6131) grad_norm: 1.0051 (1.0323) time: 0.4984 [2021-03-25 14:32:47 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 350/1251] eta: 0:07:44 lr: 0.000898 loss: 3.8079 (3.6134) grad_norm: 1.0079 (1.0333) time: 0.5072 [2021-03-25 14:32:52 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 360/1251] eta: 0:07:38 lr: 0.000898 loss: 3.9039 (3.6185) grad_norm: 1.0289 (1.0341) time: 0.5053 [2021-03-25 14:32:57 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 370/1251] eta: 0:07:33 lr: 0.000898 loss: 3.9039 (3.6265) grad_norm: 1.0735 (1.0371) time: 0.5029 [2021-03-25 14:33:03 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 380/1251] eta: 0:07:28 lr: 0.000898 loss: 3.9365 (3.6338) grad_norm: 1.1096 (1.0376) time: 0.5147 [2021-03-25 14:33:08 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 390/1251] eta: 0:07:22 lr: 0.000898 loss: 3.9391 (3.6346) grad_norm: 1.0414 (1.0380) time: 0.5131 [2021-03-25 14:33:13 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 400/1251] eta: 0:07:17 lr: 0.000898 loss: 3.8337 (3.6361) grad_norm: 1.0377 (1.0386) time: 0.5019 [2021-03-25 14:33:18 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 410/1251] eta: 0:07:11 lr: 0.000898 loss: 3.8167 (3.6353) grad_norm: 0.9723 (1.0376) time: 0.4979 [2021-03-25 14:33:23 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 420/1251] eta: 0:07:06 lr: 0.000898 loss: 3.7753 (3.6385) grad_norm: 0.9602 (1.0372) time: 0.5007 [2021-03-25 14:33:28 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 430/1251] eta: 0:07:01 lr: 0.000898 loss: 3.6907 (3.6341) grad_norm: 1.0519 (1.0388) time: 0.5020 [2021-03-25 14:33:33 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 440/1251] eta: 0:06:55 lr: 0.000898 loss: 3.3224 (3.6294) grad_norm: 1.0561 (1.0385) time: 0.5002 [2021-03-25 14:33:38 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 450/1251] eta: 0:06:50 lr: 0.000898 loss: 3.3942 (3.6257) grad_norm: 1.0379 (1.0400) time: 0.5042 [2021-03-25 14:33:43 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 460/1251] eta: 0:06:45 lr: 0.000898 loss: 3.6303 (3.6248) grad_norm: 1.0904 (1.0424) time: 0.5037 [2021-03-25 14:33:48 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 470/1251] eta: 0:06:40 lr: 0.000898 loss: 3.8756 (3.6259) grad_norm: 1.0781 (1.0435) time: 0.5033 [2021-03-25 14:33:53 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 480/1251] eta: 0:06:34 lr: 0.000898 loss: 3.8149 (3.6259) grad_norm: 1.0545 (1.0440) time: 0.5059 [2021-03-25 14:33:58 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 490/1251] eta: 0:06:29 lr: 0.000898 loss: 3.7832 (3.6272) grad_norm: 1.0105 (1.0429) time: 0.5020 [2021-03-25 14:34:03 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 500/1251] eta: 0:06:24 lr: 0.000898 loss: 3.8417 (3.6325) grad_norm: 1.0013 (1.0421) time: 0.4965 [2021-03-25 14:34:08 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 510/1251] eta: 0:06:18 lr: 0.000898 loss: 3.8843 (3.6317) grad_norm: 1.0132 (1.0425) time: 0.4981 [2021-03-25 14:34:13 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 520/1251] eta: 0:06:13 lr: 0.000898 loss: 3.7100 (3.6322) grad_norm: 0.9900 (1.0405) time: 0.5031 [2021-03-25 14:34:18 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 530/1251] eta: 0:06:08 lr: 0.000898 loss: 3.7329 (3.6355) grad_norm: 0.9529 (1.0410) time: 0.5075 [2021-03-25 14:34:23 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 540/1251] eta: 0:06:03 lr: 0.000898 loss: 3.8797 (3.6388) grad_norm: 1.0084 (1.0415) time: 0.5058 [2021-03-25 14:34:28 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 550/1251] eta: 0:05:58 lr: 0.000898 loss: 3.8425 (3.6410) grad_norm: 1.0365 (1.0424) time: 0.5143 [2021-03-25 14:34:33 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 560/1251] eta: 0:05:53 lr: 0.000898 loss: 3.9801 (3.6415) grad_norm: 1.0067 (1.0422) time: 0.5101 [2021-03-25 14:34:38 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 570/1251] eta: 0:05:47 lr: 0.000898 loss: 3.7112 (3.6440) grad_norm: 0.9794 (1.0419) time: 0.5028 [2021-03-25 14:34:43 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 580/1251] eta: 0:05:42 lr: 0.000898 loss: 3.6913 (3.6454) grad_norm: 0.9794 (1.0406) time: 0.5035 [2021-03-25 14:34:48 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 590/1251] eta: 0:05:37 lr: 0.000898 loss: 3.8699 (3.6470) grad_norm: 0.9677 (1.0397) time: 0.5031 [2021-03-25 14:34:53 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 600/1251] eta: 0:05:32 lr: 0.000898 loss: 3.8595 (3.6499) grad_norm: 1.0210 (1.0405) time: 0.5069 [2021-03-25 14:34:58 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 610/1251] eta: 0:05:27 lr: 0.000898 loss: 3.8595 (3.6524) grad_norm: 1.0966 (1.0415) time: 0.4989 [2021-03-25 14:35:03 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 620/1251] eta: 0:05:21 lr: 0.000898 loss: 3.8502 (3.6515) grad_norm: 1.0541 (1.0416) time: 0.4944 [2021-03-25 14:35:08 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 630/1251] eta: 0:05:16 lr: 0.000898 loss: 3.8530 (3.6560) grad_norm: 1.0405 (1.0414) time: 0.5013 [2021-03-25 14:35:13 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 640/1251] eta: 0:05:11 lr: 0.000898 loss: 3.7196 (3.6521) grad_norm: 0.9869 (1.0408) time: 0.5090 [2021-03-25 14:35:18 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 650/1251] eta: 0:05:06 lr: 0.000898 loss: 3.2035 (3.6492) grad_norm: 0.9982 (1.0410) time: 0.5037 [2021-03-25 14:35:23 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 660/1251] eta: 0:05:01 lr: 0.000898 loss: 3.6658 (3.6531) grad_norm: 1.0269 (1.0418) time: 0.5009 [2021-03-25 14:35:28 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 670/1251] eta: 0:04:56 lr: 0.000898 loss: 3.8724 (3.6513) grad_norm: 1.0642 (1.0420) time: 0.5025 [2021-03-25 14:35:34 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 680/1251] eta: 0:04:51 lr: 0.000898 loss: 3.9767 (3.6538) grad_norm: 1.0584 (1.0423) time: 0.5154 [2021-03-25 14:35:39 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 690/1251] eta: 0:04:45 lr: 0.000898 loss: 3.6538 (3.6504) grad_norm: 1.0875 (1.0440) time: 0.5162 [2021-03-25 14:35:44 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 700/1251] eta: 0:04:40 lr: 0.000898 loss: 3.4802 (3.6508) grad_norm: 1.0148 (1.0435) time: 0.5036 [2021-03-25 14:35:49 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 710/1251] eta: 0:04:35 lr: 0.000897 loss: 3.7594 (3.6493) grad_norm: 0.9757 (1.0429) time: 0.5004 [2021-03-25 14:35:54 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 720/1251] eta: 0:04:30 lr: 0.000897 loss: 3.7594 (3.6490) grad_norm: 0.9887 (1.0440) time: 0.4945 [2021-03-25 14:35:59 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 730/1251] eta: 0:04:25 lr: 0.000897 loss: 3.6746 (3.6473) grad_norm: 1.0013 (1.0437) time: 0.4997 [2021-03-25 14:36:04 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 740/1251] eta: 0:04:20 lr: 0.000897 loss: 3.5883 (3.6483) grad_norm: 1.0083 (1.0438) time: 0.5187 [2021-03-25 14:36:09 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 750/1251] eta: 0:04:15 lr: 0.000897 loss: 3.8220 (3.6467) grad_norm: 1.0438 (1.0451) time: 0.5178 [2021-03-25 14:36:14 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 760/1251] eta: 0:04:10 lr: 0.000897 loss: 3.8605 (3.6495) grad_norm: 1.0438 (1.0447) time: 0.5045 [2021-03-25 14:36:19 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 770/1251] eta: 0:04:04 lr: 0.000897 loss: 3.8774 (3.6495) grad_norm: 0.9931 (1.0446) time: 0.5039 [2021-03-25 14:36:24 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 780/1251] eta: 0:03:59 lr: 0.000897 loss: 3.5352 (3.6462) grad_norm: 1.0166 (1.0445) time: 0.5017 [2021-03-25 14:36:29 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 790/1251] eta: 0:03:54 lr: 0.000897 loss: 3.4618 (3.6463) grad_norm: 1.0182 (1.0438) time: 0.5038 [2021-03-25 14:36:34 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 800/1251] eta: 0:03:49 lr: 0.000897 loss: 3.4513 (3.6449) grad_norm: 0.9936 (1.0434) time: 0.5033 [2021-03-25 14:36:39 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 810/1251] eta: 0:03:44 lr: 0.000897 loss: 3.8442 (3.6466) grad_norm: 0.9842 (1.0439) time: 0.5053 [2021-03-25 14:36:44 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 820/1251] eta: 0:03:39 lr: 0.000897 loss: 3.8574 (3.6488) grad_norm: 1.0577 (1.0443) time: 0.5061 [2021-03-25 14:36:50 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 830/1251] eta: 0:03:34 lr: 0.000897 loss: 3.5673 (3.6461) grad_norm: 1.0990 (1.0462) time: 0.5092 [2021-03-25 14:36:55 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 840/1251] eta: 0:03:29 lr: 0.000897 loss: 3.5019 (3.6440) grad_norm: 1.1154 (1.0461) time: 0.5136 [2021-03-25 14:37:00 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 850/1251] eta: 0:03:24 lr: 0.000897 loss: 3.6878 (3.6458) grad_norm: 1.0600 (1.0465) time: 0.5059 [2021-03-25 14:37:05 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 860/1251] eta: 0:03:18 lr: 0.000897 loss: 3.8315 (3.6467) grad_norm: 1.0600 (1.0464) time: 0.5016 [2021-03-25 14:37:10 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 870/1251] eta: 0:03:13 lr: 0.000897 loss: 3.1486 (3.6399) grad_norm: 1.0309 (1.0462) time: 0.5103 [2021-03-25 14:37:15 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 880/1251] eta: 0:03:08 lr: 0.000897 loss: 2.9588 (3.6398) grad_norm: 1.0239 (1.0463) time: 0.5097 [2021-03-25 14:37:20 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 890/1251] eta: 0:03:03 lr: 0.000897 loss: 3.8523 (3.6410) grad_norm: 1.0118 (1.0461) time: 0.5022 [2021-03-25 14:37:25 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 900/1251] eta: 0:02:58 lr: 0.000897 loss: 3.7002 (3.6392) grad_norm: 1.0229 (1.0459) time: 0.5053 [2021-03-25 14:37:30 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 910/1251] eta: 0:02:53 lr: 0.000897 loss: 3.6380 (3.6388) grad_norm: 1.0139 (1.0456) time: 0.5043 [2021-03-25 14:37:35 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 920/1251] eta: 0:02:48 lr: 0.000897 loss: 3.7441 (3.6387) grad_norm: 1.0190 (1.0463) time: 0.5083 [2021-03-25 14:37:40 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 930/1251] eta: 0:02:43 lr: 0.000897 loss: 3.5800 (3.6372) grad_norm: 1.0646 (1.0468) time: 0.5137 [2021-03-25 14:37:46 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 940/1251] eta: 0:02:38 lr: 0.000897 loss: 3.4306 (3.6366) grad_norm: 1.0477 (1.0470) time: 0.5155 [2021-03-25 14:37:51 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 950/1251] eta: 0:02:33 lr: 0.000897 loss: 3.7581 (3.6387) grad_norm: 1.0499 (1.0476) time: 0.5076 [2021-03-25 14:37:56 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 960/1251] eta: 0:02:28 lr: 0.000897 loss: 3.7581 (3.6377) grad_norm: 1.0350 (1.0474) time: 0.5015 [2021-03-25 14:38:01 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 970/1251] eta: 0:02:22 lr: 0.000897 loss: 3.8191 (3.6391) grad_norm: 1.0342 (1.0474) time: 0.5095 [2021-03-25 14:38:06 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 980/1251] eta: 0:02:17 lr: 0.000897 loss: 3.8302 (3.6385) grad_norm: 1.0411 (1.0471) time: 0.5091 [2021-03-25 14:38:11 swin_small_patch4_window7_224] INFO: Epoch: [62] [ 990/1251] eta: 0:02:12 lr: 0.000897 loss: 3.7105 (3.6390) grad_norm: 0.9396 (1.0464) time: 0.5066 [2021-03-25 14:38:16 swin_small_patch4_window7_224] INFO: Epoch: [62] [1000/1251] eta: 0:02:07 lr: 0.000897 loss: 3.5905 (3.6369) grad_norm: 0.9396 (1.0461) time: 0.5059 [2021-03-25 14:38:21 swin_small_patch4_window7_224] INFO: Epoch: [62] [1010/1251] eta: 0:02:02 lr: 0.000897 loss: 3.6374 (3.6370) grad_norm: 0.9699 (1.0456) time: 0.5053 [2021-03-25 14:38:26 swin_small_patch4_window7_224] INFO: Epoch: [62] [1020/1251] eta: 0:01:57 lr: 0.000897 loss: 3.8518 (3.6391) grad_norm: 1.0122 (1.0459) time: 0.5026 [2021-03-25 14:38:31 swin_small_patch4_window7_224] INFO: Epoch: [62] [1030/1251] eta: 0:01:52 lr: 0.000897 loss: 3.9070 (3.6417) grad_norm: 1.0231 (1.0453) time: 0.5011 [2021-03-25 14:38:36 swin_small_patch4_window7_224] INFO: Epoch: [62] [1040/1251] eta: 0:01:47 lr: 0.000897 loss: 3.7759 (3.6417) grad_norm: 1.0119 (1.0451) time: 0.5026 [2021-03-25 14:38:41 swin_small_patch4_window7_224] INFO: Epoch: [62] [1050/1251] eta: 0:01:42 lr: 0.000897 loss: 3.6880 (3.6398) grad_norm: 1.0576 (1.0456) time: 0.5035 [2021-03-25 14:38:46 swin_small_patch4_window7_224] INFO: Epoch: [62] [1060/1251] eta: 0:01:37 lr: 0.000897 loss: 3.6303 (3.6403) grad_norm: 1.0539 (1.0455) time: 0.5030 [2021-03-25 14:38:51 swin_small_patch4_window7_224] INFO: Epoch: [62] [1070/1251] eta: 0:01:32 lr: 0.000897 loss: 3.7283 (3.6402) grad_norm: 1.0337 (1.0457) time: 0.5041 [2021-03-25 14:38:56 swin_small_patch4_window7_224] INFO: Epoch: [62] [1080/1251] eta: 0:01:26 lr: 0.000897 loss: 3.6592 (3.6405) grad_norm: 1.0475 (1.0467) time: 0.5066 [2021-03-25 14:39:01 swin_small_patch4_window7_224] INFO: Epoch: [62] [1090/1251] eta: 0:01:21 lr: 0.000897 loss: 3.8256 (3.6410) grad_norm: 1.0067 (1.0463) time: 0.5055 [2021-03-25 14:39:06 swin_small_patch4_window7_224] INFO: Epoch: [62] [1100/1251] eta: 0:01:16 lr: 0.000897 loss: 3.9189 (3.6423) grad_norm: 0.9897 (1.0462) time: 0.5070 [2021-03-25 14:39:11 swin_small_patch4_window7_224] INFO: Epoch: [62] [1110/1251] eta: 0:01:11 lr: 0.000896 loss: 3.9189 (3.6441) grad_norm: 0.9752 (1.0454) time: 0.5066 [2021-03-25 14:39:17 swin_small_patch4_window7_224] INFO: Epoch: [62] [1120/1251] eta: 0:01:06 lr: 0.000896 loss: 3.7933 (3.6452) grad_norm: 0.9694 (inf) time: 0.5095 [2021-03-25 14:39:22 swin_small_patch4_window7_224] INFO: Epoch: [62] [1130/1251] eta: 0:01:01 lr: 0.000896 loss: 3.7679 (3.6461) grad_norm: 0.9822 (inf) time: 0.5185 [2021-03-25 14:39:27 swin_small_patch4_window7_224] INFO: Epoch: [62] [1140/1251] eta: 0:00:56 lr: 0.000896 loss: 3.7289 (3.6474) grad_norm: 1.0671 (inf) time: 0.5067 [2021-03-25 14:39:32 swin_small_patch4_window7_224] INFO: Epoch: [62] [1150/1251] eta: 0:00:51 lr: 0.000896 loss: 3.6336 (3.6463) grad_norm: 1.0812 (inf) time: 0.4931 [2021-03-25 14:39:37 swin_small_patch4_window7_224] INFO: Epoch: [62] [1160/1251] eta: 0:00:46 lr: 0.000896 loss: 3.4291 (3.6455) grad_norm: 1.0846 (inf) time: 0.5060 [2021-03-25 14:39:42 swin_small_patch4_window7_224] INFO: Epoch: [62] [1170/1251] eta: 0:00:41 lr: 0.000896 loss: 3.6965 (3.6473) grad_norm: 1.0590 (inf) time: 0.5163 [2021-03-25 14:39:47 swin_small_patch4_window7_224] INFO: Epoch: [62] [1180/1251] eta: 0:00:36 lr: 0.000896 loss: 3.9909 (3.6489) grad_norm: 1.0413 (inf) time: 0.5102 [2021-03-25 14:39:52 swin_small_patch4_window7_224] INFO: Epoch: [62] [1190/1251] eta: 0:00:31 lr: 0.000896 loss: 3.9396 (3.6499) grad_norm: 0.9758 (inf) time: 0.5074 [2021-03-25 14:39:57 swin_small_patch4_window7_224] INFO: Epoch: [62] [1200/1251] eta: 0:00:25 lr: 0.000896 loss: 3.7865 (3.6500) grad_norm: 1.0026 (inf) time: 0.5091 [2021-03-25 14:40:02 swin_small_patch4_window7_224] INFO: Epoch: [62] [1210/1251] eta: 0:00:20 lr: 0.000896 loss: 3.6607 (3.6506) grad_norm: 1.0365 (inf) time: 0.5051 [2021-03-25 14:40:07 swin_small_patch4_window7_224] INFO: Epoch: [62] [1220/1251] eta: 0:00:15 lr: 0.000896 loss: 3.7731 (3.6501) grad_norm: 1.0142 (inf) time: 0.5029 [2021-03-25 14:40:12 swin_small_patch4_window7_224] INFO: Epoch: [62] [1230/1251] eta: 0:00:10 lr: 0.000896 loss: 3.4460 (3.6485) grad_norm: 1.0320 (inf) time: 0.5052 [2021-03-25 14:40:17 swin_small_patch4_window7_224] INFO: Epoch: [62] [1240/1251] eta: 0:00:05 lr: 0.000896 loss: 3.2949 (3.6464) grad_norm: 1.0374 (inf) time: 0.5015 [2021-03-25 14:40:22 swin_small_patch4_window7_224] INFO: Epoch: [62] [1250/1251] eta: 0:00:00 lr: 0.000896 loss: 3.6704 (3.6487) grad_norm: 1.0250 (inf) time: 0.5003 [2021-03-25 14:40:28 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:37 loss: 0.9879 (0.9879) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-25 14:40:30 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0025 (1.0988) acc1: 73.4375 (73.5795) acc5: 95.3125 (93.4659) [2021-03-25 14:40:33 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0971 (1.1333) acc1: 73.4375 (73.5863) acc5: 92.1875 (92.8571) [2021-03-25 14:40:36 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1089 (1.1173) acc1: 73.4375 (73.7399) acc5: 92.1875 (92.6915) [2021-03-25 14:40:37 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0521 (1.1044) acc1: 73.4375 (73.7424) acc5: 92.1875 (92.6829) [2021-03-25 14:40:38 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1087 (1.1190) acc1: 73.4375 (73.5680) acc5: 92.1875 (92.5440) [2021-03-25 14:40:40 swin_small_patch4_window7_224] INFO: * Acc@1 73.834 Acc@5 92.272 loss 1.097 [2021-03-25 14:40:40 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.8% [2021-03-25 14:40:40 swin_small_patch4_window7_224] INFO: Max accuracy: 73.93% [2021-03-25 14:40:44 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 0/1251] eta: 1:24:33 lr: 0.000896 loss: 3.5629 (3.5629) grad_norm: 1.0321 (1.0321) time: 4.0552 [2021-03-25 14:40:50 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 10/1251] eta: 0:17:44 lr: 0.000896 loss: 3.4239 (3.3646) grad_norm: 1.0656 (1.0803) time: 0.8575 [2021-03-25 14:40:55 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 20/1251] eta: 0:14:11 lr: 0.000896 loss: 3.4239 (3.4905) grad_norm: 1.0717 (1.1086) time: 0.5236 [2021-03-25 14:41:00 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 30/1251] eta: 0:12:55 lr: 0.000896 loss: 3.7252 (3.5337) grad_norm: 1.0592 (1.0683) time: 0.5129 [2021-03-25 14:41:05 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 40/1251] eta: 0:12:10 lr: 0.000896 loss: 3.7904 (3.5792) grad_norm: 0.9806 (1.0558) time: 0.5095 [2021-03-25 14:41:10 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 50/1251] eta: 0:11:43 lr: 0.000896 loss: 3.7840 (3.6125) grad_norm: 0.9999 (1.0482) time: 0.5093 [2021-03-25 14:41:15 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 60/1251] eta: 0:11:27 lr: 0.000896 loss: 3.7946 (3.6283) grad_norm: 1.0176 (1.0591) time: 0.5238 [2021-03-25 14:41:20 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 70/1251] eta: 0:11:11 lr: 0.000896 loss: 3.5773 (3.6078) grad_norm: 1.0651 (1.0643) time: 0.5242 [2021-03-25 14:41:25 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 80/1251] eta: 0:10:56 lr: 0.000896 loss: 3.4143 (3.5733) grad_norm: 1.0584 (1.0645) time: 0.5108 [2021-03-25 14:41:31 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 90/1251] eta: 0:10:43 lr: 0.000896 loss: 3.6889 (3.6089) grad_norm: 1.0447 (1.0591) time: 0.5028 [2021-03-25 14:41:36 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 100/1251] eta: 0:10:31 lr: 0.000896 loss: 3.8432 (3.6216) grad_norm: 1.0076 (1.0570) time: 0.5022 [2021-03-25 14:41:41 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 110/1251] eta: 0:10:22 lr: 0.000896 loss: 3.8721 (3.6443) grad_norm: 1.0302 (1.0557) time: 0.5080 [2021-03-25 14:41:46 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 120/1251] eta: 0:10:12 lr: 0.000896 loss: 3.7188 (3.6272) grad_norm: 0.9985 (1.0473) time: 0.5039 [2021-03-25 14:41:51 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 130/1251] eta: 0:10:04 lr: 0.000896 loss: 3.4853 (3.6254) grad_norm: 0.9985 (1.0476) time: 0.5019 [2021-03-25 14:41:56 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 140/1251] eta: 0:09:56 lr: 0.000896 loss: 3.7650 (3.6443) grad_norm: 1.0264 (1.0499) time: 0.5073 [2021-03-25 14:42:01 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 150/1251] eta: 0:09:48 lr: 0.000896 loss: 3.5997 (3.6314) grad_norm: 1.0221 (1.0479) time: 0.5039 [2021-03-25 14:42:06 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 160/1251] eta: 0:09:40 lr: 0.000896 loss: 3.3718 (3.6115) grad_norm: 1.0148 (1.0470) time: 0.5014 [2021-03-25 14:42:11 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 170/1251] eta: 0:09:33 lr: 0.000896 loss: 3.3718 (3.6107) grad_norm: 1.0092 (1.0452) time: 0.5030 [2021-03-25 14:42:16 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 180/1251] eta: 0:09:27 lr: 0.000896 loss: 3.7760 (3.6154) grad_norm: 1.0756 (1.0526) time: 0.5100 [2021-03-25 14:42:21 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 190/1251] eta: 0:09:20 lr: 0.000896 loss: 3.7760 (3.6165) grad_norm: 1.0465 (1.0506) time: 0.5084 [2021-03-25 14:42:26 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 200/1251] eta: 0:09:14 lr: 0.000896 loss: 3.5421 (3.6127) grad_norm: 1.0177 (1.0493) time: 0.5064 [2021-03-25 14:42:31 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 210/1251] eta: 0:09:08 lr: 0.000896 loss: 3.5421 (3.6058) grad_norm: 0.9766 (1.0452) time: 0.5131 [2021-03-25 14:42:36 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 220/1251] eta: 0:09:02 lr: 0.000896 loss: 3.6335 (3.6082) grad_norm: 0.9385 (1.0422) time: 0.5095 [2021-03-25 14:42:41 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 230/1251] eta: 0:08:55 lr: 0.000896 loss: 3.8823 (3.6157) grad_norm: 0.9817 (1.0418) time: 0.5013 [2021-03-25 14:42:46 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 240/1251] eta: 0:08:49 lr: 0.000896 loss: 3.7960 (3.6146) grad_norm: 1.0177 (1.0409) time: 0.5051 [2021-03-25 14:42:52 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 250/1251] eta: 0:08:44 lr: 0.000895 loss: 3.7960 (3.6203) grad_norm: 1.0175 (1.0395) time: 0.5182 [2021-03-25 14:42:57 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 260/1251] eta: 0:08:38 lr: 0.000895 loss: 3.8278 (3.6207) grad_norm: 1.0195 (1.0405) time: 0.5131 [2021-03-25 14:43:02 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 270/1251] eta: 0:08:32 lr: 0.000895 loss: 3.7334 (3.6194) grad_norm: 1.0570 (1.0414) time: 0.5045 [2021-03-25 14:43:07 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 280/1251] eta: 0:08:26 lr: 0.000895 loss: 3.5263 (3.6145) grad_norm: 1.0350 (1.0417) time: 0.5065 [2021-03-25 14:43:12 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 290/1251] eta: 0:08:21 lr: 0.000895 loss: 3.4792 (3.6112) grad_norm: 1.0113 (1.0421) time: 0.5050 [2021-03-25 14:43:17 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 300/1251] eta: 0:08:15 lr: 0.000895 loss: 3.7087 (3.6144) grad_norm: 1.0010 (1.0403) time: 0.5111 [2021-03-25 14:43:22 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 310/1251] eta: 0:08:10 lr: 0.000895 loss: 3.7954 (3.6127) grad_norm: 1.0032 (1.0400) time: 0.5126 [2021-03-25 14:43:27 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 320/1251] eta: 0:08:04 lr: 0.000895 loss: 3.6488 (3.6131) grad_norm: 1.0297 (1.0392) time: 0.5065 [2021-03-25 14:43:32 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 330/1251] eta: 0:07:58 lr: 0.000895 loss: 3.6488 (3.6095) grad_norm: 1.0297 (1.0382) time: 0.5020 [2021-03-25 14:43:37 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 340/1251] eta: 0:07:53 lr: 0.000895 loss: 3.7763 (3.6142) grad_norm: 1.0027 (1.0372) time: 0.5034 [2021-03-25 14:43:42 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 350/1251] eta: 0:07:47 lr: 0.000895 loss: 3.8261 (3.6197) grad_norm: 1.0027 (1.0366) time: 0.5065 [2021-03-25 14:43:47 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 360/1251] eta: 0:07:41 lr: 0.000895 loss: 3.8630 (3.6269) grad_norm: 0.9810 (1.0351) time: 0.5016 [2021-03-25 14:43:52 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 370/1251] eta: 0:07:36 lr: 0.000895 loss: 3.7347 (3.6252) grad_norm: 0.9761 (1.0341) time: 0.4958 [2021-03-25 14:43:57 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 380/1251] eta: 0:07:30 lr: 0.000895 loss: 3.5585 (3.6289) grad_norm: 0.9761 (1.0338) time: 0.5011 [2021-03-25 14:44:02 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 390/1251] eta: 0:07:25 lr: 0.000895 loss: 3.8918 (3.6323) grad_norm: 1.0430 (1.0353) time: 0.5034 [2021-03-25 14:44:07 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 400/1251] eta: 0:07:19 lr: 0.000895 loss: 3.8536 (3.6319) grad_norm: 1.0605 (1.0360) time: 0.4998 [2021-03-25 14:44:12 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 410/1251] eta: 0:07:14 lr: 0.000895 loss: 3.8172 (3.6373) grad_norm: 1.0389 (1.0369) time: 0.5015 [2021-03-25 14:44:17 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 420/1251] eta: 0:07:08 lr: 0.000895 loss: 3.8135 (3.6427) grad_norm: 0.9974 (1.0362) time: 0.5009 [2021-03-25 14:44:22 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 430/1251] eta: 0:07:03 lr: 0.000895 loss: 3.8566 (3.6494) grad_norm: 0.9879 (1.0349) time: 0.4980 [2021-03-25 14:44:27 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 440/1251] eta: 0:06:57 lr: 0.000895 loss: 4.0965 (3.6584) grad_norm: 0.9503 (1.0336) time: 0.4989 [2021-03-25 14:44:32 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 450/1251] eta: 0:06:52 lr: 0.000895 loss: 3.8650 (3.6556) grad_norm: 0.9744 (1.0347) time: 0.5067 [2021-03-25 14:44:37 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 460/1251] eta: 0:06:47 lr: 0.000895 loss: 3.6978 (3.6544) grad_norm: 1.0365 (1.0348) time: 0.5066 [2021-03-25 14:44:42 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 470/1251] eta: 0:06:41 lr: 0.000895 loss: 3.5131 (3.6519) grad_norm: 0.9876 (1.0333) time: 0.5007 [2021-03-25 14:44:47 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 480/1251] eta: 0:06:36 lr: 0.000895 loss: 3.4702 (3.6503) grad_norm: 1.0030 (1.0332) time: 0.4984 [2021-03-25 14:44:53 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 490/1251] eta: 0:06:31 lr: 0.000895 loss: 3.6304 (3.6503) grad_norm: 1.0778 (1.0363) time: 0.5064 [2021-03-25 14:44:58 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 500/1251] eta: 0:06:26 lr: 0.000895 loss: 3.7956 (3.6551) grad_norm: 1.1253 (1.0370) time: 0.5134 [2021-03-25 14:45:03 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 510/1251] eta: 0:06:20 lr: 0.000895 loss: 3.7956 (3.6545) grad_norm: 1.0209 (1.0368) time: 0.5092 [2021-03-25 14:45:08 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 520/1251] eta: 0:06:15 lr: 0.000895 loss: 3.5784 (3.6557) grad_norm: 0.9853 (1.0363) time: 0.5075 [2021-03-25 14:45:13 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 530/1251] eta: 0:06:10 lr: 0.000895 loss: 3.5960 (3.6565) grad_norm: 1.0312 (1.0364) time: 0.5076 [2021-03-25 14:45:18 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 540/1251] eta: 0:06:05 lr: 0.000895 loss: 3.7493 (3.6579) grad_norm: 1.0312 (1.0371) time: 0.5028 [2021-03-25 14:45:23 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 550/1251] eta: 0:06:00 lr: 0.000895 loss: 3.9004 (3.6637) grad_norm: 1.0368 (1.0373) time: 0.5110 [2021-03-25 14:45:28 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 560/1251] eta: 0:05:54 lr: 0.000895 loss: 3.9004 (3.6653) grad_norm: 1.0584 (1.0382) time: 0.5195 [2021-03-25 14:45:33 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 570/1251] eta: 0:05:49 lr: 0.000895 loss: 3.6010 (3.6605) grad_norm: 1.0149 (1.0374) time: 0.5083 [2021-03-25 14:45:38 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 580/1251] eta: 0:05:44 lr: 0.000895 loss: 3.5627 (3.6617) grad_norm: 0.9711 (1.0371) time: 0.5077 [2021-03-25 14:45:43 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 590/1251] eta: 0:05:39 lr: 0.000895 loss: 3.4463 (3.6558) grad_norm: 0.9934 (1.0366) time: 0.5087 [2021-03-25 14:45:49 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 600/1251] eta: 0:05:34 lr: 0.000895 loss: 3.4131 (3.6527) grad_norm: 1.0263 (1.0383) time: 0.5062 [2021-03-25 14:45:54 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 610/1251] eta: 0:05:28 lr: 0.000895 loss: 3.6595 (3.6545) grad_norm: 1.0690 (1.0379) time: 0.5025 [2021-03-25 14:45:59 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 620/1251] eta: 0:05:23 lr: 0.000895 loss: 3.9982 (3.6601) grad_norm: 1.0484 (1.0387) time: 0.5055 [2021-03-25 14:46:04 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 630/1251] eta: 0:05:18 lr: 0.000895 loss: 3.8398 (3.6589) grad_norm: 0.9993 (1.0379) time: 0.5066 [2021-03-25 14:46:09 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 640/1251] eta: 0:05:13 lr: 0.000894 loss: 3.7933 (3.6624) grad_norm: 0.9825 (1.0387) time: 0.5028 [2021-03-25 14:46:14 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 650/1251] eta: 0:05:08 lr: 0.000894 loss: 3.8317 (3.6646) grad_norm: 0.9825 (1.0374) time: 0.5068 [2021-03-25 14:46:19 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 660/1251] eta: 0:05:02 lr: 0.000894 loss: 3.7209 (3.6597) grad_norm: 0.9815 (1.0377) time: 0.5050 [2021-03-25 14:46:24 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 670/1251] eta: 0:04:57 lr: 0.000894 loss: 3.7162 (3.6625) grad_norm: 1.0566 (1.0378) time: 0.5046 [2021-03-25 14:46:29 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 680/1251] eta: 0:04:52 lr: 0.000894 loss: 3.7744 (3.6618) grad_norm: 1.0505 (1.0392) time: 0.5049 [2021-03-25 14:46:34 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 690/1251] eta: 0:04:47 lr: 0.000894 loss: 3.6172 (3.6570) grad_norm: 1.0489 (1.0392) time: 0.5059 [2021-03-25 14:46:39 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 700/1251] eta: 0:04:42 lr: 0.000894 loss: 3.6844 (3.6616) grad_norm: 1.0124 (1.0393) time: 0.5025 [2021-03-25 14:46:44 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 710/1251] eta: 0:04:36 lr: 0.000894 loss: 3.8559 (3.6622) grad_norm: 1.0432 (1.0393) time: 0.5006 [2021-03-25 14:46:49 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 720/1251] eta: 0:04:31 lr: 0.000894 loss: 3.4300 (3.6585) grad_norm: 0.9946 (1.0381) time: 0.5054 [2021-03-25 14:46:54 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 730/1251] eta: 0:04:26 lr: 0.000894 loss: 3.4127 (3.6551) grad_norm: 0.9915 (1.0382) time: 0.5050 [2021-03-25 14:46:59 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 740/1251] eta: 0:04:21 lr: 0.000894 loss: 3.4127 (3.6519) grad_norm: 1.0432 (1.0387) time: 0.5118 [2021-03-25 14:47:05 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 750/1251] eta: 0:04:16 lr: 0.000894 loss: 3.6055 (3.6537) grad_norm: 1.0457 (1.0383) time: 0.5230 [2021-03-25 14:47:10 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 760/1251] eta: 0:04:11 lr: 0.000894 loss: 3.7643 (3.6543) grad_norm: 1.0215 (1.0379) time: 0.5129 [2021-03-25 14:47:15 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 770/1251] eta: 0:04:06 lr: 0.000894 loss: 3.9303 (3.6554) grad_norm: 0.9960 (1.0382) time: 0.5099 [2021-03-25 14:47:20 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 780/1251] eta: 0:04:01 lr: 0.000894 loss: 3.6195 (3.6499) grad_norm: 0.9703 (1.0383) time: 0.5155 [2021-03-25 14:47:25 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 790/1251] eta: 0:03:55 lr: 0.000894 loss: 3.4291 (3.6498) grad_norm: 0.9676 (1.0377) time: 0.5112 [2021-03-25 14:47:30 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 800/1251] eta: 0:03:50 lr: 0.000894 loss: 3.5464 (3.6470) grad_norm: 1.0091 (1.0377) time: 0.5077 [2021-03-25 14:47:35 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 810/1251] eta: 0:03:45 lr: 0.000894 loss: 3.6667 (3.6476) grad_norm: 1.0082 (1.0373) time: 0.5115 [2021-03-25 14:47:40 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 820/1251] eta: 0:03:40 lr: 0.000894 loss: 3.6216 (3.6483) grad_norm: 1.0379 (1.0382) time: 0.5115 [2021-03-25 14:47:45 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 830/1251] eta: 0:03:35 lr: 0.000894 loss: 3.5337 (3.6463) grad_norm: 1.0951 (1.0385) time: 0.5011 [2021-03-25 14:47:50 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 840/1251] eta: 0:03:30 lr: 0.000894 loss: 3.7273 (3.6483) grad_norm: 1.0385 (1.0386) time: 0.5023 [2021-03-25 14:47:55 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 850/1251] eta: 0:03:25 lr: 0.000894 loss: 3.6425 (3.6457) grad_norm: 1.0058 (1.0386) time: 0.5088 [2021-03-25 14:48:01 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 860/1251] eta: 0:03:19 lr: 0.000894 loss: 3.5633 (3.6432) grad_norm: 1.0378 (1.0390) time: 0.5063 [2021-03-25 14:48:06 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 870/1251] eta: 0:03:14 lr: 0.000894 loss: 3.6972 (3.6438) grad_norm: 1.0542 (1.0393) time: 0.5054 [2021-03-25 14:48:11 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 880/1251] eta: 0:03:09 lr: 0.000894 loss: 3.7021 (3.6434) grad_norm: 1.1171 (1.0399) time: 0.5041 [2021-03-25 14:48:16 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 890/1251] eta: 0:03:04 lr: 0.000894 loss: 3.4165 (3.6403) grad_norm: 1.1339 (1.0409) time: 0.5029 [2021-03-25 14:48:21 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 900/1251] eta: 0:02:59 lr: 0.000894 loss: 3.4467 (3.6425) grad_norm: 1.0447 (1.0406) time: 0.5047 [2021-03-25 14:48:26 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 910/1251] eta: 0:02:54 lr: 0.000894 loss: 3.9302 (3.6426) grad_norm: 0.9714 (1.0399) time: 0.5085 [2021-03-25 14:48:31 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 920/1251] eta: 0:02:49 lr: 0.000894 loss: 3.4232 (3.6404) grad_norm: 0.9614 (1.0400) time: 0.5098 [2021-03-25 14:48:36 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 930/1251] eta: 0:02:44 lr: 0.000894 loss: 3.7124 (3.6437) grad_norm: 0.9990 (1.0399) time: 0.5067 [2021-03-25 14:48:41 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 940/1251] eta: 0:02:38 lr: 0.000894 loss: 3.8877 (3.6448) grad_norm: 1.0541 (1.0400) time: 0.5075 [2021-03-25 14:48:46 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 950/1251] eta: 0:02:33 lr: 0.000894 loss: 3.6583 (3.6445) grad_norm: 1.0477 (1.0404) time: 0.5100 [2021-03-25 14:48:51 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 960/1251] eta: 0:02:28 lr: 0.000894 loss: 3.6172 (3.6419) grad_norm: 1.0306 (1.0408) time: 0.5088 [2021-03-25 14:48:56 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 970/1251] eta: 0:02:23 lr: 0.000894 loss: 3.7086 (3.6434) grad_norm: 1.0513 (1.0411) time: 0.5057 [2021-03-25 14:49:01 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 980/1251] eta: 0:02:18 lr: 0.000894 loss: 3.7086 (3.6417) grad_norm: 1.0649 (1.0415) time: 0.5111 [2021-03-25 14:49:07 swin_small_patch4_window7_224] INFO: Epoch: [63] [ 990/1251] eta: 0:02:13 lr: 0.000894 loss: 3.4975 (3.6430) grad_norm: 1.0200 (1.0413) time: 0.5136 [2021-03-25 14:49:12 swin_small_patch4_window7_224] INFO: Epoch: [63] [1000/1251] eta: 0:02:08 lr: 0.000894 loss: 3.9988 (3.6484) grad_norm: 0.9906 (1.0409) time: 0.5083 [2021-03-25 14:49:17 swin_small_patch4_window7_224] INFO: Epoch: [63] [1010/1251] eta: 0:02:03 lr: 0.000894 loss: 3.8991 (3.6453) grad_norm: 1.0080 (1.0409) time: 0.5022 [2021-03-25 14:49:22 swin_small_patch4_window7_224] INFO: Epoch: [63] [1020/1251] eta: 0:01:57 lr: 0.000894 loss: 3.5458 (3.6458) grad_norm: 1.0309 (1.0414) time: 0.4996 [2021-03-25 14:49:27 swin_small_patch4_window7_224] INFO: Epoch: [63] [1030/1251] eta: 0:01:52 lr: 0.000893 loss: 3.6987 (3.6453) grad_norm: 1.0402 (1.0415) time: 0.5037 [2021-03-25 14:49:32 swin_small_patch4_window7_224] INFO: Epoch: [63] [1040/1251] eta: 0:01:47 lr: 0.000893 loss: 3.7134 (3.6467) grad_norm: 1.0099 (1.0408) time: 0.5088 [2021-03-25 14:49:37 swin_small_patch4_window7_224] INFO: Epoch: [63] [1050/1251] eta: 0:01:42 lr: 0.000893 loss: 3.7549 (3.6454) grad_norm: 0.9622 (1.0404) time: 0.5093 [2021-03-25 14:49:42 swin_small_patch4_window7_224] INFO: Epoch: [63] [1060/1251] eta: 0:01:37 lr: 0.000893 loss: 3.6694 (3.6447) grad_norm: 0.9856 (1.0402) time: 0.5035 [2021-03-25 14:49:47 swin_small_patch4_window7_224] INFO: Epoch: [63] [1070/1251] eta: 0:01:32 lr: 0.000893 loss: 3.5896 (3.6432) grad_norm: 1.0174 (1.0406) time: 0.5005 [2021-03-25 14:49:52 swin_small_patch4_window7_224] INFO: Epoch: [63] [1080/1251] eta: 0:01:27 lr: 0.000893 loss: 3.5231 (3.6435) grad_norm: 1.0157 (1.0405) time: 0.5039 [2021-03-25 14:49:57 swin_small_patch4_window7_224] INFO: Epoch: [63] [1090/1251] eta: 0:01:22 lr: 0.000893 loss: 3.6258 (3.6448) grad_norm: 1.0703 (1.0411) time: 0.5032 [2021-03-25 14:50:02 swin_small_patch4_window7_224] INFO: Epoch: [63] [1100/1251] eta: 0:01:17 lr: 0.000893 loss: 3.5340 (3.6423) grad_norm: 1.0815 (1.0420) time: 0.5022 [2021-03-25 14:50:07 swin_small_patch4_window7_224] INFO: Epoch: [63] [1110/1251] eta: 0:01:11 lr: 0.000893 loss: 3.5072 (3.6423) grad_norm: 1.0687 (1.0418) time: 0.4998 [2021-03-25 14:50:12 swin_small_patch4_window7_224] INFO: Epoch: [63] [1120/1251] eta: 0:01:06 lr: 0.000893 loss: 3.6994 (3.6423) grad_norm: 0.9918 (1.0412) time: 0.5015 [2021-03-25 14:50:17 swin_small_patch4_window7_224] INFO: Epoch: [63] [1130/1251] eta: 0:01:01 lr: 0.000893 loss: 3.5788 (3.6424) grad_norm: 0.9862 (1.0414) time: 0.5068 [2021-03-25 14:50:22 swin_small_patch4_window7_224] INFO: Epoch: [63] [1140/1251] eta: 0:00:56 lr: 0.000893 loss: 3.8241 (3.6440) grad_norm: 1.0098 (1.0414) time: 0.5082 [2021-03-25 14:50:27 swin_small_patch4_window7_224] INFO: Epoch: [63] [1150/1251] eta: 0:00:51 lr: 0.000893 loss: 3.8241 (3.6440) grad_norm: 1.0173 (1.0414) time: 0.5054 [2021-03-25 14:50:32 swin_small_patch4_window7_224] INFO: Epoch: [63] [1160/1251] eta: 0:00:46 lr: 0.000893 loss: 3.8271 (3.6457) grad_norm: 0.9686 (1.0410) time: 0.5016 [2021-03-25 14:50:37 swin_small_patch4_window7_224] INFO: Epoch: [63] [1170/1251] eta: 0:00:41 lr: 0.000893 loss: 3.8141 (3.6462) grad_norm: 0.9710 (1.0410) time: 0.5052 [2021-03-25 14:50:42 swin_small_patch4_window7_224] INFO: Epoch: [63] [1180/1251] eta: 0:00:36 lr: 0.000893 loss: 3.7926 (3.6461) grad_norm: 1.0031 (1.0413) time: 0.5076 [2021-03-25 14:50:47 swin_small_patch4_window7_224] INFO: Epoch: [63] [1190/1251] eta: 0:00:31 lr: 0.000893 loss: 3.9393 (3.6478) grad_norm: 1.0270 (1.0413) time: 0.5073 [2021-03-25 14:50:53 swin_small_patch4_window7_224] INFO: Epoch: [63] [1200/1251] eta: 0:00:25 lr: 0.000893 loss: 3.7990 (3.6465) grad_norm: 1.0776 (1.0421) time: 0.5066 [2021-03-25 14:50:58 swin_small_patch4_window7_224] INFO: Epoch: [63] [1210/1251] eta: 0:00:20 lr: 0.000893 loss: 3.6936 (3.6478) grad_norm: 1.0776 (1.0421) time: 0.5048 [2021-03-25 14:51:03 swin_small_patch4_window7_224] INFO: Epoch: [63] [1220/1251] eta: 0:00:15 lr: 0.000893 loss: 3.6376 (3.6448) grad_norm: 1.0471 (1.0422) time: 0.5007 [2021-03-25 14:51:08 swin_small_patch4_window7_224] INFO: Epoch: [63] [1230/1251] eta: 0:00:10 lr: 0.000893 loss: 3.4167 (3.6440) grad_norm: 0.9863 (1.0417) time: 0.5024 [2021-03-25 14:51:13 swin_small_patch4_window7_224] INFO: Epoch: [63] [1240/1251] eta: 0:00:05 lr: 0.000893 loss: 3.6732 (3.6438) grad_norm: 0.9822 (1.0416) time: 0.5086 [2021-03-25 14:51:18 swin_small_patch4_window7_224] INFO: Epoch: [63] [1250/1251] eta: 0:00:00 lr: 0.000893 loss: 3.6177 (3.6419) grad_norm: 1.0117 (1.0416) time: 0.5057 [2021-03-25 14:51:22 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:13 loss: 1.0913 (1.0913) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-25 14:51:24 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 1.0933 (1.1275) acc1: 75.0000 (74.2898) acc5: 92.1875 (92.7557) [2021-03-25 14:51:27 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0933 (1.1335) acc1: 75.0000 (74.1071) acc5: 92.1875 (91.9643) [2021-03-25 14:51:29 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0954 (1.1196) acc1: 73.4375 (73.8911) acc5: 92.1875 (92.3891) [2021-03-25 14:51:31 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0993 (1.1302) acc1: 73.4375 (73.0183) acc5: 93.7500 (92.3399) [2021-03-25 14:51:32 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1555 (1.1464) acc1: 73.4375 (73.0240) acc5: 92.1875 (91.9680) [2021-03-25 14:51:35 swin_small_patch4_window7_224] INFO: * Acc@1 73.634 Acc@5 92.086 loss 1.128 [2021-03-25 14:51:35 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.6% [2021-03-25 14:51:35 swin_small_patch4_window7_224] INFO: Max accuracy: 73.93% [2021-03-25 14:51:39 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 0/1251] eta: 1:24:08 lr: 0.000893 loss: 3.7890 (3.7890) grad_norm: 0.9338 (0.9338) time: 4.0359 [2021-03-25 14:51:45 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 10/1251] eta: 0:17:40 lr: 0.000893 loss: 4.0612 (4.0279) grad_norm: 1.0015 (1.0374) time: 0.8548 [2021-03-25 14:51:50 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 20/1251] eta: 0:14:11 lr: 0.000893 loss: 3.7409 (3.7930) grad_norm: 1.0015 (1.0123) time: 0.5249 [2021-03-25 14:51:55 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 30/1251] eta: 0:12:49 lr: 0.000893 loss: 3.7409 (3.7531) grad_norm: 0.9814 (1.0100) time: 0.5073 [2021-03-25 14:52:00 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 40/1251] eta: 0:12:06 lr: 0.000893 loss: 3.4977 (3.6507) grad_norm: 0.9826 (1.0259) time: 0.5039 [2021-03-25 14:52:05 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 50/1251] eta: 0:11:39 lr: 0.000893 loss: 3.5751 (3.6990) grad_norm: 1.0436 (1.0340) time: 0.5075 [2021-03-25 14:52:10 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 60/1251] eta: 0:11:22 lr: 0.000893 loss: 3.7261 (3.7104) grad_norm: 1.0587 (1.0356) time: 0.5176 [2021-03-25 14:52:15 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 70/1251] eta: 0:11:07 lr: 0.000893 loss: 3.6446 (3.7035) grad_norm: 0.9875 (1.0326) time: 0.5208 [2021-03-25 14:52:20 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 80/1251] eta: 0:10:53 lr: 0.000893 loss: 3.6371 (3.6918) grad_norm: 1.0190 (1.0354) time: 0.5119 [2021-03-25 14:52:25 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 90/1251] eta: 0:10:40 lr: 0.000893 loss: 3.5804 (3.6636) grad_norm: 1.0207 (1.0382) time: 0.5052 [2021-03-25 14:52:30 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 100/1251] eta: 0:10:29 lr: 0.000893 loss: 3.7209 (3.6729) grad_norm: 1.0273 (1.0398) time: 0.5032 [2021-03-25 14:52:36 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 110/1251] eta: 0:10:20 lr: 0.000893 loss: 3.4458 (3.6425) grad_norm: 1.0408 (1.0419) time: 0.5075 [2021-03-25 14:52:41 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 120/1251] eta: 0:10:12 lr: 0.000893 loss: 3.4313 (3.6362) grad_norm: 1.0372 (1.0384) time: 0.5115 [2021-03-25 14:52:46 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 130/1251] eta: 0:10:05 lr: 0.000893 loss: 3.6934 (3.6280) grad_norm: 1.0372 (1.0430) time: 0.5172 [2021-03-25 14:52:51 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 140/1251] eta: 0:09:57 lr: 0.000893 loss: 3.7912 (3.6375) grad_norm: 1.0735 (1.0453) time: 0.5137 [2021-03-25 14:52:56 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 150/1251] eta: 0:09:50 lr: 0.000893 loss: 3.8622 (3.6454) grad_norm: 1.0044 (1.0417) time: 0.5133 [2021-03-25 14:53:01 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 160/1251] eta: 0:09:42 lr: 0.000893 loss: 4.0057 (3.6513) grad_norm: 1.0044 (1.0396) time: 0.5104 [2021-03-25 14:53:06 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 170/1251] eta: 0:09:35 lr: 0.000892 loss: 3.8421 (3.6549) grad_norm: 1.0369 (1.0373) time: 0.5020 [2021-03-25 14:53:11 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 180/1251] eta: 0:09:29 lr: 0.000892 loss: 3.7940 (3.6530) grad_norm: 1.0061 (1.0380) time: 0.5106 [2021-03-25 14:53:16 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 190/1251] eta: 0:09:22 lr: 0.000892 loss: 3.8309 (3.6597) grad_norm: 1.0301 (1.0398) time: 0.5107 [2021-03-25 14:53:22 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 200/1251] eta: 0:09:16 lr: 0.000892 loss: 3.8262 (3.6696) grad_norm: 1.0440 (1.0395) time: 0.5107 [2021-03-25 14:53:27 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 210/1251] eta: 0:09:10 lr: 0.000892 loss: 3.8104 (3.6717) grad_norm: 1.0205 (1.0396) time: 0.5127 [2021-03-25 14:53:32 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 220/1251] eta: 0:09:03 lr: 0.000892 loss: 3.8104 (3.6739) grad_norm: 1.0205 (1.0403) time: 0.5096 [2021-03-25 14:53:37 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 230/1251] eta: 0:08:57 lr: 0.000892 loss: 3.7791 (3.6704) grad_norm: 1.0385 (1.0426) time: 0.5099 [2021-03-25 14:53:42 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 240/1251] eta: 0:08:51 lr: 0.000892 loss: 3.8988 (3.6823) grad_norm: 1.0715 (1.0435) time: 0.5042 [2021-03-25 14:53:47 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 250/1251] eta: 0:08:45 lr: 0.000892 loss: 3.6573 (3.6732) grad_norm: 1.0715 (1.0444) time: 0.5024 [2021-03-25 14:53:52 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 260/1251] eta: 0:08:39 lr: 0.000892 loss: 3.5115 (3.6748) grad_norm: 1.0165 (1.0426) time: 0.5028 [2021-03-25 14:53:57 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 270/1251] eta: 0:08:33 lr: 0.000892 loss: 3.8511 (3.6864) grad_norm: 0.9781 (1.0413) time: 0.5032 [2021-03-25 14:54:02 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 280/1251] eta: 0:08:27 lr: 0.000892 loss: 3.9199 (3.6872) grad_norm: 1.0054 (1.0438) time: 0.5065 [2021-03-25 14:54:07 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 290/1251] eta: 0:08:21 lr: 0.000892 loss: 3.6065 (3.6794) grad_norm: 1.0609 (1.0451) time: 0.5081 [2021-03-25 14:54:12 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 300/1251] eta: 0:08:15 lr: 0.000892 loss: 3.6065 (3.6724) grad_norm: 1.0831 (1.0492) time: 0.5054 [2021-03-25 14:54:17 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 310/1251] eta: 0:08:10 lr: 0.000892 loss: 3.6081 (3.6680) grad_norm: 1.0442 (1.0502) time: 0.5078 [2021-03-25 14:54:22 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 320/1251] eta: 0:08:05 lr: 0.000892 loss: 3.4748 (3.6675) grad_norm: 1.0425 (1.0512) time: 0.5131 [2021-03-25 14:54:28 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 330/1251] eta: 0:07:59 lr: 0.000892 loss: 3.8364 (3.6751) grad_norm: 1.0528 (1.0510) time: 0.5087 [2021-03-25 14:54:33 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 340/1251] eta: 0:07:53 lr: 0.000892 loss: 3.8127 (3.6706) grad_norm: 1.0595 (1.0516) time: 0.5042 [2021-03-25 14:54:38 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 350/1251] eta: 0:07:48 lr: 0.000892 loss: 3.7412 (3.6726) grad_norm: 1.0048 (1.0506) time: 0.5037 [2021-03-25 14:54:43 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 360/1251] eta: 0:07:42 lr: 0.000892 loss: 3.7412 (3.6700) grad_norm: 0.9989 (1.0506) time: 0.5051 [2021-03-25 14:54:48 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 370/1251] eta: 0:07:36 lr: 0.000892 loss: 3.5391 (3.6711) grad_norm: 1.0461 (1.0512) time: 0.5018 [2021-03-25 14:54:53 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 380/1251] eta: 0:07:31 lr: 0.000892 loss: 3.6140 (3.6654) grad_norm: 1.0311 (1.0504) time: 0.5005 [2021-03-25 14:54:58 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 390/1251] eta: 0:07:25 lr: 0.000892 loss: 3.5914 (3.6625) grad_norm: 0.9775 (1.0503) time: 0.5049 [2021-03-25 14:55:03 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 400/1251] eta: 0:07:20 lr: 0.000892 loss: 3.6687 (3.6596) grad_norm: 1.0108 (1.0486) time: 0.5023 [2021-03-25 14:55:08 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 410/1251] eta: 0:07:14 lr: 0.000892 loss: 3.6687 (3.6604) grad_norm: 1.0275 (1.0498) time: 0.5006 [2021-03-25 14:55:13 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 420/1251] eta: 0:07:09 lr: 0.000892 loss: 3.6608 (3.6547) grad_norm: 1.0275 (1.0489) time: 0.5026 [2021-03-25 14:55:18 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 430/1251] eta: 0:07:03 lr: 0.000892 loss: 3.7482 (3.6545) grad_norm: 1.0180 (1.0489) time: 0.5012 [2021-03-25 14:55:23 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 440/1251] eta: 0:06:58 lr: 0.000892 loss: 3.6998 (3.6530) grad_norm: 1.0250 (1.0486) time: 0.5024 [2021-03-25 14:55:28 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 450/1251] eta: 0:06:53 lr: 0.000892 loss: 3.6998 (3.6542) grad_norm: 1.0126 (1.0476) time: 0.5075 [2021-03-25 14:55:33 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 460/1251] eta: 0:06:48 lr: 0.000892 loss: 3.8129 (3.6577) grad_norm: 0.9768 (1.0469) time: 0.5107 [2021-03-25 14:55:38 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 470/1251] eta: 0:06:42 lr: 0.000892 loss: 3.8129 (3.6600) grad_norm: 0.9838 (1.0458) time: 0.5086 [2021-03-25 14:55:43 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 480/1251] eta: 0:06:37 lr: 0.000892 loss: 3.6830 (3.6556) grad_norm: 0.9838 (1.0452) time: 0.5073 [2021-03-25 14:55:48 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 490/1251] eta: 0:06:32 lr: 0.000892 loss: 3.6065 (3.6544) grad_norm: 0.9946 (1.0448) time: 0.5039 [2021-03-25 14:55:53 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 500/1251] eta: 0:06:26 lr: 0.000892 loss: 3.8664 (3.6580) grad_norm: 1.0079 (1.0447) time: 0.4989 [2021-03-25 14:55:58 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 510/1251] eta: 0:06:21 lr: 0.000892 loss: 3.8664 (3.6573) grad_norm: 1.0098 (1.0443) time: 0.4998 [2021-03-25 14:56:03 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 520/1251] eta: 0:06:15 lr: 0.000892 loss: 3.8919 (3.6604) grad_norm: 1.0553 (1.0454) time: 0.5017 [2021-03-25 14:56:08 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 530/1251] eta: 0:06:10 lr: 0.000892 loss: 3.9356 (3.6605) grad_norm: 1.0114 (1.0443) time: 0.4996 [2021-03-25 14:56:13 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 540/1251] eta: 0:06:05 lr: 0.000892 loss: 3.7688 (3.6610) grad_norm: 0.9854 (1.0443) time: 0.5068 [2021-03-25 14:56:19 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 550/1251] eta: 0:06:00 lr: 0.000892 loss: 3.8077 (3.6631) grad_norm: 1.0396 (1.0451) time: 0.5227 [2021-03-25 14:56:24 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 560/1251] eta: 0:05:55 lr: 0.000891 loss: 3.8758 (3.6623) grad_norm: 1.0519 (1.0448) time: 0.5187 [2021-03-25 14:56:29 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 570/1251] eta: 0:05:49 lr: 0.000891 loss: 3.6345 (3.6570) grad_norm: 1.0028 (1.0448) time: 0.5036 [2021-03-25 14:56:34 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 580/1251] eta: 0:05:44 lr: 0.000891 loss: 3.6647 (3.6584) grad_norm: 0.9769 (1.0440) time: 0.5062 [2021-03-25 14:56:39 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 590/1251] eta: 0:05:39 lr: 0.000891 loss: 3.8179 (3.6598) grad_norm: 1.0026 (1.0449) time: 0.5100 [2021-03-25 14:56:44 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 600/1251] eta: 0:05:34 lr: 0.000891 loss: 3.8179 (3.6580) grad_norm: 1.1103 (1.0473) time: 0.5058 [2021-03-25 14:56:49 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 610/1251] eta: 0:05:29 lr: 0.000891 loss: 3.6761 (3.6574) grad_norm: 1.0176 (1.0462) time: 0.5111 [2021-03-25 14:56:54 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 620/1251] eta: 0:05:24 lr: 0.000891 loss: 3.7167 (3.6610) grad_norm: 0.9994 (1.0456) time: 0.5136 [2021-03-25 14:56:59 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 630/1251] eta: 0:05:18 lr: 0.000891 loss: 3.7167 (3.6614) grad_norm: 0.9994 (1.0445) time: 0.5105 [2021-03-25 14:57:04 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 640/1251] eta: 0:05:13 lr: 0.000891 loss: 3.4701 (3.6586) grad_norm: 1.0022 (1.0446) time: 0.5112 [2021-03-25 14:57:10 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 650/1251] eta: 0:05:08 lr: 0.000891 loss: 3.3794 (3.6541) grad_norm: 1.0063 (1.0443) time: 0.5149 [2021-03-25 14:57:15 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 660/1251] eta: 0:05:03 lr: 0.000891 loss: 3.5760 (3.6551) grad_norm: 1.0005 (1.0440) time: 0.5131 [2021-03-25 14:57:20 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 670/1251] eta: 0:04:58 lr: 0.000891 loss: 3.6101 (3.6566) grad_norm: 0.9962 (1.0442) time: 0.5008 [2021-03-25 14:57:25 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 680/1251] eta: 0:04:52 lr: 0.000891 loss: 3.6765 (3.6581) grad_norm: 0.9872 (1.0436) time: 0.4966 [2021-03-25 14:57:30 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 690/1251] eta: 0:04:47 lr: 0.000891 loss: 3.8151 (3.6609) grad_norm: 0.9775 (1.0434) time: 0.4988 [2021-03-25 14:57:35 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 700/1251] eta: 0:04:42 lr: 0.000891 loss: 3.7953 (3.6584) grad_norm: 1.0092 (1.0438) time: 0.5016 [2021-03-25 14:57:40 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 710/1251] eta: 0:04:37 lr: 0.000891 loss: 3.7312 (3.6568) grad_norm: 1.0669 (1.0442) time: 0.5099 [2021-03-25 14:57:45 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 720/1251] eta: 0:04:32 lr: 0.000891 loss: 3.7312 (3.6568) grad_norm: 1.0617 (1.0441) time: 0.5081 [2021-03-25 14:57:50 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 730/1251] eta: 0:04:26 lr: 0.000891 loss: 3.7079 (3.6549) grad_norm: 1.0331 (1.0441) time: 0.5021 [2021-03-25 14:57:55 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 740/1251] eta: 0:04:22 lr: 0.000891 loss: 3.7402 (3.6561) grad_norm: 1.0293 (1.0440) time: 0.5179 [2021-03-25 14:58:00 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 750/1251] eta: 0:04:16 lr: 0.000891 loss: 3.7855 (3.6587) grad_norm: 1.0293 (1.0438) time: 0.5239 [2021-03-25 14:58:05 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 760/1251] eta: 0:04:11 lr: 0.000891 loss: 3.8415 (3.6583) grad_norm: 1.0110 (1.0441) time: 0.5081 [2021-03-25 14:58:10 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 770/1251] eta: 0:04:06 lr: 0.000891 loss: 3.4686 (3.6583) grad_norm: 1.0110 (1.0442) time: 0.4983 [2021-03-25 14:58:15 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 780/1251] eta: 0:04:01 lr: 0.000891 loss: 3.5729 (3.6587) grad_norm: 1.0911 (1.0445) time: 0.4949 [2021-03-25 14:58:20 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 790/1251] eta: 0:03:56 lr: 0.000891 loss: 3.7872 (3.6607) grad_norm: 1.0911 (1.0451) time: 0.5030 [2021-03-25 14:58:26 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 800/1251] eta: 0:03:50 lr: 0.000891 loss: 3.8755 (3.6622) grad_norm: 1.0709 (1.0453) time: 0.5118 [2021-03-25 14:58:31 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 810/1251] eta: 0:03:45 lr: 0.000891 loss: 3.7514 (3.6602) grad_norm: 1.0530 (1.0454) time: 0.5145 [2021-03-25 14:58:36 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 820/1251] eta: 0:03:40 lr: 0.000891 loss: 3.6802 (3.6605) grad_norm: 1.0212 (1.0451) time: 0.5122 [2021-03-25 14:58:41 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 830/1251] eta: 0:03:35 lr: 0.000891 loss: 3.8440 (3.6636) grad_norm: 1.0543 (1.0458) time: 0.5054 [2021-03-25 14:58:46 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 840/1251] eta: 0:03:30 lr: 0.000891 loss: 3.8807 (3.6665) grad_norm: 1.0961 (1.0461) time: 0.5026 [2021-03-25 14:58:51 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 850/1251] eta: 0:03:25 lr: 0.000891 loss: 3.6821 (3.6649) grad_norm: 1.0486 (1.0457) time: 0.5039 [2021-03-25 14:58:56 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 860/1251] eta: 0:03:20 lr: 0.000891 loss: 3.7203 (3.6667) grad_norm: 0.9673 (1.0446) time: 0.5104 [2021-03-25 14:59:01 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 870/1251] eta: 0:03:14 lr: 0.000891 loss: 3.8311 (3.6687) grad_norm: 0.9570 (1.0439) time: 0.5095 [2021-03-25 14:59:06 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 880/1251] eta: 0:03:09 lr: 0.000891 loss: 3.8311 (3.6680) grad_norm: 0.9580 (1.0435) time: 0.5041 [2021-03-25 14:59:11 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 890/1251] eta: 0:03:04 lr: 0.000891 loss: 3.6484 (3.6682) grad_norm: 0.9986 (1.0433) time: 0.5030 [2021-03-25 14:59:16 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 900/1251] eta: 0:02:59 lr: 0.000891 loss: 3.6484 (3.6684) grad_norm: 1.0212 (1.0445) time: 0.5057 [2021-03-25 14:59:21 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 910/1251] eta: 0:02:54 lr: 0.000891 loss: 3.8091 (3.6706) grad_norm: 1.1350 (1.0450) time: 0.5086 [2021-03-25 14:59:26 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 920/1251] eta: 0:02:49 lr: 0.000891 loss: 3.9076 (3.6708) grad_norm: 1.0437 (1.0449) time: 0.5032 [2021-03-25 14:59:31 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 930/1251] eta: 0:02:44 lr: 0.000891 loss: 3.8905 (3.6731) grad_norm: 1.0204 (1.0451) time: 0.5073 [2021-03-25 14:59:37 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 940/1251] eta: 0:02:39 lr: 0.000890 loss: 3.8905 (3.6741) grad_norm: 1.0118 (1.0448) time: 0.5155 [2021-03-25 14:59:42 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 950/1251] eta: 0:02:33 lr: 0.000890 loss: 3.8586 (3.6755) grad_norm: 1.0440 (1.0452) time: 0.5095 [2021-03-25 14:59:47 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 960/1251] eta: 0:02:28 lr: 0.000890 loss: 3.6841 (3.6725) grad_norm: 1.0486 (1.0448) time: 0.5025 [2021-03-25 14:59:52 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 970/1251] eta: 0:02:23 lr: 0.000890 loss: 3.5702 (3.6713) grad_norm: 1.0138 (1.0449) time: 0.5030 [2021-03-25 14:59:57 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 980/1251] eta: 0:02:18 lr: 0.000890 loss: 3.7974 (3.6726) grad_norm: 1.0569 (1.0451) time: 0.5115 [2021-03-25 15:00:02 swin_small_patch4_window7_224] INFO: Epoch: [64] [ 990/1251] eta: 0:02:13 lr: 0.000890 loss: 3.6768 (3.6696) grad_norm: 1.0199 (1.0446) time: 0.5132 [2021-03-25 15:00:07 swin_small_patch4_window7_224] INFO: Epoch: [64] [1000/1251] eta: 0:02:08 lr: 0.000890 loss: 3.5688 (3.6689) grad_norm: 0.9807 (1.0443) time: 0.5028 [2021-03-25 15:00:12 swin_small_patch4_window7_224] INFO: Epoch: [64] [1010/1251] eta: 0:02:03 lr: 0.000890 loss: 3.8413 (3.6706) grad_norm: 1.0000 (1.0441) time: 0.4982 [2021-03-25 15:00:17 swin_small_patch4_window7_224] INFO: Epoch: [64] [1020/1251] eta: 0:01:58 lr: 0.000890 loss: 3.8413 (3.6698) grad_norm: 1.0261 (1.0442) time: 0.5004 [2021-03-25 15:00:22 swin_small_patch4_window7_224] INFO: Epoch: [64] [1030/1251] eta: 0:01:52 lr: 0.000890 loss: 3.6851 (3.6684) grad_norm: 0.9903 (1.0435) time: 0.5042 [2021-03-25 15:00:27 swin_small_patch4_window7_224] INFO: Epoch: [64] [1040/1251] eta: 0:01:47 lr: 0.000890 loss: 3.6851 (3.6673) grad_norm: 0.9773 (1.0433) time: 0.5091 [2021-03-25 15:00:32 swin_small_patch4_window7_224] INFO: Epoch: [64] [1050/1251] eta: 0:01:42 lr: 0.000890 loss: 3.6870 (3.6655) grad_norm: 1.0067 (1.0430) time: 0.5093 [2021-03-25 15:00:37 swin_small_patch4_window7_224] INFO: Epoch: [64] [1060/1251] eta: 0:01:37 lr: 0.000890 loss: 3.6712 (3.6653) grad_norm: 1.0413 (1.0432) time: 0.5108 [2021-03-25 15:00:42 swin_small_patch4_window7_224] INFO: Epoch: [64] [1070/1251] eta: 0:01:32 lr: 0.000890 loss: 3.7901 (3.6650) grad_norm: 1.0413 (1.0433) time: 0.5122 [2021-03-25 15:00:48 swin_small_patch4_window7_224] INFO: Epoch: [64] [1080/1251] eta: 0:01:27 lr: 0.000890 loss: 3.6312 (3.6627) grad_norm: 0.9912 (1.0432) time: 0.5057 [2021-03-25 15:00:53 swin_small_patch4_window7_224] INFO: Epoch: [64] [1090/1251] eta: 0:01:22 lr: 0.000890 loss: 3.6386 (3.6655) grad_norm: 0.9901 (1.0426) time: 0.5030 [2021-03-25 15:00:58 swin_small_patch4_window7_224] INFO: Epoch: [64] [1100/1251] eta: 0:01:17 lr: 0.000890 loss: 3.6386 (3.6634) grad_norm: 0.9572 (1.0420) time: 0.5075 [2021-03-25 15:01:03 swin_small_patch4_window7_224] INFO: Epoch: [64] [1110/1251] eta: 0:01:12 lr: 0.000890 loss: 3.6013 (3.6645) grad_norm: 0.9716 (1.0421) time: 0.5086 [2021-03-25 15:01:08 swin_small_patch4_window7_224] INFO: Epoch: [64] [1120/1251] eta: 0:01:06 lr: 0.000890 loss: 3.7892 (3.6651) grad_norm: 1.0117 (1.0423) time: 0.5105 [2021-03-25 15:01:13 swin_small_patch4_window7_224] INFO: Epoch: [64] [1130/1251] eta: 0:01:01 lr: 0.000890 loss: 3.6025 (3.6636) grad_norm: 1.0117 (1.0423) time: 0.5095 [2021-03-25 15:01:18 swin_small_patch4_window7_224] INFO: Epoch: [64] [1140/1251] eta: 0:00:56 lr: 0.000890 loss: 3.5472 (3.6625) grad_norm: 0.9901 (1.0419) time: 0.5043 [2021-03-25 15:01:23 swin_small_patch4_window7_224] INFO: Epoch: [64] [1150/1251] eta: 0:00:51 lr: 0.000890 loss: 3.6524 (3.6631) grad_norm: 0.9872 (1.0417) time: 0.5084 [2021-03-25 15:01:28 swin_small_patch4_window7_224] INFO: Epoch: [64] [1160/1251] eta: 0:00:46 lr: 0.000890 loss: 3.6075 (3.6598) grad_norm: 1.0366 (1.0426) time: 0.5106 [2021-03-25 15:01:33 swin_small_patch4_window7_224] INFO: Epoch: [64] [1170/1251] eta: 0:00:41 lr: 0.000890 loss: 3.6075 (3.6604) grad_norm: 1.0747 (1.0432) time: 0.5044 [2021-03-25 15:01:38 swin_small_patch4_window7_224] INFO: Epoch: [64] [1180/1251] eta: 0:00:36 lr: 0.000890 loss: 3.7080 (3.6594) grad_norm: 1.0757 (1.0434) time: 0.5052 [2021-03-25 15:01:43 swin_small_patch4_window7_224] INFO: Epoch: [64] [1190/1251] eta: 0:00:31 lr: 0.000890 loss: 3.6029 (3.6583) grad_norm: 1.0103 (1.0432) time: 0.5046 [2021-03-25 15:01:48 swin_small_patch4_window7_224] INFO: Epoch: [64] [1200/1251] eta: 0:00:26 lr: 0.000890 loss: 3.7263 (3.6588) grad_norm: 1.0754 (1.0443) time: 0.5044 [2021-03-25 15:01:53 swin_small_patch4_window7_224] INFO: Epoch: [64] [1210/1251] eta: 0:00:20 lr: 0.000890 loss: 3.5596 (3.6562) grad_norm: 1.1325 (1.0448) time: 0.5084 [2021-03-25 15:01:58 swin_small_patch4_window7_224] INFO: Epoch: [64] [1220/1251] eta: 0:00:15 lr: 0.000890 loss: 3.5599 (3.6561) grad_norm: 1.0460 (1.0445) time: 0.5052 [2021-03-25 15:02:03 swin_small_patch4_window7_224] INFO: Epoch: [64] [1230/1251] eta: 0:00:10 lr: 0.000890 loss: 3.7391 (3.6579) grad_norm: 0.9990 (1.0443) time: 0.5007 [2021-03-25 15:02:09 swin_small_patch4_window7_224] INFO: Epoch: [64] [1240/1251] eta: 0:00:05 lr: 0.000890 loss: 3.7117 (3.6561) grad_norm: 1.0108 (1.0445) time: 0.5013 [2021-03-25 15:02:14 swin_small_patch4_window7_224] INFO: Epoch: [64] [1250/1251] eta: 0:00:00 lr: 0.000890 loss: 3.5267 (3.6555) grad_norm: 1.0498 (1.0447) time: 0.5039 [2021-03-25 15:02:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:25 loss: 0.9356 (0.9356) acc1: 79.6875 (79.6875) acc5: 92.1875 (92.1875) [2021-03-25 15:02:22 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9782 (1.0476) acc1: 73.4375 (74.0057) acc5: 93.7500 (93.6080) [2021-03-25 15:02:24 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1398 (1.1237) acc1: 71.8750 (72.0238) acc5: 90.6250 (91.8899) [2021-03-25 15:02:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.2020 (1.1311) acc1: 71.8750 (72.4294) acc5: 90.6250 (91.8347) [2021-03-25 15:02:28 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1119 (1.1236) acc1: 71.8750 (72.6753) acc5: 90.6250 (91.6540) [2021-03-25 15:02:29 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1119 (1.1395) acc1: 71.8750 (72.4160) acc5: 92.1875 (91.7120) [2021-03-25 15:02:32 swin_small_patch4_window7_224] INFO: * Acc@1 73.734 Acc@5 92.370 loss 1.105 [2021-03-25 15:02:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 73.7% [2021-03-25 15:02:32 swin_small_patch4_window7_224] INFO: Max accuracy: 73.93% [2021-03-25 15:02:36 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 0/1251] eta: 1:30:08 lr: 0.000890 loss: 3.2357 (3.2357) grad_norm: 1.0809 (1.0809) time: 4.3233 [2021-03-25 15:02:41 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 10/1251] eta: 0:18:05 lr: 0.000890 loss: 3.9008 (3.5807) grad_norm: 1.0501 (1.0674) time: 0.8744 [2021-03-25 15:02:46 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 20/1251] eta: 0:14:20 lr: 0.000890 loss: 3.4684 (3.4643) grad_norm: 1.0273 (1.0424) time: 0.5177 [2021-03-25 15:02:51 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 30/1251] eta: 0:13:00 lr: 0.000890 loss: 3.5894 (3.5384) grad_norm: 1.0474 (1.0570) time: 0.5098 [2021-03-25 15:02:56 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 40/1251] eta: 0:12:14 lr: 0.000890 loss: 3.7683 (3.5499) grad_norm: 1.0603 (1.0676) time: 0.5093 [2021-03-25 15:03:01 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 50/1251] eta: 0:11:44 lr: 0.000890 loss: 3.8477 (3.5915) grad_norm: 1.0461 (1.0617) time: 0.5059 [2021-03-25 15:03:07 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 60/1251] eta: 0:11:24 lr: 0.000890 loss: 3.7846 (3.5957) grad_norm: 1.0214 (1.0522) time: 0.5104 [2021-03-25 15:03:12 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 70/1251] eta: 0:11:07 lr: 0.000890 loss: 3.7001 (3.5921) grad_norm: 0.9794 (1.0427) time: 0.5109 [2021-03-25 15:03:17 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 80/1251] eta: 0:10:52 lr: 0.000889 loss: 3.5726 (3.5618) grad_norm: 1.0109 (1.0588) time: 0.5017 [2021-03-25 15:03:22 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 90/1251] eta: 0:10:41 lr: 0.000889 loss: 3.3667 (3.5470) grad_norm: 1.0709 (1.0528) time: 0.5084 [2021-03-25 15:03:27 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 100/1251] eta: 0:10:31 lr: 0.000889 loss: 3.6291 (3.5512) grad_norm: 0.9768 (1.0464) time: 0.5151 [2021-03-25 15:03:32 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 110/1251] eta: 0:10:21 lr: 0.000889 loss: 3.7686 (3.5513) grad_norm: 1.0054 (1.0454) time: 0.5066 [2021-03-25 15:03:37 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 120/1251] eta: 0:10:12 lr: 0.000889 loss: 3.4989 (3.5456) grad_norm: 1.0054 (1.0432) time: 0.5052 [2021-03-25 15:03:42 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 130/1251] eta: 0:10:02 lr: 0.000889 loss: 3.4989 (3.5486) grad_norm: 1.0655 (1.0462) time: 0.5007 [2021-03-25 15:03:47 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 140/1251] eta: 0:09:55 lr: 0.000889 loss: 3.7713 (3.5716) grad_norm: 1.0779 (1.0481) time: 0.5009 [2021-03-25 15:03:52 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 150/1251] eta: 0:09:47 lr: 0.000889 loss: 3.9751 (3.5889) grad_norm: 1.0084 (1.0465) time: 0.5052 [2021-03-25 15:03:57 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 160/1251] eta: 0:09:40 lr: 0.000889 loss: 3.7091 (3.5888) grad_norm: 1.0016 (1.0510) time: 0.5048 [2021-03-25 15:04:02 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 170/1251] eta: 0:09:32 lr: 0.000889 loss: 3.8363 (3.5984) grad_norm: 1.0317 (1.0474) time: 0.5031 [2021-03-25 15:04:07 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 180/1251] eta: 0:09:26 lr: 0.000889 loss: 3.6346 (3.5809) grad_norm: 0.9781 (1.0447) time: 0.5060 [2021-03-25 15:04:12 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 190/1251] eta: 0:09:20 lr: 0.000889 loss: 3.3151 (3.5699) grad_norm: 0.9778 (1.0412) time: 0.5115 [2021-03-25 15:04:17 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 200/1251] eta: 0:09:13 lr: 0.000889 loss: 3.7265 (3.5861) grad_norm: 1.0138 (1.0433) time: 0.5054 [2021-03-25 15:04:23 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 210/1251] eta: 0:09:07 lr: 0.000889 loss: 3.7501 (3.5881) grad_norm: 1.0673 (1.0444) time: 0.5077 [2021-03-25 15:04:28 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 220/1251] eta: 0:09:01 lr: 0.000889 loss: 3.6689 (3.5895) grad_norm: 1.0494 (1.0440) time: 0.5112 [2021-03-25 15:04:33 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 230/1251] eta: 0:08:55 lr: 0.000889 loss: 3.3805 (3.5818) grad_norm: 1.0341 (1.0458) time: 0.5043 [2021-03-25 15:04:38 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 240/1251] eta: 0:08:49 lr: 0.000889 loss: 3.5244 (3.5872) grad_norm: 1.0730 (1.0497) time: 0.5042 [2021-03-25 15:04:43 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 250/1251] eta: 0:08:43 lr: 0.000889 loss: 3.6172 (3.5865) grad_norm: 1.0647 (1.0511) time: 0.5111 [2021-03-25 15:04:48 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 260/1251] eta: 0:08:37 lr: 0.000889 loss: 3.6172 (3.5928) grad_norm: 1.0102 (1.0494) time: 0.5133 [2021-03-25 15:04:53 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 270/1251] eta: 0:08:32 lr: 0.000889 loss: 3.6603 (3.5946) grad_norm: 1.0426 (1.0504) time: 0.5076 [2021-03-25 15:04:58 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 280/1251] eta: 0:08:26 lr: 0.000889 loss: 3.6603 (3.5995) grad_norm: 1.0752 (1.0515) time: 0.5057 [2021-03-25 15:05:03 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 290/1251] eta: 0:08:20 lr: 0.000889 loss: 3.6191 (3.6017) grad_norm: 1.0302 (1.0500) time: 0.5065 [2021-03-25 15:05:08 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 300/1251] eta: 0:08:14 lr: 0.000889 loss: 3.6191 (3.6028) grad_norm: 1.0539 (1.0522) time: 0.5055 [2021-03-25 15:05:13 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 310/1251] eta: 0:08:09 lr: 0.000889 loss: 3.8364 (3.6071) grad_norm: 1.1065 (1.0544) time: 0.5044 [2021-03-25 15:05:18 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 320/1251] eta: 0:08:03 lr: 0.000889 loss: 3.7047 (3.6117) grad_norm: 1.0700 (1.0557) time: 0.5029 [2021-03-25 15:05:23 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 330/1251] eta: 0:07:57 lr: 0.000889 loss: 3.6091 (3.6071) grad_norm: 1.0521 (1.0561) time: 0.5026 [2021-03-25 15:05:28 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 340/1251] eta: 0:07:52 lr: 0.000889 loss: 3.5851 (3.6058) grad_norm: 1.0184 (1.0544) time: 0.5021 [2021-03-25 15:05:33 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 350/1251] eta: 0:07:46 lr: 0.000889 loss: 3.7419 (3.6146) grad_norm: 0.9864 (1.0533) time: 0.5029 [2021-03-25 15:05:38 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 360/1251] eta: 0:07:41 lr: 0.000889 loss: 3.7381 (3.6136) grad_norm: 1.0156 (1.0530) time: 0.5032 [2021-03-25 15:05:44 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 370/1251] eta: 0:07:35 lr: 0.000889 loss: 3.7381 (3.6148) grad_norm: 1.0225 (1.0552) time: 0.5049 [2021-03-25 15:05:49 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 380/1251] eta: 0:07:30 lr: 0.000889 loss: 3.8991 (3.6165) grad_norm: 1.0761 (1.0568) time: 0.5060 [2021-03-25 15:05:54 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 390/1251] eta: 0:07:24 lr: 0.000889 loss: 3.7334 (3.6143) grad_norm: 1.0423 (1.0561) time: 0.5049 [2021-03-25 15:05:59 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 400/1251] eta: 0:07:19 lr: 0.000889 loss: 3.5292 (3.6105) grad_norm: 1.0324 (1.0569) time: 0.5053 [2021-03-25 15:06:04 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 410/1251] eta: 0:07:13 lr: 0.000889 loss: 3.5359 (3.6113) grad_norm: 1.0468 (1.0568) time: 0.5030 [2021-03-25 15:06:09 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 420/1251] eta: 0:07:08 lr: 0.000889 loss: 3.6297 (3.6134) grad_norm: 1.1108 (1.0597) time: 0.5026 [2021-03-25 15:06:14 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 430/1251] eta: 0:07:03 lr: 0.000889 loss: 3.7444 (3.6136) grad_norm: 1.0655 (1.0591) time: 0.5040 [2021-03-25 15:06:19 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 440/1251] eta: 0:06:57 lr: 0.000889 loss: 3.4980 (3.6089) grad_norm: 0.9987 (1.0578) time: 0.5088 [2021-03-25 15:06:24 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 450/1251] eta: 0:06:52 lr: 0.000889 loss: 3.7940 (3.6109) grad_norm: 1.0280 (1.0571) time: 0.5129 [2021-03-25 15:06:29 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 460/1251] eta: 0:06:47 lr: 0.000888 loss: 3.8237 (3.6107) grad_norm: 0.9693 (1.0557) time: 0.5100 [2021-03-25 15:06:34 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 470/1251] eta: 0:06:42 lr: 0.000888 loss: 3.7651 (3.6153) grad_norm: 0.9503 (1.0541) time: 0.5053 [2021-03-25 15:06:39 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 480/1251] eta: 0:06:36 lr: 0.000888 loss: 3.7499 (3.6158) grad_norm: 0.9923 (1.0540) time: 0.5049 [2021-03-25 15:06:44 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 490/1251] eta: 0:06:31 lr: 0.000888 loss: 3.9047 (3.6203) grad_norm: 1.0097 (1.0537) time: 0.5032 [2021-03-25 15:06:49 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 500/1251] eta: 0:06:26 lr: 0.000888 loss: 3.9175 (3.6207) grad_norm: 1.0898 (1.0555) time: 0.5021 [2021-03-25 15:06:54 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 510/1251] eta: 0:06:20 lr: 0.000888 loss: 3.7659 (3.6229) grad_norm: 1.0690 (1.0556) time: 0.5016 [2021-03-25 15:06:59 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 520/1251] eta: 0:06:15 lr: 0.000888 loss: 3.6598 (3.6204) grad_norm: 1.0019 (1.0544) time: 0.4974 [2021-03-25 15:07:04 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 530/1251] eta: 0:06:10 lr: 0.000888 loss: 3.8257 (3.6249) grad_norm: 0.9657 (1.0549) time: 0.4988 [2021-03-25 15:07:09 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 540/1251] eta: 0:06:04 lr: 0.000888 loss: 3.8257 (3.6253) grad_norm: 1.0595 (1.0556) time: 0.5066 [2021-03-25 15:07:14 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 550/1251] eta: 0:05:59 lr: 0.000888 loss: 3.6912 (3.6250) grad_norm: 1.0773 (1.0559) time: 0.5119 [2021-03-25 15:07:20 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 560/1251] eta: 0:05:54 lr: 0.000888 loss: 3.5948 (3.6248) grad_norm: 1.0489 (1.0560) time: 0.5124 [2021-03-25 15:07:25 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 570/1251] eta: 0:05:49 lr: 0.000888 loss: 3.4846 (3.6217) grad_norm: 1.0154 (1.0551) time: 0.5067 [2021-03-25 15:07:30 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 580/1251] eta: 0:05:44 lr: 0.000888 loss: 3.5195 (3.6228) grad_norm: 0.9979 (1.0547) time: 0.5001 [2021-03-25 15:07:35 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 590/1251] eta: 0:05:38 lr: 0.000888 loss: 3.8464 (3.6255) grad_norm: 0.9932 (1.0532) time: 0.5046 [2021-03-25 15:07:40 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 600/1251] eta: 0:05:33 lr: 0.000888 loss: 3.8864 (3.6264) grad_norm: 0.9822 (1.0519) time: 0.5092 [2021-03-25 15:07:45 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 610/1251] eta: 0:05:28 lr: 0.000888 loss: 3.3076 (3.6201) grad_norm: 0.9973 (1.0507) time: 0.5104 [2021-03-25 15:07:50 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 620/1251] eta: 0:05:23 lr: 0.000888 loss: 3.7202 (3.6250) grad_norm: 0.9957 (1.0498) time: 0.5084 [2021-03-25 15:07:55 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 630/1251] eta: 0:05:18 lr: 0.000888 loss: 3.7349 (3.6216) grad_norm: 0.9975 (1.0492) time: 0.5077 [2021-03-25 15:08:00 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 640/1251] eta: 0:05:13 lr: 0.000888 loss: 3.7349 (3.6265) grad_norm: 0.9976 (1.0498) time: 0.5041 [2021-03-25 15:08:05 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 650/1251] eta: 0:05:07 lr: 0.000888 loss: 3.8278 (3.6285) grad_norm: 1.0751 (1.0510) time: 0.4999 [2021-03-25 15:08:10 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 660/1251] eta: 0:05:02 lr: 0.000888 loss: 3.8589 (3.6314) grad_norm: 1.0751 (1.0509) time: 0.5014 [2021-03-25 15:08:15 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 670/1251] eta: 0:04:57 lr: 0.000888 loss: 3.9469 (3.6356) grad_norm: 1.0064 (1.0506) time: 0.5049 [2021-03-25 15:08:20 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 680/1251] eta: 0:04:52 lr: 0.000888 loss: 3.8020 (3.6387) grad_norm: 1.0166 (1.0502) time: 0.5058 [2021-03-25 15:08:25 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 690/1251] eta: 0:04:47 lr: 0.000888 loss: 3.7708 (3.6406) grad_norm: 1.0160 (1.0496) time: 0.5054 [2021-03-25 15:08:30 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 700/1251] eta: 0:04:41 lr: 0.000888 loss: 3.7696 (3.6412) grad_norm: 1.0247 (1.0499) time: 0.4984 [2021-03-25 15:08:35 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 710/1251] eta: 0:04:36 lr: 0.000888 loss: 3.8290 (3.6440) grad_norm: 1.1027 (1.0509) time: 0.4958 [2021-03-25 15:08:40 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 720/1251] eta: 0:04:31 lr: 0.000888 loss: 3.7991 (3.6452) grad_norm: 1.0724 (1.0513) time: 0.5039 [2021-03-25 15:08:45 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 730/1251] eta: 0:04:26 lr: 0.000888 loss: 3.7771 (3.6459) grad_norm: 1.0170 (1.0508) time: 0.5157 [2021-03-25 15:08:51 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 740/1251] eta: 0:04:21 lr: 0.000888 loss: 3.8794 (3.6494) grad_norm: 1.0170 (1.0506) time: 0.5174 [2021-03-25 15:08:56 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 750/1251] eta: 0:04:16 lr: 0.000888 loss: 3.9487 (3.6499) grad_norm: 1.0475 (1.0504) time: 0.5161 [2021-03-25 15:09:01 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 760/1251] eta: 0:04:11 lr: 0.000888 loss: 3.8058 (3.6522) grad_norm: 1.0820 (1.0512) time: 0.5214 [2021-03-25 15:09:06 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 770/1251] eta: 0:04:06 lr: 0.000888 loss: 3.9459 (3.6554) grad_norm: 1.1160 (1.0527) time: 0.5135 [2021-03-25 15:09:11 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 780/1251] eta: 0:04:00 lr: 0.000888 loss: 3.8085 (3.6542) grad_norm: 1.0749 (1.0529) time: 0.5000 [2021-03-25 15:09:16 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 790/1251] eta: 0:03:55 lr: 0.000888 loss: 3.6522 (3.6552) grad_norm: 1.0675 (1.0537) time: 0.5043 [2021-03-25 15:09:21 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 800/1251] eta: 0:03:50 lr: 0.000888 loss: 3.5962 (3.6528) grad_norm: 1.0132 (1.0532) time: 0.5120 [2021-03-25 15:09:26 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 810/1251] eta: 0:03:45 lr: 0.000888 loss: 3.7926 (3.6568) grad_norm: 0.9988 (1.0532) time: 0.5067 [2021-03-25 15:09:31 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 820/1251] eta: 0:03:40 lr: 0.000888 loss: 3.8127 (3.6534) grad_norm: 1.0424 (1.0537) time: 0.5029 [2021-03-25 15:09:36 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 830/1251] eta: 0:03:35 lr: 0.000888 loss: 3.8883 (3.6568) grad_norm: 1.1166 (1.0544) time: 0.5032 [2021-03-25 15:09:41 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 840/1251] eta: 0:03:30 lr: 0.000887 loss: 3.7598 (3.6541) grad_norm: 1.1361 (1.0557) time: 0.5066 [2021-03-25 15:09:46 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 850/1251] eta: 0:03:24 lr: 0.000887 loss: 3.4835 (3.6528) grad_norm: 1.0938 (1.0553) time: 0.5052 [2021-03-25 15:09:52 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 860/1251] eta: 0:03:19 lr: 0.000887 loss: 3.6402 (3.6531) grad_norm: 1.0291 (1.0557) time: 0.5051 [2021-03-25 15:09:57 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 870/1251] eta: 0:03:14 lr: 0.000887 loss: 3.7116 (3.6511) grad_norm: 1.0127 (1.0556) time: 0.5050 [2021-03-25 15:10:02 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 880/1251] eta: 0:03:09 lr: 0.000887 loss: 3.7537 (3.6521) grad_norm: 1.0252 (1.0558) time: 0.5012 [2021-03-25 15:10:07 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 890/1251] eta: 0:03:04 lr: 0.000887 loss: 3.8340 (3.6539) grad_norm: 1.0797 (1.0566) time: 0.5034 [2021-03-25 15:10:12 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 900/1251] eta: 0:02:59 lr: 0.000887 loss: 3.7470 (3.6507) grad_norm: 1.0455 (1.0562) time: 0.5083 [2021-03-25 15:10:17 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 910/1251] eta: 0:02:54 lr: 0.000887 loss: 3.3045 (3.6501) grad_norm: 0.9855 (1.0558) time: 0.5054 [2021-03-25 15:10:22 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 920/1251] eta: 0:02:48 lr: 0.000887 loss: 3.8921 (3.6530) grad_norm: 1.0280 (1.0561) time: 0.5057 [2021-03-25 15:10:27 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 930/1251] eta: 0:02:43 lr: 0.000887 loss: 3.7699 (3.6509) grad_norm: 1.0339 (1.0562) time: 0.5088 [2021-03-25 15:10:32 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 940/1251] eta: 0:02:38 lr: 0.000887 loss: 3.7350 (3.6499) grad_norm: 1.0077 (1.0554) time: 0.5051 [2021-03-25 15:10:37 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 950/1251] eta: 0:02:33 lr: 0.000887 loss: 3.7609 (3.6505) grad_norm: 0.9985 (1.0551) time: 0.5081 [2021-03-25 15:10:42 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 960/1251] eta: 0:02:28 lr: 0.000887 loss: 3.6225 (3.6483) grad_norm: 1.0635 (1.0560) time: 0.5105 [2021-03-25 15:10:47 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 970/1251] eta: 0:02:23 lr: 0.000887 loss: 3.5980 (3.6491) grad_norm: 1.1021 (1.0563) time: 0.5068 [2021-03-25 15:10:52 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 980/1251] eta: 0:02:18 lr: 0.000887 loss: 3.8436 (3.6509) grad_norm: 1.0560 (1.0572) time: 0.5059 [2021-03-25 15:10:57 swin_small_patch4_window7_224] INFO: Epoch: [65] [ 990/1251] eta: 0:02:13 lr: 0.000887 loss: 3.8572 (3.6513) grad_norm: 1.0344 (1.0569) time: 0.5107 [2021-03-25 15:11:02 swin_small_patch4_window7_224] INFO: Epoch: [65] [1000/1251] eta: 0:02:08 lr: 0.000887 loss: 3.7514 (3.6513) grad_norm: 1.0300 (1.0569) time: 0.5067 [2021-03-25 15:11:07 swin_small_patch4_window7_224] INFO: Epoch: [65] [1010/1251] eta: 0:02:02 lr: 0.000887 loss: 3.6555 (3.6486) grad_norm: 1.0516 (1.0575) time: 0.5002 [2021-03-25 15:11:13 swin_small_patch4_window7_224] INFO: Epoch: [65] [1020/1251] eta: 0:01:57 lr: 0.000887 loss: 3.5331 (3.6478) grad_norm: 1.0836 (1.0585) time: 0.5126 [2021-03-25 15:11:18 swin_small_patch4_window7_224] INFO: Epoch: [65] [1030/1251] eta: 0:01:52 lr: 0.000887 loss: 3.7292 (3.6492) grad_norm: 1.0377 (1.0588) time: 0.5106 [2021-03-25 15:11:23 swin_small_patch4_window7_224] INFO: Epoch: [65] [1040/1251] eta: 0:01:47 lr: 0.000887 loss: 3.7816 (3.6498) grad_norm: 1.0356 (1.0588) time: 0.5010 [2021-03-25 15:11:28 swin_small_patch4_window7_224] INFO: Epoch: [65] [1050/1251] eta: 0:01:42 lr: 0.000887 loss: 3.7816 (3.6485) grad_norm: 1.0637 (1.0594) time: 0.5041 [2021-03-25 15:11:33 swin_small_patch4_window7_224] INFO: Epoch: [65] [1060/1251] eta: 0:01:37 lr: 0.000887 loss: 3.6184 (3.6485) grad_norm: 1.0963 (1.0600) time: 0.5075 [2021-03-25 15:11:38 swin_small_patch4_window7_224] INFO: Epoch: [65] [1070/1251] eta: 0:01:32 lr: 0.000887 loss: 3.6257 (3.6490) grad_norm: 1.0150 (1.0597) time: 0.5098 [2021-03-25 15:11:43 swin_small_patch4_window7_224] INFO: Epoch: [65] [1080/1251] eta: 0:01:27 lr: 0.000887 loss: 3.6239 (3.6469) grad_norm: 1.0514 (1.0597) time: 0.5112 [2021-03-25 15:11:48 swin_small_patch4_window7_224] INFO: Epoch: [65] [1090/1251] eta: 0:01:22 lr: 0.000887 loss: 3.3980 (3.6461) grad_norm: 1.0663 (1.0601) time: 0.5112 [2021-03-25 15:11:53 swin_small_patch4_window7_224] INFO: Epoch: [65] [1100/1251] eta: 0:01:17 lr: 0.000887 loss: 3.7806 (3.6492) grad_norm: 1.0878 (1.0605) time: 0.5102 [2021-03-25 15:11:58 swin_small_patch4_window7_224] INFO: Epoch: [65] [1110/1251] eta: 0:01:11 lr: 0.000887 loss: 3.9052 (3.6488) grad_norm: 1.0227 (1.0600) time: 0.5067 [2021-03-25 15:12:03 swin_small_patch4_window7_224] INFO: Epoch: [65] [1120/1251] eta: 0:01:06 lr: 0.000887 loss: 3.8991 (3.6518) grad_norm: 0.9770 (1.0593) time: 0.5054 [2021-03-25 15:12:08 swin_small_patch4_window7_224] INFO: Epoch: [65] [1130/1251] eta: 0:01:01 lr: 0.000887 loss: 4.0077 (3.6519) grad_norm: 1.0239 (1.0599) time: 0.5051 [2021-03-25 15:12:14 swin_small_patch4_window7_224] INFO: Epoch: [65] [1140/1251] eta: 0:00:56 lr: 0.000887 loss: 3.8221 (3.6525) grad_norm: 1.0750 (1.0600) time: 0.5045 [2021-03-25 15:12:19 swin_small_patch4_window7_224] INFO: Epoch: [65] [1150/1251] eta: 0:00:51 lr: 0.000887 loss: 3.8221 (3.6535) grad_norm: 1.0497 (1.0610) time: 0.5040 [2021-03-25 15:12:24 swin_small_patch4_window7_224] INFO: Epoch: [65] [1160/1251] eta: 0:00:46 lr: 0.000887 loss: 3.8629 (3.6539) grad_norm: 1.1179 (1.0616) time: 0.5034 [2021-03-25 15:12:29 swin_small_patch4_window7_224] INFO: Epoch: [65] [1170/1251] eta: 0:00:41 lr: 0.000887 loss: 3.5570 (3.6521) grad_norm: 1.0978 (1.0619) time: 0.5040 [2021-03-25 15:12:34 swin_small_patch4_window7_224] INFO: Epoch: [65] [1180/1251] eta: 0:00:36 lr: 0.000887 loss: 3.6577 (3.6538) grad_norm: 1.0687 (1.0623) time: 0.5112 [2021-03-25 15:12:39 swin_small_patch4_window7_224] INFO: Epoch: [65] [1190/1251] eta: 0:00:31 lr: 0.000887 loss: 3.7826 (3.6545) grad_norm: 1.0444 (1.0620) time: 0.5214 [2021-03-25 15:12:44 swin_small_patch4_window7_224] INFO: Epoch: [65] [1200/1251] eta: 0:00:26 lr: 0.000887 loss: 3.8436 (3.6559) grad_norm: 1.0398 (1.0614) time: 0.5118 [2021-03-25 15:12:49 swin_small_patch4_window7_224] INFO: Epoch: [65] [1210/1251] eta: 0:00:20 lr: 0.000887 loss: 3.6726 (3.6534) grad_norm: 0.9503 (1.0609) time: 0.5020 [2021-03-25 15:12:54 swin_small_patch4_window7_224] INFO: Epoch: [65] [1220/1251] eta: 0:00:15 lr: 0.000886 loss: 3.6854 (3.6547) grad_norm: 1.0097 (1.0604) time: 0.5073 [2021-03-25 15:12:59 swin_small_patch4_window7_224] INFO: Epoch: [65] [1230/1251] eta: 0:00:10 lr: 0.000886 loss: 3.9172 (3.6553) grad_norm: 0.9867 (1.0597) time: 0.5121 [2021-03-25 15:13:04 swin_small_patch4_window7_224] INFO: Epoch: [65] [1240/1251] eta: 0:00:05 lr: 0.000886 loss: 3.9394 (3.6569) grad_norm: 1.0625 (1.0606) time: 0.5100 [2021-03-25 15:13:09 swin_small_patch4_window7_224] INFO: Epoch: [65] [1250/1251] eta: 0:00:00 lr: 0.000886 loss: 3.9158 (3.6558) grad_norm: 1.1062 (1.0606) time: 0.5016 [2021-03-25 15:13:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 0.8431 (0.8431) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-25 15:13:51 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.1942 (1.2324) acc1: 70.3125 (70.7386) acc5: 90.6250 (90.4830) [2021-03-25 15:13:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.1511 (1.1411) acc1: 73.4375 (73.3631) acc5: 90.6250 (91.5179) [2021-03-25 15:13:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0931 (1.1351) acc1: 75.0000 (72.7823) acc5: 92.1875 (91.9355) [2021-03-25 15:13:55 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0478 (1.1191) acc1: 73.4375 (73.2088) acc5: 93.7500 (92.2256) [2021-03-25 15:13:56 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0478 (1.1132) acc1: 73.4375 (73.1520) acc5: 93.7500 (92.2880) [2021-03-25 15:14:00 swin_small_patch4_window7_224] INFO: * Acc@1 74.170 Acc@5 92.416 loss 1.087 [2021-03-25 15:14:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.2% [2021-03-25 15:14:00 swin_small_patch4_window7_224] INFO: Max accuracy: 74.17% [2021-03-25 15:14:04 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 0/1251] eta: 1:25:42 lr: 0.000886 loss: 2.8949 (2.8949) grad_norm: 0.9871 (0.9871) time: 4.1105 [2021-03-25 15:14:09 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 10/1251] eta: 0:17:42 lr: 0.000886 loss: 3.9318 (3.6669) grad_norm: 0.9666 (0.9896) time: 0.8565 [2021-03-25 15:14:14 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 20/1251] eta: 0:14:06 lr: 0.000886 loss: 3.7604 (3.6355) grad_norm: 1.0193 (1.0428) time: 0.5163 [2021-03-25 15:14:19 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 30/1251] eta: 0:12:48 lr: 0.000886 loss: 3.7604 (3.6474) grad_norm: 1.0528 (1.0574) time: 0.5051 [2021-03-25 15:14:24 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 40/1251] eta: 0:12:06 lr: 0.000886 loss: 3.8257 (3.6624) grad_norm: 0.9970 (1.0512) time: 0.5086 [2021-03-25 15:14:29 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 50/1251] eta: 0:11:36 lr: 0.000886 loss: 3.8257 (3.7356) grad_norm: 0.9889 (1.0447) time: 0.5027 [2021-03-25 15:14:34 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 60/1251] eta: 0:11:15 lr: 0.000886 loss: 3.8018 (3.7135) grad_norm: 0.9903 (1.0344) time: 0.4987 [2021-03-25 15:14:39 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 70/1251] eta: 0:10:59 lr: 0.000886 loss: 3.7045 (3.6870) grad_norm: 1.0225 (1.0396) time: 0.5024 [2021-03-25 15:14:44 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 80/1251] eta: 0:10:46 lr: 0.000886 loss: 3.7045 (3.6920) grad_norm: 1.0506 (1.0361) time: 0.5077 [2021-03-25 15:14:50 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 90/1251] eta: 0:10:35 lr: 0.000886 loss: 3.6519 (3.6682) grad_norm: 1.0465 (1.0449) time: 0.5094 [2021-03-25 15:14:55 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 100/1251] eta: 0:10:24 lr: 0.000886 loss: 3.4159 (3.6376) grad_norm: 1.0086 (1.0385) time: 0.5048 [2021-03-25 15:15:00 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 110/1251] eta: 0:10:16 lr: 0.000886 loss: 3.5208 (3.6290) grad_norm: 0.9554 (1.0312) time: 0.5098 [2021-03-25 15:15:05 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 120/1251] eta: 0:10:08 lr: 0.000886 loss: 3.7975 (3.6374) grad_norm: 1.0318 (1.0416) time: 0.5141 [2021-03-25 15:15:10 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 130/1251] eta: 0:09:59 lr: 0.000886 loss: 3.9554 (3.6629) grad_norm: 1.0861 (1.0467) time: 0.5035 [2021-03-25 15:15:15 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 140/1251] eta: 0:09:52 lr: 0.000886 loss: 4.0043 (3.6536) grad_norm: 1.0744 (1.0505) time: 0.5033 [2021-03-25 15:15:20 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 150/1251] eta: 0:09:46 lr: 0.000886 loss: 3.5867 (3.6551) grad_norm: 1.0439 (1.0480) time: 0.5162 [2021-03-25 15:15:25 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 160/1251] eta: 0:09:39 lr: 0.000886 loss: 3.6113 (3.6551) grad_norm: 1.0035 (1.0461) time: 0.5151 [2021-03-25 15:15:30 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 170/1251] eta: 0:09:32 lr: 0.000886 loss: 3.6620 (3.6488) grad_norm: 1.0509 (1.0473) time: 0.5072 [2021-03-25 15:15:35 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 180/1251] eta: 0:09:26 lr: 0.000886 loss: 3.6021 (3.6359) grad_norm: 1.1121 (1.0518) time: 0.5099 [2021-03-25 15:15:41 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 190/1251] eta: 0:09:19 lr: 0.000886 loss: 3.6678 (3.6461) grad_norm: 1.0971 (1.0558) time: 0.5118 [2021-03-25 15:15:46 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 200/1251] eta: 0:09:13 lr: 0.000886 loss: 3.9043 (3.6540) grad_norm: 1.0348 (1.0530) time: 0.5107 [2021-03-25 15:15:51 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 210/1251] eta: 0:09:07 lr: 0.000886 loss: 3.8208 (3.6536) grad_norm: 0.9947 (1.0503) time: 0.5049 [2021-03-25 15:15:56 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 220/1251] eta: 0:09:00 lr: 0.000886 loss: 3.8067 (3.6436) grad_norm: 0.9671 (1.0479) time: 0.5015 [2021-03-25 15:16:01 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 230/1251] eta: 0:08:54 lr: 0.000886 loss: 3.8067 (3.6477) grad_norm: 0.9522 (1.0437) time: 0.5048 [2021-03-25 15:16:06 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 240/1251] eta: 0:08:48 lr: 0.000886 loss: 3.8357 (3.6541) grad_norm: 0.9829 (1.0445) time: 0.5056 [2021-03-25 15:16:11 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 250/1251] eta: 0:08:42 lr: 0.000886 loss: 3.7986 (3.6355) grad_norm: 0.9984 (1.0461) time: 0.5064 [2021-03-25 15:16:16 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 260/1251] eta: 0:08:37 lr: 0.000886 loss: 3.7461 (3.6390) grad_norm: 0.9891 (1.0458) time: 0.5075 [2021-03-25 15:16:21 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 270/1251] eta: 0:08:31 lr: 0.000886 loss: 3.8179 (3.6471) grad_norm: 0.9897 (1.0449) time: 0.5060 [2021-03-25 15:16:26 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 280/1251] eta: 0:08:25 lr: 0.000886 loss: 3.8194 (3.6498) grad_norm: 1.0099 (1.0443) time: 0.5011 [2021-03-25 15:16:31 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 290/1251] eta: 0:08:19 lr: 0.000886 loss: 3.7821 (3.6584) grad_norm: 1.0014 (1.0433) time: 0.5013 [2021-03-25 15:16:36 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 300/1251] eta: 0:08:13 lr: 0.000886 loss: 3.6828 (3.6582) grad_norm: 0.9626 (1.0412) time: 0.4984 [2021-03-25 15:16:41 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 310/1251] eta: 0:08:08 lr: 0.000886 loss: 3.6445 (3.6536) grad_norm: 0.9774 (1.0422) time: 0.5050 [2021-03-25 15:16:46 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 320/1251] eta: 0:08:02 lr: 0.000886 loss: 3.7922 (3.6542) grad_norm: 1.0982 (1.0453) time: 0.5113 [2021-03-25 15:16:51 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 330/1251] eta: 0:07:57 lr: 0.000886 loss: 3.7922 (3.6572) grad_norm: 1.0640 (1.0470) time: 0.5099 [2021-03-25 15:16:56 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 340/1251] eta: 0:07:51 lr: 0.000886 loss: 3.9366 (3.6623) grad_norm: 1.0566 (1.0474) time: 0.5122 [2021-03-25 15:17:01 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 350/1251] eta: 0:07:46 lr: 0.000885 loss: 3.6392 (3.6540) grad_norm: 1.0851 (1.0499) time: 0.5065 [2021-03-25 15:17:07 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 360/1251] eta: 0:07:41 lr: 0.000885 loss: 3.7965 (3.6621) grad_norm: 1.1092 (1.0512) time: 0.5087 [2021-03-25 15:17:12 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 370/1251] eta: 0:07:36 lr: 0.000885 loss: 3.9576 (3.6708) grad_norm: 1.0589 (1.0515) time: 0.5177 [2021-03-25 15:17:17 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 380/1251] eta: 0:07:30 lr: 0.000885 loss: 3.8563 (3.6719) grad_norm: 1.0399 (1.0511) time: 0.5139 [2021-03-25 15:17:22 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 390/1251] eta: 0:07:25 lr: 0.000885 loss: 3.6130 (3.6669) grad_norm: 1.0432 (1.0525) time: 0.5080 [2021-03-25 15:17:27 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 400/1251] eta: 0:07:19 lr: 0.000885 loss: 3.6130 (3.6674) grad_norm: 0.9970 (1.0510) time: 0.5073 [2021-03-25 15:17:32 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 410/1251] eta: 0:07:14 lr: 0.000885 loss: 3.6448 (3.6617) grad_norm: 0.9989 (1.0523) time: 0.5022 [2021-03-25 15:17:37 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 420/1251] eta: 0:07:08 lr: 0.000885 loss: 3.4537 (3.6580) grad_norm: 1.0925 (1.0535) time: 0.4995 [2021-03-25 15:17:42 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 430/1251] eta: 0:07:03 lr: 0.000885 loss: 3.6797 (3.6578) grad_norm: 1.0854 (1.0528) time: 0.5002 [2021-03-25 15:17:47 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 440/1251] eta: 0:06:58 lr: 0.000885 loss: 3.6808 (3.6570) grad_norm: 1.0067 (1.0512) time: 0.5043 [2021-03-25 15:17:52 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 450/1251] eta: 0:06:52 lr: 0.000885 loss: 3.6642 (3.6571) grad_norm: 1.0067 (1.0516) time: 0.5064 [2021-03-25 15:17:57 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 460/1251] eta: 0:06:47 lr: 0.000885 loss: 3.6642 (3.6560) grad_norm: 1.0390 (1.0515) time: 0.5011 [2021-03-25 15:18:02 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 470/1251] eta: 0:06:41 lr: 0.000885 loss: 3.7821 (3.6517) grad_norm: 1.0504 (1.0533) time: 0.4995 [2021-03-25 15:18:07 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 480/1251] eta: 0:06:36 lr: 0.000885 loss: 3.7821 (3.6522) grad_norm: 1.0379 (1.0529) time: 0.5003 [2021-03-25 15:18:12 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 490/1251] eta: 0:06:31 lr: 0.000885 loss: 3.7546 (3.6468) grad_norm: 1.0360 (1.0531) time: 0.5031 [2021-03-25 15:18:17 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 500/1251] eta: 0:06:25 lr: 0.000885 loss: 3.7464 (3.6453) grad_norm: 1.0081 (1.0519) time: 0.5060 [2021-03-25 15:18:22 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 510/1251] eta: 0:06:20 lr: 0.000885 loss: 3.7575 (3.6475) grad_norm: 0.9749 (1.0510) time: 0.5075 [2021-03-25 15:18:27 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 520/1251] eta: 0:06:15 lr: 0.000885 loss: 3.8907 (3.6499) grad_norm: 0.9968 (1.0507) time: 0.5102 [2021-03-25 15:18:33 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 530/1251] eta: 0:06:10 lr: 0.000885 loss: 3.9349 (3.6538) grad_norm: 1.0458 (1.0522) time: 0.5075 [2021-03-25 15:18:38 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 540/1251] eta: 0:06:05 lr: 0.000885 loss: 3.6962 (3.6510) grad_norm: 1.0532 (1.0518) time: 0.5066 [2021-03-25 15:18:43 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 550/1251] eta: 0:06:00 lr: 0.000885 loss: 3.6393 (3.6541) grad_norm: 0.9817 (1.0515) time: 0.5138 [2021-03-25 15:18:48 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 560/1251] eta: 0:05:54 lr: 0.000885 loss: 3.8052 (3.6533) grad_norm: 0.9836 (1.0502) time: 0.5166 [2021-03-25 15:18:53 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 570/1251] eta: 0:05:49 lr: 0.000885 loss: 3.8234 (3.6558) grad_norm: 0.9993 (1.0501) time: 0.5085 [2021-03-25 15:18:58 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 580/1251] eta: 0:05:44 lr: 0.000885 loss: 3.8234 (3.6544) grad_norm: 1.0221 (1.0496) time: 0.5041 [2021-03-25 15:19:03 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 590/1251] eta: 0:05:39 lr: 0.000885 loss: 3.8399 (3.6556) grad_norm: 1.0317 (1.0495) time: 0.5052 [2021-03-25 15:19:08 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 600/1251] eta: 0:05:33 lr: 0.000885 loss: 3.8399 (3.6572) grad_norm: 1.0886 (1.0510) time: 0.4997 [2021-03-25 15:19:13 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 610/1251] eta: 0:05:28 lr: 0.000885 loss: 3.7139 (3.6586) grad_norm: 1.0986 (1.0525) time: 0.4986 [2021-03-25 15:19:18 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 620/1251] eta: 0:05:23 lr: 0.000885 loss: 3.6372 (3.6567) grad_norm: 1.0255 (1.0516) time: 0.5061 [2021-03-25 15:19:23 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 630/1251] eta: 0:05:18 lr: 0.000885 loss: 3.6277 (3.6563) grad_norm: 1.0087 (1.0513) time: 0.5112 [2021-03-25 15:19:28 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 640/1251] eta: 0:05:13 lr: 0.000885 loss: 3.8158 (3.6596) grad_norm: 1.0067 (1.0504) time: 0.5062 [2021-03-25 15:19:33 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 650/1251] eta: 0:05:07 lr: 0.000885 loss: 3.8460 (3.6611) grad_norm: 1.0026 (1.0500) time: 0.5022 [2021-03-25 15:19:38 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 660/1251] eta: 0:05:02 lr: 0.000885 loss: 3.7860 (3.6632) grad_norm: 0.9798 (1.0494) time: 0.5029 [2021-03-25 15:19:43 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 670/1251] eta: 0:04:57 lr: 0.000885 loss: 3.8899 (3.6629) grad_norm: 0.9829 (1.0492) time: 0.5008 [2021-03-25 15:19:48 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 680/1251] eta: 0:04:52 lr: 0.000885 loss: 3.8232 (3.6608) grad_norm: 1.0629 (1.0495) time: 0.5037 [2021-03-25 15:19:53 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 690/1251] eta: 0:04:47 lr: 0.000885 loss: 3.5550 (3.6614) grad_norm: 1.0776 (1.0497) time: 0.5060 [2021-03-25 15:19:59 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 700/1251] eta: 0:04:41 lr: 0.000885 loss: 3.7939 (3.6645) grad_norm: 1.0380 (1.0498) time: 0.5073 [2021-03-25 15:20:04 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 710/1251] eta: 0:04:36 lr: 0.000885 loss: 3.8534 (3.6655) grad_norm: 1.0351 (1.0496) time: 0.5058 [2021-03-25 15:20:09 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 720/1251] eta: 0:04:31 lr: 0.000884 loss: 3.8727 (3.6672) grad_norm: 1.0351 (inf) time: 0.5028 [2021-03-25 15:20:14 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 730/1251] eta: 0:04:26 lr: 0.000884 loss: 3.8727 (3.6638) grad_norm: 1.0782 (inf) time: 0.5052 [2021-03-25 15:20:19 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 740/1251] eta: 0:04:21 lr: 0.000884 loss: 3.6124 (3.6637) grad_norm: 1.1472 (inf) time: 0.5232 [2021-03-25 15:20:24 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 750/1251] eta: 0:04:16 lr: 0.000884 loss: 3.7224 (3.6665) grad_norm: 1.1472 (inf) time: 0.5264 [2021-03-25 15:20:29 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 760/1251] eta: 0:04:11 lr: 0.000884 loss: 3.8862 (3.6649) grad_norm: 1.0477 (inf) time: 0.5041 [2021-03-25 15:20:34 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 770/1251] eta: 0:04:06 lr: 0.000884 loss: 3.7123 (3.6631) grad_norm: 1.0218 (inf) time: 0.5017 [2021-03-25 15:20:39 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 780/1251] eta: 0:04:00 lr: 0.000884 loss: 3.6767 (3.6640) grad_norm: 0.9744 (inf) time: 0.5034 [2021-03-25 15:20:44 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 790/1251] eta: 0:03:55 lr: 0.000884 loss: 3.6047 (3.6624) grad_norm: 0.9980 (inf) time: 0.5055 [2021-03-25 15:20:49 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 800/1251] eta: 0:03:50 lr: 0.000884 loss: 3.4791 (3.6607) grad_norm: 1.0284 (inf) time: 0.5076 [2021-03-25 15:20:54 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 810/1251] eta: 0:03:45 lr: 0.000884 loss: 3.5565 (3.6585) grad_norm: 1.0311 (inf) time: 0.5048 [2021-03-25 15:21:00 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 820/1251] eta: 0:03:40 lr: 0.000884 loss: 3.5565 (3.6574) grad_norm: 1.0087 (inf) time: 0.5120 [2021-03-25 15:21:05 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 830/1251] eta: 0:03:35 lr: 0.000884 loss: 3.6953 (3.6583) grad_norm: 0.9904 (inf) time: 0.5105 [2021-03-25 15:21:10 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 840/1251] eta: 0:03:30 lr: 0.000884 loss: 3.6953 (3.6570) grad_norm: 1.0231 (inf) time: 0.5017 [2021-03-25 15:21:15 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 850/1251] eta: 0:03:24 lr: 0.000884 loss: 3.6347 (3.6583) grad_norm: 1.0358 (inf) time: 0.5014 [2021-03-25 15:21:20 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 860/1251] eta: 0:03:19 lr: 0.000884 loss: 3.6347 (3.6579) grad_norm: 1.0388 (inf) time: 0.5078 [2021-03-25 15:21:25 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 870/1251] eta: 0:03:14 lr: 0.000884 loss: 3.4331 (3.6557) grad_norm: 1.0664 (inf) time: 0.5084 [2021-03-25 15:21:30 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 880/1251] eta: 0:03:09 lr: 0.000884 loss: 3.3629 (3.6553) grad_norm: 1.0664 (inf) time: 0.5103 [2021-03-25 15:21:35 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 890/1251] eta: 0:03:04 lr: 0.000884 loss: 3.7143 (3.6571) grad_norm: 1.0548 (inf) time: 0.5108 [2021-03-25 15:21:40 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 900/1251] eta: 0:02:59 lr: 0.000884 loss: 3.9500 (3.6603) grad_norm: 1.0287 (inf) time: 0.5061 [2021-03-25 15:21:45 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 910/1251] eta: 0:02:54 lr: 0.000884 loss: 3.9381 (3.6620) grad_norm: 1.0318 (inf) time: 0.5036 [2021-03-25 15:21:50 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 920/1251] eta: 0:02:49 lr: 0.000884 loss: 3.9327 (3.6641) grad_norm: 1.0159 (inf) time: 0.5066 [2021-03-25 15:21:55 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 930/1251] eta: 0:02:43 lr: 0.000884 loss: 3.7179 (3.6625) grad_norm: 1.0637 (inf) time: 0.5135 [2021-03-25 15:22:01 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 940/1251] eta: 0:02:38 lr: 0.000884 loss: 3.7123 (3.6630) grad_norm: 1.0637 (inf) time: 0.5110 [2021-03-25 15:22:06 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 950/1251] eta: 0:02:33 lr: 0.000884 loss: 3.6431 (3.6608) grad_norm: 1.0497 (inf) time: 0.5038 [2021-03-25 15:22:11 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 960/1251] eta: 0:02:28 lr: 0.000884 loss: 3.3729 (3.6591) grad_norm: 1.0497 (inf) time: 0.5043 [2021-03-25 15:22:16 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 970/1251] eta: 0:02:23 lr: 0.000884 loss: 3.5955 (3.6591) grad_norm: 1.0344 (inf) time: 0.5045 [2021-03-25 15:22:21 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 980/1251] eta: 0:02:18 lr: 0.000884 loss: 3.6465 (3.6575) grad_norm: 1.0500 (inf) time: 0.4993 [2021-03-25 15:22:26 swin_small_patch4_window7_224] INFO: Epoch: [66] [ 990/1251] eta: 0:02:13 lr: 0.000884 loss: 3.3978 (3.6564) grad_norm: 1.0572 (inf) time: 0.5001 [2021-03-25 15:22:31 swin_small_patch4_window7_224] INFO: Epoch: [66] [1000/1251] eta: 0:02:08 lr: 0.000884 loss: 3.9761 (3.6591) grad_norm: 1.0722 (inf) time: 0.5025 [2021-03-25 15:22:36 swin_small_patch4_window7_224] INFO: Epoch: [66] [1010/1251] eta: 0:02:03 lr: 0.000884 loss: 3.9769 (3.6608) grad_norm: 1.0946 (inf) time: 0.5111 [2021-03-25 15:22:41 swin_small_patch4_window7_224] INFO: Epoch: [66] [1020/1251] eta: 0:01:57 lr: 0.000884 loss: 3.8725 (3.6603) grad_norm: 1.0913 (inf) time: 0.5143 [2021-03-25 15:22:46 swin_small_patch4_window7_224] INFO: Epoch: [66] [1030/1251] eta: 0:01:52 lr: 0.000884 loss: 3.8725 (3.6634) grad_norm: 1.0504 (inf) time: 0.5053 [2021-03-25 15:22:51 swin_small_patch4_window7_224] INFO: Epoch: [66] [1040/1251] eta: 0:01:47 lr: 0.000884 loss: 3.8297 (3.6624) grad_norm: 1.0233 (inf) time: 0.5029 [2021-03-25 15:22:56 swin_small_patch4_window7_224] INFO: Epoch: [66] [1050/1251] eta: 0:01:42 lr: 0.000884 loss: 3.7981 (3.6624) grad_norm: 0.9620 (inf) time: 0.5095 [2021-03-25 15:23:01 swin_small_patch4_window7_224] INFO: Epoch: [66] [1060/1251] eta: 0:01:37 lr: 0.000884 loss: 3.8331 (3.6639) grad_norm: 1.0440 (inf) time: 0.5072 [2021-03-25 15:23:06 swin_small_patch4_window7_224] INFO: Epoch: [66] [1070/1251] eta: 0:01:32 lr: 0.000884 loss: 3.8731 (3.6624) grad_norm: 1.0792 (inf) time: 0.5053 [2021-03-25 15:23:11 swin_small_patch4_window7_224] INFO: Epoch: [66] [1080/1251] eta: 0:01:27 lr: 0.000884 loss: 3.5133 (3.6604) grad_norm: 1.0792 (inf) time: 0.5087 [2021-03-25 15:23:16 swin_small_patch4_window7_224] INFO: Epoch: [66] [1090/1251] eta: 0:01:22 lr: 0.000884 loss: 3.5133 (3.6587) grad_norm: 1.0179 (inf) time: 0.5018 [2021-03-25 15:23:21 swin_small_patch4_window7_224] INFO: Epoch: [66] [1100/1251] eta: 0:01:17 lr: 0.000883 loss: 3.6813 (3.6600) grad_norm: 0.9946 (inf) time: 0.5038 [2021-03-25 15:23:27 swin_small_patch4_window7_224] INFO: Epoch: [66] [1110/1251] eta: 0:01:11 lr: 0.000883 loss: 3.8040 (3.6614) grad_norm: 0.9946 (inf) time: 0.5095 [2021-03-25 15:23:32 swin_small_patch4_window7_224] INFO: Epoch: [66] [1120/1251] eta: 0:01:06 lr: 0.000883 loss: 3.8040 (3.6621) grad_norm: 0.9768 (inf) time: 0.5052 [2021-03-25 15:23:37 swin_small_patch4_window7_224] INFO: Epoch: [66] [1130/1251] eta: 0:01:01 lr: 0.000883 loss: 3.7339 (3.6629) grad_norm: 0.9937 (inf) time: 0.5055 [2021-03-25 15:23:42 swin_small_patch4_window7_224] INFO: Epoch: [66] [1140/1251] eta: 0:00:56 lr: 0.000883 loss: 3.7194 (3.6621) grad_norm: 1.0419 (inf) time: 0.5082 [2021-03-25 15:23:47 swin_small_patch4_window7_224] INFO: Epoch: [66] [1150/1251] eta: 0:00:51 lr: 0.000883 loss: 3.5641 (3.6615) grad_norm: 1.0323 (inf) time: 0.5074 [2021-03-25 15:23:52 swin_small_patch4_window7_224] INFO: Epoch: [66] [1160/1251] eta: 0:00:46 lr: 0.000883 loss: 3.6245 (3.6600) grad_norm: 1.1110 (inf) time: 0.5082 [2021-03-25 15:23:57 swin_small_patch4_window7_224] INFO: Epoch: [66] [1170/1251] eta: 0:00:41 lr: 0.000883 loss: 3.6691 (3.6596) grad_norm: 1.1246 (inf) time: 0.5039 [2021-03-25 15:24:02 swin_small_patch4_window7_224] INFO: Epoch: [66] [1180/1251] eta: 0:00:36 lr: 0.000883 loss: 3.7667 (3.6608) grad_norm: 1.0776 (inf) time: 0.5040 [2021-03-25 15:24:07 swin_small_patch4_window7_224] INFO: Epoch: [66] [1190/1251] eta: 0:00:31 lr: 0.000883 loss: 3.7587 (3.6614) grad_norm: 1.0345 (inf) time: 0.5049 [2021-03-25 15:24:12 swin_small_patch4_window7_224] INFO: Epoch: [66] [1200/1251] eta: 0:00:25 lr: 0.000883 loss: 3.7559 (3.6605) grad_norm: 0.9613 (inf) time: 0.5044 [2021-03-25 15:24:17 swin_small_patch4_window7_224] INFO: Epoch: [66] [1210/1251] eta: 0:00:20 lr: 0.000883 loss: 3.7839 (3.6619) grad_norm: 0.9470 (inf) time: 0.5034 [2021-03-25 15:24:22 swin_small_patch4_window7_224] INFO: Epoch: [66] [1220/1251] eta: 0:00:15 lr: 0.000883 loss: 3.7867 (3.6623) grad_norm: 0.9842 (inf) time: 0.4997 [2021-03-25 15:24:27 swin_small_patch4_window7_224] INFO: Epoch: [66] [1230/1251] eta: 0:00:10 lr: 0.000883 loss: 3.6858 (3.6625) grad_norm: 1.0282 (inf) time: 0.5063 [2021-03-25 15:24:32 swin_small_patch4_window7_224] INFO: Epoch: [66] [1240/1251] eta: 0:00:05 lr: 0.000883 loss: 3.7198 (3.6628) grad_norm: 1.0282 (inf) time: 0.5071 [2021-03-25 15:24:37 swin_small_patch4_window7_224] INFO: Epoch: [66] [1250/1251] eta: 0:00:00 lr: 0.000883 loss: 3.9277 (3.6649) grad_norm: 1.0248 (inf) time: 0.4956 [2021-03-25 15:24:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.9354 (0.9354) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-25 15:24:44 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.1911 (1.1318) acc1: 71.8750 (72.3011) acc5: 92.1875 (92.3295) [2021-03-25 15:24:46 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1315 (1.0936) acc1: 73.4375 (74.4792) acc5: 92.1875 (92.1875) [2021-03-25 15:24:48 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0531 (1.0923) acc1: 76.5625 (74.4456) acc5: 92.1875 (92.4395) [2021-03-25 15:24:50 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0679 (1.1196) acc1: 75.0000 (73.7805) acc5: 92.1875 (92.3018) [2021-03-25 15:24:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0755 (1.1145) acc1: 73.4375 (73.8240) acc5: 92.1875 (92.3520) [2021-03-25 15:24:55 swin_small_patch4_window7_224] INFO: * Acc@1 74.156 Acc@5 92.364 loss 1.097 [2021-03-25 15:24:55 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.2% [2021-03-25 15:24:55 swin_small_patch4_window7_224] INFO: Max accuracy: 74.17% [2021-03-25 15:24:59 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 0/1251] eta: 1:26:09 lr: 0.000883 loss: 3.8387 (3.8387) grad_norm: 1.1883 (1.1883) time: 4.1320 [2021-03-25 15:25:04 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 10/1251] eta: 0:17:24 lr: 0.000883 loss: 3.8387 (3.8232) grad_norm: 1.0914 (1.1090) time: 0.8419 [2021-03-25 15:25:10 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 20/1251] eta: 0:14:02 lr: 0.000883 loss: 3.6646 (3.6904) grad_norm: 1.0914 (1.1097) time: 0.5120 [2021-03-25 15:25:15 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 30/1251] eta: 0:12:49 lr: 0.000883 loss: 3.7320 (3.7112) grad_norm: 1.0438 (1.0962) time: 0.5138 [2021-03-25 15:25:20 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 40/1251] eta: 0:12:09 lr: 0.000883 loss: 3.6314 (3.6322) grad_norm: 1.1001 (1.1053) time: 0.5164 [2021-03-25 15:25:25 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 50/1251] eta: 0:11:41 lr: 0.000883 loss: 3.5048 (3.5945) grad_norm: 1.1007 (1.0986) time: 0.5131 [2021-03-25 15:25:30 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 60/1251] eta: 0:11:20 lr: 0.000883 loss: 3.8158 (3.6490) grad_norm: 1.0555 (1.0890) time: 0.5079 [2021-03-25 15:25:35 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 70/1251] eta: 0:11:04 lr: 0.000883 loss: 3.8789 (3.6550) grad_norm: 1.0391 (1.0889) time: 0.5066 [2021-03-25 15:25:40 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 80/1251] eta: 0:10:50 lr: 0.000883 loss: 3.7344 (3.6459) grad_norm: 0.9956 (1.0776) time: 0.5062 [2021-03-25 15:25:45 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 90/1251] eta: 0:10:38 lr: 0.000883 loss: 3.3922 (3.6351) grad_norm: 0.9956 (1.0826) time: 0.5055 [2021-03-25 15:25:50 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 100/1251] eta: 0:10:27 lr: 0.000883 loss: 3.3834 (3.6072) grad_norm: 1.0965 (1.0824) time: 0.5035 [2021-03-25 15:25:55 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 110/1251] eta: 0:10:18 lr: 0.000883 loss: 3.5750 (3.6157) grad_norm: 1.0858 (1.0802) time: 0.5062 [2021-03-25 15:26:00 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 120/1251] eta: 0:10:09 lr: 0.000883 loss: 3.7390 (3.6236) grad_norm: 1.0693 (1.0815) time: 0.5055 [2021-03-25 15:26:05 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 130/1251] eta: 0:10:00 lr: 0.000883 loss: 3.7293 (3.6034) grad_norm: 1.0636 (1.0808) time: 0.5033 [2021-03-25 15:26:10 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 140/1251] eta: 0:09:53 lr: 0.000883 loss: 3.5541 (3.5945) grad_norm: 1.0358 (1.0744) time: 0.5071 [2021-03-25 15:26:16 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 150/1251] eta: 0:09:46 lr: 0.000883 loss: 3.6420 (3.5934) grad_norm: 1.0362 (1.0790) time: 0.5102 [2021-03-25 15:26:21 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 160/1251] eta: 0:09:39 lr: 0.000883 loss: 3.6342 (3.5889) grad_norm: 1.0830 (1.0786) time: 0.5091 [2021-03-25 15:26:26 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 170/1251] eta: 0:09:32 lr: 0.000883 loss: 3.5479 (3.5812) grad_norm: 1.0559 (1.0769) time: 0.5046 [2021-03-25 15:26:31 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 180/1251] eta: 0:09:25 lr: 0.000883 loss: 3.6865 (3.5973) grad_norm: 1.0559 (1.0749) time: 0.5048 [2021-03-25 15:26:36 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 190/1251] eta: 0:09:19 lr: 0.000883 loss: 3.7873 (3.5975) grad_norm: 1.0697 (1.0776) time: 0.5085 [2021-03-25 15:26:41 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 200/1251] eta: 0:09:13 lr: 0.000883 loss: 4.0016 (3.6213) grad_norm: 1.0360 (1.0758) time: 0.5115 [2021-03-25 15:26:46 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 210/1251] eta: 0:09:06 lr: 0.000883 loss: 3.7277 (3.6083) grad_norm: 0.9950 (1.0763) time: 0.5074 [2021-03-25 15:26:51 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 220/1251] eta: 0:09:00 lr: 0.000882 loss: 3.5585 (3.6096) grad_norm: 0.9773 (1.0714) time: 0.5053 [2021-03-25 15:26:56 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 230/1251] eta: 0:08:54 lr: 0.000882 loss: 3.8636 (3.6216) grad_norm: 0.9773 (1.0700) time: 0.5080 [2021-03-25 15:27:01 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 240/1251] eta: 0:08:49 lr: 0.000882 loss: 3.7578 (3.6175) grad_norm: 1.0095 (1.0661) time: 0.5114 [2021-03-25 15:27:06 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 250/1251] eta: 0:08:43 lr: 0.000882 loss: 3.3664 (3.6080) grad_norm: 1.0095 (1.0672) time: 0.5076 [2021-03-25 15:27:12 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 260/1251] eta: 0:08:37 lr: 0.000882 loss: 3.3664 (3.6060) grad_norm: 1.0673 (1.0690) time: 0.5088 [2021-03-25 15:27:17 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 270/1251] eta: 0:08:31 lr: 0.000882 loss: 3.7727 (3.6178) grad_norm: 1.0502 (1.0674) time: 0.5120 [2021-03-25 15:27:22 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 280/1251] eta: 0:08:25 lr: 0.000882 loss: 4.0683 (3.6322) grad_norm: 1.0688 (1.0687) time: 0.5048 [2021-03-25 15:27:27 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 290/1251] eta: 0:08:20 lr: 0.000882 loss: 3.8076 (3.6318) grad_norm: 1.0718 (1.0674) time: 0.5067 [2021-03-25 15:27:32 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 300/1251] eta: 0:08:14 lr: 0.000882 loss: 3.5826 (3.6290) grad_norm: 0.9968 (1.0644) time: 0.5073 [2021-03-25 15:27:37 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 310/1251] eta: 0:08:08 lr: 0.000882 loss: 3.7696 (3.6303) grad_norm: 1.0560 (1.0656) time: 0.5031 [2021-03-25 15:27:42 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 320/1251] eta: 0:08:03 lr: 0.000882 loss: 3.8280 (3.6308) grad_norm: 1.0560 (1.0654) time: 0.5037 [2021-03-25 15:27:47 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 330/1251] eta: 0:07:57 lr: 0.000882 loss: 3.5118 (3.6306) grad_norm: 1.0266 (1.0654) time: 0.5014 [2021-03-25 15:27:52 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 340/1251] eta: 0:07:52 lr: 0.000882 loss: 3.4986 (3.6304) grad_norm: 1.0278 (1.0657) time: 0.5052 [2021-03-25 15:27:57 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 350/1251] eta: 0:07:46 lr: 0.000882 loss: 3.6499 (3.6313) grad_norm: 1.0476 (1.0659) time: 0.5065 [2021-03-25 15:28:02 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 360/1251] eta: 0:07:41 lr: 0.000882 loss: 3.6834 (3.6315) grad_norm: 1.0419 (1.0660) time: 0.5020 [2021-03-25 15:28:07 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 370/1251] eta: 0:07:35 lr: 0.000882 loss: 3.5873 (3.6288) grad_norm: 1.0419 (1.0672) time: 0.4974 [2021-03-25 15:28:12 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 380/1251] eta: 0:07:29 lr: 0.000882 loss: 3.4227 (3.6261) grad_norm: 1.0228 (1.0653) time: 0.4964 [2021-03-25 15:28:17 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 390/1251] eta: 0:07:24 lr: 0.000882 loss: 3.6925 (3.6292) grad_norm: 1.0172 (1.0656) time: 0.5066 [2021-03-25 15:28:22 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 400/1251] eta: 0:07:19 lr: 0.000882 loss: 3.6925 (3.6238) grad_norm: 1.0387 (1.0656) time: 0.5081 [2021-03-25 15:28:27 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 410/1251] eta: 0:07:13 lr: 0.000882 loss: 3.5562 (3.6267) grad_norm: 1.0283 (1.0656) time: 0.5014 [2021-03-25 15:28:32 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 420/1251] eta: 0:07:08 lr: 0.000882 loss: 3.7689 (3.6297) grad_norm: 1.0771 (1.0661) time: 0.5023 [2021-03-25 15:28:37 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 430/1251] eta: 0:07:03 lr: 0.000882 loss: 3.5366 (3.6237) grad_norm: 1.0771 (1.0659) time: 0.5141 [2021-03-25 15:28:42 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 440/1251] eta: 0:06:57 lr: 0.000882 loss: 3.5319 (3.6256) grad_norm: 1.0441 (1.0669) time: 0.5125 [2021-03-25 15:28:48 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 450/1251] eta: 0:06:52 lr: 0.000882 loss: 3.5983 (3.6225) grad_norm: 1.0055 (1.0663) time: 0.5117 [2021-03-25 15:28:53 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 460/1251] eta: 0:06:47 lr: 0.000882 loss: 3.8211 (3.6259) grad_norm: 1.0423 (1.0659) time: 0.5088 [2021-03-25 15:28:58 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 470/1251] eta: 0:06:41 lr: 0.000882 loss: 3.9580 (3.6296) grad_norm: 1.0423 (1.0655) time: 0.5014 [2021-03-25 15:29:03 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 480/1251] eta: 0:06:36 lr: 0.000882 loss: 3.7840 (3.6296) grad_norm: 1.0473 (1.0654) time: 0.5038 [2021-03-25 15:29:08 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 490/1251] eta: 0:06:31 lr: 0.000882 loss: 3.7786 (3.6314) grad_norm: 1.0482 (1.0656) time: 0.5093 [2021-03-25 15:29:13 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 500/1251] eta: 0:06:26 lr: 0.000882 loss: 3.6954 (3.6325) grad_norm: 1.0181 (1.0642) time: 0.5095 [2021-03-25 15:29:18 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 510/1251] eta: 0:06:21 lr: 0.000882 loss: 3.7398 (3.6378) grad_norm: 0.9647 (1.0627) time: 0.5094 [2021-03-25 15:29:23 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 520/1251] eta: 0:06:15 lr: 0.000882 loss: 3.7398 (3.6385) grad_norm: 0.9658 (1.0619) time: 0.5085 [2021-03-25 15:29:28 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 530/1251] eta: 0:06:10 lr: 0.000882 loss: 3.6257 (3.6383) grad_norm: 1.0054 (1.0615) time: 0.5052 [2021-03-25 15:29:33 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 540/1251] eta: 0:06:05 lr: 0.000882 loss: 3.6435 (3.6391) grad_norm: 1.0191 (1.0607) time: 0.5109 [2021-03-25 15:29:39 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 550/1251] eta: 0:06:00 lr: 0.000882 loss: 3.6532 (3.6427) grad_norm: 1.0191 (1.0608) time: 0.5220 [2021-03-25 15:29:44 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 560/1251] eta: 0:05:55 lr: 0.000882 loss: 3.6438 (3.6369) grad_norm: 1.1251 (1.0627) time: 0.5208 [2021-03-25 15:29:49 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 570/1251] eta: 0:05:49 lr: 0.000882 loss: 3.6040 (3.6386) grad_norm: 1.1000 (1.0622) time: 0.5068 [2021-03-25 15:29:54 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 580/1251] eta: 0:05:44 lr: 0.000882 loss: 3.8615 (3.6399) grad_norm: 1.0125 (1.0619) time: 0.5067 [2021-03-25 15:29:59 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 590/1251] eta: 0:05:39 lr: 0.000881 loss: 3.7235 (3.6387) grad_norm: 1.0162 (1.0616) time: 0.5093 [2021-03-25 15:30:04 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 600/1251] eta: 0:05:34 lr: 0.000881 loss: 3.7503 (3.6425) grad_norm: 1.0264 (1.0621) time: 0.5076 [2021-03-25 15:30:09 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 610/1251] eta: 0:05:29 lr: 0.000881 loss: 3.9290 (3.6418) grad_norm: 1.1214 (1.0635) time: 0.5082 [2021-03-25 15:30:14 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 620/1251] eta: 0:05:24 lr: 0.000881 loss: 3.4324 (3.6373) grad_norm: 1.1135 (1.0638) time: 0.5087 [2021-03-25 15:30:19 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 630/1251] eta: 0:05:18 lr: 0.000881 loss: 3.5934 (3.6356) grad_norm: 1.0058 (1.0627) time: 0.5052 [2021-03-25 15:30:24 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 640/1251] eta: 0:05:13 lr: 0.000881 loss: 3.6617 (3.6371) grad_norm: 0.9806 (1.0623) time: 0.5017 [2021-03-25 15:30:29 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 650/1251] eta: 0:05:08 lr: 0.000881 loss: 3.8634 (3.6395) grad_norm: 1.0095 (1.0621) time: 0.5016 [2021-03-25 15:30:34 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 660/1251] eta: 0:05:03 lr: 0.000881 loss: 3.8959 (3.6437) grad_norm: 1.0319 (1.0619) time: 0.5016 [2021-03-25 15:30:39 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 670/1251] eta: 0:04:57 lr: 0.000881 loss: 3.7231 (3.6407) grad_norm: 1.0486 (1.0627) time: 0.5053 [2021-03-25 15:30:44 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 680/1251] eta: 0:04:52 lr: 0.000881 loss: 3.7436 (3.6423) grad_norm: 1.0486 (1.0626) time: 0.5049 [2021-03-25 15:30:49 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 690/1251] eta: 0:04:47 lr: 0.000881 loss: 3.8240 (3.6448) grad_norm: 0.9709 (1.0615) time: 0.5033 [2021-03-25 15:30:54 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 700/1251] eta: 0:04:42 lr: 0.000881 loss: 3.5352 (3.6398) grad_norm: 0.9895 (1.0615) time: 0.5058 [2021-03-25 15:30:59 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 710/1251] eta: 0:04:37 lr: 0.000881 loss: 3.5352 (3.6418) grad_norm: 1.0413 (1.0612) time: 0.5042 [2021-03-25 15:31:05 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 720/1251] eta: 0:04:31 lr: 0.000881 loss: 3.8587 (3.6407) grad_norm: 1.0950 (1.0627) time: 0.5038 [2021-03-25 15:31:10 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 730/1251] eta: 0:04:26 lr: 0.000881 loss: 3.7971 (3.6406) grad_norm: 1.0875 (1.0620) time: 0.5026 [2021-03-25 15:31:15 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 740/1251] eta: 0:04:21 lr: 0.000881 loss: 3.5887 (3.6382) grad_norm: 0.9878 (1.0618) time: 0.5185 [2021-03-25 15:31:20 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 750/1251] eta: 0:04:16 lr: 0.000881 loss: 3.4453 (3.6368) grad_norm: 0.9622 (1.0604) time: 0.5243 [2021-03-25 15:31:25 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 760/1251] eta: 0:04:11 lr: 0.000881 loss: 3.8103 (3.6375) grad_norm: 0.9683 (1.0600) time: 0.5142 [2021-03-25 15:31:30 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 770/1251] eta: 0:04:06 lr: 0.000881 loss: 3.8103 (3.6385) grad_norm: 1.0418 (1.0600) time: 0.5191 [2021-03-25 15:31:35 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 780/1251] eta: 0:04:01 lr: 0.000881 loss: 3.7513 (3.6382) grad_norm: 1.0338 (1.0597) time: 0.5138 [2021-03-25 15:31:41 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 790/1251] eta: 0:03:56 lr: 0.000881 loss: 3.7698 (3.6401) grad_norm: 1.0648 (1.0607) time: 0.5089 [2021-03-25 15:31:46 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 800/1251] eta: 0:03:51 lr: 0.000881 loss: 3.5875 (3.6370) grad_norm: 1.0621 (1.0600) time: 0.5092 [2021-03-25 15:31:51 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 810/1251] eta: 0:03:45 lr: 0.000881 loss: 3.5579 (3.6382) grad_norm: 0.9908 (1.0597) time: 0.5052 [2021-03-25 15:31:56 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 820/1251] eta: 0:03:40 lr: 0.000881 loss: 4.0720 (3.6417) grad_norm: 1.0120 (1.0596) time: 0.5051 [2021-03-25 15:32:01 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 830/1251] eta: 0:03:35 lr: 0.000881 loss: 4.0720 (3.6436) grad_norm: 1.0170 (1.0596) time: 0.5017 [2021-03-25 15:32:06 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 840/1251] eta: 0:03:30 lr: 0.000881 loss: 3.8228 (3.6427) grad_norm: 1.0436 (1.0596) time: 0.4951 [2021-03-25 15:32:11 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 850/1251] eta: 0:03:25 lr: 0.000881 loss: 3.8140 (3.6441) grad_norm: 1.0436 (1.0593) time: 0.5036 [2021-03-25 15:32:16 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 860/1251] eta: 0:03:20 lr: 0.000881 loss: 3.9386 (3.6485) grad_norm: 1.0209 (1.0595) time: 0.5136 [2021-03-25 15:32:21 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 870/1251] eta: 0:03:14 lr: 0.000881 loss: 3.9657 (3.6518) grad_norm: 1.0262 (1.0593) time: 0.5093 [2021-03-25 15:32:26 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 880/1251] eta: 0:03:09 lr: 0.000881 loss: 3.8628 (3.6502) grad_norm: 1.0329 (1.0595) time: 0.5022 [2021-03-25 15:32:31 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 890/1251] eta: 0:03:04 lr: 0.000881 loss: 3.6667 (3.6496) grad_norm: 1.0407 (1.0594) time: 0.5018 [2021-03-25 15:32:36 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 900/1251] eta: 0:02:59 lr: 0.000881 loss: 3.7830 (3.6521) grad_norm: 1.0697 (1.0602) time: 0.5086 [2021-03-25 15:32:41 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 910/1251] eta: 0:02:54 lr: 0.000881 loss: 3.9204 (3.6524) grad_norm: 1.0461 (1.0600) time: 0.5083 [2021-03-25 15:32:46 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 920/1251] eta: 0:02:49 lr: 0.000881 loss: 3.6955 (3.6513) grad_norm: 0.9963 (1.0595) time: 0.5030 [2021-03-25 15:32:51 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 930/1251] eta: 0:02:44 lr: 0.000881 loss: 3.5158 (3.6500) grad_norm: 1.0174 (1.0602) time: 0.5017 [2021-03-25 15:32:56 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 940/1251] eta: 0:02:39 lr: 0.000881 loss: 3.7312 (3.6511) grad_norm: 1.0241 (1.0595) time: 0.5101 [2021-03-25 15:33:01 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 950/1251] eta: 0:02:33 lr: 0.000881 loss: 3.6822 (3.6483) grad_norm: 1.0241 (1.0595) time: 0.5121 [2021-03-25 15:33:07 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 960/1251] eta: 0:02:28 lr: 0.000880 loss: 3.5853 (3.6477) grad_norm: 1.0565 (1.0598) time: 0.5053 [2021-03-25 15:33:12 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 970/1251] eta: 0:02:23 lr: 0.000880 loss: 3.6619 (3.6458) grad_norm: 1.0550 (1.0597) time: 0.5067 [2021-03-25 15:33:17 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 980/1251] eta: 0:02:18 lr: 0.000880 loss: 3.6619 (3.6454) grad_norm: 1.0550 (1.0600) time: 0.5095 [2021-03-25 15:33:22 swin_small_patch4_window7_224] INFO: Epoch: [67] [ 990/1251] eta: 0:02:13 lr: 0.000880 loss: 3.9995 (3.6483) grad_norm: 1.0396 (1.0598) time: 0.5098 [2021-03-25 15:33:27 swin_small_patch4_window7_224] INFO: Epoch: [67] [1000/1251] eta: 0:02:08 lr: 0.000880 loss: 3.9353 (3.6480) grad_norm: 1.0134 (1.0598) time: 0.5076 [2021-03-25 15:33:32 swin_small_patch4_window7_224] INFO: Epoch: [67] [1010/1251] eta: 0:02:03 lr: 0.000880 loss: 3.7479 (3.6493) grad_norm: 0.9847 (1.0594) time: 0.4997 [2021-03-25 15:33:37 swin_small_patch4_window7_224] INFO: Epoch: [67] [1020/1251] eta: 0:01:57 lr: 0.000880 loss: 3.7892 (3.6513) grad_norm: 0.9847 (1.0592) time: 0.4972 [2021-03-25 15:33:42 swin_small_patch4_window7_224] INFO: Epoch: [67] [1030/1251] eta: 0:01:52 lr: 0.000880 loss: 3.9574 (3.6550) grad_norm: 1.0651 (1.0599) time: 0.5018 [2021-03-25 15:33:47 swin_small_patch4_window7_224] INFO: Epoch: [67] [1040/1251] eta: 0:01:47 lr: 0.000880 loss: 3.8728 (3.6549) grad_norm: 1.0308 (1.0597) time: 0.5059 [2021-03-25 15:33:52 swin_small_patch4_window7_224] INFO: Epoch: [67] [1050/1251] eta: 0:01:42 lr: 0.000880 loss: 3.6809 (3.6550) grad_norm: 1.0098 (1.0592) time: 0.5157 [2021-03-25 15:33:57 swin_small_patch4_window7_224] INFO: Epoch: [67] [1060/1251] eta: 0:01:37 lr: 0.000880 loss: 3.7670 (3.6536) grad_norm: 1.0226 (1.0592) time: 0.5188 [2021-03-25 15:34:02 swin_small_patch4_window7_224] INFO: Epoch: [67] [1070/1251] eta: 0:01:32 lr: 0.000880 loss: 3.5545 (3.6530) grad_norm: 1.0226 (1.0593) time: 0.5099 [2021-03-25 15:34:07 swin_small_patch4_window7_224] INFO: Epoch: [67] [1080/1251] eta: 0:01:27 lr: 0.000880 loss: 3.7022 (3.6540) grad_norm: 1.0131 (1.0588) time: 0.5052 [2021-03-25 15:34:13 swin_small_patch4_window7_224] INFO: Epoch: [67] [1090/1251] eta: 0:01:22 lr: 0.000880 loss: 3.8015 (3.6533) grad_norm: 1.0043 (1.0587) time: 0.5111 [2021-03-25 15:34:18 swin_small_patch4_window7_224] INFO: Epoch: [67] [1100/1251] eta: 0:01:17 lr: 0.000880 loss: 3.9461 (3.6571) grad_norm: 1.0550 (1.0591) time: 0.5072 [2021-03-25 15:34:23 swin_small_patch4_window7_224] INFO: Epoch: [67] [1110/1251] eta: 0:01:11 lr: 0.000880 loss: 4.0385 (3.6588) grad_norm: 1.0324 (1.0589) time: 0.5024 [2021-03-25 15:34:28 swin_small_patch4_window7_224] INFO: Epoch: [67] [1120/1251] eta: 0:01:06 lr: 0.000880 loss: 3.7649 (3.6586) grad_norm: 1.0324 (1.0589) time: 0.5058 [2021-03-25 15:34:33 swin_small_patch4_window7_224] INFO: Epoch: [67] [1130/1251] eta: 0:01:01 lr: 0.000880 loss: 3.5857 (3.6583) grad_norm: 1.0477 (1.0584) time: 0.5024 [2021-03-25 15:34:38 swin_small_patch4_window7_224] INFO: Epoch: [67] [1140/1251] eta: 0:00:56 lr: 0.000880 loss: 3.8411 (3.6593) grad_norm: 1.0345 (1.0586) time: 0.5020 [2021-03-25 15:34:43 swin_small_patch4_window7_224] INFO: Epoch: [67] [1150/1251] eta: 0:00:51 lr: 0.000880 loss: 3.8411 (3.6579) grad_norm: 1.0687 (1.0590) time: 0.5038 [2021-03-25 15:34:48 swin_small_patch4_window7_224] INFO: Epoch: [67] [1160/1251] eta: 0:00:46 lr: 0.000880 loss: 3.5148 (3.6582) grad_norm: 1.0551 (1.0587) time: 0.5053 [2021-03-25 15:34:53 swin_small_patch4_window7_224] INFO: Epoch: [67] [1170/1251] eta: 0:00:41 lr: 0.000880 loss: 3.4950 (3.6554) grad_norm: 1.0184 (1.0583) time: 0.5070 [2021-03-25 15:34:58 swin_small_patch4_window7_224] INFO: Epoch: [67] [1180/1251] eta: 0:00:36 lr: 0.000880 loss: 3.5228 (3.6553) grad_norm: 1.0446 (1.0587) time: 0.5033 [2021-03-25 15:35:03 swin_small_patch4_window7_224] INFO: Epoch: [67] [1190/1251] eta: 0:00:31 lr: 0.000880 loss: 3.7518 (3.6570) grad_norm: 1.0484 (1.0586) time: 0.5043 [2021-03-25 15:35:08 swin_small_patch4_window7_224] INFO: Epoch: [67] [1200/1251] eta: 0:00:26 lr: 0.000880 loss: 3.7418 (3.6548) grad_norm: 1.0522 (1.0585) time: 0.5050 [2021-03-25 15:35:13 swin_small_patch4_window7_224] INFO: Epoch: [67] [1210/1251] eta: 0:00:20 lr: 0.000880 loss: 3.6080 (3.6539) grad_norm: 1.0777 (1.0586) time: 0.5071 [2021-03-25 15:35:18 swin_small_patch4_window7_224] INFO: Epoch: [67] [1220/1251] eta: 0:00:15 lr: 0.000880 loss: 3.8806 (3.6558) grad_norm: 1.0590 (1.0586) time: 0.5098 [2021-03-25 15:35:23 swin_small_patch4_window7_224] INFO: Epoch: [67] [1230/1251] eta: 0:00:10 lr: 0.000880 loss: 3.7861 (3.6560) grad_norm: 1.0248 (1.0587) time: 0.5058 [2021-03-25 15:35:28 swin_small_patch4_window7_224] INFO: Epoch: [67] [1240/1251] eta: 0:00:05 lr: 0.000880 loss: 3.6627 (3.6554) grad_norm: 1.1322 (1.0598) time: 0.5029 [2021-03-25 15:35:33 swin_small_patch4_window7_224] INFO: Epoch: [67] [1250/1251] eta: 0:00:00 lr: 0.000880 loss: 3.5651 (3.6540) grad_norm: 1.1365 (1.0601) time: 0.4978 [2021-03-25 15:35:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:21 loss: 1.0981 (1.0981) acc1: 70.3125 (70.3125) acc5: 92.1875 (92.1875) [2021-03-25 15:35:41 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1779 (1.1939) acc1: 71.8750 (71.0227) acc5: 92.1875 (92.1875) [2021-03-25 15:35:43 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1779 (1.1708) acc1: 73.4375 (71.6518) acc5: 92.1875 (92.1875) [2021-03-25 15:35:46 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0493 (1.1187) acc1: 75.0000 (73.4375) acc5: 92.1875 (92.2379) [2021-03-25 15:35:47 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0241 (1.1105) acc1: 75.0000 (73.5899) acc5: 92.1875 (92.3780) [2021-03-25 15:35:48 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1264 (1.1268) acc1: 73.4375 (73.2800) acc5: 92.1875 (92.1280) [2021-03-25 15:35:52 swin_small_patch4_window7_224] INFO: * Acc@1 74.284 Acc@5 92.506 loss 1.099 [2021-03-25 15:35:52 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.3% [2021-03-25 15:35:52 swin_small_patch4_window7_224] INFO: Max accuracy: 74.28% [2021-03-25 15:35:56 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 0/1251] eta: 1:31:47 lr: 0.000880 loss: 4.0933 (4.0933) grad_norm: 1.1302 (1.1302) time: 4.4022 [2021-03-25 15:36:01 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 10/1251] eta: 0:17:39 lr: 0.000880 loss: 3.6228 (3.5640) grad_norm: 1.0787 (1.0565) time: 0.8540 [2021-03-25 15:36:06 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 20/1251] eta: 0:14:06 lr: 0.000880 loss: 3.5685 (3.4677) grad_norm: 1.0230 (1.0287) time: 0.5023 [2021-03-25 15:36:11 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 30/1251] eta: 0:12:49 lr: 0.000880 loss: 3.4820 (3.5672) grad_norm: 1.0230 (1.0276) time: 0.5071 [2021-03-25 15:36:17 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 40/1251] eta: 0:12:08 lr: 0.000880 loss: 3.8174 (3.6252) grad_norm: 1.0403 (1.0338) time: 0.5104 [2021-03-25 15:36:22 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 50/1251] eta: 0:11:38 lr: 0.000880 loss: 3.7424 (3.5941) grad_norm: 1.0652 (1.0531) time: 0.5066 [2021-03-25 15:36:27 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 60/1251] eta: 0:11:15 lr: 0.000880 loss: 3.3804 (3.5658) grad_norm: 1.0349 (1.0464) time: 0.4977 [2021-03-25 15:36:32 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 70/1251] eta: 0:10:59 lr: 0.000880 loss: 3.5136 (3.5864) grad_norm: 1.0263 (1.0486) time: 0.4989 [2021-03-25 15:36:37 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 80/1251] eta: 0:10:48 lr: 0.000879 loss: 3.7396 (3.6138) grad_norm: 1.0708 (1.0576) time: 0.5118 [2021-03-25 15:36:42 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 90/1251] eta: 0:10:37 lr: 0.000879 loss: 3.7989 (3.6201) grad_norm: 1.0765 (1.0605) time: 0.5147 [2021-03-25 15:36:47 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 100/1251] eta: 0:10:27 lr: 0.000879 loss: 3.7989 (3.6325) grad_norm: 1.0824 (1.0671) time: 0.5117 [2021-03-25 15:36:52 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 110/1251] eta: 0:10:18 lr: 0.000879 loss: 3.9716 (3.6468) grad_norm: 1.0950 (1.0684) time: 0.5098 [2021-03-25 15:36:57 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 120/1251] eta: 0:10:09 lr: 0.000879 loss: 3.7952 (3.6459) grad_norm: 1.0820 (1.0694) time: 0.5045 [2021-03-25 15:37:02 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 130/1251] eta: 0:10:01 lr: 0.000879 loss: 3.4736 (3.6298) grad_norm: 1.0820 (1.0743) time: 0.5062 [2021-03-25 15:37:07 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 140/1251] eta: 0:09:53 lr: 0.000879 loss: 3.6782 (3.6254) grad_norm: 1.0881 (1.0758) time: 0.5068 [2021-03-25 15:37:12 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 150/1251] eta: 0:09:46 lr: 0.000879 loss: 3.6845 (3.6280) grad_norm: 1.0710 (1.0760) time: 0.5058 [2021-03-25 15:37:17 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 160/1251] eta: 0:09:39 lr: 0.000879 loss: 3.7514 (3.6434) grad_norm: 1.0142 (1.0693) time: 0.5117 [2021-03-25 15:37:23 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 170/1251] eta: 0:09:32 lr: 0.000879 loss: 3.9217 (3.6458) grad_norm: 1.0227 (1.0707) time: 0.5118 [2021-03-25 15:37:28 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 180/1251] eta: 0:09:26 lr: 0.000879 loss: 3.7352 (3.6398) grad_norm: 1.0994 (1.0737) time: 0.5089 [2021-03-25 15:37:33 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 190/1251] eta: 0:09:20 lr: 0.000879 loss: 3.7352 (3.6381) grad_norm: 1.0401 (1.0703) time: 0.5111 [2021-03-25 15:37:38 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 200/1251] eta: 0:09:14 lr: 0.000879 loss: 3.6803 (3.6237) grad_norm: 1.0146 (1.0687) time: 0.5138 [2021-03-25 15:37:43 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 210/1251] eta: 0:09:08 lr: 0.000879 loss: 3.6800 (3.6248) grad_norm: 1.0238 (1.0700) time: 0.5122 [2021-03-25 15:37:48 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 220/1251] eta: 0:09:01 lr: 0.000879 loss: 3.7066 (3.6178) grad_norm: 1.0668 (1.0707) time: 0.5042 [2021-03-25 15:37:53 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 230/1251] eta: 0:08:54 lr: 0.000879 loss: 3.5251 (3.6113) grad_norm: 1.0866 (1.0729) time: 0.4976 [2021-03-25 15:37:58 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 240/1251] eta: 0:08:49 lr: 0.000879 loss: 3.3127 (3.5980) grad_norm: 1.0259 (1.0689) time: 0.5040 [2021-03-25 15:38:03 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 250/1251] eta: 0:08:43 lr: 0.000879 loss: 3.6700 (3.6100) grad_norm: 0.9799 (1.0685) time: 0.5095 [2021-03-25 15:38:08 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 260/1251] eta: 0:08:37 lr: 0.000879 loss: 3.7878 (3.6088) grad_norm: 1.1014 (1.0704) time: 0.5039 [2021-03-25 15:38:13 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 270/1251] eta: 0:08:31 lr: 0.000879 loss: 3.7445 (3.6136) grad_norm: 1.1360 (1.0723) time: 0.5026 [2021-03-25 15:38:18 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 280/1251] eta: 0:08:25 lr: 0.000879 loss: 3.6594 (3.6110) grad_norm: 1.1522 (1.0753) time: 0.5054 [2021-03-25 15:38:23 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 290/1251] eta: 0:08:20 lr: 0.000879 loss: 3.8442 (3.6171) grad_norm: 1.0992 (1.0756) time: 0.5080 [2021-03-25 15:38:28 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 300/1251] eta: 0:08:14 lr: 0.000879 loss: 3.9077 (3.6189) grad_norm: 1.0689 (1.0750) time: 0.5079 [2021-03-25 15:38:34 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 310/1251] eta: 0:08:08 lr: 0.000879 loss: 3.2213 (3.6092) grad_norm: 1.0123 (1.0721) time: 0.5070 [2021-03-25 15:38:39 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 320/1251] eta: 0:08:03 lr: 0.000879 loss: 3.4407 (3.6120) grad_norm: 1.0546 (1.0734) time: 0.5063 [2021-03-25 15:38:44 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 330/1251] eta: 0:07:57 lr: 0.000879 loss: 3.6023 (3.6092) grad_norm: 1.0562 (1.0716) time: 0.5021 [2021-03-25 15:38:49 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 340/1251] eta: 0:07:51 lr: 0.000879 loss: 3.6023 (3.6114) grad_norm: 1.0208 (1.0712) time: 0.5016 [2021-03-25 15:38:54 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 350/1251] eta: 0:07:46 lr: 0.000879 loss: 3.6392 (3.6048) grad_norm: 1.0478 (1.0707) time: 0.5094 [2021-03-25 15:38:59 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 360/1251] eta: 0:07:41 lr: 0.000879 loss: 3.6392 (3.6060) grad_norm: 1.0439 (1.0682) time: 0.5172 [2021-03-25 15:39:04 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 370/1251] eta: 0:07:36 lr: 0.000879 loss: 3.9953 (3.6168) grad_norm: 0.9916 (1.0674) time: 0.5123 [2021-03-25 15:39:09 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 380/1251] eta: 0:07:30 lr: 0.000879 loss: 4.0532 (3.6220) grad_norm: 1.0177 (1.0680) time: 0.4986 [2021-03-25 15:39:14 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 390/1251] eta: 0:07:24 lr: 0.000879 loss: 3.6938 (3.6197) grad_norm: 1.0369 (1.0693) time: 0.4997 [2021-03-25 15:39:19 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 400/1251] eta: 0:07:19 lr: 0.000879 loss: 3.6938 (3.6222) grad_norm: 1.0369 (1.0694) time: 0.5076 [2021-03-25 15:39:24 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 410/1251] eta: 0:07:14 lr: 0.000879 loss: 3.6715 (3.6207) grad_norm: 0.9900 (1.0682) time: 0.5114 [2021-03-25 15:39:29 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 420/1251] eta: 0:07:08 lr: 0.000879 loss: 3.6715 (3.6224) grad_norm: 0.9900 (1.0677) time: 0.5059 [2021-03-25 15:39:34 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 430/1251] eta: 0:07:03 lr: 0.000879 loss: 3.7299 (3.6192) grad_norm: 1.0464 (1.0677) time: 0.5028 [2021-03-25 15:39:39 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 440/1251] eta: 0:06:58 lr: 0.000879 loss: 3.4567 (3.6114) grad_norm: 1.0464 (1.0690) time: 0.5029 [2021-03-25 15:39:44 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 450/1251] eta: 0:06:52 lr: 0.000878 loss: 3.5345 (3.6108) grad_norm: 1.0804 (1.0690) time: 0.5022 [2021-03-25 15:39:49 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 460/1251] eta: 0:06:47 lr: 0.000878 loss: 3.7824 (3.6149) grad_norm: 1.0804 (1.0687) time: 0.5021 [2021-03-25 15:39:54 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 470/1251] eta: 0:06:41 lr: 0.000878 loss: 3.7824 (3.6159) grad_norm: 1.0404 (1.0683) time: 0.5021 [2021-03-25 15:39:59 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 480/1251] eta: 0:06:36 lr: 0.000878 loss: 3.6168 (3.6183) grad_norm: 1.0788 (1.0690) time: 0.5073 [2021-03-25 15:40:05 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 490/1251] eta: 0:06:31 lr: 0.000878 loss: 3.6601 (3.6231) grad_norm: 1.0378 (1.0687) time: 0.5056 [2021-03-25 15:40:09 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 500/1251] eta: 0:06:25 lr: 0.000878 loss: 3.9228 (3.6291) grad_norm: 1.0100 (1.0680) time: 0.4985 [2021-03-25 15:40:14 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 510/1251] eta: 0:06:20 lr: 0.000878 loss: 3.9228 (3.6293) grad_norm: 1.0326 (1.0675) time: 0.4973 [2021-03-25 15:40:20 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 520/1251] eta: 0:06:15 lr: 0.000878 loss: 3.7142 (3.6291) grad_norm: 1.0571 (1.0672) time: 0.5069 [2021-03-25 15:40:25 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 530/1251] eta: 0:06:10 lr: 0.000878 loss: 3.6070 (3.6320) grad_norm: 1.0163 (1.0664) time: 0.5070 [2021-03-25 15:40:30 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 540/1251] eta: 0:06:04 lr: 0.000878 loss: 3.7141 (3.6295) grad_norm: 0.9823 (1.0655) time: 0.5022 [2021-03-25 15:40:35 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 550/1251] eta: 0:05:59 lr: 0.000878 loss: 3.3782 (3.6258) grad_norm: 1.0164 (1.0663) time: 0.5143 [2021-03-25 15:40:40 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 560/1251] eta: 0:05:54 lr: 0.000878 loss: 3.8316 (3.6307) grad_norm: 1.1080 (1.0674) time: 0.5173 [2021-03-25 15:40:45 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 570/1251] eta: 0:05:49 lr: 0.000878 loss: 3.8443 (3.6296) grad_norm: 1.0535 (1.0664) time: 0.5079 [2021-03-25 15:40:50 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 580/1251] eta: 0:05:44 lr: 0.000878 loss: 3.7251 (3.6306) grad_norm: 1.0437 (1.0663) time: 0.5033 [2021-03-25 15:40:55 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 590/1251] eta: 0:05:39 lr: 0.000878 loss: 3.7644 (3.6304) grad_norm: 1.0293 (1.0655) time: 0.5063 [2021-03-25 15:41:00 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 600/1251] eta: 0:05:33 lr: 0.000878 loss: 3.7489 (3.6277) grad_norm: 0.9973 (1.0654) time: 0.5082 [2021-03-25 15:41:05 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 610/1251] eta: 0:05:28 lr: 0.000878 loss: 3.4544 (3.6250) grad_norm: 1.0017 (1.0647) time: 0.5012 [2021-03-25 15:41:10 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 620/1251] eta: 0:05:23 lr: 0.000878 loss: 3.4544 (3.6266) grad_norm: 0.9683 (inf) time: 0.5008 [2021-03-25 15:41:15 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 630/1251] eta: 0:05:18 lr: 0.000878 loss: 3.7079 (3.6292) grad_norm: 0.9632 (inf) time: 0.5021 [2021-03-25 15:41:20 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 640/1251] eta: 0:05:13 lr: 0.000878 loss: 3.7079 (3.6285) grad_norm: 1.0027 (inf) time: 0.5083 [2021-03-25 15:41:26 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 650/1251] eta: 0:05:07 lr: 0.000878 loss: 3.8048 (3.6312) grad_norm: 1.0417 (inf) time: 0.5148 [2021-03-25 15:41:31 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 660/1251] eta: 0:05:02 lr: 0.000878 loss: 3.8048 (3.6317) grad_norm: 1.0417 (inf) time: 0.5074 [2021-03-25 15:41:36 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 670/1251] eta: 0:04:57 lr: 0.000878 loss: 3.6857 (3.6304) grad_norm: 1.0744 (inf) time: 0.4986 [2021-03-25 15:41:41 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 680/1251] eta: 0:04:52 lr: 0.000878 loss: 3.7670 (3.6311) grad_norm: 1.0669 (inf) time: 0.5006 [2021-03-25 15:41:46 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 690/1251] eta: 0:04:47 lr: 0.000878 loss: 3.8714 (3.6343) grad_norm: 1.0637 (inf) time: 0.5107 [2021-03-25 15:41:51 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 700/1251] eta: 0:04:41 lr: 0.000878 loss: 3.8371 (3.6368) grad_norm: 1.0384 (inf) time: 0.5066 [2021-03-25 15:41:56 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 710/1251] eta: 0:04:36 lr: 0.000878 loss: 3.7132 (3.6373) grad_norm: 1.0066 (inf) time: 0.5051 [2021-03-25 15:42:01 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 720/1251] eta: 0:04:31 lr: 0.000878 loss: 3.5436 (3.6350) grad_norm: 0.9741 (inf) time: 0.5066 [2021-03-25 15:42:06 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 730/1251] eta: 0:04:26 lr: 0.000878 loss: 3.5793 (3.6343) grad_norm: 1.0494 (inf) time: 0.5008 [2021-03-25 15:42:11 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 740/1251] eta: 0:04:21 lr: 0.000878 loss: 3.6097 (3.6308) grad_norm: 1.0192 (inf) time: 0.5135 [2021-03-25 15:42:16 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 750/1251] eta: 0:04:16 lr: 0.000878 loss: 3.7338 (3.6312) grad_norm: 1.0004 (inf) time: 0.5196 [2021-03-25 15:42:21 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 760/1251] eta: 0:04:11 lr: 0.000878 loss: 3.7840 (3.6317) grad_norm: 0.9845 (inf) time: 0.5078 [2021-03-25 15:42:26 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 770/1251] eta: 0:04:06 lr: 0.000878 loss: 3.7724 (3.6311) grad_norm: 1.0090 (inf) time: 0.5050 [2021-03-25 15:42:31 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 780/1251] eta: 0:04:00 lr: 0.000878 loss: 3.7832 (3.6334) grad_norm: 1.0452 (inf) time: 0.5081 [2021-03-25 15:42:37 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 790/1251] eta: 0:03:55 lr: 0.000878 loss: 3.8707 (3.6355) grad_norm: 1.0671 (inf) time: 0.5080 [2021-03-25 15:42:42 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 800/1251] eta: 0:03:50 lr: 0.000878 loss: 3.8704 (3.6359) grad_norm: 1.1438 (inf) time: 0.5078 [2021-03-25 15:42:47 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 810/1251] eta: 0:03:45 lr: 0.000878 loss: 3.7655 (3.6369) grad_norm: 1.0996 (inf) time: 0.5077 [2021-03-25 15:42:52 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 820/1251] eta: 0:03:40 lr: 0.000877 loss: 3.7153 (3.6369) grad_norm: 1.0298 (inf) time: 0.5056 [2021-03-25 15:42:57 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 830/1251] eta: 0:03:35 lr: 0.000877 loss: 3.5816 (3.6345) grad_norm: 1.0567 (inf) time: 0.5144 [2021-03-25 15:43:02 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 840/1251] eta: 0:03:30 lr: 0.000877 loss: 3.5300 (3.6343) grad_norm: 1.0567 (inf) time: 0.5179 [2021-03-25 15:43:07 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 850/1251] eta: 0:03:25 lr: 0.000877 loss: 3.6169 (3.6345) grad_norm: 1.0420 (inf) time: 0.5064 [2021-03-25 15:43:12 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 860/1251] eta: 0:03:19 lr: 0.000877 loss: 3.6929 (3.6329) grad_norm: 1.0403 (inf) time: 0.5046 [2021-03-25 15:43:17 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 870/1251] eta: 0:03:14 lr: 0.000877 loss: 3.7748 (3.6320) grad_norm: 1.0528 (inf) time: 0.5052 [2021-03-25 15:43:22 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 880/1251] eta: 0:03:09 lr: 0.000877 loss: 3.7748 (3.6323) grad_norm: 1.0574 (inf) time: 0.5079 [2021-03-25 15:43:27 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 890/1251] eta: 0:03:04 lr: 0.000877 loss: 3.7550 (3.6339) grad_norm: 1.0451 (inf) time: 0.5059 [2021-03-25 15:43:32 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 900/1251] eta: 0:02:59 lr: 0.000877 loss: 3.6325 (3.6327) grad_norm: 1.1402 (inf) time: 0.5005 [2021-03-25 15:43:38 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 910/1251] eta: 0:02:54 lr: 0.000877 loss: 3.7409 (3.6341) grad_norm: 1.1183 (inf) time: 0.5093 [2021-03-25 15:43:43 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 920/1251] eta: 0:02:49 lr: 0.000877 loss: 3.6646 (3.6329) grad_norm: 1.0435 (inf) time: 0.5134 [2021-03-25 15:43:48 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 930/1251] eta: 0:02:44 lr: 0.000877 loss: 3.6003 (3.6321) grad_norm: 1.0473 (inf) time: 0.5114 [2021-03-25 15:43:53 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 940/1251] eta: 0:02:38 lr: 0.000877 loss: 3.8686 (3.6346) grad_norm: 1.0505 (inf) time: 0.5158 [2021-03-25 15:43:58 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 950/1251] eta: 0:02:33 lr: 0.000877 loss: 3.8856 (3.6352) grad_norm: 1.0471 (inf) time: 0.5117 [2021-03-25 15:44:03 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 960/1251] eta: 0:02:28 lr: 0.000877 loss: 3.8856 (3.6353) grad_norm: 1.0353 (inf) time: 0.5022 [2021-03-25 15:44:08 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 970/1251] eta: 0:02:23 lr: 0.000877 loss: 3.7462 (3.6338) grad_norm: 1.0230 (inf) time: 0.5024 [2021-03-25 15:44:13 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 980/1251] eta: 0:02:18 lr: 0.000877 loss: 3.1198 (3.6286) grad_norm: 0.9928 (inf) time: 0.5051 [2021-03-25 15:44:18 swin_small_patch4_window7_224] INFO: Epoch: [68] [ 990/1251] eta: 0:02:13 lr: 0.000877 loss: 3.5369 (3.6288) grad_norm: 1.0192 (inf) time: 0.5035 [2021-03-25 15:44:23 swin_small_patch4_window7_224] INFO: Epoch: [68] [1000/1251] eta: 0:02:08 lr: 0.000877 loss: 3.5369 (3.6262) grad_norm: 1.0151 (inf) time: 0.5040 [2021-03-25 15:44:28 swin_small_patch4_window7_224] INFO: Epoch: [68] [1010/1251] eta: 0:02:03 lr: 0.000877 loss: 3.4672 (3.6258) grad_norm: 1.0236 (inf) time: 0.5014 [2021-03-25 15:44:33 swin_small_patch4_window7_224] INFO: Epoch: [68] [1020/1251] eta: 0:01:57 lr: 0.000877 loss: 3.6786 (3.6252) grad_norm: 1.1195 (inf) time: 0.4994 [2021-03-25 15:44:38 swin_small_patch4_window7_224] INFO: Epoch: [68] [1030/1251] eta: 0:01:52 lr: 0.000877 loss: 3.6786 (3.6266) grad_norm: 1.0826 (inf) time: 0.5016 [2021-03-25 15:44:43 swin_small_patch4_window7_224] INFO: Epoch: [68] [1040/1251] eta: 0:01:47 lr: 0.000877 loss: 3.6823 (3.6262) grad_norm: 1.0399 (inf) time: 0.5036 [2021-03-25 15:44:48 swin_small_patch4_window7_224] INFO: Epoch: [68] [1050/1251] eta: 0:01:42 lr: 0.000877 loss: 3.6367 (3.6249) grad_norm: 1.0245 (inf) time: 0.5032 [2021-03-25 15:44:53 swin_small_patch4_window7_224] INFO: Epoch: [68] [1060/1251] eta: 0:01:37 lr: 0.000877 loss: 3.7179 (3.6268) grad_norm: 1.0025 (inf) time: 0.5013 [2021-03-25 15:44:58 swin_small_patch4_window7_224] INFO: Epoch: [68] [1070/1251] eta: 0:01:32 lr: 0.000877 loss: 3.4591 (3.6242) grad_norm: 1.0871 (inf) time: 0.5033 [2021-03-25 15:45:03 swin_small_patch4_window7_224] INFO: Epoch: [68] [1080/1251] eta: 0:01:27 lr: 0.000877 loss: 3.3035 (3.6225) grad_norm: 1.1484 (inf) time: 0.5050 [2021-03-25 15:45:08 swin_small_patch4_window7_224] INFO: Epoch: [68] [1090/1251] eta: 0:01:22 lr: 0.000877 loss: 3.8022 (3.6226) grad_norm: 1.0123 (inf) time: 0.5073 [2021-03-25 15:45:14 swin_small_patch4_window7_224] INFO: Epoch: [68] [1100/1251] eta: 0:01:17 lr: 0.000877 loss: 3.7884 (3.6206) grad_norm: 0.9964 (inf) time: 0.5114 [2021-03-25 15:45:19 swin_small_patch4_window7_224] INFO: Epoch: [68] [1110/1251] eta: 0:01:11 lr: 0.000877 loss: 3.5038 (3.6216) grad_norm: 1.0242 (inf) time: 0.5143 [2021-03-25 15:45:24 swin_small_patch4_window7_224] INFO: Epoch: [68] [1120/1251] eta: 0:01:06 lr: 0.000877 loss: 3.7219 (3.6227) grad_norm: 1.0454 (inf) time: 0.5144 [2021-03-25 15:45:29 swin_small_patch4_window7_224] INFO: Epoch: [68] [1130/1251] eta: 0:01:01 lr: 0.000877 loss: 3.6281 (3.6214) grad_norm: 1.1013 (inf) time: 0.5067 [2021-03-25 15:45:34 swin_small_patch4_window7_224] INFO: Epoch: [68] [1140/1251] eta: 0:00:56 lr: 0.000877 loss: 3.6281 (3.6225) grad_norm: 1.0674 (inf) time: 0.4999 [2021-03-25 15:45:39 swin_small_patch4_window7_224] INFO: Epoch: [68] [1150/1251] eta: 0:00:51 lr: 0.000877 loss: 3.6394 (3.6206) grad_norm: 1.0171 (inf) time: 0.5000 [2021-03-25 15:45:44 swin_small_patch4_window7_224] INFO: Epoch: [68] [1160/1251] eta: 0:00:46 lr: 0.000877 loss: 3.4439 (3.6187) grad_norm: 1.0607 (inf) time: 0.5063 [2021-03-25 15:45:49 swin_small_patch4_window7_224] INFO: Epoch: [68] [1170/1251] eta: 0:00:41 lr: 0.000877 loss: 3.2561 (3.6173) grad_norm: 1.0721 (inf) time: 0.5098 [2021-03-25 15:45:54 swin_small_patch4_window7_224] INFO: Epoch: [68] [1180/1251] eta: 0:00:36 lr: 0.000876 loss: 3.6181 (3.6174) grad_norm: 1.1069 (inf) time: 0.5087 [2021-03-25 15:45:59 swin_small_patch4_window7_224] INFO: Epoch: [68] [1190/1251] eta: 0:00:31 lr: 0.000876 loss: 3.7661 (3.6183) grad_norm: 1.0483 (inf) time: 0.5029 [2021-03-25 15:46:04 swin_small_patch4_window7_224] INFO: Epoch: [68] [1200/1251] eta: 0:00:25 lr: 0.000876 loss: 3.7927 (3.6172) grad_norm: 1.0406 (inf) time: 0.5029 [2021-03-25 15:46:09 swin_small_patch4_window7_224] INFO: Epoch: [68] [1210/1251] eta: 0:00:20 lr: 0.000876 loss: 3.5270 (3.6155) grad_norm: 1.0340 (inf) time: 0.5040 [2021-03-25 15:46:14 swin_small_patch4_window7_224] INFO: Epoch: [68] [1220/1251] eta: 0:00:15 lr: 0.000876 loss: 3.3680 (3.6135) grad_norm: 1.0112 (inf) time: 0.4988 [2021-03-25 15:46:19 swin_small_patch4_window7_224] INFO: Epoch: [68] [1230/1251] eta: 0:00:10 lr: 0.000876 loss: 3.4929 (3.6150) grad_norm: 1.0152 (inf) time: 0.5036 [2021-03-25 15:46:24 swin_small_patch4_window7_224] INFO: Epoch: [68] [1240/1251] eta: 0:00:05 lr: 0.000876 loss: 3.7522 (3.6159) grad_norm: 1.0431 (inf) time: 0.5038 [2021-03-25 15:46:29 swin_small_patch4_window7_224] INFO: Epoch: [68] [1250/1251] eta: 0:00:00 lr: 0.000876 loss: 3.8144 (3.6179) grad_norm: 1.0453 (inf) time: 0.4968 [2021-03-25 15:46:35 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:49 loss: 0.9455 (0.9455) acc1: 70.3125 (70.3125) acc5: 96.8750 (96.8750) [2021-03-25 15:46:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0698 (1.0797) acc1: 73.4375 (73.1534) acc5: 92.1875 (91.9034) [2021-03-25 15:46:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.1249 (1.0896) acc1: 73.4375 (74.1071) acc5: 92.1875 (92.1131) [2021-03-25 15:46:42 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0711 (1.0976) acc1: 73.4375 (73.6391) acc5: 92.1875 (92.0867) [2021-03-25 15:46:44 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0645 (1.1177) acc1: 73.4375 (73.3613) acc5: 92.1875 (92.0732) [2021-03-25 15:46:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0711 (1.1176) acc1: 75.0000 (73.4400) acc5: 92.4528 (92.1600) [2021-03-25 15:46:48 swin_small_patch4_window7_224] INFO: * Acc@1 74.126 Acc@5 92.614 loss 1.091 [2021-03-25 15:46:48 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.1% [2021-03-25 15:46:48 swin_small_patch4_window7_224] INFO: Max accuracy: 74.28% [2021-03-25 15:46:52 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 0/1251] eta: 1:21:28 lr: 0.000876 loss: 3.3413 (3.3413) grad_norm: 0.9630 (0.9630) time: 3.9080 [2021-03-25 15:46:57 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 10/1251] eta: 0:18:00 lr: 0.000876 loss: 3.8390 (3.6965) grad_norm: 1.0380 (1.0445) time: 0.8707 [2021-03-25 15:47:02 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 20/1251] eta: 0:14:22 lr: 0.000876 loss: 3.7722 (3.7365) grad_norm: 1.0498 (1.0347) time: 0.5400 [2021-03-25 15:47:08 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 30/1251] eta: 0:12:59 lr: 0.000876 loss: 3.7722 (3.6889) grad_norm: 1.0498 (1.0447) time: 0.5112 [2021-03-25 15:47:13 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 40/1251] eta: 0:12:15 lr: 0.000876 loss: 3.4679 (3.6101) grad_norm: 1.0309 (1.0399) time: 0.5104 [2021-03-25 15:47:18 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 50/1251] eta: 0:11:45 lr: 0.000876 loss: 3.4679 (3.5961) grad_norm: 1.0521 (1.0550) time: 0.5089 [2021-03-25 15:47:23 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 60/1251] eta: 0:11:25 lr: 0.000876 loss: 3.7102 (3.6137) grad_norm: 1.0785 (1.0615) time: 0.5084 [2021-03-25 15:47:28 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 70/1251] eta: 0:11:10 lr: 0.000876 loss: 3.7187 (3.6265) grad_norm: 1.0299 (1.0614) time: 0.5153 [2021-03-25 15:47:33 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 80/1251] eta: 0:10:54 lr: 0.000876 loss: 3.6711 (3.6113) grad_norm: 1.0111 (1.0538) time: 0.5108 [2021-03-25 15:47:38 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 90/1251] eta: 0:10:42 lr: 0.000876 loss: 3.5160 (3.5922) grad_norm: 1.0098 (1.0522) time: 0.5046 [2021-03-25 15:47:43 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 100/1251] eta: 0:10:32 lr: 0.000876 loss: 3.7901 (3.6199) grad_norm: 1.0098 (1.0471) time: 0.5095 [2021-03-25 15:47:48 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 110/1251] eta: 0:10:21 lr: 0.000876 loss: 3.8636 (3.6276) grad_norm: 0.9782 (1.0419) time: 0.5033 [2021-03-25 15:47:53 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 120/1251] eta: 0:10:12 lr: 0.000876 loss: 3.8131 (3.6318) grad_norm: 1.0195 (1.0478) time: 0.5039 [2021-03-25 15:47:59 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 130/1251] eta: 0:10:05 lr: 0.000876 loss: 3.8326 (3.6523) grad_norm: 1.0667 (1.0458) time: 0.5138 [2021-03-25 15:48:04 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 140/1251] eta: 0:09:56 lr: 0.000876 loss: 3.8192 (3.6343) grad_norm: 0.9974 (1.0484) time: 0.5097 [2021-03-25 15:48:09 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 150/1251] eta: 0:09:49 lr: 0.000876 loss: 3.5126 (3.6303) grad_norm: 1.0593 (1.0522) time: 0.5065 [2021-03-25 15:48:14 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 160/1251] eta: 0:09:42 lr: 0.000876 loss: 3.5668 (3.6285) grad_norm: 1.0058 (1.0499) time: 0.5067 [2021-03-25 15:48:19 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 170/1251] eta: 0:09:35 lr: 0.000876 loss: 3.5134 (3.6243) grad_norm: 1.0077 (1.0544) time: 0.5088 [2021-03-25 15:48:24 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 180/1251] eta: 0:09:29 lr: 0.000876 loss: 3.2440 (3.6004) grad_norm: 1.0249 (1.0523) time: 0.5141 [2021-03-25 15:48:29 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 190/1251] eta: 0:09:22 lr: 0.000876 loss: 3.3637 (3.5945) grad_norm: 0.9907 (1.0500) time: 0.5106 [2021-03-25 15:48:34 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 200/1251] eta: 0:09:16 lr: 0.000876 loss: 3.8244 (3.5971) grad_norm: 0.9907 (1.0498) time: 0.5113 [2021-03-25 15:48:39 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 210/1251] eta: 0:09:10 lr: 0.000876 loss: 3.7111 (3.6021) grad_norm: 1.0762 (1.0505) time: 0.5162 [2021-03-25 15:48:44 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 220/1251] eta: 0:09:03 lr: 0.000876 loss: 3.6669 (3.5939) grad_norm: 1.0949 (1.0562) time: 0.5062 [2021-03-25 15:48:49 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 230/1251] eta: 0:08:57 lr: 0.000876 loss: 3.8281 (3.6006) grad_norm: 1.1101 (1.0577) time: 0.4985 [2021-03-25 15:48:54 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 240/1251] eta: 0:08:50 lr: 0.000876 loss: 3.6468 (3.5902) grad_norm: 1.0205 (1.0553) time: 0.5020 [2021-03-25 15:49:00 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 250/1251] eta: 0:08:45 lr: 0.000876 loss: 3.4112 (3.5794) grad_norm: 1.0090 (1.0558) time: 0.5075 [2021-03-25 15:49:05 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 260/1251] eta: 0:08:39 lr: 0.000876 loss: 3.5367 (3.5852) grad_norm: 1.0581 (1.0578) time: 0.5143 [2021-03-25 15:49:10 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 270/1251] eta: 0:08:33 lr: 0.000876 loss: 3.6572 (3.5802) grad_norm: 1.0503 (1.0564) time: 0.5110 [2021-03-25 15:49:15 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 280/1251] eta: 0:08:27 lr: 0.000876 loss: 3.5751 (3.5780) grad_norm: 1.0503 (1.0574) time: 0.5042 [2021-03-25 15:49:20 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 290/1251] eta: 0:08:21 lr: 0.000876 loss: 3.6244 (3.5822) grad_norm: 1.0518 (1.0571) time: 0.5048 [2021-03-25 15:49:25 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 300/1251] eta: 0:08:16 lr: 0.000875 loss: 3.7877 (3.5839) grad_norm: 1.0170 (1.0561) time: 0.5061 [2021-03-25 15:49:30 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 310/1251] eta: 0:08:10 lr: 0.000875 loss: 3.7385 (3.5850) grad_norm: 1.0245 (1.0564) time: 0.5087 [2021-03-25 15:49:35 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 320/1251] eta: 0:08:05 lr: 0.000875 loss: 3.7334 (3.5857) grad_norm: 1.0562 (1.0573) time: 0.5143 [2021-03-25 15:49:40 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 330/1251] eta: 0:07:59 lr: 0.000875 loss: 3.5466 (3.5799) grad_norm: 1.0395 (1.0584) time: 0.5130 [2021-03-25 15:49:45 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 340/1251] eta: 0:07:54 lr: 0.000875 loss: 3.4810 (3.5847) grad_norm: 1.0377 (1.0582) time: 0.5079 [2021-03-25 15:49:50 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 350/1251] eta: 0:07:48 lr: 0.000875 loss: 3.6774 (3.5850) grad_norm: 1.0377 (1.0575) time: 0.5037 [2021-03-25 15:49:55 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 360/1251] eta: 0:07:42 lr: 0.000875 loss: 3.6004 (3.5814) grad_norm: 1.1179 (1.0628) time: 0.5029 [2021-03-25 15:50:01 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 370/1251] eta: 0:07:37 lr: 0.000875 loss: 3.5893 (3.5780) grad_norm: 1.1482 (1.0643) time: 0.5093 [2021-03-25 15:50:06 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 380/1251] eta: 0:07:31 lr: 0.000875 loss: 3.3206 (3.5712) grad_norm: 1.0173 (1.0618) time: 0.5076 [2021-03-25 15:50:11 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 390/1251] eta: 0:07:26 lr: 0.000875 loss: 3.4285 (3.5757) grad_norm: 0.9945 (1.0614) time: 0.5053 [2021-03-25 15:50:16 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 400/1251] eta: 0:07:21 lr: 0.000875 loss: 3.7930 (3.5817) grad_norm: 1.0112 (1.0604) time: 0.5064 [2021-03-25 15:50:21 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 410/1251] eta: 0:07:15 lr: 0.000875 loss: 3.7930 (3.5817) grad_norm: 1.0330 (1.0603) time: 0.5053 [2021-03-25 15:50:26 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 420/1251] eta: 0:07:10 lr: 0.000875 loss: 3.2677 (3.5758) grad_norm: 1.0777 (1.0616) time: 0.5025 [2021-03-25 15:50:31 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 430/1251] eta: 0:07:04 lr: 0.000875 loss: 3.5995 (3.5788) grad_norm: 1.0737 (1.0621) time: 0.5018 [2021-03-25 15:50:36 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 440/1251] eta: 0:06:59 lr: 0.000875 loss: 3.7442 (3.5805) grad_norm: 1.0761 (1.0633) time: 0.5073 [2021-03-25 15:50:41 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 450/1251] eta: 0:06:54 lr: 0.000875 loss: 3.6399 (3.5775) grad_norm: 1.0761 (1.0630) time: 0.5093 [2021-03-25 15:50:46 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 460/1251] eta: 0:06:48 lr: 0.000875 loss: 3.5561 (3.5713) grad_norm: 1.0459 (1.0627) time: 0.5054 [2021-03-25 15:50:51 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 470/1251] eta: 0:06:43 lr: 0.000875 loss: 3.6981 (3.5783) grad_norm: 1.0639 (1.0627) time: 0.5004 [2021-03-25 15:50:56 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 480/1251] eta: 0:06:37 lr: 0.000875 loss: 3.8088 (3.5797) grad_norm: 1.0413 (1.0624) time: 0.4979 [2021-03-25 15:51:01 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 490/1251] eta: 0:06:32 lr: 0.000875 loss: 3.5883 (3.5790) grad_norm: 1.0338 (1.0622) time: 0.5022 [2021-03-25 15:51:06 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 500/1251] eta: 0:06:27 lr: 0.000875 loss: 3.6733 (3.5798) grad_norm: 1.0266 (1.0617) time: 0.5049 [2021-03-25 15:51:11 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 510/1251] eta: 0:06:21 lr: 0.000875 loss: 3.8405 (3.5866) grad_norm: 1.0281 (1.0609) time: 0.5012 [2021-03-25 15:51:16 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 520/1251] eta: 0:06:16 lr: 0.000875 loss: 3.8405 (3.5890) grad_norm: 1.0281 (1.0603) time: 0.5033 [2021-03-25 15:51:21 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 530/1251] eta: 0:06:11 lr: 0.000875 loss: 3.7269 (3.5899) grad_norm: 1.0759 (1.0614) time: 0.5067 [2021-03-25 15:51:26 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 540/1251] eta: 0:06:05 lr: 0.000875 loss: 3.5075 (3.5887) grad_norm: 1.1070 (1.0624) time: 0.5073 [2021-03-25 15:51:32 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 550/1251] eta: 0:06:00 lr: 0.000875 loss: 3.6263 (3.5892) grad_norm: 1.1182 (1.0632) time: 0.5162 [2021-03-25 15:51:37 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 560/1251] eta: 0:05:55 lr: 0.000875 loss: 3.8702 (3.5897) grad_norm: 1.1373 (1.0661) time: 0.5258 [2021-03-25 15:51:42 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 570/1251] eta: 0:05:50 lr: 0.000875 loss: 3.7869 (3.5934) grad_norm: 1.1425 (1.0669) time: 0.5197 [2021-03-25 15:51:47 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 580/1251] eta: 0:05:45 lr: 0.000875 loss: 3.7729 (3.5952) grad_norm: 1.0582 (1.0665) time: 0.5090 [2021-03-25 15:51:52 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 590/1251] eta: 0:05:40 lr: 0.000875 loss: 3.9074 (3.6030) grad_norm: 1.0582 (1.0668) time: 0.5046 [2021-03-25 15:51:57 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 600/1251] eta: 0:05:34 lr: 0.000875 loss: 3.9074 (3.6049) grad_norm: 1.0118 (1.0663) time: 0.5038 [2021-03-25 15:52:02 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 610/1251] eta: 0:05:29 lr: 0.000875 loss: 3.8436 (3.6107) grad_norm: 1.0463 (1.0664) time: 0.5024 [2021-03-25 15:52:07 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 620/1251] eta: 0:05:24 lr: 0.000875 loss: 3.9162 (3.6138) grad_norm: 1.0460 (1.0657) time: 0.5005 [2021-03-25 15:52:12 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 630/1251] eta: 0:05:19 lr: 0.000875 loss: 3.7450 (3.6119) grad_norm: 1.0115 (1.0651) time: 0.5061 [2021-03-25 15:52:17 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 640/1251] eta: 0:05:13 lr: 0.000875 loss: 3.4430 (3.6086) grad_norm: 1.0254 (1.0666) time: 0.5071 [2021-03-25 15:52:22 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 650/1251] eta: 0:05:08 lr: 0.000875 loss: 3.4430 (3.6064) grad_norm: 1.0961 (1.0668) time: 0.5082 [2021-03-25 15:52:27 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 660/1251] eta: 0:05:03 lr: 0.000874 loss: 3.7577 (3.6112) grad_norm: 1.0807 (1.0670) time: 0.5122 [2021-03-25 15:52:32 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 670/1251] eta: 0:04:58 lr: 0.000874 loss: 3.8626 (3.6157) grad_norm: 1.0120 (1.0661) time: 0.5058 [2021-03-25 15:52:37 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 680/1251] eta: 0:04:53 lr: 0.000874 loss: 3.8339 (3.6163) grad_norm: 0.9551 (1.0644) time: 0.4995 [2021-03-25 15:52:43 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 690/1251] eta: 0:04:47 lr: 0.000874 loss: 3.3965 (3.6109) grad_norm: 0.9700 (1.0637) time: 0.5020 [2021-03-25 15:52:48 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 700/1251] eta: 0:04:42 lr: 0.000874 loss: 3.2421 (3.6041) grad_norm: 0.9866 (1.0629) time: 0.5082 [2021-03-25 15:52:53 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 710/1251] eta: 0:04:37 lr: 0.000874 loss: 3.6050 (3.6060) grad_norm: 0.9836 (1.0621) time: 0.5047 [2021-03-25 15:52:58 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 720/1251] eta: 0:04:32 lr: 0.000874 loss: 3.8317 (3.6081) grad_norm: 0.9691 (1.0613) time: 0.5089 [2021-03-25 15:53:03 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 730/1251] eta: 0:04:27 lr: 0.000874 loss: 3.8016 (3.6092) grad_norm: 1.0296 (1.0614) time: 0.5167 [2021-03-25 15:53:08 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 740/1251] eta: 0:04:22 lr: 0.000874 loss: 3.7179 (3.6077) grad_norm: 1.1438 (1.0627) time: 0.5274 [2021-03-25 15:53:13 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 750/1251] eta: 0:04:17 lr: 0.000874 loss: 3.7179 (3.6095) grad_norm: 1.1438 (1.0638) time: 0.5250 [2021-03-25 15:53:19 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 760/1251] eta: 0:04:12 lr: 0.000874 loss: 3.7213 (3.6090) grad_norm: 1.1072 (1.0648) time: 0.5204 [2021-03-25 15:53:24 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 770/1251] eta: 0:04:07 lr: 0.000874 loss: 3.4319 (3.6079) grad_norm: 1.0897 (1.0654) time: 0.5198 [2021-03-25 15:53:29 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 780/1251] eta: 0:04:01 lr: 0.000874 loss: 3.4771 (3.6076) grad_norm: 1.1000 (1.0664) time: 0.5075 [2021-03-25 15:53:34 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 790/1251] eta: 0:03:56 lr: 0.000874 loss: 3.5393 (3.6040) grad_norm: 1.1191 (1.0675) time: 0.5085 [2021-03-25 15:53:39 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 800/1251] eta: 0:03:51 lr: 0.000874 loss: 3.8058 (3.6093) grad_norm: 1.0795 (1.0682) time: 0.5064 [2021-03-25 15:53:44 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 810/1251] eta: 0:03:46 lr: 0.000874 loss: 3.9736 (3.6076) grad_norm: 1.0678 (1.0685) time: 0.5048 [2021-03-25 15:53:49 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 820/1251] eta: 0:03:41 lr: 0.000874 loss: 3.6350 (3.6075) grad_norm: 1.0091 (1.0676) time: 0.5115 [2021-03-25 15:53:54 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 830/1251] eta: 0:03:36 lr: 0.000874 loss: 3.6350 (3.6081) grad_norm: 0.9722 (1.0668) time: 0.5132 [2021-03-25 15:54:00 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 840/1251] eta: 0:03:30 lr: 0.000874 loss: 3.6713 (3.6097) grad_norm: 1.0351 (1.0669) time: 0.5115 [2021-03-25 15:54:05 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 850/1251] eta: 0:03:25 lr: 0.000874 loss: 3.6334 (3.6069) grad_norm: 1.0436 (1.0667) time: 0.5118 [2021-03-25 15:54:10 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 860/1251] eta: 0:03:20 lr: 0.000874 loss: 3.7344 (3.6099) grad_norm: 1.0224 (1.0666) time: 0.5085 [2021-03-25 15:54:15 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 870/1251] eta: 0:03:15 lr: 0.000874 loss: 3.8587 (3.6145) grad_norm: 1.0466 (1.0673) time: 0.5126 [2021-03-25 15:54:20 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 880/1251] eta: 0:03:10 lr: 0.000874 loss: 3.9061 (3.6144) grad_norm: 1.0466 (1.0672) time: 0.5157 [2021-03-25 15:54:25 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 890/1251] eta: 0:03:05 lr: 0.000874 loss: 3.5827 (3.6126) grad_norm: 1.0828 (1.0679) time: 0.5112 [2021-03-25 15:54:30 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 900/1251] eta: 0:03:00 lr: 0.000874 loss: 3.4323 (3.6127) grad_norm: 1.0944 (1.0682) time: 0.5039 [2021-03-25 15:54:35 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 910/1251] eta: 0:02:54 lr: 0.000874 loss: 3.5191 (3.6127) grad_norm: 0.9849 (1.0675) time: 0.5034 [2021-03-25 15:54:40 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 920/1251] eta: 0:02:49 lr: 0.000874 loss: 3.6358 (3.6145) grad_norm: 1.0385 (1.0677) time: 0.5146 [2021-03-25 15:54:46 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 930/1251] eta: 0:02:44 lr: 0.000874 loss: 3.7430 (3.6142) grad_norm: 1.0548 (1.0674) time: 0.5169 [2021-03-25 15:54:51 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 940/1251] eta: 0:02:39 lr: 0.000874 loss: 3.6422 (3.6157) grad_norm: 1.0166 (1.0671) time: 0.5100 [2021-03-25 15:54:56 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 950/1251] eta: 0:02:34 lr: 0.000874 loss: 3.9731 (3.6172) grad_norm: 1.0270 (1.0674) time: 0.5096 [2021-03-25 15:55:01 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 960/1251] eta: 0:02:29 lr: 0.000874 loss: 3.7873 (3.6153) grad_norm: 1.0800 (1.0670) time: 0.5042 [2021-03-25 15:55:06 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 970/1251] eta: 0:02:24 lr: 0.000874 loss: 3.8587 (3.6171) grad_norm: 1.0337 (1.0667) time: 0.5012 [2021-03-25 15:55:11 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 980/1251] eta: 0:02:18 lr: 0.000874 loss: 3.5974 (3.6161) grad_norm: 1.0328 (1.0667) time: 0.5047 [2021-03-25 15:55:16 swin_small_patch4_window7_224] INFO: Epoch: [69] [ 990/1251] eta: 0:02:13 lr: 0.000874 loss: 3.7209 (3.6180) grad_norm: 1.0220 (1.0664) time: 0.5070 [2021-03-25 15:55:21 swin_small_patch4_window7_224] INFO: Epoch: [69] [1000/1251] eta: 0:02:08 lr: 0.000874 loss: 3.7209 (3.6182) grad_norm: 1.0655 (1.0671) time: 0.5104 [2021-03-25 15:55:26 swin_small_patch4_window7_224] INFO: Epoch: [69] [1010/1251] eta: 0:02:03 lr: 0.000874 loss: 3.7544 (3.6208) grad_norm: 1.0932 (1.0673) time: 0.5117 [2021-03-25 15:55:31 swin_small_patch4_window7_224] INFO: Epoch: [69] [1020/1251] eta: 0:01:58 lr: 0.000873 loss: 3.7652 (3.6217) grad_norm: 1.0099 (1.0666) time: 0.5082 [2021-03-25 15:55:36 swin_small_patch4_window7_224] INFO: Epoch: [69] [1030/1251] eta: 0:01:53 lr: 0.000873 loss: 3.6880 (3.6204) grad_norm: 1.0362 (1.0670) time: 0.5061 [2021-03-25 15:55:41 swin_small_patch4_window7_224] INFO: Epoch: [69] [1040/1251] eta: 0:01:48 lr: 0.000873 loss: 3.6998 (3.6225) grad_norm: 1.0608 (1.0670) time: 0.5062 [2021-03-25 15:55:46 swin_small_patch4_window7_224] INFO: Epoch: [69] [1050/1251] eta: 0:01:42 lr: 0.000873 loss: 3.8890 (3.6257) grad_norm: 1.0304 (1.0665) time: 0.5062 [2021-03-25 15:55:52 swin_small_patch4_window7_224] INFO: Epoch: [69] [1060/1251] eta: 0:01:37 lr: 0.000873 loss: 3.6758 (3.6238) grad_norm: 1.0304 (1.0668) time: 0.5150 [2021-03-25 15:55:57 swin_small_patch4_window7_224] INFO: Epoch: [69] [1070/1251] eta: 0:01:32 lr: 0.000873 loss: 3.6523 (3.6236) grad_norm: 1.0789 (1.0672) time: 0.5142 [2021-03-25 15:56:02 swin_small_patch4_window7_224] INFO: Epoch: [69] [1080/1251] eta: 0:01:27 lr: 0.000873 loss: 3.6523 (3.6216) grad_norm: 1.0569 (1.0670) time: 0.5072 [2021-03-25 15:56:07 swin_small_patch4_window7_224] INFO: Epoch: [69] [1090/1251] eta: 0:01:22 lr: 0.000873 loss: 3.5694 (3.6207) grad_norm: 1.0271 (1.0670) time: 0.5015 [2021-03-25 15:56:12 swin_small_patch4_window7_224] INFO: Epoch: [69] [1100/1251] eta: 0:01:17 lr: 0.000873 loss: 3.6431 (3.6211) grad_norm: 1.0367 (1.0671) time: 0.5001 [2021-03-25 15:56:17 swin_small_patch4_window7_224] INFO: Epoch: [69] [1110/1251] eta: 0:01:12 lr: 0.000873 loss: 3.7782 (3.6227) grad_norm: 1.0367 (1.0668) time: 0.5048 [2021-03-25 15:56:22 swin_small_patch4_window7_224] INFO: Epoch: [69] [1120/1251] eta: 0:01:07 lr: 0.000873 loss: 3.6481 (3.6211) grad_norm: 1.0469 (1.0667) time: 0.5064 [2021-03-25 15:56:27 swin_small_patch4_window7_224] INFO: Epoch: [69] [1130/1251] eta: 0:01:01 lr: 0.000873 loss: 3.7858 (3.6245) grad_norm: 1.0606 (1.0668) time: 0.5028 [2021-03-25 15:56:32 swin_small_patch4_window7_224] INFO: Epoch: [69] [1140/1251] eta: 0:00:56 lr: 0.000873 loss: 3.8654 (3.6251) grad_norm: 1.0291 (1.0665) time: 0.5002 [2021-03-25 15:56:37 swin_small_patch4_window7_224] INFO: Epoch: [69] [1150/1251] eta: 0:00:51 lr: 0.000873 loss: 3.6093 (3.6246) grad_norm: 1.0122 (1.0663) time: 0.5000 [2021-03-25 15:56:42 swin_small_patch4_window7_224] INFO: Epoch: [69] [1160/1251] eta: 0:00:46 lr: 0.000873 loss: 3.3808 (3.6223) grad_norm: 0.9844 (1.0657) time: 0.5044 [2021-03-25 15:56:47 swin_small_patch4_window7_224] INFO: Epoch: [69] [1170/1251] eta: 0:00:41 lr: 0.000873 loss: 3.4322 (3.6219) grad_norm: 1.0205 (1.0661) time: 0.5046 [2021-03-25 15:56:52 swin_small_patch4_window7_224] INFO: Epoch: [69] [1180/1251] eta: 0:00:36 lr: 0.000873 loss: 3.7943 (3.6227) grad_norm: 1.0536 (1.0658) time: 0.5011 [2021-03-25 15:56:57 swin_small_patch4_window7_224] INFO: Epoch: [69] [1190/1251] eta: 0:00:31 lr: 0.000873 loss: 3.5709 (3.6182) grad_norm: 1.0537 (1.0662) time: 0.5032 [2021-03-25 15:57:02 swin_small_patch4_window7_224] INFO: Epoch: [69] [1200/1251] eta: 0:00:26 lr: 0.000873 loss: 3.3780 (3.6194) grad_norm: 1.0638 (1.0659) time: 0.5000 [2021-03-25 15:57:07 swin_small_patch4_window7_224] INFO: Epoch: [69] [1210/1251] eta: 0:00:20 lr: 0.000873 loss: 3.8962 (3.6216) grad_norm: 1.0755 (1.0665) time: 0.5010 [2021-03-25 15:57:12 swin_small_patch4_window7_224] INFO: Epoch: [69] [1220/1251] eta: 0:00:15 lr: 0.000873 loss: 3.8349 (3.6218) grad_norm: 1.0986 (1.0668) time: 0.5064 [2021-03-25 15:57:17 swin_small_patch4_window7_224] INFO: Epoch: [69] [1230/1251] eta: 0:00:10 lr: 0.000873 loss: 3.7140 (3.6228) grad_norm: 1.0527 (1.0665) time: 0.5038 [2021-03-25 15:57:22 swin_small_patch4_window7_224] INFO: Epoch: [69] [1240/1251] eta: 0:00:05 lr: 0.000873 loss: 3.7618 (3.6236) grad_norm: 1.0448 (1.0668) time: 0.5050 [2021-03-25 15:57:27 swin_small_patch4_window7_224] INFO: Epoch: [69] [1250/1251] eta: 0:00:00 lr: 0.000873 loss: 3.7418 (3.6237) grad_norm: 1.0639 (1.0669) time: 0.5089 [2021-03-25 15:57:33 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:31 loss: 1.2105 (1.2105) acc1: 73.4375 (73.4375) acc5: 89.0625 (89.0625) [2021-03-25 15:57:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.1195 (1.0449) acc1: 75.0000 (74.1477) acc5: 93.7500 (92.7557) [2021-03-25 15:57:37 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0460 (1.0494) acc1: 75.0000 (74.6280) acc5: 93.7500 (93.4524) [2021-03-25 15:57:40 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1019 (1.0655) acc1: 73.4375 (74.4960) acc5: 93.7500 (93.3972) [2021-03-25 15:57:41 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1764 (1.0914) acc1: 73.4375 (73.8186) acc5: 92.1875 (93.0640) [2021-03-25 15:57:42 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1261 (1.0939) acc1: 73.4375 (73.9840) acc5: 92.1875 (92.8000) [2021-03-25 15:57:46 swin_small_patch4_window7_224] INFO: * Acc@1 74.492 Acc@5 92.668 loss 1.077 [2021-03-25 15:57:46 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.5% [2021-03-25 15:57:46 swin_small_patch4_window7_224] INFO: Max accuracy: 74.49% [2021-03-25 15:57:50 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 0/1251] eta: 1:26:33 lr: 0.000873 loss: 3.7426 (3.7426) grad_norm: 0.9160 (0.9160) time: 4.1517 [2021-03-25 15:57:55 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 10/1251] eta: 0:17:28 lr: 0.000873 loss: 3.8074 (3.7191) grad_norm: 1.0287 (1.0597) time: 0.8451 [2021-03-25 15:58:00 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 20/1251] eta: 0:14:01 lr: 0.000873 loss: 3.8074 (3.6862) grad_norm: 1.0397 (1.0474) time: 0.5102 [2021-03-25 15:58:05 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 30/1251] eta: 0:12:46 lr: 0.000873 loss: 3.6226 (3.6124) grad_norm: 1.0397 (1.0563) time: 0.5087 [2021-03-25 15:58:10 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 40/1251] eta: 0:12:05 lr: 0.000873 loss: 3.6226 (3.6401) grad_norm: 1.0746 (1.0645) time: 0.5103 [2021-03-25 15:58:16 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 50/1251] eta: 0:11:37 lr: 0.000873 loss: 3.5261 (3.5766) grad_norm: 1.0746 (1.0601) time: 0.5064 [2021-03-25 15:58:21 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 60/1251] eta: 0:11:15 lr: 0.000873 loss: 3.7318 (3.6219) grad_norm: 1.0492 (1.0680) time: 0.5027 [2021-03-25 15:58:26 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 70/1251] eta: 0:10:59 lr: 0.000873 loss: 3.7461 (3.6019) grad_norm: 1.0557 (1.0711) time: 0.5014 [2021-03-25 15:58:31 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 80/1251] eta: 0:10:45 lr: 0.000873 loss: 3.5332 (3.5950) grad_norm: 1.0201 (1.0614) time: 0.5009 [2021-03-25 15:58:36 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 90/1251] eta: 0:10:33 lr: 0.000873 loss: 3.6159 (3.5999) grad_norm: 0.9810 (1.0589) time: 0.5013 [2021-03-25 15:58:41 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 100/1251] eta: 0:10:25 lr: 0.000873 loss: 3.6159 (3.5761) grad_norm: 1.0046 (1.0554) time: 0.5108 [2021-03-25 15:58:46 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 110/1251] eta: 0:10:15 lr: 0.000873 loss: 3.6444 (3.5857) grad_norm: 1.0040 (1.0526) time: 0.5127 [2021-03-25 15:58:51 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 120/1251] eta: 0:10:06 lr: 0.000873 loss: 3.5834 (3.5713) grad_norm: 1.0295 (1.0545) time: 0.5020 [2021-03-25 15:58:56 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 130/1251] eta: 0:09:58 lr: 0.000872 loss: 3.5834 (3.5848) grad_norm: 1.0450 (1.0550) time: 0.4996 [2021-03-25 15:59:01 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 140/1251] eta: 0:09:50 lr: 0.000872 loss: 3.6053 (3.5795) grad_norm: 1.0378 (1.0535) time: 0.5007 [2021-03-25 15:59:06 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 150/1251] eta: 0:09:43 lr: 0.000872 loss: 3.7762 (3.5922) grad_norm: 0.9875 (1.0473) time: 0.5054 [2021-03-25 15:59:11 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 160/1251] eta: 0:09:36 lr: 0.000872 loss: 3.8106 (3.5965) grad_norm: 0.9298 (1.0459) time: 0.5090 [2021-03-25 15:59:16 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 170/1251] eta: 0:09:29 lr: 0.000872 loss: 3.4999 (3.5874) grad_norm: 1.0112 (1.0479) time: 0.5050 [2021-03-25 15:59:21 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 180/1251] eta: 0:09:23 lr: 0.000872 loss: 3.6034 (3.5985) grad_norm: 1.1049 (1.0528) time: 0.5105 [2021-03-25 15:59:26 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 190/1251] eta: 0:09:17 lr: 0.000872 loss: 3.8220 (3.6066) grad_norm: 1.1383 (1.0561) time: 0.5089 [2021-03-25 15:59:31 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 200/1251] eta: 0:09:11 lr: 0.000872 loss: 3.8414 (3.6110) grad_norm: 1.0765 (1.0561) time: 0.5067 [2021-03-25 15:59:36 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 210/1251] eta: 0:09:04 lr: 0.000872 loss: 3.7718 (3.6061) grad_norm: 1.0221 (1.0550) time: 0.5080 [2021-03-25 15:59:42 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 220/1251] eta: 0:08:59 lr: 0.000872 loss: 3.8538 (3.6063) grad_norm: 1.0243 (1.0583) time: 0.5095 [2021-03-25 15:59:47 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 230/1251] eta: 0:08:53 lr: 0.000872 loss: 3.7602 (3.6097) grad_norm: 1.1151 (1.0660) time: 0.5138 [2021-03-25 15:59:52 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 240/1251] eta: 0:08:47 lr: 0.000872 loss: 3.7602 (3.6087) grad_norm: 1.1159 (1.0672) time: 0.5095 [2021-03-25 15:59:57 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 250/1251] eta: 0:08:41 lr: 0.000872 loss: 3.7802 (3.6114) grad_norm: 1.0039 (1.0647) time: 0.5048 [2021-03-25 16:00:02 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 260/1251] eta: 0:08:36 lr: 0.000872 loss: 3.7046 (3.6159) grad_norm: 0.9964 (1.0635) time: 0.5060 [2021-03-25 16:00:07 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 270/1251] eta: 0:08:30 lr: 0.000872 loss: 3.7271 (3.6106) grad_norm: 1.0196 (1.0636) time: 0.5074 [2021-03-25 16:00:12 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 280/1251] eta: 0:08:24 lr: 0.000872 loss: 3.5772 (3.6077) grad_norm: 1.0741 (1.0647) time: 0.5082 [2021-03-25 16:00:17 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 290/1251] eta: 0:08:19 lr: 0.000872 loss: 3.4925 (3.6043) grad_norm: 1.0448 (1.0652) time: 0.5175 [2021-03-25 16:00:22 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 300/1251] eta: 0:08:13 lr: 0.000872 loss: 3.7346 (3.6108) grad_norm: 0.9854 (1.0631) time: 0.5096 [2021-03-25 16:00:27 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 310/1251] eta: 0:08:07 lr: 0.000872 loss: 3.9597 (3.6237) grad_norm: 0.9617 (1.0602) time: 0.4981 [2021-03-25 16:00:32 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 320/1251] eta: 0:08:02 lr: 0.000872 loss: 3.8513 (3.6212) grad_norm: 1.0171 (1.0608) time: 0.5030 [2021-03-25 16:00:37 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 330/1251] eta: 0:07:56 lr: 0.000872 loss: 3.7683 (3.6179) grad_norm: 1.0594 (1.0626) time: 0.5060 [2021-03-25 16:00:42 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 340/1251] eta: 0:07:51 lr: 0.000872 loss: 3.5985 (3.6110) grad_norm: 1.0594 (1.0632) time: 0.5061 [2021-03-25 16:00:47 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 350/1251] eta: 0:07:45 lr: 0.000872 loss: 3.5348 (3.6074) grad_norm: 1.0237 (1.0640) time: 0.5064 [2021-03-25 16:00:53 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 360/1251] eta: 0:07:40 lr: 0.000872 loss: 3.7139 (3.6130) grad_norm: 1.0514 (1.0655) time: 0.5065 [2021-03-25 16:00:58 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 370/1251] eta: 0:07:35 lr: 0.000872 loss: 3.7055 (3.6066) grad_norm: 1.1193 (1.0671) time: 0.5068 [2021-03-25 16:01:03 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 380/1251] eta: 0:07:29 lr: 0.000872 loss: 3.6189 (3.6065) grad_norm: 1.0184 (1.0653) time: 0.5037 [2021-03-25 16:01:08 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 390/1251] eta: 0:07:24 lr: 0.000872 loss: 3.6819 (3.6100) grad_norm: 1.0177 (1.0650) time: 0.5060 [2021-03-25 16:01:13 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 400/1251] eta: 0:07:18 lr: 0.000872 loss: 3.5954 (3.6029) grad_norm: 1.0177 (1.0647) time: 0.5070 [2021-03-25 16:01:18 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 410/1251] eta: 0:07:13 lr: 0.000872 loss: 3.7412 (3.6093) grad_norm: 1.0005 (1.0642) time: 0.5068 [2021-03-25 16:01:23 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 420/1251] eta: 0:07:08 lr: 0.000872 loss: 3.9414 (3.6160) grad_norm: 1.0377 (1.0659) time: 0.5085 [2021-03-25 16:01:28 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 430/1251] eta: 0:07:02 lr: 0.000872 loss: 3.9414 (3.6150) grad_norm: 1.0524 (1.0662) time: 0.5011 [2021-03-25 16:01:33 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 440/1251] eta: 0:06:57 lr: 0.000872 loss: 3.5932 (3.6094) grad_norm: 1.0304 (1.0651) time: 0.5054 [2021-03-25 16:01:38 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 450/1251] eta: 0:06:52 lr: 0.000872 loss: 3.5420 (3.6047) grad_norm: 1.0303 (1.0653) time: 0.5163 [2021-03-25 16:01:43 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 460/1251] eta: 0:06:47 lr: 0.000872 loss: 3.5420 (3.6050) grad_norm: 1.0760 (1.0661) time: 0.5107 [2021-03-25 16:01:48 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 470/1251] eta: 0:06:41 lr: 0.000872 loss: 3.6512 (3.6067) grad_norm: 1.0352 (1.0651) time: 0.5046 [2021-03-25 16:01:53 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 480/1251] eta: 0:06:36 lr: 0.000872 loss: 3.7361 (3.6065) grad_norm: 1.0352 (1.0669) time: 0.5074 [2021-03-25 16:01:59 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 490/1251] eta: 0:06:31 lr: 0.000871 loss: 3.5092 (3.5997) grad_norm: 1.0929 (1.0677) time: 0.5095 [2021-03-25 16:02:04 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 500/1251] eta: 0:06:26 lr: 0.000871 loss: 3.4637 (3.6014) grad_norm: 1.0607 (1.0671) time: 0.5078 [2021-03-25 16:02:09 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 510/1251] eta: 0:06:20 lr: 0.000871 loss: 3.5289 (3.5988) grad_norm: 1.0440 (1.0674) time: 0.5038 [2021-03-25 16:02:14 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 520/1251] eta: 0:06:15 lr: 0.000871 loss: 3.5289 (3.5988) grad_norm: 0.9747 (1.0662) time: 0.5023 [2021-03-25 16:02:19 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 530/1251] eta: 0:06:10 lr: 0.000871 loss: 3.4516 (3.5942) grad_norm: 0.9911 (1.0666) time: 0.5089 [2021-03-25 16:02:24 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 540/1251] eta: 0:06:05 lr: 0.000871 loss: 3.5514 (3.5971) grad_norm: 1.0087 (1.0651) time: 0.5120 [2021-03-25 16:02:29 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 550/1251] eta: 0:06:00 lr: 0.000871 loss: 3.5810 (3.5932) grad_norm: 0.9963 (1.0640) time: 0.5138 [2021-03-25 16:02:34 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 560/1251] eta: 0:05:54 lr: 0.000871 loss: 3.5626 (3.5911) grad_norm: 0.9650 (1.0625) time: 0.5124 [2021-03-25 16:02:39 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 570/1251] eta: 0:05:49 lr: 0.000871 loss: 3.4297 (3.5857) grad_norm: 1.0025 (1.0641) time: 0.5086 [2021-03-25 16:02:44 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 580/1251] eta: 0:05:44 lr: 0.000871 loss: 3.7360 (3.5895) grad_norm: 1.0060 (1.0631) time: 0.5048 [2021-03-25 16:02:49 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 590/1251] eta: 0:05:39 lr: 0.000871 loss: 3.7762 (3.5917) grad_norm: 0.9894 (1.0623) time: 0.5040 [2021-03-25 16:02:54 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 600/1251] eta: 0:05:34 lr: 0.000871 loss: 3.6394 (3.5905) grad_norm: 1.0091 (1.0627) time: 0.5056 [2021-03-25 16:02:59 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 610/1251] eta: 0:05:28 lr: 0.000871 loss: 3.7324 (3.5904) grad_norm: 1.0568 (1.0635) time: 0.5081 [2021-03-25 16:03:05 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 620/1251] eta: 0:05:23 lr: 0.000871 loss: 3.7503 (3.5930) grad_norm: 1.0891 (1.0644) time: 0.5108 [2021-03-25 16:03:10 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 630/1251] eta: 0:05:18 lr: 0.000871 loss: 3.6275 (3.5960) grad_norm: 1.1283 (1.0653) time: 0.5104 [2021-03-25 16:03:15 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 640/1251] eta: 0:05:13 lr: 0.000871 loss: 3.3232 (3.5926) grad_norm: 1.0979 (1.0655) time: 0.5032 [2021-03-25 16:03:20 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 650/1251] eta: 0:05:08 lr: 0.000871 loss: 3.4577 (3.5947) grad_norm: 1.0331 (1.0661) time: 0.4995 [2021-03-25 16:03:25 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 660/1251] eta: 0:05:02 lr: 0.000871 loss: 3.2045 (3.5894) grad_norm: 1.0672 (1.0669) time: 0.5052 [2021-03-25 16:03:30 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 670/1251] eta: 0:04:57 lr: 0.000871 loss: 3.2045 (3.5883) grad_norm: 1.0543 (1.0665) time: 0.5080 [2021-03-25 16:03:35 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 680/1251] eta: 0:04:52 lr: 0.000871 loss: 3.3681 (3.5869) grad_norm: 1.0025 (1.0662) time: 0.5116 [2021-03-25 16:03:40 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 690/1251] eta: 0:04:47 lr: 0.000871 loss: 3.4491 (3.5855) grad_norm: 1.0763 (1.0668) time: 0.5085 [2021-03-25 16:03:45 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 700/1251] eta: 0:04:42 lr: 0.000871 loss: 3.7225 (3.5911) grad_norm: 1.1271 (1.0671) time: 0.5070 [2021-03-25 16:03:50 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 710/1251] eta: 0:04:37 lr: 0.000871 loss: 3.7163 (3.5899) grad_norm: 1.0282 (1.0669) time: 0.5039 [2021-03-25 16:03:55 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 720/1251] eta: 0:04:31 lr: 0.000871 loss: 3.6952 (3.5902) grad_norm: 1.0282 (1.0668) time: 0.5008 [2021-03-25 16:04:00 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 730/1251] eta: 0:04:26 lr: 0.000871 loss: 3.6651 (3.5881) grad_norm: 1.1216 (1.0684) time: 0.5081 [2021-03-25 16:04:06 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 740/1251] eta: 0:04:21 lr: 0.000871 loss: 3.6393 (3.5880) grad_norm: 1.1554 (1.0702) time: 0.5190 [2021-03-25 16:04:11 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 750/1251] eta: 0:04:16 lr: 0.000871 loss: 3.6280 (3.5885) grad_norm: 1.0771 (1.0712) time: 0.5216 [2021-03-25 16:04:16 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 760/1251] eta: 0:04:11 lr: 0.000871 loss: 3.5677 (3.5877) grad_norm: 1.0527 (1.0712) time: 0.5136 [2021-03-25 16:04:21 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 770/1251] eta: 0:04:06 lr: 0.000871 loss: 3.3976 (3.5853) grad_norm: 1.0350 (1.0706) time: 0.5087 [2021-03-25 16:04:26 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 780/1251] eta: 0:04:01 lr: 0.000871 loss: 3.3976 (3.5851) grad_norm: 1.0156 (1.0703) time: 0.5086 [2021-03-25 16:04:31 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 790/1251] eta: 0:03:56 lr: 0.000871 loss: 3.8114 (3.5887) grad_norm: 1.0134 (1.0696) time: 0.5113 [2021-03-25 16:04:36 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 800/1251] eta: 0:03:50 lr: 0.000871 loss: 3.7170 (3.5900) grad_norm: 1.0216 (1.0699) time: 0.5119 [2021-03-25 16:04:41 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 810/1251] eta: 0:03:45 lr: 0.000871 loss: 3.6892 (3.5917) grad_norm: 1.0216 (1.0703) time: 0.5070 [2021-03-25 16:04:46 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 820/1251] eta: 0:03:40 lr: 0.000871 loss: 3.7160 (3.5946) grad_norm: 1.0592 (1.0706) time: 0.5053 [2021-03-25 16:04:51 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 830/1251] eta: 0:03:35 lr: 0.000871 loss: 3.6832 (3.5955) grad_norm: 1.0203 (1.0700) time: 0.5032 [2021-03-25 16:04:57 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 840/1251] eta: 0:03:30 lr: 0.000871 loss: 3.7916 (3.5979) grad_norm: 1.0236 (1.0703) time: 0.5107 [2021-03-25 16:05:02 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 850/1251] eta: 0:03:25 lr: 0.000870 loss: 3.7916 (3.5961) grad_norm: 1.0338 (1.0702) time: 0.5148 [2021-03-25 16:05:07 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 860/1251] eta: 0:03:20 lr: 0.000870 loss: 3.8075 (3.5985) grad_norm: 1.0137 (1.0697) time: 0.5042 [2021-03-25 16:05:12 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 870/1251] eta: 0:03:14 lr: 0.000870 loss: 3.8179 (3.5986) grad_norm: 1.0016 (1.0688) time: 0.5019 [2021-03-25 16:05:17 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 880/1251] eta: 0:03:09 lr: 0.000870 loss: 3.8044 (3.6021) grad_norm: 1.0156 (1.0688) time: 0.5050 [2021-03-25 16:05:22 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 890/1251] eta: 0:03:04 lr: 0.000870 loss: 3.8044 (3.6023) grad_norm: 1.0592 (1.0685) time: 0.5091 [2021-03-25 16:05:27 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 900/1251] eta: 0:02:59 lr: 0.000870 loss: 3.8851 (3.6045) grad_norm: 1.0446 (1.0682) time: 0.5083 [2021-03-25 16:05:32 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 910/1251] eta: 0:02:54 lr: 0.000870 loss: 3.8851 (3.6071) grad_norm: 1.0538 (1.0684) time: 0.5000 [2021-03-25 16:05:37 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 920/1251] eta: 0:02:49 lr: 0.000870 loss: 3.7697 (3.6053) grad_norm: 1.0334 (1.0680) time: 0.4967 [2021-03-25 16:05:42 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 930/1251] eta: 0:02:44 lr: 0.000870 loss: 3.7688 (3.6075) grad_norm: 1.0523 (1.0684) time: 0.5081 [2021-03-25 16:05:47 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 940/1251] eta: 0:02:38 lr: 0.000870 loss: 3.7964 (3.6083) grad_norm: 1.0510 (1.0679) time: 0.5111 [2021-03-25 16:05:52 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 950/1251] eta: 0:02:33 lr: 0.000870 loss: 3.7045 (3.6069) grad_norm: 1.0552 (1.0686) time: 0.5073 [2021-03-25 16:05:57 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 960/1251] eta: 0:02:28 lr: 0.000870 loss: 3.4504 (3.6067) grad_norm: 1.0552 (1.0679) time: 0.5119 [2021-03-25 16:06:02 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 970/1251] eta: 0:02:23 lr: 0.000870 loss: 3.7773 (3.6069) grad_norm: 1.0645 (1.0682) time: 0.5090 [2021-03-25 16:06:07 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 980/1251] eta: 0:02:18 lr: 0.000870 loss: 3.7576 (3.6060) grad_norm: 1.0866 (1.0680) time: 0.5015 [2021-03-25 16:06:13 swin_small_patch4_window7_224] INFO: Epoch: [70] [ 990/1251] eta: 0:02:13 lr: 0.000870 loss: 3.6062 (3.6072) grad_norm: 0.9799 (1.0672) time: 0.5102 [2021-03-25 16:06:18 swin_small_patch4_window7_224] INFO: Epoch: [70] [1000/1251] eta: 0:02:08 lr: 0.000870 loss: 3.6015 (3.6051) grad_norm: 0.9799 (1.0669) time: 0.5153 [2021-03-25 16:06:23 swin_small_patch4_window7_224] INFO: Epoch: [70] [1010/1251] eta: 0:02:03 lr: 0.000870 loss: 3.5678 (3.6039) grad_norm: 0.9962 (1.0665) time: 0.5109 [2021-03-25 16:06:28 swin_small_patch4_window7_224] INFO: Epoch: [70] [1020/1251] eta: 0:01:58 lr: 0.000870 loss: 3.9771 (3.6086) grad_norm: 0.9991 (1.0665) time: 0.5114 [2021-03-25 16:06:33 swin_small_patch4_window7_224] INFO: Epoch: [70] [1030/1251] eta: 0:01:52 lr: 0.000870 loss: 4.0645 (3.6117) grad_norm: 1.0341 (1.0664) time: 0.5103 [2021-03-25 16:06:38 swin_small_patch4_window7_224] INFO: Epoch: [70] [1040/1251] eta: 0:01:47 lr: 0.000870 loss: 3.7341 (3.6097) grad_norm: 1.0509 (1.0668) time: 0.5094 [2021-03-25 16:06:43 swin_small_patch4_window7_224] INFO: Epoch: [70] [1050/1251] eta: 0:01:42 lr: 0.000870 loss: 3.7179 (3.6126) grad_norm: 1.0501 (1.0668) time: 0.5079 [2021-03-25 16:06:48 swin_small_patch4_window7_224] INFO: Epoch: [70] [1060/1251] eta: 0:01:37 lr: 0.000870 loss: 3.9359 (3.6152) grad_norm: 1.0040 (1.0662) time: 0.5045 [2021-03-25 16:06:53 swin_small_patch4_window7_224] INFO: Epoch: [70] [1070/1251] eta: 0:01:32 lr: 0.000870 loss: 3.9359 (3.6149) grad_norm: 0.9983 (1.0658) time: 0.4997 [2021-03-25 16:06:58 swin_small_patch4_window7_224] INFO: Epoch: [70] [1080/1251] eta: 0:01:27 lr: 0.000870 loss: 3.6566 (3.6171) grad_norm: 1.0432 (1.0662) time: 0.5026 [2021-03-25 16:07:03 swin_small_patch4_window7_224] INFO: Epoch: [70] [1090/1251] eta: 0:01:22 lr: 0.000870 loss: 3.7914 (3.6178) grad_norm: 1.1099 (1.0666) time: 0.5030 [2021-03-25 16:07:08 swin_small_patch4_window7_224] INFO: Epoch: [70] [1100/1251] eta: 0:01:17 lr: 0.000870 loss: 3.6763 (3.6176) grad_norm: 1.0372 (1.0660) time: 0.5027 [2021-03-25 16:07:13 swin_small_patch4_window7_224] INFO: Epoch: [70] [1110/1251] eta: 0:01:11 lr: 0.000870 loss: 3.7200 (3.6168) grad_norm: 1.0025 (1.0661) time: 0.5026 [2021-03-25 16:07:18 swin_small_patch4_window7_224] INFO: Epoch: [70] [1120/1251] eta: 0:01:06 lr: 0.000870 loss: 3.8135 (3.6173) grad_norm: 0.9996 (1.0653) time: 0.5003 [2021-03-25 16:07:23 swin_small_patch4_window7_224] INFO: Epoch: [70] [1130/1251] eta: 0:01:01 lr: 0.000870 loss: 3.8135 (3.6177) grad_norm: 0.9858 (1.0650) time: 0.5051 [2021-03-25 16:07:28 swin_small_patch4_window7_224] INFO: Epoch: [70] [1140/1251] eta: 0:00:56 lr: 0.000870 loss: 3.6419 (3.6171) grad_norm: 1.0647 (1.0654) time: 0.5079 [2021-03-25 16:07:34 swin_small_patch4_window7_224] INFO: Epoch: [70] [1150/1251] eta: 0:00:51 lr: 0.000870 loss: 3.5906 (3.6170) grad_norm: 1.0755 (1.0661) time: 0.5064 [2021-03-25 16:07:39 swin_small_patch4_window7_224] INFO: Epoch: [70] [1160/1251] eta: 0:00:46 lr: 0.000870 loss: 3.8073 (3.6171) grad_norm: 1.0654 (1.0662) time: 0.5037 [2021-03-25 16:07:44 swin_small_patch4_window7_224] INFO: Epoch: [70] [1170/1251] eta: 0:00:41 lr: 0.000870 loss: 3.4519 (3.6148) grad_norm: 1.0557 (1.0662) time: 0.5040 [2021-03-25 16:07:49 swin_small_patch4_window7_224] INFO: Epoch: [70] [1180/1251] eta: 0:00:36 lr: 0.000870 loss: 3.3153 (3.6145) grad_norm: 1.0503 (1.0663) time: 0.5067 [2021-03-25 16:07:54 swin_small_patch4_window7_224] INFO: Epoch: [70] [1190/1251] eta: 0:00:31 lr: 0.000870 loss: 3.5320 (3.6145) grad_norm: 0.9900 (1.0658) time: 0.5145 [2021-03-25 16:07:59 swin_small_patch4_window7_224] INFO: Epoch: [70] [1200/1251] eta: 0:00:26 lr: 0.000870 loss: 3.6218 (3.6146) grad_norm: 0.9521 (1.0655) time: 0.5086 [2021-03-25 16:08:04 swin_small_patch4_window7_224] INFO: Epoch: [70] [1210/1251] eta: 0:00:20 lr: 0.000869 loss: 3.6661 (3.6139) grad_norm: 1.0405 (1.0657) time: 0.5018 [2021-03-25 16:08:09 swin_small_patch4_window7_224] INFO: Epoch: [70] [1220/1251] eta: 0:00:15 lr: 0.000869 loss: 3.5734 (3.6128) grad_norm: 1.0970 (1.0661) time: 0.5056 [2021-03-25 16:08:14 swin_small_patch4_window7_224] INFO: Epoch: [70] [1230/1251] eta: 0:00:10 lr: 0.000869 loss: 3.6364 (3.6140) grad_norm: 1.0279 (1.0654) time: 0.5053 [2021-03-25 16:08:19 swin_small_patch4_window7_224] INFO: Epoch: [70] [1240/1251] eta: 0:00:05 lr: 0.000869 loss: 3.6364 (3.6132) grad_norm: 1.0133 (1.0655) time: 0.5061 [2021-03-25 16:08:24 swin_small_patch4_window7_224] INFO: Epoch: [70] [1250/1251] eta: 0:00:00 lr: 0.000869 loss: 3.4594 (3.6114) grad_norm: 1.0267 (1.0653) time: 0.5062 [2021-03-25 16:09:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.2700 (1.2700) acc1: 71.8750 (71.8750) acc5: 90.6250 (90.6250) [2021-03-25 16:09:01 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.2815 (1.2120) acc1: 71.8750 (72.0170) acc5: 90.6250 (92.0455) [2021-03-25 16:09:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.1320 (1.1692) acc1: 71.8750 (72.3958) acc5: 90.6250 (91.8899) [2021-03-25 16:09:03 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0529 (1.1193) acc1: 73.4375 (73.5887) acc5: 92.1875 (92.1875) [2021-03-25 16:09:04 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0381 (1.1154) acc1: 75.0000 (73.8567) acc5: 92.1875 (92.1113) [2021-03-25 16:09:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0381 (1.1192) acc1: 75.0000 (73.6320) acc5: 92.1875 (92.2880) [2021-03-25 16:09:08 swin_small_patch4_window7_224] INFO: * Acc@1 74.318 Acc@5 92.564 loss 1.088 [2021-03-25 16:09:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.3% [2021-03-25 16:09:08 swin_small_patch4_window7_224] INFO: Max accuracy: 74.49% [2021-03-25 16:09:13 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 0/1251] eta: 1:26:22 lr: 0.000869 loss: 2.7663 (2.7663) grad_norm: 1.0859 (1.0859) time: 4.1428 [2021-03-25 16:09:18 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 10/1251] eta: 0:17:35 lr: 0.000869 loss: 3.6901 (3.6865) grad_norm: 0.9982 (1.0230) time: 0.8505 [2021-03-25 16:09:23 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 20/1251] eta: 0:14:08 lr: 0.000869 loss: 3.6901 (3.6827) grad_norm: 1.0166 (1.0331) time: 0.5168 [2021-03-25 16:09:28 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 30/1251] eta: 0:12:51 lr: 0.000869 loss: 3.4826 (3.5601) grad_norm: 1.0188 (1.0420) time: 0.5112 [2021-03-25 16:09:33 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 40/1251] eta: 0:12:09 lr: 0.000869 loss: 3.5285 (3.5552) grad_norm: 1.0188 (1.0407) time: 0.5116 [2021-03-25 16:09:38 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 50/1251] eta: 0:11:40 lr: 0.000869 loss: 3.5648 (3.5267) grad_norm: 1.0370 (1.0506) time: 0.5079 [2021-03-25 16:09:43 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 60/1251] eta: 0:11:20 lr: 0.000869 loss: 3.5371 (3.5636) grad_norm: 1.0640 (1.0523) time: 0.5080 [2021-03-25 16:09:48 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 70/1251] eta: 0:11:03 lr: 0.000869 loss: 3.7687 (3.5806) grad_norm: 1.0682 (1.0518) time: 0.5085 [2021-03-25 16:09:53 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 80/1251] eta: 0:10:52 lr: 0.000869 loss: 3.4398 (3.5608) grad_norm: 1.0741 (1.0605) time: 0.5122 [2021-03-25 16:09:59 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 90/1251] eta: 0:10:39 lr: 0.000869 loss: 3.6303 (3.5714) grad_norm: 1.0741 (1.0579) time: 0.5121 [2021-03-25 16:10:04 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 100/1251] eta: 0:10:29 lr: 0.000869 loss: 3.7876 (3.5796) grad_norm: 0.9675 (1.0542) time: 0.5075 [2021-03-25 16:10:09 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 110/1251] eta: 0:10:19 lr: 0.000869 loss: 3.9277 (3.6007) grad_norm: 0.9830 (1.0538) time: 0.5065 [2021-03-25 16:10:14 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 120/1251] eta: 0:10:10 lr: 0.000869 loss: 3.8039 (3.5965) grad_norm: 1.0161 (1.0530) time: 0.5013 [2021-03-25 16:10:19 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 130/1251] eta: 0:10:02 lr: 0.000869 loss: 3.4376 (3.5797) grad_norm: 1.0227 (1.0507) time: 0.5079 [2021-03-25 16:10:24 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 140/1251] eta: 0:09:54 lr: 0.000869 loss: 3.6242 (3.5863) grad_norm: 1.0227 (1.0494) time: 0.5098 [2021-03-25 16:10:29 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 150/1251] eta: 0:09:48 lr: 0.000869 loss: 3.8030 (3.5860) grad_norm: 1.0108 (1.0457) time: 0.5136 [2021-03-25 16:10:34 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 160/1251] eta: 0:09:41 lr: 0.000869 loss: 3.5808 (3.5763) grad_norm: 1.0490 (1.0506) time: 0.5165 [2021-03-25 16:10:39 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 170/1251] eta: 0:09:34 lr: 0.000869 loss: 3.5411 (3.5726) grad_norm: 1.0663 (1.0518) time: 0.5045 [2021-03-25 16:10:44 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 180/1251] eta: 0:09:27 lr: 0.000869 loss: 3.7696 (3.5887) grad_norm: 1.0447 (1.0507) time: 0.5052 [2021-03-25 16:10:49 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 190/1251] eta: 0:09:20 lr: 0.000869 loss: 3.7696 (3.5834) grad_norm: 1.0227 (1.0480) time: 0.5075 [2021-03-25 16:10:54 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 200/1251] eta: 0:09:14 lr: 0.000869 loss: 3.3625 (3.5654) grad_norm: 1.0360 (1.0512) time: 0.5075 [2021-03-25 16:11:00 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 210/1251] eta: 0:09:08 lr: 0.000869 loss: 3.6593 (3.5772) grad_norm: 1.1279 (1.0573) time: 0.5095 [2021-03-25 16:11:04 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 220/1251] eta: 0:09:01 lr: 0.000869 loss: 3.7081 (3.5695) grad_norm: 1.0389 (1.0559) time: 0.5009 [2021-03-25 16:11:10 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 230/1251] eta: 0:08:55 lr: 0.000869 loss: 3.5194 (3.5612) grad_norm: 0.9800 (1.0531) time: 0.4995 [2021-03-25 16:11:15 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 240/1251] eta: 0:08:49 lr: 0.000869 loss: 3.5589 (3.5669) grad_norm: 0.9446 (1.0506) time: 0.5060 [2021-03-25 16:11:20 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 250/1251] eta: 0:08:43 lr: 0.000869 loss: 3.4488 (3.5474) grad_norm: 1.0069 (1.0509) time: 0.5081 [2021-03-25 16:11:25 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 260/1251] eta: 0:08:37 lr: 0.000869 loss: 3.3160 (3.5488) grad_norm: 1.0069 (1.0503) time: 0.5091 [2021-03-25 16:11:30 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 270/1251] eta: 0:08:32 lr: 0.000869 loss: 3.6340 (3.5487) grad_norm: 1.0096 (1.0501) time: 0.5075 [2021-03-25 16:11:35 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 280/1251] eta: 0:08:26 lr: 0.000869 loss: 3.2710 (3.5398) grad_norm: 1.0169 (1.0501) time: 0.5032 [2021-03-25 16:11:40 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 290/1251] eta: 0:08:20 lr: 0.000869 loss: 3.2948 (3.5421) grad_norm: 1.0262 (1.0495) time: 0.5035 [2021-03-25 16:11:45 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 300/1251] eta: 0:08:14 lr: 0.000869 loss: 3.6495 (3.5419) grad_norm: 1.0576 (1.0513) time: 0.5042 [2021-03-25 16:11:50 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 310/1251] eta: 0:08:08 lr: 0.000868 loss: 3.7263 (3.5458) grad_norm: 1.1443 (1.0543) time: 0.5040 [2021-03-25 16:11:55 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 320/1251] eta: 0:08:03 lr: 0.000868 loss: 3.7873 (3.5491) grad_norm: 1.0843 (1.0547) time: 0.5084 [2021-03-25 16:12:00 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 330/1251] eta: 0:07:57 lr: 0.000868 loss: 3.6808 (3.5522) grad_norm: 1.0754 (1.0558) time: 0.5081 [2021-03-25 16:12:05 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 340/1251] eta: 0:07:52 lr: 0.000868 loss: 3.4320 (3.5482) grad_norm: 1.0759 (1.0575) time: 0.5106 [2021-03-25 16:12:10 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 350/1251] eta: 0:07:47 lr: 0.000868 loss: 3.2346 (3.5353) grad_norm: 1.0477 (1.0572) time: 0.5103 [2021-03-25 16:12:16 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 360/1251] eta: 0:07:41 lr: 0.000868 loss: 3.4143 (3.5326) grad_norm: 1.0163 (1.0554) time: 0.5084 [2021-03-25 16:12:21 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 370/1251] eta: 0:07:36 lr: 0.000868 loss: 3.6352 (3.5389) grad_norm: 1.0235 (1.0550) time: 0.5063 [2021-03-25 16:12:26 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 380/1251] eta: 0:07:30 lr: 0.000868 loss: 3.5901 (3.5398) grad_norm: 0.9850 (1.0522) time: 0.5032 [2021-03-25 16:12:31 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 390/1251] eta: 0:07:25 lr: 0.000868 loss: 3.5839 (3.5435) grad_norm: 0.9603 (1.0517) time: 0.5057 [2021-03-25 16:12:36 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 400/1251] eta: 0:07:19 lr: 0.000868 loss: 3.4024 (3.5404) grad_norm: 1.0000 (1.0506) time: 0.5067 [2021-03-25 16:12:41 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 410/1251] eta: 0:07:14 lr: 0.000868 loss: 3.2849 (3.5365) grad_norm: 1.0000 (1.0502) time: 0.5067 [2021-03-25 16:12:46 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 420/1251] eta: 0:07:09 lr: 0.000868 loss: 3.4235 (3.5357) grad_norm: 1.0314 (1.0510) time: 0.5072 [2021-03-25 16:12:51 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 430/1251] eta: 0:07:03 lr: 0.000868 loss: 3.4446 (3.5343) grad_norm: 1.0500 (1.0514) time: 0.5042 [2021-03-25 16:12:56 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 440/1251] eta: 0:06:58 lr: 0.000868 loss: 3.4446 (3.5335) grad_norm: 1.0680 (1.0526) time: 0.5038 [2021-03-25 16:13:01 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 450/1251] eta: 0:06:53 lr: 0.000868 loss: 3.7848 (3.5346) grad_norm: 1.0321 (1.0521) time: 0.5085 [2021-03-25 16:13:06 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 460/1251] eta: 0:06:47 lr: 0.000868 loss: 3.9629 (3.5406) grad_norm: 1.0313 (1.0531) time: 0.5043 [2021-03-25 16:13:11 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 470/1251] eta: 0:06:42 lr: 0.000868 loss: 3.8360 (3.5459) grad_norm: 1.1096 (1.0559) time: 0.5057 [2021-03-25 16:13:16 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 480/1251] eta: 0:06:37 lr: 0.000868 loss: 3.6488 (3.5490) grad_norm: 1.0867 (1.0555) time: 0.5123 [2021-03-25 16:13:21 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 490/1251] eta: 0:06:31 lr: 0.000868 loss: 3.6488 (3.5510) grad_norm: 1.0476 (1.0563) time: 0.5094 [2021-03-25 16:13:26 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 500/1251] eta: 0:06:26 lr: 0.000868 loss: 3.5470 (3.5469) grad_norm: 1.0426 (1.0555) time: 0.5042 [2021-03-25 16:13:32 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 510/1251] eta: 0:06:21 lr: 0.000868 loss: 3.3733 (3.5459) grad_norm: 1.0095 (1.0551) time: 0.5101 [2021-03-25 16:13:37 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 520/1251] eta: 0:06:16 lr: 0.000868 loss: 3.7129 (3.5507) grad_norm: 1.0606 (1.0564) time: 0.5186 [2021-03-25 16:13:42 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 530/1251] eta: 0:06:11 lr: 0.000868 loss: 3.6657 (3.5477) grad_norm: 1.0688 (1.0566) time: 0.5133 [2021-03-25 16:13:47 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 540/1251] eta: 0:06:05 lr: 0.000868 loss: 3.4562 (3.5503) grad_norm: 1.0488 (1.0569) time: 0.4999 [2021-03-25 16:13:52 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 550/1251] eta: 0:06:00 lr: 0.000868 loss: 3.5127 (3.5497) grad_norm: 1.0488 (1.0577) time: 0.5059 [2021-03-25 16:13:57 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 560/1251] eta: 0:05:55 lr: 0.000868 loss: 3.4868 (3.5483) grad_norm: 1.0785 (1.0579) time: 0.5165 [2021-03-25 16:14:02 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 570/1251] eta: 0:05:50 lr: 0.000868 loss: 3.6316 (3.5516) grad_norm: 1.0785 (1.0581) time: 0.5144 [2021-03-25 16:14:07 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 580/1251] eta: 0:05:45 lr: 0.000868 loss: 3.6316 (3.5471) grad_norm: 1.0809 (1.0596) time: 0.5058 [2021-03-25 16:14:12 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 590/1251] eta: 0:05:39 lr: 0.000868 loss: 3.5285 (3.5501) grad_norm: 1.1026 (1.0599) time: 0.5072 [2021-03-25 16:14:17 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 600/1251] eta: 0:05:34 lr: 0.000868 loss: 3.6055 (3.5496) grad_norm: 1.0557 (1.0601) time: 0.5124 [2021-03-25 16:14:22 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 610/1251] eta: 0:05:29 lr: 0.000868 loss: 3.7214 (3.5553) grad_norm: 1.0557 (1.0613) time: 0.5058 [2021-03-25 16:14:27 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 620/1251] eta: 0:05:24 lr: 0.000868 loss: 3.7068 (3.5569) grad_norm: 1.0662 (1.0610) time: 0.5005 [2021-03-25 16:14:33 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 630/1251] eta: 0:05:18 lr: 0.000868 loss: 3.6878 (3.5585) grad_norm: 1.0308 (1.0610) time: 0.5007 [2021-03-25 16:14:38 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 640/1251] eta: 0:05:13 lr: 0.000868 loss: 3.6878 (3.5590) grad_norm: 1.0308 (1.0609) time: 0.5053 [2021-03-25 16:14:43 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 650/1251] eta: 0:05:08 lr: 0.000868 loss: 3.7145 (3.5614) grad_norm: 1.0425 (1.0615) time: 0.5097 [2021-03-25 16:14:48 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 660/1251] eta: 0:05:03 lr: 0.000868 loss: 3.8746 (3.5638) grad_norm: 1.0810 (1.0622) time: 0.5060 [2021-03-25 16:14:53 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 670/1251] eta: 0:04:58 lr: 0.000867 loss: 4.0057 (3.5666) grad_norm: 1.0561 (1.0618) time: 0.5001 [2021-03-25 16:14:58 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 680/1251] eta: 0:04:52 lr: 0.000867 loss: 3.5933 (3.5665) grad_norm: 1.0311 (1.0617) time: 0.4995 [2021-03-25 16:15:03 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 690/1251] eta: 0:04:47 lr: 0.000867 loss: 3.6979 (3.5702) grad_norm: 1.0237 (1.0606) time: 0.5069 [2021-03-25 16:15:08 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 700/1251] eta: 0:04:42 lr: 0.000867 loss: 3.7552 (3.5697) grad_norm: 0.9919 (1.0595) time: 0.5093 [2021-03-25 16:15:13 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 710/1251] eta: 0:04:37 lr: 0.000867 loss: 3.8091 (3.5694) grad_norm: 1.0218 (1.0602) time: 0.5074 [2021-03-25 16:15:18 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 720/1251] eta: 0:04:32 lr: 0.000867 loss: 3.6395 (3.5682) grad_norm: 1.0910 (1.0598) time: 0.5125 [2021-03-25 16:15:23 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 730/1251] eta: 0:04:27 lr: 0.000867 loss: 3.6395 (3.5686) grad_norm: 1.0286 (1.0601) time: 0.5137 [2021-03-25 16:15:29 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 740/1251] eta: 0:04:22 lr: 0.000867 loss: 3.7002 (3.5697) grad_norm: 1.0319 (1.0599) time: 0.5251 [2021-03-25 16:15:34 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 750/1251] eta: 0:04:17 lr: 0.000867 loss: 3.6989 (3.5671) grad_norm: 1.0224 (1.0595) time: 0.5226 [2021-03-25 16:15:39 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 760/1251] eta: 0:04:11 lr: 0.000867 loss: 3.6240 (3.5691) grad_norm: 1.0013 (1.0587) time: 0.5063 [2021-03-25 16:15:44 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 770/1251] eta: 0:04:06 lr: 0.000867 loss: 3.7504 (3.5722) grad_norm: 0.9937 (1.0595) time: 0.5035 [2021-03-25 16:15:49 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 780/1251] eta: 0:04:01 lr: 0.000867 loss: 3.7060 (3.5734) grad_norm: 1.0783 (1.0611) time: 0.5082 [2021-03-25 16:15:54 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 790/1251] eta: 0:03:56 lr: 0.000867 loss: 3.5725 (3.5758) grad_norm: 1.1163 (1.0615) time: 0.5160 [2021-03-25 16:15:59 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 800/1251] eta: 0:03:51 lr: 0.000867 loss: 3.8801 (3.5808) grad_norm: 1.1067 (1.0621) time: 0.5159 [2021-03-25 16:16:04 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 810/1251] eta: 0:03:46 lr: 0.000867 loss: 3.7457 (3.5778) grad_norm: 1.0590 (1.0619) time: 0.5060 [2021-03-25 16:16:09 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 820/1251] eta: 0:03:40 lr: 0.000867 loss: 3.2955 (3.5770) grad_norm: 1.0275 (1.0614) time: 0.5044 [2021-03-25 16:16:14 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 830/1251] eta: 0:03:35 lr: 0.000867 loss: 3.7856 (3.5816) grad_norm: 0.9964 (1.0609) time: 0.5104 [2021-03-25 16:16:20 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 840/1251] eta: 0:03:30 lr: 0.000867 loss: 3.7934 (3.5808) grad_norm: 1.0086 (1.0611) time: 0.5093 [2021-03-25 16:16:25 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 850/1251] eta: 0:03:25 lr: 0.000867 loss: 3.5344 (3.5801) grad_norm: 1.0086 (1.0608) time: 0.5103 [2021-03-25 16:16:30 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 860/1251] eta: 0:03:20 lr: 0.000867 loss: 3.6542 (3.5821) grad_norm: 1.0106 (1.0606) time: 0.5097 [2021-03-25 16:16:35 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 870/1251] eta: 0:03:15 lr: 0.000867 loss: 3.6625 (3.5811) grad_norm: 1.0145 (1.0599) time: 0.5012 [2021-03-25 16:16:40 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 880/1251] eta: 0:03:10 lr: 0.000867 loss: 3.6918 (3.5811) grad_norm: 1.0030 (1.0598) time: 0.5076 [2021-03-25 16:16:45 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 890/1251] eta: 0:03:04 lr: 0.000867 loss: 3.4980 (3.5804) grad_norm: 1.0041 (1.0593) time: 0.5124 [2021-03-25 16:16:50 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 900/1251] eta: 0:02:59 lr: 0.000867 loss: 3.5782 (3.5816) grad_norm: 1.0219 (inf) time: 0.5055 [2021-03-25 16:16:55 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 910/1251] eta: 0:02:54 lr: 0.000867 loss: 3.7440 (3.5801) grad_norm: 1.0983 (inf) time: 0.5039 [2021-03-25 16:17:00 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 920/1251] eta: 0:02:49 lr: 0.000867 loss: 3.6232 (3.5790) grad_norm: 1.1442 (inf) time: 0.5077 [2021-03-25 16:17:05 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 930/1251] eta: 0:02:44 lr: 0.000867 loss: 3.6266 (3.5807) grad_norm: 1.0882 (inf) time: 0.5108 [2021-03-25 16:17:10 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 940/1251] eta: 0:02:39 lr: 0.000867 loss: 3.6266 (3.5796) grad_norm: 1.0349 (inf) time: 0.5050 [2021-03-25 16:17:15 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 950/1251] eta: 0:02:34 lr: 0.000867 loss: 3.8148 (3.5832) grad_norm: 1.0349 (inf) time: 0.5031 [2021-03-25 16:17:20 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 960/1251] eta: 0:02:28 lr: 0.000867 loss: 3.9718 (3.5851) grad_norm: 1.0278 (inf) time: 0.5023 [2021-03-25 16:17:25 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 970/1251] eta: 0:02:23 lr: 0.000867 loss: 3.7455 (3.5851) grad_norm: 1.0573 (inf) time: 0.5027 [2021-03-25 16:17:30 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 980/1251] eta: 0:02:18 lr: 0.000867 loss: 3.9071 (3.5868) grad_norm: 1.0524 (inf) time: 0.5049 [2021-03-25 16:17:35 swin_small_patch4_window7_224] INFO: Epoch: [71] [ 990/1251] eta: 0:02:13 lr: 0.000867 loss: 3.9327 (3.5881) grad_norm: 1.0017 (inf) time: 0.5040 [2021-03-25 16:17:41 swin_small_patch4_window7_224] INFO: Epoch: [71] [1000/1251] eta: 0:02:08 lr: 0.000867 loss: 3.8627 (3.5891) grad_norm: 1.0183 (inf) time: 0.5109 [2021-03-25 16:17:46 swin_small_patch4_window7_224] INFO: Epoch: [71] [1010/1251] eta: 0:02:03 lr: 0.000867 loss: 3.8627 (3.5909) grad_norm: 1.0659 (inf) time: 0.5142 [2021-03-25 16:17:51 swin_small_patch4_window7_224] INFO: Epoch: [71] [1020/1251] eta: 0:01:58 lr: 0.000866 loss: 3.6556 (3.5903) grad_norm: 1.0602 (inf) time: 0.5079 [2021-03-25 16:17:56 swin_small_patch4_window7_224] INFO: Epoch: [71] [1030/1251] eta: 0:01:53 lr: 0.000866 loss: 3.3703 (3.5882) grad_norm: 1.0304 (inf) time: 0.5058 [2021-03-25 16:18:01 swin_small_patch4_window7_224] INFO: Epoch: [71] [1040/1251] eta: 0:01:47 lr: 0.000866 loss: 3.2961 (3.5879) grad_norm: 1.1003 (inf) time: 0.5067 [2021-03-25 16:18:06 swin_small_patch4_window7_224] INFO: Epoch: [71] [1050/1251] eta: 0:01:42 lr: 0.000866 loss: 3.4775 (3.5861) grad_norm: 1.1034 (inf) time: 0.5032 [2021-03-25 16:18:11 swin_small_patch4_window7_224] INFO: Epoch: [71] [1060/1251] eta: 0:01:37 lr: 0.000866 loss: 3.5219 (3.5878) grad_norm: 1.0441 (inf) time: 0.5040 [2021-03-25 16:18:16 swin_small_patch4_window7_224] INFO: Epoch: [71] [1070/1251] eta: 0:01:32 lr: 0.000866 loss: 3.7730 (3.5876) grad_norm: 1.0441 (inf) time: 0.5060 [2021-03-25 16:18:21 swin_small_patch4_window7_224] INFO: Epoch: [71] [1080/1251] eta: 0:01:27 lr: 0.000866 loss: 3.6631 (3.5877) grad_norm: 1.1279 (inf) time: 0.5032 [2021-03-25 16:18:26 swin_small_patch4_window7_224] INFO: Epoch: [71] [1090/1251] eta: 0:01:22 lr: 0.000866 loss: 3.9337 (3.5910) grad_norm: 1.1039 (inf) time: 0.5046 [2021-03-25 16:18:31 swin_small_patch4_window7_224] INFO: Epoch: [71] [1100/1251] eta: 0:01:17 lr: 0.000866 loss: 3.7774 (3.5890) grad_norm: 0.9871 (inf) time: 0.5082 [2021-03-25 16:18:36 swin_small_patch4_window7_224] INFO: Epoch: [71] [1110/1251] eta: 0:01:12 lr: 0.000866 loss: 3.4216 (3.5862) grad_norm: 1.0159 (inf) time: 0.5090 [2021-03-25 16:18:41 swin_small_patch4_window7_224] INFO: Epoch: [71] [1120/1251] eta: 0:01:06 lr: 0.000866 loss: 3.4293 (3.5863) grad_norm: 1.0294 (inf) time: 0.5028 [2021-03-25 16:18:46 swin_small_patch4_window7_224] INFO: Epoch: [71] [1130/1251] eta: 0:01:01 lr: 0.000866 loss: 3.7741 (3.5875) grad_norm: 1.0294 (inf) time: 0.4978 [2021-03-25 16:18:51 swin_small_patch4_window7_224] INFO: Epoch: [71] [1140/1251] eta: 0:00:56 lr: 0.000866 loss: 3.5772 (3.5875) grad_norm: 1.0649 (inf) time: 0.4997 [2021-03-25 16:18:56 swin_small_patch4_window7_224] INFO: Epoch: [71] [1150/1251] eta: 0:00:51 lr: 0.000866 loss: 3.8745 (3.5902) grad_norm: 1.0939 (inf) time: 0.5055 [2021-03-25 16:19:01 swin_small_patch4_window7_224] INFO: Epoch: [71] [1160/1251] eta: 0:00:46 lr: 0.000866 loss: 3.8745 (3.5888) grad_norm: 1.0182 (inf) time: 0.5079 [2021-03-25 16:19:07 swin_small_patch4_window7_224] INFO: Epoch: [71] [1170/1251] eta: 0:00:41 lr: 0.000866 loss: 3.4747 (3.5883) grad_norm: 0.9998 (inf) time: 0.5046 [2021-03-25 16:19:12 swin_small_patch4_window7_224] INFO: Epoch: [71] [1180/1251] eta: 0:00:36 lr: 0.000866 loss: 3.3171 (3.5866) grad_norm: 0.9641 (inf) time: 0.5047 [2021-03-25 16:19:17 swin_small_patch4_window7_224] INFO: Epoch: [71] [1190/1251] eta: 0:00:31 lr: 0.000866 loss: 3.2732 (3.5830) grad_norm: 0.9858 (inf) time: 0.5061 [2021-03-25 16:19:22 swin_small_patch4_window7_224] INFO: Epoch: [71] [1200/1251] eta: 0:00:26 lr: 0.000866 loss: 3.4292 (3.5832) grad_norm: 1.0145 (inf) time: 0.5055 [2021-03-25 16:19:27 swin_small_patch4_window7_224] INFO: Epoch: [71] [1210/1251] eta: 0:00:20 lr: 0.000866 loss: 3.6364 (3.5833) grad_norm: 1.0888 (inf) time: 0.5041 [2021-03-25 16:19:32 swin_small_patch4_window7_224] INFO: Epoch: [71] [1220/1251] eta: 0:00:15 lr: 0.000866 loss: 3.6432 (3.5827) grad_norm: 1.0965 (inf) time: 0.5025 [2021-03-25 16:19:37 swin_small_patch4_window7_224] INFO: Epoch: [71] [1230/1251] eta: 0:00:10 lr: 0.000866 loss: 3.6432 (3.5828) grad_norm: 1.0662 (inf) time: 0.5074 [2021-03-25 16:19:42 swin_small_patch4_window7_224] INFO: Epoch: [71] [1240/1251] eta: 0:00:05 lr: 0.000866 loss: 3.7466 (3.5820) grad_norm: 1.1052 (inf) time: 0.5062 [2021-03-25 16:19:47 swin_small_patch4_window7_224] INFO: Epoch: [71] [1250/1251] eta: 0:00:00 lr: 0.000866 loss: 3.5604 (3.5818) grad_norm: 1.0446 (inf) time: 0.5054 [2021-03-25 16:19:51 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:30 loss: 0.9813 (0.9813) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.7500) [2021-03-25 16:19:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.1661 (1.1270) acc1: 73.4375 (74.7159) acc5: 93.7500 (92.6136) [2021-03-25 16:19:56 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1310 (1.1072) acc1: 73.4375 (75.1488) acc5: 93.7500 (92.4107) [2021-03-25 16:19:58 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.1507 (1.1294) acc1: 71.8750 (74.6976) acc5: 92.1875 (92.1875) [2021-03-25 16:20:00 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1507 (1.1195) acc1: 71.8750 (74.6189) acc5: 92.1875 (92.3780) [2021-03-25 16:20:01 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0964 (1.1227) acc1: 71.8750 (74.1120) acc5: 93.7500 (92.5440) [2021-03-25 16:20:04 swin_small_patch4_window7_224] INFO: * Acc@1 74.494 Acc@5 92.644 loss 1.090 [2021-03-25 16:20:04 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.5% [2021-03-25 16:20:04 swin_small_patch4_window7_224] INFO: Max accuracy: 74.49% [2021-03-25 16:20:08 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 0/1251] eta: 1:29:48 lr: 0.000866 loss: 3.6705 (3.6705) grad_norm: 1.0462 (1.0462) time: 4.3077 [2021-03-25 16:20:13 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 10/1251] eta: 0:17:41 lr: 0.000866 loss: 3.6912 (3.6182) grad_norm: 1.0256 (1.0122) time: 0.8550 [2021-03-25 16:20:18 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 20/1251] eta: 0:14:15 lr: 0.000866 loss: 3.6701 (3.5763) grad_norm: 1.0118 (1.0278) time: 0.5141 [2021-03-25 16:20:23 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 30/1251] eta: 0:12:56 lr: 0.000866 loss: 3.6097 (3.5749) grad_norm: 1.0499 (1.0349) time: 0.5159 [2021-03-25 16:20:28 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 40/1251] eta: 0:12:13 lr: 0.000866 loss: 3.6572 (3.6241) grad_norm: 1.0547 (1.0579) time: 0.5116 [2021-03-25 16:20:33 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 50/1251] eta: 0:11:42 lr: 0.000866 loss: 3.6572 (3.6086) grad_norm: 1.0310 (1.0517) time: 0.5063 [2021-03-25 16:20:38 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 60/1251] eta: 0:11:20 lr: 0.000866 loss: 3.7594 (3.6407) grad_norm: 1.0310 (1.0537) time: 0.5020 [2021-03-25 16:20:44 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 70/1251] eta: 0:11:03 lr: 0.000866 loss: 3.7511 (3.6225) grad_norm: 1.0326 (1.0539) time: 0.5025 [2021-03-25 16:20:49 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 80/1251] eta: 0:10:49 lr: 0.000866 loss: 3.5288 (3.6015) grad_norm: 1.0609 (1.0594) time: 0.5025 [2021-03-25 16:20:54 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 90/1251] eta: 0:10:37 lr: 0.000866 loss: 3.4671 (3.5698) grad_norm: 1.0609 (1.0633) time: 0.5019 [2021-03-25 16:20:59 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 100/1251] eta: 0:10:27 lr: 0.000866 loss: 3.3699 (3.5557) grad_norm: 1.0760 (1.0668) time: 0.5094 [2021-03-25 16:21:04 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 110/1251] eta: 0:10:18 lr: 0.000866 loss: 3.8500 (3.5873) grad_norm: 1.0683 (1.0680) time: 0.5101 [2021-03-25 16:21:09 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 120/1251] eta: 0:10:10 lr: 0.000865 loss: 3.8921 (3.5948) grad_norm: 1.0711 (1.0717) time: 0.5082 [2021-03-25 16:21:14 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 130/1251] eta: 0:10:01 lr: 0.000865 loss: 3.6776 (3.5854) grad_norm: 1.1203 (1.0781) time: 0.5070 [2021-03-25 16:21:19 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 140/1251] eta: 0:09:53 lr: 0.000865 loss: 3.7520 (3.5964) grad_norm: 1.0907 (1.0782) time: 0.5032 [2021-03-25 16:21:24 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 150/1251] eta: 0:09:46 lr: 0.000865 loss: 3.6365 (3.5792) grad_norm: 1.0467 (1.0778) time: 0.5095 [2021-03-25 16:21:29 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 160/1251] eta: 0:09:39 lr: 0.000865 loss: 3.5032 (3.5821) grad_norm: 1.0381 (1.0763) time: 0.5122 [2021-03-25 16:21:34 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 170/1251] eta: 0:09:33 lr: 0.000865 loss: 3.7005 (3.5826) grad_norm: 1.0379 (1.0736) time: 0.5153 [2021-03-25 16:21:40 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 180/1251] eta: 0:09:27 lr: 0.000865 loss: 3.7005 (3.5965) grad_norm: 1.0058 (1.0687) time: 0.5177 [2021-03-25 16:21:45 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 190/1251] eta: 0:09:20 lr: 0.000865 loss: 3.8092 (3.5995) grad_norm: 1.0454 (1.0708) time: 0.5102 [2021-03-25 16:21:50 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 200/1251] eta: 0:09:14 lr: 0.000865 loss: 3.8440 (3.6038) grad_norm: 1.0693 (1.0725) time: 0.5082 [2021-03-25 16:21:55 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 210/1251] eta: 0:09:09 lr: 0.000865 loss: 3.8440 (3.6087) grad_norm: 1.0204 (1.0698) time: 0.5154 [2021-03-25 16:22:00 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 220/1251] eta: 0:09:02 lr: 0.000865 loss: 3.6450 (3.5979) grad_norm: 1.0204 (1.0729) time: 0.5096 [2021-03-25 16:22:05 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 230/1251] eta: 0:08:55 lr: 0.000865 loss: 3.3070 (3.5898) grad_norm: 1.1448 (1.0768) time: 0.4991 [2021-03-25 16:22:10 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 240/1251] eta: 0:08:49 lr: 0.000865 loss: 3.4665 (3.5811) grad_norm: 1.1854 (1.0835) time: 0.5009 [2021-03-25 16:22:15 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 250/1251] eta: 0:08:43 lr: 0.000865 loss: 3.6614 (3.5868) grad_norm: 1.2081 (1.0866) time: 0.5024 [2021-03-25 16:22:20 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 260/1251] eta: 0:08:37 lr: 0.000865 loss: 3.7144 (3.5843) grad_norm: 1.1269 (1.0886) time: 0.5052 [2021-03-25 16:22:25 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 270/1251] eta: 0:08:31 lr: 0.000865 loss: 3.4328 (3.5708) grad_norm: 1.1117 (1.0882) time: 0.5049 [2021-03-25 16:22:30 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 280/1251] eta: 0:08:26 lr: 0.000865 loss: 3.7743 (3.5778) grad_norm: 1.0882 (1.0886) time: 0.5058 [2021-03-25 16:22:35 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 290/1251] eta: 0:08:20 lr: 0.000865 loss: 3.3682 (3.5644) grad_norm: 1.0880 (1.0894) time: 0.5084 [2021-03-25 16:22:40 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 300/1251] eta: 0:08:15 lr: 0.000865 loss: 3.6404 (3.5752) grad_norm: 1.0375 (1.0873) time: 0.5079 [2021-03-25 16:22:45 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 310/1251] eta: 0:08:09 lr: 0.000865 loss: 3.6886 (3.5726) grad_norm: 1.0375 (1.0871) time: 0.5066 [2021-03-25 16:22:50 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 320/1251] eta: 0:08:03 lr: 0.000865 loss: 3.5284 (3.5724) grad_norm: 1.0821 (1.0887) time: 0.5041 [2021-03-25 16:22:55 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 330/1251] eta: 0:07:58 lr: 0.000865 loss: 3.6577 (3.5715) grad_norm: 1.0772 (1.0871) time: 0.5051 [2021-03-25 16:23:00 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 340/1251] eta: 0:07:52 lr: 0.000865 loss: 4.0167 (3.5840) grad_norm: 1.0582 (1.0872) time: 0.5023 [2021-03-25 16:23:06 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 350/1251] eta: 0:07:46 lr: 0.000865 loss: 4.0167 (3.5913) grad_norm: 1.0215 (1.0841) time: 0.5046 [2021-03-25 16:23:11 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 360/1251] eta: 0:07:41 lr: 0.000865 loss: 3.6152 (3.5943) grad_norm: 1.0229 (1.0833) time: 0.5042 [2021-03-25 16:23:16 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 370/1251] eta: 0:07:35 lr: 0.000865 loss: 3.6558 (3.5942) grad_norm: 1.0538 (1.0824) time: 0.5036 [2021-03-25 16:23:21 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 380/1251] eta: 0:07:30 lr: 0.000865 loss: 3.6558 (3.5944) grad_norm: 1.0515 (1.0825) time: 0.5049 [2021-03-25 16:23:26 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 390/1251] eta: 0:07:24 lr: 0.000865 loss: 3.3490 (3.5874) grad_norm: 1.0739 (1.0827) time: 0.5024 [2021-03-25 16:23:31 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 400/1251] eta: 0:07:19 lr: 0.000865 loss: 3.5931 (3.5906) grad_norm: 1.0200 (1.0824) time: 0.5040 [2021-03-25 16:23:36 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 410/1251] eta: 0:07:13 lr: 0.000865 loss: 3.6883 (3.5917) grad_norm: 1.0193 (1.0811) time: 0.5024 [2021-03-25 16:23:41 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 420/1251] eta: 0:07:08 lr: 0.000865 loss: 3.7072 (3.5957) grad_norm: 1.0061 (1.0794) time: 0.5043 [2021-03-25 16:23:46 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 430/1251] eta: 0:07:03 lr: 0.000865 loss: 3.7094 (3.5950) grad_norm: 1.0164 (1.0789) time: 0.5017 [2021-03-25 16:23:51 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 440/1251] eta: 0:06:57 lr: 0.000865 loss: 3.7069 (3.5949) grad_norm: 1.0191 (1.0788) time: 0.4992 [2021-03-25 16:23:56 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 450/1251] eta: 0:06:52 lr: 0.000865 loss: 3.7069 (3.5904) grad_norm: 1.0849 (1.0796) time: 0.5013 [2021-03-25 16:24:01 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 460/1251] eta: 0:06:46 lr: 0.000865 loss: 3.7929 (3.5959) grad_norm: 1.0652 (1.0789) time: 0.5001 [2021-03-25 16:24:06 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 470/1251] eta: 0:06:41 lr: 0.000865 loss: 3.7904 (3.5956) grad_norm: 1.0505 (1.0792) time: 0.5017 [2021-03-25 16:24:11 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 480/1251] eta: 0:06:36 lr: 0.000864 loss: 3.8202 (3.6007) grad_norm: 1.0724 (1.0798) time: 0.5017 [2021-03-25 16:24:16 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 490/1251] eta: 0:06:30 lr: 0.000864 loss: 3.8627 (3.6000) grad_norm: 1.0525 (1.0788) time: 0.5023 [2021-03-25 16:24:21 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 500/1251] eta: 0:06:25 lr: 0.000864 loss: 3.5289 (3.5954) grad_norm: 1.0285 (1.0790) time: 0.5029 [2021-03-25 16:24:26 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 510/1251] eta: 0:06:20 lr: 0.000864 loss: 3.2367 (3.5919) grad_norm: 1.0294 (1.0782) time: 0.5002 [2021-03-25 16:24:31 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 520/1251] eta: 0:06:14 lr: 0.000864 loss: 3.5075 (3.5905) grad_norm: 1.0909 (1.0794) time: 0.5004 [2021-03-25 16:24:36 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 530/1251] eta: 0:06:09 lr: 0.000864 loss: 3.5825 (3.5900) grad_norm: 1.1251 (1.0798) time: 0.5022 [2021-03-25 16:24:41 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 540/1251] eta: 0:06:04 lr: 0.000864 loss: 3.7584 (3.5914) grad_norm: 1.0645 (1.0801) time: 0.5038 [2021-03-25 16:24:46 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 550/1251] eta: 0:05:59 lr: 0.000864 loss: 3.6537 (3.5867) grad_norm: 0.9952 (1.0785) time: 0.5105 [2021-03-25 16:24:51 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 560/1251] eta: 0:05:54 lr: 0.000864 loss: 3.5066 (3.5883) grad_norm: 0.9910 (1.0777) time: 0.5065 [2021-03-25 16:24:56 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 570/1251] eta: 0:05:48 lr: 0.000864 loss: 3.6089 (3.5850) grad_norm: 1.0176 (1.0767) time: 0.4977 [2021-03-25 16:25:01 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 580/1251] eta: 0:05:43 lr: 0.000864 loss: 3.6089 (3.5865) grad_norm: 1.0721 (1.0777) time: 0.5055 [2021-03-25 16:25:06 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 590/1251] eta: 0:05:38 lr: 0.000864 loss: 3.6039 (3.5836) grad_norm: 1.1370 (1.0796) time: 0.5114 [2021-03-25 16:25:11 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 600/1251] eta: 0:05:33 lr: 0.000864 loss: 3.4348 (3.5801) grad_norm: 1.0919 (1.0798) time: 0.5012 [2021-03-25 16:25:16 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 610/1251] eta: 0:05:27 lr: 0.000864 loss: 3.5760 (3.5812) grad_norm: 0.9980 (1.0788) time: 0.4930 [2021-03-25 16:25:21 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 620/1251] eta: 0:05:22 lr: 0.000864 loss: 3.6873 (3.5819) grad_norm: 0.9835 (1.0773) time: 0.5036 [2021-03-25 16:25:26 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 630/1251] eta: 0:05:17 lr: 0.000864 loss: 3.7762 (3.5856) grad_norm: 0.9694 (1.0759) time: 0.5119 [2021-03-25 16:25:32 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 640/1251] eta: 0:05:12 lr: 0.000864 loss: 3.8719 (3.5910) grad_norm: 1.0114 (1.0762) time: 0.5108 [2021-03-25 16:25:37 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 650/1251] eta: 0:05:07 lr: 0.000864 loss: 3.8719 (3.5944) grad_norm: 1.0594 (1.0761) time: 0.5106 [2021-03-25 16:25:42 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 660/1251] eta: 0:05:02 lr: 0.000864 loss: 3.8468 (3.5945) grad_norm: 1.0994 (1.0765) time: 0.5055 [2021-03-25 16:25:47 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 670/1251] eta: 0:04:56 lr: 0.000864 loss: 3.6476 (3.5939) grad_norm: 1.1125 (1.0778) time: 0.5020 [2021-03-25 16:25:52 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 680/1251] eta: 0:04:51 lr: 0.000864 loss: 3.2981 (3.5918) grad_norm: 1.0844 (1.0785) time: 0.4998 [2021-03-25 16:25:57 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 690/1251] eta: 0:04:46 lr: 0.000864 loss: 3.5575 (3.5943) grad_norm: 1.0844 (1.0784) time: 0.5031 [2021-03-25 16:26:02 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 700/1251] eta: 0:04:41 lr: 0.000864 loss: 3.6617 (3.5943) grad_norm: 1.0920 (1.0795) time: 0.5062 [2021-03-25 16:26:07 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 710/1251] eta: 0:04:36 lr: 0.000864 loss: 3.7556 (3.5961) grad_norm: 1.1394 (1.0807) time: 0.5052 [2021-03-25 16:26:12 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 720/1251] eta: 0:04:31 lr: 0.000864 loss: 3.8432 (3.5986) grad_norm: 1.0990 (1.0801) time: 0.5122 [2021-03-25 16:26:17 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 730/1251] eta: 0:04:26 lr: 0.000864 loss: 3.5314 (3.5975) grad_norm: 0.9447 (1.0783) time: 0.5081 [2021-03-25 16:26:22 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 740/1251] eta: 0:04:21 lr: 0.000864 loss: 3.4586 (3.5965) grad_norm: 0.9447 (1.0770) time: 0.5146 [2021-03-25 16:26:27 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 750/1251] eta: 0:04:15 lr: 0.000864 loss: 3.7121 (3.5962) grad_norm: 0.9906 (1.0771) time: 0.5185 [2021-03-25 16:26:33 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 760/1251] eta: 0:04:10 lr: 0.000864 loss: 3.7909 (3.5980) grad_norm: 1.0979 (1.0778) time: 0.5178 [2021-03-25 16:26:38 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 770/1251] eta: 0:04:05 lr: 0.000864 loss: 3.6402 (3.5961) grad_norm: 1.0899 (1.0779) time: 0.5225 [2021-03-25 16:26:43 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 780/1251] eta: 0:04:00 lr: 0.000864 loss: 3.7611 (3.5973) grad_norm: 1.0856 (1.0788) time: 0.5151 [2021-03-25 16:26:48 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 790/1251] eta: 0:03:55 lr: 0.000864 loss: 3.9654 (3.6021) grad_norm: 1.0717 (1.0785) time: 0.5092 [2021-03-25 16:26:53 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 800/1251] eta: 0:03:50 lr: 0.000864 loss: 4.0934 (3.6042) grad_norm: 1.0416 (1.0777) time: 0.5033 [2021-03-25 16:26:58 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 810/1251] eta: 0:03:45 lr: 0.000864 loss: 3.7856 (3.6060) grad_norm: 1.0291 (1.0773) time: 0.5074 [2021-03-25 16:27:03 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 820/1251] eta: 0:03:40 lr: 0.000864 loss: 3.7835 (3.6060) grad_norm: 1.0552 (1.0771) time: 0.5025 [2021-03-25 16:27:08 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 830/1251] eta: 0:03:34 lr: 0.000863 loss: 3.7558 (3.6082) grad_norm: 1.0239 (1.0766) time: 0.4926 [2021-03-25 16:27:13 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 840/1251] eta: 0:03:29 lr: 0.000863 loss: 3.6258 (3.6061) grad_norm: 1.0239 (1.0762) time: 0.5000 [2021-03-25 16:27:18 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 850/1251] eta: 0:03:24 lr: 0.000863 loss: 3.8630 (3.6088) grad_norm: 1.0368 (1.0757) time: 0.5043 [2021-03-25 16:27:23 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 860/1251] eta: 0:03:19 lr: 0.000863 loss: 3.9043 (3.6103) grad_norm: 1.0273 (1.0762) time: 0.5054 [2021-03-25 16:27:28 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 870/1251] eta: 0:03:14 lr: 0.000863 loss: 3.6517 (3.6095) grad_norm: 1.0425 (1.0759) time: 0.5050 [2021-03-25 16:27:33 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 880/1251] eta: 0:03:09 lr: 0.000863 loss: 3.6184 (3.6093) grad_norm: 1.0873 (1.0765) time: 0.4989 [2021-03-25 16:27:38 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 890/1251] eta: 0:03:04 lr: 0.000863 loss: 3.6522 (3.6104) grad_norm: 1.0873 (1.0765) time: 0.5003 [2021-03-25 16:27:43 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 900/1251] eta: 0:02:59 lr: 0.000863 loss: 3.8323 (3.6119) grad_norm: 1.0224 (1.0770) time: 0.5102 [2021-03-25 16:27:49 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 910/1251] eta: 0:02:53 lr: 0.000863 loss: 3.7184 (3.6116) grad_norm: 1.0663 (1.0768) time: 0.5147 [2021-03-25 16:27:54 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 920/1251] eta: 0:02:48 lr: 0.000863 loss: 3.7184 (3.6126) grad_norm: 1.0432 (1.0766) time: 0.5070 [2021-03-25 16:27:59 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 930/1251] eta: 0:02:43 lr: 0.000863 loss: 3.7056 (3.6115) grad_norm: 1.0664 (1.0770) time: 0.5039 [2021-03-25 16:28:04 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 940/1251] eta: 0:02:38 lr: 0.000863 loss: 3.5248 (3.6087) grad_norm: 1.0664 (1.0771) time: 0.5077 [2021-03-25 16:28:09 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 950/1251] eta: 0:02:33 lr: 0.000863 loss: 3.3263 (3.6071) grad_norm: 1.0652 (1.0776) time: 0.5211 [2021-03-25 16:28:14 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 960/1251] eta: 0:02:28 lr: 0.000863 loss: 3.5866 (3.6069) grad_norm: 1.0652 (1.0774) time: 0.5215 [2021-03-25 16:28:19 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 970/1251] eta: 0:02:23 lr: 0.000863 loss: 3.7029 (3.6079) grad_norm: 1.0262 (1.0769) time: 0.5093 [2021-03-25 16:28:24 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 980/1251] eta: 0:02:18 lr: 0.000863 loss: 3.7633 (3.6075) grad_norm: 1.0350 (1.0765) time: 0.5056 [2021-03-25 16:28:29 swin_small_patch4_window7_224] INFO: Epoch: [72] [ 990/1251] eta: 0:02:13 lr: 0.000863 loss: 3.7100 (3.6065) grad_norm: 1.0057 (1.0760) time: 0.4991 [2021-03-25 16:28:34 swin_small_patch4_window7_224] INFO: Epoch: [72] [1000/1251] eta: 0:02:08 lr: 0.000863 loss: 3.6961 (3.6061) grad_norm: 1.0057 (1.0758) time: 0.4987 [2021-03-25 16:28:39 swin_small_patch4_window7_224] INFO: Epoch: [72] [1010/1251] eta: 0:02:02 lr: 0.000863 loss: 3.8093 (3.6087) grad_norm: 1.0154 (1.0755) time: 0.5042 [2021-03-25 16:28:44 swin_small_patch4_window7_224] INFO: Epoch: [72] [1020/1251] eta: 0:01:57 lr: 0.000863 loss: 3.8660 (3.6095) grad_norm: 1.0265 (1.0756) time: 0.5079 [2021-03-25 16:28:49 swin_small_patch4_window7_224] INFO: Epoch: [72] [1030/1251] eta: 0:01:52 lr: 0.000863 loss: 3.5950 (3.6070) grad_norm: 1.0265 (1.0752) time: 0.5047 [2021-03-25 16:28:54 swin_small_patch4_window7_224] INFO: Epoch: [72] [1040/1251] eta: 0:01:47 lr: 0.000863 loss: 3.5005 (3.6075) grad_norm: 1.0135 (1.0756) time: 0.5026 [2021-03-25 16:28:59 swin_small_patch4_window7_224] INFO: Epoch: [72] [1050/1251] eta: 0:01:42 lr: 0.000863 loss: 3.6190 (3.6038) grad_norm: 1.1213 (1.0761) time: 0.4991 [2021-03-25 16:29:04 swin_small_patch4_window7_224] INFO: Epoch: [72] [1060/1251] eta: 0:01:37 lr: 0.000863 loss: 3.7002 (3.6063) grad_norm: 1.1005 (1.0763) time: 0.4965 [2021-03-25 16:29:09 swin_small_patch4_window7_224] INFO: Epoch: [72] [1070/1251] eta: 0:01:32 lr: 0.000863 loss: 3.9356 (3.6089) grad_norm: 1.0757 (1.0765) time: 0.4986 [2021-03-25 16:29:14 swin_small_patch4_window7_224] INFO: Epoch: [72] [1080/1251] eta: 0:01:27 lr: 0.000863 loss: 3.8586 (3.6108) grad_norm: 1.0928 (1.0769) time: 0.5019 [2021-03-25 16:29:19 swin_small_patch4_window7_224] INFO: Epoch: [72] [1090/1251] eta: 0:01:22 lr: 0.000863 loss: 3.8129 (3.6130) grad_norm: 1.0928 (1.0770) time: 0.5038 [2021-03-25 16:29:25 swin_small_patch4_window7_224] INFO: Epoch: [72] [1100/1251] eta: 0:01:16 lr: 0.000863 loss: 3.8546 (3.6141) grad_norm: 1.0914 (1.0778) time: 0.5040 [2021-03-25 16:29:30 swin_small_patch4_window7_224] INFO: Epoch: [72] [1110/1251] eta: 0:01:11 lr: 0.000863 loss: 3.7668 (3.6138) grad_norm: 1.0914 (1.0781) time: 0.5033 [2021-03-25 16:29:35 swin_small_patch4_window7_224] INFO: Epoch: [72] [1120/1251] eta: 0:01:06 lr: 0.000863 loss: 3.5649 (3.6099) grad_norm: 1.0935 (1.0783) time: 0.5024 [2021-03-25 16:29:40 swin_small_patch4_window7_224] INFO: Epoch: [72] [1130/1251] eta: 0:01:01 lr: 0.000863 loss: 3.5649 (3.6126) grad_norm: 1.0674 (1.0783) time: 0.5074 [2021-03-25 16:29:45 swin_small_patch4_window7_224] INFO: Epoch: [72] [1140/1251] eta: 0:00:56 lr: 0.000863 loss: 3.7168 (3.6116) grad_norm: 1.0471 (1.0781) time: 0.5036 [2021-03-25 16:29:50 swin_small_patch4_window7_224] INFO: Epoch: [72] [1150/1251] eta: 0:00:51 lr: 0.000863 loss: 3.2959 (3.6094) grad_norm: 1.0754 (1.0782) time: 0.5047 [2021-03-25 16:29:55 swin_small_patch4_window7_224] INFO: Epoch: [72] [1160/1251] eta: 0:00:46 lr: 0.000863 loss: 3.7530 (3.6108) grad_norm: 1.0580 (1.0778) time: 0.5101 [2021-03-25 16:30:00 swin_small_patch4_window7_224] INFO: Epoch: [72] [1170/1251] eta: 0:00:41 lr: 0.000863 loss: 3.7530 (3.6085) grad_norm: 1.0872 (1.0781) time: 0.5083 [2021-03-25 16:30:05 swin_small_patch4_window7_224] INFO: Epoch: [72] [1180/1251] eta: 0:00:36 lr: 0.000862 loss: 3.7055 (3.6092) grad_norm: 1.1280 (1.0786) time: 0.5103 [2021-03-25 16:30:10 swin_small_patch4_window7_224] INFO: Epoch: [72] [1190/1251] eta: 0:00:31 lr: 0.000862 loss: 3.8513 (3.6104) grad_norm: 1.0882 (1.0785) time: 0.5122 [2021-03-25 16:30:15 swin_small_patch4_window7_224] INFO: Epoch: [72] [1200/1251] eta: 0:00:25 lr: 0.000862 loss: 3.8241 (3.6111) grad_norm: 1.0466 (1.0787) time: 0.5098 [2021-03-25 16:30:20 swin_small_patch4_window7_224] INFO: Epoch: [72] [1210/1251] eta: 0:00:20 lr: 0.000862 loss: 3.8210 (3.6113) grad_norm: 1.0900 (1.0786) time: 0.5035 [2021-03-25 16:30:25 swin_small_patch4_window7_224] INFO: Epoch: [72] [1220/1251] eta: 0:00:15 lr: 0.000862 loss: 3.6764 (3.6102) grad_norm: 1.0022 (1.0782) time: 0.4986 [2021-03-25 16:30:30 swin_small_patch4_window7_224] INFO: Epoch: [72] [1230/1251] eta: 0:00:10 lr: 0.000862 loss: 3.6764 (3.6122) grad_norm: 1.0579 (1.0794) time: 0.5016 [2021-03-25 16:30:35 swin_small_patch4_window7_224] INFO: Epoch: [72] [1240/1251] eta: 0:00:05 lr: 0.000862 loss: 3.7894 (3.6124) grad_norm: 1.1187 (1.0791) time: 0.5026 [2021-03-25 16:30:40 swin_small_patch4_window7_224] INFO: Epoch: [72] [1250/1251] eta: 0:00:00 lr: 0.000862 loss: 3.8290 (3.6126) grad_norm: 1.0916 (1.0792) time: 0.5059 [2021-03-25 16:30:46 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:32 loss: 0.9727 (0.9727) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-25 16:30:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1276 (1.1294) acc1: 75.0000 (73.4375) acc5: 93.7500 (92.3295) [2021-03-25 16:30:51 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.1276 (1.1486) acc1: 71.8750 (72.2470) acc5: 90.6250 (91.8155) [2021-03-25 16:30:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.1232 (1.1383) acc1: 73.4375 (73.1351) acc5: 92.1875 (92.2379) [2021-03-25 16:30:55 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0368 (1.1126) acc1: 76.5625 (74.0473) acc5: 92.1875 (92.3780) [2021-03-25 16:30:56 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9888 (1.0852) acc1: 78.1250 (74.4960) acc5: 92.4528 (92.8000) [2021-03-25 16:30:58 swin_small_patch4_window7_224] INFO: * Acc@1 74.784 Acc@5 92.734 loss 1.076 [2021-03-25 16:30:58 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.8% [2021-03-25 16:30:58 swin_small_patch4_window7_224] INFO: Max accuracy: 74.78% [2021-03-25 16:31:02 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 0/1251] eta: 1:23:32 lr: 0.000862 loss: 3.8373 (3.8373) grad_norm: 1.1226 (1.1226) time: 4.0069 [2021-03-25 16:31:07 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 10/1251] eta: 0:17:35 lr: 0.000862 loss: 3.5520 (3.4029) grad_norm: 1.0599 (1.0813) time: 0.8503 [2021-03-25 16:31:13 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 20/1251] eta: 0:14:13 lr: 0.000862 loss: 3.5520 (3.4887) grad_norm: 1.0384 (1.0711) time: 0.5281 [2021-03-25 16:31:18 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 30/1251] eta: 0:12:56 lr: 0.000862 loss: 3.5180 (3.4205) grad_norm: 1.0311 (1.0564) time: 0.5182 [2021-03-25 16:31:23 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 40/1251] eta: 0:12:18 lr: 0.000862 loss: 3.0064 (3.3771) grad_norm: 1.0293 (1.0529) time: 0.5215 [2021-03-25 16:31:28 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 50/1251] eta: 0:11:49 lr: 0.000862 loss: 3.3078 (3.3990) grad_norm: 0.9910 (1.0492) time: 0.5202 [2021-03-25 16:31:33 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 60/1251] eta: 0:11:26 lr: 0.000862 loss: 3.6260 (3.4297) grad_norm: 1.0257 (1.0435) time: 0.5087 [2021-03-25 16:31:38 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 70/1251] eta: 0:11:08 lr: 0.000862 loss: 3.6375 (3.4535) grad_norm: 1.0389 (1.0498) time: 0.5034 [2021-03-25 16:31:43 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 80/1251] eta: 0:10:54 lr: 0.000862 loss: 3.7628 (3.4771) grad_norm: 1.0662 (1.0527) time: 0.5056 [2021-03-25 16:31:48 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 90/1251] eta: 0:10:42 lr: 0.000862 loss: 3.7572 (3.4835) grad_norm: 1.0899 (1.0604) time: 0.5099 [2021-03-25 16:31:54 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 100/1251] eta: 0:10:32 lr: 0.000862 loss: 3.4575 (3.4826) grad_norm: 1.1526 (1.0735) time: 0.5127 [2021-03-25 16:31:59 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 110/1251] eta: 0:10:22 lr: 0.000862 loss: 3.4575 (3.4935) grad_norm: 1.1321 (1.0758) time: 0.5096 [2021-03-25 16:32:04 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 120/1251] eta: 0:10:13 lr: 0.000862 loss: 3.7525 (3.5134) grad_norm: 1.0740 (1.0744) time: 0.5067 [2021-03-25 16:32:09 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 130/1251] eta: 0:10:05 lr: 0.000862 loss: 3.8224 (3.5383) grad_norm: 1.0256 (1.0727) time: 0.5101 [2021-03-25 16:32:14 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 140/1251] eta: 0:09:58 lr: 0.000862 loss: 3.8211 (3.5406) grad_norm: 1.0341 (1.0701) time: 0.5124 [2021-03-25 16:32:19 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 150/1251] eta: 0:09:50 lr: 0.000862 loss: 3.7802 (3.5554) grad_norm: 1.0384 (1.0679) time: 0.5102 [2021-03-25 16:32:24 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 160/1251] eta: 0:09:42 lr: 0.000862 loss: 3.9292 (3.5649) grad_norm: 1.0158 (1.0650) time: 0.5052 [2021-03-25 16:32:29 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 170/1251] eta: 0:09:35 lr: 0.000862 loss: 3.5424 (3.5561) grad_norm: 1.0175 (1.0641) time: 0.5053 [2021-03-25 16:32:34 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 180/1251] eta: 0:09:28 lr: 0.000862 loss: 3.4311 (3.5504) grad_norm: 1.0500 (1.0632) time: 0.5057 [2021-03-25 16:32:39 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 190/1251] eta: 0:09:22 lr: 0.000862 loss: 3.4706 (3.5392) grad_norm: 1.0105 (1.0600) time: 0.5053 [2021-03-25 16:32:44 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 200/1251] eta: 0:09:16 lr: 0.000862 loss: 3.5023 (3.5486) grad_norm: 1.0107 (1.0600) time: 0.5107 [2021-03-25 16:32:49 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 210/1251] eta: 0:09:09 lr: 0.000862 loss: 3.7571 (3.5591) grad_norm: 1.0449 (1.0613) time: 0.5083 [2021-03-25 16:32:54 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 220/1251] eta: 0:09:03 lr: 0.000862 loss: 3.8244 (3.5689) grad_norm: 1.0278 (1.0596) time: 0.5034 [2021-03-25 16:32:59 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 230/1251] eta: 0:08:56 lr: 0.000862 loss: 3.6528 (3.5665) grad_norm: 1.0241 (1.0585) time: 0.4998 [2021-03-25 16:33:04 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 240/1251] eta: 0:08:50 lr: 0.000862 loss: 3.5826 (3.5632) grad_norm: 1.0150 (1.0565) time: 0.4981 [2021-03-25 16:33:09 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 250/1251] eta: 0:08:44 lr: 0.000862 loss: 3.8118 (3.5772) grad_norm: 0.9859 (1.0569) time: 0.5030 [2021-03-25 16:33:14 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 260/1251] eta: 0:08:38 lr: 0.000862 loss: 3.7262 (3.5700) grad_norm: 1.0634 (1.0565) time: 0.5029 [2021-03-25 16:33:19 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 270/1251] eta: 0:08:31 lr: 0.000861 loss: 3.5726 (3.5739) grad_norm: 1.0710 (1.0582) time: 0.5008 [2021-03-25 16:33:25 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 280/1251] eta: 0:08:26 lr: 0.000861 loss: 3.8339 (3.5775) grad_norm: 1.1032 (1.0613) time: 0.5058 [2021-03-25 16:33:30 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 290/1251] eta: 0:08:20 lr: 0.000861 loss: 3.4687 (3.5745) grad_norm: 1.0622 (1.0618) time: 0.5099 [2021-03-25 16:33:35 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 300/1251] eta: 0:08:14 lr: 0.000861 loss: 3.3863 (3.5758) grad_norm: 1.0389 (nan) time: 0.4990 [2021-03-25 16:33:40 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 310/1251] eta: 0:08:08 lr: 0.000861 loss: 3.5589 (3.5780) grad_norm: 1.0279 (nan) time: 0.4966 [2021-03-25 16:33:45 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 320/1251] eta: 0:08:03 lr: 0.000861 loss: 3.5589 (3.5694) grad_norm: 1.0358 (nan) time: 0.5061 [2021-03-25 16:33:50 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 330/1251] eta: 0:07:57 lr: 0.000861 loss: 3.7058 (3.5758) grad_norm: 1.0481 (nan) time: 0.5100 [2021-03-25 16:33:55 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 340/1251] eta: 0:07:52 lr: 0.000861 loss: 3.8545 (3.5815) grad_norm: 0.9925 (nan) time: 0.5065 [2021-03-25 16:34:00 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 350/1251] eta: 0:07:46 lr: 0.000861 loss: 3.5185 (3.5752) grad_norm: 0.9925 (nan) time: 0.5050 [2021-03-25 16:34:05 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 360/1251] eta: 0:07:41 lr: 0.000861 loss: 3.6067 (3.5794) grad_norm: 1.0327 (nan) time: 0.5039 [2021-03-25 16:34:10 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 370/1251] eta: 0:07:35 lr: 0.000861 loss: 3.7912 (3.5771) grad_norm: 0.9895 (nan) time: 0.5023 [2021-03-25 16:34:15 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 380/1251] eta: 0:07:30 lr: 0.000861 loss: 3.5708 (3.5784) grad_norm: 1.0122 (nan) time: 0.4992 [2021-03-25 16:34:20 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 390/1251] eta: 0:07:24 lr: 0.000861 loss: 3.6411 (3.5808) grad_norm: 1.0262 (nan) time: 0.4982 [2021-03-25 16:34:25 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 400/1251] eta: 0:07:19 lr: 0.000861 loss: 3.6636 (3.5814) grad_norm: 1.1188 (nan) time: 0.5035 [2021-03-25 16:34:30 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 410/1251] eta: 0:07:13 lr: 0.000861 loss: 3.4617 (3.5806) grad_norm: 1.1732 (nan) time: 0.5061 [2021-03-25 16:34:35 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 420/1251] eta: 0:07:08 lr: 0.000861 loss: 3.2764 (3.5704) grad_norm: 1.0816 (nan) time: 0.5067 [2021-03-25 16:34:40 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 430/1251] eta: 0:07:03 lr: 0.000861 loss: 3.4245 (3.5750) grad_norm: 1.0621 (nan) time: 0.5064 [2021-03-25 16:34:45 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 440/1251] eta: 0:06:57 lr: 0.000861 loss: 3.7978 (3.5774) grad_norm: 1.0528 (nan) time: 0.5017 [2021-03-25 16:34:50 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 450/1251] eta: 0:06:52 lr: 0.000861 loss: 3.6772 (3.5719) grad_norm: 1.0199 (nan) time: 0.5009 [2021-03-25 16:34:55 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 460/1251] eta: 0:06:46 lr: 0.000861 loss: 3.4291 (3.5755) grad_norm: 1.0182 (nan) time: 0.5030 [2021-03-25 16:35:00 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 470/1251] eta: 0:06:41 lr: 0.000861 loss: 3.6656 (3.5755) grad_norm: 1.0686 (nan) time: 0.5050 [2021-03-25 16:35:05 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 480/1251] eta: 0:06:36 lr: 0.000861 loss: 3.6403 (3.5702) grad_norm: 1.0669 (nan) time: 0.5038 [2021-03-25 16:35:10 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 490/1251] eta: 0:06:31 lr: 0.000861 loss: 3.5577 (3.5742) grad_norm: 1.0448 (nan) time: 0.5026 [2021-03-25 16:35:15 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 500/1251] eta: 0:06:25 lr: 0.000861 loss: 3.4497 (3.5673) grad_norm: 1.0567 (nan) time: 0.5060 [2021-03-25 16:35:20 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 510/1251] eta: 0:06:20 lr: 0.000861 loss: 3.4129 (3.5694) grad_norm: 1.0981 (nan) time: 0.5064 [2021-03-25 16:35:26 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 520/1251] eta: 0:06:15 lr: 0.000861 loss: 3.5592 (3.5665) grad_norm: 1.0639 (nan) time: 0.5046 [2021-03-25 16:35:31 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 530/1251] eta: 0:06:09 lr: 0.000861 loss: 3.4047 (3.5631) grad_norm: 1.0446 (nan) time: 0.5018 [2021-03-25 16:35:36 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 540/1251] eta: 0:06:04 lr: 0.000861 loss: 3.2784 (3.5569) grad_norm: 1.0584 (nan) time: 0.5055 [2021-03-25 16:35:41 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 550/1251] eta: 0:05:59 lr: 0.000861 loss: 3.4511 (3.5585) grad_norm: 1.0712 (nan) time: 0.5199 [2021-03-25 16:35:46 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 560/1251] eta: 0:05:54 lr: 0.000861 loss: 3.5080 (3.5546) grad_norm: 1.1658 (nan) time: 0.5207 [2021-03-25 16:35:51 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 570/1251] eta: 0:05:49 lr: 0.000861 loss: 3.6861 (3.5584) grad_norm: 1.0720 (nan) time: 0.5035 [2021-03-25 16:35:56 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 580/1251] eta: 0:05:44 lr: 0.000861 loss: 3.7951 (3.5629) grad_norm: 1.0067 (nan) time: 0.5014 [2021-03-25 16:36:01 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 590/1251] eta: 0:05:39 lr: 0.000861 loss: 3.6214 (3.5582) grad_norm: 1.0459 (nan) time: 0.5135 [2021-03-25 16:36:06 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 600/1251] eta: 0:05:33 lr: 0.000861 loss: 3.3270 (3.5568) grad_norm: 1.0340 (nan) time: 0.5158 [2021-03-25 16:36:12 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 610/1251] eta: 0:05:28 lr: 0.000861 loss: 3.3270 (3.5543) grad_norm: 1.0483 (nan) time: 0.5123 [2021-03-25 16:36:17 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 620/1251] eta: 0:05:23 lr: 0.000860 loss: 3.6747 (3.5576) grad_norm: 1.0980 (nan) time: 0.5061 [2021-03-25 16:36:22 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 630/1251] eta: 0:05:18 lr: 0.000860 loss: 3.6747 (3.5568) grad_norm: 1.0858 (nan) time: 0.5024 [2021-03-25 16:36:27 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 640/1251] eta: 0:05:13 lr: 0.000860 loss: 3.6474 (3.5560) grad_norm: 1.0771 (nan) time: 0.5019 [2021-03-25 16:36:32 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 650/1251] eta: 0:05:07 lr: 0.000860 loss: 3.7869 (3.5602) grad_norm: 1.0872 (nan) time: 0.5022 [2021-03-25 16:36:37 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 660/1251] eta: 0:05:02 lr: 0.000860 loss: 3.8847 (3.5642) grad_norm: 1.0585 (nan) time: 0.5069 [2021-03-25 16:36:42 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 670/1251] eta: 0:04:57 lr: 0.000860 loss: 3.7660 (3.5640) grad_norm: 1.0081 (nan) time: 0.5062 [2021-03-25 16:36:47 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 680/1251] eta: 0:04:52 lr: 0.000860 loss: 3.7214 (3.5650) grad_norm: 1.0187 (nan) time: 0.5025 [2021-03-25 16:36:52 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 690/1251] eta: 0:04:47 lr: 0.000860 loss: 3.8394 (3.5680) grad_norm: 1.0834 (nan) time: 0.5010 [2021-03-25 16:36:57 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 700/1251] eta: 0:04:41 lr: 0.000860 loss: 3.6683 (3.5647) grad_norm: 1.0834 (nan) time: 0.5042 [2021-03-25 16:37:02 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 710/1251] eta: 0:04:36 lr: 0.000860 loss: 3.3088 (3.5634) grad_norm: 1.0218 (nan) time: 0.5023 [2021-03-25 16:37:07 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 720/1251] eta: 0:04:31 lr: 0.000860 loss: 3.5368 (3.5642) grad_norm: 1.0217 (nan) time: 0.5030 [2021-03-25 16:37:12 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 730/1251] eta: 0:04:26 lr: 0.000860 loss: 3.5453 (3.5627) grad_norm: 1.0885 (nan) time: 0.5072 [2021-03-25 16:37:17 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 740/1251] eta: 0:04:21 lr: 0.000860 loss: 3.5453 (3.5630) grad_norm: 1.1044 (nan) time: 0.5214 [2021-03-25 16:37:22 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 750/1251] eta: 0:04:16 lr: 0.000860 loss: 3.7106 (3.5644) grad_norm: 1.0885 (nan) time: 0.5242 [2021-03-25 16:37:28 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 760/1251] eta: 0:04:11 lr: 0.000860 loss: 3.6724 (3.5662) grad_norm: 1.0303 (nan) time: 0.5111 [2021-03-25 16:37:33 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 770/1251] eta: 0:04:06 lr: 0.000860 loss: 3.6603 (3.5641) grad_norm: 0.9839 (nan) time: 0.5046 [2021-03-25 16:37:38 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 780/1251] eta: 0:04:01 lr: 0.000860 loss: 3.5783 (3.5646) grad_norm: 0.9784 (nan) time: 0.5102 [2021-03-25 16:37:43 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 790/1251] eta: 0:03:55 lr: 0.000860 loss: 3.5075 (3.5614) grad_norm: 1.0091 (nan) time: 0.5188 [2021-03-25 16:37:48 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 800/1251] eta: 0:03:50 lr: 0.000860 loss: 3.5075 (3.5632) grad_norm: 1.0091 (nan) time: 0.5171 [2021-03-25 16:37:53 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 810/1251] eta: 0:03:45 lr: 0.000860 loss: 3.6248 (3.5621) grad_norm: 0.9829 (nan) time: 0.5115 [2021-03-25 16:37:58 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 820/1251] eta: 0:03:40 lr: 0.000860 loss: 3.5530 (3.5621) grad_norm: 0.9903 (nan) time: 0.5082 [2021-03-25 16:38:03 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 830/1251] eta: 0:03:35 lr: 0.000860 loss: 3.5868 (3.5651) grad_norm: 0.9994 (nan) time: 0.5051 [2021-03-25 16:38:08 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 840/1251] eta: 0:03:30 lr: 0.000860 loss: 3.7728 (3.5679) grad_norm: 1.0265 (nan) time: 0.5046 [2021-03-25 16:38:13 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 850/1251] eta: 0:03:25 lr: 0.000860 loss: 3.8642 (3.5708) grad_norm: 1.0247 (nan) time: 0.5081 [2021-03-25 16:38:18 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 860/1251] eta: 0:03:19 lr: 0.000860 loss: 3.8241 (3.5727) grad_norm: 1.0247 (nan) time: 0.5044 [2021-03-25 16:38:23 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 870/1251] eta: 0:03:14 lr: 0.000860 loss: 3.5251 (3.5709) grad_norm: 1.0143 (nan) time: 0.5023 [2021-03-25 16:38:29 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 880/1251] eta: 0:03:09 lr: 0.000860 loss: 3.5701 (3.5726) grad_norm: 1.0155 (nan) time: 0.5029 [2021-03-25 16:38:34 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 890/1251] eta: 0:03:04 lr: 0.000860 loss: 3.6715 (3.5740) grad_norm: 1.0095 (nan) time: 0.5081 [2021-03-25 16:38:39 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 900/1251] eta: 0:02:59 lr: 0.000860 loss: 3.8279 (3.5764) grad_norm: 1.0061 (nan) time: 0.5101 [2021-03-25 16:38:44 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 910/1251] eta: 0:02:54 lr: 0.000860 loss: 3.7367 (3.5749) grad_norm: 1.0069 (nan) time: 0.5076 [2021-03-25 16:38:49 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 920/1251] eta: 0:02:49 lr: 0.000860 loss: 3.5817 (3.5740) grad_norm: 0.9954 (nan) time: 0.5034 [2021-03-25 16:38:54 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 930/1251] eta: 0:02:44 lr: 0.000860 loss: 3.7441 (3.5755) grad_norm: 0.9954 (nan) time: 0.5010 [2021-03-25 16:38:59 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 940/1251] eta: 0:02:38 lr: 0.000860 loss: 3.7635 (3.5767) grad_norm: 1.0178 (nan) time: 0.5061 [2021-03-25 16:39:04 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 950/1251] eta: 0:02:33 lr: 0.000860 loss: 3.6513 (3.5780) grad_norm: 1.0359 (nan) time: 0.5113 [2021-03-25 16:39:09 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 960/1251] eta: 0:02:28 lr: 0.000860 loss: 3.6513 (3.5771) grad_norm: 1.0340 (nan) time: 0.5082 [2021-03-25 16:39:14 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 970/1251] eta: 0:02:23 lr: 0.000859 loss: 3.4312 (3.5731) grad_norm: 1.0264 (nan) time: 0.5042 [2021-03-25 16:39:19 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 980/1251] eta: 0:02:18 lr: 0.000859 loss: 3.3400 (3.5717) grad_norm: 1.0443 (nan) time: 0.5076 [2021-03-25 16:39:24 swin_small_patch4_window7_224] INFO: Epoch: [73] [ 990/1251] eta: 0:02:13 lr: 0.000859 loss: 3.7215 (3.5728) grad_norm: 1.0507 (nan) time: 0.5080 [2021-03-25 16:39:29 swin_small_patch4_window7_224] INFO: Epoch: [73] [1000/1251] eta: 0:02:08 lr: 0.000859 loss: 3.7215 (3.5755) grad_norm: 1.0636 (nan) time: 0.5012 [2021-03-25 16:39:34 swin_small_patch4_window7_224] INFO: Epoch: [73] [1010/1251] eta: 0:02:03 lr: 0.000859 loss: 3.6839 (3.5738) grad_norm: 1.0465 (nan) time: 0.5040 [2021-03-25 16:39:39 swin_small_patch4_window7_224] INFO: Epoch: [73] [1020/1251] eta: 0:01:57 lr: 0.000859 loss: 3.6712 (3.5746) grad_norm: 1.0465 (nan) time: 0.5069 [2021-03-25 16:39:45 swin_small_patch4_window7_224] INFO: Epoch: [73] [1030/1251] eta: 0:01:52 lr: 0.000859 loss: 3.6238 (3.5743) grad_norm: 1.1107 (nan) time: 0.5061 [2021-03-25 16:39:50 swin_small_patch4_window7_224] INFO: Epoch: [73] [1040/1251] eta: 0:01:47 lr: 0.000859 loss: 3.6238 (3.5732) grad_norm: 1.1284 (nan) time: 0.5047 [2021-03-25 16:39:55 swin_small_patch4_window7_224] INFO: Epoch: [73] [1050/1251] eta: 0:01:42 lr: 0.000859 loss: 3.5987 (3.5715) grad_norm: 1.1284 (nan) time: 0.5036 [2021-03-25 16:40:00 swin_small_patch4_window7_224] INFO: Epoch: [73] [1060/1251] eta: 0:01:37 lr: 0.000859 loss: 3.4653 (3.5716) grad_norm: 1.0760 (nan) time: 0.5058 [2021-03-25 16:40:05 swin_small_patch4_window7_224] INFO: Epoch: [73] [1070/1251] eta: 0:01:32 lr: 0.000859 loss: 3.5406 (3.5715) grad_norm: 1.0418 (nan) time: 0.5073 [2021-03-25 16:40:10 swin_small_patch4_window7_224] INFO: Epoch: [73] [1080/1251] eta: 0:01:27 lr: 0.000859 loss: 3.5558 (3.5715) grad_norm: 1.0332 (nan) time: 0.5078 [2021-03-25 16:40:15 swin_small_patch4_window7_224] INFO: Epoch: [73] [1090/1251] eta: 0:01:22 lr: 0.000859 loss: 3.7480 (3.5729) grad_norm: 1.0595 (nan) time: 0.5051 [2021-03-25 16:40:20 swin_small_patch4_window7_224] INFO: Epoch: [73] [1100/1251] eta: 0:01:17 lr: 0.000859 loss: 3.5786 (3.5687) grad_norm: 1.0797 (nan) time: 0.5018 [2021-03-25 16:40:25 swin_small_patch4_window7_224] INFO: Epoch: [73] [1110/1251] eta: 0:01:11 lr: 0.000859 loss: 3.1339 (3.5674) grad_norm: 1.0277 (nan) time: 0.5009 [2021-03-25 16:40:30 swin_small_patch4_window7_224] INFO: Epoch: [73] [1120/1251] eta: 0:01:06 lr: 0.000859 loss: 3.6273 (3.5690) grad_norm: 1.0181 (nan) time: 0.5033 [2021-03-25 16:40:35 swin_small_patch4_window7_224] INFO: Epoch: [73] [1130/1251] eta: 0:01:01 lr: 0.000859 loss: 3.6787 (3.5692) grad_norm: 1.0663 (nan) time: 0.5055 [2021-03-25 16:40:40 swin_small_patch4_window7_224] INFO: Epoch: [73] [1140/1251] eta: 0:00:56 lr: 0.000859 loss: 3.8619 (3.5696) grad_norm: 1.0730 (nan) time: 0.5016 [2021-03-25 16:40:45 swin_small_patch4_window7_224] INFO: Epoch: [73] [1150/1251] eta: 0:00:51 lr: 0.000859 loss: 3.6839 (3.5691) grad_norm: 1.0430 (nan) time: 0.5025 [2021-03-25 16:40:50 swin_small_patch4_window7_224] INFO: Epoch: [73] [1160/1251] eta: 0:00:46 lr: 0.000859 loss: 3.6236 (3.5673) grad_norm: 1.0367 (nan) time: 0.5084 [2021-03-25 16:40:55 swin_small_patch4_window7_224] INFO: Epoch: [73] [1170/1251] eta: 0:00:41 lr: 0.000859 loss: 3.6236 (3.5673) grad_norm: 1.0563 (nan) time: 0.5076 [2021-03-25 16:41:00 swin_small_patch4_window7_224] INFO: Epoch: [73] [1180/1251] eta: 0:00:36 lr: 0.000859 loss: 3.6810 (3.5674) grad_norm: 1.0845 (nan) time: 0.5032 [2021-03-25 16:41:05 swin_small_patch4_window7_224] INFO: Epoch: [73] [1190/1251] eta: 0:00:31 lr: 0.000859 loss: 3.5378 (3.5671) grad_norm: 1.0809 (nan) time: 0.5007 [2021-03-25 16:41:10 swin_small_patch4_window7_224] INFO: Epoch: [73] [1200/1251] eta: 0:00:25 lr: 0.000859 loss: 3.7483 (3.5669) grad_norm: 1.0476 (nan) time: 0.5029 [2021-03-25 16:41:15 swin_small_patch4_window7_224] INFO: Epoch: [73] [1210/1251] eta: 0:00:20 lr: 0.000859 loss: 3.8139 (3.5675) grad_norm: 1.0403 (nan) time: 0.5087 [2021-03-25 16:41:20 swin_small_patch4_window7_224] INFO: Epoch: [73] [1220/1251] eta: 0:00:15 lr: 0.000859 loss: 3.6125 (3.5666) grad_norm: 1.0623 (nan) time: 0.5107 [2021-03-25 16:41:26 swin_small_patch4_window7_224] INFO: Epoch: [73] [1230/1251] eta: 0:00:10 lr: 0.000859 loss: 3.6277 (3.5666) grad_norm: 1.0623 (nan) time: 0.5067 [2021-03-25 16:41:31 swin_small_patch4_window7_224] INFO: Epoch: [73] [1240/1251] eta: 0:00:05 lr: 0.000859 loss: 3.7108 (3.5676) grad_norm: 1.0456 (nan) time: 0.5071 [2021-03-25 16:41:36 swin_small_patch4_window7_224] INFO: Epoch: [73] [1250/1251] eta: 0:00:00 lr: 0.000859 loss: 3.7139 (3.5677) grad_norm: 1.0456 (nan) time: 0.5061 [2021-03-25 16:41:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.8835 (0.8835) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-25 16:41:44 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1893 (1.1461) acc1: 73.4375 (71.5909) acc5: 92.1875 (91.9034) [2021-03-25 16:41:46 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.1147 (1.1145) acc1: 73.4375 (73.3631) acc5: 92.1875 (92.3363) [2021-03-25 16:41:48 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0157 (1.0884) acc1: 76.5625 (73.9919) acc5: 93.7500 (92.7923) [2021-03-25 16:41:50 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1164 (1.1057) acc1: 73.4375 (73.5899) acc5: 92.1875 (92.4924) [2021-03-25 16:41:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0901 (1.0946) acc1: 75.0000 (74.2080) acc5: 90.6250 (92.3200) [2021-03-25 16:41:55 swin_small_patch4_window7_224] INFO: * Acc@1 74.438 Acc@5 92.732 loss 1.075 [2021-03-25 16:41:55 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.4% [2021-03-25 16:41:55 swin_small_patch4_window7_224] INFO: Max accuracy: 74.78% [2021-03-25 16:41:59 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 0/1251] eta: 1:19:18 lr: 0.000859 loss: 3.6854 (3.6854) grad_norm: 0.9725 (0.9725) time: 3.8039 [2021-03-25 16:42:04 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 10/1251] eta: 0:16:56 lr: 0.000859 loss: 3.6854 (3.6164) grad_norm: 1.0701 (1.1045) time: 0.8194 [2021-03-25 16:42:09 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 20/1251] eta: 0:13:45 lr: 0.000859 loss: 3.3270 (3.4127) grad_norm: 1.0994 (1.1089) time: 0.5137 [2021-03-25 16:42:14 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 30/1251] eta: 0:12:32 lr: 0.000859 loss: 3.2145 (3.3621) grad_norm: 1.1001 (1.1013) time: 0.5048 [2021-03-25 16:42:19 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 40/1251] eta: 0:11:56 lr: 0.000859 loss: 3.4551 (3.4306) grad_norm: 1.0792 (1.1041) time: 0.5088 [2021-03-25 16:42:25 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 50/1251] eta: 0:11:32 lr: 0.000859 loss: 3.6727 (3.4483) grad_norm: 1.0778 (1.1032) time: 0.5147 [2021-03-25 16:42:30 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 60/1251] eta: 0:11:11 lr: 0.000858 loss: 3.6965 (3.5036) grad_norm: 1.0855 (1.1070) time: 0.5067 [2021-03-25 16:42:35 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 70/1251] eta: 0:10:55 lr: 0.000858 loss: 3.8618 (3.5384) grad_norm: 1.0846 (1.0983) time: 0.4992 [2021-03-25 16:42:40 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 80/1251] eta: 0:10:41 lr: 0.000858 loss: 3.8618 (3.5492) grad_norm: 1.0294 (1.0924) time: 0.5003 [2021-03-25 16:42:45 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 90/1251] eta: 0:10:30 lr: 0.000858 loss: 3.7354 (3.5643) grad_norm: 1.0548 (1.0922) time: 0.5006 [2021-03-25 16:42:50 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 100/1251] eta: 0:10:19 lr: 0.000858 loss: 3.7858 (3.5957) grad_norm: 1.0824 (1.0938) time: 0.4980 [2021-03-25 16:42:55 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 110/1251] eta: 0:10:10 lr: 0.000858 loss: 3.6390 (3.5738) grad_norm: 1.0211 (1.0898) time: 0.5012 [2021-03-25 16:43:00 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 120/1251] eta: 0:10:02 lr: 0.000858 loss: 3.3385 (3.5698) grad_norm: 1.0402 (1.0920) time: 0.5058 [2021-03-25 16:43:05 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 130/1251] eta: 0:09:54 lr: 0.000858 loss: 3.6734 (3.5768) grad_norm: 1.0479 (1.0904) time: 0.5020 [2021-03-25 16:43:10 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 140/1251] eta: 0:09:46 lr: 0.000858 loss: 3.6905 (3.5841) grad_norm: 1.0479 (1.0866) time: 0.4972 [2021-03-25 16:43:15 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 150/1251] eta: 0:09:39 lr: 0.000858 loss: 3.7731 (3.5997) grad_norm: 1.0468 (1.0847) time: 0.4987 [2021-03-25 16:43:20 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 160/1251] eta: 0:09:33 lr: 0.000858 loss: 3.7731 (3.5939) grad_norm: 1.0715 (1.0859) time: 0.5086 [2021-03-25 16:43:25 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 170/1251] eta: 0:09:26 lr: 0.000858 loss: 3.7194 (3.5910) grad_norm: 1.0666 (1.0841) time: 0.5104 [2021-03-25 16:43:30 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 180/1251] eta: 0:09:21 lr: 0.000858 loss: 3.6961 (3.5993) grad_norm: 1.0513 (1.0877) time: 0.5120 [2021-03-25 16:43:35 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 190/1251] eta: 0:09:15 lr: 0.000858 loss: 3.6291 (3.5979) grad_norm: 1.0539 (1.0897) time: 0.5140 [2021-03-25 16:43:40 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 200/1251] eta: 0:09:09 lr: 0.000858 loss: 3.6073 (3.5967) grad_norm: 1.0539 (1.0902) time: 0.5176 [2021-03-25 16:43:45 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 210/1251] eta: 0:09:03 lr: 0.000858 loss: 3.5553 (3.5840) grad_norm: 1.0293 (1.0880) time: 0.5138 [2021-03-25 16:43:50 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 220/1251] eta: 0:08:57 lr: 0.000858 loss: 3.4828 (3.5748) grad_norm: 1.0265 (1.0860) time: 0.5025 [2021-03-25 16:43:56 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 230/1251] eta: 0:08:51 lr: 0.000858 loss: 3.7117 (3.5770) grad_norm: 1.0073 (1.0846) time: 0.5060 [2021-03-25 16:44:01 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 240/1251] eta: 0:08:45 lr: 0.000858 loss: 3.5590 (3.5681) grad_norm: 0.9827 (1.0813) time: 0.5058 [2021-03-25 16:44:06 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 250/1251] eta: 0:08:40 lr: 0.000858 loss: 3.4106 (3.5580) grad_norm: 0.9977 (1.0817) time: 0.5041 [2021-03-25 16:44:11 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 260/1251] eta: 0:08:34 lr: 0.000858 loss: 3.6070 (3.5631) grad_norm: 1.0754 (1.0832) time: 0.5097 [2021-03-25 16:44:16 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 270/1251] eta: 0:08:28 lr: 0.000858 loss: 3.7178 (3.5633) grad_norm: 1.0754 (1.0836) time: 0.5085 [2021-03-25 16:44:21 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 280/1251] eta: 0:08:23 lr: 0.000858 loss: 3.6150 (3.5577) grad_norm: 1.1123 (1.0859) time: 0.5065 [2021-03-25 16:44:26 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 290/1251] eta: 0:08:17 lr: 0.000858 loss: 3.4831 (3.5511) grad_norm: 1.0418 (1.0837) time: 0.5088 [2021-03-25 16:44:31 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 300/1251] eta: 0:08:12 lr: 0.000858 loss: 3.4831 (3.5449) grad_norm: 1.0201 (1.0832) time: 0.5069 [2021-03-25 16:44:36 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 310/1251] eta: 0:08:06 lr: 0.000858 loss: 3.6257 (3.5417) grad_norm: 1.1050 (1.0842) time: 0.5037 [2021-03-25 16:44:41 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 320/1251] eta: 0:08:01 lr: 0.000858 loss: 3.6914 (3.5456) grad_norm: 1.1341 (1.0857) time: 0.5022 [2021-03-25 16:44:46 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 330/1251] eta: 0:07:55 lr: 0.000858 loss: 3.6914 (3.5464) grad_norm: 1.0726 (1.0845) time: 0.5064 [2021-03-25 16:44:51 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 340/1251] eta: 0:07:50 lr: 0.000858 loss: 3.4757 (3.5447) grad_norm: 1.0413 (1.0841) time: 0.5072 [2021-03-25 16:44:56 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 350/1251] eta: 0:07:44 lr: 0.000858 loss: 3.7258 (3.5519) grad_norm: 1.0387 (1.0834) time: 0.5055 [2021-03-25 16:45:01 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 360/1251] eta: 0:07:39 lr: 0.000858 loss: 3.7258 (3.5502) grad_norm: 1.0392 (1.0831) time: 0.5023 [2021-03-25 16:45:06 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 370/1251] eta: 0:07:33 lr: 0.000858 loss: 3.7292 (3.5588) grad_norm: 1.0961 (1.0862) time: 0.5030 [2021-03-25 16:45:11 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 380/1251] eta: 0:07:28 lr: 0.000858 loss: 3.9025 (3.5673) grad_norm: 1.1001 (1.0857) time: 0.5070 [2021-03-25 16:45:16 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 390/1251] eta: 0:07:23 lr: 0.000858 loss: 3.9613 (3.5790) grad_norm: 1.0214 (1.0844) time: 0.5069 [2021-03-25 16:45:21 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 400/1251] eta: 0:07:17 lr: 0.000858 loss: 3.7546 (3.5739) grad_norm: 1.0000 (1.0824) time: 0.5003 [2021-03-25 16:45:27 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 410/1251] eta: 0:07:12 lr: 0.000857 loss: 3.6275 (3.5803) grad_norm: 1.0079 (1.0814) time: 0.5019 [2021-03-25 16:45:32 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 420/1251] eta: 0:07:07 lr: 0.000857 loss: 3.7785 (3.5792) grad_norm: 1.0295 (1.0825) time: 0.5087 [2021-03-25 16:45:37 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 430/1251] eta: 0:07:01 lr: 0.000857 loss: 3.4691 (3.5774) grad_norm: 1.0878 (1.0826) time: 0.5059 [2021-03-25 16:45:42 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 440/1251] eta: 0:06:56 lr: 0.000857 loss: 3.4602 (3.5801) grad_norm: 1.0509 (1.0828) time: 0.5019 [2021-03-25 16:45:47 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 450/1251] eta: 0:06:51 lr: 0.000857 loss: 3.9860 (3.5906) grad_norm: 1.0528 (1.0831) time: 0.5067 [2021-03-25 16:45:52 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 460/1251] eta: 0:06:46 lr: 0.000857 loss: 3.9794 (3.5889) grad_norm: 1.0620 (1.0830) time: 0.5148 [2021-03-25 16:45:57 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 470/1251] eta: 0:06:40 lr: 0.000857 loss: 3.6219 (3.5866) grad_norm: 1.0691 (1.0845) time: 0.5083 [2021-03-25 16:46:02 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 480/1251] eta: 0:06:35 lr: 0.000857 loss: 3.6116 (3.5882) grad_norm: 1.0691 (1.0852) time: 0.5041 [2021-03-25 16:46:07 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 490/1251] eta: 0:06:30 lr: 0.000857 loss: 3.4706 (3.5862) grad_norm: 1.0373 (1.0845) time: 0.5050 [2021-03-25 16:46:12 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 500/1251] eta: 0:06:24 lr: 0.000857 loss: 3.4145 (3.5825) grad_norm: 1.0588 (1.0850) time: 0.5029 [2021-03-25 16:46:17 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 510/1251] eta: 0:06:19 lr: 0.000857 loss: 3.4587 (3.5806) grad_norm: 1.0588 (1.0838) time: 0.4977 [2021-03-25 16:46:22 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 520/1251] eta: 0:06:14 lr: 0.000857 loss: 3.6261 (3.5810) grad_norm: 1.0438 (1.0839) time: 0.4972 [2021-03-25 16:46:27 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 530/1251] eta: 0:06:08 lr: 0.000857 loss: 3.7750 (3.5850) grad_norm: 1.1051 (1.0859) time: 0.4960 [2021-03-25 16:46:32 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 540/1251] eta: 0:06:03 lr: 0.000857 loss: 3.8801 (3.5896) grad_norm: 1.0950 (1.0850) time: 0.5041 [2021-03-25 16:46:37 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 550/1251] eta: 0:05:58 lr: 0.000857 loss: 3.8306 (3.5915) grad_norm: 1.0164 (1.0849) time: 0.5229 [2021-03-25 16:46:42 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 560/1251] eta: 0:05:53 lr: 0.000857 loss: 3.8980 (3.5941) grad_norm: 1.1047 (1.0865) time: 0.5179 [2021-03-25 16:46:47 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 570/1251] eta: 0:05:48 lr: 0.000857 loss: 3.9225 (3.5956) grad_norm: 1.1047 (1.0867) time: 0.5041 [2021-03-25 16:46:53 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 580/1251] eta: 0:05:43 lr: 0.000857 loss: 3.6593 (3.5974) grad_norm: 1.0437 (1.0860) time: 0.5041 [2021-03-25 16:46:58 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 590/1251] eta: 0:05:38 lr: 0.000857 loss: 3.6405 (3.5936) grad_norm: 1.0302 (1.0852) time: 0.5112 [2021-03-25 16:47:03 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 600/1251] eta: 0:05:33 lr: 0.000857 loss: 3.4326 (3.5910) grad_norm: 1.0444 (1.0847) time: 0.5145 [2021-03-25 16:47:08 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 610/1251] eta: 0:05:27 lr: 0.000857 loss: 3.5433 (3.5916) grad_norm: 1.0671 (1.0860) time: 0.5070 [2021-03-25 16:47:13 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 620/1251] eta: 0:05:22 lr: 0.000857 loss: 3.4914 (3.5876) grad_norm: 1.1093 (1.0856) time: 0.4993 [2021-03-25 16:47:18 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 630/1251] eta: 0:05:17 lr: 0.000857 loss: 3.5035 (3.5859) grad_norm: 1.0089 (1.0843) time: 0.5042 [2021-03-25 16:47:23 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 640/1251] eta: 0:05:12 lr: 0.000857 loss: 3.6287 (3.5831) grad_norm: 1.0316 (1.0841) time: 0.5090 [2021-03-25 16:47:28 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 650/1251] eta: 0:05:07 lr: 0.000857 loss: 3.3829 (3.5801) grad_norm: 1.0404 (1.0839) time: 0.5050 [2021-03-25 16:47:33 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 660/1251] eta: 0:05:01 lr: 0.000857 loss: 3.7838 (3.5799) grad_norm: 1.0323 (1.0835) time: 0.4999 [2021-03-25 16:47:38 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 670/1251] eta: 0:04:56 lr: 0.000857 loss: 3.7185 (3.5763) grad_norm: 1.0235 (1.0828) time: 0.4978 [2021-03-25 16:47:43 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 680/1251] eta: 0:04:51 lr: 0.000857 loss: 3.5112 (3.5748) grad_norm: 0.9903 (1.0821) time: 0.4956 [2021-03-25 16:47:48 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 690/1251] eta: 0:04:46 lr: 0.000857 loss: 3.6472 (3.5802) grad_norm: 1.0586 (1.0830) time: 0.5005 [2021-03-25 16:47:53 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 700/1251] eta: 0:04:41 lr: 0.000857 loss: 3.9800 (3.5800) grad_norm: 1.1426 (1.0840) time: 0.5023 [2021-03-25 16:47:58 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 710/1251] eta: 0:04:36 lr: 0.000857 loss: 3.5796 (3.5804) grad_norm: 1.1574 (1.0855) time: 0.5014 [2021-03-25 16:48:03 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 720/1251] eta: 0:04:30 lr: 0.000857 loss: 3.4992 (3.5792) grad_norm: 1.1081 (1.0856) time: 0.5069 [2021-03-25 16:48:08 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 730/1251] eta: 0:04:25 lr: 0.000857 loss: 3.4104 (3.5784) grad_norm: 1.0699 (1.0856) time: 0.5125 [2021-03-25 16:48:14 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 740/1251] eta: 0:04:20 lr: 0.000857 loss: 3.4719 (3.5758) grad_norm: 1.0580 (1.0863) time: 0.5249 [2021-03-25 16:48:19 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 750/1251] eta: 0:04:15 lr: 0.000856 loss: 3.5810 (3.5757) grad_norm: 1.0405 (1.0860) time: 0.5247 [2021-03-25 16:48:24 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 760/1251] eta: 0:04:10 lr: 0.000856 loss: 3.6606 (3.5769) grad_norm: 1.0499 (1.0860) time: 0.5115 [2021-03-25 16:48:29 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 770/1251] eta: 0:04:05 lr: 0.000856 loss: 3.6620 (3.5796) grad_norm: 1.0499 (1.0853) time: 0.5086 [2021-03-25 16:48:34 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 780/1251] eta: 0:04:00 lr: 0.000856 loss: 3.7382 (3.5818) grad_norm: 1.0254 (1.0849) time: 0.5068 [2021-03-25 16:48:39 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 790/1251] eta: 0:03:55 lr: 0.000856 loss: 3.7079 (3.5802) grad_norm: 1.0314 (1.0845) time: 0.5099 [2021-03-25 16:48:44 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 800/1251] eta: 0:03:50 lr: 0.000856 loss: 3.6809 (3.5792) grad_norm: 1.0393 (1.0847) time: 0.5128 [2021-03-25 16:48:49 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 810/1251] eta: 0:03:45 lr: 0.000856 loss: 3.4310 (3.5770) grad_norm: 1.0539 (1.0841) time: 0.5075 [2021-03-25 16:48:54 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 820/1251] eta: 0:03:40 lr: 0.000856 loss: 3.2124 (3.5721) grad_norm: 1.0379 (1.0838) time: 0.5115 [2021-03-25 16:49:00 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 830/1251] eta: 0:03:34 lr: 0.000856 loss: 3.4092 (3.5716) grad_norm: 1.0426 (1.0834) time: 0.5145 [2021-03-25 16:49:05 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 840/1251] eta: 0:03:29 lr: 0.000856 loss: 3.5321 (3.5694) grad_norm: 1.0403 (1.0829) time: 0.5061 [2021-03-25 16:49:10 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 850/1251] eta: 0:03:24 lr: 0.000856 loss: 3.4933 (3.5690) grad_norm: 1.0966 (1.0832) time: 0.5024 [2021-03-25 16:49:15 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 860/1251] eta: 0:03:19 lr: 0.000856 loss: 3.5369 (3.5703) grad_norm: 1.0613 (1.0828) time: 0.5041 [2021-03-25 16:49:20 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 870/1251] eta: 0:03:14 lr: 0.000856 loss: 3.8469 (3.5725) grad_norm: 1.0361 (1.0827) time: 0.5073 [2021-03-25 16:49:25 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 880/1251] eta: 0:03:09 lr: 0.000856 loss: 3.8473 (3.5763) grad_norm: 1.0887 (1.0835) time: 0.5111 [2021-03-25 16:49:30 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 890/1251] eta: 0:03:04 lr: 0.000856 loss: 3.8473 (3.5773) grad_norm: 1.0635 (1.0829) time: 0.5053 [2021-03-25 16:49:35 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 900/1251] eta: 0:02:59 lr: 0.000856 loss: 3.6130 (3.5775) grad_norm: 1.0413 (1.0831) time: 0.5005 [2021-03-25 16:49:40 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 910/1251] eta: 0:02:53 lr: 0.000856 loss: 3.9287 (3.5814) grad_norm: 1.0246 (1.0829) time: 0.5060 [2021-03-25 16:49:45 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 920/1251] eta: 0:02:48 lr: 0.000856 loss: 3.9287 (3.5832) grad_norm: 1.0286 (1.0826) time: 0.5058 [2021-03-25 16:49:50 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 930/1251] eta: 0:02:43 lr: 0.000856 loss: 3.7013 (3.5831) grad_norm: 1.0286 (1.0826) time: 0.5066 [2021-03-25 16:49:55 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 940/1251] eta: 0:02:38 lr: 0.000856 loss: 3.4949 (3.5828) grad_norm: 1.0249 (1.0827) time: 0.5144 [2021-03-25 16:50:00 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 950/1251] eta: 0:02:33 lr: 0.000856 loss: 3.6860 (3.5840) grad_norm: 1.0390 (1.0821) time: 0.5082 [2021-03-25 16:50:05 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 960/1251] eta: 0:02:28 lr: 0.000856 loss: 3.5462 (3.5850) grad_norm: 1.0104 (1.0819) time: 0.5012 [2021-03-25 16:50:10 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 970/1251] eta: 0:02:23 lr: 0.000856 loss: 3.5069 (3.5838) grad_norm: 1.0022 (1.0813) time: 0.5048 [2021-03-25 16:50:15 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 980/1251] eta: 0:02:18 lr: 0.000856 loss: 3.3867 (3.5826) grad_norm: 1.0399 (1.0812) time: 0.5038 [2021-03-25 16:50:21 swin_small_patch4_window7_224] INFO: Epoch: [74] [ 990/1251] eta: 0:02:13 lr: 0.000856 loss: 3.4857 (3.5830) grad_norm: 1.0630 (1.0814) time: 0.5024 [2021-03-25 16:50:26 swin_small_patch4_window7_224] INFO: Epoch: [74] [1000/1251] eta: 0:02:07 lr: 0.000856 loss: 3.5393 (3.5829) grad_norm: 1.0761 (1.0815) time: 0.5054 [2021-03-25 16:50:31 swin_small_patch4_window7_224] INFO: Epoch: [74] [1010/1251] eta: 0:02:02 lr: 0.000856 loss: 3.3417 (3.5798) grad_norm: 1.0905 (1.0817) time: 0.5085 [2021-03-25 16:50:36 swin_small_patch4_window7_224] INFO: Epoch: [74] [1020/1251] eta: 0:01:57 lr: 0.000856 loss: 3.3554 (3.5814) grad_norm: 1.1103 (1.0816) time: 0.5047 [2021-03-25 16:50:41 swin_small_patch4_window7_224] INFO: Epoch: [74] [1030/1251] eta: 0:01:52 lr: 0.000856 loss: 3.8171 (3.5794) grad_norm: 1.0481 (1.0816) time: 0.5039 [2021-03-25 16:50:46 swin_small_patch4_window7_224] INFO: Epoch: [74] [1040/1251] eta: 0:01:47 lr: 0.000856 loss: 3.2589 (3.5781) grad_norm: 1.0156 (1.0811) time: 0.5076 [2021-03-25 16:50:51 swin_small_patch4_window7_224] INFO: Epoch: [74] [1050/1251] eta: 0:01:42 lr: 0.000856 loss: 3.4305 (3.5792) grad_norm: 1.0481 (1.0818) time: 0.5065 [2021-03-25 16:50:56 swin_small_patch4_window7_224] INFO: Epoch: [74] [1060/1251] eta: 0:01:37 lr: 0.000856 loss: 3.8088 (3.5812) grad_norm: 1.1052 (1.0820) time: 0.5042 [2021-03-25 16:51:01 swin_small_patch4_window7_224] INFO: Epoch: [74] [1070/1251] eta: 0:01:32 lr: 0.000856 loss: 3.7837 (3.5813) grad_norm: 1.1011 (1.0821) time: 0.4990 [2021-03-25 16:51:06 swin_small_patch4_window7_224] INFO: Epoch: [74] [1080/1251] eta: 0:01:27 lr: 0.000856 loss: 3.6942 (3.5834) grad_norm: 1.0510 (1.0816) time: 0.5023 [2021-03-25 16:51:11 swin_small_patch4_window7_224] INFO: Epoch: [74] [1090/1251] eta: 0:01:22 lr: 0.000855 loss: 3.8390 (3.5853) grad_norm: 1.0403 (1.0816) time: 0.5061 [2021-03-25 16:51:16 swin_small_patch4_window7_224] INFO: Epoch: [74] [1100/1251] eta: 0:01:16 lr: 0.000855 loss: 3.9603 (3.5873) grad_norm: 1.0848 (1.0818) time: 0.5007 [2021-03-25 16:51:21 swin_small_patch4_window7_224] INFO: Epoch: [74] [1110/1251] eta: 0:01:11 lr: 0.000855 loss: 3.8520 (3.5875) grad_norm: 1.0788 (1.0818) time: 0.5000 [2021-03-25 16:51:26 swin_small_patch4_window7_224] INFO: Epoch: [74] [1120/1251] eta: 0:01:06 lr: 0.000855 loss: 3.7072 (3.5858) grad_norm: 1.0691 (1.0820) time: 0.5008 [2021-03-25 16:51:31 swin_small_patch4_window7_224] INFO: Epoch: [74] [1130/1251] eta: 0:01:01 lr: 0.000855 loss: 3.5946 (3.5872) grad_norm: 1.0345 (1.0817) time: 0.5045 [2021-03-25 16:51:36 swin_small_patch4_window7_224] INFO: Epoch: [74] [1140/1251] eta: 0:00:56 lr: 0.000855 loss: 3.8126 (3.5895) grad_norm: 1.0116 (1.0812) time: 0.5074 [2021-03-25 16:51:41 swin_small_patch4_window7_224] INFO: Epoch: [74] [1150/1251] eta: 0:00:51 lr: 0.000855 loss: 3.8825 (3.5892) grad_norm: 1.0374 (1.0816) time: 0.5074 [2021-03-25 16:51:46 swin_small_patch4_window7_224] INFO: Epoch: [74] [1160/1251] eta: 0:00:46 lr: 0.000855 loss: 3.3830 (3.5877) grad_norm: 1.0535 (1.0814) time: 0.5057 [2021-03-25 16:51:51 swin_small_patch4_window7_224] INFO: Epoch: [74] [1170/1251] eta: 0:00:41 lr: 0.000855 loss: 3.8595 (3.5886) grad_norm: 0.9961 (1.0810) time: 0.4984 [2021-03-25 16:51:56 swin_small_patch4_window7_224] INFO: Epoch: [74] [1180/1251] eta: 0:00:36 lr: 0.000855 loss: 3.8595 (3.5887) grad_norm: 1.0384 (1.0811) time: 0.4980 [2021-03-25 16:52:01 swin_small_patch4_window7_224] INFO: Epoch: [74] [1190/1251] eta: 0:00:31 lr: 0.000855 loss: 3.6537 (3.5872) grad_norm: 1.0934 (1.0809) time: 0.5074 [2021-03-25 16:52:07 swin_small_patch4_window7_224] INFO: Epoch: [74] [1200/1251] eta: 0:00:25 lr: 0.000855 loss: 3.5109 (3.5872) grad_norm: 1.0563 (1.0809) time: 0.5146 [2021-03-25 16:52:12 swin_small_patch4_window7_224] INFO: Epoch: [74] [1210/1251] eta: 0:00:20 lr: 0.000855 loss: 3.7769 (3.5890) grad_norm: 1.0535 (1.0806) time: 0.5091 [2021-03-25 16:52:17 swin_small_patch4_window7_224] INFO: Epoch: [74] [1220/1251] eta: 0:00:15 lr: 0.000855 loss: 3.7882 (3.5908) grad_norm: 1.0299 (1.0805) time: 0.5023 [2021-03-25 16:52:22 swin_small_patch4_window7_224] INFO: Epoch: [74] [1230/1251] eta: 0:00:10 lr: 0.000855 loss: 3.7341 (3.5913) grad_norm: 1.0419 (1.0800) time: 0.5070 [2021-03-25 16:52:27 swin_small_patch4_window7_224] INFO: Epoch: [74] [1240/1251] eta: 0:00:05 lr: 0.000855 loss: 3.7341 (3.5920) grad_norm: 1.0793 (1.0802) time: 0.5065 [2021-03-25 16:52:32 swin_small_patch4_window7_224] INFO: Epoch: [74] [1250/1251] eta: 0:00:00 lr: 0.000855 loss: 3.7262 (3.5925) grad_norm: 1.1125 (1.0807) time: 0.4998 [2021-03-25 16:52:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:50 loss: 1.2137 (1.2137) acc1: 70.3125 (70.3125) acc5: 92.1875 (92.1875) [2021-03-25 16:52:39 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.1715 (1.1260) acc1: 73.4375 (75.1420) acc5: 93.7500 (91.1932) [2021-03-25 16:52:41 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0220 (1.0998) acc1: 73.4375 (74.4048) acc5: 93.7500 (92.7083) [2021-03-25 16:52:44 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0678 (1.1224) acc1: 71.8750 (74.0927) acc5: 92.1875 (92.3387) [2021-03-25 16:52:45 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0678 (1.1144) acc1: 75.0000 (74.3521) acc5: 92.1875 (92.2256) [2021-03-25 16:52:46 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0432 (1.1117) acc1: 75.0000 (74.3680) acc5: 93.7500 (92.4480) [2021-03-25 16:52:51 swin_small_patch4_window7_224] INFO: * Acc@1 75.012 Acc@5 92.822 loss 1.078 [2021-03-25 16:52:51 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.0% [2021-03-25 16:52:51 swin_small_patch4_window7_224] INFO: Max accuracy: 75.01% [2021-03-25 16:52:55 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 0/1251] eta: 1:31:06 lr: 0.000855 loss: 4.2218 (4.2218) grad_norm: 1.0097 (1.0097) time: 4.3698 [2021-03-25 16:53:00 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 10/1251] eta: 0:18:01 lr: 0.000855 loss: 3.9183 (3.6829) grad_norm: 1.0379 (1.0708) time: 0.8711 [2021-03-25 16:53:05 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 20/1251] eta: 0:14:12 lr: 0.000855 loss: 3.6001 (3.5348) grad_norm: 1.0360 (1.0593) time: 0.5083 [2021-03-25 16:53:10 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 30/1251] eta: 0:12:50 lr: 0.000855 loss: 3.5543 (3.5885) grad_norm: 1.0042 (1.0464) time: 0.4992 [2021-03-25 16:53:15 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 40/1251] eta: 0:12:11 lr: 0.000855 loss: 3.7766 (3.6390) grad_norm: 0.9741 (1.0351) time: 0.5115 [2021-03-25 16:53:20 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 50/1251] eta: 0:11:41 lr: 0.000855 loss: 3.8603 (3.6453) grad_norm: 1.0659 (inf) time: 0.5101 [2021-03-25 16:53:25 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 60/1251] eta: 0:11:18 lr: 0.000855 loss: 3.7010 (3.6409) grad_norm: 1.1014 (inf) time: 0.5005 [2021-03-25 16:53:30 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 70/1251] eta: 0:11:01 lr: 0.000855 loss: 3.6122 (3.5946) grad_norm: 1.0467 (inf) time: 0.5011 [2021-03-25 16:53:35 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 80/1251] eta: 0:10:47 lr: 0.000855 loss: 3.1727 (3.5656) grad_norm: 1.0467 (inf) time: 0.5006 [2021-03-25 16:53:41 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 90/1251] eta: 0:10:35 lr: 0.000855 loss: 3.5512 (3.5823) grad_norm: 1.0604 (inf) time: 0.5025 [2021-03-25 16:53:46 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 100/1251] eta: 0:10:26 lr: 0.000855 loss: 3.6616 (3.6020) grad_norm: 1.0478 (inf) time: 0.5094 [2021-03-25 16:53:51 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 110/1251] eta: 0:10:17 lr: 0.000855 loss: 3.6604 (3.5962) grad_norm: 0.9705 (inf) time: 0.5137 [2021-03-25 16:53:56 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 120/1251] eta: 0:10:08 lr: 0.000855 loss: 3.6529 (3.5891) grad_norm: 0.9495 (inf) time: 0.5081 [2021-03-25 16:54:01 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 130/1251] eta: 0:10:03 lr: 0.000855 loss: 3.5691 (3.5779) grad_norm: 0.9495 (inf) time: 0.5217 [2021-03-25 16:54:06 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 140/1251] eta: 0:09:55 lr: 0.000855 loss: 3.7750 (3.6012) grad_norm: 0.9952 (inf) time: 0.5237 [2021-03-25 16:54:11 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 150/1251] eta: 0:09:48 lr: 0.000855 loss: 3.8381 (3.6121) grad_norm: 1.0353 (inf) time: 0.5058 [2021-03-25 16:54:16 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 160/1251] eta: 0:09:41 lr: 0.000855 loss: 3.8005 (3.6180) grad_norm: 1.0077 (inf) time: 0.5071 [2021-03-25 16:54:22 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 170/1251] eta: 0:09:34 lr: 0.000855 loss: 3.7048 (3.6251) grad_norm: 1.0032 (inf) time: 0.5092 [2021-03-25 16:54:27 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 180/1251] eta: 0:09:28 lr: 0.000854 loss: 3.6144 (3.6174) grad_norm: 1.0437 (inf) time: 0.5127 [2021-03-25 16:54:32 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 190/1251] eta: 0:09:21 lr: 0.000854 loss: 3.6144 (3.6158) grad_norm: 1.0303 (inf) time: 0.5119 [2021-03-25 16:54:37 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 200/1251] eta: 0:09:15 lr: 0.000854 loss: 3.7459 (3.6195) grad_norm: 1.0303 (inf) time: 0.5096 [2021-03-25 16:54:42 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 210/1251] eta: 0:09:08 lr: 0.000854 loss: 3.7744 (3.6100) grad_norm: 1.0422 (inf) time: 0.5075 [2021-03-25 16:54:47 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 220/1251] eta: 0:09:02 lr: 0.000854 loss: 3.5511 (3.6096) grad_norm: 1.0476 (inf) time: 0.5000 [2021-03-25 16:54:52 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 230/1251] eta: 0:08:56 lr: 0.000854 loss: 3.5511 (3.5984) grad_norm: 1.1068 (inf) time: 0.5016 [2021-03-25 16:54:57 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 240/1251] eta: 0:08:49 lr: 0.000854 loss: 3.5625 (3.5994) grad_norm: 1.0702 (inf) time: 0.5066 [2021-03-25 16:55:02 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 250/1251] eta: 0:08:44 lr: 0.000854 loss: 3.5625 (3.5975) grad_norm: 1.0220 (inf) time: 0.5065 [2021-03-25 16:55:07 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 260/1251] eta: 0:08:37 lr: 0.000854 loss: 3.5501 (3.5968) grad_norm: 1.0479 (inf) time: 0.5048 [2021-03-25 16:55:12 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 270/1251] eta: 0:08:32 lr: 0.000854 loss: 3.5501 (3.5894) grad_norm: 1.0733 (inf) time: 0.5084 [2021-03-25 16:55:17 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 280/1251] eta: 0:08:26 lr: 0.000854 loss: 3.6326 (3.5968) grad_norm: 1.0399 (inf) time: 0.5115 [2021-03-25 16:55:22 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 290/1251] eta: 0:08:20 lr: 0.000854 loss: 3.8388 (3.6112) grad_norm: 1.1236 (inf) time: 0.5028 [2021-03-25 16:55:27 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 300/1251] eta: 0:08:15 lr: 0.000854 loss: 3.7729 (3.6117) grad_norm: 1.1363 (inf) time: 0.5052 [2021-03-25 16:55:33 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 310/1251] eta: 0:08:09 lr: 0.000854 loss: 3.5081 (3.6041) grad_norm: 1.1203 (inf) time: 0.5149 [2021-03-25 16:55:38 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 320/1251] eta: 0:08:04 lr: 0.000854 loss: 3.5087 (3.6074) grad_norm: 1.1083 (inf) time: 0.5164 [2021-03-25 16:55:43 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 330/1251] eta: 0:07:59 lr: 0.000854 loss: 3.5087 (3.6000) grad_norm: 1.0671 (inf) time: 0.5116 [2021-03-25 16:55:48 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 340/1251] eta: 0:07:53 lr: 0.000854 loss: 3.6006 (3.6049) grad_norm: 1.1133 (inf) time: 0.5063 [2021-03-25 16:55:53 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 350/1251] eta: 0:07:47 lr: 0.000854 loss: 3.7895 (3.6064) grad_norm: 1.0537 (inf) time: 0.5070 [2021-03-25 16:55:58 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 360/1251] eta: 0:07:42 lr: 0.000854 loss: 3.6772 (3.6084) grad_norm: 1.0118 (inf) time: 0.5066 [2021-03-25 16:56:03 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 370/1251] eta: 0:07:37 lr: 0.000854 loss: 3.6917 (3.6066) grad_norm: 1.0341 (inf) time: 0.5083 [2021-03-25 16:56:08 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 380/1251] eta: 0:07:31 lr: 0.000854 loss: 3.4906 (3.6024) grad_norm: 1.1140 (inf) time: 0.5073 [2021-03-25 16:56:13 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 390/1251] eta: 0:07:25 lr: 0.000854 loss: 3.5591 (3.6026) grad_norm: 1.0434 (inf) time: 0.5031 [2021-03-25 16:56:18 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 400/1251] eta: 0:07:20 lr: 0.000854 loss: 3.7178 (3.6043) grad_norm: 1.0169 (inf) time: 0.5040 [2021-03-25 16:56:23 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 410/1251] eta: 0:07:14 lr: 0.000854 loss: 3.9164 (3.6071) grad_norm: 1.0109 (inf) time: 0.5029 [2021-03-25 16:56:28 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 420/1251] eta: 0:07:09 lr: 0.000854 loss: 3.6243 (3.6000) grad_norm: 1.0674 (inf) time: 0.5042 [2021-03-25 16:56:33 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 430/1251] eta: 0:07:04 lr: 0.000854 loss: 3.4782 (3.6020) grad_norm: 1.0754 (inf) time: 0.5047 [2021-03-25 16:56:39 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 440/1251] eta: 0:06:58 lr: 0.000854 loss: 3.7196 (3.5993) grad_norm: 1.0754 (inf) time: 0.5054 [2021-03-25 16:56:43 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 450/1251] eta: 0:06:53 lr: 0.000854 loss: 3.7001 (3.5993) grad_norm: 1.1274 (inf) time: 0.5044 [2021-03-25 16:56:48 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 460/1251] eta: 0:06:47 lr: 0.000854 loss: 3.7571 (3.6042) grad_norm: 1.0733 (inf) time: 0.4965 [2021-03-25 16:56:54 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 470/1251] eta: 0:06:42 lr: 0.000854 loss: 3.9258 (3.6054) grad_norm: 1.0546 (inf) time: 0.5006 [2021-03-25 16:56:59 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 480/1251] eta: 0:06:37 lr: 0.000854 loss: 3.7198 (3.6038) grad_norm: 1.0615 (inf) time: 0.5056 [2021-03-25 16:57:03 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 490/1251] eta: 0:06:31 lr: 0.000854 loss: 3.6469 (3.6018) grad_norm: 1.0784 (inf) time: 0.4978 [2021-03-25 16:57:09 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 500/1251] eta: 0:06:26 lr: 0.000854 loss: 3.7495 (3.6036) grad_norm: 1.0880 (inf) time: 0.5002 [2021-03-25 16:57:14 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 510/1251] eta: 0:06:21 lr: 0.000854 loss: 3.7495 (3.6011) grad_norm: 1.0863 (inf) time: 0.5017 [2021-03-25 16:57:19 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 520/1251] eta: 0:06:15 lr: 0.000853 loss: 3.7796 (3.6027) grad_norm: 1.0418 (inf) time: 0.5001 [2021-03-25 16:57:23 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 530/1251] eta: 0:06:10 lr: 0.000853 loss: 3.8748 (3.6080) grad_norm: 1.0119 (inf) time: 0.4992 [2021-03-25 16:57:29 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 540/1251] eta: 0:06:05 lr: 0.000853 loss: 3.7843 (3.6101) grad_norm: 1.0071 (inf) time: 0.5054 [2021-03-25 16:57:34 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 550/1251] eta: 0:06:00 lr: 0.000853 loss: 3.7101 (3.6098) grad_norm: 1.0474 (inf) time: 0.5210 [2021-03-25 16:57:39 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 560/1251] eta: 0:05:54 lr: 0.000853 loss: 3.7101 (3.6074) grad_norm: 1.0906 (inf) time: 0.5117 [2021-03-25 16:57:44 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 570/1251] eta: 0:05:49 lr: 0.000853 loss: 3.7794 (3.6121) grad_norm: 1.1300 (inf) time: 0.5033 [2021-03-25 16:57:49 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 580/1251] eta: 0:05:44 lr: 0.000853 loss: 3.9010 (3.6148) grad_norm: 1.0976 (inf) time: 0.5016 [2021-03-25 16:57:54 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 590/1251] eta: 0:05:39 lr: 0.000853 loss: 3.9501 (3.6202) grad_norm: 1.0625 (inf) time: 0.5069 [2021-03-25 16:57:59 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 600/1251] eta: 0:05:34 lr: 0.000853 loss: 3.8413 (3.6207) grad_norm: 1.0328 (inf) time: 0.5104 [2021-03-25 16:58:04 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 610/1251] eta: 0:05:28 lr: 0.000853 loss: 3.7382 (3.6223) grad_norm: 1.0763 (inf) time: 0.5013 [2021-03-25 16:58:09 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 620/1251] eta: 0:05:23 lr: 0.000853 loss: 3.7382 (3.6212) grad_norm: 1.1080 (inf) time: 0.5035 [2021-03-25 16:58:14 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 630/1251] eta: 0:05:18 lr: 0.000853 loss: 3.7085 (3.6208) grad_norm: 1.1052 (inf) time: 0.5046 [2021-03-25 16:58:19 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 640/1251] eta: 0:05:13 lr: 0.000853 loss: 3.7085 (3.6191) grad_norm: 1.0777 (inf) time: 0.4999 [2021-03-25 16:58:24 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 650/1251] eta: 0:05:07 lr: 0.000853 loss: 3.6974 (3.6209) grad_norm: 1.0631 (inf) time: 0.4973 [2021-03-25 16:58:29 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 660/1251] eta: 0:05:02 lr: 0.000853 loss: 3.7016 (3.6220) grad_norm: 1.0056 (inf) time: 0.5014 [2021-03-25 16:58:34 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 670/1251] eta: 0:04:57 lr: 0.000853 loss: 3.7004 (3.6221) grad_norm: 1.0029 (inf) time: 0.5073 [2021-03-25 16:58:39 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 680/1251] eta: 0:04:52 lr: 0.000853 loss: 3.6347 (3.6218) grad_norm: 1.0473 (inf) time: 0.5101 [2021-03-25 16:58:45 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 690/1251] eta: 0:04:47 lr: 0.000853 loss: 3.6350 (3.6218) grad_norm: 1.1107 (inf) time: 0.5156 [2021-03-25 16:58:50 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 700/1251] eta: 0:04:42 lr: 0.000853 loss: 3.5995 (3.6214) grad_norm: 1.0752 (inf) time: 0.5110 [2021-03-25 16:58:55 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 710/1251] eta: 0:04:36 lr: 0.000853 loss: 3.5307 (3.6162) grad_norm: 1.0586 (inf) time: 0.5039 [2021-03-25 16:59:00 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 720/1251] eta: 0:04:31 lr: 0.000853 loss: 3.3837 (3.6139) grad_norm: 1.0719 (inf) time: 0.5034 [2021-03-25 16:59:05 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 730/1251] eta: 0:04:26 lr: 0.000853 loss: 3.6749 (3.6136) grad_norm: 1.0172 (inf) time: 0.5116 [2021-03-25 16:59:10 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 740/1251] eta: 0:04:21 lr: 0.000853 loss: 3.7642 (3.6150) grad_norm: 1.0375 (inf) time: 0.5248 [2021-03-25 16:59:15 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 750/1251] eta: 0:04:16 lr: 0.000853 loss: 3.6089 (3.6088) grad_norm: 1.0519 (inf) time: 0.5228 [2021-03-25 16:59:21 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 760/1251] eta: 0:04:11 lr: 0.000853 loss: 2.8866 (3.6056) grad_norm: 1.0383 (inf) time: 0.5152 [2021-03-25 16:59:26 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 770/1251] eta: 0:04:06 lr: 0.000853 loss: 3.7903 (3.6074) grad_norm: 1.0231 (inf) time: 0.5080 [2021-03-25 16:59:31 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 780/1251] eta: 0:04:01 lr: 0.000853 loss: 3.7504 (3.6093) grad_norm: 1.0268 (inf) time: 0.5105 [2021-03-25 16:59:36 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 790/1251] eta: 0:03:56 lr: 0.000853 loss: 3.7752 (3.6135) grad_norm: 1.0101 (inf) time: 0.5171 [2021-03-25 16:59:41 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 800/1251] eta: 0:03:50 lr: 0.000853 loss: 3.9340 (3.6136) grad_norm: 1.0408 (inf) time: 0.5087 [2021-03-25 16:59:46 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 810/1251] eta: 0:03:45 lr: 0.000853 loss: 3.6617 (3.6136) grad_norm: 1.1037 (inf) time: 0.5042 [2021-03-25 16:59:51 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 820/1251] eta: 0:03:40 lr: 0.000853 loss: 3.5708 (3.6121) grad_norm: 1.0205 (inf) time: 0.5064 [2021-03-25 16:59:56 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 830/1251] eta: 0:03:35 lr: 0.000853 loss: 3.7011 (3.6131) grad_norm: 1.0202 (inf) time: 0.5022 [2021-03-25 17:00:01 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 840/1251] eta: 0:03:30 lr: 0.000853 loss: 3.7923 (3.6134) grad_norm: 1.0238 (inf) time: 0.5028 [2021-03-25 17:00:06 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 850/1251] eta: 0:03:25 lr: 0.000853 loss: 3.7362 (3.6133) grad_norm: 1.0399 (inf) time: 0.5031 [2021-03-25 17:00:11 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 860/1251] eta: 0:03:20 lr: 0.000852 loss: 3.4921 (3.6098) grad_norm: 1.0366 (inf) time: 0.5035 [2021-03-25 17:00:16 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 870/1251] eta: 0:03:14 lr: 0.000852 loss: 3.4921 (3.6093) grad_norm: 1.0349 (inf) time: 0.5095 [2021-03-25 17:00:21 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 880/1251] eta: 0:03:09 lr: 0.000852 loss: 3.8572 (3.6125) grad_norm: 1.0349 (inf) time: 0.5138 [2021-03-25 17:00:27 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 890/1251] eta: 0:03:04 lr: 0.000852 loss: 3.8659 (3.6134) grad_norm: 1.0886 (inf) time: 0.5103 [2021-03-25 17:00:32 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 900/1251] eta: 0:02:59 lr: 0.000852 loss: 3.6519 (3.6103) grad_norm: 1.1226 (inf) time: 0.5036 [2021-03-25 17:00:37 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 910/1251] eta: 0:02:54 lr: 0.000852 loss: 3.4729 (3.6080) grad_norm: 1.1387 (inf) time: 0.5013 [2021-03-25 17:00:42 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 920/1251] eta: 0:02:49 lr: 0.000852 loss: 3.4216 (3.6078) grad_norm: 1.1015 (inf) time: 0.5050 [2021-03-25 17:00:47 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 930/1251] eta: 0:02:44 lr: 0.000852 loss: 3.7179 (3.6078) grad_norm: 1.0547 (inf) time: 0.5133 [2021-03-25 17:00:52 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 940/1251] eta: 0:02:39 lr: 0.000852 loss: 3.6975 (3.6057) grad_norm: 1.0501 (inf) time: 0.5146 [2021-03-25 17:00:57 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 950/1251] eta: 0:02:33 lr: 0.000852 loss: 3.8506 (3.6100) grad_norm: 1.0501 (inf) time: 0.5045 [2021-03-25 17:01:02 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 960/1251] eta: 0:02:28 lr: 0.000852 loss: 3.9309 (3.6132) grad_norm: 1.0940 (inf) time: 0.4994 [2021-03-25 17:01:07 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 970/1251] eta: 0:02:23 lr: 0.000852 loss: 3.7268 (3.6122) grad_norm: 1.0940 (inf) time: 0.4986 [2021-03-25 17:01:12 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 980/1251] eta: 0:02:18 lr: 0.000852 loss: 3.4660 (3.6100) grad_norm: 1.0900 (inf) time: 0.4968 [2021-03-25 17:01:17 swin_small_patch4_window7_224] INFO: Epoch: [75] [ 990/1251] eta: 0:02:13 lr: 0.000852 loss: 3.5420 (3.6100) grad_norm: 1.0779 (inf) time: 0.5024 [2021-03-25 17:01:22 swin_small_patch4_window7_224] INFO: Epoch: [75] [1000/1251] eta: 0:02:08 lr: 0.000852 loss: 3.6829 (3.6116) grad_norm: 1.0964 (inf) time: 0.5065 [2021-03-25 17:01:27 swin_small_patch4_window7_224] INFO: Epoch: [75] [1010/1251] eta: 0:02:03 lr: 0.000852 loss: 3.8413 (3.6111) grad_norm: 1.0410 (inf) time: 0.5049 [2021-03-25 17:01:32 swin_small_patch4_window7_224] INFO: Epoch: [75] [1020/1251] eta: 0:01:57 lr: 0.000852 loss: 3.8413 (3.6133) grad_norm: 1.0241 (inf) time: 0.5034 [2021-03-25 17:01:37 swin_small_patch4_window7_224] INFO: Epoch: [75] [1030/1251] eta: 0:01:52 lr: 0.000852 loss: 3.8538 (3.6150) grad_norm: 1.0377 (inf) time: 0.5055 [2021-03-25 17:01:42 swin_small_patch4_window7_224] INFO: Epoch: [75] [1040/1251] eta: 0:01:47 lr: 0.000852 loss: 3.7926 (3.6142) grad_norm: 1.0372 (inf) time: 0.5116 [2021-03-25 17:01:47 swin_small_patch4_window7_224] INFO: Epoch: [75] [1050/1251] eta: 0:01:42 lr: 0.000852 loss: 3.8264 (3.6173) grad_norm: 1.0289 (inf) time: 0.5145 [2021-03-25 17:01:53 swin_small_patch4_window7_224] INFO: Epoch: [75] [1060/1251] eta: 0:01:37 lr: 0.000852 loss: 3.8726 (3.6178) grad_norm: 1.0289 (inf) time: 0.5123 [2021-03-25 17:01:58 swin_small_patch4_window7_224] INFO: Epoch: [75] [1070/1251] eta: 0:01:32 lr: 0.000852 loss: 3.8276 (3.6179) grad_norm: 1.0739 (inf) time: 0.5103 [2021-03-25 17:02:03 swin_small_patch4_window7_224] INFO: Epoch: [75] [1080/1251] eta: 0:01:27 lr: 0.000852 loss: 3.2867 (3.6153) grad_norm: 1.0507 (inf) time: 0.5131 [2021-03-25 17:02:08 swin_small_patch4_window7_224] INFO: Epoch: [75] [1090/1251] eta: 0:01:22 lr: 0.000852 loss: 3.2867 (3.6129) grad_norm: 1.0013 (inf) time: 0.5118 [2021-03-25 17:02:13 swin_small_patch4_window7_224] INFO: Epoch: [75] [1100/1251] eta: 0:01:17 lr: 0.000852 loss: 3.6320 (3.6140) grad_norm: 1.0657 (inf) time: 0.5031 [2021-03-25 17:02:18 swin_small_patch4_window7_224] INFO: Epoch: [75] [1110/1251] eta: 0:01:11 lr: 0.000852 loss: 3.7415 (3.6135) grad_norm: 1.0909 (inf) time: 0.5004 [2021-03-25 17:02:23 swin_small_patch4_window7_224] INFO: Epoch: [75] [1120/1251] eta: 0:01:06 lr: 0.000852 loss: 3.6220 (3.6118) grad_norm: 1.0788 (inf) time: 0.5004 [2021-03-25 17:02:28 swin_small_patch4_window7_224] INFO: Epoch: [75] [1130/1251] eta: 0:01:01 lr: 0.000852 loss: 3.6786 (3.6137) grad_norm: 1.0721 (inf) time: 0.5011 [2021-03-25 17:02:33 swin_small_patch4_window7_224] INFO: Epoch: [75] [1140/1251] eta: 0:00:56 lr: 0.000852 loss: 3.8543 (3.6120) grad_norm: 1.0474 (inf) time: 0.5052 [2021-03-25 17:02:38 swin_small_patch4_window7_224] INFO: Epoch: [75] [1150/1251] eta: 0:00:51 lr: 0.000852 loss: 3.4760 (3.6108) grad_norm: 0.9976 (inf) time: 0.5016 [2021-03-25 17:02:43 swin_small_patch4_window7_224] INFO: Epoch: [75] [1160/1251] eta: 0:00:46 lr: 0.000852 loss: 3.4760 (3.6109) grad_norm: 0.9918 (inf) time: 0.5005 [2021-03-25 17:02:48 swin_small_patch4_window7_224] INFO: Epoch: [75] [1170/1251] eta: 0:00:41 lr: 0.000852 loss: 3.6804 (3.6091) grad_norm: 1.0091 (inf) time: 0.5044 [2021-03-25 17:02:53 swin_small_patch4_window7_224] INFO: Epoch: [75] [1180/1251] eta: 0:00:36 lr: 0.000852 loss: 3.6729 (3.6106) grad_norm: 1.0323 (inf) time: 0.5073 [2021-03-25 17:02:58 swin_small_patch4_window7_224] INFO: Epoch: [75] [1190/1251] eta: 0:00:31 lr: 0.000852 loss: 3.6729 (3.6111) grad_norm: 1.1271 (inf) time: 0.5044 [2021-03-25 17:03:03 swin_small_patch4_window7_224] INFO: Epoch: [75] [1200/1251] eta: 0:00:26 lr: 0.000851 loss: 3.4290 (3.6094) grad_norm: 1.1710 (inf) time: 0.5049 [2021-03-25 17:03:08 swin_small_patch4_window7_224] INFO: Epoch: [75] [1210/1251] eta: 0:00:20 lr: 0.000851 loss: 3.1743 (3.6072) grad_norm: 1.1530 (inf) time: 0.5103 [2021-03-25 17:03:13 swin_small_patch4_window7_224] INFO: Epoch: [75] [1220/1251] eta: 0:00:15 lr: 0.000851 loss: 3.5813 (3.6073) grad_norm: 1.0944 (inf) time: 0.5086 [2021-03-25 17:03:18 swin_small_patch4_window7_224] INFO: Epoch: [75] [1230/1251] eta: 0:00:10 lr: 0.000851 loss: 3.6999 (3.6076) grad_norm: 1.0141 (inf) time: 0.5042 [2021-03-25 17:03:24 swin_small_patch4_window7_224] INFO: Epoch: [75] [1240/1251] eta: 0:00:05 lr: 0.000851 loss: 3.6999 (3.6080) grad_norm: 1.0384 (inf) time: 0.5013 [2021-03-25 17:03:28 swin_small_patch4_window7_224] INFO: Epoch: [75] [1250/1251] eta: 0:00:00 lr: 0.000851 loss: 3.4454 (3.6066) grad_norm: 1.0555 (inf) time: 0.4999 [2021-03-25 17:04:03 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:02 loss: 0.9759 (0.9759) acc1: 79.6875 (79.6875) acc5: 90.6250 (90.6250) [2021-03-25 17:04:05 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.1643 (1.1581) acc1: 68.7500 (72.5852) acc5: 92.1875 (91.3352) [2021-03-25 17:04:06 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.1643 (1.1272) acc1: 71.8750 (73.5119) acc5: 92.1875 (92.0387) [2021-03-25 17:04:07 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0410 (1.1145) acc1: 73.4375 (73.8911) acc5: 90.6250 (92.0363) [2021-03-25 17:04:08 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0298 (1.1006) acc1: 73.4375 (73.9710) acc5: 93.7500 (92.3018) [2021-03-25 17:04:09 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0699 (1.1098) acc1: 73.4375 (73.9840) acc5: 93.7500 (92.2880) [2021-03-25 17:04:12 swin_small_patch4_window7_224] INFO: * Acc@1 74.656 Acc@5 92.774 loss 1.088 [2021-03-25 17:04:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.7% [2021-03-25 17:04:12 swin_small_patch4_window7_224] INFO: Max accuracy: 75.01% [2021-03-25 17:04:16 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 0/1251] eta: 1:25:27 lr: 0.000851 loss: 4.1142 (4.1142) grad_norm: 0.9979 (0.9979) time: 4.0989 [2021-03-25 17:04:21 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 10/1251] eta: 0:17:32 lr: 0.000851 loss: 3.8650 (3.8354) grad_norm: 1.0207 (1.0512) time: 0.8478 [2021-03-25 17:04:27 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 20/1251] eta: 0:14:05 lr: 0.000851 loss: 3.7126 (3.6412) grad_norm: 1.0322 (1.0984) time: 0.5162 [2021-03-25 17:04:32 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 30/1251] eta: 0:12:49 lr: 0.000851 loss: 3.6025 (3.6969) grad_norm: 1.0692 (1.0976) time: 0.5105 [2021-03-25 17:04:37 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 40/1251] eta: 0:12:08 lr: 0.000851 loss: 3.7553 (3.6953) grad_norm: 1.1755 (1.1324) time: 0.5116 [2021-03-25 17:04:42 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 50/1251] eta: 0:11:40 lr: 0.000851 loss: 3.6347 (3.6571) grad_norm: 1.1032 (1.1191) time: 0.5112 [2021-03-25 17:04:47 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 60/1251] eta: 0:11:21 lr: 0.000851 loss: 3.7593 (3.6560) grad_norm: 1.0595 (1.1153) time: 0.5134 [2021-03-25 17:04:52 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 70/1251] eta: 0:11:05 lr: 0.000851 loss: 3.6879 (3.6304) grad_norm: 1.0628 (1.1084) time: 0.5114 [2021-03-25 17:04:57 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 80/1251] eta: 0:10:51 lr: 0.000851 loss: 3.5039 (3.6146) grad_norm: 1.0628 (1.1051) time: 0.5071 [2021-03-25 17:05:02 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 90/1251] eta: 0:10:41 lr: 0.000851 loss: 3.6796 (3.6539) grad_norm: 1.0428 (1.0974) time: 0.5131 [2021-03-25 17:05:07 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 100/1251] eta: 0:10:30 lr: 0.000851 loss: 3.6757 (3.6437) grad_norm: 1.0053 (1.0897) time: 0.5129 [2021-03-25 17:05:12 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 110/1251] eta: 0:10:20 lr: 0.000851 loss: 3.6497 (3.6465) grad_norm: 1.0063 (1.0855) time: 0.5068 [2021-03-25 17:05:18 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 120/1251] eta: 0:10:11 lr: 0.000851 loss: 3.6664 (3.6374) grad_norm: 1.0130 (1.0816) time: 0.5057 [2021-03-25 17:05:23 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 130/1251] eta: 0:10:03 lr: 0.000851 loss: 3.7973 (3.6516) grad_norm: 1.0072 (1.0779) time: 0.5056 [2021-03-25 17:05:28 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 140/1251] eta: 0:09:55 lr: 0.000851 loss: 3.8648 (3.6501) grad_norm: 1.0543 (1.0787) time: 0.5077 [2021-03-25 17:05:33 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 150/1251] eta: 0:09:47 lr: 0.000851 loss: 3.4296 (3.6326) grad_norm: 1.0642 (1.0791) time: 0.5053 [2021-03-25 17:05:38 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 160/1251] eta: 0:09:41 lr: 0.000851 loss: 3.7209 (3.6360) grad_norm: 1.0400 (1.0768) time: 0.5076 [2021-03-25 17:05:43 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 170/1251] eta: 0:09:34 lr: 0.000851 loss: 3.7677 (3.6339) grad_norm: 1.0302 (1.0767) time: 0.5110 [2021-03-25 17:05:48 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 180/1251] eta: 0:09:28 lr: 0.000851 loss: 3.4863 (3.6127) grad_norm: 1.0745 (1.0787) time: 0.5138 [2021-03-25 17:05:53 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 190/1251] eta: 0:09:22 lr: 0.000851 loss: 3.5496 (3.6273) grad_norm: 1.0745 (1.0795) time: 0.5179 [2021-03-25 17:05:58 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 200/1251] eta: 0:09:15 lr: 0.000851 loss: 3.8675 (3.6248) grad_norm: 1.0635 (1.0794) time: 0.5111 [2021-03-25 17:06:03 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 210/1251] eta: 0:09:09 lr: 0.000851 loss: 3.5035 (3.6146) grad_norm: 1.0424 (1.0797) time: 0.5062 [2021-03-25 17:06:09 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 220/1251] eta: 0:09:02 lr: 0.000851 loss: 3.6177 (3.6131) grad_norm: 1.0737 (1.0799) time: 0.5075 [2021-03-25 17:06:14 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 230/1251] eta: 0:08:56 lr: 0.000851 loss: 3.4978 (3.6076) grad_norm: 1.0737 (1.0817) time: 0.5050 [2021-03-25 17:06:19 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 240/1251] eta: 0:08:51 lr: 0.000851 loss: 3.5758 (3.6163) grad_norm: 1.0760 (1.0806) time: 0.5120 [2021-03-25 17:06:24 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 250/1251] eta: 0:08:45 lr: 0.000851 loss: 3.5141 (3.5944) grad_norm: 1.0596 (1.0796) time: 0.5192 [2021-03-25 17:06:29 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 260/1251] eta: 0:08:39 lr: 0.000851 loss: 3.2212 (3.5898) grad_norm: 1.0596 (1.0808) time: 0.5143 [2021-03-25 17:06:34 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 270/1251] eta: 0:08:33 lr: 0.000851 loss: 3.5209 (3.5929) grad_norm: 1.0816 (1.0819) time: 0.5036 [2021-03-25 17:06:39 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 280/1251] eta: 0:08:27 lr: 0.000851 loss: 3.7085 (3.5927) grad_norm: 1.1149 (1.0842) time: 0.5019 [2021-03-25 17:06:44 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 290/1251] eta: 0:08:21 lr: 0.000850 loss: 3.5948 (3.5897) grad_norm: 1.1149 (1.0840) time: 0.5071 [2021-03-25 17:06:49 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 300/1251] eta: 0:08:16 lr: 0.000850 loss: 3.4767 (3.5833) grad_norm: 1.0786 (1.0853) time: 0.5058 [2021-03-25 17:06:54 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 310/1251] eta: 0:08:10 lr: 0.000850 loss: 3.4050 (3.5792) grad_norm: 1.0520 (1.0849) time: 0.5057 [2021-03-25 17:06:59 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 320/1251] eta: 0:08:04 lr: 0.000850 loss: 3.6186 (3.5836) grad_norm: 1.0056 (1.0839) time: 0.5023 [2021-03-25 17:07:04 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 330/1251] eta: 0:07:58 lr: 0.000850 loss: 3.6911 (3.5767) grad_norm: 1.0299 (1.0831) time: 0.4965 [2021-03-25 17:07:09 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 340/1251] eta: 0:07:53 lr: 0.000850 loss: 3.4196 (3.5760) grad_norm: 1.0299 (1.0833) time: 0.5015 [2021-03-25 17:07:14 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 350/1251] eta: 0:07:47 lr: 0.000850 loss: 3.6124 (3.5767) grad_norm: 1.0204 (1.0813) time: 0.5063 [2021-03-25 17:07:19 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 360/1251] eta: 0:07:41 lr: 0.000850 loss: 3.7154 (3.5767) grad_norm: 1.1046 (1.0839) time: 0.4994 [2021-03-25 17:07:24 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 370/1251] eta: 0:07:36 lr: 0.000850 loss: 3.6000 (3.5658) grad_norm: 1.1205 (1.0850) time: 0.5018 [2021-03-25 17:07:29 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 380/1251] eta: 0:07:30 lr: 0.000850 loss: 3.4136 (3.5649) grad_norm: 1.0863 (1.0843) time: 0.5054 [2021-03-25 17:07:34 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 390/1251] eta: 0:07:25 lr: 0.000850 loss: 3.4136 (3.5554) grad_norm: 1.0562 (1.0849) time: 0.4994 [2021-03-25 17:07:39 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 400/1251] eta: 0:07:19 lr: 0.000850 loss: 3.4472 (3.5569) grad_norm: 1.0562 (1.0853) time: 0.4993 [2021-03-25 17:07:44 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 410/1251] eta: 0:07:14 lr: 0.000850 loss: 3.6028 (3.5598) grad_norm: 1.1161 (1.0870) time: 0.5019 [2021-03-25 17:07:49 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 420/1251] eta: 0:07:08 lr: 0.000850 loss: 3.5477 (3.5598) grad_norm: 1.0673 (1.0858) time: 0.4999 [2021-03-25 17:07:54 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 430/1251] eta: 0:07:03 lr: 0.000850 loss: 3.9032 (3.5641) grad_norm: 1.0394 (1.0858) time: 0.5048 [2021-03-25 17:08:00 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 440/1251] eta: 0:06:58 lr: 0.000850 loss: 3.7556 (3.5659) grad_norm: 1.0873 (1.0867) time: 0.5085 [2021-03-25 17:08:05 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 450/1251] eta: 0:06:52 lr: 0.000850 loss: 3.5673 (3.5646) grad_norm: 1.0759 (1.0860) time: 0.5050 [2021-03-25 17:08:10 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 460/1251] eta: 0:06:47 lr: 0.000850 loss: 3.5687 (3.5670) grad_norm: 1.0372 (1.0871) time: 0.5049 [2021-03-25 17:08:15 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 470/1251] eta: 0:06:42 lr: 0.000850 loss: 3.5688 (3.5675) grad_norm: 1.0728 (1.0877) time: 0.5059 [2021-03-25 17:08:20 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 480/1251] eta: 0:06:36 lr: 0.000850 loss: 3.4228 (3.5659) grad_norm: 1.0489 (1.0867) time: 0.5044 [2021-03-25 17:08:25 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 490/1251] eta: 0:06:31 lr: 0.000850 loss: 3.7573 (3.5685) grad_norm: 1.0453 (1.0859) time: 0.5038 [2021-03-25 17:08:30 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 500/1251] eta: 0:06:26 lr: 0.000850 loss: 3.8412 (3.5717) grad_norm: 1.0480 (1.0855) time: 0.5063 [2021-03-25 17:08:35 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 510/1251] eta: 0:06:21 lr: 0.000850 loss: 3.7929 (3.5715) grad_norm: 1.0480 (1.0858) time: 0.5068 [2021-03-25 17:08:40 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 520/1251] eta: 0:06:15 lr: 0.000850 loss: 3.5362 (3.5684) grad_norm: 1.0320 (1.0852) time: 0.5067 [2021-03-25 17:08:45 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 530/1251] eta: 0:06:10 lr: 0.000850 loss: 3.6621 (3.5705) grad_norm: 1.0302 (1.0846) time: 0.5071 [2021-03-25 17:08:50 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 540/1251] eta: 0:06:05 lr: 0.000850 loss: 3.7064 (3.5716) grad_norm: 1.0594 (1.0851) time: 0.5113 [2021-03-25 17:08:55 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 550/1251] eta: 0:06:00 lr: 0.000850 loss: 3.8339 (3.5739) grad_norm: 1.0594 (1.0845) time: 0.5149 [2021-03-25 17:09:00 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 560/1251] eta: 0:05:55 lr: 0.000850 loss: 3.6783 (3.5738) grad_norm: 1.0774 (1.0853) time: 0.5085 [2021-03-25 17:09:05 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 570/1251] eta: 0:05:49 lr: 0.000850 loss: 3.3735 (3.5672) grad_norm: 1.0925 (1.0861) time: 0.5045 [2021-03-25 17:09:11 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 580/1251] eta: 0:05:44 lr: 0.000850 loss: 3.3413 (3.5674) grad_norm: 1.1403 (1.0871) time: 0.5044 [2021-03-25 17:09:16 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 590/1251] eta: 0:05:39 lr: 0.000850 loss: 3.6372 (3.5657) grad_norm: 1.0589 (1.0870) time: 0.5067 [2021-03-25 17:09:21 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 600/1251] eta: 0:05:34 lr: 0.000850 loss: 3.5606 (3.5661) grad_norm: 1.0449 (1.0879) time: 0.5036 [2021-03-25 17:09:26 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 610/1251] eta: 0:05:28 lr: 0.000850 loss: 3.6288 (3.5661) grad_norm: 1.0631 (1.0884) time: 0.5006 [2021-03-25 17:09:31 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 620/1251] eta: 0:05:23 lr: 0.000849 loss: 3.7339 (3.5647) grad_norm: 1.0163 (1.0872) time: 0.5053 [2021-03-25 17:09:36 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 630/1251] eta: 0:05:18 lr: 0.000849 loss: 3.8260 (3.5686) grad_norm: 0.9908 (1.0863) time: 0.5013 [2021-03-25 17:09:41 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 640/1251] eta: 0:05:13 lr: 0.000849 loss: 3.6389 (3.5651) grad_norm: 1.0265 (1.0858) time: 0.5045 [2021-03-25 17:09:46 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 650/1251] eta: 0:05:08 lr: 0.000849 loss: 3.5385 (3.5690) grad_norm: 1.0292 (1.0855) time: 0.5091 [2021-03-25 17:09:51 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 660/1251] eta: 0:05:02 lr: 0.000849 loss: 3.9484 (3.5736) grad_norm: 1.0365 (1.0852) time: 0.5071 [2021-03-25 17:09:56 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 670/1251] eta: 0:04:57 lr: 0.000849 loss: 3.7611 (3.5744) grad_norm: 1.0522 (1.0855) time: 0.5104 [2021-03-25 17:10:01 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 680/1251] eta: 0:04:52 lr: 0.000849 loss: 3.9581 (3.5801) grad_norm: 1.0821 (1.0855) time: 0.5061 [2021-03-25 17:10:06 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 690/1251] eta: 0:04:47 lr: 0.000849 loss: 3.8324 (3.5772) grad_norm: 1.0821 (1.0852) time: 0.4985 [2021-03-25 17:10:11 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 700/1251] eta: 0:04:42 lr: 0.000849 loss: 3.6455 (3.5797) grad_norm: 1.0847 (1.0854) time: 0.5019 [2021-03-25 17:10:16 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 710/1251] eta: 0:04:37 lr: 0.000849 loss: 3.7597 (3.5826) grad_norm: 1.0847 (1.0857) time: 0.5174 [2021-03-25 17:10:21 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 720/1251] eta: 0:04:31 lr: 0.000849 loss: 3.8299 (3.5840) grad_norm: 1.0857 (1.0861) time: 0.5182 [2021-03-25 17:10:27 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 730/1251] eta: 0:04:26 lr: 0.000849 loss: 3.8299 (3.5848) grad_norm: 1.0805 (1.0857) time: 0.5111 [2021-03-25 17:10:32 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 740/1251] eta: 0:04:21 lr: 0.000849 loss: 3.6780 (3.5853) grad_norm: 1.0865 (1.0861) time: 0.5141 [2021-03-25 17:10:37 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 750/1251] eta: 0:04:16 lr: 0.000849 loss: 3.6896 (3.5860) grad_norm: 1.0208 (1.0847) time: 0.5110 [2021-03-25 17:10:42 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 760/1251] eta: 0:04:11 lr: 0.000849 loss: 3.7206 (3.5885) grad_norm: 0.9969 (1.0842) time: 0.5069 [2021-03-25 17:10:47 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 770/1251] eta: 0:04:06 lr: 0.000849 loss: 3.7109 (3.5902) grad_norm: 1.0595 (1.0844) time: 0.5060 [2021-03-25 17:10:52 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 780/1251] eta: 0:04:01 lr: 0.000849 loss: 3.6132 (3.5897) grad_norm: 1.0879 (1.0843) time: 0.5052 [2021-03-25 17:10:57 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 790/1251] eta: 0:03:55 lr: 0.000849 loss: 3.4383 (3.5853) grad_norm: 1.0753 (1.0843) time: 0.5080 [2021-03-25 17:11:02 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 800/1251] eta: 0:03:50 lr: 0.000849 loss: 3.3456 (3.5864) grad_norm: 1.0939 (1.0848) time: 0.5117 [2021-03-25 17:11:07 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 810/1251] eta: 0:03:45 lr: 0.000849 loss: 3.8102 (3.5890) grad_norm: 1.0807 (1.0850) time: 0.5150 [2021-03-25 17:11:12 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 820/1251] eta: 0:03:40 lr: 0.000849 loss: 3.7242 (3.5864) grad_norm: 1.0807 (1.0856) time: 0.5087 [2021-03-25 17:11:17 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 830/1251] eta: 0:03:35 lr: 0.000849 loss: 3.6056 (3.5888) grad_norm: 1.1136 (1.0862) time: 0.5005 [2021-03-25 17:11:23 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 840/1251] eta: 0:03:30 lr: 0.000849 loss: 3.7032 (3.5893) grad_norm: 1.0948 (1.0864) time: 0.5059 [2021-03-25 17:11:28 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 850/1251] eta: 0:03:25 lr: 0.000849 loss: 3.7826 (3.5913) grad_norm: 1.0691 (1.0862) time: 0.5087 [2021-03-25 17:11:33 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 860/1251] eta: 0:03:20 lr: 0.000849 loss: 3.5294 (3.5891) grad_norm: 1.0904 (1.0863) time: 0.5077 [2021-03-25 17:11:38 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 870/1251] eta: 0:03:14 lr: 0.000849 loss: 3.2531 (3.5892) grad_norm: 1.0755 (1.0862) time: 0.5073 [2021-03-25 17:11:43 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 880/1251] eta: 0:03:09 lr: 0.000849 loss: 3.3372 (3.5872) grad_norm: 1.0423 (1.0854) time: 0.5112 [2021-03-25 17:11:48 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 890/1251] eta: 0:03:04 lr: 0.000849 loss: 3.7600 (3.5895) grad_norm: 1.0112 (1.0845) time: 0.5092 [2021-03-25 17:11:53 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 900/1251] eta: 0:02:59 lr: 0.000849 loss: 3.8703 (3.5917) grad_norm: 1.0169 (1.0846) time: 0.4968 [2021-03-25 17:11:58 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 910/1251] eta: 0:02:54 lr: 0.000849 loss: 3.4972 (3.5874) grad_norm: 1.0533 (1.0848) time: 0.4960 [2021-03-25 17:12:03 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 920/1251] eta: 0:02:49 lr: 0.000849 loss: 3.3140 (3.5866) grad_norm: 1.0533 (1.0844) time: 0.5029 [2021-03-25 17:12:08 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 930/1251] eta: 0:02:44 lr: 0.000849 loss: 3.4704 (3.5856) grad_norm: 1.0267 (1.0841) time: 0.5099 [2021-03-25 17:12:13 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 940/1251] eta: 0:02:38 lr: 0.000849 loss: 3.4658 (3.5829) grad_norm: 1.0168 (1.0839) time: 0.5156 [2021-03-25 17:12:18 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 950/1251] eta: 0:02:33 lr: 0.000849 loss: 3.2872 (3.5813) grad_norm: 1.0497 (1.0838) time: 0.5098 [2021-03-25 17:12:23 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 960/1251] eta: 0:02:28 lr: 0.000848 loss: 3.6084 (3.5829) grad_norm: 1.0732 (1.0840) time: 0.5055 [2021-03-25 17:12:28 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 970/1251] eta: 0:02:23 lr: 0.000848 loss: 3.8374 (3.5834) grad_norm: 1.0895 (1.0841) time: 0.5101 [2021-03-25 17:12:34 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 980/1251] eta: 0:02:18 lr: 0.000848 loss: 3.5802 (3.5832) grad_norm: 1.0769 (1.0838) time: 0.5114 [2021-03-25 17:12:39 swin_small_patch4_window7_224] INFO: Epoch: [76] [ 990/1251] eta: 0:02:13 lr: 0.000848 loss: 3.4387 (3.5831) grad_norm: 1.0769 (1.0838) time: 0.5108 [2021-03-25 17:12:44 swin_small_patch4_window7_224] INFO: Epoch: [76] [1000/1251] eta: 0:02:08 lr: 0.000848 loss: 3.7576 (3.5832) grad_norm: 1.0844 (1.0843) time: 0.5096 [2021-03-25 17:12:49 swin_small_patch4_window7_224] INFO: Epoch: [76] [1010/1251] eta: 0:02:03 lr: 0.000848 loss: 3.7576 (3.5834) grad_norm: 1.1099 (1.0843) time: 0.5071 [2021-03-25 17:12:54 swin_small_patch4_window7_224] INFO: Epoch: [76] [1020/1251] eta: 0:01:58 lr: 0.000848 loss: 3.7234 (3.5835) grad_norm: 1.0647 (1.0840) time: 0.5043 [2021-03-25 17:12:59 swin_small_patch4_window7_224] INFO: Epoch: [76] [1030/1251] eta: 0:01:52 lr: 0.000848 loss: 3.5027 (3.5815) grad_norm: 1.0647 (1.0845) time: 0.5074 [2021-03-25 17:13:04 swin_small_patch4_window7_224] INFO: Epoch: [76] [1040/1251] eta: 0:01:47 lr: 0.000848 loss: 3.6406 (3.5838) grad_norm: 1.1264 (1.0859) time: 0.5091 [2021-03-25 17:13:09 swin_small_patch4_window7_224] INFO: Epoch: [76] [1050/1251] eta: 0:01:42 lr: 0.000848 loss: 3.8648 (3.5868) grad_norm: 1.1738 (1.0870) time: 0.5160 [2021-03-25 17:13:14 swin_small_patch4_window7_224] INFO: Epoch: [76] [1060/1251] eta: 0:01:37 lr: 0.000848 loss: 3.8280 (3.5867) grad_norm: 1.1434 (1.0870) time: 0.5150 [2021-03-25 17:13:19 swin_small_patch4_window7_224] INFO: Epoch: [76] [1070/1251] eta: 0:01:32 lr: 0.000848 loss: 3.5055 (3.5881) grad_norm: 1.0510 (1.0868) time: 0.5024 [2021-03-25 17:13:24 swin_small_patch4_window7_224] INFO: Epoch: [76] [1080/1251] eta: 0:01:27 lr: 0.000848 loss: 3.8345 (3.5896) grad_norm: 1.0887 (1.0869) time: 0.5012 [2021-03-25 17:13:30 swin_small_patch4_window7_224] INFO: Epoch: [76] [1090/1251] eta: 0:01:22 lr: 0.000848 loss: 3.7537 (3.5913) grad_norm: 1.0869 (1.0865) time: 0.5077 [2021-03-25 17:13:35 swin_small_patch4_window7_224] INFO: Epoch: [76] [1100/1251] eta: 0:01:17 lr: 0.000848 loss: 3.5707 (3.5896) grad_norm: 1.0581 (1.0865) time: 0.5114 [2021-03-25 17:13:40 swin_small_patch4_window7_224] INFO: Epoch: [76] [1110/1251] eta: 0:01:12 lr: 0.000848 loss: 3.5380 (3.5894) grad_norm: 1.0890 (1.0867) time: 0.5045 [2021-03-25 17:13:45 swin_small_patch4_window7_224] INFO: Epoch: [76] [1120/1251] eta: 0:01:06 lr: 0.000848 loss: 3.7330 (3.5914) grad_norm: 1.0760 (1.0865) time: 0.4985 [2021-03-25 17:13:50 swin_small_patch4_window7_224] INFO: Epoch: [76] [1130/1251] eta: 0:01:01 lr: 0.000848 loss: 3.3519 (3.5866) grad_norm: 1.0823 (1.0867) time: 0.5008 [2021-03-25 17:13:55 swin_small_patch4_window7_224] INFO: Epoch: [76] [1140/1251] eta: 0:00:56 lr: 0.000848 loss: 3.3284 (3.5863) grad_norm: 1.0704 (1.0861) time: 0.5088 [2021-03-25 17:14:00 swin_small_patch4_window7_224] INFO: Epoch: [76] [1150/1251] eta: 0:00:51 lr: 0.000848 loss: 3.3284 (3.5839) grad_norm: 1.0169 (1.0858) time: 0.5099 [2021-03-25 17:14:05 swin_small_patch4_window7_224] INFO: Epoch: [76] [1160/1251] eta: 0:00:46 lr: 0.000848 loss: 3.7349 (3.5846) grad_norm: 1.0200 (1.0857) time: 0.5048 [2021-03-25 17:14:10 swin_small_patch4_window7_224] INFO: Epoch: [76] [1170/1251] eta: 0:00:41 lr: 0.000848 loss: 3.6313 (3.5843) grad_norm: 1.0741 (1.0859) time: 0.5070 [2021-03-25 17:14:15 swin_small_patch4_window7_224] INFO: Epoch: [76] [1180/1251] eta: 0:00:36 lr: 0.000848 loss: 3.5510 (3.5839) grad_norm: 1.0741 (1.0864) time: 0.5075 [2021-03-25 17:14:20 swin_small_patch4_window7_224] INFO: Epoch: [76] [1190/1251] eta: 0:00:31 lr: 0.000848 loss: 3.6108 (3.5833) grad_norm: 1.1568 (1.0872) time: 0.5090 [2021-03-25 17:14:25 swin_small_patch4_window7_224] INFO: Epoch: [76] [1200/1251] eta: 0:00:26 lr: 0.000848 loss: 3.6772 (3.5835) grad_norm: 1.1710 (1.0880) time: 0.5075 [2021-03-25 17:14:30 swin_small_patch4_window7_224] INFO: Epoch: [76] [1210/1251] eta: 0:00:20 lr: 0.000848 loss: 3.6366 (3.5839) grad_norm: 1.1006 (1.0879) time: 0.5036 [2021-03-25 17:14:35 swin_small_patch4_window7_224] INFO: Epoch: [76] [1220/1251] eta: 0:00:15 lr: 0.000848 loss: 3.4930 (3.5827) grad_norm: 1.0554 (1.0876) time: 0.5031 [2021-03-25 17:14:40 swin_small_patch4_window7_224] INFO: Epoch: [76] [1230/1251] eta: 0:00:10 lr: 0.000848 loss: 3.4930 (3.5838) grad_norm: 1.0791 (1.0873) time: 0.5033 [2021-03-25 17:14:45 swin_small_patch4_window7_224] INFO: Epoch: [76] [1240/1251] eta: 0:00:05 lr: 0.000848 loss: 3.5133 (3.5821) grad_norm: 1.0800 (1.0872) time: 0.5045 [2021-03-25 17:14:50 swin_small_patch4_window7_224] INFO: Epoch: [76] [1250/1251] eta: 0:00:00 lr: 0.000848 loss: 3.3567 (3.5814) grad_norm: 1.0809 (1.0878) time: 0.5026 [2021-03-25 17:14:54 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 1.5709 (1.5709) acc1: 71.8750 (71.8750) acc5: 82.8125 (82.8125) [2021-03-25 17:14:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.0374 (1.0478) acc1: 76.5625 (76.1364) acc5: 93.7500 (92.8977) [2021-03-25 17:14:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0458 (1.0906) acc1: 75.0000 (74.4792) acc5: 92.1875 (92.8571) [2021-03-25 17:15:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0850 (1.0678) acc1: 73.4375 (74.5968) acc5: 92.1875 (92.8931) [2021-03-25 17:15:04 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0273 (1.0808) acc1: 73.4375 (74.1235) acc5: 92.1875 (92.5305) [2021-03-25 17:15:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0474 (1.0816) acc1: 73.4375 (74.0480) acc5: 92.1875 (92.4800) [2021-03-25 17:15:07 swin_small_patch4_window7_224] INFO: * Acc@1 74.822 Acc@5 92.674 loss 1.055 [2021-03-25 17:15:07 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.8% [2021-03-25 17:15:07 swin_small_patch4_window7_224] INFO: Max accuracy: 75.01% [2021-03-25 17:15:12 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 0/1251] eta: 1:31:33 lr: 0.000848 loss: 2.8381 (2.8381) grad_norm: 1.0643 (1.0643) time: 4.3910 [2021-03-25 17:15:17 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 10/1251] eta: 0:18:06 lr: 0.000848 loss: 3.6407 (3.5743) grad_norm: 1.1120 (1.1248) time: 0.8751 [2021-03-25 17:15:22 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 20/1251] eta: 0:14:20 lr: 0.000848 loss: 3.5568 (3.4482) grad_norm: 1.1026 (1.0965) time: 0.5145 [2021-03-25 17:15:27 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 30/1251] eta: 0:12:59 lr: 0.000848 loss: 3.3604 (3.4048) grad_norm: 1.0854 (1.0873) time: 0.5085 [2021-03-25 17:15:32 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 40/1251] eta: 0:12:15 lr: 0.000847 loss: 3.6043 (3.4890) grad_norm: 1.0938 (1.0997) time: 0.5105 [2021-03-25 17:15:37 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 50/1251] eta: 0:11:45 lr: 0.000847 loss: 3.7178 (3.5020) grad_norm: 1.0808 (1.0988) time: 0.5081 [2021-03-25 17:15:42 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 60/1251] eta: 0:11:23 lr: 0.000847 loss: 3.6012 (3.5182) grad_norm: 1.0416 (1.0946) time: 0.5059 [2021-03-25 17:15:47 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 70/1251] eta: 0:11:06 lr: 0.000847 loss: 3.7508 (3.5512) grad_norm: 1.0769 (1.0952) time: 0.5057 [2021-03-25 17:15:52 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 80/1251] eta: 0:10:53 lr: 0.000847 loss: 3.8187 (3.5771) grad_norm: 1.0769 (1.0933) time: 0.5100 [2021-03-25 17:15:57 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 90/1251] eta: 0:10:40 lr: 0.000847 loss: 3.8124 (3.6051) grad_norm: 1.1011 (1.0922) time: 0.5070 [2021-03-25 17:16:02 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 100/1251] eta: 0:10:29 lr: 0.000847 loss: 3.7006 (3.6190) grad_norm: 1.1150 (1.0941) time: 0.4995 [2021-03-25 17:16:08 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 110/1251] eta: 0:10:20 lr: 0.000847 loss: 3.5558 (3.6116) grad_norm: 1.0819 (1.0955) time: 0.5095 [2021-03-25 17:16:13 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 120/1251] eta: 0:10:11 lr: 0.000847 loss: 3.4762 (3.6079) grad_norm: 1.0638 (1.0909) time: 0.5109 [2021-03-25 17:16:18 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 130/1251] eta: 0:10:03 lr: 0.000847 loss: 3.6312 (3.6202) grad_norm: 1.0540 (1.0875) time: 0.5077 [2021-03-25 17:16:23 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 140/1251] eta: 0:09:55 lr: 0.000847 loss: 3.6454 (3.6344) grad_norm: 1.0540 (1.0860) time: 0.5093 [2021-03-25 17:16:28 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 150/1251] eta: 0:09:48 lr: 0.000847 loss: 3.6094 (3.6292) grad_norm: 1.0368 (1.0834) time: 0.5063 [2021-03-25 17:16:33 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 160/1251] eta: 0:09:40 lr: 0.000847 loss: 3.6537 (3.6211) grad_norm: 1.0320 (inf) time: 0.5063 [2021-03-25 17:16:38 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 170/1251] eta: 0:09:34 lr: 0.000847 loss: 3.8289 (3.6226) grad_norm: 1.0356 (inf) time: 0.5113 [2021-03-25 17:16:43 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 180/1251] eta: 0:09:28 lr: 0.000847 loss: 3.8710 (3.6199) grad_norm: 1.0584 (inf) time: 0.5154 [2021-03-25 17:16:48 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 190/1251] eta: 0:09:21 lr: 0.000847 loss: 3.7385 (3.6231) grad_norm: 1.0977 (inf) time: 0.5130 [2021-03-25 17:16:54 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 200/1251] eta: 0:09:15 lr: 0.000847 loss: 3.6687 (3.6130) grad_norm: 1.0977 (inf) time: 0.5130 [2021-03-25 17:16:59 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 210/1251] eta: 0:09:09 lr: 0.000847 loss: 3.5706 (3.6142) grad_norm: 1.0945 (inf) time: 0.5101 [2021-03-25 17:17:04 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 220/1251] eta: 0:09:03 lr: 0.000847 loss: 3.6170 (3.6050) grad_norm: 1.0573 (inf) time: 0.5062 [2021-03-25 17:17:09 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 230/1251] eta: 0:08:56 lr: 0.000847 loss: 3.6598 (3.6093) grad_norm: 1.0753 (inf) time: 0.5029 [2021-03-25 17:17:14 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 240/1251] eta: 0:08:51 lr: 0.000847 loss: 3.6871 (3.6125) grad_norm: 1.1324 (inf) time: 0.5121 [2021-03-25 17:17:19 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 250/1251] eta: 0:08:44 lr: 0.000847 loss: 3.6672 (3.6063) grad_norm: 1.1331 (inf) time: 0.5095 [2021-03-25 17:17:24 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 260/1251] eta: 0:08:38 lr: 0.000847 loss: 3.5861 (3.6105) grad_norm: 1.0553 (inf) time: 0.4978 [2021-03-25 17:17:29 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 270/1251] eta: 0:08:32 lr: 0.000847 loss: 3.7087 (3.6089) grad_norm: 1.0826 (inf) time: 0.5025 [2021-03-25 17:17:34 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 280/1251] eta: 0:08:26 lr: 0.000847 loss: 3.6282 (3.6136) grad_norm: 1.0532 (inf) time: 0.5016 [2021-03-25 17:17:39 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 290/1251] eta: 0:08:21 lr: 0.000847 loss: 3.5621 (3.6021) grad_norm: 1.0360 (inf) time: 0.5037 [2021-03-25 17:17:44 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 300/1251] eta: 0:08:15 lr: 0.000847 loss: 3.5621 (3.6053) grad_norm: 1.0502 (inf) time: 0.5049 [2021-03-25 17:17:49 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 310/1251] eta: 0:08:09 lr: 0.000847 loss: 3.7382 (3.6043) grad_norm: 1.0502 (inf) time: 0.5096 [2021-03-25 17:17:54 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 320/1251] eta: 0:08:04 lr: 0.000847 loss: 3.6524 (3.6059) grad_norm: 1.0511 (inf) time: 0.5098 [2021-03-25 17:17:59 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 330/1251] eta: 0:07:58 lr: 0.000847 loss: 3.5977 (3.6009) grad_norm: 1.0061 (inf) time: 0.5022 [2021-03-25 17:18:04 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 340/1251] eta: 0:07:52 lr: 0.000847 loss: 3.7616 (3.6108) grad_norm: 1.0659 (inf) time: 0.5021 [2021-03-25 17:18:09 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 350/1251] eta: 0:07:47 lr: 0.000847 loss: 3.7616 (3.6081) grad_norm: 1.0714 (inf) time: 0.5034 [2021-03-25 17:18:14 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 360/1251] eta: 0:07:41 lr: 0.000847 loss: 3.5375 (3.6062) grad_norm: 0.9949 (inf) time: 0.5091 [2021-03-25 17:18:20 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 370/1251] eta: 0:07:36 lr: 0.000847 loss: 3.5670 (3.6066) grad_norm: 1.0578 (inf) time: 0.5112 [2021-03-25 17:18:25 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 380/1251] eta: 0:07:31 lr: 0.000846 loss: 3.6599 (3.6120) grad_norm: 1.0649 (inf) time: 0.5080 [2021-03-25 17:18:30 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 390/1251] eta: 0:07:25 lr: 0.000846 loss: 3.6302 (3.6080) grad_norm: 1.0491 (inf) time: 0.5110 [2021-03-25 17:18:35 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 400/1251] eta: 0:07:20 lr: 0.000846 loss: 3.3355 (3.6035) grad_norm: 1.0274 (inf) time: 0.5106 [2021-03-25 17:18:40 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 410/1251] eta: 0:07:15 lr: 0.000846 loss: 3.5544 (3.6060) grad_norm: 1.0274 (inf) time: 0.5057 [2021-03-25 17:18:45 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 420/1251] eta: 0:07:09 lr: 0.000846 loss: 3.6960 (3.6081) grad_norm: 1.0798 (inf) time: 0.5086 [2021-03-25 17:18:50 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 430/1251] eta: 0:07:04 lr: 0.000846 loss: 3.8588 (3.6141) grad_norm: 1.0855 (inf) time: 0.5099 [2021-03-25 17:18:55 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 440/1251] eta: 0:06:59 lr: 0.000846 loss: 3.8574 (3.6134) grad_norm: 1.0808 (inf) time: 0.5112 [2021-03-25 17:19:00 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 450/1251] eta: 0:06:53 lr: 0.000846 loss: 3.7618 (3.6118) grad_norm: 1.0287 (inf) time: 0.5098 [2021-03-25 17:19:05 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 460/1251] eta: 0:06:48 lr: 0.000846 loss: 3.7524 (3.6148) grad_norm: 1.0388 (inf) time: 0.5074 [2021-03-25 17:19:10 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 470/1251] eta: 0:06:43 lr: 0.000846 loss: 3.7229 (3.6155) grad_norm: 1.0388 (inf) time: 0.5045 [2021-03-25 17:19:15 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 480/1251] eta: 0:06:37 lr: 0.000846 loss: 3.4412 (3.6117) grad_norm: 1.0244 (inf) time: 0.5022 [2021-03-25 17:19:20 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 490/1251] eta: 0:06:32 lr: 0.000846 loss: 3.4412 (3.6115) grad_norm: 1.0556 (inf) time: 0.4990 [2021-03-25 17:19:25 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 500/1251] eta: 0:06:26 lr: 0.000846 loss: 3.5823 (3.6109) grad_norm: 1.0592 (inf) time: 0.4981 [2021-03-25 17:19:30 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 510/1251] eta: 0:06:21 lr: 0.000846 loss: 3.6543 (3.6114) grad_norm: 1.0292 (inf) time: 0.5041 [2021-03-25 17:19:36 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 520/1251] eta: 0:06:16 lr: 0.000846 loss: 3.6147 (3.6053) grad_norm: 1.0193 (inf) time: 0.5071 [2021-03-25 17:19:41 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 530/1251] eta: 0:06:11 lr: 0.000846 loss: 3.3644 (3.6012) grad_norm: 1.0370 (inf) time: 0.5049 [2021-03-25 17:19:46 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 540/1251] eta: 0:06:05 lr: 0.000846 loss: 3.4568 (3.5971) grad_norm: 1.0699 (inf) time: 0.5064 [2021-03-25 17:19:51 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 550/1251] eta: 0:06:00 lr: 0.000846 loss: 3.6766 (3.5986) grad_norm: 1.0699 (inf) time: 0.5147 [2021-03-25 17:19:56 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 560/1251] eta: 0:05:55 lr: 0.000846 loss: 3.7047 (3.5997) grad_norm: 1.0985 (inf) time: 0.5093 [2021-03-25 17:20:01 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 570/1251] eta: 0:05:50 lr: 0.000846 loss: 3.6059 (3.6008) grad_norm: 1.0680 (inf) time: 0.5098 [2021-03-25 17:20:06 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 580/1251] eta: 0:05:45 lr: 0.000846 loss: 3.5413 (3.6012) grad_norm: 1.1059 (inf) time: 0.5102 [2021-03-25 17:20:11 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 590/1251] eta: 0:05:39 lr: 0.000846 loss: 3.5413 (3.5989) grad_norm: 1.1059 (inf) time: 0.5064 [2021-03-25 17:20:16 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 600/1251] eta: 0:05:34 lr: 0.000846 loss: 3.6539 (3.6035) grad_norm: 1.0776 (inf) time: 0.5060 [2021-03-25 17:20:21 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 610/1251] eta: 0:05:29 lr: 0.000846 loss: 3.7243 (3.6036) grad_norm: 1.0921 (inf) time: 0.5025 [2021-03-25 17:20:26 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 620/1251] eta: 0:05:24 lr: 0.000846 loss: 3.6140 (3.6030) grad_norm: 1.0584 (inf) time: 0.5111 [2021-03-25 17:20:31 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 630/1251] eta: 0:05:18 lr: 0.000846 loss: 3.6208 (3.6029) grad_norm: 1.1237 (inf) time: 0.5109 [2021-03-25 17:20:37 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 640/1251] eta: 0:05:13 lr: 0.000846 loss: 3.6208 (3.6010) grad_norm: 1.1175 (inf) time: 0.5072 [2021-03-25 17:20:42 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 650/1251] eta: 0:05:08 lr: 0.000846 loss: 3.7077 (3.5998) grad_norm: 1.0572 (inf) time: 0.5042 [2021-03-25 17:20:47 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 660/1251] eta: 0:05:03 lr: 0.000846 loss: 3.7646 (3.5990) grad_norm: 1.0647 (inf) time: 0.5018 [2021-03-25 17:20:52 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 670/1251] eta: 0:04:58 lr: 0.000846 loss: 3.5725 (3.5973) grad_norm: 1.1157 (inf) time: 0.5045 [2021-03-25 17:20:57 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 680/1251] eta: 0:04:52 lr: 0.000846 loss: 3.5725 (3.5977) grad_norm: 1.1120 (inf) time: 0.5071 [2021-03-25 17:21:02 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 690/1251] eta: 0:04:47 lr: 0.000846 loss: 3.7897 (3.6003) grad_norm: 1.0448 (inf) time: 0.5052 [2021-03-25 17:21:07 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 700/1251] eta: 0:04:42 lr: 0.000846 loss: 3.7874 (3.6017) grad_norm: 1.0448 (inf) time: 0.5022 [2021-03-25 17:21:12 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 710/1251] eta: 0:04:37 lr: 0.000845 loss: 3.7036 (3.6038) grad_norm: 1.0257 (inf) time: 0.5011 [2021-03-25 17:21:17 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 720/1251] eta: 0:04:32 lr: 0.000845 loss: 3.5800 (3.6023) grad_norm: 1.0516 (inf) time: 0.5083 [2021-03-25 17:21:22 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 730/1251] eta: 0:04:27 lr: 0.000845 loss: 3.5905 (3.6041) grad_norm: 1.1140 (inf) time: 0.5194 [2021-03-25 17:21:27 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 740/1251] eta: 0:04:22 lr: 0.000845 loss: 3.8569 (3.6073) grad_norm: 1.0346 (inf) time: 0.5184 [2021-03-25 17:21:32 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 750/1251] eta: 0:04:16 lr: 0.000845 loss: 3.6436 (3.6041) grad_norm: 1.0202 (inf) time: 0.5140 [2021-03-25 17:21:38 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 760/1251] eta: 0:04:11 lr: 0.000845 loss: 3.5617 (3.6020) grad_norm: 1.1456 (inf) time: 0.5111 [2021-03-25 17:21:43 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 770/1251] eta: 0:04:06 lr: 0.000845 loss: 3.6109 (3.6022) grad_norm: 1.0494 (inf) time: 0.5100 [2021-03-25 17:21:48 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 780/1251] eta: 0:04:01 lr: 0.000845 loss: 3.6082 (3.6033) grad_norm: 1.0215 (inf) time: 0.5033 [2021-03-25 17:21:53 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 790/1251] eta: 0:03:56 lr: 0.000845 loss: 3.5682 (3.6023) grad_norm: 1.0954 (inf) time: 0.4996 [2021-03-25 17:21:58 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 800/1251] eta: 0:03:51 lr: 0.000845 loss: 3.4225 (3.6003) grad_norm: 1.0939 (inf) time: 0.5027 [2021-03-25 17:22:03 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 810/1251] eta: 0:03:45 lr: 0.000845 loss: 3.7117 (3.6000) grad_norm: 1.0967 (inf) time: 0.5063 [2021-03-25 17:22:08 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 820/1251] eta: 0:03:40 lr: 0.000845 loss: 3.7263 (3.6006) grad_norm: 1.0845 (inf) time: 0.5052 [2021-03-25 17:22:13 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 830/1251] eta: 0:03:35 lr: 0.000845 loss: 3.6414 (3.5993) grad_norm: 1.0769 (inf) time: 0.5091 [2021-03-25 17:22:18 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 840/1251] eta: 0:03:30 lr: 0.000845 loss: 3.4461 (3.5995) grad_norm: 1.1214 (inf) time: 0.5103 [2021-03-25 17:22:23 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 850/1251] eta: 0:03:25 lr: 0.000845 loss: 3.6633 (3.5985) grad_norm: 1.1214 (inf) time: 0.5034 [2021-03-25 17:22:28 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 860/1251] eta: 0:03:20 lr: 0.000845 loss: 3.7406 (3.5988) grad_norm: 1.0860 (inf) time: 0.5097 [2021-03-25 17:22:33 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 870/1251] eta: 0:03:15 lr: 0.000845 loss: 3.6094 (3.5974) grad_norm: 1.0664 (inf) time: 0.5106 [2021-03-25 17:22:38 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 880/1251] eta: 0:03:09 lr: 0.000845 loss: 3.5689 (3.5969) grad_norm: 1.0185 (inf) time: 0.5085 [2021-03-25 17:22:43 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 890/1251] eta: 0:03:04 lr: 0.000845 loss: 3.6168 (3.5976) grad_norm: 1.0202 (inf) time: 0.5066 [2021-03-25 17:22:48 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 900/1251] eta: 0:02:59 lr: 0.000845 loss: 3.6997 (3.5960) grad_norm: 1.0225 (inf) time: 0.5069 [2021-03-25 17:22:54 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 910/1251] eta: 0:02:54 lr: 0.000845 loss: 3.6997 (3.5974) grad_norm: 1.0079 (inf) time: 0.5145 [2021-03-25 17:22:59 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 920/1251] eta: 0:02:49 lr: 0.000845 loss: 3.6603 (3.5965) grad_norm: 1.0070 (inf) time: 0.5136 [2021-03-25 17:23:04 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 930/1251] eta: 0:02:44 lr: 0.000845 loss: 3.6803 (3.5969) grad_norm: 1.0516 (inf) time: 0.5083 [2021-03-25 17:23:09 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 940/1251] eta: 0:02:39 lr: 0.000845 loss: 3.6803 (3.5942) grad_norm: 1.0519 (inf) time: 0.5123 [2021-03-25 17:23:14 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 950/1251] eta: 0:02:34 lr: 0.000845 loss: 3.6933 (3.5948) grad_norm: 1.1097 (inf) time: 0.5083 [2021-03-25 17:23:19 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 960/1251] eta: 0:02:28 lr: 0.000845 loss: 3.7253 (3.5946) grad_norm: 1.1066 (inf) time: 0.4985 [2021-03-25 17:23:24 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 970/1251] eta: 0:02:23 lr: 0.000845 loss: 3.7931 (3.5978) grad_norm: 1.1066 (inf) time: 0.5009 [2021-03-25 17:23:29 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 980/1251] eta: 0:02:18 lr: 0.000845 loss: 3.7818 (3.5982) grad_norm: 1.1479 (inf) time: 0.5024 [2021-03-25 17:23:34 swin_small_patch4_window7_224] INFO: Epoch: [77] [ 990/1251] eta: 0:02:13 lr: 0.000845 loss: 3.5873 (3.5967) grad_norm: 1.0619 (inf) time: 0.5077 [2021-03-25 17:23:39 swin_small_patch4_window7_224] INFO: Epoch: [77] [1000/1251] eta: 0:02:08 lr: 0.000845 loss: 3.4222 (3.5959) grad_norm: 1.0619 (inf) time: 0.5071 [2021-03-25 17:23:44 swin_small_patch4_window7_224] INFO: Epoch: [77] [1010/1251] eta: 0:02:03 lr: 0.000845 loss: 3.6327 (3.5976) grad_norm: 1.0727 (inf) time: 0.5047 [2021-03-25 17:23:49 swin_small_patch4_window7_224] INFO: Epoch: [77] [1020/1251] eta: 0:01:58 lr: 0.000845 loss: 3.7942 (3.5989) grad_norm: 1.0415 (inf) time: 0.5089 [2021-03-25 17:23:54 swin_small_patch4_window7_224] INFO: Epoch: [77] [1030/1251] eta: 0:01:52 lr: 0.000845 loss: 3.9014 (3.6012) grad_norm: 1.0459 (inf) time: 0.5060 [2021-03-25 17:23:59 swin_small_patch4_window7_224] INFO: Epoch: [77] [1040/1251] eta: 0:01:47 lr: 0.000844 loss: 3.8094 (3.6002) grad_norm: 1.0894 (inf) time: 0.4982 [2021-03-25 17:24:04 swin_small_patch4_window7_224] INFO: Epoch: [77] [1050/1251] eta: 0:01:42 lr: 0.000844 loss: 3.6386 (3.6003) grad_norm: 1.0733 (inf) time: 0.5049 [2021-03-25 17:24:10 swin_small_patch4_window7_224] INFO: Epoch: [77] [1060/1251] eta: 0:01:37 lr: 0.000844 loss: 3.8485 (3.6000) grad_norm: 1.0875 (inf) time: 0.5114 [2021-03-25 17:24:15 swin_small_patch4_window7_224] INFO: Epoch: [77] [1070/1251] eta: 0:01:32 lr: 0.000844 loss: 3.9568 (3.6037) grad_norm: 1.1010 (inf) time: 0.5104 [2021-03-25 17:24:20 swin_small_patch4_window7_224] INFO: Epoch: [77] [1080/1251] eta: 0:01:27 lr: 0.000844 loss: 3.7528 (3.6019) grad_norm: 1.0529 (inf) time: 0.5043 [2021-03-25 17:24:25 swin_small_patch4_window7_224] INFO: Epoch: [77] [1090/1251] eta: 0:01:22 lr: 0.000844 loss: 3.5946 (3.6017) grad_norm: 1.0448 (inf) time: 0.5003 [2021-03-25 17:24:30 swin_small_patch4_window7_224] INFO: Epoch: [77] [1100/1251] eta: 0:01:17 lr: 0.000844 loss: 3.5855 (3.5997) grad_norm: 1.0495 (inf) time: 0.5022 [2021-03-25 17:24:35 swin_small_patch4_window7_224] INFO: Epoch: [77] [1110/1251] eta: 0:01:12 lr: 0.000844 loss: 3.6036 (3.6005) grad_norm: 1.0495 (inf) time: 0.5014 [2021-03-25 17:24:40 swin_small_patch4_window7_224] INFO: Epoch: [77] [1120/1251] eta: 0:01:06 lr: 0.000844 loss: 3.6697 (3.6000) grad_norm: 1.0361 (inf) time: 0.5014 [2021-03-25 17:24:45 swin_small_patch4_window7_224] INFO: Epoch: [77] [1130/1251] eta: 0:01:01 lr: 0.000844 loss: 3.6021 (3.5987) grad_norm: 1.0476 (inf) time: 0.5103 [2021-03-25 17:24:50 swin_small_patch4_window7_224] INFO: Epoch: [77] [1140/1251] eta: 0:00:56 lr: 0.000844 loss: 3.4098 (3.5968) grad_norm: 1.0925 (inf) time: 0.5153 [2021-03-25 17:24:55 swin_small_patch4_window7_224] INFO: Epoch: [77] [1150/1251] eta: 0:00:51 lr: 0.000844 loss: 3.5136 (3.5969) grad_norm: 1.1277 (inf) time: 0.5094 [2021-03-25 17:25:00 swin_small_patch4_window7_224] INFO: Epoch: [77] [1160/1251] eta: 0:00:46 lr: 0.000844 loss: 3.5136 (3.5959) grad_norm: 1.0935 (inf) time: 0.5050 [2021-03-25 17:25:05 swin_small_patch4_window7_224] INFO: Epoch: [77] [1170/1251] eta: 0:00:41 lr: 0.000844 loss: 3.3518 (3.5922) grad_norm: 1.0406 (inf) time: 0.5003 [2021-03-25 17:25:10 swin_small_patch4_window7_224] INFO: Epoch: [77] [1180/1251] eta: 0:00:36 lr: 0.000844 loss: 3.4590 (3.5910) grad_norm: 1.0848 (inf) time: 0.5080 [2021-03-25 17:25:15 swin_small_patch4_window7_224] INFO: Epoch: [77] [1190/1251] eta: 0:00:31 lr: 0.000844 loss: 3.3783 (3.5906) grad_norm: 1.0895 (inf) time: 0.5082 [2021-03-25 17:25:20 swin_small_patch4_window7_224] INFO: Epoch: [77] [1200/1251] eta: 0:00:26 lr: 0.000844 loss: 3.3708 (3.5888) grad_norm: 1.0510 (inf) time: 0.5068 [2021-03-25 17:25:25 swin_small_patch4_window7_224] INFO: Epoch: [77] [1210/1251] eta: 0:00:20 lr: 0.000844 loss: 3.6105 (3.5904) grad_norm: 1.0420 (inf) time: 0.5059 [2021-03-25 17:25:30 swin_small_patch4_window7_224] INFO: Epoch: [77] [1220/1251] eta: 0:00:15 lr: 0.000844 loss: 3.7104 (3.5907) grad_norm: 0.9922 (inf) time: 0.5008 [2021-03-25 17:25:35 swin_small_patch4_window7_224] INFO: Epoch: [77] [1230/1251] eta: 0:00:10 lr: 0.000844 loss: 3.6962 (3.5921) grad_norm: 1.0258 (inf) time: 0.5022 [2021-03-25 17:25:41 swin_small_patch4_window7_224] INFO: Epoch: [77] [1240/1251] eta: 0:00:05 lr: 0.000844 loss: 3.8182 (3.5911) grad_norm: 1.1452 (inf) time: 0.5039 [2021-03-25 17:25:46 swin_small_patch4_window7_224] INFO: Epoch: [77] [1250/1251] eta: 0:00:00 lr: 0.000844 loss: 3.8182 (3.5924) grad_norm: 1.1591 (inf) time: 0.5032 [2021-03-25 17:26:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 0.7125 (0.7125) acc1: 87.5000 (87.5000) acc5: 95.3125 (95.3125) [2021-03-25 17:26:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1899 (1.0827) acc1: 73.4375 (74.5739) acc5: 92.1875 (92.4716) [2021-03-25 17:26:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0758 (1.0593) acc1: 73.4375 (74.8512) acc5: 92.1875 (92.5595) [2021-03-25 17:26:07 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9630 (1.0375) acc1: 76.5625 (75.4032) acc5: 92.1875 (92.7419) [2021-03-25 17:26:09 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9535 (1.0433) acc1: 75.0000 (75.0762) acc5: 93.7500 (92.7210) [2021-03-25 17:26:10 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1187 (1.0640) acc1: 73.4375 (74.4000) acc5: 93.7500 (92.7360) [2021-03-25 17:26:13 swin_small_patch4_window7_224] INFO: * Acc@1 74.992 Acc@5 92.876 loss 1.046 [2021-03-25 17:26:13 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.0% [2021-03-25 17:26:13 swin_small_patch4_window7_224] INFO: Max accuracy: 75.01% [2021-03-25 17:26:18 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 0/1251] eta: 1:27:16 lr: 0.000844 loss: 3.9140 (3.9140) grad_norm: 1.0279 (1.0279) time: 4.1859 [2021-03-25 17:26:23 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 10/1251] eta: 0:17:44 lr: 0.000844 loss: 3.9531 (3.9027) grad_norm: 1.1478 (1.1177) time: 0.8581 [2021-03-25 17:26:28 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 20/1251] eta: 0:14:08 lr: 0.000844 loss: 3.9531 (3.8343) grad_norm: 1.1215 (1.1105) time: 0.5144 [2021-03-25 17:26:33 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 30/1251] eta: 0:12:47 lr: 0.000844 loss: 3.6429 (3.7191) grad_norm: 1.0708 (1.1116) time: 0.5019 [2021-03-25 17:26:38 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 40/1251] eta: 0:12:04 lr: 0.000844 loss: 3.5280 (3.7130) grad_norm: 1.0870 (1.1062) time: 0.5036 [2021-03-25 17:26:43 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 50/1251] eta: 0:11:36 lr: 0.000844 loss: 3.4749 (3.6302) grad_norm: 1.0496 (1.1054) time: 0.5040 [2021-03-25 17:26:48 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 60/1251] eta: 0:11:14 lr: 0.000844 loss: 3.4645 (3.5679) grad_norm: 1.0984 (1.1078) time: 0.5007 [2021-03-25 17:26:53 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 70/1251] eta: 0:10:58 lr: 0.000844 loss: 3.3372 (3.5365) grad_norm: 1.0984 (1.1057) time: 0.5012 [2021-03-25 17:26:58 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 80/1251] eta: 0:10:45 lr: 0.000844 loss: 3.5545 (3.5410) grad_norm: 1.0814 (1.1055) time: 0.5057 [2021-03-25 17:27:03 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 90/1251] eta: 0:10:33 lr: 0.000844 loss: 3.7323 (3.5540) grad_norm: 1.0098 (1.0974) time: 0.5038 [2021-03-25 17:27:08 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 100/1251] eta: 0:10:24 lr: 0.000844 loss: 3.6978 (3.5716) grad_norm: 1.0038 (1.0968) time: 0.5078 [2021-03-25 17:27:13 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 110/1251] eta: 0:10:16 lr: 0.000844 loss: 3.6978 (3.5589) grad_norm: 1.0477 (1.0964) time: 0.5136 [2021-03-25 17:27:18 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 120/1251] eta: 0:10:07 lr: 0.000843 loss: 3.8078 (3.5672) grad_norm: 1.0714 (1.0966) time: 0.5101 [2021-03-25 17:27:24 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 130/1251] eta: 0:10:01 lr: 0.000843 loss: 3.8722 (3.5874) grad_norm: 1.0972 (1.1008) time: 0.5174 [2021-03-25 17:27:29 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 140/1251] eta: 0:09:53 lr: 0.000843 loss: 3.7025 (3.5887) grad_norm: 1.1175 (1.1045) time: 0.5130 [2021-03-25 17:27:34 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 150/1251] eta: 0:09:46 lr: 0.000843 loss: 3.5731 (3.5818) grad_norm: 1.0973 (1.1042) time: 0.5065 [2021-03-25 17:27:39 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 160/1251] eta: 0:09:39 lr: 0.000843 loss: 3.7203 (3.5905) grad_norm: 1.0518 (1.1019) time: 0.5081 [2021-03-25 17:27:44 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 170/1251] eta: 0:09:32 lr: 0.000843 loss: 3.6978 (3.5711) grad_norm: 1.0747 (1.1036) time: 0.5042 [2021-03-25 17:27:49 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 180/1251] eta: 0:09:25 lr: 0.000843 loss: 3.6074 (3.5694) grad_norm: 1.0982 (1.1030) time: 0.5052 [2021-03-25 17:27:54 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 190/1251] eta: 0:09:19 lr: 0.000843 loss: 3.1951 (3.5393) grad_norm: 1.0825 (1.1040) time: 0.5107 [2021-03-25 17:27:59 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 200/1251] eta: 0:09:13 lr: 0.000843 loss: 3.3484 (3.5481) grad_norm: 1.0938 (1.1053) time: 0.5108 [2021-03-25 17:28:04 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 210/1251] eta: 0:09:06 lr: 0.000843 loss: 3.7497 (3.5435) grad_norm: 1.0921 (1.1051) time: 0.5076 [2021-03-25 17:28:09 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 220/1251] eta: 0:09:00 lr: 0.000843 loss: 3.7694 (3.5450) grad_norm: 1.0541 (1.1032) time: 0.5031 [2021-03-25 17:28:14 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 230/1251] eta: 0:08:54 lr: 0.000843 loss: 3.7744 (3.5514) grad_norm: 1.0362 (1.1009) time: 0.5026 [2021-03-25 17:28:19 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 240/1251] eta: 0:08:48 lr: 0.000843 loss: 3.4779 (3.5438) grad_norm: 1.0408 (1.0997) time: 0.5131 [2021-03-25 17:28:25 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 250/1251] eta: 0:08:43 lr: 0.000843 loss: 3.4177 (3.5361) grad_norm: 1.0393 (1.0992) time: 0.5124 [2021-03-25 17:28:30 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 260/1251] eta: 0:08:37 lr: 0.000843 loss: 3.3137 (3.5246) grad_norm: 1.0274 (1.0956) time: 0.5087 [2021-03-25 17:28:35 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 270/1251] eta: 0:08:31 lr: 0.000843 loss: 3.5745 (3.5331) grad_norm: 1.0342 (1.0963) time: 0.5108 [2021-03-25 17:28:40 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 280/1251] eta: 0:08:26 lr: 0.000843 loss: 3.7500 (3.5393) grad_norm: 1.0639 (1.0961) time: 0.5091 [2021-03-25 17:28:45 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 290/1251] eta: 0:08:20 lr: 0.000843 loss: 3.7709 (3.5399) grad_norm: 1.0810 (1.0973) time: 0.5119 [2021-03-25 17:28:50 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 300/1251] eta: 0:08:15 lr: 0.000843 loss: 3.7709 (3.5429) grad_norm: 1.0600 (1.0981) time: 0.5117 [2021-03-25 17:28:55 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 310/1251] eta: 0:08:09 lr: 0.000843 loss: 3.5873 (3.5457) grad_norm: 1.1188 (1.1004) time: 0.5118 [2021-03-25 17:29:01 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 320/1251] eta: 0:08:04 lr: 0.000843 loss: 3.5415 (3.5407) grad_norm: 1.1202 (1.1032) time: 0.5221 [2021-03-25 17:29:06 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 330/1251] eta: 0:07:59 lr: 0.000843 loss: 3.1822 (3.5333) grad_norm: 1.1234 (1.1053) time: 0.5173 [2021-03-25 17:29:11 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 340/1251] eta: 0:07:53 lr: 0.000843 loss: 3.4387 (3.5330) grad_norm: 1.1541 (1.1079) time: 0.5090 [2021-03-25 17:29:16 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 350/1251] eta: 0:07:48 lr: 0.000843 loss: 3.7442 (3.5350) grad_norm: 1.1009 (1.1066) time: 0.5090 [2021-03-25 17:29:21 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 360/1251] eta: 0:07:42 lr: 0.000843 loss: 3.7833 (3.5404) grad_norm: 1.0631 (1.1060) time: 0.5041 [2021-03-25 17:29:26 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 370/1251] eta: 0:07:37 lr: 0.000843 loss: 3.7250 (3.5497) grad_norm: 1.0594 (1.1038) time: 0.5067 [2021-03-25 17:29:31 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 380/1251] eta: 0:07:31 lr: 0.000843 loss: 3.8464 (3.5521) grad_norm: 1.0911 (1.1043) time: 0.5092 [2021-03-25 17:29:36 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 390/1251] eta: 0:07:26 lr: 0.000843 loss: 3.7079 (3.5509) grad_norm: 1.0968 (1.1040) time: 0.5051 [2021-03-25 17:29:41 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 400/1251] eta: 0:07:20 lr: 0.000843 loss: 3.6572 (3.5520) grad_norm: 1.0899 (1.1039) time: 0.5054 [2021-03-25 17:29:46 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 410/1251] eta: 0:07:15 lr: 0.000843 loss: 3.6605 (3.5548) grad_norm: 1.1157 (1.1045) time: 0.5059 [2021-03-25 17:29:51 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 420/1251] eta: 0:07:09 lr: 0.000843 loss: 3.8375 (3.5636) grad_norm: 1.0346 (1.1033) time: 0.5011 [2021-03-25 17:29:56 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 430/1251] eta: 0:07:04 lr: 0.000843 loss: 3.6281 (3.5586) grad_norm: 1.0346 (1.1035) time: 0.5041 [2021-03-25 17:30:01 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 440/1251] eta: 0:06:59 lr: 0.000843 loss: 3.4615 (3.5578) grad_norm: 1.0984 (1.1035) time: 0.5069 [2021-03-25 17:30:06 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 450/1251] eta: 0:06:53 lr: 0.000842 loss: 3.5445 (3.5555) grad_norm: 1.0972 (1.1022) time: 0.5075 [2021-03-25 17:30:11 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 460/1251] eta: 0:06:48 lr: 0.000842 loss: 3.5445 (3.5564) grad_norm: 1.0541 (1.1012) time: 0.5070 [2021-03-25 17:30:16 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 470/1251] eta: 0:06:42 lr: 0.000842 loss: 3.5079 (3.5540) grad_norm: 1.0854 (1.1020) time: 0.5037 [2021-03-25 17:30:22 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 480/1251] eta: 0:06:37 lr: 0.000842 loss: 3.5346 (3.5543) grad_norm: 1.0952 (1.1015) time: 0.5074 [2021-03-25 17:30:27 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 490/1251] eta: 0:06:32 lr: 0.000842 loss: 3.6921 (3.5590) grad_norm: 1.0822 (1.1023) time: 0.5070 [2021-03-25 17:30:32 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 500/1251] eta: 0:06:27 lr: 0.000842 loss: 3.8447 (3.5626) grad_norm: 1.0690 (1.1020) time: 0.5066 [2021-03-25 17:30:37 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 510/1251] eta: 0:06:22 lr: 0.000842 loss: 3.6374 (3.5623) grad_norm: 1.0390 (1.1007) time: 0.5208 [2021-03-25 17:30:42 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 520/1251] eta: 0:06:16 lr: 0.000842 loss: 3.5275 (3.5621) grad_norm: 1.0300 (1.0991) time: 0.5181 [2021-03-25 17:30:47 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 530/1251] eta: 0:06:11 lr: 0.000842 loss: 3.3618 (3.5603) grad_norm: 1.0378 (1.0985) time: 0.5029 [2021-03-25 17:30:52 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 540/1251] eta: 0:06:06 lr: 0.000842 loss: 3.6513 (3.5642) grad_norm: 1.0764 (1.0990) time: 0.5044 [2021-03-25 17:30:57 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 550/1251] eta: 0:06:01 lr: 0.000842 loss: 3.3487 (3.5556) grad_norm: 1.0841 (1.0990) time: 0.5150 [2021-03-25 17:31:02 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 560/1251] eta: 0:05:56 lr: 0.000842 loss: 3.2349 (3.5549) grad_norm: 1.1170 (1.0998) time: 0.5155 [2021-03-25 17:31:08 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 570/1251] eta: 0:05:50 lr: 0.000842 loss: 3.5904 (3.5529) grad_norm: 1.1074 (1.0994) time: 0.5074 [2021-03-25 17:31:13 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 580/1251] eta: 0:05:45 lr: 0.000842 loss: 3.6341 (3.5562) grad_norm: 1.0590 (1.0987) time: 0.5055 [2021-03-25 17:31:18 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 590/1251] eta: 0:05:40 lr: 0.000842 loss: 3.7445 (3.5566) grad_norm: 1.0192 (1.0977) time: 0.5058 [2021-03-25 17:31:23 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 600/1251] eta: 0:05:35 lr: 0.000842 loss: 3.5634 (3.5508) grad_norm: 1.0375 (1.0984) time: 0.5070 [2021-03-25 17:31:28 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 610/1251] eta: 0:05:29 lr: 0.000842 loss: 3.5093 (3.5515) grad_norm: 1.0375 (1.0980) time: 0.5045 [2021-03-25 17:31:33 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 620/1251] eta: 0:05:24 lr: 0.000842 loss: 3.7076 (3.5538) grad_norm: 1.0376 (1.0975) time: 0.5021 [2021-03-25 17:31:38 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 630/1251] eta: 0:05:19 lr: 0.000842 loss: 3.6111 (3.5510) grad_norm: 1.0541 (1.0980) time: 0.5011 [2021-03-25 17:31:43 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 640/1251] eta: 0:05:13 lr: 0.000842 loss: 3.4173 (3.5463) grad_norm: 1.0840 (1.0989) time: 0.5007 [2021-03-25 17:31:48 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 650/1251] eta: 0:05:08 lr: 0.000842 loss: 3.5416 (3.5495) grad_norm: 1.1115 (1.0992) time: 0.4998 [2021-03-25 17:31:53 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 660/1251] eta: 0:05:03 lr: 0.000842 loss: 3.7107 (3.5463) grad_norm: 1.0155 (1.0978) time: 0.5049 [2021-03-25 17:31:58 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 670/1251] eta: 0:04:58 lr: 0.000842 loss: 3.7107 (3.5483) grad_norm: 1.0155 (1.0976) time: 0.5110 [2021-03-25 17:32:03 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 680/1251] eta: 0:04:53 lr: 0.000842 loss: 3.8385 (3.5519) grad_norm: 1.0935 (1.0977) time: 0.5124 [2021-03-25 17:32:08 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 690/1251] eta: 0:04:47 lr: 0.000842 loss: 3.8318 (3.5530) grad_norm: 1.1125 (1.0983) time: 0.5090 [2021-03-25 17:32:13 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 700/1251] eta: 0:04:42 lr: 0.000842 loss: 3.9219 (3.5530) grad_norm: 1.0962 (1.0983) time: 0.5078 [2021-03-25 17:32:18 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 710/1251] eta: 0:04:37 lr: 0.000842 loss: 3.9219 (3.5549) grad_norm: 1.1006 (1.0986) time: 0.5094 [2021-03-25 17:32:23 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 720/1251] eta: 0:04:32 lr: 0.000842 loss: 3.8442 (3.5564) grad_norm: 1.1150 (1.0995) time: 0.5051 [2021-03-25 17:32:28 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 730/1251] eta: 0:04:27 lr: 0.000842 loss: 3.8240 (3.5598) grad_norm: 1.1079 (1.0996) time: 0.5029 [2021-03-25 17:32:34 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 740/1251] eta: 0:04:22 lr: 0.000842 loss: 3.8149 (3.5595) grad_norm: 1.1319 (1.1007) time: 0.5136 [2021-03-25 17:32:39 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 750/1251] eta: 0:04:17 lr: 0.000842 loss: 3.8639 (3.5638) grad_norm: 1.1578 (1.1017) time: 0.5147 [2021-03-25 17:32:44 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 760/1251] eta: 0:04:11 lr: 0.000842 loss: 3.6826 (3.5632) grad_norm: 1.1020 (1.1014) time: 0.5084 [2021-03-25 17:32:49 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 770/1251] eta: 0:04:06 lr: 0.000842 loss: 3.6455 (3.5635) grad_norm: 1.1191 (1.1023) time: 0.5086 [2021-03-25 17:32:54 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 780/1251] eta: 0:04:01 lr: 0.000841 loss: 3.6491 (3.5655) grad_norm: 1.1378 (1.1029) time: 0.5075 [2021-03-25 17:32:59 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 790/1251] eta: 0:03:56 lr: 0.000841 loss: 3.6731 (3.5669) grad_norm: 1.1005 (1.1030) time: 0.5041 [2021-03-25 17:33:04 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 800/1251] eta: 0:03:51 lr: 0.000841 loss: 3.8108 (3.5693) grad_norm: 1.1005 (1.1031) time: 0.5014 [2021-03-25 17:33:09 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 810/1251] eta: 0:03:45 lr: 0.000841 loss: 3.7115 (3.5667) grad_norm: 1.0990 (1.1029) time: 0.5021 [2021-03-25 17:33:14 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 820/1251] eta: 0:03:40 lr: 0.000841 loss: 3.5632 (3.5674) grad_norm: 1.0582 (1.1023) time: 0.5027 [2021-03-25 17:33:19 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 830/1251] eta: 0:03:35 lr: 0.000841 loss: 3.7258 (3.5688) grad_norm: 1.0596 (1.1023) time: 0.5049 [2021-03-25 17:33:24 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 840/1251] eta: 0:03:30 lr: 0.000841 loss: 3.4532 (3.5649) grad_norm: 1.1197 (1.1030) time: 0.5058 [2021-03-25 17:33:29 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 850/1251] eta: 0:03:25 lr: 0.000841 loss: 3.5466 (3.5651) grad_norm: 1.1256 (1.1030) time: 0.5098 [2021-03-25 17:33:34 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 860/1251] eta: 0:03:20 lr: 0.000841 loss: 3.8001 (3.5699) grad_norm: 1.1256 (1.1044) time: 0.5077 [2021-03-25 17:33:40 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 870/1251] eta: 0:03:15 lr: 0.000841 loss: 3.9093 (3.5725) grad_norm: 1.1713 (1.1044) time: 0.5074 [2021-03-25 17:33:45 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 880/1251] eta: 0:03:09 lr: 0.000841 loss: 3.8019 (3.5724) grad_norm: 1.1212 (1.1049) time: 0.5105 [2021-03-25 17:33:50 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 890/1251] eta: 0:03:04 lr: 0.000841 loss: 3.7380 (3.5729) grad_norm: 1.1127 (1.1046) time: 0.5059 [2021-03-25 17:33:55 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 900/1251] eta: 0:02:59 lr: 0.000841 loss: 3.5069 (3.5719) grad_norm: 1.1102 (1.1046) time: 0.5037 [2021-03-25 17:34:00 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 910/1251] eta: 0:02:54 lr: 0.000841 loss: 3.6323 (3.5725) grad_norm: 1.1102 (1.1043) time: 0.5051 [2021-03-25 17:34:05 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 920/1251] eta: 0:02:49 lr: 0.000841 loss: 3.7102 (3.5730) grad_norm: 1.0672 (1.1039) time: 0.5029 [2021-03-25 17:34:10 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 930/1251] eta: 0:02:44 lr: 0.000841 loss: 3.6932 (3.5731) grad_norm: 1.0726 (1.1043) time: 0.5000 [2021-03-25 17:34:15 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 940/1251] eta: 0:02:39 lr: 0.000841 loss: 3.7142 (3.5749) grad_norm: 1.0919 (1.1041) time: 0.5049 [2021-03-25 17:34:20 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 950/1251] eta: 0:02:33 lr: 0.000841 loss: 3.7703 (3.5751) grad_norm: 1.0278 (1.1040) time: 0.5139 [2021-03-25 17:34:25 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 960/1251] eta: 0:02:28 lr: 0.000841 loss: 3.8102 (3.5764) grad_norm: 1.0711 (1.1041) time: 0.5097 [2021-03-25 17:34:30 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 970/1251] eta: 0:02:23 lr: 0.000841 loss: 3.8447 (3.5784) grad_norm: 1.0346 (1.1033) time: 0.5017 [2021-03-25 17:34:35 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 980/1251] eta: 0:02:18 lr: 0.000841 loss: 3.8100 (3.5790) grad_norm: 1.0168 (1.1023) time: 0.5038 [2021-03-25 17:34:40 swin_small_patch4_window7_224] INFO: Epoch: [78] [ 990/1251] eta: 0:02:13 lr: 0.000841 loss: 3.7284 (3.5798) grad_norm: 1.0361 (1.1029) time: 0.5064 [2021-03-25 17:34:45 swin_small_patch4_window7_224] INFO: Epoch: [78] [1000/1251] eta: 0:02:08 lr: 0.000841 loss: 3.5885 (3.5773) grad_norm: 1.1671 (1.1031) time: 0.5129 [2021-03-25 17:34:50 swin_small_patch4_window7_224] INFO: Epoch: [78] [1010/1251] eta: 0:02:03 lr: 0.000841 loss: 3.4497 (3.5770) grad_norm: 1.1057 (1.1032) time: 0.5110 [2021-03-25 17:34:55 swin_small_patch4_window7_224] INFO: Epoch: [78] [1020/1251] eta: 0:01:58 lr: 0.000841 loss: 3.4597 (3.5765) grad_norm: 1.0817 (inf) time: 0.4979 [2021-03-25 17:35:00 swin_small_patch4_window7_224] INFO: Epoch: [78] [1030/1251] eta: 0:01:52 lr: 0.000841 loss: 3.7382 (3.5784) grad_norm: 1.0195 (inf) time: 0.5014 [2021-03-25 17:35:05 swin_small_patch4_window7_224] INFO: Epoch: [78] [1040/1251] eta: 0:01:47 lr: 0.000841 loss: 3.8351 (3.5798) grad_norm: 1.0378 (inf) time: 0.5072 [2021-03-25 17:35:11 swin_small_patch4_window7_224] INFO: Epoch: [78] [1050/1251] eta: 0:01:42 lr: 0.000841 loss: 3.8268 (3.5824) grad_norm: 1.0727 (inf) time: 0.5084 [2021-03-25 17:35:16 swin_small_patch4_window7_224] INFO: Epoch: [78] [1060/1251] eta: 0:01:37 lr: 0.000841 loss: 3.7927 (3.5832) grad_norm: 1.0797 (inf) time: 0.5124 [2021-03-25 17:35:21 swin_small_patch4_window7_224] INFO: Epoch: [78] [1070/1251] eta: 0:01:32 lr: 0.000841 loss: 3.7380 (3.5833) grad_norm: 1.0209 (inf) time: 0.5099 [2021-03-25 17:35:26 swin_small_patch4_window7_224] INFO: Epoch: [78] [1080/1251] eta: 0:01:27 lr: 0.000841 loss: 3.6513 (3.5813) grad_norm: 1.0339 (inf) time: 0.5122 [2021-03-25 17:35:31 swin_small_patch4_window7_224] INFO: Epoch: [78] [1090/1251] eta: 0:01:22 lr: 0.000841 loss: 3.6029 (3.5804) grad_norm: 1.1130 (inf) time: 0.5140 [2021-03-25 17:35:36 swin_small_patch4_window7_224] INFO: Epoch: [78] [1100/1251] eta: 0:01:17 lr: 0.000841 loss: 3.4835 (3.5803) grad_norm: 1.0804 (inf) time: 0.5086 [2021-03-25 17:35:41 swin_small_patch4_window7_224] INFO: Epoch: [78] [1110/1251] eta: 0:01:12 lr: 0.000840 loss: 3.8293 (3.5834) grad_norm: 1.0394 (inf) time: 0.5038 [2021-03-25 17:35:46 swin_small_patch4_window7_224] INFO: Epoch: [78] [1120/1251] eta: 0:01:06 lr: 0.000840 loss: 3.9524 (3.5850) grad_norm: 1.0611 (inf) time: 0.5040 [2021-03-25 17:35:51 swin_small_patch4_window7_224] INFO: Epoch: [78] [1130/1251] eta: 0:01:01 lr: 0.000840 loss: 3.7949 (3.5853) grad_norm: 1.0887 (inf) time: 0.5054 [2021-03-25 17:35:56 swin_small_patch4_window7_224] INFO: Epoch: [78] [1140/1251] eta: 0:00:56 lr: 0.000840 loss: 3.6275 (3.5841) grad_norm: 1.1036 (inf) time: 0.5019 [2021-03-25 17:36:01 swin_small_patch4_window7_224] INFO: Epoch: [78] [1150/1251] eta: 0:00:51 lr: 0.000840 loss: 3.3973 (3.5840) grad_norm: 1.0738 (inf) time: 0.5017 [2021-03-25 17:36:06 swin_small_patch4_window7_224] INFO: Epoch: [78] [1160/1251] eta: 0:00:46 lr: 0.000840 loss: 3.3490 (3.5826) grad_norm: 1.0658 (inf) time: 0.5036 [2021-03-25 17:36:12 swin_small_patch4_window7_224] INFO: Epoch: [78] [1170/1251] eta: 0:00:41 lr: 0.000840 loss: 3.7004 (3.5839) grad_norm: 1.0060 (inf) time: 0.5085 [2021-03-25 17:36:17 swin_small_patch4_window7_224] INFO: Epoch: [78] [1180/1251] eta: 0:00:36 lr: 0.000840 loss: 3.7601 (3.5851) grad_norm: 1.0328 (inf) time: 0.5085 [2021-03-25 17:36:22 swin_small_patch4_window7_224] INFO: Epoch: [78] [1190/1251] eta: 0:00:31 lr: 0.000840 loss: 3.6627 (3.5833) grad_norm: 1.1671 (inf) time: 0.5044 [2021-03-25 17:36:27 swin_small_patch4_window7_224] INFO: Epoch: [78] [1200/1251] eta: 0:00:26 lr: 0.000840 loss: 3.6759 (3.5844) grad_norm: 1.1276 (inf) time: 0.5146 [2021-03-25 17:36:32 swin_small_patch4_window7_224] INFO: Epoch: [78] [1210/1251] eta: 0:00:20 lr: 0.000840 loss: 3.7668 (3.5851) grad_norm: 1.0716 (inf) time: 0.5156 [2021-03-25 17:36:37 swin_small_patch4_window7_224] INFO: Epoch: [78] [1220/1251] eta: 0:00:15 lr: 0.000840 loss: 3.5891 (3.5854) grad_norm: 1.0668 (inf) time: 0.5064 [2021-03-25 17:36:42 swin_small_patch4_window7_224] INFO: Epoch: [78] [1230/1251] eta: 0:00:10 lr: 0.000840 loss: 3.6638 (3.5869) grad_norm: 1.0668 (inf) time: 0.5067 [2021-03-25 17:36:47 swin_small_patch4_window7_224] INFO: Epoch: [78] [1240/1251] eta: 0:00:05 lr: 0.000840 loss: 3.7460 (3.5867) grad_norm: 1.0259 (inf) time: 0.4996 [2021-03-25 17:36:52 swin_small_patch4_window7_224] INFO: Epoch: [78] [1250/1251] eta: 0:00:00 lr: 0.000840 loss: 3.6680 (3.5865) grad_norm: 1.0057 (inf) time: 0.4907 [2021-03-25 17:36:58 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 0.9837 (0.9837) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.7500) [2021-03-25 17:36:59 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.9837 (0.9752) acc1: 76.5625 (78.2670) acc5: 93.7500 (93.4659) [2021-03-25 17:37:01 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9688 (0.9680) acc1: 76.5625 (76.3393) acc5: 93.7500 (94.2708) [2021-03-25 17:37:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.9853 (1.0276) acc1: 75.0000 (75.5040) acc5: 93.7500 (93.7500) [2021-03-25 17:37:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.1194 (1.0822) acc1: 73.4375 (74.7713) acc5: 90.6250 (92.8735) [2021-03-25 17:37:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1065 (1.0826) acc1: 75.0000 (74.7520) acc5: 90.6250 (92.8640) [2021-03-25 17:37:11 swin_small_patch4_window7_224] INFO: * Acc@1 75.124 Acc@5 92.868 loss 1.069 [2021-03-25 17:37:11 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.1% [2021-03-25 17:37:11 swin_small_patch4_window7_224] INFO: Max accuracy: 75.12% [2021-03-25 17:37:15 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 0/1251] eta: 1:24:43 lr: 0.000840 loss: 2.9730 (2.9730) grad_norm: 1.0546 (1.0546) time: 4.0638 [2021-03-25 17:37:20 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 10/1251] eta: 0:17:38 lr: 0.000840 loss: 3.6228 (3.5494) grad_norm: 1.0444 (1.0403) time: 0.8528 [2021-03-25 17:37:25 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 20/1251] eta: 0:14:08 lr: 0.000840 loss: 3.5603 (3.5318) grad_norm: 1.0689 (1.0919) time: 0.5209 [2021-03-25 17:37:30 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 30/1251] eta: 0:12:50 lr: 0.000840 loss: 3.6269 (3.6186) grad_norm: 1.1040 (1.0799) time: 0.5087 [2021-03-25 17:37:35 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 40/1251] eta: 0:12:05 lr: 0.000840 loss: 3.6478 (3.5818) grad_norm: 1.0573 (1.0820) time: 0.5045 [2021-03-25 17:37:40 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 50/1251] eta: 0:11:38 lr: 0.000840 loss: 3.4893 (3.5425) grad_norm: 1.0613 (1.0878) time: 0.5055 [2021-03-25 17:37:46 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 60/1251] eta: 0:11:17 lr: 0.000840 loss: 3.4813 (3.5325) grad_norm: 1.0792 (1.0981) time: 0.5064 [2021-03-25 17:37:51 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 70/1251] eta: 0:11:01 lr: 0.000840 loss: 3.5565 (3.5082) grad_norm: 1.0976 (1.0988) time: 0.5066 [2021-03-25 17:37:56 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 80/1251] eta: 0:10:48 lr: 0.000840 loss: 3.5565 (3.5079) grad_norm: 1.0801 (1.0942) time: 0.5083 [2021-03-25 17:38:01 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 90/1251] eta: 0:10:37 lr: 0.000840 loss: 3.5132 (3.5005) grad_norm: 1.0533 (1.0959) time: 0.5100 [2021-03-25 17:38:06 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 100/1251] eta: 0:10:27 lr: 0.000840 loss: 3.4641 (3.4999) grad_norm: 1.0345 (1.0911) time: 0.5106 [2021-03-25 17:38:11 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 110/1251] eta: 0:10:18 lr: 0.000840 loss: 3.5328 (3.5134) grad_norm: 1.0760 (1.0940) time: 0.5083 [2021-03-25 17:38:16 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 120/1251] eta: 0:10:09 lr: 0.000840 loss: 3.7399 (3.5182) grad_norm: 1.0674 (1.0934) time: 0.5048 [2021-03-25 17:38:21 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 130/1251] eta: 0:10:02 lr: 0.000840 loss: 3.7436 (3.5373) grad_norm: 1.0730 (1.0946) time: 0.5117 [2021-03-25 17:38:26 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 140/1251] eta: 0:09:55 lr: 0.000840 loss: 3.5087 (3.5247) grad_norm: 1.0859 (1.0958) time: 0.5216 [2021-03-25 17:38:31 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 150/1251] eta: 0:09:47 lr: 0.000840 loss: 3.7061 (3.5282) grad_norm: 1.0915 (1.0977) time: 0.5104 [2021-03-25 17:38:36 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 160/1251] eta: 0:09:40 lr: 0.000840 loss: 3.8613 (3.5476) grad_norm: 1.0883 (1.1038) time: 0.4996 [2021-03-25 17:38:41 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 170/1251] eta: 0:09:32 lr: 0.000840 loss: 3.8613 (3.5404) grad_norm: 1.1609 (1.1113) time: 0.5017 [2021-03-25 17:38:47 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 180/1251] eta: 0:09:26 lr: 0.000840 loss: 3.7034 (3.5546) grad_norm: 1.1393 (1.1112) time: 0.5081 [2021-03-25 17:38:52 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 190/1251] eta: 0:09:20 lr: 0.000839 loss: 3.6487 (3.5475) grad_norm: 1.1050 (1.1111) time: 0.5130 [2021-03-25 17:38:57 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 200/1251] eta: 0:09:14 lr: 0.000839 loss: 3.6403 (3.5529) grad_norm: 1.1082 (1.1129) time: 0.5159 [2021-03-25 17:39:02 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 210/1251] eta: 0:09:08 lr: 0.000839 loss: 3.7051 (3.5543) grad_norm: 1.1189 (1.1172) time: 0.5183 [2021-03-25 17:39:07 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 220/1251] eta: 0:09:02 lr: 0.000839 loss: 3.8341 (3.5569) grad_norm: 1.0614 (1.1146) time: 0.5150 [2021-03-25 17:39:12 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 230/1251] eta: 0:08:57 lr: 0.000839 loss: 3.5926 (3.5493) grad_norm: 1.0345 (1.1102) time: 0.5158 [2021-03-25 17:39:17 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 240/1251] eta: 0:08:51 lr: 0.000839 loss: 3.4303 (3.5449) grad_norm: 1.0345 (1.1086) time: 0.5131 [2021-03-25 17:39:22 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 250/1251] eta: 0:08:45 lr: 0.000839 loss: 3.3461 (3.5373) grad_norm: 1.0937 (1.1095) time: 0.5037 [2021-03-25 17:39:28 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 260/1251] eta: 0:08:39 lr: 0.000839 loss: 3.3026 (3.5344) grad_norm: 1.1298 (1.1099) time: 0.5052 [2021-03-25 17:39:33 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 270/1251] eta: 0:08:33 lr: 0.000839 loss: 3.8071 (3.5446) grad_norm: 1.1204 (1.1093) time: 0.5051 [2021-03-25 17:39:38 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 280/1251] eta: 0:08:27 lr: 0.000839 loss: 3.7916 (3.5438) grad_norm: 1.0639 (1.1089) time: 0.5012 [2021-03-25 17:39:43 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 290/1251] eta: 0:08:21 lr: 0.000839 loss: 3.5467 (3.5448) grad_norm: 1.0624 (1.1093) time: 0.5032 [2021-03-25 17:39:48 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 300/1251] eta: 0:08:15 lr: 0.000839 loss: 3.6887 (3.5493) grad_norm: 1.1213 (1.1109) time: 0.4991 [2021-03-25 17:39:53 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 310/1251] eta: 0:08:09 lr: 0.000839 loss: 3.8896 (3.5565) grad_norm: 1.1607 (1.1119) time: 0.4946 [2021-03-25 17:39:58 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 320/1251] eta: 0:08:04 lr: 0.000839 loss: 3.6400 (3.5484) grad_norm: 1.0633 (1.1092) time: 0.5083 [2021-03-25 17:40:03 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 330/1251] eta: 0:07:58 lr: 0.000839 loss: 3.4278 (3.5515) grad_norm: 1.0221 (1.1074) time: 0.5105 [2021-03-25 17:40:08 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 340/1251] eta: 0:07:52 lr: 0.000839 loss: 3.6146 (3.5501) grad_norm: 1.0291 (1.1058) time: 0.5029 [2021-03-25 17:40:13 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 350/1251] eta: 0:07:47 lr: 0.000839 loss: 3.5661 (3.5512) grad_norm: 1.0621 (1.1049) time: 0.5052 [2021-03-25 17:40:18 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 360/1251] eta: 0:07:41 lr: 0.000839 loss: 3.6133 (3.5536) grad_norm: 1.0838 (1.1045) time: 0.5063 [2021-03-25 17:40:23 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 370/1251] eta: 0:07:36 lr: 0.000839 loss: 3.6169 (3.5539) grad_norm: 1.0876 (1.1066) time: 0.5012 [2021-03-25 17:40:28 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 380/1251] eta: 0:07:30 lr: 0.000839 loss: 3.6553 (3.5535) grad_norm: 1.0660 (1.1060) time: 0.4999 [2021-03-25 17:40:33 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 390/1251] eta: 0:07:25 lr: 0.000839 loss: 3.6495 (3.5552) grad_norm: 1.0749 (1.1066) time: 0.5031 [2021-03-25 17:40:38 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 400/1251] eta: 0:07:19 lr: 0.000839 loss: 3.2702 (3.5461) grad_norm: 1.0874 (1.1063) time: 0.5074 [2021-03-25 17:40:43 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 410/1251] eta: 0:07:14 lr: 0.000839 loss: 3.6932 (3.5543) grad_norm: 1.0737 (1.1060) time: 0.5133 [2021-03-25 17:40:48 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 420/1251] eta: 0:07:09 lr: 0.000839 loss: 3.8937 (3.5625) grad_norm: 1.0627 (1.1061) time: 0.5047 [2021-03-25 17:40:53 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 430/1251] eta: 0:07:03 lr: 0.000839 loss: 3.8699 (3.5682) grad_norm: 1.0783 (1.1063) time: 0.5016 [2021-03-25 17:40:58 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 440/1251] eta: 0:06:58 lr: 0.000839 loss: 3.8811 (3.5704) grad_norm: 1.0783 (1.1055) time: 0.5073 [2021-03-25 17:41:03 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 450/1251] eta: 0:06:53 lr: 0.000839 loss: 3.6480 (3.5646) grad_norm: 1.0654 (1.1058) time: 0.5075 [2021-03-25 17:41:09 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 460/1251] eta: 0:06:47 lr: 0.000839 loss: 3.5030 (3.5634) grad_norm: 1.0960 (1.1076) time: 0.5073 [2021-03-25 17:41:14 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 470/1251] eta: 0:06:42 lr: 0.000839 loss: 3.5305 (3.5629) grad_norm: 1.1868 (1.1088) time: 0.5046 [2021-03-25 17:41:19 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 480/1251] eta: 0:06:36 lr: 0.000839 loss: 3.6125 (3.5655) grad_norm: 1.1666 (1.1094) time: 0.5013 [2021-03-25 17:41:24 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 490/1251] eta: 0:06:31 lr: 0.000839 loss: 3.7219 (3.5664) grad_norm: 1.0884 (1.1095) time: 0.5004 [2021-03-25 17:41:29 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 500/1251] eta: 0:06:26 lr: 0.000839 loss: 3.6056 (3.5621) grad_norm: 1.0587 (1.1092) time: 0.5055 [2021-03-25 17:41:34 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 510/1251] eta: 0:06:21 lr: 0.000838 loss: 3.3936 (3.5590) grad_norm: 1.1463 (1.1106) time: 0.5045 [2021-03-25 17:41:39 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 520/1251] eta: 0:06:15 lr: 0.000838 loss: 3.4113 (3.5593) grad_norm: 1.0834 (1.1094) time: 0.5041 [2021-03-25 17:41:44 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 530/1251] eta: 0:06:10 lr: 0.000838 loss: 3.5120 (3.5615) grad_norm: 1.0545 (1.1092) time: 0.5105 [2021-03-25 17:41:49 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 540/1251] eta: 0:06:05 lr: 0.000838 loss: 3.8793 (3.5660) grad_norm: 1.0826 (1.1095) time: 0.5086 [2021-03-25 17:41:54 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 550/1251] eta: 0:06:00 lr: 0.000838 loss: 3.7605 (3.5703) grad_norm: 1.0692 (1.1086) time: 0.5156 [2021-03-25 17:41:59 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 560/1251] eta: 0:05:55 lr: 0.000838 loss: 3.8040 (3.5735) grad_norm: 1.0626 (1.1082) time: 0.5203 [2021-03-25 17:42:04 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 570/1251] eta: 0:05:50 lr: 0.000838 loss: 3.7405 (3.5744) grad_norm: 1.0148 (1.1064) time: 0.5122 [2021-03-25 17:42:09 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 580/1251] eta: 0:05:44 lr: 0.000838 loss: 3.7233 (3.5771) grad_norm: 1.0219 (1.1058) time: 0.5019 [2021-03-25 17:42:14 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 590/1251] eta: 0:05:39 lr: 0.000838 loss: 3.9429 (3.5804) grad_norm: 1.0948 (1.1063) time: 0.5042 [2021-03-25 17:42:20 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 600/1251] eta: 0:05:34 lr: 0.000838 loss: 3.8834 (3.5815) grad_norm: 1.1185 (1.1058) time: 0.5100 [2021-03-25 17:42:25 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 610/1251] eta: 0:05:29 lr: 0.000838 loss: 3.7937 (3.5851) grad_norm: 1.1185 (1.1066) time: 0.5096 [2021-03-25 17:42:30 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 620/1251] eta: 0:05:24 lr: 0.000838 loss: 3.7335 (3.5881) grad_norm: 1.0756 (1.1057) time: 0.5125 [2021-03-25 17:42:35 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 630/1251] eta: 0:05:18 lr: 0.000838 loss: 3.8246 (3.5932) grad_norm: 1.0362 (1.1052) time: 0.5045 [2021-03-25 17:42:40 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 640/1251] eta: 0:05:13 lr: 0.000838 loss: 3.6958 (3.5917) grad_norm: 1.0278 (1.1038) time: 0.5010 [2021-03-25 17:42:45 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 650/1251] eta: 0:05:08 lr: 0.000838 loss: 3.3359 (3.5871) grad_norm: 1.0218 (1.1034) time: 0.5060 [2021-03-25 17:42:50 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 660/1251] eta: 0:05:03 lr: 0.000838 loss: 3.4782 (3.5857) grad_norm: 1.0320 (1.1027) time: 0.5076 [2021-03-25 17:42:55 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 670/1251] eta: 0:04:58 lr: 0.000838 loss: 3.6910 (3.5880) grad_norm: 1.0488 (1.1019) time: 0.5098 [2021-03-25 17:43:00 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 680/1251] eta: 0:04:52 lr: 0.000838 loss: 3.7807 (3.5900) grad_norm: 1.0517 (1.1021) time: 0.5109 [2021-03-25 17:43:05 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 690/1251] eta: 0:04:47 lr: 0.000838 loss: 3.7850 (3.5924) grad_norm: 1.0913 (1.1022) time: 0.5105 [2021-03-25 17:43:10 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 700/1251] eta: 0:04:42 lr: 0.000838 loss: 3.5986 (3.5897) grad_norm: 1.0782 (1.1028) time: 0.5056 [2021-03-25 17:43:15 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 710/1251] eta: 0:04:37 lr: 0.000838 loss: 3.3139 (3.5867) grad_norm: 1.0672 (1.1023) time: 0.5068 [2021-03-25 17:43:20 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 720/1251] eta: 0:04:32 lr: 0.000838 loss: 3.5630 (3.5874) grad_norm: 1.0459 (1.1015) time: 0.5073 [2021-03-25 17:43:26 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 730/1251] eta: 0:04:27 lr: 0.000838 loss: 3.6604 (3.5867) grad_norm: 1.0459 (1.1012) time: 0.5091 [2021-03-25 17:43:31 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 740/1251] eta: 0:04:22 lr: 0.000838 loss: 3.6140 (3.5883) grad_norm: 1.1570 (1.1020) time: 0.5264 [2021-03-25 17:43:36 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 750/1251] eta: 0:04:16 lr: 0.000838 loss: 3.6085 (3.5856) grad_norm: 1.1334 (1.1020) time: 0.5232 [2021-03-25 17:43:41 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 760/1251] eta: 0:04:11 lr: 0.000838 loss: 3.6967 (3.5880) grad_norm: 1.0669 (1.1013) time: 0.5049 [2021-03-25 17:43:46 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 770/1251] eta: 0:04:06 lr: 0.000838 loss: 3.6313 (3.5825) grad_norm: 1.0609 (1.1016) time: 0.5019 [2021-03-25 17:43:51 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 780/1251] eta: 0:04:01 lr: 0.000838 loss: 3.2654 (3.5802) grad_norm: 1.0985 (1.1019) time: 0.5075 [2021-03-25 17:43:56 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 790/1251] eta: 0:03:56 lr: 0.000838 loss: 3.5853 (3.5810) grad_norm: 1.0748 (1.1013) time: 0.5086 [2021-03-25 17:44:01 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 800/1251] eta: 0:03:51 lr: 0.000838 loss: 3.5166 (3.5779) grad_norm: 1.0444 (1.1012) time: 0.5075 [2021-03-25 17:44:06 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 810/1251] eta: 0:03:45 lr: 0.000838 loss: 3.6141 (3.5793) grad_norm: 1.0995 (1.1011) time: 0.5079 [2021-03-25 17:44:12 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 820/1251] eta: 0:03:40 lr: 0.000838 loss: 3.9075 (3.5809) grad_norm: 1.0995 (1.1015) time: 0.5077 [2021-03-25 17:44:17 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 830/1251] eta: 0:03:35 lr: 0.000838 loss: 3.9126 (3.5809) grad_norm: 1.0978 (1.1015) time: 0.5073 [2021-03-25 17:44:22 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 840/1251] eta: 0:03:30 lr: 0.000837 loss: 3.8996 (3.5831) grad_norm: 1.0855 (1.1012) time: 0.5077 [2021-03-25 17:44:27 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 850/1251] eta: 0:03:25 lr: 0.000837 loss: 3.5842 (3.5807) grad_norm: 1.0696 (1.1010) time: 0.5062 [2021-03-25 17:44:32 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 860/1251] eta: 0:03:20 lr: 0.000837 loss: 3.5842 (3.5817) grad_norm: 1.1178 (1.1018) time: 0.5053 [2021-03-25 17:44:37 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 870/1251] eta: 0:03:15 lr: 0.000837 loss: 3.6337 (3.5801) grad_norm: 1.1281 (1.1014) time: 0.5064 [2021-03-25 17:44:42 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 880/1251] eta: 0:03:09 lr: 0.000837 loss: 3.3661 (3.5767) grad_norm: 1.0300 (1.1007) time: 0.5128 [2021-03-25 17:44:47 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 890/1251] eta: 0:03:04 lr: 0.000837 loss: 3.4292 (3.5752) grad_norm: 1.0205 (1.1002) time: 0.5160 [2021-03-25 17:44:52 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 900/1251] eta: 0:02:59 lr: 0.000837 loss: 3.5137 (3.5741) grad_norm: 1.0420 (1.0998) time: 0.5090 [2021-03-25 17:44:57 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 910/1251] eta: 0:02:54 lr: 0.000837 loss: 3.6433 (3.5743) grad_norm: 1.0805 (1.1001) time: 0.5052 [2021-03-25 17:45:02 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 920/1251] eta: 0:02:49 lr: 0.000837 loss: 3.7101 (3.5747) grad_norm: 1.1404 (1.1006) time: 0.5046 [2021-03-25 17:45:08 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 930/1251] eta: 0:02:44 lr: 0.000837 loss: 3.5605 (3.5726) grad_norm: 1.1108 (1.1008) time: 0.5136 [2021-03-25 17:45:13 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 940/1251] eta: 0:02:39 lr: 0.000837 loss: 3.3323 (3.5698) grad_norm: 1.0695 (1.1004) time: 0.5106 [2021-03-25 17:45:18 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 950/1251] eta: 0:02:34 lr: 0.000837 loss: 3.4656 (3.5714) grad_norm: 1.0209 (1.1002) time: 0.5028 [2021-03-25 17:45:23 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 960/1251] eta: 0:02:28 lr: 0.000837 loss: 3.5407 (3.5705) grad_norm: 1.0674 (1.1000) time: 0.5096 [2021-03-25 17:45:28 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 970/1251] eta: 0:02:23 lr: 0.000837 loss: 3.5407 (3.5692) grad_norm: 1.0759 (1.0996) time: 0.5088 [2021-03-25 17:45:33 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 980/1251] eta: 0:02:18 lr: 0.000837 loss: 3.7075 (3.5697) grad_norm: 1.0700 (1.0995) time: 0.5105 [2021-03-25 17:45:38 swin_small_patch4_window7_224] INFO: Epoch: [79] [ 990/1251] eta: 0:02:13 lr: 0.000837 loss: 3.6305 (3.5710) grad_norm: 1.0822 (1.1000) time: 0.5084 [2021-03-25 17:45:43 swin_small_patch4_window7_224] INFO: Epoch: [79] [1000/1251] eta: 0:02:08 lr: 0.000837 loss: 3.7740 (3.5715) grad_norm: 1.0937 (1.1000) time: 0.5050 [2021-03-25 17:45:48 swin_small_patch4_window7_224] INFO: Epoch: [79] [1010/1251] eta: 0:02:03 lr: 0.000837 loss: 3.7740 (3.5728) grad_norm: 1.0507 (1.1002) time: 0.5095 [2021-03-25 17:45:53 swin_small_patch4_window7_224] INFO: Epoch: [79] [1020/1251] eta: 0:01:58 lr: 0.000837 loss: 3.5712 (3.5703) grad_norm: 1.0772 (1.1005) time: 0.5082 [2021-03-25 17:45:58 swin_small_patch4_window7_224] INFO: Epoch: [79] [1030/1251] eta: 0:01:53 lr: 0.000837 loss: 3.5712 (3.5712) grad_norm: 1.0772 (1.1000) time: 0.5074 [2021-03-25 17:46:04 swin_small_patch4_window7_224] INFO: Epoch: [79] [1040/1251] eta: 0:01:47 lr: 0.000837 loss: 3.6341 (3.5699) grad_norm: 1.0474 (1.0999) time: 0.5109 [2021-03-25 17:46:08 swin_small_patch4_window7_224] INFO: Epoch: [79] [1050/1251] eta: 0:01:42 lr: 0.000837 loss: 3.6453 (3.5720) grad_norm: 1.0416 (1.0994) time: 0.5060 [2021-03-25 17:46:13 swin_small_patch4_window7_224] INFO: Epoch: [79] [1060/1251] eta: 0:01:37 lr: 0.000837 loss: 3.7352 (3.5748) grad_norm: 1.0563 (1.0998) time: 0.4991 [2021-03-25 17:46:19 swin_small_patch4_window7_224] INFO: Epoch: [79] [1070/1251] eta: 0:01:32 lr: 0.000837 loss: 3.7874 (3.5745) grad_norm: 1.1801 (1.1008) time: 0.5023 [2021-03-25 17:46:24 swin_small_patch4_window7_224] INFO: Epoch: [79] [1080/1251] eta: 0:01:27 lr: 0.000837 loss: 3.6000 (3.5773) grad_norm: 1.1467 (1.1011) time: 0.5040 [2021-03-25 17:46:29 swin_small_patch4_window7_224] INFO: Epoch: [79] [1090/1251] eta: 0:01:22 lr: 0.000837 loss: 3.6085 (3.5766) grad_norm: 1.0890 (1.1020) time: 0.5030 [2021-03-25 17:46:34 swin_small_patch4_window7_224] INFO: Epoch: [79] [1100/1251] eta: 0:01:17 lr: 0.000837 loss: 3.6085 (3.5759) grad_norm: 1.0706 (1.1023) time: 0.5026 [2021-03-25 17:46:39 swin_small_patch4_window7_224] INFO: Epoch: [79] [1110/1251] eta: 0:01:12 lr: 0.000837 loss: 3.4726 (3.5735) grad_norm: 1.1344 (1.1034) time: 0.5054 [2021-03-25 17:46:44 swin_small_patch4_window7_224] INFO: Epoch: [79] [1120/1251] eta: 0:01:06 lr: 0.000837 loss: 3.4123 (3.5739) grad_norm: 1.0852 (1.1028) time: 0.5025 [2021-03-25 17:46:49 swin_small_patch4_window7_224] INFO: Epoch: [79] [1130/1251] eta: 0:01:01 lr: 0.000837 loss: 3.7533 (3.5750) grad_norm: 1.0305 (1.1028) time: 0.4998 [2021-03-25 17:46:54 swin_small_patch4_window7_224] INFO: Epoch: [79] [1140/1251] eta: 0:00:56 lr: 0.000837 loss: 3.8204 (3.5756) grad_norm: 1.0724 (1.1025) time: 0.5043 [2021-03-25 17:46:59 swin_small_patch4_window7_224] INFO: Epoch: [79] [1150/1251] eta: 0:00:51 lr: 0.000837 loss: 3.8136 (3.5777) grad_norm: 1.0777 (1.1033) time: 0.5092 [2021-03-25 17:47:04 swin_small_patch4_window7_224] INFO: Epoch: [79] [1160/1251] eta: 0:00:46 lr: 0.000836 loss: 3.7339 (3.5783) grad_norm: 1.0924 (1.1033) time: 0.5090 [2021-03-25 17:47:09 swin_small_patch4_window7_224] INFO: Epoch: [79] [1170/1251] eta: 0:00:41 lr: 0.000836 loss: 3.6634 (3.5788) grad_norm: 1.0130 (1.1024) time: 0.5066 [2021-03-25 17:47:14 swin_small_patch4_window7_224] INFO: Epoch: [79] [1180/1251] eta: 0:00:36 lr: 0.000836 loss: 3.6088 (3.5775) grad_norm: 1.0116 (1.1020) time: 0.5098 [2021-03-25 17:47:19 swin_small_patch4_window7_224] INFO: Epoch: [79] [1190/1251] eta: 0:00:31 lr: 0.000836 loss: 3.5914 (3.5771) grad_norm: 1.0564 (1.1024) time: 0.5102 [2021-03-25 17:47:24 swin_small_patch4_window7_224] INFO: Epoch: [79] [1200/1251] eta: 0:00:26 lr: 0.000836 loss: 3.5236 (3.5769) grad_norm: 1.1560 (1.1031) time: 0.5075 [2021-03-25 17:47:29 swin_small_patch4_window7_224] INFO: Epoch: [79] [1210/1251] eta: 0:00:20 lr: 0.000836 loss: 3.4799 (3.5754) grad_norm: 1.0615 (1.1028) time: 0.5061 [2021-03-25 17:47:34 swin_small_patch4_window7_224] INFO: Epoch: [79] [1220/1251] eta: 0:00:15 lr: 0.000836 loss: 3.6530 (3.5762) grad_norm: 1.0518 (1.1025) time: 0.5022 [2021-03-25 17:47:39 swin_small_patch4_window7_224] INFO: Epoch: [79] [1230/1251] eta: 0:00:10 lr: 0.000836 loss: 3.3949 (3.5740) grad_norm: 1.0518 (1.1024) time: 0.5016 [2021-03-25 17:47:45 swin_small_patch4_window7_224] INFO: Epoch: [79] [1240/1251] eta: 0:00:05 lr: 0.000836 loss: 3.1482 (3.5736) grad_norm: 1.1412 (1.1027) time: 0.5079 [2021-03-25 17:47:50 swin_small_patch4_window7_224] INFO: Epoch: [79] [1250/1251] eta: 0:00:00 lr: 0.000836 loss: 3.8196 (3.5737) grad_norm: 1.0930 (1.1026) time: 0.5054 [2021-03-25 17:47:54 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 1.4760 (1.4760) acc1: 67.1875 (67.1875) acc5: 89.0625 (89.0625) [2021-03-25 17:47:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.2164 (1.2009) acc1: 70.3125 (72.4432) acc5: 90.6250 (90.9091) [2021-03-25 17:47:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.1320 (1.1368) acc1: 75.0000 (74.4048) acc5: 90.6250 (91.8155) [2021-03-25 17:48:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0962 (1.1302) acc1: 73.4375 (74.0423) acc5: 92.1875 (92.0363) [2021-03-25 17:48:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0647 (1.0960) acc1: 75.0000 (74.4284) acc5: 95.3125 (92.7210) [2021-03-25 17:48:03 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0212 (1.0826) acc1: 75.0000 (74.4640) acc5: 95.3125 (92.9600) [2021-03-25 17:48:08 swin_small_patch4_window7_224] INFO: * Acc@1 74.856 Acc@5 92.870 loss 1.071 [2021-03-25 17:48:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.9% [2021-03-25 17:48:08 swin_small_patch4_window7_224] INFO: Max accuracy: 75.12% [2021-03-25 17:48:12 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 0/1251] eta: 1:30:21 lr: 0.000836 loss: 2.4614 (2.4614) grad_norm: 1.2637 (1.2637) time: 4.3341 [2021-03-25 17:48:17 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 10/1251] eta: 0:17:39 lr: 0.000836 loss: 3.5800 (3.3281) grad_norm: 1.1015 (1.1190) time: 0.8536 [2021-03-25 17:48:23 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 20/1251] eta: 0:14:07 lr: 0.000836 loss: 3.2741 (3.3550) grad_norm: 1.0984 (1.1378) time: 0.5062 [2021-03-25 17:48:28 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 30/1251] eta: 0:12:56 lr: 0.000836 loss: 3.4688 (3.4444) grad_norm: 1.1018 (1.1323) time: 0.5161 [2021-03-25 17:48:33 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 40/1251] eta: 0:12:13 lr: 0.000836 loss: 3.6100 (3.4842) grad_norm: 1.1141 (1.1495) time: 0.5181 [2021-03-25 17:48:38 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 50/1251] eta: 0:11:42 lr: 0.000836 loss: 3.5800 (3.4426) grad_norm: 1.1263 (1.1450) time: 0.5053 [2021-03-25 17:48:43 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 60/1251] eta: 0:11:21 lr: 0.000836 loss: 3.5722 (3.4729) grad_norm: 1.0689 (1.1301) time: 0.5035 [2021-03-25 17:48:48 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 70/1251] eta: 0:11:06 lr: 0.000836 loss: 3.5314 (3.4402) grad_norm: 1.0015 (1.1118) time: 0.5130 [2021-03-25 17:48:53 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 80/1251] eta: 0:10:53 lr: 0.000836 loss: 3.4800 (3.4704) grad_norm: 1.0015 (1.1092) time: 0.5142 [2021-03-25 17:48:58 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 90/1251] eta: 0:10:39 lr: 0.000836 loss: 3.6996 (3.5150) grad_norm: 1.0378 (1.1017) time: 0.5040 [2021-03-25 17:49:03 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 100/1251] eta: 0:10:28 lr: 0.000836 loss: 3.9315 (3.5338) grad_norm: 1.0592 (1.1037) time: 0.4985 [2021-03-25 17:49:08 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 110/1251] eta: 0:10:19 lr: 0.000836 loss: 3.5406 (3.5247) grad_norm: 1.1200 (1.1054) time: 0.5034 [2021-03-25 17:49:14 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 120/1251] eta: 0:10:11 lr: 0.000836 loss: 3.5488 (3.5408) grad_norm: 1.0914 (1.1076) time: 0.5159 [2021-03-25 17:49:19 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 130/1251] eta: 0:10:03 lr: 0.000836 loss: 3.7012 (3.5515) grad_norm: 1.0584 (1.1041) time: 0.5163 [2021-03-25 17:49:24 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 140/1251] eta: 0:09:55 lr: 0.000836 loss: 3.7012 (3.5447) grad_norm: 1.0524 (1.1002) time: 0.5071 [2021-03-25 17:49:29 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 150/1251] eta: 0:09:48 lr: 0.000836 loss: 3.4930 (3.5477) grad_norm: 1.0731 (1.1028) time: 0.5046 [2021-03-25 17:49:34 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 160/1251] eta: 0:09:40 lr: 0.000836 loss: 3.4930 (3.5475) grad_norm: 1.0936 (1.1059) time: 0.5011 [2021-03-25 17:49:39 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 170/1251] eta: 0:09:33 lr: 0.000836 loss: 3.9094 (3.5648) grad_norm: 1.0930 (1.1083) time: 0.5016 [2021-03-25 17:49:44 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 180/1251] eta: 0:09:26 lr: 0.000836 loss: 3.8090 (3.5645) grad_norm: 1.0807 (1.1061) time: 0.5065 [2021-03-25 17:49:49 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 190/1251] eta: 0:09:19 lr: 0.000836 loss: 3.5016 (3.5538) grad_norm: 1.0522 (1.1061) time: 0.5042 [2021-03-25 17:49:54 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 200/1251] eta: 0:09:13 lr: 0.000836 loss: 3.9089 (3.5730) grad_norm: 1.0721 (1.1054) time: 0.5033 [2021-03-25 17:49:59 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 210/1251] eta: 0:09:07 lr: 0.000836 loss: 3.9089 (3.5725) grad_norm: 1.0721 (1.1046) time: 0.5065 [2021-03-25 17:50:04 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 220/1251] eta: 0:09:01 lr: 0.000836 loss: 3.3314 (3.5565) grad_norm: 1.1098 (1.1064) time: 0.5095 [2021-03-25 17:50:09 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 230/1251] eta: 0:08:55 lr: 0.000836 loss: 3.7474 (3.5592) grad_norm: 1.1103 (1.1072) time: 0.5100 [2021-03-25 17:50:14 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 240/1251] eta: 0:08:49 lr: 0.000835 loss: 3.9025 (3.5780) grad_norm: 1.1042 (1.1090) time: 0.5069 [2021-03-25 17:50:19 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 250/1251] eta: 0:08:43 lr: 0.000835 loss: 3.8986 (3.5841) grad_norm: 1.1481 (1.1101) time: 0.5097 [2021-03-25 17:50:24 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 260/1251] eta: 0:08:37 lr: 0.000835 loss: 3.4934 (3.5703) grad_norm: 1.0634 (1.1110) time: 0.5113 [2021-03-25 17:50:30 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 270/1251] eta: 0:08:32 lr: 0.000835 loss: 3.3321 (3.5680) grad_norm: 1.0822 (1.1107) time: 0.5090 [2021-03-25 17:50:35 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 280/1251] eta: 0:08:26 lr: 0.000835 loss: 3.7421 (3.5760) grad_norm: 1.0822 (1.1098) time: 0.5087 [2021-03-25 17:50:40 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 290/1251] eta: 0:08:20 lr: 0.000835 loss: 3.7421 (3.5757) grad_norm: 1.0858 (1.1112) time: 0.5077 [2021-03-25 17:50:45 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 300/1251] eta: 0:08:14 lr: 0.000835 loss: 3.7497 (3.5753) grad_norm: 1.0869 (1.1105) time: 0.5048 [2021-03-25 17:50:50 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 310/1251] eta: 0:08:09 lr: 0.000835 loss: 3.5954 (3.5720) grad_norm: 1.0753 (1.1088) time: 0.5136 [2021-03-25 17:50:55 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 320/1251] eta: 0:08:04 lr: 0.000835 loss: 3.6264 (3.5747) grad_norm: 1.0612 (1.1078) time: 0.5180 [2021-03-25 17:51:00 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 330/1251] eta: 0:07:58 lr: 0.000835 loss: 3.7256 (3.5823) grad_norm: 1.0462 (1.1065) time: 0.5052 [2021-03-25 17:51:05 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 340/1251] eta: 0:07:52 lr: 0.000835 loss: 3.4363 (3.5761) grad_norm: 1.0396 (1.1071) time: 0.5016 [2021-03-25 17:51:10 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 350/1251] eta: 0:07:47 lr: 0.000835 loss: 3.3745 (3.5737) grad_norm: 1.0204 (1.1052) time: 0.5062 [2021-03-25 17:51:15 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 360/1251] eta: 0:07:41 lr: 0.000835 loss: 3.6515 (3.5754) grad_norm: 1.0619 (1.1043) time: 0.5061 [2021-03-25 17:51:20 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 370/1251] eta: 0:07:36 lr: 0.000835 loss: 3.4423 (3.5682) grad_norm: 1.0712 (1.1036) time: 0.5021 [2021-03-25 17:51:25 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 380/1251] eta: 0:07:30 lr: 0.000835 loss: 3.3461 (3.5688) grad_norm: 1.0232 (1.1012) time: 0.5007 [2021-03-25 17:51:30 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 390/1251] eta: 0:07:25 lr: 0.000835 loss: 3.4268 (3.5658) grad_norm: 1.0316 (1.1000) time: 0.5052 [2021-03-25 17:51:35 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 400/1251] eta: 0:07:19 lr: 0.000835 loss: 3.4120 (3.5644) grad_norm: 1.0329 (1.0984) time: 0.5073 [2021-03-25 17:51:41 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 410/1251] eta: 0:07:14 lr: 0.000835 loss: 3.7264 (3.5606) grad_norm: 1.0329 (1.0984) time: 0.5092 [2021-03-25 17:51:46 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 420/1251] eta: 0:07:09 lr: 0.000835 loss: 3.4634 (3.5572) grad_norm: 1.0893 (1.0988) time: 0.5117 [2021-03-25 17:51:51 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 430/1251] eta: 0:07:04 lr: 0.000835 loss: 3.3970 (3.5543) grad_norm: 1.0609 (1.0983) time: 0.5093 [2021-03-25 17:51:56 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 440/1251] eta: 0:06:58 lr: 0.000835 loss: 3.4718 (3.5550) grad_norm: 1.0609 (1.0983) time: 0.5110 [2021-03-25 17:52:01 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 450/1251] eta: 0:06:53 lr: 0.000835 loss: 3.5811 (3.5573) grad_norm: 1.0461 (1.0970) time: 0.5102 [2021-03-25 17:52:06 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 460/1251] eta: 0:06:48 lr: 0.000835 loss: 3.5811 (3.5543) grad_norm: 1.0668 (1.0975) time: 0.5064 [2021-03-25 17:52:11 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 470/1251] eta: 0:06:42 lr: 0.000835 loss: 3.3387 (3.5492) grad_norm: 1.1348 (1.0989) time: 0.5077 [2021-03-25 17:52:16 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 480/1251] eta: 0:06:37 lr: 0.000835 loss: 3.3657 (3.5486) grad_norm: 1.0874 (1.0978) time: 0.5042 [2021-03-25 17:52:21 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 490/1251] eta: 0:06:32 lr: 0.000835 loss: 3.5109 (3.5447) grad_norm: 1.0034 (1.0957) time: 0.5010 [2021-03-25 17:52:26 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 500/1251] eta: 0:06:26 lr: 0.000835 loss: 3.6383 (3.5460) grad_norm: 1.0169 (1.0949) time: 0.5005 [2021-03-25 17:52:31 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 510/1251] eta: 0:06:21 lr: 0.000835 loss: 3.6909 (3.5475) grad_norm: 1.0402 (1.0950) time: 0.4998 [2021-03-25 17:52:36 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 520/1251] eta: 0:06:16 lr: 0.000835 loss: 3.5363 (3.5436) grad_norm: 1.0629 (1.0960) time: 0.5045 [2021-03-25 17:52:41 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 530/1251] eta: 0:06:10 lr: 0.000835 loss: 3.6063 (3.5478) grad_norm: 1.0552 (1.0948) time: 0.5090 [2021-03-25 17:52:46 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 540/1251] eta: 0:06:05 lr: 0.000835 loss: 3.5068 (3.5432) grad_norm: 1.0261 (1.0940) time: 0.5075 [2021-03-25 17:52:52 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 550/1251] eta: 0:06:00 lr: 0.000835 loss: 3.3935 (3.5443) grad_norm: 1.0366 (1.0937) time: 0.5147 [2021-03-25 17:52:57 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 560/1251] eta: 0:05:55 lr: 0.000834 loss: 3.6586 (3.5425) grad_norm: 1.0554 (1.0930) time: 0.5126 [2021-03-25 17:53:02 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 570/1251] eta: 0:05:50 lr: 0.000834 loss: 3.7701 (3.5481) grad_norm: 1.0554 (1.0924) time: 0.5030 [2021-03-25 17:53:07 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 580/1251] eta: 0:05:44 lr: 0.000834 loss: 3.6815 (3.5449) grad_norm: 1.0629 (1.0920) time: 0.5107 [2021-03-25 17:53:12 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 590/1251] eta: 0:05:39 lr: 0.000834 loss: 3.7159 (3.5502) grad_norm: 1.0548 (1.0918) time: 0.5101 [2021-03-25 17:53:17 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 600/1251] eta: 0:05:34 lr: 0.000834 loss: 3.7159 (3.5454) grad_norm: 1.0060 (1.0911) time: 0.5068 [2021-03-25 17:53:22 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 610/1251] eta: 0:05:29 lr: 0.000834 loss: 3.6671 (3.5453) grad_norm: 1.0357 (1.0912) time: 0.5047 [2021-03-25 17:53:27 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 620/1251] eta: 0:05:24 lr: 0.000834 loss: 3.7153 (3.5457) grad_norm: 1.0977 (1.0922) time: 0.5096 [2021-03-25 17:53:32 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 630/1251] eta: 0:05:18 lr: 0.000834 loss: 3.5652 (3.5425) grad_norm: 1.0817 (1.0924) time: 0.5129 [2021-03-25 17:53:37 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 640/1251] eta: 0:05:13 lr: 0.000834 loss: 3.5652 (3.5442) grad_norm: 1.0941 (1.0929) time: 0.5027 [2021-03-25 17:53:42 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 650/1251] eta: 0:05:08 lr: 0.000834 loss: 3.7239 (3.5465) grad_norm: 1.0885 (1.0922) time: 0.4990 [2021-03-25 17:53:47 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 660/1251] eta: 0:05:03 lr: 0.000834 loss: 3.6494 (3.5465) grad_norm: 1.0320 (1.0927) time: 0.5017 [2021-03-25 17:53:52 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 670/1251] eta: 0:04:58 lr: 0.000834 loss: 3.5360 (3.5448) grad_norm: 1.0469 (1.0920) time: 0.5091 [2021-03-25 17:53:58 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 680/1251] eta: 0:04:52 lr: 0.000834 loss: 3.4460 (3.5436) grad_norm: 1.0410 (1.0917) time: 0.5114 [2021-03-25 17:54:03 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 690/1251] eta: 0:04:47 lr: 0.000834 loss: 3.6189 (3.5455) grad_norm: 1.0325 (1.0906) time: 0.5078 [2021-03-25 17:54:08 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 700/1251] eta: 0:04:42 lr: 0.000834 loss: 3.6673 (3.5466) grad_norm: 1.0305 (1.0910) time: 0.5067 [2021-03-25 17:54:13 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 710/1251] eta: 0:04:37 lr: 0.000834 loss: 3.8278 (3.5506) grad_norm: 1.0302 (1.0904) time: 0.5071 [2021-03-25 17:54:18 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 720/1251] eta: 0:04:32 lr: 0.000834 loss: 3.8985 (3.5470) grad_norm: 1.0465 (1.0903) time: 0.5077 [2021-03-25 17:54:23 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 730/1251] eta: 0:04:27 lr: 0.000834 loss: 3.6449 (3.5475) grad_norm: 1.0856 (1.0903) time: 0.5049 [2021-03-25 17:54:28 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 740/1251] eta: 0:04:22 lr: 0.000834 loss: 3.6688 (3.5473) grad_norm: 1.0796 (1.0905) time: 0.5177 [2021-03-25 17:54:33 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 750/1251] eta: 0:04:16 lr: 0.000834 loss: 3.6626 (3.5472) grad_norm: 1.0860 (1.0913) time: 0.5293 [2021-03-25 17:54:39 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 760/1251] eta: 0:04:11 lr: 0.000834 loss: 3.6398 (3.5479) grad_norm: 1.1524 (1.0920) time: 0.5167 [2021-03-25 17:54:44 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 770/1251] eta: 0:04:06 lr: 0.000834 loss: 3.5444 (3.5492) grad_norm: 1.0877 (1.0915) time: 0.5151 [2021-03-25 17:54:49 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 780/1251] eta: 0:04:01 lr: 0.000834 loss: 3.7867 (3.5520) grad_norm: 1.0430 (1.0908) time: 0.5167 [2021-03-25 17:54:54 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 790/1251] eta: 0:03:56 lr: 0.000834 loss: 3.8038 (3.5507) grad_norm: 1.0382 (1.0908) time: 0.5081 [2021-03-25 17:54:59 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 800/1251] eta: 0:03:51 lr: 0.000834 loss: 3.4203 (3.5514) grad_norm: 1.0881 (1.0914) time: 0.5068 [2021-03-25 17:55:04 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 810/1251] eta: 0:03:46 lr: 0.000834 loss: 3.3409 (3.5498) grad_norm: 1.0969 (1.0917) time: 0.5038 [2021-03-25 17:55:09 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 820/1251] eta: 0:03:41 lr: 0.000834 loss: 3.3351 (3.5465) grad_norm: 1.0281 (1.0908) time: 0.5121 [2021-03-25 17:55:14 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 830/1251] eta: 0:03:35 lr: 0.000834 loss: 3.4392 (3.5434) grad_norm: 1.0178 (1.0910) time: 0.5115 [2021-03-25 17:55:19 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 840/1251] eta: 0:03:30 lr: 0.000834 loss: 3.5678 (3.5417) grad_norm: 1.0921 (1.0912) time: 0.5042 [2021-03-25 17:55:24 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 850/1251] eta: 0:03:25 lr: 0.000834 loss: 3.6616 (3.5433) grad_norm: 1.1279 (1.0921) time: 0.5098 [2021-03-25 17:55:30 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 860/1251] eta: 0:03:20 lr: 0.000834 loss: 3.4907 (3.5423) grad_norm: 1.1468 (1.0930) time: 0.5203 [2021-03-25 17:55:35 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 870/1251] eta: 0:03:15 lr: 0.000834 loss: 3.3282 (3.5399) grad_norm: 1.0621 (1.0924) time: 0.5212 [2021-03-25 17:55:40 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 880/1251] eta: 0:03:10 lr: 0.000834 loss: 3.3621 (3.5390) grad_norm: 1.0517 (1.0924) time: 0.5051 [2021-03-25 17:55:45 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 890/1251] eta: 0:03:05 lr: 0.000833 loss: 3.7012 (3.5405) grad_norm: 1.0648 (1.0918) time: 0.5019 [2021-03-25 17:55:50 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 900/1251] eta: 0:02:59 lr: 0.000833 loss: 3.7033 (3.5401) grad_norm: 1.0659 (1.0919) time: 0.5067 [2021-03-25 17:55:55 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 910/1251] eta: 0:02:54 lr: 0.000833 loss: 3.6043 (3.5406) grad_norm: 1.0659 (1.0917) time: 0.5080 [2021-03-25 17:56:00 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 920/1251] eta: 0:02:49 lr: 0.000833 loss: 3.6126 (3.5416) grad_norm: 1.0519 (1.0913) time: 0.5059 [2021-03-25 17:56:05 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 930/1251] eta: 0:02:44 lr: 0.000833 loss: 3.6938 (3.5443) grad_norm: 0.9989 (1.0900) time: 0.5045 [2021-03-25 17:56:10 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 940/1251] eta: 0:02:39 lr: 0.000833 loss: 3.6938 (3.5441) grad_norm: 1.0296 (inf) time: 0.4983 [2021-03-25 17:56:15 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 950/1251] eta: 0:02:34 lr: 0.000833 loss: 3.4732 (3.5426) grad_norm: 1.1097 (inf) time: 0.4965 [2021-03-25 17:56:20 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 960/1251] eta: 0:02:28 lr: 0.000833 loss: 3.6754 (3.5435) grad_norm: 1.0864 (inf) time: 0.5073 [2021-03-25 17:56:25 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 970/1251] eta: 0:02:23 lr: 0.000833 loss: 3.7243 (3.5419) grad_norm: 1.0704 (inf) time: 0.5096 [2021-03-25 17:56:30 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 980/1251] eta: 0:02:18 lr: 0.000833 loss: 3.6274 (3.5432) grad_norm: 1.0755 (inf) time: 0.5064 [2021-03-25 17:56:35 swin_small_patch4_window7_224] INFO: Epoch: [80] [ 990/1251] eta: 0:02:13 lr: 0.000833 loss: 3.7337 (3.5457) grad_norm: 1.0931 (inf) time: 0.5036 [2021-03-25 17:56:40 swin_small_patch4_window7_224] INFO: Epoch: [80] [1000/1251] eta: 0:02:08 lr: 0.000833 loss: 3.7040 (3.5439) grad_norm: 1.0931 (inf) time: 0.5025 [2021-03-25 17:56:46 swin_small_patch4_window7_224] INFO: Epoch: [80] [1010/1251] eta: 0:02:03 lr: 0.000833 loss: 3.3040 (3.5437) grad_norm: 1.0303 (inf) time: 0.5086 [2021-03-25 17:56:51 swin_small_patch4_window7_224] INFO: Epoch: [80] [1020/1251] eta: 0:01:58 lr: 0.000833 loss: 3.6551 (3.5453) grad_norm: 1.0236 (inf) time: 0.5053 [2021-03-25 17:56:56 swin_small_patch4_window7_224] INFO: Epoch: [80] [1030/1251] eta: 0:01:53 lr: 0.000833 loss: 3.6842 (3.5460) grad_norm: 1.0378 (inf) time: 0.5015 [2021-03-25 17:57:01 swin_small_patch4_window7_224] INFO: Epoch: [80] [1040/1251] eta: 0:01:47 lr: 0.000833 loss: 3.6842 (3.5455) grad_norm: 1.0378 (inf) time: 0.5050 [2021-03-25 17:57:06 swin_small_patch4_window7_224] INFO: Epoch: [80] [1050/1251] eta: 0:01:42 lr: 0.000833 loss: 3.3962 (3.5419) grad_norm: 1.0697 (inf) time: 0.5112 [2021-03-25 17:57:11 swin_small_patch4_window7_224] INFO: Epoch: [80] [1060/1251] eta: 0:01:37 lr: 0.000833 loss: 3.5440 (3.5437) grad_norm: 1.0902 (inf) time: 0.5126 [2021-03-25 17:57:16 swin_small_patch4_window7_224] INFO: Epoch: [80] [1070/1251] eta: 0:01:32 lr: 0.000833 loss: 3.6800 (3.5443) grad_norm: 1.0878 (inf) time: 0.5065 [2021-03-25 17:57:21 swin_small_patch4_window7_224] INFO: Epoch: [80] [1080/1251] eta: 0:01:27 lr: 0.000833 loss: 3.7519 (3.5467) grad_norm: 1.0791 (inf) time: 0.5023 [2021-03-25 17:57:26 swin_small_patch4_window7_224] INFO: Epoch: [80] [1090/1251] eta: 0:01:22 lr: 0.000833 loss: 3.9192 (3.5492) grad_norm: 1.1350 (inf) time: 0.5055 [2021-03-25 17:57:31 swin_small_patch4_window7_224] INFO: Epoch: [80] [1100/1251] eta: 0:01:17 lr: 0.000833 loss: 3.6665 (3.5491) grad_norm: 1.1045 (inf) time: 0.5054 [2021-03-25 17:57:36 swin_small_patch4_window7_224] INFO: Epoch: [80] [1110/1251] eta: 0:01:12 lr: 0.000833 loss: 3.2638 (3.5455) grad_norm: 1.0419 (inf) time: 0.5006 [2021-03-25 17:57:41 swin_small_patch4_window7_224] INFO: Epoch: [80] [1120/1251] eta: 0:01:06 lr: 0.000833 loss: 3.2631 (3.5444) grad_norm: 1.0711 (inf) time: 0.5034 [2021-03-25 17:57:46 swin_small_patch4_window7_224] INFO: Epoch: [80] [1130/1251] eta: 0:01:01 lr: 0.000833 loss: 3.3686 (3.5439) grad_norm: 1.0510 (inf) time: 0.5010 [2021-03-25 17:57:51 swin_small_patch4_window7_224] INFO: Epoch: [80] [1140/1251] eta: 0:00:56 lr: 0.000833 loss: 3.5827 (3.5440) grad_norm: 1.0272 (inf) time: 0.4975 [2021-03-25 17:57:56 swin_small_patch4_window7_224] INFO: Epoch: [80] [1150/1251] eta: 0:00:51 lr: 0.000833 loss: 3.5827 (3.5430) grad_norm: 1.0321 (inf) time: 0.5021 [2021-03-25 17:58:01 swin_small_patch4_window7_224] INFO: Epoch: [80] [1160/1251] eta: 0:00:46 lr: 0.000833 loss: 3.6358 (3.5442) grad_norm: 1.0735 (inf) time: 0.5039 [2021-03-25 17:58:06 swin_small_patch4_window7_224] INFO: Epoch: [80] [1170/1251] eta: 0:00:41 lr: 0.000833 loss: 3.8048 (3.5472) grad_norm: 1.0914 (inf) time: 0.5027 [2021-03-25 17:58:11 swin_small_patch4_window7_224] INFO: Epoch: [80] [1180/1251] eta: 0:00:36 lr: 0.000833 loss: 3.8048 (3.5482) grad_norm: 1.1552 (inf) time: 0.5011 [2021-03-25 17:58:16 swin_small_patch4_window7_224] INFO: Epoch: [80] [1190/1251] eta: 0:00:31 lr: 0.000833 loss: 3.7468 (3.5486) grad_norm: 1.1825 (inf) time: 0.5071 [2021-03-25 17:58:21 swin_small_patch4_window7_224] INFO: Epoch: [80] [1200/1251] eta: 0:00:26 lr: 0.000833 loss: 3.6709 (3.5483) grad_norm: 1.1477 (inf) time: 0.5087 [2021-03-25 17:58:26 swin_small_patch4_window7_224] INFO: Epoch: [80] [1210/1251] eta: 0:00:20 lr: 0.000832 loss: 3.7802 (3.5500) grad_norm: 1.0998 (inf) time: 0.5002 [2021-03-25 17:58:31 swin_small_patch4_window7_224] INFO: Epoch: [80] [1220/1251] eta: 0:00:15 lr: 0.000832 loss: 3.8055 (3.5511) grad_norm: 1.0987 (inf) time: 0.4960 [2021-03-25 17:58:36 swin_small_patch4_window7_224] INFO: Epoch: [80] [1230/1251] eta: 0:00:10 lr: 0.000832 loss: 3.8006 (3.5517) grad_norm: 1.0628 (inf) time: 0.4983 [2021-03-25 17:58:41 swin_small_patch4_window7_224] INFO: Epoch: [80] [1240/1251] eta: 0:00:05 lr: 0.000832 loss: 3.8648 (3.5533) grad_norm: 1.0628 (inf) time: 0.5054 [2021-03-25 17:58:46 swin_small_patch4_window7_224] INFO: Epoch: [80] [1250/1251] eta: 0:00:00 lr: 0.000832 loss: 3.9029 (3.5566) grad_norm: 1.0890 (inf) time: 0.5019 [2021-03-25 17:59:29 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 1.0656 (1.0656) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-25 17:59:30 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.0656 (1.0911) acc1: 71.8750 (71.4489) acc5: 93.7500 (92.7557) [2021-03-25 17:59:31 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0568 (1.0464) acc1: 73.4375 (74.1815) acc5: 92.1875 (92.3363) [2021-03-25 17:59:32 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0107 (1.0444) acc1: 75.0000 (74.6976) acc5: 92.1875 (92.9435) [2021-03-25 17:59:33 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9535 (1.0256) acc1: 75.0000 (75.0381) acc5: 93.7500 (93.2927) [2021-03-25 17:59:34 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0812 (1.0619) acc1: 73.4375 (74.5280) acc5: 93.7500 (92.8960) [2021-03-25 17:59:38 swin_small_patch4_window7_224] INFO: * Acc@1 75.234 Acc@5 92.896 loss 1.051 [2021-03-25 17:59:38 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.2% [2021-03-25 17:59:38 swin_small_patch4_window7_224] INFO: Max accuracy: 75.23% [2021-03-25 17:59:43 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 0/1251] eta: 1:28:32 lr: 0.000832 loss: 3.3533 (3.3533) grad_norm: 1.2039 (1.2039) time: 4.2463 [2021-03-25 17:59:48 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 10/1251] eta: 0:17:40 lr: 0.000832 loss: 3.6024 (3.4609) grad_norm: 1.0382 (1.0981) time: 0.8542 [2021-03-25 17:59:53 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 20/1251] eta: 0:14:10 lr: 0.000832 loss: 3.6024 (3.5624) grad_norm: 1.0935 (1.1185) time: 0.5128 [2021-03-25 17:59:58 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 30/1251] eta: 0:12:51 lr: 0.000832 loss: 3.5728 (3.5225) grad_norm: 1.1018 (1.1266) time: 0.5092 [2021-03-25 18:00:03 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 40/1251] eta: 0:12:07 lr: 0.000832 loss: 3.4743 (3.4722) grad_norm: 1.1213 (1.1341) time: 0.5063 [2021-03-25 18:00:08 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 50/1251] eta: 0:11:44 lr: 0.000832 loss: 3.4834 (3.5145) grad_norm: 1.0738 (1.1208) time: 0.5161 [2021-03-25 18:00:14 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 60/1251] eta: 0:11:23 lr: 0.000832 loss: 3.6202 (3.5042) grad_norm: 1.0531 (1.1187) time: 0.5188 [2021-03-25 18:00:19 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 70/1251] eta: 0:11:07 lr: 0.000832 loss: 3.6666 (3.5231) grad_norm: 1.0813 (1.1194) time: 0.5100 [2021-03-25 18:00:24 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 80/1251] eta: 0:10:52 lr: 0.000832 loss: 3.8195 (3.5635) grad_norm: 1.0758 (1.1074) time: 0.5070 [2021-03-25 18:00:29 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 90/1251] eta: 0:10:39 lr: 0.000832 loss: 3.8156 (3.5745) grad_norm: 1.0626 (1.1130) time: 0.5024 [2021-03-25 18:00:34 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 100/1251] eta: 0:10:28 lr: 0.000832 loss: 3.7230 (3.5722) grad_norm: 1.0804 (1.1095) time: 0.5013 [2021-03-25 18:00:39 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 110/1251] eta: 0:10:19 lr: 0.000832 loss: 3.3543 (3.5266) grad_norm: 1.0456 (1.1022) time: 0.5041 [2021-03-25 18:00:44 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 120/1251] eta: 0:10:09 lr: 0.000832 loss: 3.3890 (3.5211) grad_norm: 1.0275 (1.0968) time: 0.5022 [2021-03-25 18:00:49 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 130/1251] eta: 0:10:00 lr: 0.000832 loss: 3.5908 (3.5242) grad_norm: 0.9999 (1.0962) time: 0.4999 [2021-03-25 18:00:54 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 140/1251] eta: 0:09:53 lr: 0.000832 loss: 3.5556 (3.5222) grad_norm: 1.0366 (1.0967) time: 0.5032 [2021-03-25 18:00:59 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 150/1251] eta: 0:09:47 lr: 0.000832 loss: 3.6532 (3.5363) grad_norm: 1.0366 (1.0934) time: 0.5164 [2021-03-25 18:01:04 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 160/1251] eta: 0:09:40 lr: 0.000832 loss: 3.7233 (3.5429) grad_norm: 1.0380 (1.0982) time: 0.5208 [2021-03-25 18:01:09 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 170/1251] eta: 0:09:33 lr: 0.000832 loss: 3.8323 (3.5652) grad_norm: 1.0397 (1.0960) time: 0.5116 [2021-03-25 18:01:14 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 180/1251] eta: 0:09:27 lr: 0.000832 loss: 3.9610 (3.5662) grad_norm: 1.0927 (1.0984) time: 0.5067 [2021-03-25 18:01:19 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 190/1251] eta: 0:09:20 lr: 0.000832 loss: 3.6130 (3.5630) grad_norm: 1.1250 (1.0987) time: 0.5036 [2021-03-25 18:01:25 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 200/1251] eta: 0:09:14 lr: 0.000832 loss: 3.6130 (3.5576) grad_norm: 1.0888 (1.0978) time: 0.5102 [2021-03-25 18:01:30 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 210/1251] eta: 0:09:07 lr: 0.000832 loss: 3.6470 (3.5584) grad_norm: 1.0636 (1.0967) time: 0.5077 [2021-03-25 18:01:35 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 220/1251] eta: 0:09:01 lr: 0.000832 loss: 3.6470 (3.5568) grad_norm: 1.0463 (1.0950) time: 0.5048 [2021-03-25 18:01:40 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 230/1251] eta: 0:08:55 lr: 0.000832 loss: 3.6448 (3.5472) grad_norm: 1.0128 (1.0934) time: 0.5121 [2021-03-25 18:01:45 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 240/1251] eta: 0:08:50 lr: 0.000832 loss: 3.6448 (3.5559) grad_norm: 1.0463 (1.0917) time: 0.5166 [2021-03-25 18:01:50 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 250/1251] eta: 0:08:44 lr: 0.000832 loss: 3.5823 (3.5502) grad_norm: 1.0889 (1.0956) time: 0.5136 [2021-03-25 18:01:55 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 260/1251] eta: 0:08:38 lr: 0.000832 loss: 3.4400 (3.5490) grad_norm: 1.1200 (1.0960) time: 0.5080 [2021-03-25 18:02:00 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 270/1251] eta: 0:08:32 lr: 0.000832 loss: 3.7044 (3.5563) grad_norm: 1.0409 (1.0950) time: 0.5089 [2021-03-25 18:02:05 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 280/1251] eta: 0:08:27 lr: 0.000831 loss: 3.7044 (3.5522) grad_norm: 1.0377 (1.0926) time: 0.5080 [2021-03-25 18:02:10 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 290/1251] eta: 0:08:21 lr: 0.000831 loss: 3.3199 (3.5463) grad_norm: 1.0281 (1.0910) time: 0.5064 [2021-03-25 18:02:15 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 300/1251] eta: 0:08:15 lr: 0.000831 loss: 3.6464 (3.5523) grad_norm: 1.0709 (1.0910) time: 0.5015 [2021-03-25 18:02:20 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 310/1251] eta: 0:08:09 lr: 0.000831 loss: 3.7271 (3.5542) grad_norm: 1.0807 (1.0915) time: 0.5009 [2021-03-25 18:02:25 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 320/1251] eta: 0:08:04 lr: 0.000831 loss: 3.6764 (3.5576) grad_norm: 1.0605 (1.0904) time: 0.5060 [2021-03-25 18:02:31 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 330/1251] eta: 0:07:58 lr: 0.000831 loss: 3.5258 (3.5550) grad_norm: 1.0581 (1.0919) time: 0.5121 [2021-03-25 18:02:36 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 340/1251] eta: 0:07:53 lr: 0.000831 loss: 3.5230 (3.5486) grad_norm: 1.0581 (1.0918) time: 0.5186 [2021-03-25 18:02:41 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 350/1251] eta: 0:07:47 lr: 0.000831 loss: 3.7717 (3.5502) grad_norm: 1.0432 (1.0919) time: 0.5104 [2021-03-25 18:02:46 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 360/1251] eta: 0:07:42 lr: 0.000831 loss: 3.7887 (3.5561) grad_norm: 1.0432 (1.0905) time: 0.5029 [2021-03-25 18:02:51 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 370/1251] eta: 0:07:36 lr: 0.000831 loss: 3.7376 (3.5555) grad_norm: 1.0131 (1.0893) time: 0.5037 [2021-03-25 18:02:56 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 380/1251] eta: 0:07:31 lr: 0.000831 loss: 3.6189 (3.5524) grad_norm: 1.0131 (1.0877) time: 0.5064 [2021-03-25 18:03:01 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 390/1251] eta: 0:07:25 lr: 0.000831 loss: 3.6369 (3.5560) grad_norm: 1.0340 (1.0875) time: 0.5032 [2021-03-25 18:03:06 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 400/1251] eta: 0:07:20 lr: 0.000831 loss: 3.8399 (3.5634) grad_norm: 1.0965 (1.0877) time: 0.4989 [2021-03-25 18:03:11 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 410/1251] eta: 0:07:14 lr: 0.000831 loss: 3.7439 (3.5556) grad_norm: 1.1015 (1.0887) time: 0.5038 [2021-03-25 18:03:16 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 420/1251] eta: 0:07:09 lr: 0.000831 loss: 3.7439 (3.5634) grad_norm: 1.0500 (1.0877) time: 0.5020 [2021-03-25 18:03:21 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 430/1251] eta: 0:07:04 lr: 0.000831 loss: 3.6295 (3.5626) grad_norm: 1.0500 (1.0877) time: 0.5061 [2021-03-25 18:03:26 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 440/1251] eta: 0:06:58 lr: 0.000831 loss: 3.5859 (3.5636) grad_norm: 1.0818 (1.0892) time: 0.5116 [2021-03-25 18:03:31 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 450/1251] eta: 0:06:53 lr: 0.000831 loss: 3.6135 (3.5647) grad_norm: 1.0805 (1.0898) time: 0.5031 [2021-03-25 18:03:36 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 460/1251] eta: 0:06:47 lr: 0.000831 loss: 3.7783 (3.5688) grad_norm: 1.0805 (1.0896) time: 0.5010 [2021-03-25 18:03:41 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 470/1251] eta: 0:06:42 lr: 0.000831 loss: 3.8599 (3.5729) grad_norm: 1.1248 (1.0920) time: 0.5024 [2021-03-25 18:03:46 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 480/1251] eta: 0:06:37 lr: 0.000831 loss: 3.7965 (3.5706) grad_norm: 1.1567 (1.0945) time: 0.5036 [2021-03-25 18:03:51 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 490/1251] eta: 0:06:31 lr: 0.000831 loss: 3.5608 (3.5714) grad_norm: 1.1602 (1.0965) time: 0.5050 [2021-03-25 18:03:56 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 500/1251] eta: 0:06:26 lr: 0.000831 loss: 3.8005 (3.5751) grad_norm: 1.1075 (1.0959) time: 0.5029 [2021-03-25 18:04:02 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 510/1251] eta: 0:06:21 lr: 0.000831 loss: 3.4332 (3.5692) grad_norm: 1.0735 (1.0960) time: 0.5031 [2021-03-25 18:04:07 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 520/1251] eta: 0:06:15 lr: 0.000831 loss: 3.2072 (3.5666) grad_norm: 1.0613 (1.0961) time: 0.5018 [2021-03-25 18:04:12 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 530/1251] eta: 0:06:10 lr: 0.000831 loss: 3.5422 (3.5668) grad_norm: 1.1181 (1.0987) time: 0.5052 [2021-03-25 18:04:17 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 540/1251] eta: 0:06:05 lr: 0.000831 loss: 3.5211 (3.5650) grad_norm: 1.1203 (1.0992) time: 0.5125 [2021-03-25 18:04:22 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 550/1251] eta: 0:06:00 lr: 0.000831 loss: 3.7257 (3.5672) grad_norm: 1.0660 (1.0979) time: 0.5224 [2021-03-25 18:04:27 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 560/1251] eta: 0:05:55 lr: 0.000831 loss: 3.7923 (3.5676) grad_norm: 1.0216 (1.0968) time: 0.5157 [2021-03-25 18:04:32 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 570/1251] eta: 0:05:49 lr: 0.000831 loss: 3.7674 (3.5685) grad_norm: 1.0441 (1.0965) time: 0.4970 [2021-03-25 18:04:37 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 580/1251] eta: 0:05:44 lr: 0.000831 loss: 3.7047 (3.5708) grad_norm: 1.0649 (1.0955) time: 0.4967 [2021-03-25 18:04:42 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 590/1251] eta: 0:05:39 lr: 0.000831 loss: 3.6081 (3.5685) grad_norm: 0.9959 (1.0945) time: 0.5082 [2021-03-25 18:04:47 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 600/1251] eta: 0:05:34 lr: 0.000830 loss: 3.6081 (3.5699) grad_norm: 1.0103 (1.0941) time: 0.5108 [2021-03-25 18:04:52 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 610/1251] eta: 0:05:29 lr: 0.000830 loss: 3.6884 (3.5713) grad_norm: 1.0756 (1.0936) time: 0.5127 [2021-03-25 18:04:57 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 620/1251] eta: 0:05:23 lr: 0.000830 loss: 3.7173 (3.5725) grad_norm: 1.0515 (1.0933) time: 0.5065 [2021-03-25 18:05:02 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 630/1251] eta: 0:05:18 lr: 0.000830 loss: 3.9206 (3.5756) grad_norm: 1.0673 (1.0948) time: 0.5005 [2021-03-25 18:05:07 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 640/1251] eta: 0:05:13 lr: 0.000830 loss: 3.8886 (3.5795) grad_norm: 1.0899 (1.0951) time: 0.5055 [2021-03-25 18:05:13 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 650/1251] eta: 0:05:08 lr: 0.000830 loss: 3.6353 (3.5788) grad_norm: 1.0492 (1.0944) time: 0.5046 [2021-03-25 18:05:18 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 660/1251] eta: 0:05:03 lr: 0.000830 loss: 3.6353 (3.5819) grad_norm: 1.0768 (1.0943) time: 0.5029 [2021-03-25 18:05:23 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 670/1251] eta: 0:04:57 lr: 0.000830 loss: 3.8243 (3.5824) grad_norm: 1.0579 (1.0936) time: 0.5007 [2021-03-25 18:05:28 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 680/1251] eta: 0:04:52 lr: 0.000830 loss: 3.8243 (3.5863) grad_norm: 1.0561 (1.0942) time: 0.5038 [2021-03-25 18:05:33 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 690/1251] eta: 0:04:47 lr: 0.000830 loss: 3.5072 (3.5827) grad_norm: 1.0561 (1.0943) time: 0.5105 [2021-03-25 18:05:38 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 700/1251] eta: 0:04:42 lr: 0.000830 loss: 3.4512 (3.5820) grad_norm: 1.0853 (1.0943) time: 0.5169 [2021-03-25 18:05:43 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 710/1251] eta: 0:04:37 lr: 0.000830 loss: 3.5948 (3.5802) grad_norm: 1.1123 (1.0946) time: 0.5133 [2021-03-25 18:05:48 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 720/1251] eta: 0:04:32 lr: 0.000830 loss: 3.4817 (3.5781) grad_norm: 1.1136 (1.0951) time: 0.5098 [2021-03-25 18:05:53 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 730/1251] eta: 0:04:27 lr: 0.000830 loss: 3.5046 (3.5787) grad_norm: 1.1039 (1.0952) time: 0.5140 [2021-03-25 18:05:59 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 740/1251] eta: 0:04:22 lr: 0.000830 loss: 3.5020 (3.5772) grad_norm: 1.0790 (1.0945) time: 0.5190 [2021-03-25 18:06:04 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 750/1251] eta: 0:04:17 lr: 0.000830 loss: 3.4435 (3.5756) grad_norm: 1.0412 (1.0942) time: 0.5302 [2021-03-25 18:06:09 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 760/1251] eta: 0:04:11 lr: 0.000830 loss: 3.5954 (3.5762) grad_norm: 1.0543 (1.0941) time: 0.5222 [2021-03-25 18:06:14 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 770/1251] eta: 0:04:06 lr: 0.000830 loss: 3.5954 (3.5734) grad_norm: 1.0742 (1.0937) time: 0.5078 [2021-03-25 18:06:19 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 780/1251] eta: 0:04:01 lr: 0.000830 loss: 3.2065 (3.5686) grad_norm: 1.1135 (1.0952) time: 0.5104 [2021-03-25 18:06:24 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 790/1251] eta: 0:03:56 lr: 0.000830 loss: 3.3604 (3.5691) grad_norm: 1.2179 (1.0969) time: 0.5100 [2021-03-25 18:06:29 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 800/1251] eta: 0:03:51 lr: 0.000830 loss: 3.5764 (3.5702) grad_norm: 1.1536 (1.0969) time: 0.5070 [2021-03-25 18:06:34 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 810/1251] eta: 0:03:46 lr: 0.000830 loss: 3.8056 (3.5727) grad_norm: 1.0701 (1.0967) time: 0.5080 [2021-03-25 18:06:40 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 820/1251] eta: 0:03:40 lr: 0.000830 loss: 3.8665 (3.5755) grad_norm: 1.0914 (1.0972) time: 0.5084 [2021-03-25 18:06:45 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 830/1251] eta: 0:03:35 lr: 0.000830 loss: 3.7243 (3.5762) grad_norm: 1.0938 (1.0973) time: 0.5037 [2021-03-25 18:06:50 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 840/1251] eta: 0:03:30 lr: 0.000830 loss: 3.7919 (3.5775) grad_norm: 1.0442 (1.0965) time: 0.5038 [2021-03-25 18:06:55 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 850/1251] eta: 0:03:25 lr: 0.000830 loss: 3.7972 (3.5779) grad_norm: 1.0410 (1.0963) time: 0.5041 [2021-03-25 18:07:00 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 860/1251] eta: 0:03:20 lr: 0.000830 loss: 3.8269 (3.5776) grad_norm: 1.0610 (1.0960) time: 0.5030 [2021-03-25 18:07:05 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 870/1251] eta: 0:03:15 lr: 0.000830 loss: 3.7420 (3.5783) grad_norm: 1.0478 (1.0952) time: 0.5046 [2021-03-25 18:07:10 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 880/1251] eta: 0:03:10 lr: 0.000830 loss: 3.4871 (3.5760) grad_norm: 1.0240 (1.0951) time: 0.5082 [2021-03-25 18:07:15 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 890/1251] eta: 0:03:04 lr: 0.000830 loss: 3.7013 (3.5774) grad_norm: 1.1302 (1.0965) time: 0.5065 [2021-03-25 18:07:20 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 900/1251] eta: 0:02:59 lr: 0.000830 loss: 3.8069 (3.5791) grad_norm: 1.1283 (1.0963) time: 0.5026 [2021-03-25 18:07:25 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 910/1251] eta: 0:02:54 lr: 0.000830 loss: 3.4863 (3.5759) grad_norm: 1.0398 (1.0962) time: 0.5043 [2021-03-25 18:07:30 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 920/1251] eta: 0:02:49 lr: 0.000829 loss: 3.3760 (3.5742) grad_norm: 1.0398 (1.0961) time: 0.5030 [2021-03-25 18:07:35 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 930/1251] eta: 0:02:44 lr: 0.000829 loss: 3.4807 (3.5739) grad_norm: 1.1011 (1.0964) time: 0.5008 [2021-03-25 18:07:40 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 940/1251] eta: 0:02:39 lr: 0.000829 loss: 3.4903 (3.5729) grad_norm: 1.1677 (1.0978) time: 0.5080 [2021-03-25 18:07:45 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 950/1251] eta: 0:02:33 lr: 0.000829 loss: 3.5187 (3.5753) grad_norm: 1.2090 (1.0988) time: 0.5057 [2021-03-25 18:07:50 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 960/1251] eta: 0:02:28 lr: 0.000829 loss: 3.6802 (3.5749) grad_norm: 1.1446 (1.0986) time: 0.5004 [2021-03-25 18:07:55 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 970/1251] eta: 0:02:23 lr: 0.000829 loss: 3.7772 (3.5760) grad_norm: 1.0657 (1.0987) time: 0.5037 [2021-03-25 18:08:00 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 980/1251] eta: 0:02:18 lr: 0.000829 loss: 3.6865 (3.5744) grad_norm: 1.1269 (1.0994) time: 0.5102 [2021-03-25 18:08:05 swin_small_patch4_window7_224] INFO: Epoch: [81] [ 990/1251] eta: 0:02:13 lr: 0.000829 loss: 3.5748 (3.5744) grad_norm: 1.0385 (1.0992) time: 0.5141 [2021-03-25 18:08:10 swin_small_patch4_window7_224] INFO: Epoch: [81] [1000/1251] eta: 0:02:08 lr: 0.000829 loss: 3.6348 (3.5741) grad_norm: 1.0505 (1.0994) time: 0.5067 [2021-03-25 18:08:15 swin_small_patch4_window7_224] INFO: Epoch: [81] [1010/1251] eta: 0:02:03 lr: 0.000829 loss: 3.6296 (3.5756) grad_norm: 1.1369 (1.0997) time: 0.5015 [2021-03-25 18:08:21 swin_small_patch4_window7_224] INFO: Epoch: [81] [1020/1251] eta: 0:01:58 lr: 0.000829 loss: 3.6068 (3.5757) grad_norm: 1.0633 (1.0994) time: 0.5016 [2021-03-25 18:08:26 swin_small_patch4_window7_224] INFO: Epoch: [81] [1030/1251] eta: 0:01:52 lr: 0.000829 loss: 3.6027 (3.5768) grad_norm: 1.0300 (1.0996) time: 0.5049 [2021-03-25 18:08:31 swin_small_patch4_window7_224] INFO: Epoch: [81] [1040/1251] eta: 0:01:47 lr: 0.000829 loss: 3.6027 (3.5746) grad_norm: 1.1015 (1.0995) time: 0.5067 [2021-03-25 18:08:36 swin_small_patch4_window7_224] INFO: Epoch: [81] [1050/1251] eta: 0:01:42 lr: 0.000829 loss: 3.6029 (3.5750) grad_norm: 1.0778 (1.0994) time: 0.5065 [2021-03-25 18:08:41 swin_small_patch4_window7_224] INFO: Epoch: [81] [1060/1251] eta: 0:01:37 lr: 0.000829 loss: 3.6470 (3.5735) grad_norm: 1.1110 (1.0996) time: 0.5036 [2021-03-25 18:08:46 swin_small_patch4_window7_224] INFO: Epoch: [81] [1070/1251] eta: 0:01:32 lr: 0.000829 loss: 3.2186 (3.5684) grad_norm: 1.1162 (1.1004) time: 0.5035 [2021-03-25 18:08:51 swin_small_patch4_window7_224] INFO: Epoch: [81] [1080/1251] eta: 0:01:27 lr: 0.000829 loss: 3.2563 (3.5701) grad_norm: 1.0995 (1.1003) time: 0.5106 [2021-03-25 18:08:56 swin_small_patch4_window7_224] INFO: Epoch: [81] [1090/1251] eta: 0:01:22 lr: 0.000829 loss: 3.8701 (3.5700) grad_norm: 1.1104 (1.1007) time: 0.5170 [2021-03-25 18:09:01 swin_small_patch4_window7_224] INFO: Epoch: [81] [1100/1251] eta: 0:01:17 lr: 0.000829 loss: 3.5864 (3.5689) grad_norm: 1.1104 (1.1007) time: 0.5121 [2021-03-25 18:09:06 swin_small_patch4_window7_224] INFO: Epoch: [81] [1110/1251] eta: 0:01:12 lr: 0.000829 loss: 3.4555 (3.5668) grad_norm: 1.0714 (1.1005) time: 0.5063 [2021-03-25 18:09:11 swin_small_patch4_window7_224] INFO: Epoch: [81] [1120/1251] eta: 0:01:06 lr: 0.000829 loss: 3.5467 (3.5655) grad_norm: 1.0582 (1.1009) time: 0.5082 [2021-03-25 18:09:16 swin_small_patch4_window7_224] INFO: Epoch: [81] [1130/1251] eta: 0:01:01 lr: 0.000829 loss: 3.6162 (3.5646) grad_norm: 1.0592 (1.1009) time: 0.5059 [2021-03-25 18:09:21 swin_small_patch4_window7_224] INFO: Epoch: [81] [1140/1251] eta: 0:00:56 lr: 0.000829 loss: 3.2996 (3.5623) grad_norm: 1.0416 (1.1005) time: 0.5027 [2021-03-25 18:09:27 swin_small_patch4_window7_224] INFO: Epoch: [81] [1150/1251] eta: 0:00:51 lr: 0.000829 loss: 3.5269 (3.5635) grad_norm: 1.0057 (1.1000) time: 0.5065 [2021-03-25 18:09:32 swin_small_patch4_window7_224] INFO: Epoch: [81] [1160/1251] eta: 0:00:46 lr: 0.000829 loss: 3.5996 (3.5635) grad_norm: 1.0125 (1.0995) time: 0.5056 [2021-03-25 18:09:37 swin_small_patch4_window7_224] INFO: Epoch: [81] [1170/1251] eta: 0:00:41 lr: 0.000829 loss: 3.6049 (3.5650) grad_norm: 1.0351 (1.0990) time: 0.4997 [2021-03-25 18:09:42 swin_small_patch4_window7_224] INFO: Epoch: [81] [1180/1251] eta: 0:00:36 lr: 0.000829 loss: 3.7066 (3.5663) grad_norm: 1.0893 (1.0996) time: 0.5097 [2021-03-25 18:09:47 swin_small_patch4_window7_224] INFO: Epoch: [81] [1190/1251] eta: 0:00:31 lr: 0.000829 loss: 3.6889 (3.5672) grad_norm: 1.1118 (1.0997) time: 0.5134 [2021-03-25 18:09:52 swin_small_patch4_window7_224] INFO: Epoch: [81] [1200/1251] eta: 0:00:26 lr: 0.000829 loss: 3.6889 (3.5677) grad_norm: 1.0966 (1.0998) time: 0.5056 [2021-03-25 18:09:57 swin_small_patch4_window7_224] INFO: Epoch: [81] [1210/1251] eta: 0:00:20 lr: 0.000829 loss: 3.5575 (3.5664) grad_norm: 1.1136 (1.1004) time: 0.4991 [2021-03-25 18:10:02 swin_small_patch4_window7_224] INFO: Epoch: [81] [1220/1251] eta: 0:00:15 lr: 0.000829 loss: 3.6799 (3.5679) grad_norm: 1.1253 (1.1005) time: 0.4992 [2021-03-25 18:10:07 swin_small_patch4_window7_224] INFO: Epoch: [81] [1230/1251] eta: 0:00:10 lr: 0.000829 loss: 3.8280 (3.5692) grad_norm: 1.1178 (1.1005) time: 0.5065 [2021-03-25 18:10:12 swin_small_patch4_window7_224] INFO: Epoch: [81] [1240/1251] eta: 0:00:05 lr: 0.000828 loss: 3.6600 (3.5687) grad_norm: 1.0846 (1.1004) time: 0.5039 [2021-03-25 18:10:17 swin_small_patch4_window7_224] INFO: Epoch: [81] [1250/1251] eta: 0:00:00 lr: 0.000828 loss: 3.7568 (3.5713) grad_norm: 1.0358 (1.1000) time: 0.5047 [2021-03-25 18:10:22 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 0.9753 (0.9753) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-25 18:10:24 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1118 (1.0986) acc1: 76.5625 (75.5682) acc5: 92.1875 (92.3295) [2021-03-25 18:10:26 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0672 (1.1080) acc1: 75.0000 (75.1488) acc5: 92.1875 (92.0387) [2021-03-25 18:10:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 1.0672 (1.0914) acc1: 73.4375 (74.7480) acc5: 92.1875 (92.3387) [2021-03-25 18:10:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0864 (1.0718) acc1: 73.4375 (74.6951) acc5: 93.7500 (92.9497) [2021-03-25 18:10:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0951 (1.0799) acc1: 73.4375 (74.2400) acc5: 93.7500 (92.8320) [2021-03-25 18:10:34 swin_small_patch4_window7_224] INFO: * Acc@1 75.120 Acc@5 92.972 loss 1.055 [2021-03-25 18:10:34 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.1% [2021-03-25 18:10:34 swin_small_patch4_window7_224] INFO: Max accuracy: 75.23% [2021-03-25 18:10:39 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 0/1251] eta: 1:32:03 lr: 0.000828 loss: 2.3395 (2.3395) grad_norm: 1.1824 (1.1824) time: 4.4157 [2021-03-25 18:10:44 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 10/1251] eta: 0:17:50 lr: 0.000828 loss: 3.6981 (3.5362) grad_norm: 1.0530 (1.0450) time: 0.8625 [2021-03-25 18:10:49 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 20/1251] eta: 0:14:12 lr: 0.000828 loss: 3.5817 (3.4875) grad_norm: 1.0339 (1.0652) time: 0.5061 [2021-03-25 18:10:54 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 30/1251] eta: 0:12:55 lr: 0.000828 loss: 3.3930 (3.4723) grad_norm: 1.1248 (1.0993) time: 0.5098 [2021-03-25 18:10:59 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 40/1251] eta: 0:12:10 lr: 0.000828 loss: 3.8272 (3.5395) grad_norm: 1.1382 (1.0961) time: 0.5101 [2021-03-25 18:11:04 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 50/1251] eta: 0:11:43 lr: 0.000828 loss: 3.8343 (3.5655) grad_norm: 1.1264 (1.1026) time: 0.5096 [2021-03-25 18:11:09 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 60/1251] eta: 0:11:24 lr: 0.000828 loss: 3.5945 (3.5362) grad_norm: 1.0719 (1.0979) time: 0.5164 [2021-03-25 18:11:14 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 70/1251] eta: 0:11:07 lr: 0.000828 loss: 3.5947 (3.5544) grad_norm: 1.0666 (1.0966) time: 0.5130 [2021-03-25 18:11:19 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 80/1251] eta: 0:10:53 lr: 0.000828 loss: 3.4226 (3.5165) grad_norm: 1.0754 (1.0956) time: 0.5053 [2021-03-25 18:11:25 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 90/1251] eta: 0:10:40 lr: 0.000828 loss: 3.3954 (3.5349) grad_norm: 1.0961 (1.1110) time: 0.5051 [2021-03-25 18:11:30 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 100/1251] eta: 0:10:29 lr: 0.000828 loss: 3.5334 (3.5305) grad_norm: 1.1415 (1.1125) time: 0.5021 [2021-03-25 18:11:34 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 110/1251] eta: 0:10:18 lr: 0.000828 loss: 3.6532 (3.5480) grad_norm: 1.1415 (1.1156) time: 0.4978 [2021-03-25 18:11:40 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 120/1251] eta: 0:10:10 lr: 0.000828 loss: 3.6829 (3.5432) grad_norm: 1.0965 (1.1109) time: 0.5041 [2021-03-25 18:11:45 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 130/1251] eta: 0:10:04 lr: 0.000828 loss: 3.5986 (3.5453) grad_norm: 1.0704 (1.1105) time: 0.5211 [2021-03-25 18:11:50 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 140/1251] eta: 0:09:56 lr: 0.000828 loss: 3.4981 (3.5516) grad_norm: 1.0771 (1.1111) time: 0.5184 [2021-03-25 18:11:55 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 150/1251] eta: 0:09:48 lr: 0.000828 loss: 3.5801 (3.5567) grad_norm: 1.1003 (1.1108) time: 0.5052 [2021-03-25 18:12:00 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 160/1251] eta: 0:09:41 lr: 0.000828 loss: 3.9057 (3.5715) grad_norm: 1.0869 (1.1092) time: 0.5063 [2021-03-25 18:12:05 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 170/1251] eta: 0:09:35 lr: 0.000828 loss: 3.6435 (3.5570) grad_norm: 1.0118 (1.1013) time: 0.5153 [2021-03-25 18:12:10 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 180/1251] eta: 0:09:28 lr: 0.000828 loss: 3.5800 (3.5614) grad_norm: 1.0184 (1.0981) time: 0.5164 [2021-03-25 18:12:16 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 190/1251] eta: 0:09:22 lr: 0.000828 loss: 3.6596 (3.5702) grad_norm: 1.0232 (1.0969) time: 0.5093 [2021-03-25 18:12:21 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 200/1251] eta: 0:09:15 lr: 0.000828 loss: 3.5991 (3.5668) grad_norm: 1.0643 (1.0977) time: 0.5065 [2021-03-25 18:12:26 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 210/1251] eta: 0:09:09 lr: 0.000828 loss: 3.4249 (3.5597) grad_norm: 1.0744 (1.0990) time: 0.5041 [2021-03-25 18:12:31 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 220/1251] eta: 0:09:02 lr: 0.000828 loss: 3.3921 (3.5483) grad_norm: 1.1084 (1.1020) time: 0.5010 [2021-03-25 18:12:36 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 230/1251] eta: 0:08:56 lr: 0.000828 loss: 3.3921 (3.5537) grad_norm: 1.1497 (1.1050) time: 0.4996 [2021-03-25 18:12:41 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 240/1251] eta: 0:08:49 lr: 0.000828 loss: 3.7095 (3.5555) grad_norm: 1.1473 (1.1056) time: 0.4990 [2021-03-25 18:12:46 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 250/1251] eta: 0:08:43 lr: 0.000828 loss: 3.6489 (3.5546) grad_norm: 1.0695 (1.1049) time: 0.5005 [2021-03-25 18:12:51 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 260/1251] eta: 0:08:37 lr: 0.000828 loss: 3.8402 (3.5656) grad_norm: 1.0343 (1.1057) time: 0.5065 [2021-03-25 18:12:56 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 270/1251] eta: 0:08:31 lr: 0.000828 loss: 3.8402 (3.5652) grad_norm: 1.0165 (1.1036) time: 0.5053 [2021-03-25 18:13:01 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 280/1251] eta: 0:08:26 lr: 0.000828 loss: 3.5538 (3.5622) grad_norm: 1.0623 (1.1051) time: 0.5059 [2021-03-25 18:13:06 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 290/1251] eta: 0:08:20 lr: 0.000828 loss: 3.6275 (3.5685) grad_norm: 1.0931 (1.1053) time: 0.5070 [2021-03-25 18:13:11 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 300/1251] eta: 0:08:14 lr: 0.000828 loss: 3.6073 (3.5599) grad_norm: 1.1486 (1.1078) time: 0.5043 [2021-03-25 18:13:16 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 310/1251] eta: 0:08:08 lr: 0.000827 loss: 3.6050 (3.5604) grad_norm: 1.1069 (1.1071) time: 0.4986 [2021-03-25 18:13:21 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 320/1251] eta: 0:08:03 lr: 0.000827 loss: 3.4515 (3.5511) grad_norm: 1.0707 (1.1066) time: 0.5017 [2021-03-25 18:13:26 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 330/1251] eta: 0:07:57 lr: 0.000827 loss: 3.6027 (3.5539) grad_norm: 1.0707 (1.1067) time: 0.5042 [2021-03-25 18:13:31 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 340/1251] eta: 0:07:51 lr: 0.000827 loss: 3.7986 (3.5608) grad_norm: 1.0756 (1.1061) time: 0.5004 [2021-03-25 18:13:36 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 350/1251] eta: 0:07:46 lr: 0.000827 loss: 3.7234 (3.5599) grad_norm: 1.0686 (1.1046) time: 0.5001 [2021-03-25 18:13:41 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 360/1251] eta: 0:07:40 lr: 0.000827 loss: 3.7234 (3.5680) grad_norm: 1.0894 (1.1041) time: 0.5002 [2021-03-25 18:13:46 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 370/1251] eta: 0:07:35 lr: 0.000827 loss: 3.5758 (3.5658) grad_norm: 1.1220 (1.1079) time: 0.5071 [2021-03-25 18:13:51 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 380/1251] eta: 0:07:29 lr: 0.000827 loss: 3.4527 (3.5614) grad_norm: 1.1220 (1.1067) time: 0.5088 [2021-03-25 18:13:56 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 390/1251] eta: 0:07:24 lr: 0.000827 loss: 3.5469 (3.5611) grad_norm: 1.0757 (1.1066) time: 0.5044 [2021-03-25 18:14:01 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 400/1251] eta: 0:07:18 lr: 0.000827 loss: 3.6163 (3.5620) grad_norm: 1.0757 (1.1071) time: 0.5011 [2021-03-25 18:14:06 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 410/1251] eta: 0:07:13 lr: 0.000827 loss: 3.8489 (3.5657) grad_norm: 1.0812 (1.1074) time: 0.5048 [2021-03-25 18:14:11 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 420/1251] eta: 0:07:08 lr: 0.000827 loss: 3.7315 (3.5642) grad_norm: 1.0812 (1.1077) time: 0.5077 [2021-03-25 18:14:16 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 430/1251] eta: 0:07:02 lr: 0.000827 loss: 3.6395 (3.5614) grad_norm: 1.1098 (1.1084) time: 0.5027 [2021-03-25 18:14:21 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 440/1251] eta: 0:06:57 lr: 0.000827 loss: 3.5624 (3.5595) grad_norm: 1.1434 (1.1088) time: 0.4959 [2021-03-25 18:14:26 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 450/1251] eta: 0:06:51 lr: 0.000827 loss: 3.5919 (3.5609) grad_norm: 1.0688 (1.1086) time: 0.4983 [2021-03-25 18:14:31 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 460/1251] eta: 0:06:46 lr: 0.000827 loss: 3.7672 (3.5609) grad_norm: 1.0726 (1.1087) time: 0.5018 [2021-03-25 18:14:36 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 470/1251] eta: 0:06:41 lr: 0.000827 loss: 3.6185 (3.5578) grad_norm: 1.0726 (1.1082) time: 0.5049 [2021-03-25 18:14:41 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 480/1251] eta: 0:06:36 lr: 0.000827 loss: 3.5024 (3.5546) grad_norm: 1.0536 (1.1076) time: 0.5092 [2021-03-25 18:14:47 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 490/1251] eta: 0:06:30 lr: 0.000827 loss: 3.5369 (3.5573) grad_norm: 1.0655 (1.1083) time: 0.5072 [2021-03-25 18:14:52 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 500/1251] eta: 0:06:25 lr: 0.000827 loss: 3.6257 (3.5556) grad_norm: 1.0904 (1.1084) time: 0.5067 [2021-03-25 18:14:57 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 510/1251] eta: 0:06:20 lr: 0.000827 loss: 3.6257 (3.5533) grad_norm: 1.0761 (inf) time: 0.5046 [2021-03-25 18:15:02 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 520/1251] eta: 0:06:15 lr: 0.000827 loss: 3.6002 (3.5520) grad_norm: 1.0694 (inf) time: 0.5038 [2021-03-25 18:15:07 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 530/1251] eta: 0:06:09 lr: 0.000827 loss: 3.5799 (3.5548) grad_norm: 0.9962 (inf) time: 0.5038 [2021-03-25 18:15:12 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 540/1251] eta: 0:06:04 lr: 0.000827 loss: 3.7668 (3.5553) grad_norm: 1.0109 (inf) time: 0.5087 [2021-03-25 18:15:17 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 550/1251] eta: 0:05:59 lr: 0.000827 loss: 3.7668 (3.5572) grad_norm: 1.1018 (inf) time: 0.5196 [2021-03-25 18:15:22 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 560/1251] eta: 0:05:54 lr: 0.000827 loss: 3.6517 (3.5545) grad_norm: 1.0721 (inf) time: 0.5170 [2021-03-25 18:15:27 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 570/1251] eta: 0:05:49 lr: 0.000827 loss: 3.3768 (3.5535) grad_norm: 1.0480 (inf) time: 0.5097 [2021-03-25 18:15:32 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 580/1251] eta: 0:05:44 lr: 0.000827 loss: 3.8248 (3.5565) grad_norm: 1.0047 (inf) time: 0.5112 [2021-03-25 18:15:38 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 590/1251] eta: 0:05:39 lr: 0.000827 loss: 3.6094 (3.5529) grad_norm: 1.0395 (inf) time: 0.5156 [2021-03-25 18:15:43 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 600/1251] eta: 0:05:33 lr: 0.000827 loss: 3.3338 (3.5487) grad_norm: 1.1391 (inf) time: 0.5098 [2021-03-25 18:15:48 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 610/1251] eta: 0:05:28 lr: 0.000827 loss: 3.7503 (3.5531) grad_norm: 1.0814 (inf) time: 0.5018 [2021-03-25 18:15:53 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 620/1251] eta: 0:05:23 lr: 0.000826 loss: 3.8575 (3.5547) grad_norm: 1.0821 (inf) time: 0.5105 [2021-03-25 18:15:58 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 630/1251] eta: 0:05:18 lr: 0.000826 loss: 3.7949 (3.5577) grad_norm: 1.0868 (inf) time: 0.5118 [2021-03-25 18:16:03 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 640/1251] eta: 0:05:13 lr: 0.000826 loss: 3.6350 (3.5564) grad_norm: 1.0868 (inf) time: 0.5030 [2021-03-25 18:16:08 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 650/1251] eta: 0:05:07 lr: 0.000826 loss: 3.5981 (3.5586) grad_norm: 1.0629 (inf) time: 0.5016 [2021-03-25 18:16:13 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 660/1251] eta: 0:05:02 lr: 0.000826 loss: 3.6292 (3.5604) grad_norm: 1.0589 (inf) time: 0.5027 [2021-03-25 18:16:18 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 670/1251] eta: 0:04:57 lr: 0.000826 loss: 3.4277 (3.5557) grad_norm: 1.0735 (inf) time: 0.5041 [2021-03-25 18:16:23 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 680/1251] eta: 0:04:52 lr: 0.000826 loss: 3.4277 (3.5550) grad_norm: 1.0724 (inf) time: 0.5100 [2021-03-25 18:16:28 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 690/1251] eta: 0:04:47 lr: 0.000826 loss: 3.5973 (3.5569) grad_norm: 1.0642 (inf) time: 0.5065 [2021-03-25 18:16:33 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 700/1251] eta: 0:04:42 lr: 0.000826 loss: 3.9223 (3.5602) grad_norm: 1.0642 (inf) time: 0.5048 [2021-03-25 18:16:38 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 710/1251] eta: 0:04:36 lr: 0.000826 loss: 3.9616 (3.5603) grad_norm: 1.0862 (inf) time: 0.5102 [2021-03-25 18:16:43 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 720/1251] eta: 0:04:31 lr: 0.000826 loss: 3.7959 (3.5602) grad_norm: 1.1753 (inf) time: 0.5108 [2021-03-25 18:16:49 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 730/1251] eta: 0:04:26 lr: 0.000826 loss: 3.6586 (3.5596) grad_norm: 1.1452 (inf) time: 0.5215 [2021-03-25 18:16:54 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 740/1251] eta: 0:04:21 lr: 0.000826 loss: 3.3976 (3.5598) grad_norm: 1.0627 (inf) time: 0.5260 [2021-03-25 18:16:59 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 750/1251] eta: 0:04:16 lr: 0.000826 loss: 3.6033 (3.5618) grad_norm: 1.1199 (inf) time: 0.5146 [2021-03-25 18:17:04 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 760/1251] eta: 0:04:11 lr: 0.000826 loss: 3.7130 (3.5618) grad_norm: 1.1610 (inf) time: 0.5061 [2021-03-25 18:17:09 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 770/1251] eta: 0:04:06 lr: 0.000826 loss: 3.3534 (3.5564) grad_norm: 1.0670 (inf) time: 0.5077 [2021-03-25 18:17:14 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 780/1251] eta: 0:04:01 lr: 0.000826 loss: 3.2425 (3.5561) grad_norm: 1.0341 (inf) time: 0.5106 [2021-03-25 18:17:19 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 790/1251] eta: 0:03:56 lr: 0.000826 loss: 3.7644 (3.5600) grad_norm: 1.0458 (inf) time: 0.5099 [2021-03-25 18:17:25 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 800/1251] eta: 0:03:50 lr: 0.000826 loss: 3.8012 (3.5601) grad_norm: 1.0933 (inf) time: 0.5080 [2021-03-25 18:17:30 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 810/1251] eta: 0:03:45 lr: 0.000826 loss: 3.7212 (3.5633) grad_norm: 1.1548 (inf) time: 0.5144 [2021-03-25 18:17:35 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 820/1251] eta: 0:03:40 lr: 0.000826 loss: 3.8616 (3.5663) grad_norm: 1.1254 (inf) time: 0.5105 [2021-03-25 18:17:40 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 830/1251] eta: 0:03:35 lr: 0.000826 loss: 3.8594 (3.5687) grad_norm: 1.1384 (inf) time: 0.5020 [2021-03-25 18:17:45 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 840/1251] eta: 0:03:30 lr: 0.000826 loss: 3.8594 (3.5717) grad_norm: 1.1520 (inf) time: 0.5063 [2021-03-25 18:17:50 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 850/1251] eta: 0:03:25 lr: 0.000826 loss: 3.7502 (3.5740) grad_norm: 1.1052 (inf) time: 0.5048 [2021-03-25 18:17:55 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 860/1251] eta: 0:03:20 lr: 0.000826 loss: 3.5687 (3.5709) grad_norm: 1.0580 (inf) time: 0.5044 [2021-03-25 18:18:00 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 870/1251] eta: 0:03:14 lr: 0.000826 loss: 3.3445 (3.5660) grad_norm: 1.0493 (inf) time: 0.5129 [2021-03-25 18:18:05 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 880/1251] eta: 0:03:09 lr: 0.000826 loss: 3.5070 (3.5667) grad_norm: 1.1393 (inf) time: 0.5160 [2021-03-25 18:18:10 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 890/1251] eta: 0:03:04 lr: 0.000826 loss: 3.6693 (3.5669) grad_norm: 1.1093 (inf) time: 0.5118 [2021-03-25 18:18:15 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 900/1251] eta: 0:02:59 lr: 0.000826 loss: 3.6679 (3.5672) grad_norm: 1.0602 (inf) time: 0.5088 [2021-03-25 18:18:21 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 910/1251] eta: 0:02:54 lr: 0.000826 loss: 3.5896 (3.5651) grad_norm: 1.1425 (inf) time: 0.5115 [2021-03-25 18:18:26 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 920/1251] eta: 0:02:49 lr: 0.000826 loss: 3.6183 (3.5662) grad_norm: 1.1631 (inf) time: 0.5156 [2021-03-25 18:18:31 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 930/1251] eta: 0:02:44 lr: 0.000826 loss: 3.7304 (3.5668) grad_norm: 1.1489 (inf) time: 0.5106 [2021-03-25 18:18:36 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 940/1251] eta: 0:02:39 lr: 0.000825 loss: 3.5561 (3.5667) grad_norm: 1.1184 (inf) time: 0.5075 [2021-03-25 18:18:41 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 950/1251] eta: 0:02:34 lr: 0.000825 loss: 3.5416 (3.5667) grad_norm: 1.0772 (inf) time: 0.5114 [2021-03-25 18:18:46 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 960/1251] eta: 0:02:28 lr: 0.000825 loss: 3.6675 (3.5678) grad_norm: 1.1644 (inf) time: 0.5044 [2021-03-25 18:18:51 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 970/1251] eta: 0:02:23 lr: 0.000825 loss: 3.5230 (3.5632) grad_norm: 1.0849 (inf) time: 0.4977 [2021-03-25 18:18:56 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 980/1251] eta: 0:02:18 lr: 0.000825 loss: 3.5372 (3.5662) grad_norm: 1.0322 (inf) time: 0.5025 [2021-03-25 18:19:01 swin_small_patch4_window7_224] INFO: Epoch: [82] [ 990/1251] eta: 0:02:13 lr: 0.000825 loss: 3.8400 (3.5684) grad_norm: 1.0864 (inf) time: 0.5046 [2021-03-25 18:19:06 swin_small_patch4_window7_224] INFO: Epoch: [82] [1000/1251] eta: 0:02:08 lr: 0.000825 loss: 3.7403 (3.5677) grad_norm: 1.1083 (inf) time: 0.4997 [2021-03-25 18:19:11 swin_small_patch4_window7_224] INFO: Epoch: [82] [1010/1251] eta: 0:02:03 lr: 0.000825 loss: 3.6059 (3.5661) grad_norm: 1.0887 (inf) time: 0.4990 [2021-03-25 18:19:16 swin_small_patch4_window7_224] INFO: Epoch: [82] [1020/1251] eta: 0:01:58 lr: 0.000825 loss: 3.6059 (3.5651) grad_norm: 1.0006 (inf) time: 0.5064 [2021-03-25 18:19:21 swin_small_patch4_window7_224] INFO: Epoch: [82] [1030/1251] eta: 0:01:52 lr: 0.000825 loss: 3.4358 (3.5636) grad_norm: 1.0479 (inf) time: 0.5072 [2021-03-25 18:19:26 swin_small_patch4_window7_224] INFO: Epoch: [82] [1040/1251] eta: 0:01:47 lr: 0.000825 loss: 3.7203 (3.5634) grad_norm: 1.1134 (inf) time: 0.5054 [2021-03-25 18:19:31 swin_small_patch4_window7_224] INFO: Epoch: [82] [1050/1251] eta: 0:01:42 lr: 0.000825 loss: 3.7203 (3.5631) grad_norm: 1.1126 (inf) time: 0.5089 [2021-03-25 18:19:36 swin_small_patch4_window7_224] INFO: Epoch: [82] [1060/1251] eta: 0:01:37 lr: 0.000825 loss: 3.5370 (3.5638) grad_norm: 1.1092 (inf) time: 0.5086 [2021-03-25 18:19:42 swin_small_patch4_window7_224] INFO: Epoch: [82] [1070/1251] eta: 0:01:32 lr: 0.000825 loss: 3.7064 (3.5644) grad_norm: 1.0560 (inf) time: 0.5095 [2021-03-25 18:19:47 swin_small_patch4_window7_224] INFO: Epoch: [82] [1080/1251] eta: 0:01:27 lr: 0.000825 loss: 3.6725 (3.5635) grad_norm: 1.0514 (inf) time: 0.5087 [2021-03-25 18:19:52 swin_small_patch4_window7_224] INFO: Epoch: [82] [1090/1251] eta: 0:01:22 lr: 0.000825 loss: 3.6680 (3.5641) grad_norm: 1.0237 (inf) time: 0.5075 [2021-03-25 18:19:57 swin_small_patch4_window7_224] INFO: Epoch: [82] [1100/1251] eta: 0:01:17 lr: 0.000825 loss: 3.7025 (3.5643) grad_norm: 1.0485 (inf) time: 0.5086 [2021-03-25 18:20:02 swin_small_patch4_window7_224] INFO: Epoch: [82] [1110/1251] eta: 0:01:12 lr: 0.000825 loss: 3.7569 (3.5643) grad_norm: 1.1195 (inf) time: 0.5118 [2021-03-25 18:20:07 swin_small_patch4_window7_224] INFO: Epoch: [82] [1120/1251] eta: 0:01:06 lr: 0.000825 loss: 3.7121 (3.5643) grad_norm: 1.1433 (inf) time: 0.5103 [2021-03-25 18:20:12 swin_small_patch4_window7_224] INFO: Epoch: [82] [1130/1251] eta: 0:01:01 lr: 0.000825 loss: 3.4141 (3.5634) grad_norm: 1.1264 (inf) time: 0.5099 [2021-03-25 18:20:17 swin_small_patch4_window7_224] INFO: Epoch: [82] [1140/1251] eta: 0:00:56 lr: 0.000825 loss: 3.4216 (3.5629) grad_norm: 1.1045 (inf) time: 0.5116 [2021-03-25 18:20:22 swin_small_patch4_window7_224] INFO: Epoch: [82] [1150/1251] eta: 0:00:51 lr: 0.000825 loss: 3.7124 (3.5638) grad_norm: 1.1000 (inf) time: 0.5033 [2021-03-25 18:20:27 swin_small_patch4_window7_224] INFO: Epoch: [82] [1160/1251] eta: 0:00:46 lr: 0.000825 loss: 3.7124 (3.5627) grad_norm: 1.0353 (inf) time: 0.4988 [2021-03-25 18:20:32 swin_small_patch4_window7_224] INFO: Epoch: [82] [1170/1251] eta: 0:00:41 lr: 0.000825 loss: 3.4154 (3.5615) grad_norm: 1.0353 (inf) time: 0.5044 [2021-03-25 18:20:37 swin_small_patch4_window7_224] INFO: Epoch: [82] [1180/1251] eta: 0:00:36 lr: 0.000825 loss: 3.4811 (3.5612) grad_norm: 1.0826 (inf) time: 0.5078 [2021-03-25 18:20:42 swin_small_patch4_window7_224] INFO: Epoch: [82] [1190/1251] eta: 0:00:31 lr: 0.000825 loss: 3.4811 (3.5602) grad_norm: 1.0417 (inf) time: 0.5043 [2021-03-25 18:20:47 swin_small_patch4_window7_224] INFO: Epoch: [82] [1200/1251] eta: 0:00:26 lr: 0.000825 loss: 3.7195 (3.5602) grad_norm: 1.0417 (inf) time: 0.5038 [2021-03-25 18:20:52 swin_small_patch4_window7_224] INFO: Epoch: [82] [1210/1251] eta: 0:00:20 lr: 0.000825 loss: 3.5423 (3.5606) grad_norm: 1.0532 (inf) time: 0.5016 [2021-03-25 18:20:58 swin_small_patch4_window7_224] INFO: Epoch: [82] [1220/1251] eta: 0:00:15 lr: 0.000825 loss: 3.4607 (3.5598) grad_norm: 1.0774 (inf) time: 0.5073 [2021-03-25 18:21:03 swin_small_patch4_window7_224] INFO: Epoch: [82] [1230/1251] eta: 0:00:10 lr: 0.000825 loss: 3.6613 (3.5604) grad_norm: 1.1270 (inf) time: 0.5135 [2021-03-25 18:21:08 swin_small_patch4_window7_224] INFO: Epoch: [82] [1240/1251] eta: 0:00:05 lr: 0.000825 loss: 3.7019 (3.5602) grad_norm: 1.1168 (inf) time: 0.5080 [2021-03-25 18:21:13 swin_small_patch4_window7_224] INFO: Epoch: [82] [1250/1251] eta: 0:00:00 lr: 0.000825 loss: 3.7557 (3.5600) grad_norm: 1.0965 (inf) time: 0.4995 [2021-03-25 18:21:21 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 1.5121 (1.5121) acc1: 64.0625 (64.0625) acc5: 90.6250 (90.6250) [2021-03-25 18:21:23 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0579 (1.1711) acc1: 71.8750 (72.4432) acc5: 92.1875 (91.7614) [2021-03-25 18:21:24 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9761 (1.1053) acc1: 73.4375 (73.5863) acc5: 93.7500 (92.6339) [2021-03-25 18:21:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0566 (1.1219) acc1: 73.4375 (73.4879) acc5: 92.1875 (92.1875) [2021-03-25 18:21:29 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0209 (1.0811) acc1: 73.4375 (74.1616) acc5: 92.1875 (92.8354) [2021-03-25 18:21:30 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0771 (1.0872) acc1: 73.4375 (74.1440) acc5: 92.1875 (92.6400) [2021-03-25 18:21:35 swin_small_patch4_window7_224] INFO: * Acc@1 74.890 Acc@5 92.934 loss 1.062 [2021-03-25 18:21:35 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 74.9% [2021-03-25 18:21:35 swin_small_patch4_window7_224] INFO: Max accuracy: 75.23% [2021-03-25 18:21:39 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 0/1251] eta: 1:36:55 lr: 0.000825 loss: 3.3351 (3.3351) grad_norm: 1.2839 (1.2839) time: 4.6488 [2021-03-25 18:21:45 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 10/1251] eta: 0:18:29 lr: 0.000824 loss: 3.2550 (3.4270) grad_norm: 1.0699 (1.1046) time: 0.8937 [2021-03-25 18:21:50 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 20/1251] eta: 0:14:27 lr: 0.000824 loss: 3.2907 (3.4699) grad_norm: 1.0699 (1.0991) time: 0.5076 [2021-03-25 18:21:55 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 30/1251] eta: 0:13:02 lr: 0.000824 loss: 3.6619 (3.4926) grad_norm: 1.0825 (1.1107) time: 0.5020 [2021-03-25 18:22:00 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 40/1251] eta: 0:12:17 lr: 0.000824 loss: 3.5873 (3.5265) grad_norm: 1.0751 (1.0931) time: 0.5079 [2021-03-25 18:22:05 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 50/1251] eta: 0:11:45 lr: 0.000824 loss: 3.7098 (3.5732) grad_norm: 1.0659 (1.1015) time: 0.5055 [2021-03-25 18:22:10 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 60/1251] eta: 0:11:25 lr: 0.000824 loss: 3.7019 (3.6165) grad_norm: 1.0703 (1.1022) time: 0.5063 [2021-03-25 18:22:15 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 70/1251] eta: 0:11:09 lr: 0.000824 loss: 3.5684 (3.5964) grad_norm: 1.0727 (1.1040) time: 0.5145 [2021-03-25 18:22:20 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 80/1251] eta: 0:10:54 lr: 0.000824 loss: 3.7479 (3.6236) grad_norm: 1.1042 (1.1098) time: 0.5106 [2021-03-25 18:22:25 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 90/1251] eta: 0:10:42 lr: 0.000824 loss: 3.7479 (3.6277) grad_norm: 1.1056 (1.1108) time: 0.5049 [2021-03-25 18:22:30 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 100/1251] eta: 0:10:32 lr: 0.000824 loss: 3.7197 (3.6475) grad_norm: 1.1181 (1.1083) time: 0.5107 [2021-03-25 18:22:35 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 110/1251] eta: 0:10:22 lr: 0.000824 loss: 3.7197 (3.6416) grad_norm: 1.1029 (1.1046) time: 0.5083 [2021-03-25 18:22:40 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 120/1251] eta: 0:10:13 lr: 0.000824 loss: 3.8607 (3.6572) grad_norm: 1.0789 (1.1055) time: 0.5058 [2021-03-25 18:22:45 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 130/1251] eta: 0:10:04 lr: 0.000824 loss: 3.4166 (3.6231) grad_norm: 1.0789 (1.1039) time: 0.5062 [2021-03-25 18:22:51 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 140/1251] eta: 0:09:57 lr: 0.000824 loss: 3.3597 (3.6275) grad_norm: 1.0414 (1.1009) time: 0.5083 [2021-03-25 18:22:56 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 150/1251] eta: 0:09:49 lr: 0.000824 loss: 3.7603 (3.6172) grad_norm: 1.1253 (1.1042) time: 0.5100 [2021-03-25 18:23:01 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 160/1251] eta: 0:09:42 lr: 0.000824 loss: 3.5642 (3.6091) grad_norm: 1.1160 (1.1030) time: 0.5074 [2021-03-25 18:23:06 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 170/1251] eta: 0:09:35 lr: 0.000824 loss: 3.6037 (3.6093) grad_norm: 1.0946 (1.1061) time: 0.5051 [2021-03-25 18:23:11 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 180/1251] eta: 0:09:28 lr: 0.000824 loss: 3.6037 (3.6048) grad_norm: 1.1472 (1.1096) time: 0.5054 [2021-03-25 18:23:16 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 190/1251] eta: 0:09:21 lr: 0.000824 loss: 3.5364 (3.5979) grad_norm: 1.1472 (1.1128) time: 0.5055 [2021-03-25 18:23:21 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 200/1251] eta: 0:09:15 lr: 0.000824 loss: 3.5364 (3.5939) grad_norm: 1.1691 (1.1180) time: 0.5087 [2021-03-25 18:23:26 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 210/1251] eta: 0:09:09 lr: 0.000824 loss: 3.3654 (3.5874) grad_norm: 1.1799 (1.1209) time: 0.5124 [2021-03-25 18:23:31 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 220/1251] eta: 0:09:03 lr: 0.000824 loss: 3.8442 (3.5978) grad_norm: 1.1356 (1.1211) time: 0.5092 [2021-03-25 18:23:36 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 230/1251] eta: 0:08:56 lr: 0.000824 loss: 3.9155 (3.5981) grad_norm: 1.0774 (1.1179) time: 0.5040 [2021-03-25 18:23:41 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 240/1251] eta: 0:08:50 lr: 0.000824 loss: 3.6660 (3.5954) grad_norm: 1.0484 (1.1164) time: 0.5011 [2021-03-25 18:23:46 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 250/1251] eta: 0:08:44 lr: 0.000824 loss: 3.2212 (3.5850) grad_norm: 1.0711 (1.1162) time: 0.5065 [2021-03-25 18:23:51 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 260/1251] eta: 0:08:38 lr: 0.000824 loss: 3.3063 (3.5793) grad_norm: 1.0768 (1.1175) time: 0.5093 [2021-03-25 18:23:56 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 270/1251] eta: 0:08:32 lr: 0.000824 loss: 3.4885 (3.5756) grad_norm: 1.0929 (1.1158) time: 0.5068 [2021-03-25 18:24:01 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 280/1251] eta: 0:08:26 lr: 0.000824 loss: 3.6179 (3.5750) grad_norm: 1.0941 (1.1169) time: 0.5013 [2021-03-25 18:24:07 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 290/1251] eta: 0:08:21 lr: 0.000824 loss: 3.6106 (3.5689) grad_norm: 1.0812 (1.1146) time: 0.5108 [2021-03-25 18:24:12 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 300/1251] eta: 0:08:15 lr: 0.000824 loss: 3.6106 (3.5746) grad_norm: 1.0705 (1.1133) time: 0.5163 [2021-03-25 18:24:17 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 310/1251] eta: 0:08:10 lr: 0.000824 loss: 3.6036 (3.5591) grad_norm: 1.0732 (1.1124) time: 0.5069 [2021-03-25 18:24:22 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 320/1251] eta: 0:08:04 lr: 0.000823 loss: 3.5049 (3.5563) grad_norm: 1.0677 (1.1115) time: 0.5023 [2021-03-25 18:24:27 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 330/1251] eta: 0:07:58 lr: 0.000823 loss: 3.6277 (3.5522) grad_norm: 1.0679 (1.1131) time: 0.5024 [2021-03-25 18:24:32 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 340/1251] eta: 0:07:53 lr: 0.000823 loss: 3.6350 (3.5580) grad_norm: 1.0957 (1.1126) time: 0.5050 [2021-03-25 18:24:37 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 350/1251] eta: 0:07:47 lr: 0.000823 loss: 3.6923 (3.5620) grad_norm: 1.0988 (1.1130) time: 0.5051 [2021-03-25 18:24:42 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 360/1251] eta: 0:07:41 lr: 0.000823 loss: 3.6123 (3.5596) grad_norm: 1.0725 (1.1110) time: 0.5018 [2021-03-25 18:24:47 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 370/1251] eta: 0:07:36 lr: 0.000823 loss: 3.5166 (3.5572) grad_norm: 1.0816 (1.1116) time: 0.5038 [2021-03-25 18:24:52 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 380/1251] eta: 0:07:30 lr: 0.000823 loss: 3.4898 (3.5588) grad_norm: 1.0816 (1.1099) time: 0.5065 [2021-03-25 18:24:57 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 390/1251] eta: 0:07:25 lr: 0.000823 loss: 3.7475 (3.5622) grad_norm: 1.0497 (1.1111) time: 0.5042 [2021-03-25 18:25:02 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 400/1251] eta: 0:07:20 lr: 0.000823 loss: 3.4389 (3.5595) grad_norm: 1.1406 (1.1120) time: 0.5048 [2021-03-25 18:25:07 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 410/1251] eta: 0:07:14 lr: 0.000823 loss: 3.6632 (3.5651) grad_norm: 1.0673 (1.1106) time: 0.5013 [2021-03-25 18:25:12 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 420/1251] eta: 0:07:09 lr: 0.000823 loss: 3.5968 (3.5609) grad_norm: 1.0932 (1.1104) time: 0.5009 [2021-03-25 18:25:17 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 430/1251] eta: 0:07:03 lr: 0.000823 loss: 3.4870 (3.5584) grad_norm: 1.0932 (1.1090) time: 0.5042 [2021-03-25 18:25:22 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 440/1251] eta: 0:06:58 lr: 0.000823 loss: 3.4870 (3.5583) grad_norm: 1.0918 (1.1091) time: 0.5075 [2021-03-25 18:25:27 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 450/1251] eta: 0:06:52 lr: 0.000823 loss: 3.4645 (3.5521) grad_norm: 1.0963 (1.1082) time: 0.5048 [2021-03-25 18:25:32 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 460/1251] eta: 0:06:47 lr: 0.000823 loss: 3.3878 (3.5472) grad_norm: 1.0891 (1.1086) time: 0.4993 [2021-03-25 18:25:37 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 470/1251] eta: 0:06:42 lr: 0.000823 loss: 3.4605 (3.5473) grad_norm: 1.1143 (1.1093) time: 0.5008 [2021-03-25 18:25:42 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 480/1251] eta: 0:06:36 lr: 0.000823 loss: 3.6908 (3.5510) grad_norm: 1.1060 (1.1092) time: 0.5043 [2021-03-25 18:25:48 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 490/1251] eta: 0:06:31 lr: 0.000823 loss: 3.6858 (3.5513) grad_norm: 1.0398 (1.1088) time: 0.5071 [2021-03-25 18:25:53 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 500/1251] eta: 0:06:26 lr: 0.000823 loss: 3.5565 (3.5469) grad_norm: 1.0937 (1.1101) time: 0.5040 [2021-03-25 18:25:58 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 510/1251] eta: 0:06:21 lr: 0.000823 loss: 3.5565 (3.5494) grad_norm: 1.1099 (1.1105) time: 0.5067 [2021-03-25 18:26:03 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 520/1251] eta: 0:06:15 lr: 0.000823 loss: 3.5460 (3.5510) grad_norm: 1.0976 (1.1101) time: 0.5084 [2021-03-25 18:26:08 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 530/1251] eta: 0:06:10 lr: 0.000823 loss: 3.3299 (3.5440) grad_norm: 1.0279 (1.1095) time: 0.5056 [2021-03-25 18:26:13 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 540/1251] eta: 0:06:05 lr: 0.000823 loss: 3.4949 (3.5436) grad_norm: 1.0752 (1.1099) time: 0.5115 [2021-03-25 18:26:18 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 550/1251] eta: 0:06:00 lr: 0.000823 loss: 3.6619 (3.5461) grad_norm: 1.0664 (1.1092) time: 0.5154 [2021-03-25 18:26:23 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 560/1251] eta: 0:05:55 lr: 0.000823 loss: 3.6570 (3.5461) grad_norm: 1.0557 (1.1088) time: 0.5068 [2021-03-25 18:26:28 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 570/1251] eta: 0:05:49 lr: 0.000823 loss: 3.9155 (3.5524) grad_norm: 1.0865 (1.1099) time: 0.4997 [2021-03-25 18:26:33 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 580/1251] eta: 0:05:44 lr: 0.000823 loss: 3.7757 (3.5497) grad_norm: 1.0865 (1.1100) time: 0.5014 [2021-03-25 18:26:38 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 590/1251] eta: 0:05:39 lr: 0.000823 loss: 3.4270 (3.5478) grad_norm: 1.0831 (1.1102) time: 0.5105 [2021-03-25 18:26:43 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 600/1251] eta: 0:05:34 lr: 0.000823 loss: 3.4270 (3.5457) grad_norm: 1.0594 (1.1088) time: 0.5096 [2021-03-25 18:26:48 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 610/1251] eta: 0:05:28 lr: 0.000823 loss: 3.6902 (3.5481) grad_norm: 1.0928 (1.1094) time: 0.5009 [2021-03-25 18:26:53 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 620/1251] eta: 0:05:23 lr: 0.000823 loss: 3.6992 (3.5521) grad_norm: 1.1250 (1.1099) time: 0.5003 [2021-03-25 18:26:58 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 630/1251] eta: 0:05:18 lr: 0.000823 loss: 3.6956 (3.5509) grad_norm: 1.0684 (1.1094) time: 0.4973 [2021-03-25 18:27:03 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 640/1251] eta: 0:05:13 lr: 0.000822 loss: 3.5821 (3.5530) grad_norm: 1.0674 (1.1087) time: 0.5016 [2021-03-25 18:27:08 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 650/1251] eta: 0:05:07 lr: 0.000822 loss: 3.6174 (3.5549) grad_norm: 1.0282 (1.1079) time: 0.5061 [2021-03-25 18:27:13 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 660/1251] eta: 0:05:02 lr: 0.000822 loss: 3.6174 (3.5562) grad_norm: 1.0407 (1.1075) time: 0.5063 [2021-03-25 18:27:19 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 670/1251] eta: 0:04:57 lr: 0.000822 loss: 3.6881 (3.5557) grad_norm: 1.0595 (1.1079) time: 0.5066 [2021-03-25 18:27:24 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 680/1251] eta: 0:04:52 lr: 0.000822 loss: 3.7186 (3.5550) grad_norm: 1.0768 (1.1085) time: 0.5044 [2021-03-25 18:27:29 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 690/1251] eta: 0:04:47 lr: 0.000822 loss: 3.6750 (3.5538) grad_norm: 1.0786 (1.1091) time: 0.5080 [2021-03-25 18:27:34 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 700/1251] eta: 0:04:42 lr: 0.000822 loss: 3.4180 (3.5502) grad_norm: 1.0422 (1.1086) time: 0.5044 [2021-03-25 18:27:39 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 710/1251] eta: 0:04:36 lr: 0.000822 loss: 3.5143 (3.5529) grad_norm: 1.0236 (1.1076) time: 0.4992 [2021-03-25 18:27:44 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 720/1251] eta: 0:04:31 lr: 0.000822 loss: 3.7590 (3.5513) grad_norm: 1.0199 (1.1068) time: 0.5032 [2021-03-25 18:27:49 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 730/1251] eta: 0:04:26 lr: 0.000822 loss: 3.6325 (3.5483) grad_norm: 1.0301 (1.1070) time: 0.5050 [2021-03-25 18:27:54 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 740/1251] eta: 0:04:21 lr: 0.000822 loss: 3.4969 (3.5472) grad_norm: 1.0846 (1.1068) time: 0.5199 [2021-03-25 18:27:59 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 750/1251] eta: 0:04:16 lr: 0.000822 loss: 3.6617 (3.5504) grad_norm: 1.0809 (1.1065) time: 0.5247 [2021-03-25 18:28:04 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 760/1251] eta: 0:04:11 lr: 0.000822 loss: 3.7442 (3.5484) grad_norm: 1.0809 (1.1067) time: 0.5106 [2021-03-25 18:28:09 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 770/1251] eta: 0:04:06 lr: 0.000822 loss: 3.3887 (3.5463) grad_norm: 1.1177 (1.1087) time: 0.5041 [2021-03-25 18:28:14 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 780/1251] eta: 0:04:00 lr: 0.000822 loss: 3.6932 (3.5501) grad_norm: 1.1160 (1.1092) time: 0.5010 [2021-03-25 18:28:19 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 790/1251] eta: 0:03:55 lr: 0.000822 loss: 3.7620 (3.5508) grad_norm: 1.0855 (1.1089) time: 0.5021 [2021-03-25 18:28:24 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 800/1251] eta: 0:03:50 lr: 0.000822 loss: 3.6762 (3.5501) grad_norm: 1.0775 (1.1089) time: 0.5040 [2021-03-25 18:28:30 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 810/1251] eta: 0:03:45 lr: 0.000822 loss: 3.4278 (3.5466) grad_norm: 1.0736 (1.1082) time: 0.5108 [2021-03-25 18:28:35 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 820/1251] eta: 0:03:40 lr: 0.000822 loss: 3.4722 (3.5469) grad_norm: 1.0759 (1.1083) time: 0.5118 [2021-03-25 18:28:40 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 830/1251] eta: 0:03:35 lr: 0.000822 loss: 3.4722 (3.5461) grad_norm: 1.0820 (1.1083) time: 0.5032 [2021-03-25 18:28:45 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 840/1251] eta: 0:03:30 lr: 0.000822 loss: 3.4517 (3.5463) grad_norm: 1.0473 (1.1081) time: 0.5029 [2021-03-25 18:28:50 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 850/1251] eta: 0:03:24 lr: 0.000822 loss: 3.5928 (3.5462) grad_norm: 1.0775 (1.1079) time: 0.5013 [2021-03-25 18:28:55 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 860/1251] eta: 0:03:19 lr: 0.000822 loss: 3.5071 (3.5450) grad_norm: 1.0577 (1.1071) time: 0.5000 [2021-03-25 18:29:00 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 870/1251] eta: 0:03:14 lr: 0.000822 loss: 3.6288 (3.5474) grad_norm: 1.0406 (1.1062) time: 0.5053 [2021-03-25 18:29:05 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 880/1251] eta: 0:03:09 lr: 0.000822 loss: 3.7721 (3.5487) grad_norm: 1.0445 (1.1056) time: 0.5142 [2021-03-25 18:29:10 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 890/1251] eta: 0:03:04 lr: 0.000822 loss: 3.7721 (3.5506) grad_norm: 1.0640 (1.1059) time: 0.5097 [2021-03-25 18:29:15 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 900/1251] eta: 0:02:59 lr: 0.000822 loss: 3.7440 (3.5498) grad_norm: 1.1282 (1.1066) time: 0.5049 [2021-03-25 18:29:20 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 910/1251] eta: 0:02:54 lr: 0.000822 loss: 3.5892 (3.5518) grad_norm: 1.0404 (1.1058) time: 0.5103 [2021-03-25 18:29:25 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 920/1251] eta: 0:02:49 lr: 0.000822 loss: 3.5892 (3.5495) grad_norm: 1.0614 (1.1060) time: 0.5106 [2021-03-25 18:29:30 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 930/1251] eta: 0:02:43 lr: 0.000822 loss: 3.5855 (3.5481) grad_norm: 1.0933 (1.1063) time: 0.5093 [2021-03-25 18:29:36 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 940/1251] eta: 0:02:38 lr: 0.000822 loss: 3.5855 (3.5489) grad_norm: 1.1278 (1.1065) time: 0.5074 [2021-03-25 18:29:41 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 950/1251] eta: 0:02:33 lr: 0.000821 loss: 3.6436 (3.5498) grad_norm: 1.1009 (1.1064) time: 0.5087 [2021-03-25 18:29:46 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 960/1251] eta: 0:02:28 lr: 0.000821 loss: 3.6436 (3.5491) grad_norm: 1.0263 (1.1055) time: 0.5071 [2021-03-25 18:29:51 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 970/1251] eta: 0:02:23 lr: 0.000821 loss: 3.7300 (3.5511) grad_norm: 1.0263 (1.1057) time: 0.5029 [2021-03-25 18:29:56 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 980/1251] eta: 0:02:18 lr: 0.000821 loss: 3.8117 (3.5524) grad_norm: 1.0736 (1.1058) time: 0.5047 [2021-03-25 18:30:01 swin_small_patch4_window7_224] INFO: Epoch: [83] [ 990/1251] eta: 0:02:13 lr: 0.000821 loss: 3.7104 (3.5527) grad_norm: 1.0764 (1.1055) time: 0.5101 [2021-03-25 18:30:06 swin_small_patch4_window7_224] INFO: Epoch: [83] [1000/1251] eta: 0:02:08 lr: 0.000821 loss: 3.5932 (3.5508) grad_norm: 1.0911 (1.1060) time: 0.5183 [2021-03-25 18:30:11 swin_small_patch4_window7_224] INFO: Epoch: [83] [1010/1251] eta: 0:02:03 lr: 0.000821 loss: 3.3730 (3.5484) grad_norm: 1.0918 (1.1054) time: 0.5176 [2021-03-25 18:30:16 swin_small_patch4_window7_224] INFO: Epoch: [83] [1020/1251] eta: 0:01:57 lr: 0.000821 loss: 3.6647 (3.5482) grad_norm: 1.0383 (1.1050) time: 0.5082 [2021-03-25 18:30:21 swin_small_patch4_window7_224] INFO: Epoch: [83] [1030/1251] eta: 0:01:52 lr: 0.000821 loss: 3.5970 (3.5456) grad_norm: 1.0001 (1.1042) time: 0.5081 [2021-03-25 18:30:27 swin_small_patch4_window7_224] INFO: Epoch: [83] [1040/1251] eta: 0:01:47 lr: 0.000821 loss: 3.2862 (3.5441) grad_norm: 1.0555 (1.1038) time: 0.5106 [2021-03-25 18:30:31 swin_small_patch4_window7_224] INFO: Epoch: [83] [1050/1251] eta: 0:01:42 lr: 0.000821 loss: 3.5159 (3.5436) grad_norm: 1.0565 (1.1034) time: 0.5022 [2021-03-25 18:30:37 swin_small_patch4_window7_224] INFO: Epoch: [83] [1060/1251] eta: 0:01:37 lr: 0.000821 loss: 3.6753 (3.5447) grad_norm: 1.0891 (1.1037) time: 0.5001 [2021-03-25 18:30:42 swin_small_patch4_window7_224] INFO: Epoch: [83] [1070/1251] eta: 0:01:32 lr: 0.000821 loss: 3.7436 (3.5463) grad_norm: 1.1004 (1.1039) time: 0.5060 [2021-03-25 18:30:47 swin_small_patch4_window7_224] INFO: Epoch: [83] [1080/1251] eta: 0:01:27 lr: 0.000821 loss: 3.6643 (3.5448) grad_norm: 1.1628 (1.1054) time: 0.5063 [2021-03-25 18:30:52 swin_small_patch4_window7_224] INFO: Epoch: [83] [1090/1251] eta: 0:01:22 lr: 0.000821 loss: 3.5166 (3.5444) grad_norm: 1.1772 (1.1058) time: 0.5062 [2021-03-25 18:30:57 swin_small_patch4_window7_224] INFO: Epoch: [83] [1100/1251] eta: 0:01:17 lr: 0.000821 loss: 3.5911 (3.5448) grad_norm: 1.0996 (1.1057) time: 0.5083 [2021-03-25 18:31:02 swin_small_patch4_window7_224] INFO: Epoch: [83] [1110/1251] eta: 0:01:11 lr: 0.000821 loss: 3.6519 (3.5451) grad_norm: 1.0996 (1.1059) time: 0.5053 [2021-03-25 18:31:07 swin_small_patch4_window7_224] INFO: Epoch: [83] [1120/1251] eta: 0:01:06 lr: 0.000821 loss: 3.5254 (3.5442) grad_norm: 1.1248 (1.1058) time: 0.5008 [2021-03-25 18:31:12 swin_small_patch4_window7_224] INFO: Epoch: [83] [1130/1251] eta: 0:01:01 lr: 0.000821 loss: 3.7295 (3.5455) grad_norm: 1.0662 (1.1058) time: 0.5008 [2021-03-25 18:31:17 swin_small_patch4_window7_224] INFO: Epoch: [83] [1140/1251] eta: 0:00:56 lr: 0.000821 loss: 3.7295 (3.5450) grad_norm: 1.0751 (1.1056) time: 0.5030 [2021-03-25 18:31:22 swin_small_patch4_window7_224] INFO: Epoch: [83] [1150/1251] eta: 0:00:51 lr: 0.000821 loss: 3.7471 (3.5478) grad_norm: 1.0522 (1.1052) time: 0.5019 [2021-03-25 18:31:27 swin_small_patch4_window7_224] INFO: Epoch: [83] [1160/1251] eta: 0:00:46 lr: 0.000821 loss: 3.7338 (3.5476) grad_norm: 1.0789 (1.1057) time: 0.4996 [2021-03-25 18:31:32 swin_small_patch4_window7_224] INFO: Epoch: [83] [1170/1251] eta: 0:00:41 lr: 0.000821 loss: 3.7900 (3.5509) grad_norm: 1.1144 (1.1057) time: 0.5022 [2021-03-25 18:31:37 swin_small_patch4_window7_224] INFO: Epoch: [83] [1180/1251] eta: 0:00:36 lr: 0.000821 loss: 3.7900 (3.5502) grad_norm: 1.0863 (1.1059) time: 0.5040 [2021-03-25 18:31:42 swin_small_patch4_window7_224] INFO: Epoch: [83] [1190/1251] eta: 0:00:31 lr: 0.000821 loss: 3.5413 (3.5504) grad_norm: 1.0863 (1.1059) time: 0.5021 [2021-03-25 18:31:47 swin_small_patch4_window7_224] INFO: Epoch: [83] [1200/1251] eta: 0:00:25 lr: 0.000821 loss: 3.5413 (3.5504) grad_norm: 1.0905 (1.1060) time: 0.5034 [2021-03-25 18:31:52 swin_small_patch4_window7_224] INFO: Epoch: [83] [1210/1251] eta: 0:00:20 lr: 0.000821 loss: 3.6007 (3.5499) grad_norm: 1.0994 (1.1061) time: 0.5080 [2021-03-25 18:31:57 swin_small_patch4_window7_224] INFO: Epoch: [83] [1220/1251] eta: 0:00:15 lr: 0.000821 loss: 3.7008 (3.5494) grad_norm: 1.1367 (1.1066) time: 0.5039 [2021-03-25 18:32:02 swin_small_patch4_window7_224] INFO: Epoch: [83] [1230/1251] eta: 0:00:10 lr: 0.000821 loss: 3.6352 (3.5507) grad_norm: 1.0891 (1.1062) time: 0.5032 [2021-03-25 18:32:07 swin_small_patch4_window7_224] INFO: Epoch: [83] [1240/1251] eta: 0:00:05 lr: 0.000821 loss: 3.7410 (3.5510) grad_norm: 1.0524 (1.1061) time: 0.4996 [2021-03-25 18:32:12 swin_small_patch4_window7_224] INFO: Epoch: [83] [1250/1251] eta: 0:00:00 lr: 0.000821 loss: 3.7311 (3.5505) grad_norm: 1.1186 (1.1068) time: 0.4958 [2021-03-25 18:32:18 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:31 loss: 1.2178 (1.2178) acc1: 65.6250 (65.6250) acc5: 92.1875 (92.1875) [2021-03-25 18:32:20 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0957 (1.0594) acc1: 75.0000 (73.7216) acc5: 93.7500 (93.6080) [2021-03-25 18:32:22 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0832 (1.0717) acc1: 75.0000 (73.8839) acc5: 92.1875 (92.9315) [2021-03-25 18:32:24 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9998 (1.0524) acc1: 76.5625 (74.7984) acc5: 92.1875 (93.2460) [2021-03-25 18:32:26 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0760 (1.0807) acc1: 73.4375 (73.7424) acc5: 92.1875 (92.8735) [2021-03-25 18:32:27 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0760 (1.0779) acc1: 70.3125 (73.7280) acc5: 92.1875 (92.7680) [2021-03-25 18:32:30 swin_small_patch4_window7_224] INFO: * Acc@1 75.056 Acc@5 92.962 loss 1.056 [2021-03-25 18:32:30 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.1% [2021-03-25 18:32:30 swin_small_patch4_window7_224] INFO: Max accuracy: 75.23% [2021-03-25 18:32:34 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 0/1251] eta: 1:25:07 lr: 0.000821 loss: 3.5031 (3.5031) grad_norm: 1.2643 (1.2643) time: 4.0828 [2021-03-25 18:32:39 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 10/1251] eta: 0:17:36 lr: 0.000820 loss: 3.5031 (3.4456) grad_norm: 1.1501 (1.1776) time: 0.8509 [2021-03-25 18:32:44 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 20/1251] eta: 0:14:00 lr: 0.000820 loss: 3.4853 (3.5130) grad_norm: 1.0664 (1.1337) time: 0.5124 [2021-03-25 18:32:49 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 30/1251] eta: 0:12:42 lr: 0.000820 loss: 3.4152 (3.4476) grad_norm: 1.0927 (1.1589) time: 0.5004 [2021-03-25 18:32:54 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 40/1251] eta: 0:11:59 lr: 0.000820 loss: 3.5839 (3.4983) grad_norm: 1.1193 (1.1419) time: 0.5018 [2021-03-25 18:32:59 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 50/1251] eta: 0:11:33 lr: 0.000820 loss: 3.6744 (3.4999) grad_norm: 1.0968 (1.1365) time: 0.5035 [2021-03-25 18:33:04 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 60/1251] eta: 0:11:14 lr: 0.000820 loss: 3.6744 (3.5268) grad_norm: 1.0968 (1.1350) time: 0.5090 [2021-03-25 18:33:10 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 70/1251] eta: 0:11:02 lr: 0.000820 loss: 3.7420 (3.5251) grad_norm: 1.1689 (1.1447) time: 0.5180 [2021-03-25 18:33:15 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 80/1251] eta: 0:10:48 lr: 0.000820 loss: 3.6310 (3.5214) grad_norm: 1.1484 (1.1418) time: 0.5160 [2021-03-25 18:33:20 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 90/1251] eta: 0:10:37 lr: 0.000820 loss: 3.6310 (3.5328) grad_norm: 1.0767 (1.1328) time: 0.5093 [2021-03-25 18:33:25 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 100/1251] eta: 0:10:27 lr: 0.000820 loss: 3.3460 (3.5121) grad_norm: 1.0757 (1.1282) time: 0.5096 [2021-03-25 18:33:30 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 110/1251] eta: 0:10:18 lr: 0.000820 loss: 3.2873 (3.5080) grad_norm: 1.1135 (1.1308) time: 0.5114 [2021-03-25 18:33:35 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 120/1251] eta: 0:10:09 lr: 0.000820 loss: 3.5250 (3.4970) grad_norm: 1.0853 (1.1233) time: 0.5099 [2021-03-25 18:33:40 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 130/1251] eta: 0:10:02 lr: 0.000820 loss: 3.7611 (3.5258) grad_norm: 1.0473 (1.1239) time: 0.5113 [2021-03-25 18:33:45 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 140/1251] eta: 0:09:54 lr: 0.000820 loss: 3.8509 (3.5300) grad_norm: 1.0748 (1.1234) time: 0.5096 [2021-03-25 18:33:50 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 150/1251] eta: 0:09:47 lr: 0.000820 loss: 3.7600 (3.5401) grad_norm: 1.0456 (1.1163) time: 0.5066 [2021-03-25 18:33:55 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 160/1251] eta: 0:09:40 lr: 0.000820 loss: 3.6030 (3.5362) grad_norm: 1.0243 (1.1142) time: 0.5081 [2021-03-25 18:34:00 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 170/1251] eta: 0:09:32 lr: 0.000820 loss: 3.5943 (3.5299) grad_norm: 1.0410 (1.1134) time: 0.5006 [2021-03-25 18:34:05 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 180/1251] eta: 0:09:25 lr: 0.000820 loss: 3.3058 (3.5305) grad_norm: 1.0937 (1.1164) time: 0.5005 [2021-03-25 18:34:11 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 190/1251] eta: 0:09:19 lr: 0.000820 loss: 3.3058 (3.5316) grad_norm: 1.1309 (1.1176) time: 0.5096 [2021-03-25 18:34:16 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 200/1251] eta: 0:09:12 lr: 0.000820 loss: 3.8054 (3.5337) grad_norm: 1.0886 (1.1155) time: 0.5058 [2021-03-25 18:34:20 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 210/1251] eta: 0:09:06 lr: 0.000820 loss: 3.3743 (3.5219) grad_norm: 1.0881 (1.1139) time: 0.4959 [2021-03-25 18:34:26 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 220/1251] eta: 0:09:00 lr: 0.000820 loss: 3.2822 (3.5160) grad_norm: 1.0881 (1.1116) time: 0.5030 [2021-03-25 18:34:31 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 230/1251] eta: 0:08:53 lr: 0.000820 loss: 3.2822 (3.5045) grad_norm: 1.0996 (1.1136) time: 0.5049 [2021-03-25 18:34:36 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 240/1251] eta: 0:08:47 lr: 0.000820 loss: 3.3767 (3.5117) grad_norm: 1.1422 (1.1164) time: 0.5013 [2021-03-25 18:34:41 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 250/1251] eta: 0:08:42 lr: 0.000820 loss: 3.4868 (3.5064) grad_norm: 1.0888 (1.1175) time: 0.5067 [2021-03-25 18:34:46 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 260/1251] eta: 0:08:36 lr: 0.000820 loss: 3.5561 (3.5115) grad_norm: 1.0789 (1.1156) time: 0.5067 [2021-03-25 18:34:51 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 270/1251] eta: 0:08:30 lr: 0.000820 loss: 3.6072 (3.5145) grad_norm: 1.0233 (1.1117) time: 0.5114 [2021-03-25 18:34:56 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 280/1251] eta: 0:08:24 lr: 0.000820 loss: 3.5173 (3.5068) grad_norm: 1.0195 (1.1104) time: 0.5086 [2021-03-25 18:35:01 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 290/1251] eta: 0:08:18 lr: 0.000820 loss: 3.6490 (3.5148) grad_norm: 1.0770 (1.1098) time: 0.4963 [2021-03-25 18:35:06 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 300/1251] eta: 0:08:13 lr: 0.000820 loss: 3.6287 (3.5126) grad_norm: 1.0653 (1.1087) time: 0.5015 [2021-03-25 18:35:11 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 310/1251] eta: 0:08:07 lr: 0.000820 loss: 3.6287 (3.5226) grad_norm: 1.0800 (1.1095) time: 0.5090 [2021-03-25 18:35:16 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 320/1251] eta: 0:08:02 lr: 0.000820 loss: 3.8940 (3.5279) grad_norm: 1.0874 (1.1092) time: 0.5143 [2021-03-25 18:35:21 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 330/1251] eta: 0:07:57 lr: 0.000819 loss: 3.8558 (3.5314) grad_norm: 1.1002 (1.1105) time: 0.5156 [2021-03-25 18:35:26 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 340/1251] eta: 0:07:51 lr: 0.000819 loss: 3.6225 (3.5301) grad_norm: 1.0834 (1.1092) time: 0.5112 [2021-03-25 18:35:31 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 350/1251] eta: 0:07:46 lr: 0.000819 loss: 3.6225 (3.5325) grad_norm: 1.0834 (1.1104) time: 0.5034 [2021-03-25 18:35:36 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 360/1251] eta: 0:07:40 lr: 0.000819 loss: 3.7139 (3.5363) grad_norm: 1.0907 (1.1095) time: 0.4956 [2021-03-25 18:35:41 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 370/1251] eta: 0:07:35 lr: 0.000819 loss: 3.6630 (3.5344) grad_norm: 1.0593 (1.1081) time: 0.4993 [2021-03-25 18:35:47 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 380/1251] eta: 0:07:29 lr: 0.000819 loss: 3.6630 (3.5361) grad_norm: 1.0593 (1.1076) time: 0.5059 [2021-03-25 18:35:52 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 390/1251] eta: 0:07:24 lr: 0.000819 loss: 3.7145 (3.5402) grad_norm: 1.0856 (1.1094) time: 0.5083 [2021-03-25 18:35:57 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 400/1251] eta: 0:07:18 lr: 0.000819 loss: 3.7234 (3.5421) grad_norm: 1.1899 (1.1124) time: 0.5036 [2021-03-25 18:36:02 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 410/1251] eta: 0:07:13 lr: 0.000819 loss: 3.6478 (3.5366) grad_norm: 1.1516 (1.1131) time: 0.5038 [2021-03-25 18:36:07 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 420/1251] eta: 0:07:08 lr: 0.000819 loss: 3.7307 (3.5432) grad_norm: 1.1214 (1.1146) time: 0.5080 [2021-03-25 18:36:12 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 430/1251] eta: 0:07:02 lr: 0.000819 loss: 3.7873 (3.5450) grad_norm: 1.1489 (1.1156) time: 0.5025 [2021-03-25 18:36:17 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 440/1251] eta: 0:06:57 lr: 0.000819 loss: 3.7801 (3.5456) grad_norm: 1.1043 (1.1141) time: 0.5008 [2021-03-25 18:36:22 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 450/1251] eta: 0:06:52 lr: 0.000819 loss: 3.6746 (3.5443) grad_norm: 1.0484 (1.1131) time: 0.5039 [2021-03-25 18:36:27 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 460/1251] eta: 0:06:46 lr: 0.000819 loss: 3.6747 (3.5450) grad_norm: 1.0839 (1.1133) time: 0.5007 [2021-03-25 18:36:32 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 470/1251] eta: 0:06:41 lr: 0.000819 loss: 3.7923 (3.5500) grad_norm: 1.1397 (1.1150) time: 0.5019 [2021-03-25 18:36:37 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 480/1251] eta: 0:06:35 lr: 0.000819 loss: 3.8209 (3.5546) grad_norm: 1.1343 (1.1148) time: 0.5043 [2021-03-25 18:36:42 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 490/1251] eta: 0:06:30 lr: 0.000819 loss: 3.8101 (3.5539) grad_norm: 1.0717 (1.1135) time: 0.5059 [2021-03-25 18:36:47 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 500/1251] eta: 0:06:25 lr: 0.000819 loss: 3.7292 (3.5526) grad_norm: 1.0415 (1.1121) time: 0.5057 [2021-03-25 18:36:52 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 510/1251] eta: 0:06:20 lr: 0.000819 loss: 3.3341 (3.5497) grad_norm: 1.0748 (1.1126) time: 0.5016 [2021-03-25 18:36:57 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 520/1251] eta: 0:06:15 lr: 0.000819 loss: 3.4092 (3.5492) grad_norm: 1.1103 (1.1123) time: 0.5065 [2021-03-25 18:37:02 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 530/1251] eta: 0:06:09 lr: 0.000819 loss: 3.6565 (3.5510) grad_norm: 1.1103 (1.1131) time: 0.5100 [2021-03-25 18:37:07 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 540/1251] eta: 0:06:04 lr: 0.000819 loss: 3.6689 (3.5509) grad_norm: 1.0929 (1.1129) time: 0.5095 [2021-03-25 18:37:13 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 550/1251] eta: 0:05:59 lr: 0.000819 loss: 3.3796 (3.5497) grad_norm: 1.0516 (1.1122) time: 0.5204 [2021-03-25 18:37:18 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 560/1251] eta: 0:05:54 lr: 0.000819 loss: 3.6065 (3.5501) grad_norm: 1.0743 (inf) time: 0.5144 [2021-03-25 18:37:23 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 570/1251] eta: 0:05:49 lr: 0.000819 loss: 3.4571 (3.5455) grad_norm: 1.0743 (inf) time: 0.5030 [2021-03-25 18:37:28 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 580/1251] eta: 0:05:44 lr: 0.000819 loss: 3.4954 (3.5474) grad_norm: 1.1083 (inf) time: 0.5100 [2021-03-25 18:37:33 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 590/1251] eta: 0:05:38 lr: 0.000819 loss: 3.6742 (3.5461) grad_norm: 1.1895 (inf) time: 0.5094 [2021-03-25 18:37:38 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 600/1251] eta: 0:05:33 lr: 0.000819 loss: 3.5893 (3.5477) grad_norm: 1.0752 (inf) time: 0.5029 [2021-03-25 18:37:43 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 610/1251] eta: 0:05:28 lr: 0.000819 loss: 3.6642 (3.5482) grad_norm: 1.0278 (inf) time: 0.4997 [2021-03-25 18:37:48 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 620/1251] eta: 0:05:23 lr: 0.000819 loss: 3.7960 (3.5502) grad_norm: 1.0301 (inf) time: 0.5038 [2021-03-25 18:37:53 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 630/1251] eta: 0:05:18 lr: 0.000819 loss: 3.7960 (3.5497) grad_norm: 1.1183 (inf) time: 0.5070 [2021-03-25 18:37:58 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 640/1251] eta: 0:05:12 lr: 0.000818 loss: 3.6079 (3.5504) grad_norm: 1.1484 (inf) time: 0.5016 [2021-03-25 18:38:03 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 650/1251] eta: 0:05:07 lr: 0.000818 loss: 3.6079 (3.5471) grad_norm: 1.1467 (inf) time: 0.4988 [2021-03-25 18:38:08 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 660/1251] eta: 0:05:02 lr: 0.000818 loss: 3.5862 (3.5487) grad_norm: 1.1599 (inf) time: 0.5012 [2021-03-25 18:38:13 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 670/1251] eta: 0:04:57 lr: 0.000818 loss: 3.7056 (3.5529) grad_norm: 1.0637 (inf) time: 0.5049 [2021-03-25 18:38:18 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 680/1251] eta: 0:04:52 lr: 0.000818 loss: 3.7588 (3.5543) grad_norm: 1.0530 (inf) time: 0.5084 [2021-03-25 18:38:23 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 690/1251] eta: 0:04:46 lr: 0.000818 loss: 3.6383 (3.5554) grad_norm: 1.0684 (inf) time: 0.5053 [2021-03-25 18:38:28 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 700/1251] eta: 0:04:41 lr: 0.000818 loss: 3.6089 (3.5571) grad_norm: 1.0684 (inf) time: 0.5063 [2021-03-25 18:38:33 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 710/1251] eta: 0:04:36 lr: 0.000818 loss: 3.7216 (3.5563) grad_norm: 1.0636 (inf) time: 0.5098 [2021-03-25 18:38:39 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 720/1251] eta: 0:04:31 lr: 0.000818 loss: 3.4922 (3.5545) grad_norm: 1.0733 (inf) time: 0.5095 [2021-03-25 18:38:44 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 730/1251] eta: 0:04:26 lr: 0.000818 loss: 3.4922 (3.5555) grad_norm: 1.0847 (inf) time: 0.5155 [2021-03-25 18:38:49 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 740/1251] eta: 0:04:21 lr: 0.000818 loss: 3.7228 (3.5556) grad_norm: 1.0860 (inf) time: 0.5260 [2021-03-25 18:38:54 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 750/1251] eta: 0:04:16 lr: 0.000818 loss: 3.6065 (3.5545) grad_norm: 1.1487 (inf) time: 0.5207 [2021-03-25 18:38:59 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 760/1251] eta: 0:04:11 lr: 0.000818 loss: 3.5827 (3.5547) grad_norm: 1.1445 (inf) time: 0.5081 [2021-03-25 18:39:04 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 770/1251] eta: 0:04:06 lr: 0.000818 loss: 3.4220 (3.5525) grad_norm: 1.1060 (inf) time: 0.5059 [2021-03-25 18:39:09 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 780/1251] eta: 0:04:00 lr: 0.000818 loss: 3.6941 (3.5518) grad_norm: 1.0927 (inf) time: 0.5023 [2021-03-25 18:39:14 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 790/1251] eta: 0:03:55 lr: 0.000818 loss: 3.7940 (3.5542) grad_norm: 1.1246 (inf) time: 0.4970 [2021-03-25 18:39:19 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 800/1251] eta: 0:03:50 lr: 0.000818 loss: 3.8435 (3.5536) grad_norm: 1.1264 (inf) time: 0.4959 [2021-03-25 18:39:24 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 810/1251] eta: 0:03:45 lr: 0.000818 loss: 3.7137 (3.5543) grad_norm: 1.0777 (inf) time: 0.5017 [2021-03-25 18:39:29 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 820/1251] eta: 0:03:40 lr: 0.000818 loss: 3.7166 (3.5581) grad_norm: 1.0694 (inf) time: 0.5116 [2021-03-25 18:39:34 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 830/1251] eta: 0:03:35 lr: 0.000818 loss: 3.7783 (3.5591) grad_norm: 1.0470 (inf) time: 0.5110 [2021-03-25 18:39:39 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 840/1251] eta: 0:03:29 lr: 0.000818 loss: 3.7192 (3.5585) grad_norm: 1.0180 (inf) time: 0.5035 [2021-03-25 18:39:45 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 850/1251] eta: 0:03:24 lr: 0.000818 loss: 3.8521 (3.5610) grad_norm: 1.0343 (inf) time: 0.5065 [2021-03-25 18:39:50 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 860/1251] eta: 0:03:19 lr: 0.000818 loss: 3.9860 (3.5631) grad_norm: 1.0934 (inf) time: 0.5098 [2021-03-25 18:39:55 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 870/1251] eta: 0:03:14 lr: 0.000818 loss: 3.5815 (3.5625) grad_norm: 1.0932 (inf) time: 0.5085 [2021-03-25 18:40:00 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 880/1251] eta: 0:03:09 lr: 0.000818 loss: 3.5446 (3.5632) grad_norm: 1.0385 (inf) time: 0.5042 [2021-03-25 18:40:05 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 890/1251] eta: 0:03:04 lr: 0.000818 loss: 3.6116 (3.5633) grad_norm: 1.0886 (inf) time: 0.5058 [2021-03-25 18:40:10 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 900/1251] eta: 0:02:59 lr: 0.000818 loss: 3.6889 (3.5640) grad_norm: 1.1203 (inf) time: 0.5098 [2021-03-25 18:40:15 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 910/1251] eta: 0:02:54 lr: 0.000818 loss: 3.7696 (3.5639) grad_norm: 1.1030 (inf) time: 0.5068 [2021-03-25 18:40:20 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 920/1251] eta: 0:02:48 lr: 0.000818 loss: 3.7467 (3.5653) grad_norm: 1.0975 (inf) time: 0.5053 [2021-03-25 18:40:25 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 930/1251] eta: 0:02:43 lr: 0.000818 loss: 3.7169 (3.5661) grad_norm: 1.0664 (inf) time: 0.5120 [2021-03-25 18:40:30 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 940/1251] eta: 0:02:38 lr: 0.000818 loss: 3.7169 (3.5663) grad_norm: 1.0656 (inf) time: 0.5108 [2021-03-25 18:40:35 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 950/1251] eta: 0:02:33 lr: 0.000817 loss: 3.6892 (3.5638) grad_norm: 1.0446 (inf) time: 0.5058 [2021-03-25 18:40:41 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 960/1251] eta: 0:02:28 lr: 0.000817 loss: 3.6892 (3.5655) grad_norm: 1.0963 (inf) time: 0.5127 [2021-03-25 18:40:46 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 970/1251] eta: 0:02:23 lr: 0.000817 loss: 3.6329 (3.5642) grad_norm: 1.0963 (inf) time: 0.5100 [2021-03-25 18:40:51 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 980/1251] eta: 0:02:18 lr: 0.000817 loss: 3.5443 (3.5649) grad_norm: 1.0467 (inf) time: 0.5011 [2021-03-25 18:40:56 swin_small_patch4_window7_224] INFO: Epoch: [84] [ 990/1251] eta: 0:02:13 lr: 0.000817 loss: 3.5935 (3.5650) grad_norm: 1.0618 (inf) time: 0.5020 [2021-03-25 18:41:01 swin_small_patch4_window7_224] INFO: Epoch: [84] [1000/1251] eta: 0:02:08 lr: 0.000817 loss: 3.6653 (3.5645) grad_norm: 1.0772 (inf) time: 0.5065 [2021-03-25 18:41:06 swin_small_patch4_window7_224] INFO: Epoch: [84] [1010/1251] eta: 0:02:02 lr: 0.000817 loss: 3.5773 (3.5614) grad_norm: 1.0632 (inf) time: 0.5115 [2021-03-25 18:41:11 swin_small_patch4_window7_224] INFO: Epoch: [84] [1020/1251] eta: 0:01:57 lr: 0.000817 loss: 3.6915 (3.5642) grad_norm: 1.1165 (inf) time: 0.5113 [2021-03-25 18:41:16 swin_small_patch4_window7_224] INFO: Epoch: [84] [1030/1251] eta: 0:01:52 lr: 0.000817 loss: 3.7244 (3.5653) grad_norm: 1.1120 (inf) time: 0.5052 [2021-03-25 18:41:21 swin_small_patch4_window7_224] INFO: Epoch: [84] [1040/1251] eta: 0:01:47 lr: 0.000817 loss: 3.6428 (3.5656) grad_norm: 1.0876 (inf) time: 0.5089 [2021-03-25 18:41:26 swin_small_patch4_window7_224] INFO: Epoch: [84] [1050/1251] eta: 0:01:42 lr: 0.000817 loss: 3.6296 (3.5635) grad_norm: 1.0910 (inf) time: 0.5106 [2021-03-25 18:41:31 swin_small_patch4_window7_224] INFO: Epoch: [84] [1060/1251] eta: 0:01:37 lr: 0.000817 loss: 3.3385 (3.5619) grad_norm: 1.0713 (inf) time: 0.5060 [2021-03-25 18:41:36 swin_small_patch4_window7_224] INFO: Epoch: [84] [1070/1251] eta: 0:01:32 lr: 0.000817 loss: 3.5598 (3.5627) grad_norm: 1.0092 (inf) time: 0.5102 [2021-03-25 18:41:41 swin_small_patch4_window7_224] INFO: Epoch: [84] [1080/1251] eta: 0:01:27 lr: 0.000817 loss: 3.5674 (3.5615) grad_norm: 1.0061 (inf) time: 0.5095 [2021-03-25 18:41:46 swin_small_patch4_window7_224] INFO: Epoch: [84] [1090/1251] eta: 0:01:22 lr: 0.000817 loss: 3.5643 (3.5620) grad_norm: 1.0290 (inf) time: 0.5019 [2021-03-25 18:41:51 swin_small_patch4_window7_224] INFO: Epoch: [84] [1100/1251] eta: 0:01:17 lr: 0.000817 loss: 3.6114 (3.5618) grad_norm: 1.0262 (inf) time: 0.5002 [2021-03-25 18:41:57 swin_small_patch4_window7_224] INFO: Epoch: [84] [1110/1251] eta: 0:01:11 lr: 0.000817 loss: 3.5466 (3.5616) grad_norm: 1.0719 (inf) time: 0.5051 [2021-03-25 18:42:02 swin_small_patch4_window7_224] INFO: Epoch: [84] [1120/1251] eta: 0:01:06 lr: 0.000817 loss: 3.6171 (3.5605) grad_norm: 1.1560 (inf) time: 0.5106 [2021-03-25 18:42:07 swin_small_patch4_window7_224] INFO: Epoch: [84] [1130/1251] eta: 0:01:01 lr: 0.000817 loss: 3.7982 (3.5611) grad_norm: 1.1271 (inf) time: 0.5084 [2021-03-25 18:42:12 swin_small_patch4_window7_224] INFO: Epoch: [84] [1140/1251] eta: 0:00:56 lr: 0.000817 loss: 3.6963 (3.5606) grad_norm: 1.1271 (inf) time: 0.5048 [2021-03-25 18:42:17 swin_small_patch4_window7_224] INFO: Epoch: [84] [1150/1251] eta: 0:00:51 lr: 0.000817 loss: 3.6164 (3.5596) grad_norm: 1.1176 (inf) time: 0.5083 [2021-03-25 18:42:22 swin_small_patch4_window7_224] INFO: Epoch: [84] [1160/1251] eta: 0:00:46 lr: 0.000817 loss: 3.6591 (3.5607) grad_norm: 1.0570 (inf) time: 0.5069 [2021-03-25 18:42:27 swin_small_patch4_window7_224] INFO: Epoch: [84] [1170/1251] eta: 0:00:41 lr: 0.000817 loss: 3.8138 (3.5636) grad_norm: 1.1366 (inf) time: 0.4963 [2021-03-25 18:42:32 swin_small_patch4_window7_224] INFO: Epoch: [84] [1180/1251] eta: 0:00:36 lr: 0.000817 loss: 3.8138 (3.5640) grad_norm: 1.1186 (inf) time: 0.4999 [2021-03-25 18:42:37 swin_small_patch4_window7_224] INFO: Epoch: [84] [1190/1251] eta: 0:00:31 lr: 0.000817 loss: 3.4562 (3.5621) grad_norm: 1.0517 (inf) time: 0.5017 [2021-03-25 18:42:42 swin_small_patch4_window7_224] INFO: Epoch: [84] [1200/1251] eta: 0:00:25 lr: 0.000817 loss: 3.4562 (3.5612) grad_norm: 1.1009 (inf) time: 0.4996 [2021-03-25 18:42:47 swin_small_patch4_window7_224] INFO: Epoch: [84] [1210/1251] eta: 0:00:20 lr: 0.000817 loss: 3.5609 (3.5606) grad_norm: 1.1256 (inf) time: 0.5026 [2021-03-25 18:42:52 swin_small_patch4_window7_224] INFO: Epoch: [84] [1220/1251] eta: 0:00:15 lr: 0.000817 loss: 3.5954 (3.5606) grad_norm: 1.0403 (inf) time: 0.5011 [2021-03-25 18:42:57 swin_small_patch4_window7_224] INFO: Epoch: [84] [1230/1251] eta: 0:00:10 lr: 0.000817 loss: 3.4915 (3.5604) grad_norm: 1.0517 (inf) time: 0.4981 [2021-03-25 18:43:02 swin_small_patch4_window7_224] INFO: Epoch: [84] [1240/1251] eta: 0:00:05 lr: 0.000817 loss: 3.8206 (3.5627) grad_norm: 1.0796 (inf) time: 0.5009 [2021-03-25 18:43:07 swin_small_patch4_window7_224] INFO: Epoch: [84] [1250/1251] eta: 0:00:00 lr: 0.000817 loss: 3.7799 (3.5620) grad_norm: 1.0639 (inf) time: 0.5061 [2021-03-25 18:43:11 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:26 loss: 0.8161 (0.8161) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-25 18:43:14 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0422 (1.0687) acc1: 76.5625 (77.2727) acc5: 92.1875 (93.0398) [2021-03-25 18:43:16 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0422 (1.0413) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.3036) [2021-03-25 18:43:18 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0288 (1.0707) acc1: 73.4375 (75.1008) acc5: 93.7500 (93.0444) [2021-03-25 18:43:21 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0438 (1.0780) acc1: 71.8750 (74.4665) acc5: 93.7500 (92.9497) [2021-03-25 18:43:21 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1193 (1.0755) acc1: 73.4375 (74.4960) acc5: 92.1875 (92.9280) [2021-03-25 18:43:26 swin_small_patch4_window7_224] INFO: * Acc@1 75.130 Acc@5 92.994 loss 1.055 [2021-03-25 18:43:26 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.1% [2021-03-25 18:43:26 swin_small_patch4_window7_224] INFO: Max accuracy: 75.23% [2021-03-25 18:43:30 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 0/1251] eta: 1:23:03 lr: 0.000817 loss: 2.5840 (2.5840) grad_norm: 1.1074 (1.1074) time: 3.9835 [2021-03-25 18:43:35 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 10/1251] eta: 0:17:28 lr: 0.000816 loss: 3.5514 (3.4680) grad_norm: 1.0825 (1.1283) time: 0.8450 [2021-03-25 18:43:40 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 20/1251] eta: 0:14:01 lr: 0.000816 loss: 3.5514 (3.5713) grad_norm: 1.0825 (1.1277) time: 0.5190 [2021-03-25 18:43:45 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 30/1251] eta: 0:12:47 lr: 0.000816 loss: 3.8224 (3.6763) grad_norm: 1.0709 (1.1053) time: 0.5090 [2021-03-25 18:43:50 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 40/1251] eta: 0:12:08 lr: 0.000816 loss: 3.7623 (3.6528) grad_norm: 1.0660 (1.1125) time: 0.5154 [2021-03-25 18:43:55 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 50/1251] eta: 0:11:40 lr: 0.000816 loss: 3.6875 (3.6282) grad_norm: 1.0682 (1.1173) time: 0.5128 [2021-03-25 18:44:00 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 60/1251] eta: 0:11:19 lr: 0.000816 loss: 3.6359 (3.5940) grad_norm: 1.1085 (1.1168) time: 0.5066 [2021-03-25 18:44:05 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 70/1251] eta: 0:11:02 lr: 0.000816 loss: 3.6359 (3.5899) grad_norm: 1.1085 (1.1168) time: 0.5036 [2021-03-25 18:44:10 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 80/1251] eta: 0:10:49 lr: 0.000816 loss: 3.6096 (3.5851) grad_norm: 1.0858 (1.1158) time: 0.5054 [2021-03-25 18:44:16 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 90/1251] eta: 0:10:37 lr: 0.000816 loss: 3.3314 (3.5586) grad_norm: 1.0486 (1.1143) time: 0.5072 [2021-03-25 18:44:21 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 100/1251] eta: 0:10:26 lr: 0.000816 loss: 3.5188 (3.5483) grad_norm: 1.0880 (1.1191) time: 0.5045 [2021-03-25 18:44:26 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 110/1251] eta: 0:10:18 lr: 0.000816 loss: 3.6684 (3.5572) grad_norm: 1.1159 (1.1171) time: 0.5112 [2021-03-25 18:44:31 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 120/1251] eta: 0:10:08 lr: 0.000816 loss: 3.6663 (3.5584) grad_norm: 1.0880 (1.1167) time: 0.5074 [2021-03-25 18:44:36 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 130/1251] eta: 0:10:01 lr: 0.000816 loss: 3.6376 (3.5602) grad_norm: 1.1703 (1.1285) time: 0.5032 [2021-03-25 18:44:41 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 140/1251] eta: 0:09:53 lr: 0.000816 loss: 3.3801 (3.5253) grad_norm: 1.2218 (1.1369) time: 0.5076 [2021-03-25 18:44:46 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 150/1251] eta: 0:09:46 lr: 0.000816 loss: 3.3135 (3.5252) grad_norm: 1.1808 (1.1392) time: 0.5075 [2021-03-25 18:44:51 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 160/1251] eta: 0:09:39 lr: 0.000816 loss: 3.4124 (3.5163) grad_norm: 1.0906 (1.1377) time: 0.5092 [2021-03-25 18:44:56 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 170/1251] eta: 0:09:33 lr: 0.000816 loss: 3.6392 (3.5210) grad_norm: 1.0605 (1.1344) time: 0.5163 [2021-03-25 18:45:01 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 180/1251] eta: 0:09:25 lr: 0.000816 loss: 3.8101 (3.5260) grad_norm: 1.0669 (1.1314) time: 0.5072 [2021-03-25 18:45:06 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 190/1251] eta: 0:09:19 lr: 0.000816 loss: 3.5527 (3.5197) grad_norm: 1.1012 (1.1328) time: 0.4972 [2021-03-25 18:45:11 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 200/1251] eta: 0:09:12 lr: 0.000816 loss: 3.7017 (3.5328) grad_norm: 1.1021 (1.1307) time: 0.5031 [2021-03-25 18:45:16 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 210/1251] eta: 0:09:06 lr: 0.000816 loss: 3.6791 (3.5215) grad_norm: 1.0929 (1.1293) time: 0.5035 [2021-03-25 18:45:21 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 220/1251] eta: 0:09:00 lr: 0.000816 loss: 3.6460 (3.5249) grad_norm: 1.0929 (1.1277) time: 0.5088 [2021-03-25 18:45:27 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 230/1251] eta: 0:08:54 lr: 0.000816 loss: 3.7544 (3.5217) grad_norm: 1.1193 (1.1283) time: 0.5156 [2021-03-25 18:45:32 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 240/1251] eta: 0:08:48 lr: 0.000816 loss: 3.5518 (3.5244) grad_norm: 1.1710 (1.1281) time: 0.5098 [2021-03-25 18:45:37 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 250/1251] eta: 0:08:43 lr: 0.000816 loss: 3.5434 (3.5216) grad_norm: 1.0894 (1.1275) time: 0.5084 [2021-03-25 18:45:42 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 260/1251] eta: 0:08:37 lr: 0.000816 loss: 3.4814 (3.5210) grad_norm: 1.0444 (1.1244) time: 0.5097 [2021-03-25 18:45:47 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 270/1251] eta: 0:08:31 lr: 0.000816 loss: 3.5443 (3.5207) grad_norm: 1.0346 (1.1243) time: 0.5075 [2021-03-25 18:45:52 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 280/1251] eta: 0:08:26 lr: 0.000816 loss: 3.7583 (3.5330) grad_norm: 1.1418 (1.1269) time: 0.5097 [2021-03-25 18:45:57 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 290/1251] eta: 0:08:20 lr: 0.000816 loss: 3.9022 (3.5370) grad_norm: 1.1418 (1.1272) time: 0.5078 [2021-03-25 18:46:02 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 300/1251] eta: 0:08:14 lr: 0.000816 loss: 3.6738 (3.5394) grad_norm: 1.1623 (1.1296) time: 0.5070 [2021-03-25 18:46:07 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 310/1251] eta: 0:08:09 lr: 0.000816 loss: 3.3910 (3.5372) grad_norm: 1.1702 (1.1312) time: 0.5068 [2021-03-25 18:46:12 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 320/1251] eta: 0:08:03 lr: 0.000815 loss: 3.6129 (3.5402) grad_norm: 1.1318 (1.1303) time: 0.5033 [2021-03-25 18:46:17 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 330/1251] eta: 0:07:57 lr: 0.000815 loss: 3.8177 (3.5465) grad_norm: 1.1170 (1.1305) time: 0.5000 [2021-03-25 18:46:22 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 340/1251] eta: 0:07:52 lr: 0.000815 loss: 3.8209 (3.5475) grad_norm: 1.0844 (1.1289) time: 0.5052 [2021-03-25 18:46:27 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 350/1251] eta: 0:07:46 lr: 0.000815 loss: 3.6773 (3.5437) grad_norm: 1.0783 (1.1286) time: 0.5097 [2021-03-25 18:46:33 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 360/1251] eta: 0:07:41 lr: 0.000815 loss: 3.3462 (3.5397) grad_norm: 1.1746 (1.1301) time: 0.5055 [2021-03-25 18:46:38 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 370/1251] eta: 0:07:35 lr: 0.000815 loss: 3.4143 (3.5374) grad_norm: 1.1259 (1.1286) time: 0.5054 [2021-03-25 18:46:43 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 380/1251] eta: 0:07:30 lr: 0.000815 loss: 3.5661 (3.5399) grad_norm: 1.0350 (1.1278) time: 0.5038 [2021-03-25 18:46:48 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 390/1251] eta: 0:07:24 lr: 0.000815 loss: 3.6831 (3.5378) grad_norm: 1.0496 (1.1276) time: 0.5046 [2021-03-25 18:46:53 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 400/1251] eta: 0:07:19 lr: 0.000815 loss: 3.5806 (3.5340) grad_norm: 1.0891 (1.1270) time: 0.5079 [2021-03-25 18:46:58 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 410/1251] eta: 0:07:14 lr: 0.000815 loss: 3.4546 (3.5346) grad_norm: 1.0537 (1.1253) time: 0.5055 [2021-03-25 18:47:03 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 420/1251] eta: 0:07:08 lr: 0.000815 loss: 3.5749 (3.5354) grad_norm: 1.0723 (1.1248) time: 0.5090 [2021-03-25 18:47:08 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 430/1251] eta: 0:07:03 lr: 0.000815 loss: 3.6022 (3.5333) grad_norm: 1.0868 (1.1248) time: 0.5150 [2021-03-25 18:47:13 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 440/1251] eta: 0:06:58 lr: 0.000815 loss: 3.4569 (3.5330) grad_norm: 1.0771 (1.1238) time: 0.5174 [2021-03-25 18:47:18 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 450/1251] eta: 0:06:53 lr: 0.000815 loss: 3.6966 (3.5327) grad_norm: 1.0743 (1.1232) time: 0.5115 [2021-03-25 18:47:23 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 460/1251] eta: 0:06:47 lr: 0.000815 loss: 3.3955 (3.5287) grad_norm: 1.1575 (1.1238) time: 0.5060 [2021-03-25 18:47:28 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 470/1251] eta: 0:06:42 lr: 0.000815 loss: 3.3955 (3.5273) grad_norm: 1.1800 (1.1254) time: 0.5042 [2021-03-25 18:47:33 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 480/1251] eta: 0:06:37 lr: 0.000815 loss: 3.3353 (3.5218) grad_norm: 1.1750 (1.1259) time: 0.5036 [2021-03-25 18:47:39 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 490/1251] eta: 0:06:31 lr: 0.000815 loss: 3.4472 (3.5227) grad_norm: 1.0985 (1.1271) time: 0.5057 [2021-03-25 18:47:44 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 500/1251] eta: 0:06:26 lr: 0.000815 loss: 3.6214 (3.5249) grad_norm: 1.0528 (1.1260) time: 0.5034 [2021-03-25 18:47:49 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 510/1251] eta: 0:06:21 lr: 0.000815 loss: 3.7001 (3.5252) grad_norm: 1.0426 (1.1259) time: 0.4992 [2021-03-25 18:47:54 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 520/1251] eta: 0:06:16 lr: 0.000815 loss: 3.5337 (3.5287) grad_norm: 1.1203 (1.1257) time: 0.5047 [2021-03-25 18:47:59 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 530/1251] eta: 0:06:10 lr: 0.000815 loss: 3.5337 (3.5284) grad_norm: 1.1099 (1.1251) time: 0.5145 [2021-03-25 18:48:04 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 540/1251] eta: 0:06:05 lr: 0.000815 loss: 3.5168 (3.5253) grad_norm: 1.1099 (1.1248) time: 0.5116 [2021-03-25 18:48:09 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 550/1251] eta: 0:06:00 lr: 0.000815 loss: 3.5168 (3.5234) grad_norm: 1.0879 (1.1239) time: 0.5092 [2021-03-25 18:48:14 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 560/1251] eta: 0:05:55 lr: 0.000815 loss: 3.5083 (3.5239) grad_norm: 1.0464 (1.1233) time: 0.5072 [2021-03-25 18:48:19 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 570/1251] eta: 0:05:49 lr: 0.000815 loss: 3.7485 (3.5296) grad_norm: 1.0464 (1.1223) time: 0.5053 [2021-03-25 18:48:24 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 580/1251] eta: 0:05:44 lr: 0.000815 loss: 3.9680 (3.5366) grad_norm: 1.0694 (1.1219) time: 0.5095 [2021-03-25 18:48:29 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 590/1251] eta: 0:05:39 lr: 0.000815 loss: 3.7761 (3.5362) grad_norm: 1.0910 (1.1220) time: 0.5108 [2021-03-25 18:48:34 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 600/1251] eta: 0:05:34 lr: 0.000815 loss: 3.3138 (3.5292) grad_norm: 1.1310 (1.1226) time: 0.5087 [2021-03-25 18:48:39 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 610/1251] eta: 0:05:29 lr: 0.000815 loss: 3.2939 (3.5269) grad_norm: 1.1531 (1.1230) time: 0.5041 [2021-03-25 18:48:44 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 620/1251] eta: 0:05:23 lr: 0.000815 loss: 3.7731 (3.5330) grad_norm: 1.1373 (1.1233) time: 0.5034 [2021-03-25 18:48:50 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 630/1251] eta: 0:05:18 lr: 0.000814 loss: 3.7731 (3.5324) grad_norm: 1.1202 (1.1232) time: 0.5062 [2021-03-25 18:48:55 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 640/1251] eta: 0:05:13 lr: 0.000814 loss: 3.6969 (3.5380) grad_norm: 1.0557 (1.1235) time: 0.5063 [2021-03-25 18:49:00 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 650/1251] eta: 0:05:08 lr: 0.000814 loss: 3.5386 (3.5345) grad_norm: 1.0453 (1.1223) time: 0.5029 [2021-03-25 18:49:05 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 660/1251] eta: 0:05:03 lr: 0.000814 loss: 3.3094 (3.5341) grad_norm: 1.0304 (1.1210) time: 0.5041 [2021-03-25 18:49:10 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 670/1251] eta: 0:04:57 lr: 0.000814 loss: 3.5468 (3.5330) grad_norm: 1.0304 (1.1203) time: 0.5089 [2021-03-25 18:49:15 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 680/1251] eta: 0:04:52 lr: 0.000814 loss: 3.5962 (3.5339) grad_norm: 1.1026 (1.1203) time: 0.5058 [2021-03-25 18:49:20 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 690/1251] eta: 0:04:47 lr: 0.000814 loss: 3.7276 (3.5375) grad_norm: 1.1438 (1.1213) time: 0.5001 [2021-03-25 18:49:25 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 700/1251] eta: 0:04:42 lr: 0.000814 loss: 3.5922 (3.5338) grad_norm: 1.0730 (1.1208) time: 0.5023 [2021-03-25 18:49:30 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 710/1251] eta: 0:04:37 lr: 0.000814 loss: 3.5256 (3.5338) grad_norm: 1.0840 (1.1207) time: 0.5107 [2021-03-25 18:49:35 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 720/1251] eta: 0:04:32 lr: 0.000814 loss: 3.5837 (3.5341) grad_norm: 1.0897 (1.1203) time: 0.5138 [2021-03-25 18:49:40 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 730/1251] eta: 0:04:26 lr: 0.000814 loss: 3.5837 (3.5328) grad_norm: 1.0561 (1.1195) time: 0.5100 [2021-03-25 18:49:45 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 740/1251] eta: 0:04:21 lr: 0.000814 loss: 3.4760 (3.5330) grad_norm: 1.0739 (1.1204) time: 0.5149 [2021-03-25 18:49:51 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 750/1251] eta: 0:04:16 lr: 0.000814 loss: 3.5791 (3.5334) grad_norm: 1.0739 (1.1197) time: 0.5152 [2021-03-25 18:49:56 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 760/1251] eta: 0:04:11 lr: 0.000814 loss: 3.6554 (3.5342) grad_norm: 1.0159 (1.1195) time: 0.5088 [2021-03-25 18:50:01 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 770/1251] eta: 0:04:06 lr: 0.000814 loss: 3.5136 (3.5319) grad_norm: 1.0159 (1.1183) time: 0.5040 [2021-03-25 18:50:06 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 780/1251] eta: 0:04:01 lr: 0.000814 loss: 3.5136 (3.5305) grad_norm: 1.0731 (1.1187) time: 0.5015 [2021-03-25 18:50:11 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 790/1251] eta: 0:03:56 lr: 0.000814 loss: 3.4108 (3.5302) grad_norm: 1.1432 (1.1192) time: 0.5064 [2021-03-25 18:50:16 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 800/1251] eta: 0:03:50 lr: 0.000814 loss: 3.4520 (3.5285) grad_norm: 1.0933 (1.1192) time: 0.5059 [2021-03-25 18:50:21 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 810/1251] eta: 0:03:45 lr: 0.000814 loss: 3.4520 (3.5248) grad_norm: 1.0724 (1.1187) time: 0.5005 [2021-03-25 18:50:26 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 820/1251] eta: 0:03:40 lr: 0.000814 loss: 3.4575 (3.5247) grad_norm: 1.1094 (1.1187) time: 0.5043 [2021-03-25 18:50:31 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 830/1251] eta: 0:03:35 lr: 0.000814 loss: 3.6544 (3.5277) grad_norm: 1.1094 (1.1185) time: 0.5054 [2021-03-25 18:50:36 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 840/1251] eta: 0:03:30 lr: 0.000814 loss: 3.5292 (3.5263) grad_norm: 1.1258 (1.1190) time: 0.4994 [2021-03-25 18:50:41 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 850/1251] eta: 0:03:25 lr: 0.000814 loss: 3.3633 (3.5228) grad_norm: 1.1482 (1.1193) time: 0.4983 [2021-03-25 18:50:46 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 860/1251] eta: 0:03:19 lr: 0.000814 loss: 3.2588 (3.5212) grad_norm: 1.1113 (1.1194) time: 0.5105 [2021-03-25 18:50:51 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 870/1251] eta: 0:03:14 lr: 0.000814 loss: 3.4755 (3.5197) grad_norm: 1.1498 (1.1194) time: 0.5159 [2021-03-25 18:50:56 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 880/1251] eta: 0:03:09 lr: 0.000814 loss: 3.5543 (3.5196) grad_norm: 1.1457 (1.1197) time: 0.5088 [2021-03-25 18:51:01 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 890/1251] eta: 0:03:04 lr: 0.000814 loss: 3.6527 (3.5202) grad_norm: 1.1088 (1.1191) time: 0.5022 [2021-03-25 18:51:06 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 900/1251] eta: 0:02:59 lr: 0.000814 loss: 3.7425 (3.5236) grad_norm: 1.0186 (1.1178) time: 0.4988 [2021-03-25 18:51:11 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 910/1251] eta: 0:02:54 lr: 0.000814 loss: 3.7990 (3.5256) grad_norm: 0.9991 (1.1168) time: 0.5046 [2021-03-25 18:51:16 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 920/1251] eta: 0:02:49 lr: 0.000814 loss: 3.7990 (3.5282) grad_norm: 1.0214 (1.1161) time: 0.5068 [2021-03-25 18:51:21 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 930/1251] eta: 0:02:43 lr: 0.000814 loss: 3.7432 (3.5287) grad_norm: 1.0526 (1.1160) time: 0.5005 [2021-03-25 18:51:26 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 940/1251] eta: 0:02:38 lr: 0.000813 loss: 3.5189 (3.5284) grad_norm: 1.1075 (1.1157) time: 0.5053 [2021-03-25 18:51:32 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 950/1251] eta: 0:02:33 lr: 0.000813 loss: 3.5189 (3.5270) grad_norm: 1.1075 (1.1162) time: 0.5159 [2021-03-25 18:51:37 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 960/1251] eta: 0:02:28 lr: 0.000813 loss: 3.2399 (3.5238) grad_norm: 1.1961 (1.1169) time: 0.5072 [2021-03-25 18:51:42 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 970/1251] eta: 0:02:23 lr: 0.000813 loss: 3.4755 (3.5260) grad_norm: 1.1176 (1.1171) time: 0.5049 [2021-03-25 18:51:47 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 980/1251] eta: 0:02:18 lr: 0.000813 loss: 3.8022 (3.5285) grad_norm: 1.1176 (1.1176) time: 0.5149 [2021-03-25 18:51:52 swin_small_patch4_window7_224] INFO: Epoch: [85] [ 990/1251] eta: 0:02:13 lr: 0.000813 loss: 3.7947 (3.5307) grad_norm: 1.1162 (1.1171) time: 0.5159 [2021-03-25 18:51:57 swin_small_patch4_window7_224] INFO: Epoch: [85] [1000/1251] eta: 0:02:08 lr: 0.000813 loss: 3.5159 (3.5274) grad_norm: 1.0923 (1.1172) time: 0.5109 [2021-03-25 18:52:02 swin_small_patch4_window7_224] INFO: Epoch: [85] [1010/1251] eta: 0:02:03 lr: 0.000813 loss: 3.4374 (3.5277) grad_norm: 1.1173 (1.1177) time: 0.5085 [2021-03-25 18:52:07 swin_small_patch4_window7_224] INFO: Epoch: [85] [1020/1251] eta: 0:01:58 lr: 0.000813 loss: 3.7380 (3.5289) grad_norm: 1.1593 (1.1186) time: 0.5127 [2021-03-25 18:52:12 swin_small_patch4_window7_224] INFO: Epoch: [85] [1030/1251] eta: 0:01:52 lr: 0.000813 loss: 3.7583 (3.5296) grad_norm: 1.1593 (1.1191) time: 0.5126 [2021-03-25 18:52:18 swin_small_patch4_window7_224] INFO: Epoch: [85] [1040/1251] eta: 0:01:47 lr: 0.000813 loss: 3.6617 (3.5291) grad_norm: 1.1182 (1.1193) time: 0.5064 [2021-03-25 18:52:23 swin_small_patch4_window7_224] INFO: Epoch: [85] [1050/1251] eta: 0:01:42 lr: 0.000813 loss: 3.6345 (3.5290) grad_norm: 1.0995 (1.1194) time: 0.5054 [2021-03-25 18:52:28 swin_small_patch4_window7_224] INFO: Epoch: [85] [1060/1251] eta: 0:01:37 lr: 0.000813 loss: 3.7437 (3.5312) grad_norm: 1.1028 (1.1196) time: 0.5093 [2021-03-25 18:52:33 swin_small_patch4_window7_224] INFO: Epoch: [85] [1070/1251] eta: 0:01:32 lr: 0.000813 loss: 3.6941 (3.5296) grad_norm: 1.1442 (1.1204) time: 0.5092 [2021-03-25 18:52:38 swin_small_patch4_window7_224] INFO: Epoch: [85] [1080/1251] eta: 0:01:27 lr: 0.000813 loss: 3.6006 (3.5298) grad_norm: 1.1136 (1.1203) time: 0.5063 [2021-03-25 18:52:43 swin_small_patch4_window7_224] INFO: Epoch: [85] [1090/1251] eta: 0:01:22 lr: 0.000813 loss: 3.8018 (3.5294) grad_norm: 1.0828 (1.1197) time: 0.5062 [2021-03-25 18:52:48 swin_small_patch4_window7_224] INFO: Epoch: [85] [1100/1251] eta: 0:01:17 lr: 0.000813 loss: 3.6066 (3.5288) grad_norm: 1.0235 (1.1192) time: 0.5027 [2021-03-25 18:52:53 swin_small_patch4_window7_224] INFO: Epoch: [85] [1110/1251] eta: 0:01:11 lr: 0.000813 loss: 3.4817 (3.5288) grad_norm: 1.0497 (1.1192) time: 0.5018 [2021-03-25 18:52:58 swin_small_patch4_window7_224] INFO: Epoch: [85] [1120/1251] eta: 0:01:06 lr: 0.000813 loss: 3.6084 (3.5311) grad_norm: 1.0765 (1.1188) time: 0.5078 [2021-03-25 18:53:03 swin_small_patch4_window7_224] INFO: Epoch: [85] [1130/1251] eta: 0:01:01 lr: 0.000813 loss: 3.7816 (3.5326) grad_norm: 1.0765 (1.1184) time: 0.5040 [2021-03-25 18:53:08 swin_small_patch4_window7_224] INFO: Epoch: [85] [1140/1251] eta: 0:00:56 lr: 0.000813 loss: 3.7324 (3.5325) grad_norm: 1.0517 (1.1177) time: 0.5052 [2021-03-25 18:53:13 swin_small_patch4_window7_224] INFO: Epoch: [85] [1150/1251] eta: 0:00:51 lr: 0.000813 loss: 3.6774 (3.5347) grad_norm: 1.0517 (1.1174) time: 0.5082 [2021-03-25 18:53:18 swin_small_patch4_window7_224] INFO: Epoch: [85] [1160/1251] eta: 0:00:46 lr: 0.000813 loss: 3.6774 (3.5336) grad_norm: 1.0543 (1.1168) time: 0.5058 [2021-03-25 18:53:23 swin_small_patch4_window7_224] INFO: Epoch: [85] [1170/1251] eta: 0:00:41 lr: 0.000813 loss: 3.5757 (3.5333) grad_norm: 1.1247 (1.1177) time: 0.5112 [2021-03-25 18:53:29 swin_small_patch4_window7_224] INFO: Epoch: [85] [1180/1251] eta: 0:00:36 lr: 0.000813 loss: 3.4870 (3.5323) grad_norm: 1.1737 (1.1182) time: 0.5112 [2021-03-25 18:53:34 swin_small_patch4_window7_224] INFO: Epoch: [85] [1190/1251] eta: 0:00:31 lr: 0.000813 loss: 3.6760 (3.5338) grad_norm: 1.1157 (1.1183) time: 0.5114 [2021-03-25 18:53:39 swin_small_patch4_window7_224] INFO: Epoch: [85] [1200/1251] eta: 0:00:26 lr: 0.000813 loss: 3.6540 (3.5337) grad_norm: 1.0995 (1.1185) time: 0.5100 [2021-03-25 18:53:44 swin_small_patch4_window7_224] INFO: Epoch: [85] [1210/1251] eta: 0:00:20 lr: 0.000813 loss: 3.4971 (3.5332) grad_norm: 1.0995 (1.1193) time: 0.5080 [2021-03-25 18:53:49 swin_small_patch4_window7_224] INFO: Epoch: [85] [1220/1251] eta: 0:00:15 lr: 0.000813 loss: 3.7238 (3.5352) grad_norm: 1.1090 (1.1194) time: 0.5040 [2021-03-25 18:53:54 swin_small_patch4_window7_224] INFO: Epoch: [85] [1230/1251] eta: 0:00:10 lr: 0.000813 loss: 3.5626 (3.5335) grad_norm: 1.0953 (1.1194) time: 0.5046 [2021-03-25 18:53:59 swin_small_patch4_window7_224] INFO: Epoch: [85] [1240/1251] eta: 0:00:05 lr: 0.000813 loss: 3.7818 (3.5353) grad_norm: 1.1450 (1.1201) time: 0.5053 [2021-03-25 18:54:04 swin_small_patch4_window7_224] INFO: Epoch: [85] [1250/1251] eta: 0:00:00 lr: 0.000812 loss: 3.7654 (3.5354) grad_norm: 1.2222 (1.1206) time: 0.5047 [2021-03-25 18:54:51 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 1.0358 (1.0358) acc1: 75.0000 (75.0000) acc5: 89.0625 (89.0625) [2021-03-25 18:54:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.0358 (1.0140) acc1: 76.5625 (76.2784) acc5: 93.7500 (93.3239) [2021-03-25 18:54:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.0334 (1.0596) acc1: 76.5625 (75.3720) acc5: 93.7500 (93.0804) [2021-03-25 18:54:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0894 (1.0902) acc1: 75.0000 (74.4456) acc5: 92.1875 (92.8931) [2021-03-25 18:54:56 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.1136 (1.0768) acc1: 73.4375 (74.7332) acc5: 92.1875 (92.8735) [2021-03-25 18:54:56 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9530 (1.0549) acc1: 75.0000 (74.9440) acc5: 93.7500 (93.1520) [2021-03-25 18:55:02 swin_small_patch4_window7_224] INFO: * Acc@1 75.368 Acc@5 92.984 loss 1.044 [2021-03-25 18:55:02 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.4% [2021-03-25 18:55:02 swin_small_patch4_window7_224] INFO: Max accuracy: 75.37% [2021-03-25 18:55:06 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 0/1251] eta: 1:25:50 lr: 0.000812 loss: 3.7760 (3.7760) grad_norm: 1.1254 (1.1254) time: 4.1167 [2021-03-25 18:55:12 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 10/1251] eta: 0:17:30 lr: 0.000812 loss: 3.9040 (3.6840) grad_norm: 1.1225 (1.0988) time: 0.8467 [2021-03-25 18:55:17 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 20/1251] eta: 0:14:10 lr: 0.000812 loss: 3.7283 (3.5908) grad_norm: 1.0820 (1.0809) time: 0.5199 [2021-03-25 18:55:22 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 30/1251] eta: 0:12:50 lr: 0.000812 loss: 3.7371 (3.6953) grad_norm: 1.0348 (1.0805) time: 0.5128 [2021-03-25 18:55:27 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 40/1251] eta: 0:12:08 lr: 0.000812 loss: 3.7603 (3.6196) grad_norm: 1.0203 (1.0793) time: 0.5077 [2021-03-25 18:55:32 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 50/1251] eta: 0:11:40 lr: 0.000812 loss: 3.6763 (3.6122) grad_norm: 1.1185 (1.0918) time: 0.5099 [2021-03-25 18:55:37 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 60/1251] eta: 0:11:19 lr: 0.000812 loss: 3.6392 (3.5360) grad_norm: 1.1351 (1.0988) time: 0.5073 [2021-03-25 18:55:42 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 70/1251] eta: 0:11:03 lr: 0.000812 loss: 3.6392 (3.5610) grad_norm: 1.0858 (1.1019) time: 0.5071 [2021-03-25 18:55:47 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 80/1251] eta: 0:10:50 lr: 0.000812 loss: 3.7619 (3.5566) grad_norm: 1.1442 (1.1102) time: 0.5085 [2021-03-25 18:55:52 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 90/1251] eta: 0:10:38 lr: 0.000812 loss: 3.6018 (3.5600) grad_norm: 1.1216 (1.1078) time: 0.5086 [2021-03-25 18:55:57 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 100/1251] eta: 0:10:27 lr: 0.000812 loss: 3.6455 (3.5666) grad_norm: 1.1003 (1.1093) time: 0.5035 [2021-03-25 18:56:02 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 110/1251] eta: 0:10:18 lr: 0.000812 loss: 3.7159 (3.5815) grad_norm: 1.1002 (1.1110) time: 0.5029 [2021-03-25 18:56:07 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 120/1251] eta: 0:10:08 lr: 0.000812 loss: 3.6768 (3.5736) grad_norm: 1.1214 (1.1141) time: 0.5047 [2021-03-25 18:56:13 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 130/1251] eta: 0:10:02 lr: 0.000812 loss: 3.5765 (3.5713) grad_norm: 1.1101 (1.1132) time: 0.5143 [2021-03-25 18:56:18 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 140/1251] eta: 0:09:55 lr: 0.000812 loss: 3.6403 (3.5782) grad_norm: 1.1101 (1.1156) time: 0.5183 [2021-03-25 18:56:23 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 150/1251] eta: 0:09:46 lr: 0.000812 loss: 3.6403 (3.5566) grad_norm: 1.1358 (1.1155) time: 0.5035 [2021-03-25 18:56:28 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 160/1251] eta: 0:09:40 lr: 0.000812 loss: 3.4869 (3.5476) grad_norm: 1.0897 (1.1142) time: 0.5063 [2021-03-25 18:56:33 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 170/1251] eta: 0:09:34 lr: 0.000812 loss: 3.5092 (3.5446) grad_norm: 1.0790 (1.1100) time: 0.5166 [2021-03-25 18:56:38 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 180/1251] eta: 0:09:27 lr: 0.000812 loss: 3.7463 (3.5592) grad_norm: 1.0324 (1.1060) time: 0.5113 [2021-03-25 18:56:43 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 190/1251] eta: 0:09:20 lr: 0.000812 loss: 3.7034 (3.5593) grad_norm: 1.0117 (1.1024) time: 0.5036 [2021-03-25 18:56:48 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 200/1251] eta: 0:09:14 lr: 0.000812 loss: 3.5490 (3.5633) grad_norm: 1.0117 (1.1000) time: 0.5082 [2021-03-25 18:56:53 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 210/1251] eta: 0:09:07 lr: 0.000812 loss: 3.7177 (3.5696) grad_norm: 1.0420 (1.0994) time: 0.5083 [2021-03-25 18:56:58 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 220/1251] eta: 0:09:01 lr: 0.000812 loss: 3.7531 (3.5770) grad_norm: 1.1358 (1.1043) time: 0.4989 [2021-03-25 18:57:03 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 230/1251] eta: 0:08:54 lr: 0.000812 loss: 3.8260 (3.5816) grad_norm: 1.1152 (1.1050) time: 0.4979 [2021-03-25 18:57:08 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 240/1251] eta: 0:08:49 lr: 0.000812 loss: 3.8260 (3.5866) grad_norm: 1.0966 (1.1058) time: 0.5058 [2021-03-25 18:57:13 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 250/1251] eta: 0:08:42 lr: 0.000812 loss: 3.6872 (3.5916) grad_norm: 1.0966 (1.1044) time: 0.5027 [2021-03-25 18:57:19 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 260/1251] eta: 0:08:37 lr: 0.000812 loss: 3.7809 (3.5967) grad_norm: 1.0649 (1.1030) time: 0.5019 [2021-03-25 18:57:24 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 270/1251] eta: 0:08:31 lr: 0.000812 loss: 3.7817 (3.6031) grad_norm: 1.0856 (1.1022) time: 0.5087 [2021-03-25 18:57:29 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 280/1251] eta: 0:08:25 lr: 0.000812 loss: 3.7661 (3.6088) grad_norm: 1.0754 (1.1015) time: 0.5075 [2021-03-25 18:57:34 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 290/1251] eta: 0:08:19 lr: 0.000812 loss: 3.7295 (3.6120) grad_norm: 1.0339 (1.0995) time: 0.5034 [2021-03-25 18:57:39 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 300/1251] eta: 0:08:13 lr: 0.000811 loss: 3.6214 (3.6109) grad_norm: 1.0675 (1.1004) time: 0.4997 [2021-03-25 18:57:44 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 310/1251] eta: 0:08:08 lr: 0.000811 loss: 3.6541 (3.6053) grad_norm: 1.0963 (inf) time: 0.4989 [2021-03-25 18:57:49 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 320/1251] eta: 0:08:02 lr: 0.000811 loss: 3.4740 (3.5982) grad_norm: 1.1017 (inf) time: 0.4980 [2021-03-25 18:57:54 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 330/1251] eta: 0:07:56 lr: 0.000811 loss: 3.4511 (3.5916) grad_norm: 1.1279 (inf) time: 0.5031 [2021-03-25 18:57:59 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 340/1251] eta: 0:07:51 lr: 0.000811 loss: 3.5384 (3.5933) grad_norm: 1.0760 (inf) time: 0.5055 [2021-03-25 18:58:04 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 350/1251] eta: 0:07:45 lr: 0.000811 loss: 3.6516 (3.5953) grad_norm: 1.0533 (inf) time: 0.4995 [2021-03-25 18:58:09 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 360/1251] eta: 0:07:40 lr: 0.000811 loss: 3.5349 (3.5893) grad_norm: 1.0392 (inf) time: 0.5070 [2021-03-25 18:58:14 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 370/1251] eta: 0:07:34 lr: 0.000811 loss: 3.5435 (3.5892) grad_norm: 1.0366 (inf) time: 0.5046 [2021-03-25 18:58:19 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 380/1251] eta: 0:07:29 lr: 0.000811 loss: 3.6128 (3.5855) grad_norm: 1.0562 (inf) time: 0.5005 [2021-03-25 18:58:24 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 390/1251] eta: 0:07:23 lr: 0.000811 loss: 3.6404 (3.5905) grad_norm: 1.0824 (inf) time: 0.5051 [2021-03-25 18:58:29 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 400/1251] eta: 0:07:18 lr: 0.000811 loss: 3.7055 (3.5885) grad_norm: 1.1031 (inf) time: 0.5011 [2021-03-25 18:58:34 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 410/1251] eta: 0:07:12 lr: 0.000811 loss: 3.6869 (3.5904) grad_norm: 1.0696 (inf) time: 0.5026 [2021-03-25 18:58:39 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 420/1251] eta: 0:07:07 lr: 0.000811 loss: 3.6315 (3.5827) grad_norm: 1.0747 (inf) time: 0.5079 [2021-03-25 18:58:44 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 430/1251] eta: 0:07:02 lr: 0.000811 loss: 3.5098 (3.5850) grad_norm: 1.1446 (inf) time: 0.5089 [2021-03-25 18:58:49 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 440/1251] eta: 0:06:57 lr: 0.000811 loss: 3.7683 (3.5819) grad_norm: 1.1524 (inf) time: 0.5104 [2021-03-25 18:58:54 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 450/1251] eta: 0:06:51 lr: 0.000811 loss: 3.5726 (3.5824) grad_norm: 1.0622 (inf) time: 0.5080 [2021-03-25 18:58:59 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 460/1251] eta: 0:06:46 lr: 0.000811 loss: 3.3309 (3.5769) grad_norm: 1.1061 (inf) time: 0.5009 [2021-03-25 18:59:04 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 470/1251] eta: 0:06:41 lr: 0.000811 loss: 3.3309 (3.5736) grad_norm: 1.1151 (inf) time: 0.5035 [2021-03-25 18:59:09 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 480/1251] eta: 0:06:36 lr: 0.000811 loss: 3.6062 (3.5738) grad_norm: 1.0887 (inf) time: 0.5076 [2021-03-25 18:59:15 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 490/1251] eta: 0:06:30 lr: 0.000811 loss: 3.6719 (3.5704) grad_norm: 1.0645 (inf) time: 0.5089 [2021-03-25 18:59:20 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 500/1251] eta: 0:06:25 lr: 0.000811 loss: 3.5810 (3.5704) grad_norm: 1.0294 (inf) time: 0.5117 [2021-03-25 18:59:25 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 510/1251] eta: 0:06:20 lr: 0.000811 loss: 3.5810 (3.5714) grad_norm: 1.0666 (inf) time: 0.5075 [2021-03-25 18:59:30 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 520/1251] eta: 0:06:15 lr: 0.000811 loss: 3.5496 (3.5694) grad_norm: 1.1136 (inf) time: 0.5046 [2021-03-25 18:59:35 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 530/1251] eta: 0:06:10 lr: 0.000811 loss: 3.5496 (3.5696) grad_norm: 1.0757 (inf) time: 0.5089 [2021-03-25 18:59:40 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 540/1251] eta: 0:06:04 lr: 0.000811 loss: 3.6435 (3.5687) grad_norm: 1.0537 (inf) time: 0.5110 [2021-03-25 18:59:45 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 550/1251] eta: 0:05:59 lr: 0.000811 loss: 3.5245 (3.5657) grad_norm: 1.0851 (inf) time: 0.5145 [2021-03-25 18:59:50 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 560/1251] eta: 0:05:54 lr: 0.000811 loss: 3.6316 (3.5654) grad_norm: 1.1349 (inf) time: 0.5125 [2021-03-25 18:59:55 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 570/1251] eta: 0:05:49 lr: 0.000811 loss: 3.7386 (3.5685) grad_norm: 1.0303 (inf) time: 0.5058 [2021-03-25 19:00:00 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 580/1251] eta: 0:05:44 lr: 0.000811 loss: 3.7386 (3.5695) grad_norm: 1.0106 (inf) time: 0.5025 [2021-03-25 19:00:05 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 590/1251] eta: 0:05:38 lr: 0.000811 loss: 3.5031 (3.5665) grad_norm: 1.0908 (inf) time: 0.5042 [2021-03-25 19:00:10 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 600/1251] eta: 0:05:33 lr: 0.000811 loss: 3.4820 (3.5660) grad_norm: 1.1427 (inf) time: 0.5023 [2021-03-25 19:00:15 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 610/1251] eta: 0:05:28 lr: 0.000810 loss: 3.7535 (3.5707) grad_norm: 1.0332 (inf) time: 0.5000 [2021-03-25 19:00:21 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 620/1251] eta: 0:05:23 lr: 0.000810 loss: 3.6574 (3.5731) grad_norm: 1.1099 (inf) time: 0.5079 [2021-03-25 19:00:26 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 630/1251] eta: 0:05:18 lr: 0.000810 loss: 3.7372 (3.5722) grad_norm: 1.0507 (inf) time: 0.5085 [2021-03-25 19:00:31 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 640/1251] eta: 0:05:12 lr: 0.000810 loss: 3.7870 (3.5768) grad_norm: 1.0263 (inf) time: 0.5059 [2021-03-25 19:00:36 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 650/1251] eta: 0:05:07 lr: 0.000810 loss: 3.7870 (3.5774) grad_norm: 1.0632 (inf) time: 0.5063 [2021-03-25 19:00:41 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 660/1251] eta: 0:05:02 lr: 0.000810 loss: 3.6400 (3.5741) grad_norm: 1.0632 (inf) time: 0.5058 [2021-03-25 19:00:46 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 670/1251] eta: 0:04:57 lr: 0.000810 loss: 3.5797 (3.5750) grad_norm: 1.0866 (inf) time: 0.5072 [2021-03-25 19:00:51 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 680/1251] eta: 0:04:52 lr: 0.000810 loss: 3.6379 (3.5745) grad_norm: 1.0800 (inf) time: 0.5115 [2021-03-25 19:00:56 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 690/1251] eta: 0:04:47 lr: 0.000810 loss: 3.6379 (3.5730) grad_norm: 1.1016 (inf) time: 0.5072 [2021-03-25 19:01:01 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 700/1251] eta: 0:04:41 lr: 0.000810 loss: 3.6063 (3.5722) grad_norm: 1.1016 (inf) time: 0.5033 [2021-03-25 19:01:06 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 710/1251] eta: 0:04:36 lr: 0.000810 loss: 3.4842 (3.5688) grad_norm: 1.0917 (inf) time: 0.5035 [2021-03-25 19:01:11 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 720/1251] eta: 0:04:31 lr: 0.000810 loss: 3.5782 (3.5734) grad_norm: 1.0784 (inf) time: 0.5069 [2021-03-25 19:01:16 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 730/1251] eta: 0:04:26 lr: 0.000810 loss: 3.7318 (3.5735) grad_norm: 1.2357 (inf) time: 0.5120 [2021-03-25 19:01:21 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 740/1251] eta: 0:04:21 lr: 0.000810 loss: 3.6010 (3.5736) grad_norm: 1.1524 (inf) time: 0.5120 [2021-03-25 19:01:27 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 750/1251] eta: 0:04:16 lr: 0.000810 loss: 3.5849 (3.5723) grad_norm: 1.1136 (inf) time: 0.5120 [2021-03-25 19:01:32 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 760/1251] eta: 0:04:11 lr: 0.000810 loss: 3.6393 (3.5707) grad_norm: 1.0974 (inf) time: 0.5126 [2021-03-25 19:01:37 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 770/1251] eta: 0:04:05 lr: 0.000810 loss: 3.7155 (3.5728) grad_norm: 1.1098 (inf) time: 0.5078 [2021-03-25 19:01:42 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 780/1251] eta: 0:04:00 lr: 0.000810 loss: 3.6253 (3.5701) grad_norm: 1.0851 (inf) time: 0.5000 [2021-03-25 19:01:47 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 790/1251] eta: 0:03:55 lr: 0.000810 loss: 3.6253 (3.5712) grad_norm: 1.0717 (inf) time: 0.5020 [2021-03-25 19:01:52 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 800/1251] eta: 0:03:50 lr: 0.000810 loss: 3.7577 (3.5736) grad_norm: 1.1026 (inf) time: 0.5052 [2021-03-25 19:01:57 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 810/1251] eta: 0:03:45 lr: 0.000810 loss: 3.7932 (3.5755) grad_norm: 1.1377 (inf) time: 0.5031 [2021-03-25 19:02:02 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 820/1251] eta: 0:03:40 lr: 0.000810 loss: 3.9352 (3.5783) grad_norm: 1.1431 (inf) time: 0.5041 [2021-03-25 19:02:07 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 830/1251] eta: 0:03:35 lr: 0.000810 loss: 3.7936 (3.5781) grad_norm: 1.1431 (inf) time: 0.5052 [2021-03-25 19:02:12 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 840/1251] eta: 0:03:29 lr: 0.000810 loss: 3.7625 (3.5765) grad_norm: 1.1448 (inf) time: 0.5017 [2021-03-25 19:02:17 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 850/1251] eta: 0:03:24 lr: 0.000810 loss: 3.6520 (3.5771) grad_norm: 1.0356 (inf) time: 0.5024 [2021-03-25 19:02:22 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 860/1251] eta: 0:03:19 lr: 0.000810 loss: 3.7509 (3.5783) grad_norm: 1.0583 (inf) time: 0.4986 [2021-03-25 19:02:27 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 870/1251] eta: 0:03:14 lr: 0.000810 loss: 3.7509 (3.5778) grad_norm: 1.0583 (inf) time: 0.5079 [2021-03-25 19:02:32 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 880/1251] eta: 0:03:09 lr: 0.000810 loss: 3.7458 (3.5777) grad_norm: 1.0326 (inf) time: 0.5181 [2021-03-25 19:02:37 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 890/1251] eta: 0:03:04 lr: 0.000810 loss: 3.5162 (3.5738) grad_norm: 1.0233 (inf) time: 0.5078 [2021-03-25 19:02:42 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 900/1251] eta: 0:02:59 lr: 0.000810 loss: 3.0704 (3.5725) grad_norm: 1.1130 (inf) time: 0.5016 [2021-03-25 19:02:48 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 910/1251] eta: 0:02:54 lr: 0.000810 loss: 3.7283 (3.5738) grad_norm: 1.1113 (inf) time: 0.5100 [2021-03-25 19:02:53 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 920/1251] eta: 0:02:48 lr: 0.000809 loss: 3.6863 (3.5732) grad_norm: 1.0809 (inf) time: 0.5121 [2021-03-25 19:02:58 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 930/1251] eta: 0:02:43 lr: 0.000809 loss: 3.6863 (3.5737) grad_norm: 1.0683 (inf) time: 0.5062 [2021-03-25 19:03:03 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 940/1251] eta: 0:02:38 lr: 0.000809 loss: 3.5129 (3.5737) grad_norm: 1.0832 (inf) time: 0.5086 [2021-03-25 19:03:08 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 950/1251] eta: 0:02:33 lr: 0.000809 loss: 3.5129 (3.5727) grad_norm: 1.0940 (inf) time: 0.5049 [2021-03-25 19:03:13 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 960/1251] eta: 0:02:28 lr: 0.000809 loss: 3.7937 (3.5738) grad_norm: 1.1274 (inf) time: 0.4990 [2021-03-25 19:03:18 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 970/1251] eta: 0:02:23 lr: 0.000809 loss: 3.7331 (3.5728) grad_norm: 1.1988 (inf) time: 0.5051 [2021-03-25 19:03:23 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 980/1251] eta: 0:02:18 lr: 0.000809 loss: 3.5754 (3.5705) grad_norm: 1.1092 (inf) time: 0.5054 [2021-03-25 19:03:28 swin_small_patch4_window7_224] INFO: Epoch: [86] [ 990/1251] eta: 0:02:13 lr: 0.000809 loss: 3.2535 (3.5690) grad_norm: 1.0961 (inf) time: 0.5018 [2021-03-25 19:03:33 swin_small_patch4_window7_224] INFO: Epoch: [86] [1000/1251] eta: 0:02:08 lr: 0.000809 loss: 3.2114 (3.5656) grad_norm: 1.0961 (inf) time: 0.5063 [2021-03-25 19:03:38 swin_small_patch4_window7_224] INFO: Epoch: [86] [1010/1251] eta: 0:02:02 lr: 0.000809 loss: 3.4175 (3.5652) grad_norm: 1.0659 (inf) time: 0.5083 [2021-03-25 19:03:43 swin_small_patch4_window7_224] INFO: Epoch: [86] [1020/1251] eta: 0:01:57 lr: 0.000809 loss: 3.4292 (3.5636) grad_norm: 1.0688 (inf) time: 0.5047 [2021-03-25 19:03:48 swin_small_patch4_window7_224] INFO: Epoch: [86] [1030/1251] eta: 0:01:52 lr: 0.000809 loss: 3.4630 (3.5622) grad_norm: 1.0883 (inf) time: 0.5043 [2021-03-25 19:03:53 swin_small_patch4_window7_224] INFO: Epoch: [86] [1040/1251] eta: 0:01:47 lr: 0.000809 loss: 3.5104 (3.5619) grad_norm: 1.0816 (inf) time: 0.5065 [2021-03-25 19:03:58 swin_small_patch4_window7_224] INFO: Epoch: [86] [1050/1251] eta: 0:01:42 lr: 0.000809 loss: 3.3571 (3.5608) grad_norm: 1.0816 (inf) time: 0.5053 [2021-03-25 19:04:03 swin_small_patch4_window7_224] INFO: Epoch: [86] [1060/1251] eta: 0:01:37 lr: 0.000809 loss: 3.3571 (3.5606) grad_norm: 1.1320 (inf) time: 0.5059 [2021-03-25 19:04:09 swin_small_patch4_window7_224] INFO: Epoch: [86] [1070/1251] eta: 0:01:32 lr: 0.000809 loss: 3.6856 (3.5616) grad_norm: 1.1320 (inf) time: 0.5136 [2021-03-25 19:04:14 swin_small_patch4_window7_224] INFO: Epoch: [86] [1080/1251] eta: 0:01:27 lr: 0.000809 loss: 3.7143 (3.5619) grad_norm: 1.0765 (inf) time: 0.5136 [2021-03-25 19:04:19 swin_small_patch4_window7_224] INFO: Epoch: [86] [1090/1251] eta: 0:01:22 lr: 0.000809 loss: 3.5954 (3.5608) grad_norm: 1.0217 (inf) time: 0.5101 [2021-03-25 19:04:24 swin_small_patch4_window7_224] INFO: Epoch: [86] [1100/1251] eta: 0:01:16 lr: 0.000809 loss: 3.6424 (3.5623) grad_norm: 1.0158 (inf) time: 0.5124 [2021-03-25 19:04:29 swin_small_patch4_window7_224] INFO: Epoch: [86] [1110/1251] eta: 0:01:11 lr: 0.000809 loss: 3.5636 (3.5615) grad_norm: 1.0851 (inf) time: 0.5104 [2021-03-25 19:04:34 swin_small_patch4_window7_224] INFO: Epoch: [86] [1120/1251] eta: 0:01:06 lr: 0.000809 loss: 3.5488 (3.5638) grad_norm: 1.0561 (inf) time: 0.5079 [2021-03-25 19:04:39 swin_small_patch4_window7_224] INFO: Epoch: [86] [1130/1251] eta: 0:01:01 lr: 0.000809 loss: 3.7978 (3.5639) grad_norm: 1.0799 (inf) time: 0.5074 [2021-03-25 19:04:44 swin_small_patch4_window7_224] INFO: Epoch: [86] [1140/1251] eta: 0:00:56 lr: 0.000809 loss: 3.6074 (3.5640) grad_norm: 1.0890 (inf) time: 0.5025 [2021-03-25 19:04:49 swin_small_patch4_window7_224] INFO: Epoch: [86] [1150/1251] eta: 0:00:51 lr: 0.000809 loss: 3.9408 (3.5668) grad_norm: 1.1438 (inf) time: 0.4999 [2021-03-25 19:04:54 swin_small_patch4_window7_224] INFO: Epoch: [86] [1160/1251] eta: 0:00:46 lr: 0.000809 loss: 3.6918 (3.5664) grad_norm: 1.0783 (inf) time: 0.5026 [2021-03-25 19:04:59 swin_small_patch4_window7_224] INFO: Epoch: [86] [1170/1251] eta: 0:00:41 lr: 0.000809 loss: 3.4080 (3.5649) grad_norm: 1.0723 (inf) time: 0.5066 [2021-03-25 19:05:04 swin_small_patch4_window7_224] INFO: Epoch: [86] [1180/1251] eta: 0:00:36 lr: 0.000809 loss: 3.0407 (3.5610) grad_norm: 1.0894 (inf) time: 0.5107 [2021-03-25 19:05:09 swin_small_patch4_window7_224] INFO: Epoch: [86] [1190/1251] eta: 0:00:31 lr: 0.000809 loss: 3.3866 (3.5621) grad_norm: 1.1336 (inf) time: 0.5094 [2021-03-25 19:05:15 swin_small_patch4_window7_224] INFO: Epoch: [86] [1200/1251] eta: 0:00:25 lr: 0.000809 loss: 3.4994 (3.5604) grad_norm: 1.0507 (inf) time: 0.5071 [2021-03-25 19:05:19 swin_small_patch4_window7_224] INFO: Epoch: [86] [1210/1251] eta: 0:00:20 lr: 0.000809 loss: 3.4109 (3.5603) grad_norm: 1.0921 (inf) time: 0.5014 [2021-03-25 19:05:25 swin_small_patch4_window7_224] INFO: Epoch: [86] [1220/1251] eta: 0:00:15 lr: 0.000808 loss: 3.6768 (3.5617) grad_norm: 1.1216 (inf) time: 0.5022 [2021-03-25 19:05:30 swin_small_patch4_window7_224] INFO: Epoch: [86] [1230/1251] eta: 0:00:10 lr: 0.000808 loss: 3.8212 (3.5634) grad_norm: 1.0753 (inf) time: 0.5081 [2021-03-25 19:05:35 swin_small_patch4_window7_224] INFO: Epoch: [86] [1240/1251] eta: 0:00:05 lr: 0.000808 loss: 3.7543 (3.5649) grad_norm: 1.0451 (inf) time: 0.5054 [2021-03-25 19:05:40 swin_small_patch4_window7_224] INFO: Epoch: [86] [1250/1251] eta: 0:00:00 lr: 0.000808 loss: 3.5637 (3.5638) grad_norm: 1.0576 (inf) time: 0.4952 [2021-03-25 19:05:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 1.2300 (1.2300) acc1: 71.8750 (71.8750) acc5: 90.6250 (90.6250) [2021-03-25 19:05:49 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.1149 (1.1293) acc1: 73.4375 (71.7330) acc5: 92.1875 (92.6136) [2021-03-25 19:05:52 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0999 (1.0807) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.1548) [2021-03-25 19:05:53 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0680 (1.0942) acc1: 75.0000 (73.6391) acc5: 92.1875 (92.5403) [2021-03-25 19:05:56 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0649 (1.0746) acc1: 75.0000 (73.6280) acc5: 92.1875 (92.9116) [2021-03-25 19:05:57 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0047 (1.0622) acc1: 76.5625 (74.2080) acc5: 93.7500 (92.9600) [2021-03-25 19:06:02 swin_small_patch4_window7_224] INFO: * Acc@1 75.374 Acc@5 93.094 loss 1.038 [2021-03-25 19:06:02 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.4% [2021-03-25 19:06:02 swin_small_patch4_window7_224] INFO: Max accuracy: 75.37% [2021-03-25 19:06:06 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 0/1251] eta: 1:30:00 lr: 0.000808 loss: 3.6744 (3.6744) grad_norm: 1.0167 (1.0167) time: 4.3170 [2021-03-25 19:06:12 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 10/1251] eta: 0:18:06 lr: 0.000808 loss: 3.5299 (3.4945) grad_norm: 1.0638 (1.0953) time: 0.8753 [2021-03-25 19:06:17 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 20/1251] eta: 0:14:20 lr: 0.000808 loss: 3.4074 (3.4715) grad_norm: 1.1227 (1.1104) time: 0.5178 [2021-03-25 19:06:22 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 30/1251] eta: 0:12:54 lr: 0.000808 loss: 3.5147 (3.4963) grad_norm: 1.1197 (1.1127) time: 0.5014 [2021-03-25 19:06:27 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 40/1251] eta: 0:12:12 lr: 0.000808 loss: 3.6064 (3.4757) grad_norm: 1.0756 (1.1054) time: 0.5060 [2021-03-25 19:06:32 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 50/1251] eta: 0:11:44 lr: 0.000808 loss: 3.6450 (3.5016) grad_norm: 1.0828 (1.1135) time: 0.5140 [2021-03-25 19:06:37 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 60/1251] eta: 0:11:24 lr: 0.000808 loss: 3.6533 (3.4985) grad_norm: 1.1149 (1.1276) time: 0.5140 [2021-03-25 19:06:42 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 70/1251] eta: 0:11:07 lr: 0.000808 loss: 3.7906 (3.5277) grad_norm: 1.0486 (1.1150) time: 0.5101 [2021-03-25 19:06:47 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 80/1251] eta: 0:10:53 lr: 0.000808 loss: 3.6378 (3.5334) grad_norm: 1.0420 (1.1081) time: 0.5068 [2021-03-25 19:06:52 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 90/1251] eta: 0:10:42 lr: 0.000808 loss: 3.4467 (3.5067) grad_norm: 1.0425 (1.1043) time: 0.5110 [2021-03-25 19:06:57 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 100/1251] eta: 0:10:30 lr: 0.000808 loss: 3.6569 (3.5343) grad_norm: 1.0498 (1.1039) time: 0.5071 [2021-03-25 19:07:02 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 110/1251] eta: 0:10:21 lr: 0.000808 loss: 3.6070 (3.5195) grad_norm: 1.1278 (1.1105) time: 0.5054 [2021-03-25 19:07:07 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 120/1251] eta: 0:10:12 lr: 0.000808 loss: 3.1729 (3.4846) grad_norm: 1.1787 (1.1194) time: 0.5093 [2021-03-25 19:07:13 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 130/1251] eta: 0:10:04 lr: 0.000808 loss: 3.0969 (3.4668) grad_norm: 1.1651 (1.1207) time: 0.5088 [2021-03-25 19:07:18 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 140/1251] eta: 0:09:56 lr: 0.000808 loss: 3.4141 (3.4721) grad_norm: 1.0700 (1.1141) time: 0.5075 [2021-03-25 19:07:23 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 150/1251] eta: 0:09:49 lr: 0.000808 loss: 3.5119 (3.4745) grad_norm: 1.0343 (1.1130) time: 0.5073 [2021-03-25 19:07:28 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 160/1251] eta: 0:09:41 lr: 0.000808 loss: 3.5395 (3.4816) grad_norm: 1.0921 (1.1162) time: 0.5071 [2021-03-25 19:07:33 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 170/1251] eta: 0:09:34 lr: 0.000808 loss: 3.5395 (3.4771) grad_norm: 1.1228 (1.1134) time: 0.5059 [2021-03-25 19:07:38 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 180/1251] eta: 0:09:27 lr: 0.000808 loss: 3.5250 (3.4616) grad_norm: 1.0330 (1.1086) time: 0.5041 [2021-03-25 19:07:43 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 190/1251] eta: 0:09:20 lr: 0.000808 loss: 3.3334 (3.4584) grad_norm: 1.0330 (1.1075) time: 0.5017 [2021-03-25 19:07:48 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 200/1251] eta: 0:09:14 lr: 0.000808 loss: 3.3334 (3.4523) grad_norm: 1.0331 (1.1080) time: 0.5061 [2021-03-25 19:07:53 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 210/1251] eta: 0:09:07 lr: 0.000808 loss: 3.3406 (3.4495) grad_norm: 1.0821 (1.1105) time: 0.5062 [2021-03-25 19:07:58 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 220/1251] eta: 0:09:01 lr: 0.000808 loss: 3.5825 (3.4597) grad_norm: 1.0678 (1.1088) time: 0.5024 [2021-03-25 19:08:03 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 230/1251] eta: 0:08:55 lr: 0.000808 loss: 3.4622 (3.4571) grad_norm: 1.0479 (1.1095) time: 0.5026 [2021-03-25 19:08:08 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 240/1251] eta: 0:08:48 lr: 0.000808 loss: 3.4439 (3.4619) grad_norm: 1.1000 (1.1095) time: 0.5002 [2021-03-25 19:08:13 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 250/1251] eta: 0:08:43 lr: 0.000808 loss: 3.6317 (3.4684) grad_norm: 1.1011 (1.1112) time: 0.5102 [2021-03-25 19:08:18 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 260/1251] eta: 0:08:37 lr: 0.000808 loss: 3.5402 (3.4624) grad_norm: 1.0741 (1.1097) time: 0.5125 [2021-03-25 19:08:23 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 270/1251] eta: 0:08:31 lr: 0.000808 loss: 3.5415 (3.4647) grad_norm: 1.0638 (1.1099) time: 0.5008 [2021-03-25 19:08:28 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 280/1251] eta: 0:08:25 lr: 0.000807 loss: 3.6767 (3.4725) grad_norm: 1.1577 (1.1131) time: 0.5007 [2021-03-25 19:08:33 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 290/1251] eta: 0:08:20 lr: 0.000807 loss: 3.6767 (3.4826) grad_norm: 1.1910 (1.1149) time: 0.5072 [2021-03-25 19:08:38 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 300/1251] eta: 0:08:14 lr: 0.000807 loss: 3.6383 (3.4774) grad_norm: 1.0961 (1.1155) time: 0.5092 [2021-03-25 19:08:44 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 310/1251] eta: 0:08:09 lr: 0.000807 loss: 3.3653 (3.4707) grad_norm: 1.0926 (1.1150) time: 0.5075 [2021-03-25 19:08:49 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 320/1251] eta: 0:08:03 lr: 0.000807 loss: 3.4330 (3.4716) grad_norm: 1.1529 (1.1192) time: 0.5138 [2021-03-25 19:08:54 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 330/1251] eta: 0:07:58 lr: 0.000807 loss: 3.7397 (3.4725) grad_norm: 1.1920 (1.1207) time: 0.5131 [2021-03-25 19:08:59 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 340/1251] eta: 0:07:52 lr: 0.000807 loss: 3.7344 (3.4760) grad_norm: 1.1181 (1.1198) time: 0.5052 [2021-03-25 19:09:04 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 350/1251] eta: 0:07:47 lr: 0.000807 loss: 3.5655 (3.4715) grad_norm: 1.0621 (1.1220) time: 0.5060 [2021-03-25 19:09:09 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 360/1251] eta: 0:07:41 lr: 0.000807 loss: 3.5854 (3.4768) grad_norm: 1.0493 (1.1202) time: 0.5053 [2021-03-25 19:09:14 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 370/1251] eta: 0:07:36 lr: 0.000807 loss: 3.7324 (3.4762) grad_norm: 1.0368 (1.1181) time: 0.5014 [2021-03-25 19:09:19 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 380/1251] eta: 0:07:30 lr: 0.000807 loss: 3.4765 (3.4790) grad_norm: 1.0819 (1.1194) time: 0.5019 [2021-03-25 19:09:24 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 390/1251] eta: 0:07:24 lr: 0.000807 loss: 3.6671 (3.4839) grad_norm: 1.1643 (1.1208) time: 0.5006 [2021-03-25 19:09:29 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 400/1251] eta: 0:07:19 lr: 0.000807 loss: 3.3955 (3.4784) grad_norm: 1.1448 (1.1211) time: 0.5033 [2021-03-25 19:09:34 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 410/1251] eta: 0:07:14 lr: 0.000807 loss: 3.1206 (3.4727) grad_norm: 1.0734 (1.1207) time: 0.5105 [2021-03-25 19:09:39 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 420/1251] eta: 0:07:08 lr: 0.000807 loss: 3.5455 (3.4753) grad_norm: 1.0664 (1.1193) time: 0.5106 [2021-03-25 19:09:44 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 430/1251] eta: 0:07:03 lr: 0.000807 loss: 3.7899 (3.4790) grad_norm: 1.0664 (1.1186) time: 0.5078 [2021-03-25 19:09:49 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 440/1251] eta: 0:06:58 lr: 0.000807 loss: 3.6441 (3.4767) grad_norm: 1.0746 (1.1186) time: 0.5065 [2021-03-25 19:09:54 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 450/1251] eta: 0:06:52 lr: 0.000807 loss: 3.6996 (3.4818) grad_norm: 1.0746 (1.1181) time: 0.5043 [2021-03-25 19:10:00 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 460/1251] eta: 0:06:47 lr: 0.000807 loss: 3.6996 (3.4797) grad_norm: 1.0805 (1.1173) time: 0.5056 [2021-03-25 19:10:05 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 470/1251] eta: 0:06:42 lr: 0.000807 loss: 3.6894 (3.4839) grad_norm: 1.1444 (1.1188) time: 0.5036 [2021-03-25 19:10:10 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 480/1251] eta: 0:06:36 lr: 0.000807 loss: 3.7807 (3.4929) grad_norm: 1.1341 (1.1179) time: 0.5018 [2021-03-25 19:10:15 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 490/1251] eta: 0:06:31 lr: 0.000807 loss: 3.6955 (3.4924) grad_norm: 1.1100 (1.1191) time: 0.5036 [2021-03-25 19:10:20 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 500/1251] eta: 0:06:26 lr: 0.000807 loss: 3.5756 (3.4956) grad_norm: 1.1063 (1.1183) time: 0.5028 [2021-03-25 19:10:25 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 510/1251] eta: 0:06:20 lr: 0.000807 loss: 3.6924 (3.4980) grad_norm: 1.0599 (1.1176) time: 0.4983 [2021-03-25 19:10:30 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 520/1251] eta: 0:06:15 lr: 0.000807 loss: 3.6835 (3.4970) grad_norm: 1.1227 (1.1183) time: 0.5004 [2021-03-25 19:10:35 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 530/1251] eta: 0:06:10 lr: 0.000807 loss: 3.6043 (3.4968) grad_norm: 1.1697 (1.1198) time: 0.5055 [2021-03-25 19:10:40 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 540/1251] eta: 0:06:05 lr: 0.000807 loss: 3.6849 (3.5000) grad_norm: 1.0725 (1.1184) time: 0.5063 [2021-03-25 19:10:45 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 550/1251] eta: 0:06:00 lr: 0.000807 loss: 3.4381 (3.4961) grad_norm: 1.0827 (1.1188) time: 0.5215 [2021-03-25 19:10:50 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 560/1251] eta: 0:05:55 lr: 0.000807 loss: 3.3191 (3.4986) grad_norm: 1.1214 (1.1192) time: 0.5234 [2021-03-25 19:10:55 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 570/1251] eta: 0:05:49 lr: 0.000807 loss: 3.7217 (3.4994) grad_norm: 1.1066 (1.1194) time: 0.5077 [2021-03-25 19:11:00 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 580/1251] eta: 0:05:44 lr: 0.000806 loss: 3.6894 (3.5034) grad_norm: 1.0643 (1.1186) time: 0.5069 [2021-03-25 19:11:06 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 590/1251] eta: 0:05:39 lr: 0.000806 loss: 3.6931 (3.5055) grad_norm: 1.0643 (1.1185) time: 0.5145 [2021-03-25 19:11:11 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 600/1251] eta: 0:05:34 lr: 0.000806 loss: 3.5539 (3.5056) grad_norm: 1.0592 (1.1174) time: 0.5096 [2021-03-25 19:11:16 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 610/1251] eta: 0:05:29 lr: 0.000806 loss: 3.4054 (3.5049) grad_norm: 1.0592 (1.1164) time: 0.5010 [2021-03-25 19:11:21 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 620/1251] eta: 0:05:23 lr: 0.000806 loss: 3.6403 (3.5072) grad_norm: 1.0781 (1.1161) time: 0.5000 [2021-03-25 19:11:26 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 630/1251] eta: 0:05:18 lr: 0.000806 loss: 3.7293 (3.5067) grad_norm: 1.0839 (1.1160) time: 0.5008 [2021-03-25 19:11:31 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 640/1251] eta: 0:05:13 lr: 0.000806 loss: 3.6392 (3.5091) grad_norm: 1.1465 (1.1177) time: 0.5060 [2021-03-25 19:11:36 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 650/1251] eta: 0:05:08 lr: 0.000806 loss: 3.7466 (3.5155) grad_norm: 1.1478 (1.1179) time: 0.5066 [2021-03-25 19:11:41 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 660/1251] eta: 0:05:02 lr: 0.000806 loss: 3.6719 (3.5137) grad_norm: 1.0912 (1.1172) time: 0.5072 [2021-03-25 19:11:46 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 670/1251] eta: 0:04:57 lr: 0.000806 loss: 3.3409 (3.5132) grad_norm: 1.0558 (1.1165) time: 0.5051 [2021-03-25 19:11:51 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 680/1251] eta: 0:04:52 lr: 0.000806 loss: 3.5516 (3.5120) grad_norm: 1.0772 (1.1164) time: 0.5046 [2021-03-25 19:11:56 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 690/1251] eta: 0:04:47 lr: 0.000806 loss: 3.4617 (3.5092) grad_norm: 1.0923 (1.1165) time: 0.5088 [2021-03-25 19:12:01 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 700/1251] eta: 0:04:42 lr: 0.000806 loss: 3.5924 (3.5118) grad_norm: 1.1286 (1.1174) time: 0.5047 [2021-03-25 19:12:06 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 710/1251] eta: 0:04:37 lr: 0.000806 loss: 3.8207 (3.5137) grad_norm: 1.1286 (1.1174) time: 0.5028 [2021-03-25 19:12:11 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 720/1251] eta: 0:04:31 lr: 0.000806 loss: 3.8191 (3.5146) grad_norm: 1.1196 (1.1176) time: 0.5001 [2021-03-25 19:12:16 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 730/1251] eta: 0:04:26 lr: 0.000806 loss: 3.7812 (3.5151) grad_norm: 1.0845 (1.1173) time: 0.5078 [2021-03-25 19:12:22 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 740/1251] eta: 0:04:21 lr: 0.000806 loss: 3.4799 (3.5127) grad_norm: 1.0696 (1.1164) time: 0.5292 [2021-03-25 19:12:27 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 750/1251] eta: 0:04:16 lr: 0.000806 loss: 3.5293 (3.5116) grad_norm: 1.0683 (1.1169) time: 0.5279 [2021-03-25 19:12:32 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 760/1251] eta: 0:04:11 lr: 0.000806 loss: 3.6286 (3.5128) grad_norm: 1.1333 (1.1178) time: 0.5137 [2021-03-25 19:12:37 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 770/1251] eta: 0:04:06 lr: 0.000806 loss: 3.6286 (3.5116) grad_norm: 1.0904 (1.1175) time: 0.5077 [2021-03-25 19:12:42 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 780/1251] eta: 0:04:01 lr: 0.000806 loss: 3.6936 (3.5155) grad_norm: 1.0537 (1.1164) time: 0.5038 [2021-03-25 19:12:47 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 790/1251] eta: 0:03:56 lr: 0.000806 loss: 3.3856 (3.5101) grad_norm: 1.0765 (1.1176) time: 0.5086 [2021-03-25 19:12:52 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 800/1251] eta: 0:03:51 lr: 0.000806 loss: 3.2220 (3.5106) grad_norm: 1.1276 (1.1176) time: 0.5223 [2021-03-25 19:12:58 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 810/1251] eta: 0:03:45 lr: 0.000806 loss: 3.2220 (3.5055) grad_norm: 1.1161 (1.1179) time: 0.5183 [2021-03-25 19:13:03 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 820/1251] eta: 0:03:40 lr: 0.000806 loss: 3.0374 (3.5037) grad_norm: 1.0967 (1.1185) time: 0.5047 [2021-03-25 19:13:08 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 830/1251] eta: 0:03:35 lr: 0.000806 loss: 3.4948 (3.5038) grad_norm: 1.1087 (1.1189) time: 0.4996 [2021-03-25 19:13:13 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 840/1251] eta: 0:03:30 lr: 0.000806 loss: 3.5497 (3.5045) grad_norm: 1.1065 (1.1184) time: 0.5042 [2021-03-25 19:13:18 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 850/1251] eta: 0:03:25 lr: 0.000806 loss: 3.6625 (3.5038) grad_norm: 1.0867 (1.1182) time: 0.5105 [2021-03-25 19:13:23 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 860/1251] eta: 0:03:20 lr: 0.000806 loss: 3.5581 (3.5032) grad_norm: 1.0727 (1.1181) time: 0.5087 [2021-03-25 19:13:28 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 870/1251] eta: 0:03:14 lr: 0.000806 loss: 3.5928 (3.5057) grad_norm: 1.1181 (1.1191) time: 0.5027 [2021-03-25 19:13:33 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 880/1251] eta: 0:03:09 lr: 0.000805 loss: 3.4855 (3.5042) grad_norm: 1.1193 (1.1194) time: 0.5047 [2021-03-25 19:13:38 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 890/1251] eta: 0:03:04 lr: 0.000805 loss: 3.4033 (3.5029) grad_norm: 1.0897 (1.1199) time: 0.5096 [2021-03-25 19:13:43 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 900/1251] eta: 0:02:59 lr: 0.000805 loss: 3.7133 (3.5055) grad_norm: 1.1102 (1.1201) time: 0.5041 [2021-03-25 19:13:48 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 910/1251] eta: 0:02:54 lr: 0.000805 loss: 3.7349 (3.5072) grad_norm: 1.1319 (1.1206) time: 0.5009 [2021-03-25 19:13:53 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 920/1251] eta: 0:02:49 lr: 0.000805 loss: 3.6033 (3.5055) grad_norm: 1.1241 (1.1204) time: 0.5052 [2021-03-25 19:13:58 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 930/1251] eta: 0:02:44 lr: 0.000805 loss: 3.4800 (3.5042) grad_norm: 1.0720 (1.1202) time: 0.5101 [2021-03-25 19:14:03 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 940/1251] eta: 0:02:39 lr: 0.000805 loss: 3.7756 (3.5064) grad_norm: 1.0720 (1.1201) time: 0.5093 [2021-03-25 19:14:08 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 950/1251] eta: 0:02:33 lr: 0.000805 loss: 3.7756 (3.5089) grad_norm: 1.1259 (1.1205) time: 0.5028 [2021-03-25 19:14:13 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 960/1251] eta: 0:02:28 lr: 0.000805 loss: 3.7088 (3.5098) grad_norm: 1.1183 (1.1205) time: 0.5034 [2021-03-25 19:14:18 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 970/1251] eta: 0:02:23 lr: 0.000805 loss: 3.5980 (3.5070) grad_norm: 1.0978 (1.1205) time: 0.5029 [2021-03-25 19:14:23 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 980/1251] eta: 0:02:18 lr: 0.000805 loss: 3.5621 (3.5086) grad_norm: 1.1304 (1.1210) time: 0.4988 [2021-03-25 19:14:29 swin_small_patch4_window7_224] INFO: Epoch: [87] [ 990/1251] eta: 0:02:13 lr: 0.000805 loss: 3.6363 (3.5080) grad_norm: 1.1269 (1.1212) time: 0.5109 [2021-03-25 19:14:34 swin_small_patch4_window7_224] INFO: Epoch: [87] [1000/1251] eta: 0:02:08 lr: 0.000805 loss: 3.6045 (3.5068) grad_norm: 1.1269 (1.1214) time: 0.5145 [2021-03-25 19:14:39 swin_small_patch4_window7_224] INFO: Epoch: [87] [1010/1251] eta: 0:02:03 lr: 0.000805 loss: 3.7114 (3.5099) grad_norm: 1.1267 (1.1214) time: 0.5046 [2021-03-25 19:14:44 swin_small_patch4_window7_224] INFO: Epoch: [87] [1020/1251] eta: 0:01:58 lr: 0.000805 loss: 3.7325 (3.5105) grad_norm: 1.0793 (1.1211) time: 0.5002 [2021-03-25 19:14:49 swin_small_patch4_window7_224] INFO: Epoch: [87] [1030/1251] eta: 0:01:52 lr: 0.000805 loss: 3.5030 (3.5103) grad_norm: 1.1285 (1.1214) time: 0.5053 [2021-03-25 19:14:54 swin_small_patch4_window7_224] INFO: Epoch: [87] [1040/1251] eta: 0:01:47 lr: 0.000805 loss: 3.6848 (3.5120) grad_norm: 1.1315 (1.1219) time: 0.5033 [2021-03-25 19:14:59 swin_small_patch4_window7_224] INFO: Epoch: [87] [1050/1251] eta: 0:01:42 lr: 0.000805 loss: 3.7353 (3.5134) grad_norm: 1.1088 (1.1219) time: 0.5021 [2021-03-25 19:15:04 swin_small_patch4_window7_224] INFO: Epoch: [87] [1060/1251] eta: 0:01:37 lr: 0.000805 loss: 3.7353 (3.5138) grad_norm: 1.1088 (1.1216) time: 0.5074 [2021-03-25 19:15:09 swin_small_patch4_window7_224] INFO: Epoch: [87] [1070/1251] eta: 0:01:32 lr: 0.000805 loss: 3.6757 (3.5133) grad_norm: 1.1105 (1.1219) time: 0.5098 [2021-03-25 19:15:14 swin_small_patch4_window7_224] INFO: Epoch: [87] [1080/1251] eta: 0:01:27 lr: 0.000805 loss: 3.5730 (3.5137) grad_norm: 1.1175 (1.1221) time: 0.5085 [2021-03-25 19:15:19 swin_small_patch4_window7_224] INFO: Epoch: [87] [1090/1251] eta: 0:01:22 lr: 0.000805 loss: 3.6186 (3.5139) grad_norm: 1.1299 (1.1222) time: 0.5006 [2021-03-25 19:15:24 swin_small_patch4_window7_224] INFO: Epoch: [87] [1100/1251] eta: 0:01:17 lr: 0.000805 loss: 3.7156 (3.5156) grad_norm: 1.1185 (1.1219) time: 0.4972 [2021-03-25 19:15:29 swin_small_patch4_window7_224] INFO: Epoch: [87] [1110/1251] eta: 0:01:11 lr: 0.000805 loss: 3.6821 (3.5152) grad_norm: 1.1043 (1.1220) time: 0.5035 [2021-03-25 19:15:34 swin_small_patch4_window7_224] INFO: Epoch: [87] [1120/1251] eta: 0:01:06 lr: 0.000805 loss: 3.6821 (3.5163) grad_norm: 1.1051 (1.1218) time: 0.5031 [2021-03-25 19:15:39 swin_small_patch4_window7_224] INFO: Epoch: [87] [1130/1251] eta: 0:01:01 lr: 0.000805 loss: 3.7554 (3.5173) grad_norm: 1.0720 (1.1218) time: 0.4981 [2021-03-25 19:15:44 swin_small_patch4_window7_224] INFO: Epoch: [87] [1140/1251] eta: 0:00:56 lr: 0.000805 loss: 3.6057 (3.5180) grad_norm: 1.1343 (inf) time: 0.4989 [2021-03-25 19:15:49 swin_small_patch4_window7_224] INFO: Epoch: [87] [1150/1251] eta: 0:00:51 lr: 0.000805 loss: 3.5649 (3.5182) grad_norm: 1.1608 (inf) time: 0.5036 [2021-03-25 19:15:54 swin_small_patch4_window7_224] INFO: Epoch: [87] [1160/1251] eta: 0:00:46 lr: 0.000805 loss: 3.5419 (3.5173) grad_norm: 1.1143 (inf) time: 0.5028 [2021-03-25 19:15:59 swin_small_patch4_window7_224] INFO: Epoch: [87] [1170/1251] eta: 0:00:41 lr: 0.000805 loss: 3.6331 (3.5207) grad_norm: 1.1210 (inf) time: 0.5040 [2021-03-25 19:16:04 swin_small_patch4_window7_224] INFO: Epoch: [87] [1180/1251] eta: 0:00:36 lr: 0.000805 loss: 3.8319 (3.5177) grad_norm: 1.1247 (inf) time: 0.5086 [2021-03-25 19:16:09 swin_small_patch4_window7_224] INFO: Epoch: [87] [1190/1251] eta: 0:00:31 lr: 0.000804 loss: 3.3889 (3.5175) grad_norm: 1.1204 (inf) time: 0.5013 [2021-03-25 19:16:14 swin_small_patch4_window7_224] INFO: Epoch: [87] [1200/1251] eta: 0:00:26 lr: 0.000804 loss: 3.5645 (3.5184) grad_norm: 1.1695 (inf) time: 0.5054 [2021-03-25 19:16:19 swin_small_patch4_window7_224] INFO: Epoch: [87] [1210/1251] eta: 0:00:20 lr: 0.000804 loss: 3.4302 (3.5187) grad_norm: 1.1441 (inf) time: 0.5094 [2021-03-25 19:16:25 swin_small_patch4_window7_224] INFO: Epoch: [87] [1220/1251] eta: 0:00:15 lr: 0.000804 loss: 3.6098 (3.5201) grad_norm: 1.1441 (inf) time: 0.5070 [2021-03-25 19:16:30 swin_small_patch4_window7_224] INFO: Epoch: [87] [1230/1251] eta: 0:00:10 lr: 0.000804 loss: 3.5110 (3.5192) grad_norm: 1.1253 (inf) time: 0.5046 [2021-03-25 19:16:35 swin_small_patch4_window7_224] INFO: Epoch: [87] [1240/1251] eta: 0:00:05 lr: 0.000804 loss: 3.4680 (3.5183) grad_norm: 1.0749 (inf) time: 0.5045 [2021-03-25 19:16:40 swin_small_patch4_window7_224] INFO: Epoch: [87] [1250/1251] eta: 0:00:00 lr: 0.000804 loss: 3.7332 (3.5188) grad_norm: 1.0777 (inf) time: 0.5050 [2021-03-25 19:16:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:19 loss: 0.7743 (0.7743) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-25 19:16:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9954 (1.0303) acc1: 75.0000 (75.1420) acc5: 93.7500 (94.3182) [2021-03-25 19:16:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0239 (1.0407) acc1: 75.0000 (75.2232) acc5: 93.7500 (94.1220) [2021-03-25 19:16:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0468 (1.0643) acc1: 73.4375 (74.3952) acc5: 92.1875 (93.2964) [2021-03-25 19:16:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0952 (1.0793) acc1: 75.0000 (74.1616) acc5: 92.1875 (92.8735) [2021-03-25 19:16:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0510 (1.0821) acc1: 75.0000 (74.4640) acc5: 92.1875 (92.8320) [2021-03-25 19:16:58 swin_small_patch4_window7_224] INFO: * Acc@1 75.570 Acc@5 93.054 loss 1.046 [2021-03-25 19:16:58 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.6% [2021-03-25 19:16:58 swin_small_patch4_window7_224] INFO: Max accuracy: 75.57% [2021-03-25 19:17:02 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 0/1251] eta: 1:25:10 lr: 0.000804 loss: 3.9921 (3.9921) grad_norm: 0.9744 (0.9744) time: 4.0853 [2021-03-25 19:17:08 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 10/1251] eta: 0:17:57 lr: 0.000804 loss: 3.0673 (3.2064) grad_norm: 1.0952 (1.1151) time: 0.8679 [2021-03-25 19:17:13 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 20/1251] eta: 0:14:17 lr: 0.000804 loss: 3.1936 (3.3240) grad_norm: 1.1616 (1.1608) time: 0.5269 [2021-03-25 19:17:18 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 30/1251] eta: 0:12:55 lr: 0.000804 loss: 3.3279 (3.2966) grad_norm: 1.1767 (1.1611) time: 0.5074 [2021-03-25 19:17:23 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 40/1251] eta: 0:12:15 lr: 0.000804 loss: 3.5852 (3.4441) grad_norm: 1.0864 (1.1527) time: 0.5140 [2021-03-25 19:17:28 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 50/1251] eta: 0:11:46 lr: 0.000804 loss: 3.8889 (3.5025) grad_norm: 1.1243 (1.1490) time: 0.5148 [2021-03-25 19:17:33 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 60/1251] eta: 0:11:24 lr: 0.000804 loss: 3.6306 (3.5221) grad_norm: 1.1324 (1.1420) time: 0.5070 [2021-03-25 19:17:38 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 70/1251] eta: 0:11:08 lr: 0.000804 loss: 3.5089 (3.4724) grad_norm: 1.0540 (1.1294) time: 0.5110 [2021-03-25 19:17:43 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 80/1251] eta: 0:10:53 lr: 0.000804 loss: 3.1293 (3.4429) grad_norm: 1.0767 (1.1268) time: 0.5095 [2021-03-25 19:17:48 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 90/1251] eta: 0:10:40 lr: 0.000804 loss: 3.5091 (3.4747) grad_norm: 1.1311 (1.1359) time: 0.5006 [2021-03-25 19:17:53 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 100/1251] eta: 0:10:29 lr: 0.000804 loss: 3.6419 (3.4814) grad_norm: 1.1515 (1.1389) time: 0.4993 [2021-03-25 19:17:58 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 110/1251] eta: 0:10:19 lr: 0.000804 loss: 3.6112 (3.4949) grad_norm: 1.1390 (1.1401) time: 0.5004 [2021-03-25 19:18:03 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 120/1251] eta: 0:10:10 lr: 0.000804 loss: 3.5415 (3.4956) grad_norm: 1.1390 (1.1411) time: 0.5028 [2021-03-25 19:18:08 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 130/1251] eta: 0:10:01 lr: 0.000804 loss: 3.4102 (3.4784) grad_norm: 1.1789 (1.1486) time: 0.5019 [2021-03-25 19:18:13 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 140/1251] eta: 0:09:53 lr: 0.000804 loss: 3.6231 (3.4878) grad_norm: 1.1402 (1.1483) time: 0.5037 [2021-03-25 19:18:19 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 150/1251] eta: 0:09:46 lr: 0.000804 loss: 3.6543 (3.5029) grad_norm: 1.0984 (1.1452) time: 0.5095 [2021-03-25 19:18:24 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 160/1251] eta: 0:09:39 lr: 0.000804 loss: 3.6483 (3.5028) grad_norm: 1.0909 (1.1426) time: 0.5090 [2021-03-25 19:18:29 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 170/1251] eta: 0:09:33 lr: 0.000804 loss: 3.1437 (3.4833) grad_norm: 1.0581 (1.1370) time: 0.5112 [2021-03-25 19:18:34 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 180/1251] eta: 0:09:26 lr: 0.000804 loss: 3.3825 (3.4845) grad_norm: 1.0762 (1.1378) time: 0.5122 [2021-03-25 19:18:39 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 190/1251] eta: 0:09:20 lr: 0.000804 loss: 3.6515 (3.4934) grad_norm: 1.1210 (1.1383) time: 0.5116 [2021-03-25 19:18:44 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 200/1251] eta: 0:09:15 lr: 0.000804 loss: 3.7187 (3.4995) grad_norm: 1.1871 (1.1418) time: 0.5211 [2021-03-25 19:18:49 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 210/1251] eta: 0:09:08 lr: 0.000804 loss: 3.7187 (3.5044) grad_norm: 1.1871 (1.1445) time: 0.5152 [2021-03-25 19:18:55 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 220/1251] eta: 0:09:03 lr: 0.000804 loss: 3.6416 (3.5049) grad_norm: 1.0540 (1.1391) time: 0.5135 [2021-03-25 19:19:00 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 230/1251] eta: 0:08:57 lr: 0.000804 loss: 3.5293 (3.5055) grad_norm: 1.0402 (1.1356) time: 0.5145 [2021-03-25 19:19:05 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 240/1251] eta: 0:08:51 lr: 0.000803 loss: 3.4032 (3.4956) grad_norm: 1.0613 (1.1334) time: 0.5062 [2021-03-25 19:19:10 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 250/1251] eta: 0:08:45 lr: 0.000803 loss: 3.5256 (3.5007) grad_norm: 1.0613 (1.1323) time: 0.5096 [2021-03-25 19:19:15 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 260/1251] eta: 0:08:39 lr: 0.000803 loss: 3.6010 (3.5048) grad_norm: 1.1000 (1.1311) time: 0.5135 [2021-03-25 19:19:20 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 270/1251] eta: 0:08:33 lr: 0.000803 loss: 3.5288 (3.5072) grad_norm: 1.1000 (1.1306) time: 0.5101 [2021-03-25 19:19:25 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 280/1251] eta: 0:08:28 lr: 0.000803 loss: 3.6420 (3.5144) grad_norm: 1.1135 (1.1309) time: 0.5093 [2021-03-25 19:19:30 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 290/1251] eta: 0:08:22 lr: 0.000803 loss: 3.7105 (3.5133) grad_norm: 1.1209 (1.1307) time: 0.5147 [2021-03-25 19:19:35 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 300/1251] eta: 0:08:16 lr: 0.000803 loss: 3.3892 (3.5113) grad_norm: 1.1455 (1.1313) time: 0.5118 [2021-03-25 19:19:40 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 310/1251] eta: 0:08:10 lr: 0.000803 loss: 3.4045 (3.5054) grad_norm: 1.1479 (1.1316) time: 0.5024 [2021-03-25 19:19:46 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 320/1251] eta: 0:08:05 lr: 0.000803 loss: 3.3582 (3.4964) grad_norm: 1.0972 (1.1315) time: 0.5042 [2021-03-25 19:19:51 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 330/1251] eta: 0:07:59 lr: 0.000803 loss: 3.5999 (3.5015) grad_norm: 1.0950 (1.1305) time: 0.5100 [2021-03-25 19:19:56 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 340/1251] eta: 0:07:54 lr: 0.000803 loss: 3.6738 (3.4980) grad_norm: 1.0711 (1.1289) time: 0.5052 [2021-03-25 19:20:01 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 350/1251] eta: 0:07:48 lr: 0.000803 loss: 3.5515 (3.4953) grad_norm: 1.1162 (1.1325) time: 0.5043 [2021-03-25 19:20:06 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 360/1251] eta: 0:07:42 lr: 0.000803 loss: 3.5515 (3.4928) grad_norm: 1.2177 (1.1366) time: 0.5039 [2021-03-25 19:20:11 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 370/1251] eta: 0:07:37 lr: 0.000803 loss: 3.5470 (3.4965) grad_norm: 1.2656 (1.1394) time: 0.5113 [2021-03-25 19:20:16 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 380/1251] eta: 0:07:32 lr: 0.000803 loss: 3.7041 (3.5009) grad_norm: 1.1006 (1.1390) time: 0.5118 [2021-03-25 19:20:21 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 390/1251] eta: 0:07:26 lr: 0.000803 loss: 3.7053 (3.4965) grad_norm: 1.0909 (1.1381) time: 0.5069 [2021-03-25 19:20:26 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 400/1251] eta: 0:07:21 lr: 0.000803 loss: 3.3166 (3.4930) grad_norm: 1.1512 (1.1388) time: 0.5070 [2021-03-25 19:20:31 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 410/1251] eta: 0:07:15 lr: 0.000803 loss: 3.5477 (3.4953) grad_norm: 1.0876 (1.1366) time: 0.5057 [2021-03-25 19:20:36 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 420/1251] eta: 0:07:10 lr: 0.000803 loss: 3.6488 (3.4979) grad_norm: 1.0408 (1.1350) time: 0.5027 [2021-03-25 19:20:41 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 430/1251] eta: 0:07:04 lr: 0.000803 loss: 3.5521 (3.5001) grad_norm: 1.0527 (1.1336) time: 0.4979 [2021-03-25 19:20:46 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 440/1251] eta: 0:06:59 lr: 0.000803 loss: 3.5047 (3.5021) grad_norm: 1.0755 (1.1333) time: 0.5013 [2021-03-25 19:20:51 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 450/1251] eta: 0:06:54 lr: 0.000803 loss: 3.8157 (3.5092) grad_norm: 1.1135 (1.1321) time: 0.5118 [2021-03-25 19:20:56 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 460/1251] eta: 0:06:48 lr: 0.000803 loss: 3.7124 (3.5046) grad_norm: 1.1295 (1.1335) time: 0.5102 [2021-03-25 19:21:01 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 470/1251] eta: 0:06:43 lr: 0.000803 loss: 3.4252 (3.5069) grad_norm: 1.1295 (1.1334) time: 0.5003 [2021-03-25 19:21:07 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 480/1251] eta: 0:06:38 lr: 0.000803 loss: 3.5278 (3.5102) grad_norm: 1.1229 (1.1339) time: 0.5069 [2021-03-25 19:21:12 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 490/1251] eta: 0:06:32 lr: 0.000803 loss: 3.6729 (3.5123) grad_norm: 1.0840 (1.1327) time: 0.5060 [2021-03-25 19:21:17 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 500/1251] eta: 0:06:27 lr: 0.000803 loss: 3.6305 (3.5124) grad_norm: 1.0974 (1.1330) time: 0.5009 [2021-03-25 19:21:22 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 510/1251] eta: 0:06:21 lr: 0.000803 loss: 3.3924 (3.5094) grad_norm: 1.1036 (1.1321) time: 0.5026 [2021-03-25 19:21:27 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 520/1251] eta: 0:06:16 lr: 0.000803 loss: 3.3556 (3.5083) grad_norm: 1.0841 (1.1312) time: 0.5009 [2021-03-25 19:21:32 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 530/1251] eta: 0:06:11 lr: 0.000803 loss: 3.4135 (3.5094) grad_norm: 1.0769 (1.1302) time: 0.5016 [2021-03-25 19:21:37 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 540/1251] eta: 0:06:06 lr: 0.000802 loss: 3.6560 (3.5107) grad_norm: 1.0727 (1.1306) time: 0.5104 [2021-03-25 19:21:42 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 550/1251] eta: 0:06:01 lr: 0.000802 loss: 3.6630 (3.5119) grad_norm: 1.1302 (1.1318) time: 0.5188 [2021-03-25 19:21:47 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 560/1251] eta: 0:05:55 lr: 0.000802 loss: 3.5206 (3.5115) grad_norm: 1.1617 (1.1330) time: 0.5144 [2021-03-25 19:21:52 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 570/1251] eta: 0:05:50 lr: 0.000802 loss: 3.4877 (3.5101) grad_norm: 1.0969 (1.1327) time: 0.5047 [2021-03-25 19:21:57 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 580/1251] eta: 0:05:45 lr: 0.000802 loss: 3.7183 (3.5156) grad_norm: 1.0820 (1.1325) time: 0.5018 [2021-03-25 19:22:02 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 590/1251] eta: 0:05:40 lr: 0.000802 loss: 3.7844 (3.5195) grad_norm: 1.0830 (1.1319) time: 0.5076 [2021-03-25 19:22:07 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 600/1251] eta: 0:05:34 lr: 0.000802 loss: 3.7844 (3.5187) grad_norm: 1.1130 (1.1320) time: 0.5124 [2021-03-25 19:22:13 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 610/1251] eta: 0:05:29 lr: 0.000802 loss: 3.4907 (3.5182) grad_norm: 1.1171 (1.1326) time: 0.5124 [2021-03-25 19:22:18 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 620/1251] eta: 0:05:24 lr: 0.000802 loss: 3.3545 (3.5159) grad_norm: 1.0625 (1.1314) time: 0.5092 [2021-03-25 19:22:23 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 630/1251] eta: 0:05:19 lr: 0.000802 loss: 3.4461 (3.5148) grad_norm: 1.0560 (1.1298) time: 0.5028 [2021-03-25 19:22:28 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 640/1251] eta: 0:05:14 lr: 0.000802 loss: 3.5031 (3.5124) grad_norm: 1.0224 (1.1286) time: 0.5047 [2021-03-25 19:22:33 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 650/1251] eta: 0:05:08 lr: 0.000802 loss: 3.5031 (3.5104) grad_norm: 1.0392 (1.1278) time: 0.5066 [2021-03-25 19:22:38 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 660/1251] eta: 0:05:03 lr: 0.000802 loss: 3.3807 (3.5058) grad_norm: 1.0924 (1.1272) time: 0.5064 [2021-03-25 19:22:43 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 670/1251] eta: 0:04:58 lr: 0.000802 loss: 3.6247 (3.5093) grad_norm: 1.1094 (1.1278) time: 0.5062 [2021-03-25 19:22:48 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 680/1251] eta: 0:04:53 lr: 0.000802 loss: 3.6565 (3.5096) grad_norm: 1.1069 (1.1274) time: 0.5064 [2021-03-25 19:22:53 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 690/1251] eta: 0:04:47 lr: 0.000802 loss: 3.5400 (3.5107) grad_norm: 1.1194 (1.1280) time: 0.5060 [2021-03-25 19:22:58 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 700/1251] eta: 0:04:42 lr: 0.000802 loss: 3.6856 (3.5125) grad_norm: 1.1324 (1.1277) time: 0.5068 [2021-03-25 19:23:03 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 710/1251] eta: 0:04:37 lr: 0.000802 loss: 3.6856 (3.5117) grad_norm: 1.1037 (1.1276) time: 0.5090 [2021-03-25 19:23:08 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 720/1251] eta: 0:04:32 lr: 0.000802 loss: 3.3876 (3.5090) grad_norm: 1.0815 (1.1273) time: 0.5044 [2021-03-25 19:23:13 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 730/1251] eta: 0:04:27 lr: 0.000802 loss: 3.5134 (3.5119) grad_norm: 1.1326 (1.1282) time: 0.5141 [2021-03-25 19:23:19 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 740/1251] eta: 0:04:22 lr: 0.000802 loss: 3.5052 (3.5074) grad_norm: 1.1326 (1.1275) time: 0.5237 [2021-03-25 19:23:24 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 750/1251] eta: 0:04:17 lr: 0.000802 loss: 3.1486 (3.5056) grad_norm: 1.0373 (1.1265) time: 0.5138 [2021-03-25 19:23:29 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 760/1251] eta: 0:04:12 lr: 0.000802 loss: 3.5292 (3.5056) grad_norm: 1.0460 (1.1255) time: 0.5116 [2021-03-25 19:23:34 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 770/1251] eta: 0:04:06 lr: 0.000802 loss: 3.6255 (3.5068) grad_norm: 1.1378 (1.1265) time: 0.5158 [2021-03-25 19:23:39 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 780/1251] eta: 0:04:01 lr: 0.000802 loss: 3.7581 (3.5117) grad_norm: 1.1266 (1.1254) time: 0.5107 [2021-03-25 19:23:44 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 790/1251] eta: 0:03:56 lr: 0.000802 loss: 3.8220 (3.5120) grad_norm: 1.0435 (1.1247) time: 0.5108 [2021-03-25 19:23:49 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 800/1251] eta: 0:03:51 lr: 0.000802 loss: 3.6211 (3.5120) grad_norm: 1.0661 (1.1242) time: 0.5079 [2021-03-25 19:23:54 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 810/1251] eta: 0:03:46 lr: 0.000802 loss: 3.6688 (3.5149) grad_norm: 1.0798 (1.1247) time: 0.5030 [2021-03-25 19:23:59 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 820/1251] eta: 0:03:41 lr: 0.000802 loss: 3.7322 (3.5178) grad_norm: 1.1430 (1.1253) time: 0.5048 [2021-03-25 19:24:04 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 830/1251] eta: 0:03:35 lr: 0.000802 loss: 3.6484 (3.5175) grad_norm: 1.1208 (1.1252) time: 0.5071 [2021-03-25 19:24:09 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 840/1251] eta: 0:03:30 lr: 0.000801 loss: 3.4654 (3.5165) grad_norm: 1.1099 (1.1248) time: 0.5064 [2021-03-25 19:24:15 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 850/1251] eta: 0:03:25 lr: 0.000801 loss: 3.3752 (3.5156) grad_norm: 1.0790 (1.1246) time: 0.5047 [2021-03-25 19:24:20 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 860/1251] eta: 0:03:20 lr: 0.000801 loss: 3.3521 (3.5167) grad_norm: 1.1296 (1.1248) time: 0.5081 [2021-03-25 19:24:25 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 870/1251] eta: 0:03:15 lr: 0.000801 loss: 3.6536 (3.5179) grad_norm: 1.1045 (1.1246) time: 0.5062 [2021-03-25 19:24:30 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 880/1251] eta: 0:03:10 lr: 0.000801 loss: 3.7331 (3.5196) grad_norm: 1.1087 (1.1249) time: 0.5015 [2021-03-25 19:24:35 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 890/1251] eta: 0:03:04 lr: 0.000801 loss: 3.7107 (3.5193) grad_norm: 1.1087 (1.1247) time: 0.5023 [2021-03-25 19:24:40 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 900/1251] eta: 0:02:59 lr: 0.000801 loss: 3.6152 (3.5203) grad_norm: 1.1062 (1.1246) time: 0.5021 [2021-03-25 19:24:45 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 910/1251] eta: 0:02:54 lr: 0.000801 loss: 3.8250 (3.5254) grad_norm: 1.1357 (1.1247) time: 0.5009 [2021-03-25 19:24:50 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 920/1251] eta: 0:02:49 lr: 0.000801 loss: 3.7751 (3.5255) grad_norm: 1.0812 (1.1241) time: 0.5043 [2021-03-25 19:24:55 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 930/1251] eta: 0:02:44 lr: 0.000801 loss: 3.5278 (3.5255) grad_norm: 1.0547 (1.1239) time: 0.5153 [2021-03-25 19:25:00 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 940/1251] eta: 0:02:39 lr: 0.000801 loss: 3.6562 (3.5248) grad_norm: 1.0524 (1.1233) time: 0.5161 [2021-03-25 19:25:05 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 950/1251] eta: 0:02:34 lr: 0.000801 loss: 3.6565 (3.5261) grad_norm: 1.1164 (1.1242) time: 0.5091 [2021-03-25 19:25:10 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 960/1251] eta: 0:02:29 lr: 0.000801 loss: 3.5277 (3.5254) grad_norm: 1.1955 (1.1249) time: 0.5099 [2021-03-25 19:25:15 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 970/1251] eta: 0:02:23 lr: 0.000801 loss: 3.6163 (3.5276) grad_norm: 1.1528 (1.1249) time: 0.5065 [2021-03-25 19:25:20 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 980/1251] eta: 0:02:18 lr: 0.000801 loss: 3.8682 (3.5300) grad_norm: 1.0646 (1.1245) time: 0.5028 [2021-03-25 19:25:26 swin_small_patch4_window7_224] INFO: Epoch: [88] [ 990/1251] eta: 0:02:13 lr: 0.000801 loss: 3.8118 (3.5328) grad_norm: 1.0538 (1.1238) time: 0.5067 [2021-03-25 19:25:31 swin_small_patch4_window7_224] INFO: Epoch: [88] [1000/1251] eta: 0:02:08 lr: 0.000801 loss: 3.8118 (3.5345) grad_norm: 1.0889 (1.1238) time: 0.5086 [2021-03-25 19:25:36 swin_small_patch4_window7_224] INFO: Epoch: [88] [1010/1251] eta: 0:02:03 lr: 0.000801 loss: 3.7936 (3.5343) grad_norm: 1.1324 (1.1241) time: 0.5076 [2021-03-25 19:25:41 swin_small_patch4_window7_224] INFO: Epoch: [88] [1020/1251] eta: 0:01:58 lr: 0.000801 loss: 3.7720 (3.5350) grad_norm: 1.1111 (1.1237) time: 0.5015 [2021-03-25 19:25:46 swin_small_patch4_window7_224] INFO: Epoch: [88] [1030/1251] eta: 0:01:53 lr: 0.000801 loss: 3.6022 (3.5371) grad_norm: 1.1037 (1.1237) time: 0.5037 [2021-03-25 19:25:51 swin_small_patch4_window7_224] INFO: Epoch: [88] [1040/1251] eta: 0:01:47 lr: 0.000801 loss: 3.6022 (3.5369) grad_norm: 1.1037 (1.1232) time: 0.5081 [2021-03-25 19:25:56 swin_small_patch4_window7_224] INFO: Epoch: [88] [1050/1251] eta: 0:01:42 lr: 0.000801 loss: 3.5892 (3.5379) grad_norm: 1.0997 (1.1232) time: 0.5052 [2021-03-25 19:26:01 swin_small_patch4_window7_224] INFO: Epoch: [88] [1060/1251] eta: 0:01:37 lr: 0.000801 loss: 3.7999 (3.5407) grad_norm: 1.1500 (1.1241) time: 0.5034 [2021-03-25 19:26:06 swin_small_patch4_window7_224] INFO: Epoch: [88] [1070/1251] eta: 0:01:32 lr: 0.000801 loss: 3.6776 (3.5405) grad_norm: 1.1454 (1.1236) time: 0.5010 [2021-03-25 19:26:11 swin_small_patch4_window7_224] INFO: Epoch: [88] [1080/1251] eta: 0:01:27 lr: 0.000801 loss: 3.5564 (3.5421) grad_norm: 1.1082 (1.1242) time: 0.4991 [2021-03-25 19:26:16 swin_small_patch4_window7_224] INFO: Epoch: [88] [1090/1251] eta: 0:01:22 lr: 0.000801 loss: 3.8304 (3.5439) grad_norm: 1.1344 (1.1242) time: 0.5019 [2021-03-25 19:26:21 swin_small_patch4_window7_224] INFO: Epoch: [88] [1100/1251] eta: 0:01:17 lr: 0.000801 loss: 3.6472 (3.5431) grad_norm: 1.1063 (1.1240) time: 0.5068 [2021-03-25 19:26:26 swin_small_patch4_window7_224] INFO: Epoch: [88] [1110/1251] eta: 0:01:12 lr: 0.000801 loss: 3.4900 (3.5429) grad_norm: 1.0705 (1.1234) time: 0.5082 [2021-03-25 19:26:31 swin_small_patch4_window7_224] INFO: Epoch: [88] [1120/1251] eta: 0:01:06 lr: 0.000801 loss: 3.3671 (3.5409) grad_norm: 1.0401 (1.1231) time: 0.5051 [2021-03-25 19:26:36 swin_small_patch4_window7_224] INFO: Epoch: [88] [1130/1251] eta: 0:01:01 lr: 0.000801 loss: 3.4174 (3.5409) grad_norm: 1.0750 (1.1230) time: 0.4998 [2021-03-25 19:26:41 swin_small_patch4_window7_224] INFO: Epoch: [88] [1140/1251] eta: 0:00:56 lr: 0.000801 loss: 3.6112 (3.5422) grad_norm: 1.1348 (1.1231) time: 0.5018 [2021-03-25 19:26:46 swin_small_patch4_window7_224] INFO: Epoch: [88] [1150/1251] eta: 0:00:51 lr: 0.000800 loss: 3.6871 (3.5446) grad_norm: 1.1348 (1.1228) time: 0.5023 [2021-03-25 19:26:51 swin_small_patch4_window7_224] INFO: Epoch: [88] [1160/1251] eta: 0:00:46 lr: 0.000800 loss: 3.7535 (3.5458) grad_norm: 1.0783 (1.1228) time: 0.5053 [2021-03-25 19:26:56 swin_small_patch4_window7_224] INFO: Epoch: [88] [1170/1251] eta: 0:00:41 lr: 0.000800 loss: 3.6739 (3.5451) grad_norm: 1.0728 (1.1226) time: 0.5062 [2021-03-25 19:27:01 swin_small_patch4_window7_224] INFO: Epoch: [88] [1180/1251] eta: 0:00:36 lr: 0.000800 loss: 3.5588 (3.5445) grad_norm: 1.0728 (1.1225) time: 0.5060 [2021-03-25 19:27:07 swin_small_patch4_window7_224] INFO: Epoch: [88] [1190/1251] eta: 0:00:31 lr: 0.000800 loss: 3.3468 (3.5421) grad_norm: 1.0964 (1.1229) time: 0.5110 [2021-03-25 19:27:12 swin_small_patch4_window7_224] INFO: Epoch: [88] [1200/1251] eta: 0:00:26 lr: 0.000800 loss: 3.3468 (3.5417) grad_norm: 1.0964 (1.1227) time: 0.5092 [2021-03-25 19:27:17 swin_small_patch4_window7_224] INFO: Epoch: [88] [1210/1251] eta: 0:00:20 lr: 0.000800 loss: 3.3985 (3.5403) grad_norm: 1.0751 (1.1225) time: 0.5026 [2021-03-25 19:27:22 swin_small_patch4_window7_224] INFO: Epoch: [88] [1220/1251] eta: 0:00:15 lr: 0.000800 loss: 3.4357 (3.5408) grad_norm: 1.1177 (1.1227) time: 0.5038 [2021-03-25 19:27:27 swin_small_patch4_window7_224] INFO: Epoch: [88] [1230/1251] eta: 0:00:10 lr: 0.000800 loss: 3.4742 (3.5383) grad_norm: 1.1504 (1.1229) time: 0.5072 [2021-03-25 19:27:32 swin_small_patch4_window7_224] INFO: Epoch: [88] [1240/1251] eta: 0:00:05 lr: 0.000800 loss: 3.4742 (3.5374) grad_norm: 1.1719 (1.1238) time: 0.5017 [2021-03-25 19:27:37 swin_small_patch4_window7_224] INFO: Epoch: [88] [1250/1251] eta: 0:00:00 lr: 0.000800 loss: 3.5651 (3.5374) grad_norm: 1.1923 (1.1245) time: 0.5001 [2021-03-25 19:27:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:53 loss: 1.3404 (1.3404) acc1: 71.8750 (71.8750) acc5: 90.6250 (90.6250) [2021-03-25 19:27:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 1.1352 (1.1203) acc1: 73.4375 (73.0114) acc5: 93.7500 (93.1818) [2021-03-25 19:27:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0584 (1.0513) acc1: 75.0000 (74.8512) acc5: 93.7500 (93.5268) [2021-03-25 19:27:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0193 (1.0853) acc1: 75.0000 (73.8911) acc5: 93.7500 (93.0948) [2021-03-25 19:27:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0188 (1.0717) acc1: 73.4375 (74.4665) acc5: 93.7500 (93.2927) [2021-03-25 19:27:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0622 (1.0843) acc1: 76.5625 (74.4640) acc5: 93.7500 (93.2160) [2021-03-25 19:27:59 swin_small_patch4_window7_224] INFO: * Acc@1 75.274 Acc@5 92.978 loss 1.067 [2021-03-25 19:27:59 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.3% [2021-03-25 19:27:59 swin_small_patch4_window7_224] INFO: Max accuracy: 75.57% [2021-03-25 19:28:03 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 0/1251] eta: 1:28:51 lr: 0.000800 loss: 3.7409 (3.7409) grad_norm: 0.9922 (0.9922) time: 4.2621 [2021-03-25 19:28:09 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 10/1251] eta: 0:17:43 lr: 0.000800 loss: 3.2892 (3.3435) grad_norm: 1.1591 (1.1663) time: 0.8571 [2021-03-25 19:28:14 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 20/1251] eta: 0:14:09 lr: 0.000800 loss: 3.4261 (3.4353) grad_norm: 1.0929 (1.1223) time: 0.5112 [2021-03-25 19:28:19 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 30/1251] eta: 0:12:46 lr: 0.000800 loss: 3.7233 (3.4786) grad_norm: 1.0421 (1.1072) time: 0.5020 [2021-03-25 19:28:24 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 40/1251] eta: 0:12:07 lr: 0.000800 loss: 3.5990 (3.4665) grad_norm: 1.1165 (1.1259) time: 0.5072 [2021-03-25 19:28:29 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 50/1251] eta: 0:11:40 lr: 0.000800 loss: 3.7122 (3.5009) grad_norm: 1.1280 (1.1405) time: 0.5139 [2021-03-25 19:28:34 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 60/1251] eta: 0:11:20 lr: 0.000800 loss: 3.5743 (3.4795) grad_norm: 1.1008 (1.1311) time: 0.5107 [2021-03-25 19:28:39 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 70/1251] eta: 0:11:04 lr: 0.000800 loss: 3.3066 (3.4554) grad_norm: 1.0856 (1.1309) time: 0.5087 [2021-03-25 19:28:44 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 80/1251] eta: 0:10:50 lr: 0.000800 loss: 3.3066 (3.4385) grad_norm: 1.0931 (1.1310) time: 0.5064 [2021-03-25 19:28:49 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 90/1251] eta: 0:10:38 lr: 0.000800 loss: 3.3742 (3.4396) grad_norm: 1.0925 (1.1244) time: 0.5062 [2021-03-25 19:28:54 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 100/1251] eta: 0:10:27 lr: 0.000800 loss: 3.3742 (3.4296) grad_norm: 1.0435 (1.1173) time: 0.5057 [2021-03-25 19:28:59 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 110/1251] eta: 0:10:19 lr: 0.000800 loss: 3.7290 (3.4433) grad_norm: 1.1325 (1.1249) time: 0.5103 [2021-03-25 19:29:05 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 120/1251] eta: 0:10:11 lr: 0.000800 loss: 3.6174 (3.4404) grad_norm: 1.1455 (1.1345) time: 0.5159 [2021-03-25 19:29:10 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 130/1251] eta: 0:10:03 lr: 0.000800 loss: 3.5063 (3.4584) grad_norm: 1.0553 (1.1284) time: 0.5124 [2021-03-25 19:29:15 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 140/1251] eta: 0:09:56 lr: 0.000800 loss: 3.7615 (3.4661) grad_norm: 1.0098 (1.1205) time: 0.5151 [2021-03-25 19:29:20 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 150/1251] eta: 0:09:48 lr: 0.000800 loss: 3.5668 (3.4729) grad_norm: 1.0157 (1.1153) time: 0.5140 [2021-03-25 19:29:25 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 160/1251] eta: 0:09:42 lr: 0.000800 loss: 3.6882 (3.4942) grad_norm: 1.0534 (1.1141) time: 0.5107 [2021-03-25 19:29:30 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 170/1251] eta: 0:09:35 lr: 0.000800 loss: 3.6320 (3.4950) grad_norm: 1.0622 (1.1118) time: 0.5113 [2021-03-25 19:29:35 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 180/1251] eta: 0:09:29 lr: 0.000800 loss: 3.5039 (3.4972) grad_norm: 1.1006 (1.1169) time: 0.5132 [2021-03-25 19:29:40 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 190/1251] eta: 0:09:22 lr: 0.000799 loss: 3.6883 (3.5059) grad_norm: 1.1112 (1.1162) time: 0.5092 [2021-03-25 19:29:46 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 200/1251] eta: 0:09:16 lr: 0.000799 loss: 3.3138 (3.5035) grad_norm: 1.0941 (1.1175) time: 0.5097 [2021-03-25 19:29:51 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 210/1251] eta: 0:09:09 lr: 0.000799 loss: 3.3393 (3.5096) grad_norm: 1.0507 (1.1141) time: 0.5107 [2021-03-25 19:29:56 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 220/1251] eta: 0:09:03 lr: 0.000799 loss: 3.6877 (3.5162) grad_norm: 1.0447 (1.1127) time: 0.5019 [2021-03-25 19:30:01 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 230/1251] eta: 0:08:56 lr: 0.000799 loss: 3.6877 (3.5211) grad_norm: 1.0582 (1.1106) time: 0.5024 [2021-03-25 19:30:06 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 240/1251] eta: 0:08:50 lr: 0.000799 loss: 3.6700 (3.5205) grad_norm: 1.0912 (1.1132) time: 0.5048 [2021-03-25 19:30:11 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 250/1251] eta: 0:08:44 lr: 0.000799 loss: 3.6155 (3.5211) grad_norm: 1.1309 (1.1153) time: 0.5019 [2021-03-25 19:30:16 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 260/1251] eta: 0:08:38 lr: 0.000799 loss: 3.6710 (3.5275) grad_norm: 1.1232 (1.1155) time: 0.5005 [2021-03-25 19:30:21 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 270/1251] eta: 0:08:32 lr: 0.000799 loss: 3.6047 (3.5146) grad_norm: 1.1459 (1.1191) time: 0.5012 [2021-03-25 19:30:26 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 280/1251] eta: 0:08:26 lr: 0.000799 loss: 3.4730 (3.5120) grad_norm: 1.1711 (1.1202) time: 0.5039 [2021-03-25 19:30:31 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 290/1251] eta: 0:08:21 lr: 0.000799 loss: 3.6584 (3.5174) grad_norm: 1.1237 (1.1200) time: 0.5140 [2021-03-25 19:30:36 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 300/1251] eta: 0:08:15 lr: 0.000799 loss: 3.7593 (3.5303) grad_norm: 1.1022 (1.1197) time: 0.5078 [2021-03-25 19:30:41 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 310/1251] eta: 0:08:09 lr: 0.000799 loss: 3.6799 (3.5303) grad_norm: 1.0835 (1.1200) time: 0.5060 [2021-03-25 19:30:46 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 320/1251] eta: 0:08:04 lr: 0.000799 loss: 3.4467 (3.5263) grad_norm: 1.0796 (1.1193) time: 0.5114 [2021-03-25 19:30:51 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 330/1251] eta: 0:07:58 lr: 0.000799 loss: 3.1931 (3.5230) grad_norm: 1.0424 (1.1173) time: 0.5084 [2021-03-25 19:30:56 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 340/1251] eta: 0:07:53 lr: 0.000799 loss: 3.4011 (3.5186) grad_norm: 1.0877 (1.1188) time: 0.5116 [2021-03-25 19:31:01 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 350/1251] eta: 0:07:47 lr: 0.000799 loss: 3.5723 (3.5283) grad_norm: 1.1672 (1.1214) time: 0.5043 [2021-03-25 19:31:06 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 360/1251] eta: 0:07:42 lr: 0.000799 loss: 3.6756 (3.5290) grad_norm: 1.1593 (1.1214) time: 0.5023 [2021-03-25 19:31:11 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 370/1251] eta: 0:07:36 lr: 0.000799 loss: 3.5529 (3.5237) grad_norm: 1.0503 (1.1196) time: 0.5038 [2021-03-25 19:31:16 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 380/1251] eta: 0:07:30 lr: 0.000799 loss: 3.4687 (3.5173) grad_norm: 1.0820 (1.1205) time: 0.5003 [2021-03-25 19:31:22 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 390/1251] eta: 0:07:25 lr: 0.000799 loss: 3.3744 (3.5089) grad_norm: 1.1068 (1.1204) time: 0.5050 [2021-03-25 19:31:27 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 400/1251] eta: 0:07:19 lr: 0.000799 loss: 3.3976 (3.5150) grad_norm: 1.0745 (1.1186) time: 0.5031 [2021-03-25 19:31:32 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 410/1251] eta: 0:07:14 lr: 0.000799 loss: 3.7417 (3.5120) grad_norm: 1.0745 (1.1188) time: 0.5054 [2021-03-25 19:31:37 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 420/1251] eta: 0:07:09 lr: 0.000799 loss: 3.5590 (3.5114) grad_norm: 1.1095 (1.1174) time: 0.5091 [2021-03-25 19:31:42 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 430/1251] eta: 0:07:03 lr: 0.000799 loss: 3.5590 (3.5074) grad_norm: 1.0899 (1.1172) time: 0.5030 [2021-03-25 19:31:47 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 440/1251] eta: 0:06:58 lr: 0.000799 loss: 3.6246 (3.5070) grad_norm: 1.0897 (1.1165) time: 0.4984 [2021-03-25 19:31:52 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 450/1251] eta: 0:06:53 lr: 0.000799 loss: 3.5341 (3.5083) grad_norm: 1.0886 (1.1169) time: 0.5055 [2021-03-25 19:31:57 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 460/1251] eta: 0:06:47 lr: 0.000799 loss: 3.5341 (3.5111) grad_norm: 1.1420 (1.1185) time: 0.5104 [2021-03-25 19:32:02 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 470/1251] eta: 0:06:42 lr: 0.000799 loss: 3.8388 (3.5153) grad_norm: 1.1596 (1.1204) time: 0.5064 [2021-03-25 19:32:07 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 480/1251] eta: 0:06:37 lr: 0.000799 loss: 3.6623 (3.5086) grad_norm: 1.1741 (1.1216) time: 0.5057 [2021-03-25 19:32:12 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 490/1251] eta: 0:06:32 lr: 0.000798 loss: 3.5471 (3.5121) grad_norm: 1.1105 (1.1208) time: 0.5096 [2021-03-25 19:32:17 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 500/1251] eta: 0:06:26 lr: 0.000798 loss: 3.6602 (3.5102) grad_norm: 1.1533 (1.1236) time: 0.5074 [2021-03-25 19:32:22 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 510/1251] eta: 0:06:21 lr: 0.000798 loss: 3.5381 (3.5076) grad_norm: 1.1703 (1.1239) time: 0.5033 [2021-03-25 19:32:27 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 520/1251] eta: 0:06:16 lr: 0.000798 loss: 3.4575 (3.5060) grad_norm: 1.0886 (1.1237) time: 0.5043 [2021-03-25 19:32:32 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 530/1251] eta: 0:06:10 lr: 0.000798 loss: 3.5278 (3.5075) grad_norm: 1.0498 (1.1220) time: 0.5045 [2021-03-25 19:32:37 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 540/1251] eta: 0:06:05 lr: 0.000798 loss: 3.7718 (3.5128) grad_norm: 1.0666 (1.1219) time: 0.5100 [2021-03-25 19:32:43 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 550/1251] eta: 0:06:00 lr: 0.000798 loss: 3.6113 (3.5071) grad_norm: 1.0994 (1.1230) time: 0.5205 [2021-03-25 19:32:48 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 560/1251] eta: 0:05:55 lr: 0.000798 loss: 3.3796 (3.5104) grad_norm: 1.1253 (1.1228) time: 0.5184 [2021-03-25 19:32:53 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 570/1251] eta: 0:05:50 lr: 0.000798 loss: 3.4910 (3.5085) grad_norm: 1.0754 (1.1223) time: 0.5057 [2021-03-25 19:32:58 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 580/1251] eta: 0:05:44 lr: 0.000798 loss: 3.4551 (3.5055) grad_norm: 1.1052 (1.1225) time: 0.5036 [2021-03-25 19:33:03 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 590/1251] eta: 0:05:39 lr: 0.000798 loss: 3.5913 (3.5062) grad_norm: 1.1399 (1.1230) time: 0.5079 [2021-03-25 19:33:08 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 600/1251] eta: 0:05:34 lr: 0.000798 loss: 3.6578 (3.5100) grad_norm: 1.0900 (1.1222) time: 0.5108 [2021-03-25 19:33:13 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 610/1251] eta: 0:05:29 lr: 0.000798 loss: 3.5608 (3.5103) grad_norm: 1.0900 (1.1236) time: 0.5091 [2021-03-25 19:33:18 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 620/1251] eta: 0:05:24 lr: 0.000798 loss: 3.4983 (3.5106) grad_norm: 1.0805 (1.1227) time: 0.5085 [2021-03-25 19:33:23 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 630/1251] eta: 0:05:19 lr: 0.000798 loss: 3.3421 (3.5081) grad_norm: 1.0799 (1.1225) time: 0.5098 [2021-03-25 19:33:28 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 640/1251] eta: 0:05:13 lr: 0.000798 loss: 3.2803 (3.5059) grad_norm: 1.0609 (1.1212) time: 0.5091 [2021-03-25 19:33:34 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 650/1251] eta: 0:05:08 lr: 0.000798 loss: 3.4829 (3.5073) grad_norm: 1.0755 (1.1219) time: 0.5070 [2021-03-25 19:33:39 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 660/1251] eta: 0:05:03 lr: 0.000798 loss: 3.4589 (3.5056) grad_norm: 1.1696 (1.1224) time: 0.5069 [2021-03-25 19:33:44 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 670/1251] eta: 0:04:58 lr: 0.000798 loss: 3.6350 (3.5100) grad_norm: 1.1283 (1.1221) time: 0.5143 [2021-03-25 19:33:49 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 680/1251] eta: 0:04:53 lr: 0.000798 loss: 3.7382 (3.5121) grad_norm: 1.1419 (1.1225) time: 0.5129 [2021-03-25 19:33:54 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 690/1251] eta: 0:04:48 lr: 0.000798 loss: 3.6740 (3.5151) grad_norm: 1.1063 (1.1221) time: 0.5081 [2021-03-25 19:33:59 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 700/1251] eta: 0:04:42 lr: 0.000798 loss: 3.7214 (3.5193) grad_norm: 1.0943 (1.1215) time: 0.5074 [2021-03-25 19:34:04 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 710/1251] eta: 0:04:37 lr: 0.000798 loss: 3.7818 (3.5224) grad_norm: 1.0894 (1.1214) time: 0.5059 [2021-03-25 19:34:09 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 720/1251] eta: 0:04:32 lr: 0.000798 loss: 3.6110 (3.5236) grad_norm: 1.0894 (1.1213) time: 0.5077 [2021-03-25 19:34:14 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 730/1251] eta: 0:04:27 lr: 0.000798 loss: 3.5655 (3.5260) grad_norm: 1.0684 (1.1208) time: 0.5101 [2021-03-25 19:34:20 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 740/1251] eta: 0:04:22 lr: 0.000798 loss: 3.5655 (3.5261) grad_norm: 1.1102 (1.1222) time: 0.5195 [2021-03-25 19:34:25 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 750/1251] eta: 0:04:17 lr: 0.000798 loss: 3.2472 (3.5204) grad_norm: 1.1850 (1.1225) time: 0.5258 [2021-03-25 19:34:30 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 760/1251] eta: 0:04:12 lr: 0.000798 loss: 3.6110 (3.5245) grad_norm: 1.1986 (1.1245) time: 0.5149 [2021-03-25 19:34:35 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 770/1251] eta: 0:04:06 lr: 0.000798 loss: 3.7321 (3.5262) grad_norm: 1.1882 (1.1252) time: 0.5075 [2021-03-25 19:34:40 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 780/1251] eta: 0:04:01 lr: 0.000798 loss: 3.7697 (3.5292) grad_norm: 1.1666 (1.1256) time: 0.5126 [2021-03-25 19:34:45 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 790/1251] eta: 0:03:56 lr: 0.000797 loss: 3.7282 (3.5280) grad_norm: 1.1124 (1.1256) time: 0.5148 [2021-03-25 19:34:50 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 800/1251] eta: 0:03:51 lr: 0.000797 loss: 3.4869 (3.5264) grad_norm: 1.1058 (1.1253) time: 0.5089 [2021-03-25 19:34:55 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 810/1251] eta: 0:03:46 lr: 0.000797 loss: 3.5617 (3.5288) grad_norm: 1.1000 (1.1252) time: 0.4981 [2021-03-25 19:35:00 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 820/1251] eta: 0:03:41 lr: 0.000797 loss: 3.7207 (3.5301) grad_norm: 1.0460 (1.1244) time: 0.4991 [2021-03-25 19:35:05 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 830/1251] eta: 0:03:35 lr: 0.000797 loss: 3.6930 (3.5299) grad_norm: 1.0460 (1.1240) time: 0.5025 [2021-03-25 19:35:10 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 840/1251] eta: 0:03:30 lr: 0.000797 loss: 3.4821 (3.5266) grad_norm: 1.1113 (inf) time: 0.4994 [2021-03-25 19:35:15 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 850/1251] eta: 0:03:25 lr: 0.000797 loss: 3.6880 (3.5294) grad_norm: 1.1113 (inf) time: 0.5031 [2021-03-25 19:35:20 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 860/1251] eta: 0:03:20 lr: 0.000797 loss: 3.6880 (3.5259) grad_norm: 1.1509 (inf) time: 0.5087 [2021-03-25 19:35:26 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 870/1251] eta: 0:03:15 lr: 0.000797 loss: 3.5098 (3.5280) grad_norm: 1.1699 (inf) time: 0.5068 [2021-03-25 19:35:31 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 880/1251] eta: 0:03:10 lr: 0.000797 loss: 3.5098 (3.5259) grad_norm: 1.0418 (inf) time: 0.5116 [2021-03-25 19:35:36 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 890/1251] eta: 0:03:04 lr: 0.000797 loss: 3.5057 (3.5267) grad_norm: 1.0922 (inf) time: 0.5098 [2021-03-25 19:35:41 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 900/1251] eta: 0:02:59 lr: 0.000797 loss: 3.7968 (3.5295) grad_norm: 1.1564 (inf) time: 0.5054 [2021-03-25 19:35:46 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 910/1251] eta: 0:02:54 lr: 0.000797 loss: 3.6475 (3.5294) grad_norm: 1.1751 (inf) time: 0.5044 [2021-03-25 19:35:51 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 920/1251] eta: 0:02:49 lr: 0.000797 loss: 3.6475 (3.5323) grad_norm: 1.1711 (inf) time: 0.5073 [2021-03-25 19:35:56 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 930/1251] eta: 0:02:44 lr: 0.000797 loss: 3.7821 (3.5342) grad_norm: 1.0757 (inf) time: 0.5128 [2021-03-25 19:36:01 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 940/1251] eta: 0:02:39 lr: 0.000797 loss: 3.7889 (3.5369) grad_norm: 1.0564 (inf) time: 0.5151 [2021-03-25 19:36:06 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 950/1251] eta: 0:02:34 lr: 0.000797 loss: 3.7658 (3.5368) grad_norm: 1.0564 (inf) time: 0.5168 [2021-03-25 19:36:12 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 960/1251] eta: 0:02:29 lr: 0.000797 loss: 3.3707 (3.5348) grad_norm: 1.1296 (inf) time: 0.5111 [2021-03-25 19:36:17 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 970/1251] eta: 0:02:23 lr: 0.000797 loss: 3.3583 (3.5340) grad_norm: 1.1766 (inf) time: 0.5086 [2021-03-25 19:36:22 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 980/1251] eta: 0:02:18 lr: 0.000797 loss: 3.6918 (3.5358) grad_norm: 1.1322 (inf) time: 0.5050 [2021-03-25 19:36:27 swin_small_patch4_window7_224] INFO: Epoch: [89] [ 990/1251] eta: 0:02:13 lr: 0.000797 loss: 3.7870 (3.5362) grad_norm: 1.0673 (inf) time: 0.5045 [2021-03-25 19:36:32 swin_small_patch4_window7_224] INFO: Epoch: [89] [1000/1251] eta: 0:02:08 lr: 0.000797 loss: 3.5636 (3.5331) grad_norm: 1.0673 (inf) time: 0.5067 [2021-03-25 19:36:37 swin_small_patch4_window7_224] INFO: Epoch: [89] [1010/1251] eta: 0:02:03 lr: 0.000797 loss: 3.5636 (3.5350) grad_norm: 1.1005 (inf) time: 0.5060 [2021-03-25 19:36:42 swin_small_patch4_window7_224] INFO: Epoch: [89] [1020/1251] eta: 0:01:58 lr: 0.000797 loss: 3.8539 (3.5362) grad_norm: 1.0872 (inf) time: 0.5036 [2021-03-25 19:36:47 swin_small_patch4_window7_224] INFO: Epoch: [89] [1030/1251] eta: 0:01:53 lr: 0.000797 loss: 3.7505 (3.5355) grad_norm: 1.1143 (inf) time: 0.5044 [2021-03-25 19:36:52 swin_small_patch4_window7_224] INFO: Epoch: [89] [1040/1251] eta: 0:01:47 lr: 0.000797 loss: 3.3577 (3.5330) grad_norm: 1.1587 (inf) time: 0.5071 [2021-03-25 19:36:57 swin_small_patch4_window7_224] INFO: Epoch: [89] [1050/1251] eta: 0:01:42 lr: 0.000797 loss: 3.4662 (3.5331) grad_norm: 1.1404 (inf) time: 0.5078 [2021-03-25 19:37:02 swin_small_patch4_window7_224] INFO: Epoch: [89] [1060/1251] eta: 0:01:37 lr: 0.000797 loss: 3.5506 (3.5329) grad_norm: 1.0583 (inf) time: 0.5024 [2021-03-25 19:37:07 swin_small_patch4_window7_224] INFO: Epoch: [89] [1070/1251] eta: 0:01:32 lr: 0.000797 loss: 3.5416 (3.5341) grad_norm: 1.0938 (inf) time: 0.5012 [2021-03-25 19:37:12 swin_small_patch4_window7_224] INFO: Epoch: [89] [1080/1251] eta: 0:01:27 lr: 0.000797 loss: 3.5067 (3.5334) grad_norm: 1.1454 (inf) time: 0.5046 [2021-03-25 19:37:17 swin_small_patch4_window7_224] INFO: Epoch: [89] [1090/1251] eta: 0:01:22 lr: 0.000796 loss: 3.4895 (3.5345) grad_norm: 1.1537 (inf) time: 0.5075 [2021-03-25 19:37:22 swin_small_patch4_window7_224] INFO: Epoch: [89] [1100/1251] eta: 0:01:17 lr: 0.000796 loss: 3.6415 (3.5366) grad_norm: 1.0462 (inf) time: 0.5064 [2021-03-25 19:37:27 swin_small_patch4_window7_224] INFO: Epoch: [89] [1110/1251] eta: 0:01:12 lr: 0.000796 loss: 3.6884 (3.5376) grad_norm: 1.0258 (inf) time: 0.5025 [2021-03-25 19:37:32 swin_small_patch4_window7_224] INFO: Epoch: [89] [1120/1251] eta: 0:01:06 lr: 0.000796 loss: 3.4726 (3.5370) grad_norm: 1.0668 (inf) time: 0.5004 [2021-03-25 19:37:37 swin_small_patch4_window7_224] INFO: Epoch: [89] [1130/1251] eta: 0:01:01 lr: 0.000796 loss: 3.3901 (3.5361) grad_norm: 1.0609 (inf) time: 0.4980 [2021-03-25 19:37:42 swin_small_patch4_window7_224] INFO: Epoch: [89] [1140/1251] eta: 0:00:56 lr: 0.000796 loss: 3.4295 (3.5360) grad_norm: 1.0755 (inf) time: 0.4983 [2021-03-25 19:37:47 swin_small_patch4_window7_224] INFO: Epoch: [89] [1150/1251] eta: 0:00:51 lr: 0.000796 loss: 3.2414 (3.5326) grad_norm: 1.1426 (inf) time: 0.4996 [2021-03-25 19:37:52 swin_small_patch4_window7_224] INFO: Epoch: [89] [1160/1251] eta: 0:00:46 lr: 0.000796 loss: 3.4590 (3.5339) grad_norm: 1.1454 (inf) time: 0.5024 [2021-03-25 19:37:57 swin_small_patch4_window7_224] INFO: Epoch: [89] [1170/1251] eta: 0:00:41 lr: 0.000796 loss: 3.7957 (3.5344) grad_norm: 1.1215 (inf) time: 0.5067 [2021-03-25 19:38:02 swin_small_patch4_window7_224] INFO: Epoch: [89] [1180/1251] eta: 0:00:36 lr: 0.000796 loss: 3.4158 (3.5347) grad_norm: 1.1180 (inf) time: 0.5015 [2021-03-25 19:38:07 swin_small_patch4_window7_224] INFO: Epoch: [89] [1190/1251] eta: 0:00:31 lr: 0.000796 loss: 3.4158 (3.5325) grad_norm: 1.0822 (inf) time: 0.4988 [2021-03-25 19:38:13 swin_small_patch4_window7_224] INFO: Epoch: [89] [1200/1251] eta: 0:00:26 lr: 0.000796 loss: 3.3816 (3.5315) grad_norm: 1.0821 (inf) time: 0.5094 [2021-03-25 19:38:18 swin_small_patch4_window7_224] INFO: Epoch: [89] [1210/1251] eta: 0:00:20 lr: 0.000796 loss: 3.4862 (3.5324) grad_norm: 1.1128 (inf) time: 0.5094 [2021-03-25 19:38:23 swin_small_patch4_window7_224] INFO: Epoch: [89] [1220/1251] eta: 0:00:15 lr: 0.000796 loss: 3.6215 (3.5320) grad_norm: 1.1204 (inf) time: 0.5089 [2021-03-25 19:38:28 swin_small_patch4_window7_224] INFO: Epoch: [89] [1230/1251] eta: 0:00:10 lr: 0.000796 loss: 3.6611 (3.5312) grad_norm: 1.0456 (inf) time: 0.5124 [2021-03-25 19:38:33 swin_small_patch4_window7_224] INFO: Epoch: [89] [1240/1251] eta: 0:00:05 lr: 0.000796 loss: 3.3739 (3.5304) grad_norm: 1.0429 (inf) time: 0.5100 [2021-03-25 19:38:38 swin_small_patch4_window7_224] INFO: Epoch: [89] [1250/1251] eta: 0:00:00 lr: 0.000796 loss: 3.4342 (3.5302) grad_norm: 1.1051 (inf) time: 0.5079 [2021-03-25 19:38:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 1.1170 (1.1170) acc1: 68.7500 (68.7500) acc5: 96.8750 (96.8750) [2021-03-25 19:38:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.1005 (1.0799) acc1: 71.8750 (73.7216) acc5: 92.1875 (92.7557) [2021-03-25 19:38:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0608 (1.0621) acc1: 75.0000 (74.4792) acc5: 93.7500 (93.3780) [2021-03-25 19:38:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0471 (1.0488) acc1: 75.0000 (74.5968) acc5: 93.7500 (93.6492) [2021-03-25 19:38:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0760 (1.0553) acc1: 73.4375 (74.5046) acc5: 93.7500 (93.6738) [2021-03-25 19:38:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1079 (1.0616) acc1: 73.4375 (74.7200) acc5: 92.4528 (93.6000) [2021-03-25 19:38:58 swin_small_patch4_window7_224] INFO: * Acc@1 75.402 Acc@5 93.154 loss 1.052 [2021-03-25 19:38:58 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.4% [2021-03-25 19:38:58 swin_small_patch4_window7_224] INFO: Max accuracy: 75.57% [2021-03-25 19:39:03 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 0/1251] eta: 1:26:30 lr: 0.000796 loss: 4.3571 (4.3571) grad_norm: 1.1649 (1.1649) time: 4.1493 [2021-03-25 19:39:08 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 10/1251] eta: 0:17:33 lr: 0.000796 loss: 3.8493 (3.7615) grad_norm: 1.1630 (1.1383) time: 0.8486 [2021-03-25 19:39:13 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 20/1251] eta: 0:14:03 lr: 0.000796 loss: 3.7163 (3.7434) grad_norm: 1.0236 (1.0754) time: 0.5118 [2021-03-25 19:39:18 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 30/1251] eta: 0:12:44 lr: 0.000796 loss: 3.6404 (3.6526) grad_norm: 1.0108 (1.0854) time: 0.5042 [2021-03-25 19:39:23 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 40/1251] eta: 0:12:07 lr: 0.000796 loss: 3.6649 (3.6411) grad_norm: 1.1019 (1.0899) time: 0.5123 [2021-03-25 19:39:28 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 50/1251] eta: 0:11:38 lr: 0.000796 loss: 3.6012 (3.6348) grad_norm: 1.0854 (1.0886) time: 0.5120 [2021-03-25 19:39:33 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 60/1251] eta: 0:11:18 lr: 0.000796 loss: 3.6012 (3.6082) grad_norm: 1.0816 (1.0885) time: 0.5060 [2021-03-25 19:39:38 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 70/1251] eta: 0:11:01 lr: 0.000796 loss: 3.6654 (3.6108) grad_norm: 1.0597 (1.0890) time: 0.5063 [2021-03-25 19:39:43 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 80/1251] eta: 0:10:47 lr: 0.000796 loss: 3.5941 (3.5951) grad_norm: 1.0597 (1.0931) time: 0.5031 [2021-03-25 19:39:48 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 90/1251] eta: 0:10:38 lr: 0.000796 loss: 3.4458 (3.5721) grad_norm: 1.0747 (1.0908) time: 0.5122 [2021-03-25 19:39:54 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 100/1251] eta: 0:10:28 lr: 0.000796 loss: 3.5713 (3.5698) grad_norm: 1.1064 (1.0979) time: 0.5146 [2021-03-25 19:39:59 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 110/1251] eta: 0:10:18 lr: 0.000796 loss: 3.5713 (3.5476) grad_norm: 1.1064 (1.0976) time: 0.5069 [2021-03-25 19:40:04 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 120/1251] eta: 0:10:09 lr: 0.000796 loss: 3.4146 (3.5601) grad_norm: 1.0849 (1.1015) time: 0.5024 [2021-03-25 19:40:09 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 130/1251] eta: 0:10:00 lr: 0.000796 loss: 3.6721 (3.5530) grad_norm: 1.1161 (1.1073) time: 0.4991 [2021-03-25 19:40:14 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 140/1251] eta: 0:09:52 lr: 0.000795 loss: 3.4429 (3.5392) grad_norm: 1.1034 (1.1032) time: 0.5021 [2021-03-25 19:40:19 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 150/1251] eta: 0:09:45 lr: 0.000795 loss: 3.2917 (3.5224) grad_norm: 1.0529 (1.1031) time: 0.5066 [2021-03-25 19:40:24 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 160/1251] eta: 0:09:37 lr: 0.000795 loss: 3.4982 (3.5361) grad_norm: 1.0678 (1.1032) time: 0.5050 [2021-03-25 19:40:29 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 170/1251] eta: 0:09:31 lr: 0.000795 loss: 3.8900 (3.5544) grad_norm: 1.0882 (1.1042) time: 0.5028 [2021-03-25 19:40:34 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 180/1251] eta: 0:09:25 lr: 0.000795 loss: 3.4186 (3.5348) grad_norm: 1.0902 (1.1080) time: 0.5110 [2021-03-25 19:40:39 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 190/1251] eta: 0:09:18 lr: 0.000795 loss: 3.2316 (3.5188) grad_norm: 1.1459 (1.1107) time: 0.5112 [2021-03-25 19:40:44 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 200/1251] eta: 0:09:11 lr: 0.000795 loss: 3.3734 (3.5188) grad_norm: 1.1208 (1.1100) time: 0.5024 [2021-03-25 19:40:49 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 210/1251] eta: 0:09:05 lr: 0.000795 loss: 3.5520 (3.5131) grad_norm: 1.0763 (1.1119) time: 0.5044 [2021-03-25 19:40:54 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 220/1251] eta: 0:08:59 lr: 0.000795 loss: 3.5173 (3.5137) grad_norm: 1.1462 (1.1120) time: 0.5061 [2021-03-25 19:40:59 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 230/1251] eta: 0:08:54 lr: 0.000795 loss: 3.5529 (3.5146) grad_norm: 1.1177 (1.1129) time: 0.5087 [2021-03-25 19:41:04 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 240/1251] eta: 0:08:48 lr: 0.000795 loss: 3.6181 (3.5176) grad_norm: 1.1177 (1.1126) time: 0.5131 [2021-03-25 19:41:09 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 250/1251] eta: 0:08:42 lr: 0.000795 loss: 3.4621 (3.5188) grad_norm: 1.0777 (1.1119) time: 0.5093 [2021-03-25 19:41:15 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 260/1251] eta: 0:08:37 lr: 0.000795 loss: 3.6698 (3.5206) grad_norm: 1.0322 (1.1093) time: 0.5108 [2021-03-25 19:41:20 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 270/1251] eta: 0:08:31 lr: 0.000795 loss: 3.6698 (3.5221) grad_norm: 1.0598 (1.1103) time: 0.5107 [2021-03-25 19:41:25 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 280/1251] eta: 0:08:25 lr: 0.000795 loss: 3.4444 (3.5170) grad_norm: 1.0598 (1.1086) time: 0.5092 [2021-03-25 19:41:30 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 290/1251] eta: 0:08:19 lr: 0.000795 loss: 3.7020 (3.5309) grad_norm: 1.0134 (1.1060) time: 0.5051 [2021-03-25 19:41:35 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 300/1251] eta: 0:08:13 lr: 0.000795 loss: 3.7930 (3.5292) grad_norm: 1.0526 (1.1077) time: 0.4972 [2021-03-25 19:41:40 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 310/1251] eta: 0:08:07 lr: 0.000795 loss: 3.8695 (3.5385) grad_norm: 1.0725 (1.1071) time: 0.4977 [2021-03-25 19:41:45 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 320/1251] eta: 0:08:02 lr: 0.000795 loss: 3.9877 (3.5445) grad_norm: 1.0714 (1.1073) time: 0.5064 [2021-03-25 19:41:50 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 330/1251] eta: 0:07:57 lr: 0.000795 loss: 3.6999 (3.5466) grad_norm: 1.0928 (1.1072) time: 0.5074 [2021-03-25 19:41:55 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 340/1251] eta: 0:07:51 lr: 0.000795 loss: 3.5229 (3.5409) grad_norm: 1.0748 (1.1060) time: 0.5004 [2021-03-25 19:42:00 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 350/1251] eta: 0:07:45 lr: 0.000795 loss: 3.5229 (3.5368) grad_norm: 1.0553 (1.1059) time: 0.5014 [2021-03-25 19:42:05 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 360/1251] eta: 0:07:40 lr: 0.000795 loss: 3.5847 (3.5356) grad_norm: 1.0553 (1.1058) time: 0.4993 [2021-03-25 19:42:10 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 370/1251] eta: 0:07:34 lr: 0.000795 loss: 3.5434 (3.5328) grad_norm: 1.0694 (1.1054) time: 0.5000 [2021-03-25 19:42:15 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 380/1251] eta: 0:07:29 lr: 0.000795 loss: 3.5937 (3.5356) grad_norm: 1.1181 (1.1061) time: 0.5065 [2021-03-25 19:42:20 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 390/1251] eta: 0:07:24 lr: 0.000795 loss: 3.5800 (3.5363) grad_norm: 1.1405 (1.1080) time: 0.5090 [2021-03-25 19:42:25 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 400/1251] eta: 0:07:18 lr: 0.000795 loss: 3.5625 (3.5357) grad_norm: 1.1224 (1.1097) time: 0.5058 [2021-03-25 19:42:30 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 410/1251] eta: 0:07:13 lr: 0.000795 loss: 3.8725 (3.5406) grad_norm: 1.1325 (1.1118) time: 0.5039 [2021-03-25 19:42:35 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 420/1251] eta: 0:07:07 lr: 0.000795 loss: 3.8553 (3.5404) grad_norm: 1.1206 (1.1122) time: 0.5040 [2021-03-25 19:42:40 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 430/1251] eta: 0:07:02 lr: 0.000795 loss: 3.5094 (3.5362) grad_norm: 1.0974 (1.1121) time: 0.5060 [2021-03-25 19:42:45 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 440/1251] eta: 0:06:57 lr: 0.000794 loss: 3.6159 (3.5419) grad_norm: 1.1024 (1.1118) time: 0.5063 [2021-03-25 19:42:50 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 450/1251] eta: 0:06:52 lr: 0.000794 loss: 3.7762 (3.5480) grad_norm: 1.1145 (1.1131) time: 0.5074 [2021-03-25 19:42:55 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 460/1251] eta: 0:06:46 lr: 0.000794 loss: 3.7393 (3.5502) grad_norm: 1.1256 (1.1144) time: 0.5076 [2021-03-25 19:43:01 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 470/1251] eta: 0:06:41 lr: 0.000794 loss: 3.5510 (3.5492) grad_norm: 1.1190 (1.1139) time: 0.5099 [2021-03-25 19:43:06 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 480/1251] eta: 0:06:36 lr: 0.000794 loss: 3.5688 (3.5516) grad_norm: 1.1326 (1.1152) time: 0.5095 [2021-03-25 19:43:11 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 490/1251] eta: 0:06:30 lr: 0.000794 loss: 3.6579 (3.5516) grad_norm: 1.1166 (1.1143) time: 0.5039 [2021-03-25 19:43:16 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 500/1251] eta: 0:06:25 lr: 0.000794 loss: 3.1815 (3.5441) grad_norm: 1.1094 (1.1149) time: 0.5061 [2021-03-25 19:43:21 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 510/1251] eta: 0:06:20 lr: 0.000794 loss: 3.3348 (3.5458) grad_norm: 1.1110 (1.1149) time: 0.5087 [2021-03-25 19:43:26 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 520/1251] eta: 0:06:15 lr: 0.000794 loss: 3.4338 (3.5462) grad_norm: 1.1217 (1.1169) time: 0.5123 [2021-03-25 19:43:31 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 530/1251] eta: 0:06:10 lr: 0.000794 loss: 3.7199 (3.5479) grad_norm: 1.0827 (1.1160) time: 0.5071 [2021-03-25 19:43:36 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 540/1251] eta: 0:06:04 lr: 0.000794 loss: 3.6383 (3.5457) grad_norm: 1.0469 (1.1151) time: 0.5037 [2021-03-25 19:43:41 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 550/1251] eta: 0:05:59 lr: 0.000794 loss: 3.4484 (3.5407) grad_norm: 1.0533 (1.1152) time: 0.5191 [2021-03-25 19:43:47 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 560/1251] eta: 0:05:54 lr: 0.000794 loss: 3.0955 (3.5347) grad_norm: 1.1144 (1.1156) time: 0.5193 [2021-03-25 19:43:52 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 570/1251] eta: 0:05:49 lr: 0.000794 loss: 3.1662 (3.5329) grad_norm: 1.0964 (1.1152) time: 0.5078 [2021-03-25 19:43:57 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 580/1251] eta: 0:05:44 lr: 0.000794 loss: 3.4375 (3.5336) grad_norm: 1.0964 (1.1154) time: 0.5071 [2021-03-25 19:44:02 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 590/1251] eta: 0:05:39 lr: 0.000794 loss: 3.6568 (3.5345) grad_norm: 1.1430 (1.1157) time: 0.5147 [2021-03-25 19:44:07 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 600/1251] eta: 0:05:34 lr: 0.000794 loss: 3.6568 (3.5367) grad_norm: 1.1106 (1.1151) time: 0.5132 [2021-03-25 19:44:12 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 610/1251] eta: 0:05:28 lr: 0.000794 loss: 3.5643 (3.5374) grad_norm: 1.1106 (1.1154) time: 0.5058 [2021-03-25 19:44:17 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 620/1251] eta: 0:05:23 lr: 0.000794 loss: 3.6573 (3.5423) grad_norm: 1.1304 (1.1158) time: 0.5048 [2021-03-25 19:44:22 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 630/1251] eta: 0:05:18 lr: 0.000794 loss: 3.6573 (3.5424) grad_norm: 1.1196 (1.1156) time: 0.5013 [2021-03-25 19:44:27 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 640/1251] eta: 0:05:13 lr: 0.000794 loss: 3.4283 (3.5400) grad_norm: 1.0873 (1.1156) time: 0.5070 [2021-03-25 19:44:32 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 650/1251] eta: 0:05:08 lr: 0.000794 loss: 3.6515 (3.5415) grad_norm: 1.0946 (1.1157) time: 0.5059 [2021-03-25 19:44:37 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 660/1251] eta: 0:05:02 lr: 0.000794 loss: 3.6990 (3.5420) grad_norm: 1.1385 (1.1175) time: 0.5003 [2021-03-25 19:44:42 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 670/1251] eta: 0:04:57 lr: 0.000794 loss: 3.7072 (3.5420) grad_norm: 1.1385 (1.1177) time: 0.5033 [2021-03-25 19:44:47 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 680/1251] eta: 0:04:52 lr: 0.000794 loss: 3.5460 (3.5411) grad_norm: 1.1023 (1.1169) time: 0.5059 [2021-03-25 19:44:52 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 690/1251] eta: 0:04:47 lr: 0.000794 loss: 3.5064 (3.5401) grad_norm: 1.0632 (1.1169) time: 0.5032 [2021-03-25 19:44:57 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 700/1251] eta: 0:04:42 lr: 0.000794 loss: 3.5064 (3.5387) grad_norm: 1.1148 (1.1173) time: 0.5038 [2021-03-25 19:45:03 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 710/1251] eta: 0:04:37 lr: 0.000794 loss: 3.6313 (3.5407) grad_norm: 1.1326 (1.1178) time: 0.5156 [2021-03-25 19:45:08 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 720/1251] eta: 0:04:31 lr: 0.000794 loss: 3.6234 (3.5391) grad_norm: 1.1019 (1.1178) time: 0.5160 [2021-03-25 19:45:13 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 730/1251] eta: 0:04:26 lr: 0.000794 loss: 3.5814 (3.5372) grad_norm: 1.0618 (1.1173) time: 0.5149 [2021-03-25 19:45:18 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 740/1251] eta: 0:04:21 lr: 0.000793 loss: 3.8620 (3.5391) grad_norm: 1.0954 (1.1175) time: 0.5310 [2021-03-25 19:45:23 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 750/1251] eta: 0:04:16 lr: 0.000793 loss: 3.8620 (3.5401) grad_norm: 1.1243 (1.1182) time: 0.5262 [2021-03-25 19:45:28 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 760/1251] eta: 0:04:11 lr: 0.000793 loss: 3.3132 (3.5360) grad_norm: 1.1006 (1.1177) time: 0.5052 [2021-03-25 19:45:33 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 770/1251] eta: 0:04:06 lr: 0.000793 loss: 3.3365 (3.5372) grad_norm: 1.0914 (1.1192) time: 0.4998 [2021-03-25 19:45:39 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 780/1251] eta: 0:04:01 lr: 0.000793 loss: 3.3307 (3.5351) grad_norm: 1.1315 (1.1202) time: 0.5056 [2021-03-25 19:45:44 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 790/1251] eta: 0:03:56 lr: 0.000793 loss: 3.2633 (3.5330) grad_norm: 1.1263 (1.1201) time: 0.5111 [2021-03-25 19:45:49 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 800/1251] eta: 0:03:50 lr: 0.000793 loss: 3.7162 (3.5348) grad_norm: 1.0782 (1.1203) time: 0.5073 [2021-03-25 19:45:54 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 810/1251] eta: 0:03:45 lr: 0.000793 loss: 3.6418 (3.5334) grad_norm: 1.0848 (1.1200) time: 0.5066 [2021-03-25 19:45:59 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 820/1251] eta: 0:03:40 lr: 0.000793 loss: 3.5243 (3.5338) grad_norm: 1.0848 (1.1194) time: 0.5023 [2021-03-25 19:46:04 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 830/1251] eta: 0:03:35 lr: 0.000793 loss: 3.5790 (3.5337) grad_norm: 1.0652 (1.1187) time: 0.5068 [2021-03-25 19:46:09 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 840/1251] eta: 0:03:30 lr: 0.000793 loss: 3.6273 (3.5355) grad_norm: 1.1050 (1.1191) time: 0.5148 [2021-03-25 19:46:14 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 850/1251] eta: 0:03:25 lr: 0.000793 loss: 3.5731 (3.5362) grad_norm: 1.1345 (1.1192) time: 0.5108 [2021-03-25 19:46:19 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 860/1251] eta: 0:03:20 lr: 0.000793 loss: 3.3682 (3.5325) grad_norm: 1.1239 (1.1197) time: 0.5077 [2021-03-25 19:46:24 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 870/1251] eta: 0:03:14 lr: 0.000793 loss: 3.2145 (3.5323) grad_norm: 1.1399 (1.1205) time: 0.5052 [2021-03-25 19:46:29 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 880/1251] eta: 0:03:09 lr: 0.000793 loss: 3.6065 (3.5337) grad_norm: 1.1761 (1.1208) time: 0.5062 [2021-03-25 19:46:34 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 890/1251] eta: 0:03:04 lr: 0.000793 loss: 3.6065 (3.5331) grad_norm: 1.0873 (1.1207) time: 0.5102 [2021-03-25 19:46:40 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 900/1251] eta: 0:02:59 lr: 0.000793 loss: 3.6065 (3.5337) grad_norm: 1.0834 (1.1210) time: 0.5122 [2021-03-25 19:46:45 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 910/1251] eta: 0:02:54 lr: 0.000793 loss: 3.5238 (3.5326) grad_norm: 1.0981 (1.1208) time: 0.5046 [2021-03-25 19:46:50 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 920/1251] eta: 0:02:49 lr: 0.000793 loss: 3.4858 (3.5310) grad_norm: 1.0404 (1.1200) time: 0.5046 [2021-03-25 19:46:55 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 930/1251] eta: 0:02:44 lr: 0.000793 loss: 3.6265 (3.5309) grad_norm: 1.0808 (1.1204) time: 0.5143 [2021-03-25 19:47:00 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 940/1251] eta: 0:02:39 lr: 0.000793 loss: 3.6976 (3.5323) grad_norm: 1.1241 (1.1203) time: 0.5143 [2021-03-25 19:47:05 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 950/1251] eta: 0:02:33 lr: 0.000793 loss: 3.6180 (3.5320) grad_norm: 1.0599 (1.1197) time: 0.5089 [2021-03-25 19:47:10 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 960/1251] eta: 0:02:28 lr: 0.000793 loss: 3.5007 (3.5295) grad_norm: 1.0800 (1.1194) time: 0.5093 [2021-03-25 19:47:15 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 970/1251] eta: 0:02:23 lr: 0.000793 loss: 3.6192 (3.5303) grad_norm: 1.1289 (1.1210) time: 0.5113 [2021-03-25 19:47:20 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 980/1251] eta: 0:02:18 lr: 0.000793 loss: 3.5534 (3.5287) grad_norm: 1.1316 (1.1205) time: 0.5080 [2021-03-25 19:47:26 swin_small_patch4_window7_224] INFO: Epoch: [90] [ 990/1251] eta: 0:02:13 lr: 0.000793 loss: 3.5534 (3.5297) grad_norm: 1.1099 (1.1202) time: 0.5127 [2021-03-25 19:47:31 swin_small_patch4_window7_224] INFO: Epoch: [90] [1000/1251] eta: 0:02:08 lr: 0.000793 loss: 3.6278 (3.5300) grad_norm: 1.1200 (1.1210) time: 0.5225 [2021-03-25 19:47:36 swin_small_patch4_window7_224] INFO: Epoch: [90] [1010/1251] eta: 0:02:03 lr: 0.000793 loss: 3.5047 (3.5291) grad_norm: 1.1539 (1.1214) time: 0.5165 [2021-03-25 19:47:41 swin_small_patch4_window7_224] INFO: Epoch: [90] [1020/1251] eta: 0:01:58 lr: 0.000793 loss: 3.5047 (3.5289) grad_norm: 1.0761 (1.1210) time: 0.5131 [2021-03-25 19:47:46 swin_small_patch4_window7_224] INFO: Epoch: [90] [1030/1251] eta: 0:01:53 lr: 0.000792 loss: 3.4926 (3.5265) grad_norm: 1.0569 (1.1205) time: 0.5130 [2021-03-25 19:47:51 swin_small_patch4_window7_224] INFO: Epoch: [90] [1040/1251] eta: 0:01:47 lr: 0.000792 loss: 3.6161 (3.5282) grad_norm: 1.0804 (1.1209) time: 0.5049 [2021-03-25 19:47:56 swin_small_patch4_window7_224] INFO: Epoch: [90] [1050/1251] eta: 0:01:42 lr: 0.000792 loss: 3.7481 (3.5295) grad_norm: 1.0804 (1.1206) time: 0.5002 [2021-03-25 19:48:01 swin_small_patch4_window7_224] INFO: Epoch: [90] [1060/1251] eta: 0:01:37 lr: 0.000792 loss: 3.7034 (3.5303) grad_norm: 1.0449 (1.1201) time: 0.5064 [2021-03-25 19:48:06 swin_small_patch4_window7_224] INFO: Epoch: [90] [1070/1251] eta: 0:01:32 lr: 0.000792 loss: 3.6867 (3.5314) grad_norm: 1.0689 (1.1201) time: 0.5114 [2021-03-25 19:48:11 swin_small_patch4_window7_224] INFO: Epoch: [90] [1080/1251] eta: 0:01:27 lr: 0.000792 loss: 3.5329 (3.5307) grad_norm: 1.0563 (1.1196) time: 0.5037 [2021-03-25 19:48:16 swin_small_patch4_window7_224] INFO: Epoch: [90] [1090/1251] eta: 0:01:22 lr: 0.000792 loss: 3.6977 (3.5325) grad_norm: 1.0602 (1.1199) time: 0.5043 [2021-03-25 19:48:22 swin_small_patch4_window7_224] INFO: Epoch: [90] [1100/1251] eta: 0:01:17 lr: 0.000792 loss: 3.7118 (3.5315) grad_norm: 1.1424 (1.1203) time: 0.5085 [2021-03-25 19:48:27 swin_small_patch4_window7_224] INFO: Epoch: [90] [1110/1251] eta: 0:01:12 lr: 0.000792 loss: 3.6263 (3.5319) grad_norm: 1.1943 (1.1213) time: 0.5091 [2021-03-25 19:48:32 swin_small_patch4_window7_224] INFO: Epoch: [90] [1120/1251] eta: 0:01:06 lr: 0.000792 loss: 3.6137 (3.5305) grad_norm: 1.2045 (1.1215) time: 0.5130 [2021-03-25 19:48:37 swin_small_patch4_window7_224] INFO: Epoch: [90] [1130/1251] eta: 0:01:01 lr: 0.000792 loss: 3.1998 (3.5251) grad_norm: 1.1306 (1.1212) time: 0.5082 [2021-03-25 19:48:42 swin_small_patch4_window7_224] INFO: Epoch: [90] [1140/1251] eta: 0:00:56 lr: 0.000792 loss: 3.3035 (3.5235) grad_norm: 1.0872 (1.1216) time: 0.5001 [2021-03-25 19:48:47 swin_small_patch4_window7_224] INFO: Epoch: [90] [1150/1251] eta: 0:00:51 lr: 0.000792 loss: 3.4628 (3.5249) grad_norm: 1.0958 (1.1220) time: 0.5013 [2021-03-25 19:48:52 swin_small_patch4_window7_224] INFO: Epoch: [90] [1160/1251] eta: 0:00:46 lr: 0.000792 loss: 3.5763 (3.5251) grad_norm: 1.1005 (1.1220) time: 0.5049 [2021-03-25 19:48:57 swin_small_patch4_window7_224] INFO: Epoch: [90] [1170/1251] eta: 0:00:41 lr: 0.000792 loss: 3.5683 (3.5260) grad_norm: 1.1224 (1.1220) time: 0.5039 [2021-03-25 19:49:02 swin_small_patch4_window7_224] INFO: Epoch: [90] [1180/1251] eta: 0:00:36 lr: 0.000792 loss: 3.6021 (3.5261) grad_norm: 1.1596 (1.1227) time: 0.5030 [2021-03-25 19:49:07 swin_small_patch4_window7_224] INFO: Epoch: [90] [1190/1251] eta: 0:00:31 lr: 0.000792 loss: 3.6021 (3.5257) grad_norm: 1.1399 (1.1224) time: 0.5044 [2021-03-25 19:49:12 swin_small_patch4_window7_224] INFO: Epoch: [90] [1200/1251] eta: 0:00:26 lr: 0.000792 loss: 3.7494 (3.5242) grad_norm: 1.0806 (1.1224) time: 0.5085 [2021-03-25 19:49:17 swin_small_patch4_window7_224] INFO: Epoch: [90] [1210/1251] eta: 0:00:20 lr: 0.000792 loss: 3.7855 (3.5264) grad_norm: 1.0989 (1.1225) time: 0.5079 [2021-03-25 19:49:22 swin_small_patch4_window7_224] INFO: Epoch: [90] [1220/1251] eta: 0:00:15 lr: 0.000792 loss: 3.7178 (3.5248) grad_norm: 1.0964 (1.1222) time: 0.5018 [2021-03-25 19:49:27 swin_small_patch4_window7_224] INFO: Epoch: [90] [1230/1251] eta: 0:00:10 lr: 0.000792 loss: 3.4706 (3.5226) grad_norm: 1.0787 (1.1221) time: 0.5035 [2021-03-25 19:49:32 swin_small_patch4_window7_224] INFO: Epoch: [90] [1240/1251] eta: 0:00:05 lr: 0.000792 loss: 3.5004 (3.5236) grad_norm: 1.0787 (1.1220) time: 0.5121 [2021-03-25 19:49:37 swin_small_patch4_window7_224] INFO: Epoch: [90] [1250/1251] eta: 0:00:00 lr: 0.000792 loss: 3.9575 (3.5256) grad_norm: 1.0949 (1.1223) time: 0.5091 [2021-03-25 19:50:26 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.9998 (0.9998) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.7500) [2021-03-25 19:50:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.0808 (1.0933) acc1: 75.0000 (73.7216) acc5: 92.1875 (92.7557) [2021-03-25 19:50:28 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.0951 (1.0994) acc1: 73.4375 (73.5119) acc5: 92.1875 (92.0387) [2021-03-25 19:50:29 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9896 (1.0524) acc1: 73.4375 (74.5464) acc5: 93.7500 (92.9435) [2021-03-25 19:50:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9702 (1.0331) acc1: 73.4375 (74.8095) acc5: 93.7500 (93.2165) [2021-03-25 19:50:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9823 (1.0406) acc1: 73.4375 (74.7200) acc5: 93.7500 (93.2160) [2021-03-25 19:50:37 swin_small_patch4_window7_224] INFO: * Acc@1 75.906 Acc@5 93.288 loss 1.018 [2021-03-25 19:50:37 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.9% [2021-03-25 19:50:37 swin_small_patch4_window7_224] INFO: Max accuracy: 75.91% [2021-03-25 19:50:41 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 0/1251] eta: 1:26:31 lr: 0.000792 loss: 2.9903 (2.9903) grad_norm: 0.9504 (0.9504) time: 4.1496 [2021-03-25 19:50:46 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 10/1251] eta: 0:17:27 lr: 0.000792 loss: 3.3625 (3.2947) grad_norm: 1.0822 (1.0737) time: 0.8440 [2021-03-25 19:50:51 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 20/1251] eta: 0:14:05 lr: 0.000792 loss: 3.4183 (3.3943) grad_norm: 1.1021 (1.1187) time: 0.5136 [2021-03-25 19:50:56 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 30/1251] eta: 0:12:50 lr: 0.000792 loss: 3.6161 (3.4767) grad_norm: 1.1492 (1.1450) time: 0.5139 [2021-03-25 19:51:01 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 40/1251] eta: 0:12:07 lr: 0.000792 loss: 3.5388 (3.4325) grad_norm: 1.1083 (1.1249) time: 0.5105 [2021-03-25 19:51:06 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 50/1251] eta: 0:11:39 lr: 0.000792 loss: 3.5720 (3.4697) grad_norm: 1.0706 (1.1254) time: 0.5066 [2021-03-25 19:51:11 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 60/1251] eta: 0:11:18 lr: 0.000792 loss: 3.7822 (3.5321) grad_norm: 1.0845 (1.1243) time: 0.5047 [2021-03-25 19:51:16 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 70/1251] eta: 0:11:02 lr: 0.000792 loss: 3.7390 (3.5280) grad_norm: 1.0862 (1.1230) time: 0.5081 [2021-03-25 19:51:21 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 80/1251] eta: 0:10:48 lr: 0.000791 loss: 3.7344 (3.5511) grad_norm: 1.1195 (1.1267) time: 0.5076 [2021-03-25 19:51:27 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 90/1251] eta: 0:10:38 lr: 0.000791 loss: 3.5191 (3.5111) grad_norm: 1.1384 (1.1324) time: 0.5078 [2021-03-25 19:51:32 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 100/1251] eta: 0:10:27 lr: 0.000791 loss: 3.3789 (3.5072) grad_norm: 1.1322 (1.1308) time: 0.5088 [2021-03-25 19:51:37 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 110/1251] eta: 0:10:18 lr: 0.000791 loss: 3.6284 (3.5091) grad_norm: 1.1522 (1.1403) time: 0.5101 [2021-03-25 19:51:42 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 120/1251] eta: 0:10:10 lr: 0.000791 loss: 3.4564 (3.5099) grad_norm: 1.1119 (1.1343) time: 0.5119 [2021-03-25 19:51:47 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 130/1251] eta: 0:10:03 lr: 0.000791 loss: 3.4250 (3.5113) grad_norm: 1.0737 (1.1307) time: 0.5150 [2021-03-25 19:51:52 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 140/1251] eta: 0:09:55 lr: 0.000791 loss: 3.6265 (3.5044) grad_norm: 1.0991 (1.1341) time: 0.5162 [2021-03-25 19:51:57 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 150/1251] eta: 0:09:47 lr: 0.000791 loss: 3.3398 (3.4907) grad_norm: 1.1386 (1.1371) time: 0.5049 [2021-03-25 19:52:02 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 160/1251] eta: 0:09:39 lr: 0.000791 loss: 3.3091 (3.4836) grad_norm: 1.0971 (1.1344) time: 0.4979 [2021-03-25 19:52:07 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 170/1251] eta: 0:09:33 lr: 0.000791 loss: 3.4682 (3.4953) grad_norm: 1.0971 (1.1342) time: 0.5040 [2021-03-25 19:52:12 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 180/1251] eta: 0:09:27 lr: 0.000791 loss: 3.6905 (3.5089) grad_norm: 1.1435 (1.1335) time: 0.5150 [2021-03-25 19:52:18 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 190/1251] eta: 0:09:21 lr: 0.000791 loss: 3.5038 (3.4906) grad_norm: 1.1377 (1.1357) time: 0.5178 [2021-03-25 19:52:23 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 200/1251] eta: 0:09:14 lr: 0.000791 loss: 3.5038 (3.5068) grad_norm: 1.1377 (1.1406) time: 0.5097 [2021-03-25 19:52:28 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 210/1251] eta: 0:09:08 lr: 0.000791 loss: 3.9262 (3.5140) grad_norm: 1.1093 (1.1375) time: 0.5056 [2021-03-25 19:52:33 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 220/1251] eta: 0:09:02 lr: 0.000791 loss: 3.3930 (3.4979) grad_norm: 1.0588 (1.1380) time: 0.5117 [2021-03-25 19:52:38 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 230/1251] eta: 0:08:56 lr: 0.000791 loss: 3.0541 (3.4901) grad_norm: 1.0867 (1.1363) time: 0.5077 [2021-03-25 19:52:43 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 240/1251] eta: 0:08:50 lr: 0.000791 loss: 3.7638 (3.5021) grad_norm: 1.0784 (1.1347) time: 0.5041 [2021-03-25 19:52:48 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 250/1251] eta: 0:08:44 lr: 0.000791 loss: 3.8571 (3.5010) grad_norm: 1.0784 (1.1342) time: 0.5076 [2021-03-25 19:52:53 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 260/1251] eta: 0:08:38 lr: 0.000791 loss: 3.5005 (3.5022) grad_norm: 1.0656 (1.1343) time: 0.5066 [2021-03-25 19:52:58 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 270/1251] eta: 0:08:32 lr: 0.000791 loss: 3.6959 (3.5083) grad_norm: 1.0598 (1.1316) time: 0.5036 [2021-03-25 19:53:03 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 280/1251] eta: 0:08:26 lr: 0.000791 loss: 3.7682 (3.5093) grad_norm: 1.0729 (1.1315) time: 0.5038 [2021-03-25 19:53:08 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 290/1251] eta: 0:08:20 lr: 0.000791 loss: 3.6589 (3.5086) grad_norm: 1.0786 (1.1331) time: 0.5043 [2021-03-25 19:53:13 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 300/1251] eta: 0:08:14 lr: 0.000791 loss: 3.6645 (3.5069) grad_norm: 1.1195 (1.1330) time: 0.4968 [2021-03-25 19:53:18 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 310/1251] eta: 0:08:09 lr: 0.000791 loss: 3.7614 (3.5186) grad_norm: 1.0706 (1.1302) time: 0.4996 [2021-03-25 19:53:23 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 320/1251] eta: 0:08:03 lr: 0.000791 loss: 3.7379 (3.5241) grad_norm: 1.0109 (1.1269) time: 0.5082 [2021-03-25 19:53:28 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 330/1251] eta: 0:07:57 lr: 0.000791 loss: 3.6649 (3.5282) grad_norm: 1.0707 (1.1286) time: 0.5064 [2021-03-25 19:53:33 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 340/1251] eta: 0:07:52 lr: 0.000791 loss: 3.4301 (3.5260) grad_norm: 1.1320 (1.1277) time: 0.5051 [2021-03-25 19:53:38 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 350/1251] eta: 0:07:46 lr: 0.000791 loss: 3.4242 (3.5287) grad_norm: 1.0994 (1.1277) time: 0.5002 [2021-03-25 19:53:43 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 360/1251] eta: 0:07:41 lr: 0.000791 loss: 3.4242 (3.5264) grad_norm: 1.0970 (1.1275) time: 0.5025 [2021-03-25 19:53:48 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 370/1251] eta: 0:07:35 lr: 0.000790 loss: 3.4248 (3.5232) grad_norm: 1.0716 (1.1257) time: 0.5065 [2021-03-25 19:53:53 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 380/1251] eta: 0:07:30 lr: 0.000790 loss: 3.6943 (3.5310) grad_norm: 1.0906 (1.1278) time: 0.5004 [2021-03-25 19:53:58 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 390/1251] eta: 0:07:24 lr: 0.000790 loss: 3.7962 (3.5307) grad_norm: 1.1311 (1.1285) time: 0.4999 [2021-03-25 19:54:03 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 400/1251] eta: 0:07:18 lr: 0.000790 loss: 3.7962 (3.5341) grad_norm: 1.1030 (1.1267) time: 0.5001 [2021-03-25 19:54:09 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 410/1251] eta: 0:07:13 lr: 0.000790 loss: 3.5939 (3.5316) grad_norm: 1.0324 (1.1253) time: 0.5036 [2021-03-25 19:54:14 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 420/1251] eta: 0:07:08 lr: 0.000790 loss: 3.4842 (3.5294) grad_norm: 1.0387 (1.1233) time: 0.5072 [2021-03-25 19:54:19 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 430/1251] eta: 0:07:03 lr: 0.000790 loss: 3.4842 (3.5286) grad_norm: 1.0569 (1.1233) time: 0.5064 [2021-03-25 19:54:24 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 440/1251] eta: 0:06:57 lr: 0.000790 loss: 3.5827 (3.5294) grad_norm: 1.1010 (1.1226) time: 0.5123 [2021-03-25 19:54:29 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 450/1251] eta: 0:06:52 lr: 0.000790 loss: 3.4363 (3.5240) grad_norm: 1.0856 (1.1228) time: 0.5072 [2021-03-25 19:54:34 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 460/1251] eta: 0:06:47 lr: 0.000790 loss: 3.4704 (3.5286) grad_norm: 1.1169 (1.1226) time: 0.4985 [2021-03-25 19:54:39 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 470/1251] eta: 0:06:41 lr: 0.000790 loss: 3.8825 (3.5290) grad_norm: 1.1498 (1.1225) time: 0.5023 [2021-03-25 19:54:44 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 480/1251] eta: 0:06:36 lr: 0.000790 loss: 3.6797 (3.5309) grad_norm: 1.1805 (1.1233) time: 0.5085 [2021-03-25 19:54:49 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 490/1251] eta: 0:06:31 lr: 0.000790 loss: 3.6797 (3.5301) grad_norm: 1.1192 (1.1227) time: 0.5120 [2021-03-25 19:54:54 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 500/1251] eta: 0:06:26 lr: 0.000790 loss: 3.5948 (3.5349) grad_norm: 1.1192 (1.1245) time: 0.5123 [2021-03-25 19:54:59 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 510/1251] eta: 0:06:20 lr: 0.000790 loss: 3.5948 (3.5356) grad_norm: 1.1449 (1.1253) time: 0.5072 [2021-03-25 19:55:04 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 520/1251] eta: 0:06:15 lr: 0.000790 loss: 3.5885 (3.5378) grad_norm: 1.2086 (1.1267) time: 0.5065 [2021-03-25 19:55:09 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 530/1251] eta: 0:06:10 lr: 0.000790 loss: 3.5528 (3.5335) grad_norm: 1.1907 (1.1274) time: 0.5036 [2021-03-25 19:55:14 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 540/1251] eta: 0:06:05 lr: 0.000790 loss: 3.5503 (3.5365) grad_norm: 1.1264 (1.1289) time: 0.5017 [2021-03-25 19:55:20 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 550/1251] eta: 0:06:00 lr: 0.000790 loss: 3.8212 (3.5382) grad_norm: 1.1036 (1.1298) time: 0.5134 [2021-03-25 19:55:25 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 560/1251] eta: 0:05:54 lr: 0.000790 loss: 3.4712 (3.5362) grad_norm: 1.0994 (1.1301) time: 0.5097 [2021-03-25 19:55:30 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 570/1251] eta: 0:05:49 lr: 0.000790 loss: 3.2505 (3.5334) grad_norm: 1.1070 (1.1306) time: 0.5008 [2021-03-25 19:55:35 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 580/1251] eta: 0:05:44 lr: 0.000790 loss: 3.6607 (3.5338) grad_norm: 1.0975 (1.1297) time: 0.5064 [2021-03-25 19:55:40 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 590/1251] eta: 0:05:39 lr: 0.000790 loss: 3.7417 (3.5369) grad_norm: 1.0975 (1.1299) time: 0.5073 [2021-03-25 19:55:45 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 600/1251] eta: 0:05:33 lr: 0.000790 loss: 3.6070 (3.5394) grad_norm: 1.0794 (1.1293) time: 0.5013 [2021-03-25 19:55:50 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 610/1251] eta: 0:05:28 lr: 0.000790 loss: 3.7219 (3.5424) grad_norm: 1.0794 (1.1306) time: 0.5035 [2021-03-25 19:55:55 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 620/1251] eta: 0:05:23 lr: 0.000790 loss: 3.6928 (3.5418) grad_norm: 1.0812 (1.1304) time: 0.5102 [2021-03-25 19:56:00 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 630/1251] eta: 0:05:18 lr: 0.000790 loss: 3.6191 (3.5414) grad_norm: 1.0812 (1.1304) time: 0.5084 [2021-03-25 19:56:05 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 640/1251] eta: 0:05:13 lr: 0.000790 loss: 3.6519 (3.5457) grad_norm: 1.0688 (1.1294) time: 0.5070 [2021-03-25 19:56:10 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 650/1251] eta: 0:05:07 lr: 0.000790 loss: 3.7508 (3.5467) grad_norm: 1.1005 (1.1296) time: 0.5039 [2021-03-25 19:56:15 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 660/1251] eta: 0:05:02 lr: 0.000790 loss: 3.6619 (3.5461) grad_norm: 1.0767 (1.1282) time: 0.5072 [2021-03-25 19:56:20 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 670/1251] eta: 0:04:57 lr: 0.000789 loss: 3.5759 (3.5482) grad_norm: 1.0704 (1.1282) time: 0.5132 [2021-03-25 19:56:25 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 680/1251] eta: 0:04:52 lr: 0.000789 loss: 3.5759 (3.5469) grad_norm: 1.1026 (1.1286) time: 0.5079 [2021-03-25 19:56:30 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 690/1251] eta: 0:04:47 lr: 0.000789 loss: 3.6891 (3.5497) grad_norm: 1.1159 (1.1284) time: 0.5037 [2021-03-25 19:56:36 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 700/1251] eta: 0:04:42 lr: 0.000789 loss: 3.7391 (3.5532) grad_norm: 1.1310 (1.1289) time: 0.5052 [2021-03-25 19:56:41 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 710/1251] eta: 0:04:36 lr: 0.000789 loss: 3.9367 (3.5542) grad_norm: 1.1475 (1.1295) time: 0.5107 [2021-03-25 19:56:46 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 720/1251] eta: 0:04:31 lr: 0.000789 loss: 3.8104 (3.5536) grad_norm: 1.0870 (1.1287) time: 0.5143 [2021-03-25 19:56:51 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 730/1251] eta: 0:04:26 lr: 0.000789 loss: 3.7087 (3.5517) grad_norm: 1.0737 (1.1290) time: 0.5120 [2021-03-25 19:56:56 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 740/1251] eta: 0:04:21 lr: 0.000789 loss: 3.7384 (3.5532) grad_norm: 1.0635 (1.1289) time: 0.5196 [2021-03-25 19:57:01 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 750/1251] eta: 0:04:16 lr: 0.000789 loss: 3.5922 (3.5507) grad_norm: 1.0635 (1.1292) time: 0.5156 [2021-03-25 19:57:06 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 760/1251] eta: 0:04:11 lr: 0.000789 loss: 3.6239 (3.5526) grad_norm: 1.1490 (1.1304) time: 0.5022 [2021-03-25 19:57:11 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 770/1251] eta: 0:04:06 lr: 0.000789 loss: 3.8098 (3.5561) grad_norm: 1.1049 (1.1294) time: 0.5104 [2021-03-25 19:57:16 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 780/1251] eta: 0:04:01 lr: 0.000789 loss: 3.8461 (3.5583) grad_norm: 1.0494 (1.1292) time: 0.5084 [2021-03-25 19:57:22 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 790/1251] eta: 0:03:55 lr: 0.000789 loss: 3.6054 (3.5546) grad_norm: 1.0906 (1.1285) time: 0.5058 [2021-03-25 19:57:27 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 800/1251] eta: 0:03:50 lr: 0.000789 loss: 3.6874 (3.5564) grad_norm: 1.0896 (1.1285) time: 0.5049 [2021-03-25 19:57:32 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 810/1251] eta: 0:03:45 lr: 0.000789 loss: 3.7526 (3.5568) grad_norm: 1.1114 (1.1290) time: 0.5103 [2021-03-25 19:57:37 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 820/1251] eta: 0:03:40 lr: 0.000789 loss: 3.4824 (3.5554) grad_norm: 1.1184 (1.1288) time: 0.5139 [2021-03-25 19:57:42 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 830/1251] eta: 0:03:35 lr: 0.000789 loss: 3.5053 (3.5576) grad_norm: 1.0614 (1.1283) time: 0.5080 [2021-03-25 19:57:47 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 840/1251] eta: 0:03:30 lr: 0.000789 loss: 3.7889 (3.5573) grad_norm: 1.0768 (1.1284) time: 0.5069 [2021-03-25 19:57:52 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 850/1251] eta: 0:03:25 lr: 0.000789 loss: 3.7517 (3.5598) grad_norm: 1.0890 (1.1287) time: 0.5045 [2021-03-25 19:57:57 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 860/1251] eta: 0:03:19 lr: 0.000789 loss: 3.6990 (3.5593) grad_norm: 1.0784 (1.1283) time: 0.5056 [2021-03-25 19:58:02 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 870/1251] eta: 0:03:14 lr: 0.000789 loss: 3.4749 (3.5579) grad_norm: 1.0859 (1.1288) time: 0.5079 [2021-03-25 19:58:07 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 880/1251] eta: 0:03:09 lr: 0.000789 loss: 3.4749 (3.5568) grad_norm: 1.1644 (1.1293) time: 0.5151 [2021-03-25 19:58:12 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 890/1251] eta: 0:03:04 lr: 0.000789 loss: 3.5367 (3.5590) grad_norm: 1.0818 (1.1285) time: 0.5092 [2021-03-25 19:58:17 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 900/1251] eta: 0:02:59 lr: 0.000789 loss: 3.6779 (3.5592) grad_norm: 1.0675 (1.1288) time: 0.5025 [2021-03-25 19:58:23 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 910/1251] eta: 0:02:54 lr: 0.000789 loss: 3.6590 (3.5585) grad_norm: 1.0677 (1.1281) time: 0.5139 [2021-03-25 19:58:28 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 920/1251] eta: 0:02:49 lr: 0.000789 loss: 3.5838 (3.5586) grad_norm: 1.0379 (1.1283) time: 0.5131 [2021-03-25 19:58:33 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 930/1251] eta: 0:02:44 lr: 0.000789 loss: 3.5593 (3.5576) grad_norm: 1.0808 (1.1286) time: 0.5035 [2021-03-25 19:58:38 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 940/1251] eta: 0:02:39 lr: 0.000789 loss: 3.5018 (3.5556) grad_norm: 1.1068 (1.1284) time: 0.5056 [2021-03-25 19:58:43 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 950/1251] eta: 0:02:33 lr: 0.000789 loss: 3.6217 (3.5566) grad_norm: 1.1068 (1.1285) time: 0.5085 [2021-03-25 19:58:48 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 960/1251] eta: 0:02:28 lr: 0.000788 loss: 3.7326 (3.5583) grad_norm: 1.1127 (1.1284) time: 0.5119 [2021-03-25 19:58:53 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 970/1251] eta: 0:02:23 lr: 0.000788 loss: 3.8104 (3.5611) grad_norm: 1.1425 (1.1284) time: 0.5130 [2021-03-25 19:58:58 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 980/1251] eta: 0:02:18 lr: 0.000788 loss: 3.7958 (3.5599) grad_norm: 1.0978 (1.1278) time: 0.5061 [2021-03-25 19:59:03 swin_small_patch4_window7_224] INFO: Epoch: [91] [ 990/1251] eta: 0:02:13 lr: 0.000788 loss: 3.6834 (3.5617) grad_norm: 1.0936 (1.1285) time: 0.5056 [2021-03-25 19:59:08 swin_small_patch4_window7_224] INFO: Epoch: [91] [1000/1251] eta: 0:02:08 lr: 0.000788 loss: 3.6389 (3.5606) grad_norm: 1.1730 (1.1286) time: 0.5033 [2021-03-25 19:59:13 swin_small_patch4_window7_224] INFO: Epoch: [91] [1010/1251] eta: 0:02:03 lr: 0.000788 loss: 3.6389 (3.5612) grad_norm: 1.0386 (1.1278) time: 0.5024 [2021-03-25 19:59:18 swin_small_patch4_window7_224] INFO: Epoch: [91] [1020/1251] eta: 0:01:58 lr: 0.000788 loss: 3.6106 (3.5600) grad_norm: 1.0331 (1.1271) time: 0.5064 [2021-03-25 19:59:23 swin_small_patch4_window7_224] INFO: Epoch: [91] [1030/1251] eta: 0:01:52 lr: 0.000788 loss: 3.6106 (3.5606) grad_norm: 1.0407 (1.1268) time: 0.5052 [2021-03-25 19:59:29 swin_small_patch4_window7_224] INFO: Epoch: [91] [1040/1251] eta: 0:01:47 lr: 0.000788 loss: 3.3722 (3.5577) grad_norm: 1.0708 (1.1262) time: 0.5087 [2021-03-25 19:59:34 swin_small_patch4_window7_224] INFO: Epoch: [91] [1050/1251] eta: 0:01:42 lr: 0.000788 loss: 3.3401 (3.5576) grad_norm: 1.0791 (1.1266) time: 0.5134 [2021-03-25 19:59:39 swin_small_patch4_window7_224] INFO: Epoch: [91] [1060/1251] eta: 0:01:37 lr: 0.000788 loss: 3.7429 (3.5586) grad_norm: 1.1557 (1.1265) time: 0.5081 [2021-03-25 19:59:44 swin_small_patch4_window7_224] INFO: Epoch: [91] [1070/1251] eta: 0:01:32 lr: 0.000788 loss: 3.6594 (3.5608) grad_norm: 1.0772 (1.1262) time: 0.5098 [2021-03-25 19:59:49 swin_small_patch4_window7_224] INFO: Epoch: [91] [1080/1251] eta: 0:01:27 lr: 0.000788 loss: 3.4981 (3.5588) grad_norm: 1.1226 (1.1265) time: 0.5120 [2021-03-25 19:59:54 swin_small_patch4_window7_224] INFO: Epoch: [91] [1090/1251] eta: 0:01:22 lr: 0.000788 loss: 3.3932 (3.5573) grad_norm: 1.1226 (1.1263) time: 0.5038 [2021-03-25 19:59:59 swin_small_patch4_window7_224] INFO: Epoch: [91] [1100/1251] eta: 0:01:17 lr: 0.000788 loss: 3.6112 (3.5577) grad_norm: 1.0742 (1.1266) time: 0.5000 [2021-03-25 20:00:04 swin_small_patch4_window7_224] INFO: Epoch: [91] [1110/1251] eta: 0:01:11 lr: 0.000788 loss: 3.7275 (3.5584) grad_norm: 1.1024 (inf) time: 0.4970 [2021-03-25 20:00:09 swin_small_patch4_window7_224] INFO: Epoch: [91] [1120/1251] eta: 0:01:06 lr: 0.000788 loss: 3.6280 (3.5581) grad_norm: 1.1138 (inf) time: 0.4992 [2021-03-25 20:00:14 swin_small_patch4_window7_224] INFO: Epoch: [91] [1130/1251] eta: 0:01:01 lr: 0.000788 loss: 3.4537 (3.5582) grad_norm: 1.1203 (inf) time: 0.5024 [2021-03-25 20:00:19 swin_small_patch4_window7_224] INFO: Epoch: [91] [1140/1251] eta: 0:00:56 lr: 0.000788 loss: 3.7290 (3.5593) grad_norm: 1.0626 (inf) time: 0.5048 [2021-03-25 20:00:24 swin_small_patch4_window7_224] INFO: Epoch: [91] [1150/1251] eta: 0:00:51 lr: 0.000788 loss: 3.7012 (3.5582) grad_norm: 1.0592 (inf) time: 0.5065 [2021-03-25 20:00:29 swin_small_patch4_window7_224] INFO: Epoch: [91] [1160/1251] eta: 0:00:46 lr: 0.000788 loss: 3.2902 (3.5573) grad_norm: 1.0783 (inf) time: 0.5027 [2021-03-25 20:00:34 swin_small_patch4_window7_224] INFO: Epoch: [91] [1170/1251] eta: 0:00:41 lr: 0.000788 loss: 3.6369 (3.5592) grad_norm: 1.1377 (inf) time: 0.4996 [2021-03-25 20:00:39 swin_small_patch4_window7_224] INFO: Epoch: [91] [1180/1251] eta: 0:00:36 lr: 0.000788 loss: 3.7741 (3.5576) grad_norm: 1.1315 (inf) time: 0.5032 [2021-03-25 20:00:44 swin_small_patch4_window7_224] INFO: Epoch: [91] [1190/1251] eta: 0:00:31 lr: 0.000788 loss: 3.6143 (3.5572) grad_norm: 1.1045 (inf) time: 0.5046 [2021-03-25 20:00:49 swin_small_patch4_window7_224] INFO: Epoch: [91] [1200/1251] eta: 0:00:26 lr: 0.000788 loss: 3.2464 (3.5541) grad_norm: 1.1132 (inf) time: 0.4980 [2021-03-25 20:00:54 swin_small_patch4_window7_224] INFO: Epoch: [91] [1210/1251] eta: 0:00:20 lr: 0.000788 loss: 3.3039 (3.5543) grad_norm: 1.1466 (inf) time: 0.5012 [2021-03-25 20:00:59 swin_small_patch4_window7_224] INFO: Epoch: [91] [1220/1251] eta: 0:00:15 lr: 0.000788 loss: 3.4826 (3.5542) grad_norm: 1.1423 (inf) time: 0.5023 [2021-03-25 20:01:04 swin_small_patch4_window7_224] INFO: Epoch: [91] [1230/1251] eta: 0:00:10 lr: 0.000788 loss: 3.6385 (3.5553) grad_norm: 1.1289 (inf) time: 0.4997 [2021-03-25 20:01:09 swin_small_patch4_window7_224] INFO: Epoch: [91] [1240/1251] eta: 0:00:05 lr: 0.000788 loss: 3.6131 (3.5529) grad_norm: 1.1862 (inf) time: 0.5041 [2021-03-25 20:01:14 swin_small_patch4_window7_224] INFO: Epoch: [91] [1250/1251] eta: 0:00:00 lr: 0.000788 loss: 3.2525 (3.5521) grad_norm: 1.2004 (inf) time: 0.5024 [2021-03-25 20:01:20 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:16 loss: 0.9201 (0.9201) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-25 20:01:23 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.9732 (0.9982) acc1: 78.1250 (75.9943) acc5: 92.1875 (93.4659) [2021-03-25 20:01:25 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9780 (1.0201) acc1: 76.5625 (75.6696) acc5: 92.1875 (93.6012) [2021-03-25 20:01:28 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0513 (1.0312) acc1: 76.5625 (75.8569) acc5: 93.7500 (93.2964) [2021-03-25 20:01:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0030 (1.0456) acc1: 75.0000 (75.1524) acc5: 93.7500 (93.1402) [2021-03-25 20:01:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9953 (1.0290) acc1: 76.5625 (75.5840) acc5: 94.3396 (93.5360) [2021-03-25 20:01:37 swin_small_patch4_window7_224] INFO: * Acc@1 75.830 Acc@5 93.268 loss 1.015 [2021-03-25 20:01:37 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-25 20:01:37 swin_small_patch4_window7_224] INFO: Max accuracy: 75.91% [2021-03-25 20:01:41 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 0/1251] eta: 1:29:03 lr: 0.000788 loss: 3.6638 (3.6638) grad_norm: 1.1537 (1.1537) time: 4.2715 [2021-03-25 20:01:46 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 10/1251] eta: 0:17:43 lr: 0.000787 loss: 3.4787 (3.3426) grad_norm: 1.1173 (1.1337) time: 0.8568 [2021-03-25 20:01:51 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 20/1251] eta: 0:14:04 lr: 0.000787 loss: 3.4787 (3.4245) grad_norm: 1.0973 (1.1317) time: 0.5068 [2021-03-25 20:01:56 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 30/1251] eta: 0:12:49 lr: 0.000787 loss: 3.5615 (3.3734) grad_norm: 1.1633 (1.1419) time: 0.5053 [2021-03-25 20:02:01 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 40/1251] eta: 0:12:05 lr: 0.000787 loss: 3.4788 (3.4262) grad_norm: 1.1664 (1.1481) time: 0.5073 [2021-03-25 20:02:06 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 50/1251] eta: 0:11:37 lr: 0.000787 loss: 3.4788 (3.4382) grad_norm: 1.0651 (1.1244) time: 0.5051 [2021-03-25 20:02:11 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 60/1251] eta: 0:11:18 lr: 0.000787 loss: 3.4510 (3.4079) grad_norm: 1.0547 (1.1396) time: 0.5095 [2021-03-25 20:02:17 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 70/1251] eta: 0:11:03 lr: 0.000787 loss: 3.4510 (3.4258) grad_norm: 1.1301 (1.1395) time: 0.5126 [2021-03-25 20:02:22 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 80/1251] eta: 0:10:49 lr: 0.000787 loss: 3.4686 (3.4351) grad_norm: 1.0853 (1.1368) time: 0.5107 [2021-03-25 20:02:27 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 90/1251] eta: 0:10:38 lr: 0.000787 loss: 3.5888 (3.4271) grad_norm: 1.0965 (1.1354) time: 0.5097 [2021-03-25 20:02:32 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 100/1251] eta: 0:10:28 lr: 0.000787 loss: 3.4536 (3.4208) grad_norm: 1.0965 (1.1320) time: 0.5109 [2021-03-25 20:02:37 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 110/1251] eta: 0:10:19 lr: 0.000787 loss: 3.5112 (3.4406) grad_norm: 1.0554 (1.1250) time: 0.5102 [2021-03-25 20:02:42 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 120/1251] eta: 0:10:10 lr: 0.000787 loss: 3.7805 (3.4704) grad_norm: 1.0438 (1.1230) time: 0.5072 [2021-03-25 20:02:47 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 130/1251] eta: 0:10:01 lr: 0.000787 loss: 3.8570 (3.4908) grad_norm: 1.1919 (1.1303) time: 0.5022 [2021-03-25 20:02:52 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 140/1251] eta: 0:09:54 lr: 0.000787 loss: 3.6418 (3.5068) grad_norm: 1.1649 (1.1269) time: 0.5050 [2021-03-25 20:02:57 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 150/1251] eta: 0:09:46 lr: 0.000787 loss: 3.5352 (3.4947) grad_norm: 1.0659 (1.1217) time: 0.5038 [2021-03-25 20:03:02 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 160/1251] eta: 0:09:38 lr: 0.000787 loss: 3.6757 (3.5145) grad_norm: 1.0702 (1.1246) time: 0.4989 [2021-03-25 20:03:07 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 170/1251] eta: 0:09:31 lr: 0.000787 loss: 3.8382 (3.5255) grad_norm: 1.1595 (1.1269) time: 0.5026 [2021-03-25 20:03:12 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 180/1251] eta: 0:09:24 lr: 0.000787 loss: 3.7979 (3.5305) grad_norm: 1.1120 (1.1265) time: 0.4997 [2021-03-25 20:03:17 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 190/1251] eta: 0:09:17 lr: 0.000787 loss: 3.4571 (3.5279) grad_norm: 1.0684 (1.1230) time: 0.4971 [2021-03-25 20:03:22 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 200/1251] eta: 0:09:12 lr: 0.000787 loss: 3.3834 (3.5113) grad_norm: 1.0684 (1.1231) time: 0.5103 [2021-03-25 20:03:27 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 210/1251] eta: 0:09:05 lr: 0.000787 loss: 3.4887 (3.5133) grad_norm: 1.1000 (1.1270) time: 0.5079 [2021-03-25 20:03:32 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 220/1251] eta: 0:08:59 lr: 0.000787 loss: 3.5574 (3.5095) grad_norm: 1.1000 (1.1255) time: 0.4985 [2021-03-25 20:03:37 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 230/1251] eta: 0:08:52 lr: 0.000787 loss: 3.6787 (3.5167) grad_norm: 1.0830 (1.1233) time: 0.4993 [2021-03-25 20:03:42 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 240/1251] eta: 0:08:47 lr: 0.000787 loss: 3.6836 (3.5171) grad_norm: 1.0870 (1.1241) time: 0.5053 [2021-03-25 20:03:47 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 250/1251] eta: 0:08:41 lr: 0.000787 loss: 3.6836 (3.5254) grad_norm: 1.0613 (1.1214) time: 0.5088 [2021-03-25 20:03:52 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 260/1251] eta: 0:08:35 lr: 0.000787 loss: 3.8218 (3.5315) grad_norm: 1.0932 (1.1225) time: 0.5068 [2021-03-25 20:03:58 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 270/1251] eta: 0:08:29 lr: 0.000787 loss: 3.7114 (3.5338) grad_norm: 1.1476 (1.1238) time: 0.5081 [2021-03-25 20:04:03 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 280/1251] eta: 0:08:24 lr: 0.000787 loss: 3.6483 (3.5294) grad_norm: 1.1391 (1.1230) time: 0.5058 [2021-03-25 20:04:08 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 290/1251] eta: 0:08:18 lr: 0.000787 loss: 3.4680 (3.5270) grad_norm: 1.1159 (1.1243) time: 0.5075 [2021-03-25 20:04:13 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 300/1251] eta: 0:08:13 lr: 0.000786 loss: 3.4381 (3.5230) grad_norm: 1.0980 (1.1236) time: 0.5115 [2021-03-25 20:04:18 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 310/1251] eta: 0:08:07 lr: 0.000786 loss: 3.6247 (3.5247) grad_norm: 1.0981 (1.1231) time: 0.5075 [2021-03-25 20:04:23 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 320/1251] eta: 0:08:02 lr: 0.000786 loss: 3.7296 (3.5301) grad_norm: 1.0960 (1.1218) time: 0.5070 [2021-03-25 20:04:28 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 330/1251] eta: 0:07:56 lr: 0.000786 loss: 3.7296 (3.5301) grad_norm: 1.0817 (1.1227) time: 0.5052 [2021-03-25 20:04:33 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 340/1251] eta: 0:07:51 lr: 0.000786 loss: 3.4517 (3.5276) grad_norm: 1.1151 (1.1236) time: 0.5069 [2021-03-25 20:04:38 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 350/1251] eta: 0:07:45 lr: 0.000786 loss: 3.4517 (3.5309) grad_norm: 1.1215 (1.1224) time: 0.5109 [2021-03-25 20:04:43 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 360/1251] eta: 0:07:40 lr: 0.000786 loss: 3.6293 (3.5345) grad_norm: 1.0759 (1.1215) time: 0.5019 [2021-03-25 20:04:48 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 370/1251] eta: 0:07:34 lr: 0.000786 loss: 3.8297 (3.5403) grad_norm: 1.0601 (1.1223) time: 0.5009 [2021-03-25 20:04:53 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 380/1251] eta: 0:07:29 lr: 0.000786 loss: 3.5357 (3.5297) grad_norm: 1.1417 (1.1234) time: 0.5041 [2021-03-25 20:04:58 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 390/1251] eta: 0:07:23 lr: 0.000786 loss: 3.2718 (3.5295) grad_norm: 1.1264 (1.1228) time: 0.5001 [2021-03-25 20:05:03 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 400/1251] eta: 0:07:18 lr: 0.000786 loss: 3.5788 (3.5305) grad_norm: 1.0570 (1.1217) time: 0.4975 [2021-03-25 20:05:08 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 410/1251] eta: 0:07:12 lr: 0.000786 loss: 3.5908 (3.5278) grad_norm: 1.1127 (1.1233) time: 0.5033 [2021-03-25 20:05:13 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 420/1251] eta: 0:07:07 lr: 0.000786 loss: 3.6003 (3.5311) grad_norm: 1.1127 (1.1223) time: 0.5078 [2021-03-25 20:05:19 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 430/1251] eta: 0:07:02 lr: 0.000786 loss: 3.6369 (3.5333) grad_norm: 1.0648 (1.1212) time: 0.5115 [2021-03-25 20:05:24 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 440/1251] eta: 0:06:57 lr: 0.000786 loss: 3.6089 (3.5337) grad_norm: 1.0714 (1.1204) time: 0.5123 [2021-03-25 20:05:29 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 450/1251] eta: 0:06:51 lr: 0.000786 loss: 3.6089 (3.5388) grad_norm: 1.0871 (1.1208) time: 0.5051 [2021-03-25 20:05:34 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 460/1251] eta: 0:06:46 lr: 0.000786 loss: 3.4316 (3.5331) grad_norm: 1.0794 (1.1206) time: 0.5036 [2021-03-25 20:05:39 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 470/1251] eta: 0:06:41 lr: 0.000786 loss: 3.5842 (3.5397) grad_norm: 1.0941 (1.1221) time: 0.5064 [2021-03-25 20:05:44 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 480/1251] eta: 0:06:36 lr: 0.000786 loss: 3.6587 (3.5397) grad_norm: 1.1459 (1.1220) time: 0.5049 [2021-03-25 20:05:49 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 490/1251] eta: 0:06:30 lr: 0.000786 loss: 3.6155 (3.5447) grad_norm: 1.0777 (1.1210) time: 0.5040 [2021-03-25 20:05:54 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 500/1251] eta: 0:06:25 lr: 0.000786 loss: 3.6155 (3.5453) grad_norm: 1.1044 (1.1227) time: 0.5054 [2021-03-25 20:05:59 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 510/1251] eta: 0:06:20 lr: 0.000786 loss: 3.5422 (3.5422) grad_norm: 1.1490 (1.1221) time: 0.5071 [2021-03-25 20:06:04 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 520/1251] eta: 0:06:15 lr: 0.000786 loss: 3.5422 (3.5416) grad_norm: 1.1160 (1.1227) time: 0.5083 [2021-03-25 20:06:09 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 530/1251] eta: 0:06:09 lr: 0.000786 loss: 3.6757 (3.5442) grad_norm: 1.1329 (1.1231) time: 0.5077 [2021-03-25 20:06:14 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 540/1251] eta: 0:06:04 lr: 0.000786 loss: 3.8493 (3.5490) grad_norm: 1.1011 (1.1230) time: 0.5126 [2021-03-25 20:06:20 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 550/1251] eta: 0:05:59 lr: 0.000786 loss: 3.6273 (3.5484) grad_norm: 1.1468 (1.1257) time: 0.5217 [2021-03-25 20:06:25 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 560/1251] eta: 0:05:54 lr: 0.000786 loss: 3.6594 (3.5542) grad_norm: 1.1957 (1.1271) time: 0.5162 [2021-03-25 20:06:30 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 570/1251] eta: 0:05:49 lr: 0.000786 loss: 3.6472 (3.5447) grad_norm: 1.1477 (1.1279) time: 0.5029 [2021-03-25 20:06:35 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 580/1251] eta: 0:05:44 lr: 0.000786 loss: 3.2335 (3.5439) grad_norm: 1.1451 (1.1281) time: 0.5016 [2021-03-25 20:06:40 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 590/1251] eta: 0:05:38 lr: 0.000785 loss: 3.6346 (3.5452) grad_norm: 1.1186 (1.1280) time: 0.5013 [2021-03-25 20:06:45 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 600/1251] eta: 0:05:33 lr: 0.000785 loss: 3.8648 (3.5479) grad_norm: 1.1334 (1.1295) time: 0.4985 [2021-03-25 20:06:50 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 610/1251] eta: 0:05:28 lr: 0.000785 loss: 3.8363 (3.5505) grad_norm: 1.1209 (1.1289) time: 0.5075 [2021-03-25 20:06:55 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 620/1251] eta: 0:05:23 lr: 0.000785 loss: 3.8363 (3.5488) grad_norm: 1.0503 (1.1279) time: 0.5123 [2021-03-25 20:07:00 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 630/1251] eta: 0:05:18 lr: 0.000785 loss: 3.5965 (3.5474) grad_norm: 1.0683 (1.1284) time: 0.5023 [2021-03-25 20:07:05 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 640/1251] eta: 0:05:12 lr: 0.000785 loss: 3.6636 (3.5513) grad_norm: 1.1255 (1.1288) time: 0.5030 [2021-03-25 20:07:10 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 650/1251] eta: 0:05:07 lr: 0.000785 loss: 3.8451 (3.5533) grad_norm: 1.1255 (1.1289) time: 0.5029 [2021-03-25 20:07:15 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 660/1251] eta: 0:05:02 lr: 0.000785 loss: 3.7862 (3.5545) grad_norm: 1.1517 (1.1296) time: 0.4966 [2021-03-25 20:07:20 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 670/1251] eta: 0:04:57 lr: 0.000785 loss: 3.6858 (3.5554) grad_norm: 1.1162 (1.1292) time: 0.5028 [2021-03-25 20:07:25 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 680/1251] eta: 0:04:52 lr: 0.000785 loss: 3.8448 (3.5584) grad_norm: 1.0503 (1.1276) time: 0.5054 [2021-03-25 20:07:30 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 690/1251] eta: 0:04:46 lr: 0.000785 loss: 3.7248 (3.5561) grad_norm: 1.0503 (1.1273) time: 0.5012 [2021-03-25 20:07:35 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 700/1251] eta: 0:04:41 lr: 0.000785 loss: 3.1711 (3.5513) grad_norm: 1.1110 (1.1269) time: 0.4996 [2021-03-25 20:07:40 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 710/1251] eta: 0:04:36 lr: 0.000785 loss: 3.4262 (3.5544) grad_norm: 1.1313 (1.1274) time: 0.5089 [2021-03-25 20:07:45 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 720/1251] eta: 0:04:31 lr: 0.000785 loss: 3.7233 (3.5544) grad_norm: 1.1807 (1.1283) time: 0.5227 [2021-03-25 20:07:50 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 730/1251] eta: 0:04:26 lr: 0.000785 loss: 3.5203 (3.5531) grad_norm: 1.1807 (1.1286) time: 0.5146 [2021-03-25 20:07:56 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 740/1251] eta: 0:04:21 lr: 0.000785 loss: 3.5331 (3.5548) grad_norm: 1.1059 (1.1288) time: 0.5180 [2021-03-25 20:08:01 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 750/1251] eta: 0:04:16 lr: 0.000785 loss: 3.8362 (3.5584) grad_norm: 1.1223 (1.1287) time: 0.5225 [2021-03-25 20:08:06 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 760/1251] eta: 0:04:11 lr: 0.000785 loss: 3.5934 (3.5556) grad_norm: 1.0659 (1.1280) time: 0.5102 [2021-03-25 20:08:11 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 770/1251] eta: 0:04:06 lr: 0.000785 loss: 3.4288 (3.5539) grad_norm: 1.0725 (1.1278) time: 0.5107 [2021-03-25 20:08:16 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 780/1251] eta: 0:04:00 lr: 0.000785 loss: 3.4161 (3.5521) grad_norm: 1.1229 (1.1282) time: 0.5109 [2021-03-25 20:08:21 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 790/1251] eta: 0:03:55 lr: 0.000785 loss: 3.5664 (3.5533) grad_norm: 1.0794 (1.1273) time: 0.5072 [2021-03-25 20:08:26 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 800/1251] eta: 0:03:50 lr: 0.000785 loss: 3.7303 (3.5532) grad_norm: 1.0631 (1.1267) time: 0.5071 [2021-03-25 20:08:31 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 810/1251] eta: 0:03:45 lr: 0.000785 loss: 3.6682 (3.5518) grad_norm: 1.0884 (1.1267) time: 0.5064 [2021-03-25 20:08:36 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 820/1251] eta: 0:03:40 lr: 0.000785 loss: 3.6243 (3.5527) grad_norm: 1.1556 (1.1285) time: 0.5010 [2021-03-25 20:08:41 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 830/1251] eta: 0:03:35 lr: 0.000785 loss: 3.6243 (3.5519) grad_norm: 1.1543 (1.1289) time: 0.5026 [2021-03-25 20:08:47 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 840/1251] eta: 0:03:30 lr: 0.000785 loss: 3.4233 (3.5498) grad_norm: 1.1268 (1.1287) time: 0.5100 [2021-03-25 20:08:52 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 850/1251] eta: 0:03:25 lr: 0.000785 loss: 3.3642 (3.5497) grad_norm: 1.1570 (1.1301) time: 0.5161 [2021-03-25 20:08:57 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 860/1251] eta: 0:03:19 lr: 0.000785 loss: 3.5187 (3.5488) grad_norm: 1.1896 (1.1308) time: 0.5126 [2021-03-25 20:09:02 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 870/1251] eta: 0:03:14 lr: 0.000785 loss: 3.6748 (3.5492) grad_norm: 1.1651 (1.1312) time: 0.5051 [2021-03-25 20:09:07 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 880/1251] eta: 0:03:09 lr: 0.000785 loss: 3.6590 (3.5478) grad_norm: 1.1087 (1.1306) time: 0.5017 [2021-03-25 20:09:12 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 890/1251] eta: 0:03:04 lr: 0.000784 loss: 3.6736 (3.5502) grad_norm: 1.1087 (1.1307) time: 0.5016 [2021-03-25 20:09:17 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 900/1251] eta: 0:02:59 lr: 0.000784 loss: 3.6822 (3.5504) grad_norm: 1.1403 (1.1310) time: 0.5017 [2021-03-25 20:09:22 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 910/1251] eta: 0:02:54 lr: 0.000784 loss: 3.6743 (3.5502) grad_norm: 1.1093 (1.1308) time: 0.5048 [2021-03-25 20:09:27 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 920/1251] eta: 0:02:49 lr: 0.000784 loss: 3.4909 (3.5503) grad_norm: 1.1210 (1.1312) time: 0.5051 [2021-03-25 20:09:32 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 930/1251] eta: 0:02:43 lr: 0.000784 loss: 3.5019 (3.5506) grad_norm: 1.1228 (1.1309) time: 0.5075 [2021-03-25 20:09:37 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 940/1251] eta: 0:02:38 lr: 0.000784 loss: 3.5019 (3.5503) grad_norm: 1.1435 (1.1314) time: 0.5136 [2021-03-25 20:09:42 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 950/1251] eta: 0:02:33 lr: 0.000784 loss: 3.5185 (3.5487) grad_norm: 1.1180 (1.1311) time: 0.5110 [2021-03-25 20:09:47 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 960/1251] eta: 0:02:28 lr: 0.000784 loss: 3.4324 (3.5455) grad_norm: 1.0984 (1.1315) time: 0.5040 [2021-03-25 20:09:53 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 970/1251] eta: 0:02:23 lr: 0.000784 loss: 3.4324 (3.5438) grad_norm: 1.1423 (1.1317) time: 0.5038 [2021-03-25 20:09:58 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 980/1251] eta: 0:02:18 lr: 0.000784 loss: 3.5979 (3.5434) grad_norm: 1.1086 (1.1317) time: 0.5073 [2021-03-25 20:10:03 swin_small_patch4_window7_224] INFO: Epoch: [92] [ 990/1251] eta: 0:02:13 lr: 0.000784 loss: 3.5979 (3.5424) grad_norm: 1.1214 (1.1318) time: 0.5049 [2021-03-25 20:10:08 swin_small_patch4_window7_224] INFO: Epoch: [92] [1000/1251] eta: 0:02:08 lr: 0.000784 loss: 3.6468 (3.5432) grad_norm: 1.1214 (1.1320) time: 0.5123 [2021-03-25 20:10:13 swin_small_patch4_window7_224] INFO: Epoch: [92] [1010/1251] eta: 0:02:03 lr: 0.000784 loss: 3.6468 (3.5420) grad_norm: 1.1116 (1.1324) time: 0.5111 [2021-03-25 20:10:18 swin_small_patch4_window7_224] INFO: Epoch: [92] [1020/1251] eta: 0:01:57 lr: 0.000784 loss: 3.5318 (3.5421) grad_norm: 1.1000 (1.1322) time: 0.4986 [2021-03-25 20:10:23 swin_small_patch4_window7_224] INFO: Epoch: [92] [1030/1251] eta: 0:01:52 lr: 0.000784 loss: 3.5737 (3.5411) grad_norm: 1.1013 (1.1322) time: 0.4980 [2021-03-25 20:10:28 swin_small_patch4_window7_224] INFO: Epoch: [92] [1040/1251] eta: 0:01:47 lr: 0.000784 loss: 3.6000 (3.5419) grad_norm: 1.1013 (1.1317) time: 0.5065 [2021-03-25 20:10:33 swin_small_patch4_window7_224] INFO: Epoch: [92] [1050/1251] eta: 0:01:42 lr: 0.000784 loss: 3.7420 (3.5420) grad_norm: 1.0749 (1.1320) time: 0.5095 [2021-03-25 20:10:38 swin_small_patch4_window7_224] INFO: Epoch: [92] [1060/1251] eta: 0:01:37 lr: 0.000784 loss: 3.4837 (3.5378) grad_norm: 1.1329 (1.1323) time: 0.5052 [2021-03-25 20:10:43 swin_small_patch4_window7_224] INFO: Epoch: [92] [1070/1251] eta: 0:01:32 lr: 0.000784 loss: 3.6819 (3.5401) grad_norm: 1.1150 (1.1322) time: 0.5051 [2021-03-25 20:10:48 swin_small_patch4_window7_224] INFO: Epoch: [92] [1080/1251] eta: 0:01:27 lr: 0.000784 loss: 3.7165 (3.5392) grad_norm: 1.1222 (1.1325) time: 0.5088 [2021-03-25 20:10:53 swin_small_patch4_window7_224] INFO: Epoch: [92] [1090/1251] eta: 0:01:22 lr: 0.000784 loss: 3.6529 (3.5398) grad_norm: 1.1391 (1.1324) time: 0.5069 [2021-03-25 20:10:58 swin_small_patch4_window7_224] INFO: Epoch: [92] [1100/1251] eta: 0:01:17 lr: 0.000784 loss: 3.7082 (3.5410) grad_norm: 1.1352 (1.1330) time: 0.5045 [2021-03-25 20:11:03 swin_small_patch4_window7_224] INFO: Epoch: [92] [1110/1251] eta: 0:01:11 lr: 0.000784 loss: 3.7698 (3.5414) grad_norm: 1.1235 (1.1332) time: 0.5037 [2021-03-25 20:11:08 swin_small_patch4_window7_224] INFO: Epoch: [92] [1120/1251] eta: 0:01:06 lr: 0.000784 loss: 3.3989 (3.5389) grad_norm: 1.1208 (1.1329) time: 0.5014 [2021-03-25 20:11:13 swin_small_patch4_window7_224] INFO: Epoch: [92] [1130/1251] eta: 0:01:01 lr: 0.000784 loss: 3.4491 (3.5393) grad_norm: 1.1014 (1.1328) time: 0.5026 [2021-03-25 20:11:18 swin_small_patch4_window7_224] INFO: Epoch: [92] [1140/1251] eta: 0:00:56 lr: 0.000784 loss: 3.6195 (3.5411) grad_norm: 1.1014 (1.1333) time: 0.5040 [2021-03-25 20:11:23 swin_small_patch4_window7_224] INFO: Epoch: [92] [1150/1251] eta: 0:00:51 lr: 0.000784 loss: 3.6195 (3.5409) grad_norm: 1.1103 (1.1329) time: 0.5039 [2021-03-25 20:11:29 swin_small_patch4_window7_224] INFO: Epoch: [92] [1160/1251] eta: 0:00:46 lr: 0.000784 loss: 3.6777 (3.5432) grad_norm: 1.0608 (1.1322) time: 0.5096 [2021-03-25 20:11:34 swin_small_patch4_window7_224] INFO: Epoch: [92] [1170/1251] eta: 0:00:41 lr: 0.000784 loss: 3.6777 (3.5423) grad_norm: 1.0913 (1.1324) time: 0.5172 [2021-03-25 20:11:39 swin_small_patch4_window7_224] INFO: Epoch: [92] [1180/1251] eta: 0:00:36 lr: 0.000783 loss: 3.4876 (3.5412) grad_norm: 1.1788 (1.1329) time: 0.5178 [2021-03-25 20:11:44 swin_small_patch4_window7_224] INFO: Epoch: [92] [1190/1251] eta: 0:00:31 lr: 0.000783 loss: 3.4518 (3.5395) grad_norm: 1.1659 (1.1327) time: 0.5097 [2021-03-25 20:11:49 swin_small_patch4_window7_224] INFO: Epoch: [92] [1200/1251] eta: 0:00:25 lr: 0.000783 loss: 3.4453 (3.5386) grad_norm: 1.1084 (1.1325) time: 0.5043 [2021-03-25 20:11:54 swin_small_patch4_window7_224] INFO: Epoch: [92] [1210/1251] eta: 0:00:20 lr: 0.000783 loss: 3.7355 (3.5412) grad_norm: 1.0532 (1.1318) time: 0.5059 [2021-03-25 20:11:59 swin_small_patch4_window7_224] INFO: Epoch: [92] [1220/1251] eta: 0:00:15 lr: 0.000783 loss: 3.7716 (3.5404) grad_norm: 1.0345 (1.1314) time: 0.5095 [2021-03-25 20:12:04 swin_small_patch4_window7_224] INFO: Epoch: [92] [1230/1251] eta: 0:00:10 lr: 0.000783 loss: 3.6817 (3.5405) grad_norm: 1.0781 (1.1318) time: 0.5063 [2021-03-25 20:12:09 swin_small_patch4_window7_224] INFO: Epoch: [92] [1240/1251] eta: 0:00:05 lr: 0.000783 loss: 3.6817 (3.5405) grad_norm: 1.0473 (1.1309) time: 0.5042 [2021-03-25 20:12:14 swin_small_patch4_window7_224] INFO: Epoch: [92] [1250/1251] eta: 0:00:00 lr: 0.000783 loss: 3.3872 (3.5408) grad_norm: 1.0351 (1.1303) time: 0.5107 [2021-03-25 20:12:20 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:56 loss: 1.0992 (1.0992) acc1: 71.8750 (71.8750) acc5: 92.1875 (92.1875) [2021-03-25 20:12:22 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.0432 (1.0467) acc1: 75.0000 (76.4205) acc5: 92.1875 (92.3295) [2021-03-25 20:12:24 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9632 (1.0516) acc1: 75.0000 (75.4464) acc5: 92.1875 (92.7827) [2021-03-25 20:12:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9455 (1.0129) acc1: 76.5625 (76.0585) acc5: 95.3125 (93.5988) [2021-03-25 20:12:29 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9742 (1.0294) acc1: 76.5625 (75.6860) acc5: 93.7500 (93.4070) [2021-03-25 20:12:30 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0997 (1.0343) acc1: 73.4375 (75.4560) acc5: 93.7500 (93.4080) [2021-03-25 20:12:35 swin_small_patch4_window7_224] INFO: * Acc@1 75.810 Acc@5 93.416 loss 1.020 [2021-03-25 20:12:35 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-25 20:12:35 swin_small_patch4_window7_224] INFO: Max accuracy: 75.91% [2021-03-25 20:12:39 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 0/1251] eta: 1:24:32 lr: 0.000783 loss: 3.8723 (3.8723) grad_norm: 1.3267 (1.3267) time: 4.0551 [2021-03-25 20:12:44 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 10/1251] eta: 0:17:24 lr: 0.000783 loss: 3.7673 (3.5538) grad_norm: 1.0901 (1.1158) time: 0.8414 [2021-03-25 20:12:49 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 20/1251] eta: 0:13:56 lr: 0.000783 loss: 3.5949 (3.6252) grad_norm: 1.0935 (1.1251) time: 0.5110 [2021-03-25 20:12:54 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 30/1251] eta: 0:12:43 lr: 0.000783 loss: 3.5949 (3.5659) grad_norm: 1.1176 (1.1171) time: 0.5065 [2021-03-25 20:12:59 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 40/1251] eta: 0:12:01 lr: 0.000783 loss: 3.6935 (3.5886) grad_norm: 1.1176 (1.1174) time: 0.5069 [2021-03-25 20:13:04 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 50/1251] eta: 0:11:32 lr: 0.000783 loss: 3.5843 (3.5412) grad_norm: 1.1109 (1.1150) time: 0.5018 [2021-03-25 20:13:09 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 60/1251] eta: 0:11:11 lr: 0.000783 loss: 3.4423 (3.5262) grad_norm: 1.1052 (1.1207) time: 0.4985 [2021-03-25 20:13:14 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 70/1251] eta: 0:10:56 lr: 0.000783 loss: 3.6202 (3.5424) grad_norm: 1.1304 (1.1264) time: 0.5035 [2021-03-25 20:13:19 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 80/1251] eta: 0:10:44 lr: 0.000783 loss: 3.6563 (3.5467) grad_norm: 1.1655 (1.1280) time: 0.5083 [2021-03-25 20:13:24 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 90/1251] eta: 0:10:31 lr: 0.000783 loss: 3.6191 (3.5474) grad_norm: 1.1709 (1.1390) time: 0.5006 [2021-03-25 20:13:30 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 100/1251] eta: 0:10:23 lr: 0.000783 loss: 3.8437 (3.5732) grad_norm: 1.1268 (1.1410) time: 0.5062 [2021-03-25 20:13:35 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 110/1251] eta: 0:10:13 lr: 0.000783 loss: 3.7248 (3.5734) grad_norm: 1.1028 (1.1383) time: 0.5085 [2021-03-25 20:13:40 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 120/1251] eta: 0:10:05 lr: 0.000783 loss: 3.6528 (3.5826) grad_norm: 1.1249 (1.1413) time: 0.5039 [2021-03-25 20:13:45 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 130/1251] eta: 0:09:59 lr: 0.000783 loss: 3.6230 (3.5795) grad_norm: 1.1289 (1.1392) time: 0.5173 [2021-03-25 20:13:50 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 140/1251] eta: 0:09:51 lr: 0.000783 loss: 3.4292 (3.5633) grad_norm: 1.0976 (1.1352) time: 0.5142 [2021-03-25 20:13:55 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 150/1251] eta: 0:09:43 lr: 0.000783 loss: 3.4744 (3.5701) grad_norm: 1.0628 (1.1346) time: 0.5008 [2021-03-25 20:14:00 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 160/1251] eta: 0:09:36 lr: 0.000783 loss: 3.7792 (3.5726) grad_norm: 1.0331 (1.1267) time: 0.5047 [2021-03-25 20:14:05 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 170/1251] eta: 0:09:30 lr: 0.000783 loss: 3.6738 (3.5687) grad_norm: 1.0420 (1.1242) time: 0.5111 [2021-03-25 20:14:10 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 180/1251] eta: 0:09:24 lr: 0.000783 loss: 3.8087 (3.5867) grad_norm: 1.0772 (1.1249) time: 0.5137 [2021-03-25 20:14:15 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 190/1251] eta: 0:09:18 lr: 0.000783 loss: 3.8587 (3.5809) grad_norm: 1.0772 (1.1256) time: 0.5147 [2021-03-25 20:14:21 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 200/1251] eta: 0:09:12 lr: 0.000783 loss: 3.1823 (3.5666) grad_norm: 1.1471 (1.1284) time: 0.5112 [2021-03-25 20:14:26 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 210/1251] eta: 0:09:06 lr: 0.000783 loss: 3.5488 (3.5652) grad_norm: 1.1543 (1.1327) time: 0.5062 [2021-03-25 20:14:31 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 220/1251] eta: 0:09:00 lr: 0.000782 loss: 3.5488 (3.5522) grad_norm: 1.1674 (1.1336) time: 0.5126 [2021-03-25 20:14:36 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 230/1251] eta: 0:08:54 lr: 0.000782 loss: 3.5922 (3.5614) grad_norm: 1.1586 (1.1328) time: 0.5173 [2021-03-25 20:14:41 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 240/1251] eta: 0:08:49 lr: 0.000782 loss: 3.5922 (3.5441) grad_norm: 1.1270 (1.1336) time: 0.5123 [2021-03-25 20:14:46 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 250/1251] eta: 0:08:42 lr: 0.000782 loss: 3.6036 (3.5464) grad_norm: 1.1089 (1.1342) time: 0.5031 [2021-03-25 20:14:51 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 260/1251] eta: 0:08:36 lr: 0.000782 loss: 3.7735 (3.5540) grad_norm: 1.1027 (1.1325) time: 0.4963 [2021-03-25 20:14:56 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 270/1251] eta: 0:08:30 lr: 0.000782 loss: 3.6920 (3.5565) grad_norm: 1.0874 (1.1318) time: 0.5033 [2021-03-25 20:15:01 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 280/1251] eta: 0:08:24 lr: 0.000782 loss: 3.6920 (3.5635) grad_norm: 1.0874 (1.1316) time: 0.5036 [2021-03-25 20:15:06 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 290/1251] eta: 0:08:19 lr: 0.000782 loss: 3.5821 (3.5579) grad_norm: 1.1360 (1.1344) time: 0.5042 [2021-03-25 20:15:11 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 300/1251] eta: 0:08:13 lr: 0.000782 loss: 3.5545 (3.5631) grad_norm: 1.2054 (1.1381) time: 0.5113 [2021-03-25 20:15:16 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 310/1251] eta: 0:08:08 lr: 0.000782 loss: 3.8453 (3.5673) grad_norm: 1.1585 (1.1367) time: 0.5129 [2021-03-25 20:15:21 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 320/1251] eta: 0:08:03 lr: 0.000782 loss: 3.8390 (3.5611) grad_norm: 1.0569 (1.1347) time: 0.5109 [2021-03-25 20:15:26 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 330/1251] eta: 0:07:57 lr: 0.000782 loss: 3.4542 (3.5564) grad_norm: 1.0789 (1.1350) time: 0.5038 [2021-03-25 20:15:32 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 340/1251] eta: 0:07:51 lr: 0.000782 loss: 3.5795 (3.5528) grad_norm: 1.0741 (1.1329) time: 0.5009 [2021-03-25 20:15:36 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 350/1251] eta: 0:07:46 lr: 0.000782 loss: 3.5816 (3.5564) grad_norm: 1.0701 (1.1327) time: 0.4987 [2021-03-25 20:15:42 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 360/1251] eta: 0:07:40 lr: 0.000782 loss: 3.7709 (3.5650) grad_norm: 1.0943 (1.1341) time: 0.4994 [2021-03-25 20:15:47 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 370/1251] eta: 0:07:34 lr: 0.000782 loss: 3.7240 (3.5558) grad_norm: 1.0893 (1.1327) time: 0.5024 [2021-03-25 20:15:52 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 380/1251] eta: 0:07:29 lr: 0.000782 loss: 3.2797 (3.5501) grad_norm: 1.0872 (1.1326) time: 0.5036 [2021-03-25 20:15:57 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 390/1251] eta: 0:07:24 lr: 0.000782 loss: 3.4532 (3.5500) grad_norm: 1.0626 (1.1308) time: 0.5049 [2021-03-25 20:16:02 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 400/1251] eta: 0:07:18 lr: 0.000782 loss: 3.6067 (3.5524) grad_norm: 1.0732 (1.1326) time: 0.5018 [2021-03-25 20:16:07 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 410/1251] eta: 0:07:13 lr: 0.000782 loss: 3.6712 (3.5576) grad_norm: 1.1857 (1.1351) time: 0.4995 [2021-03-25 20:16:12 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 420/1251] eta: 0:07:07 lr: 0.000782 loss: 3.5712 (3.5536) grad_norm: 1.1176 (1.1354) time: 0.5018 [2021-03-25 20:16:17 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 430/1251] eta: 0:07:02 lr: 0.000782 loss: 3.5009 (3.5531) grad_norm: 1.1176 (1.1375) time: 0.5046 [2021-03-25 20:16:22 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 440/1251] eta: 0:06:57 lr: 0.000782 loss: 3.3957 (3.5480) grad_norm: 1.1159 (1.1366) time: 0.5024 [2021-03-25 20:16:27 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 450/1251] eta: 0:06:51 lr: 0.000782 loss: 3.5193 (3.5505) grad_norm: 1.1159 (1.1370) time: 0.4974 [2021-03-25 20:16:32 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 460/1251] eta: 0:06:46 lr: 0.000782 loss: 3.7047 (3.5537) grad_norm: 1.1627 (1.1377) time: 0.5018 [2021-03-25 20:16:37 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 470/1251] eta: 0:06:41 lr: 0.000782 loss: 3.6584 (3.5507) grad_norm: 1.1592 (1.1387) time: 0.5061 [2021-03-25 20:16:42 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 480/1251] eta: 0:06:35 lr: 0.000782 loss: 3.6213 (3.5516) grad_norm: 1.1521 (1.1382) time: 0.5074 [2021-03-25 20:16:47 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 490/1251] eta: 0:06:30 lr: 0.000782 loss: 3.5692 (3.5496) grad_norm: 1.0657 (1.1371) time: 0.5045 [2021-03-25 20:16:52 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 500/1251] eta: 0:06:25 lr: 0.000782 loss: 3.5530 (3.5524) grad_norm: 1.0637 (1.1374) time: 0.5041 [2021-03-25 20:16:57 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 510/1251] eta: 0:06:20 lr: 0.000781 loss: 3.6581 (3.5508) grad_norm: 1.0637 (1.1366) time: 0.5076 [2021-03-25 20:17:02 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 520/1251] eta: 0:06:14 lr: 0.000781 loss: 3.5947 (3.5492) grad_norm: 1.0916 (1.1369) time: 0.5029 [2021-03-25 20:17:07 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 530/1251] eta: 0:06:09 lr: 0.000781 loss: 3.3399 (3.5410) grad_norm: 1.1283 (1.1371) time: 0.4997 [2021-03-25 20:17:12 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 540/1251] eta: 0:06:04 lr: 0.000781 loss: 3.1295 (3.5359) grad_norm: 1.1793 (1.1379) time: 0.4992 [2021-03-25 20:17:17 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 550/1251] eta: 0:05:59 lr: 0.000781 loss: 3.3203 (3.5338) grad_norm: 1.1265 (1.1379) time: 0.5108 [2021-03-25 20:17:22 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 560/1251] eta: 0:05:53 lr: 0.000781 loss: 3.6180 (3.5358) grad_norm: 1.1203 (1.1388) time: 0.5139 [2021-03-25 20:17:27 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 570/1251] eta: 0:05:48 lr: 0.000781 loss: 3.5268 (3.5351) grad_norm: 1.1203 (1.1389) time: 0.5054 [2021-03-25 20:17:32 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 580/1251] eta: 0:05:43 lr: 0.000781 loss: 3.4838 (3.5354) grad_norm: 1.1637 (1.1395) time: 0.5053 [2021-03-25 20:17:37 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 590/1251] eta: 0:05:38 lr: 0.000781 loss: 3.7438 (3.5356) grad_norm: 1.1812 (1.1402) time: 0.4991 [2021-03-25 20:17:42 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 600/1251] eta: 0:05:32 lr: 0.000781 loss: 3.5883 (3.5373) grad_norm: 1.1461 (1.1411) time: 0.4970 [2021-03-25 20:17:47 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 610/1251] eta: 0:05:27 lr: 0.000781 loss: 3.4845 (3.5349) grad_norm: 1.1066 (1.1411) time: 0.5048 [2021-03-25 20:17:52 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 620/1251] eta: 0:05:22 lr: 0.000781 loss: 3.3435 (3.5325) grad_norm: 1.0896 (1.1402) time: 0.5038 [2021-03-25 20:17:58 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 630/1251] eta: 0:05:17 lr: 0.000781 loss: 3.6876 (3.5346) grad_norm: 1.0896 (1.1412) time: 0.5074 [2021-03-25 20:18:03 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 640/1251] eta: 0:05:12 lr: 0.000781 loss: 3.7272 (3.5343) grad_norm: 1.0939 (1.1409) time: 0.5106 [2021-03-25 20:18:08 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 650/1251] eta: 0:05:07 lr: 0.000781 loss: 3.7211 (3.5356) grad_norm: 1.1131 (1.1411) time: 0.5083 [2021-03-25 20:18:13 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 660/1251] eta: 0:05:01 lr: 0.000781 loss: 3.6014 (3.5346) grad_norm: 1.1375 (1.1416) time: 0.5026 [2021-03-25 20:18:18 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 670/1251] eta: 0:04:56 lr: 0.000781 loss: 3.4264 (3.5358) grad_norm: 1.1417 (1.1419) time: 0.4976 [2021-03-25 20:18:23 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 680/1251] eta: 0:04:51 lr: 0.000781 loss: 3.6717 (3.5345) grad_norm: 1.1586 (1.1421) time: 0.5088 [2021-03-25 20:18:28 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 690/1251] eta: 0:04:46 lr: 0.000781 loss: 3.6717 (3.5362) grad_norm: 1.1446 (1.1420) time: 0.5140 [2021-03-25 20:18:33 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 700/1251] eta: 0:04:41 lr: 0.000781 loss: 3.6054 (3.5339) grad_norm: 1.1381 (1.1423) time: 0.5065 [2021-03-25 20:18:38 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 710/1251] eta: 0:04:36 lr: 0.000781 loss: 3.7161 (3.5360) grad_norm: 1.0779 (1.1412) time: 0.5008 [2021-03-25 20:18:43 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 720/1251] eta: 0:04:31 lr: 0.000781 loss: 3.4003 (3.5341) grad_norm: 1.0701 (1.1416) time: 0.5059 [2021-03-25 20:18:48 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 730/1251] eta: 0:04:26 lr: 0.000781 loss: 3.5327 (3.5359) grad_norm: 1.1369 (1.1416) time: 0.5110 [2021-03-25 20:18:54 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 740/1251] eta: 0:04:21 lr: 0.000781 loss: 3.6369 (3.5348) grad_norm: 1.0673 (1.1402) time: 0.5176 [2021-03-25 20:18:59 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 750/1251] eta: 0:04:15 lr: 0.000781 loss: 3.8278 (3.5374) grad_norm: 1.0490 (1.1401) time: 0.5189 [2021-03-25 20:19:04 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 760/1251] eta: 0:04:10 lr: 0.000781 loss: 3.8278 (3.5392) grad_norm: 1.1213 (1.1402) time: 0.5080 [2021-03-25 20:19:09 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 770/1251] eta: 0:04:05 lr: 0.000781 loss: 3.6809 (3.5398) grad_norm: 1.1050 (1.1396) time: 0.5094 [2021-03-25 20:19:14 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 780/1251] eta: 0:04:00 lr: 0.000781 loss: 3.6809 (3.5394) grad_norm: 1.0654 (1.1390) time: 0.5107 [2021-03-25 20:19:19 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 790/1251] eta: 0:03:55 lr: 0.000781 loss: 3.6130 (3.5385) grad_norm: 1.0747 (1.1389) time: 0.5080 [2021-03-25 20:19:24 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 800/1251] eta: 0:03:50 lr: 0.000780 loss: 3.6977 (3.5389) grad_norm: 1.1015 (1.1388) time: 0.5024 [2021-03-25 20:19:29 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 810/1251] eta: 0:03:45 lr: 0.000780 loss: 3.5816 (3.5370) grad_norm: 1.1223 (1.1390) time: 0.4996 [2021-03-25 20:19:34 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 820/1251] eta: 0:03:39 lr: 0.000780 loss: 3.4525 (3.5356) grad_norm: 1.1211 (1.1390) time: 0.5029 [2021-03-25 20:19:39 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 830/1251] eta: 0:03:34 lr: 0.000780 loss: 3.5589 (3.5355) grad_norm: 1.1056 (1.1379) time: 0.5085 [2021-03-25 20:19:44 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 840/1251] eta: 0:03:29 lr: 0.000780 loss: 3.5774 (3.5360) grad_norm: 1.0731 (1.1383) time: 0.5134 [2021-03-25 20:19:49 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 850/1251] eta: 0:03:24 lr: 0.000780 loss: 3.4940 (3.5351) grad_norm: 1.1291 (1.1381) time: 0.5069 [2021-03-25 20:19:54 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 860/1251] eta: 0:03:19 lr: 0.000780 loss: 3.6524 (3.5360) grad_norm: 1.1137 (1.1374) time: 0.5016 [2021-03-25 20:19:59 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 870/1251] eta: 0:03:14 lr: 0.000780 loss: 3.7074 (3.5388) grad_norm: 1.0638 (1.1371) time: 0.5073 [2021-03-25 20:20:04 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 880/1251] eta: 0:03:09 lr: 0.000780 loss: 3.5134 (3.5359) grad_norm: 1.0640 (1.1366) time: 0.5086 [2021-03-25 20:20:10 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 890/1251] eta: 0:03:04 lr: 0.000780 loss: 3.5879 (3.5370) grad_norm: 1.0946 (1.1370) time: 0.5033 [2021-03-25 20:20:15 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 900/1251] eta: 0:02:59 lr: 0.000780 loss: 3.8035 (3.5376) grad_norm: 1.1119 (1.1371) time: 0.5044 [2021-03-25 20:20:20 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 910/1251] eta: 0:02:53 lr: 0.000780 loss: 3.5211 (3.5367) grad_norm: 1.1231 (nan) time: 0.5080 [2021-03-25 20:20:25 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 920/1251] eta: 0:02:48 lr: 0.000780 loss: 3.4936 (3.5365) grad_norm: 1.1560 (nan) time: 0.5076 [2021-03-25 20:20:30 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 930/1251] eta: 0:02:43 lr: 0.000780 loss: 3.6176 (3.5371) grad_norm: 1.1266 (nan) time: 0.5124 [2021-03-25 20:20:35 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 940/1251] eta: 0:02:38 lr: 0.000780 loss: 3.6176 (3.5384) grad_norm: 1.1088 (nan) time: 0.5078 [2021-03-25 20:20:40 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 950/1251] eta: 0:02:33 lr: 0.000780 loss: 3.3943 (3.5379) grad_norm: 1.0932 (nan) time: 0.5020 [2021-03-25 20:20:45 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 960/1251] eta: 0:02:28 lr: 0.000780 loss: 3.2916 (3.5343) grad_norm: 1.1024 (nan) time: 0.5085 [2021-03-25 20:20:50 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 970/1251] eta: 0:02:23 lr: 0.000780 loss: 3.3996 (3.5338) grad_norm: 1.0623 (nan) time: 0.5063 [2021-03-25 20:20:55 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 980/1251] eta: 0:02:18 lr: 0.000780 loss: 3.6035 (3.5339) grad_norm: 1.0623 (nan) time: 0.5033 [2021-03-25 20:21:00 swin_small_patch4_window7_224] INFO: Epoch: [93] [ 990/1251] eta: 0:02:13 lr: 0.000780 loss: 3.6035 (3.5330) grad_norm: 1.1297 (nan) time: 0.5043 [2021-03-25 20:21:05 swin_small_patch4_window7_224] INFO: Epoch: [93] [1000/1251] eta: 0:02:07 lr: 0.000780 loss: 3.6312 (3.5329) grad_norm: 1.1226 (nan) time: 0.5018 [2021-03-25 20:21:10 swin_small_patch4_window7_224] INFO: Epoch: [93] [1010/1251] eta: 0:02:02 lr: 0.000780 loss: 3.5687 (3.5309) grad_norm: 1.1218 (nan) time: 0.5044 [2021-03-25 20:21:15 swin_small_patch4_window7_224] INFO: Epoch: [93] [1020/1251] eta: 0:01:57 lr: 0.000780 loss: 3.5687 (3.5306) grad_norm: 1.1218 (nan) time: 0.5044 [2021-03-25 20:21:20 swin_small_patch4_window7_224] INFO: Epoch: [93] [1030/1251] eta: 0:01:52 lr: 0.000780 loss: 3.4713 (3.5284) grad_norm: 1.1409 (nan) time: 0.5047 [2021-03-25 20:21:25 swin_small_patch4_window7_224] INFO: Epoch: [93] [1040/1251] eta: 0:01:47 lr: 0.000780 loss: 3.6496 (3.5319) grad_norm: 1.1346 (nan) time: 0.5093 [2021-03-25 20:21:31 swin_small_patch4_window7_224] INFO: Epoch: [93] [1050/1251] eta: 0:01:42 lr: 0.000780 loss: 3.6924 (3.5305) grad_norm: 1.0741 (nan) time: 0.5070 [2021-03-25 20:21:36 swin_small_patch4_window7_224] INFO: Epoch: [93] [1060/1251] eta: 0:01:37 lr: 0.000780 loss: 3.7241 (3.5327) grad_norm: 1.1117 (nan) time: 0.5018 [2021-03-25 20:21:41 swin_small_patch4_window7_224] INFO: Epoch: [93] [1070/1251] eta: 0:01:32 lr: 0.000780 loss: 3.7314 (3.5320) grad_norm: 1.1951 (nan) time: 0.5029 [2021-03-25 20:21:46 swin_small_patch4_window7_224] INFO: Epoch: [93] [1080/1251] eta: 0:01:27 lr: 0.000780 loss: 3.7032 (3.5322) grad_norm: 1.1869 (nan) time: 0.5076 [2021-03-25 20:21:51 swin_small_patch4_window7_224] INFO: Epoch: [93] [1090/1251] eta: 0:01:22 lr: 0.000779 loss: 3.7032 (3.5322) grad_norm: 1.1658 (nan) time: 0.5077 [2021-03-25 20:21:56 swin_small_patch4_window7_224] INFO: Epoch: [93] [1100/1251] eta: 0:01:16 lr: 0.000779 loss: 3.7068 (3.5338) grad_norm: 1.1233 (nan) time: 0.5078 [2021-03-25 20:22:01 swin_small_patch4_window7_224] INFO: Epoch: [93] [1110/1251] eta: 0:01:11 lr: 0.000779 loss: 3.5929 (3.5326) grad_norm: 1.1871 (nan) time: 0.5055 [2021-03-25 20:22:06 swin_small_patch4_window7_224] INFO: Epoch: [93] [1120/1251] eta: 0:01:06 lr: 0.000779 loss: 3.3034 (3.5308) grad_norm: 1.1354 (nan) time: 0.5087 [2021-03-25 20:22:11 swin_small_patch4_window7_224] INFO: Epoch: [93] [1130/1251] eta: 0:01:01 lr: 0.000779 loss: 3.5372 (3.5319) grad_norm: 1.1027 (nan) time: 0.5090 [2021-03-25 20:22:16 swin_small_patch4_window7_224] INFO: Epoch: [93] [1140/1251] eta: 0:00:56 lr: 0.000779 loss: 3.5038 (3.5292) grad_norm: 1.1366 (nan) time: 0.4995 [2021-03-25 20:22:21 swin_small_patch4_window7_224] INFO: Epoch: [93] [1150/1251] eta: 0:00:51 lr: 0.000779 loss: 3.3540 (3.5286) grad_norm: 1.0780 (nan) time: 0.4994 [2021-03-25 20:22:26 swin_small_patch4_window7_224] INFO: Epoch: [93] [1160/1251] eta: 0:00:46 lr: 0.000779 loss: 3.5247 (3.5288) grad_norm: 1.0894 (nan) time: 0.5044 [2021-03-25 20:22:31 swin_small_patch4_window7_224] INFO: Epoch: [93] [1170/1251] eta: 0:00:41 lr: 0.000779 loss: 3.7410 (3.5316) grad_norm: 1.1953 (nan) time: 0.5074 [2021-03-25 20:22:36 swin_small_patch4_window7_224] INFO: Epoch: [93] [1180/1251] eta: 0:00:36 lr: 0.000779 loss: 3.7777 (3.5306) grad_norm: 1.1371 (nan) time: 0.5068 [2021-03-25 20:22:41 swin_small_patch4_window7_224] INFO: Epoch: [93] [1190/1251] eta: 0:00:31 lr: 0.000779 loss: 3.7642 (3.5304) grad_norm: 1.0931 (nan) time: 0.5032 [2021-03-25 20:22:46 swin_small_patch4_window7_224] INFO: Epoch: [93] [1200/1251] eta: 0:00:25 lr: 0.000779 loss: 3.4043 (3.5289) grad_norm: 1.0914 (nan) time: 0.5036 [2021-03-25 20:22:51 swin_small_patch4_window7_224] INFO: Epoch: [93] [1210/1251] eta: 0:00:20 lr: 0.000779 loss: 3.4043 (3.5294) grad_norm: 1.1253 (nan) time: 0.5044 [2021-03-25 20:22:56 swin_small_patch4_window7_224] INFO: Epoch: [93] [1220/1251] eta: 0:00:15 lr: 0.000779 loss: 3.7748 (3.5302) grad_norm: 1.1253 (nan) time: 0.5043 [2021-03-25 20:23:01 swin_small_patch4_window7_224] INFO: Epoch: [93] [1230/1251] eta: 0:00:10 lr: 0.000779 loss: 3.7058 (3.5295) grad_norm: 1.1229 (nan) time: 0.5019 [2021-03-25 20:23:06 swin_small_patch4_window7_224] INFO: Epoch: [93] [1240/1251] eta: 0:00:05 lr: 0.000779 loss: 3.5102 (3.5298) grad_norm: 1.1568 (nan) time: 0.4981 [2021-03-25 20:23:11 swin_small_patch4_window7_224] INFO: Epoch: [93] [1250/1251] eta: 0:00:00 lr: 0.000779 loss: 3.5629 (3.5299) grad_norm: 1.1359 (nan) time: 0.4918 [2021-03-25 20:23:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:36 loss: 1.1670 (1.1670) acc1: 71.8750 (71.8750) acc5: 89.0625 (89.0625) [2021-03-25 20:23:21 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 1.0249 (0.9774) acc1: 79.6875 (77.8409) acc5: 93.7500 (93.8920) [2021-03-25 20:23:23 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0249 (1.0065) acc1: 78.1250 (75.8185) acc5: 93.7500 (94.2708) [2021-03-25 20:23:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0643 (1.0490) acc1: 71.8750 (74.9496) acc5: 93.7500 (93.6492) [2021-03-25 20:23:28 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0540 (1.0381) acc1: 75.0000 (75.4954) acc5: 93.7500 (93.6357) [2021-03-25 20:23:28 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9678 (1.0266) acc1: 78.1250 (75.7440) acc5: 93.7500 (93.6640) [2021-03-25 20:23:32 swin_small_patch4_window7_224] INFO: * Acc@1 76.030 Acc@5 93.366 loss 1.018 [2021-03-25 20:23:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.0% [2021-03-25 20:23:32 swin_small_patch4_window7_224] INFO: Max accuracy: 76.03% [2021-03-25 20:23:36 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 0/1251] eta: 1:26:49 lr: 0.000779 loss: 3.2872 (3.2872) grad_norm: 1.0850 (1.0850) time: 4.1640 [2021-03-25 20:23:42 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 10/1251] eta: 0:17:51 lr: 0.000779 loss: 3.5985 (3.6155) grad_norm: 1.0751 (1.0783) time: 0.8634 [2021-03-25 20:23:47 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 20/1251] eta: 0:14:16 lr: 0.000779 loss: 3.5291 (3.4383) grad_norm: 1.0609 (1.0871) time: 0.5221 [2021-03-25 20:23:52 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 30/1251] eta: 0:12:57 lr: 0.000779 loss: 3.3868 (3.4713) grad_norm: 1.1223 (1.1109) time: 0.5127 [2021-03-25 20:23:57 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 40/1251] eta: 0:12:17 lr: 0.000779 loss: 3.4095 (3.4619) grad_norm: 1.1223 (1.1076) time: 0.5187 [2021-03-25 20:24:02 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 50/1251] eta: 0:11:45 lr: 0.000779 loss: 3.5978 (3.4986) grad_norm: 1.0826 (1.1106) time: 0.5106 [2021-03-25 20:24:07 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 60/1251] eta: 0:11:25 lr: 0.000779 loss: 3.6040 (3.4563) grad_norm: 1.0569 (1.1007) time: 0.5063 [2021-03-25 20:24:12 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 70/1251] eta: 0:11:06 lr: 0.000779 loss: 3.3828 (3.4432) grad_norm: 1.0384 (1.0945) time: 0.5068 [2021-03-25 20:24:17 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 80/1251] eta: 0:10:52 lr: 0.000779 loss: 3.3801 (3.4553) grad_norm: 1.0650 (1.0980) time: 0.5011 [2021-03-25 20:24:22 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 90/1251] eta: 0:10:40 lr: 0.000779 loss: 3.5000 (3.4710) grad_norm: 1.0938 (1.0975) time: 0.5045 [2021-03-25 20:24:27 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 100/1251] eta: 0:10:30 lr: 0.000779 loss: 3.6835 (3.4726) grad_norm: 1.1116 (1.1073) time: 0.5086 [2021-03-25 20:24:32 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 110/1251] eta: 0:10:20 lr: 0.000779 loss: 3.5632 (3.4626) grad_norm: 1.2126 (1.1182) time: 0.5090 [2021-03-25 20:24:38 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 120/1251] eta: 0:10:11 lr: 0.000779 loss: 3.2956 (3.4458) grad_norm: 1.1953 (1.1219) time: 0.5073 [2021-03-25 20:24:43 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 130/1251] eta: 0:10:03 lr: 0.000778 loss: 3.6944 (3.4768) grad_norm: 1.1383 (1.1223) time: 0.5057 [2021-03-25 20:24:48 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 140/1251] eta: 0:09:56 lr: 0.000778 loss: 3.8012 (3.4817) grad_norm: 1.1139 (1.1209) time: 0.5109 [2021-03-25 20:24:53 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 150/1251] eta: 0:09:48 lr: 0.000778 loss: 3.7124 (3.4962) grad_norm: 1.1139 (1.1219) time: 0.5129 [2021-03-25 20:24:58 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 160/1251] eta: 0:09:41 lr: 0.000778 loss: 3.6262 (3.4982) grad_norm: 1.1369 (1.1264) time: 0.5088 [2021-03-25 20:25:03 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 170/1251] eta: 0:09:34 lr: 0.000778 loss: 3.5893 (3.5093) grad_norm: 1.1717 (1.1323) time: 0.5072 [2021-03-25 20:25:08 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 180/1251] eta: 0:09:28 lr: 0.000778 loss: 3.5643 (3.5050) grad_norm: 1.0799 (1.1301) time: 0.5084 [2021-03-25 20:25:13 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 190/1251] eta: 0:09:20 lr: 0.000778 loss: 3.4970 (3.5052) grad_norm: 1.0384 (1.1282) time: 0.5050 [2021-03-25 20:25:18 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 200/1251] eta: 0:09:14 lr: 0.000778 loss: 3.4970 (3.4913) grad_norm: 1.0941 (1.1292) time: 0.4987 [2021-03-25 20:25:23 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 210/1251] eta: 0:09:07 lr: 0.000778 loss: 3.4918 (3.5014) grad_norm: 1.1648 (1.1305) time: 0.5019 [2021-03-25 20:25:28 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 220/1251] eta: 0:09:01 lr: 0.000778 loss: 3.7685 (3.5130) grad_norm: 1.1063 (1.1313) time: 0.5077 [2021-03-25 20:25:33 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 230/1251] eta: 0:08:55 lr: 0.000778 loss: 3.5428 (3.4955) grad_norm: 1.1063 (1.1343) time: 0.5069 [2021-03-25 20:25:38 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 240/1251] eta: 0:08:49 lr: 0.000778 loss: 3.2666 (3.4871) grad_norm: 1.1195 (1.1340) time: 0.5033 [2021-03-25 20:25:44 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 250/1251] eta: 0:08:44 lr: 0.000778 loss: 3.3583 (3.4875) grad_norm: 1.0846 (1.1343) time: 0.5137 [2021-03-25 20:25:49 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 260/1251] eta: 0:08:38 lr: 0.000778 loss: 3.5397 (3.4892) grad_norm: 1.0822 (1.1323) time: 0.5127 [2021-03-25 20:25:54 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 270/1251] eta: 0:08:32 lr: 0.000778 loss: 3.4665 (3.4761) grad_norm: 1.0531 (1.1299) time: 0.5007 [2021-03-25 20:25:59 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 280/1251] eta: 0:08:26 lr: 0.000778 loss: 3.7961 (3.4925) grad_norm: 1.0531 (1.1282) time: 0.5026 [2021-03-25 20:26:04 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 290/1251] eta: 0:08:20 lr: 0.000778 loss: 3.8290 (3.4881) grad_norm: 1.1143 (1.1291) time: 0.5099 [2021-03-25 20:26:09 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 300/1251] eta: 0:08:15 lr: 0.000778 loss: 3.7118 (3.4973) grad_norm: 1.1143 (1.1300) time: 0.5118 [2021-03-25 20:26:14 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 310/1251] eta: 0:08:09 lr: 0.000778 loss: 3.6863 (3.4980) grad_norm: 1.1209 (1.1310) time: 0.5086 [2021-03-25 20:26:19 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 320/1251] eta: 0:08:03 lr: 0.000778 loss: 3.6204 (3.5019) grad_norm: 1.1236 (1.1321) time: 0.5062 [2021-03-25 20:26:24 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 330/1251] eta: 0:07:58 lr: 0.000778 loss: 3.7530 (3.5104) grad_norm: 1.1216 (1.1312) time: 0.5040 [2021-03-25 20:26:29 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 340/1251] eta: 0:07:52 lr: 0.000778 loss: 3.7562 (3.5131) grad_norm: 1.1232 (1.1309) time: 0.5051 [2021-03-25 20:26:34 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 350/1251] eta: 0:07:47 lr: 0.000778 loss: 3.6545 (3.5125) grad_norm: 1.1456 (1.1323) time: 0.5024 [2021-03-25 20:26:39 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 360/1251] eta: 0:07:41 lr: 0.000778 loss: 3.6545 (3.5139) grad_norm: 1.1681 (1.1337) time: 0.5017 [2021-03-25 20:26:44 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 370/1251] eta: 0:07:36 lr: 0.000778 loss: 3.5693 (3.5150) grad_norm: 1.1225 (1.1330) time: 0.5108 [2021-03-25 20:26:49 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 380/1251] eta: 0:07:30 lr: 0.000778 loss: 3.5926 (3.5201) grad_norm: 1.0981 (1.1328) time: 0.5075 [2021-03-25 20:26:54 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 390/1251] eta: 0:07:25 lr: 0.000778 loss: 3.5633 (3.5184) grad_norm: 1.1568 (1.1351) time: 0.5006 [2021-03-25 20:26:59 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 400/1251] eta: 0:07:19 lr: 0.000778 loss: 3.6453 (3.5262) grad_norm: 1.1568 (1.1353) time: 0.5031 [2021-03-25 20:27:04 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 410/1251] eta: 0:07:14 lr: 0.000778 loss: 3.5098 (3.5177) grad_norm: 1.1290 (1.1351) time: 0.5044 [2021-03-25 20:27:09 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 420/1251] eta: 0:07:08 lr: 0.000777 loss: 3.2146 (3.5141) grad_norm: 1.1075 (1.1352) time: 0.5032 [2021-03-25 20:27:15 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 430/1251] eta: 0:07:03 lr: 0.000777 loss: 3.2788 (3.5132) grad_norm: 1.0268 (1.1333) time: 0.5108 [2021-03-25 20:27:20 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 440/1251] eta: 0:06:58 lr: 0.000777 loss: 3.6768 (3.5184) grad_norm: 1.0739 (1.1343) time: 0.5071 [2021-03-25 20:27:25 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 450/1251] eta: 0:06:52 lr: 0.000777 loss: 3.7439 (3.5175) grad_norm: 1.1340 (1.1345) time: 0.5018 [2021-03-25 20:27:30 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 460/1251] eta: 0:06:47 lr: 0.000777 loss: 3.6710 (3.5163) grad_norm: 1.1225 (1.1336) time: 0.5041 [2021-03-25 20:27:35 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 470/1251] eta: 0:06:42 lr: 0.000777 loss: 3.5628 (3.5117) grad_norm: 1.0462 (1.1314) time: 0.5047 [2021-03-25 20:27:40 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 480/1251] eta: 0:06:37 lr: 0.000777 loss: 3.1962 (3.5058) grad_norm: 1.0415 (1.1306) time: 0.5089 [2021-03-25 20:27:45 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 490/1251] eta: 0:06:31 lr: 0.000777 loss: 3.1962 (3.5002) grad_norm: 1.0996 (1.1332) time: 0.5094 [2021-03-25 20:27:50 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 500/1251] eta: 0:06:26 lr: 0.000777 loss: 3.5646 (3.5065) grad_norm: 1.2159 (1.1347) time: 0.5106 [2021-03-25 20:27:55 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 510/1251] eta: 0:06:21 lr: 0.000777 loss: 3.8803 (3.5100) grad_norm: 1.1700 (1.1355) time: 0.5037 [2021-03-25 20:28:00 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 520/1251] eta: 0:06:15 lr: 0.000777 loss: 3.7158 (3.5125) grad_norm: 1.1479 (1.1351) time: 0.5026 [2021-03-25 20:28:05 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 530/1251] eta: 0:06:10 lr: 0.000777 loss: 3.6328 (3.5102) grad_norm: 1.1073 (1.1345) time: 0.5070 [2021-03-25 20:28:10 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 540/1251] eta: 0:06:05 lr: 0.000777 loss: 3.8550 (3.5144) grad_norm: 1.1109 (1.1350) time: 0.5059 [2021-03-25 20:28:15 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 550/1251] eta: 0:06:00 lr: 0.000777 loss: 3.5526 (3.5117) grad_norm: 1.1109 (1.1347) time: 0.5070 [2021-03-25 20:28:20 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 560/1251] eta: 0:05:54 lr: 0.000777 loss: 3.5427 (3.5126) grad_norm: 1.0972 (1.1343) time: 0.5050 [2021-03-25 20:28:25 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 570/1251] eta: 0:05:49 lr: 0.000777 loss: 3.5852 (3.5101) grad_norm: 1.1156 (1.1350) time: 0.5012 [2021-03-25 20:28:31 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 580/1251] eta: 0:05:44 lr: 0.000777 loss: 3.5555 (3.5108) grad_norm: 1.0997 (1.1351) time: 0.5125 [2021-03-25 20:28:36 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 590/1251] eta: 0:05:39 lr: 0.000777 loss: 3.3185 (3.5046) grad_norm: 1.0994 (1.1358) time: 0.5160 [2021-03-25 20:28:41 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 600/1251] eta: 0:05:34 lr: 0.000777 loss: 3.3678 (3.5072) grad_norm: 1.1612 (1.1369) time: 0.5114 [2021-03-25 20:28:46 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 610/1251] eta: 0:05:29 lr: 0.000777 loss: 3.8300 (3.5091) grad_norm: 1.1487 (1.1367) time: 0.5124 [2021-03-25 20:28:51 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 620/1251] eta: 0:05:23 lr: 0.000777 loss: 3.7547 (3.5093) grad_norm: 1.1487 (1.1375) time: 0.5076 [2021-03-25 20:28:56 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 630/1251] eta: 0:05:18 lr: 0.000777 loss: 3.5523 (3.5064) grad_norm: 1.1130 (1.1372) time: 0.5048 [2021-03-25 20:29:01 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 640/1251] eta: 0:05:13 lr: 0.000777 loss: 3.3425 (3.5036) grad_norm: 1.0858 (1.1372) time: 0.5049 [2021-03-25 20:29:06 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 650/1251] eta: 0:05:08 lr: 0.000777 loss: 3.6003 (3.5040) grad_norm: 1.1010 (1.1376) time: 0.5053 [2021-03-25 20:29:11 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 660/1251] eta: 0:05:03 lr: 0.000777 loss: 3.6859 (3.5044) grad_norm: 1.1557 (1.1392) time: 0.5092 [2021-03-25 20:29:16 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 670/1251] eta: 0:04:57 lr: 0.000777 loss: 3.7332 (3.5081) grad_norm: 1.1595 (1.1389) time: 0.5087 [2021-03-25 20:29:21 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 680/1251] eta: 0:04:52 lr: 0.000777 loss: 3.5118 (3.5061) grad_norm: 1.0947 (1.1388) time: 0.5026 [2021-03-25 20:29:26 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 690/1251] eta: 0:04:47 lr: 0.000777 loss: 3.5908 (3.5124) grad_norm: 1.0846 (1.1379) time: 0.5057 [2021-03-25 20:29:31 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 700/1251] eta: 0:04:42 lr: 0.000777 loss: 3.7260 (3.5156) grad_norm: 1.0613 (1.1373) time: 0.5070 [2021-03-25 20:29:36 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 710/1251] eta: 0:04:37 lr: 0.000776 loss: 3.7652 (3.5179) grad_norm: 1.0959 (1.1370) time: 0.5026 [2021-03-25 20:29:41 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 720/1251] eta: 0:04:31 lr: 0.000776 loss: 3.7498 (3.5207) grad_norm: 1.1359 (1.1373) time: 0.5009 [2021-03-25 20:29:47 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 730/1251] eta: 0:04:26 lr: 0.000776 loss: 3.7498 (3.5222) grad_norm: 1.1537 (1.1381) time: 0.5066 [2021-03-25 20:29:52 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 740/1251] eta: 0:04:21 lr: 0.000776 loss: 3.5748 (3.5212) grad_norm: 1.1985 (1.1391) time: 0.5110 [2021-03-25 20:29:57 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 750/1251] eta: 0:04:16 lr: 0.000776 loss: 3.6208 (3.5233) grad_norm: 1.1416 (1.1392) time: 0.5148 [2021-03-25 20:30:02 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 760/1251] eta: 0:04:11 lr: 0.000776 loss: 3.8665 (3.5245) grad_norm: 1.1489 (1.1403) time: 0.5143 [2021-03-25 20:30:07 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 770/1251] eta: 0:04:06 lr: 0.000776 loss: 3.5896 (3.5236) grad_norm: 1.1957 (1.1413) time: 0.5116 [2021-03-25 20:30:12 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 780/1251] eta: 0:04:01 lr: 0.000776 loss: 3.5070 (3.5230) grad_norm: 1.1306 (1.1408) time: 0.5087 [2021-03-25 20:30:17 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 790/1251] eta: 0:03:56 lr: 0.000776 loss: 3.7073 (3.5228) grad_norm: 1.0948 (1.1404) time: 0.5093 [2021-03-25 20:30:22 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 800/1251] eta: 0:03:50 lr: 0.000776 loss: 3.7470 (3.5217) grad_norm: 1.1382 (1.1409) time: 0.5140 [2021-03-25 20:30:28 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 810/1251] eta: 0:03:45 lr: 0.000776 loss: 3.5985 (3.5216) grad_norm: 1.1189 (1.1407) time: 0.5089 [2021-03-25 20:30:32 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 820/1251] eta: 0:03:40 lr: 0.000776 loss: 3.6175 (3.5226) grad_norm: 1.1312 (1.1409) time: 0.5015 [2021-03-25 20:30:38 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 830/1251] eta: 0:03:35 lr: 0.000776 loss: 3.5582 (3.5207) grad_norm: 1.1156 (1.1406) time: 0.5012 [2021-03-25 20:30:43 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 840/1251] eta: 0:03:30 lr: 0.000776 loss: 3.3244 (3.5171) grad_norm: 1.1026 (1.1405) time: 0.5073 [2021-03-25 20:30:48 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 850/1251] eta: 0:03:25 lr: 0.000776 loss: 3.3244 (3.5149) grad_norm: 1.1465 (1.1413) time: 0.5145 [2021-03-25 20:30:53 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 860/1251] eta: 0:03:20 lr: 0.000776 loss: 3.5360 (3.5166) grad_norm: 1.1465 (1.1411) time: 0.5131 [2021-03-25 20:30:58 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 870/1251] eta: 0:03:14 lr: 0.000776 loss: 3.6546 (3.5157) grad_norm: 1.0777 (1.1407) time: 0.5054 [2021-03-25 20:31:03 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 880/1251] eta: 0:03:09 lr: 0.000776 loss: 3.7259 (3.5184) grad_norm: 1.1363 (1.1413) time: 0.5032 [2021-03-25 20:31:08 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 890/1251] eta: 0:03:04 lr: 0.000776 loss: 3.5829 (3.5159) grad_norm: 1.1168 (1.1405) time: 0.5064 [2021-03-25 20:31:13 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 900/1251] eta: 0:02:59 lr: 0.000776 loss: 3.5829 (3.5197) grad_norm: 1.0541 (1.1397) time: 0.5095 [2021-03-25 20:31:18 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 910/1251] eta: 0:02:54 lr: 0.000776 loss: 3.8243 (3.5194) grad_norm: 1.1046 (1.1404) time: 0.5076 [2021-03-25 20:31:23 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 920/1251] eta: 0:02:49 lr: 0.000776 loss: 3.3430 (3.5189) grad_norm: 1.1131 (1.1401) time: 0.5021 [2021-03-25 20:31:28 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 930/1251] eta: 0:02:44 lr: 0.000776 loss: 3.3430 (3.5175) grad_norm: 1.1131 (1.1402) time: 0.4998 [2021-03-25 20:31:33 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 940/1251] eta: 0:02:38 lr: 0.000776 loss: 3.5452 (3.5188) grad_norm: 1.1574 (1.1405) time: 0.5035 [2021-03-25 20:31:38 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 950/1251] eta: 0:02:33 lr: 0.000776 loss: 3.7610 (3.5193) grad_norm: 1.0753 (1.1403) time: 0.5056 [2021-03-25 20:31:43 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 960/1251] eta: 0:02:28 lr: 0.000776 loss: 3.7610 (3.5211) grad_norm: 1.0649 (1.1398) time: 0.5036 [2021-03-25 20:31:48 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 970/1251] eta: 0:02:23 lr: 0.000776 loss: 3.4493 (3.5196) grad_norm: 1.0634 (1.1387) time: 0.5067 [2021-03-25 20:31:54 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 980/1251] eta: 0:02:18 lr: 0.000776 loss: 3.4493 (3.5204) grad_norm: 1.0457 (1.1391) time: 0.5108 [2021-03-25 20:31:59 swin_small_patch4_window7_224] INFO: Epoch: [94] [ 990/1251] eta: 0:02:13 lr: 0.000776 loss: 3.5798 (3.5197) grad_norm: 1.1212 (1.1399) time: 0.5127 [2021-03-25 20:32:04 swin_small_patch4_window7_224] INFO: Epoch: [94] [1000/1251] eta: 0:02:08 lr: 0.000775 loss: 3.5904 (3.5204) grad_norm: 1.1449 (1.1407) time: 0.5103 [2021-03-25 20:32:09 swin_small_patch4_window7_224] INFO: Epoch: [94] [1010/1251] eta: 0:02:03 lr: 0.000775 loss: 3.6075 (3.5201) grad_norm: 1.1470 (1.1407) time: 0.5033 [2021-03-25 20:32:14 swin_small_patch4_window7_224] INFO: Epoch: [94] [1020/1251] eta: 0:01:58 lr: 0.000775 loss: 3.3835 (3.5179) grad_norm: 1.1054 (1.1403) time: 0.5012 [2021-03-25 20:32:19 swin_small_patch4_window7_224] INFO: Epoch: [94] [1030/1251] eta: 0:01:52 lr: 0.000775 loss: 2.9672 (3.5159) grad_norm: 1.1054 (1.1402) time: 0.5054 [2021-03-25 20:32:24 swin_small_patch4_window7_224] INFO: Epoch: [94] [1040/1251] eta: 0:01:47 lr: 0.000775 loss: 3.3833 (3.5151) grad_norm: 1.1262 (1.1406) time: 0.5081 [2021-03-25 20:32:29 swin_small_patch4_window7_224] INFO: Epoch: [94] [1050/1251] eta: 0:01:42 lr: 0.000775 loss: 3.7715 (3.5179) grad_norm: 1.1159 (1.1402) time: 0.5018 [2021-03-25 20:32:34 swin_small_patch4_window7_224] INFO: Epoch: [94] [1060/1251] eta: 0:01:37 lr: 0.000775 loss: 3.8271 (3.5191) grad_norm: 1.0878 (1.1399) time: 0.5017 [2021-03-25 20:32:39 swin_small_patch4_window7_224] INFO: Epoch: [94] [1070/1251] eta: 0:01:32 lr: 0.000775 loss: 3.5617 (3.5184) grad_norm: 1.0878 (1.1395) time: 0.5078 [2021-03-25 20:32:44 swin_small_patch4_window7_224] INFO: Epoch: [94] [1080/1251] eta: 0:01:27 lr: 0.000775 loss: 3.4845 (3.5178) grad_norm: 1.1052 (1.1397) time: 0.5040 [2021-03-25 20:32:49 swin_small_patch4_window7_224] INFO: Epoch: [94] [1090/1251] eta: 0:01:22 lr: 0.000775 loss: 3.4746 (3.5167) grad_norm: 1.1177 (1.1396) time: 0.4981 [2021-03-25 20:32:54 swin_small_patch4_window7_224] INFO: Epoch: [94] [1100/1251] eta: 0:01:17 lr: 0.000775 loss: 3.4898 (3.5169) grad_norm: 1.1104 (1.1392) time: 0.4993 [2021-03-25 20:32:59 swin_small_patch4_window7_224] INFO: Epoch: [94] [1110/1251] eta: 0:01:11 lr: 0.000775 loss: 3.5729 (3.5175) grad_norm: 1.1104 (1.1387) time: 0.5005 [2021-03-25 20:33:04 swin_small_patch4_window7_224] INFO: Epoch: [94] [1120/1251] eta: 0:01:06 lr: 0.000775 loss: 3.4844 (3.5157) grad_norm: 1.0941 (1.1383) time: 0.4977 [2021-03-25 20:33:09 swin_small_patch4_window7_224] INFO: Epoch: [94] [1130/1251] eta: 0:01:01 lr: 0.000775 loss: 3.6003 (3.5166) grad_norm: 1.0917 (1.1380) time: 0.4954 [2021-03-25 20:33:14 swin_small_patch4_window7_224] INFO: Epoch: [94] [1140/1251] eta: 0:00:56 lr: 0.000775 loss: 3.6171 (3.5166) grad_norm: 1.1476 (1.1386) time: 0.4950 [2021-03-25 20:33:19 swin_small_patch4_window7_224] INFO: Epoch: [94] [1150/1251] eta: 0:00:51 lr: 0.000775 loss: 3.4594 (3.5156) grad_norm: 1.1094 (1.1384) time: 0.4982 [2021-03-25 20:33:24 swin_small_patch4_window7_224] INFO: Epoch: [94] [1160/1251] eta: 0:00:46 lr: 0.000775 loss: 3.5449 (3.5156) grad_norm: 1.0972 (1.1385) time: 0.5088 [2021-03-25 20:33:29 swin_small_patch4_window7_224] INFO: Epoch: [94] [1170/1251] eta: 0:00:41 lr: 0.000775 loss: 3.4386 (3.5135) grad_norm: 1.0972 (1.1383) time: 0.5131 [2021-03-25 20:33:34 swin_small_patch4_window7_224] INFO: Epoch: [94] [1180/1251] eta: 0:00:36 lr: 0.000775 loss: 3.4386 (3.5139) grad_norm: 1.1227 (1.1382) time: 0.5098 [2021-03-25 20:33:39 swin_small_patch4_window7_224] INFO: Epoch: [94] [1190/1251] eta: 0:00:31 lr: 0.000775 loss: 3.5382 (3.5111) grad_norm: 1.1068 (1.1382) time: 0.5090 [2021-03-25 20:33:44 swin_small_patch4_window7_224] INFO: Epoch: [94] [1200/1251] eta: 0:00:25 lr: 0.000775 loss: 3.2953 (3.5121) grad_norm: 1.1022 (1.1380) time: 0.5055 [2021-03-25 20:33:49 swin_small_patch4_window7_224] INFO: Epoch: [94] [1210/1251] eta: 0:00:20 lr: 0.000775 loss: 3.6424 (3.5130) grad_norm: 1.1059 (1.1381) time: 0.5027 [2021-03-25 20:33:55 swin_small_patch4_window7_224] INFO: Epoch: [94] [1220/1251] eta: 0:00:15 lr: 0.000775 loss: 3.6424 (3.5117) grad_norm: 1.0902 (1.1377) time: 0.5043 [2021-03-25 20:34:00 swin_small_patch4_window7_224] INFO: Epoch: [94] [1230/1251] eta: 0:00:10 lr: 0.000775 loss: 3.4099 (3.5099) grad_norm: 1.0903 (1.1379) time: 0.5081 [2021-03-25 20:34:05 swin_small_patch4_window7_224] INFO: Epoch: [94] [1240/1251] eta: 0:00:05 lr: 0.000775 loss: 3.5477 (3.5100) grad_norm: 1.1485 (1.1380) time: 0.5087 [2021-03-25 20:34:10 swin_small_patch4_window7_224] INFO: Epoch: [94] [1250/1251] eta: 0:00:00 lr: 0.000775 loss: 3.6953 (3.5114) grad_norm: 1.1486 (1.1385) time: 0.5022 [2021-03-25 20:34:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:52 loss: 1.0048 (1.0048) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-25 20:34:20 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.0048 (1.0053) acc1: 76.5625 (75.9943) acc5: 95.3125 (94.1761) [2021-03-25 20:34:22 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0305 (1.0364) acc1: 75.0000 (75.1488) acc5: 93.7500 (93.0804) [2021-03-25 20:34:24 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0086 (1.0020) acc1: 75.0000 (76.1089) acc5: 93.7500 (93.5484) [2021-03-25 20:34:26 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9987 (1.0156) acc1: 76.5625 (76.1052) acc5: 93.7500 (93.4070) [2021-03-25 20:34:27 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0325 (1.0316) acc1: 76.5625 (75.6160) acc5: 92.1875 (93.2480) [2021-03-25 20:34:32 swin_small_patch4_window7_224] INFO: * Acc@1 75.890 Acc@5 93.434 loss 1.005 [2021-03-25 20:34:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.9% [2021-03-25 20:34:32 swin_small_patch4_window7_224] INFO: Max accuracy: 76.03% [2021-03-25 20:34:36 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 0/1251] eta: 1:32:20 lr: 0.000775 loss: 3.8485 (3.8485) grad_norm: 1.1086 (1.1086) time: 4.4285 [2021-03-25 20:34:41 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 10/1251] eta: 0:17:52 lr: 0.000775 loss: 3.4239 (3.2730) grad_norm: 1.2433 (1.2127) time: 0.8641 [2021-03-25 20:34:46 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 20/1251] eta: 0:14:15 lr: 0.000775 loss: 3.1871 (3.3066) grad_norm: 1.1601 (1.1706) time: 0.5085 [2021-03-25 20:34:51 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 30/1251] eta: 0:12:58 lr: 0.000774 loss: 3.2240 (3.3202) grad_norm: 1.1474 (1.1585) time: 0.5127 [2021-03-25 20:34:56 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 40/1251] eta: 0:12:13 lr: 0.000774 loss: 3.6133 (3.4030) grad_norm: 1.1289 (1.1536) time: 0.5121 [2021-03-25 20:35:02 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 50/1251] eta: 0:11:44 lr: 0.000774 loss: 3.6567 (3.4297) grad_norm: 1.1267 (1.1501) time: 0.5077 [2021-03-25 20:35:07 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 60/1251] eta: 0:11:22 lr: 0.000774 loss: 3.6130 (3.4551) grad_norm: 1.0983 (1.1439) time: 0.5050 [2021-03-25 20:35:12 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 70/1251] eta: 0:11:05 lr: 0.000774 loss: 3.5802 (3.4637) grad_norm: 1.0983 (1.1497) time: 0.5039 [2021-03-25 20:35:17 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 80/1251] eta: 0:10:52 lr: 0.000774 loss: 3.5691 (3.4559) grad_norm: 1.1152 (1.1444) time: 0.5089 [2021-03-25 20:35:22 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 90/1251] eta: 0:10:39 lr: 0.000774 loss: 3.7839 (3.5134) grad_norm: 1.1152 (1.1500) time: 0.5085 [2021-03-25 20:35:27 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 100/1251] eta: 0:10:28 lr: 0.000774 loss: 3.8443 (3.5199) grad_norm: 1.1577 (1.1576) time: 0.5033 [2021-03-25 20:35:32 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 110/1251] eta: 0:10:18 lr: 0.000774 loss: 3.7461 (3.5326) grad_norm: 1.1289 (1.1549) time: 0.5005 [2021-03-25 20:35:37 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 120/1251] eta: 0:10:09 lr: 0.000774 loss: 3.7461 (3.5344) grad_norm: 1.1092 (1.1540) time: 0.5003 [2021-03-25 20:35:42 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 130/1251] eta: 0:10:00 lr: 0.000774 loss: 3.5181 (3.5154) grad_norm: 1.1186 (1.1530) time: 0.5001 [2021-03-25 20:35:47 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 140/1251] eta: 0:09:53 lr: 0.000774 loss: 3.4051 (3.5095) grad_norm: 1.1045 (1.1519) time: 0.5036 [2021-03-25 20:35:52 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 150/1251] eta: 0:09:45 lr: 0.000774 loss: 3.5516 (3.5193) grad_norm: 1.1257 (1.1529) time: 0.5035 [2021-03-25 20:35:57 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 160/1251] eta: 0:09:38 lr: 0.000774 loss: 3.5050 (3.5079) grad_norm: 1.1545 (1.1544) time: 0.5044 [2021-03-25 20:36:02 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 170/1251] eta: 0:09:31 lr: 0.000774 loss: 3.5050 (3.5063) grad_norm: 1.1858 (1.1524) time: 0.5067 [2021-03-25 20:36:07 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 180/1251] eta: 0:09:24 lr: 0.000774 loss: 3.5833 (3.5076) grad_norm: 1.0849 (1.1516) time: 0.5031 [2021-03-25 20:36:12 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 190/1251] eta: 0:09:18 lr: 0.000774 loss: 3.6066 (3.5109) grad_norm: 1.0650 (1.1502) time: 0.5063 [2021-03-25 20:36:17 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 200/1251] eta: 0:09:12 lr: 0.000774 loss: 3.5518 (3.5058) grad_norm: 1.0916 (1.1514) time: 0.5138 [2021-03-25 20:36:22 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 210/1251] eta: 0:09:06 lr: 0.000774 loss: 3.4758 (3.5061) grad_norm: 1.0916 (1.1499) time: 0.5116 [2021-03-25 20:36:27 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 220/1251] eta: 0:08:59 lr: 0.000774 loss: 3.5709 (3.5153) grad_norm: 1.1183 (1.1491) time: 0.5004 [2021-03-25 20:36:32 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 230/1251] eta: 0:08:53 lr: 0.000774 loss: 3.6850 (3.5108) grad_norm: 1.0967 (1.1454) time: 0.5021 [2021-03-25 20:36:37 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 240/1251] eta: 0:08:47 lr: 0.000774 loss: 3.4520 (3.5161) grad_norm: 1.0758 (1.1440) time: 0.5034 [2021-03-25 20:36:43 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 250/1251] eta: 0:08:42 lr: 0.000774 loss: 3.6160 (3.5235) grad_norm: 1.1212 (1.1463) time: 0.5069 [2021-03-25 20:36:48 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 260/1251] eta: 0:08:36 lr: 0.000774 loss: 3.4383 (3.5158) grad_norm: 1.1688 (1.1477) time: 0.5081 [2021-03-25 20:36:53 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 270/1251] eta: 0:08:30 lr: 0.000774 loss: 3.4589 (3.5223) grad_norm: 1.1527 (1.1475) time: 0.5018 [2021-03-25 20:36:58 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 280/1251] eta: 0:08:24 lr: 0.000774 loss: 3.7145 (3.5263) grad_norm: 1.1228 (1.1472) time: 0.5007 [2021-03-25 20:37:03 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 290/1251] eta: 0:08:18 lr: 0.000774 loss: 3.5946 (3.5254) grad_norm: 1.1058 (1.1470) time: 0.4967 [2021-03-25 20:37:07 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 300/1251] eta: 0:08:12 lr: 0.000774 loss: 3.6808 (3.5384) grad_norm: 1.1586 (1.1490) time: 0.4963 [2021-03-25 20:37:13 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 310/1251] eta: 0:08:06 lr: 0.000774 loss: 3.7838 (3.5387) grad_norm: 1.1586 (1.1491) time: 0.5024 [2021-03-25 20:37:18 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 320/1251] eta: 0:08:01 lr: 0.000773 loss: 3.4704 (3.5374) grad_norm: 1.1371 (1.1513) time: 0.5052 [2021-03-25 20:37:23 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 330/1251] eta: 0:07:55 lr: 0.000773 loss: 3.4704 (3.5336) grad_norm: 1.1139 (1.1501) time: 0.5052 [2021-03-25 20:37:28 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 340/1251] eta: 0:07:50 lr: 0.000773 loss: 3.7744 (3.5423) grad_norm: 1.0758 (1.1486) time: 0.5030 [2021-03-25 20:37:33 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 350/1251] eta: 0:07:44 lr: 0.000773 loss: 3.6966 (3.5367) grad_norm: 1.1422 (1.1494) time: 0.5009 [2021-03-25 20:37:38 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 360/1251] eta: 0:07:39 lr: 0.000773 loss: 3.5656 (3.5360) grad_norm: 1.1439 (1.1494) time: 0.5054 [2021-03-25 20:37:43 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 370/1251] eta: 0:07:34 lr: 0.000773 loss: 3.7376 (3.5388) grad_norm: 1.1512 (1.1501) time: 0.5105 [2021-03-25 20:37:48 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 380/1251] eta: 0:07:28 lr: 0.000773 loss: 3.4570 (3.5317) grad_norm: 1.1511 (1.1492) time: 0.5068 [2021-03-25 20:37:53 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 390/1251] eta: 0:07:23 lr: 0.000773 loss: 3.4203 (3.5309) grad_norm: 1.0334 (1.1464) time: 0.5002 [2021-03-25 20:37:58 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 400/1251] eta: 0:07:17 lr: 0.000773 loss: 3.4167 (3.5237) grad_norm: 1.0616 (1.1466) time: 0.5004 [2021-03-25 20:38:03 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 410/1251] eta: 0:07:12 lr: 0.000773 loss: 3.3534 (3.5263) grad_norm: 1.0915 (1.1452) time: 0.5002 [2021-03-25 20:38:08 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 420/1251] eta: 0:07:06 lr: 0.000773 loss: 3.3079 (3.5156) grad_norm: 1.1153 (1.1472) time: 0.4993 [2021-03-25 20:38:13 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 430/1251] eta: 0:07:01 lr: 0.000773 loss: 3.3079 (3.5144) grad_norm: 1.1153 (1.1449) time: 0.5024 [2021-03-25 20:38:18 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 440/1251] eta: 0:06:56 lr: 0.000773 loss: 3.5235 (3.5188) grad_norm: 1.0510 (1.1445) time: 0.5036 [2021-03-25 20:38:23 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 450/1251] eta: 0:06:50 lr: 0.000773 loss: 3.5235 (3.5117) grad_norm: 1.1178 (1.1442) time: 0.4998 [2021-03-25 20:38:28 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 460/1251] eta: 0:06:45 lr: 0.000773 loss: 3.6255 (3.5156) grad_norm: 1.1033 (1.1428) time: 0.5009 [2021-03-25 20:38:33 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 470/1251] eta: 0:06:40 lr: 0.000773 loss: 3.6915 (3.5137) grad_norm: 1.1033 (1.1432) time: 0.5056 [2021-03-25 20:38:38 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 480/1251] eta: 0:06:34 lr: 0.000773 loss: 3.6466 (3.5150) grad_norm: 1.1513 (1.1447) time: 0.5015 [2021-03-25 20:38:43 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 490/1251] eta: 0:06:29 lr: 0.000773 loss: 3.6082 (3.5151) grad_norm: 1.1513 (1.1447) time: 0.4973 [2021-03-25 20:38:48 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 500/1251] eta: 0:06:24 lr: 0.000773 loss: 3.5693 (3.5130) grad_norm: 1.0665 (1.1441) time: 0.4997 [2021-03-25 20:38:53 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 510/1251] eta: 0:06:19 lr: 0.000773 loss: 3.4709 (3.5123) grad_norm: 1.1303 (1.1447) time: 0.5037 [2021-03-25 20:38:58 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 520/1251] eta: 0:06:13 lr: 0.000773 loss: 3.4497 (3.5146) grad_norm: 1.1500 (1.1451) time: 0.5086 [2021-03-25 20:39:03 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 530/1251] eta: 0:06:08 lr: 0.000773 loss: 3.6143 (3.5135) grad_norm: 1.0999 (1.1446) time: 0.5055 [2021-03-25 20:39:08 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 540/1251] eta: 0:06:03 lr: 0.000773 loss: 3.6595 (3.5166) grad_norm: 1.0667 (1.1448) time: 0.5025 [2021-03-25 20:39:14 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 550/1251] eta: 0:05:58 lr: 0.000773 loss: 3.5712 (3.5187) grad_norm: 1.0905 (1.1443) time: 0.5226 [2021-03-25 20:39:19 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 560/1251] eta: 0:05:53 lr: 0.000773 loss: 3.4885 (3.5173) grad_norm: 1.1121 (1.1437) time: 0.5199 [2021-03-25 20:39:24 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 570/1251] eta: 0:05:48 lr: 0.000773 loss: 3.5810 (3.5184) grad_norm: 1.0984 (1.1429) time: 0.5129 [2021-03-25 20:39:29 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 580/1251] eta: 0:05:43 lr: 0.000773 loss: 3.6815 (3.5200) grad_norm: 1.0984 (1.1426) time: 0.5117 [2021-03-25 20:39:34 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 590/1251] eta: 0:05:38 lr: 0.000773 loss: 3.6910 (3.5190) grad_norm: 1.1275 (1.1425) time: 0.5021 [2021-03-25 20:39:39 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 600/1251] eta: 0:05:32 lr: 0.000773 loss: 3.2689 (3.5137) grad_norm: 1.1182 (1.1422) time: 0.5017 [2021-03-25 20:39:44 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 610/1251] eta: 0:05:27 lr: 0.000772 loss: 3.2892 (3.5111) grad_norm: 1.1015 (1.1421) time: 0.4970 [2021-03-25 20:39:49 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 620/1251] eta: 0:05:22 lr: 0.000772 loss: 3.6097 (3.5104) grad_norm: 1.0875 (1.1414) time: 0.5036 [2021-03-25 20:39:54 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 630/1251] eta: 0:05:17 lr: 0.000772 loss: 3.6797 (3.5100) grad_norm: 1.0847 (1.1404) time: 0.5088 [2021-03-25 20:39:59 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 640/1251] eta: 0:05:12 lr: 0.000772 loss: 3.7121 (3.5129) grad_norm: 1.1350 (1.1418) time: 0.5073 [2021-03-25 20:40:04 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 650/1251] eta: 0:05:07 lr: 0.000772 loss: 3.3785 (3.5109) grad_norm: 1.1350 (1.1408) time: 0.5087 [2021-03-25 20:40:09 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 660/1251] eta: 0:05:01 lr: 0.000772 loss: 3.5949 (3.5165) grad_norm: 1.0887 (1.1398) time: 0.5089 [2021-03-25 20:40:14 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 670/1251] eta: 0:04:56 lr: 0.000772 loss: 3.5949 (3.5149) grad_norm: 1.0826 (1.1394) time: 0.5063 [2021-03-25 20:40:19 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 680/1251] eta: 0:04:51 lr: 0.000772 loss: 3.3553 (3.5091) grad_norm: 1.0615 (1.1379) time: 0.5051 [2021-03-25 20:40:24 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 690/1251] eta: 0:04:46 lr: 0.000772 loss: 3.1816 (3.5050) grad_norm: 1.0476 (1.1374) time: 0.5036 [2021-03-25 20:40:29 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 700/1251] eta: 0:04:41 lr: 0.000772 loss: 3.5042 (3.5065) grad_norm: 1.0963 (1.1373) time: 0.5019 [2021-03-25 20:40:35 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 710/1251] eta: 0:04:36 lr: 0.000772 loss: 3.6133 (3.5055) grad_norm: 1.1156 (1.1374) time: 0.5014 [2021-03-25 20:40:40 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 720/1251] eta: 0:04:30 lr: 0.000772 loss: 3.5282 (3.5040) grad_norm: 1.1330 (1.1387) time: 0.5009 [2021-03-25 20:40:45 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 730/1251] eta: 0:04:25 lr: 0.000772 loss: 3.2141 (3.5003) grad_norm: 1.0811 (1.1378) time: 0.5009 [2021-03-25 20:40:50 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 740/1251] eta: 0:04:20 lr: 0.000772 loss: 3.5846 (3.4985) grad_norm: 1.0711 (1.1377) time: 0.5162 [2021-03-25 20:40:55 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 750/1251] eta: 0:04:15 lr: 0.000772 loss: 3.6308 (3.4981) grad_norm: 1.0711 (1.1369) time: 0.5309 [2021-03-25 20:41:00 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 760/1251] eta: 0:04:10 lr: 0.000772 loss: 3.4848 (3.4961) grad_norm: 1.1240 (1.1372) time: 0.5200 [2021-03-25 20:41:05 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 770/1251] eta: 0:04:05 lr: 0.000772 loss: 3.5707 (3.4975) grad_norm: 1.1240 (1.1371) time: 0.5016 [2021-03-25 20:41:10 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 780/1251] eta: 0:04:00 lr: 0.000772 loss: 3.6682 (3.4995) grad_norm: 1.1013 (1.1369) time: 0.5010 [2021-03-25 20:41:15 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 790/1251] eta: 0:03:55 lr: 0.000772 loss: 3.7548 (3.5001) grad_norm: 1.1013 (1.1364) time: 0.5031 [2021-03-25 20:41:20 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 800/1251] eta: 0:03:50 lr: 0.000772 loss: 3.6545 (3.5016) grad_norm: 1.0579 (1.1354) time: 0.5058 [2021-03-25 20:41:26 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 810/1251] eta: 0:03:45 lr: 0.000772 loss: 3.6392 (3.5013) grad_norm: 1.0603 (1.1372) time: 0.5117 [2021-03-25 20:41:31 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 820/1251] eta: 0:03:39 lr: 0.000772 loss: 3.4047 (3.5007) grad_norm: 1.2713 (1.1381) time: 0.5113 [2021-03-25 20:41:36 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 830/1251] eta: 0:03:34 lr: 0.000772 loss: 3.5994 (3.5027) grad_norm: 1.2141 (1.1380) time: 0.5090 [2021-03-25 20:41:41 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 840/1251] eta: 0:03:29 lr: 0.000772 loss: 3.6799 (3.5041) grad_norm: 1.1221 (1.1381) time: 0.5040 [2021-03-25 20:41:46 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 850/1251] eta: 0:03:24 lr: 0.000772 loss: 3.6799 (3.5035) grad_norm: 1.1127 (1.1375) time: 0.5057 [2021-03-25 20:41:51 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 860/1251] eta: 0:03:19 lr: 0.000772 loss: 3.6871 (3.5059) grad_norm: 1.1127 (1.1378) time: 0.5075 [2021-03-25 20:41:56 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 870/1251] eta: 0:03:14 lr: 0.000772 loss: 3.6336 (3.5049) grad_norm: 1.1570 (1.1381) time: 0.5033 [2021-03-25 20:42:01 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 880/1251] eta: 0:03:09 lr: 0.000772 loss: 3.4619 (3.5051) grad_norm: 1.1532 (1.1379) time: 0.4981 [2021-03-25 20:42:06 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 890/1251] eta: 0:03:04 lr: 0.000771 loss: 3.3591 (3.5018) grad_norm: 1.1254 (1.1385) time: 0.4998 [2021-03-25 20:42:11 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 900/1251] eta: 0:02:58 lr: 0.000771 loss: 3.4526 (3.5049) grad_norm: 1.0954 (1.1381) time: 0.5014 [2021-03-25 20:42:16 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 910/1251] eta: 0:02:53 lr: 0.000771 loss: 3.6850 (3.5060) grad_norm: 1.0871 (1.1385) time: 0.4992 [2021-03-25 20:42:21 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 920/1251] eta: 0:02:48 lr: 0.000771 loss: 3.5683 (3.5066) grad_norm: 1.1622 (1.1388) time: 0.4982 [2021-03-25 20:42:26 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 930/1251] eta: 0:02:43 lr: 0.000771 loss: 3.5827 (3.5087) grad_norm: 1.1216 (1.1385) time: 0.5001 [2021-03-25 20:42:31 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 940/1251] eta: 0:02:38 lr: 0.000771 loss: 3.8775 (3.5112) grad_norm: 1.0965 (1.1383) time: 0.5100 [2021-03-25 20:42:36 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 950/1251] eta: 0:02:33 lr: 0.000771 loss: 3.6684 (3.5103) grad_norm: 1.1504 (1.1387) time: 0.5105 [2021-03-25 20:42:41 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 960/1251] eta: 0:02:28 lr: 0.000771 loss: 3.3516 (3.5106) grad_norm: 1.1530 (1.1387) time: 0.5040 [2021-03-25 20:42:46 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 970/1251] eta: 0:02:23 lr: 0.000771 loss: 3.4365 (3.5099) grad_norm: 1.1795 (1.1393) time: 0.5041 [2021-03-25 20:42:51 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 980/1251] eta: 0:02:17 lr: 0.000771 loss: 3.4160 (3.5068) grad_norm: 1.2375 (1.1401) time: 0.5043 [2021-03-25 20:42:56 swin_small_patch4_window7_224] INFO: Epoch: [95] [ 990/1251] eta: 0:02:12 lr: 0.000771 loss: 3.1953 (3.5054) grad_norm: 1.1186 (1.1399) time: 0.5047 [2021-03-25 20:43:01 swin_small_patch4_window7_224] INFO: Epoch: [95] [1000/1251] eta: 0:02:07 lr: 0.000771 loss: 3.1211 (3.5035) grad_norm: 1.0756 (1.1398) time: 0.5024 [2021-03-25 20:43:06 swin_small_patch4_window7_224] INFO: Epoch: [95] [1010/1251] eta: 0:02:02 lr: 0.000771 loss: 3.7135 (3.5048) grad_norm: 1.0855 (1.1400) time: 0.4997 [2021-03-25 20:43:11 swin_small_patch4_window7_224] INFO: Epoch: [95] [1020/1251] eta: 0:01:57 lr: 0.000771 loss: 3.7135 (3.5045) grad_norm: 1.1048 (1.1399) time: 0.5057 [2021-03-25 20:43:16 swin_small_patch4_window7_224] INFO: Epoch: [95] [1030/1251] eta: 0:01:52 lr: 0.000771 loss: 3.6204 (3.5053) grad_norm: 1.1096 (1.1397) time: 0.5081 [2021-03-25 20:43:21 swin_small_patch4_window7_224] INFO: Epoch: [95] [1040/1251] eta: 0:01:47 lr: 0.000771 loss: 3.6666 (3.5067) grad_norm: 1.1219 (1.1398) time: 0.5060 [2021-03-25 20:43:27 swin_small_patch4_window7_224] INFO: Epoch: [95] [1050/1251] eta: 0:01:42 lr: 0.000771 loss: 3.4588 (3.5066) grad_norm: 1.1508 (1.1401) time: 0.5081 [2021-03-25 20:43:32 swin_small_patch4_window7_224] INFO: Epoch: [95] [1060/1251] eta: 0:01:37 lr: 0.000771 loss: 3.6310 (3.5086) grad_norm: 1.1471 (1.1396) time: 0.5063 [2021-03-25 20:43:37 swin_small_patch4_window7_224] INFO: Epoch: [95] [1070/1251] eta: 0:01:32 lr: 0.000771 loss: 3.6961 (3.5087) grad_norm: 1.0577 (1.1393) time: 0.5069 [2021-03-25 20:43:42 swin_small_patch4_window7_224] INFO: Epoch: [95] [1080/1251] eta: 0:01:27 lr: 0.000771 loss: 3.4817 (3.5075) grad_norm: 1.0715 (1.1392) time: 0.5068 [2021-03-25 20:43:47 swin_small_patch4_window7_224] INFO: Epoch: [95] [1090/1251] eta: 0:01:21 lr: 0.000771 loss: 3.4329 (3.5071) grad_norm: 1.1386 (1.1397) time: 0.5028 [2021-03-25 20:43:52 swin_small_patch4_window7_224] INFO: Epoch: [95] [1100/1251] eta: 0:01:16 lr: 0.000771 loss: 3.6403 (3.5083) grad_norm: 1.2322 (1.1410) time: 0.5074 [2021-03-25 20:43:57 swin_small_patch4_window7_224] INFO: Epoch: [95] [1110/1251] eta: 0:01:11 lr: 0.000771 loss: 3.6403 (3.5071) grad_norm: 1.2174 (1.1412) time: 0.5113 [2021-03-25 20:44:02 swin_small_patch4_window7_224] INFO: Epoch: [95] [1120/1251] eta: 0:01:06 lr: 0.000771 loss: 3.3007 (3.5059) grad_norm: 1.1413 (1.1412) time: 0.5104 [2021-03-25 20:44:07 swin_small_patch4_window7_224] INFO: Epoch: [95] [1130/1251] eta: 0:01:01 lr: 0.000771 loss: 3.7108 (3.5075) grad_norm: 1.1331 (1.1415) time: 0.5060 [2021-03-25 20:44:12 swin_small_patch4_window7_224] INFO: Epoch: [95] [1140/1251] eta: 0:00:56 lr: 0.000771 loss: 3.7748 (3.5102) grad_norm: 1.1501 (1.1422) time: 0.5054 [2021-03-25 20:44:17 swin_small_patch4_window7_224] INFO: Epoch: [95] [1150/1251] eta: 0:00:51 lr: 0.000771 loss: 3.5739 (3.5085) grad_norm: 1.1937 (1.1432) time: 0.5016 [2021-03-25 20:44:22 swin_small_patch4_window7_224] INFO: Epoch: [95] [1160/1251] eta: 0:00:46 lr: 0.000771 loss: 3.2277 (3.5065) grad_norm: 1.1287 (1.1429) time: 0.4966 [2021-03-25 20:44:27 swin_small_patch4_window7_224] INFO: Epoch: [95] [1170/1251] eta: 0:00:41 lr: 0.000771 loss: 3.4400 (3.5073) grad_norm: 1.1143 (1.1434) time: 0.5017 [2021-03-25 20:44:32 swin_small_patch4_window7_224] INFO: Epoch: [95] [1180/1251] eta: 0:00:36 lr: 0.000770 loss: 3.6741 (3.5068) grad_norm: 1.1231 (1.1434) time: 0.5032 [2021-03-25 20:44:37 swin_small_patch4_window7_224] INFO: Epoch: [95] [1190/1251] eta: 0:00:31 lr: 0.000770 loss: 3.6303 (3.5063) grad_norm: 1.1103 (1.1429) time: 0.5006 [2021-03-25 20:44:42 swin_small_patch4_window7_224] INFO: Epoch: [95] [1200/1251] eta: 0:00:25 lr: 0.000770 loss: 3.6749 (3.5081) grad_norm: 1.0638 (1.1429) time: 0.5033 [2021-03-25 20:44:47 swin_small_patch4_window7_224] INFO: Epoch: [95] [1210/1251] eta: 0:00:20 lr: 0.000770 loss: 3.7145 (3.5083) grad_norm: 1.1661 (1.1429) time: 0.5075 [2021-03-25 20:44:52 swin_small_patch4_window7_224] INFO: Epoch: [95] [1220/1251] eta: 0:00:15 lr: 0.000770 loss: 3.5928 (3.5083) grad_norm: 1.0916 (1.1427) time: 0.5041 [2021-03-25 20:44:57 swin_small_patch4_window7_224] INFO: Epoch: [95] [1230/1251] eta: 0:00:10 lr: 0.000770 loss: 3.6289 (3.5093) grad_norm: 1.0868 (1.1423) time: 0.5037 [2021-03-25 20:45:03 swin_small_patch4_window7_224] INFO: Epoch: [95] [1240/1251] eta: 0:00:05 lr: 0.000770 loss: 3.6559 (3.5095) grad_norm: 1.1068 (1.1423) time: 0.5080 [2021-03-25 20:45:08 swin_small_patch4_window7_224] INFO: Epoch: [95] [1250/1251] eta: 0:00:00 lr: 0.000770 loss: 3.4772 (3.5086) grad_norm: 1.1459 (1.1429) time: 0.5086 [2021-03-25 20:45:59 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 1.0800 (1.0800) acc1: 78.1250 (78.1250) acc5: 92.1875 (92.1875) [2021-03-25 20:46:01 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.0157 (1.0713) acc1: 78.1250 (74.7159) acc5: 92.1875 (91.6193) [2021-03-25 20:46:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.0099 (1.0673) acc1: 75.0000 (74.0327) acc5: 92.1875 (92.4851) [2021-03-25 20:46:03 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9834 (1.0414) acc1: 75.0000 (75.0504) acc5: 93.7500 (92.8427) [2021-03-25 20:46:04 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9494 (1.0571) acc1: 76.5625 (74.7713) acc5: 93.7500 (92.7973) [2021-03-25 20:46:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9937 (1.0362) acc1: 76.5625 (75.3600) acc5: 93.7500 (93.3120) [2021-03-25 20:46:12 swin_small_patch4_window7_224] INFO: * Acc@1 75.848 Acc@5 93.260 loss 1.020 [2021-03-25 20:46:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-25 20:46:12 swin_small_patch4_window7_224] INFO: Max accuracy: 76.03% [2021-03-25 20:46:17 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 0/1251] eta: 1:34:19 lr: 0.000770 loss: 4.1155 (4.1155) grad_norm: 1.3297 (1.3297) time: 4.5242 [2021-03-25 20:46:22 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 10/1251] eta: 0:18:29 lr: 0.000770 loss: 3.5371 (3.4731) grad_norm: 1.2090 (1.2518) time: 0.8938 [2021-03-25 20:46:27 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 20/1251] eta: 0:14:32 lr: 0.000770 loss: 3.4041 (3.4449) grad_norm: 1.1723 (1.2182) time: 0.5183 [2021-03-25 20:46:32 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 30/1251] eta: 0:13:05 lr: 0.000770 loss: 3.6523 (3.5254) grad_norm: 1.1276 (1.1843) time: 0.5051 [2021-03-25 20:46:37 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 40/1251] eta: 0:12:21 lr: 0.000770 loss: 3.3060 (3.3991) grad_norm: 1.0762 (inf) time: 0.5108 [2021-03-25 20:46:42 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 50/1251] eta: 0:11:53 lr: 0.000770 loss: 2.8667 (3.3353) grad_norm: 1.0976 (inf) time: 0.5186 [2021-03-25 20:46:47 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 60/1251] eta: 0:11:30 lr: 0.000770 loss: 3.3439 (3.3872) grad_norm: 1.1201 (inf) time: 0.5137 [2021-03-25 20:46:53 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 70/1251] eta: 0:11:13 lr: 0.000770 loss: 3.6687 (3.3752) grad_norm: 1.1315 (inf) time: 0.5092 [2021-03-25 20:46:58 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 80/1251] eta: 0:10:59 lr: 0.000770 loss: 3.5752 (3.3897) grad_norm: 1.1074 (inf) time: 0.5103 [2021-03-25 20:47:03 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 90/1251] eta: 0:10:46 lr: 0.000770 loss: 3.7151 (3.4231) grad_norm: 1.0854 (inf) time: 0.5081 [2021-03-25 20:47:08 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 100/1251] eta: 0:10:34 lr: 0.000770 loss: 3.4934 (3.4135) grad_norm: 1.1337 (inf) time: 0.5054 [2021-03-25 20:47:13 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 110/1251] eta: 0:10:23 lr: 0.000770 loss: 3.4934 (3.4252) grad_norm: 1.1351 (inf) time: 0.5024 [2021-03-25 20:47:18 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 120/1251] eta: 0:10:14 lr: 0.000770 loss: 3.7027 (3.4609) grad_norm: 1.1351 (inf) time: 0.5024 [2021-03-25 20:47:23 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 130/1251] eta: 0:10:07 lr: 0.000770 loss: 3.7795 (3.4695) grad_norm: 1.1185 (inf) time: 0.5126 [2021-03-25 20:47:28 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 140/1251] eta: 0:09:58 lr: 0.000770 loss: 3.5891 (3.4612) grad_norm: 1.1591 (inf) time: 0.5124 [2021-03-25 20:47:33 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 150/1251] eta: 0:09:51 lr: 0.000770 loss: 3.5891 (3.4672) grad_norm: 1.1347 (inf) time: 0.5089 [2021-03-25 20:47:38 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 160/1251] eta: 0:09:43 lr: 0.000770 loss: 3.6098 (3.4629) grad_norm: 1.1335 (inf) time: 0.5033 [2021-03-25 20:47:43 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 170/1251] eta: 0:09:35 lr: 0.000770 loss: 3.6317 (3.4777) grad_norm: 1.1603 (inf) time: 0.4986 [2021-03-25 20:47:48 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 180/1251] eta: 0:09:28 lr: 0.000770 loss: 3.7239 (3.4857) grad_norm: 1.1392 (inf) time: 0.5031 [2021-03-25 20:47:53 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 190/1251] eta: 0:09:21 lr: 0.000770 loss: 3.7081 (3.4850) grad_norm: 1.1384 (inf) time: 0.5023 [2021-03-25 20:47:58 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 200/1251] eta: 0:09:15 lr: 0.000770 loss: 3.6620 (3.4827) grad_norm: 1.1826 (inf) time: 0.5090 [2021-03-25 20:48:03 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 210/1251] eta: 0:09:09 lr: 0.000769 loss: 3.7453 (3.5009) grad_norm: 1.1242 (inf) time: 0.5066 [2021-03-25 20:48:08 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 220/1251] eta: 0:09:02 lr: 0.000769 loss: 3.4712 (3.4803) grad_norm: 1.1905 (inf) time: 0.4979 [2021-03-25 20:48:14 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 230/1251] eta: 0:08:57 lr: 0.000769 loss: 3.1679 (3.4737) grad_norm: 1.1411 (inf) time: 0.5143 [2021-03-25 20:48:19 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 240/1251] eta: 0:08:51 lr: 0.000769 loss: 3.2163 (3.4711) grad_norm: 1.0934 (inf) time: 0.5192 [2021-03-25 20:48:24 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 250/1251] eta: 0:08:44 lr: 0.000769 loss: 3.1954 (3.4648) grad_norm: 1.0801 (inf) time: 0.5026 [2021-03-25 20:48:29 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 260/1251] eta: 0:08:38 lr: 0.000769 loss: 3.5124 (3.4724) grad_norm: 1.0746 (inf) time: 0.4999 [2021-03-25 20:48:34 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 270/1251] eta: 0:08:32 lr: 0.000769 loss: 3.5796 (3.4754) grad_norm: 1.0607 (inf) time: 0.4996 [2021-03-25 20:48:39 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 280/1251] eta: 0:08:26 lr: 0.000769 loss: 3.3961 (3.4678) grad_norm: 1.0772 (inf) time: 0.4965 [2021-03-25 20:48:44 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 290/1251] eta: 0:08:20 lr: 0.000769 loss: 3.3774 (3.4702) grad_norm: 1.1257 (inf) time: 0.5001 [2021-03-25 20:48:49 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 300/1251] eta: 0:08:14 lr: 0.000769 loss: 3.3774 (3.4685) grad_norm: 1.1449 (inf) time: 0.4988 [2021-03-25 20:48:54 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 310/1251] eta: 0:08:08 lr: 0.000769 loss: 3.3697 (3.4668) grad_norm: 1.1283 (inf) time: 0.4996 [2021-03-25 20:48:59 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 320/1251] eta: 0:08:03 lr: 0.000769 loss: 3.6057 (3.4724) grad_norm: 1.1577 (inf) time: 0.5073 [2021-03-25 20:49:04 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 330/1251] eta: 0:07:57 lr: 0.000769 loss: 3.7187 (3.4764) grad_norm: 1.1586 (inf) time: 0.5084 [2021-03-25 20:49:09 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 340/1251] eta: 0:07:52 lr: 0.000769 loss: 3.6644 (3.4803) grad_norm: 1.0942 (inf) time: 0.5085 [2021-03-25 20:49:14 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 350/1251] eta: 0:07:47 lr: 0.000769 loss: 3.4888 (3.4782) grad_norm: 1.1012 (inf) time: 0.5088 [2021-03-25 20:49:19 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 360/1251] eta: 0:07:41 lr: 0.000769 loss: 3.5265 (3.4813) grad_norm: 1.0938 (inf) time: 0.5007 [2021-03-25 20:49:24 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 370/1251] eta: 0:07:35 lr: 0.000769 loss: 3.5780 (3.4835) grad_norm: 1.0362 (inf) time: 0.5021 [2021-03-25 20:49:29 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 380/1251] eta: 0:07:30 lr: 0.000769 loss: 3.5735 (3.4866) grad_norm: 1.0906 (inf) time: 0.5077 [2021-03-25 20:49:34 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 390/1251] eta: 0:07:25 lr: 0.000769 loss: 3.6004 (3.4880) grad_norm: 1.0994 (inf) time: 0.5064 [2021-03-25 20:49:39 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 400/1251] eta: 0:07:19 lr: 0.000769 loss: 3.4717 (3.4827) grad_norm: 1.1225 (inf) time: 0.5116 [2021-03-25 20:49:44 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 410/1251] eta: 0:07:14 lr: 0.000769 loss: 3.3752 (3.4838) grad_norm: 1.0964 (inf) time: 0.5089 [2021-03-25 20:49:49 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 420/1251] eta: 0:07:08 lr: 0.000769 loss: 3.4794 (3.4842) grad_norm: 1.0776 (inf) time: 0.5012 [2021-03-25 20:49:54 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 430/1251] eta: 0:07:03 lr: 0.000769 loss: 3.4854 (3.4838) grad_norm: 1.1298 (inf) time: 0.5060 [2021-03-25 20:49:59 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 440/1251] eta: 0:06:58 lr: 0.000769 loss: 3.5085 (3.4846) grad_norm: 1.1449 (inf) time: 0.5057 [2021-03-25 20:50:04 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 450/1251] eta: 0:06:52 lr: 0.000769 loss: 3.6335 (3.4860) grad_norm: 1.1449 (inf) time: 0.5000 [2021-03-25 20:50:09 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 460/1251] eta: 0:06:47 lr: 0.000769 loss: 3.3398 (3.4790) grad_norm: 1.1498 (inf) time: 0.4992 [2021-03-25 20:50:14 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 470/1251] eta: 0:06:41 lr: 0.000769 loss: 3.2918 (3.4728) grad_norm: 1.1530 (inf) time: 0.5002 [2021-03-25 20:50:20 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 480/1251] eta: 0:06:36 lr: 0.000769 loss: 3.2950 (3.4710) grad_norm: 1.1600 (inf) time: 0.5052 [2021-03-25 20:50:25 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 490/1251] eta: 0:06:31 lr: 0.000769 loss: 3.2950 (3.4682) grad_norm: 1.1552 (inf) time: 0.5058 [2021-03-25 20:50:30 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 500/1251] eta: 0:06:25 lr: 0.000768 loss: 3.5000 (3.4702) grad_norm: 1.0994 (inf) time: 0.4995 [2021-03-25 20:50:35 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 510/1251] eta: 0:06:20 lr: 0.000768 loss: 3.6599 (3.4732) grad_norm: 1.1217 (inf) time: 0.4969 [2021-03-25 20:50:40 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 520/1251] eta: 0:06:15 lr: 0.000768 loss: 3.5223 (3.4707) grad_norm: 1.1139 (inf) time: 0.5054 [2021-03-25 20:50:45 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 530/1251] eta: 0:06:10 lr: 0.000768 loss: 3.5223 (3.4738) grad_norm: 1.1046 (inf) time: 0.5089 [2021-03-25 20:50:50 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 540/1251] eta: 0:06:04 lr: 0.000768 loss: 3.6997 (3.4766) grad_norm: 1.1254 (inf) time: 0.5068 [2021-03-25 20:50:55 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 550/1251] eta: 0:05:59 lr: 0.000768 loss: 3.7125 (3.4823) grad_norm: 1.1250 (inf) time: 0.5149 [2021-03-25 20:51:00 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 560/1251] eta: 0:05:54 lr: 0.000768 loss: 3.7945 (3.4865) grad_norm: 1.0545 (inf) time: 0.5226 [2021-03-25 20:51:05 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 570/1251] eta: 0:05:49 lr: 0.000768 loss: 3.6522 (3.4880) grad_norm: 1.0591 (inf) time: 0.5131 [2021-03-25 20:51:10 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 580/1251] eta: 0:05:44 lr: 0.000768 loss: 3.5677 (3.4852) grad_norm: 1.0663 (inf) time: 0.5060 [2021-03-25 20:51:15 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 590/1251] eta: 0:05:39 lr: 0.000768 loss: 3.5790 (3.4910) grad_norm: 1.1221 (inf) time: 0.5070 [2021-03-25 20:51:20 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 600/1251] eta: 0:05:33 lr: 0.000768 loss: 3.7494 (3.4933) grad_norm: 1.1383 (inf) time: 0.5010 [2021-03-25 20:51:25 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 610/1251] eta: 0:05:28 lr: 0.000768 loss: 3.7263 (3.4950) grad_norm: 1.1280 (inf) time: 0.4979 [2021-03-25 20:51:31 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 620/1251] eta: 0:05:23 lr: 0.000768 loss: 3.7508 (3.4996) grad_norm: 1.1026 (inf) time: 0.5066 [2021-03-25 20:51:36 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 630/1251] eta: 0:05:18 lr: 0.000768 loss: 3.7528 (3.4990) grad_norm: 1.1265 (inf) time: 0.5094 [2021-03-25 20:51:41 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 640/1251] eta: 0:05:13 lr: 0.000768 loss: 3.4606 (3.4977) grad_norm: 1.1177 (inf) time: 0.5050 [2021-03-25 20:51:46 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 650/1251] eta: 0:05:07 lr: 0.000768 loss: 3.6239 (3.5027) grad_norm: 1.1288 (inf) time: 0.5053 [2021-03-25 20:51:51 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 660/1251] eta: 0:05:02 lr: 0.000768 loss: 3.6239 (3.5018) grad_norm: 1.2113 (inf) time: 0.4992 [2021-03-25 20:51:56 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 670/1251] eta: 0:04:57 lr: 0.000768 loss: 3.4835 (3.5036) grad_norm: 1.1743 (inf) time: 0.4955 [2021-03-25 20:52:01 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 680/1251] eta: 0:04:52 lr: 0.000768 loss: 3.3963 (3.5027) grad_norm: 1.0980 (inf) time: 0.4956 [2021-03-25 20:52:06 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 690/1251] eta: 0:04:46 lr: 0.000768 loss: 3.1883 (3.4988) grad_norm: 1.1349 (inf) time: 0.4992 [2021-03-25 20:52:11 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 700/1251] eta: 0:04:41 lr: 0.000768 loss: 3.4457 (3.4982) grad_norm: 1.1611 (inf) time: 0.5035 [2021-03-25 20:52:16 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 710/1251] eta: 0:04:36 lr: 0.000768 loss: 3.5555 (3.4997) grad_norm: 1.1381 (inf) time: 0.5036 [2021-03-25 20:52:21 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 720/1251] eta: 0:04:31 lr: 0.000768 loss: 3.5555 (3.5010) grad_norm: 1.0955 (inf) time: 0.5049 [2021-03-25 20:52:26 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 730/1251] eta: 0:04:26 lr: 0.000768 loss: 3.4659 (3.5007) grad_norm: 1.1032 (inf) time: 0.5026 [2021-03-25 20:52:31 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 740/1251] eta: 0:04:21 lr: 0.000768 loss: 3.4659 (3.4992) grad_norm: 1.1099 (inf) time: 0.5154 [2021-03-25 20:52:36 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 750/1251] eta: 0:04:16 lr: 0.000768 loss: 3.5521 (3.5007) grad_norm: 1.1099 (inf) time: 0.5262 [2021-03-25 20:52:41 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 760/1251] eta: 0:04:11 lr: 0.000768 loss: 3.7128 (3.5036) grad_norm: 1.1331 (inf) time: 0.5103 [2021-03-25 20:52:46 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 770/1251] eta: 0:04:05 lr: 0.000768 loss: 3.7019 (3.5050) grad_norm: 1.0677 (inf) time: 0.4952 [2021-03-25 20:52:51 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 780/1251] eta: 0:04:00 lr: 0.000767 loss: 3.6665 (3.5069) grad_norm: 1.0943 (inf) time: 0.5039 [2021-03-25 20:52:56 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 790/1251] eta: 0:03:55 lr: 0.000767 loss: 3.6623 (3.5078) grad_norm: 1.1167 (inf) time: 0.5131 [2021-03-25 20:53:01 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 800/1251] eta: 0:03:50 lr: 0.000767 loss: 3.5186 (3.5086) grad_norm: 1.1167 (inf) time: 0.5059 [2021-03-25 20:53:06 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 810/1251] eta: 0:03:45 lr: 0.000767 loss: 3.7164 (3.5094) grad_norm: 1.0876 (inf) time: 0.5005 [2021-03-25 20:53:12 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 820/1251] eta: 0:03:40 lr: 0.000767 loss: 3.4003 (3.5074) grad_norm: 1.0876 (inf) time: 0.5030 [2021-03-25 20:53:17 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 830/1251] eta: 0:03:34 lr: 0.000767 loss: 3.4938 (3.5066) grad_norm: 1.0827 (inf) time: 0.5032 [2021-03-25 20:53:22 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 840/1251] eta: 0:03:29 lr: 0.000767 loss: 3.6472 (3.5103) grad_norm: 1.1251 (inf) time: 0.4998 [2021-03-25 20:53:27 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 850/1251] eta: 0:03:24 lr: 0.000767 loss: 3.8120 (3.5100) grad_norm: 1.1789 (inf) time: 0.5027 [2021-03-25 20:53:32 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 860/1251] eta: 0:03:19 lr: 0.000767 loss: 3.5810 (3.5097) grad_norm: 1.1521 (inf) time: 0.5090 [2021-03-25 20:53:37 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 870/1251] eta: 0:03:14 lr: 0.000767 loss: 3.5083 (3.5082) grad_norm: 1.1168 (inf) time: 0.5126 [2021-03-25 20:53:42 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 880/1251] eta: 0:03:09 lr: 0.000767 loss: 3.3661 (3.5072) grad_norm: 1.0873 (inf) time: 0.5088 [2021-03-25 20:53:47 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 890/1251] eta: 0:03:04 lr: 0.000767 loss: 3.4814 (3.5070) grad_norm: 1.0873 (inf) time: 0.5040 [2021-03-25 20:53:52 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 900/1251] eta: 0:02:59 lr: 0.000767 loss: 3.6848 (3.5109) grad_norm: 1.1110 (inf) time: 0.5025 [2021-03-25 20:53:57 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 910/1251] eta: 0:02:53 lr: 0.000767 loss: 3.6384 (3.5067) grad_norm: 1.1574 (inf) time: 0.5020 [2021-03-25 20:54:02 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 920/1251] eta: 0:02:48 lr: 0.000767 loss: 3.3405 (3.5067) grad_norm: 1.1508 (inf) time: 0.5007 [2021-03-25 20:54:07 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 930/1251] eta: 0:02:43 lr: 0.000767 loss: 3.6297 (3.5053) grad_norm: 1.0880 (inf) time: 0.5028 [2021-03-25 20:54:12 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 940/1251] eta: 0:02:38 lr: 0.000767 loss: 3.6119 (3.5063) grad_norm: 1.0794 (inf) time: 0.5062 [2021-03-25 20:54:17 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 950/1251] eta: 0:02:33 lr: 0.000767 loss: 3.4404 (3.5047) grad_norm: 1.1255 (inf) time: 0.4997 [2021-03-25 20:54:22 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 960/1251] eta: 0:02:28 lr: 0.000767 loss: 3.4365 (3.5065) grad_norm: 1.1639 (inf) time: 0.4934 [2021-03-25 20:54:27 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 970/1251] eta: 0:02:23 lr: 0.000767 loss: 3.6295 (3.5060) grad_norm: 1.1828 (inf) time: 0.5086 [2021-03-25 20:54:32 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 980/1251] eta: 0:02:18 lr: 0.000767 loss: 3.6812 (3.5090) grad_norm: 1.1336 (inf) time: 0.5188 [2021-03-25 20:54:37 swin_small_patch4_window7_224] INFO: Epoch: [96] [ 990/1251] eta: 0:02:13 lr: 0.000767 loss: 3.7584 (3.5080) grad_norm: 1.1326 (inf) time: 0.5078 [2021-03-25 20:54:42 swin_small_patch4_window7_224] INFO: Epoch: [96] [1000/1251] eta: 0:02:07 lr: 0.000767 loss: 3.4783 (3.5077) grad_norm: 1.1036 (inf) time: 0.5022 [2021-03-25 20:54:47 swin_small_patch4_window7_224] INFO: Epoch: [96] [1010/1251] eta: 0:02:02 lr: 0.000767 loss: 3.4774 (3.5078) grad_norm: 1.1036 (inf) time: 0.5022 [2021-03-25 20:54:52 swin_small_patch4_window7_224] INFO: Epoch: [96] [1020/1251] eta: 0:01:57 lr: 0.000767 loss: 3.5544 (3.5084) grad_norm: 1.1223 (inf) time: 0.5033 [2021-03-25 20:54:57 swin_small_patch4_window7_224] INFO: Epoch: [96] [1030/1251] eta: 0:01:52 lr: 0.000767 loss: 3.6470 (3.5095) grad_norm: 1.1317 (inf) time: 0.5044 [2021-03-25 20:55:02 swin_small_patch4_window7_224] INFO: Epoch: [96] [1040/1251] eta: 0:01:47 lr: 0.000767 loss: 3.4452 (3.5069) grad_norm: 1.1175 (inf) time: 0.5000 [2021-03-25 20:55:07 swin_small_patch4_window7_224] INFO: Epoch: [96] [1050/1251] eta: 0:01:42 lr: 0.000767 loss: 3.2620 (3.5048) grad_norm: 1.1184 (inf) time: 0.4967 [2021-03-25 20:55:13 swin_small_patch4_window7_224] INFO: Epoch: [96] [1060/1251] eta: 0:01:37 lr: 0.000767 loss: 3.5095 (3.5054) grad_norm: 1.1886 (inf) time: 0.5034 [2021-03-25 20:55:18 swin_small_patch4_window7_224] INFO: Epoch: [96] [1070/1251] eta: 0:01:32 lr: 0.000766 loss: 3.7919 (3.5081) grad_norm: 1.1911 (inf) time: 0.5086 [2021-03-25 20:55:23 swin_small_patch4_window7_224] INFO: Epoch: [96] [1080/1251] eta: 0:01:27 lr: 0.000766 loss: 3.7769 (3.5109) grad_norm: 1.1601 (inf) time: 0.5032 [2021-03-25 20:55:28 swin_small_patch4_window7_224] INFO: Epoch: [96] [1090/1251] eta: 0:01:21 lr: 0.000766 loss: 3.7638 (3.5110) grad_norm: 1.1324 (inf) time: 0.4992 [2021-03-25 20:55:33 swin_small_patch4_window7_224] INFO: Epoch: [96] [1100/1251] eta: 0:01:16 lr: 0.000766 loss: 3.5580 (3.5110) grad_norm: 1.0956 (inf) time: 0.5006 [2021-03-25 20:55:38 swin_small_patch4_window7_224] INFO: Epoch: [96] [1110/1251] eta: 0:01:11 lr: 0.000766 loss: 3.7516 (3.5130) grad_norm: 1.1496 (inf) time: 0.4987 [2021-03-25 20:55:43 swin_small_patch4_window7_224] INFO: Epoch: [96] [1120/1251] eta: 0:01:06 lr: 0.000766 loss: 3.6095 (3.5124) grad_norm: 1.1628 (inf) time: 0.5021 [2021-03-25 20:55:48 swin_small_patch4_window7_224] INFO: Epoch: [96] [1130/1251] eta: 0:01:01 lr: 0.000766 loss: 3.5019 (3.5115) grad_norm: 1.1125 (inf) time: 0.5013 [2021-03-25 20:55:53 swin_small_patch4_window7_224] INFO: Epoch: [96] [1140/1251] eta: 0:00:56 lr: 0.000766 loss: 3.7131 (3.5133) grad_norm: 1.1093 (inf) time: 0.5022 [2021-03-25 20:55:58 swin_small_patch4_window7_224] INFO: Epoch: [96] [1150/1251] eta: 0:00:51 lr: 0.000766 loss: 3.7552 (3.5138) grad_norm: 1.1655 (inf) time: 0.5065 [2021-03-25 20:56:03 swin_small_patch4_window7_224] INFO: Epoch: [96] [1160/1251] eta: 0:00:46 lr: 0.000766 loss: 3.5881 (3.5135) grad_norm: 1.1731 (inf) time: 0.5030 [2021-03-25 20:56:08 swin_small_patch4_window7_224] INFO: Epoch: [96] [1170/1251] eta: 0:00:41 lr: 0.000766 loss: 3.4657 (3.5116) grad_norm: 1.1428 (inf) time: 0.5080 [2021-03-25 20:56:13 swin_small_patch4_window7_224] INFO: Epoch: [96] [1180/1251] eta: 0:00:36 lr: 0.000766 loss: 3.4926 (3.5120) grad_norm: 1.0971 (inf) time: 0.5088 [2021-03-25 20:56:18 swin_small_patch4_window7_224] INFO: Epoch: [96] [1190/1251] eta: 0:00:31 lr: 0.000766 loss: 3.5424 (3.5131) grad_norm: 1.0694 (inf) time: 0.5052 [2021-03-25 20:56:23 swin_small_patch4_window7_224] INFO: Epoch: [96] [1200/1251] eta: 0:00:25 lr: 0.000766 loss: 3.7235 (3.5141) grad_norm: 1.1298 (inf) time: 0.5033 [2021-03-25 20:56:28 swin_small_patch4_window7_224] INFO: Epoch: [96] [1210/1251] eta: 0:00:20 lr: 0.000766 loss: 3.7235 (3.5162) grad_norm: 1.1213 (inf) time: 0.5031 [2021-03-25 20:56:33 swin_small_patch4_window7_224] INFO: Epoch: [96] [1220/1251] eta: 0:00:15 lr: 0.000766 loss: 3.6585 (3.5148) grad_norm: 1.0825 (inf) time: 0.5053 [2021-03-25 20:56:38 swin_small_patch4_window7_224] INFO: Epoch: [96] [1230/1251] eta: 0:00:10 lr: 0.000766 loss: 3.5490 (3.5152) grad_norm: 1.1175 (inf) time: 0.5033 [2021-03-25 20:56:43 swin_small_patch4_window7_224] INFO: Epoch: [96] [1240/1251] eta: 0:00:05 lr: 0.000766 loss: 3.2678 (3.5140) grad_norm: 1.1589 (inf) time: 0.5043 [2021-03-25 20:56:48 swin_small_patch4_window7_224] INFO: Epoch: [96] [1250/1251] eta: 0:00:00 lr: 0.000766 loss: 3.3312 (3.5139) grad_norm: 1.1553 (inf) time: 0.5071 [2021-03-25 20:56:55 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 0.8242 (0.8242) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-25 20:56:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0042 (1.0024) acc1: 76.5625 (76.1364) acc5: 95.3125 (94.4602) [2021-03-25 20:56:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0042 (1.0030) acc1: 76.5625 (76.2649) acc5: 93.7500 (94.0476) [2021-03-25 20:57:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0259 (1.0277) acc1: 76.5625 (75.2016) acc5: 93.7500 (93.7500) [2021-03-25 20:57:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0836 (1.0296) acc1: 76.5625 (75.3811) acc5: 92.1875 (93.2927) [2021-03-25 20:57:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.1093 (1.0454) acc1: 73.4375 (74.9440) acc5: 92.1875 (93.1200) [2021-03-25 20:57:08 swin_small_patch4_window7_224] INFO: * Acc@1 76.000 Acc@5 93.432 loss 1.021 [2021-03-25 20:57:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.0% [2021-03-25 20:57:08 swin_small_patch4_window7_224] INFO: Max accuracy: 76.03% [2021-03-25 20:57:12 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 0/1251] eta: 1:28:06 lr: 0.000766 loss: 3.0670 (3.0670) grad_norm: 1.2096 (1.2096) time: 4.2258 [2021-03-25 20:57:17 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 10/1251] eta: 0:17:45 lr: 0.000766 loss: 3.5722 (3.5635) grad_norm: 1.1979 (1.2059) time: 0.8582 [2021-03-25 20:57:23 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 20/1251] eta: 0:14:08 lr: 0.000766 loss: 3.6821 (3.6916) grad_norm: 1.1609 (1.1787) time: 0.5127 [2021-03-25 20:57:28 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 30/1251] eta: 0:12:50 lr: 0.000766 loss: 3.7517 (3.6590) grad_norm: 1.1523 (1.1937) time: 0.5056 [2021-03-25 20:57:33 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 40/1251] eta: 0:12:05 lr: 0.000766 loss: 3.3770 (3.5830) grad_norm: 1.1694 (1.1807) time: 0.5046 [2021-03-25 20:57:38 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 50/1251] eta: 0:11:37 lr: 0.000766 loss: 3.2688 (3.5618) grad_norm: 1.1068 (1.1704) time: 0.5028 [2021-03-25 20:57:43 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 60/1251] eta: 0:11:16 lr: 0.000766 loss: 3.5273 (3.5668) grad_norm: 1.1178 (1.1742) time: 0.5046 [2021-03-25 20:57:48 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 70/1251] eta: 0:11:00 lr: 0.000766 loss: 3.5273 (3.5391) grad_norm: 1.1546 (1.1692) time: 0.5035 [2021-03-25 20:57:53 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 80/1251] eta: 0:10:46 lr: 0.000766 loss: 3.4197 (3.5313) grad_norm: 1.2022 (1.1835) time: 0.5019 [2021-03-25 20:57:58 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 90/1251] eta: 0:10:35 lr: 0.000766 loss: 3.4431 (3.5282) grad_norm: 1.2497 (1.1895) time: 0.5058 [2021-03-25 20:58:03 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 100/1251] eta: 0:10:25 lr: 0.000765 loss: 3.6151 (3.5180) grad_norm: 1.2454 (1.1927) time: 0.5080 [2021-03-25 20:58:08 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 110/1251] eta: 0:10:15 lr: 0.000765 loss: 3.7329 (3.5376) grad_norm: 1.1722 (1.1897) time: 0.5032 [2021-03-25 20:58:13 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 120/1251] eta: 0:10:06 lr: 0.000765 loss: 3.7329 (3.5521) grad_norm: 1.1076 (1.1842) time: 0.5021 [2021-03-25 20:58:18 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 130/1251] eta: 0:09:59 lr: 0.000765 loss: 3.8510 (3.5710) grad_norm: 1.1596 (1.1876) time: 0.5071 [2021-03-25 20:58:23 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 140/1251] eta: 0:09:51 lr: 0.000765 loss: 3.7276 (3.5607) grad_norm: 1.1821 (1.1830) time: 0.5103 [2021-03-25 20:58:28 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 150/1251] eta: 0:09:44 lr: 0.000765 loss: 3.5011 (3.5637) grad_norm: 1.1437 (1.1835) time: 0.5054 [2021-03-25 20:58:33 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 160/1251] eta: 0:09:37 lr: 0.000765 loss: 3.4135 (3.5506) grad_norm: 1.1377 (1.1833) time: 0.5064 [2021-03-25 20:58:38 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 170/1251] eta: 0:09:31 lr: 0.000765 loss: 3.4114 (3.5504) grad_norm: 1.1072 (1.1786) time: 0.5129 [2021-03-25 20:58:44 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 180/1251] eta: 0:09:25 lr: 0.000765 loss: 3.6684 (3.5574) grad_norm: 1.1933 (1.1855) time: 0.5189 [2021-03-25 20:58:49 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 190/1251] eta: 0:09:19 lr: 0.000765 loss: 3.7066 (3.5528) grad_norm: 1.1948 (1.1832) time: 0.5134 [2021-03-25 20:58:54 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 200/1251] eta: 0:09:13 lr: 0.000765 loss: 3.6477 (3.5529) grad_norm: 1.1062 (1.1791) time: 0.5115 [2021-03-25 20:58:59 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 210/1251] eta: 0:09:07 lr: 0.000765 loss: 3.6071 (3.5501) grad_norm: 1.0965 (1.1758) time: 0.5152 [2021-03-25 20:59:04 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 220/1251] eta: 0:09:01 lr: 0.000765 loss: 3.2563 (3.5300) grad_norm: 1.1015 (1.1742) time: 0.5095 [2021-03-25 20:59:09 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 230/1251] eta: 0:08:55 lr: 0.000765 loss: 3.4974 (3.5353) grad_norm: 1.1551 (1.1759) time: 0.5061 [2021-03-25 20:59:14 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 240/1251] eta: 0:08:49 lr: 0.000765 loss: 3.7245 (3.5412) grad_norm: 1.1859 (1.1777) time: 0.5049 [2021-03-25 20:59:19 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 250/1251] eta: 0:08:42 lr: 0.000765 loss: 3.7794 (3.5402) grad_norm: 1.1671 (1.1760) time: 0.5034 [2021-03-25 20:59:24 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 260/1251] eta: 0:08:37 lr: 0.000765 loss: 3.5145 (3.5315) grad_norm: 1.1785 (1.1764) time: 0.5065 [2021-03-25 20:59:29 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 270/1251] eta: 0:08:31 lr: 0.000765 loss: 3.5145 (3.5362) grad_norm: 1.1280 (1.1743) time: 0.5061 [2021-03-25 20:59:34 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 280/1251] eta: 0:08:25 lr: 0.000765 loss: 3.7048 (3.5378) grad_norm: 1.1162 (1.1730) time: 0.5011 [2021-03-25 20:59:39 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 290/1251] eta: 0:08:19 lr: 0.000765 loss: 3.7097 (3.5355) grad_norm: 1.1162 (1.1753) time: 0.5018 [2021-03-25 20:59:44 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 300/1251] eta: 0:08:13 lr: 0.000765 loss: 3.6553 (3.5378) grad_norm: 1.1508 (1.1763) time: 0.4999 [2021-03-25 20:59:49 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 310/1251] eta: 0:08:08 lr: 0.000765 loss: 3.7585 (3.5448) grad_norm: 1.1508 (1.1756) time: 0.5008 [2021-03-25 20:59:55 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 320/1251] eta: 0:08:02 lr: 0.000765 loss: 3.8135 (3.5435) grad_norm: 1.1092 (1.1735) time: 0.5067 [2021-03-25 20:59:59 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 330/1251] eta: 0:07:56 lr: 0.000765 loss: 3.6768 (3.5458) grad_norm: 1.0867 (1.1713) time: 0.5048 [2021-03-25 21:00:05 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 340/1251] eta: 0:07:51 lr: 0.000765 loss: 3.6706 (3.5456) grad_norm: 1.0748 (1.1696) time: 0.5032 [2021-03-25 21:00:10 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 350/1251] eta: 0:07:46 lr: 0.000765 loss: 3.4773 (3.5361) grad_norm: 1.1077 (1.1688) time: 0.5098 [2021-03-25 21:00:15 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 360/1251] eta: 0:07:41 lr: 0.000765 loss: 3.2973 (3.5348) grad_norm: 1.1238 (1.1688) time: 0.5239 [2021-03-25 21:00:20 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 370/1251] eta: 0:07:36 lr: 0.000765 loss: 3.4270 (3.5279) grad_norm: 1.1725 (1.1705) time: 0.5219 [2021-03-25 21:00:25 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 380/1251] eta: 0:07:30 lr: 0.000765 loss: 3.4795 (3.5311) grad_norm: 1.1725 (1.1721) time: 0.5069 [2021-03-25 21:00:30 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 390/1251] eta: 0:07:25 lr: 0.000764 loss: 3.6102 (3.5333) grad_norm: 1.1494 (1.1720) time: 0.5066 [2021-03-25 21:00:35 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 400/1251] eta: 0:07:19 lr: 0.000764 loss: 3.6548 (3.5384) grad_norm: 1.0774 (1.1700) time: 0.5073 [2021-03-25 21:00:40 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 410/1251] eta: 0:07:14 lr: 0.000764 loss: 3.6548 (3.5346) grad_norm: 1.0774 (1.1686) time: 0.5006 [2021-03-25 21:00:45 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 420/1251] eta: 0:07:08 lr: 0.000764 loss: 3.5729 (3.5311) grad_norm: 1.1322 (1.1689) time: 0.5020 [2021-03-25 21:00:50 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 430/1251] eta: 0:07:03 lr: 0.000764 loss: 3.5011 (3.5270) grad_norm: 1.1330 (1.1689) time: 0.5038 [2021-03-25 21:00:55 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 440/1251] eta: 0:06:58 lr: 0.000764 loss: 3.6055 (3.5289) grad_norm: 1.1315 (1.1680) time: 0.5010 [2021-03-25 21:01:01 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 450/1251] eta: 0:06:53 lr: 0.000764 loss: 3.6055 (3.5288) grad_norm: 1.1278 (1.1680) time: 0.5152 [2021-03-25 21:01:06 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 460/1251] eta: 0:06:47 lr: 0.000764 loss: 3.5410 (3.5311) grad_norm: 1.1460 (1.1684) time: 0.5142 [2021-03-25 21:01:11 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 470/1251] eta: 0:06:42 lr: 0.000764 loss: 3.7127 (3.5301) grad_norm: 1.1119 (1.1669) time: 0.5059 [2021-03-25 21:01:16 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 480/1251] eta: 0:06:37 lr: 0.000764 loss: 3.5265 (3.5276) grad_norm: 1.1457 (1.1693) time: 0.5056 [2021-03-25 21:01:21 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 490/1251] eta: 0:06:31 lr: 0.000764 loss: 3.3770 (3.5272) grad_norm: 1.1862 (1.1689) time: 0.5054 [2021-03-25 21:01:26 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 500/1251] eta: 0:06:26 lr: 0.000764 loss: 3.6271 (3.5277) grad_norm: 1.0907 (1.1677) time: 0.5090 [2021-03-25 21:01:31 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 510/1251] eta: 0:06:21 lr: 0.000764 loss: 3.4738 (3.5230) grad_norm: 1.0703 (1.1665) time: 0.5087 [2021-03-25 21:01:36 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 520/1251] eta: 0:06:16 lr: 0.000764 loss: 3.4071 (3.5228) grad_norm: 1.0417 (1.1643) time: 0.5075 [2021-03-25 21:01:41 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 530/1251] eta: 0:06:10 lr: 0.000764 loss: 3.7189 (3.5254) grad_norm: 1.1061 (1.1659) time: 0.5036 [2021-03-25 21:01:46 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 540/1251] eta: 0:06:05 lr: 0.000764 loss: 3.7189 (3.5203) grad_norm: 1.1722 (1.1656) time: 0.5100 [2021-03-25 21:01:52 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 550/1251] eta: 0:06:00 lr: 0.000764 loss: 3.4266 (3.5179) grad_norm: 1.1192 (1.1647) time: 0.5301 [2021-03-25 21:01:57 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 560/1251] eta: 0:05:55 lr: 0.000764 loss: 3.6234 (3.5209) grad_norm: 1.1237 (1.1646) time: 0.5183 [2021-03-25 21:02:02 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 570/1251] eta: 0:05:50 lr: 0.000764 loss: 3.6083 (3.5185) grad_norm: 1.1587 (1.1650) time: 0.4967 [2021-03-25 21:02:07 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 580/1251] eta: 0:05:44 lr: 0.000764 loss: 3.5644 (3.5193) grad_norm: 1.0938 (1.1637) time: 0.4991 [2021-03-25 21:02:12 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 590/1251] eta: 0:05:39 lr: 0.000764 loss: 3.3077 (3.5134) grad_norm: 1.0868 (1.1625) time: 0.5035 [2021-03-25 21:02:17 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 600/1251] eta: 0:05:34 lr: 0.000764 loss: 3.4399 (3.5189) grad_norm: 1.0956 (1.1622) time: 0.5046 [2021-03-25 21:02:22 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 610/1251] eta: 0:05:29 lr: 0.000764 loss: 3.9515 (3.5239) grad_norm: 1.1674 (1.1632) time: 0.5049 [2021-03-25 21:02:27 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 620/1251] eta: 0:05:23 lr: 0.000764 loss: 3.8353 (3.5254) grad_norm: 1.1985 (1.1640) time: 0.5005 [2021-03-25 21:02:32 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 630/1251] eta: 0:05:18 lr: 0.000764 loss: 3.5638 (3.5238) grad_norm: 1.1693 (1.1640) time: 0.5000 [2021-03-25 21:02:37 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 640/1251] eta: 0:05:13 lr: 0.000764 loss: 3.2700 (3.5244) grad_norm: 1.1693 (1.1653) time: 0.5096 [2021-03-25 21:02:42 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 650/1251] eta: 0:05:08 lr: 0.000764 loss: 3.2654 (3.5196) grad_norm: 1.1295 (1.1650) time: 0.5053 [2021-03-25 21:02:47 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 660/1251] eta: 0:05:02 lr: 0.000764 loss: 3.3618 (3.5199) grad_norm: 1.1461 (1.1654) time: 0.4999 [2021-03-25 21:02:52 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 670/1251] eta: 0:04:57 lr: 0.000763 loss: 3.5614 (3.5234) grad_norm: 1.1740 (1.1656) time: 0.5037 [2021-03-25 21:02:57 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 680/1251] eta: 0:04:52 lr: 0.000763 loss: 3.5183 (3.5218) grad_norm: 1.1715 (1.1655) time: 0.5057 [2021-03-25 21:03:02 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 690/1251] eta: 0:04:47 lr: 0.000763 loss: 3.5187 (3.5221) grad_norm: 1.1951 (1.1668) time: 0.5042 [2021-03-25 21:03:07 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 700/1251] eta: 0:04:42 lr: 0.000763 loss: 3.4987 (3.5169) grad_norm: 1.2160 (1.1682) time: 0.5005 [2021-03-25 21:03:12 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 710/1251] eta: 0:04:36 lr: 0.000763 loss: 2.9774 (3.5101) grad_norm: 1.1126 (1.1673) time: 0.5011 [2021-03-25 21:03:17 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 720/1251] eta: 0:04:31 lr: 0.000763 loss: 3.0195 (3.5098) grad_norm: 1.1070 (1.1673) time: 0.5080 [2021-03-25 21:03:23 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 730/1251] eta: 0:04:26 lr: 0.000763 loss: 3.6415 (3.5093) grad_norm: 1.1131 (1.1665) time: 0.5185 [2021-03-25 21:03:28 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 740/1251] eta: 0:04:21 lr: 0.000763 loss: 3.6103 (3.5121) grad_norm: 1.1152 (1.1658) time: 0.5342 [2021-03-25 21:03:33 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 750/1251] eta: 0:04:16 lr: 0.000763 loss: 3.4989 (3.5098) grad_norm: 1.1601 (1.1659) time: 0.5284 [2021-03-25 21:03:38 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 760/1251] eta: 0:04:11 lr: 0.000763 loss: 3.5718 (3.5109) grad_norm: 1.1550 (1.1656) time: 0.5119 [2021-03-25 21:03:43 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 770/1251] eta: 0:04:06 lr: 0.000763 loss: 3.7157 (3.5127) grad_norm: 1.1460 (1.1659) time: 0.5089 [2021-03-25 21:03:48 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 780/1251] eta: 0:04:01 lr: 0.000763 loss: 3.8007 (3.5145) grad_norm: 1.1460 (1.1662) time: 0.5018 [2021-03-25 21:03:53 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 790/1251] eta: 0:03:56 lr: 0.000763 loss: 3.6109 (3.5130) grad_norm: 1.0997 (1.1655) time: 0.5037 [2021-03-25 21:03:58 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 800/1251] eta: 0:03:50 lr: 0.000763 loss: 3.4787 (3.5135) grad_norm: 1.0905 (1.1650) time: 0.5041 [2021-03-25 21:04:03 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 810/1251] eta: 0:03:45 lr: 0.000763 loss: 3.6774 (3.5155) grad_norm: 1.1291 (1.1646) time: 0.4985 [2021-03-25 21:04:08 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 820/1251] eta: 0:03:40 lr: 0.000763 loss: 3.6762 (3.5165) grad_norm: 1.1670 (1.1650) time: 0.5014 [2021-03-25 21:04:13 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 830/1251] eta: 0:03:35 lr: 0.000763 loss: 3.6762 (3.5164) grad_norm: 1.1541 (1.1645) time: 0.5039 [2021-03-25 21:04:18 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 840/1251] eta: 0:03:30 lr: 0.000763 loss: 3.7225 (3.5174) grad_norm: 1.1153 (1.1643) time: 0.5030 [2021-03-25 21:04:24 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 850/1251] eta: 0:03:25 lr: 0.000763 loss: 3.5881 (3.5187) grad_norm: 1.1314 (1.1641) time: 0.5047 [2021-03-25 21:04:29 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 860/1251] eta: 0:03:19 lr: 0.000763 loss: 3.5095 (3.5191) grad_norm: 1.1314 (1.1632) time: 0.5044 [2021-03-25 21:04:34 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 870/1251] eta: 0:03:14 lr: 0.000763 loss: 3.7276 (3.5219) grad_norm: 1.1326 (1.1637) time: 0.5010 [2021-03-25 21:04:39 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 880/1251] eta: 0:03:09 lr: 0.000763 loss: 3.7276 (3.5216) grad_norm: 1.1501 (1.1632) time: 0.5010 [2021-03-25 21:04:44 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 890/1251] eta: 0:03:04 lr: 0.000763 loss: 3.5720 (3.5207) grad_norm: 1.1777 (1.1643) time: 0.5070 [2021-03-25 21:04:49 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 900/1251] eta: 0:02:59 lr: 0.000763 loss: 3.6593 (3.5214) grad_norm: 1.1777 (1.1645) time: 0.5078 [2021-03-25 21:04:54 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 910/1251] eta: 0:02:54 lr: 0.000763 loss: 3.7269 (3.5232) grad_norm: 1.1348 (1.1642) time: 0.5067 [2021-03-25 21:04:59 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 920/1251] eta: 0:02:49 lr: 0.000763 loss: 3.4694 (3.5184) grad_norm: 1.0620 (1.1633) time: 0.5104 [2021-03-25 21:05:04 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 930/1251] eta: 0:02:44 lr: 0.000763 loss: 3.0517 (3.5178) grad_norm: 1.0885 (1.1635) time: 0.5084 [2021-03-25 21:05:09 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 940/1251] eta: 0:02:38 lr: 0.000763 loss: 3.0491 (3.5138) grad_norm: 1.0726 (1.1623) time: 0.5034 [2021-03-25 21:05:14 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 950/1251] eta: 0:02:33 lr: 0.000762 loss: 3.0089 (3.5120) grad_norm: 1.0734 (1.1624) time: 0.5105 [2021-03-25 21:05:19 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 960/1251] eta: 0:02:28 lr: 0.000762 loss: 3.5342 (3.5120) grad_norm: 1.1553 (1.1622) time: 0.5084 [2021-03-25 21:05:24 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 970/1251] eta: 0:02:23 lr: 0.000762 loss: 3.5342 (3.5094) grad_norm: 1.1106 (1.1617) time: 0.4949 [2021-03-25 21:05:29 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 980/1251] eta: 0:02:18 lr: 0.000762 loss: 3.6008 (3.5106) grad_norm: 1.1071 (1.1615) time: 0.4976 [2021-03-25 21:05:34 swin_small_patch4_window7_224] INFO: Epoch: [97] [ 990/1251] eta: 0:02:13 lr: 0.000762 loss: 3.6836 (3.5092) grad_norm: 1.1193 (1.1610) time: 0.5010 [2021-03-25 21:05:39 swin_small_patch4_window7_224] INFO: Epoch: [97] [1000/1251] eta: 0:02:08 lr: 0.000762 loss: 3.3417 (3.5079) grad_norm: 1.1402 (1.1608) time: 0.5045 [2021-03-25 21:05:44 swin_small_patch4_window7_224] INFO: Epoch: [97] [1010/1251] eta: 0:02:03 lr: 0.000762 loss: 3.3460 (3.5077) grad_norm: 1.1340 (1.1602) time: 0.5050 [2021-03-25 21:05:49 swin_small_patch4_window7_224] INFO: Epoch: [97] [1020/1251] eta: 0:01:57 lr: 0.000762 loss: 3.6367 (3.5090) grad_norm: 1.0920 (1.1597) time: 0.5031 [2021-03-25 21:05:54 swin_small_patch4_window7_224] INFO: Epoch: [97] [1030/1251] eta: 0:01:52 lr: 0.000762 loss: 3.6437 (3.5098) grad_norm: 1.1268 (1.1600) time: 0.5036 [2021-03-25 21:05:59 swin_small_patch4_window7_224] INFO: Epoch: [97] [1040/1251] eta: 0:01:47 lr: 0.000762 loss: 3.3884 (3.5069) grad_norm: 1.1231 (1.1595) time: 0.5045 [2021-03-25 21:06:04 swin_small_patch4_window7_224] INFO: Epoch: [97] [1050/1251] eta: 0:01:42 lr: 0.000762 loss: 3.3884 (3.5082) grad_norm: 1.1281 (1.1606) time: 0.5048 [2021-03-25 21:06:09 swin_small_patch4_window7_224] INFO: Epoch: [97] [1060/1251] eta: 0:01:37 lr: 0.000762 loss: 3.5463 (3.5058) grad_norm: 1.1386 (1.1600) time: 0.5037 [2021-03-25 21:06:15 swin_small_patch4_window7_224] INFO: Epoch: [97] [1070/1251] eta: 0:01:32 lr: 0.000762 loss: 3.2888 (3.5035) grad_norm: 1.1205 (1.1599) time: 0.5072 [2021-03-25 21:06:20 swin_small_patch4_window7_224] INFO: Epoch: [97] [1080/1251] eta: 0:01:27 lr: 0.000762 loss: 3.4753 (3.5031) grad_norm: 1.1237 (1.1599) time: 0.5095 [2021-03-25 21:06:25 swin_small_patch4_window7_224] INFO: Epoch: [97] [1090/1251] eta: 0:01:22 lr: 0.000762 loss: 3.6474 (3.5015) grad_norm: 1.0696 (1.1595) time: 0.5101 [2021-03-25 21:06:30 swin_small_patch4_window7_224] INFO: Epoch: [97] [1100/1251] eta: 0:01:17 lr: 0.000762 loss: 3.5358 (3.5016) grad_norm: 1.0885 (1.1593) time: 0.5173 [2021-03-25 21:06:35 swin_small_patch4_window7_224] INFO: Epoch: [97] [1110/1251] eta: 0:01:11 lr: 0.000762 loss: 3.4156 (3.4992) grad_norm: 1.1458 (1.1592) time: 0.5099 [2021-03-25 21:06:40 swin_small_patch4_window7_224] INFO: Epoch: [97] [1120/1251] eta: 0:01:06 lr: 0.000762 loss: 3.4312 (3.4990) grad_norm: 1.0944 (1.1590) time: 0.5032 [2021-03-25 21:06:45 swin_small_patch4_window7_224] INFO: Epoch: [97] [1130/1251] eta: 0:01:01 lr: 0.000762 loss: 3.6890 (3.5011) grad_norm: 1.1074 (1.1594) time: 0.5106 [2021-03-25 21:06:50 swin_small_patch4_window7_224] INFO: Epoch: [97] [1140/1251] eta: 0:00:56 lr: 0.000762 loss: 3.6890 (3.5013) grad_norm: 1.1074 (1.1597) time: 0.5076 [2021-03-25 21:06:55 swin_small_patch4_window7_224] INFO: Epoch: [97] [1150/1251] eta: 0:00:51 lr: 0.000762 loss: 3.5997 (3.5010) grad_norm: 1.1235 (1.1594) time: 0.5057 [2021-03-25 21:07:00 swin_small_patch4_window7_224] INFO: Epoch: [97] [1160/1251] eta: 0:00:46 lr: 0.000762 loss: 3.5775 (3.5015) grad_norm: 1.1235 (1.1592) time: 0.5050 [2021-03-25 21:07:05 swin_small_patch4_window7_224] INFO: Epoch: [97] [1170/1251] eta: 0:00:41 lr: 0.000762 loss: 3.5775 (3.5029) grad_norm: 1.1039 (1.1593) time: 0.5027 [2021-03-25 21:07:10 swin_small_patch4_window7_224] INFO: Epoch: [97] [1180/1251] eta: 0:00:36 lr: 0.000762 loss: 3.6278 (3.5042) grad_norm: 1.1003 (1.1589) time: 0.5007 [2021-03-25 21:07:16 swin_small_patch4_window7_224] INFO: Epoch: [97] [1190/1251] eta: 0:00:31 lr: 0.000762 loss: 3.6660 (3.5062) grad_norm: 1.0981 (1.1591) time: 0.5087 [2021-03-25 21:07:20 swin_small_patch4_window7_224] INFO: Epoch: [97] [1200/1251] eta: 0:00:25 lr: 0.000762 loss: 3.5501 (3.5058) grad_norm: 1.1886 (inf) time: 0.5027 [2021-03-25 21:07:25 swin_small_patch4_window7_224] INFO: Epoch: [97] [1210/1251] eta: 0:00:20 lr: 0.000762 loss: 3.4854 (3.5049) grad_norm: 1.1767 (inf) time: 0.4943 [2021-03-25 21:07:30 swin_small_patch4_window7_224] INFO: Epoch: [97] [1220/1251] eta: 0:00:15 lr: 0.000762 loss: 3.4051 (3.5051) grad_norm: 1.1579 (inf) time: 0.4978 [2021-03-25 21:07:35 swin_small_patch4_window7_224] INFO: Epoch: [97] [1230/1251] eta: 0:00:10 lr: 0.000761 loss: 3.6173 (3.5049) grad_norm: 1.1463 (inf) time: 0.4970 [2021-03-25 21:07:40 swin_small_patch4_window7_224] INFO: Epoch: [97] [1240/1251] eta: 0:00:05 lr: 0.000761 loss: 3.4287 (3.5022) grad_norm: 1.1212 (inf) time: 0.4981 [2021-03-25 21:07:45 swin_small_patch4_window7_224] INFO: Epoch: [97] [1250/1251] eta: 0:00:00 lr: 0.000761 loss: 3.3779 (3.5022) grad_norm: 1.1212 (inf) time: 0.4960 [2021-03-25 21:07:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:41 loss: 1.3867 (1.3867) acc1: 65.6250 (65.6250) acc5: 87.5000 (87.5000) [2021-03-25 21:07:55 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0013 (1.0554) acc1: 76.5625 (75.4261) acc5: 93.7500 (92.3295) [2021-03-25 21:07:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0013 (1.0709) acc1: 76.5625 (75.2232) acc5: 92.1875 (92.0387) [2021-03-25 21:08:00 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0240 (1.0420) acc1: 76.5625 (75.7560) acc5: 92.1875 (92.6411) [2021-03-25 21:08:02 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9588 (1.0226) acc1: 76.5625 (76.1433) acc5: 93.7500 (92.9878) [2021-03-25 21:08:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9388 (1.0178) acc1: 76.5625 (76.0000) acc5: 95.3125 (93.1520) [2021-03-25 21:08:10 swin_small_patch4_window7_224] INFO: * Acc@1 75.906 Acc@5 93.318 loss 1.012 [2021-03-25 21:08:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.9% [2021-03-25 21:08:10 swin_small_patch4_window7_224] INFO: Max accuracy: 76.03% [2021-03-25 21:08:14 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 0/1251] eta: 1:32:01 lr: 0.000761 loss: 3.9510 (3.9510) grad_norm: 1.1796 (1.1796) time: 4.4135 [2021-03-25 21:08:19 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 10/1251] eta: 0:17:50 lr: 0.000761 loss: 2.8932 (3.3132) grad_norm: 1.1455 (1.1236) time: 0.8625 [2021-03-25 21:08:24 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 20/1251] eta: 0:14:12 lr: 0.000761 loss: 3.5265 (3.4432) grad_norm: 1.1510 (1.1439) time: 0.5064 [2021-03-25 21:08:29 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 30/1251] eta: 0:12:50 lr: 0.000761 loss: 3.8229 (3.5667) grad_norm: 1.1524 (1.1405) time: 0.5042 [2021-03-25 21:08:35 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 40/1251] eta: 0:12:11 lr: 0.000761 loss: 3.8783 (3.6015) grad_norm: 1.1575 (1.1593) time: 0.5106 [2021-03-25 21:08:40 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 50/1251] eta: 0:11:42 lr: 0.000761 loss: 3.6913 (3.6032) grad_norm: 1.2381 (1.1757) time: 0.5125 [2021-03-25 21:08:45 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 60/1251] eta: 0:11:20 lr: 0.000761 loss: 3.6557 (3.5694) grad_norm: 1.1425 (1.1729) time: 0.5051 [2021-03-25 21:08:50 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 70/1251] eta: 0:11:03 lr: 0.000761 loss: 3.4686 (3.5400) grad_norm: 1.0993 (1.1668) time: 0.5030 [2021-03-25 21:08:55 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 80/1251] eta: 0:10:49 lr: 0.000761 loss: 3.4686 (3.5343) grad_norm: 1.1445 (1.1664) time: 0.5044 [2021-03-25 21:09:00 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 90/1251] eta: 0:10:37 lr: 0.000761 loss: 3.6613 (3.5553) grad_norm: 1.1469 (1.1649) time: 0.5040 [2021-03-25 21:09:05 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 100/1251] eta: 0:10:26 lr: 0.000761 loss: 3.7074 (3.5606) grad_norm: 1.1469 (1.1689) time: 0.5028 [2021-03-25 21:09:10 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 110/1251] eta: 0:10:17 lr: 0.000761 loss: 3.3145 (3.5388) grad_norm: 1.1938 (1.1780) time: 0.5050 [2021-03-25 21:09:15 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 120/1251] eta: 0:10:08 lr: 0.000761 loss: 3.3067 (3.5235) grad_norm: 1.1938 (1.1791) time: 0.5036 [2021-03-25 21:09:20 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 130/1251] eta: 0:10:00 lr: 0.000761 loss: 3.6130 (3.5398) grad_norm: 1.1178 (1.1736) time: 0.5029 [2021-03-25 21:09:25 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 140/1251] eta: 0:09:52 lr: 0.000761 loss: 3.6130 (3.5370) grad_norm: 1.1377 (1.1733) time: 0.5059 [2021-03-25 21:09:30 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 150/1251] eta: 0:09:44 lr: 0.000761 loss: 3.3341 (3.5193) grad_norm: 1.1564 (1.1739) time: 0.5038 [2021-03-25 21:09:35 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 160/1251] eta: 0:09:37 lr: 0.000761 loss: 3.2782 (3.5131) grad_norm: 1.1580 (1.1748) time: 0.5021 [2021-03-25 21:09:40 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 170/1251] eta: 0:09:30 lr: 0.000761 loss: 3.3659 (3.5090) grad_norm: 1.1292 (1.1732) time: 0.5062 [2021-03-25 21:09:45 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 180/1251] eta: 0:09:24 lr: 0.000761 loss: 3.5382 (3.5107) grad_norm: 1.0659 (1.1677) time: 0.5106 [2021-03-25 21:09:50 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 190/1251] eta: 0:09:18 lr: 0.000761 loss: 3.6138 (3.5169) grad_norm: 1.0824 (1.1664) time: 0.5096 [2021-03-25 21:09:56 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 200/1251] eta: 0:09:12 lr: 0.000761 loss: 3.6138 (3.5111) grad_norm: 1.1327 (1.1651) time: 0.5070 [2021-03-25 21:10:01 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 210/1251] eta: 0:09:06 lr: 0.000761 loss: 3.5165 (3.5094) grad_norm: 1.1126 (1.1625) time: 0.5092 [2021-03-25 21:10:06 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 220/1251] eta: 0:09:00 lr: 0.000761 loss: 3.6880 (3.5162) grad_norm: 1.1373 (1.1625) time: 0.5098 [2021-03-25 21:10:11 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 230/1251] eta: 0:08:54 lr: 0.000761 loss: 3.7034 (3.5247) grad_norm: 1.1716 (1.1628) time: 0.5080 [2021-03-25 21:10:16 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 240/1251] eta: 0:08:48 lr: 0.000761 loss: 3.6304 (3.5252) grad_norm: 1.1791 (1.1655) time: 0.5069 [2021-03-25 21:10:21 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 250/1251] eta: 0:08:42 lr: 0.000761 loss: 3.5707 (3.5308) grad_norm: 1.1747 (1.1628) time: 0.5060 [2021-03-25 21:10:26 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 260/1251] eta: 0:08:36 lr: 0.000761 loss: 3.5223 (3.5178) grad_norm: 1.1101 (1.1623) time: 0.5119 [2021-03-25 21:10:31 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 270/1251] eta: 0:08:31 lr: 0.000760 loss: 3.4880 (3.5133) grad_norm: 1.1341 (1.1622) time: 0.5106 [2021-03-25 21:10:36 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 280/1251] eta: 0:08:25 lr: 0.000760 loss: 3.3982 (3.5067) grad_norm: 1.1321 (1.1600) time: 0.4995 [2021-03-25 21:10:41 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 290/1251] eta: 0:08:19 lr: 0.000760 loss: 3.5821 (3.5103) grad_norm: 1.1060 (1.1600) time: 0.5090 [2021-03-25 21:10:46 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 300/1251] eta: 0:08:14 lr: 0.000760 loss: 3.5976 (3.5186) grad_norm: 1.1669 (1.1603) time: 0.5147 [2021-03-25 21:10:51 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 310/1251] eta: 0:08:08 lr: 0.000760 loss: 3.5682 (3.5137) grad_norm: 1.1438 (1.1602) time: 0.5029 [2021-03-25 21:10:56 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 320/1251] eta: 0:08:02 lr: 0.000760 loss: 3.3065 (3.5078) grad_norm: 1.1668 (1.1654) time: 0.4976 [2021-03-25 21:11:01 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 330/1251] eta: 0:07:57 lr: 0.000760 loss: 3.5157 (3.5079) grad_norm: 1.1629 (1.1661) time: 0.5026 [2021-03-25 21:11:06 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 340/1251] eta: 0:07:51 lr: 0.000760 loss: 3.5880 (3.5027) grad_norm: 1.1561 (1.1664) time: 0.5063 [2021-03-25 21:11:12 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 350/1251] eta: 0:07:46 lr: 0.000760 loss: 3.7306 (3.5100) grad_norm: 1.1151 (1.1667) time: 0.5057 [2021-03-25 21:11:17 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 360/1251] eta: 0:07:40 lr: 0.000760 loss: 3.6775 (3.5080) grad_norm: 1.1497 (1.1671) time: 0.5036 [2021-03-25 21:11:22 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 370/1251] eta: 0:07:35 lr: 0.000760 loss: 3.3003 (3.4997) grad_norm: 1.1662 (1.1666) time: 0.5033 [2021-03-25 21:11:27 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 380/1251] eta: 0:07:29 lr: 0.000760 loss: 3.6224 (3.5042) grad_norm: 1.1505 (1.1675) time: 0.5039 [2021-03-25 21:11:32 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 390/1251] eta: 0:07:24 lr: 0.000760 loss: 3.6456 (3.5020) grad_norm: 1.2223 (1.1695) time: 0.5039 [2021-03-25 21:11:37 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 400/1251] eta: 0:07:18 lr: 0.000760 loss: 3.6456 (3.5051) grad_norm: 1.1672 (1.1682) time: 0.5035 [2021-03-25 21:11:42 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 410/1251] eta: 0:07:13 lr: 0.000760 loss: 3.7323 (3.5113) grad_norm: 1.1406 (1.1695) time: 0.5025 [2021-03-25 21:11:47 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 420/1251] eta: 0:07:07 lr: 0.000760 loss: 3.7835 (3.5114) grad_norm: 1.2119 (1.1704) time: 0.5038 [2021-03-25 21:11:52 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 430/1251] eta: 0:07:02 lr: 0.000760 loss: 3.6984 (3.5086) grad_norm: 1.1116 (1.1685) time: 0.5051 [2021-03-25 21:11:57 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 440/1251] eta: 0:06:57 lr: 0.000760 loss: 3.6984 (3.5129) grad_norm: 1.1030 (1.1661) time: 0.5063 [2021-03-25 21:12:02 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 450/1251] eta: 0:06:52 lr: 0.000760 loss: 3.7526 (3.5156) grad_norm: 1.0669 (1.1646) time: 0.5116 [2021-03-25 21:12:07 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 460/1251] eta: 0:06:46 lr: 0.000760 loss: 3.5331 (3.5149) grad_norm: 1.0953 (1.1636) time: 0.5093 [2021-03-25 21:12:12 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 470/1251] eta: 0:06:41 lr: 0.000760 loss: 3.2960 (3.5096) grad_norm: 1.0782 (1.1625) time: 0.5026 [2021-03-25 21:12:17 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 480/1251] eta: 0:06:36 lr: 0.000760 loss: 3.2960 (3.5106) grad_norm: 1.0673 (1.1606) time: 0.5155 [2021-03-25 21:12:22 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 490/1251] eta: 0:06:31 lr: 0.000760 loss: 3.2273 (3.5046) grad_norm: 1.0695 (1.1590) time: 0.5163 [2021-03-25 21:12:28 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 500/1251] eta: 0:06:26 lr: 0.000760 loss: 3.4119 (3.5032) grad_norm: 1.0726 (1.1582) time: 0.5046 [2021-03-25 21:12:33 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 510/1251] eta: 0:06:20 lr: 0.000760 loss: 3.4724 (3.5042) grad_norm: 1.1104 (1.1588) time: 0.5097 [2021-03-25 21:12:38 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 520/1251] eta: 0:06:15 lr: 0.000760 loss: 3.4724 (3.5047) grad_norm: 1.1398 (1.1584) time: 0.5145 [2021-03-25 21:12:43 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 530/1251] eta: 0:06:10 lr: 0.000760 loss: 3.4977 (3.5053) grad_norm: 1.1058 (1.1570) time: 0.5137 [2021-03-25 21:12:48 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 540/1251] eta: 0:06:05 lr: 0.000760 loss: 3.4417 (3.5012) grad_norm: 1.1146 (1.1565) time: 0.5176 [2021-03-25 21:12:54 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 550/1251] eta: 0:06:00 lr: 0.000759 loss: 3.2579 (3.4952) grad_norm: 1.1146 (1.1561) time: 0.5282 [2021-03-25 21:12:59 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 560/1251] eta: 0:05:55 lr: 0.000759 loss: 3.3656 (3.4961) grad_norm: 1.1118 (1.1561) time: 0.5208 [2021-03-25 21:13:04 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 570/1251] eta: 0:05:50 lr: 0.000759 loss: 3.6346 (3.4970) grad_norm: 1.1035 (1.1559) time: 0.5056 [2021-03-25 21:13:09 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 580/1251] eta: 0:05:44 lr: 0.000759 loss: 3.7140 (3.4948) grad_norm: 1.1540 (1.1563) time: 0.5030 [2021-03-25 21:13:14 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 590/1251] eta: 0:05:39 lr: 0.000759 loss: 3.5981 (3.4929) grad_norm: 1.1669 (1.1566) time: 0.5063 [2021-03-25 21:13:19 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 600/1251] eta: 0:05:34 lr: 0.000759 loss: 3.6027 (3.4960) grad_norm: 1.1107 (1.1558) time: 0.5087 [2021-03-25 21:13:24 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 610/1251] eta: 0:05:29 lr: 0.000759 loss: 3.6395 (3.4921) grad_norm: 1.1108 (1.1560) time: 0.5012 [2021-03-25 21:13:29 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 620/1251] eta: 0:05:24 lr: 0.000759 loss: 3.4454 (3.4896) grad_norm: 1.1108 (1.1554) time: 0.5039 [2021-03-25 21:13:34 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 630/1251] eta: 0:05:18 lr: 0.000759 loss: 3.4575 (3.4895) grad_norm: 1.0746 (1.1547) time: 0.5073 [2021-03-25 21:13:39 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 640/1251] eta: 0:05:13 lr: 0.000759 loss: 3.4363 (3.4884) grad_norm: 1.1077 (1.1546) time: 0.5078 [2021-03-25 21:13:44 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 650/1251] eta: 0:05:08 lr: 0.000759 loss: 3.4196 (3.4854) grad_norm: 1.1146 (1.1540) time: 0.5073 [2021-03-25 21:13:49 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 660/1251] eta: 0:05:03 lr: 0.000759 loss: 3.5500 (3.4885) grad_norm: 1.0992 (1.1538) time: 0.5012 [2021-03-25 21:13:54 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 670/1251] eta: 0:04:57 lr: 0.000759 loss: 3.7234 (3.4888) grad_norm: 1.1166 (1.1538) time: 0.5026 [2021-03-25 21:13:59 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 680/1251] eta: 0:04:52 lr: 0.000759 loss: 3.6608 (3.4908) grad_norm: 1.1394 (1.1532) time: 0.5049 [2021-03-25 21:14:04 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 690/1251] eta: 0:04:47 lr: 0.000759 loss: 3.5139 (3.4910) grad_norm: 1.1254 (1.1533) time: 0.5076 [2021-03-25 21:14:09 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 700/1251] eta: 0:04:42 lr: 0.000759 loss: 3.5643 (3.4939) grad_norm: 1.1282 (1.1538) time: 0.5112 [2021-03-25 21:14:15 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 710/1251] eta: 0:04:37 lr: 0.000759 loss: 3.6176 (3.4920) grad_norm: 1.1738 (1.1542) time: 0.5119 [2021-03-25 21:14:20 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 720/1251] eta: 0:04:32 lr: 0.000759 loss: 3.4129 (3.4920) grad_norm: 1.1753 (1.1543) time: 0.5047 [2021-03-25 21:14:25 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 730/1251] eta: 0:04:27 lr: 0.000759 loss: 3.5574 (3.4923) grad_norm: 1.1579 (1.1542) time: 0.5154 [2021-03-25 21:14:30 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 740/1251] eta: 0:04:22 lr: 0.000759 loss: 3.6130 (3.4952) grad_norm: 1.0914 (1.1541) time: 0.5297 [2021-03-25 21:14:35 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 750/1251] eta: 0:04:16 lr: 0.000759 loss: 3.5153 (3.4920) grad_norm: 1.1275 (1.1543) time: 0.5194 [2021-03-25 21:14:40 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 760/1251] eta: 0:04:11 lr: 0.000759 loss: 3.2321 (3.4888) grad_norm: 1.1400 (1.1544) time: 0.5101 [2021-03-25 21:14:45 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 770/1251] eta: 0:04:06 lr: 0.000759 loss: 3.4119 (3.4877) grad_norm: 1.1400 (1.1540) time: 0.5061 [2021-03-25 21:14:50 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 780/1251] eta: 0:04:01 lr: 0.000759 loss: 3.5770 (3.4879) grad_norm: 1.1404 (1.1545) time: 0.5035 [2021-03-25 21:14:56 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 790/1251] eta: 0:03:56 lr: 0.000759 loss: 3.7550 (3.4906) grad_norm: 1.2043 (1.1555) time: 0.5075 [2021-03-25 21:15:01 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 800/1251] eta: 0:03:51 lr: 0.000759 loss: 3.8058 (3.4910) grad_norm: 1.1442 (1.1548) time: 0.5101 [2021-03-25 21:15:06 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 810/1251] eta: 0:03:46 lr: 0.000759 loss: 3.3793 (3.4873) grad_norm: 1.1314 (1.1552) time: 0.5078 [2021-03-25 21:15:11 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 820/1251] eta: 0:03:40 lr: 0.000759 loss: 3.1938 (3.4865) grad_norm: 1.1424 (1.1547) time: 0.5085 [2021-03-25 21:15:16 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 830/1251] eta: 0:03:35 lr: 0.000758 loss: 3.1938 (3.4827) grad_norm: 1.1779 (1.1557) time: 0.5105 [2021-03-25 21:15:21 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 840/1251] eta: 0:03:30 lr: 0.000758 loss: 3.2747 (3.4813) grad_norm: 1.1915 (1.1553) time: 0.5085 [2021-03-25 21:15:26 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 850/1251] eta: 0:03:25 lr: 0.000758 loss: 3.4736 (3.4814) grad_norm: 1.1269 (1.1551) time: 0.5036 [2021-03-25 21:15:31 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 860/1251] eta: 0:03:20 lr: 0.000758 loss: 3.5303 (3.4832) grad_norm: 1.1577 (1.1555) time: 0.5041 [2021-03-25 21:15:36 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 870/1251] eta: 0:03:15 lr: 0.000758 loss: 3.5671 (3.4843) grad_norm: 1.1854 (1.1561) time: 0.5063 [2021-03-25 21:15:41 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 880/1251] eta: 0:03:10 lr: 0.000758 loss: 3.5729 (3.4869) grad_norm: 1.1967 (1.1572) time: 0.5139 [2021-03-25 21:15:46 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 890/1251] eta: 0:03:04 lr: 0.000758 loss: 3.5583 (3.4878) grad_norm: 1.1967 (1.1576) time: 0.5139 [2021-03-25 21:15:51 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 900/1251] eta: 0:02:59 lr: 0.000758 loss: 3.5234 (3.4866) grad_norm: 1.1573 (1.1577) time: 0.5087 [2021-03-25 21:15:56 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 910/1251] eta: 0:02:54 lr: 0.000758 loss: 3.6534 (3.4879) grad_norm: 1.1503 (1.1577) time: 0.5049 [2021-03-25 21:16:02 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 920/1251] eta: 0:02:49 lr: 0.000758 loss: 3.7390 (3.4891) grad_norm: 1.1443 (1.1578) time: 0.5060 [2021-03-25 21:16:07 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 930/1251] eta: 0:02:44 lr: 0.000758 loss: 3.6722 (3.4903) grad_norm: 1.1162 (1.1570) time: 0.5116 [2021-03-25 21:16:12 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 940/1251] eta: 0:02:39 lr: 0.000758 loss: 3.6301 (3.4922) grad_norm: 1.0642 (1.1562) time: 0.5099 [2021-03-25 21:16:17 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 950/1251] eta: 0:02:34 lr: 0.000758 loss: 3.7554 (3.4968) grad_norm: 1.0922 (1.1560) time: 0.5067 [2021-03-25 21:16:22 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 960/1251] eta: 0:02:28 lr: 0.000758 loss: 3.7554 (3.4979) grad_norm: 1.1522 (1.1558) time: 0.5027 [2021-03-25 21:16:27 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 970/1251] eta: 0:02:23 lr: 0.000758 loss: 3.4405 (3.4969) grad_norm: 1.1404 (1.1557) time: 0.5030 [2021-03-25 21:16:32 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 980/1251] eta: 0:02:18 lr: 0.000758 loss: 3.5787 (3.4981) grad_norm: 1.1246 (1.1554) time: 0.5000 [2021-03-25 21:16:37 swin_small_patch4_window7_224] INFO: Epoch: [98] [ 990/1251] eta: 0:02:13 lr: 0.000758 loss: 3.6441 (3.4968) grad_norm: 1.1084 (1.1549) time: 0.5010 [2021-03-25 21:16:42 swin_small_patch4_window7_224] INFO: Epoch: [98] [1000/1251] eta: 0:02:08 lr: 0.000758 loss: 3.5384 (3.4979) grad_norm: 1.1329 (1.1558) time: 0.5079 [2021-03-25 21:16:47 swin_small_patch4_window7_224] INFO: Epoch: [98] [1010/1251] eta: 0:02:03 lr: 0.000758 loss: 3.5865 (3.4981) grad_norm: 1.0822 (1.1548) time: 0.5028 [2021-03-25 21:16:52 swin_small_patch4_window7_224] INFO: Epoch: [98] [1020/1251] eta: 0:01:58 lr: 0.000758 loss: 3.5865 (3.4983) grad_norm: 1.0959 (1.1547) time: 0.5012 [2021-03-25 21:16:57 swin_small_patch4_window7_224] INFO: Epoch: [98] [1030/1251] eta: 0:01:53 lr: 0.000758 loss: 3.4633 (3.4972) grad_norm: 1.1074 (1.1539) time: 0.5133 [2021-03-25 21:17:02 swin_small_patch4_window7_224] INFO: Epoch: [98] [1040/1251] eta: 0:01:47 lr: 0.000758 loss: 3.5768 (3.4983) grad_norm: 1.1264 (1.1543) time: 0.5148 [2021-03-25 21:17:07 swin_small_patch4_window7_224] INFO: Epoch: [98] [1050/1251] eta: 0:01:42 lr: 0.000758 loss: 3.6096 (3.4998) grad_norm: 1.1625 (1.1537) time: 0.5082 [2021-03-25 21:17:12 swin_small_patch4_window7_224] INFO: Epoch: [98] [1060/1251] eta: 0:01:37 lr: 0.000758 loss: 3.6390 (3.4995) grad_norm: 1.1278 (1.1545) time: 0.5070 [2021-03-25 21:17:18 swin_small_patch4_window7_224] INFO: Epoch: [98] [1070/1251] eta: 0:01:32 lr: 0.000758 loss: 3.5524 (3.4986) grad_norm: 1.1795 (1.1544) time: 0.5086 [2021-03-25 21:17:23 swin_small_patch4_window7_224] INFO: Epoch: [98] [1080/1251] eta: 0:01:27 lr: 0.000758 loss: 3.6535 (3.5013) grad_norm: 1.1346 (1.1545) time: 0.5046 [2021-03-25 21:17:28 swin_small_patch4_window7_224] INFO: Epoch: [98] [1090/1251] eta: 0:01:22 lr: 0.000758 loss: 3.6279 (3.4997) grad_norm: 1.1346 (1.1546) time: 0.5033 [2021-03-25 21:17:33 swin_small_patch4_window7_224] INFO: Epoch: [98] [1100/1251] eta: 0:01:17 lr: 0.000758 loss: 3.3595 (3.5000) grad_norm: 1.1121 (1.1547) time: 0.5089 [2021-03-25 21:17:38 swin_small_patch4_window7_224] INFO: Epoch: [98] [1110/1251] eta: 0:01:12 lr: 0.000757 loss: 3.5318 (3.4991) grad_norm: 1.1348 (1.1552) time: 0.5048 [2021-03-25 21:17:43 swin_small_patch4_window7_224] INFO: Epoch: [98] [1120/1251] eta: 0:01:06 lr: 0.000757 loss: 3.5196 (3.4992) grad_norm: 1.1917 (1.1557) time: 0.5029 [2021-03-25 21:17:48 swin_small_patch4_window7_224] INFO: Epoch: [98] [1130/1251] eta: 0:01:01 lr: 0.000757 loss: 3.5196 (3.4992) grad_norm: 1.1653 (1.1559) time: 0.5041 [2021-03-25 21:17:53 swin_small_patch4_window7_224] INFO: Epoch: [98] [1140/1251] eta: 0:00:56 lr: 0.000757 loss: 3.5003 (3.4987) grad_norm: 1.1653 (1.1565) time: 0.5020 [2021-03-25 21:17:58 swin_small_patch4_window7_224] INFO: Epoch: [98] [1150/1251] eta: 0:00:51 lr: 0.000757 loss: 3.7896 (3.5002) grad_norm: 1.1989 (1.1567) time: 0.5011 [2021-03-25 21:18:03 swin_small_patch4_window7_224] INFO: Epoch: [98] [1160/1251] eta: 0:00:46 lr: 0.000757 loss: 3.6411 (3.4996) grad_norm: 1.0633 (1.1558) time: 0.4994 [2021-03-25 21:18:08 swin_small_patch4_window7_224] INFO: Epoch: [98] [1170/1251] eta: 0:00:41 lr: 0.000757 loss: 3.5869 (3.5011) grad_norm: 1.0753 (1.1558) time: 0.5007 [2021-03-25 21:18:13 swin_small_patch4_window7_224] INFO: Epoch: [98] [1180/1251] eta: 0:00:36 lr: 0.000757 loss: 3.7430 (3.5018) grad_norm: 1.1138 (1.1556) time: 0.5043 [2021-03-25 21:18:18 swin_small_patch4_window7_224] INFO: Epoch: [98] [1190/1251] eta: 0:00:31 lr: 0.000757 loss: 3.4853 (3.5007) grad_norm: 1.1138 (1.1557) time: 0.5061 [2021-03-25 21:18:23 swin_small_patch4_window7_224] INFO: Epoch: [98] [1200/1251] eta: 0:00:26 lr: 0.000757 loss: 3.5890 (3.5017) grad_norm: 1.1787 (1.1564) time: 0.5076 [2021-03-25 21:18:28 swin_small_patch4_window7_224] INFO: Epoch: [98] [1210/1251] eta: 0:00:20 lr: 0.000757 loss: 3.4806 (3.5009) grad_norm: 1.1719 (1.1562) time: 0.5019 [2021-03-25 21:18:33 swin_small_patch4_window7_224] INFO: Epoch: [98] [1220/1251] eta: 0:00:15 lr: 0.000757 loss: 3.4456 (3.5002) grad_norm: 1.1588 (1.1572) time: 0.5038 [2021-03-25 21:18:38 swin_small_patch4_window7_224] INFO: Epoch: [98] [1230/1251] eta: 0:00:10 lr: 0.000757 loss: 3.4925 (3.4997) grad_norm: 1.1415 (1.1567) time: 0.5118 [2021-03-25 21:18:43 swin_small_patch4_window7_224] INFO: Epoch: [98] [1240/1251] eta: 0:00:05 lr: 0.000757 loss: 3.2687 (3.4970) grad_norm: 1.0746 (1.1561) time: 0.5070 [2021-03-25 21:18:48 swin_small_patch4_window7_224] INFO: Epoch: [98] [1250/1251] eta: 0:00:00 lr: 0.000757 loss: 3.2938 (3.4993) grad_norm: 1.0893 (1.1559) time: 0.4944 [2021-03-25 21:18:56 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:28 loss: 0.7810 (0.7810) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-25 21:18:59 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 1.0449 (1.0324) acc1: 75.0000 (75.5682) acc5: 92.1875 (92.8977) [2021-03-25 21:19:01 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0440 (1.0333) acc1: 75.0000 (75.9673) acc5: 92.1875 (93.0060) [2021-03-25 21:19:03 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0391 (1.0489) acc1: 73.4375 (74.6976) acc5: 92.1875 (92.8931) [2021-03-25 21:19:05 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0075 (1.0256) acc1: 73.4375 (75.0762) acc5: 93.7500 (93.3308) [2021-03-25 21:19:06 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0022 (1.0340) acc1: 75.0000 (74.8800) acc5: 93.7500 (93.3440) [2021-03-25 21:19:12 swin_small_patch4_window7_224] INFO: * Acc@1 75.806 Acc@5 93.350 loss 1.021 [2021-03-25 21:19:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-25 21:19:12 swin_small_patch4_window7_224] INFO: Max accuracy: 76.03% [2021-03-25 21:19:16 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 0/1251] eta: 1:25:45 lr: 0.000757 loss: 3.1228 (3.1228) grad_norm: 1.0975 (1.0975) time: 4.1130 [2021-03-25 21:19:21 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 10/1251] eta: 0:17:26 lr: 0.000757 loss: 3.2253 (3.1654) grad_norm: 1.1020 (1.1234) time: 0.8434 [2021-03-25 21:19:26 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 20/1251] eta: 0:13:59 lr: 0.000757 loss: 3.4771 (3.5296) grad_norm: 1.1098 (1.1458) time: 0.5101 [2021-03-25 21:19:31 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 30/1251] eta: 0:12:40 lr: 0.000757 loss: 3.7420 (3.5350) grad_norm: 1.1273 (1.1447) time: 0.5014 [2021-03-25 21:19:36 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 40/1251] eta: 0:12:02 lr: 0.000757 loss: 3.6026 (3.5451) grad_norm: 1.1498 (1.1514) time: 0.5081 [2021-03-25 21:19:41 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 50/1251] eta: 0:11:33 lr: 0.000757 loss: 3.6654 (3.5415) grad_norm: 1.1400 (1.1440) time: 0.5080 [2021-03-25 21:19:46 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 60/1251] eta: 0:11:12 lr: 0.000757 loss: 3.5028 (3.4701) grad_norm: 1.0954 (1.1402) time: 0.4980 [2021-03-25 21:19:51 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 70/1251] eta: 0:10:57 lr: 0.000757 loss: 3.3914 (3.4658) grad_norm: 1.1209 (1.1416) time: 0.5039 [2021-03-25 21:19:56 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 80/1251] eta: 0:10:44 lr: 0.000757 loss: 3.3914 (3.4688) grad_norm: 1.1611 (1.1498) time: 0.5065 [2021-03-25 21:20:01 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 90/1251] eta: 0:10:33 lr: 0.000757 loss: 3.5487 (3.4731) grad_norm: 1.1611 (1.1519) time: 0.5057 [2021-03-25 21:20:06 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 100/1251] eta: 0:10:23 lr: 0.000757 loss: 3.1885 (3.4332) grad_norm: 1.1130 (1.1419) time: 0.5059 [2021-03-25 21:20:11 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 110/1251] eta: 0:10:14 lr: 0.000757 loss: 3.0664 (3.4431) grad_norm: 1.0892 (1.1399) time: 0.5049 [2021-03-25 21:20:16 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 120/1251] eta: 0:10:05 lr: 0.000757 loss: 3.5781 (3.4536) grad_norm: 1.1333 (1.1450) time: 0.5059 [2021-03-25 21:20:22 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 130/1251] eta: 0:09:59 lr: 0.000757 loss: 3.4330 (3.4167) grad_norm: 1.1737 (1.1499) time: 0.5130 [2021-03-25 21:20:27 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 140/1251] eta: 0:09:52 lr: 0.000756 loss: 3.1884 (3.4096) grad_norm: 1.1878 (1.1528) time: 0.5228 [2021-03-25 21:20:32 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 150/1251] eta: 0:09:46 lr: 0.000756 loss: 3.3097 (3.3946) grad_norm: 1.2003 (1.1545) time: 0.5179 [2021-03-25 21:20:37 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 160/1251] eta: 0:09:39 lr: 0.000756 loss: 3.3804 (3.4126) grad_norm: 1.1365 (1.1519) time: 0.5099 [2021-03-25 21:20:42 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 170/1251] eta: 0:09:33 lr: 0.000756 loss: 3.6708 (3.4168) grad_norm: 1.1188 (1.1536) time: 0.5150 [2021-03-25 21:20:47 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 180/1251] eta: 0:09:25 lr: 0.000756 loss: 3.4292 (3.4143) grad_norm: 1.1518 (1.1536) time: 0.5083 [2021-03-25 21:20:52 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 190/1251] eta: 0:09:19 lr: 0.000756 loss: 3.6440 (3.4303) grad_norm: 1.1689 (1.1550) time: 0.4983 [2021-03-25 21:20:57 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 200/1251] eta: 0:09:12 lr: 0.000756 loss: 3.3657 (3.4200) grad_norm: 1.1418 (1.1551) time: 0.4991 [2021-03-25 21:21:02 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 210/1251] eta: 0:09:05 lr: 0.000756 loss: 3.2382 (3.4220) grad_norm: 1.1282 (1.1545) time: 0.5003 [2021-03-25 21:21:07 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 220/1251] eta: 0:08:59 lr: 0.000756 loss: 3.5726 (3.4198) grad_norm: 1.1282 (1.1547) time: 0.5004 [2021-03-25 21:21:12 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 230/1251] eta: 0:08:52 lr: 0.000756 loss: 3.3813 (3.4172) grad_norm: 1.1062 (1.1539) time: 0.4948 [2021-03-25 21:21:17 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 240/1251] eta: 0:08:46 lr: 0.000756 loss: 3.6512 (3.4399) grad_norm: 1.1227 (1.1548) time: 0.4945 [2021-03-25 21:21:22 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 250/1251] eta: 0:08:40 lr: 0.000756 loss: 3.7253 (3.4427) grad_norm: 1.1214 (1.1526) time: 0.4985 [2021-03-25 21:21:27 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 260/1251] eta: 0:08:35 lr: 0.000756 loss: 3.7218 (3.4568) grad_norm: 1.0790 (1.1521) time: 0.5074 [2021-03-25 21:21:32 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 270/1251] eta: 0:08:29 lr: 0.000756 loss: 3.7509 (3.4513) grad_norm: 1.0958 (1.1507) time: 0.5130 [2021-03-25 21:21:38 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 280/1251] eta: 0:08:23 lr: 0.000756 loss: 3.3338 (3.4463) grad_norm: 1.1061 (1.1509) time: 0.5100 [2021-03-25 21:21:43 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 290/1251] eta: 0:08:18 lr: 0.000756 loss: 3.4245 (3.4451) grad_norm: 1.1453 (1.1518) time: 0.5066 [2021-03-25 21:21:48 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 300/1251] eta: 0:08:12 lr: 0.000756 loss: 3.2510 (3.4389) grad_norm: 1.1123 (1.1511) time: 0.5059 [2021-03-25 21:21:53 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 310/1251] eta: 0:08:07 lr: 0.000756 loss: 3.2802 (3.4451) grad_norm: 1.0719 (1.1493) time: 0.5119 [2021-03-25 21:21:58 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 320/1251] eta: 0:08:02 lr: 0.000756 loss: 3.5324 (3.4445) grad_norm: 1.1232 (1.1502) time: 0.5115 [2021-03-25 21:22:03 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 330/1251] eta: 0:07:56 lr: 0.000756 loss: 3.4980 (3.4483) grad_norm: 1.0836 (1.1484) time: 0.5041 [2021-03-25 21:22:08 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 340/1251] eta: 0:07:50 lr: 0.000756 loss: 3.6639 (3.4546) grad_norm: 1.1795 (1.1507) time: 0.5051 [2021-03-25 21:22:13 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 350/1251] eta: 0:07:45 lr: 0.000756 loss: 3.5640 (3.4576) grad_norm: 1.1795 (1.1517) time: 0.5051 [2021-03-25 21:22:18 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 360/1251] eta: 0:07:40 lr: 0.000756 loss: 3.4262 (3.4527) grad_norm: 1.1591 (1.1535) time: 0.5068 [2021-03-25 21:22:23 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 370/1251] eta: 0:07:34 lr: 0.000756 loss: 3.6391 (3.4623) grad_norm: 1.1886 (1.1534) time: 0.5023 [2021-03-25 21:22:28 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 380/1251] eta: 0:07:28 lr: 0.000756 loss: 3.6884 (3.4661) grad_norm: 1.1015 (1.1530) time: 0.4943 [2021-03-25 21:22:33 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 390/1251] eta: 0:07:23 lr: 0.000756 loss: 3.6786 (3.4728) grad_norm: 1.0822 (1.1510) time: 0.5026 [2021-03-25 21:22:38 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 400/1251] eta: 0:07:18 lr: 0.000756 loss: 3.5771 (3.4730) grad_norm: 1.0700 (1.1498) time: 0.5093 [2021-03-25 21:22:43 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 410/1251] eta: 0:07:13 lr: 0.000756 loss: 3.3449 (3.4726) grad_norm: 1.0945 (1.1495) time: 0.5108 [2021-03-25 21:22:48 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 420/1251] eta: 0:07:07 lr: 0.000755 loss: 3.4152 (3.4733) grad_norm: 1.0989 (1.1499) time: 0.5052 [2021-03-25 21:22:53 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 430/1251] eta: 0:07:02 lr: 0.000755 loss: 3.5214 (3.4745) grad_norm: 1.1457 (1.1516) time: 0.4970 [2021-03-25 21:22:58 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 440/1251] eta: 0:06:56 lr: 0.000755 loss: 3.5970 (3.4717) grad_norm: 1.1282 (1.1509) time: 0.4992 [2021-03-25 21:23:03 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 450/1251] eta: 0:06:51 lr: 0.000755 loss: 3.6413 (3.4763) grad_norm: 1.1192 (1.1502) time: 0.4995 [2021-03-25 21:23:08 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 460/1251] eta: 0:06:46 lr: 0.000755 loss: 3.7332 (3.4820) grad_norm: 1.1333 (1.1513) time: 0.5014 [2021-03-25 21:23:14 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 470/1251] eta: 0:06:40 lr: 0.000755 loss: 3.5721 (3.4740) grad_norm: 1.1711 (1.1523) time: 0.5089 [2021-03-25 21:23:19 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 480/1251] eta: 0:06:35 lr: 0.000755 loss: 3.2404 (3.4713) grad_norm: 1.1828 (1.1536) time: 0.5074 [2021-03-25 21:23:24 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 490/1251] eta: 0:06:30 lr: 0.000755 loss: 3.5522 (3.4736) grad_norm: 1.1895 (1.1541) time: 0.5043 [2021-03-25 21:23:29 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 500/1251] eta: 0:06:25 lr: 0.000755 loss: 3.6620 (3.4765) grad_norm: 1.1400 (1.1537) time: 0.5067 [2021-03-25 21:23:34 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 510/1251] eta: 0:06:19 lr: 0.000755 loss: 3.4479 (3.4725) grad_norm: 1.0895 (1.1524) time: 0.5054 [2021-03-25 21:23:39 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 520/1251] eta: 0:06:14 lr: 0.000755 loss: 3.5632 (3.4731) grad_norm: 1.0869 (1.1527) time: 0.5116 [2021-03-25 21:23:44 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 530/1251] eta: 0:06:09 lr: 0.000755 loss: 3.5632 (3.4678) grad_norm: 1.1467 (1.1534) time: 0.5123 [2021-03-25 21:23:49 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 540/1251] eta: 0:06:04 lr: 0.000755 loss: 3.3631 (3.4645) grad_norm: 1.1467 (1.1534) time: 0.5048 [2021-03-25 21:23:54 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 550/1251] eta: 0:05:59 lr: 0.000755 loss: 3.5220 (3.4658) grad_norm: 1.1572 (1.1540) time: 0.5175 [2021-03-25 21:23:59 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 560/1251] eta: 0:05:54 lr: 0.000755 loss: 3.6518 (3.4660) grad_norm: 1.1893 (1.1552) time: 0.5184 [2021-03-25 21:24:04 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 570/1251] eta: 0:05:48 lr: 0.000755 loss: 3.6518 (3.4706) grad_norm: 1.1163 (1.1544) time: 0.5024 [2021-03-25 21:24:09 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 580/1251] eta: 0:05:43 lr: 0.000755 loss: 3.6942 (3.4712) grad_norm: 1.0697 (1.1533) time: 0.5011 [2021-03-25 21:24:14 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 590/1251] eta: 0:05:38 lr: 0.000755 loss: 3.7282 (3.4717) grad_norm: 1.1418 (1.1534) time: 0.5044 [2021-03-25 21:24:20 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 600/1251] eta: 0:05:33 lr: 0.000755 loss: 3.5503 (3.4723) grad_norm: 1.1535 (1.1534) time: 0.5065 [2021-03-25 21:24:25 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 610/1251] eta: 0:05:28 lr: 0.000755 loss: 3.5467 (3.4730) grad_norm: 1.1176 (1.1531) time: 0.5055 [2021-03-25 21:24:30 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 620/1251] eta: 0:05:22 lr: 0.000755 loss: 3.5008 (3.4676) grad_norm: 1.1225 (1.1539) time: 0.5058 [2021-03-25 21:24:35 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 630/1251] eta: 0:05:17 lr: 0.000755 loss: 3.3032 (3.4661) grad_norm: 1.1489 (1.1544) time: 0.5083 [2021-03-25 21:24:40 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 640/1251] eta: 0:05:12 lr: 0.000755 loss: 3.6239 (3.4692) grad_norm: 1.1709 (1.1549) time: 0.5060 [2021-03-25 21:24:45 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 650/1251] eta: 0:05:07 lr: 0.000755 loss: 3.7439 (3.4738) grad_norm: 1.2155 (1.1567) time: 0.5044 [2021-03-25 21:24:50 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 660/1251] eta: 0:05:02 lr: 0.000755 loss: 3.7147 (3.4732) grad_norm: 1.1931 (1.1569) time: 0.5009 [2021-03-25 21:24:55 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 670/1251] eta: 0:04:57 lr: 0.000755 loss: 3.4928 (3.4728) grad_norm: 1.2127 (1.1578) time: 0.4987 [2021-03-25 21:25:00 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 680/1251] eta: 0:04:51 lr: 0.000755 loss: 3.3893 (3.4698) grad_norm: 1.2127 (1.1584) time: 0.5050 [2021-03-25 21:25:05 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 690/1251] eta: 0:04:46 lr: 0.000755 loss: 3.3893 (3.4698) grad_norm: 1.1822 (1.1596) time: 0.5111 [2021-03-25 21:25:10 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 700/1251] eta: 0:04:41 lr: 0.000754 loss: 3.5675 (3.4708) grad_norm: 1.1541 (1.1590) time: 0.5115 [2021-03-25 21:25:15 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 710/1251] eta: 0:04:36 lr: 0.000754 loss: 3.5692 (3.4678) grad_norm: 1.1443 (1.1584) time: 0.5107 [2021-03-25 21:25:20 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 720/1251] eta: 0:04:31 lr: 0.000754 loss: 3.5179 (3.4677) grad_norm: 1.1477 (inf) time: 0.5124 [2021-03-25 21:25:25 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 730/1251] eta: 0:04:26 lr: 0.000754 loss: 3.5179 (3.4673) grad_norm: 1.1057 (inf) time: 0.5114 [2021-03-25 21:25:31 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 740/1251] eta: 0:04:21 lr: 0.000754 loss: 3.5364 (3.4696) grad_norm: 1.0894 (inf) time: 0.5209 [2021-03-25 21:25:36 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 750/1251] eta: 0:04:16 lr: 0.000754 loss: 3.6823 (3.4727) grad_norm: 1.1325 (inf) time: 0.5176 [2021-03-25 21:25:41 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 760/1251] eta: 0:04:10 lr: 0.000754 loss: 3.6295 (3.4729) grad_norm: 1.1142 (inf) time: 0.5003 [2021-03-25 21:25:46 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 770/1251] eta: 0:04:05 lr: 0.000754 loss: 3.4672 (3.4704) grad_norm: 1.1092 (inf) time: 0.4994 [2021-03-25 21:25:51 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 780/1251] eta: 0:04:00 lr: 0.000754 loss: 3.6360 (3.4725) grad_norm: 1.1162 (inf) time: 0.5050 [2021-03-25 21:25:56 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 790/1251] eta: 0:03:55 lr: 0.000754 loss: 3.8094 (3.4767) grad_norm: 1.1159 (inf) time: 0.5087 [2021-03-25 21:26:01 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 800/1251] eta: 0:03:50 lr: 0.000754 loss: 3.6428 (3.4757) grad_norm: 1.1332 (inf) time: 0.5036 [2021-03-25 21:26:06 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 810/1251] eta: 0:03:45 lr: 0.000754 loss: 3.5864 (3.4789) grad_norm: 1.1332 (inf) time: 0.5094 [2021-03-25 21:26:11 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 820/1251] eta: 0:03:40 lr: 0.000754 loss: 3.6721 (3.4802) grad_norm: 1.1827 (inf) time: 0.5098 [2021-03-25 21:26:16 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 830/1251] eta: 0:03:35 lr: 0.000754 loss: 3.7008 (3.4824) grad_norm: 1.1550 (inf) time: 0.5029 [2021-03-25 21:26:21 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 840/1251] eta: 0:03:29 lr: 0.000754 loss: 3.5885 (3.4805) grad_norm: 1.1555 (inf) time: 0.5147 [2021-03-25 21:26:27 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 850/1251] eta: 0:03:24 lr: 0.000754 loss: 3.4125 (3.4808) grad_norm: 1.1623 (inf) time: 0.5134 [2021-03-25 21:26:32 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 860/1251] eta: 0:03:19 lr: 0.000754 loss: 3.7115 (3.4838) grad_norm: 1.1175 (inf) time: 0.5069 [2021-03-25 21:26:37 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 870/1251] eta: 0:03:14 lr: 0.000754 loss: 3.6362 (3.4845) grad_norm: 1.1534 (inf) time: 0.5111 [2021-03-25 21:26:42 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 880/1251] eta: 0:03:09 lr: 0.000754 loss: 3.5225 (3.4858) grad_norm: 1.1681 (inf) time: 0.5141 [2021-03-25 21:26:47 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 890/1251] eta: 0:03:04 lr: 0.000754 loss: 3.5378 (3.4850) grad_norm: 1.1359 (inf) time: 0.5148 [2021-03-25 21:26:52 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 900/1251] eta: 0:02:59 lr: 0.000754 loss: 3.5388 (3.4853) grad_norm: 1.0988 (inf) time: 0.5062 [2021-03-25 21:26:57 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 910/1251] eta: 0:02:54 lr: 0.000754 loss: 3.3547 (3.4837) grad_norm: 1.1626 (inf) time: 0.5050 [2021-03-25 21:27:02 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 920/1251] eta: 0:02:49 lr: 0.000754 loss: 3.5968 (3.4851) grad_norm: 1.2096 (inf) time: 0.5125 [2021-03-25 21:27:07 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 930/1251] eta: 0:02:43 lr: 0.000754 loss: 3.3251 (3.4820) grad_norm: 1.1858 (inf) time: 0.5075 [2021-03-25 21:27:12 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 940/1251] eta: 0:02:38 lr: 0.000754 loss: 3.3658 (3.4851) grad_norm: 1.1784 (inf) time: 0.5003 [2021-03-25 21:27:17 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 950/1251] eta: 0:02:33 lr: 0.000754 loss: 3.8695 (3.4884) grad_norm: 1.1151 (inf) time: 0.5009 [2021-03-25 21:27:22 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 960/1251] eta: 0:02:28 lr: 0.000754 loss: 3.5349 (3.4852) grad_norm: 1.1161 (inf) time: 0.5030 [2021-03-25 21:27:27 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 970/1251] eta: 0:02:23 lr: 0.000754 loss: 3.4690 (3.4878) grad_norm: 1.1566 (inf) time: 0.5054 [2021-03-25 21:27:33 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 980/1251] eta: 0:02:18 lr: 0.000753 loss: 3.6574 (3.4872) grad_norm: 1.1828 (inf) time: 0.5097 [2021-03-25 21:27:38 swin_small_patch4_window7_224] INFO: Epoch: [99] [ 990/1251] eta: 0:02:13 lr: 0.000753 loss: 3.6574 (3.4893) grad_norm: 1.1230 (inf) time: 0.5073 [2021-03-25 21:27:43 swin_small_patch4_window7_224] INFO: Epoch: [99] [1000/1251] eta: 0:02:08 lr: 0.000753 loss: 3.7352 (3.4913) grad_norm: 1.1678 (inf) time: 0.5020 [2021-03-25 21:27:48 swin_small_patch4_window7_224] INFO: Epoch: [99] [1010/1251] eta: 0:02:02 lr: 0.000753 loss: 3.7352 (3.4937) grad_norm: 1.2277 (inf) time: 0.5046 [2021-03-25 21:27:53 swin_small_patch4_window7_224] INFO: Epoch: [99] [1020/1251] eta: 0:01:57 lr: 0.000753 loss: 3.7896 (3.4953) grad_norm: 1.2004 (inf) time: 0.5060 [2021-03-25 21:27:58 swin_small_patch4_window7_224] INFO: Epoch: [99] [1030/1251] eta: 0:01:52 lr: 0.000753 loss: 3.7323 (3.4954) grad_norm: 1.2004 (inf) time: 0.5005 [2021-03-25 21:28:03 swin_small_patch4_window7_224] INFO: Epoch: [99] [1040/1251] eta: 0:01:47 lr: 0.000753 loss: 3.5805 (3.4951) grad_norm: 1.2036 (inf) time: 0.4988 [2021-03-25 21:28:08 swin_small_patch4_window7_224] INFO: Epoch: [99] [1050/1251] eta: 0:01:42 lr: 0.000753 loss: 3.5078 (3.4927) grad_norm: 1.1708 (inf) time: 0.5065 [2021-03-25 21:28:13 swin_small_patch4_window7_224] INFO: Epoch: [99] [1060/1251] eta: 0:01:37 lr: 0.000753 loss: 3.5293 (3.4930) grad_norm: 1.1722 (inf) time: 0.5066 [2021-03-25 21:28:18 swin_small_patch4_window7_224] INFO: Epoch: [99] [1070/1251] eta: 0:01:32 lr: 0.000753 loss: 3.5652 (3.4919) grad_norm: 1.1417 (inf) time: 0.5021 [2021-03-25 21:28:23 swin_small_patch4_window7_224] INFO: Epoch: [99] [1080/1251] eta: 0:01:27 lr: 0.000753 loss: 3.6266 (3.4922) grad_norm: 1.1738 (inf) time: 0.4989 [2021-03-25 21:28:28 swin_small_patch4_window7_224] INFO: Epoch: [99] [1090/1251] eta: 0:01:22 lr: 0.000753 loss: 3.7767 (3.4927) grad_norm: 1.1854 (inf) time: 0.4963 [2021-03-25 21:28:33 swin_small_patch4_window7_224] INFO: Epoch: [99] [1100/1251] eta: 0:01:16 lr: 0.000753 loss: 3.8011 (3.4939) grad_norm: 1.1850 (inf) time: 0.4968 [2021-03-25 21:28:38 swin_small_patch4_window7_224] INFO: Epoch: [99] [1110/1251] eta: 0:01:11 lr: 0.000753 loss: 3.6396 (3.4923) grad_norm: 1.1905 (inf) time: 0.5030 [2021-03-25 21:28:43 swin_small_patch4_window7_224] INFO: Epoch: [99] [1120/1251] eta: 0:01:06 lr: 0.000753 loss: 3.5001 (3.4916) grad_norm: 1.1905 (inf) time: 0.5052 [2021-03-25 21:28:48 swin_small_patch4_window7_224] INFO: Epoch: [99] [1130/1251] eta: 0:01:01 lr: 0.000753 loss: 3.7001 (3.4951) grad_norm: 1.1784 (inf) time: 0.5006 [2021-03-25 21:28:53 swin_small_patch4_window7_224] INFO: Epoch: [99] [1140/1251] eta: 0:00:56 lr: 0.000753 loss: 3.7098 (3.4956) grad_norm: 1.2016 (inf) time: 0.4973 [2021-03-25 21:28:58 swin_small_patch4_window7_224] INFO: Epoch: [99] [1150/1251] eta: 0:00:51 lr: 0.000753 loss: 3.4568 (3.4945) grad_norm: 1.2243 (inf) time: 0.5005 [2021-03-25 21:29:03 swin_small_patch4_window7_224] INFO: Epoch: [99] [1160/1251] eta: 0:00:46 lr: 0.000753 loss: 3.4452 (3.4942) grad_norm: 1.1516 (inf) time: 0.5052 [2021-03-25 21:29:08 swin_small_patch4_window7_224] INFO: Epoch: [99] [1170/1251] eta: 0:00:41 lr: 0.000753 loss: 3.4666 (3.4939) grad_norm: 1.1223 (inf) time: 0.5017 [2021-03-25 21:29:13 swin_small_patch4_window7_224] INFO: Epoch: [99] [1180/1251] eta: 0:00:36 lr: 0.000753 loss: 3.5019 (3.4948) grad_norm: 1.1364 (inf) time: 0.4997 [2021-03-25 21:29:18 swin_small_patch4_window7_224] INFO: Epoch: [99] [1190/1251] eta: 0:00:31 lr: 0.000753 loss: 3.6525 (3.4966) grad_norm: 1.1956 (inf) time: 0.5037 [2021-03-25 21:29:23 swin_small_patch4_window7_224] INFO: Epoch: [99] [1200/1251] eta: 0:00:25 lr: 0.000753 loss: 3.7431 (3.4988) grad_norm: 1.1894 (inf) time: 0.5027 [2021-03-25 21:29:28 swin_small_patch4_window7_224] INFO: Epoch: [99] [1210/1251] eta: 0:00:20 lr: 0.000753 loss: 3.7580 (3.5008) grad_norm: 1.0918 (inf) time: 0.5034 [2021-03-25 21:29:33 swin_small_patch4_window7_224] INFO: Epoch: [99] [1220/1251] eta: 0:00:15 lr: 0.000753 loss: 3.6256 (3.5004) grad_norm: 1.1061 (inf) time: 0.5056 [2021-03-25 21:29:38 swin_small_patch4_window7_224] INFO: Epoch: [99] [1230/1251] eta: 0:00:10 lr: 0.000753 loss: 3.6256 (3.5034) grad_norm: 1.1244 (inf) time: 0.5004 [2021-03-25 21:29:43 swin_small_patch4_window7_224] INFO: Epoch: [99] [1240/1251] eta: 0:00:05 lr: 0.000753 loss: 3.7896 (3.5045) grad_norm: 1.1567 (inf) time: 0.4982 [2021-03-25 21:29:48 swin_small_patch4_window7_224] INFO: Epoch: [99] [1250/1251] eta: 0:00:00 lr: 0.000753 loss: 3.5901 (3.5034) grad_norm: 1.1557 (inf) time: 0.5046 [2021-03-25 21:29:56 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:34 loss: 0.8027 (0.8027) acc1: 82.8125 (82.8125) acc5: 93.7500 (93.7500) [2021-03-25 21:29:58 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9991 (0.9941) acc1: 78.1250 (76.9886) acc5: 93.7500 (93.4659) [2021-03-25 21:30:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0281 (1.0316) acc1: 75.0000 (75.2976) acc5: 93.7500 (92.8571) [2021-03-25 21:30:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0755 (1.0453) acc1: 73.4375 (75.0504) acc5: 92.1875 (92.7923) [2021-03-25 21:30:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0465 (1.0312) acc1: 73.4375 (75.3430) acc5: 93.7500 (92.9116) [2021-03-25 21:30:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0084 (1.0204) acc1: 75.0000 (75.5200) acc5: 93.7500 (93.0880) [2021-03-25 21:30:12 swin_small_patch4_window7_224] INFO: * Acc@1 76.108 Acc@5 93.432 loss 1.007 [2021-03-25 21:30:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.1% [2021-03-25 21:30:12 swin_small_patch4_window7_224] INFO: Max accuracy: 76.11% [2021-03-25 21:30:16 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 0/1251] eta: 1:25:45 lr: 0.000753 loss: 2.9471 (2.9471) grad_norm: 1.2398 (1.2398) time: 4.1128 [2021-03-25 21:30:21 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 10/1251] eta: 0:17:37 lr: 0.000752 loss: 3.4518 (3.3998) grad_norm: 1.0804 (1.1021) time: 0.8525 [2021-03-25 21:30:26 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 20/1251] eta: 0:14:11 lr: 0.000752 loss: 3.5442 (3.4772) grad_norm: 1.1028 (1.1639) time: 0.5205 [2021-03-25 21:30:32 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 30/1251] eta: 0:12:54 lr: 0.000752 loss: 3.7039 (3.5408) grad_norm: 1.2072 (1.1826) time: 0.5143 [2021-03-25 21:30:37 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 40/1251] eta: 0:12:10 lr: 0.000752 loss: 3.5749 (3.4910) grad_norm: 1.2392 (1.2064) time: 0.5105 [2021-03-25 21:30:42 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 50/1251] eta: 0:11:40 lr: 0.000752 loss: 3.4975 (3.4963) grad_norm: 1.2197 (1.2053) time: 0.5043 [2021-03-25 21:30:47 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 60/1251] eta: 0:11:20 lr: 0.000752 loss: 3.4613 (3.4716) grad_norm: 1.2016 (1.1996) time: 0.5059 [2021-03-25 21:30:52 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 70/1251] eta: 0:11:05 lr: 0.000752 loss: 3.5069 (3.4523) grad_norm: 1.2016 (1.1994) time: 0.5139 [2021-03-25 21:30:57 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 80/1251] eta: 0:10:51 lr: 0.000752 loss: 3.4956 (3.4528) grad_norm: 1.2406 (1.2038) time: 0.5122 [2021-03-25 21:31:02 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 90/1251] eta: 0:10:40 lr: 0.000752 loss: 3.8953 (3.4960) grad_norm: 1.1710 (1.1963) time: 0.5079 [2021-03-25 21:31:07 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 100/1251] eta: 0:10:29 lr: 0.000752 loss: 3.7255 (3.4834) grad_norm: 1.0913 (1.1881) time: 0.5084 [2021-03-25 21:31:12 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 110/1251] eta: 0:10:19 lr: 0.000752 loss: 3.4502 (3.4556) grad_norm: 1.1189 (1.1834) time: 0.5057 [2021-03-25 21:31:17 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 120/1251] eta: 0:10:11 lr: 0.000752 loss: 3.0243 (3.4398) grad_norm: 1.1249 (1.1829) time: 0.5055 [2021-03-25 21:31:22 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 130/1251] eta: 0:10:02 lr: 0.000752 loss: 3.3292 (3.4223) grad_norm: 1.1262 (1.1791) time: 0.5081 [2021-03-25 21:31:27 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 140/1251] eta: 0:09:54 lr: 0.000752 loss: 3.0172 (3.3960) grad_norm: 1.1826 (1.1800) time: 0.5053 [2021-03-25 21:31:32 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 150/1251] eta: 0:09:47 lr: 0.000752 loss: 3.3474 (3.4144) grad_norm: 1.1826 (1.1776) time: 0.5044 [2021-03-25 21:31:37 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 160/1251] eta: 0:09:39 lr: 0.000752 loss: 3.4478 (3.3971) grad_norm: 1.0878 (1.1740) time: 0.5054 [2021-03-25 21:31:43 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 170/1251] eta: 0:09:33 lr: 0.000752 loss: 3.1863 (3.3911) grad_norm: 1.1469 (1.1756) time: 0.5065 [2021-03-25 21:31:48 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 180/1251] eta: 0:09:26 lr: 0.000752 loss: 3.4446 (3.3974) grad_norm: 1.1304 (1.1728) time: 0.5062 [2021-03-25 21:31:53 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 190/1251] eta: 0:09:20 lr: 0.000752 loss: 3.6397 (3.4103) grad_norm: 1.1288 (1.1736) time: 0.5073 [2021-03-25 21:31:58 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 200/1251] eta: 0:09:14 lr: 0.000752 loss: 3.6397 (3.4071) grad_norm: 1.1288 (1.1724) time: 0.5157 [2021-03-25 21:32:03 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 210/1251] eta: 0:09:07 lr: 0.000752 loss: 3.6426 (3.4168) grad_norm: 1.1599 (1.1736) time: 0.5080 [2021-03-25 21:32:08 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 220/1251] eta: 0:09:01 lr: 0.000752 loss: 3.8366 (3.4286) grad_norm: 1.1635 (1.1734) time: 0.4975 [2021-03-25 21:32:13 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 230/1251] eta: 0:08:54 lr: 0.000752 loss: 3.6935 (3.4304) grad_norm: 1.1092 (1.1707) time: 0.4988 [2021-03-25 21:32:18 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 240/1251] eta: 0:08:48 lr: 0.000752 loss: 3.6442 (3.4408) grad_norm: 1.1213 (1.1715) time: 0.5014 [2021-03-25 21:32:23 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 250/1251] eta: 0:08:42 lr: 0.000752 loss: 3.5964 (3.4340) grad_norm: 1.1333 (1.1703) time: 0.5072 [2021-03-25 21:32:28 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 260/1251] eta: 0:08:37 lr: 0.000752 loss: 3.3646 (3.4305) grad_norm: 1.0860 (1.1665) time: 0.5146 [2021-03-25 21:32:33 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 270/1251] eta: 0:08:32 lr: 0.000752 loss: 3.3646 (3.4301) grad_norm: 1.0837 (1.1644) time: 0.5220 [2021-03-25 21:32:39 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 280/1251] eta: 0:08:26 lr: 0.000751 loss: 3.6076 (3.4356) grad_norm: 1.0966 (1.1654) time: 0.5138 [2021-03-25 21:32:44 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 290/1251] eta: 0:08:20 lr: 0.000751 loss: 3.6578 (3.4373) grad_norm: 1.1045 (1.1633) time: 0.5030 [2021-03-25 21:32:49 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 300/1251] eta: 0:08:14 lr: 0.000751 loss: 3.5233 (3.4312) grad_norm: 1.0977 (1.1651) time: 0.5005 [2021-03-25 21:32:54 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 310/1251] eta: 0:08:08 lr: 0.000751 loss: 3.3531 (3.4314) grad_norm: 1.1984 (1.1659) time: 0.4992 [2021-03-25 21:32:58 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 320/1251] eta: 0:08:03 lr: 0.000751 loss: 3.4814 (3.4378) grad_norm: 1.1024 (1.1664) time: 0.4987 [2021-03-25 21:33:04 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 330/1251] eta: 0:07:57 lr: 0.000751 loss: 3.6802 (3.4386) grad_norm: 1.1751 (1.1690) time: 0.5027 [2021-03-25 21:33:09 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 340/1251] eta: 0:07:52 lr: 0.000751 loss: 3.6802 (3.4458) grad_norm: 1.2069 (1.1677) time: 0.5070 [2021-03-25 21:33:14 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 350/1251] eta: 0:07:46 lr: 0.000751 loss: 3.6048 (3.4471) grad_norm: 1.1286 (1.1682) time: 0.5008 [2021-03-25 21:33:19 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 360/1251] eta: 0:07:40 lr: 0.000751 loss: 3.5987 (3.4474) grad_norm: 1.1137 (1.1669) time: 0.4989 [2021-03-25 21:33:24 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 370/1251] eta: 0:07:35 lr: 0.000751 loss: 3.3414 (3.4434) grad_norm: 1.2169 (1.1699) time: 0.5002 [2021-03-25 21:33:29 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 380/1251] eta: 0:07:29 lr: 0.000751 loss: 3.3837 (3.4413) grad_norm: 1.2169 (1.1694) time: 0.4989 [2021-03-25 21:33:34 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 390/1251] eta: 0:07:24 lr: 0.000751 loss: 3.3837 (3.4400) grad_norm: 1.1395 (1.1706) time: 0.4996 [2021-03-25 21:33:39 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 400/1251] eta: 0:07:18 lr: 0.000751 loss: 3.3638 (3.4439) grad_norm: 1.1986 (1.1721) time: 0.5021 [2021-03-25 21:33:44 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 410/1251] eta: 0:07:13 lr: 0.000751 loss: 3.5237 (3.4453) grad_norm: 1.1986 (1.1726) time: 0.5061 [2021-03-25 21:33:49 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 420/1251] eta: 0:07:07 lr: 0.000751 loss: 3.5275 (3.4467) grad_norm: 1.1793 (1.1744) time: 0.5033 [2021-03-25 21:33:54 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 430/1251] eta: 0:07:02 lr: 0.000751 loss: 3.6218 (3.4494) grad_norm: 1.1622 (1.1748) time: 0.5046 [2021-03-25 21:33:59 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 440/1251] eta: 0:06:57 lr: 0.000751 loss: 3.4172 (3.4490) grad_norm: 1.1619 (1.1761) time: 0.5147 [2021-03-25 21:34:04 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 450/1251] eta: 0:06:52 lr: 0.000751 loss: 3.3684 (3.4489) grad_norm: 1.1621 (1.1768) time: 0.5108 [2021-03-25 21:34:09 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 460/1251] eta: 0:06:46 lr: 0.000751 loss: 3.4155 (3.4526) grad_norm: 1.2930 (1.1805) time: 0.5017 [2021-03-25 21:34:14 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 470/1251] eta: 0:06:41 lr: 0.000751 loss: 3.6121 (3.4562) grad_norm: 1.1792 (1.1800) time: 0.5019 [2021-03-25 21:34:19 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 480/1251] eta: 0:06:36 lr: 0.000751 loss: 3.5944 (3.4541) grad_norm: 1.1734 (1.1809) time: 0.5072 [2021-03-25 21:34:24 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 490/1251] eta: 0:06:30 lr: 0.000751 loss: 3.6563 (3.4611) grad_norm: 1.1813 (1.1805) time: 0.5076 [2021-03-25 21:34:29 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 500/1251] eta: 0:06:25 lr: 0.000751 loss: 3.7806 (3.4642) grad_norm: 1.1188 (1.1794) time: 0.4983 [2021-03-25 21:34:34 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 510/1251] eta: 0:06:20 lr: 0.000751 loss: 3.7909 (3.4660) grad_norm: 1.1188 (1.1788) time: 0.4959 [2021-03-25 21:34:39 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 520/1251] eta: 0:06:14 lr: 0.000751 loss: 3.7945 (3.4677) grad_norm: 1.1761 (1.1795) time: 0.5015 [2021-03-25 21:34:44 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 530/1251] eta: 0:06:09 lr: 0.000751 loss: 3.6070 (3.4712) grad_norm: 1.1598 (1.1790) time: 0.5042 [2021-03-25 21:34:49 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 540/1251] eta: 0:06:04 lr: 0.000751 loss: 3.6321 (3.4736) grad_norm: 1.1318 (1.1787) time: 0.5035 [2021-03-25 21:34:55 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 550/1251] eta: 0:05:59 lr: 0.000751 loss: 3.5599 (3.4748) grad_norm: 1.0747 (1.1767) time: 0.5191 [2021-03-25 21:35:00 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 560/1251] eta: 0:05:54 lr: 0.000750 loss: 3.4704 (3.4753) grad_norm: 1.1310 (1.1773) time: 0.5256 [2021-03-25 21:35:05 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 570/1251] eta: 0:05:49 lr: 0.000750 loss: 3.5586 (3.4757) grad_norm: 1.1866 (1.1772) time: 0.5080 [2021-03-25 21:35:10 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 580/1251] eta: 0:05:43 lr: 0.000750 loss: 3.7267 (3.4806) grad_norm: 1.1498 (1.1770) time: 0.5019 [2021-03-25 21:35:15 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 590/1251] eta: 0:05:38 lr: 0.000750 loss: 3.7452 (3.4835) grad_norm: 1.1219 (1.1763) time: 0.5009 [2021-03-25 21:35:20 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 600/1251] eta: 0:05:33 lr: 0.000750 loss: 3.6782 (3.4833) grad_norm: 1.1212 (1.1758) time: 0.5016 [2021-03-25 21:35:25 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 610/1251] eta: 0:05:28 lr: 0.000750 loss: 3.0432 (3.4791) grad_norm: 1.1562 (1.1757) time: 0.5062 [2021-03-25 21:35:30 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 620/1251] eta: 0:05:23 lr: 0.000750 loss: 3.0432 (3.4789) grad_norm: 1.1562 (1.1750) time: 0.5049 [2021-03-25 21:35:35 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 630/1251] eta: 0:05:17 lr: 0.000750 loss: 3.4721 (3.4782) grad_norm: 1.1440 (1.1755) time: 0.5019 [2021-03-25 21:35:40 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 640/1251] eta: 0:05:12 lr: 0.000750 loss: 3.3846 (3.4794) grad_norm: 1.2116 (1.1772) time: 0.5091 [2021-03-25 21:35:45 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 650/1251] eta: 0:05:07 lr: 0.000750 loss: 3.4932 (3.4796) grad_norm: 1.2116 (1.1774) time: 0.5077 [2021-03-25 21:35:50 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 660/1251] eta: 0:05:02 lr: 0.000750 loss: 3.7798 (3.4847) grad_norm: 1.1703 (1.1773) time: 0.5026 [2021-03-25 21:35:55 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 670/1251] eta: 0:04:57 lr: 0.000750 loss: 3.8264 (3.4890) grad_norm: 1.1638 (1.1768) time: 0.5069 [2021-03-25 21:36:00 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 680/1251] eta: 0:04:52 lr: 0.000750 loss: 3.6856 (3.4892) grad_norm: 1.1523 (1.1765) time: 0.5050 [2021-03-25 21:36:05 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 690/1251] eta: 0:04:46 lr: 0.000750 loss: 3.6898 (3.4895) grad_norm: 1.0896 (1.1752) time: 0.5017 [2021-03-25 21:36:10 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 700/1251] eta: 0:04:41 lr: 0.000750 loss: 3.7119 (3.4925) grad_norm: 1.0960 (1.1742) time: 0.5010 [2021-03-25 21:36:15 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 710/1251] eta: 0:04:36 lr: 0.000750 loss: 3.7257 (3.4930) grad_norm: 1.1145 (1.1741) time: 0.5037 [2021-03-25 21:36:20 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 720/1251] eta: 0:04:31 lr: 0.000750 loss: 3.4267 (3.4889) grad_norm: 1.1326 (1.1736) time: 0.5077 [2021-03-25 21:36:26 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 730/1251] eta: 0:04:26 lr: 0.000750 loss: 3.2302 (3.4888) grad_norm: 1.1582 (1.1748) time: 0.5088 [2021-03-25 21:36:31 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 740/1251] eta: 0:04:21 lr: 0.000750 loss: 3.3337 (3.4872) grad_norm: 1.1864 (1.1751) time: 0.5232 [2021-03-25 21:36:36 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 750/1251] eta: 0:04:16 lr: 0.000750 loss: 3.1484 (3.4862) grad_norm: 1.1311 (1.1748) time: 0.5249 [2021-03-25 21:36:41 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 760/1251] eta: 0:04:11 lr: 0.000750 loss: 3.5488 (3.4848) grad_norm: 1.1311 (1.1747) time: 0.5104 [2021-03-25 21:36:46 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 770/1251] eta: 0:04:05 lr: 0.000750 loss: 3.5791 (3.4858) grad_norm: 1.1235 (1.1745) time: 0.5077 [2021-03-25 21:36:51 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 780/1251] eta: 0:04:00 lr: 0.000750 loss: 3.4184 (3.4830) grad_norm: 1.1008 (1.1736) time: 0.5037 [2021-03-25 21:36:56 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 790/1251] eta: 0:03:55 lr: 0.000750 loss: 3.4541 (3.4844) grad_norm: 1.1363 (1.1741) time: 0.5049 [2021-03-25 21:37:01 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 800/1251] eta: 0:03:50 lr: 0.000750 loss: 3.6435 (3.4856) grad_norm: 1.1579 (1.1741) time: 0.5056 [2021-03-25 21:37:06 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 810/1251] eta: 0:03:45 lr: 0.000750 loss: 3.5029 (3.4831) grad_norm: 1.1381 (1.1734) time: 0.5069 [2021-03-25 21:37:12 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 820/1251] eta: 0:03:40 lr: 0.000750 loss: 3.2215 (3.4811) grad_norm: 1.1285 (1.1728) time: 0.5108 [2021-03-25 21:37:17 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 830/1251] eta: 0:03:35 lr: 0.000750 loss: 3.1295 (3.4778) grad_norm: 1.1608 (1.1729) time: 0.5103 [2021-03-25 21:37:22 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 840/1251] eta: 0:03:29 lr: 0.000749 loss: 3.6552 (3.4809) grad_norm: 1.1551 (1.1721) time: 0.5073 [2021-03-25 21:37:27 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 850/1251] eta: 0:03:24 lr: 0.000749 loss: 3.6714 (3.4811) grad_norm: 1.1036 (1.1717) time: 0.5084 [2021-03-25 21:37:32 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 860/1251] eta: 0:03:19 lr: 0.000749 loss: 3.4145 (3.4799) grad_norm: 1.1382 (1.1726) time: 0.5083 [2021-03-25 21:37:37 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 870/1251] eta: 0:03:14 lr: 0.000749 loss: 3.4863 (3.4793) grad_norm: 1.1622 (1.1722) time: 0.5011 [2021-03-25 21:37:42 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 880/1251] eta: 0:03:09 lr: 0.000749 loss: 3.6055 (3.4797) grad_norm: 1.1759 (1.1725) time: 0.5004 [2021-03-25 21:37:47 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 890/1251] eta: 0:03:04 lr: 0.000749 loss: 3.6265 (3.4813) grad_norm: 1.2043 (1.1726) time: 0.5035 [2021-03-25 21:37:52 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 900/1251] eta: 0:02:59 lr: 0.000749 loss: 3.6429 (3.4836) grad_norm: 1.1674 (1.1726) time: 0.5050 [2021-03-25 21:37:57 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 910/1251] eta: 0:02:54 lr: 0.000749 loss: 3.6370 (3.4819) grad_norm: 1.1177 (1.1725) time: 0.5079 [2021-03-25 21:38:02 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 920/1251] eta: 0:02:48 lr: 0.000749 loss: 3.2696 (3.4814) grad_norm: 1.2009 (1.1736) time: 0.5068 [2021-03-25 21:38:07 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 930/1251] eta: 0:02:43 lr: 0.000749 loss: 3.5227 (3.4834) grad_norm: 1.2009 (1.1733) time: 0.5051 [2021-03-25 21:38:12 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 940/1251] eta: 0:02:38 lr: 0.000749 loss: 3.8201 (3.4864) grad_norm: 1.1634 (1.1739) time: 0.5079 [2021-03-25 21:38:17 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 950/1251] eta: 0:02:33 lr: 0.000749 loss: 3.7105 (3.4867) grad_norm: 1.1403 (1.1736) time: 0.5097 [2021-03-25 21:38:22 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 960/1251] eta: 0:02:28 lr: 0.000749 loss: 3.5454 (3.4863) grad_norm: 1.0974 (1.1729) time: 0.5032 [2021-03-25 21:38:27 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 970/1251] eta: 0:02:23 lr: 0.000749 loss: 3.5865 (3.4873) grad_norm: 1.0897 (1.1724) time: 0.4999 [2021-03-25 21:38:33 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 980/1251] eta: 0:02:18 lr: 0.000749 loss: 3.5227 (3.4856) grad_norm: 1.1042 (1.1719) time: 0.5076 [2021-03-25 21:38:38 swin_small_patch4_window7_224] INFO: Epoch: [100] [ 990/1251] eta: 0:02:13 lr: 0.000749 loss: 3.4095 (3.4836) grad_norm: 1.1211 (1.1721) time: 0.5109 [2021-03-25 21:38:43 swin_small_patch4_window7_224] INFO: Epoch: [100] [1000/1251] eta: 0:02:08 lr: 0.000749 loss: 3.4095 (3.4826) grad_norm: 1.1549 (1.1722) time: 0.5065 [2021-03-25 21:38:48 swin_small_patch4_window7_224] INFO: Epoch: [100] [1010/1251] eta: 0:02:02 lr: 0.000749 loss: 3.3565 (3.4812) grad_norm: 1.1330 (1.1719) time: 0.5064 [2021-03-25 21:38:53 swin_small_patch4_window7_224] INFO: Epoch: [100] [1020/1251] eta: 0:01:57 lr: 0.000749 loss: 3.6118 (3.4816) grad_norm: 1.1345 (1.1721) time: 0.5085 [2021-03-25 21:38:58 swin_small_patch4_window7_224] INFO: Epoch: [100] [1030/1251] eta: 0:01:52 lr: 0.000749 loss: 3.5735 (3.4803) grad_norm: 1.0702 (1.1712) time: 0.5065 [2021-03-25 21:39:03 swin_small_patch4_window7_224] INFO: Epoch: [100] [1040/1251] eta: 0:01:47 lr: 0.000749 loss: 3.5510 (3.4815) grad_norm: 1.0867 (1.1712) time: 0.5082 [2021-03-25 21:39:08 swin_small_patch4_window7_224] INFO: Epoch: [100] [1050/1251] eta: 0:01:42 lr: 0.000749 loss: 3.4700 (3.4797) grad_norm: 1.2023 (1.1718) time: 0.5039 [2021-03-25 21:39:13 swin_small_patch4_window7_224] INFO: Epoch: [100] [1060/1251] eta: 0:01:37 lr: 0.000749 loss: 3.6207 (3.4821) grad_norm: 1.2306 (1.1719) time: 0.5045 [2021-03-25 21:39:18 swin_small_patch4_window7_224] INFO: Epoch: [100] [1070/1251] eta: 0:01:32 lr: 0.000749 loss: 3.7264 (3.4839) grad_norm: 1.1722 (1.1717) time: 0.5051 [2021-03-25 21:39:23 swin_small_patch4_window7_224] INFO: Epoch: [100] [1080/1251] eta: 0:01:27 lr: 0.000749 loss: 3.6241 (3.4852) grad_norm: 1.1049 (1.1711) time: 0.5034 [2021-03-25 21:39:28 swin_small_patch4_window7_224] INFO: Epoch: [100] [1090/1251] eta: 0:01:22 lr: 0.000749 loss: 3.6413 (3.4875) grad_norm: 1.1554 (1.1718) time: 0.5061 [2021-03-25 21:39:33 swin_small_patch4_window7_224] INFO: Epoch: [100] [1100/1251] eta: 0:01:16 lr: 0.000749 loss: 3.5796 (3.4849) grad_norm: 1.1777 (1.1721) time: 0.5036 [2021-03-25 21:39:38 swin_small_patch4_window7_224] INFO: Epoch: [100] [1110/1251] eta: 0:01:11 lr: 0.000749 loss: 3.1466 (3.4845) grad_norm: 1.1755 (1.1723) time: 0.5022 [2021-03-25 21:39:43 swin_small_patch4_window7_224] INFO: Epoch: [100] [1120/1251] eta: 0:01:06 lr: 0.000748 loss: 3.4464 (3.4839) grad_norm: 1.1648 (1.1726) time: 0.5023 [2021-03-25 21:39:48 swin_small_patch4_window7_224] INFO: Epoch: [100] [1130/1251] eta: 0:01:01 lr: 0.000748 loss: 3.7328 (3.4860) grad_norm: 1.1607 (1.1724) time: 0.5062 [2021-03-25 21:39:53 swin_small_patch4_window7_224] INFO: Epoch: [100] [1140/1251] eta: 0:00:56 lr: 0.000748 loss: 3.7348 (3.4874) grad_norm: 1.1322 (1.1723) time: 0.5055 [2021-03-25 21:39:58 swin_small_patch4_window7_224] INFO: Epoch: [100] [1150/1251] eta: 0:00:51 lr: 0.000748 loss: 3.4191 (3.4861) grad_norm: 1.1642 (1.1726) time: 0.4983 [2021-03-25 21:40:03 swin_small_patch4_window7_224] INFO: Epoch: [100] [1160/1251] eta: 0:00:46 lr: 0.000748 loss: 3.2792 (3.4852) grad_norm: 1.2055 (1.1726) time: 0.4968 [2021-03-25 21:40:08 swin_small_patch4_window7_224] INFO: Epoch: [100] [1170/1251] eta: 0:00:41 lr: 0.000748 loss: 3.4867 (3.4858) grad_norm: 1.1475 (1.1729) time: 0.5021 [2021-03-25 21:40:13 swin_small_patch4_window7_224] INFO: Epoch: [100] [1180/1251] eta: 0:00:36 lr: 0.000748 loss: 3.4867 (3.4855) grad_norm: 1.2029 (1.1738) time: 0.5056 [2021-03-25 21:40:19 swin_small_patch4_window7_224] INFO: Epoch: [100] [1190/1251] eta: 0:00:31 lr: 0.000748 loss: 3.4046 (3.4843) grad_norm: 1.1621 (1.1738) time: 0.5081 [2021-03-25 21:40:24 swin_small_patch4_window7_224] INFO: Epoch: [100] [1200/1251] eta: 0:00:25 lr: 0.000748 loss: 3.5119 (3.4841) grad_norm: 1.1498 (1.1740) time: 0.5029 [2021-03-25 21:40:29 swin_small_patch4_window7_224] INFO: Epoch: [100] [1210/1251] eta: 0:00:20 lr: 0.000748 loss: 3.6477 (3.4859) grad_norm: 1.1478 (1.1737) time: 0.4990 [2021-03-25 21:40:34 swin_small_patch4_window7_224] INFO: Epoch: [100] [1220/1251] eta: 0:00:15 lr: 0.000748 loss: 3.5002 (3.4841) grad_norm: 1.1381 (1.1733) time: 0.5036 [2021-03-25 21:40:39 swin_small_patch4_window7_224] INFO: Epoch: [100] [1230/1251] eta: 0:00:10 lr: 0.000748 loss: 3.2036 (3.4831) grad_norm: 1.1249 (1.1732) time: 0.5056 [2021-03-25 21:40:44 swin_small_patch4_window7_224] INFO: Epoch: [100] [1240/1251] eta: 0:00:05 lr: 0.000748 loss: 3.6155 (3.4843) grad_norm: 1.1491 (1.1733) time: 0.5073 [2021-03-25 21:40:49 swin_small_patch4_window7_224] INFO: Epoch: [100] [1250/1251] eta: 0:00:00 lr: 0.000748 loss: 3.7205 (3.4847) grad_norm: 1.1773 (1.1737) time: 0.5087 [2021-03-25 21:41:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 1.2083 (1.2083) acc1: 73.4375 (73.4375) acc5: 87.5000 (87.5000) [2021-03-25 21:41:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.9418 (0.9707) acc1: 76.5625 (77.5568) acc5: 95.3125 (94.0341) [2021-03-25 21:41:39 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.9418 (0.9885) acc1: 78.1250 (77.6786) acc5: 95.3125 (93.8988) [2021-03-25 21:41:40 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0262 (1.0377) acc1: 75.0000 (76.3105) acc5: 92.1875 (93.3972) [2021-03-25 21:41:41 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0082 (1.0201) acc1: 76.5625 (76.6387) acc5: 93.7500 (93.5976) [2021-03-25 21:41:42 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0460 (1.0368) acc1: 76.5625 (76.1600) acc5: 93.7500 (93.4400) [2021-03-25 21:41:47 swin_small_patch4_window7_224] INFO: * Acc@1 76.144 Acc@5 93.370 loss 1.030 [2021-03-25 21:41:47 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.1% [2021-03-25 21:41:47 swin_small_patch4_window7_224] INFO: Max accuracy: 76.14% [2021-03-25 21:41:51 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 0/1251] eta: 1:32:02 lr: 0.000748 loss: 3.1425 (3.1425) grad_norm: 1.0868 (1.0868) time: 4.4141 [2021-03-25 21:41:57 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 10/1251] eta: 0:17:54 lr: 0.000748 loss: 3.4064 (3.3193) grad_norm: 1.1348 (1.2203) time: 0.8660 [2021-03-25 21:42:02 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 20/1251] eta: 0:14:13 lr: 0.000748 loss: 3.3881 (3.2427) grad_norm: 1.1507 (1.1971) time: 0.5072 [2021-03-25 21:42:07 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 30/1251] eta: 0:12:54 lr: 0.000748 loss: 3.1649 (3.2317) grad_norm: 1.1882 (1.2032) time: 0.5069 [2021-03-25 21:42:12 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 40/1251] eta: 0:12:09 lr: 0.000748 loss: 3.4842 (3.3676) grad_norm: 1.1729 (1.1888) time: 0.5063 [2021-03-25 21:42:17 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 50/1251] eta: 0:11:39 lr: 0.000748 loss: 3.7609 (3.4108) grad_norm: 1.1269 (1.1871) time: 0.5029 [2021-03-25 21:42:22 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 60/1251] eta: 0:11:19 lr: 0.000748 loss: 3.7431 (3.4470) grad_norm: 1.1482 (1.1851) time: 0.5065 [2021-03-25 21:42:27 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 70/1251] eta: 0:11:05 lr: 0.000748 loss: 3.6423 (3.4547) grad_norm: 1.1529 (1.1853) time: 0.5132 [2021-03-25 21:42:32 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 80/1251] eta: 0:10:50 lr: 0.000748 loss: 3.6423 (3.4694) grad_norm: 1.1474 (1.1786) time: 0.5087 [2021-03-25 21:42:37 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 90/1251] eta: 0:10:37 lr: 0.000748 loss: 3.5739 (3.4671) grad_norm: 1.1546 (1.1823) time: 0.5007 [2021-03-25 21:42:42 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 100/1251] eta: 0:10:27 lr: 0.000748 loss: 3.4309 (3.4769) grad_norm: 1.2185 (1.1866) time: 0.5022 [2021-03-25 21:42:47 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 110/1251] eta: 0:10:18 lr: 0.000748 loss: 3.4309 (3.4856) grad_norm: 1.2185 (1.1903) time: 0.5085 [2021-03-25 21:42:52 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 120/1251] eta: 0:10:09 lr: 0.000748 loss: 3.5117 (3.4875) grad_norm: 1.0775 (1.1810) time: 0.5067 [2021-03-25 21:42:57 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 130/1251] eta: 0:10:01 lr: 0.000748 loss: 3.5117 (3.4871) grad_norm: 1.0582 (1.1766) time: 0.5060 [2021-03-25 21:43:02 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 140/1251] eta: 0:09:53 lr: 0.000747 loss: 3.5605 (3.4901) grad_norm: 1.1499 (1.1769) time: 0.5059 [2021-03-25 21:43:07 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 150/1251] eta: 0:09:45 lr: 0.000747 loss: 3.6177 (3.4935) grad_norm: 1.1655 (1.1779) time: 0.4994 [2021-03-25 21:43:12 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 160/1251] eta: 0:09:38 lr: 0.000747 loss: 3.6177 (3.4967) grad_norm: 1.1169 (1.1766) time: 0.5029 [2021-03-25 21:43:17 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 170/1251] eta: 0:09:31 lr: 0.000747 loss: 3.6136 (3.4941) grad_norm: 1.0982 (1.1750) time: 0.5063 [2021-03-25 21:43:23 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 180/1251] eta: 0:09:25 lr: 0.000747 loss: 3.5965 (3.4983) grad_norm: 1.1430 (1.1730) time: 0.5089 [2021-03-25 21:43:28 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 190/1251] eta: 0:09:18 lr: 0.000747 loss: 3.5910 (3.4969) grad_norm: 1.1396 (1.1721) time: 0.5069 [2021-03-25 21:43:33 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 200/1251] eta: 0:09:12 lr: 0.000747 loss: 3.5640 (3.4964) grad_norm: 1.1321 (1.1697) time: 0.5110 [2021-03-25 21:43:38 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 210/1251] eta: 0:09:06 lr: 0.000747 loss: 3.3911 (3.4856) grad_norm: 1.1268 (1.1712) time: 0.5065 [2021-03-25 21:43:43 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 220/1251] eta: 0:09:00 lr: 0.000747 loss: 3.2949 (3.4834) grad_norm: 1.1503 (1.1700) time: 0.5016 [2021-03-25 21:43:48 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 230/1251] eta: 0:08:54 lr: 0.000747 loss: 3.7180 (3.4901) grad_norm: 1.1521 (1.1726) time: 0.5098 [2021-03-25 21:43:53 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 240/1251] eta: 0:08:48 lr: 0.000747 loss: 3.5723 (3.4806) grad_norm: 1.1677 (1.1709) time: 0.5081 [2021-03-25 21:43:58 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 250/1251] eta: 0:08:42 lr: 0.000747 loss: 3.1339 (3.4708) grad_norm: 1.1083 (1.1693) time: 0.5052 [2021-03-25 21:44:03 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 260/1251] eta: 0:08:36 lr: 0.000747 loss: 3.3484 (3.4703) grad_norm: 1.0713 (1.1647) time: 0.5046 [2021-03-25 21:44:08 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 270/1251] eta: 0:08:30 lr: 0.000747 loss: 3.5635 (3.4683) grad_norm: 1.0500 (1.1648) time: 0.5057 [2021-03-25 21:44:13 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 280/1251] eta: 0:08:24 lr: 0.000747 loss: 3.4956 (3.4729) grad_norm: 1.2198 (1.1673) time: 0.5015 [2021-03-25 21:44:18 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 290/1251] eta: 0:08:19 lr: 0.000747 loss: 3.4956 (3.4716) grad_norm: 1.1915 (1.1672) time: 0.5008 [2021-03-25 21:44:23 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 300/1251] eta: 0:08:13 lr: 0.000747 loss: 3.5750 (3.4717) grad_norm: 1.1237 (1.1656) time: 0.5047 [2021-03-25 21:44:28 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 310/1251] eta: 0:08:07 lr: 0.000747 loss: 3.5907 (3.4723) grad_norm: 1.0826 (1.1657) time: 0.5075 [2021-03-25 21:44:33 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 320/1251] eta: 0:08:02 lr: 0.000747 loss: 3.5845 (3.4723) grad_norm: 1.1788 (1.1671) time: 0.5135 [2021-03-25 21:44:39 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 330/1251] eta: 0:07:57 lr: 0.000747 loss: 3.5845 (3.4747) grad_norm: 1.1495 (1.1660) time: 0.5102 [2021-03-25 21:44:44 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 340/1251] eta: 0:07:51 lr: 0.000747 loss: 3.5444 (3.4756) grad_norm: 1.1026 (1.1647) time: 0.5047 [2021-03-25 21:44:49 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 350/1251] eta: 0:07:46 lr: 0.000747 loss: 3.4984 (3.4732) grad_norm: 1.1345 (1.1653) time: 0.5074 [2021-03-25 21:44:54 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 360/1251] eta: 0:07:40 lr: 0.000747 loss: 3.3249 (3.4702) grad_norm: 1.1956 (1.1670) time: 0.5079 [2021-03-25 21:44:59 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 370/1251] eta: 0:07:35 lr: 0.000747 loss: 3.5898 (3.4700) grad_norm: 1.2276 (1.1687) time: 0.5080 [2021-03-25 21:45:04 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 380/1251] eta: 0:07:29 lr: 0.000747 loss: 3.5775 (3.4679) grad_norm: 1.2276 (1.1702) time: 0.5042 [2021-03-25 21:45:09 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 390/1251] eta: 0:07:24 lr: 0.000747 loss: 3.3882 (3.4630) grad_norm: 1.1683 (1.1708) time: 0.5019 [2021-03-25 21:45:14 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 400/1251] eta: 0:07:19 lr: 0.000747 loss: 3.4557 (3.4636) grad_norm: 1.1610 (1.1704) time: 0.5068 [2021-03-25 21:45:19 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 410/1251] eta: 0:07:13 lr: 0.000747 loss: 3.5672 (3.4664) grad_norm: 1.1191 (1.1695) time: 0.5075 [2021-03-25 21:45:24 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 420/1251] eta: 0:07:08 lr: 0.000746 loss: 3.3926 (3.4595) grad_norm: 1.0986 (1.1697) time: 0.5085 [2021-03-25 21:45:29 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 430/1251] eta: 0:07:02 lr: 0.000746 loss: 3.5081 (3.4645) grad_norm: 1.0941 (1.1678) time: 0.5027 [2021-03-25 21:45:34 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 440/1251] eta: 0:06:57 lr: 0.000746 loss: 3.6833 (3.4667) grad_norm: 1.0839 (1.1671) time: 0.5002 [2021-03-25 21:45:39 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 450/1251] eta: 0:06:52 lr: 0.000746 loss: 3.4823 (3.4648) grad_norm: 1.0750 (1.1652) time: 0.5079 [2021-03-25 21:45:44 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 460/1251] eta: 0:06:47 lr: 0.000746 loss: 3.4573 (3.4696) grad_norm: 1.0971 (1.1647) time: 0.5083 [2021-03-25 21:45:49 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 470/1251] eta: 0:06:41 lr: 0.000746 loss: 3.4806 (3.4659) grad_norm: 1.1725 (1.1678) time: 0.5043 [2021-03-25 21:45:54 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 480/1251] eta: 0:06:36 lr: 0.000746 loss: 3.6010 (3.4676) grad_norm: 1.2236 (1.1684) time: 0.5021 [2021-03-25 21:45:59 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 490/1251] eta: 0:06:31 lr: 0.000746 loss: 3.6761 (3.4693) grad_norm: 1.0809 (1.1669) time: 0.5055 [2021-03-25 21:46:04 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 500/1251] eta: 0:06:25 lr: 0.000746 loss: 3.5349 (3.4668) grad_norm: 1.0940 (1.1657) time: 0.5029 [2021-03-25 21:46:10 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 510/1251] eta: 0:06:20 lr: 0.000746 loss: 3.5911 (3.4714) grad_norm: 1.1369 (1.1665) time: 0.5067 [2021-03-25 21:46:15 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 520/1251] eta: 0:06:15 lr: 0.000746 loss: 3.6157 (3.4693) grad_norm: 1.1451 (1.1660) time: 0.5094 [2021-03-25 21:46:20 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 530/1251] eta: 0:06:10 lr: 0.000746 loss: 3.5123 (3.4697) grad_norm: 1.0941 (1.1650) time: 0.5023 [2021-03-25 21:46:25 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 540/1251] eta: 0:06:04 lr: 0.000746 loss: 3.5488 (3.4690) grad_norm: 1.0957 (1.1641) time: 0.5065 [2021-03-25 21:46:30 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 550/1251] eta: 0:05:59 lr: 0.000746 loss: 3.6269 (3.4727) grad_norm: 1.1101 (1.1640) time: 0.5167 [2021-03-25 21:46:35 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 560/1251] eta: 0:05:54 lr: 0.000746 loss: 3.7134 (3.4777) grad_norm: 1.0902 (1.1640) time: 0.5175 [2021-03-25 21:46:40 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 570/1251] eta: 0:05:49 lr: 0.000746 loss: 3.7816 (3.4819) grad_norm: 1.1848 (1.1656) time: 0.5124 [2021-03-25 21:46:45 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 580/1251] eta: 0:05:44 lr: 0.000746 loss: 3.5113 (3.4791) grad_norm: 1.1959 (1.1658) time: 0.5040 [2021-03-25 21:46:50 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 590/1251] eta: 0:05:39 lr: 0.000746 loss: 3.5113 (3.4812) grad_norm: 1.1464 (1.1651) time: 0.5017 [2021-03-25 21:46:55 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 600/1251] eta: 0:05:33 lr: 0.000746 loss: 3.5952 (3.4797) grad_norm: 1.1420 (1.1646) time: 0.5019 [2021-03-25 21:47:00 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 610/1251] eta: 0:05:28 lr: 0.000746 loss: 3.3561 (3.4801) grad_norm: 1.1640 (1.1645) time: 0.5041 [2021-03-25 21:47:06 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 620/1251] eta: 0:05:23 lr: 0.000746 loss: 3.7005 (3.4829) grad_norm: 1.0830 (1.1635) time: 0.5145 [2021-03-25 21:47:11 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 630/1251] eta: 0:05:18 lr: 0.000746 loss: 3.6345 (3.4825) grad_norm: 1.0822 (1.1636) time: 0.5136 [2021-03-25 21:47:16 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 640/1251] eta: 0:05:13 lr: 0.000746 loss: 3.5597 (3.4829) grad_norm: 1.0988 (1.1630) time: 0.5092 [2021-03-25 21:47:21 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 650/1251] eta: 0:05:08 lr: 0.000746 loss: 3.4746 (3.4815) grad_norm: 1.0940 (1.1626) time: 0.5067 [2021-03-25 21:47:26 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 660/1251] eta: 0:05:02 lr: 0.000746 loss: 3.4744 (3.4808) grad_norm: 1.2162 (1.1638) time: 0.5044 [2021-03-25 21:47:31 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 670/1251] eta: 0:04:57 lr: 0.000746 loss: 3.2831 (3.4753) grad_norm: 1.2224 (1.1645) time: 0.5007 [2021-03-25 21:47:36 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 680/1251] eta: 0:04:52 lr: 0.000746 loss: 3.2779 (3.4727) grad_norm: 1.2152 (1.1653) time: 0.5032 [2021-03-25 21:47:41 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 690/1251] eta: 0:04:47 lr: 0.000746 loss: 3.4933 (3.4744) grad_norm: 1.1775 (1.1651) time: 0.5095 [2021-03-25 21:47:46 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 700/1251] eta: 0:04:42 lr: 0.000745 loss: 3.6731 (3.4775) grad_norm: 1.1775 (1.1661) time: 0.5071 [2021-03-25 21:47:51 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 710/1251] eta: 0:04:36 lr: 0.000745 loss: 3.8371 (3.4803) grad_norm: 1.1485 (1.1660) time: 0.4985 [2021-03-25 21:47:56 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 720/1251] eta: 0:04:31 lr: 0.000745 loss: 3.8103 (3.4810) grad_norm: 1.1469 (1.1663) time: 0.4985 [2021-03-25 21:48:01 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 730/1251] eta: 0:04:26 lr: 0.000745 loss: 3.5811 (3.4814) grad_norm: 1.1381 (1.1662) time: 0.5068 [2021-03-25 21:48:06 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 740/1251] eta: 0:04:21 lr: 0.000745 loss: 3.5354 (3.4796) grad_norm: 1.1360 (inf) time: 0.5230 [2021-03-25 21:48:12 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 750/1251] eta: 0:04:16 lr: 0.000745 loss: 3.5354 (3.4807) grad_norm: 1.0932 (inf) time: 0.5232 [2021-03-25 21:48:17 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 760/1251] eta: 0:04:11 lr: 0.000745 loss: 3.5929 (3.4838) grad_norm: 1.1115 (inf) time: 0.5167 [2021-03-25 21:48:22 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 770/1251] eta: 0:04:06 lr: 0.000745 loss: 3.6516 (3.4852) grad_norm: 1.1115 (inf) time: 0.5145 [2021-03-25 21:48:27 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 780/1251] eta: 0:04:01 lr: 0.000745 loss: 3.8687 (3.4901) grad_norm: 1.1390 (inf) time: 0.5106 [2021-03-25 21:48:32 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 790/1251] eta: 0:03:56 lr: 0.000745 loss: 3.8351 (3.4928) grad_norm: 1.2104 (inf) time: 0.5119 [2021-03-25 21:48:37 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 800/1251] eta: 0:03:50 lr: 0.000745 loss: 3.4768 (3.4892) grad_norm: 1.1839 (inf) time: 0.5038 [2021-03-25 21:48:42 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 810/1251] eta: 0:03:45 lr: 0.000745 loss: 3.3338 (3.4882) grad_norm: 1.1489 (inf) time: 0.5041 [2021-03-25 21:48:47 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 820/1251] eta: 0:03:40 lr: 0.000745 loss: 3.4608 (3.4870) grad_norm: 1.1323 (inf) time: 0.5103 [2021-03-25 21:48:52 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 830/1251] eta: 0:03:35 lr: 0.000745 loss: 3.4608 (3.4853) grad_norm: 1.1204 (inf) time: 0.5121 [2021-03-25 21:48:58 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 840/1251] eta: 0:03:30 lr: 0.000745 loss: 3.4893 (3.4863) grad_norm: 1.1404 (inf) time: 0.5146 [2021-03-25 21:49:03 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 850/1251] eta: 0:03:25 lr: 0.000745 loss: 3.6528 (3.4891) grad_norm: 1.1246 (inf) time: 0.5114 [2021-03-25 21:49:08 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 860/1251] eta: 0:03:20 lr: 0.000745 loss: 3.7518 (3.4911) grad_norm: 1.1223 (inf) time: 0.5039 [2021-03-25 21:49:13 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 870/1251] eta: 0:03:14 lr: 0.000745 loss: 3.7152 (3.4893) grad_norm: 1.1223 (inf) time: 0.5076 [2021-03-25 21:49:18 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 880/1251] eta: 0:03:09 lr: 0.000745 loss: 3.4758 (3.4857) grad_norm: 1.1839 (inf) time: 0.5123 [2021-03-25 21:49:23 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 890/1251] eta: 0:03:04 lr: 0.000745 loss: 3.4991 (3.4870) grad_norm: 1.1352 (inf) time: 0.5079 [2021-03-25 21:49:28 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 900/1251] eta: 0:02:59 lr: 0.000745 loss: 3.5042 (3.4856) grad_norm: 1.1337 (inf) time: 0.5051 [2021-03-25 21:49:33 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 910/1251] eta: 0:02:54 lr: 0.000745 loss: 3.2686 (3.4840) grad_norm: 1.1340 (inf) time: 0.5020 [2021-03-25 21:49:38 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 920/1251] eta: 0:02:49 lr: 0.000745 loss: 3.3985 (3.4841) grad_norm: 1.1214 (inf) time: 0.5045 [2021-03-25 21:49:43 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 930/1251] eta: 0:02:44 lr: 0.000745 loss: 3.3810 (3.4812) grad_norm: 1.1206 (inf) time: 0.5020 [2021-03-25 21:49:48 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 940/1251] eta: 0:02:38 lr: 0.000745 loss: 3.6941 (3.4858) grad_norm: 1.1206 (inf) time: 0.5021 [2021-03-25 21:49:53 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 950/1251] eta: 0:02:33 lr: 0.000745 loss: 3.7889 (3.4871) grad_norm: 1.1761 (inf) time: 0.5099 [2021-03-25 21:49:58 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 960/1251] eta: 0:02:28 lr: 0.000745 loss: 3.5358 (3.4867) grad_norm: 1.1738 (inf) time: 0.5058 [2021-03-25 21:50:03 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 970/1251] eta: 0:02:23 lr: 0.000744 loss: 3.6133 (3.4876) grad_norm: 1.1531 (inf) time: 0.5038 [2021-03-25 21:50:08 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 980/1251] eta: 0:02:18 lr: 0.000744 loss: 3.6015 (3.4884) grad_norm: 1.1531 (inf) time: 0.5089 [2021-03-25 21:50:14 swin_small_patch4_window7_224] INFO: Epoch: [101] [ 990/1251] eta: 0:02:13 lr: 0.000744 loss: 3.5642 (3.4870) grad_norm: 1.1718 (inf) time: 0.5107 [2021-03-25 21:50:19 swin_small_patch4_window7_224] INFO: Epoch: [101] [1000/1251] eta: 0:02:08 lr: 0.000744 loss: 3.5014 (3.4878) grad_norm: 1.1325 (inf) time: 0.5035 [2021-03-25 21:50:24 swin_small_patch4_window7_224] INFO: Epoch: [101] [1010/1251] eta: 0:02:03 lr: 0.000744 loss: 3.4731 (3.4866) grad_norm: 1.1163 (inf) time: 0.5024 [2021-03-25 21:50:29 swin_small_patch4_window7_224] INFO: Epoch: [101] [1020/1251] eta: 0:01:57 lr: 0.000744 loss: 3.5885 (3.4875) grad_norm: 1.1698 (inf) time: 0.5069 [2021-03-25 21:50:34 swin_small_patch4_window7_224] INFO: Epoch: [101] [1030/1251] eta: 0:01:52 lr: 0.000744 loss: 3.5282 (3.4862) grad_norm: 1.1834 (inf) time: 0.5125 [2021-03-25 21:50:39 swin_small_patch4_window7_224] INFO: Epoch: [101] [1040/1251] eta: 0:01:47 lr: 0.000744 loss: 3.3005 (3.4845) grad_norm: 1.0774 (inf) time: 0.5136 [2021-03-25 21:50:44 swin_small_patch4_window7_224] INFO: Epoch: [101] [1050/1251] eta: 0:01:42 lr: 0.000744 loss: 3.7133 (3.4881) grad_norm: 1.0726 (inf) time: 0.5041 [2021-03-25 21:50:49 swin_small_patch4_window7_224] INFO: Epoch: [101] [1060/1251] eta: 0:01:37 lr: 0.000744 loss: 3.7295 (3.4890) grad_norm: 1.1048 (inf) time: 0.4997 [2021-03-25 21:50:54 swin_small_patch4_window7_224] INFO: Epoch: [101] [1070/1251] eta: 0:01:32 lr: 0.000744 loss: 3.5938 (3.4875) grad_norm: 1.1535 (inf) time: 0.5121 [2021-03-25 21:50:59 swin_small_patch4_window7_224] INFO: Epoch: [101] [1080/1251] eta: 0:01:27 lr: 0.000744 loss: 3.5960 (3.4891) grad_norm: 1.1605 (inf) time: 0.5159 [2021-03-25 21:51:04 swin_small_patch4_window7_224] INFO: Epoch: [101] [1090/1251] eta: 0:01:22 lr: 0.000744 loss: 3.5761 (3.4887) grad_norm: 1.2893 (inf) time: 0.5077 [2021-03-25 21:51:09 swin_small_patch4_window7_224] INFO: Epoch: [101] [1100/1251] eta: 0:01:17 lr: 0.000744 loss: 3.5428 (3.4898) grad_norm: 1.2807 (inf) time: 0.5056 [2021-03-25 21:51:14 swin_small_patch4_window7_224] INFO: Epoch: [101] [1110/1251] eta: 0:01:11 lr: 0.000744 loss: 3.6738 (3.4898) grad_norm: 1.1781 (inf) time: 0.5030 [2021-03-25 21:51:19 swin_small_patch4_window7_224] INFO: Epoch: [101] [1120/1251] eta: 0:01:06 lr: 0.000744 loss: 3.6797 (3.4916) grad_norm: 1.1398 (inf) time: 0.5064 [2021-03-25 21:51:24 swin_small_patch4_window7_224] INFO: Epoch: [101] [1130/1251] eta: 0:01:01 lr: 0.000744 loss: 3.7864 (3.4930) grad_norm: 1.1179 (inf) time: 0.5050 [2021-03-25 21:51:30 swin_small_patch4_window7_224] INFO: Epoch: [101] [1140/1251] eta: 0:00:56 lr: 0.000744 loss: 3.6292 (3.4919) grad_norm: 1.1342 (inf) time: 0.5078 [2021-03-25 21:51:35 swin_small_patch4_window7_224] INFO: Epoch: [101] [1150/1251] eta: 0:00:51 lr: 0.000744 loss: 3.4213 (3.4900) grad_norm: 1.1867 (inf) time: 0.5105 [2021-03-25 21:51:40 swin_small_patch4_window7_224] INFO: Epoch: [101] [1160/1251] eta: 0:00:46 lr: 0.000744 loss: 3.4860 (3.4902) grad_norm: 1.1208 (inf) time: 0.5025 [2021-03-25 21:51:45 swin_small_patch4_window7_224] INFO: Epoch: [101] [1170/1251] eta: 0:00:41 lr: 0.000744 loss: 3.7723 (3.4920) grad_norm: 1.1113 (inf) time: 0.4995 [2021-03-25 21:51:50 swin_small_patch4_window7_224] INFO: Epoch: [101] [1180/1251] eta: 0:00:36 lr: 0.000744 loss: 3.5809 (3.4907) grad_norm: 1.1229 (inf) time: 0.5010 [2021-03-25 21:51:55 swin_small_patch4_window7_224] INFO: Epoch: [101] [1190/1251] eta: 0:00:31 lr: 0.000744 loss: 3.5729 (3.4917) grad_norm: 1.1394 (inf) time: 0.5063 [2021-03-25 21:52:00 swin_small_patch4_window7_224] INFO: Epoch: [101] [1200/1251] eta: 0:00:26 lr: 0.000744 loss: 3.7096 (3.4936) grad_norm: 1.1067 (inf) time: 0.5101 [2021-03-25 21:52:05 swin_small_patch4_window7_224] INFO: Epoch: [101] [1210/1251] eta: 0:00:20 lr: 0.000744 loss: 3.6057 (3.4947) grad_norm: 1.1578 (inf) time: 0.5043 [2021-03-25 21:52:10 swin_small_patch4_window7_224] INFO: Epoch: [101] [1220/1251] eta: 0:00:15 lr: 0.000744 loss: 3.5053 (3.4940) grad_norm: 1.1786 (inf) time: 0.5037 [2021-03-25 21:52:15 swin_small_patch4_window7_224] INFO: Epoch: [101] [1230/1251] eta: 0:00:10 lr: 0.000744 loss: 3.6309 (3.4948) grad_norm: 1.1786 (inf) time: 0.5120 [2021-03-25 21:52:20 swin_small_patch4_window7_224] INFO: Epoch: [101] [1240/1251] eta: 0:00:05 lr: 0.000744 loss: 3.6457 (3.4954) grad_norm: 1.1989 (inf) time: 0.5057 [2021-03-25 21:52:25 swin_small_patch4_window7_224] INFO: Epoch: [101] [1250/1251] eta: 0:00:00 lr: 0.000743 loss: 3.5460 (3.4964) grad_norm: 1.1562 (inf) time: 0.4965 [2021-03-25 21:52:33 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:42 loss: 1.3069 (1.3069) acc1: 68.7500 (68.7500) acc5: 87.5000 (87.5000) [2021-03-25 21:52:36 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:22 loss: 1.0838 (1.0728) acc1: 75.0000 (74.4318) acc5: 93.7500 (92.8977) [2021-03-25 21:52:38 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.0446 (1.0451) acc1: 75.0000 (74.4048) acc5: 93.7500 (93.0804) [2021-03-25 21:52:41 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9591 (1.0209) acc1: 76.5625 (75.7056) acc5: 95.3125 (93.9516) [2021-03-25 21:52:42 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0179 (1.0377) acc1: 75.0000 (75.3811) acc5: 95.3125 (93.6357) [2021-03-25 21:52:43 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0596 (1.0360) acc1: 75.0000 (75.5840) acc5: 93.7500 (93.7280) [2021-03-25 21:52:48 swin_small_patch4_window7_224] INFO: * Acc@1 75.810 Acc@5 93.446 loss 1.029 [2021-03-25 21:52:48 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 75.8% [2021-03-25 21:52:48 swin_small_patch4_window7_224] INFO: Max accuracy: 76.14% [2021-03-25 21:52:52 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 0/1251] eta: 1:26:14 lr: 0.000743 loss: 4.0129 (4.0129) grad_norm: 1.2307 (1.2307) time: 4.1362 [2021-03-25 21:52:57 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 10/1251] eta: 0:17:43 lr: 0.000743 loss: 3.7539 (3.3765) grad_norm: 1.1822 (1.1629) time: 0.8567 [2021-03-25 21:53:02 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 20/1251] eta: 0:14:10 lr: 0.000743 loss: 3.2972 (3.3915) grad_norm: 1.1283 (1.1586) time: 0.5182 [2021-03-25 21:53:07 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 30/1251] eta: 0:12:51 lr: 0.000743 loss: 3.2972 (3.3618) grad_norm: 1.1154 (1.1436) time: 0.5077 [2021-03-25 21:53:12 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 40/1251] eta: 0:12:09 lr: 0.000743 loss: 3.5676 (3.4414) grad_norm: 1.0923 (1.1367) time: 0.5102 [2021-03-25 21:53:17 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 50/1251] eta: 0:11:39 lr: 0.000743 loss: 3.7990 (3.4723) grad_norm: 1.1628 (1.1512) time: 0.5068 [2021-03-25 21:53:22 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 60/1251] eta: 0:11:17 lr: 0.000743 loss: 3.4136 (3.4524) grad_norm: 1.1136 (1.1421) time: 0.5007 [2021-03-25 21:53:27 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 70/1251] eta: 0:10:59 lr: 0.000743 loss: 2.8450 (3.3614) grad_norm: 1.1354 (1.1525) time: 0.4981 [2021-03-25 21:53:32 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 80/1251] eta: 0:10:47 lr: 0.000743 loss: 3.1512 (3.3874) grad_norm: 1.1311 (1.1462) time: 0.5048 [2021-03-25 21:53:37 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 90/1251] eta: 0:10:36 lr: 0.000743 loss: 3.5821 (3.3973) grad_norm: 1.1093 (1.1453) time: 0.5116 [2021-03-25 21:53:43 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 100/1251] eta: 0:10:26 lr: 0.000743 loss: 3.4502 (3.4170) grad_norm: 1.1195 (1.1426) time: 0.5084 [2021-03-25 21:53:48 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 110/1251] eta: 0:10:16 lr: 0.000743 loss: 3.6080 (3.4133) grad_norm: 1.1178 (1.1441) time: 0.5032 [2021-03-25 21:53:53 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 120/1251] eta: 0:10:07 lr: 0.000743 loss: 3.1746 (3.3869) grad_norm: 1.1528 (1.1492) time: 0.5022 [2021-03-25 21:53:58 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 130/1251] eta: 0:10:00 lr: 0.000743 loss: 3.4286 (3.3987) grad_norm: 1.1659 (1.1500) time: 0.5086 [2021-03-25 21:54:03 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 140/1251] eta: 0:09:52 lr: 0.000743 loss: 3.5311 (3.3955) grad_norm: 1.1055 (1.1476) time: 0.5067 [2021-03-25 21:54:08 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 150/1251] eta: 0:09:44 lr: 0.000743 loss: 3.5311 (3.3893) grad_norm: 1.1449 (1.1515) time: 0.5007 [2021-03-25 21:54:13 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 160/1251] eta: 0:09:37 lr: 0.000743 loss: 3.6435 (3.3906) grad_norm: 1.2244 (1.1612) time: 0.5015 [2021-03-25 21:54:18 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 170/1251] eta: 0:09:29 lr: 0.000743 loss: 3.5861 (3.3885) grad_norm: 1.1790 (1.1626) time: 0.4989 [2021-03-25 21:54:23 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 180/1251] eta: 0:09:23 lr: 0.000743 loss: 3.5861 (3.3892) grad_norm: 1.0870 (1.1605) time: 0.5030 [2021-03-25 21:54:28 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 190/1251] eta: 0:09:18 lr: 0.000743 loss: 3.2046 (3.3783) grad_norm: 1.1261 (1.1605) time: 0.5201 [2021-03-25 21:54:33 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 200/1251] eta: 0:09:12 lr: 0.000743 loss: 3.3910 (3.3880) grad_norm: 1.1577 (1.1597) time: 0.5225 [2021-03-25 21:54:38 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 210/1251] eta: 0:09:05 lr: 0.000743 loss: 3.4299 (3.3821) grad_norm: 1.1643 (1.1628) time: 0.5053 [2021-03-25 21:54:43 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 220/1251] eta: 0:08:59 lr: 0.000743 loss: 3.3312 (3.3856) grad_norm: 1.1886 (1.1625) time: 0.4943 [2021-03-25 21:54:48 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 230/1251] eta: 0:08:52 lr: 0.000743 loss: 3.5375 (3.3963) grad_norm: 1.1021 (1.1593) time: 0.4965 [2021-03-25 21:54:53 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 240/1251] eta: 0:08:46 lr: 0.000743 loss: 3.6782 (3.4031) grad_norm: 1.1286 (1.1626) time: 0.4988 [2021-03-25 21:54:58 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 250/1251] eta: 0:08:40 lr: 0.000743 loss: 3.6635 (3.4056) grad_norm: 1.1485 (1.1626) time: 0.4986 [2021-03-25 21:55:03 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 260/1251] eta: 0:08:35 lr: 0.000743 loss: 3.5853 (3.4064) grad_norm: 1.1638 (1.1646) time: 0.5054 [2021-03-25 21:55:08 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 270/1251] eta: 0:08:29 lr: 0.000742 loss: 3.5853 (3.4122) grad_norm: 1.1678 (1.1649) time: 0.5093 [2021-03-25 21:55:13 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 280/1251] eta: 0:08:23 lr: 0.000742 loss: 3.7027 (3.4206) grad_norm: 1.1332 (1.1658) time: 0.5072 [2021-03-25 21:55:18 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 290/1251] eta: 0:08:18 lr: 0.000742 loss: 3.7027 (3.4294) grad_norm: 1.1420 (1.1677) time: 0.5092 [2021-03-25 21:55:24 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 300/1251] eta: 0:08:12 lr: 0.000742 loss: 3.8517 (3.4381) grad_norm: 1.1649 (1.1671) time: 0.5074 [2021-03-25 21:55:29 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 310/1251] eta: 0:08:07 lr: 0.000742 loss: 3.7270 (3.4481) grad_norm: 1.1395 (1.1683) time: 0.5034 [2021-03-25 21:55:34 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 320/1251] eta: 0:08:01 lr: 0.000742 loss: 3.6057 (3.4495) grad_norm: 1.1843 (1.1688) time: 0.5080 [2021-03-25 21:55:39 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 330/1251] eta: 0:07:56 lr: 0.000742 loss: 3.6409 (3.4590) grad_norm: 1.1572 (1.1694) time: 0.5136 [2021-03-25 21:55:44 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 340/1251] eta: 0:07:51 lr: 0.000742 loss: 3.6244 (3.4599) grad_norm: 1.1649 (1.1690) time: 0.5095 [2021-03-25 21:55:49 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 350/1251] eta: 0:07:45 lr: 0.000742 loss: 3.4484 (3.4589) grad_norm: 1.1619 (1.1684) time: 0.5081 [2021-03-25 21:55:54 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 360/1251] eta: 0:07:40 lr: 0.000742 loss: 3.4158 (3.4566) grad_norm: 1.1843 (1.1699) time: 0.5059 [2021-03-25 21:55:59 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 370/1251] eta: 0:07:34 lr: 0.000742 loss: 3.3687 (3.4501) grad_norm: 1.1953 (1.1717) time: 0.5030 [2021-03-25 21:56:04 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 380/1251] eta: 0:07:29 lr: 0.000742 loss: 3.3687 (3.4523) grad_norm: 1.1824 (1.1724) time: 0.5024 [2021-03-25 21:56:09 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 390/1251] eta: 0:07:23 lr: 0.000742 loss: 3.5771 (3.4511) grad_norm: 1.1672 (1.1726) time: 0.4978 [2021-03-25 21:56:14 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 400/1251] eta: 0:07:18 lr: 0.000742 loss: 3.7116 (3.4602) grad_norm: 1.1723 (1.1721) time: 0.5017 [2021-03-25 21:56:19 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 410/1251] eta: 0:07:12 lr: 0.000742 loss: 3.6863 (3.4575) grad_norm: 1.1595 (1.1720) time: 0.5056 [2021-03-25 21:56:24 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 420/1251] eta: 0:07:07 lr: 0.000742 loss: 3.3780 (3.4590) grad_norm: 1.2197 (1.1749) time: 0.5064 [2021-03-25 21:56:29 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 430/1251] eta: 0:07:02 lr: 0.000742 loss: 3.6212 (3.4660) grad_norm: 1.3045 (1.1786) time: 0.5045 [2021-03-25 21:56:34 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 440/1251] eta: 0:06:56 lr: 0.000742 loss: 3.5739 (3.4634) grad_norm: 1.2739 (1.1787) time: 0.5024 [2021-03-25 21:56:39 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 450/1251] eta: 0:06:51 lr: 0.000742 loss: 3.3603 (3.4645) grad_norm: 1.1124 (1.1780) time: 0.4994 [2021-03-25 21:56:44 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 460/1251] eta: 0:06:46 lr: 0.000742 loss: 3.6306 (3.4694) grad_norm: 1.1137 (1.1766) time: 0.4970 [2021-03-25 21:56:49 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 470/1251] eta: 0:06:40 lr: 0.000742 loss: 3.5251 (3.4651) grad_norm: 1.1137 (1.1754) time: 0.5005 [2021-03-25 21:56:54 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 480/1251] eta: 0:06:35 lr: 0.000742 loss: 3.3214 (3.4629) grad_norm: 1.1623 (1.1777) time: 0.5059 [2021-03-25 21:56:59 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 490/1251] eta: 0:06:30 lr: 0.000742 loss: 3.3153 (3.4592) grad_norm: 1.1623 (1.1766) time: 0.5125 [2021-03-25 21:57:05 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 500/1251] eta: 0:06:25 lr: 0.000742 loss: 3.3153 (3.4590) grad_norm: 1.1225 (1.1756) time: 0.5111 [2021-03-25 21:57:10 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 510/1251] eta: 0:06:19 lr: 0.000742 loss: 3.3382 (3.4547) grad_norm: 1.1364 (1.1755) time: 0.5043 [2021-03-25 21:57:15 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 520/1251] eta: 0:06:14 lr: 0.000742 loss: 3.3782 (3.4580) grad_norm: 1.1364 (1.1751) time: 0.5080 [2021-03-25 21:57:20 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 530/1251] eta: 0:06:09 lr: 0.000742 loss: 3.6014 (3.4527) grad_norm: 1.1274 (1.1738) time: 0.5097 [2021-03-25 21:57:25 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 540/1251] eta: 0:06:04 lr: 0.000742 loss: 3.4975 (3.4550) grad_norm: 1.1274 (1.1738) time: 0.4989 [2021-03-25 21:57:30 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 550/1251] eta: 0:05:59 lr: 0.000741 loss: 3.4975 (3.4537) grad_norm: 1.1112 (1.1737) time: 0.5152 [2021-03-25 21:57:35 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 560/1251] eta: 0:05:54 lr: 0.000741 loss: 3.1648 (3.4481) grad_norm: 1.0855 (1.1742) time: 0.5181 [2021-03-25 21:57:40 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 570/1251] eta: 0:05:48 lr: 0.000741 loss: 3.3731 (3.4507) grad_norm: 1.1098 (1.1733) time: 0.5028 [2021-03-25 21:57:45 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 580/1251] eta: 0:05:43 lr: 0.000741 loss: 3.6557 (3.4541) grad_norm: 1.1093 (1.1722) time: 0.5037 [2021-03-25 21:57:50 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 590/1251] eta: 0:05:38 lr: 0.000741 loss: 3.5804 (3.4539) grad_norm: 1.1091 (1.1712) time: 0.5019 [2021-03-25 21:57:55 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 600/1251] eta: 0:05:33 lr: 0.000741 loss: 3.4851 (3.4554) grad_norm: 1.1151 (1.1710) time: 0.5008 [2021-03-25 21:58:00 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 610/1251] eta: 0:05:27 lr: 0.000741 loss: 3.5618 (3.4558) grad_norm: 1.1358 (1.1707) time: 0.5031 [2021-03-25 21:58:05 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 620/1251] eta: 0:05:22 lr: 0.000741 loss: 3.7267 (3.4627) grad_norm: 1.1703 (1.1715) time: 0.5083 [2021-03-25 21:58:10 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 630/1251] eta: 0:05:17 lr: 0.000741 loss: 3.8189 (3.4630) grad_norm: 1.1826 (1.1711) time: 0.5066 [2021-03-25 21:58:16 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 640/1251] eta: 0:05:12 lr: 0.000741 loss: 3.3558 (3.4602) grad_norm: 1.1766 (1.1716) time: 0.5086 [2021-03-25 21:58:21 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 650/1251] eta: 0:05:07 lr: 0.000741 loss: 3.3558 (3.4580) grad_norm: 1.1278 (1.1710) time: 0.5071 [2021-03-25 21:58:26 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 660/1251] eta: 0:05:02 lr: 0.000741 loss: 3.6551 (3.4624) grad_norm: 1.1525 (1.1711) time: 0.5000 [2021-03-25 21:58:31 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 670/1251] eta: 0:04:56 lr: 0.000741 loss: 3.6076 (3.4612) grad_norm: 1.1855 (1.1711) time: 0.5014 [2021-03-25 21:58:36 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 680/1251] eta: 0:04:51 lr: 0.000741 loss: 3.4523 (3.4614) grad_norm: 1.1548 (1.1707) time: 0.5075 [2021-03-25 21:58:41 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 690/1251] eta: 0:04:46 lr: 0.000741 loss: 3.4523 (3.4603) grad_norm: 1.1390 (1.1704) time: 0.5086 [2021-03-25 21:58:46 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 700/1251] eta: 0:04:41 lr: 0.000741 loss: 3.4103 (3.4591) grad_norm: 1.1390 (1.1713) time: 0.4991 [2021-03-25 21:58:51 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 710/1251] eta: 0:04:36 lr: 0.000741 loss: 3.4400 (3.4576) grad_norm: 1.1636 (1.1717) time: 0.4952 [2021-03-25 21:58:56 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 720/1251] eta: 0:04:31 lr: 0.000741 loss: 3.2805 (3.4526) grad_norm: 1.1647 (1.1721) time: 0.5018 [2021-03-25 21:59:01 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 730/1251] eta: 0:04:25 lr: 0.000741 loss: 3.4283 (3.4559) grad_norm: 1.1647 (1.1718) time: 0.5067 [2021-03-25 21:59:06 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 740/1251] eta: 0:04:20 lr: 0.000741 loss: 3.6063 (3.4552) grad_norm: 1.1401 (1.1716) time: 0.5181 [2021-03-25 21:59:11 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 750/1251] eta: 0:04:16 lr: 0.000741 loss: 3.4604 (3.4572) grad_norm: 1.1668 (1.1721) time: 0.5328 [2021-03-25 21:59:16 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 760/1251] eta: 0:04:10 lr: 0.000741 loss: 3.5959 (3.4593) grad_norm: 1.1096 (1.1711) time: 0.5178 [2021-03-25 21:59:22 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 770/1251] eta: 0:04:05 lr: 0.000741 loss: 3.7626 (3.4620) grad_norm: 1.0924 (1.1708) time: 0.5029 [2021-03-25 21:59:26 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 780/1251] eta: 0:04:00 lr: 0.000741 loss: 3.8013 (3.4648) grad_norm: 1.1023 (1.1699) time: 0.5019 [2021-03-25 21:59:31 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 790/1251] eta: 0:03:55 lr: 0.000741 loss: 3.7154 (3.4667) grad_norm: 1.0916 (1.1699) time: 0.4985 [2021-03-25 21:59:37 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 800/1251] eta: 0:03:50 lr: 0.000741 loss: 3.6274 (3.4669) grad_norm: 1.0920 (1.1693) time: 0.5051 [2021-03-25 21:59:42 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 810/1251] eta: 0:03:45 lr: 0.000741 loss: 3.5248 (3.4656) grad_norm: 1.1167 (1.1689) time: 0.5059 [2021-03-25 21:59:47 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 820/1251] eta: 0:03:39 lr: 0.000740 loss: 3.6459 (3.4669) grad_norm: 1.1252 (1.1685) time: 0.5036 [2021-03-25 21:59:52 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 830/1251] eta: 0:03:34 lr: 0.000740 loss: 3.6459 (3.4676) grad_norm: 1.1252 (1.1684) time: 0.5099 [2021-03-25 21:59:57 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 840/1251] eta: 0:03:29 lr: 0.000740 loss: 3.7297 (3.4691) grad_norm: 1.1199 (1.1676) time: 0.5093 [2021-03-25 22:00:02 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 850/1251] eta: 0:03:24 lr: 0.000740 loss: 3.6582 (3.4696) grad_norm: 1.1148 (1.1671) time: 0.5016 [2021-03-25 22:00:07 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 860/1251] eta: 0:03:19 lr: 0.000740 loss: 3.1693 (3.4641) grad_norm: 1.1377 (1.1677) time: 0.5055 [2021-03-25 22:00:12 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 870/1251] eta: 0:03:14 lr: 0.000740 loss: 3.0130 (3.4622) grad_norm: 1.1792 (1.1682) time: 0.5110 [2021-03-25 22:00:17 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 880/1251] eta: 0:03:09 lr: 0.000740 loss: 3.5738 (3.4635) grad_norm: 1.2248 (1.1695) time: 0.5024 [2021-03-25 22:00:22 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 890/1251] eta: 0:03:04 lr: 0.000740 loss: 3.6085 (3.4659) grad_norm: 1.2064 (1.1697) time: 0.5011 [2021-03-25 22:00:27 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 900/1251] eta: 0:02:58 lr: 0.000740 loss: 3.6229 (3.4678) grad_norm: 1.1586 (1.1699) time: 0.5068 [2021-03-25 22:00:32 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 910/1251] eta: 0:02:53 lr: 0.000740 loss: 3.6568 (3.4676) grad_norm: 1.1698 (1.1701) time: 0.5015 [2021-03-25 22:00:37 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 920/1251] eta: 0:02:48 lr: 0.000740 loss: 3.6813 (3.4707) grad_norm: 1.1604 (1.1702) time: 0.5045 [2021-03-25 22:00:42 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 930/1251] eta: 0:02:43 lr: 0.000740 loss: 3.5676 (3.4697) grad_norm: 1.1179 (1.1700) time: 0.5157 [2021-03-25 22:00:48 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 940/1251] eta: 0:02:38 lr: 0.000740 loss: 3.5886 (3.4729) grad_norm: 1.1196 (1.1702) time: 0.5189 [2021-03-25 22:00:53 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 950/1251] eta: 0:02:33 lr: 0.000740 loss: 3.7510 (3.4754) grad_norm: 1.1588 (1.1704) time: 0.5170 [2021-03-25 22:00:58 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 960/1251] eta: 0:02:28 lr: 0.000740 loss: 3.6933 (3.4752) grad_norm: 1.1443 (1.1707) time: 0.5120 [2021-03-25 22:01:03 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 970/1251] eta: 0:02:23 lr: 0.000740 loss: 3.6157 (3.4758) grad_norm: 1.1185 (1.1701) time: 0.5032 [2021-03-25 22:01:08 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 980/1251] eta: 0:02:18 lr: 0.000740 loss: 3.4878 (3.4749) grad_norm: 1.0400 (1.1690) time: 0.5020 [2021-03-25 22:01:13 swin_small_patch4_window7_224] INFO: Epoch: [102] [ 990/1251] eta: 0:02:13 lr: 0.000740 loss: 3.4284 (3.4743) grad_norm: 1.0392 (1.1684) time: 0.5048 [2021-03-25 22:01:18 swin_small_patch4_window7_224] INFO: Epoch: [102] [1000/1251] eta: 0:02:07 lr: 0.000740 loss: 3.4628 (3.4742) grad_norm: 1.1619 (1.1689) time: 0.5062 [2021-03-25 22:01:23 swin_small_patch4_window7_224] INFO: Epoch: [102] [1010/1251] eta: 0:02:02 lr: 0.000740 loss: 3.5460 (3.4745) grad_norm: 1.1994 (1.1693) time: 0.5052 [2021-03-25 22:01:28 swin_small_patch4_window7_224] INFO: Epoch: [102] [1020/1251] eta: 0:01:57 lr: 0.000740 loss: 3.5460 (3.4765) grad_norm: 1.1521 (1.1689) time: 0.5026 [2021-03-25 22:01:33 swin_small_patch4_window7_224] INFO: Epoch: [102] [1030/1251] eta: 0:01:52 lr: 0.000740 loss: 3.6884 (3.4777) grad_norm: 1.1496 (1.1690) time: 0.5025 [2021-03-25 22:01:38 swin_small_patch4_window7_224] INFO: Epoch: [102] [1040/1251] eta: 0:01:47 lr: 0.000740 loss: 3.5685 (3.4784) grad_norm: 1.1118 (1.1684) time: 0.5007 [2021-03-25 22:01:43 swin_small_patch4_window7_224] INFO: Epoch: [102] [1050/1251] eta: 0:01:42 lr: 0.000740 loss: 3.4964 (3.4777) grad_norm: 1.1113 (1.1686) time: 0.5024 [2021-03-25 22:01:48 swin_small_patch4_window7_224] INFO: Epoch: [102] [1060/1251] eta: 0:01:37 lr: 0.000740 loss: 3.4964 (3.4775) grad_norm: 1.1448 (1.1683) time: 0.5038 [2021-03-25 22:01:53 swin_small_patch4_window7_224] INFO: Epoch: [102] [1070/1251] eta: 0:01:32 lr: 0.000740 loss: 3.7463 (3.4790) grad_norm: 1.1356 (1.1679) time: 0.5086 [2021-03-25 22:01:58 swin_small_patch4_window7_224] INFO: Epoch: [102] [1080/1251] eta: 0:01:27 lr: 0.000740 loss: 3.7749 (3.4790) grad_norm: 1.1336 (1.1679) time: 0.5055 [2021-03-25 22:02:03 swin_small_patch4_window7_224] INFO: Epoch: [102] [1090/1251] eta: 0:01:21 lr: 0.000740 loss: 3.6932 (3.4780) grad_norm: 1.1276 (1.1678) time: 0.5011 [2021-03-25 22:02:08 swin_small_patch4_window7_224] INFO: Epoch: [102] [1100/1251] eta: 0:01:16 lr: 0.000739 loss: 3.6796 (3.4789) grad_norm: 1.1276 (1.1674) time: 0.5061 [2021-03-25 22:02:13 swin_small_patch4_window7_224] INFO: Epoch: [102] [1110/1251] eta: 0:01:11 lr: 0.000739 loss: 3.6683 (3.4799) grad_norm: 1.1302 (1.1676) time: 0.5024 [2021-03-25 22:02:18 swin_small_patch4_window7_224] INFO: Epoch: [102] [1120/1251] eta: 0:01:06 lr: 0.000739 loss: 3.4459 (3.4798) grad_norm: 1.1349 (1.1675) time: 0.4973 [2021-03-25 22:02:23 swin_small_patch4_window7_224] INFO: Epoch: [102] [1130/1251] eta: 0:01:01 lr: 0.000739 loss: 3.3878 (3.4791) grad_norm: 1.1229 (1.1675) time: 0.4975 [2021-03-25 22:02:28 swin_small_patch4_window7_224] INFO: Epoch: [102] [1140/1251] eta: 0:00:56 lr: 0.000739 loss: 3.3878 (3.4774) grad_norm: 1.1737 (1.1678) time: 0.5016 [2021-03-25 22:02:34 swin_small_patch4_window7_224] INFO: Epoch: [102] [1150/1251] eta: 0:00:51 lr: 0.000739 loss: 3.2978 (3.4749) grad_norm: 1.1737 (1.1676) time: 0.5070 [2021-03-25 22:02:39 swin_small_patch4_window7_224] INFO: Epoch: [102] [1160/1251] eta: 0:00:46 lr: 0.000739 loss: 3.1300 (3.4742) grad_norm: 1.1513 (1.1676) time: 0.5051 [2021-03-25 22:02:44 swin_small_patch4_window7_224] INFO: Epoch: [102] [1170/1251] eta: 0:00:41 lr: 0.000739 loss: 3.6674 (3.4769) grad_norm: 1.1732 (1.1678) time: 0.5036 [2021-03-25 22:02:49 swin_small_patch4_window7_224] INFO: Epoch: [102] [1180/1251] eta: 0:00:36 lr: 0.000739 loss: 3.7046 (3.4778) grad_norm: 1.1191 (1.1675) time: 0.5058 [2021-03-25 22:02:54 swin_small_patch4_window7_224] INFO: Epoch: [102] [1190/1251] eta: 0:00:31 lr: 0.000739 loss: 3.4423 (3.4759) grad_norm: 1.1189 (1.1676) time: 0.5093 [2021-03-25 22:02:59 swin_small_patch4_window7_224] INFO: Epoch: [102] [1200/1251] eta: 0:00:25 lr: 0.000739 loss: 3.1477 (3.4746) grad_norm: 1.1189 (1.1677) time: 0.5058 [2021-03-25 22:03:04 swin_small_patch4_window7_224] INFO: Epoch: [102] [1210/1251] eta: 0:00:20 lr: 0.000739 loss: 3.1477 (3.4719) grad_norm: 1.2065 (1.1680) time: 0.4987 [2021-03-25 22:03:09 swin_small_patch4_window7_224] INFO: Epoch: [102] [1220/1251] eta: 0:00:15 lr: 0.000739 loss: 3.6119 (3.4737) grad_norm: 1.1096 (1.1674) time: 0.5006 [2021-03-25 22:03:14 swin_small_patch4_window7_224] INFO: Epoch: [102] [1230/1251] eta: 0:00:10 lr: 0.000739 loss: 3.6256 (3.4734) grad_norm: 1.0698 (1.1678) time: 0.5014 [2021-03-25 22:03:19 swin_small_patch4_window7_224] INFO: Epoch: [102] [1240/1251] eta: 0:00:05 lr: 0.000739 loss: 3.5635 (3.4727) grad_norm: 1.1490 (1.1675) time: 0.5009 [2021-03-25 22:03:24 swin_small_patch4_window7_224] INFO: Epoch: [102] [1250/1251] eta: 0:00:00 lr: 0.000739 loss: 3.7270 (3.4744) grad_norm: 1.1490 (1.1675) time: 0.5076 [2021-03-25 22:03:31 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:32 loss: 1.4138 (1.4138) acc1: 73.4375 (73.4375) acc5: 85.9375 (85.9375) [2021-03-25 22:03:34 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9856 (1.0563) acc1: 75.0000 (75.7102) acc5: 92.1875 (92.7557) [2021-03-25 22:03:36 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9284 (1.0059) acc1: 76.5625 (76.1161) acc5: 93.7500 (93.6012) [2021-03-25 22:03:38 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9422 (0.9949) acc1: 76.5625 (76.4617) acc5: 93.7500 (93.9012) [2021-03-25 22:03:40 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0045 (1.0114) acc1: 75.0000 (76.0290) acc5: 93.7500 (93.6738) [2021-03-25 22:03:41 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0466 (1.0135) acc1: 75.0000 (76.0960) acc5: 93.7500 (93.6960) [2021-03-25 22:03:47 swin_small_patch4_window7_224] INFO: * Acc@1 76.318 Acc@5 93.454 loss 0.996 [2021-03-25 22:03:47 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.3% [2021-03-25 22:03:47 swin_small_patch4_window7_224] INFO: Max accuracy: 76.32% [2021-03-25 22:03:52 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 0/1251] eta: 1:28:48 lr: 0.000739 loss: 3.6058 (3.6058) grad_norm: 1.1502 (1.1502) time: 4.2593 [2021-03-25 22:03:57 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 10/1251] eta: 0:17:52 lr: 0.000739 loss: 3.6058 (3.2996) grad_norm: 1.2084 (1.2235) time: 0.8641 [2021-03-25 22:04:02 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 20/1251] eta: 0:14:08 lr: 0.000739 loss: 3.5836 (3.4122) grad_norm: 1.1767 (1.1931) time: 0.5110 [2021-03-25 22:04:07 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 30/1251] eta: 0:12:48 lr: 0.000739 loss: 3.4812 (3.4517) grad_norm: 1.1560 (1.1697) time: 0.5000 [2021-03-25 22:04:12 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 40/1251] eta: 0:12:09 lr: 0.000739 loss: 3.2914 (3.4035) grad_norm: 1.0822 (1.1665) time: 0.5104 [2021-03-25 22:04:17 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 50/1251] eta: 0:11:41 lr: 0.000739 loss: 3.2042 (3.3642) grad_norm: 1.1108 (1.1594) time: 0.5151 [2021-03-25 22:04:22 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 60/1251] eta: 0:11:21 lr: 0.000739 loss: 3.6064 (3.4287) grad_norm: 1.1615 (1.1685) time: 0.5103 [2021-03-25 22:04:27 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 70/1251] eta: 0:11:06 lr: 0.000739 loss: 3.6151 (3.4509) grad_norm: 1.1972 (1.1746) time: 0.5121 [2021-03-25 22:04:32 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 80/1251] eta: 0:10:51 lr: 0.000739 loss: 3.6151 (3.4649) grad_norm: 1.1535 (1.1692) time: 0.5069 [2021-03-25 22:04:37 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 90/1251] eta: 0:10:39 lr: 0.000739 loss: 3.7368 (3.4818) grad_norm: 1.1502 (1.1751) time: 0.5024 [2021-03-25 22:04:42 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 100/1251] eta: 0:10:28 lr: 0.000739 loss: 3.6650 (3.4613) grad_norm: 1.1502 (1.1755) time: 0.5072 [2021-03-25 22:04:48 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 110/1251] eta: 0:10:20 lr: 0.000739 loss: 3.0771 (3.4332) grad_norm: 1.1297 (1.1722) time: 0.5124 [2021-03-25 22:04:53 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 120/1251] eta: 0:10:11 lr: 0.000738 loss: 3.3216 (3.4366) grad_norm: 1.1216 (1.1724) time: 0.5138 [2021-03-25 22:04:58 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 130/1251] eta: 0:10:03 lr: 0.000738 loss: 3.6202 (3.4369) grad_norm: 1.1350 (1.1717) time: 0.5098 [2021-03-25 22:05:03 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 140/1251] eta: 0:09:55 lr: 0.000738 loss: 3.6420 (3.4408) grad_norm: 1.2211 (1.1787) time: 0.5050 [2021-03-25 22:05:08 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 150/1251] eta: 0:09:47 lr: 0.000738 loss: 3.6420 (3.4429) grad_norm: 1.1801 (1.1794) time: 0.5042 [2021-03-25 22:05:13 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 160/1251] eta: 0:09:40 lr: 0.000738 loss: 3.7013 (3.4569) grad_norm: 1.1656 (1.1795) time: 0.5083 [2021-03-25 22:05:18 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 170/1251] eta: 0:09:33 lr: 0.000738 loss: 3.6430 (3.4590) grad_norm: 1.1755 (1.1813) time: 0.5025 [2021-03-25 22:05:23 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 180/1251] eta: 0:09:26 lr: 0.000738 loss: 3.4464 (3.4549) grad_norm: 1.2134 (1.1809) time: 0.5046 [2021-03-25 22:05:28 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 190/1251] eta: 0:09:20 lr: 0.000738 loss: 3.4288 (3.4504) grad_norm: 1.1826 (1.1798) time: 0.5135 [2021-03-25 22:05:33 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 200/1251] eta: 0:09:14 lr: 0.000738 loss: 3.6052 (3.4664) grad_norm: 1.1826 (1.1808) time: 0.5079 [2021-03-25 22:05:38 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 210/1251] eta: 0:09:07 lr: 0.000738 loss: 3.6304 (3.4718) grad_norm: 1.1826 (1.1814) time: 0.5057 [2021-03-25 22:05:43 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 220/1251] eta: 0:09:01 lr: 0.000738 loss: 3.4911 (3.4723) grad_norm: 1.1810 (1.1825) time: 0.5062 [2021-03-25 22:05:48 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 230/1251] eta: 0:08:55 lr: 0.000738 loss: 3.4544 (3.4694) grad_norm: 1.1522 (1.1768) time: 0.5038 [2021-03-25 22:05:54 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 240/1251] eta: 0:08:49 lr: 0.000738 loss: 3.2513 (3.4707) grad_norm: 1.1352 (1.1769) time: 0.5049 [2021-03-25 22:05:59 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 250/1251] eta: 0:08:43 lr: 0.000738 loss: 3.5265 (3.4761) grad_norm: 1.1610 (1.1772) time: 0.5019 [2021-03-25 22:06:04 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 260/1251] eta: 0:08:37 lr: 0.000738 loss: 3.5029 (3.4745) grad_norm: 1.1337 (1.1765) time: 0.5045 [2021-03-25 22:06:09 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 270/1251] eta: 0:08:31 lr: 0.000738 loss: 3.4872 (3.4733) grad_norm: 1.1515 (1.1780) time: 0.5078 [2021-03-25 22:06:14 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 280/1251] eta: 0:08:25 lr: 0.000738 loss: 3.3708 (3.4661) grad_norm: 1.2107 (1.1805) time: 0.5008 [2021-03-25 22:06:19 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 290/1251] eta: 0:08:19 lr: 0.000738 loss: 3.3708 (3.4593) grad_norm: 1.1746 (1.1821) time: 0.5021 [2021-03-25 22:06:24 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 300/1251] eta: 0:08:14 lr: 0.000738 loss: 3.2376 (3.4537) grad_norm: 1.1820 (1.1824) time: 0.5132 [2021-03-25 22:06:29 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 310/1251] eta: 0:08:09 lr: 0.000738 loss: 3.2146 (3.4525) grad_norm: 1.1525 (1.1804) time: 0.5133 [2021-03-25 22:06:34 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 320/1251] eta: 0:08:03 lr: 0.000738 loss: 3.2087 (3.4459) grad_norm: 1.1519 (1.1812) time: 0.5125 [2021-03-25 22:06:39 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 330/1251] eta: 0:07:58 lr: 0.000738 loss: 3.5315 (3.4511) grad_norm: 1.1586 (1.1813) time: 0.5109 [2021-03-25 22:06:44 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 340/1251] eta: 0:07:52 lr: 0.000738 loss: 3.5563 (3.4466) grad_norm: 1.1426 (1.1810) time: 0.5012 [2021-03-25 22:06:49 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 350/1251] eta: 0:07:46 lr: 0.000738 loss: 3.3734 (3.4457) grad_norm: 1.1685 (1.1809) time: 0.4991 [2021-03-25 22:06:54 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 360/1251] eta: 0:07:41 lr: 0.000738 loss: 3.5296 (3.4474) grad_norm: 1.1831 (1.1826) time: 0.5050 [2021-03-25 22:06:59 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 370/1251] eta: 0:07:35 lr: 0.000738 loss: 3.4479 (3.4448) grad_norm: 1.1831 (1.1819) time: 0.5064 [2021-03-25 22:07:04 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 380/1251] eta: 0:07:30 lr: 0.000738 loss: 3.5266 (3.4499) grad_norm: 1.1863 (1.1842) time: 0.5074 [2021-03-25 22:07:09 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 390/1251] eta: 0:07:25 lr: 0.000737 loss: 3.6952 (3.4535) grad_norm: 1.2064 (1.1845) time: 0.5069 [2021-03-25 22:07:14 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 400/1251] eta: 0:07:19 lr: 0.000737 loss: 3.6360 (3.4518) grad_norm: 1.1676 (1.1851) time: 0.5018 [2021-03-25 22:07:19 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 410/1251] eta: 0:07:14 lr: 0.000737 loss: 3.6682 (3.4591) grad_norm: 1.1618 (1.1860) time: 0.4997 [2021-03-25 22:07:24 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 420/1251] eta: 0:07:08 lr: 0.000737 loss: 3.6512 (3.4580) grad_norm: 1.1979 (1.1861) time: 0.5009 [2021-03-25 22:07:30 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 430/1251] eta: 0:07:03 lr: 0.000737 loss: 3.2975 (3.4566) grad_norm: 1.1602 (1.1853) time: 0.5046 [2021-03-25 22:07:35 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 440/1251] eta: 0:06:57 lr: 0.000737 loss: 3.6970 (3.4624) grad_norm: 1.1602 (1.1858) time: 0.5029 [2021-03-25 22:07:40 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 450/1251] eta: 0:06:52 lr: 0.000737 loss: 3.4367 (3.4537) grad_norm: 1.1878 (1.1857) time: 0.5095 [2021-03-25 22:07:45 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 460/1251] eta: 0:06:47 lr: 0.000737 loss: 3.1001 (3.4487) grad_norm: 1.1378 (1.1847) time: 0.5126 [2021-03-25 22:07:50 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 470/1251] eta: 0:06:41 lr: 0.000737 loss: 3.4606 (3.4511) grad_norm: 1.1537 (1.1854) time: 0.5002 [2021-03-25 22:07:55 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 480/1251] eta: 0:06:36 lr: 0.000737 loss: 3.4938 (3.4514) grad_norm: 1.2194 (1.1864) time: 0.5005 [2021-03-25 22:08:00 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 490/1251] eta: 0:06:31 lr: 0.000737 loss: 3.5022 (3.4523) grad_norm: 1.2194 (1.1881) time: 0.5090 [2021-03-25 22:08:05 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 500/1251] eta: 0:06:26 lr: 0.000737 loss: 3.6335 (3.4518) grad_norm: 1.1528 (1.1869) time: 0.5081 [2021-03-25 22:08:10 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 510/1251] eta: 0:06:20 lr: 0.000737 loss: 3.6652 (3.4538) grad_norm: 1.1439 (1.1866) time: 0.5057 [2021-03-25 22:08:15 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 520/1251] eta: 0:06:15 lr: 0.000737 loss: 3.6206 (3.4560) grad_norm: 1.1549 (1.1863) time: 0.5095 [2021-03-25 22:08:20 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 530/1251] eta: 0:06:10 lr: 0.000737 loss: 3.5546 (3.4532) grad_norm: 1.1674 (1.1873) time: 0.5080 [2021-03-25 22:08:25 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 540/1251] eta: 0:06:05 lr: 0.000737 loss: 3.2465 (3.4498) grad_norm: 1.1674 (1.1867) time: 0.5048 [2021-03-25 22:08:31 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 550/1251] eta: 0:06:00 lr: 0.000737 loss: 3.2690 (3.4487) grad_norm: 1.1140 (1.1859) time: 0.5165 [2021-03-25 22:08:36 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 560/1251] eta: 0:05:55 lr: 0.000737 loss: 3.4016 (3.4471) grad_norm: 1.1413 (1.1865) time: 0.5207 [2021-03-25 22:08:41 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 570/1251] eta: 0:05:49 lr: 0.000737 loss: 3.6748 (3.4522) grad_norm: 1.1546 (1.1862) time: 0.5114 [2021-03-25 22:08:46 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 580/1251] eta: 0:05:44 lr: 0.000737 loss: 3.6748 (3.4557) grad_norm: 1.1686 (1.1867) time: 0.5056 [2021-03-25 22:08:51 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 590/1251] eta: 0:05:39 lr: 0.000737 loss: 3.6385 (3.4565) grad_norm: 1.1715 (1.1866) time: 0.5091 [2021-03-25 22:08:56 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 600/1251] eta: 0:05:34 lr: 0.000737 loss: 3.2558 (3.4510) grad_norm: 1.1720 (1.1869) time: 0.5139 [2021-03-25 22:09:01 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 610/1251] eta: 0:05:29 lr: 0.000737 loss: 3.5847 (3.4544) grad_norm: 1.1297 (1.1862) time: 0.5078 [2021-03-25 22:09:06 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 620/1251] eta: 0:05:23 lr: 0.000737 loss: 3.6373 (3.4551) grad_norm: 1.1528 (1.1871) time: 0.4983 [2021-03-25 22:09:11 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 630/1251] eta: 0:05:18 lr: 0.000737 loss: 3.5486 (3.4568) grad_norm: 1.1546 (1.1869) time: 0.4959 [2021-03-25 22:09:16 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 640/1251] eta: 0:05:13 lr: 0.000737 loss: 3.5825 (3.4604) grad_norm: 1.1418 (1.1866) time: 0.5054 [2021-03-25 22:09:21 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 650/1251] eta: 0:05:08 lr: 0.000737 loss: 3.6983 (3.4624) grad_norm: 1.1145 (1.1855) time: 0.5047 [2021-03-25 22:09:26 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 660/1251] eta: 0:05:02 lr: 0.000736 loss: 3.6983 (3.4639) grad_norm: 1.1488 (1.1858) time: 0.5015 [2021-03-25 22:09:31 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 670/1251] eta: 0:04:57 lr: 0.000736 loss: 3.4135 (3.4627) grad_norm: 1.1458 (1.1845) time: 0.5023 [2021-03-25 22:09:36 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 680/1251] eta: 0:04:52 lr: 0.000736 loss: 3.5310 (3.4623) grad_norm: 1.1210 (1.1840) time: 0.4958 [2021-03-25 22:09:41 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 690/1251] eta: 0:04:47 lr: 0.000736 loss: 3.6516 (3.4643) grad_norm: 1.1743 (1.1843) time: 0.4960 [2021-03-25 22:09:46 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 700/1251] eta: 0:04:42 lr: 0.000736 loss: 3.7010 (3.4639) grad_norm: 1.1437 (1.1832) time: 0.5042 [2021-03-25 22:09:51 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 710/1251] eta: 0:04:36 lr: 0.000736 loss: 3.5795 (3.4635) grad_norm: 1.1109 (1.1828) time: 0.5123 [2021-03-25 22:09:56 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 720/1251] eta: 0:04:31 lr: 0.000736 loss: 3.5235 (3.4644) grad_norm: 1.1202 (1.1819) time: 0.5108 [2021-03-25 22:10:01 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 730/1251] eta: 0:04:26 lr: 0.000736 loss: 3.3894 (3.4642) grad_norm: 1.1518 (1.1819) time: 0.5049 [2021-03-25 22:10:07 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 740/1251] eta: 0:04:21 lr: 0.000736 loss: 3.3894 (3.4639) grad_norm: 1.1518 (1.1813) time: 0.5217 [2021-03-25 22:10:12 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 750/1251] eta: 0:04:16 lr: 0.000736 loss: 3.6719 (3.4660) grad_norm: 1.1306 (1.1803) time: 0.5327 [2021-03-25 22:10:17 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 760/1251] eta: 0:04:11 lr: 0.000736 loss: 3.4434 (3.4616) grad_norm: 1.0705 (1.1794) time: 0.5151 [2021-03-25 22:10:22 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 770/1251] eta: 0:04:06 lr: 0.000736 loss: 3.2409 (3.4609) grad_norm: 1.1040 (1.1788) time: 0.5060 [2021-03-25 22:10:27 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 780/1251] eta: 0:04:01 lr: 0.000736 loss: 3.5146 (3.4618) grad_norm: 1.1312 (1.1779) time: 0.5018 [2021-03-25 22:10:32 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 790/1251] eta: 0:03:56 lr: 0.000736 loss: 3.5313 (3.4610) grad_norm: 1.1356 (1.1775) time: 0.5058 [2021-03-25 22:10:37 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 800/1251] eta: 0:03:50 lr: 0.000736 loss: 3.0948 (3.4546) grad_norm: 1.1421 (1.1770) time: 0.5132 [2021-03-25 22:10:43 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 810/1251] eta: 0:03:45 lr: 0.000736 loss: 3.1957 (3.4543) grad_norm: 1.1485 (1.1766) time: 0.5078 [2021-03-25 22:10:48 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 820/1251] eta: 0:03:40 lr: 0.000736 loss: 3.5866 (3.4564) grad_norm: 1.1422 (1.1763) time: 0.5036 [2021-03-25 22:10:53 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 830/1251] eta: 0:03:35 lr: 0.000736 loss: 3.7316 (3.4594) grad_norm: 1.1349 (1.1759) time: 0.5038 [2021-03-25 22:10:58 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 840/1251] eta: 0:03:30 lr: 0.000736 loss: 3.7863 (3.4622) grad_norm: 1.1465 (1.1759) time: 0.5069 [2021-03-25 22:11:03 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 850/1251] eta: 0:03:25 lr: 0.000736 loss: 3.6828 (3.4603) grad_norm: 1.1453 (1.1757) time: 0.5133 [2021-03-25 22:11:08 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 860/1251] eta: 0:03:20 lr: 0.000736 loss: 3.2658 (3.4587) grad_norm: 1.1353 (1.1752) time: 0.5104 [2021-03-25 22:11:13 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 870/1251] eta: 0:03:14 lr: 0.000736 loss: 3.4318 (3.4579) grad_norm: 1.1276 (1.1751) time: 0.5094 [2021-03-25 22:11:18 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 880/1251] eta: 0:03:09 lr: 0.000736 loss: 3.4843 (3.4586) grad_norm: 1.1680 (1.1750) time: 0.5118 [2021-03-25 22:11:23 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 890/1251] eta: 0:03:04 lr: 0.000736 loss: 3.4843 (3.4560) grad_norm: 1.1680 (1.1748) time: 0.5078 [2021-03-25 22:11:28 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 900/1251] eta: 0:02:59 lr: 0.000736 loss: 3.2871 (3.4544) grad_norm: 1.1142 (1.1751) time: 0.5039 [2021-03-25 22:11:33 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 910/1251] eta: 0:02:54 lr: 0.000736 loss: 3.5468 (3.4553) grad_norm: 1.1391 (1.1750) time: 0.5041 [2021-03-25 22:11:38 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 920/1251] eta: 0:02:49 lr: 0.000736 loss: 3.5685 (3.4555) grad_norm: 1.1481 (1.1744) time: 0.5060 [2021-03-25 22:11:43 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 930/1251] eta: 0:02:44 lr: 0.000736 loss: 3.6201 (3.4586) grad_norm: 1.1037 (1.1742) time: 0.5081 [2021-03-25 22:11:49 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 940/1251] eta: 0:02:39 lr: 0.000735 loss: 3.6473 (3.4589) grad_norm: 1.1464 (1.1749) time: 0.5093 [2021-03-25 22:11:54 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 950/1251] eta: 0:02:33 lr: 0.000735 loss: 3.6755 (3.4622) grad_norm: 1.1478 (1.1747) time: 0.5038 [2021-03-25 22:11:59 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 960/1251] eta: 0:02:28 lr: 0.000735 loss: 3.6865 (3.4640) grad_norm: 1.1504 (1.1750) time: 0.4992 [2021-03-25 22:12:04 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 970/1251] eta: 0:02:23 lr: 0.000735 loss: 3.7559 (3.4656) grad_norm: 1.1498 (1.1745) time: 0.4994 [2021-03-25 22:12:09 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 980/1251] eta: 0:02:18 lr: 0.000735 loss: 3.6251 (3.4666) grad_norm: 1.1277 (1.1740) time: 0.5048 [2021-03-25 22:12:14 swin_small_patch4_window7_224] INFO: Epoch: [103] [ 990/1251] eta: 0:02:13 lr: 0.000735 loss: 3.6251 (3.4690) grad_norm: 1.1595 (1.1744) time: 0.5019 [2021-03-25 22:12:19 swin_small_patch4_window7_224] INFO: Epoch: [103] [1000/1251] eta: 0:02:08 lr: 0.000735 loss: 3.7141 (3.4690) grad_norm: 1.1677 (1.1743) time: 0.5024 [2021-03-25 22:12:24 swin_small_patch4_window7_224] INFO: Epoch: [103] [1010/1251] eta: 0:02:03 lr: 0.000735 loss: 3.6309 (3.4699) grad_norm: 1.1235 (1.1744) time: 0.5038 [2021-03-25 22:12:29 swin_small_patch4_window7_224] INFO: Epoch: [103] [1020/1251] eta: 0:01:57 lr: 0.000735 loss: 3.4604 (3.4692) grad_norm: 1.1235 (1.1744) time: 0.5022 [2021-03-25 22:12:34 swin_small_patch4_window7_224] INFO: Epoch: [103] [1030/1251] eta: 0:01:52 lr: 0.000735 loss: 3.4453 (3.4677) grad_norm: 1.1477 (1.1743) time: 0.5067 [2021-03-25 22:12:39 swin_small_patch4_window7_224] INFO: Epoch: [103] [1040/1251] eta: 0:01:47 lr: 0.000735 loss: 3.6547 (3.4686) grad_norm: 1.1548 (1.1742) time: 0.5083 [2021-03-25 22:12:44 swin_small_patch4_window7_224] INFO: Epoch: [103] [1050/1251] eta: 0:01:42 lr: 0.000735 loss: 3.5870 (3.4686) grad_norm: 1.1146 (nan) time: 0.5116 [2021-03-25 22:12:49 swin_small_patch4_window7_224] INFO: Epoch: [103] [1060/1251] eta: 0:01:37 lr: 0.000735 loss: 3.4291 (3.4671) grad_norm: 1.1679 (nan) time: 0.5178 [2021-03-25 22:12:54 swin_small_patch4_window7_224] INFO: Epoch: [103] [1070/1251] eta: 0:01:32 lr: 0.000735 loss: 3.1365 (3.4661) grad_norm: 1.1529 (nan) time: 0.5110 [2021-03-25 22:12:59 swin_small_patch4_window7_224] INFO: Epoch: [103] [1080/1251] eta: 0:01:27 lr: 0.000735 loss: 3.3324 (3.4654) grad_norm: 1.0908 (nan) time: 0.5020 [2021-03-25 22:13:04 swin_small_patch4_window7_224] INFO: Epoch: [103] [1090/1251] eta: 0:01:22 lr: 0.000735 loss: 3.4167 (3.4668) grad_norm: 1.1840 (nan) time: 0.5038 [2021-03-25 22:13:09 swin_small_patch4_window7_224] INFO: Epoch: [103] [1100/1251] eta: 0:01:17 lr: 0.000735 loss: 3.4966 (3.4675) grad_norm: 1.2060 (nan) time: 0.5064 [2021-03-25 22:13:15 swin_small_patch4_window7_224] INFO: Epoch: [103] [1110/1251] eta: 0:01:11 lr: 0.000735 loss: 3.6485 (3.4695) grad_norm: 1.1646 (nan) time: 0.5080 [2021-03-25 22:13:20 swin_small_patch4_window7_224] INFO: Epoch: [103] [1120/1251] eta: 0:01:06 lr: 0.000735 loss: 3.8147 (3.4701) grad_norm: 1.2038 (nan) time: 0.5086 [2021-03-25 22:13:25 swin_small_patch4_window7_224] INFO: Epoch: [103] [1130/1251] eta: 0:01:01 lr: 0.000735 loss: 3.6675 (3.4717) grad_norm: 1.1910 (nan) time: 0.5042 [2021-03-25 22:13:30 swin_small_patch4_window7_224] INFO: Epoch: [103] [1140/1251] eta: 0:00:56 lr: 0.000735 loss: 3.6601 (3.4720) grad_norm: 1.1965 (nan) time: 0.4991 [2021-03-25 22:13:35 swin_small_patch4_window7_224] INFO: Epoch: [103] [1150/1251] eta: 0:00:51 lr: 0.000735 loss: 3.4040 (3.4732) grad_norm: 1.1614 (nan) time: 0.5001 [2021-03-25 22:13:40 swin_small_patch4_window7_224] INFO: Epoch: [103] [1160/1251] eta: 0:00:46 lr: 0.000735 loss: 3.7179 (3.4754) grad_norm: 1.1255 (nan) time: 0.5035 [2021-03-25 22:13:45 swin_small_patch4_window7_224] INFO: Epoch: [103] [1170/1251] eta: 0:00:41 lr: 0.000735 loss: 3.7063 (3.4763) grad_norm: 1.0918 (nan) time: 0.5035 [2021-03-25 22:13:50 swin_small_patch4_window7_224] INFO: Epoch: [103] [1180/1251] eta: 0:00:36 lr: 0.000735 loss: 3.4706 (3.4748) grad_norm: 1.1104 (nan) time: 0.5014 [2021-03-25 22:13:55 swin_small_patch4_window7_224] INFO: Epoch: [103] [1190/1251] eta: 0:00:31 lr: 0.000735 loss: 3.4568 (3.4740) grad_norm: 1.1548 (nan) time: 0.5051 [2021-03-25 22:14:00 swin_small_patch4_window7_224] INFO: Epoch: [103] [1200/1251] eta: 0:00:26 lr: 0.000735 loss: 3.5160 (3.4739) grad_norm: 1.1094 (nan) time: 0.5069 [2021-03-25 22:14:05 swin_small_patch4_window7_224] INFO: Epoch: [103] [1210/1251] eta: 0:00:20 lr: 0.000734 loss: 3.6037 (3.4751) grad_norm: 1.1035 (nan) time: 0.5039 [2021-03-25 22:14:10 swin_small_patch4_window7_224] INFO: Epoch: [103] [1220/1251] eta: 0:00:15 lr: 0.000734 loss: 3.4006 (3.4728) grad_norm: 1.1500 (nan) time: 0.5043 [2021-03-25 22:14:15 swin_small_patch4_window7_224] INFO: Epoch: [103] [1230/1251] eta: 0:00:10 lr: 0.000734 loss: 3.4006 (3.4736) grad_norm: 1.1780 (nan) time: 0.5100 [2021-03-25 22:14:20 swin_small_patch4_window7_224] INFO: Epoch: [103] [1240/1251] eta: 0:00:05 lr: 0.000734 loss: 3.7746 (3.4749) grad_norm: 1.1381 (nan) time: 0.5089 [2021-03-25 22:14:25 swin_small_patch4_window7_224] INFO: Epoch: [103] [1250/1251] eta: 0:00:00 lr: 0.000734 loss: 3.7195 (3.4744) grad_norm: 1.1381 (nan) time: 0.5082 [2021-03-25 22:14:33 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 0.9122 (0.9122) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-25 22:14:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0228 (1.0515) acc1: 73.4375 (73.5795) acc5: 92.1875 (93.4659) [2021-03-25 22:14:36 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 1.0397 (1.0527) acc1: 73.4375 (74.4792) acc5: 92.1875 (93.3780) [2021-03-25 22:14:39 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0398 (1.0482) acc1: 75.0000 (74.7984) acc5: 93.7500 (93.2964) [2021-03-25 22:14:41 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0557 (1.0368) acc1: 75.0000 (75.1905) acc5: 93.7500 (93.3689) [2021-03-25 22:14:42 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9910 (1.0216) acc1: 75.0000 (75.2960) acc5: 93.7500 (93.5680) [2021-03-25 22:14:49 swin_small_patch4_window7_224] INFO: * Acc@1 76.116 Acc@5 93.454 loss 1.000 [2021-03-25 22:14:49 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.1% [2021-03-25 22:14:49 swin_small_patch4_window7_224] INFO: Max accuracy: 76.32% [2021-03-25 22:14:52 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 0/1251] eta: 1:15:08 lr: 0.000734 loss: 3.5963 (3.5963) grad_norm: 1.2071 (1.2071) time: 3.6037 [2021-03-25 22:14:58 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 10/1251] eta: 0:17:19 lr: 0.000734 loss: 3.4783 (3.3553) grad_norm: 1.2018 (1.2517) time: 0.8379 [2021-03-25 22:15:03 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 20/1251] eta: 0:13:52 lr: 0.000734 loss: 3.3363 (3.2788) grad_norm: 1.2324 (1.2807) time: 0.5302 [2021-03-25 22:15:08 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 30/1251] eta: 0:12:39 lr: 0.000734 loss: 3.3713 (3.3206) grad_norm: 1.1807 (1.2421) time: 0.5032 [2021-03-25 22:15:13 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 40/1251] eta: 0:12:01 lr: 0.000734 loss: 3.4187 (3.3689) grad_norm: 1.1673 (1.2308) time: 0.5109 [2021-03-25 22:15:18 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 50/1251] eta: 0:11:35 lr: 0.000734 loss: 3.2733 (3.3392) grad_norm: 1.1700 (1.2142) time: 0.5127 [2021-03-25 22:15:23 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 60/1251] eta: 0:11:15 lr: 0.000734 loss: 3.6610 (3.3872) grad_norm: 1.1203 (1.2052) time: 0.5098 [2021-03-25 22:15:28 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 70/1251] eta: 0:11:00 lr: 0.000734 loss: 3.3946 (3.3703) grad_norm: 1.2166 (1.2167) time: 0.5086 [2021-03-25 22:15:33 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 80/1251] eta: 0:10:49 lr: 0.000734 loss: 3.3946 (3.3940) grad_norm: 1.2672 (1.2202) time: 0.5144 [2021-03-25 22:15:39 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 90/1251] eta: 0:10:38 lr: 0.000734 loss: 3.6444 (3.4124) grad_norm: 1.2282 (1.2188) time: 0.5177 [2021-03-25 22:15:44 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 100/1251] eta: 0:10:29 lr: 0.000734 loss: 3.8261 (3.4515) grad_norm: 1.2251 (1.2230) time: 0.5160 [2021-03-25 22:15:49 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 110/1251] eta: 0:10:21 lr: 0.000734 loss: 3.6474 (3.4481) grad_norm: 1.1906 (1.2149) time: 0.5183 [2021-03-25 22:15:54 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 120/1251] eta: 0:10:12 lr: 0.000734 loss: 3.4954 (3.4639) grad_norm: 1.1619 (1.2119) time: 0.5139 [2021-03-25 22:15:59 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 130/1251] eta: 0:10:04 lr: 0.000734 loss: 3.6996 (3.4833) grad_norm: 1.1831 (1.2088) time: 0.5088 [2021-03-25 22:16:04 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 140/1251] eta: 0:09:55 lr: 0.000734 loss: 3.6996 (3.4740) grad_norm: 1.1241 (1.2005) time: 0.5016 [2021-03-25 22:16:09 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 150/1251] eta: 0:09:47 lr: 0.000734 loss: 3.4990 (3.4676) grad_norm: 1.0825 (1.1959) time: 0.4972 [2021-03-25 22:16:14 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 160/1251] eta: 0:09:39 lr: 0.000734 loss: 3.5941 (3.4880) grad_norm: 1.0887 (1.1907) time: 0.4983 [2021-03-25 22:16:19 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 170/1251] eta: 0:09:32 lr: 0.000734 loss: 3.7028 (3.4946) grad_norm: 1.1024 (1.1875) time: 0.5023 [2021-03-25 22:16:24 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 180/1251] eta: 0:09:26 lr: 0.000734 loss: 3.5086 (3.4865) grad_norm: 1.1568 (1.1893) time: 0.5125 [2021-03-25 22:16:29 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 190/1251] eta: 0:09:20 lr: 0.000734 loss: 3.3491 (3.4805) grad_norm: 1.1440 (1.1893) time: 0.5117 [2021-03-25 22:16:34 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 200/1251] eta: 0:09:13 lr: 0.000734 loss: 3.4455 (3.4774) grad_norm: 1.1205 (1.1861) time: 0.5043 [2021-03-25 22:16:39 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 210/1251] eta: 0:09:06 lr: 0.000734 loss: 3.5246 (3.4813) grad_norm: 1.1459 (1.1828) time: 0.4981 [2021-03-25 22:16:44 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 220/1251] eta: 0:09:00 lr: 0.000734 loss: 3.5075 (3.4736) grad_norm: 1.1530 (1.1838) time: 0.5001 [2021-03-25 22:16:49 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 230/1251] eta: 0:08:53 lr: 0.000733 loss: 3.6797 (3.4800) grad_norm: 1.1554 (1.1818) time: 0.5014 [2021-03-25 22:16:54 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 240/1251] eta: 0:08:48 lr: 0.000733 loss: 3.5758 (3.4692) grad_norm: 1.1535 (1.1828) time: 0.5030 [2021-03-25 22:17:00 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 250/1251] eta: 0:08:42 lr: 0.000733 loss: 3.4830 (3.4704) grad_norm: 1.2178 (1.1849) time: 0.5131 [2021-03-25 22:17:05 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 260/1251] eta: 0:08:36 lr: 0.000733 loss: 3.7198 (3.4642) grad_norm: 1.1741 (1.1844) time: 0.5119 [2021-03-25 22:17:10 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 270/1251] eta: 0:08:30 lr: 0.000733 loss: 3.6292 (3.4689) grad_norm: 1.1289 (1.1849) time: 0.5025 [2021-03-25 22:17:15 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 280/1251] eta: 0:08:25 lr: 0.000733 loss: 3.6292 (3.4681) grad_norm: 1.2085 (1.1859) time: 0.5016 [2021-03-25 22:17:20 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 290/1251] eta: 0:08:19 lr: 0.000733 loss: 3.5558 (3.4740) grad_norm: 1.1232 (1.1850) time: 0.5015 [2021-03-25 22:17:25 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 300/1251] eta: 0:08:13 lr: 0.000733 loss: 3.6238 (3.4764) grad_norm: 1.1645 (1.1869) time: 0.5023 [2021-03-25 22:17:30 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 310/1251] eta: 0:08:08 lr: 0.000733 loss: 3.5890 (3.4772) grad_norm: 1.1662 (1.1856) time: 0.5108 [2021-03-25 22:17:35 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 320/1251] eta: 0:08:02 lr: 0.000733 loss: 3.3603 (3.4684) grad_norm: 1.0904 (1.1822) time: 0.5101 [2021-03-25 22:17:40 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 330/1251] eta: 0:07:57 lr: 0.000733 loss: 3.0946 (3.4666) grad_norm: 1.1146 (1.1806) time: 0.5033 [2021-03-25 22:17:45 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 340/1251] eta: 0:07:51 lr: 0.000733 loss: 3.5294 (3.4693) grad_norm: 1.0908 (1.1779) time: 0.5079 [2021-03-25 22:17:50 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 350/1251] eta: 0:07:46 lr: 0.000733 loss: 3.4967 (3.4595) grad_norm: 1.0721 (1.1769) time: 0.5095 [2021-03-25 22:17:55 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 360/1251] eta: 0:07:40 lr: 0.000733 loss: 3.0596 (3.4545) grad_norm: 1.0966 (1.1750) time: 0.5032 [2021-03-25 22:18:00 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 370/1251] eta: 0:07:35 lr: 0.000733 loss: 3.7345 (3.4638) grad_norm: 1.1424 (1.1750) time: 0.5020 [2021-03-25 22:18:05 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 380/1251] eta: 0:07:29 lr: 0.000733 loss: 3.8033 (3.4714) grad_norm: 1.1658 (1.1759) time: 0.5057 [2021-03-25 22:18:10 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 390/1251] eta: 0:07:24 lr: 0.000733 loss: 3.6639 (3.4734) grad_norm: 1.2125 (1.1770) time: 0.5034 [2021-03-25 22:18:15 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 400/1251] eta: 0:07:18 lr: 0.000733 loss: 3.6064 (3.4704) grad_norm: 1.2121 (1.1785) time: 0.5012 [2021-03-25 22:18:20 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 410/1251] eta: 0:07:13 lr: 0.000733 loss: 3.3511 (3.4646) grad_norm: 1.1951 (1.1789) time: 0.5013 [2021-03-25 22:18:25 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 420/1251] eta: 0:07:07 lr: 0.000733 loss: 3.2677 (3.4618) grad_norm: 1.1646 (1.1788) time: 0.5015 [2021-03-25 22:18:31 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 430/1251] eta: 0:07:02 lr: 0.000733 loss: 3.4581 (3.4597) grad_norm: 1.1187 (1.1773) time: 0.5067 [2021-03-25 22:18:36 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 440/1251] eta: 0:06:57 lr: 0.000733 loss: 3.3871 (3.4548) grad_norm: 1.1068 (1.1755) time: 0.5126 [2021-03-25 22:18:41 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 450/1251] eta: 0:06:52 lr: 0.000733 loss: 3.3871 (3.4530) grad_norm: 1.1323 (1.1772) time: 0.5084 [2021-03-25 22:18:46 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 460/1251] eta: 0:06:46 lr: 0.000733 loss: 3.3043 (3.4484) grad_norm: 1.1565 (1.1777) time: 0.5063 [2021-03-25 22:18:51 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 470/1251] eta: 0:06:41 lr: 0.000733 loss: 3.2461 (3.4459) grad_norm: 1.1283 (1.1765) time: 0.5104 [2021-03-25 22:18:56 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 480/1251] eta: 0:06:36 lr: 0.000733 loss: 3.6399 (3.4526) grad_norm: 1.1030 (1.1762) time: 0.5084 [2021-03-25 22:19:01 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 490/1251] eta: 0:06:31 lr: 0.000733 loss: 3.7425 (3.4554) grad_norm: 1.1686 (1.1756) time: 0.5058 [2021-03-25 22:19:06 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 500/1251] eta: 0:06:25 lr: 0.000732 loss: 3.7425 (3.4610) grad_norm: 1.1687 (1.1758) time: 0.5044 [2021-03-25 22:19:11 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 510/1251] eta: 0:06:20 lr: 0.000732 loss: 3.7187 (3.4642) grad_norm: 1.1687 (1.1759) time: 0.5070 [2021-03-25 22:19:16 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 520/1251] eta: 0:06:15 lr: 0.000732 loss: 3.5139 (3.4664) grad_norm: 1.1365 (1.1745) time: 0.5067 [2021-03-25 22:19:21 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 530/1251] eta: 0:06:10 lr: 0.000732 loss: 3.5705 (3.4702) grad_norm: 1.0680 (1.1732) time: 0.5038 [2021-03-25 22:19:26 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 540/1251] eta: 0:06:04 lr: 0.000732 loss: 3.5705 (3.4692) grad_norm: 1.0965 (1.1735) time: 0.5046 [2021-03-25 22:19:32 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 550/1251] eta: 0:06:00 lr: 0.000732 loss: 3.6668 (3.4741) grad_norm: 1.1853 (1.1738) time: 0.5271 [2021-03-25 22:19:37 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 560/1251] eta: 0:05:55 lr: 0.000732 loss: 3.6668 (3.4720) grad_norm: 1.1782 (1.1737) time: 0.5273 [2021-03-25 22:19:42 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 570/1251] eta: 0:05:49 lr: 0.000732 loss: 3.6452 (3.4708) grad_norm: 1.1832 (1.1744) time: 0.5020 [2021-03-25 22:19:47 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 580/1251] eta: 0:05:44 lr: 0.000732 loss: 3.6600 (3.4687) grad_norm: 1.1985 (1.1747) time: 0.4960 [2021-03-25 22:19:52 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 590/1251] eta: 0:05:39 lr: 0.000732 loss: 3.3540 (3.4649) grad_norm: 1.2042 (1.1755) time: 0.5014 [2021-03-25 22:19:57 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 600/1251] eta: 0:05:33 lr: 0.000732 loss: 3.3540 (3.4639) grad_norm: 1.1975 (1.1754) time: 0.5036 [2021-03-25 22:20:02 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 610/1251] eta: 0:05:28 lr: 0.000732 loss: 3.6789 (3.4706) grad_norm: 1.1336 (1.1749) time: 0.5039 [2021-03-25 22:20:07 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 620/1251] eta: 0:05:23 lr: 0.000732 loss: 3.7937 (3.4729) grad_norm: 1.2122 (1.1768) time: 0.5057 [2021-03-25 22:20:12 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 630/1251] eta: 0:05:18 lr: 0.000732 loss: 3.5381 (3.4723) grad_norm: 1.2122 (1.1763) time: 0.5066 [2021-03-25 22:20:17 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 640/1251] eta: 0:05:13 lr: 0.000732 loss: 3.2693 (3.4684) grad_norm: 1.1575 (1.1766) time: 0.5188 [2021-03-25 22:20:22 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 650/1251] eta: 0:05:08 lr: 0.000732 loss: 3.1217 (3.4630) grad_norm: 1.1690 (1.1762) time: 0.5179 [2021-03-25 22:20:27 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 660/1251] eta: 0:05:02 lr: 0.000732 loss: 3.1376 (3.4607) grad_norm: 1.1463 (1.1775) time: 0.5045 [2021-03-25 22:20:32 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 670/1251] eta: 0:04:57 lr: 0.000732 loss: 3.3443 (3.4601) grad_norm: 1.1463 (1.1766) time: 0.4997 [2021-03-25 22:20:38 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 680/1251] eta: 0:04:52 lr: 0.000732 loss: 3.6612 (3.4648) grad_norm: 1.1171 (1.1759) time: 0.5039 [2021-03-25 22:20:43 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 690/1251] eta: 0:04:47 lr: 0.000732 loss: 3.6729 (3.4658) grad_norm: 1.1446 (1.1761) time: 0.5106 [2021-03-25 22:20:48 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 700/1251] eta: 0:04:42 lr: 0.000732 loss: 3.3542 (3.4623) grad_norm: 1.1843 (1.1769) time: 0.5100 [2021-03-25 22:20:53 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 710/1251] eta: 0:04:37 lr: 0.000732 loss: 3.5789 (3.4632) grad_norm: 1.1004 (1.1761) time: 0.5050 [2021-03-25 22:20:58 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 720/1251] eta: 0:04:31 lr: 0.000732 loss: 3.5587 (3.4604) grad_norm: 1.0988 (1.1758) time: 0.5068 [2021-03-25 22:21:03 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 730/1251] eta: 0:04:26 lr: 0.000732 loss: 3.4599 (3.4629) grad_norm: 1.1446 (1.1757) time: 0.5102 [2021-03-25 22:21:08 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 740/1251] eta: 0:04:21 lr: 0.000732 loss: 3.6797 (3.4620) grad_norm: 1.1029 (1.1750) time: 0.5286 [2021-03-25 22:21:13 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 750/1251] eta: 0:04:16 lr: 0.000732 loss: 3.5897 (3.4654) grad_norm: 1.0975 (1.1748) time: 0.5262 [2021-03-25 22:21:19 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 760/1251] eta: 0:04:11 lr: 0.000732 loss: 3.5897 (3.4641) grad_norm: 1.1213 (1.1746) time: 0.5054 [2021-03-25 22:21:24 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 770/1251] eta: 0:04:06 lr: 0.000731 loss: 3.6376 (3.4634) grad_norm: 1.1601 (1.1749) time: 0.5076 [2021-03-25 22:21:29 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 780/1251] eta: 0:04:01 lr: 0.000731 loss: 3.7045 (3.4658) grad_norm: 1.1346 (1.1747) time: 0.5046 [2021-03-25 22:21:34 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 790/1251] eta: 0:03:56 lr: 0.000731 loss: 3.4562 (3.4658) grad_norm: 1.1346 (1.1750) time: 0.5073 [2021-03-25 22:21:39 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 800/1251] eta: 0:03:50 lr: 0.000731 loss: 3.7410 (3.4699) grad_norm: 1.2043 (1.1754) time: 0.5095 [2021-03-25 22:21:44 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 810/1251] eta: 0:03:45 lr: 0.000731 loss: 3.8002 (3.4700) grad_norm: 1.1301 (1.1744) time: 0.5070 [2021-03-25 22:21:49 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 820/1251] eta: 0:03:40 lr: 0.000731 loss: 3.4704 (3.4694) grad_norm: 1.1099 (1.1741) time: 0.5052 [2021-03-25 22:21:54 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 830/1251] eta: 0:03:35 lr: 0.000731 loss: 3.4704 (3.4688) grad_norm: 1.1446 (1.1740) time: 0.5123 [2021-03-25 22:21:59 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 840/1251] eta: 0:03:30 lr: 0.000731 loss: 3.6346 (3.4700) grad_norm: 1.1966 (1.1752) time: 0.5159 [2021-03-25 22:22:04 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 850/1251] eta: 0:03:25 lr: 0.000731 loss: 3.7994 (3.4727) grad_norm: 1.1787 (1.1744) time: 0.5102 [2021-03-25 22:22:09 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 860/1251] eta: 0:03:20 lr: 0.000731 loss: 3.5446 (3.4708) grad_norm: 1.1522 (1.1748) time: 0.5088 [2021-03-25 22:22:14 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 870/1251] eta: 0:03:15 lr: 0.000731 loss: 3.3120 (3.4696) grad_norm: 1.1717 (1.1751) time: 0.5045 [2021-03-25 22:22:20 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 880/1251] eta: 0:03:09 lr: 0.000731 loss: 3.5394 (3.4705) grad_norm: 1.1474 (1.1748) time: 0.5141 [2021-03-25 22:22:25 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 890/1251] eta: 0:03:04 lr: 0.000731 loss: 3.6010 (3.4706) grad_norm: 1.1293 (1.1746) time: 0.5125 [2021-03-25 22:22:30 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 900/1251] eta: 0:02:59 lr: 0.000731 loss: 3.7238 (3.4705) grad_norm: 1.1130 (1.1742) time: 0.4968 [2021-03-25 22:22:35 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 910/1251] eta: 0:02:54 lr: 0.000731 loss: 3.7259 (3.4714) grad_norm: 1.1130 (1.1741) time: 0.5047 [2021-03-25 22:22:40 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 920/1251] eta: 0:02:49 lr: 0.000731 loss: 3.5722 (3.4696) grad_norm: 1.1328 (1.1741) time: 0.5140 [2021-03-25 22:22:45 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 930/1251] eta: 0:02:44 lr: 0.000731 loss: 3.2683 (3.4670) grad_norm: 1.1116 (1.1736) time: 0.5100 [2021-03-25 22:22:50 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 940/1251] eta: 0:02:39 lr: 0.000731 loss: 3.3521 (3.4659) grad_norm: 1.1146 (1.1735) time: 0.5085 [2021-03-25 22:22:55 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 950/1251] eta: 0:02:33 lr: 0.000731 loss: 3.4803 (3.4662) grad_norm: 1.1524 (1.1740) time: 0.5051 [2021-03-25 22:23:00 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 960/1251] eta: 0:02:28 lr: 0.000731 loss: 3.6009 (3.4668) grad_norm: 1.1201 (1.1735) time: 0.5005 [2021-03-25 22:23:05 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 970/1251] eta: 0:02:23 lr: 0.000731 loss: 3.4004 (3.4634) grad_norm: 1.1067 (1.1733) time: 0.5033 [2021-03-25 22:23:10 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 980/1251] eta: 0:02:18 lr: 0.000731 loss: 3.4004 (3.4633) grad_norm: 1.1448 (1.1736) time: 0.5082 [2021-03-25 22:23:15 swin_small_patch4_window7_224] INFO: Epoch: [104] [ 990/1251] eta: 0:02:13 lr: 0.000731 loss: 3.4950 (3.4636) grad_norm: 1.2004 (1.1739) time: 0.5063 [2021-03-25 22:23:20 swin_small_patch4_window7_224] INFO: Epoch: [104] [1000/1251] eta: 0:02:08 lr: 0.000731 loss: 3.5310 (3.4646) grad_norm: 1.1523 (1.1739) time: 0.5079 [2021-03-25 22:23:26 swin_small_patch4_window7_224] INFO: Epoch: [104] [1010/1251] eta: 0:02:03 lr: 0.000731 loss: 3.4811 (3.4650) grad_norm: 1.1569 (1.1742) time: 0.5083 [2021-03-25 22:23:31 swin_small_patch4_window7_224] INFO: Epoch: [104] [1020/1251] eta: 0:01:58 lr: 0.000731 loss: 3.4588 (3.4642) grad_norm: 1.1534 (1.1738) time: 0.5071 [2021-03-25 22:23:36 swin_small_patch4_window7_224] INFO: Epoch: [104] [1030/1251] eta: 0:01:52 lr: 0.000731 loss: 3.6573 (3.4650) grad_norm: 1.1692 (1.1747) time: 0.5068 [2021-03-25 22:23:41 swin_small_patch4_window7_224] INFO: Epoch: [104] [1040/1251] eta: 0:01:47 lr: 0.000731 loss: 3.7750 (3.4682) grad_norm: 1.2214 (1.1747) time: 0.5068 [2021-03-25 22:23:46 swin_small_patch4_window7_224] INFO: Epoch: [104] [1050/1251] eta: 0:01:42 lr: 0.000730 loss: 3.5412 (3.4666) grad_norm: 1.0842 (1.1742) time: 0.5156 [2021-03-25 22:23:51 swin_small_patch4_window7_224] INFO: Epoch: [104] [1060/1251] eta: 0:01:37 lr: 0.000730 loss: 3.4518 (3.4668) grad_norm: 1.1561 (1.1756) time: 0.5160 [2021-03-25 22:23:56 swin_small_patch4_window7_224] INFO: Epoch: [104] [1070/1251] eta: 0:01:32 lr: 0.000730 loss: 3.5172 (3.4672) grad_norm: 1.1629 (1.1753) time: 0.5078 [2021-03-25 22:24:01 swin_small_patch4_window7_224] INFO: Epoch: [104] [1080/1251] eta: 0:01:27 lr: 0.000730 loss: 3.5172 (3.4658) grad_norm: 1.1143 (1.1746) time: 0.5014 [2021-03-25 22:24:06 swin_small_patch4_window7_224] INFO: Epoch: [104] [1090/1251] eta: 0:01:22 lr: 0.000730 loss: 3.2984 (3.4643) grad_norm: 1.1154 (1.1745) time: 0.4966 [2021-03-25 22:24:11 swin_small_patch4_window7_224] INFO: Epoch: [104] [1100/1251] eta: 0:01:17 lr: 0.000730 loss: 3.2984 (3.4624) grad_norm: 1.1561 (1.1746) time: 0.5009 [2021-03-25 22:24:16 swin_small_patch4_window7_224] INFO: Epoch: [104] [1110/1251] eta: 0:01:12 lr: 0.000730 loss: 3.5254 (3.4599) grad_norm: 1.1309 (1.1740) time: 0.5036 [2021-03-25 22:24:21 swin_small_patch4_window7_224] INFO: Epoch: [104] [1120/1251] eta: 0:01:06 lr: 0.000730 loss: 3.4874 (3.4609) grad_norm: 1.1035 (1.1733) time: 0.4999 [2021-03-25 22:24:26 swin_small_patch4_window7_224] INFO: Epoch: [104] [1130/1251] eta: 0:01:01 lr: 0.000730 loss: 3.4874 (3.4620) grad_norm: 1.1035 (1.1728) time: 0.5013 [2021-03-25 22:24:31 swin_small_patch4_window7_224] INFO: Epoch: [104] [1140/1251] eta: 0:00:56 lr: 0.000730 loss: 3.7591 (3.4630) grad_norm: 1.1634 (1.1730) time: 0.5045 [2021-03-25 22:24:36 swin_small_patch4_window7_224] INFO: Epoch: [104] [1150/1251] eta: 0:00:51 lr: 0.000730 loss: 3.7991 (3.4652) grad_norm: 1.1772 (1.1730) time: 0.5044 [2021-03-25 22:24:41 swin_small_patch4_window7_224] INFO: Epoch: [104] [1160/1251] eta: 0:00:46 lr: 0.000730 loss: 3.6306 (3.4637) grad_norm: 1.1772 (1.1728) time: 0.5051 [2021-03-25 22:24:46 swin_small_patch4_window7_224] INFO: Epoch: [104] [1170/1251] eta: 0:00:41 lr: 0.000730 loss: 3.4961 (3.4641) grad_norm: 1.2090 (1.1735) time: 0.5088 [2021-03-25 22:24:52 swin_small_patch4_window7_224] INFO: Epoch: [104] [1180/1251] eta: 0:00:36 lr: 0.000730 loss: 3.4961 (3.4625) grad_norm: 1.1755 (1.1730) time: 0.5099 [2021-03-25 22:24:57 swin_small_patch4_window7_224] INFO: Epoch: [104] [1190/1251] eta: 0:00:31 lr: 0.000730 loss: 3.6225 (3.4642) grad_norm: 1.1261 (1.1727) time: 0.5056 [2021-03-25 22:25:02 swin_small_patch4_window7_224] INFO: Epoch: [104] [1200/1251] eta: 0:00:26 lr: 0.000730 loss: 3.7275 (3.4641) grad_norm: 1.1261 (1.1727) time: 0.5021 [2021-03-25 22:25:07 swin_small_patch4_window7_224] INFO: Epoch: [104] [1210/1251] eta: 0:00:20 lr: 0.000730 loss: 3.7275 (3.4666) grad_norm: 1.1945 (1.1732) time: 0.5021 [2021-03-25 22:25:12 swin_small_patch4_window7_224] INFO: Epoch: [104] [1220/1251] eta: 0:00:15 lr: 0.000730 loss: 3.6952 (3.4669) grad_norm: 1.1945 (1.1731) time: 0.5000 [2021-03-25 22:25:17 swin_small_patch4_window7_224] INFO: Epoch: [104] [1230/1251] eta: 0:00:10 lr: 0.000730 loss: 3.5342 (3.4661) grad_norm: 1.1560 (1.1732) time: 0.5039 [2021-03-25 22:25:22 swin_small_patch4_window7_224] INFO: Epoch: [104] [1240/1251] eta: 0:00:05 lr: 0.000730 loss: 3.5107 (3.4646) grad_norm: 1.1610 (1.1742) time: 0.5017 [2021-03-25 22:25:27 swin_small_patch4_window7_224] INFO: Epoch: [104] [1250/1251] eta: 0:00:00 lr: 0.000730 loss: 3.4900 (3.4642) grad_norm: 1.1743 (1.1743) time: 0.4973 [2021-03-25 22:25:36 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:03:18 loss: 0.9601 (0.9601) acc1: 70.3125 (70.3125) acc5: 95.3125 (95.3125) [2021-03-25 22:25:39 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:24 loss: 1.0316 (1.0756) acc1: 73.4375 (74.0057) acc5: 93.7500 (93.3239) [2021-03-25 22:25:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.0323 (1.0585) acc1: 73.4375 (73.5119) acc5: 93.7500 (93.6756) [2021-03-25 22:25:42 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9526 (1.0180) acc1: 75.0000 (75.3528) acc5: 93.7500 (93.8508) [2021-03-25 22:25:44 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9217 (1.0284) acc1: 76.5625 (75.3049) acc5: 93.7500 (93.6738) [2021-03-25 22:25:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9672 (1.0209) acc1: 76.5625 (75.4560) acc5: 93.7500 (93.6640) [2021-03-25 22:25:50 swin_small_patch4_window7_224] INFO: * Acc@1 76.248 Acc@5 93.666 loss 1.009 [2021-03-25 22:25:50 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-25 22:25:50 swin_small_patch4_window7_224] INFO: Max accuracy: 76.32% [2021-03-25 22:25:55 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 0/1251] eta: 1:28:25 lr: 0.000730 loss: 3.7613 (3.7613) grad_norm: 1.2327 (1.2327) time: 4.2414 [2021-03-25 22:26:00 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 10/1251] eta: 0:18:04 lr: 0.000730 loss: 3.7613 (3.6961) grad_norm: 1.2090 (1.2000) time: 0.8736 [2021-03-25 22:26:05 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 20/1251] eta: 0:14:25 lr: 0.000730 loss: 3.7153 (3.6234) grad_norm: 1.1557 (1.1628) time: 0.5259 [2021-03-25 22:26:10 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 30/1251] eta: 0:12:59 lr: 0.000730 loss: 3.4622 (3.5370) grad_norm: 1.1151 (1.1499) time: 0.5092 [2021-03-25 22:26:15 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 40/1251] eta: 0:12:18 lr: 0.000730 loss: 3.5831 (3.5659) grad_norm: 1.1036 (1.1389) time: 0.5124 [2021-03-25 22:26:20 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 50/1251] eta: 0:11:46 lr: 0.000730 loss: 3.4166 (3.5127) grad_norm: 1.1036 (1.1352) time: 0.5107 [2021-03-25 22:26:25 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 60/1251] eta: 0:11:23 lr: 0.000730 loss: 3.1166 (3.4592) grad_norm: 1.1144 (1.1474) time: 0.4995 [2021-03-25 22:26:31 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 70/1251] eta: 0:11:08 lr: 0.000729 loss: 3.3776 (3.4872) grad_norm: 1.1654 (1.1573) time: 0.5077 [2021-03-25 22:26:36 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 80/1251] eta: 0:10:53 lr: 0.000729 loss: 3.5499 (3.4524) grad_norm: 1.1677 (1.1630) time: 0.5116 [2021-03-25 22:26:41 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 90/1251] eta: 0:10:42 lr: 0.000729 loss: 3.3521 (3.4086) grad_norm: 1.2155 (1.1684) time: 0.5114 [2021-03-25 22:26:46 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 100/1251] eta: 0:10:30 lr: 0.000729 loss: 3.5193 (3.4136) grad_norm: 1.1465 (1.1677) time: 0.5047 [2021-03-25 22:26:51 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 110/1251] eta: 0:10:20 lr: 0.000729 loss: 3.4906 (3.4078) grad_norm: 1.1498 (1.1684) time: 0.4976 [2021-03-25 22:26:56 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 120/1251] eta: 0:10:11 lr: 0.000729 loss: 3.3923 (3.4046) grad_norm: 1.1901 (1.1756) time: 0.5031 [2021-03-25 22:27:01 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 130/1251] eta: 0:10:03 lr: 0.000729 loss: 3.4744 (3.4152) grad_norm: 1.2423 (1.1818) time: 0.5073 [2021-03-25 22:27:06 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 140/1251] eta: 0:09:55 lr: 0.000729 loss: 3.7053 (3.4113) grad_norm: 1.1508 (1.1790) time: 0.5084 [2021-03-25 22:27:11 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 150/1251] eta: 0:09:48 lr: 0.000729 loss: 3.4850 (3.4186) grad_norm: 1.1193 (1.1770) time: 0.5078 [2021-03-25 22:27:16 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 160/1251] eta: 0:09:40 lr: 0.000729 loss: 3.4258 (3.4071) grad_norm: 1.1495 (1.1778) time: 0.5089 [2021-03-25 22:27:21 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 170/1251] eta: 0:09:34 lr: 0.000729 loss: 3.4185 (3.4194) grad_norm: 1.1495 (1.1772) time: 0.5079 [2021-03-25 22:27:26 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 180/1251] eta: 0:09:27 lr: 0.000729 loss: 3.4965 (3.4183) grad_norm: 1.1830 (1.1832) time: 0.5099 [2021-03-25 22:27:31 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 190/1251] eta: 0:09:20 lr: 0.000729 loss: 3.3159 (3.4086) grad_norm: 1.1294 (1.1796) time: 0.5065 [2021-03-25 22:27:36 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 200/1251] eta: 0:09:14 lr: 0.000729 loss: 3.2705 (3.4002) grad_norm: 1.1191 (1.1779) time: 0.5041 [2021-03-25 22:27:41 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 210/1251] eta: 0:09:08 lr: 0.000729 loss: 3.4903 (3.4094) grad_norm: 1.1363 (1.1785) time: 0.5097 [2021-03-25 22:27:47 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 220/1251] eta: 0:09:02 lr: 0.000729 loss: 3.5001 (3.4099) grad_norm: 1.2021 (1.1802) time: 0.5084 [2021-03-25 22:27:52 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 230/1251] eta: 0:08:55 lr: 0.000729 loss: 3.4146 (3.4028) grad_norm: 1.2150 (1.1817) time: 0.5052 [2021-03-25 22:27:57 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 240/1251] eta: 0:08:49 lr: 0.000729 loss: 3.4901 (3.4106) grad_norm: 1.1941 (1.1826) time: 0.5002 [2021-03-25 22:28:02 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 250/1251] eta: 0:08:43 lr: 0.000729 loss: 3.5617 (3.4074) grad_norm: 1.1773 (1.1827) time: 0.5041 [2021-03-25 22:28:07 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 260/1251] eta: 0:08:37 lr: 0.000729 loss: 3.2148 (3.4008) grad_norm: 1.1165 (1.1793) time: 0.5111 [2021-03-25 22:28:12 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 270/1251] eta: 0:08:32 lr: 0.000729 loss: 3.3752 (3.4100) grad_norm: 1.1165 (1.1796) time: 0.5074 [2021-03-25 22:28:17 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 280/1251] eta: 0:08:25 lr: 0.000729 loss: 3.6167 (3.4142) grad_norm: 1.1559 (1.1806) time: 0.5005 [2021-03-25 22:28:22 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 290/1251] eta: 0:08:20 lr: 0.000729 loss: 3.6236 (3.4185) grad_norm: 1.1255 (1.1797) time: 0.5012 [2021-03-25 22:28:27 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 300/1251] eta: 0:08:14 lr: 0.000729 loss: 3.6837 (3.4267) grad_norm: 1.1155 (1.1770) time: 0.5000 [2021-03-25 22:28:32 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 310/1251] eta: 0:08:08 lr: 0.000729 loss: 3.6912 (3.4294) grad_norm: 1.0626 (1.1754) time: 0.5039 [2021-03-25 22:28:37 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 320/1251] eta: 0:08:03 lr: 0.000729 loss: 3.5299 (3.4270) grad_norm: 1.1432 (1.1749) time: 0.5116 [2021-03-25 22:28:42 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 330/1251] eta: 0:07:57 lr: 0.000729 loss: 3.4048 (3.4273) grad_norm: 1.1521 (1.1744) time: 0.5088 [2021-03-25 22:28:47 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 340/1251] eta: 0:07:52 lr: 0.000728 loss: 3.4715 (3.4270) grad_norm: 1.1531 (1.1744) time: 0.5079 [2021-03-25 22:28:52 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 350/1251] eta: 0:07:46 lr: 0.000728 loss: 3.4715 (3.4205) grad_norm: 1.1624 (1.1751) time: 0.5044 [2021-03-25 22:28:57 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 360/1251] eta: 0:07:41 lr: 0.000728 loss: 3.3174 (3.4184) grad_norm: 1.1003 (1.1729) time: 0.5000 [2021-03-25 22:29:02 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 370/1251] eta: 0:07:35 lr: 0.000728 loss: 3.3653 (3.4172) grad_norm: 1.1122 (1.1737) time: 0.4971 [2021-03-25 22:29:07 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 380/1251] eta: 0:07:29 lr: 0.000728 loss: 3.4360 (3.4192) grad_norm: 1.1655 (1.1738) time: 0.4983 [2021-03-25 22:29:12 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 390/1251] eta: 0:07:24 lr: 0.000728 loss: 3.7296 (3.4266) grad_norm: 1.1570 (1.1736) time: 0.5038 [2021-03-25 22:29:17 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 400/1251] eta: 0:07:18 lr: 0.000728 loss: 3.4638 (3.4213) grad_norm: 1.1197 (1.1724) time: 0.5037 [2021-03-25 22:29:22 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 410/1251] eta: 0:07:13 lr: 0.000728 loss: 3.4638 (3.4278) grad_norm: 1.1197 (1.1733) time: 0.5027 [2021-03-25 22:29:27 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 420/1251] eta: 0:07:08 lr: 0.000728 loss: 3.5888 (3.4257) grad_norm: 1.1386 (1.1733) time: 0.5020 [2021-03-25 22:29:32 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 430/1251] eta: 0:07:02 lr: 0.000728 loss: 3.5498 (3.4236) grad_norm: 1.1262 (1.1743) time: 0.5043 [2021-03-25 22:29:37 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 440/1251] eta: 0:06:57 lr: 0.000728 loss: 3.6679 (3.4274) grad_norm: 1.2220 (1.1758) time: 0.5100 [2021-03-25 22:29:43 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 450/1251] eta: 0:06:52 lr: 0.000728 loss: 3.6225 (3.4240) grad_norm: 1.2129 (1.1757) time: 0.5094 [2021-03-25 22:29:48 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 460/1251] eta: 0:06:46 lr: 0.000728 loss: 3.4770 (3.4241) grad_norm: 1.1402 (1.1746) time: 0.5045 [2021-03-25 22:29:53 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 470/1251] eta: 0:06:41 lr: 0.000728 loss: 3.4876 (3.4248) grad_norm: 1.1461 (1.1766) time: 0.5060 [2021-03-25 22:29:58 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 480/1251] eta: 0:06:36 lr: 0.000728 loss: 3.5311 (3.4299) grad_norm: 1.1335 (1.1745) time: 0.5115 [2021-03-25 22:30:03 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 490/1251] eta: 0:06:31 lr: 0.000728 loss: 3.5479 (3.4323) grad_norm: 1.1265 (1.1753) time: 0.5073 [2021-03-25 22:30:08 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 500/1251] eta: 0:06:25 lr: 0.000728 loss: 3.6741 (3.4354) grad_norm: 1.2168 (1.1778) time: 0.4996 [2021-03-25 22:30:13 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 510/1251] eta: 0:06:20 lr: 0.000728 loss: 3.4227 (3.4340) grad_norm: 1.1951 (1.1777) time: 0.4968 [2021-03-25 22:30:18 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 520/1251] eta: 0:06:15 lr: 0.000728 loss: 3.4227 (3.4368) grad_norm: 1.1690 (1.1784) time: 0.5013 [2021-03-25 22:30:23 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 530/1251] eta: 0:06:09 lr: 0.000728 loss: 3.6639 (3.4385) grad_norm: 1.1187 (1.1779) time: 0.5044 [2021-03-25 22:30:28 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 540/1251] eta: 0:06:04 lr: 0.000728 loss: 3.6450 (3.4367) grad_norm: 1.1037 (1.1771) time: 0.5097 [2021-03-25 22:30:33 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 550/1251] eta: 0:05:59 lr: 0.000728 loss: 3.2500 (3.4360) grad_norm: 1.1161 (1.1775) time: 0.5196 [2021-03-25 22:30:38 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 560/1251] eta: 0:05:54 lr: 0.000728 loss: 3.2500 (3.4338) grad_norm: 1.1100 (1.1764) time: 0.5171 [2021-03-25 22:30:43 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 570/1251] eta: 0:05:49 lr: 0.000728 loss: 3.3826 (3.4339) grad_norm: 1.1173 (1.1761) time: 0.5046 [2021-03-25 22:30:48 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 580/1251] eta: 0:05:44 lr: 0.000728 loss: 3.5423 (3.4352) grad_norm: 1.1752 (1.1765) time: 0.5041 [2021-03-25 22:30:54 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 590/1251] eta: 0:05:39 lr: 0.000728 loss: 3.5423 (3.4312) grad_norm: 1.1875 (1.1763) time: 0.5117 [2021-03-25 22:30:59 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 600/1251] eta: 0:05:33 lr: 0.000728 loss: 3.3809 (3.4316) grad_norm: 1.1234 (1.1752) time: 0.5072 [2021-03-25 22:31:04 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 610/1251] eta: 0:05:28 lr: 0.000727 loss: 3.5037 (3.4348) grad_norm: 1.1234 (1.1764) time: 0.5038 [2021-03-25 22:31:09 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 620/1251] eta: 0:05:23 lr: 0.000727 loss: 3.4758 (3.4344) grad_norm: 1.1384 (1.1763) time: 0.5027 [2021-03-25 22:31:14 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 630/1251] eta: 0:05:18 lr: 0.000727 loss: 3.4557 (3.4351) grad_norm: 1.1384 (1.1766) time: 0.5068 [2021-03-25 22:31:19 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 640/1251] eta: 0:05:13 lr: 0.000727 loss: 3.4288 (3.4342) grad_norm: 1.1409 (1.1769) time: 0.5136 [2021-03-25 22:31:24 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 650/1251] eta: 0:05:07 lr: 0.000727 loss: 3.4747 (3.4357) grad_norm: 1.1549 (1.1770) time: 0.5103 [2021-03-25 22:31:29 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 660/1251] eta: 0:05:02 lr: 0.000727 loss: 3.6648 (3.4372) grad_norm: 1.1200 (1.1760) time: 0.5062 [2021-03-25 22:31:34 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 670/1251] eta: 0:04:57 lr: 0.000727 loss: 3.5638 (3.4365) grad_norm: 1.0894 (1.1754) time: 0.5017 [2021-03-25 22:31:39 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 680/1251] eta: 0:04:52 lr: 0.000727 loss: 3.6249 (3.4386) grad_norm: 1.0749 (1.1744) time: 0.4994 [2021-03-25 22:31:44 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 690/1251] eta: 0:04:47 lr: 0.000727 loss: 3.6313 (3.4391) grad_norm: 1.1208 (1.1743) time: 0.5049 [2021-03-25 22:31:49 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 700/1251] eta: 0:04:41 lr: 0.000727 loss: 3.7191 (3.4416) grad_norm: 1.1845 (nan) time: 0.5042 [2021-03-25 22:31:54 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 710/1251] eta: 0:04:36 lr: 0.000727 loss: 3.5012 (3.4403) grad_norm: 1.2101 (nan) time: 0.4971 [2021-03-25 22:31:59 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 720/1251] eta: 0:04:31 lr: 0.000727 loss: 3.5429 (3.4432) grad_norm: 1.1475 (nan) time: 0.4978 [2021-03-25 22:32:04 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 730/1251] eta: 0:04:26 lr: 0.000727 loss: 3.7083 (3.4471) grad_norm: 1.1475 (nan) time: 0.5064 [2021-03-25 22:32:10 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 740/1251] eta: 0:04:21 lr: 0.000727 loss: 3.6773 (3.4490) grad_norm: 1.1877 (nan) time: 0.5206 [2021-03-25 22:32:15 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 750/1251] eta: 0:04:16 lr: 0.000727 loss: 3.6728 (3.4516) grad_norm: 1.1827 (nan) time: 0.5210 [2021-03-25 22:32:20 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 760/1251] eta: 0:04:11 lr: 0.000727 loss: 3.6274 (3.4512) grad_norm: 1.1686 (nan) time: 0.5168 [2021-03-25 22:32:25 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 770/1251] eta: 0:04:06 lr: 0.000727 loss: 3.3878 (3.4507) grad_norm: 1.2093 (nan) time: 0.5103 [2021-03-25 22:32:30 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 780/1251] eta: 0:04:00 lr: 0.000727 loss: 3.3153 (3.4472) grad_norm: 1.2083 (nan) time: 0.5024 [2021-03-25 22:32:35 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 790/1251] eta: 0:03:55 lr: 0.000727 loss: 3.2221 (3.4446) grad_norm: 1.1508 (nan) time: 0.5126 [2021-03-25 22:32:40 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 800/1251] eta: 0:03:50 lr: 0.000727 loss: 3.5542 (3.4486) grad_norm: 1.1444 (nan) time: 0.5136 [2021-03-25 22:32:45 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 810/1251] eta: 0:03:45 lr: 0.000727 loss: 3.7842 (3.4516) grad_norm: 1.2030 (nan) time: 0.5084 [2021-03-25 22:32:50 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 820/1251] eta: 0:03:40 lr: 0.000727 loss: 3.7842 (3.4549) grad_norm: 1.2072 (nan) time: 0.5037 [2021-03-25 22:32:55 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 830/1251] eta: 0:03:35 lr: 0.000727 loss: 3.5328 (3.4556) grad_norm: 1.1604 (nan) time: 0.5003 [2021-03-25 22:33:00 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 840/1251] eta: 0:03:30 lr: 0.000727 loss: 3.4563 (3.4550) grad_norm: 1.1376 (nan) time: 0.5012 [2021-03-25 22:33:05 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 850/1251] eta: 0:03:24 lr: 0.000727 loss: 3.3157 (3.4543) grad_norm: 1.1511 (nan) time: 0.4993 [2021-03-25 22:33:10 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 860/1251] eta: 0:03:19 lr: 0.000727 loss: 3.5315 (3.4561) grad_norm: 1.1896 (nan) time: 0.5014 [2021-03-25 22:33:15 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 870/1251] eta: 0:03:14 lr: 0.000727 loss: 3.4794 (3.4551) grad_norm: 1.1896 (nan) time: 0.5032 [2021-03-25 22:33:20 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 880/1251] eta: 0:03:09 lr: 0.000726 loss: 3.5996 (3.4571) grad_norm: 1.2030 (nan) time: 0.5057 [2021-03-25 22:33:25 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 890/1251] eta: 0:03:04 lr: 0.000726 loss: 3.6484 (3.4585) grad_norm: 1.1433 (nan) time: 0.5032 [2021-03-25 22:33:31 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 900/1251] eta: 0:02:59 lr: 0.000726 loss: 3.3870 (3.4561) grad_norm: 1.1428 (nan) time: 0.5027 [2021-03-25 22:33:36 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 910/1251] eta: 0:02:54 lr: 0.000726 loss: 3.3541 (3.4580) grad_norm: 1.1615 (nan) time: 0.5097 [2021-03-25 22:33:41 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 920/1251] eta: 0:02:48 lr: 0.000726 loss: 3.6058 (3.4601) grad_norm: 1.1887 (nan) time: 0.5095 [2021-03-25 22:33:46 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 930/1251] eta: 0:02:43 lr: 0.000726 loss: 3.5719 (3.4592) grad_norm: 1.2099 (nan) time: 0.5104 [2021-03-25 22:33:51 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 940/1251] eta: 0:02:38 lr: 0.000726 loss: 3.2556 (3.4574) grad_norm: 1.1680 (nan) time: 0.5129 [2021-03-25 22:33:56 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 950/1251] eta: 0:02:33 lr: 0.000726 loss: 3.6408 (3.4611) grad_norm: 1.1757 (nan) time: 0.5110 [2021-03-25 22:34:01 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 960/1251] eta: 0:02:28 lr: 0.000726 loss: 3.6970 (3.4613) grad_norm: 1.1623 (nan) time: 0.5072 [2021-03-25 22:34:06 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 970/1251] eta: 0:02:23 lr: 0.000726 loss: 3.3362 (3.4587) grad_norm: 1.1364 (nan) time: 0.5051 [2021-03-25 22:34:11 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 980/1251] eta: 0:02:18 lr: 0.000726 loss: 3.3454 (3.4582) grad_norm: 1.1201 (nan) time: 0.5074 [2021-03-25 22:34:16 swin_small_patch4_window7_224] INFO: Epoch: [105] [ 990/1251] eta: 0:02:13 lr: 0.000726 loss: 3.6354 (3.4591) grad_norm: 1.1201 (nan) time: 0.5067 [2021-03-25 22:34:21 swin_small_patch4_window7_224] INFO: Epoch: [105] [1000/1251] eta: 0:02:08 lr: 0.000726 loss: 3.5123 (3.4573) grad_norm: 1.1200 (nan) time: 0.5086 [2021-03-25 22:34:26 swin_small_patch4_window7_224] INFO: Epoch: [105] [1010/1251] eta: 0:02:03 lr: 0.000726 loss: 3.4596 (3.4566) grad_norm: 1.1320 (nan) time: 0.5084 [2021-03-25 22:34:31 swin_small_patch4_window7_224] INFO: Epoch: [105] [1020/1251] eta: 0:01:57 lr: 0.000726 loss: 3.4596 (3.4571) grad_norm: 1.1634 (nan) time: 0.5020 [2021-03-25 22:34:36 swin_small_patch4_window7_224] INFO: Epoch: [105] [1030/1251] eta: 0:01:52 lr: 0.000726 loss: 3.4725 (3.4582) grad_norm: 1.1551 (nan) time: 0.5002 [2021-03-25 22:34:41 swin_small_patch4_window7_224] INFO: Epoch: [105] [1040/1251] eta: 0:01:47 lr: 0.000726 loss: 3.4959 (3.4577) grad_norm: 1.1353 (nan) time: 0.4999 [2021-03-25 22:34:47 swin_small_patch4_window7_224] INFO: Epoch: [105] [1050/1251] eta: 0:01:42 lr: 0.000726 loss: 3.4745 (3.4591) grad_norm: 1.1276 (nan) time: 0.5010 [2021-03-25 22:34:52 swin_small_patch4_window7_224] INFO: Epoch: [105] [1060/1251] eta: 0:01:37 lr: 0.000726 loss: 3.3818 (3.4570) grad_norm: 1.1389 (nan) time: 0.5041 [2021-03-25 22:34:57 swin_small_patch4_window7_224] INFO: Epoch: [105] [1070/1251] eta: 0:01:32 lr: 0.000726 loss: 3.3899 (3.4594) grad_norm: 1.2333 (nan) time: 0.5072 [2021-03-25 22:35:02 swin_small_patch4_window7_224] INFO: Epoch: [105] [1080/1251] eta: 0:01:27 lr: 0.000726 loss: 3.6378 (3.4613) grad_norm: 1.2426 (nan) time: 0.5119 [2021-03-25 22:35:07 swin_small_patch4_window7_224] INFO: Epoch: [105] [1090/1251] eta: 0:01:22 lr: 0.000726 loss: 3.6659 (3.4620) grad_norm: 1.1705 (nan) time: 0.5108 [2021-03-25 22:35:12 swin_small_patch4_window7_224] INFO: Epoch: [105] [1100/1251] eta: 0:01:17 lr: 0.000726 loss: 3.6856 (3.4613) grad_norm: 1.1500 (nan) time: 0.5078 [2021-03-25 22:35:17 swin_small_patch4_window7_224] INFO: Epoch: [105] [1110/1251] eta: 0:01:11 lr: 0.000726 loss: 3.7707 (3.4620) grad_norm: 1.1530 (nan) time: 0.5015 [2021-03-25 22:35:22 swin_small_patch4_window7_224] INFO: Epoch: [105] [1120/1251] eta: 0:01:06 lr: 0.000726 loss: 3.5764 (3.4614) grad_norm: 1.1271 (nan) time: 0.5013 [2021-03-25 22:35:27 swin_small_patch4_window7_224] INFO: Epoch: [105] [1130/1251] eta: 0:01:01 lr: 0.000726 loss: 3.4348 (3.4607) grad_norm: 1.1263 (nan) time: 0.5060 [2021-03-25 22:35:32 swin_small_patch4_window7_224] INFO: Epoch: [105] [1140/1251] eta: 0:00:56 lr: 0.000726 loss: 3.5924 (3.4628) grad_norm: 1.1263 (nan) time: 0.5013 [2021-03-25 22:35:37 swin_small_patch4_window7_224] INFO: Epoch: [105] [1150/1251] eta: 0:00:51 lr: 0.000725 loss: 3.6622 (3.4642) grad_norm: 1.1183 (nan) time: 0.4954 [2021-03-25 22:35:42 swin_small_patch4_window7_224] INFO: Epoch: [105] [1160/1251] eta: 0:00:46 lr: 0.000725 loss: 3.6207 (3.4640) grad_norm: 1.1302 (nan) time: 0.5017 [2021-03-25 22:35:47 swin_small_patch4_window7_224] INFO: Epoch: [105] [1170/1251] eta: 0:00:41 lr: 0.000725 loss: 3.6207 (3.4660) grad_norm: 1.1302 (nan) time: 0.5054 [2021-03-25 22:35:52 swin_small_patch4_window7_224] INFO: Epoch: [105] [1180/1251] eta: 0:00:36 lr: 0.000725 loss: 3.6820 (3.4659) grad_norm: 1.1153 (nan) time: 0.5017 [2021-03-25 22:35:57 swin_small_patch4_window7_224] INFO: Epoch: [105] [1190/1251] eta: 0:00:31 lr: 0.000725 loss: 3.3658 (3.4649) grad_norm: 1.1234 (nan) time: 0.4990 [2021-03-25 22:36:02 swin_small_patch4_window7_224] INFO: Epoch: [105] [1200/1251] eta: 0:00:25 lr: 0.000725 loss: 3.4320 (3.4656) grad_norm: 1.1866 (nan) time: 0.4976 [2021-03-25 22:36:07 swin_small_patch4_window7_224] INFO: Epoch: [105] [1210/1251] eta: 0:00:20 lr: 0.000725 loss: 3.7902 (3.4683) grad_norm: 1.1866 (nan) time: 0.4988 [2021-03-25 22:36:12 swin_small_patch4_window7_224] INFO: Epoch: [105] [1220/1251] eta: 0:00:15 lr: 0.000725 loss: 3.6483 (3.4669) grad_norm: 1.1652 (nan) time: 0.5007 [2021-03-25 22:36:17 swin_small_patch4_window7_224] INFO: Epoch: [105] [1230/1251] eta: 0:00:10 lr: 0.000725 loss: 3.5629 (3.4687) grad_norm: 1.1688 (nan) time: 0.5036 [2021-03-25 22:36:22 swin_small_patch4_window7_224] INFO: Epoch: [105] [1240/1251] eta: 0:00:05 lr: 0.000725 loss: 3.5629 (3.4683) grad_norm: 1.1155 (nan) time: 0.5028 [2021-03-25 22:36:27 swin_small_patch4_window7_224] INFO: Epoch: [105] [1250/1251] eta: 0:00:00 lr: 0.000725 loss: 3.1779 (3.4667) grad_norm: 1.0987 (nan) time: 0.5001 [2021-03-25 22:37:12 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 1.0817 (1.0817) acc1: 76.5625 (76.5625) acc5: 85.9375 (85.9375) [2021-03-25 22:37:13 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.9473 (0.9825) acc1: 78.1250 (77.5568) acc5: 93.7500 (92.7557) [2021-03-25 22:37:14 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9783 (1.0153) acc1: 75.0000 (76.5625) acc5: 93.7500 (92.9315) [2021-03-25 22:37:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9783 (1.0019) acc1: 75.0000 (76.3609) acc5: 95.3125 (93.7500) [2021-03-25 22:37:16 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9983 (1.0240) acc1: 75.0000 (75.9146) acc5: 93.7500 (93.4070) [2021-03-25 22:37:17 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0248 (1.0129) acc1: 75.0000 (76.2880) acc5: 93.7500 (93.5360) [2021-03-25 22:37:25 swin_small_patch4_window7_224] INFO: * Acc@1 76.240 Acc@5 93.514 loss 1.010 [2021-03-25 22:37:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.2% [2021-03-25 22:37:25 swin_small_patch4_window7_224] INFO: Max accuracy: 76.32% [2021-03-25 22:37:29 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 0/1251] eta: 1:22:17 lr: 0.000725 loss: 3.3113 (3.3113) grad_norm: 1.1294 (1.1294) time: 3.9465 [2021-03-25 22:37:34 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 10/1251] eta: 0:17:21 lr: 0.000725 loss: 3.3494 (3.3539) grad_norm: 1.1294 (1.1220) time: 0.8395 [2021-03-25 22:37:39 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 20/1251] eta: 0:14:06 lr: 0.000725 loss: 3.3494 (3.3239) grad_norm: 1.1536 (1.1363) time: 0.5249 [2021-03-25 22:37:44 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 30/1251] eta: 0:12:45 lr: 0.000725 loss: 3.3451 (3.3140) grad_norm: 1.1685 (1.1603) time: 0.5096 [2021-03-25 22:37:50 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 40/1251] eta: 0:12:05 lr: 0.000725 loss: 3.5132 (3.3611) grad_norm: 1.1749 (1.1817) time: 0.5062 [2021-03-25 22:37:55 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 50/1251] eta: 0:11:39 lr: 0.000725 loss: 3.6878 (3.3761) grad_norm: 1.1905 (1.1973) time: 0.5141 [2021-03-25 22:38:00 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 60/1251] eta: 0:11:18 lr: 0.000725 loss: 3.6878 (3.4162) grad_norm: 1.1905 (1.1993) time: 0.5092 [2021-03-25 22:38:05 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 70/1251] eta: 0:11:03 lr: 0.000725 loss: 3.5290 (3.4141) grad_norm: 1.1727 (1.1925) time: 0.5089 [2021-03-25 22:38:10 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 80/1251] eta: 0:10:48 lr: 0.000725 loss: 3.1250 (3.3698) grad_norm: 1.1727 (1.1985) time: 0.5067 [2021-03-25 22:38:15 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 90/1251] eta: 0:10:36 lr: 0.000725 loss: 3.1070 (3.3796) grad_norm: 1.2065 (1.2022) time: 0.4987 [2021-03-25 22:38:20 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 100/1251] eta: 0:10:24 lr: 0.000725 loss: 3.4106 (3.3840) grad_norm: 1.2199 (1.2080) time: 0.4946 [2021-03-25 22:38:25 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 110/1251] eta: 0:10:14 lr: 0.000725 loss: 3.4106 (3.3728) grad_norm: 1.2008 (1.2079) time: 0.4974 [2021-03-25 22:38:30 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 120/1251] eta: 0:10:06 lr: 0.000725 loss: 3.5377 (3.3844) grad_norm: 1.1665 (1.2032) time: 0.5030 [2021-03-25 22:38:35 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 130/1251] eta: 0:09:57 lr: 0.000725 loss: 3.3503 (3.3780) grad_norm: 1.1665 (1.2012) time: 0.5012 [2021-03-25 22:38:40 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 140/1251] eta: 0:09:50 lr: 0.000725 loss: 3.1734 (3.3688) grad_norm: 1.1670 (1.1999) time: 0.5030 [2021-03-25 22:38:45 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 150/1251] eta: 0:09:42 lr: 0.000725 loss: 3.0592 (3.3416) grad_norm: 1.1344 (1.1966) time: 0.5027 [2021-03-25 22:38:50 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 160/1251] eta: 0:09:36 lr: 0.000725 loss: 3.4849 (3.3608) grad_norm: 1.1183 (1.1940) time: 0.5053 [2021-03-25 22:38:55 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 170/1251] eta: 0:09:29 lr: 0.000724 loss: 3.7288 (3.3713) grad_norm: 1.1595 (1.1979) time: 0.5076 [2021-03-25 22:39:00 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 180/1251] eta: 0:09:23 lr: 0.000724 loss: 3.5897 (3.3699) grad_norm: 1.2550 (1.2061) time: 0.5107 [2021-03-25 22:39:06 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 190/1251] eta: 0:09:18 lr: 0.000724 loss: 3.5681 (3.3889) grad_norm: 1.1777 (1.2056) time: 0.5250 [2021-03-25 22:39:11 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 200/1251] eta: 0:09:12 lr: 0.000724 loss: 3.5681 (3.3887) grad_norm: 1.1766 (1.2067) time: 0.5219 [2021-03-25 22:39:16 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 210/1251] eta: 0:09:06 lr: 0.000724 loss: 3.5659 (3.3982) grad_norm: 1.1958 (1.2088) time: 0.5152 [2021-03-25 22:39:21 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 220/1251] eta: 0:09:00 lr: 0.000724 loss: 3.5738 (3.4009) grad_norm: 1.1892 (1.2072) time: 0.5114 [2021-03-25 22:39:26 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 230/1251] eta: 0:08:54 lr: 0.000724 loss: 3.5738 (3.4092) grad_norm: 1.1780 (1.2092) time: 0.5085 [2021-03-25 22:39:31 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 240/1251] eta: 0:08:48 lr: 0.000724 loss: 3.6625 (3.4192) grad_norm: 1.1563 (1.2082) time: 0.5088 [2021-03-25 22:39:36 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 250/1251] eta: 0:08:42 lr: 0.000724 loss: 3.6625 (3.4290) grad_norm: 1.1480 (1.2064) time: 0.5033 [2021-03-25 22:39:41 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 260/1251] eta: 0:08:37 lr: 0.000724 loss: 3.6759 (3.4415) grad_norm: 1.1306 (1.2018) time: 0.5078 [2021-03-25 22:39:46 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 270/1251] eta: 0:08:31 lr: 0.000724 loss: 3.6759 (3.4430) grad_norm: 1.0813 (1.1978) time: 0.5103 [2021-03-25 22:39:51 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 280/1251] eta: 0:08:25 lr: 0.000724 loss: 3.7990 (3.4562) grad_norm: 1.1043 (1.1982) time: 0.5037 [2021-03-25 22:39:56 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 290/1251] eta: 0:08:19 lr: 0.000724 loss: 3.6237 (3.4554) grad_norm: 1.1849 (1.1981) time: 0.5015 [2021-03-25 22:40:01 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 300/1251] eta: 0:08:13 lr: 0.000724 loss: 3.5808 (3.4512) grad_norm: 1.1625 (1.1973) time: 0.4974 [2021-03-25 22:40:06 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 310/1251] eta: 0:08:08 lr: 0.000724 loss: 3.4526 (3.4544) grad_norm: 1.1505 (1.1980) time: 0.5044 [2021-03-25 22:40:11 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 320/1251] eta: 0:08:02 lr: 0.000724 loss: 3.5517 (3.4625) grad_norm: 1.1422 (1.1965) time: 0.5102 [2021-03-25 22:40:17 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 330/1251] eta: 0:07:57 lr: 0.000724 loss: 3.5281 (3.4588) grad_norm: 1.1365 (1.1945) time: 0.5069 [2021-03-25 22:40:22 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 340/1251] eta: 0:07:51 lr: 0.000724 loss: 3.5594 (3.4650) grad_norm: 1.1160 (1.1928) time: 0.5049 [2021-03-25 22:40:27 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 350/1251] eta: 0:07:46 lr: 0.000724 loss: 3.6368 (3.4639) grad_norm: 1.1064 (1.1923) time: 0.5019 [2021-03-25 22:40:32 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 360/1251] eta: 0:07:40 lr: 0.000724 loss: 3.6162 (3.4664) grad_norm: 1.1625 (1.1915) time: 0.5057 [2021-03-25 22:40:37 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 370/1251] eta: 0:07:35 lr: 0.000724 loss: 3.6596 (3.4684) grad_norm: 1.2008 (1.1917) time: 0.5070 [2021-03-25 22:40:42 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 380/1251] eta: 0:07:29 lr: 0.000724 loss: 3.6596 (3.4672) grad_norm: 1.1515 (1.1904) time: 0.5080 [2021-03-25 22:40:47 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 390/1251] eta: 0:07:24 lr: 0.000724 loss: 3.4329 (3.4653) grad_norm: 1.1551 (1.1905) time: 0.5117 [2021-03-25 22:40:52 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 400/1251] eta: 0:07:19 lr: 0.000724 loss: 3.5365 (3.4666) grad_norm: 1.1671 (1.1909) time: 0.5115 [2021-03-25 22:40:57 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 410/1251] eta: 0:07:14 lr: 0.000724 loss: 3.4407 (3.4615) grad_norm: 1.1061 (1.1899) time: 0.5096 [2021-03-25 22:41:02 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 420/1251] eta: 0:07:08 lr: 0.000724 loss: 3.5576 (3.4657) grad_norm: 1.0987 (1.1879) time: 0.5025 [2021-03-25 22:41:07 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 430/1251] eta: 0:07:03 lr: 0.000723 loss: 3.7410 (3.4681) grad_norm: 1.1356 (1.1900) time: 0.5006 [2021-03-25 22:41:12 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 440/1251] eta: 0:06:57 lr: 0.000723 loss: 3.5632 (3.4638) grad_norm: 1.2487 (1.1930) time: 0.5071 [2021-03-25 22:41:17 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 450/1251] eta: 0:06:52 lr: 0.000723 loss: 3.6185 (3.4706) grad_norm: 1.2460 (1.1924) time: 0.5057 [2021-03-25 22:41:22 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 460/1251] eta: 0:06:47 lr: 0.000723 loss: 3.8667 (3.4755) grad_norm: 1.1646 (1.1916) time: 0.4987 [2021-03-25 22:41:27 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 470/1251] eta: 0:06:41 lr: 0.000723 loss: 3.6939 (3.4694) grad_norm: 1.1640 (1.1918) time: 0.4993 [2021-03-25 22:41:32 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 480/1251] eta: 0:06:36 lr: 0.000723 loss: 3.3057 (3.4696) grad_norm: 1.1352 (1.1903) time: 0.5070 [2021-03-25 22:41:37 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 490/1251] eta: 0:06:31 lr: 0.000723 loss: 3.4223 (3.4693) grad_norm: 1.1210 (1.1915) time: 0.5091 [2021-03-25 22:41:43 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 500/1251] eta: 0:06:26 lr: 0.000723 loss: 3.7690 (3.4771) grad_norm: 1.2392 (1.1925) time: 0.5106 [2021-03-25 22:41:48 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 510/1251] eta: 0:06:20 lr: 0.000723 loss: 3.7874 (3.4816) grad_norm: 1.2029 (1.1921) time: 0.5106 [2021-03-25 22:41:53 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 520/1251] eta: 0:06:15 lr: 0.000723 loss: 3.6779 (3.4803) grad_norm: 1.2287 (1.1938) time: 0.5078 [2021-03-25 22:41:58 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 530/1251] eta: 0:06:10 lr: 0.000723 loss: 3.3032 (3.4818) grad_norm: 1.2330 (1.1953) time: 0.5072 [2021-03-25 22:42:03 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 540/1251] eta: 0:06:05 lr: 0.000723 loss: 3.4619 (3.4822) grad_norm: 1.1656 (1.1945) time: 0.5093 [2021-03-25 22:42:08 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 550/1251] eta: 0:06:00 lr: 0.000723 loss: 3.4323 (3.4761) grad_norm: 1.1310 (1.1930) time: 0.5181 [2021-03-25 22:42:13 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 560/1251] eta: 0:05:54 lr: 0.000723 loss: 3.4431 (3.4772) grad_norm: 1.1235 (1.1924) time: 0.5101 [2021-03-25 22:42:18 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 570/1251] eta: 0:05:49 lr: 0.000723 loss: 3.4234 (3.4707) grad_norm: 1.1383 (1.1926) time: 0.4984 [2021-03-25 22:42:23 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 580/1251] eta: 0:05:44 lr: 0.000723 loss: 3.3341 (3.4701) grad_norm: 1.1595 (1.1923) time: 0.5003 [2021-03-25 22:42:28 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 590/1251] eta: 0:05:39 lr: 0.000723 loss: 3.3973 (3.4698) grad_norm: 1.1520 (1.1915) time: 0.5000 [2021-03-25 22:42:33 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 600/1251] eta: 0:05:33 lr: 0.000723 loss: 3.5106 (3.4700) grad_norm: 1.1171 (1.1901) time: 0.5053 [2021-03-25 22:42:38 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 610/1251] eta: 0:05:28 lr: 0.000723 loss: 3.5982 (3.4708) grad_norm: 1.1394 (1.1901) time: 0.5048 [2021-03-25 22:42:43 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 620/1251] eta: 0:05:23 lr: 0.000723 loss: 3.6187 (3.4736) grad_norm: 1.1404 (1.1894) time: 0.5014 [2021-03-25 22:42:48 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 630/1251] eta: 0:05:18 lr: 0.000723 loss: 3.6187 (3.4750) grad_norm: 1.1323 (1.1884) time: 0.5059 [2021-03-25 22:42:53 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 640/1251] eta: 0:05:12 lr: 0.000723 loss: 3.5445 (3.4748) grad_norm: 1.1895 (1.1894) time: 0.5017 [2021-03-25 22:42:58 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 650/1251] eta: 0:05:07 lr: 0.000723 loss: 3.4705 (3.4756) grad_norm: 1.2674 (1.1911) time: 0.5043 [2021-03-25 22:43:04 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 660/1251] eta: 0:05:02 lr: 0.000723 loss: 3.4841 (3.4734) grad_norm: 1.2538 (1.1910) time: 0.5100 [2021-03-25 22:43:09 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 670/1251] eta: 0:04:57 lr: 0.000723 loss: 3.5174 (3.4731) grad_norm: 1.1408 (1.1903) time: 0.5087 [2021-03-25 22:43:14 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 680/1251] eta: 0:04:52 lr: 0.000723 loss: 3.5629 (3.4766) grad_norm: 1.1490 (1.1900) time: 0.5069 [2021-03-25 22:43:19 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 690/1251] eta: 0:04:47 lr: 0.000723 loss: 3.7285 (3.4778) grad_norm: 1.1690 (1.1900) time: 0.5043 [2021-03-25 22:43:24 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 700/1251] eta: 0:04:41 lr: 0.000722 loss: 3.3250 (3.4745) grad_norm: 1.2049 (1.1901) time: 0.5029 [2021-03-25 22:43:29 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 710/1251] eta: 0:04:36 lr: 0.000722 loss: 3.2485 (3.4720) grad_norm: 1.1495 (1.1891) time: 0.4988 [2021-03-25 22:43:34 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 720/1251] eta: 0:04:31 lr: 0.000722 loss: 3.4309 (3.4700) grad_norm: 1.0864 (1.1888) time: 0.5041 [2021-03-25 22:43:39 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 730/1251] eta: 0:04:26 lr: 0.000722 loss: 3.5155 (3.4715) grad_norm: 1.1639 (1.1892) time: 0.5127 [2021-03-25 22:43:45 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 740/1251] eta: 0:04:21 lr: 0.000722 loss: 3.8247 (3.4751) grad_norm: 1.1789 (1.1893) time: 0.5389 [2021-03-25 22:43:50 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 750/1251] eta: 0:04:16 lr: 0.000722 loss: 3.7536 (3.4786) grad_norm: 1.1370 (1.1881) time: 0.5312 [2021-03-25 22:43:55 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 760/1251] eta: 0:04:11 lr: 0.000722 loss: 3.6004 (3.4790) grad_norm: 1.0895 (1.1872) time: 0.5067 [2021-03-25 22:44:00 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 770/1251] eta: 0:04:06 lr: 0.000722 loss: 3.5315 (3.4776) grad_norm: 1.1367 (1.1875) time: 0.5090 [2021-03-25 22:44:05 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 780/1251] eta: 0:04:01 lr: 0.000722 loss: 3.5382 (3.4784) grad_norm: 1.1725 (1.1874) time: 0.5076 [2021-03-25 22:44:10 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 790/1251] eta: 0:03:55 lr: 0.000722 loss: 3.5464 (3.4774) grad_norm: 1.2029 (1.1883) time: 0.5061 [2021-03-25 22:44:15 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 800/1251] eta: 0:03:50 lr: 0.000722 loss: 3.3371 (3.4773) grad_norm: 1.2029 (1.1883) time: 0.5041 [2021-03-25 22:44:20 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 810/1251] eta: 0:03:45 lr: 0.000722 loss: 3.5466 (3.4788) grad_norm: 1.1564 (1.1883) time: 0.5067 [2021-03-25 22:44:25 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 820/1251] eta: 0:03:40 lr: 0.000722 loss: 3.5313 (3.4791) grad_norm: 1.1701 (1.1880) time: 0.5006 [2021-03-25 22:44:30 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 830/1251] eta: 0:03:35 lr: 0.000722 loss: 3.5313 (3.4824) grad_norm: 1.1850 (1.1884) time: 0.5021 [2021-03-25 22:44:35 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 840/1251] eta: 0:03:30 lr: 0.000722 loss: 3.7140 (3.4825) grad_norm: 1.2016 (1.1887) time: 0.5091 [2021-03-25 22:44:40 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 850/1251] eta: 0:03:25 lr: 0.000722 loss: 3.4013 (3.4811) grad_norm: 1.1762 (1.1889) time: 0.5063 [2021-03-25 22:44:45 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 860/1251] eta: 0:03:19 lr: 0.000722 loss: 3.4064 (3.4802) grad_norm: 1.1695 (1.1894) time: 0.5051 [2021-03-25 22:44:50 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 870/1251] eta: 0:03:14 lr: 0.000722 loss: 3.6242 (3.4816) grad_norm: 1.1695 (1.1894) time: 0.5066 [2021-03-25 22:44:56 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 880/1251] eta: 0:03:09 lr: 0.000722 loss: 3.5774 (3.4828) grad_norm: 1.1789 (1.1903) time: 0.5141 [2021-03-25 22:45:01 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 890/1251] eta: 0:03:04 lr: 0.000722 loss: 3.6795 (3.4841) grad_norm: 1.1646 (1.1901) time: 0.5096 [2021-03-25 22:45:06 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 900/1251] eta: 0:02:59 lr: 0.000722 loss: 3.6392 (3.4830) grad_norm: 1.1250 (1.1888) time: 0.5009 [2021-03-25 22:45:11 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 910/1251] eta: 0:02:54 lr: 0.000722 loss: 3.6795 (3.4865) grad_norm: 1.0811 (1.1881) time: 0.5052 [2021-03-25 22:45:16 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 920/1251] eta: 0:02:49 lr: 0.000722 loss: 3.7131 (3.4820) grad_norm: 1.0663 (1.1871) time: 0.5085 [2021-03-25 22:45:21 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 930/1251] eta: 0:02:44 lr: 0.000722 loss: 3.1367 (3.4815) grad_norm: 1.0976 (1.1864) time: 0.5066 [2021-03-25 22:45:26 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 940/1251] eta: 0:02:38 lr: 0.000722 loss: 3.5352 (3.4815) grad_norm: 1.1099 (1.1864) time: 0.5126 [2021-03-25 22:45:31 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 950/1251] eta: 0:02:33 lr: 0.000722 loss: 3.2697 (3.4784) grad_norm: 1.2284 (1.1874) time: 0.5170 [2021-03-25 22:45:36 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 960/1251] eta: 0:02:28 lr: 0.000722 loss: 3.4221 (3.4785) grad_norm: 1.2601 (1.1885) time: 0.5095 [2021-03-25 22:45:41 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 970/1251] eta: 0:02:23 lr: 0.000721 loss: 3.5099 (3.4778) grad_norm: 1.1890 (1.1884) time: 0.5065 [2021-03-25 22:45:46 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 980/1251] eta: 0:02:18 lr: 0.000721 loss: 3.5099 (3.4794) grad_norm: 1.1898 (1.1894) time: 0.5017 [2021-03-25 22:45:51 swin_small_patch4_window7_224] INFO: Epoch: [106] [ 990/1251] eta: 0:02:13 lr: 0.000721 loss: 3.8072 (3.4811) grad_norm: 1.2257 (1.1896) time: 0.4996 [2021-03-25 22:45:56 swin_small_patch4_window7_224] INFO: Epoch: [106] [1000/1251] eta: 0:02:08 lr: 0.000721 loss: 3.8454 (3.4830) grad_norm: 1.2192 (1.1907) time: 0.5082 [2021-03-25 22:46:01 swin_small_patch4_window7_224] INFO: Epoch: [106] [1010/1251] eta: 0:02:03 lr: 0.000721 loss: 3.5943 (3.4819) grad_norm: 1.2074 (1.1912) time: 0.5074 [2021-03-25 22:46:06 swin_small_patch4_window7_224] INFO: Epoch: [106] [1020/1251] eta: 0:01:57 lr: 0.000721 loss: 3.4775 (3.4822) grad_norm: 1.1607 (1.1906) time: 0.5028 [2021-03-25 22:46:11 swin_small_patch4_window7_224] INFO: Epoch: [106] [1030/1251] eta: 0:01:52 lr: 0.000721 loss: 3.5336 (3.4834) grad_norm: 1.1348 (1.1903) time: 0.5019 [2021-03-25 22:46:16 swin_small_patch4_window7_224] INFO: Epoch: [106] [1040/1251] eta: 0:01:47 lr: 0.000721 loss: 3.7091 (3.4837) grad_norm: 1.1119 (1.1898) time: 0.4984 [2021-03-25 22:46:22 swin_small_patch4_window7_224] INFO: Epoch: [106] [1050/1251] eta: 0:01:42 lr: 0.000721 loss: 3.5626 (3.4821) grad_norm: 1.0978 (1.1890) time: 0.5020 [2021-03-25 22:46:27 swin_small_patch4_window7_224] INFO: Epoch: [106] [1060/1251] eta: 0:01:37 lr: 0.000721 loss: 3.5626 (3.4827) grad_norm: 1.1055 (1.1885) time: 0.5067 [2021-03-25 22:46:32 swin_small_patch4_window7_224] INFO: Epoch: [106] [1070/1251] eta: 0:01:32 lr: 0.000721 loss: 3.4972 (3.4834) grad_norm: 1.1872 (1.1896) time: 0.5109 [2021-03-25 22:46:37 swin_small_patch4_window7_224] INFO: Epoch: [106] [1080/1251] eta: 0:01:27 lr: 0.000721 loss: 3.5702 (3.4840) grad_norm: 1.2332 (1.1902) time: 0.5064 [2021-03-25 22:46:42 swin_small_patch4_window7_224] INFO: Epoch: [106] [1090/1251] eta: 0:01:22 lr: 0.000721 loss: 3.4813 (3.4836) grad_norm: 1.1718 (1.1901) time: 0.5046 [2021-03-25 22:46:47 swin_small_patch4_window7_224] INFO: Epoch: [106] [1100/1251] eta: 0:01:17 lr: 0.000721 loss: 3.4813 (3.4836) grad_norm: 1.1716 (1.1901) time: 0.5116 [2021-03-25 22:46:52 swin_small_patch4_window7_224] INFO: Epoch: [106] [1110/1251] eta: 0:01:11 lr: 0.000721 loss: 3.6844 (3.4838) grad_norm: 1.1285 (1.1895) time: 0.5065 [2021-03-25 22:46:57 swin_small_patch4_window7_224] INFO: Epoch: [106] [1120/1251] eta: 0:01:06 lr: 0.000721 loss: 3.2550 (3.4811) grad_norm: 1.1285 (1.1893) time: 0.5050 [2021-03-25 22:47:02 swin_small_patch4_window7_224] INFO: Epoch: [106] [1130/1251] eta: 0:01:01 lr: 0.000721 loss: 3.2655 (3.4823) grad_norm: 1.1440 (1.1888) time: 0.5113 [2021-03-25 22:47:07 swin_small_patch4_window7_224] INFO: Epoch: [106] [1140/1251] eta: 0:00:56 lr: 0.000721 loss: 3.5566 (3.4804) grad_norm: 1.1231 (1.1889) time: 0.5080 [2021-03-25 22:47:12 swin_small_patch4_window7_224] INFO: Epoch: [106] [1150/1251] eta: 0:00:51 lr: 0.000721 loss: 3.5159 (3.4794) grad_norm: 1.1763 (1.1890) time: 0.5003 [2021-03-25 22:47:17 swin_small_patch4_window7_224] INFO: Epoch: [106] [1160/1251] eta: 0:00:46 lr: 0.000721 loss: 3.4197 (3.4793) grad_norm: 1.1816 (1.1890) time: 0.5045 [2021-03-25 22:47:22 swin_small_patch4_window7_224] INFO: Epoch: [106] [1170/1251] eta: 0:00:41 lr: 0.000721 loss: 3.4112 (3.4784) grad_norm: 1.1558 (1.1887) time: 0.5108 [2021-03-25 22:47:27 swin_small_patch4_window7_224] INFO: Epoch: [106] [1180/1251] eta: 0:00:36 lr: 0.000721 loss: 3.4455 (3.4776) grad_norm: 1.1533 (1.1889) time: 0.5033 [2021-03-25 22:47:32 swin_small_patch4_window7_224] INFO: Epoch: [106] [1190/1251] eta: 0:00:31 lr: 0.000721 loss: 3.5325 (3.4769) grad_norm: 1.1591 (1.1894) time: 0.4961 [2021-03-25 22:47:37 swin_small_patch4_window7_224] INFO: Epoch: [106] [1200/1251] eta: 0:00:25 lr: 0.000721 loss: 3.4441 (3.4750) grad_norm: 1.2458 (1.1910) time: 0.5006 [2021-03-25 22:47:42 swin_small_patch4_window7_224] INFO: Epoch: [106] [1210/1251] eta: 0:00:20 lr: 0.000721 loss: 3.3506 (3.4755) grad_norm: 1.2139 (1.1907) time: 0.5074 [2021-03-25 22:47:48 swin_small_patch4_window7_224] INFO: Epoch: [106] [1220/1251] eta: 0:00:15 lr: 0.000721 loss: 3.5829 (3.4774) grad_norm: 1.1726 (1.1911) time: 0.5071 [2021-03-25 22:47:53 swin_small_patch4_window7_224] INFO: Epoch: [106] [1230/1251] eta: 0:00:10 lr: 0.000721 loss: 3.5575 (3.4771) grad_norm: 1.1726 (1.1908) time: 0.5036 [2021-03-25 22:47:58 swin_small_patch4_window7_224] INFO: Epoch: [106] [1240/1251] eta: 0:00:05 lr: 0.000720 loss: 3.4596 (3.4759) grad_norm: 1.1648 (1.1909) time: 0.5044 [2021-03-25 22:48:03 swin_small_patch4_window7_224] INFO: Epoch: [106] [1250/1251] eta: 0:00:00 lr: 0.000720 loss: 3.4596 (3.4754) grad_norm: 1.1732 (1.1909) time: 0.5095 [2021-03-25 22:48:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:33 loss: 0.8374 (0.8374) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-25 22:48:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 1.0754 (1.1268) acc1: 75.0000 (74.5739) acc5: 93.7500 (93.1818) [2021-03-25 22:48:14 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.0754 (1.1173) acc1: 76.5625 (75.8929) acc5: 92.1875 (92.5595) [2021-03-25 22:48:17 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0358 (1.0884) acc1: 78.1250 (76.2097) acc5: 92.1875 (93.2964) [2021-03-25 22:48:18 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0134 (1.0748) acc1: 75.0000 (76.2195) acc5: 93.7500 (93.5595) [2021-03-25 22:48:19 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0230 (1.0653) acc1: 75.0000 (76.2560) acc5: 93.7500 (93.6640) [2021-03-25 22:48:23 swin_small_patch4_window7_224] INFO: * Acc@1 76.448 Acc@5 93.346 loss 1.052 [2021-03-25 22:48:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.4% [2021-03-25 22:48:23 swin_small_patch4_window7_224] INFO: Max accuracy: 76.45% [2021-03-25 22:48:28 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 0/1251] eta: 1:27:42 lr: 0.000720 loss: 2.4766 (2.4766) grad_norm: 1.0240 (1.0240) time: 4.2068 [2021-03-25 22:48:33 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 10/1251] eta: 0:17:26 lr: 0.000720 loss: 3.2434 (3.2812) grad_norm: 1.1451 (1.1702) time: 0.8430 [2021-03-25 22:48:38 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 20/1251] eta: 0:14:01 lr: 0.000720 loss: 3.2976 (3.2757) grad_norm: 1.1869 (1.1826) time: 0.5073 [2021-03-25 22:48:43 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 30/1251] eta: 0:12:46 lr: 0.000720 loss: 3.2976 (3.3014) grad_norm: 1.1882 (1.1902) time: 0.5090 [2021-03-25 22:48:48 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 40/1251] eta: 0:12:04 lr: 0.000720 loss: 3.4924 (3.3500) grad_norm: 1.1480 (1.2026) time: 0.5085 [2021-03-25 22:48:53 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 50/1251] eta: 0:11:36 lr: 0.000720 loss: 3.5758 (3.3692) grad_norm: 1.1364 (1.1923) time: 0.5059 [2021-03-25 22:48:58 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 60/1251] eta: 0:11:16 lr: 0.000720 loss: 3.5129 (3.3707) grad_norm: 1.1849 (1.1999) time: 0.5059 [2021-03-25 22:49:03 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 70/1251] eta: 0:11:00 lr: 0.000720 loss: 3.4637 (3.3756) grad_norm: 1.2609 (1.2132) time: 0.5065 [2021-03-25 22:49:08 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 80/1251] eta: 0:10:46 lr: 0.000720 loss: 3.5212 (3.4022) grad_norm: 1.2253 (1.2127) time: 0.5033 [2021-03-25 22:49:13 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 90/1251] eta: 0:10:36 lr: 0.000720 loss: 3.4253 (3.3775) grad_norm: 1.1499 (1.2091) time: 0.5078 [2021-03-25 22:49:18 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 100/1251] eta: 0:10:25 lr: 0.000720 loss: 3.4511 (3.3994) grad_norm: 1.1247 (1.2031) time: 0.5075 [2021-03-25 22:49:23 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 110/1251] eta: 0:10:16 lr: 0.000720 loss: 3.5486 (3.3940) grad_norm: 1.1045 (1.1961) time: 0.5040 [2021-03-25 22:49:28 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 120/1251] eta: 0:10:07 lr: 0.000720 loss: 3.2521 (3.4022) grad_norm: 1.1660 (1.1974) time: 0.5055 [2021-03-25 22:49:33 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 130/1251] eta: 0:09:58 lr: 0.000720 loss: 3.3434 (3.4032) grad_norm: 1.1113 (1.1895) time: 0.5019 [2021-03-25 22:49:38 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 140/1251] eta: 0:09:51 lr: 0.000720 loss: 3.3442 (3.4021) grad_norm: 1.1113 (1.1919) time: 0.5078 [2021-03-25 22:49:43 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 150/1251] eta: 0:09:43 lr: 0.000720 loss: 3.4354 (3.4108) grad_norm: 1.1762 (1.1899) time: 0.5054 [2021-03-25 22:49:49 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 160/1251] eta: 0:09:36 lr: 0.000720 loss: 3.4842 (3.4138) grad_norm: 1.1557 (1.1943) time: 0.5009 [2021-03-25 22:49:54 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 170/1251] eta: 0:09:30 lr: 0.000720 loss: 3.4924 (3.4219) grad_norm: 1.1997 (1.1950) time: 0.5051 [2021-03-25 22:49:59 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 180/1251] eta: 0:09:23 lr: 0.000720 loss: 3.7720 (3.4409) grad_norm: 1.1891 (1.1938) time: 0.5067 [2021-03-25 22:50:04 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 190/1251] eta: 0:09:17 lr: 0.000720 loss: 3.8254 (3.4269) grad_norm: 1.1790 (1.1943) time: 0.5111 [2021-03-25 22:50:09 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 200/1251] eta: 0:09:12 lr: 0.000720 loss: 3.3006 (3.4179) grad_norm: 1.1862 (1.1958) time: 0.5183 [2021-03-25 22:50:14 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 210/1251] eta: 0:09:05 lr: 0.000720 loss: 3.5103 (3.4253) grad_norm: 1.1569 (1.1927) time: 0.5114 [2021-03-25 22:50:19 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 220/1251] eta: 0:08:59 lr: 0.000720 loss: 3.5283 (3.4187) grad_norm: 1.1485 (1.1938) time: 0.5021 [2021-03-25 22:50:24 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 230/1251] eta: 0:08:53 lr: 0.000720 loss: 3.2760 (3.4075) grad_norm: 1.1592 (1.1931) time: 0.5068 [2021-03-25 22:50:29 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 240/1251] eta: 0:08:47 lr: 0.000720 loss: 3.3790 (3.4158) grad_norm: 1.1319 (1.1917) time: 0.5013 [2021-03-25 22:50:34 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 250/1251] eta: 0:08:41 lr: 0.000720 loss: 3.5636 (3.4199) grad_norm: 1.1492 (1.1923) time: 0.4988 [2021-03-25 22:50:39 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 260/1251] eta: 0:08:35 lr: 0.000719 loss: 3.5636 (3.4190) grad_norm: 1.2448 (1.1953) time: 0.5075 [2021-03-25 22:50:44 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 270/1251] eta: 0:08:29 lr: 0.000719 loss: 3.4647 (3.4209) grad_norm: 1.2551 (1.1968) time: 0.5067 [2021-03-25 22:50:49 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 280/1251] eta: 0:08:24 lr: 0.000719 loss: 3.5644 (3.4179) grad_norm: 1.1644 (1.1954) time: 0.5020 [2021-03-25 22:50:54 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 290/1251] eta: 0:08:18 lr: 0.000719 loss: 3.7091 (3.4336) grad_norm: 1.1644 (1.1961) time: 0.5023 [2021-03-25 22:50:59 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 300/1251] eta: 0:08:12 lr: 0.000719 loss: 3.7153 (3.4351) grad_norm: 1.1186 (1.1929) time: 0.5042 [2021-03-25 22:51:04 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 310/1251] eta: 0:08:06 lr: 0.000719 loss: 3.5996 (3.4415) grad_norm: 1.1186 (1.1924) time: 0.5007 [2021-03-25 22:51:09 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 320/1251] eta: 0:08:01 lr: 0.000719 loss: 3.4839 (3.4391) grad_norm: 1.1466 (1.1923) time: 0.5019 [2021-03-25 22:51:14 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 330/1251] eta: 0:07:56 lr: 0.000719 loss: 3.5906 (3.4489) grad_norm: 1.1941 (1.1925) time: 0.5071 [2021-03-25 22:51:19 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 340/1251] eta: 0:07:50 lr: 0.000719 loss: 3.7396 (3.4506) grad_norm: 1.1833 (1.1935) time: 0.5035 [2021-03-25 22:51:25 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 350/1251] eta: 0:07:44 lr: 0.000719 loss: 3.5220 (3.4497) grad_norm: 1.2073 (1.1951) time: 0.5028 [2021-03-25 22:51:30 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 360/1251] eta: 0:07:39 lr: 0.000719 loss: 3.4588 (3.4474) grad_norm: 1.2193 (1.1961) time: 0.5025 [2021-03-25 22:51:35 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 370/1251] eta: 0:07:34 lr: 0.000719 loss: 3.4571 (3.4482) grad_norm: 1.2072 (1.1973) time: 0.5027 [2021-03-25 22:51:40 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 380/1251] eta: 0:07:28 lr: 0.000719 loss: 3.5361 (3.4521) grad_norm: 1.2072 (1.1977) time: 0.5055 [2021-03-25 22:51:45 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 390/1251] eta: 0:07:23 lr: 0.000719 loss: 3.5571 (3.4502) grad_norm: 1.2266 (1.1997) time: 0.5081 [2021-03-25 22:51:50 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 400/1251] eta: 0:07:18 lr: 0.000719 loss: 3.5066 (3.4520) grad_norm: 1.2511 (1.2007) time: 0.5093 [2021-03-25 22:51:55 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 410/1251] eta: 0:07:12 lr: 0.000719 loss: 3.5075 (3.4518) grad_norm: 1.2390 (1.2017) time: 0.5038 [2021-03-25 22:52:00 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 420/1251] eta: 0:07:07 lr: 0.000719 loss: 3.6125 (3.4591) grad_norm: 1.2390 (1.2025) time: 0.5036 [2021-03-25 22:52:05 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 430/1251] eta: 0:07:02 lr: 0.000719 loss: 3.6125 (3.4576) grad_norm: 1.1925 (1.2026) time: 0.5075 [2021-03-25 22:52:10 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 440/1251] eta: 0:06:56 lr: 0.000719 loss: 3.4872 (3.4605) grad_norm: 1.1094 (1.2000) time: 0.5033 [2021-03-25 22:52:15 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 450/1251] eta: 0:06:51 lr: 0.000719 loss: 3.5133 (3.4580) grad_norm: 1.1064 (1.1986) time: 0.5067 [2021-03-25 22:52:20 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 460/1251] eta: 0:06:46 lr: 0.000719 loss: 3.3895 (3.4569) grad_norm: 1.1076 (1.1963) time: 0.5078 [2021-03-25 22:52:25 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 470/1251] eta: 0:06:40 lr: 0.000719 loss: 3.3895 (3.4540) grad_norm: 1.1076 (1.1952) time: 0.4995 [2021-03-25 22:52:30 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 480/1251] eta: 0:06:35 lr: 0.000719 loss: 3.5044 (3.4579) grad_norm: 1.1443 (1.1940) time: 0.5038 [2021-03-25 22:52:35 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 490/1251] eta: 0:06:30 lr: 0.000719 loss: 3.5044 (3.4566) grad_norm: 1.1417 (1.1932) time: 0.5098 [2021-03-25 22:52:40 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 500/1251] eta: 0:06:25 lr: 0.000719 loss: 3.5233 (3.4580) grad_norm: 1.1613 (1.1941) time: 0.5069 [2021-03-25 22:52:45 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 510/1251] eta: 0:06:19 lr: 0.000719 loss: 3.6513 (3.4609) grad_norm: 1.1413 (1.1930) time: 0.5065 [2021-03-25 22:52:51 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 520/1251] eta: 0:06:14 lr: 0.000718 loss: 3.6033 (3.4598) grad_norm: 1.1320 (1.1937) time: 0.5083 [2021-03-25 22:52:56 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 530/1251] eta: 0:06:09 lr: 0.000718 loss: 3.2075 (3.4566) grad_norm: 1.1393 (1.1928) time: 0.5143 [2021-03-25 22:53:01 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 540/1251] eta: 0:06:04 lr: 0.000718 loss: 3.5078 (3.4589) grad_norm: 1.1621 (nan) time: 0.5148 [2021-03-25 22:53:06 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 550/1251] eta: 0:05:59 lr: 0.000718 loss: 3.6592 (3.4593) grad_norm: 1.2185 (nan) time: 0.5126 [2021-03-25 22:53:11 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 560/1251] eta: 0:05:54 lr: 0.000718 loss: 3.5708 (3.4611) grad_norm: 1.1803 (nan) time: 0.5148 [2021-03-25 22:53:16 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 570/1251] eta: 0:05:49 lr: 0.000718 loss: 3.6375 (3.4658) grad_norm: 1.1648 (nan) time: 0.5096 [2021-03-25 22:53:21 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 580/1251] eta: 0:05:43 lr: 0.000718 loss: 3.6529 (3.4660) grad_norm: 1.1586 (nan) time: 0.5055 [2021-03-25 22:53:26 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 590/1251] eta: 0:05:38 lr: 0.000718 loss: 3.5032 (3.4651) grad_norm: 1.1446 (nan) time: 0.5110 [2021-03-25 22:53:32 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 600/1251] eta: 0:05:33 lr: 0.000718 loss: 3.3575 (3.4595) grad_norm: 1.2351 (nan) time: 0.5131 [2021-03-25 22:53:37 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 610/1251] eta: 0:05:28 lr: 0.000718 loss: 3.2315 (3.4571) grad_norm: 1.2901 (nan) time: 0.5068 [2021-03-25 22:53:42 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 620/1251] eta: 0:05:23 lr: 0.000718 loss: 3.2430 (3.4556) grad_norm: 1.2025 (nan) time: 0.5057 [2021-03-25 22:53:47 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 630/1251] eta: 0:05:18 lr: 0.000718 loss: 3.5869 (3.4573) grad_norm: 1.2025 (nan) time: 0.5067 [2021-03-25 22:53:52 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 640/1251] eta: 0:05:13 lr: 0.000718 loss: 3.6219 (3.4597) grad_norm: 1.1654 (nan) time: 0.5095 [2021-03-25 22:53:57 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 650/1251] eta: 0:05:07 lr: 0.000718 loss: 3.7241 (3.4650) grad_norm: 1.1484 (nan) time: 0.5074 [2021-03-25 22:54:02 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 660/1251] eta: 0:05:02 lr: 0.000718 loss: 3.5612 (3.4638) grad_norm: 1.1596 (nan) time: 0.5083 [2021-03-25 22:54:07 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 670/1251] eta: 0:04:57 lr: 0.000718 loss: 3.5198 (3.4645) grad_norm: 1.1825 (nan) time: 0.5128 [2021-03-25 22:54:12 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 680/1251] eta: 0:04:52 lr: 0.000718 loss: 3.5509 (3.4645) grad_norm: 1.1825 (nan) time: 0.5079 [2021-03-25 22:54:17 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 690/1251] eta: 0:04:47 lr: 0.000718 loss: 3.4118 (3.4612) grad_norm: 1.2087 (nan) time: 0.5069 [2021-03-25 22:54:22 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 700/1251] eta: 0:04:42 lr: 0.000718 loss: 3.4118 (3.4642) grad_norm: 1.2112 (nan) time: 0.5058 [2021-03-25 22:54:27 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 710/1251] eta: 0:04:36 lr: 0.000718 loss: 3.5515 (3.4634) grad_norm: 1.1074 (nan) time: 0.5023 [2021-03-25 22:54:32 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 720/1251] eta: 0:04:31 lr: 0.000718 loss: 3.4003 (3.4610) grad_norm: 1.1074 (nan) time: 0.5038 [2021-03-25 22:54:38 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 730/1251] eta: 0:04:26 lr: 0.000718 loss: 3.3812 (3.4600) grad_norm: 1.1358 (nan) time: 0.5099 [2021-03-25 22:54:43 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 740/1251] eta: 0:04:21 lr: 0.000718 loss: 3.4871 (3.4592) grad_norm: 1.1385 (nan) time: 0.5262 [2021-03-25 22:54:48 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 750/1251] eta: 0:04:16 lr: 0.000718 loss: 3.3547 (3.4558) grad_norm: 1.1835 (nan) time: 0.5265 [2021-03-25 22:54:53 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 760/1251] eta: 0:04:11 lr: 0.000718 loss: 3.3569 (3.4566) grad_norm: 1.1464 (nan) time: 0.5075 [2021-03-25 22:54:58 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 770/1251] eta: 0:04:06 lr: 0.000718 loss: 3.4199 (3.4565) grad_norm: 1.1029 (nan) time: 0.5017 [2021-03-25 22:55:03 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 780/1251] eta: 0:04:00 lr: 0.000718 loss: 3.4855 (3.4560) grad_norm: 1.0915 (nan) time: 0.5008 [2021-03-25 22:55:08 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 790/1251] eta: 0:03:55 lr: 0.000717 loss: 3.6316 (3.4599) grad_norm: 1.1262 (nan) time: 0.5099 [2021-03-25 22:55:13 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 800/1251] eta: 0:03:50 lr: 0.000717 loss: 3.7266 (3.4608) grad_norm: 1.1501 (nan) time: 0.5158 [2021-03-25 22:55:18 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 810/1251] eta: 0:03:45 lr: 0.000717 loss: 3.5484 (3.4594) grad_norm: 1.1314 (nan) time: 0.5099 [2021-03-25 22:55:24 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 820/1251] eta: 0:03:40 lr: 0.000717 loss: 3.6938 (3.4633) grad_norm: 1.1397 (nan) time: 0.5082 [2021-03-25 22:55:29 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 830/1251] eta: 0:03:35 lr: 0.000717 loss: 3.7833 (3.4636) grad_norm: 1.1727 (nan) time: 0.5059 [2021-03-25 22:55:34 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 840/1251] eta: 0:03:30 lr: 0.000717 loss: 3.7420 (3.4633) grad_norm: 1.1734 (nan) time: 0.5079 [2021-03-25 22:55:39 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 850/1251] eta: 0:03:25 lr: 0.000717 loss: 3.5214 (3.4633) grad_norm: 1.1734 (nan) time: 0.5065 [2021-03-25 22:55:44 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 860/1251] eta: 0:03:19 lr: 0.000717 loss: 3.6679 (3.4641) grad_norm: 1.1430 (nan) time: 0.5081 [2021-03-25 22:55:49 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 870/1251] eta: 0:03:14 lr: 0.000717 loss: 3.7296 (3.4653) grad_norm: 1.1412 (nan) time: 0.5079 [2021-03-25 22:55:54 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 880/1251] eta: 0:03:09 lr: 0.000717 loss: 3.7224 (3.4653) grad_norm: 1.1961 (nan) time: 0.5057 [2021-03-25 22:55:59 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 890/1251] eta: 0:03:04 lr: 0.000717 loss: 3.7224 (3.4670) grad_norm: 1.2087 (nan) time: 0.5080 [2021-03-25 22:56:04 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 900/1251] eta: 0:02:59 lr: 0.000717 loss: 3.2903 (3.4628) grad_norm: 1.1561 (nan) time: 0.5043 [2021-03-25 22:56:09 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 910/1251] eta: 0:02:54 lr: 0.000717 loss: 3.3318 (3.4645) grad_norm: 1.1565 (nan) time: 0.5016 [2021-03-25 22:56:14 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 920/1251] eta: 0:02:49 lr: 0.000717 loss: 3.6659 (3.4664) grad_norm: 1.2189 (nan) time: 0.5077 [2021-03-25 22:56:19 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 930/1251] eta: 0:02:44 lr: 0.000717 loss: 3.6659 (3.4676) grad_norm: 1.1941 (nan) time: 0.5065 [2021-03-25 22:56:24 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 940/1251] eta: 0:02:38 lr: 0.000717 loss: 3.5855 (3.4688) grad_norm: 1.1877 (nan) time: 0.5116 [2021-03-25 22:56:30 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 950/1251] eta: 0:02:33 lr: 0.000717 loss: 3.5855 (3.4689) grad_norm: 1.1877 (nan) time: 0.5145 [2021-03-25 22:56:35 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 960/1251] eta: 0:02:28 lr: 0.000717 loss: 3.7043 (3.4708) grad_norm: 1.1662 (nan) time: 0.5046 [2021-03-25 22:56:40 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 970/1251] eta: 0:02:23 lr: 0.000717 loss: 3.7083 (3.4724) grad_norm: 1.1323 (nan) time: 0.5014 [2021-03-25 22:56:45 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 980/1251] eta: 0:02:18 lr: 0.000717 loss: 3.6707 (3.4734) grad_norm: 1.1598 (nan) time: 0.5034 [2021-03-25 22:56:50 swin_small_patch4_window7_224] INFO: Epoch: [107] [ 990/1251] eta: 0:02:13 lr: 0.000717 loss: 3.5602 (3.4709) grad_norm: 1.1598 (nan) time: 0.5089 [2021-03-25 22:56:55 swin_small_patch4_window7_224] INFO: Epoch: [107] [1000/1251] eta: 0:02:08 lr: 0.000717 loss: 3.4829 (3.4699) grad_norm: 1.1646 (nan) time: 0.5102 [2021-03-25 22:57:00 swin_small_patch4_window7_224] INFO: Epoch: [107] [1010/1251] eta: 0:02:03 lr: 0.000717 loss: 3.6085 (3.4713) grad_norm: 1.2224 (nan) time: 0.5051 [2021-03-25 22:57:05 swin_small_patch4_window7_224] INFO: Epoch: [107] [1020/1251] eta: 0:01:57 lr: 0.000717 loss: 3.6966 (3.4731) grad_norm: 1.1959 (nan) time: 0.5009 [2021-03-25 22:57:10 swin_small_patch4_window7_224] INFO: Epoch: [107] [1030/1251] eta: 0:01:52 lr: 0.000717 loss: 3.6740 (3.4738) grad_norm: 1.1805 (nan) time: 0.5046 [2021-03-25 22:57:15 swin_small_patch4_window7_224] INFO: Epoch: [107] [1040/1251] eta: 0:01:47 lr: 0.000717 loss: 3.5459 (3.4737) grad_norm: 1.1821 (nan) time: 0.5066 [2021-03-25 22:57:20 swin_small_patch4_window7_224] INFO: Epoch: [107] [1050/1251] eta: 0:01:42 lr: 0.000717 loss: 3.5281 (3.4730) grad_norm: 1.1917 (nan) time: 0.5039 [2021-03-25 22:57:25 swin_small_patch4_window7_224] INFO: Epoch: [107] [1060/1251] eta: 0:01:37 lr: 0.000716 loss: 3.3066 (3.4738) grad_norm: 1.1917 (nan) time: 0.5010 [2021-03-25 22:57:30 swin_small_patch4_window7_224] INFO: Epoch: [107] [1070/1251] eta: 0:01:32 lr: 0.000716 loss: 3.5696 (3.4748) grad_norm: 1.1585 (nan) time: 0.5050 [2021-03-25 22:57:35 swin_small_patch4_window7_224] INFO: Epoch: [107] [1080/1251] eta: 0:01:27 lr: 0.000716 loss: 3.8268 (3.4779) grad_norm: 1.1184 (nan) time: 0.5091 [2021-03-25 22:57:40 swin_small_patch4_window7_224] INFO: Epoch: [107] [1090/1251] eta: 0:01:22 lr: 0.000716 loss: 3.7123 (3.4783) grad_norm: 1.1184 (nan) time: 0.5097 [2021-03-25 22:57:45 swin_small_patch4_window7_224] INFO: Epoch: [107] [1100/1251] eta: 0:01:17 lr: 0.000716 loss: 3.3325 (3.4758) grad_norm: 1.1907 (nan) time: 0.5075 [2021-03-25 22:57:50 swin_small_patch4_window7_224] INFO: Epoch: [107] [1110/1251] eta: 0:01:11 lr: 0.000716 loss: 3.3768 (3.4752) grad_norm: 1.1377 (nan) time: 0.5029 [2021-03-25 22:57:55 swin_small_patch4_window7_224] INFO: Epoch: [107] [1120/1251] eta: 0:01:06 lr: 0.000716 loss: 3.3837 (3.4739) grad_norm: 1.1545 (nan) time: 0.4993 [2021-03-25 22:58:00 swin_small_patch4_window7_224] INFO: Epoch: [107] [1130/1251] eta: 0:01:01 lr: 0.000716 loss: 3.3440 (3.4727) grad_norm: 1.1698 (nan) time: 0.5014 [2021-03-25 22:58:05 swin_small_patch4_window7_224] INFO: Epoch: [107] [1140/1251] eta: 0:00:56 lr: 0.000716 loss: 3.6271 (3.4738) grad_norm: 1.2032 (nan) time: 0.5034 [2021-03-25 22:58:10 swin_small_patch4_window7_224] INFO: Epoch: [107] [1150/1251] eta: 0:00:51 lr: 0.000716 loss: 3.6271 (3.4721) grad_norm: 1.2138 (nan) time: 0.5044 [2021-03-25 22:58:15 swin_small_patch4_window7_224] INFO: Epoch: [107] [1160/1251] eta: 0:00:46 lr: 0.000716 loss: 3.4128 (3.4726) grad_norm: 1.1505 (nan) time: 0.5032 [2021-03-25 22:58:20 swin_small_patch4_window7_224] INFO: Epoch: [107] [1170/1251] eta: 0:00:41 lr: 0.000716 loss: 3.5639 (3.4719) grad_norm: 1.1373 (nan) time: 0.4959 [2021-03-25 22:58:25 swin_small_patch4_window7_224] INFO: Epoch: [107] [1180/1251] eta: 0:00:36 lr: 0.000716 loss: 3.5222 (3.4723) grad_norm: 1.1305 (nan) time: 0.5005 [2021-03-25 22:58:31 swin_small_patch4_window7_224] INFO: Epoch: [107] [1190/1251] eta: 0:00:31 lr: 0.000716 loss: 3.4491 (3.4702) grad_norm: 1.1359 (nan) time: 0.5127 [2021-03-25 22:58:36 swin_small_patch4_window7_224] INFO: Epoch: [107] [1200/1251] eta: 0:00:25 lr: 0.000716 loss: 3.4880 (3.4709) grad_norm: 1.1546 (nan) time: 0.5128 [2021-03-25 22:58:41 swin_small_patch4_window7_224] INFO: Epoch: [107] [1210/1251] eta: 0:00:20 lr: 0.000716 loss: 3.4880 (3.4690) grad_norm: 1.1246 (nan) time: 0.5016 [2021-03-25 22:58:46 swin_small_patch4_window7_224] INFO: Epoch: [107] [1220/1251] eta: 0:00:15 lr: 0.000716 loss: 3.2454 (3.4676) grad_norm: 1.1601 (nan) time: 0.5021 [2021-03-25 22:58:51 swin_small_patch4_window7_224] INFO: Epoch: [107] [1230/1251] eta: 0:00:10 lr: 0.000716 loss: 3.3955 (3.4663) grad_norm: 1.2593 (nan) time: 0.5064 [2021-03-25 22:58:56 swin_small_patch4_window7_224] INFO: Epoch: [107] [1240/1251] eta: 0:00:05 lr: 0.000716 loss: 3.4493 (3.4666) grad_norm: 1.1773 (nan) time: 0.5063 [2021-03-25 22:59:01 swin_small_patch4_window7_224] INFO: Epoch: [107] [1250/1251] eta: 0:00:00 lr: 0.000716 loss: 3.4991 (3.4649) grad_norm: 1.1564 (nan) time: 0.5007 [2021-03-25 22:59:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:27 loss: 1.2195 (1.2195) acc1: 65.6250 (65.6250) acc5: 93.7500 (93.7500) [2021-03-25 22:59:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 0.9220 (0.9422) acc1: 78.1250 (77.8409) acc5: 93.7500 (93.7500) [2021-03-25 22:59:15 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.9303 (0.9872) acc1: 78.1250 (76.5625) acc5: 92.1875 (92.7827) [2021-03-25 22:59:17 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0084 (1.0164) acc1: 75.0000 (76.1089) acc5: 92.1875 (92.7923) [2021-03-25 22:59:18 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0145 (1.0204) acc1: 73.4375 (75.5716) acc5: 93.7500 (93.1784) [2021-03-25 22:59:19 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0099 (1.0068) acc1: 75.0000 (75.7760) acc5: 94.3396 (93.3440) [2021-03-25 22:59:25 swin_small_patch4_window7_224] INFO: * Acc@1 76.392 Acc@5 93.652 loss 0.989 [2021-03-25 22:59:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.4% [2021-03-25 22:59:25 swin_small_patch4_window7_224] INFO: Max accuracy: 76.45% [2021-03-25 22:59:29 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 0/1251] eta: 1:30:42 lr: 0.000716 loss: 3.4411 (3.4411) grad_norm: 1.1902 (1.1902) time: 4.3505 [2021-03-25 22:59:35 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 10/1251] eta: 0:17:54 lr: 0.000716 loss: 3.3716 (3.3483) grad_norm: 1.1525 (1.1823) time: 0.8656 [2021-03-25 22:59:40 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 20/1251] eta: 0:14:11 lr: 0.000716 loss: 3.4509 (3.4724) grad_norm: 1.1789 (1.2393) time: 0.5091 [2021-03-25 22:59:45 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 30/1251] eta: 0:12:52 lr: 0.000716 loss: 3.8340 (3.5312) grad_norm: 1.1789 (1.2132) time: 0.5042 [2021-03-25 22:59:50 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 40/1251] eta: 0:12:07 lr: 0.000716 loss: 3.3801 (3.5061) grad_norm: 1.2113 (1.2339) time: 0.5052 [2021-03-25 22:59:55 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 50/1251] eta: 0:11:38 lr: 0.000716 loss: 3.4396 (3.5294) grad_norm: 1.1971 (1.2201) time: 0.5034 [2021-03-25 23:00:00 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 60/1251] eta: 0:11:18 lr: 0.000716 loss: 3.6505 (3.5314) grad_norm: 1.1936 (1.2175) time: 0.5067 [2021-03-25 23:00:05 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 70/1251] eta: 0:11:02 lr: 0.000715 loss: 3.4878 (3.5313) grad_norm: 1.2021 (1.2216) time: 0.5084 [2021-03-25 23:00:10 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 80/1251] eta: 0:10:49 lr: 0.000715 loss: 3.5216 (3.5274) grad_norm: 1.2308 (1.2243) time: 0.5079 [2021-03-25 23:00:15 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 90/1251] eta: 0:10:39 lr: 0.000715 loss: 3.5216 (3.5009) grad_norm: 1.2361 (1.2318) time: 0.5121 [2021-03-25 23:00:20 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 100/1251] eta: 0:10:28 lr: 0.000715 loss: 3.3774 (3.5048) grad_norm: 1.2361 (1.2383) time: 0.5112 [2021-03-25 23:00:25 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 110/1251] eta: 0:10:19 lr: 0.000715 loss: 3.6859 (3.5086) grad_norm: 1.1803 (1.2346) time: 0.5111 [2021-03-25 23:00:30 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 120/1251] eta: 0:10:11 lr: 0.000715 loss: 3.5828 (3.4989) grad_norm: 1.2091 (1.2401) time: 0.5124 [2021-03-25 23:00:36 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 130/1251] eta: 0:10:03 lr: 0.000715 loss: 3.5819 (3.5178) grad_norm: 1.2312 (1.2358) time: 0.5094 [2021-03-25 23:00:41 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 140/1251] eta: 0:09:55 lr: 0.000715 loss: 3.5881 (3.5094) grad_norm: 1.1178 (1.2261) time: 0.5097 [2021-03-25 23:00:46 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 150/1251] eta: 0:09:48 lr: 0.000715 loss: 3.5033 (3.5148) grad_norm: 1.1149 (1.2246) time: 0.5080 [2021-03-25 23:00:51 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 160/1251] eta: 0:09:41 lr: 0.000715 loss: 3.5446 (3.5076) grad_norm: 1.2604 (1.2335) time: 0.5109 [2021-03-25 23:00:56 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 170/1251] eta: 0:09:34 lr: 0.000715 loss: 3.5446 (3.5011) grad_norm: 1.2585 (1.2307) time: 0.5111 [2021-03-25 23:01:01 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 180/1251] eta: 0:09:27 lr: 0.000715 loss: 3.4875 (3.4952) grad_norm: 1.1466 (1.2255) time: 0.5058 [2021-03-25 23:01:06 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 190/1251] eta: 0:09:21 lr: 0.000715 loss: 3.5008 (3.5018) grad_norm: 1.1424 (1.2218) time: 0.5075 [2021-03-25 23:01:11 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 200/1251] eta: 0:09:14 lr: 0.000715 loss: 3.6517 (3.4999) grad_norm: 1.1590 (1.2231) time: 0.5076 [2021-03-25 23:01:16 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 210/1251] eta: 0:09:08 lr: 0.000715 loss: 3.5873 (3.4954) grad_norm: 1.1590 (1.2204) time: 0.5074 [2021-03-25 23:01:21 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 220/1251] eta: 0:09:02 lr: 0.000715 loss: 3.5616 (3.5010) grad_norm: 1.1392 (1.2179) time: 0.5069 [2021-03-25 23:01:26 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 230/1251] eta: 0:08:55 lr: 0.000715 loss: 3.5949 (3.5002) grad_norm: 1.1321 (1.2143) time: 0.5034 [2021-03-25 23:01:31 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 240/1251] eta: 0:08:49 lr: 0.000715 loss: 3.5526 (3.4983) grad_norm: 1.1479 (1.2149) time: 0.5034 [2021-03-25 23:01:36 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 250/1251] eta: 0:08:43 lr: 0.000715 loss: 3.5668 (3.5036) grad_norm: 1.1607 (1.2128) time: 0.5054 [2021-03-25 23:01:42 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 260/1251] eta: 0:08:37 lr: 0.000715 loss: 3.5887 (3.4970) grad_norm: 1.1390 (1.2094) time: 0.5067 [2021-03-25 23:01:47 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 270/1251] eta: 0:08:32 lr: 0.000715 loss: 3.4782 (3.5027) grad_norm: 1.1283 (1.2073) time: 0.5072 [2021-03-25 23:01:52 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 280/1251] eta: 0:08:26 lr: 0.000715 loss: 3.4782 (3.4963) grad_norm: 1.1520 (1.2070) time: 0.5081 [2021-03-25 23:01:57 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 290/1251] eta: 0:08:20 lr: 0.000715 loss: 3.4881 (3.4977) grad_norm: 1.1487 (1.2065) time: 0.5034 [2021-03-25 23:02:02 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 300/1251] eta: 0:08:15 lr: 0.000715 loss: 3.4955 (3.4973) grad_norm: 1.1806 (1.2080) time: 0.5074 [2021-03-25 23:02:07 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 310/1251] eta: 0:08:09 lr: 0.000715 loss: 3.6378 (3.4935) grad_norm: 1.1844 (1.2076) time: 0.5091 [2021-03-25 23:02:12 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 320/1251] eta: 0:08:04 lr: 0.000715 loss: 3.6834 (3.4958) grad_norm: 1.2076 (1.2082) time: 0.5078 [2021-03-25 23:02:17 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 330/1251] eta: 0:07:58 lr: 0.000715 loss: 3.6652 (3.5006) grad_norm: 1.2099 (1.2092) time: 0.5124 [2021-03-25 23:02:22 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 340/1251] eta: 0:07:53 lr: 0.000714 loss: 3.6326 (3.4975) grad_norm: 1.2318 (1.2096) time: 0.5099 [2021-03-25 23:02:27 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 350/1251] eta: 0:07:47 lr: 0.000714 loss: 3.5615 (3.5009) grad_norm: 1.1994 (1.2100) time: 0.5082 [2021-03-25 23:02:32 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 360/1251] eta: 0:07:42 lr: 0.000714 loss: 3.7381 (3.5005) grad_norm: 1.1618 (1.2086) time: 0.5064 [2021-03-25 23:02:37 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 370/1251] eta: 0:07:36 lr: 0.000714 loss: 3.0997 (3.4878) grad_norm: 1.1565 (1.2075) time: 0.5042 [2021-03-25 23:02:42 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 380/1251] eta: 0:07:31 lr: 0.000714 loss: 3.0768 (3.4872) grad_norm: 1.1565 (1.2070) time: 0.5039 [2021-03-25 23:02:48 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 390/1251] eta: 0:07:25 lr: 0.000714 loss: 3.1505 (3.4783) grad_norm: 1.1716 (1.2069) time: 0.5057 [2021-03-25 23:02:52 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 400/1251] eta: 0:07:20 lr: 0.000714 loss: 3.1707 (3.4758) grad_norm: 1.1373 (1.2042) time: 0.5027 [2021-03-25 23:02:57 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 410/1251] eta: 0:07:14 lr: 0.000714 loss: 3.6215 (3.4853) grad_norm: 1.1373 (1.2042) time: 0.4977 [2021-03-25 23:03:02 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 420/1251] eta: 0:07:08 lr: 0.000714 loss: 3.6027 (3.4810) grad_norm: 1.1915 (1.2044) time: 0.4963 [2021-03-25 23:03:07 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 430/1251] eta: 0:07:03 lr: 0.000714 loss: 3.4111 (3.4827) grad_norm: 1.2392 (1.2058) time: 0.4983 [2021-03-25 23:03:12 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 440/1251] eta: 0:06:57 lr: 0.000714 loss: 3.6796 (3.4900) grad_norm: 1.1987 (1.2050) time: 0.5010 [2021-03-25 23:03:18 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 450/1251] eta: 0:06:52 lr: 0.000714 loss: 3.7082 (3.4932) grad_norm: 1.1824 (1.2061) time: 0.5037 [2021-03-25 23:03:23 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 460/1251] eta: 0:06:47 lr: 0.000714 loss: 3.6808 (3.4938) grad_norm: 1.1406 (1.2042) time: 0.5053 [2021-03-25 23:03:28 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 470/1251] eta: 0:06:41 lr: 0.000714 loss: 3.4298 (3.4872) grad_norm: 1.1525 (1.2061) time: 0.5024 [2021-03-25 23:03:33 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 480/1251] eta: 0:06:36 lr: 0.000714 loss: 3.3548 (3.4851) grad_norm: 1.2706 (1.2080) time: 0.5000 [2021-03-25 23:03:38 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 490/1251] eta: 0:06:31 lr: 0.000714 loss: 3.6276 (3.4878) grad_norm: 1.2143 (1.2077) time: 0.5048 [2021-03-25 23:03:43 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 500/1251] eta: 0:06:25 lr: 0.000714 loss: 3.5700 (3.4866) grad_norm: 1.1089 (1.2058) time: 0.5033 [2021-03-25 23:03:48 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 510/1251] eta: 0:06:20 lr: 0.000714 loss: 3.5219 (3.4859) grad_norm: 1.1089 (1.2043) time: 0.5054 [2021-03-25 23:03:53 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 520/1251] eta: 0:06:15 lr: 0.000714 loss: 3.6124 (3.4879) grad_norm: 1.1923 (1.2049) time: 0.5095 [2021-03-25 23:03:58 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 530/1251] eta: 0:06:10 lr: 0.000714 loss: 3.7112 (3.4900) grad_norm: 1.1728 (1.2031) time: 0.5068 [2021-03-25 23:04:03 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 540/1251] eta: 0:06:05 lr: 0.000714 loss: 3.6654 (3.4915) grad_norm: 1.1395 (1.2023) time: 0.5119 [2021-03-25 23:04:08 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 550/1251] eta: 0:06:00 lr: 0.000714 loss: 3.5000 (3.4905) grad_norm: 1.1531 (1.2017) time: 0.5199 [2021-03-25 23:04:13 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 560/1251] eta: 0:05:55 lr: 0.000714 loss: 3.5000 (3.4920) grad_norm: 1.1655 (1.2031) time: 0.5203 [2021-03-25 23:04:18 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 570/1251] eta: 0:05:49 lr: 0.000714 loss: 3.8737 (3.5006) grad_norm: 1.2251 (1.2051) time: 0.5070 [2021-03-25 23:04:24 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 580/1251] eta: 0:05:44 lr: 0.000714 loss: 3.8737 (3.5000) grad_norm: 1.1659 (1.2046) time: 0.5040 [2021-03-25 23:04:29 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 590/1251] eta: 0:05:39 lr: 0.000714 loss: 3.4476 (3.4982) grad_norm: 1.1918 (1.2053) time: 0.5089 [2021-03-25 23:04:34 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 600/1251] eta: 0:05:34 lr: 0.000714 loss: 3.6028 (3.4993) grad_norm: 1.1802 (1.2044) time: 0.5082 [2021-03-25 23:04:39 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 610/1251] eta: 0:05:28 lr: 0.000713 loss: 3.6437 (3.5026) grad_norm: 1.1648 (1.2039) time: 0.5062 [2021-03-25 23:04:44 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 620/1251] eta: 0:05:23 lr: 0.000713 loss: 3.6244 (3.5034) grad_norm: 1.1363 (1.2034) time: 0.4998 [2021-03-25 23:04:49 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 630/1251] eta: 0:05:18 lr: 0.000713 loss: 3.3671 (3.4978) grad_norm: 1.1277 (1.2026) time: 0.5009 [2021-03-25 23:04:54 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 640/1251] eta: 0:05:13 lr: 0.000713 loss: 3.1529 (3.4983) grad_norm: 1.1069 (1.2011) time: 0.5023 [2021-03-25 23:04:59 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 650/1251] eta: 0:05:07 lr: 0.000713 loss: 3.7138 (3.5011) grad_norm: 1.1215 (1.2011) time: 0.5011 [2021-03-25 23:05:04 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 660/1251] eta: 0:05:02 lr: 0.000713 loss: 3.7138 (3.5026) grad_norm: 1.2219 (1.2010) time: 0.5056 [2021-03-25 23:05:09 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 670/1251] eta: 0:04:57 lr: 0.000713 loss: 3.6996 (3.5053) grad_norm: 1.2503 (1.2031) time: 0.5043 [2021-03-25 23:05:14 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 680/1251] eta: 0:04:52 lr: 0.000713 loss: 3.6154 (3.5012) grad_norm: 1.1465 (1.2017) time: 0.5023 [2021-03-25 23:05:19 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 690/1251] eta: 0:04:47 lr: 0.000713 loss: 3.0939 (3.4952) grad_norm: 1.1224 (1.2012) time: 0.5070 [2021-03-25 23:05:24 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 700/1251] eta: 0:04:42 lr: 0.000713 loss: 3.2426 (3.4941) grad_norm: 1.1819 (1.2013) time: 0.5079 [2021-03-25 23:05:29 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 710/1251] eta: 0:04:36 lr: 0.000713 loss: 3.7118 (3.4940) grad_norm: 1.1986 (1.2018) time: 0.5030 [2021-03-25 23:05:34 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 720/1251] eta: 0:04:31 lr: 0.000713 loss: 3.5462 (3.4936) grad_norm: 1.1848 (1.2015) time: 0.5058 [2021-03-25 23:05:40 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 730/1251] eta: 0:04:26 lr: 0.000713 loss: 3.3959 (3.4923) grad_norm: 1.2058 (1.2014) time: 0.5256 [2021-03-25 23:05:45 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 740/1251] eta: 0:04:21 lr: 0.000713 loss: 3.5175 (3.4928) grad_norm: 1.2112 (1.2016) time: 0.5339 [2021-03-25 23:05:50 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 750/1251] eta: 0:04:16 lr: 0.000713 loss: 3.3745 (3.4903) grad_norm: 1.1651 (1.2009) time: 0.5165 [2021-03-25 23:05:55 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 760/1251] eta: 0:04:11 lr: 0.000713 loss: 3.3497 (3.4885) grad_norm: 1.1567 (1.2014) time: 0.5150 [2021-03-25 23:06:00 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 770/1251] eta: 0:04:06 lr: 0.000713 loss: 3.3473 (3.4860) grad_norm: 1.1673 (1.2022) time: 0.5132 [2021-03-25 23:06:05 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 780/1251] eta: 0:04:01 lr: 0.000713 loss: 3.3165 (3.4850) grad_norm: 1.2538 (1.2038) time: 0.5048 [2021-03-25 23:06:10 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 790/1251] eta: 0:03:56 lr: 0.000713 loss: 3.4370 (3.4850) grad_norm: 1.2362 (1.2034) time: 0.5059 [2021-03-25 23:06:15 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 800/1251] eta: 0:03:50 lr: 0.000713 loss: 3.7332 (3.4893) grad_norm: 1.1696 (1.2034) time: 0.5054 [2021-03-25 23:06:20 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 810/1251] eta: 0:03:45 lr: 0.000713 loss: 3.7795 (3.4896) grad_norm: 1.1696 (1.2032) time: 0.5047 [2021-03-25 23:06:25 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 820/1251] eta: 0:03:40 lr: 0.000713 loss: 3.6104 (3.4897) grad_norm: 1.1563 (1.2029) time: 0.5000 [2021-03-25 23:06:30 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 830/1251] eta: 0:03:35 lr: 0.000713 loss: 3.5535 (3.4905) grad_norm: 1.1885 (1.2036) time: 0.5004 [2021-03-25 23:06:36 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 840/1251] eta: 0:03:30 lr: 0.000713 loss: 3.8369 (3.4942) grad_norm: 1.1827 (1.2038) time: 0.5067 [2021-03-25 23:06:41 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 850/1251] eta: 0:03:25 lr: 0.000713 loss: 3.8895 (3.4972) grad_norm: 1.1620 (1.2035) time: 0.5109 [2021-03-25 23:06:46 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 860/1251] eta: 0:03:20 lr: 0.000713 loss: 3.8365 (3.4980) grad_norm: 1.1172 (1.2024) time: 0.5090 [2021-03-25 23:06:51 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 870/1251] eta: 0:03:14 lr: 0.000712 loss: 3.6785 (3.4985) grad_norm: 1.1778 (1.2028) time: 0.5062 [2021-03-25 23:06:56 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 880/1251] eta: 0:03:09 lr: 0.000712 loss: 3.5398 (3.4980) grad_norm: 1.2154 (1.2032) time: 0.5110 [2021-03-25 23:07:01 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 890/1251] eta: 0:03:04 lr: 0.000712 loss: 3.4446 (3.4985) grad_norm: 1.2020 (1.2029) time: 0.5127 [2021-03-25 23:07:06 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 900/1251] eta: 0:02:59 lr: 0.000712 loss: 3.4004 (3.4946) grad_norm: 1.1693 (1.2028) time: 0.5055 [2021-03-25 23:07:11 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 910/1251] eta: 0:02:54 lr: 0.000712 loss: 3.2016 (3.4952) grad_norm: 1.1619 (1.2022) time: 0.5056 [2021-03-25 23:07:16 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 920/1251] eta: 0:02:49 lr: 0.000712 loss: 3.3104 (3.4920) grad_norm: 1.1823 (1.2026) time: 0.5088 [2021-03-25 23:07:21 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 930/1251] eta: 0:02:44 lr: 0.000712 loss: 3.3104 (3.4910) grad_norm: 1.1742 (1.2022) time: 0.5136 [2021-03-25 23:07:26 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 940/1251] eta: 0:02:39 lr: 0.000712 loss: 3.5981 (3.4937) grad_norm: 1.1742 (1.2025) time: 0.5085 [2021-03-25 23:07:31 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 950/1251] eta: 0:02:33 lr: 0.000712 loss: 3.6888 (3.4950) grad_norm: 1.1807 (1.2019) time: 0.4981 [2021-03-25 23:07:36 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 960/1251] eta: 0:02:28 lr: 0.000712 loss: 3.5354 (3.4932) grad_norm: 1.1707 (1.2019) time: 0.4990 [2021-03-25 23:07:41 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 970/1251] eta: 0:02:23 lr: 0.000712 loss: 3.5354 (3.4943) grad_norm: 1.1667 (1.2011) time: 0.5000 [2021-03-25 23:07:46 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 980/1251] eta: 0:02:18 lr: 0.000712 loss: 3.4114 (3.4935) grad_norm: 1.1667 (1.2012) time: 0.4977 [2021-03-25 23:07:51 swin_small_patch4_window7_224] INFO: Epoch: [108] [ 990/1251] eta: 0:02:13 lr: 0.000712 loss: 3.6716 (3.4966) grad_norm: 1.2389 (1.2014) time: 0.5017 [2021-03-25 23:07:56 swin_small_patch4_window7_224] INFO: Epoch: [108] [1000/1251] eta: 0:02:08 lr: 0.000712 loss: 3.8093 (3.4982) grad_norm: 1.2544 (1.2022) time: 0.5025 [2021-03-25 23:08:02 swin_small_patch4_window7_224] INFO: Epoch: [108] [1010/1251] eta: 0:02:03 lr: 0.000712 loss: 3.7460 (3.4976) grad_norm: 1.2410 (1.2031) time: 0.5044 [2021-03-25 23:08:07 swin_small_patch4_window7_224] INFO: Epoch: [108] [1020/1251] eta: 0:01:57 lr: 0.000712 loss: 3.6071 (3.4989) grad_norm: 1.2410 (1.2033) time: 0.5129 [2021-03-25 23:08:12 swin_small_patch4_window7_224] INFO: Epoch: [108] [1030/1251] eta: 0:01:52 lr: 0.000712 loss: 3.5359 (3.4979) grad_norm: 1.2414 (1.2035) time: 0.5078 [2021-03-25 23:08:17 swin_small_patch4_window7_224] INFO: Epoch: [108] [1040/1251] eta: 0:01:47 lr: 0.000712 loss: 3.2929 (3.4957) grad_norm: 1.2069 (1.2034) time: 0.5130 [2021-03-25 23:08:22 swin_small_patch4_window7_224] INFO: Epoch: [108] [1050/1251] eta: 0:01:42 lr: 0.000712 loss: 3.2929 (3.4947) grad_norm: 1.1951 (1.2036) time: 0.5133 [2021-03-25 23:08:27 swin_small_patch4_window7_224] INFO: Epoch: [108] [1060/1251] eta: 0:01:37 lr: 0.000712 loss: 3.2616 (3.4907) grad_norm: 1.1246 (1.2026) time: 0.5078 [2021-03-25 23:08:32 swin_small_patch4_window7_224] INFO: Epoch: [108] [1070/1251] eta: 0:01:32 lr: 0.000712 loss: 3.2616 (3.4921) grad_norm: 1.1127 (1.2025) time: 0.5132 [2021-03-25 23:08:37 swin_small_patch4_window7_224] INFO: Epoch: [108] [1080/1251] eta: 0:01:27 lr: 0.000712 loss: 3.7115 (3.4939) grad_norm: 1.1745 (1.2031) time: 0.5100 [2021-03-25 23:08:42 swin_small_patch4_window7_224] INFO: Epoch: [108] [1090/1251] eta: 0:01:22 lr: 0.000712 loss: 3.7456 (3.4952) grad_norm: 1.2086 (1.2030) time: 0.5024 [2021-03-25 23:08:47 swin_small_patch4_window7_224] INFO: Epoch: [108] [1100/1251] eta: 0:01:17 lr: 0.000712 loss: 3.7270 (3.4961) grad_norm: 1.1822 (1.2028) time: 0.5006 [2021-03-25 23:08:52 swin_small_patch4_window7_224] INFO: Epoch: [108] [1110/1251] eta: 0:01:11 lr: 0.000712 loss: 3.5358 (3.4953) grad_norm: 1.1427 (1.2024) time: 0.5017 [2021-03-25 23:08:57 swin_small_patch4_window7_224] INFO: Epoch: [108] [1120/1251] eta: 0:01:06 lr: 0.000712 loss: 3.5236 (3.4957) grad_norm: 1.1413 (1.2022) time: 0.5059 [2021-03-25 23:09:02 swin_small_patch4_window7_224] INFO: Epoch: [108] [1130/1251] eta: 0:01:01 lr: 0.000712 loss: 3.3678 (3.4924) grad_norm: 1.1344 (1.2017) time: 0.5045 [2021-03-25 23:09:07 swin_small_patch4_window7_224] INFO: Epoch: [108] [1140/1251] eta: 0:00:56 lr: 0.000711 loss: 3.2870 (3.4917) grad_norm: 1.1944 (1.2024) time: 0.4998 [2021-03-25 23:09:12 swin_small_patch4_window7_224] INFO: Epoch: [108] [1150/1251] eta: 0:00:51 lr: 0.000711 loss: 3.6981 (3.4936) grad_norm: 1.1907 (1.2021) time: 0.5015 [2021-03-25 23:09:17 swin_small_patch4_window7_224] INFO: Epoch: [108] [1160/1251] eta: 0:00:46 lr: 0.000711 loss: 3.8152 (3.4956) grad_norm: 1.1804 (1.2020) time: 0.5019 [2021-03-25 23:09:23 swin_small_patch4_window7_224] INFO: Epoch: [108] [1170/1251] eta: 0:00:41 lr: 0.000711 loss: 3.7096 (3.4970) grad_norm: 1.1934 (1.2019) time: 0.5035 [2021-03-25 23:09:28 swin_small_patch4_window7_224] INFO: Epoch: [108] [1180/1251] eta: 0:00:36 lr: 0.000711 loss: 3.6287 (3.4981) grad_norm: 1.1934 (1.2020) time: 0.5098 [2021-03-25 23:09:33 swin_small_patch4_window7_224] INFO: Epoch: [108] [1190/1251] eta: 0:00:31 lr: 0.000711 loss: 3.7844 (3.4991) grad_norm: 1.1940 (1.2019) time: 0.5096 [2021-03-25 23:09:38 swin_small_patch4_window7_224] INFO: Epoch: [108] [1200/1251] eta: 0:00:26 lr: 0.000711 loss: 3.7554 (3.5004) grad_norm: 1.2601 (1.2026) time: 0.5018 [2021-03-25 23:09:43 swin_small_patch4_window7_224] INFO: Epoch: [108] [1210/1251] eta: 0:00:20 lr: 0.000711 loss: 3.5231 (3.4984) grad_norm: 1.2601 (1.2024) time: 0.5006 [2021-03-25 23:09:48 swin_small_patch4_window7_224] INFO: Epoch: [108] [1220/1251] eta: 0:00:15 lr: 0.000711 loss: 3.5231 (3.4997) grad_norm: 1.1566 (1.2028) time: 0.5018 [2021-03-25 23:09:53 swin_small_patch4_window7_224] INFO: Epoch: [108] [1230/1251] eta: 0:00:10 lr: 0.000711 loss: 3.6344 (3.5015) grad_norm: 1.2909 (1.2038) time: 0.5070 [2021-03-25 23:09:58 swin_small_patch4_window7_224] INFO: Epoch: [108] [1240/1251] eta: 0:00:05 lr: 0.000711 loss: 3.6344 (3.5011) grad_norm: 1.2583 (1.2041) time: 0.5094 [2021-03-25 23:10:03 swin_small_patch4_window7_224] INFO: Epoch: [108] [1250/1251] eta: 0:00:00 lr: 0.000711 loss: 3.6501 (3.5030) grad_norm: 1.2155 (1.2039) time: 0.5090 [2021-03-25 23:10:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:20 loss: 0.7717 (0.7717) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-25 23:10:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9165 (0.9044) acc1: 78.1250 (78.8352) acc5: 95.3125 (94.7443) [2021-03-25 23:10:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9246 (0.9454) acc1: 76.5625 (77.3065) acc5: 95.3125 (94.2708) [2021-03-25 23:10:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9871 (1.0061) acc1: 75.0000 (75.7560) acc5: 93.7500 (93.5988) [2021-03-25 23:10:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9560 (0.9860) acc1: 75.0000 (75.5716) acc5: 93.7500 (94.0168) [2021-03-25 23:10:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9500 (0.9862) acc1: 73.4375 (75.5520) acc5: 95.3125 (94.0160) [2021-03-25 23:10:22 swin_small_patch4_window7_224] INFO: * Acc@1 76.628 Acc@5 93.792 loss 0.972 [2021-03-25 23:10:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.6% [2021-03-25 23:10:22 swin_small_patch4_window7_224] INFO: Max accuracy: 76.63% [2021-03-25 23:10:27 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 0/1251] eta: 1:34:13 lr: 0.000711 loss: 3.0991 (3.0991) grad_norm: 1.0887 (1.0887) time: 4.5193 [2021-03-25 23:10:32 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 10/1251] eta: 0:18:03 lr: 0.000711 loss: 3.2865 (3.3552) grad_norm: 1.1274 (1.1540) time: 0.8729 [2021-03-25 23:10:37 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 20/1251] eta: 0:14:20 lr: 0.000711 loss: 3.2865 (3.4283) grad_norm: 1.1826 (1.1837) time: 0.5081 [2021-03-25 23:10:42 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 30/1251] eta: 0:12:59 lr: 0.000711 loss: 3.4874 (3.4170) grad_norm: 1.1836 (1.1852) time: 0.5094 [2021-03-25 23:10:47 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 40/1251] eta: 0:12:17 lr: 0.000711 loss: 3.5929 (3.4489) grad_norm: 1.1614 (1.1734) time: 0.5143 [2021-03-25 23:10:52 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 50/1251] eta: 0:11:44 lr: 0.000711 loss: 3.6073 (3.4771) grad_norm: 1.1414 (1.1760) time: 0.5054 [2021-03-25 23:10:57 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 60/1251] eta: 0:11:22 lr: 0.000711 loss: 3.7050 (3.5287) grad_norm: 1.1414 (1.1714) time: 0.4995 [2021-03-25 23:11:02 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 70/1251] eta: 0:11:05 lr: 0.000711 loss: 3.5779 (3.4981) grad_norm: 1.0836 (1.1620) time: 0.5068 [2021-03-25 23:11:07 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 80/1251] eta: 0:10:53 lr: 0.000711 loss: 3.3489 (3.4686) grad_norm: 1.0635 (1.1577) time: 0.5134 [2021-03-25 23:11:12 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 90/1251] eta: 0:10:42 lr: 0.000711 loss: 3.3800 (3.4420) grad_norm: 1.0804 (1.1513) time: 0.5145 [2021-03-25 23:11:18 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 100/1251] eta: 0:10:30 lr: 0.000711 loss: 3.4891 (3.4390) grad_norm: 1.1160 (1.1506) time: 0.5050 [2021-03-25 23:11:22 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 110/1251] eta: 0:10:19 lr: 0.000711 loss: 3.4891 (3.4260) grad_norm: 1.1231 (1.1530) time: 0.4988 [2021-03-25 23:11:27 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 120/1251] eta: 0:10:09 lr: 0.000711 loss: 3.6658 (3.4456) grad_norm: 1.1783 (1.1648) time: 0.4967 [2021-03-25 23:11:33 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 130/1251] eta: 0:10:01 lr: 0.000711 loss: 3.7830 (3.4489) grad_norm: 1.2708 (1.1738) time: 0.5009 [2021-03-25 23:11:38 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 140/1251] eta: 0:09:53 lr: 0.000711 loss: 3.3622 (3.4208) grad_norm: 1.2221 (1.1740) time: 0.5043 [2021-03-25 23:11:43 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 150/1251] eta: 0:09:46 lr: 0.000710 loss: 3.4557 (3.4197) grad_norm: 1.1491 (1.1771) time: 0.5064 [2021-03-25 23:11:48 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 160/1251] eta: 0:09:39 lr: 0.000710 loss: 3.4303 (3.3963) grad_norm: 1.1499 (1.1783) time: 0.5056 [2021-03-25 23:11:53 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 170/1251] eta: 0:09:31 lr: 0.000710 loss: 3.4303 (3.4067) grad_norm: 1.2007 (1.1788) time: 0.5017 [2021-03-25 23:11:58 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 180/1251] eta: 0:09:25 lr: 0.000710 loss: 3.4687 (3.4110) grad_norm: 1.1839 (1.1812) time: 0.5097 [2021-03-25 23:12:03 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 190/1251] eta: 0:09:19 lr: 0.000710 loss: 3.3708 (3.4065) grad_norm: 1.1392 (1.1771) time: 0.5130 [2021-03-25 23:12:08 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 200/1251] eta: 0:09:12 lr: 0.000710 loss: 3.4635 (3.4139) grad_norm: 1.1334 (1.1774) time: 0.5030 [2021-03-25 23:12:13 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 210/1251] eta: 0:09:06 lr: 0.000710 loss: 3.7831 (3.4356) grad_norm: 1.1725 (1.1797) time: 0.5048 [2021-03-25 23:12:18 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 220/1251] eta: 0:09:00 lr: 0.000710 loss: 3.8879 (3.4516) grad_norm: 1.1784 (1.1792) time: 0.5060 [2021-03-25 23:12:23 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 230/1251] eta: 0:08:54 lr: 0.000710 loss: 3.8024 (3.4558) grad_norm: 1.1451 (1.1798) time: 0.5014 [2021-03-25 23:12:28 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 240/1251] eta: 0:08:48 lr: 0.000710 loss: 3.5067 (3.4577) grad_norm: 1.1768 (1.1811) time: 0.5053 [2021-03-25 23:12:33 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 250/1251] eta: 0:08:42 lr: 0.000710 loss: 3.3610 (3.4540) grad_norm: 1.1768 (1.1805) time: 0.5069 [2021-03-25 23:12:38 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 260/1251] eta: 0:08:36 lr: 0.000710 loss: 3.3756 (3.4522) grad_norm: 1.1715 (1.1824) time: 0.5107 [2021-03-25 23:12:43 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 270/1251] eta: 0:08:30 lr: 0.000710 loss: 3.2817 (3.4412) grad_norm: 1.1483 (1.1819) time: 0.5058 [2021-03-25 23:12:48 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 280/1251] eta: 0:08:25 lr: 0.000710 loss: 3.2755 (3.4423) grad_norm: 1.1870 (1.1830) time: 0.5028 [2021-03-25 23:12:54 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 290/1251] eta: 0:08:19 lr: 0.000710 loss: 3.4679 (3.4434) grad_norm: 1.2464 (1.1841) time: 0.5095 [2021-03-25 23:12:59 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 300/1251] eta: 0:08:14 lr: 0.000710 loss: 3.2084 (3.4299) grad_norm: 1.2466 (1.1875) time: 0.5099 [2021-03-25 23:13:04 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 310/1251] eta: 0:08:08 lr: 0.000710 loss: 3.1230 (3.4276) grad_norm: 1.2528 (1.1911) time: 0.5088 [2021-03-25 23:13:09 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 320/1251] eta: 0:08:02 lr: 0.000710 loss: 3.4107 (3.4264) grad_norm: 1.2096 (1.1907) time: 0.5049 [2021-03-25 23:13:14 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 330/1251] eta: 0:07:56 lr: 0.000710 loss: 3.4536 (3.4243) grad_norm: 1.1791 (1.1903) time: 0.4970 [2021-03-25 23:13:19 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 340/1251] eta: 0:07:51 lr: 0.000710 loss: 3.6778 (3.4289) grad_norm: 1.1500 (1.1887) time: 0.5005 [2021-03-25 23:13:24 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 350/1251] eta: 0:07:45 lr: 0.000710 loss: 3.4537 (3.4216) grad_norm: 1.1131 (1.1864) time: 0.5033 [2021-03-25 23:13:29 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 360/1251] eta: 0:07:40 lr: 0.000710 loss: 3.4537 (3.4272) grad_norm: 1.1131 (1.1867) time: 0.5023 [2021-03-25 23:13:34 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 370/1251] eta: 0:07:35 lr: 0.000710 loss: 3.6619 (3.4328) grad_norm: 1.1403 (1.1854) time: 0.5075 [2021-03-25 23:13:39 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 380/1251] eta: 0:07:29 lr: 0.000710 loss: 3.5849 (3.4342) grad_norm: 1.1484 (1.1870) time: 0.5053 [2021-03-25 23:13:44 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 390/1251] eta: 0:07:24 lr: 0.000710 loss: 3.2463 (3.4317) grad_norm: 1.1684 (1.1863) time: 0.5037 [2021-03-25 23:13:49 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 400/1251] eta: 0:07:18 lr: 0.000710 loss: 3.2463 (3.4324) grad_norm: 1.1198 (1.1849) time: 0.5086 [2021-03-25 23:13:54 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 410/1251] eta: 0:07:13 lr: 0.000710 loss: 3.6147 (3.4369) grad_norm: 1.1095 (1.1852) time: 0.5100 [2021-03-25 23:13:59 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 420/1251] eta: 0:07:08 lr: 0.000709 loss: 3.6386 (3.4378) grad_norm: 1.2096 (1.1863) time: 0.5058 [2021-03-25 23:14:04 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 430/1251] eta: 0:07:02 lr: 0.000709 loss: 3.5904 (3.4341) grad_norm: 1.2181 (1.1866) time: 0.5069 [2021-03-25 23:14:09 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 440/1251] eta: 0:06:57 lr: 0.000709 loss: 3.4582 (3.4325) grad_norm: 1.1606 (1.1859) time: 0.5061 [2021-03-25 23:14:14 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 450/1251] eta: 0:06:52 lr: 0.000709 loss: 3.4301 (3.4324) grad_norm: 1.1410 (1.1845) time: 0.5048 [2021-03-25 23:14:19 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 460/1251] eta: 0:06:47 lr: 0.000709 loss: 3.6920 (3.4329) grad_norm: 1.1152 (1.1832) time: 0.5090 [2021-03-25 23:14:24 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 470/1251] eta: 0:06:41 lr: 0.000709 loss: 3.6920 (3.4353) grad_norm: 1.1318 (1.1829) time: 0.5054 [2021-03-25 23:14:30 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 480/1251] eta: 0:06:36 lr: 0.000709 loss: 3.6221 (3.4393) grad_norm: 1.2235 (1.1842) time: 0.5070 [2021-03-25 23:14:35 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 490/1251] eta: 0:06:31 lr: 0.000709 loss: 3.3970 (3.4377) grad_norm: 1.2342 (1.1848) time: 0.5100 [2021-03-25 23:14:40 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 500/1251] eta: 0:06:25 lr: 0.000709 loss: 3.5794 (3.4405) grad_norm: 1.1890 (1.1846) time: 0.5039 [2021-03-25 23:14:45 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 510/1251] eta: 0:06:20 lr: 0.000709 loss: 3.6799 (3.4434) grad_norm: 1.1358 (1.1834) time: 0.5055 [2021-03-25 23:14:50 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 520/1251] eta: 0:06:15 lr: 0.000709 loss: 3.6799 (3.4478) grad_norm: 1.1435 (1.1848) time: 0.5037 [2021-03-25 23:14:55 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 530/1251] eta: 0:06:10 lr: 0.000709 loss: 3.4148 (3.4450) grad_norm: 1.1876 (1.1861) time: 0.4984 [2021-03-25 23:15:00 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 540/1251] eta: 0:06:04 lr: 0.000709 loss: 3.2863 (3.4454) grad_norm: 1.1876 (1.1864) time: 0.5038 [2021-03-25 23:15:05 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 550/1251] eta: 0:05:59 lr: 0.000709 loss: 3.4148 (3.4453) grad_norm: 1.1751 (1.1872) time: 0.5153 [2021-03-25 23:15:10 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 560/1251] eta: 0:05:54 lr: 0.000709 loss: 3.4859 (3.4446) grad_norm: 1.1700 (1.1863) time: 0.5139 [2021-03-25 23:15:15 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 570/1251] eta: 0:05:49 lr: 0.000709 loss: 3.3791 (3.4433) grad_norm: 1.1430 (1.1856) time: 0.5049 [2021-03-25 23:15:20 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 580/1251] eta: 0:05:44 lr: 0.000709 loss: 3.5266 (3.4461) grad_norm: 1.1293 (1.1850) time: 0.5087 [2021-03-25 23:15:25 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 590/1251] eta: 0:05:39 lr: 0.000709 loss: 3.5685 (3.4501) grad_norm: 1.1525 (1.1850) time: 0.5151 [2021-03-25 23:15:31 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 600/1251] eta: 0:05:33 lr: 0.000709 loss: 3.3110 (3.4467) grad_norm: 1.1525 (1.1843) time: 0.5106 [2021-03-25 23:15:36 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 610/1251] eta: 0:05:28 lr: 0.000709 loss: 3.4648 (3.4512) grad_norm: 1.1260 (1.1845) time: 0.5074 [2021-03-25 23:15:41 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 620/1251] eta: 0:05:23 lr: 0.000709 loss: 3.5760 (3.4531) grad_norm: 1.1106 (1.1834) time: 0.5062 [2021-03-25 23:15:46 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 630/1251] eta: 0:05:18 lr: 0.000709 loss: 3.5273 (3.4545) grad_norm: 1.1228 (1.1829) time: 0.5047 [2021-03-25 23:15:51 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 640/1251] eta: 0:05:13 lr: 0.000709 loss: 3.5471 (3.4548) grad_norm: 1.1312 (1.1821) time: 0.5111 [2021-03-25 23:15:56 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 650/1251] eta: 0:05:08 lr: 0.000709 loss: 3.5482 (3.4566) grad_norm: 1.1363 (1.1820) time: 0.5170 [2021-03-25 23:16:01 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 660/1251] eta: 0:05:03 lr: 0.000709 loss: 3.4752 (3.4546) grad_norm: 1.2152 (1.1837) time: 0.5127 [2021-03-25 23:16:06 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 670/1251] eta: 0:04:57 lr: 0.000709 loss: 3.8218 (3.4606) grad_norm: 1.2444 (1.1849) time: 0.5075 [2021-03-25 23:16:11 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 680/1251] eta: 0:04:52 lr: 0.000708 loss: 3.5784 (3.4584) grad_norm: 1.1763 (1.1842) time: 0.5028 [2021-03-25 23:16:16 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 690/1251] eta: 0:04:47 lr: 0.000708 loss: 3.3886 (3.4619) grad_norm: 1.1655 (1.1849) time: 0.4989 [2021-03-25 23:16:21 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 700/1251] eta: 0:04:42 lr: 0.000708 loss: 3.6693 (3.4633) grad_norm: 1.1655 (1.1862) time: 0.4985 [2021-03-25 23:16:26 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 710/1251] eta: 0:04:36 lr: 0.000708 loss: 3.6693 (3.4640) grad_norm: 1.2223 (1.1867) time: 0.4968 [2021-03-25 23:16:31 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 720/1251] eta: 0:04:31 lr: 0.000708 loss: 3.6214 (3.4642) grad_norm: 1.2223 (1.1879) time: 0.4980 [2021-03-25 23:16:36 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 730/1251] eta: 0:04:26 lr: 0.000708 loss: 3.5813 (3.4647) grad_norm: 1.2469 (1.1897) time: 0.5144 [2021-03-25 23:16:42 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 740/1251] eta: 0:04:21 lr: 0.000708 loss: 3.4949 (3.4627) grad_norm: 1.2261 (1.1898) time: 0.5238 [2021-03-25 23:16:47 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 750/1251] eta: 0:04:16 lr: 0.000708 loss: 3.6599 (3.4655) grad_norm: 1.1947 (1.1904) time: 0.5083 [2021-03-25 23:16:52 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 760/1251] eta: 0:04:11 lr: 0.000708 loss: 3.6381 (3.4638) grad_norm: 1.1947 (1.1900) time: 0.4999 [2021-03-25 23:16:57 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 770/1251] eta: 0:04:06 lr: 0.000708 loss: 3.3999 (3.4640) grad_norm: 1.1376 (1.1892) time: 0.5090 [2021-03-25 23:17:02 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 780/1251] eta: 0:04:00 lr: 0.000708 loss: 3.5472 (3.4631) grad_norm: 1.1466 (1.1887) time: 0.5112 [2021-03-25 23:17:07 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 790/1251] eta: 0:03:55 lr: 0.000708 loss: 3.2680 (3.4616) grad_norm: 1.1560 (1.1893) time: 0.5137 [2021-03-25 23:17:12 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 800/1251] eta: 0:03:50 lr: 0.000708 loss: 3.5829 (3.4635) grad_norm: 1.1862 (1.1901) time: 0.5096 [2021-03-25 23:17:17 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 810/1251] eta: 0:03:45 lr: 0.000708 loss: 3.7287 (3.4654) grad_norm: 1.1924 (1.1903) time: 0.4997 [2021-03-25 23:17:22 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 820/1251] eta: 0:03:40 lr: 0.000708 loss: 3.6184 (3.4645) grad_norm: 1.1565 (1.1896) time: 0.4983 [2021-03-25 23:17:27 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 830/1251] eta: 0:03:35 lr: 0.000708 loss: 3.4352 (3.4629) grad_norm: 1.1234 (1.1891) time: 0.5015 [2021-03-25 23:17:32 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 840/1251] eta: 0:03:30 lr: 0.000708 loss: 3.4313 (3.4602) grad_norm: 1.1459 (1.1887) time: 0.5054 [2021-03-25 23:17:37 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 850/1251] eta: 0:03:24 lr: 0.000708 loss: 3.2709 (3.4577) grad_norm: 1.1459 (1.1882) time: 0.5015 [2021-03-25 23:17:42 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 860/1251] eta: 0:03:19 lr: 0.000708 loss: 3.5385 (3.4587) grad_norm: 1.1470 (1.1884) time: 0.5050 [2021-03-25 23:17:47 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 870/1251] eta: 0:03:14 lr: 0.000708 loss: 3.6104 (3.4581) grad_norm: 1.1894 (1.1884) time: 0.5072 [2021-03-25 23:17:52 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 880/1251] eta: 0:03:09 lr: 0.000708 loss: 3.3912 (3.4577) grad_norm: 1.1562 (1.1883) time: 0.5087 [2021-03-25 23:17:57 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 890/1251] eta: 0:03:04 lr: 0.000708 loss: 3.3912 (3.4598) grad_norm: 1.1956 (1.1898) time: 0.5100 [2021-03-25 23:18:03 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 900/1251] eta: 0:02:59 lr: 0.000708 loss: 3.2740 (3.4580) grad_norm: 1.2682 (1.1906) time: 0.5078 [2021-03-25 23:18:08 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 910/1251] eta: 0:02:54 lr: 0.000708 loss: 3.5432 (3.4594) grad_norm: 1.1606 (1.1903) time: 0.5062 [2021-03-25 23:18:13 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 920/1251] eta: 0:02:49 lr: 0.000708 loss: 3.6431 (3.4614) grad_norm: 1.1595 (1.1903) time: 0.5101 [2021-03-25 23:18:18 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 930/1251] eta: 0:02:43 lr: 0.000708 loss: 3.9015 (3.4656) grad_norm: 1.1019 (1.1897) time: 0.5102 [2021-03-25 23:18:23 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 940/1251] eta: 0:02:38 lr: 0.000708 loss: 3.5715 (3.4660) grad_norm: 1.1526 (1.1898) time: 0.5072 [2021-03-25 23:18:28 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 950/1251] eta: 0:02:33 lr: 0.000707 loss: 3.3913 (3.4638) grad_norm: 1.1653 (1.1890) time: 0.5058 [2021-03-25 23:18:33 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 960/1251] eta: 0:02:28 lr: 0.000707 loss: 3.3855 (3.4613) grad_norm: 1.0972 (1.1884) time: 0.5139 [2021-03-25 23:18:38 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 970/1251] eta: 0:02:23 lr: 0.000707 loss: 3.3855 (3.4603) grad_norm: 1.1307 (1.1883) time: 0.5158 [2021-03-25 23:18:43 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 980/1251] eta: 0:02:18 lr: 0.000707 loss: 3.5077 (3.4600) grad_norm: 1.1307 (1.1874) time: 0.5047 [2021-03-25 23:18:48 swin_small_patch4_window7_224] INFO: Epoch: [109] [ 990/1251] eta: 0:02:13 lr: 0.000707 loss: 3.5182 (3.4611) grad_norm: 1.0941 (1.1870) time: 0.5072 [2021-03-25 23:18:53 swin_small_patch4_window7_224] INFO: Epoch: [109] [1000/1251] eta: 0:02:08 lr: 0.000707 loss: 3.4498 (3.4597) grad_norm: 1.1539 (1.1872) time: 0.5088 [2021-03-25 23:18:58 swin_small_patch4_window7_224] INFO: Epoch: [109] [1010/1251] eta: 0:02:03 lr: 0.000707 loss: 3.4498 (3.4580) grad_norm: 1.1546 (1.1873) time: 0.5025 [2021-03-25 23:19:03 swin_small_patch4_window7_224] INFO: Epoch: [109] [1020/1251] eta: 0:01:57 lr: 0.000707 loss: 3.5453 (3.4576) grad_norm: 1.1483 (1.1875) time: 0.4960 [2021-03-25 23:19:08 swin_small_patch4_window7_224] INFO: Epoch: [109] [1030/1251] eta: 0:01:52 lr: 0.000707 loss: 3.2555 (3.4546) grad_norm: 1.1164 (1.1871) time: 0.5016 [2021-03-25 23:19:14 swin_small_patch4_window7_224] INFO: Epoch: [109] [1040/1251] eta: 0:01:47 lr: 0.000707 loss: 3.4360 (3.4551) grad_norm: 1.1297 (1.1875) time: 0.5091 [2021-03-25 23:19:19 swin_small_patch4_window7_224] INFO: Epoch: [109] [1050/1251] eta: 0:01:42 lr: 0.000707 loss: 3.4687 (3.4544) grad_norm: 1.2225 (1.1883) time: 0.5046 [2021-03-25 23:19:24 swin_small_patch4_window7_224] INFO: Epoch: [109] [1060/1251] eta: 0:01:37 lr: 0.000707 loss: 3.3119 (3.4529) grad_norm: 1.2649 (1.1891) time: 0.5013 [2021-03-25 23:19:29 swin_small_patch4_window7_224] INFO: Epoch: [109] [1070/1251] eta: 0:01:32 lr: 0.000707 loss: 3.4490 (3.4544) grad_norm: 1.2487 (1.1895) time: 0.5068 [2021-03-25 23:19:34 swin_small_patch4_window7_224] INFO: Epoch: [109] [1080/1251] eta: 0:01:27 lr: 0.000707 loss: 3.6064 (3.4545) grad_norm: 1.2002 (1.1902) time: 0.5093 [2021-03-25 23:19:39 swin_small_patch4_window7_224] INFO: Epoch: [109] [1090/1251] eta: 0:01:22 lr: 0.000707 loss: 3.4350 (3.4557) grad_norm: 1.1800 (1.1903) time: 0.5017 [2021-03-25 23:19:44 swin_small_patch4_window7_224] INFO: Epoch: [109] [1100/1251] eta: 0:01:16 lr: 0.000707 loss: 3.5488 (3.4551) grad_norm: 1.1947 (1.1905) time: 0.4972 [2021-03-25 23:19:49 swin_small_patch4_window7_224] INFO: Epoch: [109] [1110/1251] eta: 0:01:11 lr: 0.000707 loss: 3.6847 (3.4563) grad_norm: 1.1641 (1.1904) time: 0.4992 [2021-03-25 23:19:54 swin_small_patch4_window7_224] INFO: Epoch: [109] [1120/1251] eta: 0:01:06 lr: 0.000707 loss: 3.6813 (3.4567) grad_norm: 1.0936 (1.1897) time: 0.5038 [2021-03-25 23:19:59 swin_small_patch4_window7_224] INFO: Epoch: [109] [1130/1251] eta: 0:01:01 lr: 0.000707 loss: 3.6751 (3.4571) grad_norm: 1.0946 (1.1898) time: 0.5095 [2021-03-25 23:20:04 swin_small_patch4_window7_224] INFO: Epoch: [109] [1140/1251] eta: 0:00:56 lr: 0.000707 loss: 3.6038 (3.4564) grad_norm: 1.2024 (1.1901) time: 0.5092 [2021-03-25 23:20:09 swin_small_patch4_window7_224] INFO: Epoch: [109] [1150/1251] eta: 0:00:51 lr: 0.000707 loss: 3.2976 (3.4556) grad_norm: 1.2141 (1.1905) time: 0.5125 [2021-03-25 23:20:14 swin_small_patch4_window7_224] INFO: Epoch: [109] [1160/1251] eta: 0:00:46 lr: 0.000707 loss: 3.5107 (3.4561) grad_norm: 1.2088 (1.1907) time: 0.5160 [2021-03-25 23:20:19 swin_small_patch4_window7_224] INFO: Epoch: [109] [1170/1251] eta: 0:00:41 lr: 0.000707 loss: 3.5107 (3.4551) grad_norm: 1.1928 (1.1909) time: 0.5097 [2021-03-25 23:20:24 swin_small_patch4_window7_224] INFO: Epoch: [109] [1180/1251] eta: 0:00:36 lr: 0.000707 loss: 3.5507 (3.4550) grad_norm: 1.1774 (1.1907) time: 0.5030 [2021-03-25 23:20:29 swin_small_patch4_window7_224] INFO: Epoch: [109] [1190/1251] eta: 0:00:31 lr: 0.000707 loss: 3.3961 (3.4532) grad_norm: 1.1731 (1.1905) time: 0.5048 [2021-03-25 23:20:35 swin_small_patch4_window7_224] INFO: Epoch: [109] [1200/1251] eta: 0:00:25 lr: 0.000707 loss: 3.3474 (3.4532) grad_norm: 1.1427 (1.1903) time: 0.5086 [2021-03-25 23:20:40 swin_small_patch4_window7_224] INFO: Epoch: [109] [1210/1251] eta: 0:00:20 lr: 0.000706 loss: 3.4416 (3.4535) grad_norm: 1.1365 (1.1904) time: 0.5042 [2021-03-25 23:20:45 swin_small_patch4_window7_224] INFO: Epoch: [109] [1220/1251] eta: 0:00:15 lr: 0.000706 loss: 3.4315 (3.4529) grad_norm: 1.2090 (1.1904) time: 0.5033 [2021-03-25 23:20:50 swin_small_patch4_window7_224] INFO: Epoch: [109] [1230/1251] eta: 0:00:10 lr: 0.000706 loss: 3.3124 (3.4516) grad_norm: 1.1522 (1.1900) time: 0.5037 [2021-03-25 23:20:55 swin_small_patch4_window7_224] INFO: Epoch: [109] [1240/1251] eta: 0:00:05 lr: 0.000706 loss: 3.5958 (3.4523) grad_norm: 1.1632 (1.1898) time: 0.5036 [2021-03-25 23:21:00 swin_small_patch4_window7_224] INFO: Epoch: [109] [1250/1251] eta: 0:00:00 lr: 0.000706 loss: 3.5790 (3.4514) grad_norm: 1.2365 (1.1910) time: 0.5024 [2021-03-25 23:21:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:32 loss: 1.1416 (1.1416) acc1: 71.8750 (71.8750) acc5: 95.3125 (95.3125) [2021-03-25 23:21:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9534 (0.9555) acc1: 76.5625 (75.7102) acc5: 95.3125 (95.0284) [2021-03-25 23:21:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9293 (0.9629) acc1: 76.5625 (76.0417) acc5: 95.3125 (94.7917) [2021-03-25 23:21:14 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9704 (0.9893) acc1: 76.5625 (75.8065) acc5: 93.7500 (94.4556) [2021-03-25 23:21:16 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9273 (0.9844) acc1: 76.5625 (76.6387) acc5: 93.7500 (94.0168) [2021-03-25 23:21:17 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9273 (0.9880) acc1: 78.1250 (76.6080) acc5: 93.7500 (94.0160) [2021-03-25 23:21:21 swin_small_patch4_window7_224] INFO: * Acc@1 76.596 Acc@5 93.724 loss 0.984 [2021-03-25 23:21:21 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.6% [2021-03-25 23:21:21 swin_small_patch4_window7_224] INFO: Max accuracy: 76.63% [2021-03-25 23:21:25 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 0/1251] eta: 1:25:24 lr: 0.000706 loss: 4.0149 (4.0149) grad_norm: 1.2266 (1.2266) time: 4.0961 [2021-03-25 23:21:30 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 10/1251] eta: 0:17:47 lr: 0.000706 loss: 3.8416 (3.5741) grad_norm: 1.2019 (1.2124) time: 0.8601 [2021-03-25 23:21:35 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 20/1251] eta: 0:14:12 lr: 0.000706 loss: 3.6781 (3.5148) grad_norm: 1.2019 (1.1962) time: 0.5222 [2021-03-25 23:21:40 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 30/1251] eta: 0:12:52 lr: 0.000706 loss: 3.6863 (3.5205) grad_norm: 1.2077 (1.2072) time: 0.5075 [2021-03-25 23:21:45 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 40/1251] eta: 0:12:11 lr: 0.000706 loss: 3.5133 (3.4764) grad_norm: 1.1951 (1.2016) time: 0.5109 [2021-03-25 23:21:50 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 50/1251] eta: 0:11:40 lr: 0.000706 loss: 3.3984 (3.4767) grad_norm: 1.1739 (1.2050) time: 0.5058 [2021-03-25 23:21:55 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 60/1251] eta: 0:11:18 lr: 0.000706 loss: 3.3727 (3.4793) grad_norm: 1.1739 (1.2050) time: 0.4988 [2021-03-25 23:22:00 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 70/1251] eta: 0:11:00 lr: 0.000706 loss: 3.3727 (3.4570) grad_norm: 1.1889 (1.2200) time: 0.4999 [2021-03-25 23:22:05 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 80/1251] eta: 0:10:47 lr: 0.000706 loss: 3.4468 (3.4567) grad_norm: 1.1943 (1.2199) time: 0.5027 [2021-03-25 23:22:10 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 90/1251] eta: 0:10:36 lr: 0.000706 loss: 3.4635 (3.4529) grad_norm: 1.1653 (1.2167) time: 0.5075 [2021-03-25 23:22:15 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 100/1251] eta: 0:10:25 lr: 0.000706 loss: 3.4699 (3.4566) grad_norm: 1.1911 (1.2156) time: 0.5043 [2021-03-25 23:22:21 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 110/1251] eta: 0:10:17 lr: 0.000706 loss: 3.6318 (3.4600) grad_norm: 1.1944 (1.2150) time: 0.5100 [2021-03-25 23:22:26 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 120/1251] eta: 0:10:08 lr: 0.000706 loss: 3.6318 (3.4768) grad_norm: 1.2196 (1.2162) time: 0.5096 [2021-03-25 23:22:31 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 130/1251] eta: 0:09:59 lr: 0.000706 loss: 3.6418 (3.4850) grad_norm: 1.1736 (1.2117) time: 0.5000 [2021-03-25 23:22:36 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 140/1251] eta: 0:09:52 lr: 0.000706 loss: 3.6567 (3.4966) grad_norm: 1.1659 (1.2107) time: 0.5076 [2021-03-25 23:22:41 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 150/1251] eta: 0:09:45 lr: 0.000706 loss: 3.6041 (3.4753) grad_norm: 1.1489 (1.2065) time: 0.5084 [2021-03-25 23:22:46 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 160/1251] eta: 0:09:37 lr: 0.000706 loss: 3.3792 (3.4693) grad_norm: 1.1489 (1.2056) time: 0.5029 [2021-03-25 23:22:51 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 170/1251] eta: 0:09:30 lr: 0.000706 loss: 3.5214 (3.4657) grad_norm: 1.2006 (1.2062) time: 0.5013 [2021-03-25 23:22:56 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 180/1251] eta: 0:09:24 lr: 0.000706 loss: 3.6299 (3.4779) grad_norm: 1.1752 (1.2041) time: 0.5021 [2021-03-25 23:23:01 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 190/1251] eta: 0:09:17 lr: 0.000706 loss: 3.6299 (3.4707) grad_norm: 1.1461 (1.2012) time: 0.5082 [2021-03-25 23:23:06 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 200/1251] eta: 0:09:11 lr: 0.000706 loss: 3.4593 (3.4707) grad_norm: 1.1271 (1.1986) time: 0.5058 [2021-03-25 23:23:11 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 210/1251] eta: 0:09:05 lr: 0.000706 loss: 3.5370 (3.4761) grad_norm: 1.1523 (1.2029) time: 0.5029 [2021-03-25 23:23:16 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 220/1251] eta: 0:08:58 lr: 0.000706 loss: 3.5280 (3.4772) grad_norm: 1.1278 (1.1985) time: 0.5039 [2021-03-25 23:23:21 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 230/1251] eta: 0:08:52 lr: 0.000705 loss: 3.5122 (3.4718) grad_norm: 1.1555 (1.2016) time: 0.5014 [2021-03-25 23:23:26 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 240/1251] eta: 0:08:46 lr: 0.000705 loss: 3.5051 (3.4761) grad_norm: 1.1732 (1.2000) time: 0.4977 [2021-03-25 23:23:31 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 250/1251] eta: 0:08:40 lr: 0.000705 loss: 3.3738 (3.4676) grad_norm: 1.1505 (1.1994) time: 0.4965 [2021-03-25 23:23:36 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 260/1251] eta: 0:08:34 lr: 0.000705 loss: 3.5974 (3.4685) grad_norm: 1.1433 (1.1971) time: 0.5038 [2021-03-25 23:23:41 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 270/1251] eta: 0:08:28 lr: 0.000705 loss: 3.6832 (3.4696) grad_norm: 1.1433 (1.1947) time: 0.5071 [2021-03-25 23:23:46 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 280/1251] eta: 0:08:23 lr: 0.000705 loss: 3.6223 (3.4708) grad_norm: 1.1582 (1.1946) time: 0.5084 [2021-03-25 23:23:51 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 290/1251] eta: 0:08:18 lr: 0.000705 loss: 3.5133 (3.4727) grad_norm: 1.1752 (1.1953) time: 0.5136 [2021-03-25 23:23:57 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 300/1251] eta: 0:08:13 lr: 0.000705 loss: 3.5133 (3.4691) grad_norm: 1.1926 (1.1962) time: 0.5188 [2021-03-25 23:24:02 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 310/1251] eta: 0:08:07 lr: 0.000705 loss: 3.6974 (3.4709) grad_norm: 1.2000 (1.1970) time: 0.5153 [2021-03-25 23:24:07 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 320/1251] eta: 0:08:02 lr: 0.000705 loss: 3.6890 (3.4628) grad_norm: 1.1398 (1.1944) time: 0.5052 [2021-03-25 23:24:12 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 330/1251] eta: 0:07:56 lr: 0.000705 loss: 3.3608 (3.4656) grad_norm: 1.1429 (1.1939) time: 0.5093 [2021-03-25 23:24:17 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 340/1251] eta: 0:07:51 lr: 0.000705 loss: 3.4661 (3.4622) grad_norm: 1.1725 (1.1934) time: 0.5114 [2021-03-25 23:24:22 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 350/1251] eta: 0:07:45 lr: 0.000705 loss: 3.4988 (3.4606) grad_norm: 1.1725 (1.1916) time: 0.5063 [2021-03-25 23:24:27 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 360/1251] eta: 0:07:40 lr: 0.000705 loss: 3.4988 (3.4566) grad_norm: 1.1594 (1.1907) time: 0.5063 [2021-03-25 23:24:32 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 370/1251] eta: 0:07:34 lr: 0.000705 loss: 3.2817 (3.4541) grad_norm: 1.1594 (1.1904) time: 0.5048 [2021-03-25 23:24:37 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 380/1251] eta: 0:07:29 lr: 0.000705 loss: 3.3530 (3.4534) grad_norm: 1.1752 (1.1917) time: 0.5106 [2021-03-25 23:24:43 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 390/1251] eta: 0:07:24 lr: 0.000705 loss: 3.6281 (3.4663) grad_norm: 1.2150 (1.1942) time: 0.5176 [2021-03-25 23:24:48 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 400/1251] eta: 0:07:19 lr: 0.000705 loss: 3.8489 (3.4706) grad_norm: 1.2226 (1.1942) time: 0.5102 [2021-03-25 23:24:53 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 410/1251] eta: 0:07:13 lr: 0.000705 loss: 3.6647 (3.4716) grad_norm: 1.1867 (1.1953) time: 0.5043 [2021-03-25 23:24:58 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 420/1251] eta: 0:07:08 lr: 0.000705 loss: 3.4231 (3.4727) grad_norm: 1.2017 (1.1953) time: 0.5063 [2021-03-25 23:25:03 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 430/1251] eta: 0:07:03 lr: 0.000705 loss: 3.5981 (3.4765) grad_norm: 1.1369 (1.1939) time: 0.5047 [2021-03-25 23:25:08 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 440/1251] eta: 0:06:57 lr: 0.000705 loss: 3.5319 (3.4698) grad_norm: 1.1494 (1.1949) time: 0.5047 [2021-03-25 23:25:13 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 450/1251] eta: 0:06:52 lr: 0.000705 loss: 3.2268 (3.4647) grad_norm: 1.1853 (1.1958) time: 0.5051 [2021-03-25 23:25:18 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 460/1251] eta: 0:06:47 lr: 0.000705 loss: 3.4725 (3.4662) grad_norm: 1.2489 (1.1978) time: 0.5046 [2021-03-25 23:25:23 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 470/1251] eta: 0:06:41 lr: 0.000705 loss: 3.4782 (3.4625) grad_norm: 1.1827 (1.1967) time: 0.5024 [2021-03-25 23:25:28 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 480/1251] eta: 0:06:36 lr: 0.000705 loss: 3.4334 (3.4637) grad_norm: 1.1827 (1.1973) time: 0.5018 [2021-03-25 23:25:33 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 490/1251] eta: 0:06:31 lr: 0.000704 loss: 3.4693 (3.4626) grad_norm: 1.2014 (1.1969) time: 0.5026 [2021-03-25 23:25:38 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 500/1251] eta: 0:06:25 lr: 0.000704 loss: 3.5379 (3.4645) grad_norm: 1.1799 (1.1971) time: 0.4996 [2021-03-25 23:25:43 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 510/1251] eta: 0:06:20 lr: 0.000704 loss: 3.5899 (3.4652) grad_norm: 1.1799 (1.1968) time: 0.4992 [2021-03-25 23:25:48 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 520/1251] eta: 0:06:14 lr: 0.000704 loss: 3.5899 (3.4648) grad_norm: 1.2088 (1.1979) time: 0.4972 [2021-03-25 23:25:53 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 530/1251] eta: 0:06:09 lr: 0.000704 loss: 3.6599 (3.4707) grad_norm: 1.1893 (1.1967) time: 0.5004 [2021-03-25 23:25:58 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 540/1251] eta: 0:06:04 lr: 0.000704 loss: 3.5238 (3.4740) grad_norm: 1.1908 (1.1985) time: 0.5113 [2021-03-25 23:26:03 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 550/1251] eta: 0:05:59 lr: 0.000704 loss: 3.5196 (3.4731) grad_norm: 1.2218 (1.1988) time: 0.5276 [2021-03-25 23:26:09 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 560/1251] eta: 0:05:54 lr: 0.000704 loss: 3.3394 (3.4717) grad_norm: 1.1873 (1.1993) time: 0.5273 [2021-03-25 23:26:14 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 570/1251] eta: 0:05:49 lr: 0.000704 loss: 3.2917 (3.4722) grad_norm: 1.1873 (1.1997) time: 0.5126 [2021-03-25 23:26:19 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 580/1251] eta: 0:05:44 lr: 0.000704 loss: 3.3512 (3.4717) grad_norm: 1.1946 (1.1999) time: 0.5087 [2021-03-25 23:26:24 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 590/1251] eta: 0:05:39 lr: 0.000704 loss: 3.4024 (3.4695) grad_norm: 1.1735 (1.1988) time: 0.5060 [2021-03-25 23:26:29 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 600/1251] eta: 0:05:33 lr: 0.000704 loss: 3.6077 (3.4734) grad_norm: 1.1841 (1.1991) time: 0.5031 [2021-03-25 23:26:34 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 610/1251] eta: 0:05:28 lr: 0.000704 loss: 3.8073 (3.4737) grad_norm: 1.1841 (1.1987) time: 0.5026 [2021-03-25 23:26:39 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 620/1251] eta: 0:05:23 lr: 0.000704 loss: 3.4883 (3.4747) grad_norm: 1.1673 (1.2004) time: 0.5056 [2021-03-25 23:26:44 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 630/1251] eta: 0:05:18 lr: 0.000704 loss: 3.4883 (3.4753) grad_norm: 1.2393 (1.2022) time: 0.5038 [2021-03-25 23:26:49 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 640/1251] eta: 0:05:12 lr: 0.000704 loss: 3.5256 (3.4767) grad_norm: 1.2760 (1.2037) time: 0.4982 [2021-03-25 23:26:54 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 650/1251] eta: 0:05:07 lr: 0.000704 loss: 3.5047 (3.4763) grad_norm: 1.2249 (1.2038) time: 0.5013 [2021-03-25 23:26:59 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 660/1251] eta: 0:05:02 lr: 0.000704 loss: 3.3375 (3.4738) grad_norm: 1.1741 (1.2037) time: 0.5045 [2021-03-25 23:27:04 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 670/1251] eta: 0:04:57 lr: 0.000704 loss: 3.4765 (3.4750) grad_norm: 1.1741 (1.2045) time: 0.5036 [2021-03-25 23:27:09 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 680/1251] eta: 0:04:52 lr: 0.000704 loss: 3.2493 (3.4706) grad_norm: 1.1941 (1.2045) time: 0.5008 [2021-03-25 23:27:14 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 690/1251] eta: 0:04:46 lr: 0.000704 loss: 3.1372 (3.4712) grad_norm: 1.1804 (1.2043) time: 0.5012 [2021-03-25 23:27:19 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 700/1251] eta: 0:04:41 lr: 0.000704 loss: 3.2979 (3.4678) grad_norm: 1.1866 (1.2041) time: 0.5028 [2021-03-25 23:27:24 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 710/1251] eta: 0:04:36 lr: 0.000704 loss: 3.3219 (3.4687) grad_norm: 1.1440 (1.2029) time: 0.5031 [2021-03-25 23:27:29 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 720/1251] eta: 0:04:31 lr: 0.000704 loss: 3.5919 (3.4705) grad_norm: 1.1424 (1.2024) time: 0.5051 [2021-03-25 23:27:34 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 730/1251] eta: 0:04:26 lr: 0.000704 loss: 3.5025 (3.4677) grad_norm: 1.1390 (1.2014) time: 0.5096 [2021-03-25 23:27:40 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 740/1251] eta: 0:04:21 lr: 0.000704 loss: 3.1679 (3.4625) grad_norm: 1.1567 (1.2011) time: 0.5337 [2021-03-25 23:27:45 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 750/1251] eta: 0:04:16 lr: 0.000703 loss: 3.3757 (3.4632) grad_norm: 1.1723 (1.2009) time: 0.5377 [2021-03-25 23:27:50 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 760/1251] eta: 0:04:11 lr: 0.000703 loss: 3.1122 (3.4592) grad_norm: 1.1556 (1.2011) time: 0.5126 [2021-03-25 23:27:55 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 770/1251] eta: 0:04:06 lr: 0.000703 loss: 3.1122 (3.4591) grad_norm: 1.1556 (1.2010) time: 0.5037 [2021-03-25 23:28:00 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 780/1251] eta: 0:04:00 lr: 0.000703 loss: 3.3556 (3.4573) grad_norm: 1.1477 (1.2003) time: 0.5046 [2021-03-25 23:28:05 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 790/1251] eta: 0:03:55 lr: 0.000703 loss: 3.6748 (3.4608) grad_norm: 1.1348 (1.1998) time: 0.5043 [2021-03-25 23:28:10 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 800/1251] eta: 0:03:50 lr: 0.000703 loss: 3.6420 (3.4584) grad_norm: 1.1796 (1.2004) time: 0.4984 [2021-03-25 23:28:15 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 810/1251] eta: 0:03:45 lr: 0.000703 loss: 3.3228 (3.4571) grad_norm: 1.2186 (1.1998) time: 0.4975 [2021-03-25 23:28:20 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 820/1251] eta: 0:03:40 lr: 0.000703 loss: 3.4243 (3.4573) grad_norm: 1.1739 (1.1995) time: 0.5004 [2021-03-25 23:28:25 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 830/1251] eta: 0:03:35 lr: 0.000703 loss: 3.5865 (3.4583) grad_norm: 1.1739 (1.1997) time: 0.5031 [2021-03-25 23:28:30 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 840/1251] eta: 0:03:30 lr: 0.000703 loss: 3.5750 (3.4586) grad_norm: 1.1873 (1.1996) time: 0.5078 [2021-03-25 23:28:36 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 850/1251] eta: 0:03:24 lr: 0.000703 loss: 3.5286 (3.4599) grad_norm: 1.1332 (1.1988) time: 0.5118 [2021-03-25 23:28:41 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 860/1251] eta: 0:03:19 lr: 0.000703 loss: 3.5286 (3.4605) grad_norm: 1.1816 (1.1996) time: 0.5088 [2021-03-25 23:28:46 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 870/1251] eta: 0:03:14 lr: 0.000703 loss: 3.4659 (3.4592) grad_norm: 1.2369 (1.2005) time: 0.5070 [2021-03-25 23:28:51 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 880/1251] eta: 0:03:09 lr: 0.000703 loss: 3.3158 (3.4563) grad_norm: 1.1785 (1.1998) time: 0.5077 [2021-03-25 23:28:56 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 890/1251] eta: 0:03:04 lr: 0.000703 loss: 3.3158 (3.4543) grad_norm: 1.1526 (1.2007) time: 0.5083 [2021-03-25 23:29:01 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 900/1251] eta: 0:02:59 lr: 0.000703 loss: 3.5079 (3.4529) grad_norm: 1.2342 (1.2010) time: 0.5070 [2021-03-25 23:29:06 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 910/1251] eta: 0:02:54 lr: 0.000703 loss: 3.3724 (3.4516) grad_norm: 1.2109 (1.2009) time: 0.5047 [2021-03-25 23:29:11 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 920/1251] eta: 0:02:49 lr: 0.000703 loss: 3.5091 (3.4541) grad_norm: 1.1754 (1.2018) time: 0.5075 [2021-03-25 23:29:16 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 930/1251] eta: 0:02:43 lr: 0.000703 loss: 3.8086 (3.4539) grad_norm: 1.1754 (1.2020) time: 0.5025 [2021-03-25 23:29:21 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 940/1251] eta: 0:02:38 lr: 0.000703 loss: 3.4694 (3.4522) grad_norm: 1.1875 (1.2023) time: 0.5043 [2021-03-25 23:29:26 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 950/1251] eta: 0:02:33 lr: 0.000703 loss: 3.6709 (3.4531) grad_norm: 1.2462 (1.2030) time: 0.5080 [2021-03-25 23:29:31 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 960/1251] eta: 0:02:28 lr: 0.000703 loss: 3.5290 (3.4519) grad_norm: 1.2494 (1.2037) time: 0.5039 [2021-03-25 23:29:36 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 970/1251] eta: 0:02:23 lr: 0.000703 loss: 3.6710 (3.4545) grad_norm: 1.2238 (1.2042) time: 0.5070 [2021-03-25 23:29:41 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 980/1251] eta: 0:02:18 lr: 0.000703 loss: 3.4863 (3.4537) grad_norm: 1.2030 (1.2047) time: 0.5090 [2021-03-25 23:29:46 swin_small_patch4_window7_224] INFO: Epoch: [110] [ 990/1251] eta: 0:02:13 lr: 0.000703 loss: 3.3731 (3.4525) grad_norm: 1.1997 (1.2044) time: 0.5008 [2021-03-25 23:29:51 swin_small_patch4_window7_224] INFO: Epoch: [110] [1000/1251] eta: 0:02:08 lr: 0.000703 loss: 3.3268 (3.4501) grad_norm: 1.1997 (1.2047) time: 0.5024 [2021-03-25 23:29:57 swin_small_patch4_window7_224] INFO: Epoch: [110] [1010/1251] eta: 0:02:02 lr: 0.000703 loss: 3.1049 (3.4481) grad_norm: 1.1750 (1.2044) time: 0.5098 [2021-03-25 23:30:02 swin_small_patch4_window7_224] INFO: Epoch: [110] [1020/1251] eta: 0:01:57 lr: 0.000702 loss: 3.2005 (3.4467) grad_norm: 1.1750 (1.2047) time: 0.5079 [2021-03-25 23:30:07 swin_small_patch4_window7_224] INFO: Epoch: [110] [1030/1251] eta: 0:01:52 lr: 0.000702 loss: 3.3629 (3.4462) grad_norm: 1.2521 (1.2051) time: 0.5022 [2021-03-25 23:30:12 swin_small_patch4_window7_224] INFO: Epoch: [110] [1040/1251] eta: 0:01:47 lr: 0.000702 loss: 3.2567 (3.4447) grad_norm: 1.2172 (1.2048) time: 0.5016 [2021-03-25 23:30:17 swin_small_patch4_window7_224] INFO: Epoch: [110] [1050/1251] eta: 0:01:42 lr: 0.000702 loss: 3.2793 (3.4448) grad_norm: 1.1692 (1.2045) time: 0.5086 [2021-03-25 23:30:22 swin_small_patch4_window7_224] INFO: Epoch: [110] [1060/1251] eta: 0:01:37 lr: 0.000702 loss: 3.6027 (3.4450) grad_norm: 1.1692 (1.2046) time: 0.5075 [2021-03-25 23:30:27 swin_small_patch4_window7_224] INFO: Epoch: [110] [1070/1251] eta: 0:01:32 lr: 0.000702 loss: 3.6288 (3.4447) grad_norm: 1.2350 (1.2049) time: 0.5038 [2021-03-25 23:30:32 swin_small_patch4_window7_224] INFO: Epoch: [110] [1080/1251] eta: 0:01:27 lr: 0.000702 loss: 3.5256 (3.4448) grad_norm: 1.1894 (1.2043) time: 0.5071 [2021-03-25 23:30:37 swin_small_patch4_window7_224] INFO: Epoch: [110] [1090/1251] eta: 0:01:22 lr: 0.000702 loss: 3.5256 (3.4458) grad_norm: 1.1019 (1.2034) time: 0.5053 [2021-03-25 23:30:42 swin_small_patch4_window7_224] INFO: Epoch: [110] [1100/1251] eta: 0:01:16 lr: 0.000702 loss: 3.3593 (3.4427) grad_norm: 1.0978 (1.2030) time: 0.5006 [2021-03-25 23:30:47 swin_small_patch4_window7_224] INFO: Epoch: [110] [1110/1251] eta: 0:01:11 lr: 0.000702 loss: 3.1419 (3.4425) grad_norm: 1.1494 (1.2026) time: 0.5024 [2021-03-25 23:30:52 swin_small_patch4_window7_224] INFO: Epoch: [110] [1120/1251] eta: 0:01:06 lr: 0.000702 loss: 3.5950 (3.4441) grad_norm: 1.1700 (1.2023) time: 0.5005 [2021-03-25 23:30:57 swin_small_patch4_window7_224] INFO: Epoch: [110] [1130/1251] eta: 0:01:01 lr: 0.000702 loss: 3.6227 (3.4453) grad_norm: 1.1929 (1.2028) time: 0.5010 [2021-03-25 23:31:02 swin_small_patch4_window7_224] INFO: Epoch: [110] [1140/1251] eta: 0:00:56 lr: 0.000702 loss: 3.6304 (3.4462) grad_norm: 1.2402 (1.2031) time: 0.5041 [2021-03-25 23:31:07 swin_small_patch4_window7_224] INFO: Epoch: [110] [1150/1251] eta: 0:00:51 lr: 0.000702 loss: 3.5090 (3.4454) grad_norm: 1.2535 (1.2038) time: 0.5028 [2021-03-25 23:31:12 swin_small_patch4_window7_224] INFO: Epoch: [110] [1160/1251] eta: 0:00:46 lr: 0.000702 loss: 3.1472 (3.4432) grad_norm: 1.2300 (1.2040) time: 0.5026 [2021-03-25 23:31:17 swin_small_patch4_window7_224] INFO: Epoch: [110] [1170/1251] eta: 0:00:41 lr: 0.000702 loss: 3.0047 (3.4409) grad_norm: 1.1907 (1.2037) time: 0.5063 [2021-03-25 23:31:22 swin_small_patch4_window7_224] INFO: Epoch: [110] [1180/1251] eta: 0:00:36 lr: 0.000702 loss: 3.4343 (3.4417) grad_norm: 1.1517 (1.2040) time: 0.5069 [2021-03-25 23:31:27 swin_small_patch4_window7_224] INFO: Epoch: [110] [1190/1251] eta: 0:00:31 lr: 0.000702 loss: 3.4362 (3.4410) grad_norm: 1.1646 (1.2046) time: 0.5032 [2021-03-25 23:31:32 swin_small_patch4_window7_224] INFO: Epoch: [110] [1200/1251] eta: 0:00:25 lr: 0.000702 loss: 3.4221 (3.4404) grad_norm: 1.2200 (1.2049) time: 0.5036 [2021-03-25 23:31:37 swin_small_patch4_window7_224] INFO: Epoch: [110] [1210/1251] eta: 0:00:20 lr: 0.000702 loss: 3.5788 (3.4426) grad_norm: 1.2523 (1.2053) time: 0.5026 [2021-03-25 23:31:42 swin_small_patch4_window7_224] INFO: Epoch: [110] [1220/1251] eta: 0:00:15 lr: 0.000702 loss: 3.5196 (3.4415) grad_norm: 1.3113 (inf) time: 0.5038 [2021-03-25 23:31:48 swin_small_patch4_window7_224] INFO: Epoch: [110] [1230/1251] eta: 0:00:10 lr: 0.000702 loss: 3.5418 (3.4436) grad_norm: 1.3150 (inf) time: 0.5082 [2021-03-25 23:31:53 swin_small_patch4_window7_224] INFO: Epoch: [110] [1240/1251] eta: 0:00:05 lr: 0.000702 loss: 3.5418 (3.4431) grad_norm: 1.2717 (inf) time: 0.5096 [2021-03-25 23:31:58 swin_small_patch4_window7_224] INFO: Epoch: [110] [1250/1251] eta: 0:00:00 lr: 0.000702 loss: 3.4032 (3.4430) grad_norm: 1.2174 (inf) time: 0.5107 [2021-03-25 23:32:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 1.3797 (1.3797) acc1: 70.3125 (70.3125) acc5: 89.0625 (89.0625) [2021-03-25 23:32:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.0131 (1.0811) acc1: 75.0000 (73.7216) acc5: 92.1875 (93.0398) [2021-03-25 23:32:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9461 (0.9963) acc1: 76.5625 (76.4881) acc5: 95.3125 (94.1220) [2021-03-25 23:32:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8999 (0.9963) acc1: 78.1250 (76.7641) acc5: 93.7500 (93.3972) [2021-03-25 23:32:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0451 (1.0070) acc1: 76.5625 (76.5625) acc5: 92.1875 (93.4070) [2021-03-25 23:32:52 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9674 (1.0073) acc1: 75.4717 (76.1280) acc5: 93.7500 (93.5680) [2021-03-25 23:33:00 swin_small_patch4_window7_224] INFO: * Acc@1 76.712 Acc@5 93.634 loss 0.987 [2021-03-25 23:33:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.7% [2021-03-25 23:33:00 swin_small_patch4_window7_224] INFO: Max accuracy: 76.71% [2021-03-25 23:33:04 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 0/1251] eta: 1:23:39 lr: 0.000702 loss: 3.2562 (3.2562) grad_norm: 1.2678 (1.2678) time: 4.0125 [2021-03-25 23:33:09 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 10/1251] eta: 0:17:17 lr: 0.000702 loss: 3.3812 (3.5093) grad_norm: 1.2493 (1.2354) time: 0.8363 [2021-03-25 23:33:14 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 20/1251] eta: 0:13:55 lr: 0.000702 loss: 3.3363 (3.3781) grad_norm: 1.2275 (1.2428) time: 0.5121 [2021-03-25 23:33:19 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 30/1251] eta: 0:12:42 lr: 0.000701 loss: 3.3363 (3.3813) grad_norm: 1.2054 (1.2416) time: 0.5084 [2021-03-25 23:33:24 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 40/1251] eta: 0:12:03 lr: 0.000701 loss: 3.3749 (3.3720) grad_norm: 1.1694 (1.2196) time: 0.5121 [2021-03-25 23:33:30 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 50/1251] eta: 0:11:38 lr: 0.000701 loss: 3.3860 (3.3963) grad_norm: 1.1356 (1.2139) time: 0.5145 [2021-03-25 23:33:35 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 60/1251] eta: 0:11:17 lr: 0.000701 loss: 3.6546 (3.4356) grad_norm: 1.1478 (1.2054) time: 0.5094 [2021-03-25 23:33:40 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 70/1251] eta: 0:11:00 lr: 0.000701 loss: 3.6533 (3.4366) grad_norm: 1.1474 (1.2044) time: 0.5034 [2021-03-25 23:33:45 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 80/1251] eta: 0:10:48 lr: 0.000701 loss: 3.5589 (3.4387) grad_norm: 1.1170 (1.1973) time: 0.5088 [2021-03-25 23:33:50 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 90/1251] eta: 0:10:36 lr: 0.000701 loss: 3.5393 (3.4137) grad_norm: 1.1511 (1.1960) time: 0.5101 [2021-03-25 23:33:55 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 100/1251] eta: 0:10:25 lr: 0.000701 loss: 3.2645 (3.4285) grad_norm: 1.1973 (1.2036) time: 0.5027 [2021-03-25 23:34:00 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 110/1251] eta: 0:10:16 lr: 0.000701 loss: 3.5021 (3.4197) grad_norm: 1.1837 (1.2010) time: 0.5045 [2021-03-25 23:34:05 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 120/1251] eta: 0:10:08 lr: 0.000701 loss: 3.4291 (3.4286) grad_norm: 1.1837 (1.2034) time: 0.5088 [2021-03-25 23:34:10 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 130/1251] eta: 0:10:00 lr: 0.000701 loss: 3.3598 (3.4011) grad_norm: 1.1728 (1.2045) time: 0.5059 [2021-03-25 23:34:15 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 140/1251] eta: 0:09:52 lr: 0.000701 loss: 3.2216 (3.3941) grad_norm: 1.2360 (1.2085) time: 0.5062 [2021-03-25 23:34:20 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 150/1251] eta: 0:09:45 lr: 0.000701 loss: 3.3270 (3.3915) grad_norm: 1.2657 (1.2130) time: 0.5093 [2021-03-25 23:34:25 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 160/1251] eta: 0:09:39 lr: 0.000701 loss: 3.3270 (3.3953) grad_norm: 1.2657 (1.2164) time: 0.5119 [2021-03-25 23:34:30 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 170/1251] eta: 0:09:32 lr: 0.000701 loss: 3.4552 (3.3924) grad_norm: 1.1825 (1.2163) time: 0.5114 [2021-03-25 23:34:36 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 180/1251] eta: 0:09:25 lr: 0.000701 loss: 3.6572 (3.4096) grad_norm: 1.1322 (1.2133) time: 0.5090 [2021-03-25 23:34:41 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 190/1251] eta: 0:09:19 lr: 0.000701 loss: 3.7225 (3.4096) grad_norm: 1.1827 (1.2155) time: 0.5043 [2021-03-25 23:34:46 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 200/1251] eta: 0:09:13 lr: 0.000701 loss: 3.5582 (3.4176) grad_norm: 1.2587 (1.2173) time: 0.5083 [2021-03-25 23:34:51 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 210/1251] eta: 0:09:07 lr: 0.000701 loss: 3.6521 (3.4251) grad_norm: 1.1849 (1.2165) time: 0.5119 [2021-03-25 23:34:56 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 220/1251] eta: 0:09:00 lr: 0.000701 loss: 3.4995 (3.4207) grad_norm: 1.1745 (1.2166) time: 0.5082 [2021-03-25 23:35:01 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 230/1251] eta: 0:08:55 lr: 0.000701 loss: 3.3616 (3.4172) grad_norm: 1.1742 (1.2136) time: 0.5102 [2021-03-25 23:35:06 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 240/1251] eta: 0:08:48 lr: 0.000701 loss: 3.3624 (3.4199) grad_norm: 1.1389 (1.2126) time: 0.5036 [2021-03-25 23:35:11 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 250/1251] eta: 0:08:42 lr: 0.000701 loss: 3.6983 (3.4321) grad_norm: 1.1441 (1.2098) time: 0.5001 [2021-03-25 23:35:16 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 260/1251] eta: 0:08:37 lr: 0.000701 loss: 3.8004 (3.4428) grad_norm: 1.1697 (1.2126) time: 0.5079 [2021-03-25 23:35:21 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 270/1251] eta: 0:08:30 lr: 0.000701 loss: 3.6768 (3.4422) grad_norm: 1.2116 (1.2131) time: 0.5025 [2021-03-25 23:35:26 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 280/1251] eta: 0:08:24 lr: 0.000701 loss: 3.3561 (3.4419) grad_norm: 1.2117 (1.2139) time: 0.4972 [2021-03-25 23:35:31 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 290/1251] eta: 0:08:19 lr: 0.000700 loss: 3.3823 (3.4462) grad_norm: 1.2117 (1.2134) time: 0.5029 [2021-03-25 23:35:36 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 300/1251] eta: 0:08:13 lr: 0.000700 loss: 3.3032 (3.4359) grad_norm: 1.2206 (1.2187) time: 0.5104 [2021-03-25 23:35:41 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 310/1251] eta: 0:08:08 lr: 0.000700 loss: 3.5373 (3.4406) grad_norm: 1.2237 (1.2203) time: 0.5118 [2021-03-25 23:35:46 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 320/1251] eta: 0:08:02 lr: 0.000700 loss: 3.6839 (3.4433) grad_norm: 1.1972 (1.2195) time: 0.5057 [2021-03-25 23:35:51 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 330/1251] eta: 0:07:57 lr: 0.000700 loss: 3.6312 (3.4436) grad_norm: 1.1738 (1.2191) time: 0.5010 [2021-03-25 23:35:56 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 340/1251] eta: 0:07:51 lr: 0.000700 loss: 3.6206 (3.4335) grad_norm: 1.1989 (1.2201) time: 0.5025 [2021-03-25 23:36:01 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 350/1251] eta: 0:07:45 lr: 0.000700 loss: 3.3312 (3.4305) grad_norm: 1.2298 (1.2212) time: 0.5031 [2021-03-25 23:36:06 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 360/1251] eta: 0:07:40 lr: 0.000700 loss: 3.3312 (3.4218) grad_norm: 1.2623 (1.2218) time: 0.5032 [2021-03-25 23:36:12 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 370/1251] eta: 0:07:34 lr: 0.000700 loss: 3.3528 (3.4207) grad_norm: 1.2386 (1.2209) time: 0.5048 [2021-03-25 23:36:17 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 380/1251] eta: 0:07:29 lr: 0.000700 loss: 3.4176 (3.4193) grad_norm: 1.1351 (1.2179) time: 0.5025 [2021-03-25 23:36:22 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 390/1251] eta: 0:07:24 lr: 0.000700 loss: 3.6181 (3.4263) grad_norm: 1.1351 (1.2167) time: 0.5043 [2021-03-25 23:36:27 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 400/1251] eta: 0:07:18 lr: 0.000700 loss: 3.5808 (3.4287) grad_norm: 1.1882 (1.2171) time: 0.5050 [2021-03-25 23:36:32 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 410/1251] eta: 0:07:13 lr: 0.000700 loss: 3.6841 (3.4402) grad_norm: 1.1734 (1.2158) time: 0.5052 [2021-03-25 23:36:37 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 420/1251] eta: 0:07:07 lr: 0.000700 loss: 3.8374 (3.4464) grad_norm: 1.1713 (1.2152) time: 0.5040 [2021-03-25 23:36:42 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 430/1251] eta: 0:07:02 lr: 0.000700 loss: 3.6556 (3.4421) grad_norm: 1.1269 (1.2137) time: 0.5045 [2021-03-25 23:36:47 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 440/1251] eta: 0:06:57 lr: 0.000700 loss: 3.5580 (3.4455) grad_norm: 1.1641 (1.2146) time: 0.5045 [2021-03-25 23:36:52 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 450/1251] eta: 0:06:51 lr: 0.000700 loss: 3.5580 (3.4423) grad_norm: 1.2307 (1.2142) time: 0.5019 [2021-03-25 23:36:57 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 460/1251] eta: 0:06:46 lr: 0.000700 loss: 3.5192 (3.4441) grad_norm: 1.1800 (1.2138) time: 0.5028 [2021-03-25 23:37:02 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 470/1251] eta: 0:06:41 lr: 0.000700 loss: 3.4277 (3.4454) grad_norm: 1.1928 (1.2143) time: 0.5049 [2021-03-25 23:37:07 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 480/1251] eta: 0:06:35 lr: 0.000700 loss: 3.4277 (3.4466) grad_norm: 1.1616 (1.2131) time: 0.4990 [2021-03-25 23:37:12 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 490/1251] eta: 0:06:30 lr: 0.000700 loss: 3.4791 (3.4482) grad_norm: 1.1504 (1.2134) time: 0.4968 [2021-03-25 23:37:17 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 500/1251] eta: 0:06:25 lr: 0.000700 loss: 3.4791 (3.4501) grad_norm: 1.2092 (1.2140) time: 0.5047 [2021-03-25 23:37:22 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 510/1251] eta: 0:06:19 lr: 0.000700 loss: 3.6248 (3.4498) grad_norm: 1.2343 (1.2156) time: 0.5046 [2021-03-25 23:37:27 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 520/1251] eta: 0:06:14 lr: 0.000700 loss: 3.6834 (3.4520) grad_norm: 1.2343 (1.2167) time: 0.5039 [2021-03-25 23:37:32 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 530/1251] eta: 0:06:09 lr: 0.000700 loss: 3.6615 (3.4488) grad_norm: 1.2029 (1.2154) time: 0.5088 [2021-03-25 23:37:37 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 540/1251] eta: 0:06:04 lr: 0.000700 loss: 3.4724 (3.4505) grad_norm: 1.1381 (1.2152) time: 0.5062 [2021-03-25 23:37:42 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 550/1251] eta: 0:05:59 lr: 0.000699 loss: 3.5348 (3.4486) grad_norm: 1.2211 (1.2149) time: 0.5131 [2021-03-25 23:37:47 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 560/1251] eta: 0:05:54 lr: 0.000699 loss: 3.5163 (3.4468) grad_norm: 1.1562 (1.2142) time: 0.5153 [2021-03-25 23:37:53 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 570/1251] eta: 0:05:48 lr: 0.000699 loss: 3.5249 (3.4494) grad_norm: 1.1531 (1.2137) time: 0.5052 [2021-03-25 23:37:58 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 580/1251] eta: 0:05:43 lr: 0.000699 loss: 3.5249 (3.4481) grad_norm: 1.1822 (1.2133) time: 0.5049 [2021-03-25 23:38:03 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 590/1251] eta: 0:05:38 lr: 0.000699 loss: 3.7111 (3.4486) grad_norm: 1.2111 (1.2131) time: 0.5078 [2021-03-25 23:38:08 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 600/1251] eta: 0:05:33 lr: 0.000699 loss: 3.6102 (3.4508) grad_norm: 1.2199 (inf) time: 0.5089 [2021-03-25 23:38:13 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 610/1251] eta: 0:05:28 lr: 0.000699 loss: 3.6102 (3.4539) grad_norm: 1.2060 (inf) time: 0.5052 [2021-03-25 23:38:18 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 620/1251] eta: 0:05:23 lr: 0.000699 loss: 3.6682 (3.4553) grad_norm: 1.1980 (inf) time: 0.5038 [2021-03-25 23:38:23 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 630/1251] eta: 0:05:17 lr: 0.000699 loss: 3.3324 (3.4516) grad_norm: 1.1812 (inf) time: 0.5087 [2021-03-25 23:38:28 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 640/1251] eta: 0:05:12 lr: 0.000699 loss: 3.5757 (3.4558) grad_norm: 1.1724 (inf) time: 0.5092 [2021-03-25 23:38:33 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 650/1251] eta: 0:05:07 lr: 0.000699 loss: 3.6453 (3.4555) grad_norm: 1.1668 (inf) time: 0.5115 [2021-03-25 23:38:38 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 660/1251] eta: 0:05:02 lr: 0.000699 loss: 3.4087 (3.4544) grad_norm: 1.1101 (inf) time: 0.5159 [2021-03-25 23:38:43 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 670/1251] eta: 0:04:57 lr: 0.000699 loss: 3.7216 (3.4581) grad_norm: 1.0958 (inf) time: 0.5072 [2021-03-25 23:38:48 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 680/1251] eta: 0:04:52 lr: 0.000699 loss: 3.7216 (3.4598) grad_norm: 1.2231 (inf) time: 0.5023 [2021-03-25 23:38:53 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 690/1251] eta: 0:04:46 lr: 0.000699 loss: 3.4253 (3.4573) grad_norm: 1.2250 (inf) time: 0.5051 [2021-03-25 23:38:59 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 700/1251] eta: 0:04:41 lr: 0.000699 loss: 3.4038 (3.4573) grad_norm: 1.1632 (inf) time: 0.5075 [2021-03-25 23:39:04 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 710/1251] eta: 0:04:36 lr: 0.000699 loss: 3.4418 (3.4556) grad_norm: 1.2109 (inf) time: 0.5082 [2021-03-25 23:39:09 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 720/1251] eta: 0:04:31 lr: 0.000699 loss: 3.4627 (3.4551) grad_norm: 1.2069 (inf) time: 0.5064 [2021-03-25 23:39:14 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 730/1251] eta: 0:04:26 lr: 0.000699 loss: 3.4627 (3.4517) grad_norm: 1.1825 (inf) time: 0.5082 [2021-03-25 23:39:19 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 740/1251] eta: 0:04:21 lr: 0.000699 loss: 3.4522 (3.4512) grad_norm: 1.1713 (inf) time: 0.5261 [2021-03-25 23:39:24 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 750/1251] eta: 0:04:16 lr: 0.000699 loss: 3.6413 (3.4546) grad_norm: 1.1743 (inf) time: 0.5242 [2021-03-25 23:39:29 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 760/1251] eta: 0:04:11 lr: 0.000699 loss: 3.6747 (3.4594) grad_norm: 1.1635 (inf) time: 0.5006 [2021-03-25 23:39:34 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 770/1251] eta: 0:04:05 lr: 0.000699 loss: 3.5330 (3.4587) grad_norm: 1.1632 (inf) time: 0.4964 [2021-03-25 23:39:39 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 780/1251] eta: 0:04:00 lr: 0.000699 loss: 3.4742 (3.4585) grad_norm: 1.1259 (inf) time: 0.5079 [2021-03-25 23:39:44 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 790/1251] eta: 0:03:55 lr: 0.000699 loss: 3.3175 (3.4560) grad_norm: 1.1448 (inf) time: 0.5130 [2021-03-25 23:39:49 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 800/1251] eta: 0:03:50 lr: 0.000699 loss: 3.0275 (3.4548) grad_norm: 1.1743 (inf) time: 0.5054 [2021-03-25 23:39:55 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 810/1251] eta: 0:03:45 lr: 0.000699 loss: 3.3376 (3.4544) grad_norm: 1.1911 (inf) time: 0.5096 [2021-03-25 23:40:00 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 820/1251] eta: 0:03:40 lr: 0.000698 loss: 3.5315 (3.4540) grad_norm: 1.1911 (inf) time: 0.5147 [2021-03-25 23:40:05 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 830/1251] eta: 0:03:35 lr: 0.000698 loss: 3.7219 (3.4577) grad_norm: 1.1770 (inf) time: 0.5023 [2021-03-25 23:40:10 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 840/1251] eta: 0:03:30 lr: 0.000698 loss: 3.5780 (3.4554) grad_norm: 1.1998 (inf) time: 0.5044 [2021-03-25 23:40:15 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 850/1251] eta: 0:03:24 lr: 0.000698 loss: 3.3772 (3.4555) grad_norm: 1.1699 (inf) time: 0.5116 [2021-03-25 23:40:20 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 860/1251] eta: 0:03:19 lr: 0.000698 loss: 3.6195 (3.4553) grad_norm: 1.1952 (inf) time: 0.5035 [2021-03-25 23:40:25 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 870/1251] eta: 0:03:14 lr: 0.000698 loss: 3.5995 (3.4558) grad_norm: 1.2255 (inf) time: 0.5019 [2021-03-25 23:40:30 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 880/1251] eta: 0:03:09 lr: 0.000698 loss: 3.5995 (3.4566) grad_norm: 1.2087 (inf) time: 0.5070 [2021-03-25 23:40:35 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 890/1251] eta: 0:03:04 lr: 0.000698 loss: 3.4528 (3.4556) grad_norm: 1.1891 (inf) time: 0.5059 [2021-03-25 23:40:40 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 900/1251] eta: 0:02:59 lr: 0.000698 loss: 3.4528 (3.4542) grad_norm: 1.2319 (inf) time: 0.5045 [2021-03-25 23:40:45 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 910/1251] eta: 0:02:54 lr: 0.000698 loss: 3.4343 (3.4548) grad_norm: 1.2065 (inf) time: 0.5068 [2021-03-25 23:40:50 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 920/1251] eta: 0:02:49 lr: 0.000698 loss: 3.7442 (3.4578) grad_norm: 1.2009 (inf) time: 0.5033 [2021-03-25 23:40:55 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 930/1251] eta: 0:02:43 lr: 0.000698 loss: 3.7442 (3.4576) grad_norm: 1.1880 (inf) time: 0.4997 [2021-03-25 23:41:00 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 940/1251] eta: 0:02:38 lr: 0.000698 loss: 3.3699 (3.4573) grad_norm: 1.1723 (inf) time: 0.5102 [2021-03-25 23:41:05 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 950/1251] eta: 0:02:33 lr: 0.000698 loss: 3.6400 (3.4568) grad_norm: 1.1480 (inf) time: 0.5123 [2021-03-25 23:41:11 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 960/1251] eta: 0:02:28 lr: 0.000698 loss: 3.6400 (3.4571) grad_norm: 1.1474 (inf) time: 0.5039 [2021-03-25 23:41:16 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 970/1251] eta: 0:02:23 lr: 0.000698 loss: 3.7695 (3.4593) grad_norm: 1.1775 (inf) time: 0.5089 [2021-03-25 23:41:21 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 980/1251] eta: 0:02:18 lr: 0.000698 loss: 3.7514 (3.4605) grad_norm: 1.1775 (inf) time: 0.5109 [2021-03-25 23:41:26 swin_small_patch4_window7_224] INFO: Epoch: [111] [ 990/1251] eta: 0:02:13 lr: 0.000698 loss: 3.5914 (3.4587) grad_norm: 1.2053 (inf) time: 0.5051 [2021-03-25 23:41:31 swin_small_patch4_window7_224] INFO: Epoch: [111] [1000/1251] eta: 0:02:08 lr: 0.000698 loss: 3.5914 (3.4608) grad_norm: 1.2080 (inf) time: 0.5004 [2021-03-25 23:41:36 swin_small_patch4_window7_224] INFO: Epoch: [111] [1010/1251] eta: 0:02:02 lr: 0.000698 loss: 3.6777 (3.4613) grad_norm: 1.1799 (inf) time: 0.4969 [2021-03-25 23:41:41 swin_small_patch4_window7_224] INFO: Epoch: [111] [1020/1251] eta: 0:01:57 lr: 0.000698 loss: 3.6994 (3.4638) grad_norm: 1.1997 (inf) time: 0.5027 [2021-03-25 23:41:46 swin_small_patch4_window7_224] INFO: Epoch: [111] [1030/1251] eta: 0:01:52 lr: 0.000698 loss: 3.5523 (3.4635) grad_norm: 1.1997 (inf) time: 0.5080 [2021-03-25 23:41:51 swin_small_patch4_window7_224] INFO: Epoch: [111] [1040/1251] eta: 0:01:47 lr: 0.000698 loss: 3.6561 (3.4652) grad_norm: 1.1668 (inf) time: 0.5116 [2021-03-25 23:41:56 swin_small_patch4_window7_224] INFO: Epoch: [111] [1050/1251] eta: 0:01:42 lr: 0.000698 loss: 3.6561 (3.4658) grad_norm: 1.1668 (inf) time: 0.5065 [2021-03-25 23:42:01 swin_small_patch4_window7_224] INFO: Epoch: [111] [1060/1251] eta: 0:01:37 lr: 0.000698 loss: 3.6384 (3.4677) grad_norm: 1.1515 (inf) time: 0.4961 [2021-03-25 23:42:06 swin_small_patch4_window7_224] INFO: Epoch: [111] [1070/1251] eta: 0:01:32 lr: 0.000698 loss: 3.5293 (3.4639) grad_norm: 1.1423 (inf) time: 0.5041 [2021-03-25 23:42:11 swin_small_patch4_window7_224] INFO: Epoch: [111] [1080/1251] eta: 0:01:27 lr: 0.000697 loss: 3.4973 (3.4650) grad_norm: 1.1474 (inf) time: 0.5045 [2021-03-25 23:42:16 swin_small_patch4_window7_224] INFO: Epoch: [111] [1090/1251] eta: 0:01:22 lr: 0.000697 loss: 3.6075 (3.4647) grad_norm: 1.2045 (inf) time: 0.5005 [2021-03-25 23:42:21 swin_small_patch4_window7_224] INFO: Epoch: [111] [1100/1251] eta: 0:01:16 lr: 0.000697 loss: 3.2667 (3.4607) grad_norm: 1.1646 (inf) time: 0.4992 [2021-03-25 23:42:26 swin_small_patch4_window7_224] INFO: Epoch: [111] [1110/1251] eta: 0:01:11 lr: 0.000697 loss: 3.1230 (3.4580) grad_norm: 1.1822 (inf) time: 0.4997 [2021-03-25 23:42:31 swin_small_patch4_window7_224] INFO: Epoch: [111] [1120/1251] eta: 0:01:06 lr: 0.000697 loss: 3.3221 (3.4574) grad_norm: 1.1870 (inf) time: 0.5035 [2021-03-25 23:42:36 swin_small_patch4_window7_224] INFO: Epoch: [111] [1130/1251] eta: 0:01:01 lr: 0.000697 loss: 3.5814 (3.4589) grad_norm: 1.2146 (inf) time: 0.5064 [2021-03-25 23:42:41 swin_small_patch4_window7_224] INFO: Epoch: [111] [1140/1251] eta: 0:00:56 lr: 0.000697 loss: 3.5396 (3.4580) grad_norm: 1.2055 (inf) time: 0.5025 [2021-03-25 23:42:46 swin_small_patch4_window7_224] INFO: Epoch: [111] [1150/1251] eta: 0:00:51 lr: 0.000697 loss: 3.3186 (3.4571) grad_norm: 1.1660 (inf) time: 0.4928 [2021-03-25 23:42:51 swin_small_patch4_window7_224] INFO: Epoch: [111] [1160/1251] eta: 0:00:46 lr: 0.000697 loss: 3.4994 (3.4574) grad_norm: 1.1687 (inf) time: 0.4963 [2021-03-25 23:42:56 swin_small_patch4_window7_224] INFO: Epoch: [111] [1170/1251] eta: 0:00:41 lr: 0.000697 loss: 3.5719 (3.4580) grad_norm: 1.1885 (inf) time: 0.5023 [2021-03-25 23:43:01 swin_small_patch4_window7_224] INFO: Epoch: [111] [1180/1251] eta: 0:00:36 lr: 0.000697 loss: 3.6769 (3.4603) grad_norm: 1.1527 (inf) time: 0.5005 [2021-03-25 23:43:06 swin_small_patch4_window7_224] INFO: Epoch: [111] [1190/1251] eta: 0:00:31 lr: 0.000697 loss: 3.6769 (3.4613) grad_norm: 1.2776 (inf) time: 0.4995 [2021-03-25 23:43:11 swin_small_patch4_window7_224] INFO: Epoch: [111] [1200/1251] eta: 0:00:25 lr: 0.000697 loss: 3.7497 (3.4652) grad_norm: 1.2560 (inf) time: 0.5012 [2021-03-25 23:43:16 swin_small_patch4_window7_224] INFO: Epoch: [111] [1210/1251] eta: 0:00:20 lr: 0.000697 loss: 3.7788 (3.4642) grad_norm: 1.1793 (inf) time: 0.5016 [2021-03-25 23:43:21 swin_small_patch4_window7_224] INFO: Epoch: [111] [1220/1251] eta: 0:00:15 lr: 0.000697 loss: 3.7788 (3.4662) grad_norm: 1.1760 (inf) time: 0.4984 [2021-03-25 23:43:26 swin_small_patch4_window7_224] INFO: Epoch: [111] [1230/1251] eta: 0:00:10 lr: 0.000697 loss: 3.5550 (3.4666) grad_norm: 1.2257 (inf) time: 0.4990 [2021-03-25 23:43:31 swin_small_patch4_window7_224] INFO: Epoch: [111] [1240/1251] eta: 0:00:05 lr: 0.000697 loss: 3.3965 (3.4641) grad_norm: 1.1790 (inf) time: 0.5051 [2021-03-25 23:43:36 swin_small_patch4_window7_224] INFO: Epoch: [111] [1250/1251] eta: 0:00:00 lr: 0.000697 loss: 3.0056 (3.4626) grad_norm: 1.1790 (inf) time: 0.5062 [2021-03-25 23:43:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 1.0274 (1.0274) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-25 23:43:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8835 (0.9083) acc1: 76.5625 (77.6989) acc5: 95.3125 (95.3125) [2021-03-25 23:43:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9765 (1.0025) acc1: 76.5625 (76.4881) acc5: 92.1875 (93.6012) [2021-03-25 23:43:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9957 (0.9981) acc1: 75.0000 (76.2601) acc5: 92.1875 (93.7500) [2021-03-25 23:43:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9410 (0.9935) acc1: 76.5625 (76.4101) acc5: 93.7500 (93.8262) [2021-03-25 23:43:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9410 (0.9895) acc1: 77.3585 (76.4480) acc5: 93.7500 (93.7280) [2021-03-25 23:43:59 swin_small_patch4_window7_224] INFO: * Acc@1 76.682 Acc@5 93.708 loss 0.984 [2021-03-25 23:43:59 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.7% [2021-03-25 23:43:59 swin_small_patch4_window7_224] INFO: Max accuracy: 76.71% [2021-03-25 23:44:04 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 0/1251] eta: 1:28:28 lr: 0.000697 loss: 3.6049 (3.6049) grad_norm: 1.1289 (1.1289) time: 4.2437 [2021-03-25 23:44:09 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 10/1251] eta: 0:17:48 lr: 0.000697 loss: 3.6049 (3.4684) grad_norm: 1.1700 (1.1922) time: 0.8606 [2021-03-25 23:44:14 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 20/1251] eta: 0:14:07 lr: 0.000697 loss: 3.7900 (3.5027) grad_norm: 1.1835 (1.1938) time: 0.5111 [2021-03-25 23:44:19 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 30/1251] eta: 0:12:52 lr: 0.000697 loss: 3.5501 (3.4475) grad_norm: 1.1752 (1.1866) time: 0.5076 [2021-03-25 23:44:24 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 40/1251] eta: 0:12:13 lr: 0.000697 loss: 3.5065 (3.4500) grad_norm: 1.1782 (1.2066) time: 0.5182 [2021-03-25 23:44:29 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 50/1251] eta: 0:11:42 lr: 0.000697 loss: 3.4202 (3.4222) grad_norm: 1.2326 (1.2152) time: 0.5102 [2021-03-25 23:44:34 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 60/1251] eta: 0:11:21 lr: 0.000697 loss: 3.5001 (3.4351) grad_norm: 1.1754 (1.2100) time: 0.5026 [2021-03-25 23:44:39 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 70/1251] eta: 0:11:04 lr: 0.000697 loss: 3.5112 (3.4498) grad_norm: 1.2010 (1.2197) time: 0.5056 [2021-03-25 23:44:44 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 80/1251] eta: 0:10:52 lr: 0.000697 loss: 3.5112 (3.4547) grad_norm: 1.2180 (1.2204) time: 0.5139 [2021-03-25 23:44:50 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 90/1251] eta: 0:10:41 lr: 0.000696 loss: 3.5672 (3.4477) grad_norm: 1.2436 (1.2256) time: 0.5159 [2021-03-25 23:44:55 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 100/1251] eta: 0:10:30 lr: 0.000696 loss: 3.5678 (3.4587) grad_norm: 1.2424 (1.2235) time: 0.5068 [2021-03-25 23:45:00 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 110/1251] eta: 0:10:20 lr: 0.000696 loss: 3.5917 (3.4448) grad_norm: 1.2424 (1.2299) time: 0.5052 [2021-03-25 23:45:05 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 120/1251] eta: 0:10:11 lr: 0.000696 loss: 3.1830 (3.4293) grad_norm: 1.1887 (1.2226) time: 0.5039 [2021-03-25 23:45:10 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 130/1251] eta: 0:10:03 lr: 0.000696 loss: 3.4722 (3.4245) grad_norm: 1.1497 (1.2203) time: 0.5085 [2021-03-25 23:45:15 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 140/1251] eta: 0:09:55 lr: 0.000696 loss: 3.6959 (3.4351) grad_norm: 1.1751 (1.2209) time: 0.5114 [2021-03-25 23:45:20 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 150/1251] eta: 0:09:47 lr: 0.000696 loss: 3.6858 (3.4469) grad_norm: 1.1269 (1.2154) time: 0.5029 [2021-03-25 23:45:25 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 160/1251] eta: 0:09:40 lr: 0.000696 loss: 3.6858 (3.4533) grad_norm: 1.1131 (1.2094) time: 0.4998 [2021-03-25 23:45:30 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 170/1251] eta: 0:09:32 lr: 0.000696 loss: 3.7500 (3.4695) grad_norm: 1.1547 (1.2101) time: 0.5014 [2021-03-25 23:45:35 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 180/1251] eta: 0:09:26 lr: 0.000696 loss: 3.3709 (3.4503) grad_norm: 1.1762 (1.2090) time: 0.5061 [2021-03-25 23:45:40 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 190/1251] eta: 0:09:19 lr: 0.000696 loss: 3.2431 (3.4509) grad_norm: 1.1762 (1.2115) time: 0.5031 [2021-03-25 23:45:45 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 200/1251] eta: 0:09:13 lr: 0.000696 loss: 3.4408 (3.4480) grad_norm: 1.2165 (1.2118) time: 0.5067 [2021-03-25 23:45:50 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 210/1251] eta: 0:09:07 lr: 0.000696 loss: 3.3863 (3.4421) grad_norm: 1.2165 (1.2122) time: 0.5117 [2021-03-25 23:45:55 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 220/1251] eta: 0:09:01 lr: 0.000696 loss: 3.3254 (3.4412) grad_norm: 1.2310 (1.2147) time: 0.5057 [2021-03-25 23:46:00 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 230/1251] eta: 0:08:54 lr: 0.000696 loss: 3.3254 (3.4333) grad_norm: 1.2253 (1.2151) time: 0.5013 [2021-03-25 23:46:05 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 240/1251] eta: 0:08:48 lr: 0.000696 loss: 3.1849 (3.4326) grad_norm: 1.1824 (1.2154) time: 0.4985 [2021-03-25 23:46:10 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 250/1251] eta: 0:08:42 lr: 0.000696 loss: 3.2342 (3.4266) grad_norm: 1.1463 (1.2125) time: 0.5015 [2021-03-25 23:46:15 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 260/1251] eta: 0:08:36 lr: 0.000696 loss: 3.1918 (3.4207) grad_norm: 1.1155 (1.2103) time: 0.5001 [2021-03-25 23:46:20 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 270/1251] eta: 0:08:30 lr: 0.000696 loss: 3.3376 (3.4265) grad_norm: 1.1158 (1.2076) time: 0.5008 [2021-03-25 23:46:25 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 280/1251] eta: 0:08:24 lr: 0.000696 loss: 3.4106 (3.4226) grad_norm: 1.1459 (1.2060) time: 0.5057 [2021-03-25 23:46:30 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 290/1251] eta: 0:08:18 lr: 0.000696 loss: 3.7459 (3.4290) grad_norm: 1.1601 (1.2070) time: 0.5044 [2021-03-25 23:46:35 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 300/1251] eta: 0:08:13 lr: 0.000696 loss: 3.6059 (3.4274) grad_norm: 1.2058 (1.2076) time: 0.5038 [2021-03-25 23:46:41 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 310/1251] eta: 0:08:07 lr: 0.000696 loss: 3.6059 (3.4347) grad_norm: 1.1829 (1.2079) time: 0.5067 [2021-03-25 23:46:46 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 320/1251] eta: 0:08:02 lr: 0.000696 loss: 3.3893 (3.4246) grad_norm: 1.2039 (1.2097) time: 0.5076 [2021-03-25 23:46:51 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 330/1251] eta: 0:07:56 lr: 0.000696 loss: 3.1652 (3.4270) grad_norm: 1.2533 (1.2111) time: 0.5047 [2021-03-25 23:46:56 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 340/1251] eta: 0:07:51 lr: 0.000696 loss: 3.5727 (3.4226) grad_norm: 1.2083 (1.2109) time: 0.5013 [2021-03-25 23:47:01 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 350/1251] eta: 0:07:45 lr: 0.000695 loss: 3.5421 (3.4234) grad_norm: 1.2063 (1.2122) time: 0.5041 [2021-03-25 23:47:06 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 360/1251] eta: 0:07:39 lr: 0.000695 loss: 3.5337 (3.4251) grad_norm: 1.2068 (1.2122) time: 0.5023 [2021-03-25 23:47:11 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 370/1251] eta: 0:07:34 lr: 0.000695 loss: 3.5140 (3.4267) grad_norm: 1.1691 (1.2113) time: 0.4991 [2021-03-25 23:47:16 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 380/1251] eta: 0:07:28 lr: 0.000695 loss: 3.5281 (3.4305) grad_norm: 1.1664 (1.2113) time: 0.5025 [2021-03-25 23:47:21 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 390/1251] eta: 0:07:23 lr: 0.000695 loss: 3.5980 (3.4342) grad_norm: 1.1894 (1.2112) time: 0.5036 [2021-03-25 23:47:26 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 400/1251] eta: 0:07:18 lr: 0.000695 loss: 3.6054 (3.4395) grad_norm: 1.1697 (1.2104) time: 0.5058 [2021-03-25 23:47:31 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 410/1251] eta: 0:07:12 lr: 0.000695 loss: 3.5745 (3.4340) grad_norm: 1.1564 (1.2093) time: 0.5059 [2021-03-25 23:47:36 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 420/1251] eta: 0:07:07 lr: 0.000695 loss: 3.4942 (3.4379) grad_norm: 1.1654 (1.2088) time: 0.5073 [2021-03-25 23:47:41 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 430/1251] eta: 0:07:02 lr: 0.000695 loss: 3.7188 (3.4399) grad_norm: 1.1793 (1.2096) time: 0.5049 [2021-03-25 23:47:46 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 440/1251] eta: 0:06:56 lr: 0.000695 loss: 3.5342 (3.4425) grad_norm: 1.2325 (1.2109) time: 0.5000 [2021-03-25 23:47:51 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 450/1251] eta: 0:06:51 lr: 0.000695 loss: 3.5060 (3.4433) grad_norm: 1.2283 (1.2109) time: 0.5065 [2021-03-25 23:47:56 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 460/1251] eta: 0:06:46 lr: 0.000695 loss: 3.3687 (3.4408) grad_norm: 1.1880 (1.2106) time: 0.5048 [2021-03-25 23:48:01 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 470/1251] eta: 0:06:40 lr: 0.000695 loss: 3.4744 (3.4424) grad_norm: 1.2486 (1.2124) time: 0.4990 [2021-03-25 23:48:06 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 480/1251] eta: 0:06:35 lr: 0.000695 loss: 3.4578 (3.4391) grad_norm: 1.1979 (1.2125) time: 0.5029 [2021-03-25 23:48:11 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 490/1251] eta: 0:06:30 lr: 0.000695 loss: 3.3924 (3.4395) grad_norm: 1.1979 (1.2135) time: 0.5066 [2021-03-25 23:48:16 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 500/1251] eta: 0:06:25 lr: 0.000695 loss: 3.6149 (3.4418) grad_norm: 1.1909 (1.2137) time: 0.5071 [2021-03-25 23:48:21 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 510/1251] eta: 0:06:19 lr: 0.000695 loss: 3.6390 (3.4476) grad_norm: 1.1694 (1.2133) time: 0.5035 [2021-03-25 23:48:26 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 520/1251] eta: 0:06:14 lr: 0.000695 loss: 3.6222 (3.4472) grad_norm: 1.1553 (1.2138) time: 0.5019 [2021-03-25 23:48:31 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 530/1251] eta: 0:06:09 lr: 0.000695 loss: 3.6709 (3.4517) grad_norm: 1.1553 (1.2142) time: 0.5019 [2021-03-25 23:48:36 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 540/1251] eta: 0:06:04 lr: 0.000695 loss: 3.6428 (3.4537) grad_norm: 1.2349 (1.2148) time: 0.5044 [2021-03-25 23:48:42 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 550/1251] eta: 0:05:59 lr: 0.000695 loss: 3.6341 (3.4534) grad_norm: 1.2349 (1.2162) time: 0.5165 [2021-03-25 23:48:47 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 560/1251] eta: 0:05:54 lr: 0.000695 loss: 3.4773 (3.4506) grad_norm: 1.2218 (1.2167) time: 0.5160 [2021-03-25 23:48:52 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 570/1251] eta: 0:05:48 lr: 0.000695 loss: 3.5184 (3.4524) grad_norm: 1.1913 (1.2158) time: 0.5083 [2021-03-25 23:48:57 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 580/1251] eta: 0:05:43 lr: 0.000695 loss: 3.5184 (3.4492) grad_norm: 1.1692 (1.2153) time: 0.5027 [2021-03-25 23:49:02 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 590/1251] eta: 0:05:38 lr: 0.000695 loss: 3.3582 (3.4441) grad_norm: 1.1992 (1.2158) time: 0.5105 [2021-03-25 23:49:07 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 600/1251] eta: 0:05:33 lr: 0.000695 loss: 3.3497 (3.4452) grad_norm: 1.1619 (1.2151) time: 0.5196 [2021-03-25 23:49:12 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 610/1251] eta: 0:05:28 lr: 0.000694 loss: 3.3918 (3.4481) grad_norm: 1.1642 (1.2155) time: 0.5099 [2021-03-25 23:49:17 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 620/1251] eta: 0:05:23 lr: 0.000694 loss: 3.3422 (3.4416) grad_norm: 1.1733 (1.2149) time: 0.5021 [2021-03-25 23:49:22 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 630/1251] eta: 0:05:17 lr: 0.000694 loss: 3.2251 (3.4396) grad_norm: 1.1761 (1.2150) time: 0.5041 [2021-03-25 23:49:28 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 640/1251] eta: 0:05:12 lr: 0.000694 loss: 3.4196 (3.4406) grad_norm: 1.2030 (1.2150) time: 0.5115 [2021-03-25 23:49:32 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 650/1251] eta: 0:05:07 lr: 0.000694 loss: 3.5482 (3.4406) grad_norm: 1.1561 (1.2142) time: 0.5046 [2021-03-25 23:49:38 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 660/1251] eta: 0:05:02 lr: 0.000694 loss: 3.5325 (3.4418) grad_norm: 1.1717 (1.2157) time: 0.4992 [2021-03-25 23:49:43 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 670/1251] eta: 0:04:57 lr: 0.000694 loss: 3.4194 (3.4382) grad_norm: 1.2777 (1.2167) time: 0.5114 [2021-03-25 23:49:48 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 680/1251] eta: 0:04:52 lr: 0.000694 loss: 3.4194 (3.4376) grad_norm: 1.2594 (1.2182) time: 0.5082 [2021-03-25 23:49:53 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 690/1251] eta: 0:04:46 lr: 0.000694 loss: 3.5481 (3.4389) grad_norm: 1.2593 (1.2181) time: 0.4986 [2021-03-25 23:49:58 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 700/1251] eta: 0:04:41 lr: 0.000694 loss: 3.6607 (3.4420) grad_norm: 1.2236 (1.2189) time: 0.4983 [2021-03-25 23:50:03 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 710/1251] eta: 0:04:36 lr: 0.000694 loss: 3.6484 (3.4421) grad_norm: 1.1965 (1.2186) time: 0.4995 [2021-03-25 23:50:08 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 720/1251] eta: 0:04:31 lr: 0.000694 loss: 3.6042 (3.4433) grad_norm: 1.1469 (1.2183) time: 0.5030 [2021-03-25 23:50:13 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 730/1251] eta: 0:04:26 lr: 0.000694 loss: 3.4976 (3.4436) grad_norm: 1.1699 (1.2191) time: 0.5061 [2021-03-25 23:50:18 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 740/1251] eta: 0:04:21 lr: 0.000694 loss: 3.4225 (3.4416) grad_norm: 1.1900 (1.2190) time: 0.5236 [2021-03-25 23:50:24 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 750/1251] eta: 0:04:16 lr: 0.000694 loss: 3.3800 (3.4400) grad_norm: 1.1965 (1.2194) time: 0.5364 [2021-03-25 23:50:29 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 760/1251] eta: 0:04:11 lr: 0.000694 loss: 3.6088 (3.4419) grad_norm: 1.2597 (1.2203) time: 0.5221 [2021-03-25 23:50:34 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 770/1251] eta: 0:04:06 lr: 0.000694 loss: 3.4552 (3.4432) grad_norm: 1.1556 (1.2193) time: 0.5117 [2021-03-25 23:50:39 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 780/1251] eta: 0:04:00 lr: 0.000694 loss: 3.4284 (3.4430) grad_norm: 1.1556 (1.2188) time: 0.5132 [2021-03-25 23:50:44 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 790/1251] eta: 0:03:55 lr: 0.000694 loss: 3.3505 (3.4424) grad_norm: 1.1925 (1.2192) time: 0.5098 [2021-03-25 23:50:49 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 800/1251] eta: 0:03:50 lr: 0.000694 loss: 3.3480 (3.4424) grad_norm: 1.2104 (1.2191) time: 0.5060 [2021-03-25 23:50:54 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 810/1251] eta: 0:03:45 lr: 0.000694 loss: 3.7486 (3.4447) grad_norm: 1.1820 (1.2185) time: 0.5071 [2021-03-25 23:50:59 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 820/1251] eta: 0:03:40 lr: 0.000694 loss: 3.7083 (3.4445) grad_norm: 1.1736 (1.2183) time: 0.5010 [2021-03-25 23:51:04 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 830/1251] eta: 0:03:35 lr: 0.000694 loss: 3.5570 (3.4447) grad_norm: 1.1617 (1.2178) time: 0.5021 [2021-03-25 23:51:09 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 840/1251] eta: 0:03:30 lr: 0.000694 loss: 3.6247 (3.4444) grad_norm: 1.1598 (1.2175) time: 0.5099 [2021-03-25 23:51:14 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 850/1251] eta: 0:03:24 lr: 0.000694 loss: 3.4690 (3.4437) grad_norm: 1.2256 (1.2183) time: 0.5043 [2021-03-25 23:51:19 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 860/1251] eta: 0:03:19 lr: 0.000694 loss: 3.4342 (3.4428) grad_norm: 1.2267 (1.2187) time: 0.5087 [2021-03-25 23:51:24 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 870/1251] eta: 0:03:14 lr: 0.000693 loss: 3.5580 (3.4439) grad_norm: 1.1927 (1.2180) time: 0.5078 [2021-03-25 23:51:30 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 880/1251] eta: 0:03:09 lr: 0.000693 loss: 3.5867 (3.4421) grad_norm: 1.1438 (1.2177) time: 0.5053 [2021-03-25 23:51:35 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 890/1251] eta: 0:03:04 lr: 0.000693 loss: 3.5867 (3.4423) grad_norm: 1.1646 (1.2177) time: 0.5082 [2021-03-25 23:51:40 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 900/1251] eta: 0:02:59 lr: 0.000693 loss: 3.5683 (3.4425) grad_norm: 1.1334 (1.2173) time: 0.5037 [2021-03-25 23:51:45 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 910/1251] eta: 0:02:54 lr: 0.000693 loss: 3.5430 (3.4427) grad_norm: 1.2231 (1.2182) time: 0.5013 [2021-03-25 23:51:50 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 920/1251] eta: 0:02:48 lr: 0.000693 loss: 3.4808 (3.4438) grad_norm: 1.2494 (1.2185) time: 0.5030 [2021-03-25 23:51:55 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 930/1251] eta: 0:02:43 lr: 0.000693 loss: 3.4808 (3.4434) grad_norm: 1.2363 (1.2193) time: 0.5072 [2021-03-25 23:52:00 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 940/1251] eta: 0:02:38 lr: 0.000693 loss: 3.4263 (3.4420) grad_norm: 1.2363 (1.2194) time: 0.5069 [2021-03-25 23:52:05 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 950/1251] eta: 0:02:33 lr: 0.000693 loss: 3.2079 (3.4401) grad_norm: 1.1747 (1.2192) time: 0.5010 [2021-03-25 23:52:10 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 960/1251] eta: 0:02:28 lr: 0.000693 loss: 3.5219 (3.4414) grad_norm: 1.1747 (1.2199) time: 0.5027 [2021-03-25 23:52:15 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 970/1251] eta: 0:02:23 lr: 0.000693 loss: 3.5924 (3.4424) grad_norm: 1.1865 (1.2199) time: 0.5079 [2021-03-25 23:52:20 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 980/1251] eta: 0:02:18 lr: 0.000693 loss: 3.5072 (3.4423) grad_norm: 1.1650 (1.2195) time: 0.5034 [2021-03-25 23:52:25 swin_small_patch4_window7_224] INFO: Epoch: [112] [ 990/1251] eta: 0:02:13 lr: 0.000693 loss: 3.5803 (3.4448) grad_norm: 1.2001 (1.2198) time: 0.5068 [2021-03-25 23:52:30 swin_small_patch4_window7_224] INFO: Epoch: [112] [1000/1251] eta: 0:02:08 lr: 0.000693 loss: 3.8316 (3.4477) grad_norm: 1.2420 (1.2200) time: 0.5068 [2021-03-25 23:52:35 swin_small_patch4_window7_224] INFO: Epoch: [112] [1010/1251] eta: 0:02:02 lr: 0.000693 loss: 3.5392 (3.4452) grad_norm: 1.2432 (1.2201) time: 0.5010 [2021-03-25 23:52:40 swin_small_patch4_window7_224] INFO: Epoch: [112] [1020/1251] eta: 0:01:57 lr: 0.000693 loss: 3.5815 (3.4495) grad_norm: 1.2285 (1.2201) time: 0.5088 [2021-03-25 23:52:45 swin_small_patch4_window7_224] INFO: Epoch: [112] [1030/1251] eta: 0:01:52 lr: 0.000693 loss: 3.7636 (3.4479) grad_norm: 1.1862 (1.2198) time: 0.5118 [2021-03-25 23:52:50 swin_small_patch4_window7_224] INFO: Epoch: [112] [1040/1251] eta: 0:01:47 lr: 0.000693 loss: 3.2640 (3.4464) grad_norm: 1.1989 (1.2200) time: 0.5114 [2021-03-25 23:52:56 swin_small_patch4_window7_224] INFO: Epoch: [112] [1050/1251] eta: 0:01:42 lr: 0.000693 loss: 3.2015 (3.4441) grad_norm: 1.2201 (1.2203) time: 0.5081 [2021-03-25 23:53:01 swin_small_patch4_window7_224] INFO: Epoch: [112] [1060/1251] eta: 0:01:37 lr: 0.000693 loss: 3.3244 (3.4441) grad_norm: 1.2745 (1.2213) time: 0.5006 [2021-03-25 23:53:06 swin_small_patch4_window7_224] INFO: Epoch: [112] [1070/1251] eta: 0:01:32 lr: 0.000693 loss: 3.5752 (3.4455) grad_norm: 1.2869 (1.2212) time: 0.5018 [2021-03-25 23:53:11 swin_small_patch4_window7_224] INFO: Epoch: [112] [1080/1251] eta: 0:01:27 lr: 0.000693 loss: 3.7327 (3.4481) grad_norm: 1.2062 (1.2214) time: 0.5060 [2021-03-25 23:53:16 swin_small_patch4_window7_224] INFO: Epoch: [112] [1090/1251] eta: 0:01:22 lr: 0.000693 loss: 3.6409 (3.4464) grad_norm: 1.2062 (1.2214) time: 0.5096 [2021-03-25 23:53:21 swin_small_patch4_window7_224] INFO: Epoch: [112] [1100/1251] eta: 0:01:16 lr: 0.000693 loss: 3.2101 (3.4431) grad_norm: 1.1821 (1.2210) time: 0.5036 [2021-03-25 23:53:26 swin_small_patch4_window7_224] INFO: Epoch: [112] [1110/1251] eta: 0:01:11 lr: 0.000693 loss: 3.1240 (3.4397) grad_norm: 1.1605 (1.2202) time: 0.5003 [2021-03-25 23:53:31 swin_small_patch4_window7_224] INFO: Epoch: [112] [1120/1251] eta: 0:01:06 lr: 0.000693 loss: 3.0801 (3.4390) grad_norm: 1.1724 (1.2203) time: 0.5026 [2021-03-25 23:53:36 swin_small_patch4_window7_224] INFO: Epoch: [112] [1130/1251] eta: 0:01:01 lr: 0.000692 loss: 3.4942 (3.4399) grad_norm: 1.1759 (1.2200) time: 0.5025 [2021-03-25 23:53:41 swin_small_patch4_window7_224] INFO: Epoch: [112] [1140/1251] eta: 0:00:56 lr: 0.000692 loss: 3.5789 (3.4384) grad_norm: 1.1392 (1.2196) time: 0.5036 [2021-03-25 23:53:46 swin_small_patch4_window7_224] INFO: Epoch: [112] [1150/1251] eta: 0:00:51 lr: 0.000692 loss: 3.1278 (3.4359) grad_norm: 1.1523 (1.2190) time: 0.5012 [2021-03-25 23:53:51 swin_small_patch4_window7_224] INFO: Epoch: [112] [1160/1251] eta: 0:00:46 lr: 0.000692 loss: 3.3157 (3.4355) grad_norm: 1.1699 (1.2188) time: 0.5047 [2021-03-25 23:53:56 swin_small_patch4_window7_224] INFO: Epoch: [112] [1170/1251] eta: 0:00:41 lr: 0.000692 loss: 3.6651 (3.4354) grad_norm: 1.1708 (1.2193) time: 0.5093 [2021-03-25 23:54:01 swin_small_patch4_window7_224] INFO: Epoch: [112] [1180/1251] eta: 0:00:36 lr: 0.000692 loss: 3.6822 (3.4357) grad_norm: 1.1833 (1.2194) time: 0.5045 [2021-03-25 23:54:06 swin_small_patch4_window7_224] INFO: Epoch: [112] [1190/1251] eta: 0:00:31 lr: 0.000692 loss: 3.2429 (3.4344) grad_norm: 1.1783 (1.2190) time: 0.4977 [2021-03-25 23:54:11 swin_small_patch4_window7_224] INFO: Epoch: [112] [1200/1251] eta: 0:00:25 lr: 0.000692 loss: 3.6785 (3.4367) grad_norm: 1.1780 (1.2190) time: 0.4949 [2021-03-25 23:54:16 swin_small_patch4_window7_224] INFO: Epoch: [112] [1210/1251] eta: 0:00:20 lr: 0.000692 loss: 3.6322 (3.4370) grad_norm: 1.2175 (1.2194) time: 0.5021 [2021-03-25 23:54:21 swin_small_patch4_window7_224] INFO: Epoch: [112] [1220/1251] eta: 0:00:15 lr: 0.000692 loss: 3.3355 (3.4345) grad_norm: 1.2229 (1.2199) time: 0.5041 [2021-03-25 23:54:26 swin_small_patch4_window7_224] INFO: Epoch: [112] [1230/1251] eta: 0:00:10 lr: 0.000692 loss: 3.4809 (3.4355) grad_norm: 1.2581 (1.2206) time: 0.5011 [2021-03-25 23:54:31 swin_small_patch4_window7_224] INFO: Epoch: [112] [1240/1251] eta: 0:00:05 lr: 0.000692 loss: 3.6454 (3.4349) grad_norm: 1.2581 (1.2209) time: 0.5012 [2021-03-25 23:54:36 swin_small_patch4_window7_224] INFO: Epoch: [112] [1250/1251] eta: 0:00:00 lr: 0.000692 loss: 3.6454 (3.4346) grad_norm: 1.1859 (1.2206) time: 0.4977 [2021-03-25 23:54:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:55 loss: 1.0644 (1.0644) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.1875) [2021-03-25 23:54:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8879 (0.9274) acc1: 76.5625 (77.1307) acc5: 93.7500 (93.8920) [2021-03-25 23:54:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9694 (0.9814) acc1: 75.0000 (75.8185) acc5: 95.3125 (93.9732) [2021-03-25 23:54:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9771 (0.9691) acc1: 75.0000 (76.7641) acc5: 93.7500 (94.0524) [2021-03-25 23:54:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0049 (0.9979) acc1: 75.0000 (76.3720) acc5: 93.7500 (93.8262) [2021-03-25 23:54:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0410 (1.0143) acc1: 75.0000 (76.0960) acc5: 93.7500 (93.5040) [2021-03-25 23:55:00 swin_small_patch4_window7_224] INFO: * Acc@1 76.702 Acc@5 93.698 loss 0.995 [2021-03-25 23:55:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.7% [2021-03-25 23:55:00 swin_small_patch4_window7_224] INFO: Max accuracy: 76.71% [2021-03-25 23:55:04 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 0/1251] eta: 1:26:18 lr: 0.000692 loss: 2.8656 (2.8656) grad_norm: 1.1596 (1.1596) time: 4.1391 [2021-03-25 23:55:09 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 10/1251] eta: 0:17:43 lr: 0.000692 loss: 3.7672 (3.5665) grad_norm: 1.1596 (1.1987) time: 0.8572 [2021-03-25 23:55:15 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 20/1251] eta: 0:14:12 lr: 0.000692 loss: 3.3890 (3.3496) grad_norm: 1.1709 (1.2022) time: 0.5204 [2021-03-25 23:55:20 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 30/1251] eta: 0:12:55 lr: 0.000692 loss: 3.3386 (3.3605) grad_norm: 1.2220 (1.2186) time: 0.5124 [2021-03-25 23:55:25 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 40/1251] eta: 0:12:09 lr: 0.000692 loss: 3.5084 (3.3726) grad_norm: 1.1662 (1.2049) time: 0.5079 [2021-03-25 23:55:30 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 50/1251] eta: 0:11:41 lr: 0.000692 loss: 3.2423 (3.3568) grad_norm: 1.2136 (1.2052) time: 0.5056 [2021-03-25 23:55:35 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 60/1251] eta: 0:11:19 lr: 0.000692 loss: 3.2779 (3.3902) grad_norm: 1.1606 (1.1993) time: 0.5042 [2021-03-25 23:55:40 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 70/1251] eta: 0:11:04 lr: 0.000692 loss: 3.6917 (3.4294) grad_norm: 1.1567 (1.2039) time: 0.5073 [2021-03-25 23:55:45 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 80/1251] eta: 0:10:50 lr: 0.000692 loss: 3.7012 (3.4356) grad_norm: 1.1571 (1.2014) time: 0.5110 [2021-03-25 23:55:50 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 90/1251] eta: 0:10:38 lr: 0.000692 loss: 3.6568 (3.4450) grad_norm: 1.1509 (1.1958) time: 0.5058 [2021-03-25 23:55:55 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 100/1251] eta: 0:10:27 lr: 0.000692 loss: 3.4188 (3.4224) grad_norm: 1.1474 (1.1949) time: 0.5044 [2021-03-25 23:56:00 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 110/1251] eta: 0:10:18 lr: 0.000692 loss: 3.3690 (3.4230) grad_norm: 1.1664 (1.1983) time: 0.5063 [2021-03-25 23:56:05 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 120/1251] eta: 0:10:09 lr: 0.000692 loss: 3.6541 (3.4295) grad_norm: 1.1664 (1.1982) time: 0.5037 [2021-03-25 23:56:10 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 130/1251] eta: 0:10:01 lr: 0.000692 loss: 3.6836 (3.4495) grad_norm: 1.1819 (1.1986) time: 0.5062 [2021-03-25 23:56:15 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 140/1251] eta: 0:09:53 lr: 0.000691 loss: 3.6224 (3.4445) grad_norm: 1.1822 (1.2000) time: 0.5091 [2021-03-25 23:56:21 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 150/1251] eta: 0:09:47 lr: 0.000691 loss: 3.6147 (3.4452) grad_norm: 1.2349 (1.2021) time: 0.5110 [2021-03-25 23:56:26 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 160/1251] eta: 0:09:39 lr: 0.000691 loss: 3.4904 (3.4359) grad_norm: 1.1932 (1.2003) time: 0.5118 [2021-03-25 23:56:31 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 170/1251] eta: 0:09:32 lr: 0.000691 loss: 3.3538 (3.4307) grad_norm: 1.1761 (1.1984) time: 0.5025 [2021-03-25 23:56:36 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 180/1251] eta: 0:09:26 lr: 0.000691 loss: 3.5924 (3.4329) grad_norm: 1.2011 (1.2008) time: 0.5079 [2021-03-25 23:56:41 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 190/1251] eta: 0:09:20 lr: 0.000691 loss: 3.3215 (3.4307) grad_norm: 1.2392 (1.2019) time: 0.5131 [2021-03-25 23:56:46 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 200/1251] eta: 0:09:14 lr: 0.000691 loss: 3.5892 (3.4346) grad_norm: 1.2215 (1.2016) time: 0.5157 [2021-03-25 23:56:51 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 210/1251] eta: 0:09:08 lr: 0.000691 loss: 3.6021 (3.4345) grad_norm: 1.2349 (1.2041) time: 0.5157 [2021-03-25 23:56:56 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 220/1251] eta: 0:09:02 lr: 0.000691 loss: 3.5549 (3.4321) grad_norm: 1.2544 (1.2088) time: 0.5075 [2021-03-25 23:57:01 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 230/1251] eta: 0:08:55 lr: 0.000691 loss: 3.4940 (3.4283) grad_norm: 1.2855 (1.2124) time: 0.5040 [2021-03-25 23:57:06 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 240/1251] eta: 0:08:49 lr: 0.000691 loss: 3.4940 (3.4294) grad_norm: 1.2311 (1.2145) time: 0.5026 [2021-03-25 23:57:11 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 250/1251] eta: 0:08:43 lr: 0.000691 loss: 3.3620 (3.4243) grad_norm: 1.2406 (1.2185) time: 0.5067 [2021-03-25 23:57:16 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 260/1251] eta: 0:08:37 lr: 0.000691 loss: 3.4157 (3.4283) grad_norm: 1.2034 (1.2189) time: 0.5035 [2021-03-25 23:57:21 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 270/1251] eta: 0:08:31 lr: 0.000691 loss: 3.2855 (3.4203) grad_norm: 1.2034 (1.2192) time: 0.5031 [2021-03-25 23:57:26 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 280/1251] eta: 0:08:25 lr: 0.000691 loss: 3.2783 (3.4142) grad_norm: 1.2292 (1.2211) time: 0.5028 [2021-03-25 23:57:31 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 290/1251] eta: 0:08:19 lr: 0.000691 loss: 3.3889 (3.4205) grad_norm: 1.2142 (1.2197) time: 0.4976 [2021-03-25 23:57:37 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 300/1251] eta: 0:08:14 lr: 0.000691 loss: 3.7089 (3.4283) grad_norm: 1.1353 (1.2175) time: 0.5055 [2021-03-25 23:57:42 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 310/1251] eta: 0:08:08 lr: 0.000691 loss: 3.4536 (3.4244) grad_norm: 1.1353 (1.2207) time: 0.5098 [2021-03-25 23:57:47 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 320/1251] eta: 0:08:03 lr: 0.000691 loss: 3.4536 (3.4223) grad_norm: 1.2550 (1.2218) time: 0.5084 [2021-03-25 23:57:52 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 330/1251] eta: 0:07:57 lr: 0.000691 loss: 3.6075 (3.4250) grad_norm: 1.2528 (1.2231) time: 0.5029 [2021-03-25 23:57:57 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 340/1251] eta: 0:07:52 lr: 0.000691 loss: 3.5866 (3.4291) grad_norm: 1.2131 (1.2227) time: 0.5049 [2021-03-25 23:58:02 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 350/1251] eta: 0:07:46 lr: 0.000691 loss: 3.5866 (3.4344) grad_norm: 1.1769 (1.2219) time: 0.5074 [2021-03-25 23:58:07 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 360/1251] eta: 0:07:41 lr: 0.000691 loss: 3.6814 (3.4406) grad_norm: 1.1857 (1.2218) time: 0.5028 [2021-03-25 23:58:12 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 370/1251] eta: 0:07:35 lr: 0.000691 loss: 3.5609 (3.4371) grad_norm: 1.1857 (1.2214) time: 0.5006 [2021-03-25 23:58:17 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 380/1251] eta: 0:07:29 lr: 0.000691 loss: 3.5351 (3.4409) grad_norm: 1.2068 (1.2226) time: 0.4986 [2021-03-25 23:58:22 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 390/1251] eta: 0:07:24 lr: 0.000691 loss: 3.6701 (3.4453) grad_norm: 1.2578 (1.2242) time: 0.5041 [2021-03-25 23:58:27 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 400/1251] eta: 0:07:19 lr: 0.000690 loss: 3.6149 (3.4452) grad_norm: 1.2578 (1.2246) time: 0.5086 [2021-03-25 23:58:32 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 410/1251] eta: 0:07:13 lr: 0.000690 loss: 3.3453 (3.4418) grad_norm: 1.1970 (1.2241) time: 0.5045 [2021-03-25 23:58:37 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 420/1251] eta: 0:07:08 lr: 0.000690 loss: 3.1865 (3.4377) grad_norm: 1.1755 (1.2242) time: 0.5044 [2021-03-25 23:58:42 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 430/1251] eta: 0:07:03 lr: 0.000690 loss: 3.3453 (3.4395) grad_norm: 1.1686 (1.2230) time: 0.5055 [2021-03-25 23:58:47 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 440/1251] eta: 0:06:57 lr: 0.000690 loss: 3.3453 (3.4380) grad_norm: 1.2004 (1.2227) time: 0.5020 [2021-03-25 23:58:52 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 450/1251] eta: 0:06:52 lr: 0.000690 loss: 3.3553 (3.4380) grad_norm: 1.2004 (1.2217) time: 0.5033 [2021-03-25 23:58:57 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 460/1251] eta: 0:06:46 lr: 0.000690 loss: 3.4072 (3.4349) grad_norm: 1.1424 (1.2200) time: 0.5032 [2021-03-25 23:59:02 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 470/1251] eta: 0:06:41 lr: 0.000690 loss: 3.5033 (3.4395) grad_norm: 1.1447 (1.2197) time: 0.5057 [2021-03-25 23:59:07 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 480/1251] eta: 0:06:36 lr: 0.000690 loss: 3.4974 (3.4377) grad_norm: 1.2255 (1.2195) time: 0.5101 [2021-03-25 23:59:12 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 490/1251] eta: 0:06:31 lr: 0.000690 loss: 3.4825 (3.4395) grad_norm: 1.1844 (1.2188) time: 0.5031 [2021-03-25 23:59:17 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 500/1251] eta: 0:06:25 lr: 0.000690 loss: 3.4247 (3.4425) grad_norm: 1.1663 (1.2180) time: 0.4973 [2021-03-25 23:59:22 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 510/1251] eta: 0:06:20 lr: 0.000690 loss: 3.4326 (3.4352) grad_norm: 1.1663 (1.2182) time: 0.5014 [2021-03-25 23:59:27 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 520/1251] eta: 0:06:15 lr: 0.000690 loss: 3.4489 (3.4387) grad_norm: 1.2032 (1.2182) time: 0.4994 [2021-03-25 23:59:32 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 530/1251] eta: 0:06:09 lr: 0.000690 loss: 3.5029 (3.4391) grad_norm: 1.2032 (1.2185) time: 0.4985 [2021-03-25 23:59:38 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 540/1251] eta: 0:06:04 lr: 0.000690 loss: 3.4154 (3.4388) grad_norm: 1.2144 (1.2182) time: 0.5084 [2021-03-25 23:59:43 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 550/1251] eta: 0:05:59 lr: 0.000690 loss: 3.5391 (3.4424) grad_norm: 1.1776 (1.2182) time: 0.5211 [2021-03-25 23:59:48 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 560/1251] eta: 0:05:54 lr: 0.000690 loss: 3.5660 (3.4419) grad_norm: 1.1844 (1.2183) time: 0.5123 [2021-03-25 23:59:53 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 570/1251] eta: 0:05:49 lr: 0.000690 loss: 3.3103 (3.4389) grad_norm: 1.2325 (1.2194) time: 0.5037 [2021-03-25 23:59:58 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 580/1251] eta: 0:05:43 lr: 0.000690 loss: 3.2352 (3.4369) grad_norm: 1.2690 (1.2205) time: 0.5055 [2021-03-26 00:00:03 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 590/1251] eta: 0:05:38 lr: 0.000690 loss: 3.3180 (3.4389) grad_norm: 1.1982 (1.2200) time: 0.4991 [2021-03-26 00:00:08 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 600/1251] eta: 0:05:33 lr: 0.000690 loss: 3.4721 (3.4360) grad_norm: 1.1965 (1.2201) time: 0.5008 [2021-03-26 00:00:13 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 610/1251] eta: 0:05:28 lr: 0.000690 loss: 3.2796 (3.4328) grad_norm: 1.1965 (1.2208) time: 0.5065 [2021-03-26 00:00:18 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 620/1251] eta: 0:05:23 lr: 0.000690 loss: 3.3477 (3.4323) grad_norm: 1.1303 (1.2190) time: 0.5048 [2021-03-26 00:00:23 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 630/1251] eta: 0:05:17 lr: 0.000690 loss: 3.3906 (3.4306) grad_norm: 1.1320 (1.2189) time: 0.5070 [2021-03-26 00:00:28 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 640/1251] eta: 0:05:12 lr: 0.000690 loss: 3.4474 (3.4305) grad_norm: 1.2520 (1.2202) time: 0.5094 [2021-03-26 00:00:33 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 650/1251] eta: 0:05:07 lr: 0.000690 loss: 3.4552 (3.4289) grad_norm: 1.2520 (1.2202) time: 0.5046 [2021-03-26 00:00:38 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 660/1251] eta: 0:05:02 lr: 0.000689 loss: 3.4556 (3.4271) grad_norm: 1.1840 (1.2207) time: 0.5020 [2021-03-26 00:00:43 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 670/1251] eta: 0:04:57 lr: 0.000689 loss: 3.4556 (3.4271) grad_norm: 1.2033 (1.2207) time: 0.5084 [2021-03-26 00:00:48 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 680/1251] eta: 0:04:52 lr: 0.000689 loss: 3.4476 (3.4251) grad_norm: 1.1812 (1.2200) time: 0.5096 [2021-03-26 00:00:53 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 690/1251] eta: 0:04:46 lr: 0.000689 loss: 3.4505 (3.4271) grad_norm: 1.2083 (1.2219) time: 0.5020 [2021-03-26 00:00:59 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 700/1251] eta: 0:04:41 lr: 0.000689 loss: 3.5758 (3.4267) grad_norm: 1.2505 (1.2219) time: 0.5039 [2021-03-26 00:01:04 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 710/1251] eta: 0:04:36 lr: 0.000689 loss: 3.5525 (3.4259) grad_norm: 1.1626 (1.2215) time: 0.5023 [2021-03-26 00:01:09 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 720/1251] eta: 0:04:31 lr: 0.000689 loss: 3.3114 (3.4250) grad_norm: 1.1882 (1.2212) time: 0.5006 [2021-03-26 00:01:14 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 730/1251] eta: 0:04:26 lr: 0.000689 loss: 3.4524 (3.4275) grad_norm: 1.1966 (1.2219) time: 0.5133 [2021-03-26 00:01:19 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 740/1251] eta: 0:04:21 lr: 0.000689 loss: 3.5798 (3.4294) grad_norm: 1.2457 (1.2222) time: 0.5255 [2021-03-26 00:01:24 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 750/1251] eta: 0:04:16 lr: 0.000689 loss: 3.5194 (3.4280) grad_norm: 1.1631 (1.2214) time: 0.5150 [2021-03-26 00:01:29 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 760/1251] eta: 0:04:11 lr: 0.000689 loss: 3.2873 (3.4279) grad_norm: 1.1615 (1.2211) time: 0.5098 [2021-03-26 00:01:34 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 770/1251] eta: 0:04:05 lr: 0.000689 loss: 3.7299 (3.4326) grad_norm: 1.2019 (1.2216) time: 0.5111 [2021-03-26 00:01:39 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 780/1251] eta: 0:04:00 lr: 0.000689 loss: 3.5763 (3.4303) grad_norm: 1.1848 (1.2217) time: 0.5036 [2021-03-26 00:01:44 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 790/1251] eta: 0:03:55 lr: 0.000689 loss: 3.2862 (3.4316) grad_norm: 1.1613 (1.2216) time: 0.5023 [2021-03-26 00:01:49 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 800/1251] eta: 0:03:50 lr: 0.000689 loss: 3.4835 (3.4338) grad_norm: 1.1613 (1.2209) time: 0.5023 [2021-03-26 00:01:54 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 810/1251] eta: 0:03:45 lr: 0.000689 loss: 3.4835 (3.4335) grad_norm: 1.1929 (1.2216) time: 0.5022 [2021-03-26 00:01:59 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 820/1251] eta: 0:03:40 lr: 0.000689 loss: 3.3774 (3.4341) grad_norm: 1.2246 (1.2208) time: 0.4982 [2021-03-26 00:02:04 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 830/1251] eta: 0:03:34 lr: 0.000689 loss: 3.4793 (3.4334) grad_norm: 1.2216 (1.2211) time: 0.5018 [2021-03-26 00:02:09 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 840/1251] eta: 0:03:29 lr: 0.000689 loss: 3.4793 (3.4315) grad_norm: 1.2216 (1.2207) time: 0.5033 [2021-03-26 00:02:15 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 850/1251] eta: 0:03:24 lr: 0.000689 loss: 3.1559 (3.4289) grad_norm: 1.1751 (1.2206) time: 0.5056 [2021-03-26 00:02:20 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 860/1251] eta: 0:03:19 lr: 0.000689 loss: 3.1722 (3.4297) grad_norm: 1.1993 (1.2205) time: 0.5089 [2021-03-26 00:02:25 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 870/1251] eta: 0:03:14 lr: 0.000689 loss: 3.6266 (3.4318) grad_norm: 1.1642 (1.2200) time: 0.5072 [2021-03-26 00:02:30 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 880/1251] eta: 0:03:09 lr: 0.000689 loss: 3.5083 (3.4289) grad_norm: 1.1618 (1.2199) time: 0.5082 [2021-03-26 00:02:35 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 890/1251] eta: 0:03:04 lr: 0.000689 loss: 3.0920 (3.4277) grad_norm: 1.2038 (1.2203) time: 0.5078 [2021-03-26 00:02:40 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 900/1251] eta: 0:02:59 lr: 0.000689 loss: 3.6092 (3.4298) grad_norm: 1.2041 (1.2203) time: 0.5091 [2021-03-26 00:02:45 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 910/1251] eta: 0:02:53 lr: 0.000689 loss: 3.5546 (3.4288) grad_norm: 1.1777 (1.2199) time: 0.5049 [2021-03-26 00:02:50 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 920/1251] eta: 0:02:48 lr: 0.000688 loss: 3.5352 (3.4300) grad_norm: 1.2158 (1.2205) time: 0.4998 [2021-03-26 00:02:55 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 930/1251] eta: 0:02:43 lr: 0.000688 loss: 3.5676 (3.4306) grad_norm: 1.2419 (1.2205) time: 0.5082 [2021-03-26 00:03:00 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 940/1251] eta: 0:02:38 lr: 0.000688 loss: 3.4972 (3.4285) grad_norm: 1.1468 (1.2199) time: 0.5090 [2021-03-26 00:03:05 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 950/1251] eta: 0:02:33 lr: 0.000688 loss: 3.6169 (3.4299) grad_norm: 1.1615 (1.2198) time: 0.5122 [2021-03-26 00:03:10 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 960/1251] eta: 0:02:28 lr: 0.000688 loss: 3.4402 (3.4290) grad_norm: 1.2553 (1.2212) time: 0.5132 [2021-03-26 00:03:15 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 970/1251] eta: 0:02:23 lr: 0.000688 loss: 3.3695 (3.4265) grad_norm: 1.2426 (1.2207) time: 0.5024 [2021-03-26 00:03:20 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 980/1251] eta: 0:02:18 lr: 0.000688 loss: 3.2524 (3.4256) grad_norm: 1.1052 (1.2197) time: 0.5022 [2021-03-26 00:03:26 swin_small_patch4_window7_224] INFO: Epoch: [113] [ 990/1251] eta: 0:02:13 lr: 0.000688 loss: 3.6678 (3.4270) grad_norm: 1.1052 (1.2192) time: 0.5058 [2021-03-26 00:03:31 swin_small_patch4_window7_224] INFO: Epoch: [113] [1000/1251] eta: 0:02:08 lr: 0.000688 loss: 3.5446 (3.4245) grad_norm: 1.1735 (1.2188) time: 0.5085 [2021-03-26 00:03:36 swin_small_patch4_window7_224] INFO: Epoch: [113] [1010/1251] eta: 0:02:02 lr: 0.000688 loss: 3.5446 (3.4252) grad_norm: 1.1404 (1.2184) time: 0.5067 [2021-03-26 00:03:41 swin_small_patch4_window7_224] INFO: Epoch: [113] [1020/1251] eta: 0:01:57 lr: 0.000688 loss: 3.5821 (3.4251) grad_norm: 1.1710 (1.2190) time: 0.5029 [2021-03-26 00:03:46 swin_small_patch4_window7_224] INFO: Epoch: [113] [1030/1251] eta: 0:01:52 lr: 0.000688 loss: 3.3768 (3.4252) grad_norm: 1.1710 (1.2182) time: 0.5080 [2021-03-26 00:03:51 swin_small_patch4_window7_224] INFO: Epoch: [113] [1040/1251] eta: 0:01:47 lr: 0.000688 loss: 3.4354 (3.4233) grad_norm: 1.1131 (1.2180) time: 0.5147 [2021-03-26 00:03:56 swin_small_patch4_window7_224] INFO: Epoch: [113] [1050/1251] eta: 0:01:42 lr: 0.000688 loss: 3.1146 (3.4215) grad_norm: 1.1548 (1.2171) time: 0.5103 [2021-03-26 00:04:01 swin_small_patch4_window7_224] INFO: Epoch: [113] [1060/1251] eta: 0:01:37 lr: 0.000688 loss: 3.3823 (3.4213) grad_norm: 1.1602 (inf) time: 0.5006 [2021-03-26 00:04:06 swin_small_patch4_window7_224] INFO: Epoch: [113] [1070/1251] eta: 0:01:32 lr: 0.000688 loss: 3.5952 (3.4207) grad_norm: 1.1709 (inf) time: 0.5042 [2021-03-26 00:04:11 swin_small_patch4_window7_224] INFO: Epoch: [113] [1080/1251] eta: 0:01:27 lr: 0.000688 loss: 3.5214 (3.4220) grad_norm: 1.1966 (inf) time: 0.5208 [2021-03-26 00:04:17 swin_small_patch4_window7_224] INFO: Epoch: [113] [1090/1251] eta: 0:01:22 lr: 0.000688 loss: 3.5785 (3.4237) grad_norm: 1.1595 (inf) time: 0.5181 [2021-03-26 00:04:22 swin_small_patch4_window7_224] INFO: Epoch: [113] [1100/1251] eta: 0:01:17 lr: 0.000688 loss: 3.5483 (3.4254) grad_norm: 1.1738 (inf) time: 0.5100 [2021-03-26 00:04:27 swin_small_patch4_window7_224] INFO: Epoch: [113] [1110/1251] eta: 0:01:11 lr: 0.000688 loss: 3.4153 (3.4233) grad_norm: 1.2154 (inf) time: 0.5083 [2021-03-26 00:04:32 swin_small_patch4_window7_224] INFO: Epoch: [113] [1120/1251] eta: 0:01:06 lr: 0.000688 loss: 3.4153 (3.4244) grad_norm: 1.2476 (inf) time: 0.5095 [2021-03-26 00:04:37 swin_small_patch4_window7_224] INFO: Epoch: [113] [1130/1251] eta: 0:01:01 lr: 0.000688 loss: 3.3624 (3.4233) grad_norm: 1.2422 (inf) time: 0.5096 [2021-03-26 00:04:42 swin_small_patch4_window7_224] INFO: Epoch: [113] [1140/1251] eta: 0:00:56 lr: 0.000688 loss: 3.4549 (3.4253) grad_norm: 1.1903 (inf) time: 0.5097 [2021-03-26 00:04:47 swin_small_patch4_window7_224] INFO: Epoch: [113] [1150/1251] eta: 0:00:51 lr: 0.000688 loss: 3.5391 (3.4259) grad_norm: 1.2634 (inf) time: 0.5113 [2021-03-26 00:04:52 swin_small_patch4_window7_224] INFO: Epoch: [113] [1160/1251] eta: 0:00:46 lr: 0.000688 loss: 3.4385 (3.4264) grad_norm: 1.2072 (inf) time: 0.5080 [2021-03-26 00:04:57 swin_small_patch4_window7_224] INFO: Epoch: [113] [1170/1251] eta: 0:00:41 lr: 0.000688 loss: 3.3946 (3.4259) grad_norm: 1.1709 (inf) time: 0.5039 [2021-03-26 00:05:02 swin_small_patch4_window7_224] INFO: Epoch: [113] [1180/1251] eta: 0:00:36 lr: 0.000687 loss: 3.4423 (3.4256) grad_norm: 1.1851 (inf) time: 0.5021 [2021-03-26 00:05:07 swin_small_patch4_window7_224] INFO: Epoch: [113] [1190/1251] eta: 0:00:31 lr: 0.000687 loss: 3.4604 (3.4256) grad_norm: 1.2041 (inf) time: 0.5065 [2021-03-26 00:05:12 swin_small_patch4_window7_224] INFO: Epoch: [113] [1200/1251] eta: 0:00:25 lr: 0.000687 loss: 3.5748 (3.4279) grad_norm: 1.1822 (inf) time: 0.5075 [2021-03-26 00:05:17 swin_small_patch4_window7_224] INFO: Epoch: [113] [1210/1251] eta: 0:00:20 lr: 0.000687 loss: 3.7133 (3.4282) grad_norm: 1.1813 (inf) time: 0.5053 [2021-03-26 00:05:22 swin_small_patch4_window7_224] INFO: Epoch: [113] [1220/1251] eta: 0:00:15 lr: 0.000687 loss: 3.5614 (3.4283) grad_norm: 1.1813 (inf) time: 0.5038 [2021-03-26 00:05:28 swin_small_patch4_window7_224] INFO: Epoch: [113] [1230/1251] eta: 0:00:10 lr: 0.000687 loss: 3.4117 (3.4275) grad_norm: 1.1967 (inf) time: 0.5036 [2021-03-26 00:05:33 swin_small_patch4_window7_224] INFO: Epoch: [113] [1240/1251] eta: 0:00:05 lr: 0.000687 loss: 3.3857 (3.4274) grad_norm: 1.1854 (inf) time: 0.5074 [2021-03-26 00:05:38 swin_small_patch4_window7_224] INFO: Epoch: [113] [1250/1251] eta: 0:00:00 lr: 0.000687 loss: 3.3857 (3.4265) grad_norm: 1.2088 (inf) time: 0.5088 [2021-03-26 00:05:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 1.4090 (1.4090) acc1: 68.7500 (68.7500) acc5: 89.0625 (89.0625) [2021-03-26 00:05:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8825 (0.9490) acc1: 76.5625 (76.4205) acc5: 95.3125 (94.6023) [2021-03-26 00:05:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8837 (0.9636) acc1: 76.5625 (75.9673) acc5: 93.7500 (93.6756) [2021-03-26 00:05:50 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0058 (0.9721) acc1: 76.5625 (76.4113) acc5: 93.7500 (93.7500) [2021-03-26 00:05:51 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0117 (0.9792) acc1: 75.0000 (76.1814) acc5: 93.7500 (94.0549) [2021-03-26 00:05:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9734 (0.9756) acc1: 76.5625 (76.2880) acc5: 93.7500 (93.9840) [2021-03-26 00:06:00 swin_small_patch4_window7_224] INFO: * Acc@1 76.798 Acc@5 93.814 loss 0.970 [2021-03-26 00:06:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.8% [2021-03-26 00:06:00 swin_small_patch4_window7_224] INFO: Max accuracy: 76.80% [2021-03-26 00:06:04 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 0/1251] eta: 1:23:27 lr: 0.000687 loss: 4.1942 (4.1942) grad_norm: 1.1724 (1.1724) time: 4.0028 [2021-03-26 00:06:09 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 10/1251] eta: 0:17:50 lr: 0.000687 loss: 3.7329 (3.5754) grad_norm: 1.1724 (1.1625) time: 0.8625 [2021-03-26 00:06:14 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 20/1251] eta: 0:14:16 lr: 0.000687 loss: 3.6895 (3.5998) grad_norm: 1.1907 (1.1850) time: 0.5302 [2021-03-26 00:06:19 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 30/1251] eta: 0:12:54 lr: 0.000687 loss: 3.4825 (3.4840) grad_norm: 1.1919 (1.1901) time: 0.5084 [2021-03-26 00:06:25 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 40/1251] eta: 0:12:12 lr: 0.000687 loss: 3.0371 (3.4022) grad_norm: 1.2335 (1.2006) time: 0.5105 [2021-03-26 00:06:30 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 50/1251] eta: 0:11:46 lr: 0.000687 loss: 2.9124 (3.3725) grad_norm: 1.2057 (1.2022) time: 0.5171 [2021-03-26 00:06:35 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 60/1251] eta: 0:11:23 lr: 0.000687 loss: 3.4554 (3.3938) grad_norm: 1.2057 (1.2085) time: 0.5099 [2021-03-26 00:06:40 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 70/1251] eta: 0:11:04 lr: 0.000687 loss: 3.5639 (3.3900) grad_norm: 1.2011 (1.2076) time: 0.4981 [2021-03-26 00:06:45 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 80/1251] eta: 0:10:51 lr: 0.000687 loss: 3.7455 (3.3969) grad_norm: 1.2011 (1.2099) time: 0.5022 [2021-03-26 00:06:50 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 90/1251] eta: 0:10:40 lr: 0.000687 loss: 3.6782 (3.3892) grad_norm: 1.2077 (1.2093) time: 0.5110 [2021-03-26 00:06:55 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 100/1251] eta: 0:10:29 lr: 0.000687 loss: 3.5453 (3.3995) grad_norm: 1.1848 (1.2119) time: 0.5101 [2021-03-26 00:07:00 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 110/1251] eta: 0:10:20 lr: 0.000687 loss: 3.5731 (3.4144) grad_norm: 1.1918 (1.2282) time: 0.5071 [2021-03-26 00:07:05 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 120/1251] eta: 0:10:11 lr: 0.000687 loss: 3.7143 (3.4320) grad_norm: 1.2748 (1.2317) time: 0.5064 [2021-03-26 00:07:10 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 130/1251] eta: 0:10:03 lr: 0.000687 loss: 3.5540 (3.4405) grad_norm: 1.2776 (1.2365) time: 0.5102 [2021-03-26 00:07:15 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 140/1251] eta: 0:09:54 lr: 0.000687 loss: 3.5517 (3.4448) grad_norm: 1.3043 (1.2423) time: 0.5055 [2021-03-26 00:07:20 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 150/1251] eta: 0:09:47 lr: 0.000687 loss: 3.4823 (3.4506) grad_norm: 1.2924 (1.2408) time: 0.5023 [2021-03-26 00:07:25 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 160/1251] eta: 0:09:40 lr: 0.000687 loss: 3.5784 (3.4569) grad_norm: 1.1876 (1.2381) time: 0.5055 [2021-03-26 00:07:30 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 170/1251] eta: 0:09:32 lr: 0.000687 loss: 3.4966 (3.4498) grad_norm: 1.1647 (1.2330) time: 0.5035 [2021-03-26 00:07:35 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 180/1251] eta: 0:09:26 lr: 0.000687 loss: 3.4966 (3.4477) grad_norm: 1.1647 (1.2337) time: 0.5069 [2021-03-26 00:07:40 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 190/1251] eta: 0:09:19 lr: 0.000686 loss: 3.4330 (3.4467) grad_norm: 1.3024 (1.2450) time: 0.5046 [2021-03-26 00:07:46 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 200/1251] eta: 0:09:13 lr: 0.000686 loss: 3.4330 (3.4427) grad_norm: 1.2884 (1.2438) time: 0.5031 [2021-03-26 00:07:51 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 210/1251] eta: 0:09:06 lr: 0.000686 loss: 3.4830 (3.4348) grad_norm: 1.2676 (1.2471) time: 0.5065 [2021-03-26 00:07:56 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 220/1251] eta: 0:09:00 lr: 0.000686 loss: 3.4550 (3.4348) grad_norm: 1.2108 (1.2441) time: 0.5074 [2021-03-26 00:08:01 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 230/1251] eta: 0:08:55 lr: 0.000686 loss: 3.4550 (3.4362) grad_norm: 1.1820 (1.2423) time: 0.5124 [2021-03-26 00:08:06 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 240/1251] eta: 0:08:49 lr: 0.000686 loss: 3.5351 (3.4381) grad_norm: 1.1871 (1.2401) time: 0.5107 [2021-03-26 00:08:11 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 250/1251] eta: 0:08:43 lr: 0.000686 loss: 3.5667 (3.4383) grad_norm: 1.1871 (1.2388) time: 0.5058 [2021-03-26 00:08:16 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 260/1251] eta: 0:08:37 lr: 0.000686 loss: 3.4209 (3.4405) grad_norm: 1.2001 (1.2395) time: 0.5087 [2021-03-26 00:08:21 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 270/1251] eta: 0:08:31 lr: 0.000686 loss: 3.5659 (3.4472) grad_norm: 1.1968 (1.2372) time: 0.5081 [2021-03-26 00:08:26 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 280/1251] eta: 0:08:26 lr: 0.000686 loss: 3.5659 (3.4470) grad_norm: 1.1624 (1.2353) time: 0.5060 [2021-03-26 00:08:31 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 290/1251] eta: 0:08:20 lr: 0.000686 loss: 3.6662 (3.4533) grad_norm: 1.1790 (1.2340) time: 0.5069 [2021-03-26 00:08:36 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 300/1251] eta: 0:08:14 lr: 0.000686 loss: 3.5765 (3.4456) grad_norm: 1.1790 (1.2335) time: 0.5031 [2021-03-26 00:08:41 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 310/1251] eta: 0:08:09 lr: 0.000686 loss: 3.2905 (3.4430) grad_norm: 1.2025 (1.2338) time: 0.5060 [2021-03-26 00:08:47 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 320/1251] eta: 0:08:03 lr: 0.000686 loss: 3.4563 (3.4420) grad_norm: 1.1762 (1.2335) time: 0.5150 [2021-03-26 00:08:52 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 330/1251] eta: 0:07:58 lr: 0.000686 loss: 3.5846 (3.4428) grad_norm: 1.1807 (1.2333) time: 0.5101 [2021-03-26 00:08:57 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 340/1251] eta: 0:07:52 lr: 0.000686 loss: 3.2053 (3.4357) grad_norm: 1.1936 (1.2322) time: 0.4980 [2021-03-26 00:09:01 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 350/1251] eta: 0:07:46 lr: 0.000686 loss: 3.4561 (3.4402) grad_norm: 1.1984 (1.2318) time: 0.4948 [2021-03-26 00:09:07 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 360/1251] eta: 0:07:41 lr: 0.000686 loss: 3.5705 (3.4430) grad_norm: 1.2352 (1.2322) time: 0.5020 [2021-03-26 00:09:12 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 370/1251] eta: 0:07:35 lr: 0.000686 loss: 3.7935 (3.4427) grad_norm: 1.1872 (1.2313) time: 0.5027 [2021-03-26 00:09:17 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 380/1251] eta: 0:07:29 lr: 0.000686 loss: 3.6128 (3.4430) grad_norm: 1.1658 (1.2304) time: 0.4979 [2021-03-26 00:09:22 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 390/1251] eta: 0:07:24 lr: 0.000686 loss: 3.4066 (3.4412) grad_norm: 1.1879 (1.2302) time: 0.5041 [2021-03-26 00:09:27 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 400/1251] eta: 0:07:19 lr: 0.000686 loss: 3.6026 (3.4466) grad_norm: 1.1570 (1.2289) time: 0.5072 [2021-03-26 00:09:32 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 410/1251] eta: 0:07:13 lr: 0.000686 loss: 3.6547 (3.4418) grad_norm: 1.2302 (1.2297) time: 0.5031 [2021-03-26 00:09:37 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 420/1251] eta: 0:07:08 lr: 0.000686 loss: 3.2638 (3.4370) grad_norm: 1.2314 (1.2288) time: 0.5089 [2021-03-26 00:09:42 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 430/1251] eta: 0:07:03 lr: 0.000686 loss: 3.4181 (3.4396) grad_norm: 1.2314 (1.2297) time: 0.5135 [2021-03-26 00:09:47 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 440/1251] eta: 0:06:58 lr: 0.000686 loss: 3.4539 (3.4368) grad_norm: 1.2301 (1.2288) time: 0.5108 [2021-03-26 00:09:52 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 450/1251] eta: 0:06:52 lr: 0.000685 loss: 3.4746 (3.4374) grad_norm: 1.1703 (1.2275) time: 0.5106 [2021-03-26 00:09:57 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 460/1251] eta: 0:06:47 lr: 0.000685 loss: 3.5309 (3.4403) grad_norm: 1.1513 (1.2264) time: 0.5045 [2021-03-26 00:10:02 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 470/1251] eta: 0:06:42 lr: 0.000685 loss: 3.6344 (3.4462) grad_norm: 1.2132 (1.2267) time: 0.5008 [2021-03-26 00:10:07 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 480/1251] eta: 0:06:36 lr: 0.000685 loss: 3.4419 (3.4374) grad_norm: 1.2132 (1.2255) time: 0.5038 [2021-03-26 00:10:12 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 490/1251] eta: 0:06:31 lr: 0.000685 loss: 3.2145 (3.4370) grad_norm: 1.1497 (1.2239) time: 0.5087 [2021-03-26 00:10:17 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 500/1251] eta: 0:06:26 lr: 0.000685 loss: 3.2145 (3.4312) grad_norm: 1.2011 (1.2259) time: 0.5063 [2021-03-26 00:10:22 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 510/1251] eta: 0:06:20 lr: 0.000685 loss: 3.1060 (3.4308) grad_norm: 1.2571 (1.2251) time: 0.5040 [2021-03-26 00:10:28 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 520/1251] eta: 0:06:15 lr: 0.000685 loss: 3.3070 (3.4287) grad_norm: 1.1647 (1.2248) time: 0.5060 [2021-03-26 00:10:33 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 530/1251] eta: 0:06:10 lr: 0.000685 loss: 3.4927 (3.4281) grad_norm: 1.1552 (1.2232) time: 0.5107 [2021-03-26 00:10:38 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 540/1251] eta: 0:06:05 lr: 0.000685 loss: 3.1999 (3.4244) grad_norm: 1.1830 (1.2249) time: 0.5082 [2021-03-26 00:10:43 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 550/1251] eta: 0:06:00 lr: 0.000685 loss: 3.1792 (3.4201) grad_norm: 1.3122 (1.2263) time: 0.5091 [2021-03-26 00:10:48 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 560/1251] eta: 0:05:54 lr: 0.000685 loss: 3.4788 (3.4215) grad_norm: 1.2658 (1.2267) time: 0.5132 [2021-03-26 00:10:53 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 570/1251] eta: 0:05:49 lr: 0.000685 loss: 3.4373 (3.4163) grad_norm: 1.2093 (1.2263) time: 0.5058 [2021-03-26 00:10:58 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 580/1251] eta: 0:05:44 lr: 0.000685 loss: 3.3613 (3.4177) grad_norm: 1.1912 (1.2252) time: 0.5016 [2021-03-26 00:11:03 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 590/1251] eta: 0:05:39 lr: 0.000685 loss: 3.4138 (3.4109) grad_norm: 1.1927 (1.2257) time: 0.5060 [2021-03-26 00:11:08 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 600/1251] eta: 0:05:34 lr: 0.000685 loss: 3.4277 (3.4143) grad_norm: 1.2271 (1.2257) time: 0.5118 [2021-03-26 00:11:13 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 610/1251] eta: 0:05:28 lr: 0.000685 loss: 3.6444 (3.4151) grad_norm: 1.2589 (1.2275) time: 0.5055 [2021-03-26 00:11:18 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 620/1251] eta: 0:05:23 lr: 0.000685 loss: 3.7663 (3.4226) grad_norm: 1.2631 (1.2283) time: 0.5029 [2021-03-26 00:11:23 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 630/1251] eta: 0:05:18 lr: 0.000685 loss: 3.8361 (3.4270) grad_norm: 1.2196 (1.2271) time: 0.5050 [2021-03-26 00:11:28 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 640/1251] eta: 0:05:13 lr: 0.000685 loss: 3.7497 (3.4322) grad_norm: 1.1650 (1.2268) time: 0.5044 [2021-03-26 00:11:33 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 650/1251] eta: 0:05:07 lr: 0.000685 loss: 3.6070 (3.4303) grad_norm: 1.1833 (1.2270) time: 0.5015 [2021-03-26 00:11:38 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 660/1251] eta: 0:05:02 lr: 0.000685 loss: 3.5135 (3.4298) grad_norm: 1.1833 (1.2268) time: 0.4972 [2021-03-26 00:11:43 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 670/1251] eta: 0:04:57 lr: 0.000685 loss: 3.5749 (3.4317) grad_norm: 1.1775 (1.2273) time: 0.4969 [2021-03-26 00:11:48 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 680/1251] eta: 0:04:52 lr: 0.000685 loss: 3.5749 (3.4327) grad_norm: 1.1868 (1.2266) time: 0.5073 [2021-03-26 00:11:54 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 690/1251] eta: 0:04:47 lr: 0.000685 loss: 3.5464 (3.4342) grad_norm: 1.1868 (1.2263) time: 0.5114 [2021-03-26 00:11:59 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 700/1251] eta: 0:04:41 lr: 0.000685 loss: 3.4943 (3.4343) grad_norm: 1.1764 (1.2259) time: 0.5025 [2021-03-26 00:12:04 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 710/1251] eta: 0:04:36 lr: 0.000684 loss: 3.5452 (3.4362) grad_norm: 1.1884 (1.2258) time: 0.5036 [2021-03-26 00:12:09 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 720/1251] eta: 0:04:31 lr: 0.000684 loss: 3.5100 (3.4344) grad_norm: 1.1884 (1.2254) time: 0.5068 [2021-03-26 00:12:14 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 730/1251] eta: 0:04:26 lr: 0.000684 loss: 3.3222 (3.4341) grad_norm: 1.1910 (1.2257) time: 0.5182 [2021-03-26 00:12:19 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 740/1251] eta: 0:04:21 lr: 0.000684 loss: 3.2942 (3.4318) grad_norm: 1.2049 (1.2252) time: 0.5327 [2021-03-26 00:12:24 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 750/1251] eta: 0:04:16 lr: 0.000684 loss: 3.6277 (3.4346) grad_norm: 1.1664 (1.2251) time: 0.5233 [2021-03-26 00:12:30 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 760/1251] eta: 0:04:11 lr: 0.000684 loss: 3.6256 (3.4323) grad_norm: 1.2005 (1.2253) time: 0.5150 [2021-03-26 00:12:35 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 770/1251] eta: 0:04:06 lr: 0.000684 loss: 3.5481 (3.4340) grad_norm: 1.1945 (1.2245) time: 0.5062 [2021-03-26 00:12:40 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 780/1251] eta: 0:04:01 lr: 0.000684 loss: 3.2652 (3.4281) grad_norm: 1.1874 (1.2244) time: 0.4974 [2021-03-26 00:12:45 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 790/1251] eta: 0:03:55 lr: 0.000684 loss: 3.3207 (3.4292) grad_norm: 1.1874 (1.2239) time: 0.5066 [2021-03-26 00:12:50 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 800/1251] eta: 0:03:50 lr: 0.000684 loss: 3.6549 (3.4323) grad_norm: 1.1518 (1.2234) time: 0.5110 [2021-03-26 00:12:55 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 810/1251] eta: 0:03:45 lr: 0.000684 loss: 3.5597 (3.4316) grad_norm: 1.1929 (1.2237) time: 0.5061 [2021-03-26 00:13:00 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 820/1251] eta: 0:03:40 lr: 0.000684 loss: 3.2996 (3.4283) grad_norm: 1.1730 (1.2234) time: 0.5057 [2021-03-26 00:13:05 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 830/1251] eta: 0:03:35 lr: 0.000684 loss: 3.3348 (3.4301) grad_norm: 1.2135 (1.2238) time: 0.5086 [2021-03-26 00:13:10 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 840/1251] eta: 0:03:30 lr: 0.000684 loss: 3.6710 (3.4336) grad_norm: 1.2837 (1.2251) time: 0.5143 [2021-03-26 00:13:15 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 850/1251] eta: 0:03:25 lr: 0.000684 loss: 3.6960 (3.4339) grad_norm: 1.1987 (1.2245) time: 0.5101 [2021-03-26 00:13:20 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 860/1251] eta: 0:03:20 lr: 0.000684 loss: 3.7774 (3.4387) grad_norm: 1.1785 (1.2250) time: 0.5079 [2021-03-26 00:13:25 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 870/1251] eta: 0:03:14 lr: 0.000684 loss: 3.7745 (3.4395) grad_norm: 1.2695 (1.2266) time: 0.5090 [2021-03-26 00:13:30 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 880/1251] eta: 0:03:09 lr: 0.000684 loss: 3.4394 (3.4388) grad_norm: 1.2682 (1.2269) time: 0.5051 [2021-03-26 00:13:36 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 890/1251] eta: 0:03:04 lr: 0.000684 loss: 3.4868 (3.4386) grad_norm: 1.1832 (1.2262) time: 0.5091 [2021-03-26 00:13:41 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 900/1251] eta: 0:02:59 lr: 0.000684 loss: 3.5310 (3.4404) grad_norm: 1.1708 (1.2263) time: 0.5072 [2021-03-26 00:13:46 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 910/1251] eta: 0:02:54 lr: 0.000684 loss: 3.5016 (3.4380) grad_norm: 1.2226 (1.2271) time: 0.5009 [2021-03-26 00:13:51 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 920/1251] eta: 0:02:49 lr: 0.000684 loss: 3.3280 (3.4388) grad_norm: 1.2455 (1.2268) time: 0.5089 [2021-03-26 00:13:56 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 930/1251] eta: 0:02:44 lr: 0.000684 loss: 3.5980 (3.4412) grad_norm: 1.1836 (1.2262) time: 0.5151 [2021-03-26 00:14:01 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 940/1251] eta: 0:02:38 lr: 0.000684 loss: 3.5327 (3.4394) grad_norm: 1.1668 (1.2257) time: 0.5022 [2021-03-26 00:14:06 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 950/1251] eta: 0:02:33 lr: 0.000684 loss: 3.3667 (3.4398) grad_norm: 1.2103 (1.2258) time: 0.5008 [2021-03-26 00:14:11 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 960/1251] eta: 0:02:28 lr: 0.000684 loss: 3.3667 (3.4389) grad_norm: 1.2103 (1.2257) time: 0.5080 [2021-03-26 00:14:16 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 970/1251] eta: 0:02:23 lr: 0.000683 loss: 3.2741 (3.4387) grad_norm: 1.1749 (1.2257) time: 0.5072 [2021-03-26 00:14:21 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 980/1251] eta: 0:02:18 lr: 0.000683 loss: 3.5138 (3.4390) grad_norm: 1.1733 (1.2254) time: 0.5063 [2021-03-26 00:14:26 swin_small_patch4_window7_224] INFO: Epoch: [114] [ 990/1251] eta: 0:02:13 lr: 0.000683 loss: 3.5354 (3.4387) grad_norm: 1.2024 (1.2255) time: 0.5086 [2021-03-26 00:14:31 swin_small_patch4_window7_224] INFO: Epoch: [114] [1000/1251] eta: 0:02:08 lr: 0.000683 loss: 3.3036 (3.4355) grad_norm: 1.2437 (1.2256) time: 0.5147 [2021-03-26 00:14:36 swin_small_patch4_window7_224] INFO: Epoch: [114] [1010/1251] eta: 0:02:03 lr: 0.000683 loss: 3.3036 (3.4344) grad_norm: 1.2412 (1.2260) time: 0.5103 [2021-03-26 00:14:42 swin_small_patch4_window7_224] INFO: Epoch: [114] [1020/1251] eta: 0:01:58 lr: 0.000683 loss: 3.3268 (3.4317) grad_norm: 1.2240 (1.2258) time: 0.5076 [2021-03-26 00:14:47 swin_small_patch4_window7_224] INFO: Epoch: [114] [1030/1251] eta: 0:01:52 lr: 0.000683 loss: 3.3268 (3.4309) grad_norm: 1.1808 (1.2255) time: 0.5073 [2021-03-26 00:14:52 swin_small_patch4_window7_224] INFO: Epoch: [114] [1040/1251] eta: 0:01:47 lr: 0.000683 loss: 3.4131 (3.4298) grad_norm: 1.1497 (1.2249) time: 0.5011 [2021-03-26 00:14:57 swin_small_patch4_window7_224] INFO: Epoch: [114] [1050/1251] eta: 0:01:42 lr: 0.000683 loss: 3.4412 (3.4296) grad_norm: 1.1580 (1.2246) time: 0.5050 [2021-03-26 00:15:02 swin_small_patch4_window7_224] INFO: Epoch: [114] [1060/1251] eta: 0:01:37 lr: 0.000683 loss: 3.4857 (3.4299) grad_norm: 1.2218 (1.2247) time: 0.5078 [2021-03-26 00:15:07 swin_small_patch4_window7_224] INFO: Epoch: [114] [1070/1251] eta: 0:01:32 lr: 0.000683 loss: 3.5002 (3.4292) grad_norm: 1.2435 (1.2248) time: 0.5059 [2021-03-26 00:15:12 swin_small_patch4_window7_224] INFO: Epoch: [114] [1080/1251] eta: 0:01:27 lr: 0.000683 loss: 3.5153 (3.4289) grad_norm: 1.2435 (1.2247) time: 0.5047 [2021-03-26 00:15:17 swin_small_patch4_window7_224] INFO: Epoch: [114] [1090/1251] eta: 0:01:22 lr: 0.000683 loss: 3.2209 (3.4263) grad_norm: 1.2142 (1.2249) time: 0.5003 [2021-03-26 00:15:22 swin_small_patch4_window7_224] INFO: Epoch: [114] [1100/1251] eta: 0:01:17 lr: 0.000683 loss: 3.4385 (3.4288) grad_norm: 1.2350 (1.2252) time: 0.4998 [2021-03-26 00:15:27 swin_small_patch4_window7_224] INFO: Epoch: [114] [1110/1251] eta: 0:01:11 lr: 0.000683 loss: 3.6024 (3.4304) grad_norm: 1.1948 (1.2250) time: 0.5023 [2021-03-26 00:15:32 swin_small_patch4_window7_224] INFO: Epoch: [114] [1120/1251] eta: 0:01:06 lr: 0.000683 loss: 3.6024 (3.4309) grad_norm: 1.1223 (1.2241) time: 0.5049 [2021-03-26 00:15:37 swin_small_patch4_window7_224] INFO: Epoch: [114] [1130/1251] eta: 0:01:01 lr: 0.000683 loss: 3.3696 (3.4294) grad_norm: 1.1128 (1.2233) time: 0.5041 [2021-03-26 00:15:42 swin_small_patch4_window7_224] INFO: Epoch: [114] [1140/1251] eta: 0:00:56 lr: 0.000683 loss: 3.2321 (3.4272) grad_norm: 1.1709 (1.2232) time: 0.4990 [2021-03-26 00:15:47 swin_small_patch4_window7_224] INFO: Epoch: [114] [1150/1251] eta: 0:00:51 lr: 0.000683 loss: 3.4787 (3.4304) grad_norm: 1.2092 (1.2233) time: 0.4985 [2021-03-26 00:15:52 swin_small_patch4_window7_224] INFO: Epoch: [114] [1160/1251] eta: 0:00:46 lr: 0.000683 loss: 3.6336 (3.4305) grad_norm: 1.2205 (1.2230) time: 0.5028 [2021-03-26 00:15:57 swin_small_patch4_window7_224] INFO: Epoch: [114] [1170/1251] eta: 0:00:41 lr: 0.000683 loss: 3.4905 (3.4298) grad_norm: 1.1385 (1.2222) time: 0.5092 [2021-03-26 00:16:02 swin_small_patch4_window7_224] INFO: Epoch: [114] [1180/1251] eta: 0:00:36 lr: 0.000683 loss: 3.4004 (3.4295) grad_norm: 1.1605 (1.2219) time: 0.5076 [2021-03-26 00:16:07 swin_small_patch4_window7_224] INFO: Epoch: [114] [1190/1251] eta: 0:00:31 lr: 0.000683 loss: 3.2156 (3.4273) grad_norm: 1.1675 (1.2215) time: 0.5100 [2021-03-26 00:16:12 swin_small_patch4_window7_224] INFO: Epoch: [114] [1200/1251] eta: 0:00:26 lr: 0.000683 loss: 3.4713 (3.4294) grad_norm: 1.1608 (1.2209) time: 0.5090 [2021-03-26 00:16:17 swin_small_patch4_window7_224] INFO: Epoch: [114] [1210/1251] eta: 0:00:20 lr: 0.000683 loss: 3.2146 (3.4263) grad_norm: 1.1994 (1.2209) time: 0.5003 [2021-03-26 00:16:22 swin_small_patch4_window7_224] INFO: Epoch: [114] [1220/1251] eta: 0:00:15 lr: 0.000683 loss: 2.9848 (3.4251) grad_norm: 1.1801 (1.2203) time: 0.4994 [2021-03-26 00:16:27 swin_small_patch4_window7_224] INFO: Epoch: [114] [1230/1251] eta: 0:00:10 lr: 0.000682 loss: 3.4420 (3.4249) grad_norm: 1.1302 (1.2198) time: 0.5000 [2021-03-26 00:16:32 swin_small_patch4_window7_224] INFO: Epoch: [114] [1240/1251] eta: 0:00:05 lr: 0.000682 loss: 3.5963 (3.4261) grad_norm: 1.2019 (1.2202) time: 0.5034 [2021-03-26 00:16:37 swin_small_patch4_window7_224] INFO: Epoch: [114] [1250/1251] eta: 0:00:00 lr: 0.000682 loss: 3.4035 (3.4241) grad_norm: 1.2296 (1.2206) time: 0.5036 [2021-03-26 00:16:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:35 loss: 0.9146 (0.9146) acc1: 71.8750 (71.8750) acc5: 95.3125 (95.3125) [2021-03-26 00:16:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9146 (1.0013) acc1: 78.1250 (78.6932) acc5: 93.7500 (94.0341) [2021-03-26 00:16:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9720 (1.0064) acc1: 76.5625 (77.2321) acc5: 95.3125 (94.1964) [2021-03-26 00:16:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9242 (0.9683) acc1: 76.5625 (77.2177) acc5: 95.3125 (94.9597) [2021-03-26 00:16:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9114 (0.9832) acc1: 75.0000 (76.9436) acc5: 96.8750 (94.6646) [2021-03-26 00:16:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9702 (0.9999) acc1: 75.0000 (76.7360) acc5: 95.3125 (94.3360) [2021-03-26 00:17:00 swin_small_patch4_window7_224] INFO: * Acc@1 76.816 Acc@5 93.770 loss 0.996 [2021-03-26 00:17:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.8% [2021-03-26 00:17:00 swin_small_patch4_window7_224] INFO: Max accuracy: 76.82% [2021-03-26 00:17:04 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 0/1251] eta: 1:23:54 lr: 0.000682 loss: 3.8580 (3.8580) grad_norm: 1.2549 (1.2549) time: 4.0240 [2021-03-26 00:17:09 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 10/1251] eta: 0:17:10 lr: 0.000682 loss: 3.9142 (3.6967) grad_norm: 1.2029 (1.2131) time: 0.8305 [2021-03-26 00:17:14 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 20/1251] eta: 0:13:53 lr: 0.000682 loss: 3.5922 (3.5290) grad_norm: 1.1912 (1.2249) time: 0.5095 [2021-03-26 00:17:19 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 30/1251] eta: 0:12:39 lr: 0.000682 loss: 3.1949 (3.4367) grad_norm: 1.2280 (1.2422) time: 0.5074 [2021-03-26 00:17:25 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 40/1251] eta: 0:12:01 lr: 0.000682 loss: 3.2980 (3.4117) grad_norm: 1.2280 (1.2559) time: 0.5112 [2021-03-26 00:17:30 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 50/1251] eta: 0:11:34 lr: 0.000682 loss: 3.3453 (3.3978) grad_norm: 1.1921 (1.2621) time: 0.5104 [2021-03-26 00:17:35 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 60/1251] eta: 0:11:15 lr: 0.000682 loss: 3.4860 (3.4345) grad_norm: 1.2482 (1.2564) time: 0.5091 [2021-03-26 00:17:40 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 70/1251] eta: 0:10:59 lr: 0.000682 loss: 3.7026 (3.4715) grad_norm: 1.2265 (1.2515) time: 0.5068 [2021-03-26 00:17:45 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 80/1251] eta: 0:10:45 lr: 0.000682 loss: 3.4078 (3.4213) grad_norm: 1.1789 (1.2435) time: 0.5011 [2021-03-26 00:17:50 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 90/1251] eta: 0:10:33 lr: 0.000682 loss: 3.0172 (3.3807) grad_norm: 1.1789 (1.2432) time: 0.5026 [2021-03-26 00:17:55 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 100/1251] eta: 0:10:24 lr: 0.000682 loss: 3.2123 (3.4007) grad_norm: 1.1870 (1.2358) time: 0.5077 [2021-03-26 00:18:00 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 110/1251] eta: 0:10:16 lr: 0.000682 loss: 3.5791 (3.4165) grad_norm: 1.1652 (1.2332) time: 0.5123 [2021-03-26 00:18:05 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 120/1251] eta: 0:10:07 lr: 0.000682 loss: 3.5488 (3.4040) grad_norm: 1.2009 (1.2345) time: 0.5100 [2021-03-26 00:18:10 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 130/1251] eta: 0:10:01 lr: 0.000682 loss: 3.4119 (3.4157) grad_norm: 1.2020 (1.2347) time: 0.5165 [2021-03-26 00:18:15 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 140/1251] eta: 0:09:52 lr: 0.000682 loss: 3.3960 (3.3907) grad_norm: 1.2037 (1.2364) time: 0.5117 [2021-03-26 00:18:20 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 150/1251] eta: 0:09:44 lr: 0.000682 loss: 3.4422 (3.3919) grad_norm: 1.1865 (1.2322) time: 0.4972 [2021-03-26 00:18:25 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 160/1251] eta: 0:09:37 lr: 0.000682 loss: 3.5856 (3.3987) grad_norm: 1.1429 (1.2297) time: 0.4996 [2021-03-26 00:18:30 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 170/1251] eta: 0:09:30 lr: 0.000682 loss: 3.5165 (3.4026) grad_norm: 1.1761 (1.2292) time: 0.5046 [2021-03-26 00:18:36 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 180/1251] eta: 0:09:24 lr: 0.000682 loss: 3.6288 (3.4112) grad_norm: 1.2076 (1.2310) time: 0.5117 [2021-03-26 00:18:41 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 190/1251] eta: 0:09:19 lr: 0.000682 loss: 3.2373 (3.3950) grad_norm: 1.2304 (1.2298) time: 0.5209 [2021-03-26 00:18:46 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 200/1251] eta: 0:09:13 lr: 0.000682 loss: 3.1308 (3.3851) grad_norm: 1.1954 (1.2273) time: 0.5172 [2021-03-26 00:18:51 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 210/1251] eta: 0:09:07 lr: 0.000682 loss: 3.6152 (3.4054) grad_norm: 1.1798 (1.2257) time: 0.5109 [2021-03-26 00:18:56 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 220/1251] eta: 0:09:01 lr: 0.000682 loss: 3.6498 (3.4118) grad_norm: 1.1900 (1.2254) time: 0.5107 [2021-03-26 00:19:01 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 230/1251] eta: 0:08:54 lr: 0.000682 loss: 3.6172 (3.4257) grad_norm: 1.1880 (1.2235) time: 0.5031 [2021-03-26 00:19:06 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 240/1251] eta: 0:08:49 lr: 0.000681 loss: 3.6757 (3.4305) grad_norm: 1.1605 (1.2242) time: 0.5078 [2021-03-26 00:19:11 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 250/1251] eta: 0:08:43 lr: 0.000681 loss: 3.4300 (3.4280) grad_norm: 1.1744 (1.2225) time: 0.5104 [2021-03-26 00:19:16 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 260/1251] eta: 0:08:37 lr: 0.000681 loss: 3.6116 (3.4320) grad_norm: 1.1603 (1.2213) time: 0.5013 [2021-03-26 00:19:21 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 270/1251] eta: 0:08:31 lr: 0.000681 loss: 3.6199 (3.4299) grad_norm: 1.1250 (1.2191) time: 0.5009 [2021-03-26 00:19:26 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 280/1251] eta: 0:08:25 lr: 0.000681 loss: 3.2553 (3.4176) grad_norm: 1.1662 (1.2173) time: 0.5057 [2021-03-26 00:19:32 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 290/1251] eta: 0:08:19 lr: 0.000681 loss: 3.2524 (3.4195) grad_norm: 1.2297 (1.2177) time: 0.5089 [2021-03-26 00:19:37 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 300/1251] eta: 0:08:14 lr: 0.000681 loss: 3.2604 (3.4171) grad_norm: 1.2289 (1.2169) time: 0.5100 [2021-03-26 00:19:42 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 310/1251] eta: 0:08:08 lr: 0.000681 loss: 3.3491 (3.4128) grad_norm: 1.1499 (1.2172) time: 0.5080 [2021-03-26 00:19:47 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 320/1251] eta: 0:08:03 lr: 0.000681 loss: 3.3491 (3.4093) grad_norm: 1.1952 (1.2172) time: 0.5039 [2021-03-26 00:19:52 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 330/1251] eta: 0:07:57 lr: 0.000681 loss: 3.5419 (3.4193) grad_norm: 1.1952 (1.2174) time: 0.5005 [2021-03-26 00:19:57 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 340/1251] eta: 0:07:51 lr: 0.000681 loss: 3.7074 (3.4240) grad_norm: 1.1945 (1.2169) time: 0.5007 [2021-03-26 00:20:02 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 350/1251] eta: 0:07:46 lr: 0.000681 loss: 3.4782 (3.4227) grad_norm: 1.1626 (1.2166) time: 0.5034 [2021-03-26 00:20:07 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 360/1251] eta: 0:07:40 lr: 0.000681 loss: 3.5464 (3.4261) grad_norm: 1.2513 (1.2189) time: 0.5083 [2021-03-26 00:20:12 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 370/1251] eta: 0:07:35 lr: 0.000681 loss: 3.4705 (3.4227) grad_norm: 1.2968 (1.2221) time: 0.5059 [2021-03-26 00:20:17 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 380/1251] eta: 0:07:29 lr: 0.000681 loss: 3.1914 (3.4137) grad_norm: 1.2505 (1.2222) time: 0.5027 [2021-03-26 00:20:22 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 390/1251] eta: 0:07:24 lr: 0.000681 loss: 3.2169 (3.4130) grad_norm: 1.2031 (1.2220) time: 0.5043 [2021-03-26 00:20:27 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 400/1251] eta: 0:07:18 lr: 0.000681 loss: 3.3534 (3.4115) grad_norm: 1.1903 (1.2219) time: 0.4996 [2021-03-26 00:20:32 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 410/1251] eta: 0:07:13 lr: 0.000681 loss: 3.2966 (3.4086) grad_norm: 1.1757 (1.2220) time: 0.4975 [2021-03-26 00:20:37 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 420/1251] eta: 0:07:08 lr: 0.000681 loss: 3.3704 (3.4060) grad_norm: 1.1721 (1.2205) time: 0.5037 [2021-03-26 00:20:42 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 430/1251] eta: 0:07:02 lr: 0.000681 loss: 3.4824 (3.4068) grad_norm: 1.1804 (1.2213) time: 0.5128 [2021-03-26 00:20:47 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 440/1251] eta: 0:06:57 lr: 0.000681 loss: 3.6396 (3.4110) grad_norm: 1.2146 (1.2205) time: 0.5065 [2021-03-26 00:20:52 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 450/1251] eta: 0:06:52 lr: 0.000681 loss: 3.7185 (3.4140) grad_norm: 1.1999 (1.2203) time: 0.5002 [2021-03-26 00:20:57 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 460/1251] eta: 0:06:46 lr: 0.000681 loss: 3.3214 (3.4094) grad_norm: 1.1784 (1.2187) time: 0.5043 [2021-03-26 00:21:02 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 470/1251] eta: 0:06:41 lr: 0.000681 loss: 3.2813 (3.4072) grad_norm: 1.1630 (1.2187) time: 0.5044 [2021-03-26 00:21:07 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 480/1251] eta: 0:06:36 lr: 0.000681 loss: 3.2954 (3.4064) grad_norm: 1.2016 (1.2188) time: 0.5050 [2021-03-26 00:21:12 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 490/1251] eta: 0:06:30 lr: 0.000680 loss: 3.3956 (3.4082) grad_norm: 1.2164 (1.2195) time: 0.5041 [2021-03-26 00:21:18 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 500/1251] eta: 0:06:25 lr: 0.000680 loss: 3.4862 (3.4113) grad_norm: 1.2294 (1.2205) time: 0.5087 [2021-03-26 00:21:23 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 510/1251] eta: 0:06:20 lr: 0.000680 loss: 3.6705 (3.4122) grad_norm: 1.1810 (1.2202) time: 0.5127 [2021-03-26 00:21:28 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 520/1251] eta: 0:06:15 lr: 0.000680 loss: 3.6790 (3.4187) grad_norm: 1.2097 (1.2211) time: 0.5041 [2021-03-26 00:21:33 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 530/1251] eta: 0:06:10 lr: 0.000680 loss: 3.4970 (3.4171) grad_norm: 1.1931 (1.2197) time: 0.5062 [2021-03-26 00:21:38 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 540/1251] eta: 0:06:04 lr: 0.000680 loss: 3.4104 (3.4198) grad_norm: 1.1360 (1.2208) time: 0.5115 [2021-03-26 00:21:43 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 550/1251] eta: 0:05:59 lr: 0.000680 loss: 3.6787 (3.4187) grad_norm: 1.2499 (1.2214) time: 0.5156 [2021-03-26 00:21:48 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 560/1251] eta: 0:05:54 lr: 0.000680 loss: 3.3641 (3.4169) grad_norm: 1.2513 (1.2228) time: 0.5113 [2021-03-26 00:21:53 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 570/1251] eta: 0:05:49 lr: 0.000680 loss: 3.4029 (3.4184) grad_norm: 1.2347 (1.2227) time: 0.5016 [2021-03-26 00:21:58 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 580/1251] eta: 0:05:44 lr: 0.000680 loss: 3.4804 (3.4165) grad_norm: 1.2084 (1.2228) time: 0.5033 [2021-03-26 00:22:03 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 590/1251] eta: 0:05:39 lr: 0.000680 loss: 3.2773 (3.4172) grad_norm: 1.2029 (1.2227) time: 0.5125 [2021-03-26 00:22:08 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 600/1251] eta: 0:05:33 lr: 0.000680 loss: 3.4858 (3.4162) grad_norm: 1.2009 (1.2222) time: 0.5142 [2021-03-26 00:22:14 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 610/1251] eta: 0:05:28 lr: 0.000680 loss: 3.4858 (3.4123) grad_norm: 1.1325 (1.2210) time: 0.5115 [2021-03-26 00:22:19 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 620/1251] eta: 0:05:23 lr: 0.000680 loss: 3.4748 (3.4137) grad_norm: 1.1452 (1.2207) time: 0.5089 [2021-03-26 00:22:24 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 630/1251] eta: 0:05:18 lr: 0.000680 loss: 3.5962 (3.4136) grad_norm: 1.1537 (1.2205) time: 0.5030 [2021-03-26 00:22:29 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 640/1251] eta: 0:05:13 lr: 0.000680 loss: 3.4802 (3.4139) grad_norm: 1.2563 (1.2217) time: 0.5015 [2021-03-26 00:22:34 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 650/1251] eta: 0:05:07 lr: 0.000680 loss: 3.1803 (3.4108) grad_norm: 1.2502 (1.2226) time: 0.5023 [2021-03-26 00:22:39 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 660/1251] eta: 0:05:02 lr: 0.000680 loss: 3.3066 (3.4098) grad_norm: 1.2341 (1.2224) time: 0.4995 [2021-03-26 00:22:44 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 670/1251] eta: 0:04:57 lr: 0.000680 loss: 3.5434 (3.4094) grad_norm: 1.2294 (1.2226) time: 0.4971 [2021-03-26 00:22:49 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 680/1251] eta: 0:04:52 lr: 0.000680 loss: 3.6639 (3.4148) grad_norm: 1.1931 (1.2226) time: 0.5002 [2021-03-26 00:22:54 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 690/1251] eta: 0:04:47 lr: 0.000680 loss: 3.7391 (3.4159) grad_norm: 1.2563 (1.2241) time: 0.5035 [2021-03-26 00:22:59 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 700/1251] eta: 0:04:41 lr: 0.000680 loss: 3.6948 (3.4202) grad_norm: 1.2434 (1.2240) time: 0.5035 [2021-03-26 00:23:04 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 710/1251] eta: 0:04:36 lr: 0.000680 loss: 3.6160 (3.4203) grad_norm: 1.2104 (1.2250) time: 0.4995 [2021-03-26 00:23:09 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 720/1251] eta: 0:04:31 lr: 0.000680 loss: 3.5082 (3.4192) grad_norm: 1.2450 (1.2263) time: 0.5017 [2021-03-26 00:23:14 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 730/1251] eta: 0:04:26 lr: 0.000680 loss: 3.3993 (3.4205) grad_norm: 1.2213 (1.2259) time: 0.5117 [2021-03-26 00:23:19 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 740/1251] eta: 0:04:21 lr: 0.000680 loss: 3.5795 (3.4224) grad_norm: 1.1730 (1.2255) time: 0.5239 [2021-03-26 00:23:24 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 750/1251] eta: 0:04:16 lr: 0.000679 loss: 3.6872 (3.4239) grad_norm: 1.1588 (1.2249) time: 0.5207 [2021-03-26 00:23:29 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 760/1251] eta: 0:04:11 lr: 0.000679 loss: 3.6810 (3.4261) grad_norm: 1.2269 (1.2254) time: 0.5063 [2021-03-26 00:23:34 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 770/1251] eta: 0:04:05 lr: 0.000679 loss: 3.5974 (3.4268) grad_norm: 1.2282 (1.2256) time: 0.5028 [2021-03-26 00:23:39 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 780/1251] eta: 0:04:00 lr: 0.000679 loss: 3.5974 (3.4284) grad_norm: 1.1858 (1.2249) time: 0.5020 [2021-03-26 00:23:45 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 790/1251] eta: 0:03:55 lr: 0.000679 loss: 3.6237 (3.4294) grad_norm: 1.1737 (1.2248) time: 0.5044 [2021-03-26 00:23:50 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 800/1251] eta: 0:03:50 lr: 0.000679 loss: 3.6798 (3.4285) grad_norm: 1.1564 (1.2244) time: 0.5111 [2021-03-26 00:23:55 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 810/1251] eta: 0:03:45 lr: 0.000679 loss: 3.2193 (3.4259) grad_norm: 1.1564 (1.2239) time: 0.5134 [2021-03-26 00:24:00 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 820/1251] eta: 0:03:40 lr: 0.000679 loss: 3.2131 (3.4248) grad_norm: 1.1903 (1.2241) time: 0.5070 [2021-03-26 00:24:05 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 830/1251] eta: 0:03:35 lr: 0.000679 loss: 3.3917 (3.4251) grad_norm: 1.1738 (1.2234) time: 0.5048 [2021-03-26 00:24:10 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 840/1251] eta: 0:03:30 lr: 0.000679 loss: 3.2865 (3.4219) grad_norm: 1.1631 (1.2230) time: 0.5070 [2021-03-26 00:24:15 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 850/1251] eta: 0:03:24 lr: 0.000679 loss: 3.1757 (3.4202) grad_norm: 1.2040 (1.2233) time: 0.5085 [2021-03-26 00:24:20 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 860/1251] eta: 0:03:19 lr: 0.000679 loss: 3.3798 (3.4204) grad_norm: 1.2040 (1.2235) time: 0.5109 [2021-03-26 00:24:25 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 870/1251] eta: 0:03:14 lr: 0.000679 loss: 3.4226 (3.4179) grad_norm: 1.1859 (1.2237) time: 0.5155 [2021-03-26 00:24:31 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 880/1251] eta: 0:03:09 lr: 0.000679 loss: 3.3498 (3.4172) grad_norm: 1.2344 (1.2241) time: 0.5187 [2021-03-26 00:24:35 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 890/1251] eta: 0:03:04 lr: 0.000679 loss: 3.4749 (3.4171) grad_norm: 1.2445 (1.2248) time: 0.5040 [2021-03-26 00:24:40 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 900/1251] eta: 0:02:59 lr: 0.000679 loss: 3.4749 (3.4166) grad_norm: 1.2494 (1.2253) time: 0.4975 [2021-03-26 00:24:45 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 910/1251] eta: 0:02:54 lr: 0.000679 loss: 3.5582 (3.4186) grad_norm: 1.2926 (1.2260) time: 0.5013 [2021-03-26 00:24:50 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 920/1251] eta: 0:02:49 lr: 0.000679 loss: 3.5836 (3.4183) grad_norm: 1.2460 (1.2259) time: 0.5011 [2021-03-26 00:24:56 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 930/1251] eta: 0:02:43 lr: 0.000679 loss: 3.4488 (3.4174) grad_norm: 1.2079 (1.2252) time: 0.5097 [2021-03-26 00:25:01 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 940/1251] eta: 0:02:38 lr: 0.000679 loss: 3.5530 (3.4182) grad_norm: 1.1821 (1.2253) time: 0.5163 [2021-03-26 00:25:06 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 950/1251] eta: 0:02:33 lr: 0.000679 loss: 3.5599 (3.4191) grad_norm: 1.2280 (1.2255) time: 0.5087 [2021-03-26 00:25:11 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 960/1251] eta: 0:02:28 lr: 0.000679 loss: 3.3917 (3.4192) grad_norm: 1.1343 (1.2246) time: 0.5043 [2021-03-26 00:25:16 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 970/1251] eta: 0:02:23 lr: 0.000679 loss: 3.3917 (3.4199) grad_norm: 1.0862 (1.2238) time: 0.5027 [2021-03-26 00:25:21 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 980/1251] eta: 0:02:18 lr: 0.000679 loss: 3.4294 (3.4209) grad_norm: 1.1684 (1.2237) time: 0.5053 [2021-03-26 00:25:26 swin_small_patch4_window7_224] INFO: Epoch: [115] [ 990/1251] eta: 0:02:13 lr: 0.000679 loss: 3.3750 (3.4201) grad_norm: 1.1571 (1.2236) time: 0.5078 [2021-03-26 00:25:31 swin_small_patch4_window7_224] INFO: Epoch: [115] [1000/1251] eta: 0:02:08 lr: 0.000679 loss: 3.3937 (3.4192) grad_norm: 1.1571 (1.2235) time: 0.5048 [2021-03-26 00:25:36 swin_small_patch4_window7_224] INFO: Epoch: [115] [1010/1251] eta: 0:02:02 lr: 0.000678 loss: 3.5256 (3.4215) grad_norm: 1.2169 (1.2243) time: 0.5048 [2021-03-26 00:25:41 swin_small_patch4_window7_224] INFO: Epoch: [115] [1020/1251] eta: 0:01:57 lr: 0.000678 loss: 3.6044 (3.4227) grad_norm: 1.2144 (1.2243) time: 0.5073 [2021-03-26 00:25:46 swin_small_patch4_window7_224] INFO: Epoch: [115] [1030/1251] eta: 0:01:52 lr: 0.000678 loss: 3.4859 (3.4214) grad_norm: 1.1810 (1.2239) time: 0.5049 [2021-03-26 00:25:51 swin_small_patch4_window7_224] INFO: Epoch: [115] [1040/1251] eta: 0:01:47 lr: 0.000678 loss: 3.4859 (3.4227) grad_norm: 1.2419 (1.2250) time: 0.5114 [2021-03-26 00:25:57 swin_small_patch4_window7_224] INFO: Epoch: [115] [1050/1251] eta: 0:01:42 lr: 0.000678 loss: 3.4257 (3.4213) grad_norm: 1.2980 (1.2253) time: 0.5125 [2021-03-26 00:26:02 swin_small_patch4_window7_224] INFO: Epoch: [115] [1060/1251] eta: 0:01:37 lr: 0.000678 loss: 3.3993 (3.4219) grad_norm: 1.2110 (1.2250) time: 0.5068 [2021-03-26 00:26:07 swin_small_patch4_window7_224] INFO: Epoch: [115] [1070/1251] eta: 0:01:32 lr: 0.000678 loss: 3.3884 (3.4203) grad_norm: 1.2251 (1.2253) time: 0.5079 [2021-03-26 00:26:12 swin_small_patch4_window7_224] INFO: Epoch: [115] [1080/1251] eta: 0:01:27 lr: 0.000678 loss: 3.2812 (3.4198) grad_norm: 1.2062 (1.2249) time: 0.5023 [2021-03-26 00:26:17 swin_small_patch4_window7_224] INFO: Epoch: [115] [1090/1251] eta: 0:01:22 lr: 0.000678 loss: 3.2812 (3.4183) grad_norm: 1.2044 (1.2248) time: 0.5021 [2021-03-26 00:26:22 swin_small_patch4_window7_224] INFO: Epoch: [115] [1100/1251] eta: 0:01:17 lr: 0.000678 loss: 3.2588 (3.4168) grad_norm: 1.2241 (1.2249) time: 0.5028 [2021-03-26 00:26:27 swin_small_patch4_window7_224] INFO: Epoch: [115] [1110/1251] eta: 0:01:11 lr: 0.000678 loss: 3.2171 (3.4161) grad_norm: 1.2432 (1.2253) time: 0.5100 [2021-03-26 00:26:32 swin_small_patch4_window7_224] INFO: Epoch: [115] [1120/1251] eta: 0:01:06 lr: 0.000678 loss: 3.2506 (3.4153) grad_norm: 1.3209 (1.2265) time: 0.5132 [2021-03-26 00:26:37 swin_small_patch4_window7_224] INFO: Epoch: [115] [1130/1251] eta: 0:01:01 lr: 0.000678 loss: 3.6109 (3.4193) grad_norm: 1.2569 (1.2268) time: 0.5076 [2021-03-26 00:26:42 swin_small_patch4_window7_224] INFO: Epoch: [115] [1140/1251] eta: 0:00:56 lr: 0.000678 loss: 3.7981 (3.4195) grad_norm: 1.2061 (1.2271) time: 0.5049 [2021-03-26 00:26:47 swin_small_patch4_window7_224] INFO: Epoch: [115] [1150/1251] eta: 0:00:51 lr: 0.000678 loss: 3.4216 (3.4183) grad_norm: 1.2019 (1.2272) time: 0.5051 [2021-03-26 00:26:52 swin_small_patch4_window7_224] INFO: Epoch: [115] [1160/1251] eta: 0:00:46 lr: 0.000678 loss: 3.3008 (3.4174) grad_norm: 1.1849 (1.2266) time: 0.5052 [2021-03-26 00:26:57 swin_small_patch4_window7_224] INFO: Epoch: [115] [1170/1251] eta: 0:00:41 lr: 0.000678 loss: 3.3008 (3.4164) grad_norm: 1.1661 (1.2263) time: 0.5052 [2021-03-26 00:27:02 swin_small_patch4_window7_224] INFO: Epoch: [115] [1180/1251] eta: 0:00:36 lr: 0.000678 loss: 3.4280 (3.4176) grad_norm: 1.1906 (1.2265) time: 0.5070 [2021-03-26 00:27:07 swin_small_patch4_window7_224] INFO: Epoch: [115] [1190/1251] eta: 0:00:31 lr: 0.000678 loss: 3.3370 (3.4164) grad_norm: 1.2007 (1.2262) time: 0.5054 [2021-03-26 00:27:12 swin_small_patch4_window7_224] INFO: Epoch: [115] [1200/1251] eta: 0:00:25 lr: 0.000678 loss: 3.2081 (3.4140) grad_norm: 1.1740 (1.2260) time: 0.5038 [2021-03-26 00:27:18 swin_small_patch4_window7_224] INFO: Epoch: [115] [1210/1251] eta: 0:00:20 lr: 0.000678 loss: 3.1341 (3.4123) grad_norm: 1.2250 (1.2261) time: 0.5073 [2021-03-26 00:27:23 swin_small_patch4_window7_224] INFO: Epoch: [115] [1220/1251] eta: 0:00:15 lr: 0.000678 loss: 3.6679 (3.4151) grad_norm: 1.2250 (1.2264) time: 0.5082 [2021-03-26 00:27:28 swin_small_patch4_window7_224] INFO: Epoch: [115] [1230/1251] eta: 0:00:10 lr: 0.000678 loss: 3.6679 (3.4154) grad_norm: 1.2009 (1.2260) time: 0.5108 [2021-03-26 00:27:33 swin_small_patch4_window7_224] INFO: Epoch: [115] [1240/1251] eta: 0:00:05 lr: 0.000678 loss: 3.4694 (3.4145) grad_norm: 1.1929 (1.2257) time: 0.5133 [2021-03-26 00:27:38 swin_small_patch4_window7_224] INFO: Epoch: [115] [1250/1251] eta: 0:00:00 lr: 0.000678 loss: 3.4138 (3.4143) grad_norm: 1.2204 (1.2263) time: 0.5060 [2021-03-26 00:28:24 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 0.9868 (0.9868) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-26 00:28:26 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.9762 (0.9886) acc1: 76.5625 (76.9886) acc5: 92.1875 (93.0398) [2021-03-26 00:28:27 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 1.0053 (1.0278) acc1: 76.5625 (76.4137) acc5: 92.1875 (92.6339) [2021-03-26 00:28:28 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 1.0487 (1.0416) acc1: 75.0000 (76.1089) acc5: 92.1875 (92.8427) [2021-03-26 00:28:29 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 1.0456 (1.0128) acc1: 75.0000 (76.2576) acc5: 93.7500 (93.1402) [2021-03-26 00:28:30 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9402 (0.9878) acc1: 76.5625 (76.7360) acc5: 93.7500 (93.3120) [2021-03-26 00:28:36 swin_small_patch4_window7_224] INFO: * Acc@1 77.046 Acc@5 93.826 loss 0.963 [2021-03-26 00:28:36 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.0% [2021-03-26 00:28:36 swin_small_patch4_window7_224] INFO: Max accuracy: 77.05% [2021-03-26 00:28:40 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 0/1251] eta: 1:27:51 lr: 0.000678 loss: 3.4955 (3.4955) grad_norm: 1.2433 (1.2433) time: 4.2142 [2021-03-26 00:28:45 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 10/1251] eta: 0:17:44 lr: 0.000678 loss: 3.4955 (3.5025) grad_norm: 1.2133 (1.2118) time: 0.8580 [2021-03-26 00:28:50 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 20/1251] eta: 0:14:09 lr: 0.000677 loss: 3.4902 (3.4463) grad_norm: 1.1973 (1.2100) time: 0.5139 [2021-03-26 00:28:55 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 30/1251] eta: 0:12:49 lr: 0.000677 loss: 3.7036 (3.4910) grad_norm: 1.1673 (1.2012) time: 0.5047 [2021-03-26 00:29:00 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 40/1251] eta: 0:12:08 lr: 0.000677 loss: 3.4418 (3.4707) grad_norm: 1.1449 (1.1894) time: 0.5087 [2021-03-26 00:29:06 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 50/1251] eta: 0:11:43 lr: 0.000677 loss: 3.3778 (3.4694) grad_norm: 1.1498 (1.1878) time: 0.5164 [2021-03-26 00:29:11 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 60/1251] eta: 0:11:21 lr: 0.000677 loss: 3.4049 (3.4480) grad_norm: 1.1777 (1.1961) time: 0.5124 [2021-03-26 00:29:16 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 70/1251] eta: 0:11:06 lr: 0.000677 loss: 3.6436 (3.4898) grad_norm: 1.1766 (1.1918) time: 0.5111 [2021-03-26 00:29:21 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 80/1251] eta: 0:10:52 lr: 0.000677 loss: 3.6436 (3.4568) grad_norm: 1.1498 (1.1914) time: 0.5113 [2021-03-26 00:29:26 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 90/1251] eta: 0:10:40 lr: 0.000677 loss: 3.4555 (3.4497) grad_norm: 1.1976 (1.1913) time: 0.5044 [2021-03-26 00:29:31 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 100/1251] eta: 0:10:29 lr: 0.000677 loss: 3.4980 (3.4627) grad_norm: 1.2137 (1.1927) time: 0.5046 [2021-03-26 00:29:36 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 110/1251] eta: 0:10:20 lr: 0.000677 loss: 3.4480 (3.4220) grad_norm: 1.2283 (1.1995) time: 0.5096 [2021-03-26 00:29:41 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 120/1251] eta: 0:10:11 lr: 0.000677 loss: 3.2664 (3.4304) grad_norm: 1.2255 (1.1958) time: 0.5087 [2021-03-26 00:29:46 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 130/1251] eta: 0:10:03 lr: 0.000677 loss: 3.5423 (3.4363) grad_norm: 1.1402 (1.1925) time: 0.5069 [2021-03-26 00:29:51 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 140/1251] eta: 0:09:54 lr: 0.000677 loss: 3.5690 (3.4355) grad_norm: 1.1295 (1.1868) time: 0.5052 [2021-03-26 00:29:56 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 150/1251] eta: 0:09:47 lr: 0.000677 loss: 3.5375 (3.4153) grad_norm: 1.1374 (1.1881) time: 0.5011 [2021-03-26 00:30:01 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 160/1251] eta: 0:09:39 lr: 0.000677 loss: 3.4576 (3.4218) grad_norm: 1.2032 (1.1911) time: 0.5018 [2021-03-26 00:30:06 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 170/1251] eta: 0:09:32 lr: 0.000677 loss: 3.4987 (3.4244) grad_norm: 1.2166 (1.1935) time: 0.5043 [2021-03-26 00:30:11 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 180/1251] eta: 0:09:26 lr: 0.000677 loss: 3.4987 (3.4343) grad_norm: 1.2159 (1.1921) time: 0.5095 [2021-03-26 00:30:17 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 190/1251] eta: 0:09:20 lr: 0.000677 loss: 3.5391 (3.4320) grad_norm: 1.1733 (1.1927) time: 0.5141 [2021-03-26 00:30:22 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 200/1251] eta: 0:09:14 lr: 0.000677 loss: 3.3787 (3.4217) grad_norm: 1.1887 (1.1948) time: 0.5162 [2021-03-26 00:30:27 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 210/1251] eta: 0:09:08 lr: 0.000677 loss: 3.2636 (3.4135) grad_norm: 1.1917 (1.1956) time: 0.5106 [2021-03-26 00:30:32 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 220/1251] eta: 0:09:01 lr: 0.000677 loss: 3.4633 (3.4181) grad_norm: 1.2131 (1.1994) time: 0.5048 [2021-03-26 00:30:37 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 230/1251] eta: 0:08:56 lr: 0.000677 loss: 3.4633 (3.4076) grad_norm: 1.2477 (1.2005) time: 0.5137 [2021-03-26 00:30:42 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 240/1251] eta: 0:08:50 lr: 0.000677 loss: 3.4235 (3.4106) grad_norm: 1.2380 (1.2023) time: 0.5189 [2021-03-26 00:30:47 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 250/1251] eta: 0:08:44 lr: 0.000677 loss: 3.4239 (3.4135) grad_norm: 1.2156 (1.2032) time: 0.5075 [2021-03-26 00:30:52 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 260/1251] eta: 0:08:39 lr: 0.000677 loss: 3.3300 (3.4089) grad_norm: 1.2156 (1.2054) time: 0.5080 [2021-03-26 00:30:57 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 270/1251] eta: 0:08:32 lr: 0.000676 loss: 3.4588 (3.4146) grad_norm: 1.2396 (1.2069) time: 0.5092 [2021-03-26 00:31:03 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 280/1251] eta: 0:08:27 lr: 0.000676 loss: 3.5328 (3.4145) grad_norm: 1.1262 (1.2053) time: 0.5038 [2021-03-26 00:31:08 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 290/1251] eta: 0:08:21 lr: 0.000676 loss: 3.3907 (3.4176) grad_norm: 1.1276 (1.2058) time: 0.5061 [2021-03-26 00:31:13 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 300/1251] eta: 0:08:15 lr: 0.000676 loss: 3.4420 (3.4117) grad_norm: 1.1754 (1.2066) time: 0.5072 [2021-03-26 00:31:18 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 310/1251] eta: 0:08:10 lr: 0.000676 loss: 3.4542 (3.4079) grad_norm: 1.2061 (1.2074) time: 0.5060 [2021-03-26 00:31:23 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 320/1251] eta: 0:08:04 lr: 0.000676 loss: 3.4911 (3.4117) grad_norm: 1.1760 (1.2077) time: 0.5030 [2021-03-26 00:31:28 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 330/1251] eta: 0:07:58 lr: 0.000676 loss: 3.6966 (3.4243) grad_norm: 1.1666 (1.2070) time: 0.5016 [2021-03-26 00:31:33 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 340/1251] eta: 0:07:53 lr: 0.000676 loss: 3.8386 (3.4318) grad_norm: 1.1666 (1.2066) time: 0.5046 [2021-03-26 00:31:38 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 350/1251] eta: 0:07:47 lr: 0.000676 loss: 3.4088 (3.4232) grad_norm: 1.2099 (1.2083) time: 0.5047 [2021-03-26 00:31:43 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 360/1251] eta: 0:07:41 lr: 0.000676 loss: 3.2465 (3.4210) grad_norm: 1.2706 (1.2107) time: 0.5030 [2021-03-26 00:31:48 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 370/1251] eta: 0:07:36 lr: 0.000676 loss: 3.4833 (3.4235) grad_norm: 1.2948 (1.2117) time: 0.5026 [2021-03-26 00:31:53 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 380/1251] eta: 0:07:30 lr: 0.000676 loss: 3.5878 (3.4206) grad_norm: 1.1912 (1.2099) time: 0.5039 [2021-03-26 00:31:58 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 390/1251] eta: 0:07:25 lr: 0.000676 loss: 3.4415 (3.4199) grad_norm: 1.1637 (1.2111) time: 0.5073 [2021-03-26 00:32:03 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 400/1251] eta: 0:07:20 lr: 0.000676 loss: 2.9740 (3.4127) grad_norm: 1.2159 (1.2128) time: 0.5095 [2021-03-26 00:32:08 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 410/1251] eta: 0:07:14 lr: 0.000676 loss: 2.9740 (3.4113) grad_norm: 1.2287 (1.2127) time: 0.5103 [2021-03-26 00:32:13 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 420/1251] eta: 0:07:09 lr: 0.000676 loss: 3.4855 (3.4108) grad_norm: 1.2436 (1.2155) time: 0.5100 [2021-03-26 00:32:18 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 430/1251] eta: 0:07:04 lr: 0.000676 loss: 3.5676 (3.4142) grad_norm: 1.2512 (1.2164) time: 0.5080 [2021-03-26 00:32:23 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 440/1251] eta: 0:06:58 lr: 0.000676 loss: 3.5676 (3.4138) grad_norm: 1.2353 (1.2162) time: 0.5020 [2021-03-26 00:32:28 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 450/1251] eta: 0:06:53 lr: 0.000676 loss: 3.4294 (3.4112) grad_norm: 1.2353 (1.2180) time: 0.5034 [2021-03-26 00:32:33 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 460/1251] eta: 0:06:47 lr: 0.000676 loss: 3.5505 (3.4162) grad_norm: 1.2560 (1.2190) time: 0.5032 [2021-03-26 00:32:38 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 470/1251] eta: 0:06:42 lr: 0.000676 loss: 3.5237 (3.4167) grad_norm: 1.1522 (1.2177) time: 0.4983 [2021-03-26 00:32:44 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 480/1251] eta: 0:06:37 lr: 0.000676 loss: 3.6107 (3.4216) grad_norm: 1.1889 (1.2205) time: 0.5009 [2021-03-26 00:32:49 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 490/1251] eta: 0:06:31 lr: 0.000676 loss: 3.6091 (3.4171) grad_norm: 1.1902 (1.2193) time: 0.5066 [2021-03-26 00:32:54 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 500/1251] eta: 0:06:26 lr: 0.000676 loss: 3.4842 (3.4208) grad_norm: 1.1766 (1.2194) time: 0.5067 [2021-03-26 00:32:59 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 510/1251] eta: 0:06:21 lr: 0.000676 loss: 3.4685 (3.4170) grad_norm: 1.2122 (1.2208) time: 0.5037 [2021-03-26 00:33:04 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 520/1251] eta: 0:06:15 lr: 0.000676 loss: 3.2784 (3.4175) grad_norm: 1.2135 (1.2205) time: 0.5026 [2021-03-26 00:33:09 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 530/1251] eta: 0:06:10 lr: 0.000675 loss: 3.3041 (3.4144) grad_norm: 1.2185 (1.2206) time: 0.5023 [2021-03-26 00:33:14 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 540/1251] eta: 0:06:05 lr: 0.000675 loss: 3.3761 (3.4113) grad_norm: 1.2202 (1.2206) time: 0.5075 [2021-03-26 00:33:19 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 550/1251] eta: 0:06:00 lr: 0.000675 loss: 3.4025 (3.4101) grad_norm: 1.2320 (1.2212) time: 0.5170 [2021-03-26 00:33:24 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 560/1251] eta: 0:05:55 lr: 0.000675 loss: 3.4170 (3.4120) grad_norm: 1.2349 (1.2217) time: 0.5154 [2021-03-26 00:33:29 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 570/1251] eta: 0:05:49 lr: 0.000675 loss: 3.5291 (3.4143) grad_norm: 1.2555 (1.2223) time: 0.5052 [2021-03-26 00:33:34 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 580/1251] eta: 0:05:44 lr: 0.000675 loss: 3.6195 (3.4176) grad_norm: 1.2384 (1.2238) time: 0.5027 [2021-03-26 00:33:39 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 590/1251] eta: 0:05:39 lr: 0.000675 loss: 3.6557 (3.4200) grad_norm: 1.2699 (1.2266) time: 0.5085 [2021-03-26 00:33:45 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 600/1251] eta: 0:05:34 lr: 0.000675 loss: 3.6769 (3.4247) grad_norm: 1.2389 (1.2261) time: 0.5151 [2021-03-26 00:33:50 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 610/1251] eta: 0:05:29 lr: 0.000675 loss: 3.5048 (3.4239) grad_norm: 1.2155 (1.2269) time: 0.5125 [2021-03-26 00:33:55 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 620/1251] eta: 0:05:23 lr: 0.000675 loss: 3.3607 (3.4238) grad_norm: 1.2383 (1.2266) time: 0.5070 [2021-03-26 00:34:00 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 630/1251] eta: 0:05:18 lr: 0.000675 loss: 3.4089 (3.4223) grad_norm: 1.2425 (1.2278) time: 0.5070 [2021-03-26 00:34:05 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 640/1251] eta: 0:05:13 lr: 0.000675 loss: 3.4886 (3.4226) grad_norm: 1.2115 (1.2276) time: 0.5067 [2021-03-26 00:34:10 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 650/1251] eta: 0:05:08 lr: 0.000675 loss: 3.4605 (3.4214) grad_norm: 1.2077 (1.2297) time: 0.5051 [2021-03-26 00:34:15 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 660/1251] eta: 0:05:03 lr: 0.000675 loss: 3.4605 (3.4217) grad_norm: 1.3099 (1.2305) time: 0.5067 [2021-03-26 00:34:20 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 670/1251] eta: 0:04:58 lr: 0.000675 loss: 3.4689 (3.4217) grad_norm: 1.2143 (1.2308) time: 0.5063 [2021-03-26 00:34:25 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 680/1251] eta: 0:04:52 lr: 0.000675 loss: 3.5072 (3.4243) grad_norm: 1.1705 (1.2297) time: 0.5069 [2021-03-26 00:34:30 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 690/1251] eta: 0:04:47 lr: 0.000675 loss: 3.5072 (3.4215) grad_norm: 1.1684 (1.2291) time: 0.5016 [2021-03-26 00:34:35 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 700/1251] eta: 0:04:42 lr: 0.000675 loss: 3.5815 (3.4248) grad_norm: 1.1559 (1.2278) time: 0.4936 [2021-03-26 00:34:40 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 710/1251] eta: 0:04:37 lr: 0.000675 loss: 3.5909 (3.4262) grad_norm: 1.1559 (1.2274) time: 0.5002 [2021-03-26 00:34:45 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 720/1251] eta: 0:04:31 lr: 0.000675 loss: 3.5598 (3.4269) grad_norm: 1.1615 (1.2267) time: 0.5084 [2021-03-26 00:34:50 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 730/1251] eta: 0:04:26 lr: 0.000675 loss: 3.6872 (3.4278) grad_norm: 1.2045 (1.2266) time: 0.5125 [2021-03-26 00:34:56 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 740/1251] eta: 0:04:21 lr: 0.000675 loss: 3.7450 (3.4329) grad_norm: 1.1794 (1.2255) time: 0.5182 [2021-03-26 00:35:01 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 750/1251] eta: 0:04:16 lr: 0.000675 loss: 3.5567 (3.4294) grad_norm: 1.1727 (1.2259) time: 0.5183 [2021-03-26 00:35:06 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 760/1251] eta: 0:04:11 lr: 0.000675 loss: 3.2433 (3.4268) grad_norm: 1.2983 (1.2274) time: 0.5095 [2021-03-26 00:35:11 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 770/1251] eta: 0:04:06 lr: 0.000675 loss: 3.4998 (3.4263) grad_norm: 1.2416 (1.2268) time: 0.5039 [2021-03-26 00:35:16 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 780/1251] eta: 0:04:01 lr: 0.000675 loss: 3.4728 (3.4257) grad_norm: 1.2398 (1.2277) time: 0.5045 [2021-03-26 00:35:21 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 790/1251] eta: 0:03:56 lr: 0.000674 loss: 3.4809 (3.4268) grad_norm: 1.2656 (1.2279) time: 0.5160 [2021-03-26 00:35:26 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 800/1251] eta: 0:03:51 lr: 0.000674 loss: 3.4826 (3.4246) grad_norm: 1.2596 (1.2281) time: 0.5198 [2021-03-26 00:35:31 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 810/1251] eta: 0:03:45 lr: 0.000674 loss: 3.6644 (3.4283) grad_norm: 1.2375 (1.2285) time: 0.5103 [2021-03-26 00:35:36 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 820/1251] eta: 0:03:40 lr: 0.000674 loss: 3.7522 (3.4271) grad_norm: 1.2158 (1.2287) time: 0.5072 [2021-03-26 00:35:41 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 830/1251] eta: 0:03:35 lr: 0.000674 loss: 3.3802 (3.4253) grad_norm: 1.2647 (1.2293) time: 0.5102 [2021-03-26 00:35:47 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 840/1251] eta: 0:03:30 lr: 0.000674 loss: 3.4349 (3.4236) grad_norm: 1.2574 (1.2299) time: 0.5129 [2021-03-26 00:35:52 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 850/1251] eta: 0:03:25 lr: 0.000674 loss: 3.4541 (3.4242) grad_norm: 1.1792 (1.2292) time: 0.5038 [2021-03-26 00:35:57 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 860/1251] eta: 0:03:20 lr: 0.000674 loss: 3.4541 (3.4242) grad_norm: 1.1792 (1.2293) time: 0.5002 [2021-03-26 00:36:02 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 870/1251] eta: 0:03:15 lr: 0.000674 loss: 3.3298 (3.4225) grad_norm: 1.2799 (1.2308) time: 0.5062 [2021-03-26 00:36:07 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 880/1251] eta: 0:03:09 lr: 0.000674 loss: 3.5439 (3.4250) grad_norm: 1.2962 (1.2320) time: 0.5041 [2021-03-26 00:36:12 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 890/1251] eta: 0:03:04 lr: 0.000674 loss: 3.6903 (3.4287) grad_norm: 1.2457 (1.2318) time: 0.4985 [2021-03-26 00:36:17 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 900/1251] eta: 0:02:59 lr: 0.000674 loss: 3.6479 (3.4296) grad_norm: 1.1979 (1.2314) time: 0.5058 [2021-03-26 00:36:22 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 910/1251] eta: 0:02:54 lr: 0.000674 loss: 3.4246 (3.4296) grad_norm: 1.1628 (1.2316) time: 0.5149 [2021-03-26 00:36:27 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 920/1251] eta: 0:02:49 lr: 0.000674 loss: 3.3967 (3.4308) grad_norm: 1.2359 (1.2314) time: 0.5083 [2021-03-26 00:36:32 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 930/1251] eta: 0:02:44 lr: 0.000674 loss: 3.4784 (3.4308) grad_norm: 1.1852 (1.2310) time: 0.5043 [2021-03-26 00:36:37 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 940/1251] eta: 0:02:39 lr: 0.000674 loss: 3.4943 (3.4322) grad_norm: 1.1680 (1.2307) time: 0.5068 [2021-03-26 00:36:42 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 950/1251] eta: 0:02:33 lr: 0.000674 loss: 3.4909 (3.4297) grad_norm: 1.1848 (1.2308) time: 0.5047 [2021-03-26 00:36:47 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 960/1251] eta: 0:02:28 lr: 0.000674 loss: 3.4909 (3.4303) grad_norm: 1.2182 (1.2305) time: 0.5041 [2021-03-26 00:36:52 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 970/1251] eta: 0:02:23 lr: 0.000674 loss: 3.4974 (3.4316) grad_norm: 1.1898 (1.2300) time: 0.5113 [2021-03-26 00:36:57 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 980/1251] eta: 0:02:18 lr: 0.000674 loss: 3.4216 (3.4301) grad_norm: 1.1818 (1.2297) time: 0.5101 [2021-03-26 00:37:02 swin_small_patch4_window7_224] INFO: Epoch: [116] [ 990/1251] eta: 0:02:13 lr: 0.000674 loss: 3.4978 (3.4309) grad_norm: 1.1745 (1.2289) time: 0.5015 [2021-03-26 00:37:07 swin_small_patch4_window7_224] INFO: Epoch: [116] [1000/1251] eta: 0:02:08 lr: 0.000674 loss: 3.5927 (3.4310) grad_norm: 1.1213 (1.2286) time: 0.5016 [2021-03-26 00:37:13 swin_small_patch4_window7_224] INFO: Epoch: [116] [1010/1251] eta: 0:02:03 lr: 0.000674 loss: 3.5822 (3.4312) grad_norm: 1.1821 (1.2284) time: 0.5079 [2021-03-26 00:37:18 swin_small_patch4_window7_224] INFO: Epoch: [116] [1020/1251] eta: 0:01:58 lr: 0.000674 loss: 3.3864 (3.4302) grad_norm: 1.2009 (1.2286) time: 0.5087 [2021-03-26 00:37:23 swin_small_patch4_window7_224] INFO: Epoch: [116] [1030/1251] eta: 0:01:52 lr: 0.000674 loss: 3.3864 (3.4300) grad_norm: 1.2138 (1.2287) time: 0.5030 [2021-03-26 00:37:28 swin_small_patch4_window7_224] INFO: Epoch: [116] [1040/1251] eta: 0:01:47 lr: 0.000673 loss: 3.5191 (3.4281) grad_norm: 1.2197 (1.2289) time: 0.5037 [2021-03-26 00:37:33 swin_small_patch4_window7_224] INFO: Epoch: [116] [1050/1251] eta: 0:01:42 lr: 0.000673 loss: 3.4583 (3.4283) grad_norm: 1.2477 (1.2295) time: 0.5152 [2021-03-26 00:37:38 swin_small_patch4_window7_224] INFO: Epoch: [116] [1060/1251] eta: 0:01:37 lr: 0.000673 loss: 3.4805 (3.4294) grad_norm: 1.2418 (1.2299) time: 0.5162 [2021-03-26 00:37:43 swin_small_patch4_window7_224] INFO: Epoch: [116] [1070/1251] eta: 0:01:32 lr: 0.000673 loss: 3.4683 (3.4278) grad_norm: 1.2390 (1.2303) time: 0.5073 [2021-03-26 00:37:48 swin_small_patch4_window7_224] INFO: Epoch: [116] [1080/1251] eta: 0:01:27 lr: 0.000673 loss: 3.6783 (3.4303) grad_norm: 1.3438 (1.2315) time: 0.5078 [2021-03-26 00:37:53 swin_small_patch4_window7_224] INFO: Epoch: [116] [1090/1251] eta: 0:01:22 lr: 0.000673 loss: 3.7076 (3.4305) grad_norm: 1.3359 (1.2319) time: 0.5068 [2021-03-26 00:37:58 swin_small_patch4_window7_224] INFO: Epoch: [116] [1100/1251] eta: 0:01:17 lr: 0.000673 loss: 3.6006 (3.4332) grad_norm: 1.2081 (1.2314) time: 0.5068 [2021-03-26 00:38:03 swin_small_patch4_window7_224] INFO: Epoch: [116] [1110/1251] eta: 0:01:12 lr: 0.000673 loss: 3.5445 (3.4339) grad_norm: 1.2162 (1.2322) time: 0.5103 [2021-03-26 00:38:08 swin_small_patch4_window7_224] INFO: Epoch: [116] [1120/1251] eta: 0:01:06 lr: 0.000673 loss: 3.4675 (3.4351) grad_norm: 1.3146 (1.2329) time: 0.5057 [2021-03-26 00:38:13 swin_small_patch4_window7_224] INFO: Epoch: [116] [1130/1251] eta: 0:01:01 lr: 0.000673 loss: 3.2997 (3.4337) grad_norm: 1.2577 (1.2333) time: 0.5025 [2021-03-26 00:38:19 swin_small_patch4_window7_224] INFO: Epoch: [116] [1140/1251] eta: 0:00:56 lr: 0.000673 loss: 3.2869 (3.4332) grad_norm: 1.1699 (1.2326) time: 0.5067 [2021-03-26 00:38:24 swin_small_patch4_window7_224] INFO: Epoch: [116] [1150/1251] eta: 0:00:51 lr: 0.000673 loss: 3.3916 (3.4322) grad_norm: 1.1812 (1.2327) time: 0.5063 [2021-03-26 00:38:29 swin_small_patch4_window7_224] INFO: Epoch: [116] [1160/1251] eta: 0:00:46 lr: 0.000673 loss: 3.4917 (3.4314) grad_norm: 1.2079 (1.2331) time: 0.5061 [2021-03-26 00:38:34 swin_small_patch4_window7_224] INFO: Epoch: [116] [1170/1251] eta: 0:00:41 lr: 0.000673 loss: 3.4917 (3.4304) grad_norm: 1.2159 (1.2332) time: 0.5093 [2021-03-26 00:38:39 swin_small_patch4_window7_224] INFO: Epoch: [116] [1180/1251] eta: 0:00:36 lr: 0.000673 loss: 3.5106 (3.4294) grad_norm: 1.2225 (1.2331) time: 0.5058 [2021-03-26 00:38:44 swin_small_patch4_window7_224] INFO: Epoch: [116] [1190/1251] eta: 0:00:31 lr: 0.000673 loss: 3.5977 (3.4298) grad_norm: 1.2543 (1.2331) time: 0.5072 [2021-03-26 00:38:49 swin_small_patch4_window7_224] INFO: Epoch: [116] [1200/1251] eta: 0:00:26 lr: 0.000673 loss: 3.5476 (3.4302) grad_norm: 1.2543 (1.2334) time: 0.5107 [2021-03-26 00:38:54 swin_small_patch4_window7_224] INFO: Epoch: [116] [1210/1251] eta: 0:00:20 lr: 0.000673 loss: 3.5361 (3.4295) grad_norm: 1.2317 (1.2336) time: 0.5093 [2021-03-26 00:38:59 swin_small_patch4_window7_224] INFO: Epoch: [116] [1220/1251] eta: 0:00:15 lr: 0.000673 loss: 3.5762 (3.4300) grad_norm: 1.2667 (1.2340) time: 0.5092 [2021-03-26 00:39:04 swin_small_patch4_window7_224] INFO: Epoch: [116] [1230/1251] eta: 0:00:10 lr: 0.000673 loss: 3.5300 (3.4297) grad_norm: 1.3137 (1.2348) time: 0.5111 [2021-03-26 00:39:09 swin_small_patch4_window7_224] INFO: Epoch: [116] [1240/1251] eta: 0:00:05 lr: 0.000673 loss: 3.4500 (3.4290) grad_norm: 1.2144 (1.2346) time: 0.5063 [2021-03-26 00:39:14 swin_small_patch4_window7_224] INFO: Epoch: [116] [1250/1251] eta: 0:00:00 lr: 0.000673 loss: 3.5388 (3.4293) grad_norm: 1.1633 (1.2344) time: 0.4975 [2021-03-26 00:39:21 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 1.0320 (1.0320) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.7500) [2021-03-26 00:39:23 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9156 (0.9597) acc1: 76.5625 (76.9886) acc5: 95.3125 (94.3182) [2021-03-26 00:39:24 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.9674 (0.9996) acc1: 75.0000 (76.4881) acc5: 92.1875 (93.6756) [2021-03-26 00:39:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0432 (0.9939) acc1: 75.0000 (76.5625) acc5: 93.7500 (93.5484) [2021-03-26 00:39:28 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0080 (0.9999) acc1: 76.5625 (76.6768) acc5: 93.7500 (93.8262) [2021-03-26 00:39:29 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0336 (1.0021) acc1: 76.5625 (76.8320) acc5: 93.7500 (93.6960) [2021-03-26 00:39:35 swin_small_patch4_window7_224] INFO: * Acc@1 76.854 Acc@5 93.900 loss 0.987 [2021-03-26 00:39:35 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.9% [2021-03-26 00:39:35 swin_small_patch4_window7_224] INFO: Max accuracy: 77.05% [2021-03-26 00:39:39 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 0/1251] eta: 1:26:13 lr: 0.000673 loss: 3.4850 (3.4850) grad_norm: 1.1004 (1.1004) time: 4.1356 [2021-03-26 00:39:45 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 10/1251] eta: 0:17:45 lr: 0.000673 loss: 3.5778 (3.3754) grad_norm: 1.1942 (1.2244) time: 0.8583 [2021-03-26 00:39:50 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 20/1251] eta: 0:14:08 lr: 0.000673 loss: 3.4050 (3.4040) grad_norm: 1.1906 (1.1934) time: 0.5170 [2021-03-26 00:39:55 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 30/1251] eta: 0:12:53 lr: 0.000673 loss: 3.4130 (3.4873) grad_norm: 1.1774 (1.2049) time: 0.5099 [2021-03-26 00:40:00 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 40/1251] eta: 0:12:10 lr: 0.000673 loss: 3.4130 (3.3976) grad_norm: 1.2466 (1.2256) time: 0.5121 [2021-03-26 00:40:05 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 50/1251] eta: 0:11:40 lr: 0.000672 loss: 3.4590 (3.4650) grad_norm: 1.2789 (1.2324) time: 0.5057 [2021-03-26 00:40:10 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 60/1251] eta: 0:11:19 lr: 0.000672 loss: 3.6459 (3.4366) grad_norm: 1.2180 (1.2275) time: 0.5051 [2021-03-26 00:40:15 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 70/1251] eta: 0:11:03 lr: 0.000672 loss: 3.4029 (3.4340) grad_norm: 1.1539 (1.2177) time: 0.5062 [2021-03-26 00:40:20 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 80/1251] eta: 0:10:49 lr: 0.000672 loss: 3.4029 (3.4331) grad_norm: 1.1429 (1.2172) time: 0.5056 [2021-03-26 00:40:25 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 90/1251] eta: 0:10:36 lr: 0.000672 loss: 3.4928 (3.4497) grad_norm: 1.2034 (1.2184) time: 0.5025 [2021-03-26 00:40:30 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 100/1251] eta: 0:10:26 lr: 0.000672 loss: 3.6084 (3.4561) grad_norm: 1.1900 (1.2149) time: 0.5030 [2021-03-26 00:40:35 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 110/1251] eta: 0:10:16 lr: 0.000672 loss: 3.5591 (3.4644) grad_norm: 1.1977 (inf) time: 0.5034 [2021-03-26 00:40:40 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 120/1251] eta: 0:10:07 lr: 0.000672 loss: 3.3952 (3.4510) grad_norm: 1.2791 (inf) time: 0.5006 [2021-03-26 00:40:45 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 130/1251] eta: 0:10:00 lr: 0.000672 loss: 3.3476 (3.4508) grad_norm: 1.2133 (inf) time: 0.5062 [2021-03-26 00:40:50 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 140/1251] eta: 0:09:51 lr: 0.000672 loss: 3.3955 (3.4486) grad_norm: 1.2138 (inf) time: 0.5063 [2021-03-26 00:40:55 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 150/1251] eta: 0:09:45 lr: 0.000672 loss: 3.5710 (3.4558) grad_norm: 1.2496 (inf) time: 0.5059 [2021-03-26 00:41:00 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 160/1251] eta: 0:09:37 lr: 0.000672 loss: 3.5019 (3.4518) grad_norm: 1.2559 (inf) time: 0.5065 [2021-03-26 00:41:05 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 170/1251] eta: 0:09:30 lr: 0.000672 loss: 3.5639 (3.4609) grad_norm: 1.2657 (inf) time: 0.5026 [2021-03-26 00:41:11 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 180/1251] eta: 0:09:24 lr: 0.000672 loss: 3.6238 (3.4554) grad_norm: 1.2652 (inf) time: 0.5085 [2021-03-26 00:41:16 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 190/1251] eta: 0:09:19 lr: 0.000672 loss: 3.6238 (3.4632) grad_norm: 1.2303 (inf) time: 0.5220 [2021-03-26 00:41:21 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 200/1251] eta: 0:09:13 lr: 0.000672 loss: 3.6018 (3.4583) grad_norm: 1.2295 (inf) time: 0.5230 [2021-03-26 00:41:26 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 210/1251] eta: 0:09:07 lr: 0.000672 loss: 3.4254 (3.4505) grad_norm: 1.2182 (inf) time: 0.5111 [2021-03-26 00:41:31 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 220/1251] eta: 0:09:01 lr: 0.000672 loss: 3.4701 (3.4499) grad_norm: 1.2151 (inf) time: 0.5084 [2021-03-26 00:41:36 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 230/1251] eta: 0:08:55 lr: 0.000672 loss: 3.4818 (3.4442) grad_norm: 1.2151 (inf) time: 0.5081 [2021-03-26 00:41:41 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 240/1251] eta: 0:08:49 lr: 0.000672 loss: 3.3510 (3.4359) grad_norm: 1.2311 (inf) time: 0.5068 [2021-03-26 00:41:46 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 250/1251] eta: 0:08:43 lr: 0.000672 loss: 3.3608 (3.4401) grad_norm: 1.2311 (inf) time: 0.5078 [2021-03-26 00:41:52 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 260/1251] eta: 0:08:37 lr: 0.000672 loss: 3.4512 (3.4323) grad_norm: 1.2086 (inf) time: 0.5064 [2021-03-26 00:41:57 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 270/1251] eta: 0:08:31 lr: 0.000672 loss: 3.2090 (3.4275) grad_norm: 1.2555 (inf) time: 0.5065 [2021-03-26 00:42:02 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 280/1251] eta: 0:08:25 lr: 0.000672 loss: 3.1029 (3.4182) grad_norm: 1.2468 (inf) time: 0.5037 [2021-03-26 00:42:07 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 290/1251] eta: 0:08:19 lr: 0.000672 loss: 3.3763 (3.4207) grad_norm: 1.2301 (inf) time: 0.4995 [2021-03-26 00:42:12 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 300/1251] eta: 0:08:14 lr: 0.000672 loss: 3.3877 (3.4166) grad_norm: 1.2347 (inf) time: 0.5002 [2021-03-26 00:42:17 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 310/1251] eta: 0:08:08 lr: 0.000671 loss: 3.4642 (3.4227) grad_norm: 1.2591 (inf) time: 0.5045 [2021-03-26 00:42:22 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 320/1251] eta: 0:08:03 lr: 0.000671 loss: 3.6077 (3.4229) grad_norm: 1.2337 (inf) time: 0.5096 [2021-03-26 00:42:27 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 330/1251] eta: 0:07:57 lr: 0.000671 loss: 3.4659 (3.4246) grad_norm: 1.2438 (inf) time: 0.5058 [2021-03-26 00:42:32 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 340/1251] eta: 0:07:52 lr: 0.000671 loss: 3.5787 (3.4253) grad_norm: 1.2658 (inf) time: 0.5049 [2021-03-26 00:42:37 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 350/1251] eta: 0:07:46 lr: 0.000671 loss: 3.4246 (3.4232) grad_norm: 1.2658 (inf) time: 0.5114 [2021-03-26 00:42:42 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 360/1251] eta: 0:07:41 lr: 0.000671 loss: 3.4246 (3.4225) grad_norm: 1.2097 (inf) time: 0.5047 [2021-03-26 00:42:47 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 370/1251] eta: 0:07:35 lr: 0.000671 loss: 3.4412 (3.4269) grad_norm: 1.2578 (inf) time: 0.5029 [2021-03-26 00:42:52 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 380/1251] eta: 0:07:30 lr: 0.000671 loss: 3.4699 (3.4207) grad_norm: 1.2770 (inf) time: 0.5094 [2021-03-26 00:42:57 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 390/1251] eta: 0:07:24 lr: 0.000671 loss: 3.4404 (3.4189) grad_norm: 1.2081 (inf) time: 0.5090 [2021-03-26 00:43:02 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 400/1251] eta: 0:07:19 lr: 0.000671 loss: 3.4404 (3.4188) grad_norm: 1.1584 (inf) time: 0.5060 [2021-03-26 00:43:07 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 410/1251] eta: 0:07:14 lr: 0.000671 loss: 3.5754 (3.4189) grad_norm: 1.1591 (inf) time: 0.5055 [2021-03-26 00:43:13 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 420/1251] eta: 0:07:08 lr: 0.000671 loss: 3.6331 (3.4210) grad_norm: 1.1964 (inf) time: 0.5102 [2021-03-26 00:43:18 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 430/1251] eta: 0:07:03 lr: 0.000671 loss: 3.7248 (3.4228) grad_norm: 1.2425 (inf) time: 0.5133 [2021-03-26 00:43:23 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 440/1251] eta: 0:06:58 lr: 0.000671 loss: 3.5276 (3.4265) grad_norm: 1.2664 (inf) time: 0.5095 [2021-03-26 00:43:28 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 450/1251] eta: 0:06:52 lr: 0.000671 loss: 3.5276 (3.4300) grad_norm: 1.2493 (inf) time: 0.5033 [2021-03-26 00:43:33 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 460/1251] eta: 0:06:47 lr: 0.000671 loss: 3.4902 (3.4310) grad_norm: 1.2087 (inf) time: 0.5012 [2021-03-26 00:43:38 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 470/1251] eta: 0:06:42 lr: 0.000671 loss: 3.7063 (3.4380) grad_norm: 1.1252 (inf) time: 0.5022 [2021-03-26 00:43:43 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 480/1251] eta: 0:06:36 lr: 0.000671 loss: 3.7191 (3.4403) grad_norm: 1.1668 (inf) time: 0.5055 [2021-03-26 00:43:48 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 490/1251] eta: 0:06:31 lr: 0.000671 loss: 3.3477 (3.4370) grad_norm: 1.1999 (inf) time: 0.5020 [2021-03-26 00:43:53 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 500/1251] eta: 0:06:26 lr: 0.000671 loss: 3.2793 (3.4363) grad_norm: 1.2522 (inf) time: 0.5011 [2021-03-26 00:43:58 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 510/1251] eta: 0:06:20 lr: 0.000671 loss: 3.2769 (3.4303) grad_norm: 1.2649 (inf) time: 0.5026 [2021-03-26 00:44:03 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 520/1251] eta: 0:06:15 lr: 0.000671 loss: 3.5809 (3.4315) grad_norm: 1.3027 (inf) time: 0.5011 [2021-03-26 00:44:08 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 530/1251] eta: 0:06:10 lr: 0.000671 loss: 3.6563 (3.4364) grad_norm: 1.3050 (inf) time: 0.5028 [2021-03-26 00:44:13 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 540/1251] eta: 0:06:04 lr: 0.000671 loss: 3.6402 (3.4387) grad_norm: 1.2385 (inf) time: 0.5015 [2021-03-26 00:44:18 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 550/1251] eta: 0:05:59 lr: 0.000671 loss: 3.5157 (3.4343) grad_norm: 1.2465 (inf) time: 0.5113 [2021-03-26 00:44:23 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 560/1251] eta: 0:05:54 lr: 0.000670 loss: 3.3486 (3.4350) grad_norm: 1.2599 (inf) time: 0.5195 [2021-03-26 00:44:28 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 570/1251] eta: 0:05:49 lr: 0.000670 loss: 3.6251 (3.4352) grad_norm: 1.2030 (inf) time: 0.5080 [2021-03-26 00:44:33 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 580/1251] eta: 0:05:44 lr: 0.000670 loss: 3.3128 (3.4345) grad_norm: 1.1768 (inf) time: 0.5054 [2021-03-26 00:44:38 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 590/1251] eta: 0:05:39 lr: 0.000670 loss: 3.5649 (3.4355) grad_norm: 1.1631 (inf) time: 0.5039 [2021-03-26 00:44:43 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 600/1251] eta: 0:05:33 lr: 0.000670 loss: 3.5649 (3.4359) grad_norm: 1.1670 (inf) time: 0.4977 [2021-03-26 00:44:48 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 610/1251] eta: 0:05:28 lr: 0.000670 loss: 3.4616 (3.4331) grad_norm: 1.1976 (inf) time: 0.5002 [2021-03-26 00:44:53 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 620/1251] eta: 0:05:23 lr: 0.000670 loss: 3.3944 (3.4345) grad_norm: 1.2511 (inf) time: 0.5030 [2021-03-26 00:44:59 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 630/1251] eta: 0:05:18 lr: 0.000670 loss: 3.4408 (3.4345) grad_norm: 1.2216 (inf) time: 0.5055 [2021-03-26 00:45:04 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 640/1251] eta: 0:05:12 lr: 0.000670 loss: 3.4787 (3.4344) grad_norm: 1.1855 (inf) time: 0.5050 [2021-03-26 00:45:09 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 650/1251] eta: 0:05:07 lr: 0.000670 loss: 3.4179 (3.4354) grad_norm: 1.1481 (inf) time: 0.5051 [2021-03-26 00:45:14 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 660/1251] eta: 0:05:02 lr: 0.000670 loss: 3.2652 (3.4320) grad_norm: 1.1582 (inf) time: 0.5051 [2021-03-26 00:45:19 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 670/1251] eta: 0:04:57 lr: 0.000670 loss: 3.3380 (3.4320) grad_norm: 1.1777 (inf) time: 0.5030 [2021-03-26 00:45:24 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 680/1251] eta: 0:04:52 lr: 0.000670 loss: 3.3174 (3.4292) grad_norm: 1.2172 (inf) time: 0.5060 [2021-03-26 00:45:29 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 690/1251] eta: 0:04:47 lr: 0.000670 loss: 3.3174 (3.4279) grad_norm: 1.2172 (inf) time: 0.5039 [2021-03-26 00:45:34 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 700/1251] eta: 0:04:41 lr: 0.000670 loss: 3.4689 (3.4278) grad_norm: 1.1467 (inf) time: 0.4961 [2021-03-26 00:45:39 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 710/1251] eta: 0:04:36 lr: 0.000670 loss: 3.5501 (3.4278) grad_norm: 1.1374 (inf) time: 0.5023 [2021-03-26 00:45:44 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 720/1251] eta: 0:04:31 lr: 0.000670 loss: 3.6260 (3.4303) grad_norm: 1.1360 (inf) time: 0.5094 [2021-03-26 00:45:49 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 730/1251] eta: 0:04:26 lr: 0.000670 loss: 3.4858 (3.4265) grad_norm: 1.2345 (inf) time: 0.5109 [2021-03-26 00:45:54 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 740/1251] eta: 0:04:21 lr: 0.000670 loss: 3.2140 (3.4254) grad_norm: 1.2345 (inf) time: 0.5210 [2021-03-26 00:46:00 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 750/1251] eta: 0:04:16 lr: 0.000670 loss: 3.3149 (3.4216) grad_norm: 1.2331 (inf) time: 0.5246 [2021-03-26 00:46:05 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 760/1251] eta: 0:04:11 lr: 0.000670 loss: 3.4096 (3.4226) grad_norm: 1.2386 (inf) time: 0.5146 [2021-03-26 00:46:10 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 770/1251] eta: 0:04:06 lr: 0.000670 loss: 3.5353 (3.4252) grad_norm: 1.2915 (inf) time: 0.5126 [2021-03-26 00:46:15 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 780/1251] eta: 0:04:01 lr: 0.000670 loss: 3.5934 (3.4260) grad_norm: 1.2793 (inf) time: 0.5143 [2021-03-26 00:46:20 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 790/1251] eta: 0:03:55 lr: 0.000670 loss: 3.5334 (3.4262) grad_norm: 1.2392 (inf) time: 0.5100 [2021-03-26 00:46:25 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 800/1251] eta: 0:03:50 lr: 0.000670 loss: 3.5049 (3.4269) grad_norm: 1.2256 (inf) time: 0.5086 [2021-03-26 00:46:30 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 810/1251] eta: 0:03:45 lr: 0.000670 loss: 3.4665 (3.4252) grad_norm: 1.1556 (inf) time: 0.5066 [2021-03-26 00:46:35 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 820/1251] eta: 0:03:40 lr: 0.000669 loss: 3.4491 (3.4249) grad_norm: 1.1365 (inf) time: 0.5034 [2021-03-26 00:46:40 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 830/1251] eta: 0:03:35 lr: 0.000669 loss: 3.4862 (3.4246) grad_norm: 1.1486 (inf) time: 0.4987 [2021-03-26 00:46:45 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 840/1251] eta: 0:03:30 lr: 0.000669 loss: 3.5441 (3.4262) grad_norm: 1.2243 (inf) time: 0.5024 [2021-03-26 00:46:50 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 850/1251] eta: 0:03:24 lr: 0.000669 loss: 3.6978 (3.4269) grad_norm: 1.2061 (inf) time: 0.5067 [2021-03-26 00:46:55 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 860/1251] eta: 0:03:19 lr: 0.000669 loss: 3.7171 (3.4297) grad_norm: 1.1714 (inf) time: 0.5081 [2021-03-26 00:47:00 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 870/1251] eta: 0:03:14 lr: 0.000669 loss: 3.7171 (3.4300) grad_norm: 1.1976 (inf) time: 0.5116 [2021-03-26 00:47:06 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 880/1251] eta: 0:03:09 lr: 0.000669 loss: 3.3921 (3.4270) grad_norm: 1.2007 (inf) time: 0.5081 [2021-03-26 00:47:11 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 890/1251] eta: 0:03:04 lr: 0.000669 loss: 3.2458 (3.4247) grad_norm: 1.1993 (inf) time: 0.5074 [2021-03-26 00:47:16 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 900/1251] eta: 0:02:59 lr: 0.000669 loss: 3.2874 (3.4236) grad_norm: 1.2620 (inf) time: 0.5052 [2021-03-26 00:47:21 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 910/1251] eta: 0:02:54 lr: 0.000669 loss: 3.2874 (3.4232) grad_norm: 1.2228 (inf) time: 0.4965 [2021-03-26 00:47:26 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 920/1251] eta: 0:02:49 lr: 0.000669 loss: 3.6099 (3.4245) grad_norm: 1.1691 (inf) time: 0.4982 [2021-03-26 00:47:31 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 930/1251] eta: 0:02:43 lr: 0.000669 loss: 3.6128 (3.4237) grad_norm: 1.1547 (inf) time: 0.5118 [2021-03-26 00:47:36 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 940/1251] eta: 0:02:38 lr: 0.000669 loss: 3.4801 (3.4214) grad_norm: 1.1547 (inf) time: 0.5148 [2021-03-26 00:47:41 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 950/1251] eta: 0:02:33 lr: 0.000669 loss: 3.5545 (3.4244) grad_norm: 1.1738 (inf) time: 0.5035 [2021-03-26 00:47:46 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 960/1251] eta: 0:02:28 lr: 0.000669 loss: 3.6234 (3.4250) grad_norm: 1.1719 (inf) time: 0.4964 [2021-03-26 00:47:51 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 970/1251] eta: 0:02:23 lr: 0.000669 loss: 3.5811 (3.4264) grad_norm: 1.1886 (inf) time: 0.5037 [2021-03-26 00:47:56 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 980/1251] eta: 0:02:18 lr: 0.000669 loss: 3.5873 (3.4277) grad_norm: 1.1921 (inf) time: 0.5036 [2021-03-26 00:48:01 swin_small_patch4_window7_224] INFO: Epoch: [117] [ 990/1251] eta: 0:02:13 lr: 0.000669 loss: 3.5167 (3.4289) grad_norm: 1.2017 (inf) time: 0.5050 [2021-03-26 00:48:06 swin_small_patch4_window7_224] INFO: Epoch: [117] [1000/1251] eta: 0:02:08 lr: 0.000669 loss: 3.4703 (3.4291) grad_norm: 1.2755 (inf) time: 0.5117 [2021-03-26 00:48:11 swin_small_patch4_window7_224] INFO: Epoch: [117] [1010/1251] eta: 0:02:02 lr: 0.000669 loss: 3.4555 (3.4287) grad_norm: 1.2755 (inf) time: 0.5071 [2021-03-26 00:48:16 swin_small_patch4_window7_224] INFO: Epoch: [117] [1020/1251] eta: 0:01:57 lr: 0.000669 loss: 3.4849 (3.4291) grad_norm: 1.2271 (inf) time: 0.5056 [2021-03-26 00:48:21 swin_small_patch4_window7_224] INFO: Epoch: [117] [1030/1251] eta: 0:01:52 lr: 0.000669 loss: 3.4929 (3.4295) grad_norm: 1.2201 (inf) time: 0.5052 [2021-03-26 00:48:26 swin_small_patch4_window7_224] INFO: Epoch: [117] [1040/1251] eta: 0:01:47 lr: 0.000669 loss: 3.4412 (3.4282) grad_norm: 1.2149 (inf) time: 0.5017 [2021-03-26 00:48:31 swin_small_patch4_window7_224] INFO: Epoch: [117] [1050/1251] eta: 0:01:42 lr: 0.000669 loss: 3.1821 (3.4268) grad_norm: 1.2149 (inf) time: 0.5070 [2021-03-26 00:48:37 swin_small_patch4_window7_224] INFO: Epoch: [117] [1060/1251] eta: 0:01:37 lr: 0.000669 loss: 3.1944 (3.4247) grad_norm: 1.2679 (inf) time: 0.5135 [2021-03-26 00:48:42 swin_small_patch4_window7_224] INFO: Epoch: [117] [1070/1251] eta: 0:01:32 lr: 0.000668 loss: 3.2205 (3.4237) grad_norm: 1.2815 (inf) time: 0.5135 [2021-03-26 00:48:47 swin_small_patch4_window7_224] INFO: Epoch: [117] [1080/1251] eta: 0:01:27 lr: 0.000668 loss: 3.4033 (3.4239) grad_norm: 1.2307 (inf) time: 0.5064 [2021-03-26 00:48:52 swin_small_patch4_window7_224] INFO: Epoch: [117] [1090/1251] eta: 0:01:22 lr: 0.000668 loss: 3.5230 (3.4257) grad_norm: 1.2000 (inf) time: 0.5042 [2021-03-26 00:48:57 swin_small_patch4_window7_224] INFO: Epoch: [117] [1100/1251] eta: 0:01:17 lr: 0.000668 loss: 3.5937 (3.4277) grad_norm: 1.2410 (inf) time: 0.5075 [2021-03-26 00:49:02 swin_small_patch4_window7_224] INFO: Epoch: [117] [1110/1251] eta: 0:01:11 lr: 0.000668 loss: 3.8306 (3.4292) grad_norm: 1.2258 (inf) time: 0.5009 [2021-03-26 00:49:07 swin_small_patch4_window7_224] INFO: Epoch: [117] [1120/1251] eta: 0:01:06 lr: 0.000668 loss: 3.6178 (3.4292) grad_norm: 1.2014 (inf) time: 0.5061 [2021-03-26 00:49:12 swin_small_patch4_window7_224] INFO: Epoch: [117] [1130/1251] eta: 0:01:01 lr: 0.000668 loss: 3.1181 (3.4276) grad_norm: 1.1885 (inf) time: 0.5160 [2021-03-26 00:49:17 swin_small_patch4_window7_224] INFO: Epoch: [117] [1140/1251] eta: 0:00:56 lr: 0.000668 loss: 3.5069 (3.4284) grad_norm: 1.1954 (inf) time: 0.5045 [2021-03-26 00:49:22 swin_small_patch4_window7_224] INFO: Epoch: [117] [1150/1251] eta: 0:00:51 lr: 0.000668 loss: 3.5069 (3.4283) grad_norm: 1.1998 (inf) time: 0.4993 [2021-03-26 00:49:27 swin_small_patch4_window7_224] INFO: Epoch: [117] [1160/1251] eta: 0:00:46 lr: 0.000668 loss: 3.4323 (3.4287) grad_norm: 1.2201 (inf) time: 0.5070 [2021-03-26 00:49:32 swin_small_patch4_window7_224] INFO: Epoch: [117] [1170/1251] eta: 0:00:41 lr: 0.000668 loss: 3.5332 (3.4289) grad_norm: 1.2201 (inf) time: 0.5098 [2021-03-26 00:49:37 swin_small_patch4_window7_224] INFO: Epoch: [117] [1180/1251] eta: 0:00:36 lr: 0.000668 loss: 3.4136 (3.4271) grad_norm: 1.2188 (inf) time: 0.5123 [2021-03-26 00:49:43 swin_small_patch4_window7_224] INFO: Epoch: [117] [1190/1251] eta: 0:00:31 lr: 0.000668 loss: 3.5595 (3.4285) grad_norm: 1.2270 (inf) time: 0.5120 [2021-03-26 00:49:48 swin_small_patch4_window7_224] INFO: Epoch: [117] [1200/1251] eta: 0:00:26 lr: 0.000668 loss: 3.5963 (3.4278) grad_norm: 1.1365 (inf) time: 0.5081 [2021-03-26 00:49:53 swin_small_patch4_window7_224] INFO: Epoch: [117] [1210/1251] eta: 0:00:20 lr: 0.000668 loss: 3.5967 (3.4303) grad_norm: 1.1805 (inf) time: 0.5057 [2021-03-26 00:49:58 swin_small_patch4_window7_224] INFO: Epoch: [117] [1220/1251] eta: 0:00:15 lr: 0.000668 loss: 3.7662 (3.4331) grad_norm: 1.2620 (inf) time: 0.5069 [2021-03-26 00:50:03 swin_small_patch4_window7_224] INFO: Epoch: [117] [1230/1251] eta: 0:00:10 lr: 0.000668 loss: 3.6155 (3.4333) grad_norm: 1.2389 (inf) time: 0.5024 [2021-03-26 00:50:08 swin_small_patch4_window7_224] INFO: Epoch: [117] [1240/1251] eta: 0:00:05 lr: 0.000668 loss: 3.6077 (3.4329) grad_norm: 1.2069 (inf) time: 0.5004 [2021-03-26 00:50:13 swin_small_patch4_window7_224] INFO: Epoch: [117] [1250/1251] eta: 0:00:00 lr: 0.000668 loss: 3.7386 (3.4350) grad_norm: 1.2439 (inf) time: 0.5011 [2021-03-26 00:50:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:51 loss: 0.8208 (0.8208) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-26 00:50:23 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 1.0385 (1.0651) acc1: 71.8750 (73.7216) acc5: 92.1875 (93.0398) [2021-03-26 00:50:26 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 1.0120 (1.0069) acc1: 75.0000 (75.2976) acc5: 93.7500 (93.9732) [2021-03-26 00:50:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9501 (0.9745) acc1: 76.5625 (76.0585) acc5: 95.3125 (94.4052) [2021-03-26 00:50:29 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9329 (0.9732) acc1: 79.6875 (76.4101) acc5: 95.3125 (94.0549) [2021-03-26 00:50:29 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0270 (0.9845) acc1: 73.4375 (76.1600) acc5: 93.7500 (93.9840) [2021-03-26 00:50:37 swin_small_patch4_window7_224] INFO: * Acc@1 76.998 Acc@5 93.976 loss 0.971 [2021-03-26 00:50:37 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.0% [2021-03-26 00:50:37 swin_small_patch4_window7_224] INFO: Max accuracy: 77.05% [2021-03-26 00:50:41 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 0/1251] eta: 1:30:36 lr: 0.000668 loss: 2.4255 (2.4255) grad_norm: 1.3178 (1.3178) time: 4.3460 [2021-03-26 00:50:46 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 10/1251] eta: 0:17:47 lr: 0.000668 loss: 3.4213 (3.3872) grad_norm: 1.2093 (1.2848) time: 0.8603 [2021-03-26 00:50:52 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 20/1251] eta: 0:14:15 lr: 0.000668 loss: 3.4366 (3.4763) grad_norm: 1.1970 (1.2461) time: 0.5120 [2021-03-26 00:50:57 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 30/1251] eta: 0:12:50 lr: 0.000668 loss: 3.5391 (3.5007) grad_norm: 1.1851 (1.2325) time: 0.5054 [2021-03-26 00:51:02 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 40/1251] eta: 0:12:12 lr: 0.000668 loss: 3.5036 (3.4654) grad_norm: 1.1828 (1.2278) time: 0.5113 [2021-03-26 00:51:07 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 50/1251] eta: 0:11:42 lr: 0.000668 loss: 3.6725 (3.5243) grad_norm: 1.2023 (1.2264) time: 0.5135 [2021-03-26 00:51:12 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 60/1251] eta: 0:11:21 lr: 0.000668 loss: 3.7367 (3.5469) grad_norm: 1.2471 (1.2333) time: 0.5044 [2021-03-26 00:51:17 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 70/1251] eta: 0:11:04 lr: 0.000668 loss: 3.3051 (3.4654) grad_norm: 1.2358 (1.2324) time: 0.5042 [2021-03-26 00:51:22 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 80/1251] eta: 0:10:49 lr: 0.000667 loss: 3.3909 (3.4793) grad_norm: 1.1999 (1.2287) time: 0.4999 [2021-03-26 00:51:27 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 90/1251] eta: 0:10:37 lr: 0.000667 loss: 3.5372 (3.4583) grad_norm: 1.1642 (1.2231) time: 0.5033 [2021-03-26 00:51:32 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 100/1251] eta: 0:10:26 lr: 0.000667 loss: 3.4217 (3.4503) grad_norm: 1.1804 (1.2194) time: 0.5056 [2021-03-26 00:51:37 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 110/1251] eta: 0:10:17 lr: 0.000667 loss: 3.5991 (3.4682) grad_norm: 1.1946 (1.2286) time: 0.5059 [2021-03-26 00:51:42 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 120/1251] eta: 0:10:09 lr: 0.000667 loss: 3.6747 (3.4614) grad_norm: 1.2116 (1.2313) time: 0.5094 [2021-03-26 00:51:47 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 130/1251] eta: 0:10:02 lr: 0.000667 loss: 3.3890 (3.4385) grad_norm: 1.2116 (1.2307) time: 0.5122 [2021-03-26 00:51:52 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 140/1251] eta: 0:09:54 lr: 0.000667 loss: 3.2965 (3.4294) grad_norm: 1.2195 (1.2347) time: 0.5095 [2021-03-26 00:51:57 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 150/1251] eta: 0:09:46 lr: 0.000667 loss: 3.3809 (3.4374) grad_norm: 1.2410 (1.2373) time: 0.5023 [2021-03-26 00:52:02 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 160/1251] eta: 0:09:39 lr: 0.000667 loss: 3.6749 (3.4431) grad_norm: 1.2692 (1.2376) time: 0.5029 [2021-03-26 00:52:07 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 170/1251] eta: 0:09:31 lr: 0.000667 loss: 3.7036 (3.4609) grad_norm: 1.2692 (1.2418) time: 0.5007 [2021-03-26 00:52:13 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 180/1251] eta: 0:09:25 lr: 0.000667 loss: 3.7434 (3.4709) grad_norm: 1.2583 (1.2411) time: 0.5079 [2021-03-26 00:52:18 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 190/1251] eta: 0:09:19 lr: 0.000667 loss: 3.4813 (3.4664) grad_norm: 1.1891 (1.2417) time: 0.5148 [2021-03-26 00:52:23 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 200/1251] eta: 0:09:12 lr: 0.000667 loss: 3.4429 (3.4613) grad_norm: 1.1822 (1.2400) time: 0.5065 [2021-03-26 00:52:28 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 210/1251] eta: 0:09:06 lr: 0.000667 loss: 3.3060 (3.4556) grad_norm: 1.1822 (1.2382) time: 0.5050 [2021-03-26 00:52:33 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 220/1251] eta: 0:09:00 lr: 0.000667 loss: 3.3301 (3.4496) grad_norm: 1.1827 (1.2357) time: 0.5101 [2021-03-26 00:52:38 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 230/1251] eta: 0:08:54 lr: 0.000667 loss: 3.5265 (3.4484) grad_norm: 1.1827 (1.2347) time: 0.5091 [2021-03-26 00:52:43 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 240/1251] eta: 0:08:48 lr: 0.000667 loss: 3.3449 (3.4401) grad_norm: 1.1861 (1.2333) time: 0.5023 [2021-03-26 00:52:48 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 250/1251] eta: 0:08:42 lr: 0.000667 loss: 3.3449 (3.4389) grad_norm: 1.2600 (1.2355) time: 0.5035 [2021-03-26 00:52:53 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 260/1251] eta: 0:08:37 lr: 0.000667 loss: 3.3718 (3.4289) grad_norm: 1.2107 (1.2348) time: 0.5145 [2021-03-26 00:52:58 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 270/1251] eta: 0:08:31 lr: 0.000667 loss: 3.2672 (3.4173) grad_norm: 1.1833 (1.2357) time: 0.5114 [2021-03-26 00:53:03 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 280/1251] eta: 0:08:25 lr: 0.000667 loss: 3.3782 (3.4271) grad_norm: 1.2365 (1.2379) time: 0.5067 [2021-03-26 00:53:08 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 290/1251] eta: 0:08:19 lr: 0.000667 loss: 3.7411 (3.4274) grad_norm: 1.2941 (nan) time: 0.5021 [2021-03-26 00:53:14 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 300/1251] eta: 0:08:14 lr: 0.000667 loss: 3.5041 (3.4234) grad_norm: 1.2245 (nan) time: 0.5013 [2021-03-26 00:53:19 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 310/1251] eta: 0:08:09 lr: 0.000667 loss: 3.2053 (3.4182) grad_norm: 1.2875 (nan) time: 0.5155 [2021-03-26 00:53:24 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 320/1251] eta: 0:08:04 lr: 0.000667 loss: 3.1517 (3.4088) grad_norm: 1.2875 (nan) time: 0.5224 [2021-03-26 00:53:29 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 330/1251] eta: 0:07:58 lr: 0.000666 loss: 3.5782 (3.4191) grad_norm: 1.2797 (nan) time: 0.5086 [2021-03-26 00:53:34 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 340/1251] eta: 0:07:52 lr: 0.000666 loss: 3.6802 (3.4161) grad_norm: 1.2957 (nan) time: 0.4999 [2021-03-26 00:53:39 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 350/1251] eta: 0:07:47 lr: 0.000666 loss: 3.5711 (3.4222) grad_norm: 1.2561 (nan) time: 0.5069 [2021-03-26 00:53:44 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 360/1251] eta: 0:07:41 lr: 0.000666 loss: 3.5711 (3.4251) grad_norm: 1.2288 (nan) time: 0.5049 [2021-03-26 00:53:49 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 370/1251] eta: 0:07:35 lr: 0.000666 loss: 3.5618 (3.4308) grad_norm: 1.2288 (nan) time: 0.4993 [2021-03-26 00:53:54 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 380/1251] eta: 0:07:30 lr: 0.000666 loss: 3.6091 (3.4287) grad_norm: 1.2569 (nan) time: 0.5035 [2021-03-26 00:53:59 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 390/1251] eta: 0:07:25 lr: 0.000666 loss: 3.6091 (3.4298) grad_norm: 1.2606 (nan) time: 0.5090 [2021-03-26 00:54:04 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 400/1251] eta: 0:07:19 lr: 0.000666 loss: 3.7305 (3.4350) grad_norm: 1.2270 (nan) time: 0.5077 [2021-03-26 00:54:09 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 410/1251] eta: 0:07:14 lr: 0.000666 loss: 3.4002 (3.4238) grad_norm: 1.2557 (nan) time: 0.5060 [2021-03-26 00:54:14 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 420/1251] eta: 0:07:08 lr: 0.000666 loss: 3.3938 (3.4250) grad_norm: 1.2511 (nan) time: 0.5019 [2021-03-26 00:54:19 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 430/1251] eta: 0:07:03 lr: 0.000666 loss: 3.6106 (3.4276) grad_norm: 1.1993 (nan) time: 0.5039 [2021-03-26 00:54:24 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 440/1251] eta: 0:06:58 lr: 0.000666 loss: 3.7096 (3.4312) grad_norm: 1.2149 (nan) time: 0.5038 [2021-03-26 00:54:30 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 450/1251] eta: 0:06:52 lr: 0.000666 loss: 3.4271 (3.4298) grad_norm: 1.2467 (nan) time: 0.5090 [2021-03-26 00:54:35 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 460/1251] eta: 0:06:47 lr: 0.000666 loss: 3.2585 (3.4236) grad_norm: 1.2101 (nan) time: 0.5112 [2021-03-26 00:54:40 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 470/1251] eta: 0:06:42 lr: 0.000666 loss: 3.3036 (3.4221) grad_norm: 1.1717 (nan) time: 0.5044 [2021-03-26 00:54:45 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 480/1251] eta: 0:06:36 lr: 0.000666 loss: 3.3804 (3.4251) grad_norm: 1.2068 (nan) time: 0.5012 [2021-03-26 00:54:50 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 490/1251] eta: 0:06:31 lr: 0.000666 loss: 3.7029 (3.4302) grad_norm: 1.2642 (nan) time: 0.4992 [2021-03-26 00:54:55 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 500/1251] eta: 0:06:26 lr: 0.000666 loss: 3.6427 (3.4325) grad_norm: 1.3365 (nan) time: 0.5021 [2021-03-26 00:55:00 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 510/1251] eta: 0:06:20 lr: 0.000666 loss: 3.3930 (3.4267) grad_norm: 1.2216 (nan) time: 0.5085 [2021-03-26 00:55:05 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 520/1251] eta: 0:06:15 lr: 0.000666 loss: 3.4998 (3.4308) grad_norm: 1.2214 (nan) time: 0.5095 [2021-03-26 00:55:10 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 530/1251] eta: 0:06:10 lr: 0.000666 loss: 3.5874 (3.4306) grad_norm: 1.2039 (nan) time: 0.5058 [2021-03-26 00:55:15 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 540/1251] eta: 0:06:05 lr: 0.000666 loss: 3.5874 (3.4321) grad_norm: 1.1784 (nan) time: 0.5035 [2021-03-26 00:55:20 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 550/1251] eta: 0:06:00 lr: 0.000666 loss: 3.2827 (3.4288) grad_norm: 1.1692 (nan) time: 0.5135 [2021-03-26 00:55:25 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 560/1251] eta: 0:05:54 lr: 0.000666 loss: 3.5448 (3.4309) grad_norm: 1.2070 (nan) time: 0.5102 [2021-03-26 00:55:30 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 570/1251] eta: 0:05:49 lr: 0.000666 loss: 3.5707 (3.4341) grad_norm: 1.2244 (nan) time: 0.4985 [2021-03-26 00:55:35 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 580/1251] eta: 0:05:44 lr: 0.000666 loss: 3.6396 (3.4378) grad_norm: 1.2018 (nan) time: 0.5043 [2021-03-26 00:55:40 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 590/1251] eta: 0:05:39 lr: 0.000665 loss: 3.7324 (3.4394) grad_norm: 1.1627 (nan) time: 0.5069 [2021-03-26 00:55:46 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 600/1251] eta: 0:05:34 lr: 0.000665 loss: 3.7324 (3.4422) grad_norm: 1.1929 (nan) time: 0.5137 [2021-03-26 00:55:51 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 610/1251] eta: 0:05:28 lr: 0.000665 loss: 3.4207 (3.4377) grad_norm: 1.1929 (nan) time: 0.5100 [2021-03-26 00:55:56 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 620/1251] eta: 0:05:23 lr: 0.000665 loss: 3.4669 (3.4425) grad_norm: 1.1869 (nan) time: 0.5042 [2021-03-26 00:56:01 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 630/1251] eta: 0:05:18 lr: 0.000665 loss: 3.6264 (3.4424) grad_norm: 1.1568 (nan) time: 0.5056 [2021-03-26 00:56:06 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 640/1251] eta: 0:05:13 lr: 0.000665 loss: 3.6220 (3.4466) grad_norm: 1.1379 (nan) time: 0.5034 [2021-03-26 00:56:11 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 650/1251] eta: 0:05:08 lr: 0.000665 loss: 3.5966 (3.4452) grad_norm: 1.1644 (nan) time: 0.5042 [2021-03-26 00:56:16 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 660/1251] eta: 0:05:02 lr: 0.000665 loss: 3.4200 (3.4461) grad_norm: 1.2609 (nan) time: 0.5038 [2021-03-26 00:56:21 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 670/1251] eta: 0:04:57 lr: 0.000665 loss: 3.5026 (3.4456) grad_norm: 1.2224 (nan) time: 0.5013 [2021-03-26 00:56:26 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 680/1251] eta: 0:04:52 lr: 0.000665 loss: 3.3255 (3.4428) grad_norm: 1.2354 (nan) time: 0.5056 [2021-03-26 00:56:31 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 690/1251] eta: 0:04:47 lr: 0.000665 loss: 3.2849 (3.4400) grad_norm: 1.2412 (nan) time: 0.5077 [2021-03-26 00:56:36 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 700/1251] eta: 0:04:42 lr: 0.000665 loss: 3.3997 (3.4410) grad_norm: 1.2139 (nan) time: 0.5007 [2021-03-26 00:56:41 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 710/1251] eta: 0:04:36 lr: 0.000665 loss: 3.6149 (3.4425) grad_norm: 1.2113 (nan) time: 0.4982 [2021-03-26 00:56:46 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 720/1251] eta: 0:04:31 lr: 0.000665 loss: 3.5462 (3.4411) grad_norm: 1.1988 (nan) time: 0.5015 [2021-03-26 00:56:51 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 730/1251] eta: 0:04:26 lr: 0.000665 loss: 3.5165 (3.4423) grad_norm: 1.2430 (nan) time: 0.5070 [2021-03-26 00:56:56 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 740/1251] eta: 0:04:21 lr: 0.000665 loss: 3.5165 (3.4417) grad_norm: 1.2580 (nan) time: 0.5242 [2021-03-26 00:57:02 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 750/1251] eta: 0:04:16 lr: 0.000665 loss: 3.3130 (3.4369) grad_norm: 1.2509 (nan) time: 0.5255 [2021-03-26 00:57:07 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 760/1251] eta: 0:04:11 lr: 0.000665 loss: 3.3475 (3.4392) grad_norm: 1.2544 (nan) time: 0.5098 [2021-03-26 00:57:12 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 770/1251] eta: 0:04:06 lr: 0.000665 loss: 3.5922 (3.4410) grad_norm: 1.2544 (nan) time: 0.5070 [2021-03-26 00:57:17 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 780/1251] eta: 0:04:01 lr: 0.000665 loss: 3.6453 (3.4430) grad_norm: 1.2277 (nan) time: 0.5064 [2021-03-26 00:57:22 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 790/1251] eta: 0:03:55 lr: 0.000665 loss: 3.7269 (3.4456) grad_norm: 1.2321 (nan) time: 0.5114 [2021-03-26 00:57:27 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 800/1251] eta: 0:03:50 lr: 0.000665 loss: 3.7418 (3.4462) grad_norm: 1.2262 (nan) time: 0.5086 [2021-03-26 00:57:32 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 810/1251] eta: 0:03:45 lr: 0.000665 loss: 3.5338 (3.4469) grad_norm: 1.1687 (nan) time: 0.4984 [2021-03-26 00:57:37 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 820/1251] eta: 0:03:40 lr: 0.000665 loss: 3.3571 (3.4442) grad_norm: 1.1687 (nan) time: 0.5007 [2021-03-26 00:57:42 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 830/1251] eta: 0:03:35 lr: 0.000665 loss: 3.3117 (3.4417) grad_norm: 1.1556 (nan) time: 0.5069 [2021-03-26 00:57:47 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 840/1251] eta: 0:03:30 lr: 0.000664 loss: 3.4217 (3.4432) grad_norm: 1.1943 (nan) time: 0.5056 [2021-03-26 00:57:52 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 850/1251] eta: 0:03:25 lr: 0.000664 loss: 3.4217 (3.4431) grad_norm: 1.2036 (nan) time: 0.5091 [2021-03-26 00:57:57 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 860/1251] eta: 0:03:19 lr: 0.000664 loss: 3.3847 (3.4440) grad_norm: 1.1811 (nan) time: 0.5125 [2021-03-26 00:58:02 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 870/1251] eta: 0:03:14 lr: 0.000664 loss: 3.5126 (3.4449) grad_norm: 1.2295 (nan) time: 0.5055 [2021-03-26 00:58:07 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 880/1251] eta: 0:03:09 lr: 0.000664 loss: 3.5555 (3.4410) grad_norm: 1.2295 (nan) time: 0.5079 [2021-03-26 00:58:13 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 890/1251] eta: 0:03:04 lr: 0.000664 loss: 2.8259 (3.4369) grad_norm: 1.1717 (nan) time: 0.5093 [2021-03-26 00:58:18 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 900/1251] eta: 0:02:59 lr: 0.000664 loss: 3.4700 (3.4382) grad_norm: 1.1717 (nan) time: 0.5060 [2021-03-26 00:58:23 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 910/1251] eta: 0:02:54 lr: 0.000664 loss: 3.7182 (3.4429) grad_norm: 1.2069 (nan) time: 0.5069 [2021-03-26 00:58:28 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 920/1251] eta: 0:02:49 lr: 0.000664 loss: 3.7084 (3.4409) grad_norm: 1.1656 (nan) time: 0.5070 [2021-03-26 00:58:33 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 930/1251] eta: 0:02:43 lr: 0.000664 loss: 3.2818 (3.4408) grad_norm: 1.1971 (nan) time: 0.5032 [2021-03-26 00:58:38 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 940/1251] eta: 0:02:38 lr: 0.000664 loss: 3.5047 (3.4412) grad_norm: 1.1996 (nan) time: 0.5059 [2021-03-26 00:58:43 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 950/1251] eta: 0:02:33 lr: 0.000664 loss: 3.6678 (3.4411) grad_norm: 1.2193 (nan) time: 0.5092 [2021-03-26 00:58:48 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 960/1251] eta: 0:02:28 lr: 0.000664 loss: 3.5566 (3.4392) grad_norm: 1.2193 (nan) time: 0.5068 [2021-03-26 00:58:53 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 970/1251] eta: 0:02:23 lr: 0.000664 loss: 3.5566 (3.4412) grad_norm: 1.2177 (nan) time: 0.5061 [2021-03-26 00:58:58 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 980/1251] eta: 0:02:18 lr: 0.000664 loss: 3.4281 (3.4398) grad_norm: 1.1952 (nan) time: 0.5017 [2021-03-26 00:59:03 swin_small_patch4_window7_224] INFO: Epoch: [118] [ 990/1251] eta: 0:02:13 lr: 0.000664 loss: 3.4281 (3.4390) grad_norm: 1.2087 (nan) time: 0.5057 [2021-03-26 00:59:08 swin_small_patch4_window7_224] INFO: Epoch: [118] [1000/1251] eta: 0:02:08 lr: 0.000664 loss: 3.4341 (3.4375) grad_norm: 1.2087 (nan) time: 0.5168 [2021-03-26 00:59:13 swin_small_patch4_window7_224] INFO: Epoch: [118] [1010/1251] eta: 0:02:03 lr: 0.000664 loss: 3.5306 (3.4380) grad_norm: 1.2032 (nan) time: 0.5104 [2021-03-26 00:59:18 swin_small_patch4_window7_224] INFO: Epoch: [118] [1020/1251] eta: 0:01:57 lr: 0.000664 loss: 3.7262 (3.4395) grad_norm: 1.2258 (nan) time: 0.4984 [2021-03-26 00:59:23 swin_small_patch4_window7_224] INFO: Epoch: [118] [1030/1251] eta: 0:01:52 lr: 0.000664 loss: 3.6606 (3.4415) grad_norm: 1.2049 (nan) time: 0.4997 [2021-03-26 00:59:28 swin_small_patch4_window7_224] INFO: Epoch: [118] [1040/1251] eta: 0:01:47 lr: 0.000664 loss: 3.5557 (3.4423) grad_norm: 1.1886 (nan) time: 0.5024 [2021-03-26 00:59:34 swin_small_patch4_window7_224] INFO: Epoch: [118] [1050/1251] eta: 0:01:42 lr: 0.000664 loss: 3.3962 (3.4425) grad_norm: 1.1872 (nan) time: 0.5111 [2021-03-26 00:59:39 swin_small_patch4_window7_224] INFO: Epoch: [118] [1060/1251] eta: 0:01:37 lr: 0.000664 loss: 3.4050 (3.4427) grad_norm: 1.1848 (nan) time: 0.5129 [2021-03-26 00:59:44 swin_small_patch4_window7_224] INFO: Epoch: [118] [1070/1251] eta: 0:01:32 lr: 0.000664 loss: 3.4391 (3.4425) grad_norm: 1.1673 (nan) time: 0.5108 [2021-03-26 00:59:49 swin_small_patch4_window7_224] INFO: Epoch: [118] [1080/1251] eta: 0:01:27 lr: 0.000664 loss: 3.4391 (3.4441) grad_norm: 1.1878 (nan) time: 0.5052 [2021-03-26 00:59:54 swin_small_patch4_window7_224] INFO: Epoch: [118] [1090/1251] eta: 0:01:22 lr: 0.000664 loss: 3.4074 (3.4416) grad_norm: 1.1941 (nan) time: 0.5019 [2021-03-26 00:59:59 swin_small_patch4_window7_224] INFO: Epoch: [118] [1100/1251] eta: 0:01:17 lr: 0.000663 loss: 3.1533 (3.4382) grad_norm: 1.1941 (nan) time: 0.5038 [2021-03-26 01:00:04 swin_small_patch4_window7_224] INFO: Epoch: [118] [1110/1251] eta: 0:01:11 lr: 0.000663 loss: 3.3605 (3.4401) grad_norm: 1.1997 (nan) time: 0.4975 [2021-03-26 01:00:09 swin_small_patch4_window7_224] INFO: Epoch: [118] [1120/1251] eta: 0:01:06 lr: 0.000663 loss: 3.5737 (3.4409) grad_norm: 1.1999 (nan) time: 0.4945 [2021-03-26 01:00:14 swin_small_patch4_window7_224] INFO: Epoch: [118] [1130/1251] eta: 0:01:01 lr: 0.000663 loss: 3.5737 (3.4422) grad_norm: 1.2341 (nan) time: 0.4961 [2021-03-26 01:00:19 swin_small_patch4_window7_224] INFO: Epoch: [118] [1140/1251] eta: 0:00:56 lr: 0.000663 loss: 3.5514 (3.4409) grad_norm: 1.2321 (nan) time: 0.4999 [2021-03-26 01:00:24 swin_small_patch4_window7_224] INFO: Epoch: [118] [1150/1251] eta: 0:00:51 lr: 0.000663 loss: 3.5182 (3.4420) grad_norm: 1.2731 (nan) time: 0.5032 [2021-03-26 01:00:29 swin_small_patch4_window7_224] INFO: Epoch: [118] [1160/1251] eta: 0:00:46 lr: 0.000663 loss: 3.5956 (3.4438) grad_norm: 1.2911 (nan) time: 0.5033 [2021-03-26 01:00:34 swin_small_patch4_window7_224] INFO: Epoch: [118] [1170/1251] eta: 0:00:41 lr: 0.000663 loss: 3.4728 (3.4417) grad_norm: 1.2649 (nan) time: 0.4980 [2021-03-26 01:00:39 swin_small_patch4_window7_224] INFO: Epoch: [118] [1180/1251] eta: 0:00:36 lr: 0.000663 loss: 3.2826 (3.4407) grad_norm: 1.2741 (nan) time: 0.5002 [2021-03-26 01:00:44 swin_small_patch4_window7_224] INFO: Epoch: [118] [1190/1251] eta: 0:00:31 lr: 0.000663 loss: 3.3813 (3.4394) grad_norm: 1.2812 (nan) time: 0.5090 [2021-03-26 01:00:49 swin_small_patch4_window7_224] INFO: Epoch: [118] [1200/1251] eta: 0:00:25 lr: 0.000663 loss: 3.3813 (3.4391) grad_norm: 1.2494 (nan) time: 0.5143 [2021-03-26 01:00:54 swin_small_patch4_window7_224] INFO: Epoch: [118] [1210/1251] eta: 0:00:20 lr: 0.000663 loss: 3.4817 (3.4409) grad_norm: 1.2189 (nan) time: 0.5111 [2021-03-26 01:00:59 swin_small_patch4_window7_224] INFO: Epoch: [118] [1220/1251] eta: 0:00:15 lr: 0.000663 loss: 3.5119 (3.4394) grad_norm: 1.1684 (nan) time: 0.5038 [2021-03-26 01:01:04 swin_small_patch4_window7_224] INFO: Epoch: [118] [1230/1251] eta: 0:00:10 lr: 0.000663 loss: 3.1995 (3.4375) grad_norm: 1.1849 (nan) time: 0.5007 [2021-03-26 01:01:09 swin_small_patch4_window7_224] INFO: Epoch: [118] [1240/1251] eta: 0:00:05 lr: 0.000663 loss: 3.4965 (3.4389) grad_norm: 1.2249 (nan) time: 0.5018 [2021-03-26 01:01:14 swin_small_patch4_window7_224] INFO: Epoch: [118] [1250/1251] eta: 0:00:00 lr: 0.000663 loss: 3.4483 (3.4374) grad_norm: 1.2126 (nan) time: 0.5036 [2021-03-26 01:01:21 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:25 loss: 0.6622 (0.6622) acc1: 85.9375 (85.9375) acc5: 96.8750 (96.8750) [2021-03-26 01:01:23 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7648 (0.7831) acc1: 81.2500 (81.1080) acc5: 96.8750 (96.7330) [2021-03-26 01:01:25 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8662 (0.8938) acc1: 75.0000 (77.3810) acc5: 95.3125 (95.2381) [2021-03-26 01:01:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0877 (0.9702) acc1: 75.0000 (76.4617) acc5: 92.1875 (93.8508) [2021-03-26 01:01:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0526 (0.9801) acc1: 75.0000 (76.1052) acc5: 92.1875 (93.8643) [2021-03-26 01:01:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9457 (0.9943) acc1: 75.0000 (75.9360) acc5: 93.7500 (93.8560) [2021-03-26 01:01:36 swin_small_patch4_window7_224] INFO: * Acc@1 76.710 Acc@5 93.802 loss 0.983 [2021-03-26 01:01:36 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.7% [2021-03-26 01:01:36 swin_small_patch4_window7_224] INFO: Max accuracy: 77.05% [2021-03-26 01:01:40 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 0/1251] eta: 1:23:38 lr: 0.000663 loss: 3.8843 (3.8843) grad_norm: 1.1372 (1.1372) time: 4.0112 [2021-03-26 01:01:45 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 10/1251] eta: 0:17:16 lr: 0.000663 loss: 3.6690 (3.3027) grad_norm: 1.2711 (1.2981) time: 0.8350 [2021-03-26 01:01:50 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 20/1251] eta: 0:13:49 lr: 0.000663 loss: 3.5566 (3.4027) grad_norm: 1.2200 (1.2639) time: 0.5067 [2021-03-26 01:01:55 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 30/1251] eta: 0:12:35 lr: 0.000663 loss: 3.4047 (3.3841) grad_norm: 1.1924 (1.2670) time: 0.5003 [2021-03-26 01:02:00 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 40/1251] eta: 0:11:54 lr: 0.000663 loss: 3.5761 (3.4627) grad_norm: 1.2771 (1.2756) time: 0.5029 [2021-03-26 01:02:05 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 50/1251] eta: 0:11:29 lr: 0.000663 loss: 3.7551 (3.4798) grad_norm: 1.3080 (1.2794) time: 0.5055 [2021-03-26 01:02:10 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 60/1251] eta: 0:11:09 lr: 0.000663 loss: 3.2746 (3.4058) grad_norm: 1.2495 (1.2727) time: 0.5045 [2021-03-26 01:02:15 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 70/1251] eta: 0:10:54 lr: 0.000663 loss: 3.1432 (3.3721) grad_norm: 1.1882 (1.2557) time: 0.5034 [2021-03-26 01:02:20 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 80/1251] eta: 0:10:40 lr: 0.000663 loss: 3.3142 (3.3676) grad_norm: 1.1509 (1.2526) time: 0.5006 [2021-03-26 01:02:26 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 90/1251] eta: 0:10:31 lr: 0.000663 loss: 3.4820 (3.3850) grad_norm: 1.2690 (1.2619) time: 0.5072 [2021-03-26 01:02:31 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 100/1251] eta: 0:10:21 lr: 0.000662 loss: 3.4820 (3.3788) grad_norm: 1.3111 (1.2640) time: 0.5130 [2021-03-26 01:02:36 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 110/1251] eta: 0:10:12 lr: 0.000662 loss: 3.4641 (3.3843) grad_norm: 1.2559 (1.2659) time: 0.5042 [2021-03-26 01:02:41 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 120/1251] eta: 0:10:04 lr: 0.000662 loss: 3.4641 (3.3862) grad_norm: 1.2122 (1.2608) time: 0.5046 [2021-03-26 01:02:46 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 130/1251] eta: 0:09:57 lr: 0.000662 loss: 3.1956 (3.3730) grad_norm: 1.1489 (1.2567) time: 0.5094 [2021-03-26 01:02:51 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 140/1251] eta: 0:09:49 lr: 0.000662 loss: 3.1806 (3.3746) grad_norm: 1.1802 (1.2538) time: 0.5104 [2021-03-26 01:02:56 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 150/1251] eta: 0:09:42 lr: 0.000662 loss: 3.5399 (3.3749) grad_norm: 1.1966 (1.2498) time: 0.5033 [2021-03-26 01:03:01 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 160/1251] eta: 0:09:34 lr: 0.000662 loss: 3.3788 (3.3677) grad_norm: 1.2441 (1.2503) time: 0.4989 [2021-03-26 01:03:06 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 170/1251] eta: 0:09:28 lr: 0.000662 loss: 3.4940 (3.3761) grad_norm: 1.2815 (1.2551) time: 0.5022 [2021-03-26 01:03:11 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 180/1251] eta: 0:09:21 lr: 0.000662 loss: 3.5489 (3.3787) grad_norm: 1.2862 (1.2571) time: 0.5059 [2021-03-26 01:03:16 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 190/1251] eta: 0:09:16 lr: 0.000662 loss: 3.0788 (3.3722) grad_norm: 1.2591 (1.2576) time: 0.5138 [2021-03-26 01:03:21 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 200/1251] eta: 0:09:10 lr: 0.000662 loss: 3.3075 (3.3724) grad_norm: 1.2915 (1.2625) time: 0.5127 [2021-03-26 01:03:26 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 210/1251] eta: 0:09:03 lr: 0.000662 loss: 3.5283 (3.3801) grad_norm: 1.2409 (1.2600) time: 0.5028 [2021-03-26 01:03:31 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 220/1251] eta: 0:08:57 lr: 0.000662 loss: 3.6175 (3.3875) grad_norm: 1.1927 (1.2573) time: 0.5016 [2021-03-26 01:03:36 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 230/1251] eta: 0:08:51 lr: 0.000662 loss: 3.5862 (3.3925) grad_norm: 1.2087 (1.2582) time: 0.5015 [2021-03-26 01:03:41 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 240/1251] eta: 0:08:45 lr: 0.000662 loss: 3.4440 (3.3943) grad_norm: 1.2360 (1.2561) time: 0.5018 [2021-03-26 01:03:46 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 250/1251] eta: 0:08:39 lr: 0.000662 loss: 3.4800 (3.3923) grad_norm: 1.2268 (1.2579) time: 0.5029 [2021-03-26 01:03:52 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 260/1251] eta: 0:08:34 lr: 0.000662 loss: 3.1730 (3.3866) grad_norm: 1.2118 (1.2547) time: 0.5102 [2021-03-26 01:03:57 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 270/1251] eta: 0:08:28 lr: 0.000662 loss: 3.2379 (3.3832) grad_norm: 1.1820 (1.2538) time: 0.5118 [2021-03-26 01:04:02 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 280/1251] eta: 0:08:22 lr: 0.000662 loss: 2.9570 (3.3693) grad_norm: 1.2167 (1.2530) time: 0.5016 [2021-03-26 01:04:07 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 290/1251] eta: 0:08:17 lr: 0.000662 loss: 2.9249 (3.3637) grad_norm: 1.2060 (1.2530) time: 0.4993 [2021-03-26 01:04:12 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 300/1251] eta: 0:08:11 lr: 0.000662 loss: 3.2456 (3.3613) grad_norm: 1.1955 (1.2516) time: 0.5062 [2021-03-26 01:04:17 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 310/1251] eta: 0:08:05 lr: 0.000662 loss: 3.5288 (3.3692) grad_norm: 1.2002 (1.2508) time: 0.5037 [2021-03-26 01:04:22 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 320/1251] eta: 0:08:00 lr: 0.000662 loss: 3.6296 (3.3747) grad_norm: 1.2234 (1.2508) time: 0.4955 [2021-03-26 01:04:27 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 330/1251] eta: 0:07:54 lr: 0.000662 loss: 3.4425 (3.3681) grad_norm: 1.2234 (1.2508) time: 0.5024 [2021-03-26 01:04:32 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 340/1251] eta: 0:07:49 lr: 0.000662 loss: 3.5276 (3.3706) grad_norm: 1.1927 (1.2502) time: 0.5044 [2021-03-26 01:04:37 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 350/1251] eta: 0:07:43 lr: 0.000662 loss: 3.5392 (3.3672) grad_norm: 1.1927 (1.2487) time: 0.5023 [2021-03-26 01:04:42 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 360/1251] eta: 0:07:38 lr: 0.000661 loss: 3.3516 (3.3702) grad_norm: 1.2004 (1.2490) time: 0.5030 [2021-03-26 01:04:47 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 370/1251] eta: 0:07:32 lr: 0.000661 loss: 3.5563 (3.3755) grad_norm: 1.2063 (1.2486) time: 0.5015 [2021-03-26 01:04:52 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 380/1251] eta: 0:07:27 lr: 0.000661 loss: 3.6495 (3.3835) grad_norm: 1.2063 (1.2501) time: 0.5027 [2021-03-26 01:04:57 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 390/1251] eta: 0:07:22 lr: 0.000661 loss: 3.6850 (3.3878) grad_norm: 1.2082 (1.2493) time: 0.5069 [2021-03-26 01:05:02 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 400/1251] eta: 0:07:16 lr: 0.000661 loss: 3.3942 (3.3816) grad_norm: 1.2077 (1.2472) time: 0.5032 [2021-03-26 01:05:07 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 410/1251] eta: 0:07:11 lr: 0.000661 loss: 3.2688 (3.3810) grad_norm: 1.2037 (1.2459) time: 0.4959 [2021-03-26 01:05:12 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 420/1251] eta: 0:07:05 lr: 0.000661 loss: 3.5011 (3.3811) grad_norm: 1.2037 (1.2462) time: 0.5000 [2021-03-26 01:05:17 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 430/1251] eta: 0:07:00 lr: 0.000661 loss: 3.2267 (3.3743) grad_norm: 1.2187 (1.2459) time: 0.4997 [2021-03-26 01:05:22 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 440/1251] eta: 0:06:55 lr: 0.000661 loss: 3.2267 (3.3732) grad_norm: 1.2187 (1.2459) time: 0.5002 [2021-03-26 01:05:27 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 450/1251] eta: 0:06:50 lr: 0.000661 loss: 3.5493 (3.3730) grad_norm: 1.2102 (1.2456) time: 0.5066 [2021-03-26 01:05:32 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 460/1251] eta: 0:06:44 lr: 0.000661 loss: 3.6616 (3.3747) grad_norm: 1.2304 (1.2462) time: 0.5056 [2021-03-26 01:05:37 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 470/1251] eta: 0:06:39 lr: 0.000661 loss: 3.5519 (3.3790) grad_norm: 1.2453 (1.2462) time: 0.5008 [2021-03-26 01:05:42 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 480/1251] eta: 0:06:34 lr: 0.000661 loss: 3.5279 (3.3794) grad_norm: 1.2619 (1.2486) time: 0.5012 [2021-03-26 01:05:47 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 490/1251] eta: 0:06:29 lr: 0.000661 loss: 3.6159 (3.3857) grad_norm: 1.2451 (1.2475) time: 0.5033 [2021-03-26 01:05:52 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 500/1251] eta: 0:06:23 lr: 0.000661 loss: 3.6078 (3.3881) grad_norm: 1.1866 (1.2465) time: 0.5082 [2021-03-26 01:05:57 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 510/1251] eta: 0:06:18 lr: 0.000661 loss: 3.4878 (3.3866) grad_norm: 1.2037 (1.2463) time: 0.5085 [2021-03-26 01:06:02 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 520/1251] eta: 0:06:13 lr: 0.000661 loss: 3.3772 (3.3883) grad_norm: 1.2664 (1.2475) time: 0.5063 [2021-03-26 01:06:07 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 530/1251] eta: 0:06:08 lr: 0.000661 loss: 3.3308 (3.3877) grad_norm: 1.2962 (1.2485) time: 0.5079 [2021-03-26 01:06:13 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 540/1251] eta: 0:06:03 lr: 0.000661 loss: 3.3356 (3.3885) grad_norm: 1.2742 (1.2472) time: 0.5087 [2021-03-26 01:06:18 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 550/1251] eta: 0:05:58 lr: 0.000661 loss: 3.5837 (3.3946) grad_norm: 1.1701 (1.2464) time: 0.5229 [2021-03-26 01:06:23 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 560/1251] eta: 0:05:53 lr: 0.000661 loss: 3.5359 (3.3938) grad_norm: 1.2104 (1.2464) time: 0.5202 [2021-03-26 01:06:28 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 570/1251] eta: 0:05:48 lr: 0.000661 loss: 3.5803 (3.3986) grad_norm: 1.2282 (1.2457) time: 0.5048 [2021-03-26 01:06:33 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 580/1251] eta: 0:05:42 lr: 0.000661 loss: 3.5803 (3.3989) grad_norm: 1.2282 (1.2462) time: 0.5061 [2021-03-26 01:06:38 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 590/1251] eta: 0:05:37 lr: 0.000661 loss: 3.3741 (3.3993) grad_norm: 1.2194 (1.2461) time: 0.5084 [2021-03-26 01:06:43 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 600/1251] eta: 0:05:32 lr: 0.000661 loss: 3.5334 (3.3997) grad_norm: 1.2046 (1.2459) time: 0.5076 [2021-03-26 01:06:48 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 610/1251] eta: 0:05:27 lr: 0.000660 loss: 3.5933 (3.4007) grad_norm: 1.2124 (1.2471) time: 0.5025 [2021-03-26 01:06:53 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 620/1251] eta: 0:05:22 lr: 0.000660 loss: 3.7314 (3.4061) grad_norm: 1.2667 (1.2479) time: 0.5010 [2021-03-26 01:06:58 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 630/1251] eta: 0:05:17 lr: 0.000660 loss: 3.7096 (3.4072) grad_norm: 1.2315 (1.2474) time: 0.5032 [2021-03-26 01:07:03 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 640/1251] eta: 0:05:11 lr: 0.000660 loss: 3.4496 (3.4038) grad_norm: 1.2057 (1.2470) time: 0.5052 [2021-03-26 01:07:08 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 650/1251] eta: 0:05:06 lr: 0.000660 loss: 3.4380 (3.4060) grad_norm: 1.1831 (1.2461) time: 0.5076 [2021-03-26 01:07:13 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 660/1251] eta: 0:05:01 lr: 0.000660 loss: 3.5586 (3.4076) grad_norm: 1.1831 (1.2457) time: 0.5074 [2021-03-26 01:07:19 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 670/1251] eta: 0:04:56 lr: 0.000660 loss: 3.6376 (3.4098) grad_norm: 1.2376 (1.2465) time: 0.5076 [2021-03-26 01:07:24 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 680/1251] eta: 0:04:51 lr: 0.000660 loss: 3.6376 (3.4096) grad_norm: 1.2395 (1.2465) time: 0.5148 [2021-03-26 01:07:29 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 690/1251] eta: 0:04:46 lr: 0.000660 loss: 3.4093 (3.4098) grad_norm: 1.1984 (1.2465) time: 0.5057 [2021-03-26 01:07:34 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 700/1251] eta: 0:04:41 lr: 0.000660 loss: 3.4656 (3.4100) grad_norm: 1.2244 (1.2475) time: 0.5009 [2021-03-26 01:07:39 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 710/1251] eta: 0:04:35 lr: 0.000660 loss: 3.4656 (3.4090) grad_norm: 1.3049 (1.2486) time: 0.5074 [2021-03-26 01:07:44 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 720/1251] eta: 0:04:30 lr: 0.000660 loss: 3.2102 (3.4055) grad_norm: 1.2477 (1.2489) time: 0.5035 [2021-03-26 01:07:49 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 730/1251] eta: 0:04:25 lr: 0.000660 loss: 3.2028 (3.4048) grad_norm: 1.2145 (1.2481) time: 0.5024 [2021-03-26 01:07:54 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 740/1251] eta: 0:04:20 lr: 0.000660 loss: 3.3089 (3.4022) grad_norm: 1.2080 (1.2480) time: 0.5278 [2021-03-26 01:07:59 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 750/1251] eta: 0:04:15 lr: 0.000660 loss: 3.4066 (3.4003) grad_norm: 1.2285 (1.2476) time: 0.5238 [2021-03-26 01:08:04 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 760/1251] eta: 0:04:10 lr: 0.000660 loss: 3.4066 (3.4016) grad_norm: 1.1499 (1.2478) time: 0.5017 [2021-03-26 01:08:10 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 770/1251] eta: 0:04:05 lr: 0.000660 loss: 3.4978 (3.4001) grad_norm: 1.1745 (1.2473) time: 0.5062 [2021-03-26 01:08:15 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 780/1251] eta: 0:04:00 lr: 0.000660 loss: 3.4652 (3.4010) grad_norm: 1.2463 (1.2478) time: 0.5019 [2021-03-26 01:08:20 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 790/1251] eta: 0:03:55 lr: 0.000660 loss: 3.4652 (3.4024) grad_norm: 1.3110 (1.2489) time: 0.5095 [2021-03-26 01:08:25 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 800/1251] eta: 0:03:50 lr: 0.000660 loss: 3.3312 (3.4032) grad_norm: 1.2754 (1.2489) time: 0.5123 [2021-03-26 01:08:30 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 810/1251] eta: 0:03:45 lr: 0.000660 loss: 3.3382 (3.4044) grad_norm: 1.2419 (1.2494) time: 0.5111 [2021-03-26 01:08:35 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 820/1251] eta: 0:03:39 lr: 0.000660 loss: 3.4499 (3.4043) grad_norm: 1.2257 (1.2490) time: 0.5153 [2021-03-26 01:08:40 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 830/1251] eta: 0:03:34 lr: 0.000660 loss: 3.4499 (3.4033) grad_norm: 1.1996 (1.2485) time: 0.5203 [2021-03-26 01:08:45 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 840/1251] eta: 0:03:29 lr: 0.000660 loss: 3.3818 (3.4010) grad_norm: 1.1953 (1.2477) time: 0.5135 [2021-03-26 01:08:51 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 850/1251] eta: 0:03:24 lr: 0.000660 loss: 3.3818 (3.3993) grad_norm: 1.1953 (1.2469) time: 0.5094 [2021-03-26 01:08:56 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 860/1251] eta: 0:03:19 lr: 0.000660 loss: 3.4684 (3.4005) grad_norm: 1.1955 (1.2469) time: 0.5124 [2021-03-26 01:09:01 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 870/1251] eta: 0:03:14 lr: 0.000659 loss: 3.5500 (3.4015) grad_norm: 1.2292 (1.2474) time: 0.5091 [2021-03-26 01:09:06 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 880/1251] eta: 0:03:09 lr: 0.000659 loss: 3.5500 (3.4009) grad_norm: 1.2289 (1.2473) time: 0.5068 [2021-03-26 01:09:11 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 890/1251] eta: 0:03:04 lr: 0.000659 loss: 3.5567 (3.4026) grad_norm: 1.1920 (1.2470) time: 0.5046 [2021-03-26 01:09:16 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 900/1251] eta: 0:02:59 lr: 0.000659 loss: 3.5268 (3.4011) grad_norm: 1.2036 (1.2472) time: 0.5091 [2021-03-26 01:09:21 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 910/1251] eta: 0:02:53 lr: 0.000659 loss: 3.3897 (3.3991) grad_norm: 1.2394 (1.2472) time: 0.5048 [2021-03-26 01:09:26 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 920/1251] eta: 0:02:48 lr: 0.000659 loss: 3.5765 (3.4025) grad_norm: 1.2394 (1.2473) time: 0.5022 [2021-03-26 01:09:31 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 930/1251] eta: 0:02:43 lr: 0.000659 loss: 3.6048 (3.4050) grad_norm: 1.2556 (1.2476) time: 0.5137 [2021-03-26 01:09:36 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 940/1251] eta: 0:02:38 lr: 0.000659 loss: 3.5342 (3.4041) grad_norm: 1.2592 (1.2480) time: 0.5136 [2021-03-26 01:09:41 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 950/1251] eta: 0:02:33 lr: 0.000659 loss: 3.0863 (3.4016) grad_norm: 1.2551 (1.2474) time: 0.5023 [2021-03-26 01:09:46 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 960/1251] eta: 0:02:28 lr: 0.000659 loss: 3.2195 (3.4001) grad_norm: 1.1620 (1.2468) time: 0.5048 [2021-03-26 01:09:51 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 970/1251] eta: 0:02:23 lr: 0.000659 loss: 3.2886 (3.3991) grad_norm: 1.2001 (1.2470) time: 0.5056 [2021-03-26 01:09:56 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 980/1251] eta: 0:02:18 lr: 0.000659 loss: 3.4200 (3.3996) grad_norm: 1.2269 (nan) time: 0.4988 [2021-03-26 01:10:01 swin_small_patch4_window7_224] INFO: Epoch: [119] [ 990/1251] eta: 0:02:13 lr: 0.000659 loss: 3.4338 (3.4001) grad_norm: 1.2745 (nan) time: 0.5023 [2021-03-26 01:10:07 swin_small_patch4_window7_224] INFO: Epoch: [119] [1000/1251] eta: 0:02:07 lr: 0.000659 loss: 3.4117 (3.4005) grad_norm: 1.2258 (nan) time: 0.5112 [2021-03-26 01:10:12 swin_small_patch4_window7_224] INFO: Epoch: [119] [1010/1251] eta: 0:02:02 lr: 0.000659 loss: 3.5693 (3.4015) grad_norm: 1.1805 (nan) time: 0.5118 [2021-03-26 01:10:17 swin_small_patch4_window7_224] INFO: Epoch: [119] [1020/1251] eta: 0:01:57 lr: 0.000659 loss: 3.5693 (3.4024) grad_norm: 1.1905 (nan) time: 0.5032 [2021-03-26 01:10:22 swin_small_patch4_window7_224] INFO: Epoch: [119] [1030/1251] eta: 0:01:52 lr: 0.000659 loss: 3.4306 (3.4029) grad_norm: 1.1581 (nan) time: 0.5024 [2021-03-26 01:10:27 swin_small_patch4_window7_224] INFO: Epoch: [119] [1040/1251] eta: 0:01:47 lr: 0.000659 loss: 3.3162 (3.4024) grad_norm: 1.2218 (nan) time: 0.5087 [2021-03-26 01:10:32 swin_small_patch4_window7_224] INFO: Epoch: [119] [1050/1251] eta: 0:01:42 lr: 0.000659 loss: 3.5562 (3.4051) grad_norm: 1.2538 (nan) time: 0.5135 [2021-03-26 01:10:37 swin_small_patch4_window7_224] INFO: Epoch: [119] [1060/1251] eta: 0:01:37 lr: 0.000659 loss: 3.5788 (3.4044) grad_norm: 1.1927 (nan) time: 0.5105 [2021-03-26 01:10:42 swin_small_patch4_window7_224] INFO: Epoch: [119] [1070/1251] eta: 0:01:32 lr: 0.000659 loss: 3.2802 (3.4030) grad_norm: 1.2044 (nan) time: 0.5026 [2021-03-26 01:10:47 swin_small_patch4_window7_224] INFO: Epoch: [119] [1080/1251] eta: 0:01:27 lr: 0.000659 loss: 3.5937 (3.4037) grad_norm: 1.2442 (nan) time: 0.5012 [2021-03-26 01:10:52 swin_small_patch4_window7_224] INFO: Epoch: [119] [1090/1251] eta: 0:01:22 lr: 0.000659 loss: 3.6287 (3.4067) grad_norm: 1.2473 (nan) time: 0.5007 [2021-03-26 01:10:57 swin_small_patch4_window7_224] INFO: Epoch: [119] [1100/1251] eta: 0:01:16 lr: 0.000659 loss: 3.7281 (3.4077) grad_norm: 1.1659 (nan) time: 0.4981 [2021-03-26 01:11:02 swin_small_patch4_window7_224] INFO: Epoch: [119] [1110/1251] eta: 0:01:11 lr: 0.000659 loss: 3.7281 (3.4096) grad_norm: 1.1807 (nan) time: 0.5021 [2021-03-26 01:11:07 swin_small_patch4_window7_224] INFO: Epoch: [119] [1120/1251] eta: 0:01:06 lr: 0.000658 loss: 3.6264 (3.4100) grad_norm: 1.2135 (nan) time: 0.5006 [2021-03-26 01:11:12 swin_small_patch4_window7_224] INFO: Epoch: [119] [1130/1251] eta: 0:01:01 lr: 0.000658 loss: 3.5826 (3.4112) grad_norm: 1.1830 (nan) time: 0.5006 [2021-03-26 01:11:17 swin_small_patch4_window7_224] INFO: Epoch: [119] [1140/1251] eta: 0:00:56 lr: 0.000658 loss: 3.5375 (3.4112) grad_norm: 1.1830 (nan) time: 0.5043 [2021-03-26 01:11:22 swin_small_patch4_window7_224] INFO: Epoch: [119] [1150/1251] eta: 0:00:51 lr: 0.000658 loss: 3.5246 (3.4121) grad_norm: 1.2247 (nan) time: 0.5066 [2021-03-26 01:11:27 swin_small_patch4_window7_224] INFO: Epoch: [119] [1160/1251] eta: 0:00:46 lr: 0.000658 loss: 3.6206 (3.4137) grad_norm: 1.2799 (nan) time: 0.5070 [2021-03-26 01:11:32 swin_small_patch4_window7_224] INFO: Epoch: [119] [1170/1251] eta: 0:00:41 lr: 0.000658 loss: 3.6206 (3.4147) grad_norm: 1.2529 (nan) time: 0.5047 [2021-03-26 01:11:37 swin_small_patch4_window7_224] INFO: Epoch: [119] [1180/1251] eta: 0:00:36 lr: 0.000658 loss: 3.6158 (3.4151) grad_norm: 1.2221 (nan) time: 0.5026 [2021-03-26 01:11:42 swin_small_patch4_window7_224] INFO: Epoch: [119] [1190/1251] eta: 0:00:31 lr: 0.000658 loss: 3.5215 (3.4157) grad_norm: 1.1732 (nan) time: 0.5069 [2021-03-26 01:11:48 swin_small_patch4_window7_224] INFO: Epoch: [119] [1200/1251] eta: 0:00:25 lr: 0.000658 loss: 3.4720 (3.4148) grad_norm: 1.1707 (nan) time: 0.5100 [2021-03-26 01:11:53 swin_small_patch4_window7_224] INFO: Epoch: [119] [1210/1251] eta: 0:00:20 lr: 0.000658 loss: 3.5803 (3.4173) grad_norm: 1.2206 (nan) time: 0.5032 [2021-03-26 01:11:58 swin_small_patch4_window7_224] INFO: Epoch: [119] [1220/1251] eta: 0:00:15 lr: 0.000658 loss: 3.5558 (3.4155) grad_norm: 1.2215 (nan) time: 0.5002 [2021-03-26 01:12:03 swin_small_patch4_window7_224] INFO: Epoch: [119] [1230/1251] eta: 0:00:10 lr: 0.000658 loss: 3.2014 (3.4148) grad_norm: 1.2719 (nan) time: 0.5000 [2021-03-26 01:12:08 swin_small_patch4_window7_224] INFO: Epoch: [119] [1240/1251] eta: 0:00:05 lr: 0.000658 loss: 3.7420 (3.4162) grad_norm: 1.2574 (nan) time: 0.5049 [2021-03-26 01:12:13 swin_small_patch4_window7_224] INFO: Epoch: [119] [1250/1251] eta: 0:00:00 lr: 0.000658 loss: 3.7228 (3.4168) grad_norm: 1.2324 (nan) time: 0.5071 [2021-03-26 01:12:22 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:27 loss: 1.0251 (1.0251) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-26 01:12:25 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.0661 (1.0399) acc1: 73.4375 (75.0000) acc5: 93.7500 (94.0341) [2021-03-26 01:12:27 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0367 (1.0023) acc1: 73.4375 (75.7440) acc5: 93.7500 (93.9732) [2021-03-26 01:12:30 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9973 (0.9981) acc1: 76.5625 (76.1089) acc5: 93.7500 (94.1532) [2021-03-26 01:12:32 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0432 (1.0028) acc1: 75.0000 (75.9527) acc5: 95.3125 (94.2073) [2021-03-26 01:12:32 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9834 (0.9937) acc1: 73.4375 (75.8080) acc5: 96.8750 (94.4000) [2021-03-26 01:12:38 swin_small_patch4_window7_224] INFO: * Acc@1 77.012 Acc@5 93.904 loss 0.970 [2021-03-26 01:12:38 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.0% [2021-03-26 01:12:38 swin_small_patch4_window7_224] INFO: Max accuracy: 77.05% [2021-03-26 01:12:42 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 0/1251] eta: 1:27:18 lr: 0.000658 loss: 3.1758 (3.1758) grad_norm: 1.0334 (1.0334) time: 4.1878 [2021-03-26 01:12:47 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 10/1251] eta: 0:17:30 lr: 0.000658 loss: 3.2552 (3.3218) grad_norm: 1.1339 (1.1462) time: 0.8469 [2021-03-26 01:12:53 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 20/1251] eta: 0:14:04 lr: 0.000658 loss: 3.4545 (3.3927) grad_norm: 1.2151 (1.2066) time: 0.5113 [2021-03-26 01:12:58 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 30/1251] eta: 0:12:48 lr: 0.000658 loss: 3.5134 (3.4430) grad_norm: 1.2510 (1.2311) time: 0.5095 [2021-03-26 01:13:03 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 40/1251] eta: 0:12:07 lr: 0.000658 loss: 3.5447 (3.4690) grad_norm: 1.2988 (1.2614) time: 0.5115 [2021-03-26 01:13:08 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 50/1251] eta: 0:11:39 lr: 0.000658 loss: 3.6387 (3.4877) grad_norm: 1.2577 (1.2582) time: 0.5098 [2021-03-26 01:13:13 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 60/1251] eta: 0:11:19 lr: 0.000658 loss: 3.4123 (3.4439) grad_norm: 1.2242 (1.2588) time: 0.5081 [2021-03-26 01:13:18 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 70/1251] eta: 0:11:01 lr: 0.000658 loss: 3.3018 (3.4283) grad_norm: 1.2521 (1.2712) time: 0.5036 [2021-03-26 01:13:23 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 80/1251] eta: 0:10:48 lr: 0.000658 loss: 3.3181 (3.4136) grad_norm: 1.2665 (1.2792) time: 0.5015 [2021-03-26 01:13:28 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 90/1251] eta: 0:10:36 lr: 0.000658 loss: 3.3181 (3.4082) grad_norm: 1.2397 (1.2803) time: 0.5052 [2021-03-26 01:13:33 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 100/1251] eta: 0:10:26 lr: 0.000658 loss: 3.4127 (3.4260) grad_norm: 1.2318 (1.2791) time: 0.5085 [2021-03-26 01:13:38 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 110/1251] eta: 0:10:16 lr: 0.000658 loss: 3.5345 (3.4335) grad_norm: 1.2062 (1.2733) time: 0.5028 [2021-03-26 01:13:43 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 120/1251] eta: 0:10:07 lr: 0.000657 loss: 3.3531 (3.4105) grad_norm: 1.2642 (1.2755) time: 0.4987 [2021-03-26 01:13:48 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 130/1251] eta: 0:09:59 lr: 0.000657 loss: 3.3809 (3.4196) grad_norm: 1.2620 (1.2732) time: 0.5077 [2021-03-26 01:13:53 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 140/1251] eta: 0:09:51 lr: 0.000657 loss: 3.3152 (3.4041) grad_norm: 1.2072 (1.2671) time: 0.5073 [2021-03-26 01:13:58 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 150/1251] eta: 0:09:45 lr: 0.000657 loss: 3.2555 (3.4014) grad_norm: 1.1498 (1.2615) time: 0.5075 [2021-03-26 01:14:03 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 160/1251] eta: 0:09:37 lr: 0.000657 loss: 3.4840 (3.4154) grad_norm: 1.1761 (1.2599) time: 0.5085 [2021-03-26 01:14:08 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 170/1251] eta: 0:09:31 lr: 0.000657 loss: 3.5688 (3.4113) grad_norm: 1.1811 (1.2612) time: 0.5054 [2021-03-26 01:14:14 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 180/1251] eta: 0:09:24 lr: 0.000657 loss: 3.4979 (3.4149) grad_norm: 1.2031 (1.2602) time: 0.5043 [2021-03-26 01:14:19 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 190/1251] eta: 0:09:19 lr: 0.000657 loss: 3.4979 (3.4042) grad_norm: 1.2257 (1.2627) time: 0.5164 [2021-03-26 01:14:24 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 200/1251] eta: 0:09:12 lr: 0.000657 loss: 3.5313 (3.4124) grad_norm: 1.2781 (1.2613) time: 0.5181 [2021-03-26 01:14:29 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 210/1251] eta: 0:09:06 lr: 0.000657 loss: 3.5130 (3.4136) grad_norm: 1.2455 (1.2617) time: 0.5095 [2021-03-26 01:14:34 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 220/1251] eta: 0:09:00 lr: 0.000657 loss: 3.4130 (3.4153) grad_norm: 1.2394 (1.2611) time: 0.5090 [2021-03-26 01:14:39 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 230/1251] eta: 0:08:55 lr: 0.000657 loss: 3.7006 (3.4237) grad_norm: 1.2209 (1.2604) time: 0.5098 [2021-03-26 01:14:44 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 240/1251] eta: 0:08:48 lr: 0.000657 loss: 3.5852 (3.4177) grad_norm: 1.2209 (1.2614) time: 0.5054 [2021-03-26 01:14:49 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 250/1251] eta: 0:08:42 lr: 0.000657 loss: 3.4361 (3.4236) grad_norm: 1.2551 (1.2613) time: 0.5028 [2021-03-26 01:14:54 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 260/1251] eta: 0:08:36 lr: 0.000657 loss: 3.5928 (3.4292) grad_norm: 1.2652 (1.2620) time: 0.5050 [2021-03-26 01:14:59 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 270/1251] eta: 0:08:31 lr: 0.000657 loss: 3.6180 (3.4352) grad_norm: 1.2700 (1.2610) time: 0.5070 [2021-03-26 01:15:04 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 280/1251] eta: 0:08:25 lr: 0.000657 loss: 3.6180 (3.4374) grad_norm: 1.1973 (1.2606) time: 0.5056 [2021-03-26 01:15:10 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 290/1251] eta: 0:08:19 lr: 0.000657 loss: 3.5427 (3.4338) grad_norm: 1.1936 (1.2596) time: 0.5063 [2021-03-26 01:15:15 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 300/1251] eta: 0:08:14 lr: 0.000657 loss: 3.4245 (3.4334) grad_norm: 1.2037 (1.2585) time: 0.5072 [2021-03-26 01:15:20 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 310/1251] eta: 0:08:08 lr: 0.000657 loss: 3.5115 (3.4373) grad_norm: 1.2783 (1.2615) time: 0.5077 [2021-03-26 01:15:25 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 320/1251] eta: 0:08:03 lr: 0.000657 loss: 3.7292 (3.4409) grad_norm: 1.3097 (1.2615) time: 0.5114 [2021-03-26 01:15:30 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 330/1251] eta: 0:07:57 lr: 0.000657 loss: 3.8563 (3.4438) grad_norm: 1.2205 (1.2610) time: 0.5080 [2021-03-26 01:15:35 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 340/1251] eta: 0:07:52 lr: 0.000657 loss: 3.5884 (3.4423) grad_norm: 1.1905 (1.2604) time: 0.5078 [2021-03-26 01:15:40 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 350/1251] eta: 0:07:46 lr: 0.000657 loss: 3.4685 (3.4409) grad_norm: 1.2056 (1.2605) time: 0.5037 [2021-03-26 01:15:45 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 360/1251] eta: 0:07:41 lr: 0.000657 loss: 3.3969 (3.4362) grad_norm: 1.2056 (1.2585) time: 0.5051 [2021-03-26 01:15:50 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 370/1251] eta: 0:07:35 lr: 0.000657 loss: 3.3990 (3.4377) grad_norm: 1.1340 (1.2543) time: 0.5068 [2021-03-26 01:15:55 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 380/1251] eta: 0:07:30 lr: 0.000656 loss: 3.7888 (3.4472) grad_norm: 1.1219 (1.2524) time: 0.5055 [2021-03-26 01:16:00 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 390/1251] eta: 0:07:25 lr: 0.000656 loss: 3.6905 (3.4471) grad_norm: 1.1953 (1.2523) time: 0.5105 [2021-03-26 01:16:05 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 400/1251] eta: 0:07:19 lr: 0.000656 loss: 3.5088 (3.4488) grad_norm: 1.2370 (1.2543) time: 0.5100 [2021-03-26 01:16:10 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 410/1251] eta: 0:07:14 lr: 0.000656 loss: 3.3445 (3.4427) grad_norm: 1.2502 (1.2554) time: 0.5039 [2021-03-26 01:16:15 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 420/1251] eta: 0:07:08 lr: 0.000656 loss: 3.3445 (3.4446) grad_norm: 1.2422 (1.2556) time: 0.5016 [2021-03-26 01:16:20 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 430/1251] eta: 0:07:03 lr: 0.000656 loss: 3.6213 (3.4450) grad_norm: 1.2218 (1.2541) time: 0.5018 [2021-03-26 01:16:25 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 440/1251] eta: 0:06:57 lr: 0.000656 loss: 3.5400 (3.4489) grad_norm: 1.2218 (1.2545) time: 0.5019 [2021-03-26 01:16:31 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 450/1251] eta: 0:06:52 lr: 0.000656 loss: 3.7064 (3.4518) grad_norm: 1.2540 (1.2534) time: 0.5077 [2021-03-26 01:16:36 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 460/1251] eta: 0:06:47 lr: 0.000656 loss: 3.6262 (3.4493) grad_norm: 1.2433 (1.2538) time: 0.5076 [2021-03-26 01:16:41 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 470/1251] eta: 0:06:42 lr: 0.000656 loss: 3.5356 (3.4495) grad_norm: 1.2308 (1.2534) time: 0.5038 [2021-03-26 01:16:46 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 480/1251] eta: 0:06:36 lr: 0.000656 loss: 3.5200 (3.4490) grad_norm: 1.2732 (1.2551) time: 0.5032 [2021-03-26 01:16:51 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 490/1251] eta: 0:06:31 lr: 0.000656 loss: 3.4326 (3.4468) grad_norm: 1.2848 (1.2551) time: 0.4992 [2021-03-26 01:16:56 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 500/1251] eta: 0:06:25 lr: 0.000656 loss: 3.5095 (3.4485) grad_norm: 1.2098 (1.2541) time: 0.4985 [2021-03-26 01:17:01 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 510/1251] eta: 0:06:20 lr: 0.000656 loss: 3.5095 (3.4480) grad_norm: 1.1959 (1.2536) time: 0.5008 [2021-03-26 01:17:06 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 520/1251] eta: 0:06:15 lr: 0.000656 loss: 3.1926 (3.4476) grad_norm: 1.2023 (1.2536) time: 0.5038 [2021-03-26 01:17:11 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 530/1251] eta: 0:06:10 lr: 0.000656 loss: 3.3650 (3.4461) grad_norm: 1.2343 (1.2535) time: 0.5038 [2021-03-26 01:17:16 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 540/1251] eta: 0:06:04 lr: 0.000656 loss: 3.5107 (3.4500) grad_norm: 1.2407 (1.2531) time: 0.4997 [2021-03-26 01:17:21 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 550/1251] eta: 0:05:59 lr: 0.000656 loss: 3.5114 (3.4530) grad_norm: 1.2407 (1.2535) time: 0.5059 [2021-03-26 01:17:26 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 560/1251] eta: 0:05:54 lr: 0.000656 loss: 3.5114 (3.4500) grad_norm: 1.2582 (1.2545) time: 0.5137 [2021-03-26 01:17:31 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 570/1251] eta: 0:05:49 lr: 0.000656 loss: 3.5199 (3.4520) grad_norm: 1.2455 (1.2541) time: 0.5133 [2021-03-26 01:17:36 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 580/1251] eta: 0:05:44 lr: 0.000656 loss: 3.6122 (3.4556) grad_norm: 1.1875 (1.2544) time: 0.5120 [2021-03-26 01:17:41 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 590/1251] eta: 0:05:38 lr: 0.000656 loss: 3.5512 (3.4521) grad_norm: 1.2325 (1.2537) time: 0.5060 [2021-03-26 01:17:46 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 600/1251] eta: 0:05:33 lr: 0.000656 loss: 3.6127 (3.4539) grad_norm: 1.1913 (1.2527) time: 0.5072 [2021-03-26 01:17:51 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 610/1251] eta: 0:05:28 lr: 0.000656 loss: 3.5830 (3.4536) grad_norm: 1.1913 (1.2522) time: 0.5091 [2021-03-26 01:17:56 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 620/1251] eta: 0:05:23 lr: 0.000656 loss: 3.4116 (3.4513) grad_norm: 1.2149 (1.2516) time: 0.5065 [2021-03-26 01:18:01 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 630/1251] eta: 0:05:18 lr: 0.000655 loss: 3.5151 (3.4518) grad_norm: 1.1886 (1.2508) time: 0.5026 [2021-03-26 01:18:07 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 640/1251] eta: 0:05:13 lr: 0.000655 loss: 3.5170 (3.4503) grad_norm: 1.1848 (1.2504) time: 0.5054 [2021-03-26 01:18:12 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 650/1251] eta: 0:05:07 lr: 0.000655 loss: 3.1897 (3.4463) grad_norm: 1.1829 (1.2500) time: 0.5082 [2021-03-26 01:18:17 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 660/1251] eta: 0:05:02 lr: 0.000655 loss: 3.2695 (3.4447) grad_norm: 1.2012 (1.2500) time: 0.5054 [2021-03-26 01:18:22 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 670/1251] eta: 0:04:57 lr: 0.000655 loss: 3.4040 (3.4432) grad_norm: 1.2567 (1.2513) time: 0.5047 [2021-03-26 01:18:27 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 680/1251] eta: 0:04:52 lr: 0.000655 loss: 3.6701 (3.4441) grad_norm: 1.2556 (1.2518) time: 0.5073 [2021-03-26 01:18:32 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 690/1251] eta: 0:04:47 lr: 0.000655 loss: 3.7071 (3.4454) grad_norm: 1.2467 (1.2514) time: 0.5130 [2021-03-26 01:18:37 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 700/1251] eta: 0:04:41 lr: 0.000655 loss: 3.6550 (3.4464) grad_norm: 1.2058 (1.2507) time: 0.5054 [2021-03-26 01:18:42 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 710/1251] eta: 0:04:36 lr: 0.000655 loss: 3.5943 (3.4488) grad_norm: 1.2224 (1.2504) time: 0.5035 [2021-03-26 01:18:47 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 720/1251] eta: 0:04:31 lr: 0.000655 loss: 3.3948 (3.4484) grad_norm: 1.2282 (1.2503) time: 0.5059 [2021-03-26 01:18:52 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 730/1251] eta: 0:04:26 lr: 0.000655 loss: 3.3262 (3.4503) grad_norm: 1.2370 (1.2517) time: 0.5073 [2021-03-26 01:18:57 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 740/1251] eta: 0:04:21 lr: 0.000655 loss: 3.3264 (3.4459) grad_norm: 1.3277 (1.2523) time: 0.5188 [2021-03-26 01:19:03 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 750/1251] eta: 0:04:16 lr: 0.000655 loss: 3.3814 (3.4472) grad_norm: 1.2277 (1.2522) time: 0.5205 [2021-03-26 01:19:08 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 760/1251] eta: 0:04:11 lr: 0.000655 loss: 3.4802 (3.4477) grad_norm: 1.2204 (1.2521) time: 0.5146 [2021-03-26 01:19:13 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 770/1251] eta: 0:04:06 lr: 0.000655 loss: 3.5686 (3.4479) grad_norm: 1.2204 (1.2523) time: 0.5143 [2021-03-26 01:19:18 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 780/1251] eta: 0:04:01 lr: 0.000655 loss: 3.5364 (3.4481) grad_norm: 1.2146 (1.2516) time: 0.5066 [2021-03-26 01:19:23 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 790/1251] eta: 0:03:55 lr: 0.000655 loss: 3.4352 (3.4472) grad_norm: 1.2151 (1.2514) time: 0.5083 [2021-03-26 01:19:28 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 800/1251] eta: 0:03:50 lr: 0.000655 loss: 3.1645 (3.4424) grad_norm: 1.2229 (1.2509) time: 0.5086 [2021-03-26 01:19:33 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 810/1251] eta: 0:03:45 lr: 0.000655 loss: 3.1645 (3.4425) grad_norm: 1.2229 (1.2513) time: 0.5027 [2021-03-26 01:19:38 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 820/1251] eta: 0:03:40 lr: 0.000655 loss: 3.6134 (3.4437) grad_norm: 1.2817 (1.2517) time: 0.5055 [2021-03-26 01:19:43 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 830/1251] eta: 0:03:35 lr: 0.000655 loss: 3.7398 (3.4485) grad_norm: 1.2607 (1.2525) time: 0.5076 [2021-03-26 01:19:48 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 840/1251] eta: 0:03:30 lr: 0.000655 loss: 3.7398 (3.4470) grad_norm: 1.3628 (1.2543) time: 0.5088 [2021-03-26 01:19:53 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 850/1251] eta: 0:03:25 lr: 0.000655 loss: 3.3147 (3.4454) grad_norm: 1.3041 (1.2543) time: 0.5077 [2021-03-26 01:19:58 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 860/1251] eta: 0:03:19 lr: 0.000655 loss: 3.5442 (3.4469) grad_norm: 1.2573 (1.2545) time: 0.5043 [2021-03-26 01:20:04 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 870/1251] eta: 0:03:14 lr: 0.000655 loss: 3.5363 (3.4468) grad_norm: 1.2375 (1.2537) time: 0.5037 [2021-03-26 01:20:08 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 880/1251] eta: 0:03:09 lr: 0.000654 loss: 3.5363 (3.4467) grad_norm: 1.2063 (1.2539) time: 0.5005 [2021-03-26 01:20:13 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 890/1251] eta: 0:03:04 lr: 0.000654 loss: 3.5649 (3.4451) grad_norm: 1.2261 (1.2537) time: 0.4951 [2021-03-26 01:20:18 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 900/1251] eta: 0:02:59 lr: 0.000654 loss: 3.4071 (3.4451) grad_norm: 1.2073 (1.2539) time: 0.5006 [2021-03-26 01:20:24 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 910/1251] eta: 0:02:54 lr: 0.000654 loss: 3.5213 (3.4456) grad_norm: 1.2118 (1.2534) time: 0.5060 [2021-03-26 01:20:29 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 920/1251] eta: 0:02:49 lr: 0.000654 loss: 3.4181 (3.4439) grad_norm: 1.2118 (1.2532) time: 0.5082 [2021-03-26 01:20:34 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 930/1251] eta: 0:02:43 lr: 0.000654 loss: 3.3812 (3.4421) grad_norm: 1.2463 (1.2536) time: 0.5164 [2021-03-26 01:20:39 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 940/1251] eta: 0:02:38 lr: 0.000654 loss: 3.5427 (3.4431) grad_norm: 1.2621 (1.2538) time: 0.5135 [2021-03-26 01:20:44 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 950/1251] eta: 0:02:33 lr: 0.000654 loss: 3.6116 (3.4433) grad_norm: 1.2612 (1.2537) time: 0.5134 [2021-03-26 01:20:49 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 960/1251] eta: 0:02:28 lr: 0.000654 loss: 3.6271 (3.4427) grad_norm: 1.2146 (1.2534) time: 0.5140 [2021-03-26 01:20:54 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 970/1251] eta: 0:02:23 lr: 0.000654 loss: 3.6271 (3.4427) grad_norm: 1.2185 (1.2535) time: 0.5062 [2021-03-26 01:20:59 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 980/1251] eta: 0:02:18 lr: 0.000654 loss: 3.6296 (3.4446) grad_norm: 1.2824 (1.2539) time: 0.5083 [2021-03-26 01:21:04 swin_small_patch4_window7_224] INFO: Epoch: [120] [ 990/1251] eta: 0:02:13 lr: 0.000654 loss: 3.5497 (3.4444) grad_norm: 1.3135 (1.2554) time: 0.5021 [2021-03-26 01:21:09 swin_small_patch4_window7_224] INFO: Epoch: [120] [1000/1251] eta: 0:02:08 lr: 0.000654 loss: 3.5314 (3.4454) grad_norm: 1.3223 (1.2563) time: 0.4979 [2021-03-26 01:21:14 swin_small_patch4_window7_224] INFO: Epoch: [120] [1010/1251] eta: 0:02:03 lr: 0.000654 loss: 3.4472 (3.4456) grad_norm: 1.2995 (1.2570) time: 0.5039 [2021-03-26 01:21:19 swin_small_patch4_window7_224] INFO: Epoch: [120] [1020/1251] eta: 0:01:57 lr: 0.000654 loss: 3.3183 (3.4435) grad_norm: 1.2793 (1.2574) time: 0.5056 [2021-03-26 01:21:25 swin_small_patch4_window7_224] INFO: Epoch: [120] [1030/1251] eta: 0:01:52 lr: 0.000654 loss: 3.5060 (3.4466) grad_norm: 1.2353 (1.2573) time: 0.5050 [2021-03-26 01:21:30 swin_small_patch4_window7_224] INFO: Epoch: [120] [1040/1251] eta: 0:01:47 lr: 0.000654 loss: 3.5832 (3.4444) grad_norm: 1.1903 (1.2570) time: 0.5061 [2021-03-26 01:21:35 swin_small_patch4_window7_224] INFO: Epoch: [120] [1050/1251] eta: 0:01:42 lr: 0.000654 loss: 3.5636 (3.4456) grad_norm: 1.2115 (1.2570) time: 0.5034 [2021-03-26 01:21:40 swin_small_patch4_window7_224] INFO: Epoch: [120] [1060/1251] eta: 0:01:37 lr: 0.000654 loss: 3.6762 (3.4467) grad_norm: 1.2697 (1.2575) time: 0.5061 [2021-03-26 01:21:45 swin_small_patch4_window7_224] INFO: Epoch: [120] [1070/1251] eta: 0:01:32 lr: 0.000654 loss: 3.6762 (3.4470) grad_norm: 1.2507 (1.2572) time: 0.5081 [2021-03-26 01:21:50 swin_small_patch4_window7_224] INFO: Epoch: [120] [1080/1251] eta: 0:01:27 lr: 0.000654 loss: 3.4952 (3.4451) grad_norm: 1.2507 (1.2576) time: 0.5014 [2021-03-26 01:21:55 swin_small_patch4_window7_224] INFO: Epoch: [120] [1090/1251] eta: 0:01:22 lr: 0.000654 loss: 3.4964 (3.4450) grad_norm: 1.2306 (1.2573) time: 0.5020 [2021-03-26 01:22:00 swin_small_patch4_window7_224] INFO: Epoch: [120] [1100/1251] eta: 0:01:17 lr: 0.000654 loss: 3.6621 (3.4450) grad_norm: 1.2306 (1.2571) time: 0.5077 [2021-03-26 01:22:05 swin_small_patch4_window7_224] INFO: Epoch: [120] [1110/1251] eta: 0:01:11 lr: 0.000654 loss: 3.6303 (3.4447) grad_norm: 1.2609 (1.2577) time: 0.5039 [2021-03-26 01:22:10 swin_small_patch4_window7_224] INFO: Epoch: [120] [1120/1251] eta: 0:01:06 lr: 0.000654 loss: 3.3005 (3.4421) grad_norm: 1.2497 (1.2573) time: 0.4960 [2021-03-26 01:22:15 swin_small_patch4_window7_224] INFO: Epoch: [120] [1130/1251] eta: 0:01:01 lr: 0.000654 loss: 3.3005 (3.4426) grad_norm: 1.2524 (1.2578) time: 0.4995 [2021-03-26 01:22:20 swin_small_patch4_window7_224] INFO: Epoch: [120] [1140/1251] eta: 0:00:56 lr: 0.000653 loss: 3.4166 (3.4428) grad_norm: 1.2667 (1.2583) time: 0.5107 [2021-03-26 01:22:25 swin_small_patch4_window7_224] INFO: Epoch: [120] [1150/1251] eta: 0:00:51 lr: 0.000653 loss: 3.3268 (3.4418) grad_norm: 1.2690 (1.2584) time: 0.5124 [2021-03-26 01:22:30 swin_small_patch4_window7_224] INFO: Epoch: [120] [1160/1251] eta: 0:00:46 lr: 0.000653 loss: 3.5175 (3.4415) grad_norm: 1.1487 (1.2576) time: 0.5046 [2021-03-26 01:22:35 swin_small_patch4_window7_224] INFO: Epoch: [120] [1170/1251] eta: 0:00:41 lr: 0.000653 loss: 3.5175 (3.4410) grad_norm: 1.1842 (1.2575) time: 0.5074 [2021-03-26 01:22:40 swin_small_patch4_window7_224] INFO: Epoch: [120] [1180/1251] eta: 0:00:36 lr: 0.000653 loss: 3.5723 (3.4418) grad_norm: 1.2698 (1.2586) time: 0.5115 [2021-03-26 01:22:45 swin_small_patch4_window7_224] INFO: Epoch: [120] [1190/1251] eta: 0:00:31 lr: 0.000653 loss: 3.4060 (3.4402) grad_norm: 1.2698 (1.2587) time: 0.5074 [2021-03-26 01:22:51 swin_small_patch4_window7_224] INFO: Epoch: [120] [1200/1251] eta: 0:00:25 lr: 0.000653 loss: 3.4079 (3.4411) grad_norm: 1.2464 (1.2585) time: 0.5070 [2021-03-26 01:22:56 swin_small_patch4_window7_224] INFO: Epoch: [120] [1210/1251] eta: 0:00:20 lr: 0.000653 loss: 3.5977 (3.4427) grad_norm: 1.2758 (1.2588) time: 0.5062 [2021-03-26 01:23:01 swin_small_patch4_window7_224] INFO: Epoch: [120] [1220/1251] eta: 0:00:15 lr: 0.000653 loss: 3.6949 (3.4433) grad_norm: 1.2758 (1.2589) time: 0.5041 [2021-03-26 01:23:06 swin_small_patch4_window7_224] INFO: Epoch: [120] [1230/1251] eta: 0:00:10 lr: 0.000653 loss: 3.6616 (3.4440) grad_norm: 1.2179 (1.2585) time: 0.5052 [2021-03-26 01:23:11 swin_small_patch4_window7_224] INFO: Epoch: [120] [1240/1251] eta: 0:00:05 lr: 0.000653 loss: 3.4534 (3.4429) grad_norm: 1.1809 (1.2576) time: 0.5030 [2021-03-26 01:23:16 swin_small_patch4_window7_224] INFO: Epoch: [120] [1250/1251] eta: 0:00:00 lr: 0.000653 loss: 3.4135 (3.4425) grad_norm: 1.1800 (1.2570) time: 0.4938 [2021-03-26 01:23:58 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.0426 (1.0426) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.1875) [2021-03-26 01:23:59 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 1.0166 (0.9804) acc1: 76.5625 (75.4261) acc5: 93.7500 (93.7500) [2021-03-26 01:24:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9527 (1.0030) acc1: 75.0000 (75.3720) acc5: 93.7500 (94.2708) [2021-03-26 01:24:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9527 (0.9858) acc1: 78.1250 (76.4113) acc5: 93.7500 (93.8508) [2021-03-26 01:24:02 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9231 (0.9730) acc1: 76.5625 (76.1814) acc5: 93.7500 (94.0168) [2021-03-26 01:24:03 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9793 (0.9806) acc1: 76.5625 (76.0960) acc5: 93.7500 (94.0160) [2021-03-26 01:24:07 swin_small_patch4_window7_224] INFO: * Acc@1 76.884 Acc@5 93.834 loss 0.965 [2021-03-26 01:24:07 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 76.9% [2021-03-26 01:24:07 swin_small_patch4_window7_224] INFO: Max accuracy: 77.05% [2021-03-26 01:24:11 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 0/1251] eta: 1:33:16 lr: 0.000653 loss: 2.5693 (2.5693) grad_norm: 1.2867 (1.2867) time: 4.4737 [2021-03-26 01:24:16 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 10/1251] eta: 0:17:52 lr: 0.000653 loss: 3.8376 (3.6110) grad_norm: 1.1927 (1.2007) time: 0.8639 [2021-03-26 01:24:21 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 20/1251] eta: 0:14:10 lr: 0.000653 loss: 3.7628 (3.5848) grad_norm: 1.2089 (1.2397) time: 0.5021 [2021-03-26 01:24:26 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 30/1251] eta: 0:12:52 lr: 0.000653 loss: 3.6876 (3.5978) grad_norm: 1.2290 (1.2443) time: 0.5053 [2021-03-26 01:24:31 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 40/1251] eta: 0:12:11 lr: 0.000653 loss: 3.4226 (3.5243) grad_norm: 1.1688 (1.2321) time: 0.5118 [2021-03-26 01:24:37 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 50/1251] eta: 0:11:43 lr: 0.000653 loss: 3.4216 (3.4837) grad_norm: 1.1881 (1.2410) time: 0.5139 [2021-03-26 01:24:42 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 60/1251] eta: 0:11:22 lr: 0.000653 loss: 3.3195 (3.4374) grad_norm: 1.2518 (1.2593) time: 0.5110 [2021-03-26 01:24:47 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 70/1251] eta: 0:11:07 lr: 0.000653 loss: 3.3125 (3.4231) grad_norm: 1.2518 (1.2571) time: 0.5128 [2021-03-26 01:24:52 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 80/1251] eta: 0:10:53 lr: 0.000653 loss: 3.5095 (3.4054) grad_norm: 1.2274 (1.2582) time: 0.5124 [2021-03-26 01:24:57 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 90/1251] eta: 0:10:40 lr: 0.000653 loss: 3.4503 (3.3873) grad_norm: 1.2600 (1.2595) time: 0.5033 [2021-03-26 01:25:02 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 100/1251] eta: 0:10:29 lr: 0.000653 loss: 3.3246 (3.3883) grad_norm: 1.2481 (1.2557) time: 0.5009 [2021-03-26 01:25:07 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 110/1251] eta: 0:10:20 lr: 0.000653 loss: 3.3203 (3.3726) grad_norm: 1.2481 (1.2583) time: 0.5057 [2021-03-26 01:25:12 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 120/1251] eta: 0:10:12 lr: 0.000653 loss: 3.2948 (3.3621) grad_norm: 1.2781 (1.2585) time: 0.5140 [2021-03-26 01:25:17 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 130/1251] eta: 0:10:03 lr: 0.000653 loss: 3.4117 (3.3611) grad_norm: 1.2437 (1.2563) time: 0.5103 [2021-03-26 01:25:22 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 140/1251] eta: 0:09:56 lr: 0.000652 loss: 3.5321 (3.3554) grad_norm: 1.2313 (1.2533) time: 0.5107 [2021-03-26 01:25:28 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 150/1251] eta: 0:09:48 lr: 0.000652 loss: 3.5013 (3.3608) grad_norm: 1.2167 (1.2556) time: 0.5115 [2021-03-26 01:25:33 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 160/1251] eta: 0:09:41 lr: 0.000652 loss: 3.4694 (3.3404) grad_norm: 1.2333 (1.2562) time: 0.5036 [2021-03-26 01:25:38 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 170/1251] eta: 0:09:34 lr: 0.000652 loss: 3.5344 (3.3485) grad_norm: 1.2391 (1.2592) time: 0.5057 [2021-03-26 01:25:43 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 180/1251] eta: 0:09:28 lr: 0.000652 loss: 3.4763 (3.3514) grad_norm: 1.3051 (1.2608) time: 0.5111 [2021-03-26 01:25:48 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 190/1251] eta: 0:09:21 lr: 0.000652 loss: 3.3696 (3.3554) grad_norm: 1.2258 (1.2624) time: 0.5071 [2021-03-26 01:25:53 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 200/1251] eta: 0:09:14 lr: 0.000652 loss: 3.4886 (3.3649) grad_norm: 1.2217 (1.2611) time: 0.5013 [2021-03-26 01:25:58 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 210/1251] eta: 0:09:08 lr: 0.000652 loss: 3.3370 (3.3605) grad_norm: 1.1741 (1.2573) time: 0.5047 [2021-03-26 01:26:03 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 220/1251] eta: 0:09:01 lr: 0.000652 loss: 3.2431 (3.3610) grad_norm: 1.1872 (1.2573) time: 0.5062 [2021-03-26 01:26:08 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 230/1251] eta: 0:08:55 lr: 0.000652 loss: 3.6863 (3.3745) grad_norm: 1.1879 (1.2550) time: 0.5043 [2021-03-26 01:26:13 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 240/1251] eta: 0:08:50 lr: 0.000652 loss: 3.5962 (3.3765) grad_norm: 1.1756 (1.2525) time: 0.5104 [2021-03-26 01:26:18 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 250/1251] eta: 0:08:44 lr: 0.000652 loss: 3.3784 (3.3740) grad_norm: 1.2008 (1.2545) time: 0.5161 [2021-03-26 01:26:23 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 260/1251] eta: 0:08:38 lr: 0.000652 loss: 3.4706 (3.3815) grad_norm: 1.2095 (1.2533) time: 0.5109 [2021-03-26 01:26:28 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 270/1251] eta: 0:08:32 lr: 0.000652 loss: 3.6086 (3.3879) grad_norm: 1.1892 (1.2521) time: 0.5074 [2021-03-26 01:26:34 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 280/1251] eta: 0:08:27 lr: 0.000652 loss: 3.4846 (3.3857) grad_norm: 1.1787 (1.2496) time: 0.5079 [2021-03-26 01:26:39 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 290/1251] eta: 0:08:21 lr: 0.000652 loss: 3.1492 (3.3798) grad_norm: 1.1743 (1.2474) time: 0.5041 [2021-03-26 01:26:44 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 300/1251] eta: 0:08:15 lr: 0.000652 loss: 3.1940 (3.3861) grad_norm: 1.2009 (1.2492) time: 0.4983 [2021-03-26 01:26:49 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 310/1251] eta: 0:08:10 lr: 0.000652 loss: 3.6197 (3.3847) grad_norm: 1.2323 (1.2487) time: 0.5100 [2021-03-26 01:26:54 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 320/1251] eta: 0:08:04 lr: 0.000652 loss: 3.4446 (3.3868) grad_norm: 1.2323 (1.2509) time: 0.5203 [2021-03-26 01:26:59 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 330/1251] eta: 0:07:59 lr: 0.000652 loss: 3.4679 (3.3866) grad_norm: 1.2351 (1.2500) time: 0.5125 [2021-03-26 01:27:04 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 340/1251] eta: 0:07:53 lr: 0.000652 loss: 3.4679 (3.3851) grad_norm: 1.2461 (1.2507) time: 0.5056 [2021-03-26 01:27:09 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 350/1251] eta: 0:07:48 lr: 0.000652 loss: 3.5277 (3.3910) grad_norm: 1.2735 (1.2496) time: 0.5089 [2021-03-26 01:27:14 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 360/1251] eta: 0:07:42 lr: 0.000652 loss: 3.7339 (3.3935) grad_norm: 1.1816 (1.2480) time: 0.5062 [2021-03-26 01:27:19 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 370/1251] eta: 0:07:36 lr: 0.000652 loss: 3.7087 (3.3975) grad_norm: 1.2102 (1.2494) time: 0.5008 [2021-03-26 01:27:24 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 380/1251] eta: 0:07:31 lr: 0.000652 loss: 3.6709 (3.4017) grad_norm: 1.2660 (1.2488) time: 0.5091 [2021-03-26 01:27:29 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 390/1251] eta: 0:07:26 lr: 0.000651 loss: 3.5035 (3.4011) grad_norm: 1.2291 (1.2485) time: 0.5120 [2021-03-26 01:27:34 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 400/1251] eta: 0:07:20 lr: 0.000651 loss: 3.4025 (3.3971) grad_norm: 1.2520 (1.2500) time: 0.5059 [2021-03-26 01:27:39 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 410/1251] eta: 0:07:15 lr: 0.000651 loss: 3.4921 (3.4023) grad_norm: 1.2520 (1.2491) time: 0.5022 [2021-03-26 01:27:45 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 420/1251] eta: 0:07:09 lr: 0.000651 loss: 3.6383 (3.4074) grad_norm: 1.2086 (1.2493) time: 0.5025 [2021-03-26 01:27:50 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 430/1251] eta: 0:07:04 lr: 0.000651 loss: 3.5438 (3.4103) grad_norm: 1.2231 (1.2497) time: 0.5021 [2021-03-26 01:27:55 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 440/1251] eta: 0:06:59 lr: 0.000651 loss: 3.4108 (3.4096) grad_norm: 1.2276 (1.2496) time: 0.5084 [2021-03-26 01:28:00 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 450/1251] eta: 0:06:53 lr: 0.000651 loss: 3.5373 (3.4097) grad_norm: 1.2426 (1.2500) time: 0.5110 [2021-03-26 01:28:05 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 460/1251] eta: 0:06:48 lr: 0.000651 loss: 3.5512 (3.4085) grad_norm: 1.2455 (1.2500) time: 0.5064 [2021-03-26 01:28:10 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 470/1251] eta: 0:06:43 lr: 0.000651 loss: 3.6981 (3.4136) grad_norm: 1.2509 (1.2508) time: 0.5065 [2021-03-26 01:28:15 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 480/1251] eta: 0:06:37 lr: 0.000651 loss: 3.6981 (3.4166) grad_norm: 1.2826 (1.2518) time: 0.5060 [2021-03-26 01:28:20 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 490/1251] eta: 0:06:32 lr: 0.000651 loss: 3.5382 (3.4159) grad_norm: 1.2826 (1.2523) time: 0.5074 [2021-03-26 01:28:25 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 500/1251] eta: 0:06:27 lr: 0.000651 loss: 3.3072 (3.4133) grad_norm: 1.2642 (1.2527) time: 0.5096 [2021-03-26 01:28:30 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 510/1251] eta: 0:06:22 lr: 0.000651 loss: 3.3072 (3.4125) grad_norm: 1.2298 (1.2519) time: 0.5110 [2021-03-26 01:28:35 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 520/1251] eta: 0:06:16 lr: 0.000651 loss: 3.4297 (3.4120) grad_norm: 1.2397 (1.2527) time: 0.5066 [2021-03-26 01:28:40 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 530/1251] eta: 0:06:11 lr: 0.000651 loss: 3.3219 (3.4109) grad_norm: 1.2598 (1.2531) time: 0.5035 [2021-03-26 01:28:45 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 540/1251] eta: 0:06:06 lr: 0.000651 loss: 3.4897 (3.4140) grad_norm: 1.2809 (1.2545) time: 0.5069 [2021-03-26 01:28:51 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 550/1251] eta: 0:06:01 lr: 0.000651 loss: 3.6581 (3.4156) grad_norm: 1.3199 (1.2556) time: 0.5205 [2021-03-26 01:28:56 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 560/1251] eta: 0:05:55 lr: 0.000651 loss: 3.5730 (3.4143) grad_norm: 1.2444 (1.2556) time: 0.5213 [2021-03-26 01:29:01 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 570/1251] eta: 0:05:50 lr: 0.000651 loss: 3.4626 (3.4131) grad_norm: 1.2052 (1.2554) time: 0.5070 [2021-03-26 01:29:06 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 580/1251] eta: 0:05:45 lr: 0.000651 loss: 3.4816 (3.4116) grad_norm: 1.1828 (1.2538) time: 0.5069 [2021-03-26 01:29:11 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 590/1251] eta: 0:05:40 lr: 0.000651 loss: 3.4816 (3.4098) grad_norm: 1.1419 (1.2521) time: 0.5110 [2021-03-26 01:29:16 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 600/1251] eta: 0:05:35 lr: 0.000651 loss: 3.4165 (3.4111) grad_norm: 1.1615 (1.2515) time: 0.5090 [2021-03-26 01:29:21 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 610/1251] eta: 0:05:29 lr: 0.000651 loss: 3.5258 (3.4139) grad_norm: 1.2359 (1.2519) time: 0.5070 [2021-03-26 01:29:26 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 620/1251] eta: 0:05:24 lr: 0.000651 loss: 3.7695 (3.4151) grad_norm: 1.2660 (1.2525) time: 0.5086 [2021-03-26 01:29:31 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 630/1251] eta: 0:05:19 lr: 0.000651 loss: 3.2906 (3.4143) grad_norm: 1.2771 (1.2529) time: 0.5065 [2021-03-26 01:29:36 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 640/1251] eta: 0:05:14 lr: 0.000650 loss: 3.1643 (3.4107) grad_norm: 1.2652 (1.2534) time: 0.5029 [2021-03-26 01:29:41 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 650/1251] eta: 0:05:08 lr: 0.000650 loss: 3.5972 (3.4157) grad_norm: 1.2607 (1.2529) time: 0.5018 [2021-03-26 01:29:47 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 660/1251] eta: 0:05:03 lr: 0.000650 loss: 3.6766 (3.4162) grad_norm: 1.2483 (1.2542) time: 0.5065 [2021-03-26 01:29:52 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 670/1251] eta: 0:04:58 lr: 0.000650 loss: 3.4669 (3.4156) grad_norm: 1.2483 (1.2537) time: 0.5131 [2021-03-26 01:29:57 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 680/1251] eta: 0:04:53 lr: 0.000650 loss: 3.4689 (3.4153) grad_norm: 1.1606 (1.2531) time: 0.5129 [2021-03-26 01:30:02 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 690/1251] eta: 0:04:48 lr: 0.000650 loss: 3.4387 (3.4150) grad_norm: 1.2073 (1.2528) time: 0.5055 [2021-03-26 01:30:07 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 700/1251] eta: 0:04:43 lr: 0.000650 loss: 3.2531 (3.4137) grad_norm: 1.2227 (1.2527) time: 0.5055 [2021-03-26 01:30:12 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 710/1251] eta: 0:04:37 lr: 0.000650 loss: 3.2863 (3.4144) grad_norm: 1.2366 (1.2530) time: 0.5085 [2021-03-26 01:30:17 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 720/1251] eta: 0:04:32 lr: 0.000650 loss: 3.6230 (3.4181) grad_norm: 1.2366 (1.2525) time: 0.5019 [2021-03-26 01:30:22 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 730/1251] eta: 0:04:27 lr: 0.000650 loss: 3.6342 (3.4193) grad_norm: 1.2188 (1.2514) time: 0.5044 [2021-03-26 01:30:27 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 740/1251] eta: 0:04:22 lr: 0.000650 loss: 3.6342 (3.4215) grad_norm: 1.2261 (1.2525) time: 0.5228 [2021-03-26 01:30:33 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 750/1251] eta: 0:04:17 lr: 0.000650 loss: 3.6546 (3.4233) grad_norm: 1.2569 (1.2526) time: 0.5283 [2021-03-26 01:30:38 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 760/1251] eta: 0:04:12 lr: 0.000650 loss: 3.5383 (3.4232) grad_norm: 1.2817 (1.2531) time: 0.5165 [2021-03-26 01:30:43 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 770/1251] eta: 0:04:07 lr: 0.000650 loss: 3.3893 (3.4219) grad_norm: 1.3098 (1.2533) time: 0.5090 [2021-03-26 01:30:48 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 780/1251] eta: 0:04:01 lr: 0.000650 loss: 3.4521 (3.4250) grad_norm: 1.2190 (1.2530) time: 0.5113 [2021-03-26 01:30:53 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 790/1251] eta: 0:03:56 lr: 0.000650 loss: 3.4864 (3.4220) grad_norm: 1.2107 (1.2523) time: 0.5056 [2021-03-26 01:30:58 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 800/1251] eta: 0:03:51 lr: 0.000650 loss: 3.3561 (3.4224) grad_norm: 1.2233 (1.2526) time: 0.5014 [2021-03-26 01:31:03 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 810/1251] eta: 0:03:46 lr: 0.000650 loss: 3.3250 (3.4214) grad_norm: 1.2419 (1.2526) time: 0.5071 [2021-03-26 01:31:08 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 820/1251] eta: 0:03:41 lr: 0.000650 loss: 3.2809 (3.4180) grad_norm: 1.2072 (1.2521) time: 0.5068 [2021-03-26 01:31:13 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 830/1251] eta: 0:03:35 lr: 0.000650 loss: 3.3369 (3.4186) grad_norm: 1.2443 (1.2525) time: 0.4998 [2021-03-26 01:31:18 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 840/1251] eta: 0:03:30 lr: 0.000650 loss: 3.4126 (3.4191) grad_norm: 1.2903 (1.2538) time: 0.4995 [2021-03-26 01:31:23 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 850/1251] eta: 0:03:25 lr: 0.000650 loss: 3.6302 (3.4215) grad_norm: 1.2674 (1.2545) time: 0.5100 [2021-03-26 01:31:28 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 860/1251] eta: 0:03:20 lr: 0.000650 loss: 3.4510 (3.4215) grad_norm: 1.2600 (1.2539) time: 0.5168 [2021-03-26 01:31:34 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 870/1251] eta: 0:03:15 lr: 0.000650 loss: 3.3587 (3.4197) grad_norm: 1.2600 (1.2542) time: 0.5149 [2021-03-26 01:31:39 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 880/1251] eta: 0:03:10 lr: 0.000650 loss: 3.4976 (3.4203) grad_norm: 1.2716 (1.2543) time: 0.5105 [2021-03-26 01:31:44 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 890/1251] eta: 0:03:05 lr: 0.000650 loss: 3.5241 (3.4218) grad_norm: 1.2030 (1.2535) time: 0.5094 [2021-03-26 01:31:49 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 900/1251] eta: 0:02:59 lr: 0.000649 loss: 3.4594 (3.4217) grad_norm: 1.2030 (1.2534) time: 0.5059 [2021-03-26 01:31:54 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 910/1251] eta: 0:02:54 lr: 0.000649 loss: 3.4909 (3.4233) grad_norm: 1.2187 (1.2532) time: 0.5055 [2021-03-26 01:31:59 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 920/1251] eta: 0:02:49 lr: 0.000649 loss: 3.4909 (3.4217) grad_norm: 1.2331 (1.2529) time: 0.5127 [2021-03-26 01:32:04 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 930/1251] eta: 0:02:44 lr: 0.000649 loss: 3.3887 (3.4227) grad_norm: 1.2163 (1.2527) time: 0.5060 [2021-03-26 01:32:09 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 940/1251] eta: 0:02:39 lr: 0.000649 loss: 3.3058 (3.4206) grad_norm: 1.2029 (1.2521) time: 0.5006 [2021-03-26 01:32:14 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 950/1251] eta: 0:02:34 lr: 0.000649 loss: 3.2877 (3.4194) grad_norm: 1.1934 (1.2515) time: 0.5062 [2021-03-26 01:32:19 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 960/1251] eta: 0:02:29 lr: 0.000649 loss: 3.3684 (3.4198) grad_norm: 1.2093 (1.2519) time: 0.5010 [2021-03-26 01:32:24 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 970/1251] eta: 0:02:23 lr: 0.000649 loss: 3.5234 (3.4224) grad_norm: 1.3211 (1.2533) time: 0.5002 [2021-03-26 01:32:29 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 980/1251] eta: 0:02:18 lr: 0.000649 loss: 3.5234 (3.4240) grad_norm: 1.3208 (1.2540) time: 0.5004 [2021-03-26 01:32:34 swin_small_patch4_window7_224] INFO: Epoch: [121] [ 990/1251] eta: 0:02:13 lr: 0.000649 loss: 3.5316 (3.4237) grad_norm: 1.2167 (1.2536) time: 0.5043 [2021-03-26 01:32:39 swin_small_patch4_window7_224] INFO: Epoch: [121] [1000/1251] eta: 0:02:08 lr: 0.000649 loss: 3.2496 (3.4212) grad_norm: 1.2253 (1.2538) time: 0.5085 [2021-03-26 01:32:44 swin_small_patch4_window7_224] INFO: Epoch: [121] [1010/1251] eta: 0:02:03 lr: 0.000649 loss: 3.3081 (3.4208) grad_norm: 1.2417 (1.2538) time: 0.5071 [2021-03-26 01:32:49 swin_small_patch4_window7_224] INFO: Epoch: [121] [1020/1251] eta: 0:01:58 lr: 0.000649 loss: 3.4579 (3.4206) grad_norm: 1.2728 (1.2541) time: 0.5036 [2021-03-26 01:32:54 swin_small_patch4_window7_224] INFO: Epoch: [121] [1030/1251] eta: 0:01:53 lr: 0.000649 loss: 3.5753 (3.4223) grad_norm: 1.2735 (1.2541) time: 0.5042 [2021-03-26 01:32:59 swin_small_patch4_window7_224] INFO: Epoch: [121] [1040/1251] eta: 0:01:47 lr: 0.000649 loss: 3.5476 (3.4234) grad_norm: 1.2388 (1.2535) time: 0.5058 [2021-03-26 01:33:05 swin_small_patch4_window7_224] INFO: Epoch: [121] [1050/1251] eta: 0:01:42 lr: 0.000649 loss: 3.4866 (3.4217) grad_norm: 1.1829 (1.2534) time: 0.5073 [2021-03-26 01:33:10 swin_small_patch4_window7_224] INFO: Epoch: [121] [1060/1251] eta: 0:01:37 lr: 0.000649 loss: 3.3570 (3.4209) grad_norm: 1.2205 (1.2534) time: 0.5113 [2021-03-26 01:33:15 swin_small_patch4_window7_224] INFO: Epoch: [121] [1070/1251] eta: 0:01:32 lr: 0.000649 loss: 3.3791 (3.4208) grad_norm: 1.2360 (1.2538) time: 0.5095 [2021-03-26 01:33:20 swin_small_patch4_window7_224] INFO: Epoch: [121] [1080/1251] eta: 0:01:27 lr: 0.000649 loss: 3.3791 (3.4198) grad_norm: 1.3104 (1.2547) time: 0.5089 [2021-03-26 01:33:25 swin_small_patch4_window7_224] INFO: Epoch: [121] [1090/1251] eta: 0:01:22 lr: 0.000649 loss: 3.4107 (3.4187) grad_norm: 1.3226 (1.2557) time: 0.5075 [2021-03-26 01:33:30 swin_small_patch4_window7_224] INFO: Epoch: [121] [1100/1251] eta: 0:01:17 lr: 0.000649 loss: 3.4107 (3.4175) grad_norm: 1.2959 (1.2559) time: 0.5093 [2021-03-26 01:33:35 swin_small_patch4_window7_224] INFO: Epoch: [121] [1110/1251] eta: 0:01:12 lr: 0.000649 loss: 3.3739 (3.4148) grad_norm: 1.2702 (1.2558) time: 0.5084 [2021-03-26 01:33:40 swin_small_patch4_window7_224] INFO: Epoch: [121] [1120/1251] eta: 0:01:06 lr: 0.000649 loss: 3.3637 (3.4129) grad_norm: 1.2524 (1.2563) time: 0.5035 [2021-03-26 01:33:45 swin_small_patch4_window7_224] INFO: Epoch: [121] [1130/1251] eta: 0:01:01 lr: 0.000649 loss: 3.4741 (3.4134) grad_norm: 1.2524 (1.2564) time: 0.5062 [2021-03-26 01:33:50 swin_small_patch4_window7_224] INFO: Epoch: [121] [1140/1251] eta: 0:00:56 lr: 0.000649 loss: 3.5923 (3.4144) grad_norm: 1.1910 (1.2557) time: 0.5077 [2021-03-26 01:33:55 swin_small_patch4_window7_224] INFO: Epoch: [121] [1150/1251] eta: 0:00:51 lr: 0.000648 loss: 3.5060 (3.4126) grad_norm: 1.1910 (1.2563) time: 0.5028 [2021-03-26 01:34:00 swin_small_patch4_window7_224] INFO: Epoch: [121] [1160/1251] eta: 0:00:46 lr: 0.000648 loss: 3.3902 (3.4122) grad_norm: 1.3550 (1.2571) time: 0.5009 [2021-03-26 01:34:05 swin_small_patch4_window7_224] INFO: Epoch: [121] [1170/1251] eta: 0:00:41 lr: 0.000648 loss: 3.1134 (3.4101) grad_norm: 1.3064 (1.2572) time: 0.5018 [2021-03-26 01:34:10 swin_small_patch4_window7_224] INFO: Epoch: [121] [1180/1251] eta: 0:00:36 lr: 0.000648 loss: 3.6884 (3.4139) grad_norm: 1.2186 (1.2569) time: 0.5084 [2021-03-26 01:34:16 swin_small_patch4_window7_224] INFO: Epoch: [121] [1190/1251] eta: 0:00:31 lr: 0.000648 loss: 3.6884 (3.4138) grad_norm: 1.2020 (1.2571) time: 0.5085 [2021-03-26 01:34:21 swin_small_patch4_window7_224] INFO: Epoch: [121] [1200/1251] eta: 0:00:26 lr: 0.000648 loss: 3.3597 (3.4134) grad_norm: 1.2195 (1.2570) time: 0.5031 [2021-03-26 01:34:26 swin_small_patch4_window7_224] INFO: Epoch: [121] [1210/1251] eta: 0:00:20 lr: 0.000648 loss: 3.3754 (3.4131) grad_norm: 1.2707 (1.2571) time: 0.5042 [2021-03-26 01:34:31 swin_small_patch4_window7_224] INFO: Epoch: [121] [1220/1251] eta: 0:00:15 lr: 0.000648 loss: 3.6076 (3.4145) grad_norm: 1.3101 (1.2577) time: 0.5014 [2021-03-26 01:34:36 swin_small_patch4_window7_224] INFO: Epoch: [121] [1230/1251] eta: 0:00:10 lr: 0.000648 loss: 3.7310 (3.4172) grad_norm: 1.2403 (1.2573) time: 0.5035 [2021-03-26 01:34:41 swin_small_patch4_window7_224] INFO: Epoch: [121] [1240/1251] eta: 0:00:05 lr: 0.000648 loss: 3.6259 (3.4174) grad_norm: 1.2403 (1.2575) time: 0.5034 [2021-03-26 01:34:46 swin_small_patch4_window7_224] INFO: Epoch: [121] [1250/1251] eta: 0:00:00 lr: 0.000648 loss: 3.5088 (3.4159) grad_norm: 1.2715 (1.2587) time: 0.5036 [2021-03-26 01:34:55 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:47 loss: 0.8623 (0.8623) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-26 01:34:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8623 (0.9529) acc1: 79.6875 (78.5511) acc5: 93.7500 (94.8864) [2021-03-26 01:34:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9043 (0.9592) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.0893) [2021-03-26 01:35:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9876 (0.9970) acc1: 75.0000 (76.6633) acc5: 95.3125 (94.5060) [2021-03-26 01:35:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0872 (1.0206) acc1: 71.8750 (75.7622) acc5: 92.1875 (94.3216) [2021-03-26 01:35:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9876 (1.0084) acc1: 73.4375 (76.0640) acc5: 93.7500 (94.3040) [2021-03-26 01:35:10 swin_small_patch4_window7_224] INFO: * Acc@1 77.188 Acc@5 93.994 loss 0.996 [2021-03-26 01:35:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.2% [2021-03-26 01:35:10 swin_small_patch4_window7_224] INFO: Max accuracy: 77.19% [2021-03-26 01:35:14 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 0/1251] eta: 1:30:38 lr: 0.000648 loss: 3.6958 (3.6958) grad_norm: 1.4268 (1.4268) time: 4.3475 [2021-03-26 01:35:19 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 10/1251] eta: 0:17:48 lr: 0.000648 loss: 3.4040 (3.2485) grad_norm: 1.2584 (1.2355) time: 0.8611 [2021-03-26 01:35:25 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 20/1251] eta: 0:14:13 lr: 0.000648 loss: 3.6521 (3.4376) grad_norm: 1.2053 (1.2457) time: 0.5108 [2021-03-26 01:35:30 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 30/1251] eta: 0:12:52 lr: 0.000648 loss: 3.6521 (3.4209) grad_norm: 1.1982 (1.2428) time: 0.5072 [2021-03-26 01:35:35 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 40/1251] eta: 0:12:12 lr: 0.000648 loss: 3.4743 (3.4227) grad_norm: 1.2015 (1.2404) time: 0.5115 [2021-03-26 01:35:40 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 50/1251] eta: 0:11:42 lr: 0.000648 loss: 3.4743 (3.3941) grad_norm: 1.2612 (1.2508) time: 0.5100 [2021-03-26 01:35:45 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 60/1251] eta: 0:11:20 lr: 0.000648 loss: 3.3322 (3.3481) grad_norm: 1.2479 (1.2472) time: 0.5039 [2021-03-26 01:35:50 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 70/1251] eta: 0:11:04 lr: 0.000648 loss: 3.1333 (3.3191) grad_norm: 1.2176 (1.2490) time: 0.5071 [2021-03-26 01:35:55 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 80/1251] eta: 0:10:50 lr: 0.000648 loss: 3.3510 (3.3223) grad_norm: 1.1940 (1.2491) time: 0.5070 [2021-03-26 01:36:00 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 90/1251] eta: 0:10:39 lr: 0.000648 loss: 3.5818 (3.3227) grad_norm: 1.2853 (1.2612) time: 0.5078 [2021-03-26 01:36:05 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 100/1251] eta: 0:10:28 lr: 0.000648 loss: 3.3253 (3.2985) grad_norm: 1.3947 (1.2763) time: 0.5080 [2021-03-26 01:36:10 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 110/1251] eta: 0:10:20 lr: 0.000648 loss: 3.2646 (3.2927) grad_norm: 1.3291 (1.2812) time: 0.5129 [2021-03-26 01:36:15 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 120/1251] eta: 0:10:11 lr: 0.000648 loss: 3.2726 (3.2964) grad_norm: 1.2517 (1.2816) time: 0.5122 [2021-03-26 01:36:21 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 130/1251] eta: 0:10:03 lr: 0.000648 loss: 3.5396 (3.3140) grad_norm: 1.2821 (1.2817) time: 0.5071 [2021-03-26 01:36:25 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 140/1251] eta: 0:09:54 lr: 0.000648 loss: 3.5088 (3.3137) grad_norm: 1.2433 (1.2781) time: 0.5032 [2021-03-26 01:36:31 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 150/1251] eta: 0:09:47 lr: 0.000647 loss: 3.3733 (3.3152) grad_norm: 1.2301 (1.2752) time: 0.5061 [2021-03-26 01:36:36 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 160/1251] eta: 0:09:40 lr: 0.000647 loss: 3.2265 (3.3110) grad_norm: 1.2545 (1.2729) time: 0.5094 [2021-03-26 01:36:41 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 170/1251] eta: 0:09:33 lr: 0.000647 loss: 3.1835 (3.3128) grad_norm: 1.2362 (1.2698) time: 0.5027 [2021-03-26 01:36:46 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 180/1251] eta: 0:09:26 lr: 0.000647 loss: 3.2916 (3.3133) grad_norm: 1.2138 (1.2673) time: 0.5071 [2021-03-26 01:36:51 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 190/1251] eta: 0:09:20 lr: 0.000647 loss: 3.2945 (3.3112) grad_norm: 1.2075 (1.2667) time: 0.5110 [2021-03-26 01:36:56 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 200/1251] eta: 0:09:14 lr: 0.000647 loss: 3.3432 (3.3112) grad_norm: 1.2361 (1.2655) time: 0.5105 [2021-03-26 01:37:01 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 210/1251] eta: 0:09:07 lr: 0.000647 loss: 3.4279 (3.3126) grad_norm: 1.2305 (1.2619) time: 0.5052 [2021-03-26 01:37:06 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 220/1251] eta: 0:09:01 lr: 0.000647 loss: 3.3573 (3.3189) grad_norm: 1.2314 (1.2621) time: 0.5015 [2021-03-26 01:37:11 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 230/1251] eta: 0:08:54 lr: 0.000647 loss: 3.6241 (3.3218) grad_norm: 1.2425 (1.2629) time: 0.5008 [2021-03-26 01:37:16 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 240/1251] eta: 0:08:49 lr: 0.000647 loss: 3.5528 (3.3255) grad_norm: 1.2138 (1.2630) time: 0.5051 [2021-03-26 01:37:21 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 250/1251] eta: 0:08:42 lr: 0.000647 loss: 3.3973 (3.3202) grad_norm: 1.2668 (1.2633) time: 0.5056 [2021-03-26 01:37:26 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 260/1251] eta: 0:08:37 lr: 0.000647 loss: 3.3928 (3.3190) grad_norm: 1.2750 (1.2650) time: 0.5038 [2021-03-26 01:37:31 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 270/1251] eta: 0:08:31 lr: 0.000647 loss: 3.3928 (3.3260) grad_norm: 1.2710 (1.2665) time: 0.5147 [2021-03-26 01:37:37 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 280/1251] eta: 0:08:26 lr: 0.000647 loss: 3.5536 (3.3298) grad_norm: 1.2418 (1.2650) time: 0.5130 [2021-03-26 01:37:42 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 290/1251] eta: 0:08:20 lr: 0.000647 loss: 3.5536 (3.3360) grad_norm: 1.1980 (1.2634) time: 0.5067 [2021-03-26 01:37:47 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 300/1251] eta: 0:08:15 lr: 0.000647 loss: 3.3139 (3.3257) grad_norm: 1.2250 (1.2624) time: 0.5097 [2021-03-26 01:37:52 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 310/1251] eta: 0:08:09 lr: 0.000647 loss: 3.0045 (3.3178) grad_norm: 1.2301 (1.2624) time: 0.5024 [2021-03-26 01:37:57 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 320/1251] eta: 0:08:03 lr: 0.000647 loss: 3.5795 (3.3288) grad_norm: 1.2231 (1.2604) time: 0.4972 [2021-03-26 01:38:02 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 330/1251] eta: 0:07:57 lr: 0.000647 loss: 3.4028 (3.3224) grad_norm: 1.2161 (1.2617) time: 0.5037 [2021-03-26 01:38:07 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 340/1251] eta: 0:07:51 lr: 0.000647 loss: 3.3164 (3.3255) grad_norm: 1.2156 (1.2610) time: 0.5023 [2021-03-26 01:38:12 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 350/1251] eta: 0:07:46 lr: 0.000647 loss: 3.4666 (3.3299) grad_norm: 1.2862 (1.2645) time: 0.5002 [2021-03-26 01:38:17 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 360/1251] eta: 0:07:40 lr: 0.000647 loss: 3.5097 (3.3326) grad_norm: 1.4170 (1.2693) time: 0.5010 [2021-03-26 01:38:22 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 370/1251] eta: 0:07:35 lr: 0.000647 loss: 3.4259 (3.3294) grad_norm: 1.3888 (1.2720) time: 0.4968 [2021-03-26 01:38:27 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 380/1251] eta: 0:07:29 lr: 0.000647 loss: 3.2716 (3.3268) grad_norm: 1.3110 (1.2720) time: 0.4988 [2021-03-26 01:38:32 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 390/1251] eta: 0:07:24 lr: 0.000647 loss: 3.5131 (3.3301) grad_norm: 1.2065 (1.2710) time: 0.5015 [2021-03-26 01:38:37 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 400/1251] eta: 0:07:18 lr: 0.000646 loss: 3.4763 (3.3269) grad_norm: 1.2074 (1.2709) time: 0.4998 [2021-03-26 01:38:42 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 410/1251] eta: 0:07:13 lr: 0.000646 loss: 3.3893 (3.3303) grad_norm: 1.2467 (1.2715) time: 0.5023 [2021-03-26 01:38:47 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 420/1251] eta: 0:07:07 lr: 0.000646 loss: 3.5481 (3.3340) grad_norm: 1.2996 (1.2723) time: 0.5043 [2021-03-26 01:38:52 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 430/1251] eta: 0:07:02 lr: 0.000646 loss: 3.6003 (3.3398) grad_norm: 1.3046 (1.2735) time: 0.5103 [2021-03-26 01:38:57 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 440/1251] eta: 0:06:57 lr: 0.000646 loss: 3.5561 (3.3391) grad_norm: 1.2532 (1.2737) time: 0.5074 [2021-03-26 01:39:02 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 450/1251] eta: 0:06:51 lr: 0.000646 loss: 3.4347 (3.3403) grad_norm: 1.2217 (1.2725) time: 0.5027 [2021-03-26 01:39:07 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 460/1251] eta: 0:06:46 lr: 0.000646 loss: 3.4791 (3.3411) grad_norm: 1.2032 (1.2723) time: 0.5090 [2021-03-26 01:39:12 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 470/1251] eta: 0:06:41 lr: 0.000646 loss: 3.1537 (3.3387) grad_norm: 1.2338 (1.2733) time: 0.5072 [2021-03-26 01:39:17 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 480/1251] eta: 0:06:35 lr: 0.000646 loss: 3.4043 (3.3405) grad_norm: 1.2894 (1.2741) time: 0.4983 [2021-03-26 01:39:22 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 490/1251] eta: 0:06:30 lr: 0.000646 loss: 3.4563 (3.3422) grad_norm: 1.2721 (1.2739) time: 0.5021 [2021-03-26 01:39:27 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 500/1251] eta: 0:06:25 lr: 0.000646 loss: 3.3401 (3.3394) grad_norm: 1.2647 (1.2735) time: 0.5021 [2021-03-26 01:39:32 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 510/1251] eta: 0:06:20 lr: 0.000646 loss: 3.3735 (3.3381) grad_norm: 1.2647 (1.2744) time: 0.4975 [2021-03-26 01:39:37 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 520/1251] eta: 0:06:14 lr: 0.000646 loss: 3.4733 (3.3374) grad_norm: 1.2626 (1.2747) time: 0.5023 [2021-03-26 01:39:42 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 530/1251] eta: 0:06:09 lr: 0.000646 loss: 3.5845 (3.3376) grad_norm: 1.3157 (1.2755) time: 0.5061 [2021-03-26 01:39:47 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 540/1251] eta: 0:06:04 lr: 0.000646 loss: 3.6048 (3.3396) grad_norm: 1.1929 (1.2744) time: 0.5062 [2021-03-26 01:39:53 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 550/1251] eta: 0:05:59 lr: 0.000646 loss: 3.4411 (3.3404) grad_norm: 1.1929 (1.2746) time: 0.5196 [2021-03-26 01:39:58 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 560/1251] eta: 0:05:54 lr: 0.000646 loss: 3.4783 (3.3422) grad_norm: 1.2138 (1.2734) time: 0.5285 [2021-03-26 01:40:03 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 570/1251] eta: 0:05:49 lr: 0.000646 loss: 3.3996 (3.3426) grad_norm: 1.2503 (1.2737) time: 0.5115 [2021-03-26 01:40:08 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 580/1251] eta: 0:05:43 lr: 0.000646 loss: 3.2790 (3.3378) grad_norm: 1.2657 (1.2736) time: 0.5018 [2021-03-26 01:40:13 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 590/1251] eta: 0:05:38 lr: 0.000646 loss: 3.1567 (3.3341) grad_norm: 1.2548 (1.2743) time: 0.5078 [2021-03-26 01:40:18 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 600/1251] eta: 0:05:33 lr: 0.000646 loss: 3.5365 (3.3374) grad_norm: 1.2009 (1.2734) time: 0.5090 [2021-03-26 01:40:23 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 610/1251] eta: 0:05:28 lr: 0.000646 loss: 3.6058 (3.3364) grad_norm: 1.1941 (1.2728) time: 0.5066 [2021-03-26 01:40:28 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 620/1251] eta: 0:05:23 lr: 0.000646 loss: 3.5359 (3.3408) grad_norm: 1.2213 (1.2718) time: 0.5100 [2021-03-26 01:40:33 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 630/1251] eta: 0:05:18 lr: 0.000646 loss: 3.4232 (3.3402) grad_norm: 1.1860 (1.2705) time: 0.5074 [2021-03-26 01:40:38 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 640/1251] eta: 0:05:12 lr: 0.000646 loss: 3.5776 (3.3446) grad_norm: 1.1568 (1.2694) time: 0.5054 [2021-03-26 01:40:43 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 650/1251] eta: 0:05:07 lr: 0.000645 loss: 3.6629 (3.3502) grad_norm: 1.2079 (1.2689) time: 0.5052 [2021-03-26 01:40:48 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 660/1251] eta: 0:05:02 lr: 0.000645 loss: 3.4601 (3.3460) grad_norm: 1.2218 (1.2689) time: 0.4991 [2021-03-26 01:40:53 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 670/1251] eta: 0:04:57 lr: 0.000645 loss: 3.2763 (3.3483) grad_norm: 1.2516 (1.2698) time: 0.4985 [2021-03-26 01:40:59 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 680/1251] eta: 0:04:52 lr: 0.000645 loss: 3.5456 (3.3505) grad_norm: 1.2628 (1.2693) time: 0.5061 [2021-03-26 01:41:04 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 690/1251] eta: 0:04:46 lr: 0.000645 loss: 3.6242 (3.3541) grad_norm: 1.2409 (1.2706) time: 0.5063 [2021-03-26 01:41:09 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 700/1251] eta: 0:04:41 lr: 0.000645 loss: 3.6169 (3.3583) grad_norm: 1.2478 (1.2705) time: 0.4995 [2021-03-26 01:41:14 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 710/1251] eta: 0:04:36 lr: 0.000645 loss: 3.5053 (3.3591) grad_norm: 1.2441 (1.2708) time: 0.5049 [2021-03-26 01:41:19 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 720/1251] eta: 0:04:31 lr: 0.000645 loss: 3.4198 (3.3611) grad_norm: 1.1947 (1.2694) time: 0.5108 [2021-03-26 01:41:24 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 730/1251] eta: 0:04:26 lr: 0.000645 loss: 3.6592 (3.3642) grad_norm: 1.2403 (1.2703) time: 0.5105 [2021-03-26 01:41:29 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 740/1251] eta: 0:04:21 lr: 0.000645 loss: 3.6263 (3.3670) grad_norm: 1.3141 (1.2699) time: 0.5336 [2021-03-26 01:41:35 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 750/1251] eta: 0:04:16 lr: 0.000645 loss: 3.4055 (3.3648) grad_norm: 1.2015 (1.2694) time: 0.5326 [2021-03-26 01:41:40 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 760/1251] eta: 0:04:11 lr: 0.000645 loss: 3.5075 (3.3682) grad_norm: 1.2306 (1.2694) time: 0.5042 [2021-03-26 01:41:45 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 770/1251] eta: 0:04:06 lr: 0.000645 loss: 3.7202 (3.3717) grad_norm: 1.2372 (1.2698) time: 0.4997 [2021-03-26 01:41:50 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 780/1251] eta: 0:04:00 lr: 0.000645 loss: 3.4491 (3.3702) grad_norm: 1.2158 (1.2693) time: 0.5070 [2021-03-26 01:41:55 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 790/1251] eta: 0:03:55 lr: 0.000645 loss: 3.1318 (3.3699) grad_norm: 1.2653 (1.2702) time: 0.5096 [2021-03-26 01:42:00 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 800/1251] eta: 0:03:50 lr: 0.000645 loss: 3.6452 (3.3726) grad_norm: 1.2853 (1.2699) time: 0.5014 [2021-03-26 01:42:05 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 810/1251] eta: 0:03:45 lr: 0.000645 loss: 3.7039 (3.3765) grad_norm: 1.2225 (1.2694) time: 0.4990 [2021-03-26 01:42:10 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 820/1251] eta: 0:03:40 lr: 0.000645 loss: 3.6283 (3.3798) grad_norm: 1.2235 (1.2692) time: 0.5034 [2021-03-26 01:42:15 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 830/1251] eta: 0:03:35 lr: 0.000645 loss: 3.5864 (3.3808) grad_norm: 1.2351 (1.2694) time: 0.5070 [2021-03-26 01:42:20 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 840/1251] eta: 0:03:30 lr: 0.000645 loss: 3.6367 (3.3820) grad_norm: 1.3201 (1.2706) time: 0.5029 [2021-03-26 01:42:25 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 850/1251] eta: 0:03:24 lr: 0.000645 loss: 3.6181 (3.3818) grad_norm: 1.3336 (1.2708) time: 0.5036 [2021-03-26 01:42:30 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 860/1251] eta: 0:03:19 lr: 0.000645 loss: 3.5418 (3.3825) grad_norm: 1.1656 (1.2700) time: 0.5123 [2021-03-26 01:42:35 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 870/1251] eta: 0:03:14 lr: 0.000645 loss: 3.3676 (3.3799) grad_norm: 1.1593 (1.2692) time: 0.5060 [2021-03-26 01:42:40 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 880/1251] eta: 0:03:09 lr: 0.000645 loss: 3.3676 (3.3821) grad_norm: 1.1955 (1.2695) time: 0.5020 [2021-03-26 01:42:45 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 890/1251] eta: 0:03:04 lr: 0.000645 loss: 3.6240 (3.3851) grad_norm: 1.1955 (1.2686) time: 0.5045 [2021-03-26 01:42:50 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 900/1251] eta: 0:02:59 lr: 0.000644 loss: 3.5082 (3.3839) grad_norm: 1.2037 (1.2690) time: 0.5081 [2021-03-26 01:42:55 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 910/1251] eta: 0:02:54 lr: 0.000644 loss: 3.6092 (3.3873) grad_norm: 1.2496 (1.2684) time: 0.5053 [2021-03-26 01:43:00 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 920/1251] eta: 0:02:49 lr: 0.000644 loss: 3.6092 (3.3865) grad_norm: 1.2324 (1.2685) time: 0.5062 [2021-03-26 01:43:05 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 930/1251] eta: 0:02:43 lr: 0.000644 loss: 3.4278 (3.3873) grad_norm: 1.2411 (1.2684) time: 0.5059 [2021-03-26 01:43:10 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 940/1251] eta: 0:02:38 lr: 0.000644 loss: 3.4003 (3.3855) grad_norm: 1.2495 (1.2685) time: 0.5013 [2021-03-26 01:43:15 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 950/1251] eta: 0:02:33 lr: 0.000644 loss: 3.2407 (3.3852) grad_norm: 1.2451 (1.2682) time: 0.5037 [2021-03-26 01:43:21 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 960/1251] eta: 0:02:28 lr: 0.000644 loss: 3.3154 (3.3857) grad_norm: 1.2502 (1.2683) time: 0.5041 [2021-03-26 01:43:26 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 970/1251] eta: 0:02:23 lr: 0.000644 loss: 3.5562 (3.3887) grad_norm: 1.2607 (1.2690) time: 0.5021 [2021-03-26 01:43:31 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 980/1251] eta: 0:02:18 lr: 0.000644 loss: 3.6232 (3.3893) grad_norm: 1.2213 (1.2686) time: 0.5015 [2021-03-26 01:43:36 swin_small_patch4_window7_224] INFO: Epoch: [122] [ 990/1251] eta: 0:02:13 lr: 0.000644 loss: 3.2469 (3.3868) grad_norm: 1.1970 (1.2681) time: 0.5065 [2021-03-26 01:43:41 swin_small_patch4_window7_224] INFO: Epoch: [122] [1000/1251] eta: 0:02:08 lr: 0.000644 loss: 3.2141 (3.3868) grad_norm: 1.1970 (1.2675) time: 0.5108 [2021-03-26 01:43:46 swin_small_patch4_window7_224] INFO: Epoch: [122] [1010/1251] eta: 0:02:02 lr: 0.000644 loss: 3.5135 (3.3879) grad_norm: 1.2211 (1.2678) time: 0.5128 [2021-03-26 01:43:51 swin_small_patch4_window7_224] INFO: Epoch: [122] [1020/1251] eta: 0:01:57 lr: 0.000644 loss: 3.3871 (3.3856) grad_norm: 1.2465 (1.2675) time: 0.5065 [2021-03-26 01:43:56 swin_small_patch4_window7_224] INFO: Epoch: [122] [1030/1251] eta: 0:01:52 lr: 0.000644 loss: 3.3871 (3.3863) grad_norm: 1.2090 (1.2670) time: 0.4995 [2021-03-26 01:44:01 swin_small_patch4_window7_224] INFO: Epoch: [122] [1040/1251] eta: 0:01:47 lr: 0.000644 loss: 3.5920 (3.3871) grad_norm: 1.2090 (1.2669) time: 0.5050 [2021-03-26 01:44:06 swin_small_patch4_window7_224] INFO: Epoch: [122] [1050/1251] eta: 0:01:42 lr: 0.000644 loss: 3.5838 (3.3864) grad_norm: 1.2152 (1.2667) time: 0.5093 [2021-03-26 01:44:11 swin_small_patch4_window7_224] INFO: Epoch: [122] [1060/1251] eta: 0:01:37 lr: 0.000644 loss: 3.5397 (3.3877) grad_norm: 1.1896 (1.2659) time: 0.5078 [2021-03-26 01:44:16 swin_small_patch4_window7_224] INFO: Epoch: [122] [1070/1251] eta: 0:01:32 lr: 0.000644 loss: 3.6691 (3.3896) grad_norm: 1.2184 (1.2662) time: 0.5091 [2021-03-26 01:44:21 swin_small_patch4_window7_224] INFO: Epoch: [122] [1080/1251] eta: 0:01:27 lr: 0.000644 loss: 3.2980 (3.3852) grad_norm: 1.2602 (1.2666) time: 0.5058 [2021-03-26 01:44:26 swin_small_patch4_window7_224] INFO: Epoch: [122] [1090/1251] eta: 0:01:22 lr: 0.000644 loss: 3.1337 (3.3852) grad_norm: 1.2241 (1.2661) time: 0.5047 [2021-03-26 01:44:31 swin_small_patch4_window7_224] INFO: Epoch: [122] [1100/1251] eta: 0:01:16 lr: 0.000644 loss: 3.4559 (3.3857) grad_norm: 1.1885 (1.2655) time: 0.5058 [2021-03-26 01:44:36 swin_small_patch4_window7_224] INFO: Epoch: [122] [1110/1251] eta: 0:01:11 lr: 0.000644 loss: 3.4942 (3.3854) grad_norm: 1.1810 (1.2650) time: 0.5037 [2021-03-26 01:44:42 swin_small_patch4_window7_224] INFO: Epoch: [122] [1120/1251] eta: 0:01:06 lr: 0.000644 loss: 3.4942 (3.3871) grad_norm: 1.2412 (1.2653) time: 0.5075 [2021-03-26 01:44:47 swin_small_patch4_window7_224] INFO: Epoch: [122] [1130/1251] eta: 0:01:01 lr: 0.000644 loss: 3.7208 (3.3883) grad_norm: 1.2633 (1.2655) time: 0.5102 [2021-03-26 01:44:52 swin_small_patch4_window7_224] INFO: Epoch: [122] [1140/1251] eta: 0:00:56 lr: 0.000644 loss: 3.5552 (3.3883) grad_norm: 1.2314 (1.2651) time: 0.5022 [2021-03-26 01:44:57 swin_small_patch4_window7_224] INFO: Epoch: [122] [1150/1251] eta: 0:00:51 lr: 0.000644 loss: 3.4569 (3.3897) grad_norm: 1.2254 (1.2650) time: 0.4967 [2021-03-26 01:45:02 swin_small_patch4_window7_224] INFO: Epoch: [122] [1160/1251] eta: 0:00:46 lr: 0.000643 loss: 3.5128 (3.3915) grad_norm: 1.2508 (1.2647) time: 0.5010 [2021-03-26 01:45:07 swin_small_patch4_window7_224] INFO: Epoch: [122] [1170/1251] eta: 0:00:41 lr: 0.000643 loss: 3.4381 (3.3909) grad_norm: 1.2177 (1.2645) time: 0.5058 [2021-03-26 01:45:12 swin_small_patch4_window7_224] INFO: Epoch: [122] [1180/1251] eta: 0:00:36 lr: 0.000643 loss: 3.2719 (3.3896) grad_norm: 1.2047 (1.2645) time: 0.5036 [2021-03-26 01:45:17 swin_small_patch4_window7_224] INFO: Epoch: [122] [1190/1251] eta: 0:00:31 lr: 0.000643 loss: 3.4389 (3.3909) grad_norm: 1.1994 (1.2639) time: 0.5025 [2021-03-26 01:45:22 swin_small_patch4_window7_224] INFO: Epoch: [122] [1200/1251] eta: 0:00:25 lr: 0.000643 loss: 3.5402 (3.3901) grad_norm: 1.1870 (1.2640) time: 0.5072 [2021-03-26 01:45:27 swin_small_patch4_window7_224] INFO: Epoch: [122] [1210/1251] eta: 0:00:20 lr: 0.000643 loss: 3.5019 (3.3923) grad_norm: 1.2242 (1.2638) time: 0.5104 [2021-03-26 01:45:32 swin_small_patch4_window7_224] INFO: Epoch: [122] [1220/1251] eta: 0:00:15 lr: 0.000643 loss: 3.5562 (3.3915) grad_norm: 1.2061 (1.2636) time: 0.5056 [2021-03-26 01:45:37 swin_small_patch4_window7_224] INFO: Epoch: [122] [1230/1251] eta: 0:00:10 lr: 0.000643 loss: 3.3731 (3.3915) grad_norm: 1.2594 (1.2638) time: 0.4993 [2021-03-26 01:45:42 swin_small_patch4_window7_224] INFO: Epoch: [122] [1240/1251] eta: 0:00:05 lr: 0.000643 loss: 3.3854 (3.3913) grad_norm: 1.2753 (1.2640) time: 0.5056 [2021-03-26 01:45:47 swin_small_patch4_window7_224] INFO: Epoch: [122] [1250/1251] eta: 0:00:00 lr: 0.000643 loss: 3.5870 (3.3923) grad_norm: 1.2713 (1.2644) time: 0.5109 [2021-03-26 01:45:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.8989 (0.8989) acc1: 79.6875 (79.6875) acc5: 90.6250 (90.6250) [2021-03-26 01:45:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9378 (0.9952) acc1: 76.5625 (75.9943) acc5: 92.1875 (92.7557) [2021-03-26 01:45:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9378 (0.9861) acc1: 76.5625 (75.4464) acc5: 93.7500 (93.3036) [2021-03-26 01:46:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9394 (0.9796) acc1: 76.5625 (76.0585) acc5: 93.7500 (93.1956) [2021-03-26 01:46:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9009 (0.9654) acc1: 76.5625 (76.2195) acc5: 93.7500 (93.5213) [2021-03-26 01:46:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9145 (0.9799) acc1: 76.5625 (76.1600) acc5: 93.7500 (93.6960) [2021-03-26 01:46:09 swin_small_patch4_window7_224] INFO: * Acc@1 77.188 Acc@5 93.966 loss 0.964 [2021-03-26 01:46:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.2% [2021-03-26 01:46:09 swin_small_patch4_window7_224] INFO: Max accuracy: 77.19% [2021-03-26 01:46:14 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 0/1251] eta: 1:26:35 lr: 0.000643 loss: 3.7569 (3.7569) grad_norm: 1.1526 (1.1526) time: 4.1527 [2021-03-26 01:46:19 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 10/1251] eta: 0:17:52 lr: 0.000643 loss: 3.3396 (3.3732) grad_norm: 1.2403 (1.2140) time: 0.8642 [2021-03-26 01:46:24 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 20/1251] eta: 0:14:16 lr: 0.000643 loss: 3.3991 (3.4705) grad_norm: 1.2403 (1.2422) time: 0.5228 [2021-03-26 01:46:29 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 30/1251] eta: 0:12:54 lr: 0.000643 loss: 3.4212 (3.4226) grad_norm: 1.2963 (1.2596) time: 0.5073 [2021-03-26 01:46:34 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 40/1251] eta: 0:12:07 lr: 0.000643 loss: 3.2756 (3.3648) grad_norm: 1.2757 (1.2609) time: 0.5013 [2021-03-26 01:46:39 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 50/1251] eta: 0:11:37 lr: 0.000643 loss: 3.2809 (3.3776) grad_norm: 1.2238 (1.2557) time: 0.4987 [2021-03-26 01:46:44 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 60/1251] eta: 0:11:17 lr: 0.000643 loss: 3.4049 (3.3383) grad_norm: 1.2589 (1.2641) time: 0.5027 [2021-03-26 01:46:49 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 70/1251] eta: 0:11:02 lr: 0.000643 loss: 3.1557 (3.3282) grad_norm: 1.2536 (1.2632) time: 0.5094 [2021-03-26 01:46:54 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 80/1251] eta: 0:10:50 lr: 0.000643 loss: 3.4625 (3.3594) grad_norm: 1.1950 (1.2548) time: 0.5151 [2021-03-26 01:47:00 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 90/1251] eta: 0:10:39 lr: 0.000643 loss: 3.5410 (3.3658) grad_norm: 1.2353 (1.2555) time: 0.5148 [2021-03-26 01:47:05 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 100/1251] eta: 0:10:28 lr: 0.000643 loss: 3.3986 (3.3507) grad_norm: 1.2627 (1.2569) time: 0.5088 [2021-03-26 01:47:10 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 110/1251] eta: 0:10:19 lr: 0.000643 loss: 3.6808 (3.3675) grad_norm: 1.2391 (1.2594) time: 0.5088 [2021-03-26 01:47:15 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 120/1251] eta: 0:10:11 lr: 0.000643 loss: 3.4690 (3.3656) grad_norm: 1.2507 (1.2695) time: 0.5141 [2021-03-26 01:47:20 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 130/1251] eta: 0:10:05 lr: 0.000643 loss: 3.4387 (3.3659) grad_norm: 1.2507 (1.2672) time: 0.5225 [2021-03-26 01:47:25 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 140/1251] eta: 0:09:57 lr: 0.000643 loss: 3.5650 (3.3698) grad_norm: 1.2356 (1.2680) time: 0.5184 [2021-03-26 01:47:30 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 150/1251] eta: 0:09:49 lr: 0.000643 loss: 3.5738 (3.3754) grad_norm: 1.2689 (1.2687) time: 0.5023 [2021-03-26 01:47:35 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 160/1251] eta: 0:09:41 lr: 0.000642 loss: 3.3236 (3.3704) grad_norm: 1.2689 (1.2723) time: 0.4964 [2021-03-26 01:47:40 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 170/1251] eta: 0:09:33 lr: 0.000642 loss: 3.6242 (3.3942) grad_norm: 1.2289 (1.2717) time: 0.4996 [2021-03-26 01:47:45 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 180/1251] eta: 0:09:27 lr: 0.000642 loss: 3.7903 (3.4036) grad_norm: 1.2915 (1.2773) time: 0.5102 [2021-03-26 01:47:51 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 190/1251] eta: 0:09:21 lr: 0.000642 loss: 3.6365 (3.4084) grad_norm: 1.3196 (1.2802) time: 0.5185 [2021-03-26 01:47:56 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 200/1251] eta: 0:09:15 lr: 0.000642 loss: 3.4903 (3.4066) grad_norm: 1.2334 (1.2789) time: 0.5169 [2021-03-26 01:48:01 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 210/1251] eta: 0:09:09 lr: 0.000642 loss: 3.4536 (3.4099) grad_norm: 1.2294 (1.2787) time: 0.5075 [2021-03-26 01:48:06 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 220/1251] eta: 0:09:02 lr: 0.000642 loss: 3.5250 (3.4162) grad_norm: 1.2308 (1.2789) time: 0.5039 [2021-03-26 01:48:11 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 230/1251] eta: 0:08:56 lr: 0.000642 loss: 3.4883 (3.4132) grad_norm: 1.2712 (1.2792) time: 0.5052 [2021-03-26 01:48:16 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 240/1251] eta: 0:08:50 lr: 0.000642 loss: 3.3682 (3.4068) grad_norm: 1.2631 (1.2779) time: 0.5049 [2021-03-26 01:48:21 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 250/1251] eta: 0:08:44 lr: 0.000642 loss: 3.3682 (3.3967) grad_norm: 1.2761 (1.2802) time: 0.5026 [2021-03-26 01:48:26 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 260/1251] eta: 0:08:38 lr: 0.000642 loss: 3.4223 (3.3950) grad_norm: 1.3176 (1.2823) time: 0.4993 [2021-03-26 01:48:31 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 270/1251] eta: 0:08:32 lr: 0.000642 loss: 3.4869 (3.3980) grad_norm: 1.2726 (1.2846) time: 0.5069 [2021-03-26 01:48:36 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 280/1251] eta: 0:08:26 lr: 0.000642 loss: 3.4374 (3.3921) grad_norm: 1.2417 (1.2828) time: 0.5104 [2021-03-26 01:48:41 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 290/1251] eta: 0:08:21 lr: 0.000642 loss: 3.4374 (3.3922) grad_norm: 1.2195 (1.2826) time: 0.5064 [2021-03-26 01:48:46 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 300/1251] eta: 0:08:15 lr: 0.000642 loss: 3.3272 (3.3805) grad_norm: 1.1539 (1.2788) time: 0.5094 [2021-03-26 01:48:51 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 310/1251] eta: 0:08:10 lr: 0.000642 loss: 3.4953 (3.3915) grad_norm: 1.1425 (1.2788) time: 0.5123 [2021-03-26 01:48:57 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 320/1251] eta: 0:08:04 lr: 0.000642 loss: 3.5467 (3.3888) grad_norm: 1.2279 (1.2777) time: 0.5144 [2021-03-26 01:49:02 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 330/1251] eta: 0:07:59 lr: 0.000642 loss: 3.4693 (3.3920) grad_norm: 1.2068 (1.2756) time: 0.5098 [2021-03-26 01:49:07 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 340/1251] eta: 0:07:53 lr: 0.000642 loss: 3.5552 (3.4010) grad_norm: 1.2011 (1.2760) time: 0.5032 [2021-03-26 01:49:12 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 350/1251] eta: 0:07:47 lr: 0.000642 loss: 3.6626 (3.4043) grad_norm: 1.2514 (1.2774) time: 0.5066 [2021-03-26 01:49:17 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 360/1251] eta: 0:07:42 lr: 0.000642 loss: 3.5624 (3.4053) grad_norm: 1.2884 (1.2777) time: 0.5087 [2021-03-26 01:49:22 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 370/1251] eta: 0:07:36 lr: 0.000642 loss: 3.5919 (3.4103) grad_norm: 1.2323 (1.2768) time: 0.5031 [2021-03-26 01:49:27 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 380/1251] eta: 0:07:31 lr: 0.000642 loss: 3.5919 (3.4118) grad_norm: 1.2840 (1.2779) time: 0.5043 [2021-03-26 01:49:32 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 390/1251] eta: 0:07:26 lr: 0.000642 loss: 3.2926 (3.4051) grad_norm: 1.2933 (1.2784) time: 0.5096 [2021-03-26 01:49:37 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 400/1251] eta: 0:07:20 lr: 0.000642 loss: 3.3870 (3.4119) grad_norm: 1.2904 (1.2785) time: 0.5022 [2021-03-26 01:49:42 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 410/1251] eta: 0:07:14 lr: 0.000641 loss: 3.6868 (3.4152) grad_norm: 1.2830 (1.2806) time: 0.4981 [2021-03-26 01:49:47 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 420/1251] eta: 0:07:09 lr: 0.000641 loss: 3.6166 (3.4179) grad_norm: 1.2531 (1.2790) time: 0.4987 [2021-03-26 01:49:52 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 430/1251] eta: 0:07:03 lr: 0.000641 loss: 3.4993 (3.4146) grad_norm: 1.2203 (1.2782) time: 0.5020 [2021-03-26 01:49:57 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 440/1251] eta: 0:06:58 lr: 0.000641 loss: 3.4871 (3.4122) grad_norm: 1.2237 (1.2766) time: 0.5048 [2021-03-26 01:50:02 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 450/1251] eta: 0:06:53 lr: 0.000641 loss: 3.4871 (3.4124) grad_norm: 1.2205 (1.2762) time: 0.5032 [2021-03-26 01:50:07 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 460/1251] eta: 0:06:47 lr: 0.000641 loss: 3.5140 (3.4115) grad_norm: 1.1802 (1.2741) time: 0.5033 [2021-03-26 01:50:12 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 470/1251] eta: 0:06:42 lr: 0.000641 loss: 3.4474 (3.4089) grad_norm: 1.1686 (1.2721) time: 0.5019 [2021-03-26 01:50:17 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 480/1251] eta: 0:06:37 lr: 0.000641 loss: 3.4145 (3.4047) grad_norm: 1.1929 (1.2717) time: 0.5031 [2021-03-26 01:50:22 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 490/1251] eta: 0:06:31 lr: 0.000641 loss: 3.4028 (3.4011) grad_norm: 1.2356 (1.2715) time: 0.5023 [2021-03-26 01:50:27 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 500/1251] eta: 0:06:26 lr: 0.000641 loss: 3.5285 (3.4041) grad_norm: 1.2557 (1.2713) time: 0.5037 [2021-03-26 01:50:32 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 510/1251] eta: 0:06:21 lr: 0.000641 loss: 3.6344 (3.4079) grad_norm: 1.2411 (1.2707) time: 0.5040 [2021-03-26 01:50:37 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 520/1251] eta: 0:06:15 lr: 0.000641 loss: 3.4807 (3.4036) grad_norm: 1.2209 (1.2701) time: 0.5030 [2021-03-26 01:50:42 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 530/1251] eta: 0:06:10 lr: 0.000641 loss: 3.4625 (3.4052) grad_norm: 1.2209 (1.2700) time: 0.5039 [2021-03-26 01:50:47 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 540/1251] eta: 0:06:05 lr: 0.000641 loss: 3.5402 (3.4062) grad_norm: 1.2006 (1.2698) time: 0.5063 [2021-03-26 01:50:53 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 550/1251] eta: 0:06:00 lr: 0.000641 loss: 3.6632 (3.4095) grad_norm: 1.2311 (1.2695) time: 0.5264 [2021-03-26 01:50:58 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 560/1251] eta: 0:05:55 lr: 0.000641 loss: 3.6296 (3.4104) grad_norm: 1.2823 (1.2698) time: 0.5233 [2021-03-26 01:51:03 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 570/1251] eta: 0:05:49 lr: 0.000641 loss: 3.5317 (3.4137) grad_norm: 1.3225 (nan) time: 0.4983 [2021-03-26 01:51:08 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 580/1251] eta: 0:05:44 lr: 0.000641 loss: 3.6324 (3.4154) grad_norm: 1.3225 (nan) time: 0.4974 [2021-03-26 01:51:13 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 590/1251] eta: 0:05:39 lr: 0.000641 loss: 3.4754 (3.4116) grad_norm: 1.2285 (nan) time: 0.5009 [2021-03-26 01:51:18 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 600/1251] eta: 0:05:34 lr: 0.000641 loss: 3.3993 (3.4153) grad_norm: 1.2362 (nan) time: 0.5012 [2021-03-26 01:51:23 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 610/1251] eta: 0:05:28 lr: 0.000641 loss: 3.3993 (3.4122) grad_norm: 1.2520 (nan) time: 0.4986 [2021-03-26 01:51:28 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 620/1251] eta: 0:05:23 lr: 0.000641 loss: 3.3588 (3.4150) grad_norm: 1.2534 (nan) time: 0.4990 [2021-03-26 01:51:33 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 630/1251] eta: 0:05:18 lr: 0.000641 loss: 3.7040 (3.4154) grad_norm: 1.2534 (nan) time: 0.5008 [2021-03-26 01:51:38 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 640/1251] eta: 0:05:13 lr: 0.000641 loss: 3.5250 (3.4168) grad_norm: 1.2058 (nan) time: 0.5003 [2021-03-26 01:51:43 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 650/1251] eta: 0:05:07 lr: 0.000641 loss: 3.6561 (3.4203) grad_norm: 1.2561 (nan) time: 0.5074 [2021-03-26 01:51:48 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 660/1251] eta: 0:05:02 lr: 0.000640 loss: 3.5516 (3.4203) grad_norm: 1.2714 (nan) time: 0.5083 [2021-03-26 01:51:53 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 670/1251] eta: 0:04:57 lr: 0.000640 loss: 3.4735 (3.4192) grad_norm: 1.2651 (nan) time: 0.5026 [2021-03-26 01:51:58 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 680/1251] eta: 0:04:52 lr: 0.000640 loss: 3.5248 (3.4203) grad_norm: 1.2130 (nan) time: 0.5039 [2021-03-26 01:52:03 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 690/1251] eta: 0:04:47 lr: 0.000640 loss: 3.4965 (3.4185) grad_norm: 1.2566 (nan) time: 0.5117 [2021-03-26 01:52:08 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 700/1251] eta: 0:04:42 lr: 0.000640 loss: 3.4206 (3.4187) grad_norm: 1.2863 (nan) time: 0.5142 [2021-03-26 01:52:13 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 710/1251] eta: 0:04:36 lr: 0.000640 loss: 3.4206 (3.4167) grad_norm: 1.2703 (nan) time: 0.5059 [2021-03-26 01:52:19 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 720/1251] eta: 0:04:31 lr: 0.000640 loss: 3.4253 (3.4162) grad_norm: 1.2703 (nan) time: 0.5027 [2021-03-26 01:52:24 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 730/1251] eta: 0:04:26 lr: 0.000640 loss: 3.4480 (3.4155) grad_norm: 1.3129 (nan) time: 0.5096 [2021-03-26 01:52:29 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 740/1251] eta: 0:04:21 lr: 0.000640 loss: 3.4480 (3.4127) grad_norm: 1.3265 (nan) time: 0.5326 [2021-03-26 01:52:34 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 750/1251] eta: 0:04:16 lr: 0.000640 loss: 3.4781 (3.4153) grad_norm: 1.3265 (nan) time: 0.5395 [2021-03-26 01:52:40 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 760/1251] eta: 0:04:11 lr: 0.000640 loss: 3.4853 (3.4168) grad_norm: 1.2048 (nan) time: 0.5172 [2021-03-26 01:52:45 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 770/1251] eta: 0:04:06 lr: 0.000640 loss: 3.4627 (3.4170) grad_norm: 1.1984 (nan) time: 0.5125 [2021-03-26 01:52:50 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 780/1251] eta: 0:04:01 lr: 0.000640 loss: 3.4139 (3.4175) grad_norm: 1.2938 (nan) time: 0.5128 [2021-03-26 01:52:55 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 790/1251] eta: 0:03:56 lr: 0.000640 loss: 3.4715 (3.4174) grad_norm: 1.2998 (nan) time: 0.5036 [2021-03-26 01:53:00 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 800/1251] eta: 0:03:50 lr: 0.000640 loss: 3.4715 (3.4165) grad_norm: 1.3057 (nan) time: 0.4948 [2021-03-26 01:53:05 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 810/1251] eta: 0:03:45 lr: 0.000640 loss: 3.5272 (3.4162) grad_norm: 1.2555 (nan) time: 0.4951 [2021-03-26 01:53:10 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 820/1251] eta: 0:03:40 lr: 0.000640 loss: 3.5384 (3.4182) grad_norm: 1.2164 (nan) time: 0.5024 [2021-03-26 01:53:15 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 830/1251] eta: 0:03:35 lr: 0.000640 loss: 3.4242 (3.4162) grad_norm: 1.2246 (nan) time: 0.5123 [2021-03-26 01:53:20 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 840/1251] eta: 0:03:30 lr: 0.000640 loss: 3.4242 (3.4157) grad_norm: 1.2560 (nan) time: 0.5118 [2021-03-26 01:53:25 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 850/1251] eta: 0:03:25 lr: 0.000640 loss: 3.3558 (3.4164) grad_norm: 1.2279 (nan) time: 0.5095 [2021-03-26 01:53:30 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 860/1251] eta: 0:03:20 lr: 0.000640 loss: 3.4602 (3.4152) grad_norm: 1.2278 (nan) time: 0.5047 [2021-03-26 01:53:35 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 870/1251] eta: 0:03:14 lr: 0.000640 loss: 3.5188 (3.4164) grad_norm: 1.2194 (nan) time: 0.5074 [2021-03-26 01:53:40 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 880/1251] eta: 0:03:09 lr: 0.000640 loss: 3.4844 (3.4142) grad_norm: 1.2118 (nan) time: 0.5184 [2021-03-26 01:53:45 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 890/1251] eta: 0:03:04 lr: 0.000640 loss: 3.3832 (3.4126) grad_norm: 1.2102 (nan) time: 0.5067 [2021-03-26 01:53:50 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 900/1251] eta: 0:02:59 lr: 0.000640 loss: 3.4105 (3.4111) grad_norm: 1.2122 (nan) time: 0.4949 [2021-03-26 01:53:55 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 910/1251] eta: 0:02:54 lr: 0.000639 loss: 3.4818 (3.4105) grad_norm: 1.2472 (nan) time: 0.4980 [2021-03-26 01:54:00 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 920/1251] eta: 0:02:49 lr: 0.000639 loss: 3.2554 (3.4068) grad_norm: 1.2660 (nan) time: 0.5054 [2021-03-26 01:54:06 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 930/1251] eta: 0:02:44 lr: 0.000639 loss: 3.3292 (3.4061) grad_norm: 1.2422 (nan) time: 0.5088 [2021-03-26 01:54:11 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 940/1251] eta: 0:02:38 lr: 0.000639 loss: 3.5139 (3.4063) grad_norm: 1.2677 (nan) time: 0.5111 [2021-03-26 01:54:16 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 950/1251] eta: 0:02:33 lr: 0.000639 loss: 3.6860 (3.4089) grad_norm: 1.3275 (nan) time: 0.5099 [2021-03-26 01:54:21 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 960/1251] eta: 0:02:28 lr: 0.000639 loss: 3.6706 (3.4107) grad_norm: 1.3275 (nan) time: 0.5062 [2021-03-26 01:54:26 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 970/1251] eta: 0:02:23 lr: 0.000639 loss: 3.5129 (3.4124) grad_norm: 1.2694 (nan) time: 0.5043 [2021-03-26 01:54:31 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 980/1251] eta: 0:02:18 lr: 0.000639 loss: 3.4611 (3.4123) grad_norm: 1.2134 (nan) time: 0.5038 [2021-03-26 01:54:36 swin_small_patch4_window7_224] INFO: Epoch: [123] [ 990/1251] eta: 0:02:13 lr: 0.000639 loss: 3.3436 (3.4115) grad_norm: 1.2134 (nan) time: 0.5056 [2021-03-26 01:54:41 swin_small_patch4_window7_224] INFO: Epoch: [123] [1000/1251] eta: 0:02:08 lr: 0.000639 loss: 3.3493 (3.4113) grad_norm: 1.1799 (nan) time: 0.5010 [2021-03-26 01:54:46 swin_small_patch4_window7_224] INFO: Epoch: [123] [1010/1251] eta: 0:02:03 lr: 0.000639 loss: 3.4328 (3.4114) grad_norm: 1.1684 (nan) time: 0.4990 [2021-03-26 01:54:51 swin_small_patch4_window7_224] INFO: Epoch: [123] [1020/1251] eta: 0:01:57 lr: 0.000639 loss: 3.4428 (3.4111) grad_norm: 1.2456 (nan) time: 0.5038 [2021-03-26 01:54:56 swin_small_patch4_window7_224] INFO: Epoch: [123] [1030/1251] eta: 0:01:52 lr: 0.000639 loss: 3.4637 (3.4109) grad_norm: 1.2617 (nan) time: 0.5088 [2021-03-26 01:55:01 swin_small_patch4_window7_224] INFO: Epoch: [123] [1040/1251] eta: 0:01:47 lr: 0.000639 loss: 3.4455 (3.4110) grad_norm: 1.2460 (nan) time: 0.5045 [2021-03-26 01:55:06 swin_small_patch4_window7_224] INFO: Epoch: [123] [1050/1251] eta: 0:01:42 lr: 0.000639 loss: 3.4455 (3.4118) grad_norm: 1.2510 (nan) time: 0.5024 [2021-03-26 01:55:11 swin_small_patch4_window7_224] INFO: Epoch: [123] [1060/1251] eta: 0:01:37 lr: 0.000639 loss: 3.5338 (3.4143) grad_norm: 1.2980 (nan) time: 0.5087 [2021-03-26 01:55:16 swin_small_patch4_window7_224] INFO: Epoch: [123] [1070/1251] eta: 0:01:32 lr: 0.000639 loss: 3.4689 (3.4133) grad_norm: 1.3273 (nan) time: 0.5058 [2021-03-26 01:55:21 swin_small_patch4_window7_224] INFO: Epoch: [123] [1080/1251] eta: 0:01:27 lr: 0.000639 loss: 3.4418 (3.4156) grad_norm: 1.3114 (nan) time: 0.5043 [2021-03-26 01:55:26 swin_small_patch4_window7_224] INFO: Epoch: [123] [1090/1251] eta: 0:01:22 lr: 0.000639 loss: 3.7084 (3.4145) grad_norm: 1.3026 (nan) time: 0.5030 [2021-03-26 01:55:31 swin_small_patch4_window7_224] INFO: Epoch: [123] [1100/1251] eta: 0:01:17 lr: 0.000639 loss: 3.1175 (3.4137) grad_norm: 1.3026 (nan) time: 0.5046 [2021-03-26 01:55:36 swin_small_patch4_window7_224] INFO: Epoch: [123] [1110/1251] eta: 0:01:11 lr: 0.000639 loss: 3.1493 (3.4115) grad_norm: 1.2719 (nan) time: 0.5052 [2021-03-26 01:55:41 swin_small_patch4_window7_224] INFO: Epoch: [123] [1120/1251] eta: 0:01:06 lr: 0.000639 loss: 3.1493 (3.4111) grad_norm: 1.2974 (nan) time: 0.5032 [2021-03-26 01:55:47 swin_small_patch4_window7_224] INFO: Epoch: [123] [1130/1251] eta: 0:01:01 lr: 0.000639 loss: 3.5914 (3.4117) grad_norm: 1.2974 (nan) time: 0.5076 [2021-03-26 01:55:52 swin_small_patch4_window7_224] INFO: Epoch: [123] [1140/1251] eta: 0:00:56 lr: 0.000639 loss: 3.6514 (3.4124) grad_norm: 1.2420 (nan) time: 0.5096 [2021-03-26 01:55:57 swin_small_patch4_window7_224] INFO: Epoch: [123] [1150/1251] eta: 0:00:51 lr: 0.000639 loss: 3.6029 (3.4129) grad_norm: 1.2397 (nan) time: 0.5066 [2021-03-26 01:56:02 swin_small_patch4_window7_224] INFO: Epoch: [123] [1160/1251] eta: 0:00:46 lr: 0.000638 loss: 3.6029 (3.4136) grad_norm: 1.2567 (nan) time: 0.5031 [2021-03-26 01:56:07 swin_small_patch4_window7_224] INFO: Epoch: [123] [1170/1251] eta: 0:00:41 lr: 0.000638 loss: 3.5723 (3.4138) grad_norm: 1.2711 (nan) time: 0.4997 [2021-03-26 01:56:12 swin_small_patch4_window7_224] INFO: Epoch: [123] [1180/1251] eta: 0:00:36 lr: 0.000638 loss: 3.5723 (3.4139) grad_norm: 1.2338 (nan) time: 0.5025 [2021-03-26 01:56:17 swin_small_patch4_window7_224] INFO: Epoch: [123] [1190/1251] eta: 0:00:31 lr: 0.000638 loss: 3.6493 (3.4150) grad_norm: 1.2338 (nan) time: 0.5038 [2021-03-26 01:56:22 swin_small_patch4_window7_224] INFO: Epoch: [123] [1200/1251] eta: 0:00:25 lr: 0.000638 loss: 3.5595 (3.4149) grad_norm: 1.2551 (nan) time: 0.5002 [2021-03-26 01:56:27 swin_small_patch4_window7_224] INFO: Epoch: [123] [1210/1251] eta: 0:00:20 lr: 0.000638 loss: 3.2343 (3.4113) grad_norm: 1.2841 (nan) time: 0.5058 [2021-03-26 01:56:32 swin_small_patch4_window7_224] INFO: Epoch: [123] [1220/1251] eta: 0:00:15 lr: 0.000638 loss: 3.2343 (3.4107) grad_norm: 1.2629 (nan) time: 0.5077 [2021-03-26 01:56:37 swin_small_patch4_window7_224] INFO: Epoch: [123] [1230/1251] eta: 0:00:10 lr: 0.000638 loss: 3.5368 (3.4101) grad_norm: 1.2159 (nan) time: 0.5074 [2021-03-26 01:56:42 swin_small_patch4_window7_224] INFO: Epoch: [123] [1240/1251] eta: 0:00:05 lr: 0.000638 loss: 3.4149 (3.4100) grad_norm: 1.2193 (nan) time: 0.5090 [2021-03-26 01:56:47 swin_small_patch4_window7_224] INFO: Epoch: [123] [1250/1251] eta: 0:00:00 lr: 0.000638 loss: 3.5322 (3.4110) grad_norm: 1.2193 (nan) time: 0.5064 [2021-03-26 01:56:55 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:41 loss: 1.1333 (1.1333) acc1: 70.3125 (70.3125) acc5: 93.7500 (93.7500) [2021-03-26 01:56:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9429 (0.9413) acc1: 78.1250 (78.5511) acc5: 95.3125 (94.4602) [2021-03-26 01:57:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9224 (0.9395) acc1: 78.1250 (77.4554) acc5: 93.7500 (94.2708) [2021-03-26 01:57:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0158 (0.9975) acc1: 76.5625 (76.5625) acc5: 92.1875 (93.4476) [2021-03-26 01:57:02 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0158 (0.9957) acc1: 76.5625 (76.1814) acc5: 92.1875 (93.4832) [2021-03-26 01:57:03 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9577 (0.9860) acc1: 76.5625 (76.5120) acc5: 93.7500 (93.6640) [2021-03-26 01:57:08 swin_small_patch4_window7_224] INFO: * Acc@1 77.488 Acc@5 94.100 loss 0.958 [2021-03-26 01:57:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.5% [2021-03-26 01:57:08 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 01:57:12 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 0/1251] eta: 1:23:26 lr: 0.000638 loss: 3.5674 (3.5674) grad_norm: 1.3987 (1.3987) time: 4.0021 [2021-03-26 01:57:18 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 10/1251] eta: 0:17:17 lr: 0.000638 loss: 3.5674 (3.3063) grad_norm: 1.2211 (1.2467) time: 0.8364 [2021-03-26 01:57:23 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 20/1251] eta: 0:13:58 lr: 0.000638 loss: 3.3754 (3.2972) grad_norm: 1.2349 (1.2775) time: 0.5152 [2021-03-26 01:57:28 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 30/1251] eta: 0:12:48 lr: 0.000638 loss: 3.5319 (3.3464) grad_norm: 1.2779 (1.2651) time: 0.5151 [2021-03-26 01:57:33 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 40/1251] eta: 0:12:07 lr: 0.000638 loss: 3.7064 (3.3840) grad_norm: 1.2605 (1.2791) time: 0.5161 [2021-03-26 01:57:38 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 50/1251] eta: 0:11:41 lr: 0.000638 loss: 3.7064 (3.3941) grad_norm: 1.2998 (1.2859) time: 0.5151 [2021-03-26 01:57:43 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 60/1251] eta: 0:11:20 lr: 0.000638 loss: 3.5109 (3.4177) grad_norm: 1.2948 (1.2836) time: 0.5125 [2021-03-26 01:57:48 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 70/1251] eta: 0:11:06 lr: 0.000638 loss: 3.4442 (3.3978) grad_norm: 1.2958 (1.2887) time: 0.5129 [2021-03-26 01:57:54 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 80/1251] eta: 0:10:52 lr: 0.000638 loss: 3.4408 (3.3881) grad_norm: 1.2741 (1.2847) time: 0.5142 [2021-03-26 01:57:59 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 90/1251] eta: 0:10:40 lr: 0.000638 loss: 3.0964 (3.3462) grad_norm: 1.2339 (1.2815) time: 0.5053 [2021-03-26 01:58:04 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 100/1251] eta: 0:10:29 lr: 0.000638 loss: 3.0964 (3.3527) grad_norm: 1.2588 (1.2836) time: 0.5046 [2021-03-26 01:58:09 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 110/1251] eta: 0:10:20 lr: 0.000638 loss: 3.3033 (3.3597) grad_norm: 1.2567 (1.2819) time: 0.5114 [2021-03-26 01:58:14 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 120/1251] eta: 0:10:11 lr: 0.000638 loss: 3.3121 (3.3691) grad_norm: 1.2095 (1.2756) time: 0.5103 [2021-03-26 01:58:19 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 130/1251] eta: 0:10:03 lr: 0.000638 loss: 3.5222 (3.3934) grad_norm: 1.2189 (1.2764) time: 0.5081 [2021-03-26 01:58:24 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 140/1251] eta: 0:09:56 lr: 0.000638 loss: 3.4004 (3.3700) grad_norm: 1.2491 (1.2818) time: 0.5113 [2021-03-26 01:58:29 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 150/1251] eta: 0:09:48 lr: 0.000638 loss: 3.2859 (3.3738) grad_norm: 1.3146 (1.2846) time: 0.5106 [2021-03-26 01:58:34 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 160/1251] eta: 0:09:41 lr: 0.000637 loss: 3.4036 (3.3704) grad_norm: 1.2679 (1.2825) time: 0.5079 [2021-03-26 01:58:39 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 170/1251] eta: 0:09:34 lr: 0.000637 loss: 3.3193 (3.3631) grad_norm: 1.2078 (1.2809) time: 0.5038 [2021-03-26 01:58:44 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 180/1251] eta: 0:09:27 lr: 0.000637 loss: 3.4304 (3.3682) grad_norm: 1.2018 (1.2824) time: 0.5070 [2021-03-26 01:58:49 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 190/1251] eta: 0:09:20 lr: 0.000637 loss: 3.3471 (3.3716) grad_norm: 1.2590 (1.2831) time: 0.5064 [2021-03-26 01:58:55 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 200/1251] eta: 0:09:15 lr: 0.000637 loss: 3.4380 (3.3741) grad_norm: 1.2896 (1.2840) time: 0.5106 [2021-03-26 01:59:00 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 210/1251] eta: 0:09:09 lr: 0.000637 loss: 3.5633 (3.3761) grad_norm: 1.2896 (1.2896) time: 0.5160 [2021-03-26 01:59:05 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 220/1251] eta: 0:09:02 lr: 0.000637 loss: 3.5675 (3.3798) grad_norm: 1.2706 (1.2880) time: 0.5051 [2021-03-26 01:59:10 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 230/1251] eta: 0:08:56 lr: 0.000637 loss: 3.5734 (3.3844) grad_norm: 1.2746 (1.2888) time: 0.5040 [2021-03-26 01:59:15 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 240/1251] eta: 0:08:50 lr: 0.000637 loss: 3.6331 (3.4022) grad_norm: 1.2770 (1.2876) time: 0.5039 [2021-03-26 01:59:20 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 250/1251] eta: 0:08:44 lr: 0.000637 loss: 3.6112 (3.4031) grad_norm: 1.2997 (1.2884) time: 0.5088 [2021-03-26 01:59:25 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 260/1251] eta: 0:08:39 lr: 0.000637 loss: 3.5127 (3.3968) grad_norm: 1.2754 (1.2880) time: 0.5169 [2021-03-26 01:59:30 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 270/1251] eta: 0:08:33 lr: 0.000637 loss: 3.6273 (3.4031) grad_norm: 1.2716 (1.2864) time: 0.5117 [2021-03-26 01:59:35 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 280/1251] eta: 0:08:27 lr: 0.000637 loss: 3.4129 (3.3946) grad_norm: 1.2339 (1.2851) time: 0.5019 [2021-03-26 01:59:40 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 290/1251] eta: 0:08:20 lr: 0.000637 loss: 3.4129 (3.3978) grad_norm: 1.2562 (1.2849) time: 0.4959 [2021-03-26 01:59:45 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 300/1251] eta: 0:08:15 lr: 0.000637 loss: 3.4343 (3.3970) grad_norm: 1.2939 (1.2857) time: 0.5019 [2021-03-26 01:59:50 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 310/1251] eta: 0:08:09 lr: 0.000637 loss: 3.3381 (3.3978) grad_norm: 1.3094 (1.2883) time: 0.5064 [2021-03-26 01:59:55 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 320/1251] eta: 0:08:04 lr: 0.000637 loss: 3.4902 (3.3965) grad_norm: 1.3183 (1.2899) time: 0.5046 [2021-03-26 02:00:00 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 330/1251] eta: 0:07:58 lr: 0.000637 loss: 3.6097 (3.4011) grad_norm: 1.3183 (1.2889) time: 0.5067 [2021-03-26 02:00:05 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 340/1251] eta: 0:07:52 lr: 0.000637 loss: 3.6179 (3.4047) grad_norm: 1.2646 (1.2885) time: 0.5071 [2021-03-26 02:00:10 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 350/1251] eta: 0:07:47 lr: 0.000637 loss: 3.6179 (3.4117) grad_norm: 1.2836 (1.2894) time: 0.4988 [2021-03-26 02:00:15 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 360/1251] eta: 0:07:41 lr: 0.000637 loss: 3.5874 (3.4076) grad_norm: 1.3098 (1.2878) time: 0.4949 [2021-03-26 02:00:21 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 370/1251] eta: 0:07:36 lr: 0.000637 loss: 3.3741 (3.4091) grad_norm: 1.1917 (1.2861) time: 0.5053 [2021-03-26 02:00:26 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 380/1251] eta: 0:07:30 lr: 0.000637 loss: 3.5623 (3.4102) grad_norm: 1.2297 (1.2870) time: 0.5098 [2021-03-26 02:00:31 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 390/1251] eta: 0:07:25 lr: 0.000637 loss: 3.5623 (3.4109) grad_norm: 1.2786 (1.2867) time: 0.5055 [2021-03-26 02:00:36 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 400/1251] eta: 0:07:19 lr: 0.000637 loss: 3.4806 (3.4088) grad_norm: 1.2591 (1.2859) time: 0.5064 [2021-03-26 02:00:41 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 410/1251] eta: 0:07:14 lr: 0.000636 loss: 3.3341 (3.4051) grad_norm: 1.3209 (1.2885) time: 0.5103 [2021-03-26 02:00:46 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 420/1251] eta: 0:07:09 lr: 0.000636 loss: 3.3341 (3.4066) grad_norm: 1.3268 (1.2887) time: 0.5055 [2021-03-26 02:00:51 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 430/1251] eta: 0:07:03 lr: 0.000636 loss: 3.4343 (3.4073) grad_norm: 1.2710 (1.2890) time: 0.5060 [2021-03-26 02:00:56 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 440/1251] eta: 0:06:58 lr: 0.000636 loss: 3.4585 (3.4100) grad_norm: 1.2710 (1.2891) time: 0.5112 [2021-03-26 02:01:01 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 450/1251] eta: 0:06:53 lr: 0.000636 loss: 3.5553 (3.4070) grad_norm: 1.2252 (1.2880) time: 0.5054 [2021-03-26 02:01:06 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 460/1251] eta: 0:06:47 lr: 0.000636 loss: 3.5553 (3.4093) grad_norm: 1.2200 (1.2862) time: 0.4993 [2021-03-26 02:01:11 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 470/1251] eta: 0:06:42 lr: 0.000636 loss: 3.4974 (3.4118) grad_norm: 1.1846 (1.2841) time: 0.5073 [2021-03-26 02:01:16 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 480/1251] eta: 0:06:37 lr: 0.000636 loss: 3.4755 (3.4098) grad_norm: 1.1697 (1.2824) time: 0.5160 [2021-03-26 02:01:21 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 490/1251] eta: 0:06:32 lr: 0.000636 loss: 3.5049 (3.4154) grad_norm: 1.1878 (1.2818) time: 0.5098 [2021-03-26 02:01:27 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 500/1251] eta: 0:06:26 lr: 0.000636 loss: 3.5110 (3.4147) grad_norm: 1.2369 (1.2814) time: 0.5084 [2021-03-26 02:01:32 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 510/1251] eta: 0:06:21 lr: 0.000636 loss: 3.4858 (3.4147) grad_norm: 1.2560 (1.2820) time: 0.5103 [2021-03-26 02:01:37 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 520/1251] eta: 0:06:16 lr: 0.000636 loss: 3.3526 (3.4156) grad_norm: 1.2560 (1.2807) time: 0.5090 [2021-03-26 02:01:42 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 530/1251] eta: 0:06:11 lr: 0.000636 loss: 3.3526 (3.4172) grad_norm: 1.3128 (1.2832) time: 0.5095 [2021-03-26 02:01:47 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 540/1251] eta: 0:06:05 lr: 0.000636 loss: 3.5183 (3.4194) grad_norm: 1.3257 (1.2825) time: 0.5060 [2021-03-26 02:01:52 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 550/1251] eta: 0:06:00 lr: 0.000636 loss: 3.3770 (3.4179) grad_norm: 1.3001 (1.2827) time: 0.5133 [2021-03-26 02:01:57 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 560/1251] eta: 0:05:55 lr: 0.000636 loss: 3.5441 (3.4205) grad_norm: 1.2854 (1.2824) time: 0.5151 [2021-03-26 02:02:02 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 570/1251] eta: 0:05:50 lr: 0.000636 loss: 3.7976 (3.4246) grad_norm: 1.2738 (1.2828) time: 0.5086 [2021-03-26 02:02:07 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 580/1251] eta: 0:05:45 lr: 0.000636 loss: 3.5427 (3.4211) grad_norm: 1.2431 (1.2816) time: 0.5157 [2021-03-26 02:02:13 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 590/1251] eta: 0:05:40 lr: 0.000636 loss: 3.2024 (3.4176) grad_norm: 1.2036 (1.2809) time: 0.5119 [2021-03-26 02:02:18 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 600/1251] eta: 0:05:34 lr: 0.000636 loss: 3.4302 (3.4171) grad_norm: 1.2369 (1.2809) time: 0.5041 [2021-03-26 02:02:23 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 610/1251] eta: 0:05:29 lr: 0.000636 loss: 3.5002 (3.4204) grad_norm: 1.2350 (1.2803) time: 0.5008 [2021-03-26 02:02:28 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 620/1251] eta: 0:05:24 lr: 0.000636 loss: 3.4422 (3.4199) grad_norm: 1.1977 (1.2794) time: 0.5028 [2021-03-26 02:02:33 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 630/1251] eta: 0:05:18 lr: 0.000636 loss: 3.4240 (3.4185) grad_norm: 1.2159 (1.2797) time: 0.5044 [2021-03-26 02:02:38 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 640/1251] eta: 0:05:13 lr: 0.000636 loss: 3.4240 (3.4170) grad_norm: 1.2192 (1.2793) time: 0.5045 [2021-03-26 02:02:43 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 650/1251] eta: 0:05:08 lr: 0.000636 loss: 3.2329 (3.4155) grad_norm: 1.1935 (1.2781) time: 0.5071 [2021-03-26 02:02:48 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 660/1251] eta: 0:05:03 lr: 0.000635 loss: 3.3486 (3.4142) grad_norm: 1.2178 (1.2782) time: 0.5045 [2021-03-26 02:02:53 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 670/1251] eta: 0:04:58 lr: 0.000635 loss: 3.3486 (3.4132) grad_norm: 1.2667 (1.2785) time: 0.5031 [2021-03-26 02:02:58 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 680/1251] eta: 0:04:52 lr: 0.000635 loss: 3.5659 (3.4149) grad_norm: 1.2513 (1.2786) time: 0.5035 [2021-03-26 02:03:03 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 690/1251] eta: 0:04:47 lr: 0.000635 loss: 3.2955 (3.4094) grad_norm: 1.2513 (1.2793) time: 0.5057 [2021-03-26 02:03:08 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 700/1251] eta: 0:04:42 lr: 0.000635 loss: 3.1233 (3.4080) grad_norm: 1.2197 (1.2790) time: 0.5077 [2021-03-26 02:03:13 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 710/1251] eta: 0:04:37 lr: 0.000635 loss: 3.5811 (3.4116) grad_norm: 1.2410 (1.2802) time: 0.5102 [2021-03-26 02:03:18 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 720/1251] eta: 0:04:32 lr: 0.000635 loss: 3.4778 (3.4087) grad_norm: 1.2947 (1.2806) time: 0.5060 [2021-03-26 02:03:23 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 730/1251] eta: 0:04:27 lr: 0.000635 loss: 3.2090 (3.4075) grad_norm: 1.2693 (1.2803) time: 0.5108 [2021-03-26 02:03:29 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 740/1251] eta: 0:04:22 lr: 0.000635 loss: 3.6144 (3.4101) grad_norm: 1.2783 (1.2801) time: 0.5268 [2021-03-26 02:03:34 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 750/1251] eta: 0:04:17 lr: 0.000635 loss: 3.7614 (3.4141) grad_norm: 1.3016 (1.2805) time: 0.5242 [2021-03-26 02:03:39 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 760/1251] eta: 0:04:11 lr: 0.000635 loss: 3.7614 (3.4168) grad_norm: 1.3016 (1.2806) time: 0.5114 [2021-03-26 02:03:44 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 770/1251] eta: 0:04:06 lr: 0.000635 loss: 3.5799 (3.4146) grad_norm: 1.2346 (1.2805) time: 0.5125 [2021-03-26 02:03:49 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 780/1251] eta: 0:04:01 lr: 0.000635 loss: 3.2350 (3.4118) grad_norm: 1.2421 (1.2804) time: 0.5119 [2021-03-26 02:03:54 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 790/1251] eta: 0:03:56 lr: 0.000635 loss: 3.2848 (3.4106) grad_norm: 1.2625 (1.2802) time: 0.5071 [2021-03-26 02:03:59 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 800/1251] eta: 0:03:51 lr: 0.000635 loss: 3.4459 (3.4114) grad_norm: 1.2824 (1.2797) time: 0.5128 [2021-03-26 02:04:05 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 810/1251] eta: 0:03:46 lr: 0.000635 loss: 3.5959 (3.4134) grad_norm: 1.2268 (1.2788) time: 0.5148 [2021-03-26 02:04:10 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 820/1251] eta: 0:03:41 lr: 0.000635 loss: 3.4276 (3.4123) grad_norm: 1.2097 (1.2790) time: 0.5081 [2021-03-26 02:04:15 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 830/1251] eta: 0:03:35 lr: 0.000635 loss: 3.3549 (3.4113) grad_norm: 1.2414 (1.2795) time: 0.5050 [2021-03-26 02:04:20 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 840/1251] eta: 0:03:30 lr: 0.000635 loss: 3.6197 (3.4131) grad_norm: 1.2717 (1.2793) time: 0.5061 [2021-03-26 02:04:25 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 850/1251] eta: 0:03:25 lr: 0.000635 loss: 3.1835 (3.4074) grad_norm: 1.2717 (1.2795) time: 0.5093 [2021-03-26 02:04:30 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 860/1251] eta: 0:03:20 lr: 0.000635 loss: 3.2005 (3.4064) grad_norm: 1.3107 (1.2801) time: 0.5043 [2021-03-26 02:04:35 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 870/1251] eta: 0:03:15 lr: 0.000635 loss: 3.3901 (3.4033) grad_norm: 1.3277 (1.2808) time: 0.5043 [2021-03-26 02:04:40 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 880/1251] eta: 0:03:10 lr: 0.000635 loss: 3.5483 (3.4061) grad_norm: 1.2910 (1.2807) time: 0.5039 [2021-03-26 02:04:45 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 890/1251] eta: 0:03:04 lr: 0.000635 loss: 3.6597 (3.4073) grad_norm: 1.2006 (1.2794) time: 0.4953 [2021-03-26 02:04:50 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 900/1251] eta: 0:02:59 lr: 0.000635 loss: 3.6111 (3.4086) grad_norm: 1.1832 (1.2791) time: 0.4991 [2021-03-26 02:04:55 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 910/1251] eta: 0:02:54 lr: 0.000634 loss: 3.6111 (3.4104) grad_norm: 1.2658 (1.2788) time: 0.5077 [2021-03-26 02:05:00 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 920/1251] eta: 0:02:49 lr: 0.000634 loss: 3.4626 (3.4103) grad_norm: 1.2773 (1.2791) time: 0.5153 [2021-03-26 02:05:05 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 930/1251] eta: 0:02:44 lr: 0.000634 loss: 3.4466 (3.4089) grad_norm: 1.2554 (1.2786) time: 0.5094 [2021-03-26 02:05:10 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 940/1251] eta: 0:02:39 lr: 0.000634 loss: 3.5219 (3.4106) grad_norm: 1.2471 (1.2788) time: 0.5050 [2021-03-26 02:05:15 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 950/1251] eta: 0:02:34 lr: 0.000634 loss: 3.4593 (3.4109) grad_norm: 1.2512 (1.2790) time: 0.5058 [2021-03-26 02:05:20 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 960/1251] eta: 0:02:28 lr: 0.000634 loss: 3.4394 (3.4114) grad_norm: 1.3108 (1.2804) time: 0.5069 [2021-03-26 02:05:25 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 970/1251] eta: 0:02:23 lr: 0.000634 loss: 3.4594 (3.4112) grad_norm: 1.3482 (1.2808) time: 0.5093 [2021-03-26 02:05:31 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 980/1251] eta: 0:02:18 lr: 0.000634 loss: 3.4248 (3.4113) grad_norm: 1.2649 (1.2804) time: 0.5051 [2021-03-26 02:05:36 swin_small_patch4_window7_224] INFO: Epoch: [124] [ 990/1251] eta: 0:02:13 lr: 0.000634 loss: 3.4248 (3.4112) grad_norm: 1.2392 (1.2798) time: 0.5048 [2021-03-26 02:05:41 swin_small_patch4_window7_224] INFO: Epoch: [124] [1000/1251] eta: 0:02:08 lr: 0.000634 loss: 3.4745 (3.4107) grad_norm: 1.2255 (1.2798) time: 0.5065 [2021-03-26 02:05:46 swin_small_patch4_window7_224] INFO: Epoch: [124] [1010/1251] eta: 0:02:03 lr: 0.000634 loss: 3.3767 (3.4093) grad_norm: 1.2802 (1.2801) time: 0.5061 [2021-03-26 02:05:51 swin_small_patch4_window7_224] INFO: Epoch: [124] [1020/1251] eta: 0:01:58 lr: 0.000634 loss: 3.3435 (3.4099) grad_norm: 1.2234 (1.2795) time: 0.5046 [2021-03-26 02:05:56 swin_small_patch4_window7_224] INFO: Epoch: [124] [1030/1251] eta: 0:01:53 lr: 0.000634 loss: 3.3949 (3.4090) grad_norm: 1.2197 (1.2791) time: 0.5020 [2021-03-26 02:06:01 swin_small_patch4_window7_224] INFO: Epoch: [124] [1040/1251] eta: 0:01:47 lr: 0.000634 loss: 3.4536 (3.4094) grad_norm: 1.2766 (1.2806) time: 0.5064 [2021-03-26 02:06:06 swin_small_patch4_window7_224] INFO: Epoch: [124] [1050/1251] eta: 0:01:42 lr: 0.000634 loss: 3.4536 (3.4079) grad_norm: 1.3122 (1.2813) time: 0.5098 [2021-03-26 02:06:11 swin_small_patch4_window7_224] INFO: Epoch: [124] [1060/1251] eta: 0:01:37 lr: 0.000634 loss: 3.4658 (3.4099) grad_norm: 1.2967 (1.2810) time: 0.5001 [2021-03-26 02:06:16 swin_small_patch4_window7_224] INFO: Epoch: [124] [1070/1251] eta: 0:01:32 lr: 0.000634 loss: 3.6897 (3.4118) grad_norm: 1.2430 (1.2809) time: 0.5009 [2021-03-26 02:06:21 swin_small_patch4_window7_224] INFO: Epoch: [124] [1080/1251] eta: 0:01:27 lr: 0.000634 loss: 3.7648 (3.4149) grad_norm: 1.2430 (1.2806) time: 0.5080 [2021-03-26 02:06:26 swin_small_patch4_window7_224] INFO: Epoch: [124] [1090/1251] eta: 0:01:22 lr: 0.000634 loss: 3.5735 (3.4153) grad_norm: 1.2263 (1.2806) time: 0.5000 [2021-03-26 02:06:31 swin_small_patch4_window7_224] INFO: Epoch: [124] [1100/1251] eta: 0:01:17 lr: 0.000634 loss: 3.5523 (3.4159) grad_norm: 1.2114 (1.2804) time: 0.4989 [2021-03-26 02:06:36 swin_small_patch4_window7_224] INFO: Epoch: [124] [1110/1251] eta: 0:01:12 lr: 0.000634 loss: 3.5523 (3.4152) grad_norm: 1.2650 (1.2809) time: 0.5070 [2021-03-26 02:06:41 swin_small_patch4_window7_224] INFO: Epoch: [124] [1120/1251] eta: 0:01:06 lr: 0.000634 loss: 3.4315 (3.4157) grad_norm: 1.2900 (1.2816) time: 0.5074 [2021-03-26 02:06:46 swin_small_patch4_window7_224] INFO: Epoch: [124] [1130/1251] eta: 0:01:01 lr: 0.000634 loss: 3.4444 (3.4161) grad_norm: 1.3376 (1.2826) time: 0.5060 [2021-03-26 02:06:51 swin_small_patch4_window7_224] INFO: Epoch: [124] [1140/1251] eta: 0:00:56 lr: 0.000634 loss: 3.5459 (3.4176) grad_norm: 1.2947 (1.2826) time: 0.5018 [2021-03-26 02:06:56 swin_small_patch4_window7_224] INFO: Epoch: [124] [1150/1251] eta: 0:00:51 lr: 0.000634 loss: 3.5663 (3.4185) grad_norm: 1.2451 (1.2826) time: 0.5101 [2021-03-26 02:07:02 swin_small_patch4_window7_224] INFO: Epoch: [124] [1160/1251] eta: 0:00:46 lr: 0.000633 loss: 3.3950 (3.4179) grad_norm: 1.2451 (1.2826) time: 0.5141 [2021-03-26 02:07:07 swin_small_patch4_window7_224] INFO: Epoch: [124] [1170/1251] eta: 0:00:41 lr: 0.000633 loss: 3.6071 (3.4190) grad_norm: 1.2128 (1.2823) time: 0.5038 [2021-03-26 02:07:12 swin_small_patch4_window7_224] INFO: Epoch: [124] [1180/1251] eta: 0:00:36 lr: 0.000633 loss: 3.7275 (3.4231) grad_norm: 1.2128 (1.2817) time: 0.5019 [2021-03-26 02:07:17 swin_small_patch4_window7_224] INFO: Epoch: [124] [1190/1251] eta: 0:00:31 lr: 0.000633 loss: 3.6924 (3.4219) grad_norm: 1.2345 (1.2821) time: 0.5013 [2021-03-26 02:07:22 swin_small_patch4_window7_224] INFO: Epoch: [124] [1200/1251] eta: 0:00:26 lr: 0.000633 loss: 3.3665 (3.4205) grad_norm: 1.2634 (1.2820) time: 0.5073 [2021-03-26 02:07:27 swin_small_patch4_window7_224] INFO: Epoch: [124] [1210/1251] eta: 0:00:20 lr: 0.000633 loss: 3.6983 (3.4232) grad_norm: 1.2634 (1.2820) time: 0.5064 [2021-03-26 02:07:32 swin_small_patch4_window7_224] INFO: Epoch: [124] [1220/1251] eta: 0:00:15 lr: 0.000633 loss: 3.6983 (3.4219) grad_norm: 1.3150 (1.2827) time: 0.5028 [2021-03-26 02:07:37 swin_small_patch4_window7_224] INFO: Epoch: [124] [1230/1251] eta: 0:00:10 lr: 0.000633 loss: 3.1956 (3.4208) grad_norm: 1.2950 (1.2825) time: 0.5046 [2021-03-26 02:07:42 swin_small_patch4_window7_224] INFO: Epoch: [124] [1240/1251] eta: 0:00:05 lr: 0.000633 loss: 3.1815 (3.4201) grad_norm: 1.2831 (1.2827) time: 0.5065 [2021-03-26 02:07:47 swin_small_patch4_window7_224] INFO: Epoch: [124] [1250/1251] eta: 0:00:00 lr: 0.000633 loss: 3.4552 (3.4212) grad_norm: 1.2831 (1.2822) time: 0.5069 [2021-03-26 02:07:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:34 loss: 1.2709 (1.2709) acc1: 68.7500 (68.7500) acc5: 90.6250 (90.6250) [2021-03-26 02:07:56 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.0664 (1.0807) acc1: 75.0000 (74.7159) acc5: 92.1875 (92.7557) [2021-03-26 02:07:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9673 (1.0237) acc1: 75.0000 (75.2232) acc5: 92.1875 (93.0060) [2021-03-26 02:08:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9117 (1.0118) acc1: 76.5625 (75.6048) acc5: 93.7500 (93.2460) [2021-03-26 02:08:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9299 (1.0095) acc1: 76.5625 (75.8765) acc5: 93.7500 (93.4070) [2021-03-26 02:08:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9521 (0.9962) acc1: 78.1250 (76.1920) acc5: 93.7500 (93.5360) [2021-03-26 02:08:10 swin_small_patch4_window7_224] INFO: * Acc@1 77.116 Acc@5 93.940 loss 0.973 [2021-03-26 02:08:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.1% [2021-03-26 02:08:10 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 02:08:14 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 0/1251] eta: 1:25:42 lr: 0.000633 loss: 3.4624 (3.4624) grad_norm: 1.2141 (1.2141) time: 4.1105 [2021-03-26 02:08:19 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 10/1251] eta: 0:17:41 lr: 0.000633 loss: 3.4624 (3.2512) grad_norm: 1.2517 (1.2612) time: 0.8553 [2021-03-26 02:08:24 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 20/1251] eta: 0:14:09 lr: 0.000633 loss: 3.6059 (3.4582) grad_norm: 1.1881 (1.2522) time: 0.5186 [2021-03-26 02:08:30 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 30/1251] eta: 0:12:49 lr: 0.000633 loss: 3.5404 (3.3544) grad_norm: 1.2488 (1.2745) time: 0.5066 [2021-03-26 02:08:35 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 40/1251] eta: 0:12:05 lr: 0.000633 loss: 3.3433 (3.2982) grad_norm: 1.2610 (1.2731) time: 0.5047 [2021-03-26 02:08:40 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 50/1251] eta: 0:11:39 lr: 0.000633 loss: 3.4693 (3.3191) grad_norm: 1.2420 (1.2754) time: 0.5083 [2021-03-26 02:08:45 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 60/1251] eta: 0:11:19 lr: 0.000633 loss: 3.6755 (3.3613) grad_norm: 1.2420 (1.2673) time: 0.5110 [2021-03-26 02:08:50 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 70/1251] eta: 0:11:02 lr: 0.000633 loss: 3.6045 (3.3606) grad_norm: 1.2041 (1.2658) time: 0.5057 [2021-03-26 02:08:55 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 80/1251] eta: 0:10:49 lr: 0.000633 loss: 3.3484 (3.3533) grad_norm: 1.2080 (1.2718) time: 0.5069 [2021-03-26 02:09:00 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 90/1251] eta: 0:10:37 lr: 0.000633 loss: 3.1875 (3.3572) grad_norm: 1.1956 (1.2645) time: 0.5087 [2021-03-26 02:09:05 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 100/1251] eta: 0:10:26 lr: 0.000633 loss: 3.1524 (3.3507) grad_norm: 1.1953 (1.2652) time: 0.5001 [2021-03-26 02:09:10 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 110/1251] eta: 0:10:17 lr: 0.000633 loss: 3.4575 (3.3538) grad_norm: 1.2387 (nan) time: 0.5016 [2021-03-26 02:09:15 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 120/1251] eta: 0:10:08 lr: 0.000633 loss: 3.6023 (3.3948) grad_norm: 1.2387 (nan) time: 0.5072 [2021-03-26 02:09:20 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 130/1251] eta: 0:10:01 lr: 0.000633 loss: 3.7655 (3.4006) grad_norm: 1.2708 (nan) time: 0.5109 [2021-03-26 02:09:25 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 140/1251] eta: 0:09:53 lr: 0.000633 loss: 3.4058 (3.4049) grad_norm: 1.3012 (nan) time: 0.5119 [2021-03-26 02:09:30 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 150/1251] eta: 0:09:46 lr: 0.000633 loss: 3.5574 (3.4153) grad_norm: 1.3207 (nan) time: 0.5067 [2021-03-26 02:09:35 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 160/1251] eta: 0:09:39 lr: 0.000632 loss: 3.5232 (3.4094) grad_norm: 1.2804 (nan) time: 0.5065 [2021-03-26 02:09:40 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 170/1251] eta: 0:09:31 lr: 0.000632 loss: 3.4849 (3.4072) grad_norm: 1.2825 (nan) time: 0.5038 [2021-03-26 02:09:46 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 180/1251] eta: 0:09:25 lr: 0.000632 loss: 3.3067 (3.3940) grad_norm: 1.2899 (nan) time: 0.5089 [2021-03-26 02:09:51 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 190/1251] eta: 0:09:20 lr: 0.000632 loss: 3.3356 (3.3997) grad_norm: 1.2988 (nan) time: 0.5183 [2021-03-26 02:09:56 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 200/1251] eta: 0:09:14 lr: 0.000632 loss: 3.4943 (3.3915) grad_norm: 1.2740 (nan) time: 0.5200 [2021-03-26 02:10:01 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 210/1251] eta: 0:09:07 lr: 0.000632 loss: 3.5769 (3.4004) grad_norm: 1.2637 (nan) time: 0.5103 [2021-03-26 02:10:06 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 220/1251] eta: 0:09:01 lr: 0.000632 loss: 3.5769 (3.4003) grad_norm: 1.2441 (nan) time: 0.4972 [2021-03-26 02:10:11 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 230/1251] eta: 0:08:55 lr: 0.000632 loss: 3.3941 (3.4023) grad_norm: 1.2627 (nan) time: 0.5078 [2021-03-26 02:10:16 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 240/1251] eta: 0:08:49 lr: 0.000632 loss: 3.3941 (3.4034) grad_norm: 1.3486 (nan) time: 0.5111 [2021-03-26 02:10:21 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 250/1251] eta: 0:08:43 lr: 0.000632 loss: 3.5273 (3.4038) grad_norm: 1.3382 (nan) time: 0.5032 [2021-03-26 02:10:26 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 260/1251] eta: 0:08:37 lr: 0.000632 loss: 3.5607 (3.4136) grad_norm: 1.2911 (nan) time: 0.5027 [2021-03-26 02:10:31 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 270/1251] eta: 0:08:31 lr: 0.000632 loss: 3.7374 (3.4267) grad_norm: 1.2897 (nan) time: 0.4987 [2021-03-26 02:10:36 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 280/1251] eta: 0:08:25 lr: 0.000632 loss: 3.6364 (3.4257) grad_norm: 1.2897 (nan) time: 0.5004 [2021-03-26 02:10:41 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 290/1251] eta: 0:08:19 lr: 0.000632 loss: 3.5356 (3.4272) grad_norm: 1.3060 (nan) time: 0.5088 [2021-03-26 02:10:47 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 300/1251] eta: 0:08:14 lr: 0.000632 loss: 3.4032 (3.4311) grad_norm: 1.3060 (nan) time: 0.5155 [2021-03-26 02:10:52 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 310/1251] eta: 0:08:09 lr: 0.000632 loss: 3.3442 (3.4231) grad_norm: 1.2694 (nan) time: 0.5119 [2021-03-26 02:10:57 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 320/1251] eta: 0:08:03 lr: 0.000632 loss: 3.3442 (3.4209) grad_norm: 1.2947 (nan) time: 0.5115 [2021-03-26 02:11:02 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 330/1251] eta: 0:07:57 lr: 0.000632 loss: 3.4501 (3.4212) grad_norm: 1.2947 (nan) time: 0.5065 [2021-03-26 02:11:07 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 340/1251] eta: 0:07:52 lr: 0.000632 loss: 3.4416 (3.4223) grad_norm: 1.2388 (nan) time: 0.5102 [2021-03-26 02:11:12 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 350/1251] eta: 0:07:47 lr: 0.000632 loss: 3.4112 (3.4212) grad_norm: 1.2494 (nan) time: 0.5100 [2021-03-26 02:11:17 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 360/1251] eta: 0:07:41 lr: 0.000632 loss: 3.2242 (3.4151) grad_norm: 1.2427 (nan) time: 0.5015 [2021-03-26 02:11:22 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 370/1251] eta: 0:07:36 lr: 0.000632 loss: 3.0533 (3.4100) grad_norm: 1.2299 (nan) time: 0.5040 [2021-03-26 02:11:27 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 380/1251] eta: 0:07:30 lr: 0.000632 loss: 3.5063 (3.4110) grad_norm: 1.2528 (nan) time: 0.4991 [2021-03-26 02:11:32 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 390/1251] eta: 0:07:25 lr: 0.000632 loss: 3.5181 (3.4126) grad_norm: 1.2843 (nan) time: 0.5075 [2021-03-26 02:11:37 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 400/1251] eta: 0:07:19 lr: 0.000632 loss: 3.4840 (3.4130) grad_norm: 1.2937 (nan) time: 0.5132 [2021-03-26 02:11:42 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 410/1251] eta: 0:07:14 lr: 0.000631 loss: 3.4880 (3.4166) grad_norm: 1.2799 (nan) time: 0.5023 [2021-03-26 02:11:47 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 420/1251] eta: 0:07:09 lr: 0.000631 loss: 3.4168 (3.4139) grad_norm: 1.2788 (nan) time: 0.5052 [2021-03-26 02:11:52 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 430/1251] eta: 0:07:03 lr: 0.000631 loss: 3.2812 (3.4129) grad_norm: 1.2788 (nan) time: 0.5088 [2021-03-26 02:11:58 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 440/1251] eta: 0:06:58 lr: 0.000631 loss: 3.1679 (3.4089) grad_norm: 1.2584 (nan) time: 0.5087 [2021-03-26 02:12:03 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 450/1251] eta: 0:06:53 lr: 0.000631 loss: 3.4100 (3.4111) grad_norm: 1.2584 (nan) time: 0.5064 [2021-03-26 02:12:08 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 460/1251] eta: 0:06:47 lr: 0.000631 loss: 3.5083 (3.4093) grad_norm: 1.2314 (nan) time: 0.5069 [2021-03-26 02:12:13 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 470/1251] eta: 0:06:42 lr: 0.000631 loss: 3.2591 (3.4037) grad_norm: 1.2404 (nan) time: 0.5102 [2021-03-26 02:12:18 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 480/1251] eta: 0:06:37 lr: 0.000631 loss: 3.2591 (3.3998) grad_norm: 1.2709 (nan) time: 0.5040 [2021-03-26 02:12:23 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 490/1251] eta: 0:06:31 lr: 0.000631 loss: 3.4837 (3.3986) grad_norm: 1.2338 (nan) time: 0.5038 [2021-03-26 02:12:28 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 500/1251] eta: 0:06:26 lr: 0.000631 loss: 3.5008 (3.3971) grad_norm: 1.2441 (nan) time: 0.5090 [2021-03-26 02:12:33 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 510/1251] eta: 0:06:21 lr: 0.000631 loss: 3.4529 (3.3963) grad_norm: 1.3102 (nan) time: 0.5137 [2021-03-26 02:12:38 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 520/1251] eta: 0:06:16 lr: 0.000631 loss: 3.5483 (3.4015) grad_norm: 1.3139 (nan) time: 0.5131 [2021-03-26 02:12:43 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 530/1251] eta: 0:06:11 lr: 0.000631 loss: 3.5483 (3.4015) grad_norm: 1.2331 (nan) time: 0.5087 [2021-03-26 02:12:48 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 540/1251] eta: 0:06:05 lr: 0.000631 loss: 3.3952 (3.3996) grad_norm: 1.2337 (nan) time: 0.5110 [2021-03-26 02:12:54 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 550/1251] eta: 0:06:00 lr: 0.000631 loss: 3.3510 (3.3993) grad_norm: 1.2337 (nan) time: 0.5194 [2021-03-26 02:12:59 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 560/1251] eta: 0:05:55 lr: 0.000631 loss: 3.4373 (3.4015) grad_norm: 1.2259 (nan) time: 0.5141 [2021-03-26 02:13:04 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 570/1251] eta: 0:05:50 lr: 0.000631 loss: 3.4460 (3.4003) grad_norm: 1.2767 (nan) time: 0.5074 [2021-03-26 02:13:09 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 580/1251] eta: 0:05:45 lr: 0.000631 loss: 3.4068 (3.3991) grad_norm: 1.2748 (nan) time: 0.5084 [2021-03-26 02:13:14 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 590/1251] eta: 0:05:39 lr: 0.000631 loss: 3.4670 (3.4010) grad_norm: 1.2845 (nan) time: 0.5053 [2021-03-26 02:13:19 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 600/1251] eta: 0:05:34 lr: 0.000631 loss: 3.4780 (3.4002) grad_norm: 1.2987 (nan) time: 0.5055 [2021-03-26 02:13:24 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 610/1251] eta: 0:05:29 lr: 0.000631 loss: 3.2745 (3.3958) grad_norm: 1.2673 (nan) time: 0.5074 [2021-03-26 02:13:29 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 620/1251] eta: 0:05:24 lr: 0.000631 loss: 3.5627 (3.3986) grad_norm: 1.2122 (nan) time: 0.5071 [2021-03-26 02:13:34 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 630/1251] eta: 0:05:19 lr: 0.000631 loss: 3.5147 (3.3951) grad_norm: 1.2097 (nan) time: 0.5047 [2021-03-26 02:13:39 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 640/1251] eta: 0:05:13 lr: 0.000631 loss: 3.1594 (3.3962) grad_norm: 1.2252 (nan) time: 0.5050 [2021-03-26 02:13:44 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 650/1251] eta: 0:05:08 lr: 0.000631 loss: 3.4090 (3.3928) grad_norm: 1.2174 (nan) time: 0.5082 [2021-03-26 02:13:49 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 660/1251] eta: 0:05:03 lr: 0.000630 loss: 3.2657 (3.3903) grad_norm: 1.2042 (nan) time: 0.5094 [2021-03-26 02:13:55 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 670/1251] eta: 0:04:58 lr: 0.000630 loss: 3.2657 (3.3869) grad_norm: 1.2028 (nan) time: 0.5093 [2021-03-26 02:14:00 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 680/1251] eta: 0:04:53 lr: 0.000630 loss: 3.4119 (3.3888) grad_norm: 1.2204 (nan) time: 0.5054 [2021-03-26 02:14:05 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 690/1251] eta: 0:04:47 lr: 0.000630 loss: 3.5548 (3.3876) grad_norm: 1.3391 (nan) time: 0.5020 [2021-03-26 02:14:10 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 700/1251] eta: 0:04:42 lr: 0.000630 loss: 3.4861 (3.3850) grad_norm: 1.2571 (nan) time: 0.5047 [2021-03-26 02:14:15 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 710/1251] eta: 0:04:37 lr: 0.000630 loss: 3.6367 (3.3870) grad_norm: 1.2845 (nan) time: 0.5113 [2021-03-26 02:14:20 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 720/1251] eta: 0:04:32 lr: 0.000630 loss: 3.7196 (3.3865) grad_norm: 1.2103 (nan) time: 0.5103 [2021-03-26 02:14:25 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 730/1251] eta: 0:04:27 lr: 0.000630 loss: 3.3292 (3.3879) grad_norm: 1.1731 (nan) time: 0.5069 [2021-03-26 02:14:30 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 740/1251] eta: 0:04:22 lr: 0.000630 loss: 3.3292 (3.3879) grad_norm: 1.2054 (nan) time: 0.5170 [2021-03-26 02:14:35 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 750/1251] eta: 0:04:17 lr: 0.000630 loss: 3.3058 (3.3858) grad_norm: 1.2489 (nan) time: 0.5193 [2021-03-26 02:14:41 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 760/1251] eta: 0:04:11 lr: 0.000630 loss: 3.2055 (3.3844) grad_norm: 1.2791 (nan) time: 0.5149 [2021-03-26 02:14:46 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 770/1251] eta: 0:04:06 lr: 0.000630 loss: 3.4248 (3.3861) grad_norm: 1.2466 (nan) time: 0.5082 [2021-03-26 02:14:51 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 780/1251] eta: 0:04:01 lr: 0.000630 loss: 3.5065 (3.3876) grad_norm: 1.2660 (nan) time: 0.5018 [2021-03-26 02:14:56 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 790/1251] eta: 0:03:56 lr: 0.000630 loss: 3.3830 (3.3857) grad_norm: 1.2314 (nan) time: 0.5071 [2021-03-26 02:15:01 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 800/1251] eta: 0:03:51 lr: 0.000630 loss: 3.1647 (3.3842) grad_norm: 1.2418 (nan) time: 0.5088 [2021-03-26 02:15:06 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 810/1251] eta: 0:03:46 lr: 0.000630 loss: 3.1220 (3.3815) grad_norm: 1.2423 (nan) time: 0.5038 [2021-03-26 02:15:11 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 820/1251] eta: 0:03:40 lr: 0.000630 loss: 3.3493 (3.3833) grad_norm: 1.2360 (nan) time: 0.4994 [2021-03-26 02:15:16 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 830/1251] eta: 0:03:35 lr: 0.000630 loss: 3.3406 (3.3809) grad_norm: 1.2488 (nan) time: 0.5006 [2021-03-26 02:15:21 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 840/1251] eta: 0:03:30 lr: 0.000630 loss: 2.9581 (3.3793) grad_norm: 1.2657 (nan) time: 0.5080 [2021-03-26 02:15:26 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 850/1251] eta: 0:03:25 lr: 0.000630 loss: 3.5989 (3.3803) grad_norm: 1.3074 (nan) time: 0.5154 [2021-03-26 02:15:31 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 860/1251] eta: 0:03:20 lr: 0.000630 loss: 3.6568 (3.3832) grad_norm: 1.2877 (nan) time: 0.5104 [2021-03-26 02:15:36 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 870/1251] eta: 0:03:15 lr: 0.000630 loss: 3.3899 (3.3824) grad_norm: 1.2388 (nan) time: 0.5049 [2021-03-26 02:15:41 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 880/1251] eta: 0:03:09 lr: 0.000630 loss: 3.3779 (3.3835) grad_norm: 1.2805 (nan) time: 0.5043 [2021-03-26 02:15:46 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 890/1251] eta: 0:03:04 lr: 0.000630 loss: 3.3930 (3.3832) grad_norm: 1.2774 (nan) time: 0.5021 [2021-03-26 02:15:51 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 900/1251] eta: 0:02:59 lr: 0.000630 loss: 3.5127 (3.3854) grad_norm: 1.2266 (nan) time: 0.4998 [2021-03-26 02:15:56 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 910/1251] eta: 0:02:54 lr: 0.000629 loss: 3.5127 (3.3853) grad_norm: 1.2745 (nan) time: 0.5067 [2021-03-26 02:16:01 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 920/1251] eta: 0:02:49 lr: 0.000629 loss: 3.5213 (3.3854) grad_norm: 1.2929 (nan) time: 0.5104 [2021-03-26 02:16:07 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 930/1251] eta: 0:02:44 lr: 0.000629 loss: 3.5213 (3.3842) grad_norm: 1.2491 (nan) time: 0.5082 [2021-03-26 02:16:12 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 940/1251] eta: 0:02:39 lr: 0.000629 loss: 3.2732 (3.3836) grad_norm: 1.2968 (nan) time: 0.5115 [2021-03-26 02:16:17 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 950/1251] eta: 0:02:34 lr: 0.000629 loss: 3.3687 (3.3834) grad_norm: 1.3607 (nan) time: 0.5167 [2021-03-26 02:16:22 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 960/1251] eta: 0:02:28 lr: 0.000629 loss: 3.2957 (3.3814) grad_norm: 1.3248 (nan) time: 0.5100 [2021-03-26 02:16:27 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 970/1251] eta: 0:02:23 lr: 0.000629 loss: 3.3167 (3.3820) grad_norm: 1.2502 (nan) time: 0.5028 [2021-03-26 02:16:32 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 980/1251] eta: 0:02:18 lr: 0.000629 loss: 3.4514 (3.3819) grad_norm: 1.2439 (nan) time: 0.5029 [2021-03-26 02:16:37 swin_small_patch4_window7_224] INFO: Epoch: [125] [ 990/1251] eta: 0:02:13 lr: 0.000629 loss: 3.3789 (3.3817) grad_norm: 1.3461 (nan) time: 0.5016 [2021-03-26 02:16:42 swin_small_patch4_window7_224] INFO: Epoch: [125] [1000/1251] eta: 0:02:08 lr: 0.000629 loss: 3.6203 (3.3850) grad_norm: 1.3461 (nan) time: 0.5063 [2021-03-26 02:16:47 swin_small_patch4_window7_224] INFO: Epoch: [125] [1010/1251] eta: 0:02:03 lr: 0.000629 loss: 3.7379 (3.3887) grad_norm: 1.2617 (nan) time: 0.5048 [2021-03-26 02:16:52 swin_small_patch4_window7_224] INFO: Epoch: [125] [1020/1251] eta: 0:01:58 lr: 0.000629 loss: 3.7379 (3.3893) grad_norm: 1.1594 (nan) time: 0.5031 [2021-03-26 02:16:57 swin_small_patch4_window7_224] INFO: Epoch: [125] [1030/1251] eta: 0:01:52 lr: 0.000629 loss: 3.3777 (3.3883) grad_norm: 1.2053 (nan) time: 0.5058 [2021-03-26 02:17:02 swin_small_patch4_window7_224] INFO: Epoch: [125] [1040/1251] eta: 0:01:47 lr: 0.000629 loss: 3.3777 (3.3873) grad_norm: 1.2789 (nan) time: 0.5077 [2021-03-26 02:17:07 swin_small_patch4_window7_224] INFO: Epoch: [125] [1050/1251] eta: 0:01:42 lr: 0.000629 loss: 3.2705 (3.3868) grad_norm: 1.2164 (nan) time: 0.5051 [2021-03-26 02:17:12 swin_small_patch4_window7_224] INFO: Epoch: [125] [1060/1251] eta: 0:01:37 lr: 0.000629 loss: 3.1993 (3.3856) grad_norm: 1.2164 (nan) time: 0.5080 [2021-03-26 02:17:18 swin_small_patch4_window7_224] INFO: Epoch: [125] [1070/1251] eta: 0:01:32 lr: 0.000629 loss: 3.3425 (3.3861) grad_norm: 1.2316 (nan) time: 0.5100 [2021-03-26 02:17:23 swin_small_patch4_window7_224] INFO: Epoch: [125] [1080/1251] eta: 0:01:27 lr: 0.000629 loss: 3.5629 (3.3870) grad_norm: 1.2468 (nan) time: 0.5076 [2021-03-26 02:17:28 swin_small_patch4_window7_224] INFO: Epoch: [125] [1090/1251] eta: 0:01:22 lr: 0.000629 loss: 3.3296 (3.3844) grad_norm: 1.2402 (nan) time: 0.5079 [2021-03-26 02:17:33 swin_small_patch4_window7_224] INFO: Epoch: [125] [1100/1251] eta: 0:01:17 lr: 0.000629 loss: 3.0834 (3.3838) grad_norm: 1.2253 (nan) time: 0.5022 [2021-03-26 02:17:38 swin_small_patch4_window7_224] INFO: Epoch: [125] [1110/1251] eta: 0:01:12 lr: 0.000629 loss: 3.4603 (3.3845) grad_norm: 1.2659 (nan) time: 0.4973 [2021-03-26 02:17:43 swin_small_patch4_window7_224] INFO: Epoch: [125] [1120/1251] eta: 0:01:06 lr: 0.000629 loss: 3.6457 (3.3862) grad_norm: 1.2443 (nan) time: 0.5001 [2021-03-26 02:17:48 swin_small_patch4_window7_224] INFO: Epoch: [125] [1130/1251] eta: 0:01:01 lr: 0.000629 loss: 3.7004 (3.3877) grad_norm: 1.2443 (nan) time: 0.5019 [2021-03-26 02:17:53 swin_small_patch4_window7_224] INFO: Epoch: [125] [1140/1251] eta: 0:00:56 lr: 0.000629 loss: 3.6621 (3.3889) grad_norm: 1.2895 (nan) time: 0.5016 [2021-03-26 02:17:58 swin_small_patch4_window7_224] INFO: Epoch: [125] [1150/1251] eta: 0:00:51 lr: 0.000629 loss: 3.5547 (3.3885) grad_norm: 1.2667 (nan) time: 0.5035 [2021-03-26 02:18:03 swin_small_patch4_window7_224] INFO: Epoch: [125] [1160/1251] eta: 0:00:46 lr: 0.000628 loss: 3.5044 (3.3893) grad_norm: 1.2615 (nan) time: 0.5088 [2021-03-26 02:18:08 swin_small_patch4_window7_224] INFO: Epoch: [125] [1170/1251] eta: 0:00:41 lr: 0.000628 loss: 3.5577 (3.3919) grad_norm: 1.2621 (nan) time: 0.5062 [2021-03-26 02:18:13 swin_small_patch4_window7_224] INFO: Epoch: [125] [1180/1251] eta: 0:00:36 lr: 0.000628 loss: 3.7138 (3.3934) grad_norm: 1.2285 (nan) time: 0.5079 [2021-03-26 02:18:18 swin_small_patch4_window7_224] INFO: Epoch: [125] [1190/1251] eta: 0:00:31 lr: 0.000628 loss: 3.6908 (3.3935) grad_norm: 1.2187 (nan) time: 0.5123 [2021-03-26 02:18:23 swin_small_patch4_window7_224] INFO: Epoch: [125] [1200/1251] eta: 0:00:26 lr: 0.000628 loss: 3.5900 (3.3939) grad_norm: 1.2311 (nan) time: 0.5076 [2021-03-26 02:18:28 swin_small_patch4_window7_224] INFO: Epoch: [125] [1210/1251] eta: 0:00:20 lr: 0.000628 loss: 3.4674 (3.3935) grad_norm: 1.2677 (nan) time: 0.5047 [2021-03-26 02:18:33 swin_small_patch4_window7_224] INFO: Epoch: [125] [1220/1251] eta: 0:00:15 lr: 0.000628 loss: 3.4674 (3.3937) grad_norm: 1.2828 (nan) time: 0.5053 [2021-03-26 02:18:38 swin_small_patch4_window7_224] INFO: Epoch: [125] [1230/1251] eta: 0:00:10 lr: 0.000628 loss: 3.6644 (3.3957) grad_norm: 1.3145 (nan) time: 0.5070 [2021-03-26 02:18:43 swin_small_patch4_window7_224] INFO: Epoch: [125] [1240/1251] eta: 0:00:05 lr: 0.000628 loss: 3.5820 (3.3957) grad_norm: 1.3508 (nan) time: 0.5050 [2021-03-26 02:18:48 swin_small_patch4_window7_224] INFO: Epoch: [125] [1250/1251] eta: 0:00:00 lr: 0.000628 loss: 3.4905 (3.3954) grad_norm: 1.3277 (nan) time: 0.5037 [2021-03-26 02:19:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 0.8817 (0.8817) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-26 02:19:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9686 (0.9592) acc1: 75.0000 (76.2784) acc5: 93.7500 (93.7500) [2021-03-26 02:19:39 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 1.0438 (0.9920) acc1: 75.0000 (76.4881) acc5: 93.7500 (93.6756) [2021-03-26 02:19:40 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9684 (0.9814) acc1: 78.1250 (76.8649) acc5: 93.7500 (94.0020) [2021-03-26 02:19:41 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9106 (0.9823) acc1: 76.5625 (76.4101) acc5: 95.3125 (94.1311) [2021-03-26 02:19:42 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9731 (0.9878) acc1: 75.0000 (76.4480) acc5: 93.7500 (94.1120) [2021-03-26 02:19:50 swin_small_patch4_window7_224] INFO: * Acc@1 77.268 Acc@5 93.984 loss 0.960 [2021-03-26 02:19:50 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.3% [2021-03-26 02:19:50 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 02:19:54 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 0/1251] eta: 1:23:15 lr: 0.000628 loss: 3.7295 (3.7295) grad_norm: 1.3243 (1.3243) time: 3.9936 [2021-03-26 02:19:59 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 10/1251] eta: 0:17:26 lr: 0.000628 loss: 3.3420 (3.3557) grad_norm: 1.3138 (1.2914) time: 0.8433 [2021-03-26 02:20:04 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 20/1251] eta: 0:14:01 lr: 0.000628 loss: 3.3774 (3.3749) grad_norm: 1.2674 (1.2922) time: 0.5177 [2021-03-26 02:20:09 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 30/1251] eta: 0:12:44 lr: 0.000628 loss: 3.4446 (3.4014) grad_norm: 1.2563 (1.2977) time: 0.5073 [2021-03-26 02:20:14 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 40/1251] eta: 0:12:04 lr: 0.000628 loss: 3.4400 (3.3981) grad_norm: 1.2563 (1.3019) time: 0.5089 [2021-03-26 02:20:19 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 50/1251] eta: 0:11:37 lr: 0.000628 loss: 3.5092 (3.4234) grad_norm: 1.2417 (1.2977) time: 0.5094 [2021-03-26 02:20:24 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 60/1251] eta: 0:11:18 lr: 0.000628 loss: 3.5500 (3.4234) grad_norm: 1.2300 (1.2906) time: 0.5122 [2021-03-26 02:20:29 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 70/1251] eta: 0:11:02 lr: 0.000628 loss: 3.5191 (3.4204) grad_norm: 1.2269 (1.2829) time: 0.5104 [2021-03-26 02:20:35 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 80/1251] eta: 0:10:51 lr: 0.000628 loss: 3.1734 (3.3931) grad_norm: 1.1864 (1.2695) time: 0.5138 [2021-03-26 02:20:40 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 90/1251] eta: 0:10:38 lr: 0.000628 loss: 3.3421 (3.3951) grad_norm: 1.1845 (1.2681) time: 0.5132 [2021-03-26 02:20:45 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 100/1251] eta: 0:10:27 lr: 0.000628 loss: 3.5842 (3.4200) grad_norm: 1.2334 (1.2644) time: 0.5006 [2021-03-26 02:20:50 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 110/1251] eta: 0:10:18 lr: 0.000628 loss: 3.6308 (3.4314) grad_norm: 1.2391 (1.2715) time: 0.5033 [2021-03-26 02:20:55 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 120/1251] eta: 0:10:10 lr: 0.000628 loss: 3.5884 (3.4252) grad_norm: 1.2354 (1.2687) time: 0.5113 [2021-03-26 02:21:00 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 130/1251] eta: 0:10:02 lr: 0.000628 loss: 3.3210 (3.4159) grad_norm: 1.2504 (1.2729) time: 0.5128 [2021-03-26 02:21:05 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 140/1251] eta: 0:09:54 lr: 0.000628 loss: 3.2445 (3.4105) grad_norm: 1.2378 (1.2675) time: 0.5081 [2021-03-26 02:21:10 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 150/1251] eta: 0:09:47 lr: 0.000627 loss: 3.5305 (3.4133) grad_norm: 1.2310 (1.2701) time: 0.5063 [2021-03-26 02:21:15 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 160/1251] eta: 0:09:40 lr: 0.000627 loss: 3.5826 (3.4183) grad_norm: 1.2620 (1.2682) time: 0.5079 [2021-03-26 02:21:20 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 170/1251] eta: 0:09:33 lr: 0.000627 loss: 3.5826 (3.4181) grad_norm: 1.2481 (1.2668) time: 0.5129 [2021-03-26 02:21:26 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 180/1251] eta: 0:09:27 lr: 0.000627 loss: 3.4732 (3.4075) grad_norm: 1.2481 (1.2680) time: 0.5160 [2021-03-26 02:21:31 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 190/1251] eta: 0:09:20 lr: 0.000627 loss: 3.5016 (3.4132) grad_norm: 1.2229 (1.2648) time: 0.5077 [2021-03-26 02:21:36 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 200/1251] eta: 0:09:14 lr: 0.000627 loss: 3.6017 (3.4194) grad_norm: 1.2229 (1.2633) time: 0.5063 [2021-03-26 02:21:41 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 210/1251] eta: 0:09:08 lr: 0.000627 loss: 3.3983 (3.4103) grad_norm: 1.2290 (1.2641) time: 0.5115 [2021-03-26 02:21:46 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 220/1251] eta: 0:09:02 lr: 0.000627 loss: 3.3435 (3.4136) grad_norm: 1.2806 (1.2652) time: 0.5069 [2021-03-26 02:21:51 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 230/1251] eta: 0:08:56 lr: 0.000627 loss: 3.2695 (3.3986) grad_norm: 1.2806 (1.2652) time: 0.5056 [2021-03-26 02:21:56 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 240/1251] eta: 0:08:49 lr: 0.000627 loss: 3.2742 (3.4039) grad_norm: 1.2320 (1.2657) time: 0.5046 [2021-03-26 02:22:01 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 250/1251] eta: 0:08:43 lr: 0.000627 loss: 3.5196 (3.4036) grad_norm: 1.2164 (1.2675) time: 0.4993 [2021-03-26 02:22:06 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 260/1251] eta: 0:08:38 lr: 0.000627 loss: 3.5196 (3.4074) grad_norm: 1.2632 (1.2725) time: 0.5104 [2021-03-26 02:22:11 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 270/1251] eta: 0:08:32 lr: 0.000627 loss: 3.5920 (3.4144) grad_norm: 1.2896 (1.2742) time: 0.5098 [2021-03-26 02:22:16 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 280/1251] eta: 0:08:26 lr: 0.000627 loss: 3.6317 (3.4256) grad_norm: 1.2487 (1.2734) time: 0.4988 [2021-03-26 02:22:21 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 290/1251] eta: 0:08:20 lr: 0.000627 loss: 3.6317 (3.4333) grad_norm: 1.2631 (1.2732) time: 0.5049 [2021-03-26 02:22:26 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 300/1251] eta: 0:08:15 lr: 0.000627 loss: 3.4110 (3.4231) grad_norm: 1.2932 (1.2739) time: 0.5122 [2021-03-26 02:22:31 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 310/1251] eta: 0:08:09 lr: 0.000627 loss: 3.2595 (3.4209) grad_norm: 1.2410 (1.2733) time: 0.5115 [2021-03-26 02:22:36 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 320/1251] eta: 0:08:03 lr: 0.000627 loss: 3.4975 (3.4231) grad_norm: 1.2420 (1.2760) time: 0.5044 [2021-03-26 02:22:42 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 330/1251] eta: 0:07:58 lr: 0.000627 loss: 3.3365 (3.4103) grad_norm: 1.2420 (1.2752) time: 0.5042 [2021-03-26 02:22:47 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 340/1251] eta: 0:07:52 lr: 0.000627 loss: 3.2426 (3.4133) grad_norm: 1.2133 (1.2758) time: 0.5056 [2021-03-26 02:22:52 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 350/1251] eta: 0:07:46 lr: 0.000627 loss: 3.3627 (3.4147) grad_norm: 1.2587 (1.2767) time: 0.5014 [2021-03-26 02:22:57 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 360/1251] eta: 0:07:41 lr: 0.000627 loss: 3.6802 (3.4184) grad_norm: 1.2826 (1.2782) time: 0.4990 [2021-03-26 02:23:02 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 370/1251] eta: 0:07:35 lr: 0.000627 loss: 3.3697 (3.4164) grad_norm: 1.3236 (1.2816) time: 0.5030 [2021-03-26 02:23:07 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 380/1251] eta: 0:07:30 lr: 0.000627 loss: 3.3697 (3.4136) grad_norm: 1.2939 (1.2823) time: 0.5060 [2021-03-26 02:23:12 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 390/1251] eta: 0:07:25 lr: 0.000627 loss: 3.3839 (3.4164) grad_norm: 1.3322 (1.2857) time: 0.5062 [2021-03-26 02:23:17 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 400/1251] eta: 0:07:19 lr: 0.000626 loss: 3.3530 (3.4118) grad_norm: 1.3454 (1.2876) time: 0.5067 [2021-03-26 02:23:22 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 410/1251] eta: 0:07:14 lr: 0.000626 loss: 3.4085 (3.4132) grad_norm: 1.3162 (1.2882) time: 0.5045 [2021-03-26 02:23:27 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 420/1251] eta: 0:07:08 lr: 0.000626 loss: 3.5279 (3.4154) grad_norm: 1.2765 (1.2878) time: 0.5078 [2021-03-26 02:23:32 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 430/1251] eta: 0:07:03 lr: 0.000626 loss: 3.5118 (3.4150) grad_norm: 1.2723 (1.2882) time: 0.5112 [2021-03-26 02:23:37 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 440/1251] eta: 0:06:58 lr: 0.000626 loss: 3.4967 (3.4163) grad_norm: 1.2972 (1.2903) time: 0.5044 [2021-03-26 02:23:42 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 450/1251] eta: 0:06:52 lr: 0.000626 loss: 3.4296 (3.4141) grad_norm: 1.3131 (1.2908) time: 0.5041 [2021-03-26 02:23:47 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 460/1251] eta: 0:06:47 lr: 0.000626 loss: 3.2966 (3.4113) grad_norm: 1.2567 (1.2901) time: 0.5132 [2021-03-26 02:23:52 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 470/1251] eta: 0:06:42 lr: 0.000626 loss: 3.7754 (3.4187) grad_norm: 1.2211 (1.2902) time: 0.5084 [2021-03-26 02:23:57 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 480/1251] eta: 0:06:37 lr: 0.000626 loss: 3.7718 (3.4174) grad_norm: 1.2719 (1.2910) time: 0.5077 [2021-03-26 02:24:03 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 490/1251] eta: 0:06:31 lr: 0.000626 loss: 3.3264 (3.4181) grad_norm: 1.2812 (1.2903) time: 0.5124 [2021-03-26 02:24:08 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 500/1251] eta: 0:06:26 lr: 0.000626 loss: 3.2861 (3.4138) grad_norm: 1.2813 (1.2908) time: 0.5056 [2021-03-26 02:24:13 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 510/1251] eta: 0:06:21 lr: 0.000626 loss: 3.2405 (3.4095) grad_norm: 1.3053 (1.2920) time: 0.5025 [2021-03-26 02:24:18 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 520/1251] eta: 0:06:16 lr: 0.000626 loss: 3.3292 (3.4109) grad_norm: 1.3474 (1.2944) time: 0.5052 [2021-03-26 02:24:23 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 530/1251] eta: 0:06:10 lr: 0.000626 loss: 3.1405 (3.4057) grad_norm: 1.3373 (1.2948) time: 0.5067 [2021-03-26 02:24:28 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 540/1251] eta: 0:06:05 lr: 0.000626 loss: 3.1405 (3.4060) grad_norm: 1.2741 (1.2943) time: 0.5086 [2021-03-26 02:24:33 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 550/1251] eta: 0:06:00 lr: 0.000626 loss: 3.5918 (3.4048) grad_norm: 1.2907 (1.2940) time: 0.5191 [2021-03-26 02:24:38 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 560/1251] eta: 0:05:55 lr: 0.000626 loss: 3.3931 (3.4034) grad_norm: 1.2553 (1.2938) time: 0.5206 [2021-03-26 02:24:43 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 570/1251] eta: 0:05:50 lr: 0.000626 loss: 3.3279 (3.4017) grad_norm: 1.2415 (1.2930) time: 0.5126 [2021-03-26 02:24:49 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 580/1251] eta: 0:05:45 lr: 0.000626 loss: 3.3793 (3.4018) grad_norm: 1.2479 (1.2928) time: 0.5104 [2021-03-26 02:24:54 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 590/1251] eta: 0:05:40 lr: 0.000626 loss: 3.5975 (3.4067) grad_norm: 1.2518 (1.2920) time: 0.5141 [2021-03-26 02:24:59 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 600/1251] eta: 0:05:34 lr: 0.000626 loss: 3.5792 (3.4065) grad_norm: 1.2814 (1.2925) time: 0.5132 [2021-03-26 02:25:04 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 610/1251] eta: 0:05:29 lr: 0.000626 loss: 3.4269 (3.4077) grad_norm: 1.3379 (1.2938) time: 0.5036 [2021-03-26 02:25:09 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 620/1251] eta: 0:05:24 lr: 0.000626 loss: 3.5841 (3.4073) grad_norm: 1.2834 (1.2933) time: 0.4996 [2021-03-26 02:25:14 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 630/1251] eta: 0:05:18 lr: 0.000626 loss: 3.4976 (3.4083) grad_norm: 1.2664 (1.2921) time: 0.5021 [2021-03-26 02:25:19 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 640/1251] eta: 0:05:13 lr: 0.000626 loss: 3.5288 (3.4080) grad_norm: 1.2262 (1.2914) time: 0.5079 [2021-03-26 02:25:24 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 650/1251] eta: 0:05:08 lr: 0.000625 loss: 3.6067 (3.4085) grad_norm: 1.2530 (1.2919) time: 0.5087 [2021-03-26 02:25:29 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 660/1251] eta: 0:05:03 lr: 0.000625 loss: 3.4508 (3.4052) grad_norm: 1.2984 (1.2929) time: 0.5104 [2021-03-26 02:25:34 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 670/1251] eta: 0:04:58 lr: 0.000625 loss: 3.1113 (3.4028) grad_norm: 1.3062 (1.2940) time: 0.5055 [2021-03-26 02:25:39 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 680/1251] eta: 0:04:53 lr: 0.000625 loss: 3.4801 (3.4037) grad_norm: 1.2720 (1.2935) time: 0.5040 [2021-03-26 02:25:44 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 690/1251] eta: 0:04:47 lr: 0.000625 loss: 3.5497 (3.4084) grad_norm: 1.2573 (1.2930) time: 0.5078 [2021-03-26 02:25:49 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 700/1251] eta: 0:04:42 lr: 0.000625 loss: 3.6434 (3.4122) grad_norm: 1.2767 (1.2933) time: 0.5008 [2021-03-26 02:25:54 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 710/1251] eta: 0:04:37 lr: 0.000625 loss: 3.5248 (3.4110) grad_norm: 1.2728 (1.2933) time: 0.5017 [2021-03-26 02:25:59 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 720/1251] eta: 0:04:32 lr: 0.000625 loss: 3.3479 (3.4116) grad_norm: 1.3134 (1.2944) time: 0.5087 [2021-03-26 02:26:05 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 730/1251] eta: 0:04:27 lr: 0.000625 loss: 3.4693 (3.4103) grad_norm: 1.3479 (1.2953) time: 0.5149 [2021-03-26 02:26:10 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 740/1251] eta: 0:04:22 lr: 0.000625 loss: 3.1960 (3.4083) grad_norm: 1.2414 (1.2949) time: 0.5265 [2021-03-26 02:26:15 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 750/1251] eta: 0:04:17 lr: 0.000625 loss: 3.3698 (3.4083) grad_norm: 1.2366 (1.2939) time: 0.5242 [2021-03-26 02:26:20 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 760/1251] eta: 0:04:11 lr: 0.000625 loss: 3.3518 (3.4046) grad_norm: 1.2475 (1.2937) time: 0.5110 [2021-03-26 02:26:25 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 770/1251] eta: 0:04:06 lr: 0.000625 loss: 3.4359 (3.4088) grad_norm: 1.3148 (1.2942) time: 0.5100 [2021-03-26 02:26:30 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 780/1251] eta: 0:04:01 lr: 0.000625 loss: 3.4891 (3.4061) grad_norm: 1.3229 (1.2944) time: 0.5073 [2021-03-26 02:26:35 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 790/1251] eta: 0:03:56 lr: 0.000625 loss: 3.3860 (3.4064) grad_norm: 1.2875 (1.2945) time: 0.5075 [2021-03-26 02:26:40 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 800/1251] eta: 0:03:51 lr: 0.000625 loss: 3.4625 (3.4066) grad_norm: 1.2296 (1.2938) time: 0.5064 [2021-03-26 02:26:46 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 810/1251] eta: 0:03:46 lr: 0.000625 loss: 3.5233 (3.4072) grad_norm: 1.2154 (1.2934) time: 0.5094 [2021-03-26 02:26:51 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 820/1251] eta: 0:03:40 lr: 0.000625 loss: 3.4636 (3.4065) grad_norm: 1.2154 (1.2925) time: 0.5096 [2021-03-26 02:26:56 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 830/1251] eta: 0:03:35 lr: 0.000625 loss: 3.6221 (3.4091) grad_norm: 1.2661 (1.2930) time: 0.5065 [2021-03-26 02:27:01 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 840/1251] eta: 0:03:30 lr: 0.000625 loss: 3.6376 (3.4102) grad_norm: 1.3074 (1.2934) time: 0.5079 [2021-03-26 02:27:06 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 850/1251] eta: 0:03:25 lr: 0.000625 loss: 3.7234 (3.4134) grad_norm: 1.2571 (1.2939) time: 0.5058 [2021-03-26 02:27:11 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 860/1251] eta: 0:03:20 lr: 0.000625 loss: 3.5059 (3.4108) grad_norm: 1.3289 (1.2947) time: 0.5000 [2021-03-26 02:27:16 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 870/1251] eta: 0:03:15 lr: 0.000625 loss: 3.4471 (3.4124) grad_norm: 1.3533 (1.2955) time: 0.5013 [2021-03-26 02:27:21 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 880/1251] eta: 0:03:10 lr: 0.000625 loss: 3.4866 (3.4136) grad_norm: 1.3330 (1.2954) time: 0.5101 [2021-03-26 02:27:26 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 890/1251] eta: 0:03:04 lr: 0.000625 loss: 3.5020 (3.4125) grad_norm: 1.2653 (1.2956) time: 0.5103 [2021-03-26 02:27:31 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 900/1251] eta: 0:02:59 lr: 0.000624 loss: 3.1923 (3.4096) grad_norm: 1.2357 (1.2953) time: 0.5107 [2021-03-26 02:27:36 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 910/1251] eta: 0:02:54 lr: 0.000624 loss: 3.0275 (3.4068) grad_norm: 1.2100 (1.2954) time: 0.5076 [2021-03-26 02:27:41 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 920/1251] eta: 0:02:49 lr: 0.000624 loss: 3.2345 (3.4055) grad_norm: 1.3351 (1.2960) time: 0.5047 [2021-03-26 02:27:47 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 930/1251] eta: 0:02:44 lr: 0.000624 loss: 3.4145 (3.4055) grad_norm: 1.3351 (1.2964) time: 0.5124 [2021-03-26 02:27:52 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 940/1251] eta: 0:02:39 lr: 0.000624 loss: 3.5028 (3.4053) grad_norm: 1.2843 (1.2966) time: 0.5221 [2021-03-26 02:27:57 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 950/1251] eta: 0:02:34 lr: 0.000624 loss: 3.4882 (3.4038) grad_norm: 1.2791 (1.2968) time: 0.5133 [2021-03-26 02:28:02 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 960/1251] eta: 0:02:29 lr: 0.000624 loss: 3.2362 (3.4027) grad_norm: 1.2656 (1.2965) time: 0.5046 [2021-03-26 02:28:07 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 970/1251] eta: 0:02:23 lr: 0.000624 loss: 3.4304 (3.4040) grad_norm: 1.2819 (1.2967) time: 0.5044 [2021-03-26 02:28:12 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 980/1251] eta: 0:02:18 lr: 0.000624 loss: 3.4243 (3.4028) grad_norm: 1.2833 (1.2966) time: 0.5005 [2021-03-26 02:28:17 swin_small_patch4_window7_224] INFO: Epoch: [126] [ 990/1251] eta: 0:02:13 lr: 0.000624 loss: 3.6167 (3.4045) grad_norm: 1.2563 (1.2966) time: 0.5012 [2021-03-26 02:28:22 swin_small_patch4_window7_224] INFO: Epoch: [126] [1000/1251] eta: 0:02:08 lr: 0.000624 loss: 3.5888 (3.4045) grad_norm: 1.2453 (1.2965) time: 0.5085 [2021-03-26 02:28:27 swin_small_patch4_window7_224] INFO: Epoch: [126] [1010/1251] eta: 0:02:03 lr: 0.000624 loss: 3.4353 (3.4053) grad_norm: 1.2302 (1.2960) time: 0.5081 [2021-03-26 02:28:32 swin_small_patch4_window7_224] INFO: Epoch: [126] [1020/1251] eta: 0:01:58 lr: 0.000624 loss: 3.5062 (3.4055) grad_norm: 1.1968 (1.2950) time: 0.5029 [2021-03-26 02:28:37 swin_small_patch4_window7_224] INFO: Epoch: [126] [1030/1251] eta: 0:01:53 lr: 0.000624 loss: 3.5688 (3.4066) grad_norm: 1.2239 (1.2950) time: 0.5057 [2021-03-26 02:28:42 swin_small_patch4_window7_224] INFO: Epoch: [126] [1040/1251] eta: 0:01:47 lr: 0.000624 loss: 3.5611 (3.4048) grad_norm: 1.2801 (1.2948) time: 0.5062 [2021-03-26 02:28:47 swin_small_patch4_window7_224] INFO: Epoch: [126] [1050/1251] eta: 0:01:42 lr: 0.000624 loss: 3.1292 (3.4039) grad_norm: 1.2976 (1.2951) time: 0.5062 [2021-03-26 02:28:52 swin_small_patch4_window7_224] INFO: Epoch: [126] [1060/1251] eta: 0:01:37 lr: 0.000624 loss: 3.3331 (3.4037) grad_norm: 1.2976 (1.2950) time: 0.5089 [2021-03-26 02:28:58 swin_small_patch4_window7_224] INFO: Epoch: [126] [1070/1251] eta: 0:01:32 lr: 0.000624 loss: 3.3331 (3.4028) grad_norm: 1.3075 (1.2952) time: 0.5086 [2021-03-26 02:29:03 swin_small_patch4_window7_224] INFO: Epoch: [126] [1080/1251] eta: 0:01:27 lr: 0.000624 loss: 3.2262 (3.4021) grad_norm: 1.3294 (1.2962) time: 0.5032 [2021-03-26 02:29:08 swin_small_patch4_window7_224] INFO: Epoch: [126] [1090/1251] eta: 0:01:22 lr: 0.000624 loss: 3.2985 (3.4009) grad_norm: 1.3030 (1.2954) time: 0.5027 [2021-03-26 02:29:13 swin_small_patch4_window7_224] INFO: Epoch: [126] [1100/1251] eta: 0:01:17 lr: 0.000624 loss: 3.3900 (3.4008) grad_norm: 1.2153 (1.2952) time: 0.5059 [2021-03-26 02:29:18 swin_small_patch4_window7_224] INFO: Epoch: [126] [1110/1251] eta: 0:01:12 lr: 0.000624 loss: 3.4149 (3.4012) grad_norm: 1.2324 (1.2956) time: 0.5053 [2021-03-26 02:29:23 swin_small_patch4_window7_224] INFO: Epoch: [126] [1120/1251] eta: 0:01:06 lr: 0.000624 loss: 3.4126 (3.4004) grad_norm: 1.3119 (1.2956) time: 0.5108 [2021-03-26 02:29:28 swin_small_patch4_window7_224] INFO: Epoch: [126] [1130/1251] eta: 0:01:01 lr: 0.000624 loss: 3.3081 (3.4010) grad_norm: 1.2179 (1.2954) time: 0.5052 [2021-03-26 02:29:33 swin_small_patch4_window7_224] INFO: Epoch: [126] [1140/1251] eta: 0:00:56 lr: 0.000624 loss: 3.2919 (3.4009) grad_norm: 1.2472 (1.2953) time: 0.4970 [2021-03-26 02:29:38 swin_small_patch4_window7_224] INFO: Epoch: [126] [1150/1251] eta: 0:00:51 lr: 0.000623 loss: 3.2919 (3.4009) grad_norm: 1.2835 (1.2951) time: 0.4996 [2021-03-26 02:29:43 swin_small_patch4_window7_224] INFO: Epoch: [126] [1160/1251] eta: 0:00:46 lr: 0.000623 loss: 3.2693 (3.3998) grad_norm: 1.2474 (1.2952) time: 0.5018 [2021-03-26 02:29:48 swin_small_patch4_window7_224] INFO: Epoch: [126] [1170/1251] eta: 0:00:41 lr: 0.000623 loss: 3.2624 (3.3992) grad_norm: 1.2474 (1.2955) time: 0.5037 [2021-03-26 02:29:53 swin_small_patch4_window7_224] INFO: Epoch: [126] [1180/1251] eta: 0:00:36 lr: 0.000623 loss: 3.1751 (3.3970) grad_norm: 1.2673 (1.2954) time: 0.5052 [2021-03-26 02:29:58 swin_small_patch4_window7_224] INFO: Epoch: [126] [1190/1251] eta: 0:00:31 lr: 0.000623 loss: 3.3137 (3.3968) grad_norm: 1.2673 (1.2955) time: 0.5154 [2021-03-26 02:30:03 swin_small_patch4_window7_224] INFO: Epoch: [126] [1200/1251] eta: 0:00:26 lr: 0.000623 loss: 3.5146 (3.3961) grad_norm: 1.2858 (1.2954) time: 0.5183 [2021-03-26 02:30:08 swin_small_patch4_window7_224] INFO: Epoch: [126] [1210/1251] eta: 0:00:20 lr: 0.000623 loss: 3.5956 (3.3993) grad_norm: 1.3043 (1.2960) time: 0.5064 [2021-03-26 02:30:13 swin_small_patch4_window7_224] INFO: Epoch: [126] [1220/1251] eta: 0:00:15 lr: 0.000623 loss: 3.5701 (3.4000) grad_norm: 1.3043 (1.2961) time: 0.5018 [2021-03-26 02:30:18 swin_small_patch4_window7_224] INFO: Epoch: [126] [1230/1251] eta: 0:00:10 lr: 0.000623 loss: 3.5242 (3.4011) grad_norm: 1.2655 (1.2969) time: 0.5049 [2021-03-26 02:30:23 swin_small_patch4_window7_224] INFO: Epoch: [126] [1240/1251] eta: 0:00:05 lr: 0.000623 loss: 3.5739 (3.4020) grad_norm: 1.2211 (1.2961) time: 0.5026 [2021-03-26 02:30:28 swin_small_patch4_window7_224] INFO: Epoch: [126] [1250/1251] eta: 0:00:00 lr: 0.000623 loss: 3.5423 (3.4033) grad_norm: 1.2019 (1.2959) time: 0.4931 [2021-03-26 02:30:34 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:24 loss: 1.2797 (1.2797) acc1: 67.1875 (67.1875) acc5: 92.1875 (92.1875) [2021-03-26 02:30:37 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 1.0029 (1.0239) acc1: 75.0000 (76.9886) acc5: 93.7500 (94.0341) [2021-03-26 02:30:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9879 (1.0321) acc1: 75.0000 (76.3393) acc5: 93.7500 (93.8988) [2021-03-26 02:30:41 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9864 (0.9932) acc1: 76.5625 (77.2177) acc5: 95.3125 (94.4052) [2021-03-26 02:30:43 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8725 (0.9768) acc1: 78.1250 (77.2485) acc5: 93.7500 (94.3216) [2021-03-26 02:30:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9855 (0.9787) acc1: 75.4717 (77.2800) acc5: 93.7500 (94.1760) [2021-03-26 02:30:51 swin_small_patch4_window7_224] INFO: * Acc@1 77.420 Acc@5 94.148 loss 0.965 [2021-03-26 02:30:51 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.4% [2021-03-26 02:30:51 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 02:30:56 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 0/1251] eta: 1:29:57 lr: 0.000623 loss: 4.0791 (4.0791) grad_norm: 1.2784 (1.2784) time: 4.3148 [2021-03-26 02:31:01 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 10/1251] eta: 0:17:38 lr: 0.000623 loss: 3.7591 (3.6464) grad_norm: 1.2650 (1.2553) time: 0.8528 [2021-03-26 02:31:06 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 20/1251] eta: 0:14:05 lr: 0.000623 loss: 3.3437 (3.4412) grad_norm: 1.2650 (1.2768) time: 0.5056 [2021-03-26 02:31:11 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 30/1251] eta: 0:12:47 lr: 0.000623 loss: 3.3301 (3.3981) grad_norm: 1.2760 (1.2768) time: 0.5058 [2021-03-26 02:31:16 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 40/1251] eta: 0:12:08 lr: 0.000623 loss: 3.3361 (3.3862) grad_norm: 1.2791 (1.2875) time: 0.5113 [2021-03-26 02:31:21 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 50/1251] eta: 0:11:41 lr: 0.000623 loss: 3.2760 (3.3567) grad_norm: 1.2756 (1.2886) time: 0.5138 [2021-03-26 02:31:26 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 60/1251] eta: 0:11:18 lr: 0.000623 loss: 3.2522 (3.3594) grad_norm: 1.2274 (1.2807) time: 0.5038 [2021-03-26 02:31:31 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 70/1251] eta: 0:11:03 lr: 0.000623 loss: 3.2522 (3.3449) grad_norm: 1.2229 (1.2701) time: 0.5060 [2021-03-26 02:31:36 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 80/1251] eta: 0:10:50 lr: 0.000623 loss: 3.1723 (3.3069) grad_norm: 1.2001 (1.2659) time: 0.5130 [2021-03-26 02:31:41 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 90/1251] eta: 0:10:38 lr: 0.000623 loss: 3.1391 (3.2915) grad_norm: 1.1974 (1.2590) time: 0.5057 [2021-03-26 02:31:47 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 100/1251] eta: 0:10:27 lr: 0.000623 loss: 3.4768 (3.3104) grad_norm: 1.2051 (1.2580) time: 0.5027 [2021-03-26 02:31:52 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 110/1251] eta: 0:10:19 lr: 0.000623 loss: 3.4861 (3.3258) grad_norm: 1.2288 (1.2617) time: 0.5115 [2021-03-26 02:31:57 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 120/1251] eta: 0:10:09 lr: 0.000623 loss: 3.4717 (3.3368) grad_norm: 1.2579 (1.2626) time: 0.5091 [2021-03-26 02:32:02 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 130/1251] eta: 0:10:02 lr: 0.000623 loss: 3.2523 (3.3195) grad_norm: 1.2579 (1.2624) time: 0.5071 [2021-03-26 02:32:07 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 140/1251] eta: 0:09:55 lr: 0.000623 loss: 3.1979 (3.3176) grad_norm: 1.1842 (1.2574) time: 0.5179 [2021-03-26 02:32:12 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 150/1251] eta: 0:09:47 lr: 0.000622 loss: 3.3647 (3.3240) grad_norm: 1.2271 (1.2603) time: 0.5112 [2021-03-26 02:32:17 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 160/1251] eta: 0:09:40 lr: 0.000622 loss: 3.2568 (3.3149) grad_norm: 1.2412 (1.2617) time: 0.5021 [2021-03-26 02:32:22 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 170/1251] eta: 0:09:33 lr: 0.000622 loss: 3.5187 (3.3284) grad_norm: 1.2398 (1.2626) time: 0.5027 [2021-03-26 02:32:27 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 180/1251] eta: 0:09:26 lr: 0.000622 loss: 3.5401 (3.3352) grad_norm: 1.2524 (1.2674) time: 0.5057 [2021-03-26 02:32:32 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 190/1251] eta: 0:09:19 lr: 0.000622 loss: 3.6542 (3.3596) grad_norm: 1.3100 (1.2761) time: 0.5071 [2021-03-26 02:32:37 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 200/1251] eta: 0:09:14 lr: 0.000622 loss: 3.6816 (3.3682) grad_norm: 1.3100 (1.2775) time: 0.5112 [2021-03-26 02:32:42 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 210/1251] eta: 0:09:07 lr: 0.000622 loss: 3.3983 (3.3533) grad_norm: 1.3039 (1.2795) time: 0.5092 [2021-03-26 02:32:47 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 220/1251] eta: 0:09:00 lr: 0.000622 loss: 3.2437 (3.3633) grad_norm: 1.2419 (1.2785) time: 0.5000 [2021-03-26 02:32:53 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 230/1251] eta: 0:08:55 lr: 0.000622 loss: 3.5593 (3.3633) grad_norm: 1.2416 (1.2786) time: 0.5059 [2021-03-26 02:32:58 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 240/1251] eta: 0:08:49 lr: 0.000622 loss: 3.6398 (3.3697) grad_norm: 1.2500 (1.2784) time: 0.5093 [2021-03-26 02:33:03 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 250/1251] eta: 0:08:43 lr: 0.000622 loss: 3.4870 (3.3743) grad_norm: 1.2464 (1.2781) time: 0.5096 [2021-03-26 02:33:08 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 260/1251] eta: 0:08:37 lr: 0.000622 loss: 3.4100 (3.3743) grad_norm: 1.2442 (1.2786) time: 0.5038 [2021-03-26 02:33:13 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 270/1251] eta: 0:08:31 lr: 0.000622 loss: 3.4100 (3.3676) grad_norm: 1.2562 (1.2809) time: 0.4993 [2021-03-26 02:33:18 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 280/1251] eta: 0:08:25 lr: 0.000622 loss: 3.4620 (3.3701) grad_norm: 1.3341 (1.2858) time: 0.5066 [2021-03-26 02:33:23 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 290/1251] eta: 0:08:20 lr: 0.000622 loss: 3.4667 (3.3728) grad_norm: 1.3341 (1.2881) time: 0.5076 [2021-03-26 02:33:28 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 300/1251] eta: 0:08:14 lr: 0.000622 loss: 3.5335 (3.3688) grad_norm: 1.3017 (1.2885) time: 0.5014 [2021-03-26 02:33:33 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 310/1251] eta: 0:08:08 lr: 0.000622 loss: 3.4905 (3.3659) grad_norm: 1.2673 (1.2867) time: 0.5016 [2021-03-26 02:33:38 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 320/1251] eta: 0:08:03 lr: 0.000622 loss: 3.4905 (3.3694) grad_norm: 1.2433 (1.2876) time: 0.5080 [2021-03-26 02:33:43 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 330/1251] eta: 0:07:57 lr: 0.000622 loss: 3.5740 (3.3745) grad_norm: 1.2433 (1.2866) time: 0.5056 [2021-03-26 02:33:48 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 340/1251] eta: 0:07:51 lr: 0.000622 loss: 3.5001 (3.3739) grad_norm: 1.2227 (1.2848) time: 0.5018 [2021-03-26 02:33:53 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 350/1251] eta: 0:07:46 lr: 0.000622 loss: 3.4787 (3.3738) grad_norm: 1.2354 (1.2842) time: 0.5029 [2021-03-26 02:33:58 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 360/1251] eta: 0:07:40 lr: 0.000622 loss: 3.3381 (3.3747) grad_norm: 1.2599 (1.2828) time: 0.5044 [2021-03-26 02:34:03 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 370/1251] eta: 0:07:35 lr: 0.000622 loss: 3.4680 (3.3784) grad_norm: 1.2400 (1.2827) time: 0.5040 [2021-03-26 02:34:08 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 380/1251] eta: 0:07:29 lr: 0.000622 loss: 3.5619 (3.3803) grad_norm: 1.2918 (1.2823) time: 0.5077 [2021-03-26 02:34:13 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 390/1251] eta: 0:07:24 lr: 0.000622 loss: 3.5971 (3.3883) grad_norm: 1.3101 (1.2836) time: 0.5029 [2021-03-26 02:34:18 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 400/1251] eta: 0:07:18 lr: 0.000621 loss: 3.5105 (3.3853) grad_norm: 1.2648 (1.2831) time: 0.4989 [2021-03-26 02:34:23 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 410/1251] eta: 0:07:13 lr: 0.000621 loss: 3.2216 (3.3834) grad_norm: 1.2047 (1.2821) time: 0.5086 [2021-03-26 02:34:28 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 420/1251] eta: 0:07:08 lr: 0.000621 loss: 3.3957 (3.3851) grad_norm: 1.1932 (1.2805) time: 0.5083 [2021-03-26 02:34:34 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 430/1251] eta: 0:07:03 lr: 0.000621 loss: 3.4990 (3.3860) grad_norm: 1.2249 (1.2805) time: 0.5064 [2021-03-26 02:34:39 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 440/1251] eta: 0:06:57 lr: 0.000621 loss: 3.3892 (3.3812) grad_norm: 1.2487 (1.2801) time: 0.5062 [2021-03-26 02:34:44 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 450/1251] eta: 0:06:52 lr: 0.000621 loss: 3.3892 (3.3829) grad_norm: 1.2603 (1.2811) time: 0.5007 [2021-03-26 02:34:49 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 460/1251] eta: 0:06:46 lr: 0.000621 loss: 3.4016 (3.3808) grad_norm: 1.3326 (1.2821) time: 0.5024 [2021-03-26 02:34:54 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 470/1251] eta: 0:06:41 lr: 0.000621 loss: 3.3795 (3.3803) grad_norm: 1.3329 (1.2840) time: 0.5081 [2021-03-26 02:34:59 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 480/1251] eta: 0:06:36 lr: 0.000621 loss: 3.4429 (3.3808) grad_norm: 1.3711 (1.2859) time: 0.5119 [2021-03-26 02:35:04 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 490/1251] eta: 0:06:31 lr: 0.000621 loss: 3.4501 (3.3811) grad_norm: 1.4331 (1.2885) time: 0.5064 [2021-03-26 02:35:09 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 500/1251] eta: 0:06:25 lr: 0.000621 loss: 3.3805 (3.3799) grad_norm: 1.3103 (1.2885) time: 0.5045 [2021-03-26 02:35:14 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 510/1251] eta: 0:06:20 lr: 0.000621 loss: 3.2202 (3.3721) grad_norm: 1.2734 (1.2874) time: 0.5074 [2021-03-26 02:35:19 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 520/1251] eta: 0:06:15 lr: 0.000621 loss: 2.9718 (3.3686) grad_norm: 1.1914 (1.2868) time: 0.5069 [2021-03-26 02:35:24 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 530/1251] eta: 0:06:10 lr: 0.000621 loss: 3.4664 (3.3712) grad_norm: 1.2453 (1.2865) time: 0.5053 [2021-03-26 02:35:29 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 540/1251] eta: 0:06:04 lr: 0.000621 loss: 3.2163 (3.3652) grad_norm: 1.2123 (1.2846) time: 0.5042 [2021-03-26 02:35:34 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 550/1251] eta: 0:05:59 lr: 0.000621 loss: 3.5905 (3.3696) grad_norm: 1.2123 (1.2841) time: 0.5152 [2021-03-26 02:35:39 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 560/1251] eta: 0:05:54 lr: 0.000621 loss: 3.6992 (3.3743) grad_norm: 1.2664 (1.2843) time: 0.5099 [2021-03-26 02:35:45 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 570/1251] eta: 0:05:49 lr: 0.000621 loss: 3.6394 (3.3756) grad_norm: 1.2710 (1.2849) time: 0.5026 [2021-03-26 02:35:50 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 580/1251] eta: 0:05:44 lr: 0.000621 loss: 3.3938 (3.3731) grad_norm: 1.2811 (1.2860) time: 0.5112 [2021-03-26 02:35:55 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 590/1251] eta: 0:05:39 lr: 0.000621 loss: 3.3938 (3.3759) grad_norm: 1.2985 (1.2857) time: 0.5104 [2021-03-26 02:36:00 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 600/1251] eta: 0:05:33 lr: 0.000621 loss: 3.4665 (3.3751) grad_norm: 1.3259 (1.2879) time: 0.5100 [2021-03-26 02:36:05 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 610/1251] eta: 0:05:28 lr: 0.000621 loss: 3.3886 (3.3743) grad_norm: 1.3803 (1.2892) time: 0.5084 [2021-03-26 02:36:10 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 620/1251] eta: 0:05:23 lr: 0.000621 loss: 3.4373 (3.3781) grad_norm: 1.3659 (1.2901) time: 0.5064 [2021-03-26 02:36:15 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 630/1251] eta: 0:05:18 lr: 0.000621 loss: 3.4933 (3.3764) grad_norm: 1.3217 (1.2904) time: 0.5011 [2021-03-26 02:36:20 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 640/1251] eta: 0:05:12 lr: 0.000620 loss: 3.5243 (3.3789) grad_norm: 1.2445 (1.2897) time: 0.4941 [2021-03-26 02:36:25 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 650/1251] eta: 0:05:07 lr: 0.000620 loss: 3.5243 (3.3805) grad_norm: 1.3117 (1.2914) time: 0.4974 [2021-03-26 02:36:30 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 660/1251] eta: 0:05:02 lr: 0.000620 loss: 3.4776 (3.3797) grad_norm: 1.3698 (1.2920) time: 0.5053 [2021-03-26 02:36:35 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 670/1251] eta: 0:04:57 lr: 0.000620 loss: 3.3279 (3.3788) grad_norm: 1.2819 (1.2911) time: 0.5040 [2021-03-26 02:36:40 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 680/1251] eta: 0:04:52 lr: 0.000620 loss: 3.3702 (3.3760) grad_norm: 1.2405 (1.2925) time: 0.4979 [2021-03-26 02:36:45 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 690/1251] eta: 0:04:47 lr: 0.000620 loss: 3.4953 (3.3784) grad_norm: 1.3486 (1.2942) time: 0.5062 [2021-03-26 02:36:50 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 700/1251] eta: 0:04:41 lr: 0.000620 loss: 3.6962 (3.3831) grad_norm: 1.2974 (1.2937) time: 0.5120 [2021-03-26 02:36:55 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 710/1251] eta: 0:04:36 lr: 0.000620 loss: 3.5994 (3.3806) grad_norm: 1.2333 (1.2941) time: 0.5073 [2021-03-26 02:37:00 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 720/1251] eta: 0:04:31 lr: 0.000620 loss: 3.4583 (3.3796) grad_norm: 1.2491 (1.2940) time: 0.5042 [2021-03-26 02:37:05 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 730/1251] eta: 0:04:26 lr: 0.000620 loss: 3.4583 (3.3811) grad_norm: 1.2884 (1.2949) time: 0.5027 [2021-03-26 02:37:11 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 740/1251] eta: 0:04:21 lr: 0.000620 loss: 3.5796 (3.3832) grad_norm: 1.2470 (1.2940) time: 0.5181 [2021-03-26 02:37:16 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 750/1251] eta: 0:04:16 lr: 0.000620 loss: 3.5333 (3.3851) grad_norm: 1.2470 (1.2938) time: 0.5229 [2021-03-26 02:37:21 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 760/1251] eta: 0:04:11 lr: 0.000620 loss: 3.4437 (3.3849) grad_norm: 1.2661 (1.2934) time: 0.5218 [2021-03-26 02:37:26 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 770/1251] eta: 0:04:06 lr: 0.000620 loss: 3.4437 (3.3880) grad_norm: 1.2458 (1.2933) time: 0.5218 [2021-03-26 02:37:31 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 780/1251] eta: 0:04:01 lr: 0.000620 loss: 3.0189 (3.3800) grad_norm: 1.2487 (1.2930) time: 0.5066 [2021-03-26 02:37:36 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 790/1251] eta: 0:03:55 lr: 0.000620 loss: 2.9338 (3.3787) grad_norm: 1.2340 (1.2923) time: 0.5072 [2021-03-26 02:37:41 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 800/1251] eta: 0:03:50 lr: 0.000620 loss: 3.2724 (3.3770) grad_norm: 1.2286 (1.2918) time: 0.5089 [2021-03-26 02:37:47 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 810/1251] eta: 0:03:45 lr: 0.000620 loss: 3.4252 (3.3791) grad_norm: 1.2478 (1.2915) time: 0.5099 [2021-03-26 02:37:52 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 820/1251] eta: 0:03:40 lr: 0.000620 loss: 3.4261 (3.3803) grad_norm: 1.3078 (1.2918) time: 0.5107 [2021-03-26 02:37:57 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 830/1251] eta: 0:03:35 lr: 0.000620 loss: 3.3845 (3.3789) grad_norm: 1.3183 (1.2927) time: 0.5025 [2021-03-26 02:38:02 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 840/1251] eta: 0:03:30 lr: 0.000620 loss: 3.4458 (3.3789) grad_norm: 1.3408 (1.2937) time: 0.5014 [2021-03-26 02:38:07 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 850/1251] eta: 0:03:25 lr: 0.000620 loss: 3.5485 (3.3805) grad_norm: 1.2250 (1.2926) time: 0.5054 [2021-03-26 02:38:12 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 860/1251] eta: 0:03:19 lr: 0.000620 loss: 3.5229 (3.3783) grad_norm: 1.2250 (1.2926) time: 0.5130 [2021-03-26 02:38:17 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 870/1251] eta: 0:03:14 lr: 0.000620 loss: 3.1904 (3.3740) grad_norm: 1.2658 (1.2926) time: 0.5149 [2021-03-26 02:38:22 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 880/1251] eta: 0:03:09 lr: 0.000620 loss: 3.2486 (3.3733) grad_norm: 1.2658 (1.2924) time: 0.5115 [2021-03-26 02:38:27 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 890/1251] eta: 0:03:04 lr: 0.000619 loss: 3.2486 (3.3720) grad_norm: 1.2611 (1.2921) time: 0.5044 [2021-03-26 02:38:32 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 900/1251] eta: 0:02:59 lr: 0.000619 loss: 3.3562 (3.3741) grad_norm: 1.2611 (1.2918) time: 0.4990 [2021-03-26 02:38:37 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 910/1251] eta: 0:02:54 lr: 0.000619 loss: 3.5343 (3.3753) grad_norm: 1.2314 (1.2914) time: 0.5060 [2021-03-26 02:38:42 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 920/1251] eta: 0:02:49 lr: 0.000619 loss: 3.5980 (3.3784) grad_norm: 1.2834 (1.2918) time: 0.5089 [2021-03-26 02:38:47 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 930/1251] eta: 0:02:44 lr: 0.000619 loss: 3.5687 (3.3770) grad_norm: 1.3246 (1.2916) time: 0.5051 [2021-03-26 02:38:52 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 940/1251] eta: 0:02:38 lr: 0.000619 loss: 3.3983 (3.3773) grad_norm: 1.2356 (1.2916) time: 0.5039 [2021-03-26 02:38:58 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 950/1251] eta: 0:02:33 lr: 0.000619 loss: 3.5723 (3.3787) grad_norm: 1.2356 (1.2916) time: 0.5076 [2021-03-26 02:39:02 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 960/1251] eta: 0:02:28 lr: 0.000619 loss: 3.5217 (3.3785) grad_norm: 1.2994 (1.2921) time: 0.5032 [2021-03-26 02:39:07 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 970/1251] eta: 0:02:23 lr: 0.000619 loss: 3.5111 (3.3794) grad_norm: 1.2661 (1.2917) time: 0.4986 [2021-03-26 02:39:13 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 980/1251] eta: 0:02:18 lr: 0.000619 loss: 3.5111 (3.3802) grad_norm: 1.2466 (1.2921) time: 0.5076 [2021-03-26 02:39:18 swin_small_patch4_window7_224] INFO: Epoch: [127] [ 990/1251] eta: 0:02:13 lr: 0.000619 loss: 3.4215 (3.3797) grad_norm: 1.2407 (1.2922) time: 0.5135 [2021-03-26 02:39:23 swin_small_patch4_window7_224] INFO: Epoch: [127] [1000/1251] eta: 0:02:08 lr: 0.000619 loss: 3.4334 (3.3796) grad_norm: 1.2837 (1.2924) time: 0.5088 [2021-03-26 02:39:28 swin_small_patch4_window7_224] INFO: Epoch: [127] [1010/1251] eta: 0:02:03 lr: 0.000619 loss: 3.4334 (3.3796) grad_norm: 1.2837 (1.2922) time: 0.5037 [2021-03-26 02:39:33 swin_small_patch4_window7_224] INFO: Epoch: [127] [1020/1251] eta: 0:01:57 lr: 0.000619 loss: 3.4509 (3.3791) grad_norm: 1.2551 (1.2923) time: 0.5018 [2021-03-26 02:39:38 swin_small_patch4_window7_224] INFO: Epoch: [127] [1030/1251] eta: 0:01:52 lr: 0.000619 loss: 3.4509 (3.3777) grad_norm: 1.2603 (1.2923) time: 0.5018 [2021-03-26 02:39:43 swin_small_patch4_window7_224] INFO: Epoch: [127] [1040/1251] eta: 0:01:47 lr: 0.000619 loss: 3.4654 (3.3758) grad_norm: 1.2294 (1.2915) time: 0.5061 [2021-03-26 02:39:48 swin_small_patch4_window7_224] INFO: Epoch: [127] [1050/1251] eta: 0:01:42 lr: 0.000619 loss: 3.5095 (3.3755) grad_norm: 1.2292 (1.2913) time: 0.5141 [2021-03-26 02:39:53 swin_small_patch4_window7_224] INFO: Epoch: [127] [1060/1251] eta: 0:01:37 lr: 0.000619 loss: 3.6267 (3.3762) grad_norm: 1.2904 (1.2921) time: 0.5087 [2021-03-26 02:39:58 swin_small_patch4_window7_224] INFO: Epoch: [127] [1070/1251] eta: 0:01:32 lr: 0.000619 loss: 3.5184 (3.3761) grad_norm: 1.2904 (1.2923) time: 0.5022 [2021-03-26 02:40:03 swin_small_patch4_window7_224] INFO: Epoch: [127] [1080/1251] eta: 0:01:27 lr: 0.000619 loss: 3.3806 (3.3755) grad_norm: 1.2247 (1.2924) time: 0.5068 [2021-03-26 02:40:08 swin_small_patch4_window7_224] INFO: Epoch: [127] [1090/1251] eta: 0:01:22 lr: 0.000619 loss: 3.3921 (3.3761) grad_norm: 1.2508 (nan) time: 0.5044 [2021-03-26 02:40:13 swin_small_patch4_window7_224] INFO: Epoch: [127] [1100/1251] eta: 0:01:17 lr: 0.000619 loss: 3.5710 (3.3772) grad_norm: 1.3037 (nan) time: 0.5003 [2021-03-26 02:40:18 swin_small_patch4_window7_224] INFO: Epoch: [127] [1110/1251] eta: 0:01:11 lr: 0.000619 loss: 3.5034 (3.3761) grad_norm: 1.2850 (nan) time: 0.5018 [2021-03-26 02:40:23 swin_small_patch4_window7_224] INFO: Epoch: [127] [1120/1251] eta: 0:01:06 lr: 0.000619 loss: 3.0860 (3.3740) grad_norm: 1.2898 (nan) time: 0.5083 [2021-03-26 02:40:28 swin_small_patch4_window7_224] INFO: Epoch: [127] [1130/1251] eta: 0:01:01 lr: 0.000619 loss: 3.2806 (3.3734) grad_norm: 1.3630 (nan) time: 0.5069 [2021-03-26 02:40:34 swin_small_patch4_window7_224] INFO: Epoch: [127] [1140/1251] eta: 0:00:56 lr: 0.000618 loss: 3.6002 (3.3751) grad_norm: 1.2986 (nan) time: 0.5035 [2021-03-26 02:40:39 swin_small_patch4_window7_224] INFO: Epoch: [127] [1150/1251] eta: 0:00:51 lr: 0.000618 loss: 3.3955 (3.3735) grad_norm: 1.2472 (nan) time: 0.5071 [2021-03-26 02:40:44 swin_small_patch4_window7_224] INFO: Epoch: [127] [1160/1251] eta: 0:00:46 lr: 0.000618 loss: 3.4539 (3.3744) grad_norm: 1.2837 (nan) time: 0.5051 [2021-03-26 02:40:49 swin_small_patch4_window7_224] INFO: Epoch: [127] [1170/1251] eta: 0:00:41 lr: 0.000618 loss: 3.4539 (3.3746) grad_norm: 1.2503 (nan) time: 0.4992 [2021-03-26 02:40:54 swin_small_patch4_window7_224] INFO: Epoch: [127] [1180/1251] eta: 0:00:36 lr: 0.000618 loss: 3.4025 (3.3757) grad_norm: 1.2388 (nan) time: 0.4972 [2021-03-26 02:40:59 swin_small_patch4_window7_224] INFO: Epoch: [127] [1190/1251] eta: 0:00:31 lr: 0.000618 loss: 3.4216 (3.3743) grad_norm: 1.2456 (nan) time: 0.4995 [2021-03-26 02:41:04 swin_small_patch4_window7_224] INFO: Epoch: [127] [1200/1251] eta: 0:00:25 lr: 0.000618 loss: 3.4943 (3.3759) grad_norm: 1.2611 (nan) time: 0.5058 [2021-03-26 02:41:09 swin_small_patch4_window7_224] INFO: Epoch: [127] [1210/1251] eta: 0:00:20 lr: 0.000618 loss: 3.5250 (3.3755) grad_norm: 1.2828 (nan) time: 0.5081 [2021-03-26 02:41:14 swin_small_patch4_window7_224] INFO: Epoch: [127] [1220/1251] eta: 0:00:15 lr: 0.000618 loss: 3.5452 (3.3763) grad_norm: 1.2862 (nan) time: 0.5068 [2021-03-26 02:41:19 swin_small_patch4_window7_224] INFO: Epoch: [127] [1230/1251] eta: 0:00:10 lr: 0.000618 loss: 3.5452 (3.3758) grad_norm: 1.2220 (nan) time: 0.5091 [2021-03-26 02:41:24 swin_small_patch4_window7_224] INFO: Epoch: [127] [1240/1251] eta: 0:00:05 lr: 0.000618 loss: 3.7097 (3.3775) grad_norm: 1.2220 (nan) time: 0.5054 [2021-03-26 02:41:29 swin_small_patch4_window7_224] INFO: Epoch: [127] [1250/1251] eta: 0:00:00 lr: 0.000618 loss: 3.4472 (3.3763) grad_norm: 1.2278 (nan) time: 0.5036 [2021-03-26 02:41:36 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:53 loss: 0.8344 (0.8344) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-26 02:41:39 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 1.1431 (1.0533) acc1: 75.0000 (73.7216) acc5: 93.7500 (93.3239) [2021-03-26 02:41:42 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 1.0207 (1.0300) acc1: 75.0000 (75.2232) acc5: 93.7500 (93.3036) [2021-03-26 02:41:44 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9338 (0.9967) acc1: 76.5625 (76.3105) acc5: 93.7500 (93.8508) [2021-03-26 02:41:46 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9338 (1.0008) acc1: 76.5625 (76.3338) acc5: 93.7500 (93.7119) [2021-03-26 02:41:47 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9762 (0.9871) acc1: 76.5625 (76.6400) acc5: 93.7500 (94.0160) [2021-03-26 02:41:53 swin_small_patch4_window7_224] INFO: * Acc@1 77.338 Acc@5 94.078 loss 0.960 [2021-03-26 02:41:53 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.3% [2021-03-26 02:41:53 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 02:41:57 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 0/1251] eta: 1:26:25 lr: 0.000618 loss: 3.1776 (3.1776) grad_norm: 1.2373 (1.2373) time: 4.1454 [2021-03-26 02:42:03 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 10/1251] eta: 0:17:27 lr: 0.000618 loss: 3.3750 (3.3510) grad_norm: 1.2043 (1.2174) time: 0.8440 [2021-03-26 02:42:08 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 20/1251] eta: 0:13:57 lr: 0.000618 loss: 3.4729 (3.4280) grad_norm: 1.2594 (1.2745) time: 0.5071 [2021-03-26 02:42:13 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 30/1251] eta: 0:12:41 lr: 0.000618 loss: 3.3517 (3.2428) grad_norm: 1.3280 (1.2872) time: 0.5025 [2021-03-26 02:42:18 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 40/1251] eta: 0:12:03 lr: 0.000618 loss: 3.1926 (3.3005) grad_norm: 1.2877 (1.2847) time: 0.5107 [2021-03-26 02:42:23 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 50/1251] eta: 0:11:36 lr: 0.000618 loss: 3.5374 (3.3371) grad_norm: 1.2692 (1.2815) time: 0.5114 [2021-03-26 02:42:28 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 60/1251] eta: 0:11:17 lr: 0.000618 loss: 3.5374 (3.3534) grad_norm: 1.2522 (1.2776) time: 0.5088 [2021-03-26 02:42:33 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 70/1251] eta: 0:11:03 lr: 0.000618 loss: 3.4243 (3.3636) grad_norm: 1.2556 (1.2785) time: 0.5167 [2021-03-26 02:42:38 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 80/1251] eta: 0:10:49 lr: 0.000618 loss: 3.4243 (3.3773) grad_norm: 1.2596 (1.2764) time: 0.5127 [2021-03-26 02:42:43 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 90/1251] eta: 0:10:37 lr: 0.000618 loss: 3.5592 (3.4013) grad_norm: 1.2684 (1.2806) time: 0.5044 [2021-03-26 02:42:48 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 100/1251] eta: 0:10:27 lr: 0.000618 loss: 3.6054 (3.4068) grad_norm: 1.2780 (1.2828) time: 0.5068 [2021-03-26 02:42:53 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 110/1251] eta: 0:10:17 lr: 0.000618 loss: 3.6054 (3.4078) grad_norm: 1.3325 (1.2827) time: 0.5030 [2021-03-26 02:42:58 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 120/1251] eta: 0:10:08 lr: 0.000618 loss: 3.7090 (3.4391) grad_norm: 1.2536 (1.2818) time: 0.5024 [2021-03-26 02:43:04 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 130/1251] eta: 0:10:01 lr: 0.000618 loss: 3.5614 (3.4164) grad_norm: 1.2914 (1.2840) time: 0.5106 [2021-03-26 02:43:08 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 140/1251] eta: 0:09:52 lr: 0.000617 loss: 3.3371 (3.4147) grad_norm: 1.3075 (1.2867) time: 0.5058 [2021-03-26 02:43:13 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 150/1251] eta: 0:09:44 lr: 0.000617 loss: 3.6282 (3.4178) grad_norm: 1.3593 (1.2912) time: 0.4983 [2021-03-26 02:43:19 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 160/1251] eta: 0:09:37 lr: 0.000617 loss: 3.6094 (3.4160) grad_norm: 1.2600 (1.2884) time: 0.5005 [2021-03-26 02:43:24 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 170/1251] eta: 0:09:32 lr: 0.000617 loss: 3.6094 (3.4242) grad_norm: 1.2503 (1.2884) time: 0.5139 [2021-03-26 02:43:29 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 180/1251] eta: 0:09:25 lr: 0.000617 loss: 3.6224 (3.4175) grad_norm: 1.2621 (1.2872) time: 0.5165 [2021-03-26 02:43:34 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 190/1251] eta: 0:09:18 lr: 0.000617 loss: 3.6224 (3.4290) grad_norm: 1.2221 (1.2869) time: 0.5022 [2021-03-26 02:43:39 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 200/1251] eta: 0:09:12 lr: 0.000617 loss: 3.6344 (3.4295) grad_norm: 1.2221 (1.2857) time: 0.5046 [2021-03-26 02:43:44 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 210/1251] eta: 0:09:06 lr: 0.000617 loss: 3.3593 (3.4263) grad_norm: 1.2607 (1.2842) time: 0.5090 [2021-03-26 02:43:49 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 220/1251] eta: 0:09:00 lr: 0.000617 loss: 3.4835 (3.4244) grad_norm: 1.3110 (1.2865) time: 0.5050 [2021-03-26 02:43:54 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 230/1251] eta: 0:08:54 lr: 0.000617 loss: 3.4005 (3.4239) grad_norm: 1.2889 (1.2879) time: 0.5076 [2021-03-26 02:43:59 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 240/1251] eta: 0:08:48 lr: 0.000617 loss: 3.3088 (3.4171) grad_norm: 1.2889 (1.2883) time: 0.5112 [2021-03-26 02:44:04 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 250/1251] eta: 0:08:42 lr: 0.000617 loss: 3.3140 (3.4107) grad_norm: 1.2649 (1.2871) time: 0.5059 [2021-03-26 02:44:09 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 260/1251] eta: 0:08:37 lr: 0.000617 loss: 3.3147 (3.4074) grad_norm: 1.2649 (1.2875) time: 0.5090 [2021-03-26 02:44:15 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 270/1251] eta: 0:08:31 lr: 0.000617 loss: 3.4507 (3.4104) grad_norm: 1.3182 (1.2912) time: 0.5167 [2021-03-26 02:44:20 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 280/1251] eta: 0:08:25 lr: 0.000617 loss: 3.5679 (3.4035) grad_norm: 1.3550 (1.2932) time: 0.5129 [2021-03-26 02:44:25 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 290/1251] eta: 0:08:20 lr: 0.000617 loss: 3.5081 (3.4024) grad_norm: 1.3064 (1.2945) time: 0.5078 [2021-03-26 02:44:30 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 300/1251] eta: 0:08:14 lr: 0.000617 loss: 3.3497 (3.3978) grad_norm: 1.2903 (1.2948) time: 0.5061 [2021-03-26 02:44:35 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 310/1251] eta: 0:08:08 lr: 0.000617 loss: 3.3133 (3.3943) grad_norm: 1.3049 (1.2950) time: 0.5007 [2021-03-26 02:44:40 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 320/1251] eta: 0:08:03 lr: 0.000617 loss: 3.2004 (3.3895) grad_norm: 1.2773 (1.2936) time: 0.5053 [2021-03-26 02:44:45 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 330/1251] eta: 0:07:57 lr: 0.000617 loss: 3.3750 (3.3932) grad_norm: 1.2280 (1.2910) time: 0.5079 [2021-03-26 02:44:50 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 340/1251] eta: 0:07:52 lr: 0.000617 loss: 3.4072 (3.3911) grad_norm: 1.2317 (1.2914) time: 0.5065 [2021-03-26 02:44:55 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 350/1251] eta: 0:07:46 lr: 0.000617 loss: 3.4072 (3.3854) grad_norm: 1.2967 (1.2917) time: 0.5072 [2021-03-26 02:45:00 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 360/1251] eta: 0:07:41 lr: 0.000617 loss: 3.5239 (3.3908) grad_norm: 1.2861 (1.2907) time: 0.5045 [2021-03-26 02:45:05 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 370/1251] eta: 0:07:35 lr: 0.000617 loss: 3.7150 (3.3963) grad_norm: 1.2585 (1.2907) time: 0.5063 [2021-03-26 02:45:10 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 380/1251] eta: 0:07:30 lr: 0.000617 loss: 3.5761 (3.3923) grad_norm: 1.2579 (1.2892) time: 0.5036 [2021-03-26 02:45:15 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 390/1251] eta: 0:07:24 lr: 0.000616 loss: 3.5761 (3.3939) grad_norm: 1.2712 (1.2896) time: 0.5018 [2021-03-26 02:45:20 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 400/1251] eta: 0:07:19 lr: 0.000616 loss: 3.5016 (3.3957) grad_norm: 1.3147 (1.2906) time: 0.5041 [2021-03-26 02:45:25 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 410/1251] eta: 0:07:13 lr: 0.000616 loss: 3.4765 (3.3917) grad_norm: 1.2514 (1.2890) time: 0.5055 [2021-03-26 02:45:31 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 420/1251] eta: 0:07:08 lr: 0.000616 loss: 3.4783 (3.3928) grad_norm: 1.3105 (1.2902) time: 0.5115 [2021-03-26 02:45:36 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 430/1251] eta: 0:07:03 lr: 0.000616 loss: 3.6249 (3.3943) grad_norm: 1.3135 (1.2890) time: 0.5129 [2021-03-26 02:45:41 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 440/1251] eta: 0:06:57 lr: 0.000616 loss: 3.4958 (3.3914) grad_norm: 1.2179 (1.2879) time: 0.5009 [2021-03-26 02:45:46 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 450/1251] eta: 0:06:52 lr: 0.000616 loss: 3.4191 (3.3858) grad_norm: 1.2774 (1.2913) time: 0.4970 [2021-03-26 02:45:51 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 460/1251] eta: 0:06:47 lr: 0.000616 loss: 3.5358 (3.3916) grad_norm: 1.3201 (1.2920) time: 0.5022 [2021-03-26 02:45:56 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 470/1251] eta: 0:06:41 lr: 0.000616 loss: 3.6489 (3.3940) grad_norm: 1.2813 (1.2921) time: 0.5057 [2021-03-26 02:46:01 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 480/1251] eta: 0:06:36 lr: 0.000616 loss: 3.5051 (3.3945) grad_norm: 1.3116 (1.2943) time: 0.5063 [2021-03-26 02:46:06 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 490/1251] eta: 0:06:31 lr: 0.000616 loss: 3.3837 (3.3911) grad_norm: 1.2666 (1.2939) time: 0.5053 [2021-03-26 02:46:11 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 500/1251] eta: 0:06:26 lr: 0.000616 loss: 3.4332 (3.3932) grad_norm: 1.2301 (1.2935) time: 0.5063 [2021-03-26 02:46:16 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 510/1251] eta: 0:06:20 lr: 0.000616 loss: 3.4332 (3.3861) grad_norm: 1.2200 (1.2920) time: 0.5035 [2021-03-26 02:46:21 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 520/1251] eta: 0:06:15 lr: 0.000616 loss: 3.1679 (3.3831) grad_norm: 1.2084 (1.2925) time: 0.4996 [2021-03-26 02:46:26 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 530/1251] eta: 0:06:10 lr: 0.000616 loss: 3.3640 (3.3843) grad_norm: 1.2713 (1.2922) time: 0.5079 [2021-03-26 02:46:31 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 540/1251] eta: 0:06:05 lr: 0.000616 loss: 3.5010 (3.3871) grad_norm: 1.2609 (1.2916) time: 0.5180 [2021-03-26 02:46:37 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 550/1251] eta: 0:06:00 lr: 0.000616 loss: 3.6169 (3.3910) grad_norm: 1.2579 (1.2925) time: 0.5250 [2021-03-26 02:46:42 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 560/1251] eta: 0:05:55 lr: 0.000616 loss: 3.3970 (3.3863) grad_norm: 1.2646 (1.2923) time: 0.5214 [2021-03-26 02:46:47 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 570/1251] eta: 0:05:49 lr: 0.000616 loss: 3.3328 (3.3852) grad_norm: 1.2559 (1.2919) time: 0.5121 [2021-03-26 02:46:52 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 580/1251] eta: 0:05:44 lr: 0.000616 loss: 3.4727 (3.3832) grad_norm: 1.3180 (1.2932) time: 0.5058 [2021-03-26 02:46:57 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 590/1251] eta: 0:05:39 lr: 0.000616 loss: 3.3697 (3.3836) grad_norm: 1.3531 (1.2931) time: 0.5084 [2021-03-26 02:47:02 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 600/1251] eta: 0:05:34 lr: 0.000616 loss: 3.3412 (3.3831) grad_norm: 1.2988 (1.2939) time: 0.5079 [2021-03-26 02:47:07 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 610/1251] eta: 0:05:29 lr: 0.000616 loss: 3.3769 (3.3852) grad_norm: 1.2901 (1.2930) time: 0.5059 [2021-03-26 02:47:12 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 620/1251] eta: 0:05:23 lr: 0.000616 loss: 3.4279 (3.3829) grad_norm: 1.1950 (1.2928) time: 0.5040 [2021-03-26 02:47:17 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 630/1251] eta: 0:05:18 lr: 0.000615 loss: 3.3664 (3.3802) grad_norm: 1.1965 (1.2924) time: 0.4984 [2021-03-26 02:47:22 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 640/1251] eta: 0:05:13 lr: 0.000615 loss: 3.3275 (3.3793) grad_norm: 1.2424 (1.2925) time: 0.5016 [2021-03-26 02:47:27 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 650/1251] eta: 0:05:08 lr: 0.000615 loss: 3.3275 (3.3787) grad_norm: 1.2661 (1.2924) time: 0.4999 [2021-03-26 02:47:32 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 660/1251] eta: 0:05:02 lr: 0.000615 loss: 3.5006 (3.3781) grad_norm: 1.2610 (1.2922) time: 0.5020 [2021-03-26 02:47:37 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 670/1251] eta: 0:04:57 lr: 0.000615 loss: 3.3308 (3.3758) grad_norm: 1.2575 (1.2924) time: 0.5071 [2021-03-26 02:47:42 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 680/1251] eta: 0:04:52 lr: 0.000615 loss: 3.1950 (3.3718) grad_norm: 1.2653 (1.2924) time: 0.5030 [2021-03-26 02:47:47 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 690/1251] eta: 0:04:47 lr: 0.000615 loss: 3.3151 (3.3751) grad_norm: 1.2356 (1.2922) time: 0.5003 [2021-03-26 02:47:52 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 700/1251] eta: 0:04:42 lr: 0.000615 loss: 3.6587 (3.3767) grad_norm: 1.2356 (1.2916) time: 0.5017 [2021-03-26 02:47:57 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 710/1251] eta: 0:04:36 lr: 0.000615 loss: 3.4944 (3.3753) grad_norm: 1.2419 (1.2912) time: 0.5010 [2021-03-26 02:48:02 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 720/1251] eta: 0:04:31 lr: 0.000615 loss: 3.4944 (3.3792) grad_norm: 1.2860 (1.2915) time: 0.5077 [2021-03-26 02:48:08 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 730/1251] eta: 0:04:26 lr: 0.000615 loss: 3.5065 (3.3779) grad_norm: 1.3519 (1.2931) time: 0.5141 [2021-03-26 02:48:13 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 740/1251] eta: 0:04:21 lr: 0.000615 loss: 3.2184 (3.3749) grad_norm: 1.2702 (1.2925) time: 0.5160 [2021-03-26 02:48:18 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 750/1251] eta: 0:04:16 lr: 0.000615 loss: 3.2927 (3.3775) grad_norm: 1.2636 (1.2931) time: 0.5178 [2021-03-26 02:48:23 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 760/1251] eta: 0:04:11 lr: 0.000615 loss: 3.3816 (3.3763) grad_norm: 1.2987 (1.2933) time: 0.5085 [2021-03-26 02:48:28 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 770/1251] eta: 0:04:06 lr: 0.000615 loss: 3.3816 (3.3772) grad_norm: 1.2815 (1.2929) time: 0.4995 [2021-03-26 02:48:33 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 780/1251] eta: 0:04:01 lr: 0.000615 loss: 3.2288 (3.3705) grad_norm: 1.2296 (1.2928) time: 0.5065 [2021-03-26 02:48:38 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 790/1251] eta: 0:03:55 lr: 0.000615 loss: 3.5076 (3.3748) grad_norm: 1.2921 (1.2940) time: 0.5079 [2021-03-26 02:48:43 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 800/1251] eta: 0:03:50 lr: 0.000615 loss: 3.6935 (3.3755) grad_norm: 1.2921 (1.2940) time: 0.5092 [2021-03-26 02:48:48 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 810/1251] eta: 0:03:45 lr: 0.000615 loss: 3.4570 (3.3758) grad_norm: 1.2103 (1.2940) time: 0.5137 [2021-03-26 02:48:53 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 820/1251] eta: 0:03:40 lr: 0.000615 loss: 3.4092 (3.3752) grad_norm: 1.2098 (1.2942) time: 0.5104 [2021-03-26 02:48:58 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 830/1251] eta: 0:03:35 lr: 0.000615 loss: 3.4730 (3.3775) grad_norm: 1.2862 (1.2944) time: 0.5091 [2021-03-26 02:49:03 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 840/1251] eta: 0:03:30 lr: 0.000615 loss: 3.3435 (3.3751) grad_norm: 1.2704 (1.2941) time: 0.5051 [2021-03-26 02:49:09 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 850/1251] eta: 0:03:25 lr: 0.000615 loss: 3.4590 (3.3767) grad_norm: 1.2189 (1.2937) time: 0.5042 [2021-03-26 02:49:14 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 860/1251] eta: 0:03:19 lr: 0.000615 loss: 3.5027 (3.3788) grad_norm: 1.2037 (1.2932) time: 0.5081 [2021-03-26 02:49:19 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 870/1251] eta: 0:03:14 lr: 0.000615 loss: 3.5730 (3.3771) grad_norm: 1.2037 (1.2931) time: 0.5056 [2021-03-26 02:49:24 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 880/1251] eta: 0:03:09 lr: 0.000614 loss: 3.5730 (3.3787) grad_norm: 1.1983 (1.2930) time: 0.5105 [2021-03-26 02:49:29 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 890/1251] eta: 0:03:04 lr: 0.000614 loss: 3.4151 (3.3757) grad_norm: 1.2582 (1.2933) time: 0.5113 [2021-03-26 02:49:34 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 900/1251] eta: 0:02:59 lr: 0.000614 loss: 3.0858 (3.3743) grad_norm: 1.2565 (1.2928) time: 0.5043 [2021-03-26 02:49:39 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 910/1251] eta: 0:02:54 lr: 0.000614 loss: 3.5729 (3.3769) grad_norm: 1.2401 (1.2935) time: 0.5068 [2021-03-26 02:49:44 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 920/1251] eta: 0:02:49 lr: 0.000614 loss: 3.4348 (3.3745) grad_norm: 1.2487 (1.2932) time: 0.5118 [2021-03-26 02:49:49 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 930/1251] eta: 0:02:44 lr: 0.000614 loss: 3.3542 (3.3763) grad_norm: 1.2715 (1.2934) time: 0.5119 [2021-03-26 02:49:54 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 940/1251] eta: 0:02:38 lr: 0.000614 loss: 3.5353 (3.3784) grad_norm: 1.2594 (1.2930) time: 0.5116 [2021-03-26 02:49:59 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 950/1251] eta: 0:02:33 lr: 0.000614 loss: 3.4905 (3.3778) grad_norm: 1.2155 (1.2920) time: 0.5097 [2021-03-26 02:50:04 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 960/1251] eta: 0:02:28 lr: 0.000614 loss: 3.3475 (3.3763) grad_norm: 1.2570 (1.2929) time: 0.5026 [2021-03-26 02:50:10 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 970/1251] eta: 0:02:23 lr: 0.000614 loss: 3.4441 (3.3778) grad_norm: 1.3442 (1.2933) time: 0.5031 [2021-03-26 02:50:15 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 980/1251] eta: 0:02:18 lr: 0.000614 loss: 3.6374 (3.3806) grad_norm: 1.3237 (1.2931) time: 0.5082 [2021-03-26 02:50:20 swin_small_patch4_window7_224] INFO: Epoch: [128] [ 990/1251] eta: 0:02:13 lr: 0.000614 loss: 3.5918 (3.3814) grad_norm: 1.2067 (1.2931) time: 0.5126 [2021-03-26 02:50:25 swin_small_patch4_window7_224] INFO: Epoch: [128] [1000/1251] eta: 0:02:08 lr: 0.000614 loss: 3.5596 (3.3828) grad_norm: 1.2957 (1.2934) time: 0.5156 [2021-03-26 02:50:30 swin_small_patch4_window7_224] INFO: Epoch: [128] [1010/1251] eta: 0:02:03 lr: 0.000614 loss: 3.5596 (3.3856) grad_norm: 1.2665 (1.2931) time: 0.5165 [2021-03-26 02:50:35 swin_small_patch4_window7_224] INFO: Epoch: [128] [1020/1251] eta: 0:01:58 lr: 0.000614 loss: 3.4358 (3.3849) grad_norm: 1.2375 (1.2925) time: 0.5107 [2021-03-26 02:50:40 swin_small_patch4_window7_224] INFO: Epoch: [128] [1030/1251] eta: 0:01:52 lr: 0.000614 loss: 3.0854 (3.3827) grad_norm: 1.2128 (1.2915) time: 0.5076 [2021-03-26 02:50:45 swin_small_patch4_window7_224] INFO: Epoch: [128] [1040/1251] eta: 0:01:47 lr: 0.000614 loss: 3.4826 (3.3833) grad_norm: 1.2415 (1.2920) time: 0.5092 [2021-03-26 02:50:50 swin_small_patch4_window7_224] INFO: Epoch: [128] [1050/1251] eta: 0:01:42 lr: 0.000614 loss: 3.4826 (3.3817) grad_norm: 1.2680 (1.2914) time: 0.5078 [2021-03-26 02:50:56 swin_small_patch4_window7_224] INFO: Epoch: [128] [1060/1251] eta: 0:01:37 lr: 0.000614 loss: 3.3604 (3.3812) grad_norm: 1.2189 (1.2906) time: 0.5080 [2021-03-26 02:51:01 swin_small_patch4_window7_224] INFO: Epoch: [128] [1070/1251] eta: 0:01:32 lr: 0.000614 loss: 3.7318 (3.3841) grad_norm: 1.2154 (1.2898) time: 0.5099 [2021-03-26 02:51:06 swin_small_patch4_window7_224] INFO: Epoch: [128] [1080/1251] eta: 0:01:27 lr: 0.000614 loss: 3.6013 (3.3809) grad_norm: 1.2175 (1.2897) time: 0.5084 [2021-03-26 02:51:11 swin_small_patch4_window7_224] INFO: Epoch: [128] [1090/1251] eta: 0:01:22 lr: 0.000614 loss: 3.3357 (3.3806) grad_norm: 1.2728 (1.2904) time: 0.5033 [2021-03-26 02:51:16 swin_small_patch4_window7_224] INFO: Epoch: [128] [1100/1251] eta: 0:01:17 lr: 0.000614 loss: 3.5502 (3.3828) grad_norm: 1.3458 (1.2912) time: 0.5017 [2021-03-26 02:51:21 swin_small_patch4_window7_224] INFO: Epoch: [128] [1110/1251] eta: 0:01:12 lr: 0.000614 loss: 3.5502 (3.3834) grad_norm: 1.3359 (1.2910) time: 0.5049 [2021-03-26 02:51:26 swin_small_patch4_window7_224] INFO: Epoch: [128] [1120/1251] eta: 0:01:06 lr: 0.000614 loss: 3.3186 (3.3805) grad_norm: 1.2509 (1.2911) time: 0.5048 [2021-03-26 02:51:31 swin_small_patch4_window7_224] INFO: Epoch: [128] [1130/1251] eta: 0:01:01 lr: 0.000613 loss: 3.4648 (3.3813) grad_norm: 1.2643 (1.2911) time: 0.4999 [2021-03-26 02:51:36 swin_small_patch4_window7_224] INFO: Epoch: [128] [1140/1251] eta: 0:00:56 lr: 0.000613 loss: 3.3720 (3.3793) grad_norm: 1.3106 (1.2912) time: 0.5058 [2021-03-26 02:51:41 swin_small_patch4_window7_224] INFO: Epoch: [128] [1150/1251] eta: 0:00:51 lr: 0.000613 loss: 3.4231 (3.3805) grad_norm: 1.2511 (1.2907) time: 0.5092 [2021-03-26 02:51:46 swin_small_patch4_window7_224] INFO: Epoch: [128] [1160/1251] eta: 0:00:46 lr: 0.000613 loss: 3.8093 (3.3839) grad_norm: 1.2485 (1.2915) time: 0.5086 [2021-03-26 02:51:51 swin_small_patch4_window7_224] INFO: Epoch: [128] [1170/1251] eta: 0:00:41 lr: 0.000613 loss: 3.4644 (3.3829) grad_norm: 1.2433 (1.2909) time: 0.5061 [2021-03-26 02:51:56 swin_small_patch4_window7_224] INFO: Epoch: [128] [1180/1251] eta: 0:00:36 lr: 0.000613 loss: 3.2145 (3.3802) grad_norm: 1.2642 (1.2909) time: 0.5076 [2021-03-26 02:52:01 swin_small_patch4_window7_224] INFO: Epoch: [128] [1190/1251] eta: 0:00:31 lr: 0.000613 loss: 3.1932 (3.3790) grad_norm: 1.3070 (1.2916) time: 0.5100 [2021-03-26 02:52:06 swin_small_patch4_window7_224] INFO: Epoch: [128] [1200/1251] eta: 0:00:26 lr: 0.000613 loss: 3.5326 (3.3799) grad_norm: 1.3063 (1.2914) time: 0.5041 [2021-03-26 02:52:11 swin_small_patch4_window7_224] INFO: Epoch: [128] [1210/1251] eta: 0:00:20 lr: 0.000613 loss: 3.6149 (3.3806) grad_norm: 1.2710 (1.2912) time: 0.5048 [2021-03-26 02:52:16 swin_small_patch4_window7_224] INFO: Epoch: [128] [1220/1251] eta: 0:00:15 lr: 0.000613 loss: 3.6296 (3.3815) grad_norm: 1.2729 (1.2915) time: 0.5046 [2021-03-26 02:52:21 swin_small_patch4_window7_224] INFO: Epoch: [128] [1230/1251] eta: 0:00:10 lr: 0.000613 loss: 3.4703 (3.3813) grad_norm: 1.2729 (1.2919) time: 0.5005 [2021-03-26 02:52:26 swin_small_patch4_window7_224] INFO: Epoch: [128] [1240/1251] eta: 0:00:05 lr: 0.000613 loss: 3.2839 (3.3783) grad_norm: 1.2764 (1.2926) time: 0.4983 [2021-03-26 02:52:31 swin_small_patch4_window7_224] INFO: Epoch: [128] [1250/1251] eta: 0:00:00 lr: 0.000613 loss: 3.2839 (3.3792) grad_norm: 1.2764 (1.2925) time: 0.4926 [2021-03-26 02:52:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 0.5691 (0.5691) acc1: 90.6250 (90.6250) acc5: 98.4375 (98.4375) [2021-03-26 02:52:40 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9227 (1.0268) acc1: 76.5625 (76.2784) acc5: 93.7500 (93.6080) [2021-03-26 02:52:42 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 1.0188 (1.0258) acc1: 75.0000 (75.3720) acc5: 93.7500 (93.7500) [2021-03-26 02:52:45 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0188 (1.0146) acc1: 75.0000 (76.2601) acc5: 93.7500 (93.8004) [2021-03-26 02:52:46 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9530 (0.9922) acc1: 78.1250 (76.4482) acc5: 93.7500 (94.0168) [2021-03-26 02:52:47 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9271 (0.9639) acc1: 78.1250 (76.9920) acc5: 93.7500 (94.2400) [2021-03-26 02:52:52 swin_small_patch4_window7_224] INFO: * Acc@1 77.470 Acc@5 94.118 loss 0.943 [2021-03-26 02:52:52 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.5% [2021-03-26 02:52:52 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 02:52:56 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 0/1251] eta: 1:25:40 lr: 0.000613 loss: 4.2492 (4.2492) grad_norm: 1.1560 (1.1560) time: 4.1087 [2021-03-26 02:53:02 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 10/1251] eta: 0:17:51 lr: 0.000613 loss: 3.5856 (3.5487) grad_norm: 1.1883 (1.2415) time: 0.8636 [2021-03-26 02:53:07 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 20/1251] eta: 0:14:15 lr: 0.000613 loss: 3.4577 (3.5207) grad_norm: 1.2012 (1.2536) time: 0.5239 [2021-03-26 02:53:12 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 30/1251] eta: 0:12:55 lr: 0.000613 loss: 3.4577 (3.4924) grad_norm: 1.2543 (1.2540) time: 0.5089 [2021-03-26 02:53:17 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 40/1251] eta: 0:12:17 lr: 0.000613 loss: 3.2998 (3.4437) grad_norm: 1.2639 (1.2619) time: 0.5196 [2021-03-26 02:53:22 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 50/1251] eta: 0:11:48 lr: 0.000613 loss: 3.2348 (3.3752) grad_norm: 1.2580 (1.2605) time: 0.5201 [2021-03-26 02:53:27 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 60/1251] eta: 0:11:25 lr: 0.000613 loss: 3.1287 (3.3472) grad_norm: 1.2423 (1.2588) time: 0.5075 [2021-03-26 02:53:32 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 70/1251] eta: 0:11:09 lr: 0.000613 loss: 3.3698 (3.3605) grad_norm: 1.2668 (1.2721) time: 0.5074 [2021-03-26 02:53:37 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 80/1251] eta: 0:10:55 lr: 0.000613 loss: 3.5006 (3.3540) grad_norm: 1.3769 (1.2870) time: 0.5117 [2021-03-26 02:53:43 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 90/1251] eta: 0:10:43 lr: 0.000613 loss: 3.4234 (3.3556) grad_norm: 1.4075 (1.2995) time: 0.5119 [2021-03-26 02:53:48 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 100/1251] eta: 0:10:31 lr: 0.000613 loss: 3.4234 (3.3561) grad_norm: 1.3403 (1.3062) time: 0.5045 [2021-03-26 02:53:53 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 110/1251] eta: 0:10:21 lr: 0.000613 loss: 3.4085 (3.3595) grad_norm: 1.2249 (1.2991) time: 0.4993 [2021-03-26 02:53:58 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 120/1251] eta: 0:10:12 lr: 0.000612 loss: 3.4485 (3.3721) grad_norm: 1.2185 (1.2954) time: 0.5038 [2021-03-26 02:54:03 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 130/1251] eta: 0:10:04 lr: 0.000612 loss: 3.4089 (3.3628) grad_norm: 1.2887 (1.2959) time: 0.5088 [2021-03-26 02:54:08 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 140/1251] eta: 0:09:56 lr: 0.000612 loss: 3.4089 (3.3609) grad_norm: 1.3019 (1.2979) time: 0.5062 [2021-03-26 02:54:13 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 150/1251] eta: 0:09:47 lr: 0.000612 loss: 3.6267 (3.3628) grad_norm: 1.2301 (1.2926) time: 0.4969 [2021-03-26 02:54:18 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 160/1251] eta: 0:09:40 lr: 0.000612 loss: 3.3133 (3.3667) grad_norm: 1.2817 (1.2997) time: 0.4997 [2021-03-26 02:54:23 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 170/1251] eta: 0:09:33 lr: 0.000612 loss: 3.4768 (3.3740) grad_norm: 1.3149 (1.2975) time: 0.5066 [2021-03-26 02:54:28 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 180/1251] eta: 0:09:26 lr: 0.000612 loss: 3.6142 (3.3787) grad_norm: 1.3005 (1.3023) time: 0.5086 [2021-03-26 02:54:33 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 190/1251] eta: 0:09:20 lr: 0.000612 loss: 3.5519 (3.3786) grad_norm: 1.2424 (1.2972) time: 0.5123 [2021-03-26 02:54:38 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 200/1251] eta: 0:09:15 lr: 0.000612 loss: 3.5519 (3.3805) grad_norm: 1.2404 (1.3015) time: 0.5169 [2021-03-26 02:54:43 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 210/1251] eta: 0:09:09 lr: 0.000612 loss: 3.6011 (3.3840) grad_norm: 1.2826 (1.3008) time: 0.5170 [2021-03-26 02:54:48 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 220/1251] eta: 0:09:02 lr: 0.000612 loss: 3.6728 (3.3944) grad_norm: 1.2313 (1.2987) time: 0.5066 [2021-03-26 02:54:54 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 230/1251] eta: 0:08:56 lr: 0.000612 loss: 3.6728 (3.4017) grad_norm: 1.2220 (1.2956) time: 0.5034 [2021-03-26 02:54:59 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 240/1251] eta: 0:08:50 lr: 0.000612 loss: 3.4731 (3.3993) grad_norm: 1.2465 (1.2962) time: 0.5040 [2021-03-26 02:55:04 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 250/1251] eta: 0:08:43 lr: 0.000612 loss: 3.4464 (3.3996) grad_norm: 1.2629 (1.2974) time: 0.5007 [2021-03-26 02:55:09 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 260/1251] eta: 0:08:37 lr: 0.000612 loss: 3.3757 (3.4033) grad_norm: 1.2502 (1.2977) time: 0.4999 [2021-03-26 02:55:14 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 270/1251] eta: 0:08:31 lr: 0.000612 loss: 3.4676 (3.4060) grad_norm: 1.2708 (1.2985) time: 0.5035 [2021-03-26 02:55:19 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 280/1251] eta: 0:08:26 lr: 0.000612 loss: 3.4737 (3.4048) grad_norm: 1.2963 (1.2988) time: 0.5047 [2021-03-26 02:55:24 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 290/1251] eta: 0:08:20 lr: 0.000612 loss: 3.4457 (3.4007) grad_norm: 1.3052 (1.3004) time: 0.5037 [2021-03-26 02:55:29 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 300/1251] eta: 0:08:14 lr: 0.000612 loss: 3.3874 (3.4026) grad_norm: 1.3201 (1.3012) time: 0.5031 [2021-03-26 02:55:34 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 310/1251] eta: 0:08:08 lr: 0.000612 loss: 3.3874 (3.3991) grad_norm: 1.3076 (1.3014) time: 0.5032 [2021-03-26 02:55:39 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 320/1251] eta: 0:08:03 lr: 0.000612 loss: 3.3681 (3.4008) grad_norm: 1.2833 (1.2989) time: 0.5043 [2021-03-26 02:55:44 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 330/1251] eta: 0:07:57 lr: 0.000612 loss: 3.6373 (3.4088) grad_norm: 1.2678 (1.2989) time: 0.5051 [2021-03-26 02:55:49 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 340/1251] eta: 0:07:51 lr: 0.000612 loss: 3.5862 (3.4095) grad_norm: 1.2678 (1.2972) time: 0.4993 [2021-03-26 02:55:54 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 350/1251] eta: 0:07:46 lr: 0.000612 loss: 3.4655 (3.4070) grad_norm: 1.2588 (1.2979) time: 0.4983 [2021-03-26 02:55:59 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 360/1251] eta: 0:07:40 lr: 0.000612 loss: 3.3900 (3.4091) grad_norm: 1.2447 (1.2959) time: 0.4998 [2021-03-26 02:56:04 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 370/1251] eta: 0:07:35 lr: 0.000611 loss: 3.7137 (3.4141) grad_norm: 1.2588 (1.2973) time: 0.5017 [2021-03-26 02:56:09 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 380/1251] eta: 0:07:29 lr: 0.000611 loss: 3.7167 (3.4159) grad_norm: 1.2912 (1.2958) time: 0.5052 [2021-03-26 02:56:14 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 390/1251] eta: 0:07:24 lr: 0.000611 loss: 3.5667 (3.4171) grad_norm: 1.2912 (1.2964) time: 0.5064 [2021-03-26 02:56:19 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 400/1251] eta: 0:07:18 lr: 0.000611 loss: 3.5892 (3.4189) grad_norm: 1.3172 (1.2961) time: 0.5051 [2021-03-26 02:56:24 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 410/1251] eta: 0:07:13 lr: 0.000611 loss: 3.4538 (3.4179) grad_norm: 1.2978 (1.2970) time: 0.5016 [2021-03-26 02:56:29 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 420/1251] eta: 0:07:08 lr: 0.000611 loss: 3.3116 (3.4181) grad_norm: 1.2660 (1.2953) time: 0.5029 [2021-03-26 02:56:34 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 430/1251] eta: 0:07:02 lr: 0.000611 loss: 3.3898 (3.4175) grad_norm: 1.2146 (1.2949) time: 0.5043 [2021-03-26 02:56:39 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 440/1251] eta: 0:06:57 lr: 0.000611 loss: 3.6127 (3.4229) grad_norm: 1.2760 (1.2959) time: 0.5024 [2021-03-26 02:56:44 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 450/1251] eta: 0:06:51 lr: 0.000611 loss: 3.6246 (3.4152) grad_norm: 1.2760 (1.2964) time: 0.4997 [2021-03-26 02:56:49 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 460/1251] eta: 0:06:46 lr: 0.000611 loss: 3.2611 (3.4153) grad_norm: 1.3219 (1.2980) time: 0.4990 [2021-03-26 02:56:54 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 470/1251] eta: 0:06:41 lr: 0.000611 loss: 3.5856 (3.4161) grad_norm: 1.2686 (1.2967) time: 0.4974 [2021-03-26 02:56:59 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 480/1251] eta: 0:06:35 lr: 0.000611 loss: 3.6402 (3.4194) grad_norm: 1.2686 (1.2980) time: 0.4967 [2021-03-26 02:57:04 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 490/1251] eta: 0:06:30 lr: 0.000611 loss: 3.4920 (3.4165) grad_norm: 1.3208 (1.2986) time: 0.4974 [2021-03-26 02:57:09 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 500/1251] eta: 0:06:24 lr: 0.000611 loss: 3.4910 (3.4166) grad_norm: 1.3279 (1.2994) time: 0.4968 [2021-03-26 02:57:14 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 510/1251] eta: 0:06:19 lr: 0.000611 loss: 3.4445 (3.4128) grad_norm: 1.3201 (1.3008) time: 0.4962 [2021-03-26 02:57:19 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 520/1251] eta: 0:06:14 lr: 0.000611 loss: 3.4413 (3.4141) grad_norm: 1.2819 (1.2999) time: 0.5012 [2021-03-26 02:57:24 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 530/1251] eta: 0:06:08 lr: 0.000611 loss: 3.4413 (3.4107) grad_norm: 1.1907 (1.2988) time: 0.5011 [2021-03-26 02:57:29 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 540/1251] eta: 0:06:04 lr: 0.000611 loss: 3.2963 (3.4086) grad_norm: 1.1907 (1.2976) time: 0.5171 [2021-03-26 02:57:35 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 550/1251] eta: 0:05:59 lr: 0.000611 loss: 3.2614 (3.4049) grad_norm: 1.2577 (1.2981) time: 0.5295 [2021-03-26 02:57:40 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 560/1251] eta: 0:05:54 lr: 0.000611 loss: 3.5986 (3.4093) grad_norm: 1.2744 (1.2973) time: 0.5182 [2021-03-26 02:57:45 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 570/1251] eta: 0:05:48 lr: 0.000611 loss: 3.6586 (3.4113) grad_norm: 1.2442 (1.2972) time: 0.5120 [2021-03-26 02:57:50 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 580/1251] eta: 0:05:43 lr: 0.000611 loss: 3.4597 (3.4133) grad_norm: 1.3039 (1.2978) time: 0.5036 [2021-03-26 02:57:55 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 590/1251] eta: 0:05:38 lr: 0.000611 loss: 3.4597 (3.4109) grad_norm: 1.3039 (1.2985) time: 0.5094 [2021-03-26 02:58:00 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 600/1251] eta: 0:05:33 lr: 0.000611 loss: 3.4486 (3.4119) grad_norm: 1.2924 (1.2986) time: 0.5095 [2021-03-26 02:58:05 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 610/1251] eta: 0:05:28 lr: 0.000611 loss: 3.4461 (3.4095) grad_norm: 1.2469 (1.2986) time: 0.5015 [2021-03-26 02:58:10 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 620/1251] eta: 0:05:23 lr: 0.000610 loss: 3.3580 (3.4086) grad_norm: 1.2390 (1.2988) time: 0.5069 [2021-03-26 02:58:15 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 630/1251] eta: 0:05:17 lr: 0.000610 loss: 3.3366 (3.4086) grad_norm: 1.3031 (1.2991) time: 0.5146 [2021-03-26 02:58:20 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 640/1251] eta: 0:05:12 lr: 0.000610 loss: 3.3366 (3.4079) grad_norm: 1.2817 (1.2982) time: 0.5117 [2021-03-26 02:58:25 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 650/1251] eta: 0:05:07 lr: 0.000610 loss: 3.3169 (3.4082) grad_norm: 1.2678 (1.2980) time: 0.5037 [2021-03-26 02:58:30 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 660/1251] eta: 0:05:02 lr: 0.000610 loss: 3.2237 (3.4052) grad_norm: 1.2902 (1.2978) time: 0.5008 [2021-03-26 02:58:35 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 670/1251] eta: 0:04:57 lr: 0.000610 loss: 3.4117 (3.4046) grad_norm: 1.2693 (1.2980) time: 0.4990 [2021-03-26 02:58:40 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 680/1251] eta: 0:04:51 lr: 0.000610 loss: 3.4155 (3.4038) grad_norm: 1.3157 (1.2992) time: 0.5048 [2021-03-26 02:58:45 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 690/1251] eta: 0:04:46 lr: 0.000610 loss: 3.3422 (3.4014) grad_norm: 1.3157 (1.2995) time: 0.5032 [2021-03-26 02:58:51 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 700/1251] eta: 0:04:41 lr: 0.000610 loss: 3.4059 (3.4019) grad_norm: 1.2578 (1.2983) time: 0.5025 [2021-03-26 02:58:56 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 710/1251] eta: 0:04:36 lr: 0.000610 loss: 3.5250 (3.4014) grad_norm: 1.2578 (1.2996) time: 0.5065 [2021-03-26 02:59:01 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 720/1251] eta: 0:04:31 lr: 0.000610 loss: 3.5491 (3.4026) grad_norm: 1.3093 (1.3000) time: 0.5105 [2021-03-26 02:59:06 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 730/1251] eta: 0:04:26 lr: 0.000610 loss: 3.2539 (3.4006) grad_norm: 1.3449 (1.3007) time: 0.5221 [2021-03-26 02:59:11 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 740/1251] eta: 0:04:21 lr: 0.000610 loss: 3.4284 (3.4032) grad_norm: 1.3449 (1.3005) time: 0.5243 [2021-03-26 02:59:16 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 750/1251] eta: 0:04:16 lr: 0.000610 loss: 3.5121 (3.4031) grad_norm: 1.2901 (1.3003) time: 0.5137 [2021-03-26 02:59:21 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 760/1251] eta: 0:04:11 lr: 0.000610 loss: 3.5069 (3.4039) grad_norm: 1.2901 (1.2999) time: 0.5056 [2021-03-26 02:59:26 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 770/1251] eta: 0:04:05 lr: 0.000610 loss: 3.5838 (3.4062) grad_norm: 1.2003 (1.2987) time: 0.5023 [2021-03-26 02:59:32 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 780/1251] eta: 0:04:00 lr: 0.000610 loss: 3.5838 (3.4046) grad_norm: 1.2789 (1.3004) time: 0.5119 [2021-03-26 02:59:37 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 790/1251] eta: 0:03:55 lr: 0.000610 loss: 3.6627 (3.4095) grad_norm: 1.3418 (1.3014) time: 0.5143 [2021-03-26 02:59:42 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 800/1251] eta: 0:03:50 lr: 0.000610 loss: 3.6519 (3.4079) grad_norm: 1.3418 (1.3017) time: 0.5029 [2021-03-26 02:59:47 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 810/1251] eta: 0:03:45 lr: 0.000610 loss: 3.4220 (3.4069) grad_norm: 1.2751 (1.3010) time: 0.4975 [2021-03-26 02:59:52 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 820/1251] eta: 0:03:40 lr: 0.000610 loss: 3.3996 (3.4076) grad_norm: 1.2751 (1.3010) time: 0.5001 [2021-03-26 02:59:57 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 830/1251] eta: 0:03:35 lr: 0.000610 loss: 3.6373 (3.4088) grad_norm: 1.2750 (1.3003) time: 0.5058 [2021-03-26 03:00:02 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 840/1251] eta: 0:03:29 lr: 0.000610 loss: 3.5617 (3.4069) grad_norm: 1.1979 (1.2989) time: 0.5095 [2021-03-26 03:00:07 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 850/1251] eta: 0:03:24 lr: 0.000610 loss: 3.4225 (3.4074) grad_norm: 1.2774 (1.2992) time: 0.5091 [2021-03-26 03:00:12 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 860/1251] eta: 0:03:19 lr: 0.000610 loss: 3.6278 (3.4107) grad_norm: 1.2884 (1.2991) time: 0.5037 [2021-03-26 03:00:17 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 870/1251] eta: 0:03:14 lr: 0.000609 loss: 3.6808 (3.4087) grad_norm: 1.3021 (1.2994) time: 0.5036 [2021-03-26 03:00:22 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 880/1251] eta: 0:03:09 lr: 0.000609 loss: 3.2708 (3.4086) grad_norm: 1.3081 (1.2997) time: 0.5061 [2021-03-26 03:00:27 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 890/1251] eta: 0:03:04 lr: 0.000609 loss: 3.6892 (3.4103) grad_norm: 1.3041 (1.2996) time: 0.5066 [2021-03-26 03:00:32 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 900/1251] eta: 0:02:59 lr: 0.000609 loss: 3.7255 (3.4137) grad_norm: 1.2941 (1.3002) time: 0.5032 [2021-03-26 03:00:37 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 910/1251] eta: 0:02:54 lr: 0.000609 loss: 3.7172 (3.4153) grad_norm: 1.3388 (1.3011) time: 0.5016 [2021-03-26 03:00:42 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 920/1251] eta: 0:02:48 lr: 0.000609 loss: 3.5554 (3.4154) grad_norm: 1.3388 (1.3007) time: 0.5076 [2021-03-26 03:00:47 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 930/1251] eta: 0:02:43 lr: 0.000609 loss: 3.6505 (3.4176) grad_norm: 1.3257 (1.3016) time: 0.5137 [2021-03-26 03:00:52 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 940/1251] eta: 0:02:38 lr: 0.000609 loss: 3.6008 (3.4174) grad_norm: 1.2978 (1.3014) time: 0.5096 [2021-03-26 03:00:57 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 950/1251] eta: 0:02:33 lr: 0.000609 loss: 3.2849 (3.4146) grad_norm: 1.2833 (1.3012) time: 0.5028 [2021-03-26 03:01:03 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 960/1251] eta: 0:02:28 lr: 0.000609 loss: 3.4458 (3.4148) grad_norm: 1.2701 (1.3012) time: 0.5040 [2021-03-26 03:01:08 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 970/1251] eta: 0:02:23 lr: 0.000609 loss: 3.5663 (3.4143) grad_norm: 1.2151 (1.3005) time: 0.5020 [2021-03-26 03:01:13 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 980/1251] eta: 0:02:18 lr: 0.000609 loss: 3.5165 (3.4150) grad_norm: 1.2145 (1.3001) time: 0.5019 [2021-03-26 03:01:18 swin_small_patch4_window7_224] INFO: Epoch: [129] [ 990/1251] eta: 0:02:13 lr: 0.000609 loss: 3.5640 (3.4153) grad_norm: 1.2292 (1.3003) time: 0.5058 [2021-03-26 03:01:23 swin_small_patch4_window7_224] INFO: Epoch: [129] [1000/1251] eta: 0:02:07 lr: 0.000609 loss: 3.4139 (3.4144) grad_norm: 1.2760 (1.3004) time: 0.5067 [2021-03-26 03:01:28 swin_small_patch4_window7_224] INFO: Epoch: [129] [1010/1251] eta: 0:02:02 lr: 0.000609 loss: 3.4285 (3.4153) grad_norm: 1.2465 (1.3004) time: 0.5038 [2021-03-26 03:01:33 swin_small_patch4_window7_224] INFO: Epoch: [129] [1020/1251] eta: 0:01:57 lr: 0.000609 loss: 3.7193 (3.4180) grad_norm: 1.2494 (1.3006) time: 0.5001 [2021-03-26 03:01:38 swin_small_patch4_window7_224] INFO: Epoch: [129] [1030/1251] eta: 0:01:52 lr: 0.000609 loss: 3.7567 (3.4196) grad_norm: 1.2695 (1.3003) time: 0.4999 [2021-03-26 03:01:43 swin_small_patch4_window7_224] INFO: Epoch: [129] [1040/1251] eta: 0:01:47 lr: 0.000609 loss: 3.4831 (3.4184) grad_norm: 1.2290 (1.2999) time: 0.5015 [2021-03-26 03:01:48 swin_small_patch4_window7_224] INFO: Epoch: [129] [1050/1251] eta: 0:01:42 lr: 0.000609 loss: 3.2745 (3.4173) grad_norm: 1.2246 (1.2990) time: 0.4988 [2021-03-26 03:01:53 swin_small_patch4_window7_224] INFO: Epoch: [129] [1060/1251] eta: 0:01:37 lr: 0.000609 loss: 3.4068 (3.4175) grad_norm: 1.1983 (1.2986) time: 0.5000 [2021-03-26 03:01:58 swin_small_patch4_window7_224] INFO: Epoch: [129] [1070/1251] eta: 0:01:32 lr: 0.000609 loss: 3.7079 (3.4207) grad_norm: 1.2323 (1.2983) time: 0.5035 [2021-03-26 03:02:03 swin_small_patch4_window7_224] INFO: Epoch: [129] [1080/1251] eta: 0:01:27 lr: 0.000609 loss: 3.7996 (3.4193) grad_norm: 1.2880 (1.2983) time: 0.5023 [2021-03-26 03:02:08 swin_small_patch4_window7_224] INFO: Epoch: [129] [1090/1251] eta: 0:01:21 lr: 0.000609 loss: 3.0946 (3.4181) grad_norm: 1.2880 (1.2985) time: 0.5056 [2021-03-26 03:02:13 swin_small_patch4_window7_224] INFO: Epoch: [129] [1100/1251] eta: 0:01:16 lr: 0.000609 loss: 3.5250 (3.4195) grad_norm: 1.2962 (1.2990) time: 0.5058 [2021-03-26 03:02:18 swin_small_patch4_window7_224] INFO: Epoch: [129] [1110/1251] eta: 0:01:11 lr: 0.000608 loss: 3.5299 (3.4184) grad_norm: 1.3022 (1.2995) time: 0.5020 [2021-03-26 03:02:23 swin_small_patch4_window7_224] INFO: Epoch: [129] [1120/1251] eta: 0:01:06 lr: 0.000608 loss: 3.5132 (3.4185) grad_norm: 1.3161 (1.3007) time: 0.5066 [2021-03-26 03:02:28 swin_small_patch4_window7_224] INFO: Epoch: [129] [1130/1251] eta: 0:01:01 lr: 0.000608 loss: 3.4128 (3.4170) grad_norm: 1.2587 (1.2999) time: 0.5156 [2021-03-26 03:02:33 swin_small_patch4_window7_224] INFO: Epoch: [129] [1140/1251] eta: 0:00:56 lr: 0.000608 loss: 3.0985 (3.4141) grad_norm: 1.2313 (1.2992) time: 0.5123 [2021-03-26 03:02:38 swin_small_patch4_window7_224] INFO: Epoch: [129] [1150/1251] eta: 0:00:51 lr: 0.000608 loss: 3.2301 (3.4115) grad_norm: 1.2360 (1.2994) time: 0.5051 [2021-03-26 03:02:43 swin_small_patch4_window7_224] INFO: Epoch: [129] [1160/1251] eta: 0:00:46 lr: 0.000608 loss: 3.3614 (3.4122) grad_norm: 1.2360 (1.2993) time: 0.5081 [2021-03-26 03:02:48 swin_small_patch4_window7_224] INFO: Epoch: [129] [1170/1251] eta: 0:00:41 lr: 0.000608 loss: 3.5586 (3.4125) grad_norm: 1.2416 (1.2994) time: 0.5042 [2021-03-26 03:02:53 swin_small_patch4_window7_224] INFO: Epoch: [129] [1180/1251] eta: 0:00:36 lr: 0.000608 loss: 3.5359 (3.4118) grad_norm: 1.2553 (1.2989) time: 0.4995 [2021-03-26 03:02:59 swin_small_patch4_window7_224] INFO: Epoch: [129] [1190/1251] eta: 0:00:31 lr: 0.000608 loss: 3.5945 (3.4148) grad_norm: 1.2553 (1.2988) time: 0.5029 [2021-03-26 03:03:03 swin_small_patch4_window7_224] INFO: Epoch: [129] [1200/1251] eta: 0:00:25 lr: 0.000608 loss: 3.5925 (3.4145) grad_norm: 1.2725 (inf) time: 0.5018 [2021-03-26 03:03:08 swin_small_patch4_window7_224] INFO: Epoch: [129] [1210/1251] eta: 0:00:20 lr: 0.000608 loss: 3.4148 (3.4130) grad_norm: 1.2315 (inf) time: 0.4994 [2021-03-26 03:03:14 swin_small_patch4_window7_224] INFO: Epoch: [129] [1220/1251] eta: 0:00:15 lr: 0.000608 loss: 3.4530 (3.4108) grad_norm: 1.2136 (inf) time: 0.5018 [2021-03-26 03:03:19 swin_small_patch4_window7_224] INFO: Epoch: [129] [1230/1251] eta: 0:00:10 lr: 0.000608 loss: 3.5530 (3.4114) grad_norm: 1.2728 (inf) time: 0.5057 [2021-03-26 03:03:24 swin_small_patch4_window7_224] INFO: Epoch: [129] [1240/1251] eta: 0:00:05 lr: 0.000608 loss: 3.5348 (3.4106) grad_norm: 1.2737 (inf) time: 0.5015 [2021-03-26 03:03:29 swin_small_patch4_window7_224] INFO: Epoch: [129] [1250/1251] eta: 0:00:00 lr: 0.000608 loss: 3.5014 (3.4114) grad_norm: 1.3054 (inf) time: 0.4973 [2021-03-26 03:03:35 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:54 loss: 0.9739 (0.9739) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-26 03:03:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9491 (0.9558) acc1: 75.0000 (76.1364) acc5: 96.8750 (95.0284) [2021-03-26 03:03:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8994 (0.9300) acc1: 76.5625 (77.0833) acc5: 95.3125 (94.7917) [2021-03-26 03:03:43 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9425 (0.9561) acc1: 75.0000 (76.4617) acc5: 95.3125 (94.6069) [2021-03-26 03:03:45 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9425 (0.9495) acc1: 76.5625 (76.7912) acc5: 93.7500 (94.5884) [2021-03-26 03:03:46 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0276 (0.9709) acc1: 75.0000 (76.5440) acc5: 92.1875 (94.1440) [2021-03-26 03:03:50 swin_small_patch4_window7_224] INFO: * Acc@1 77.446 Acc@5 94.054 loss 0.946 [2021-03-26 03:03:50 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.4% [2021-03-26 03:03:50 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 03:03:54 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 0/1251] eta: 1:30:14 lr: 0.000608 loss: 3.5907 (3.5907) grad_norm: 1.2624 (1.2624) time: 4.3285 [2021-03-26 03:04:00 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 10/1251] eta: 0:18:03 lr: 0.000608 loss: 3.4368 (3.1502) grad_norm: 1.2231 (1.2190) time: 0.8728 [2021-03-26 03:04:05 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 20/1251] eta: 0:14:21 lr: 0.000608 loss: 3.4910 (3.3313) grad_norm: 1.2263 (1.2947) time: 0.5188 [2021-03-26 03:04:10 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 30/1251] eta: 0:13:03 lr: 0.000608 loss: 3.5915 (3.4735) grad_norm: 1.3677 (1.3183) time: 0.5146 [2021-03-26 03:04:15 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 40/1251] eta: 0:12:19 lr: 0.000608 loss: 3.6536 (3.5018) grad_norm: 1.3307 (1.3198) time: 0.5173 [2021-03-26 03:04:20 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 50/1251] eta: 0:11:48 lr: 0.000608 loss: 3.5130 (3.4880) grad_norm: 1.2273 (1.3041) time: 0.5100 [2021-03-26 03:04:25 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 60/1251] eta: 0:11:27 lr: 0.000608 loss: 3.5654 (3.4997) grad_norm: 1.2216 (1.2941) time: 0.5086 [2021-03-26 03:04:30 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 70/1251] eta: 0:11:09 lr: 0.000608 loss: 3.5491 (3.4684) grad_norm: 1.2094 (1.2892) time: 0.5093 [2021-03-26 03:04:35 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 80/1251] eta: 0:10:55 lr: 0.000608 loss: 3.3106 (3.4406) grad_norm: 1.2497 (1.2847) time: 0.5049 [2021-03-26 03:04:41 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 90/1251] eta: 0:10:42 lr: 0.000608 loss: 3.4829 (3.4502) grad_norm: 1.2709 (1.2854) time: 0.5048 [2021-03-26 03:04:46 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 100/1251] eta: 0:10:31 lr: 0.000608 loss: 3.1242 (3.4100) grad_norm: 1.3011 (1.2934) time: 0.5054 [2021-03-26 03:04:51 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 110/1251] eta: 0:10:22 lr: 0.000607 loss: 3.3991 (3.4252) grad_norm: 1.3435 (1.3004) time: 0.5074 [2021-03-26 03:04:56 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 120/1251] eta: 0:10:13 lr: 0.000607 loss: 3.5651 (3.4288) grad_norm: 1.2786 (1.2995) time: 0.5105 [2021-03-26 03:05:01 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 130/1251] eta: 0:10:05 lr: 0.000607 loss: 3.5255 (3.4321) grad_norm: 1.2703 (1.2969) time: 0.5111 [2021-03-26 03:05:06 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 140/1251] eta: 0:09:56 lr: 0.000607 loss: 3.0377 (3.4035) grad_norm: 1.2862 (1.2950) time: 0.5019 [2021-03-26 03:05:11 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 150/1251] eta: 0:09:48 lr: 0.000607 loss: 3.4360 (3.4185) grad_norm: 1.2655 (1.2932) time: 0.4987 [2021-03-26 03:05:16 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 160/1251] eta: 0:09:40 lr: 0.000607 loss: 3.5386 (3.4176) grad_norm: 1.2841 (1.2972) time: 0.5014 [2021-03-26 03:05:21 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 170/1251] eta: 0:09:34 lr: 0.000607 loss: 3.6388 (3.4254) grad_norm: 1.3249 (1.2995) time: 0.5047 [2021-03-26 03:05:26 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 180/1251] eta: 0:09:27 lr: 0.000607 loss: 3.5489 (3.4258) grad_norm: 1.3086 (1.3015) time: 0.5134 [2021-03-26 03:05:31 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 190/1251] eta: 0:09:20 lr: 0.000607 loss: 3.5489 (3.4323) grad_norm: 1.2765 (1.2987) time: 0.5050 [2021-03-26 03:05:36 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 200/1251] eta: 0:09:14 lr: 0.000607 loss: 3.6401 (3.4252) grad_norm: 1.2342 (1.2973) time: 0.5048 [2021-03-26 03:05:41 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 210/1251] eta: 0:09:08 lr: 0.000607 loss: 3.5463 (3.4239) grad_norm: 1.2826 (1.3000) time: 0.5102 [2021-03-26 03:05:46 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 220/1251] eta: 0:09:01 lr: 0.000607 loss: 3.6416 (3.4379) grad_norm: 1.2729 (1.2980) time: 0.5041 [2021-03-26 03:05:51 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 230/1251] eta: 0:08:55 lr: 0.000607 loss: 3.6966 (3.4391) grad_norm: 1.2473 (1.2961) time: 0.5030 [2021-03-26 03:05:56 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 240/1251] eta: 0:08:49 lr: 0.000607 loss: 3.3056 (3.4200) grad_norm: 1.2917 (1.2981) time: 0.5069 [2021-03-26 03:06:02 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 250/1251] eta: 0:08:43 lr: 0.000607 loss: 3.1223 (3.4126) grad_norm: 1.2628 (1.2963) time: 0.5085 [2021-03-26 03:06:07 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 260/1251] eta: 0:08:38 lr: 0.000607 loss: 3.2729 (3.4068) grad_norm: 1.2447 (1.2948) time: 0.5086 [2021-03-26 03:06:12 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 270/1251] eta: 0:08:32 lr: 0.000607 loss: 3.5389 (3.4117) grad_norm: 1.2596 (1.2962) time: 0.5054 [2021-03-26 03:06:17 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 280/1251] eta: 0:08:26 lr: 0.000607 loss: 3.5794 (3.4189) grad_norm: 1.2450 (1.2947) time: 0.5005 [2021-03-26 03:06:22 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 290/1251] eta: 0:08:20 lr: 0.000607 loss: 3.5653 (3.4262) grad_norm: 1.2785 (1.2951) time: 0.5066 [2021-03-26 03:06:27 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 300/1251] eta: 0:08:15 lr: 0.000607 loss: 3.6530 (3.4351) grad_norm: 1.2796 (1.2931) time: 0.5101 [2021-03-26 03:06:32 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 310/1251] eta: 0:08:09 lr: 0.000607 loss: 3.7550 (3.4399) grad_norm: 1.2489 (1.2924) time: 0.5118 [2021-03-26 03:06:37 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 320/1251] eta: 0:08:04 lr: 0.000607 loss: 3.5804 (3.4363) grad_norm: 1.2987 (1.2930) time: 0.5190 [2021-03-26 03:06:42 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 330/1251] eta: 0:07:58 lr: 0.000607 loss: 3.4603 (3.4311) grad_norm: 1.2792 (1.2914) time: 0.5134 [2021-03-26 03:06:47 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 340/1251] eta: 0:07:53 lr: 0.000607 loss: 3.1552 (3.4161) grad_norm: 1.2660 (1.2920) time: 0.5054 [2021-03-26 03:06:52 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 350/1251] eta: 0:07:47 lr: 0.000606 loss: 3.0341 (3.4108) grad_norm: 1.2660 (1.2929) time: 0.5091 [2021-03-26 03:06:58 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 360/1251] eta: 0:07:42 lr: 0.000606 loss: 3.2619 (3.4082) grad_norm: 1.2841 (1.2926) time: 0.5105 [2021-03-26 03:07:03 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 370/1251] eta: 0:07:36 lr: 0.000606 loss: 3.4646 (3.4121) grad_norm: 1.2804 (1.2922) time: 0.5046 [2021-03-26 03:07:08 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 380/1251] eta: 0:07:31 lr: 0.000606 loss: 3.6386 (3.4119) grad_norm: 1.2409 (1.2896) time: 0.5009 [2021-03-26 03:07:13 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 390/1251] eta: 0:07:25 lr: 0.000606 loss: 3.5469 (3.4101) grad_norm: 1.2692 (1.2903) time: 0.5030 [2021-03-26 03:07:18 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 400/1251] eta: 0:07:20 lr: 0.000606 loss: 3.5469 (3.4098) grad_norm: 1.2969 (1.2920) time: 0.5077 [2021-03-26 03:07:23 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 410/1251] eta: 0:07:14 lr: 0.000606 loss: 3.4287 (3.4053) grad_norm: 1.3062 (1.2921) time: 0.5069 [2021-03-26 03:07:28 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 420/1251] eta: 0:07:09 lr: 0.000606 loss: 3.4829 (3.4038) grad_norm: 1.3049 (1.2920) time: 0.5035 [2021-03-26 03:07:33 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 430/1251] eta: 0:07:04 lr: 0.000606 loss: 3.6493 (3.4104) grad_norm: 1.2520 (1.2915) time: 0.5054 [2021-03-26 03:07:38 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 440/1251] eta: 0:06:58 lr: 0.000606 loss: 3.6027 (3.4072) grad_norm: 1.2520 (1.2921) time: 0.5032 [2021-03-26 03:07:43 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 450/1251] eta: 0:06:53 lr: 0.000606 loss: 3.4823 (3.4095) grad_norm: 1.3149 (1.2919) time: 0.5023 [2021-03-26 03:07:48 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 460/1251] eta: 0:06:48 lr: 0.000606 loss: 3.4759 (3.4052) grad_norm: 1.2942 (1.2930) time: 0.5052 [2021-03-26 03:07:53 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 470/1251] eta: 0:06:42 lr: 0.000606 loss: 3.5264 (3.4074) grad_norm: 1.3071 (1.2932) time: 0.5091 [2021-03-26 03:07:58 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 480/1251] eta: 0:06:37 lr: 0.000606 loss: 3.5451 (3.4068) grad_norm: 1.3071 (1.2935) time: 0.5067 [2021-03-26 03:08:03 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 490/1251] eta: 0:06:32 lr: 0.000606 loss: 3.6506 (3.4109) grad_norm: 1.2698 (1.2930) time: 0.5071 [2021-03-26 03:08:08 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 500/1251] eta: 0:06:26 lr: 0.000606 loss: 3.6430 (3.4129) grad_norm: 1.2732 (1.2936) time: 0.5054 [2021-03-26 03:08:13 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 510/1251] eta: 0:06:21 lr: 0.000606 loss: 3.4661 (3.4144) grad_norm: 1.2973 (1.2930) time: 0.5060 [2021-03-26 03:08:18 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 520/1251] eta: 0:06:16 lr: 0.000606 loss: 3.4828 (3.4136) grad_norm: 1.2859 (1.2939) time: 0.5072 [2021-03-26 03:08:23 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 530/1251] eta: 0:06:11 lr: 0.000606 loss: 3.6048 (3.4160) grad_norm: 1.3118 (1.2950) time: 0.5048 [2021-03-26 03:08:29 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 540/1251] eta: 0:06:06 lr: 0.000606 loss: 3.6048 (3.4111) grad_norm: 1.3067 (1.2946) time: 0.5180 [2021-03-26 03:08:34 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 550/1251] eta: 0:06:01 lr: 0.000606 loss: 3.5244 (3.4151) grad_norm: 1.2532 (1.2938) time: 0.5265 [2021-03-26 03:08:39 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 560/1251] eta: 0:05:55 lr: 0.000606 loss: 3.5972 (3.4147) grad_norm: 1.2423 (1.2929) time: 0.5154 [2021-03-26 03:08:44 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 570/1251] eta: 0:05:50 lr: 0.000606 loss: 3.5395 (3.4154) grad_norm: 1.2515 (1.2929) time: 0.5072 [2021-03-26 03:08:49 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 580/1251] eta: 0:05:45 lr: 0.000606 loss: 3.3563 (3.4125) grad_norm: 1.2732 (1.2928) time: 0.5123 [2021-03-26 03:08:54 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 590/1251] eta: 0:05:40 lr: 0.000606 loss: 3.5048 (3.4160) grad_norm: 1.2339 (1.2922) time: 0.5165 [2021-03-26 03:08:59 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 600/1251] eta: 0:05:34 lr: 0.000605 loss: 3.5813 (3.4133) grad_norm: 1.2619 (1.2928) time: 0.5047 [2021-03-26 03:09:04 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 610/1251] eta: 0:05:29 lr: 0.000605 loss: 3.2931 (3.4124) grad_norm: 1.3380 (1.2925) time: 0.4933 [2021-03-26 03:09:09 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 620/1251] eta: 0:05:24 lr: 0.000605 loss: 3.1397 (3.4077) grad_norm: 1.2820 (1.2930) time: 0.4992 [2021-03-26 03:09:14 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 630/1251] eta: 0:05:19 lr: 0.000605 loss: 3.2886 (3.4106) grad_norm: 1.2790 (1.2931) time: 0.5050 [2021-03-26 03:09:20 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 640/1251] eta: 0:05:13 lr: 0.000605 loss: 3.5131 (3.4109) grad_norm: 1.2474 (1.2918) time: 0.5079 [2021-03-26 03:09:25 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 650/1251] eta: 0:05:08 lr: 0.000605 loss: 3.3791 (3.4085) grad_norm: 1.2335 (1.2915) time: 0.5083 [2021-03-26 03:09:30 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 660/1251] eta: 0:05:03 lr: 0.000605 loss: 3.5687 (3.4085) grad_norm: 1.2655 (1.2919) time: 0.5087 [2021-03-26 03:09:35 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 670/1251] eta: 0:04:58 lr: 0.000605 loss: 3.2314 (3.4039) grad_norm: 1.3185 (1.2927) time: 0.5031 [2021-03-26 03:09:40 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 680/1251] eta: 0:04:52 lr: 0.000605 loss: 3.3850 (3.4076) grad_norm: 1.2526 (1.2920) time: 0.4960 [2021-03-26 03:09:45 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 690/1251] eta: 0:04:47 lr: 0.000605 loss: 3.5818 (3.4063) grad_norm: 1.2389 (1.2922) time: 0.5008 [2021-03-26 03:09:50 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 700/1251] eta: 0:04:42 lr: 0.000605 loss: 3.3078 (3.4032) grad_norm: 1.2966 (1.2927) time: 0.5031 [2021-03-26 03:09:55 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 710/1251] eta: 0:04:37 lr: 0.000605 loss: 3.6395 (3.4062) grad_norm: 1.2876 (1.2920) time: 0.5027 [2021-03-26 03:10:00 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 720/1251] eta: 0:04:32 lr: 0.000605 loss: 3.6604 (3.4068) grad_norm: 1.2876 (1.2919) time: 0.5023 [2021-03-26 03:10:05 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 730/1251] eta: 0:04:27 lr: 0.000605 loss: 3.5839 (3.4091) grad_norm: 1.3092 (1.2926) time: 0.5085 [2021-03-26 03:10:10 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 740/1251] eta: 0:04:22 lr: 0.000605 loss: 3.5043 (3.4112) grad_norm: 1.2882 (1.2918) time: 0.5235 [2021-03-26 03:10:15 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 750/1251] eta: 0:04:16 lr: 0.000605 loss: 3.7187 (3.4122) grad_norm: 1.2481 (1.2919) time: 0.5198 [2021-03-26 03:10:21 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 760/1251] eta: 0:04:11 lr: 0.000605 loss: 3.6760 (3.4136) grad_norm: 1.3110 (1.2927) time: 0.5136 [2021-03-26 03:10:26 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 770/1251] eta: 0:04:06 lr: 0.000605 loss: 3.5183 (3.4101) grad_norm: 1.3184 (1.2935) time: 0.5200 [2021-03-26 03:10:31 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 780/1251] eta: 0:04:01 lr: 0.000605 loss: 3.5752 (3.4147) grad_norm: 1.2691 (1.2923) time: 0.5137 [2021-03-26 03:10:36 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 790/1251] eta: 0:03:56 lr: 0.000605 loss: 3.4266 (3.4112) grad_norm: 1.1924 (1.2925) time: 0.5088 [2021-03-26 03:10:41 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 800/1251] eta: 0:03:51 lr: 0.000605 loss: 3.3008 (3.4090) grad_norm: 1.2830 (1.2922) time: 0.5082 [2021-03-26 03:10:46 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 810/1251] eta: 0:03:46 lr: 0.000605 loss: 3.3278 (3.4071) grad_norm: 1.2617 (1.2920) time: 0.5025 [2021-03-26 03:10:51 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 820/1251] eta: 0:03:40 lr: 0.000605 loss: 3.2308 (3.4028) grad_norm: 1.2819 (1.2927) time: 0.5020 [2021-03-26 03:10:56 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 830/1251] eta: 0:03:35 lr: 0.000605 loss: 3.1355 (3.4019) grad_norm: 1.3082 (1.2930) time: 0.4993 [2021-03-26 03:11:01 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 840/1251] eta: 0:03:30 lr: 0.000605 loss: 3.5937 (3.4052) grad_norm: 1.2681 (1.2927) time: 0.5033 [2021-03-26 03:11:06 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 850/1251] eta: 0:03:25 lr: 0.000604 loss: 3.5685 (3.4040) grad_norm: 1.2681 (1.2930) time: 0.5073 [2021-03-26 03:11:11 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 860/1251] eta: 0:03:20 lr: 0.000604 loss: 3.5329 (3.4059) grad_norm: 1.3220 (1.2944) time: 0.5081 [2021-03-26 03:11:16 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 870/1251] eta: 0:03:15 lr: 0.000604 loss: 3.7109 (3.4093) grad_norm: 1.4051 (1.2955) time: 0.5128 [2021-03-26 03:11:21 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 880/1251] eta: 0:03:09 lr: 0.000604 loss: 3.5665 (3.4069) grad_norm: 1.3051 (1.2958) time: 0.5108 [2021-03-26 03:11:26 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 890/1251] eta: 0:03:04 lr: 0.000604 loss: 3.4815 (3.4079) grad_norm: 1.3028 (1.2966) time: 0.5027 [2021-03-26 03:11:31 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 900/1251] eta: 0:02:59 lr: 0.000604 loss: 3.5093 (3.4098) grad_norm: 1.3028 (1.2965) time: 0.4966 [2021-03-26 03:11:36 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 910/1251] eta: 0:02:54 lr: 0.000604 loss: 3.5447 (3.4124) grad_norm: 1.2831 (1.2970) time: 0.5014 [2021-03-26 03:11:42 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 920/1251] eta: 0:02:49 lr: 0.000604 loss: 3.4705 (3.4113) grad_norm: 1.2959 (1.2975) time: 0.5111 [2021-03-26 03:11:47 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 930/1251] eta: 0:02:44 lr: 0.000604 loss: 3.3261 (3.4115) grad_norm: 1.2653 (1.2974) time: 0.5154 [2021-03-26 03:11:52 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 940/1251] eta: 0:02:39 lr: 0.000604 loss: 3.3306 (3.4107) grad_norm: 1.2653 (1.2985) time: 0.5149 [2021-03-26 03:11:57 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 950/1251] eta: 0:02:34 lr: 0.000604 loss: 3.6020 (3.4133) grad_norm: 1.3240 (1.2985) time: 0.5061 [2021-03-26 03:12:02 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 960/1251] eta: 0:02:28 lr: 0.000604 loss: 3.6321 (3.4148) grad_norm: 1.2955 (1.2990) time: 0.5029 [2021-03-26 03:12:07 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 970/1251] eta: 0:02:23 lr: 0.000604 loss: 3.6321 (3.4160) grad_norm: 1.3013 (1.2988) time: 0.5061 [2021-03-26 03:12:12 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 980/1251] eta: 0:02:18 lr: 0.000604 loss: 3.3791 (3.4149) grad_norm: 1.2668 (1.2986) time: 0.5028 [2021-03-26 03:12:17 swin_small_patch4_window7_224] INFO: Epoch: [130] [ 990/1251] eta: 0:02:13 lr: 0.000604 loss: 3.4247 (3.4149) grad_norm: 1.2697 (1.2993) time: 0.5022 [2021-03-26 03:12:22 swin_small_patch4_window7_224] INFO: Epoch: [130] [1000/1251] eta: 0:02:08 lr: 0.000604 loss: 3.4116 (3.4145) grad_norm: 1.3042 (1.2998) time: 0.5025 [2021-03-26 03:12:27 swin_small_patch4_window7_224] INFO: Epoch: [130] [1010/1251] eta: 0:02:03 lr: 0.000604 loss: 3.4514 (3.4166) grad_norm: 1.2403 (1.2994) time: 0.5015 [2021-03-26 03:12:32 swin_small_patch4_window7_224] INFO: Epoch: [130] [1020/1251] eta: 0:01:58 lr: 0.000604 loss: 3.6289 (3.4177) grad_norm: 1.2571 (1.3001) time: 0.5018 [2021-03-26 03:12:37 swin_small_patch4_window7_224] INFO: Epoch: [130] [1030/1251] eta: 0:01:52 lr: 0.000604 loss: 3.3940 (3.4148) grad_norm: 1.3159 (1.3002) time: 0.4994 [2021-03-26 03:12:42 swin_small_patch4_window7_224] INFO: Epoch: [130] [1040/1251] eta: 0:01:47 lr: 0.000604 loss: 3.2363 (3.4150) grad_norm: 1.2958 (1.3004) time: 0.4987 [2021-03-26 03:12:47 swin_small_patch4_window7_224] INFO: Epoch: [130] [1050/1251] eta: 0:01:42 lr: 0.000604 loss: 3.6074 (3.4150) grad_norm: 1.2338 (1.3000) time: 0.5052 [2021-03-26 03:12:52 swin_small_patch4_window7_224] INFO: Epoch: [130] [1060/1251] eta: 0:01:37 lr: 0.000604 loss: 3.4008 (3.4137) grad_norm: 1.2086 (1.2996) time: 0.5102 [2021-03-26 03:12:57 swin_small_patch4_window7_224] INFO: Epoch: [130] [1070/1251] eta: 0:01:32 lr: 0.000604 loss: 3.3053 (3.4117) grad_norm: 1.2989 (1.3001) time: 0.5093 [2021-03-26 03:13:02 swin_small_patch4_window7_224] INFO: Epoch: [130] [1080/1251] eta: 0:01:27 lr: 0.000604 loss: 3.3389 (3.4124) grad_norm: 1.2660 (1.2995) time: 0.5049 [2021-03-26 03:13:08 swin_small_patch4_window7_224] INFO: Epoch: [130] [1090/1251] eta: 0:01:22 lr: 0.000603 loss: 3.5012 (3.4119) grad_norm: 1.2389 (1.2988) time: 0.5077 [2021-03-26 03:13:13 swin_small_patch4_window7_224] INFO: Epoch: [130] [1100/1251] eta: 0:01:17 lr: 0.000603 loss: 3.5001 (3.4116) grad_norm: 1.2407 (1.2987) time: 0.5070 [2021-03-26 03:13:17 swin_small_patch4_window7_224] INFO: Epoch: [130] [1110/1251] eta: 0:01:11 lr: 0.000603 loss: 3.4167 (3.4122) grad_norm: 1.2767 (1.2988) time: 0.4974 [2021-03-26 03:13:23 swin_small_patch4_window7_224] INFO: Epoch: [130] [1120/1251] eta: 0:01:06 lr: 0.000603 loss: 3.4167 (3.4121) grad_norm: 1.3095 (1.2991) time: 0.4974 [2021-03-26 03:13:27 swin_small_patch4_window7_224] INFO: Epoch: [130] [1130/1251] eta: 0:01:01 lr: 0.000603 loss: 3.5249 (3.4140) grad_norm: 1.2862 (1.2988) time: 0.4995 [2021-03-26 03:13:33 swin_small_patch4_window7_224] INFO: Epoch: [130] [1140/1251] eta: 0:00:56 lr: 0.000603 loss: 3.4834 (3.4131) grad_norm: 1.2574 (1.2985) time: 0.5003 [2021-03-26 03:13:38 swin_small_patch4_window7_224] INFO: Epoch: [130] [1150/1251] eta: 0:00:51 lr: 0.000603 loss: 3.4104 (3.4136) grad_norm: 1.2651 (1.2982) time: 0.5051 [2021-03-26 03:13:43 swin_small_patch4_window7_224] INFO: Epoch: [130] [1160/1251] eta: 0:00:46 lr: 0.000603 loss: 3.6179 (3.4132) grad_norm: 1.3260 (1.2990) time: 0.5034 [2021-03-26 03:13:48 swin_small_patch4_window7_224] INFO: Epoch: [130] [1170/1251] eta: 0:00:41 lr: 0.000603 loss: 3.3655 (3.4128) grad_norm: 1.3319 (1.2987) time: 0.5003 [2021-03-26 03:13:53 swin_small_patch4_window7_224] INFO: Epoch: [130] [1180/1251] eta: 0:00:36 lr: 0.000603 loss: 3.3655 (3.4124) grad_norm: 1.2442 (1.2984) time: 0.5016 [2021-03-26 03:13:58 swin_small_patch4_window7_224] INFO: Epoch: [130] [1190/1251] eta: 0:00:31 lr: 0.000603 loss: 3.2195 (3.4105) grad_norm: 1.2356 (1.2984) time: 0.5043 [2021-03-26 03:14:03 swin_small_patch4_window7_224] INFO: Epoch: [130] [1200/1251] eta: 0:00:26 lr: 0.000603 loss: 3.5574 (3.4138) grad_norm: 1.2287 (1.2981) time: 0.5040 [2021-03-26 03:14:08 swin_small_patch4_window7_224] INFO: Epoch: [130] [1210/1251] eta: 0:00:20 lr: 0.000603 loss: 3.6082 (3.4146) grad_norm: 1.2620 (1.2981) time: 0.4984 [2021-03-26 03:14:13 swin_small_patch4_window7_224] INFO: Epoch: [130] [1220/1251] eta: 0:00:15 lr: 0.000603 loss: 3.5594 (3.4153) grad_norm: 1.2620 (1.2982) time: 0.5004 [2021-03-26 03:14:18 swin_small_patch4_window7_224] INFO: Epoch: [130] [1230/1251] eta: 0:00:10 lr: 0.000603 loss: 3.4370 (3.4149) grad_norm: 1.2984 (1.2987) time: 0.5073 [2021-03-26 03:14:23 swin_small_patch4_window7_224] INFO: Epoch: [130] [1240/1251] eta: 0:00:05 lr: 0.000603 loss: 3.2878 (3.4141) grad_norm: 1.2983 (1.2988) time: 0.5068 [2021-03-26 03:14:28 swin_small_patch4_window7_224] INFO: Epoch: [130] [1250/1251] eta: 0:00:00 lr: 0.000603 loss: 3.4283 (3.4161) grad_norm: 1.2777 (1.2987) time: 0.5038 [2021-03-26 03:15:10 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 1.0049 (1.0049) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-26 03:15:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.9743 (0.9104) acc1: 76.5625 (77.6989) acc5: 95.3125 (95.1705) [2021-03-26 03:15:12 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.9424 (0.9321) acc1: 76.5625 (77.5298) acc5: 95.3125 (94.3452) [2021-03-26 03:15:13 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9424 (0.9451) acc1: 76.5625 (77.2681) acc5: 93.7500 (94.6069) [2021-03-26 03:15:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9358 (0.9441) acc1: 76.5625 (77.1341) acc5: 93.7500 (94.5122) [2021-03-26 03:15:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9933 (0.9566) acc1: 75.0000 (76.6720) acc5: 93.7500 (94.4320) [2021-03-26 03:15:22 swin_small_patch4_window7_224] INFO: * Acc@1 77.374 Acc@5 94.034 loss 0.950 [2021-03-26 03:15:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.4% [2021-03-26 03:15:22 swin_small_patch4_window7_224] INFO: Max accuracy: 77.49% [2021-03-26 03:15:26 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 0/1251] eta: 1:24:12 lr: 0.000603 loss: 3.3394 (3.3394) grad_norm: 1.2307 (1.2307) time: 4.0384 [2021-03-26 03:15:31 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 10/1251] eta: 0:17:23 lr: 0.000603 loss: 3.5775 (3.4730) grad_norm: 1.2307 (1.2597) time: 0.8406 [2021-03-26 03:15:36 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 20/1251] eta: 0:13:56 lr: 0.000603 loss: 3.4634 (3.3151) grad_norm: 1.2340 (1.2835) time: 0.5117 [2021-03-26 03:15:41 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 30/1251] eta: 0:12:40 lr: 0.000603 loss: 3.3057 (3.2957) grad_norm: 1.2553 (1.2921) time: 0.5032 [2021-03-26 03:15:46 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 40/1251] eta: 0:11:57 lr: 0.000603 loss: 3.4644 (3.3346) grad_norm: 1.2551 (1.2915) time: 0.5009 [2021-03-26 03:15:52 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 50/1251] eta: 0:11:31 lr: 0.000603 loss: 3.4944 (3.3555) grad_norm: 1.2785 (1.2975) time: 0.5036 [2021-03-26 03:15:57 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 60/1251] eta: 0:11:11 lr: 0.000603 loss: 3.3992 (3.3566) grad_norm: 1.2947 (1.3030) time: 0.5045 [2021-03-26 03:16:02 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 70/1251] eta: 0:10:56 lr: 0.000603 loss: 3.1308 (3.2854) grad_norm: 1.3095 (1.3138) time: 0.5046 [2021-03-26 03:16:07 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 80/1251] eta: 0:10:43 lr: 0.000603 loss: 2.9957 (3.2980) grad_norm: 1.4120 (1.3482) time: 0.5053 [2021-03-26 03:16:12 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 90/1251] eta: 0:10:33 lr: 0.000602 loss: 3.5203 (3.3166) grad_norm: 1.4329 (1.3532) time: 0.5090 [2021-03-26 03:16:17 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 100/1251] eta: 0:10:22 lr: 0.000602 loss: 3.5203 (3.3315) grad_norm: 1.2686 (1.3458) time: 0.5073 [2021-03-26 03:16:22 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 110/1251] eta: 0:10:14 lr: 0.000602 loss: 3.6470 (3.3537) grad_norm: 1.2268 (1.3346) time: 0.5058 [2021-03-26 03:16:27 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 120/1251] eta: 0:10:06 lr: 0.000602 loss: 3.6470 (3.3574) grad_norm: 1.1946 (1.3247) time: 0.5112 [2021-03-26 03:16:32 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 130/1251] eta: 0:09:58 lr: 0.000602 loss: 3.3007 (3.3340) grad_norm: 1.2074 (1.3262) time: 0.5082 [2021-03-26 03:16:37 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 140/1251] eta: 0:09:50 lr: 0.000602 loss: 3.3656 (3.3374) grad_norm: 1.2239 (1.3202) time: 0.5028 [2021-03-26 03:16:42 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 150/1251] eta: 0:09:42 lr: 0.000602 loss: 3.4215 (3.3215) grad_norm: 1.2464 (1.3185) time: 0.5003 [2021-03-26 03:16:47 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 160/1251] eta: 0:09:36 lr: 0.000602 loss: 3.3585 (3.3221) grad_norm: 1.2704 (1.3164) time: 0.5089 [2021-03-26 03:16:52 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 170/1251] eta: 0:09:29 lr: 0.000602 loss: 3.4727 (3.3313) grad_norm: 1.2590 (1.3161) time: 0.5112 [2021-03-26 03:16:57 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 180/1251] eta: 0:09:23 lr: 0.000602 loss: 3.4746 (3.3247) grad_norm: 1.2607 (1.3173) time: 0.5082 [2021-03-26 03:17:02 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 190/1251] eta: 0:09:17 lr: 0.000602 loss: 3.5676 (3.3335) grad_norm: 1.3016 (1.3192) time: 0.5068 [2021-03-26 03:17:08 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 200/1251] eta: 0:09:11 lr: 0.000602 loss: 3.4459 (3.3366) grad_norm: 1.2867 (1.3190) time: 0.5070 [2021-03-26 03:17:13 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 210/1251] eta: 0:09:04 lr: 0.000602 loss: 3.3402 (3.3340) grad_norm: 1.2781 (1.3183) time: 0.5043 [2021-03-26 03:17:18 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 220/1251] eta: 0:08:58 lr: 0.000602 loss: 3.1979 (3.3248) grad_norm: 1.2781 (1.3184) time: 0.4985 [2021-03-26 03:17:23 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 230/1251] eta: 0:08:51 lr: 0.000602 loss: 3.1979 (3.3230) grad_norm: 1.2223 (1.3149) time: 0.4985 [2021-03-26 03:17:28 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 240/1251] eta: 0:08:46 lr: 0.000602 loss: 3.3498 (3.3280) grad_norm: 1.2144 (1.3113) time: 0.5046 [2021-03-26 03:17:33 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 250/1251] eta: 0:08:40 lr: 0.000602 loss: 3.4479 (3.3234) grad_norm: 1.2494 (1.3107) time: 0.5056 [2021-03-26 03:17:38 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 260/1251] eta: 0:08:34 lr: 0.000602 loss: 3.4760 (3.3293) grad_norm: 1.3010 (1.3125) time: 0.5008 [2021-03-26 03:17:43 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 270/1251] eta: 0:08:28 lr: 0.000602 loss: 3.6341 (3.3336) grad_norm: 1.3451 (1.3128) time: 0.5057 [2021-03-26 03:17:48 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 280/1251] eta: 0:08:23 lr: 0.000602 loss: 3.6835 (3.3472) grad_norm: 1.3288 (1.3143) time: 0.5084 [2021-03-26 03:17:53 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 290/1251] eta: 0:08:17 lr: 0.000602 loss: 3.6045 (3.3486) grad_norm: 1.3694 (1.3159) time: 0.5029 [2021-03-26 03:17:58 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 300/1251] eta: 0:08:12 lr: 0.000602 loss: 3.4097 (3.3535) grad_norm: 1.3044 (1.3147) time: 0.5075 [2021-03-26 03:18:03 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 310/1251] eta: 0:08:06 lr: 0.000602 loss: 3.7282 (3.3650) grad_norm: 1.2123 (1.3104) time: 0.5131 [2021-03-26 03:18:08 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 320/1251] eta: 0:08:01 lr: 0.000602 loss: 3.6308 (3.3612) grad_norm: 1.2123 (1.3123) time: 0.5122 [2021-03-26 03:18:13 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 330/1251] eta: 0:07:55 lr: 0.000601 loss: 3.4378 (3.3627) grad_norm: 1.3565 (1.3129) time: 0.5054 [2021-03-26 03:18:18 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 340/1251] eta: 0:07:50 lr: 0.000601 loss: 3.2180 (3.3554) grad_norm: 1.2968 (1.3122) time: 0.5033 [2021-03-26 03:18:23 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 350/1251] eta: 0:07:44 lr: 0.000601 loss: 3.3512 (3.3580) grad_norm: 1.2936 (1.3124) time: 0.5067 [2021-03-26 03:18:28 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 360/1251] eta: 0:07:39 lr: 0.000601 loss: 3.5287 (3.3643) grad_norm: 1.2604 (1.3109) time: 0.5034 [2021-03-26 03:18:33 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 370/1251] eta: 0:07:34 lr: 0.000601 loss: 3.5294 (3.3630) grad_norm: 1.2530 (1.3100) time: 0.5035 [2021-03-26 03:18:38 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 380/1251] eta: 0:07:28 lr: 0.000601 loss: 3.2385 (3.3570) grad_norm: 1.2811 (1.3102) time: 0.5035 [2021-03-26 03:18:43 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 390/1251] eta: 0:07:23 lr: 0.000601 loss: 3.2385 (3.3554) grad_norm: 1.3310 (1.3113) time: 0.5006 [2021-03-26 03:18:48 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 400/1251] eta: 0:07:17 lr: 0.000601 loss: 3.4133 (3.3537) grad_norm: 1.3200 (1.3106) time: 0.5025 [2021-03-26 03:18:54 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 410/1251] eta: 0:07:12 lr: 0.000601 loss: 3.2862 (3.3528) grad_norm: 1.2542 (1.3103) time: 0.5058 [2021-03-26 03:18:59 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 420/1251] eta: 0:07:07 lr: 0.000601 loss: 3.2730 (3.3483) grad_norm: 1.2354 (1.3092) time: 0.5071 [2021-03-26 03:19:04 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 430/1251] eta: 0:07:02 lr: 0.000601 loss: 3.3498 (3.3499) grad_norm: 1.2401 (1.3083) time: 0.5150 [2021-03-26 03:19:09 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 440/1251] eta: 0:06:56 lr: 0.000601 loss: 3.4888 (3.3501) grad_norm: 1.3085 (1.3099) time: 0.5113 [2021-03-26 03:19:14 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 450/1251] eta: 0:06:51 lr: 0.000601 loss: 3.4167 (3.3433) grad_norm: 1.3085 (1.3095) time: 0.5056 [2021-03-26 03:19:19 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 460/1251] eta: 0:06:46 lr: 0.000601 loss: 3.2586 (3.3416) grad_norm: 1.3082 (1.3101) time: 0.5067 [2021-03-26 03:19:24 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 470/1251] eta: 0:06:41 lr: 0.000601 loss: 3.4273 (3.3436) grad_norm: 1.3631 (1.3115) time: 0.5049 [2021-03-26 03:19:29 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 480/1251] eta: 0:06:35 lr: 0.000601 loss: 3.3932 (3.3345) grad_norm: 1.3527 (1.3134) time: 0.5035 [2021-03-26 03:19:34 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 490/1251] eta: 0:06:30 lr: 0.000601 loss: 2.9833 (3.3319) grad_norm: 1.2395 (1.3127) time: 0.5031 [2021-03-26 03:19:39 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 500/1251] eta: 0:06:25 lr: 0.000601 loss: 3.4266 (3.3324) grad_norm: 1.2360 (1.3121) time: 0.5029 [2021-03-26 03:19:44 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 510/1251] eta: 0:06:19 lr: 0.000601 loss: 3.5223 (3.3360) grad_norm: 1.2743 (1.3118) time: 0.5061 [2021-03-26 03:19:49 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 520/1251] eta: 0:06:14 lr: 0.000601 loss: 3.4397 (3.3379) grad_norm: 1.3184 (1.3129) time: 0.5092 [2021-03-26 03:19:54 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 530/1251] eta: 0:06:09 lr: 0.000601 loss: 3.4294 (3.3366) grad_norm: 1.3407 (1.3136) time: 0.5076 [2021-03-26 03:20:00 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 540/1251] eta: 0:06:04 lr: 0.000601 loss: 3.4742 (3.3390) grad_norm: 1.3465 (1.3150) time: 0.5114 [2021-03-26 03:20:05 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 550/1251] eta: 0:05:59 lr: 0.000601 loss: 3.6628 (3.3425) grad_norm: 1.3465 (1.3157) time: 0.5186 [2021-03-26 03:20:10 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 560/1251] eta: 0:05:54 lr: 0.000601 loss: 3.2925 (3.3385) grad_norm: 1.3665 (1.3169) time: 0.5078 [2021-03-26 03:20:15 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 570/1251] eta: 0:05:48 lr: 0.000601 loss: 3.4300 (3.3399) grad_norm: 1.3997 (1.3192) time: 0.4966 [2021-03-26 03:20:20 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 580/1251] eta: 0:05:43 lr: 0.000600 loss: 3.6596 (3.3463) grad_norm: 1.3292 (1.3199) time: 0.5003 [2021-03-26 03:20:25 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 590/1251] eta: 0:05:38 lr: 0.000600 loss: 3.5008 (3.3442) grad_norm: 1.2740 (1.3194) time: 0.4967 [2021-03-26 03:20:30 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 600/1251] eta: 0:05:33 lr: 0.000600 loss: 3.4621 (3.3464) grad_norm: 1.2855 (1.3207) time: 0.5024 [2021-03-26 03:20:35 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 610/1251] eta: 0:05:27 lr: 0.000600 loss: 3.5830 (3.3483) grad_norm: 1.3584 (1.3206) time: 0.5090 [2021-03-26 03:20:40 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 620/1251] eta: 0:05:22 lr: 0.000600 loss: 3.5500 (3.3512) grad_norm: 1.2584 (1.3208) time: 0.5045 [2021-03-26 03:20:45 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 630/1251] eta: 0:05:17 lr: 0.000600 loss: 3.3587 (3.3487) grad_norm: 1.2563 (1.3194) time: 0.5047 [2021-03-26 03:20:50 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 640/1251] eta: 0:05:12 lr: 0.000600 loss: 3.3419 (3.3501) grad_norm: 1.2133 (1.3179) time: 0.5047 [2021-03-26 03:20:55 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 650/1251] eta: 0:05:07 lr: 0.000600 loss: 3.1816 (3.3488) grad_norm: 1.2445 (1.3173) time: 0.5002 [2021-03-26 03:21:00 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 660/1251] eta: 0:05:01 lr: 0.000600 loss: 3.3441 (3.3480) grad_norm: 1.2474 (1.3159) time: 0.4963 [2021-03-26 03:21:05 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 670/1251] eta: 0:04:56 lr: 0.000600 loss: 3.4819 (3.3496) grad_norm: 1.2741 (1.3156) time: 0.5032 [2021-03-26 03:21:10 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 680/1251] eta: 0:04:51 lr: 0.000600 loss: 3.4662 (3.3510) grad_norm: 1.3317 (1.3158) time: 0.5080 [2021-03-26 03:21:15 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 690/1251] eta: 0:04:46 lr: 0.000600 loss: 3.4301 (3.3516) grad_norm: 1.3271 (1.3158) time: 0.5040 [2021-03-26 03:21:20 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 700/1251] eta: 0:04:41 lr: 0.000600 loss: 3.4741 (3.3528) grad_norm: 1.3042 (1.3154) time: 0.5078 [2021-03-26 03:21:25 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 710/1251] eta: 0:04:36 lr: 0.000600 loss: 3.5606 (3.3569) grad_norm: 1.2562 (1.3146) time: 0.5098 [2021-03-26 03:21:30 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 720/1251] eta: 0:04:31 lr: 0.000600 loss: 3.6620 (3.3583) grad_norm: 1.2426 (1.3138) time: 0.5076 [2021-03-26 03:21:36 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 730/1251] eta: 0:04:26 lr: 0.000600 loss: 3.4450 (3.3554) grad_norm: 1.2294 (1.3134) time: 0.5181 [2021-03-26 03:21:41 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 740/1251] eta: 0:04:21 lr: 0.000600 loss: 3.3491 (3.3583) grad_norm: 1.3094 (1.3150) time: 0.5321 [2021-03-26 03:21:46 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 750/1251] eta: 0:04:16 lr: 0.000600 loss: 3.6039 (3.3606) grad_norm: 1.2890 (1.3146) time: 0.5242 [2021-03-26 03:21:51 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 760/1251] eta: 0:04:10 lr: 0.000600 loss: 3.5228 (3.3597) grad_norm: 1.2628 (1.3149) time: 0.5068 [2021-03-26 03:21:56 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 770/1251] eta: 0:04:05 lr: 0.000600 loss: 3.2237 (3.3545) grad_norm: 1.3023 (1.3150) time: 0.5010 [2021-03-26 03:22:01 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 780/1251] eta: 0:04:00 lr: 0.000600 loss: 3.2237 (3.3559) grad_norm: 1.3113 (1.3149) time: 0.5020 [2021-03-26 03:22:06 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 790/1251] eta: 0:03:55 lr: 0.000600 loss: 3.5072 (3.3561) grad_norm: 1.3113 (1.3154) time: 0.5045 [2021-03-26 03:22:11 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 800/1251] eta: 0:03:50 lr: 0.000600 loss: 3.5216 (3.3575) grad_norm: 1.2767 (1.3148) time: 0.5058 [2021-03-26 03:22:16 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 810/1251] eta: 0:03:45 lr: 0.000600 loss: 3.4732 (3.3566) grad_norm: 1.2619 (1.3137) time: 0.5048 [2021-03-26 03:22:21 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 820/1251] eta: 0:03:39 lr: 0.000600 loss: 3.3924 (3.3591) grad_norm: 1.2386 (1.3131) time: 0.4992 [2021-03-26 03:22:26 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 830/1251] eta: 0:03:34 lr: 0.000599 loss: 3.5141 (3.3600) grad_norm: 1.2386 (1.3120) time: 0.5009 [2021-03-26 03:22:31 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 840/1251] eta: 0:03:29 lr: 0.000599 loss: 3.5141 (3.3618) grad_norm: 1.2707 (1.3122) time: 0.5049 [2021-03-26 03:22:37 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 850/1251] eta: 0:03:24 lr: 0.000599 loss: 3.5708 (3.3635) grad_norm: 1.2848 (1.3120) time: 0.5079 [2021-03-26 03:22:42 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 860/1251] eta: 0:03:19 lr: 0.000599 loss: 3.3027 (3.3621) grad_norm: 1.2312 (1.3116) time: 0.5098 [2021-03-26 03:22:47 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 870/1251] eta: 0:03:14 lr: 0.000599 loss: 3.2429 (3.3612) grad_norm: 1.3103 (1.3120) time: 0.5077 [2021-03-26 03:22:52 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 880/1251] eta: 0:03:09 lr: 0.000599 loss: 3.2551 (3.3613) grad_norm: 1.3219 (1.3118) time: 0.5103 [2021-03-26 03:22:57 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 890/1251] eta: 0:03:04 lr: 0.000599 loss: 3.4368 (3.3602) grad_norm: 1.2990 (1.3124) time: 0.5115 [2021-03-26 03:23:02 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 900/1251] eta: 0:02:59 lr: 0.000599 loss: 3.3091 (3.3619) grad_norm: 1.3364 (1.3125) time: 0.5122 [2021-03-26 03:23:07 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 910/1251] eta: 0:02:53 lr: 0.000599 loss: 3.3091 (3.3603) grad_norm: 1.2497 (inf) time: 0.5059 [2021-03-26 03:23:12 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 920/1251] eta: 0:02:48 lr: 0.000599 loss: 3.4639 (3.3622) grad_norm: 1.2644 (inf) time: 0.5024 [2021-03-26 03:23:17 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 930/1251] eta: 0:02:43 lr: 0.000599 loss: 3.4692 (3.3612) grad_norm: 1.3308 (inf) time: 0.5062 [2021-03-26 03:23:22 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 940/1251] eta: 0:02:38 lr: 0.000599 loss: 3.3205 (3.3618) grad_norm: 1.3440 (inf) time: 0.5085 [2021-03-26 03:23:27 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 950/1251] eta: 0:02:33 lr: 0.000599 loss: 3.2673 (3.3603) grad_norm: 1.2145 (inf) time: 0.5069 [2021-03-26 03:23:32 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 960/1251] eta: 0:02:28 lr: 0.000599 loss: 3.4128 (3.3644) grad_norm: 1.2431 (inf) time: 0.5019 [2021-03-26 03:23:37 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 970/1251] eta: 0:02:23 lr: 0.000599 loss: 3.4639 (3.3617) grad_norm: 1.2431 (inf) time: 0.5021 [2021-03-26 03:23:42 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 980/1251] eta: 0:02:18 lr: 0.000599 loss: 3.2763 (3.3611) grad_norm: 1.2729 (inf) time: 0.5015 [2021-03-26 03:23:48 swin_small_patch4_window7_224] INFO: Epoch: [131] [ 990/1251] eta: 0:02:13 lr: 0.000599 loss: 3.4269 (3.3606) grad_norm: 1.3196 (inf) time: 0.5077 [2021-03-26 03:23:53 swin_small_patch4_window7_224] INFO: Epoch: [131] [1000/1251] eta: 0:02:07 lr: 0.000599 loss: 3.1933 (3.3607) grad_norm: 1.2804 (inf) time: 0.5103 [2021-03-26 03:23:58 swin_small_patch4_window7_224] INFO: Epoch: [131] [1010/1251] eta: 0:02:02 lr: 0.000599 loss: 3.1933 (3.3603) grad_norm: 1.2804 (inf) time: 0.5028 [2021-03-26 03:24:03 swin_small_patch4_window7_224] INFO: Epoch: [131] [1020/1251] eta: 0:01:57 lr: 0.000599 loss: 3.5254 (3.3618) grad_norm: 1.3225 (inf) time: 0.4993 [2021-03-26 03:24:08 swin_small_patch4_window7_224] INFO: Epoch: [131] [1030/1251] eta: 0:01:52 lr: 0.000599 loss: 3.6237 (3.3643) grad_norm: 1.2742 (inf) time: 0.5004 [2021-03-26 03:24:13 swin_small_patch4_window7_224] INFO: Epoch: [131] [1040/1251] eta: 0:01:47 lr: 0.000599 loss: 3.5953 (3.3650) grad_norm: 1.2544 (inf) time: 0.5075 [2021-03-26 03:24:18 swin_small_patch4_window7_224] INFO: Epoch: [131] [1050/1251] eta: 0:01:42 lr: 0.000599 loss: 3.6226 (3.3673) grad_norm: 1.2544 (inf) time: 0.5164 [2021-03-26 03:24:23 swin_small_patch4_window7_224] INFO: Epoch: [131] [1060/1251] eta: 0:01:37 lr: 0.000599 loss: 3.6226 (3.3684) grad_norm: 1.2620 (inf) time: 0.5104 [2021-03-26 03:24:28 swin_small_patch4_window7_224] INFO: Epoch: [131] [1070/1251] eta: 0:01:32 lr: 0.000598 loss: 3.5895 (3.3687) grad_norm: 1.2881 (inf) time: 0.5015 [2021-03-26 03:24:33 swin_small_patch4_window7_224] INFO: Epoch: [131] [1080/1251] eta: 0:01:27 lr: 0.000598 loss: 3.4339 (3.3695) grad_norm: 1.2815 (inf) time: 0.5039 [2021-03-26 03:24:38 swin_small_patch4_window7_224] INFO: Epoch: [131] [1090/1251] eta: 0:01:22 lr: 0.000598 loss: 3.4339 (3.3698) grad_norm: 1.2097 (inf) time: 0.5042 [2021-03-26 03:24:43 swin_small_patch4_window7_224] INFO: Epoch: [131] [1100/1251] eta: 0:01:16 lr: 0.000598 loss: 3.5382 (3.3723) grad_norm: 1.3433 (inf) time: 0.5054 [2021-03-26 03:24:48 swin_small_patch4_window7_224] INFO: Epoch: [131] [1110/1251] eta: 0:01:11 lr: 0.000598 loss: 3.5753 (3.3737) grad_norm: 1.3433 (inf) time: 0.5070 [2021-03-26 03:24:53 swin_small_patch4_window7_224] INFO: Epoch: [131] [1120/1251] eta: 0:01:06 lr: 0.000598 loss: 3.5753 (3.3751) grad_norm: 1.3284 (inf) time: 0.5052 [2021-03-26 03:24:58 swin_small_patch4_window7_224] INFO: Epoch: [131] [1130/1251] eta: 0:01:01 lr: 0.000598 loss: 3.4631 (3.3731) grad_norm: 1.3071 (inf) time: 0.5019 [2021-03-26 03:25:03 swin_small_patch4_window7_224] INFO: Epoch: [131] [1140/1251] eta: 0:00:56 lr: 0.000598 loss: 3.4390 (3.3739) grad_norm: 1.2858 (inf) time: 0.5015 [2021-03-26 03:25:08 swin_small_patch4_window7_224] INFO: Epoch: [131] [1150/1251] eta: 0:00:51 lr: 0.000598 loss: 3.4994 (3.3723) grad_norm: 1.2852 (inf) time: 0.5044 [2021-03-26 03:25:13 swin_small_patch4_window7_224] INFO: Epoch: [131] [1160/1251] eta: 0:00:46 lr: 0.000598 loss: 3.2967 (3.3719) grad_norm: 1.2786 (inf) time: 0.5043 [2021-03-26 03:25:18 swin_small_patch4_window7_224] INFO: Epoch: [131] [1170/1251] eta: 0:00:41 lr: 0.000598 loss: 3.6044 (3.3744) grad_norm: 1.3871 (inf) time: 0.5057 [2021-03-26 03:25:24 swin_small_patch4_window7_224] INFO: Epoch: [131] [1180/1251] eta: 0:00:36 lr: 0.000598 loss: 3.6105 (3.3750) grad_norm: 1.3650 (inf) time: 0.5117 [2021-03-26 03:25:29 swin_small_patch4_window7_224] INFO: Epoch: [131] [1190/1251] eta: 0:00:31 lr: 0.000598 loss: 3.6105 (3.3764) grad_norm: 1.3353 (inf) time: 0.5113 [2021-03-26 03:25:34 swin_small_patch4_window7_224] INFO: Epoch: [131] [1200/1251] eta: 0:00:25 lr: 0.000598 loss: 3.5585 (3.3764) grad_norm: 1.3120 (inf) time: 0.5037 [2021-03-26 03:25:39 swin_small_patch4_window7_224] INFO: Epoch: [131] [1210/1251] eta: 0:00:20 lr: 0.000598 loss: 3.5585 (3.3773) grad_norm: 1.2953 (inf) time: 0.5041 [2021-03-26 03:25:44 swin_small_patch4_window7_224] INFO: Epoch: [131] [1220/1251] eta: 0:00:15 lr: 0.000598 loss: 3.6162 (3.3783) grad_norm: 1.2684 (inf) time: 0.5019 [2021-03-26 03:25:49 swin_small_patch4_window7_224] INFO: Epoch: [131] [1230/1251] eta: 0:00:10 lr: 0.000598 loss: 3.5815 (3.3792) grad_norm: 1.2684 (inf) time: 0.4983 [2021-03-26 03:25:54 swin_small_patch4_window7_224] INFO: Epoch: [131] [1240/1251] eta: 0:00:05 lr: 0.000598 loss: 3.3691 (3.3778) grad_norm: 1.2799 (inf) time: 0.4951 [2021-03-26 03:25:58 swin_small_patch4_window7_224] INFO: Epoch: [131] [1250/1251] eta: 0:00:00 lr: 0.000598 loss: 3.2386 (3.3765) grad_norm: 1.2994 (inf) time: 0.4883 [2021-03-26 03:26:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 0.7351 (0.7351) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 03:26:08 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 1.0181 (0.9985) acc1: 75.0000 (76.2784) acc5: 93.7500 (94.0341) [2021-03-26 03:26:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9442 (0.9270) acc1: 78.1250 (77.6786) acc5: 95.3125 (94.9405) [2021-03-26 03:26:13 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9101 (0.9439) acc1: 79.6875 (77.4698) acc5: 96.8750 (94.8589) [2021-03-26 03:26:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9232 (0.9483) acc1: 76.5625 (77.0198) acc5: 93.7500 (94.6646) [2021-03-26 03:26:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9218 (0.9560) acc1: 76.5625 (77.0240) acc5: 93.7500 (94.4320) [2021-03-26 03:26:21 swin_small_patch4_window7_224] INFO: * Acc@1 77.534 Acc@5 94.058 loss 0.953 [2021-03-26 03:26:21 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.5% [2021-03-26 03:26:21 swin_small_patch4_window7_224] INFO: Max accuracy: 77.53% [2021-03-26 03:26:25 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 0/1251] eta: 1:27:58 lr: 0.000598 loss: 3.7574 (3.7574) grad_norm: 1.4772 (1.4772) time: 4.2190 [2021-03-26 03:26:30 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 10/1251] eta: 0:17:57 lr: 0.000598 loss: 3.0387 (2.9826) grad_norm: 1.3045 (1.2961) time: 0.8684 [2021-03-26 03:26:35 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 20/1251] eta: 0:14:17 lr: 0.000598 loss: 3.1233 (3.1544) grad_norm: 1.3045 (1.3036) time: 0.5205 [2021-03-26 03:26:40 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 30/1251] eta: 0:12:55 lr: 0.000598 loss: 3.3266 (3.1890) grad_norm: 1.2567 (1.2873) time: 0.5072 [2021-03-26 03:26:46 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 40/1251] eta: 0:12:12 lr: 0.000598 loss: 3.1876 (3.2470) grad_norm: 1.1769 (1.2773) time: 0.5086 [2021-03-26 03:26:51 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 50/1251] eta: 0:11:40 lr: 0.000598 loss: 3.1816 (3.2394) grad_norm: 1.2212 (1.2727) time: 0.5035 [2021-03-26 03:26:56 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 60/1251] eta: 0:11:19 lr: 0.000598 loss: 3.3578 (3.2843) grad_norm: 1.3383 (1.2905) time: 0.5010 [2021-03-26 03:27:01 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 70/1251] eta: 0:11:01 lr: 0.000597 loss: 3.3578 (3.2639) grad_norm: 1.3247 (1.2886) time: 0.5000 [2021-03-26 03:27:06 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 80/1251] eta: 0:10:48 lr: 0.000597 loss: 3.4731 (3.2990) grad_norm: 1.2253 (1.2819) time: 0.5016 [2021-03-26 03:27:11 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 90/1251] eta: 0:10:36 lr: 0.000597 loss: 3.4907 (3.2961) grad_norm: 1.3291 (1.2904) time: 0.5078 [2021-03-26 03:27:16 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 100/1251] eta: 0:10:26 lr: 0.000597 loss: 3.1539 (3.2817) grad_norm: 1.3291 (1.2952) time: 0.5060 [2021-03-26 03:27:21 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 110/1251] eta: 0:10:17 lr: 0.000597 loss: 3.3536 (3.2919) grad_norm: 1.2731 (1.2898) time: 0.5084 [2021-03-26 03:27:26 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 120/1251] eta: 0:10:09 lr: 0.000597 loss: 3.3498 (3.2884) grad_norm: 1.2687 (1.2885) time: 0.5127 [2021-03-26 03:27:31 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 130/1251] eta: 0:10:01 lr: 0.000597 loss: 3.3785 (3.3069) grad_norm: 1.2742 (1.2914) time: 0.5092 [2021-03-26 03:27:36 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 140/1251] eta: 0:09:53 lr: 0.000597 loss: 3.3864 (3.3033) grad_norm: 1.2899 (1.2915) time: 0.5029 [2021-03-26 03:27:41 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 150/1251] eta: 0:09:45 lr: 0.000597 loss: 3.3334 (3.2988) grad_norm: 1.2727 (1.2917) time: 0.4998 [2021-03-26 03:27:46 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 160/1251] eta: 0:09:38 lr: 0.000597 loss: 3.3334 (3.2959) grad_norm: 1.2980 (1.2945) time: 0.5013 [2021-03-26 03:27:51 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 170/1251] eta: 0:09:31 lr: 0.000597 loss: 3.4409 (3.3016) grad_norm: 1.3357 (1.2964) time: 0.5072 [2021-03-26 03:27:56 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 180/1251] eta: 0:09:25 lr: 0.000597 loss: 3.5395 (3.3112) grad_norm: 1.3089 (1.2978) time: 0.5123 [2021-03-26 03:28:01 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 190/1251] eta: 0:09:18 lr: 0.000597 loss: 3.5303 (3.3195) grad_norm: 1.2987 (1.3019) time: 0.5107 [2021-03-26 03:28:07 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 200/1251] eta: 0:09:12 lr: 0.000597 loss: 3.4112 (3.3284) grad_norm: 1.3364 (1.3053) time: 0.5097 [2021-03-26 03:28:12 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 210/1251] eta: 0:09:06 lr: 0.000597 loss: 3.3723 (3.3164) grad_norm: 1.3642 (1.3128) time: 0.5094 [2021-03-26 03:28:17 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 220/1251] eta: 0:09:00 lr: 0.000597 loss: 3.4715 (3.3221) grad_norm: 1.3275 (1.3122) time: 0.5069 [2021-03-26 03:28:22 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 230/1251] eta: 0:08:55 lr: 0.000597 loss: 3.4715 (3.3200) grad_norm: 1.3179 (1.3130) time: 0.5180 [2021-03-26 03:28:27 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 240/1251] eta: 0:08:49 lr: 0.000597 loss: 3.4712 (3.3278) grad_norm: 1.3488 (1.3137) time: 0.5141 [2021-03-26 03:28:32 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 250/1251] eta: 0:08:43 lr: 0.000597 loss: 3.4943 (3.3296) grad_norm: 1.2826 (1.3132) time: 0.5009 [2021-03-26 03:28:37 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 260/1251] eta: 0:08:37 lr: 0.000597 loss: 3.3981 (3.3256) grad_norm: 1.2597 (1.3117) time: 0.5052 [2021-03-26 03:28:42 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 270/1251] eta: 0:08:31 lr: 0.000597 loss: 3.4439 (3.3330) grad_norm: 1.2580 (1.3119) time: 0.5040 [2021-03-26 03:28:47 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 280/1251] eta: 0:08:25 lr: 0.000597 loss: 3.5741 (3.3436) grad_norm: 1.3088 (1.3118) time: 0.5025 [2021-03-26 03:28:52 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 290/1251] eta: 0:08:20 lr: 0.000597 loss: 3.4697 (3.3412) grad_norm: 1.3131 (1.3115) time: 0.5069 [2021-03-26 03:28:57 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 300/1251] eta: 0:08:14 lr: 0.000597 loss: 3.1432 (3.3352) grad_norm: 1.2914 (1.3108) time: 0.5028 [2021-03-26 03:29:02 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 310/1251] eta: 0:08:08 lr: 0.000596 loss: 3.1923 (3.3315) grad_norm: 1.2785 (1.3107) time: 0.5039 [2021-03-26 03:29:07 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 320/1251] eta: 0:08:03 lr: 0.000596 loss: 3.4220 (3.3294) grad_norm: 1.2849 (1.3103) time: 0.5138 [2021-03-26 03:29:12 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 330/1251] eta: 0:07:57 lr: 0.000596 loss: 3.5296 (3.3331) grad_norm: 1.2770 (1.3112) time: 0.5092 [2021-03-26 03:29:18 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 340/1251] eta: 0:07:52 lr: 0.000596 loss: 3.5339 (3.3402) grad_norm: 1.3023 (1.3121) time: 0.5095 [2021-03-26 03:29:23 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 350/1251] eta: 0:07:46 lr: 0.000596 loss: 3.4939 (3.3440) grad_norm: 1.3023 (1.3126) time: 0.5115 [2021-03-26 03:29:28 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 360/1251] eta: 0:07:41 lr: 0.000596 loss: 3.2578 (3.3362) grad_norm: 1.2964 (1.3133) time: 0.5010 [2021-03-26 03:29:33 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 370/1251] eta: 0:07:35 lr: 0.000596 loss: 3.2578 (3.3365) grad_norm: 1.3023 (1.3127) time: 0.5032 [2021-03-26 03:29:38 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 380/1251] eta: 0:07:30 lr: 0.000596 loss: 3.3564 (3.3376) grad_norm: 1.2516 (1.3108) time: 0.5061 [2021-03-26 03:29:43 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 390/1251] eta: 0:07:24 lr: 0.000596 loss: 3.5906 (3.3496) grad_norm: 1.2100 (1.3076) time: 0.5047 [2021-03-26 03:29:48 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 400/1251] eta: 0:07:19 lr: 0.000596 loss: 3.5906 (3.3542) grad_norm: 1.2411 (1.3089) time: 0.5093 [2021-03-26 03:29:53 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 410/1251] eta: 0:07:14 lr: 0.000596 loss: 3.3044 (3.3498) grad_norm: 1.3091 (1.3117) time: 0.5048 [2021-03-26 03:29:58 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 420/1251] eta: 0:07:08 lr: 0.000596 loss: 3.3334 (3.3535) grad_norm: 1.2934 (1.3121) time: 0.5025 [2021-03-26 03:30:03 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 430/1251] eta: 0:07:03 lr: 0.000596 loss: 3.4447 (3.3491) grad_norm: 1.2976 (1.3130) time: 0.5091 [2021-03-26 03:30:08 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 440/1251] eta: 0:06:58 lr: 0.000596 loss: 3.2857 (3.3488) grad_norm: 1.2976 (1.3131) time: 0.5064 [2021-03-26 03:30:13 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 450/1251] eta: 0:06:52 lr: 0.000596 loss: 3.5207 (3.3506) grad_norm: 1.2736 (1.3121) time: 0.5086 [2021-03-26 03:30:18 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 460/1251] eta: 0:06:47 lr: 0.000596 loss: 3.6209 (3.3521) grad_norm: 1.2911 (1.3129) time: 0.5073 [2021-03-26 03:30:23 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 470/1251] eta: 0:06:42 lr: 0.000596 loss: 3.6607 (3.3576) grad_norm: 1.3315 (1.3142) time: 0.5027 [2021-03-26 03:30:28 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 480/1251] eta: 0:06:36 lr: 0.000596 loss: 3.5426 (3.3566) grad_norm: 1.3315 (1.3150) time: 0.5024 [2021-03-26 03:30:33 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 490/1251] eta: 0:06:31 lr: 0.000596 loss: 3.1630 (3.3526) grad_norm: 1.3276 (1.3151) time: 0.5017 [2021-03-26 03:30:38 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 500/1251] eta: 0:06:26 lr: 0.000596 loss: 3.2348 (3.3549) grad_norm: 1.3276 (1.3147) time: 0.5007 [2021-03-26 03:30:43 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 510/1251] eta: 0:06:20 lr: 0.000596 loss: 3.4349 (3.3535) grad_norm: 1.2612 (1.3147) time: 0.4970 [2021-03-26 03:30:48 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 520/1251] eta: 0:06:15 lr: 0.000596 loss: 3.3988 (3.3555) grad_norm: 1.2893 (1.3147) time: 0.5049 [2021-03-26 03:30:53 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 530/1251] eta: 0:06:10 lr: 0.000596 loss: 3.5379 (3.3613) grad_norm: 1.2909 (1.3142) time: 0.5054 [2021-03-26 03:30:58 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 540/1251] eta: 0:06:04 lr: 0.000596 loss: 3.4917 (3.3631) grad_norm: 1.3215 (1.3142) time: 0.5001 [2021-03-26 03:31:04 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 550/1251] eta: 0:05:59 lr: 0.000596 loss: 3.4600 (3.3667) grad_norm: 1.3297 (1.3141) time: 0.5075 [2021-03-26 03:31:09 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 560/1251] eta: 0:05:54 lr: 0.000595 loss: 3.6184 (3.3702) grad_norm: 1.3041 (1.3133) time: 0.5049 [2021-03-26 03:31:14 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 570/1251] eta: 0:05:49 lr: 0.000595 loss: 3.5737 (3.3726) grad_norm: 1.3011 (1.3147) time: 0.5004 [2021-03-26 03:31:19 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 580/1251] eta: 0:05:44 lr: 0.000595 loss: 3.4797 (3.3705) grad_norm: 1.3176 (1.3158) time: 0.5053 [2021-03-26 03:31:24 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 590/1251] eta: 0:05:38 lr: 0.000595 loss: 3.3014 (3.3720) grad_norm: 1.3288 (1.3160) time: 0.5058 [2021-03-26 03:31:29 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 600/1251] eta: 0:05:33 lr: 0.000595 loss: 3.3393 (3.3718) grad_norm: 1.3166 (1.3162) time: 0.5099 [2021-03-26 03:31:34 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 610/1251] eta: 0:05:28 lr: 0.000595 loss: 3.3477 (3.3730) grad_norm: 1.2592 (1.3152) time: 0.5083 [2021-03-26 03:31:39 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 620/1251] eta: 0:05:23 lr: 0.000595 loss: 3.3620 (3.3742) grad_norm: 1.2292 (1.3149) time: 0.4998 [2021-03-26 03:31:44 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 630/1251] eta: 0:05:18 lr: 0.000595 loss: 3.3620 (3.3716) grad_norm: 1.2431 (1.3145) time: 0.5034 [2021-03-26 03:31:49 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 640/1251] eta: 0:05:12 lr: 0.000595 loss: 3.4233 (3.3750) grad_norm: 1.2431 (1.3135) time: 0.5068 [2021-03-26 03:31:54 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 650/1251] eta: 0:05:07 lr: 0.000595 loss: 3.4714 (3.3733) grad_norm: 1.2611 (1.3129) time: 0.5056 [2021-03-26 03:31:59 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 660/1251] eta: 0:05:02 lr: 0.000595 loss: 3.3942 (3.3759) grad_norm: 1.2620 (1.3117) time: 0.5045 [2021-03-26 03:32:04 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 670/1251] eta: 0:04:57 lr: 0.000595 loss: 3.1776 (3.3678) grad_norm: 1.2813 (1.3132) time: 0.5084 [2021-03-26 03:32:09 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 680/1251] eta: 0:04:52 lr: 0.000595 loss: 3.1776 (3.3674) grad_norm: 1.3265 (1.3128) time: 0.5127 [2021-03-26 03:32:14 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 690/1251] eta: 0:04:47 lr: 0.000595 loss: 3.3405 (3.3673) grad_norm: 1.2779 (1.3129) time: 0.5082 [2021-03-26 03:32:20 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 700/1251] eta: 0:04:41 lr: 0.000595 loss: 3.2851 (3.3680) grad_norm: 1.3301 (1.3133) time: 0.5062 [2021-03-26 03:32:25 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 710/1251] eta: 0:04:36 lr: 0.000595 loss: 3.3974 (3.3678) grad_norm: 1.3370 (1.3136) time: 0.5076 [2021-03-26 03:32:30 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 720/1251] eta: 0:04:31 lr: 0.000595 loss: 3.4012 (3.3671) grad_norm: 1.3370 (1.3138) time: 0.5085 [2021-03-26 03:32:35 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 730/1251] eta: 0:04:26 lr: 0.000595 loss: 3.2612 (3.3664) grad_norm: 1.3085 (1.3136) time: 0.5038 [2021-03-26 03:32:40 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 740/1251] eta: 0:04:21 lr: 0.000595 loss: 3.4141 (3.3697) grad_norm: 1.3085 (1.3145) time: 0.5159 [2021-03-26 03:32:45 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 750/1251] eta: 0:04:16 lr: 0.000595 loss: 3.5714 (3.3676) grad_norm: 1.3390 (1.3152) time: 0.5264 [2021-03-26 03:32:50 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 760/1251] eta: 0:04:11 lr: 0.000595 loss: 3.2914 (3.3671) grad_norm: 1.3405 (1.3153) time: 0.5093 [2021-03-26 03:32:55 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 770/1251] eta: 0:04:06 lr: 0.000595 loss: 3.2914 (3.3660) grad_norm: 1.3311 (1.3153) time: 0.5000 [2021-03-26 03:33:00 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 780/1251] eta: 0:04:00 lr: 0.000595 loss: 3.3426 (3.3659) grad_norm: 1.3324 (1.3154) time: 0.5010 [2021-03-26 03:33:05 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 790/1251] eta: 0:03:55 lr: 0.000595 loss: 3.3002 (3.3663) grad_norm: 1.3548 (1.3157) time: 0.5063 [2021-03-26 03:33:10 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 800/1251] eta: 0:03:50 lr: 0.000594 loss: 3.3002 (3.3662) grad_norm: 1.3512 (1.3157) time: 0.5021 [2021-03-26 03:33:15 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 810/1251] eta: 0:03:45 lr: 0.000594 loss: 3.4569 (3.3686) grad_norm: 1.3506 (1.3161) time: 0.4976 [2021-03-26 03:33:20 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 820/1251] eta: 0:03:40 lr: 0.000594 loss: 3.5254 (3.3711) grad_norm: 1.2944 (1.3158) time: 0.5027 [2021-03-26 03:33:25 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 830/1251] eta: 0:03:35 lr: 0.000594 loss: 3.3386 (3.3691) grad_norm: 1.2361 (1.3147) time: 0.5035 [2021-03-26 03:33:30 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 840/1251] eta: 0:03:29 lr: 0.000594 loss: 3.3386 (3.3705) grad_norm: 1.2507 (1.3153) time: 0.5036 [2021-03-26 03:33:35 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 850/1251] eta: 0:03:24 lr: 0.000594 loss: 3.4564 (3.3691) grad_norm: 1.2601 (1.3156) time: 0.5042 [2021-03-26 03:33:40 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 860/1251] eta: 0:03:19 lr: 0.000594 loss: 3.5249 (3.3691) grad_norm: 1.2656 (1.3154) time: 0.5010 [2021-03-26 03:33:46 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 870/1251] eta: 0:03:14 lr: 0.000594 loss: 3.2824 (3.3672) grad_norm: 1.2918 (1.3157) time: 0.5031 [2021-03-26 03:33:51 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 880/1251] eta: 0:03:09 lr: 0.000594 loss: 2.9940 (3.3630) grad_norm: 1.3140 (1.3158) time: 0.5114 [2021-03-26 03:33:56 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 890/1251] eta: 0:03:04 lr: 0.000594 loss: 3.3531 (3.3657) grad_norm: 1.3181 (1.3163) time: 0.5060 [2021-03-26 03:34:01 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 900/1251] eta: 0:02:59 lr: 0.000594 loss: 3.4392 (3.3677) grad_norm: 1.3181 (1.3167) time: 0.5009 [2021-03-26 03:34:06 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 910/1251] eta: 0:02:53 lr: 0.000594 loss: 3.5690 (3.3685) grad_norm: 1.2970 (1.3166) time: 0.5000 [2021-03-26 03:34:11 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 920/1251] eta: 0:02:48 lr: 0.000594 loss: 3.6235 (3.3701) grad_norm: 1.3058 (1.3172) time: 0.5017 [2021-03-26 03:34:16 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 930/1251] eta: 0:02:43 lr: 0.000594 loss: 3.4278 (3.3680) grad_norm: 1.3193 (1.3178) time: 0.5047 [2021-03-26 03:34:21 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 940/1251] eta: 0:02:38 lr: 0.000594 loss: 3.4918 (3.3712) grad_norm: 1.3263 (1.3180) time: 0.5068 [2021-03-26 03:34:26 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 950/1251] eta: 0:02:33 lr: 0.000594 loss: 3.4925 (3.3721) grad_norm: 1.3379 (1.3182) time: 0.5140 [2021-03-26 03:34:31 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 960/1251] eta: 0:02:28 lr: 0.000594 loss: 3.4677 (3.3741) grad_norm: 1.2620 (1.3182) time: 0.5150 [2021-03-26 03:34:36 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 970/1251] eta: 0:02:23 lr: 0.000594 loss: 3.5493 (3.3727) grad_norm: 1.3128 (1.3187) time: 0.5083 [2021-03-26 03:34:41 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 980/1251] eta: 0:02:18 lr: 0.000594 loss: 3.4885 (3.3708) grad_norm: 1.3426 (1.3189) time: 0.5074 [2021-03-26 03:34:46 swin_small_patch4_window7_224] INFO: Epoch: [132] [ 990/1251] eta: 0:02:13 lr: 0.000594 loss: 3.4333 (3.3712) grad_norm: 1.3117 (1.3187) time: 0.5077 [2021-03-26 03:34:52 swin_small_patch4_window7_224] INFO: Epoch: [132] [1000/1251] eta: 0:02:08 lr: 0.000594 loss: 3.3957 (3.3708) grad_norm: 1.2597 (1.3180) time: 0.5113 [2021-03-26 03:34:57 swin_small_patch4_window7_224] INFO: Epoch: [132] [1010/1251] eta: 0:02:02 lr: 0.000594 loss: 3.2258 (3.3703) grad_norm: 1.2595 (1.3180) time: 0.5089 [2021-03-26 03:35:02 swin_small_patch4_window7_224] INFO: Epoch: [132] [1020/1251] eta: 0:01:57 lr: 0.000594 loss: 3.3854 (3.3719) grad_norm: 1.3114 (1.3185) time: 0.5037 [2021-03-26 03:35:07 swin_small_patch4_window7_224] INFO: Epoch: [132] [1030/1251] eta: 0:01:52 lr: 0.000594 loss: 3.5387 (3.3735) grad_norm: 1.3114 (1.3181) time: 0.5045 [2021-03-26 03:35:12 swin_small_patch4_window7_224] INFO: Epoch: [132] [1040/1251] eta: 0:01:47 lr: 0.000594 loss: 3.4144 (3.3722) grad_norm: 1.2462 (1.3179) time: 0.4995 [2021-03-26 03:35:17 swin_small_patch4_window7_224] INFO: Epoch: [132] [1050/1251] eta: 0:01:42 lr: 0.000593 loss: 3.4144 (3.3721) grad_norm: 1.2734 (1.3189) time: 0.5001 [2021-03-26 03:35:22 swin_small_patch4_window7_224] INFO: Epoch: [132] [1060/1251] eta: 0:01:37 lr: 0.000593 loss: 3.5407 (3.3738) grad_norm: 1.3384 (1.3188) time: 0.5064 [2021-03-26 03:35:27 swin_small_patch4_window7_224] INFO: Epoch: [132] [1070/1251] eta: 0:01:32 lr: 0.000593 loss: 3.6002 (3.3769) grad_norm: 1.2951 (1.3191) time: 0.5095 [2021-03-26 03:35:32 swin_small_patch4_window7_224] INFO: Epoch: [132] [1080/1251] eta: 0:01:27 lr: 0.000593 loss: 3.5366 (3.3758) grad_norm: 1.3175 (1.3193) time: 0.5083 [2021-03-26 03:35:37 swin_small_patch4_window7_224] INFO: Epoch: [132] [1090/1251] eta: 0:01:22 lr: 0.000593 loss: 3.2984 (3.3743) grad_norm: 1.3007 (1.3191) time: 0.5061 [2021-03-26 03:35:42 swin_small_patch4_window7_224] INFO: Epoch: [132] [1100/1251] eta: 0:01:16 lr: 0.000593 loss: 3.2314 (3.3731) grad_norm: 1.2732 (1.3194) time: 0.5045 [2021-03-26 03:35:47 swin_small_patch4_window7_224] INFO: Epoch: [132] [1110/1251] eta: 0:01:11 lr: 0.000593 loss: 3.4367 (3.3736) grad_norm: 1.2976 (1.3197) time: 0.5050 [2021-03-26 03:35:52 swin_small_patch4_window7_224] INFO: Epoch: [132] [1120/1251] eta: 0:01:06 lr: 0.000593 loss: 3.4367 (3.3750) grad_norm: 1.2976 (1.3195) time: 0.5011 [2021-03-26 03:35:57 swin_small_patch4_window7_224] INFO: Epoch: [132] [1130/1251] eta: 0:01:01 lr: 0.000593 loss: 3.3615 (3.3747) grad_norm: 1.2469 (1.3194) time: 0.4994 [2021-03-26 03:36:02 swin_small_patch4_window7_224] INFO: Epoch: [132] [1140/1251] eta: 0:00:56 lr: 0.000593 loss: 3.4133 (3.3746) grad_norm: 1.2730 (1.3189) time: 0.5046 [2021-03-26 03:36:07 swin_small_patch4_window7_224] INFO: Epoch: [132] [1150/1251] eta: 0:00:51 lr: 0.000593 loss: 3.4356 (3.3756) grad_norm: 1.2730 (1.3186) time: 0.5040 [2021-03-26 03:36:12 swin_small_patch4_window7_224] INFO: Epoch: [132] [1160/1251] eta: 0:00:46 lr: 0.000593 loss: 3.5401 (3.3771) grad_norm: 1.3105 (1.3191) time: 0.4998 [2021-03-26 03:36:17 swin_small_patch4_window7_224] INFO: Epoch: [132] [1170/1251] eta: 0:00:41 lr: 0.000593 loss: 3.6182 (3.3802) grad_norm: 1.3307 (1.3197) time: 0.5068 [2021-03-26 03:36:22 swin_small_patch4_window7_224] INFO: Epoch: [132] [1180/1251] eta: 0:00:36 lr: 0.000593 loss: 3.5859 (3.3814) grad_norm: 1.2952 (1.3191) time: 0.5067 [2021-03-26 03:36:27 swin_small_patch4_window7_224] INFO: Epoch: [132] [1190/1251] eta: 0:00:31 lr: 0.000593 loss: 3.3930 (3.3804) grad_norm: 1.2834 (1.3194) time: 0.5020 [2021-03-26 03:36:32 swin_small_patch4_window7_224] INFO: Epoch: [132] [1200/1251] eta: 0:00:25 lr: 0.000593 loss: 3.2615 (3.3819) grad_norm: 1.2834 (1.3192) time: 0.5057 [2021-03-26 03:36:37 swin_small_patch4_window7_224] INFO: Epoch: [132] [1210/1251] eta: 0:00:20 lr: 0.000593 loss: 3.5578 (3.3820) grad_norm: 1.2967 (1.3198) time: 0.5060 [2021-03-26 03:36:42 swin_small_patch4_window7_224] INFO: Epoch: [132] [1220/1251] eta: 0:00:15 lr: 0.000593 loss: 3.3350 (3.3817) grad_norm: 1.3119 (1.3195) time: 0.5065 [2021-03-26 03:36:48 swin_small_patch4_window7_224] INFO: Epoch: [132] [1230/1251] eta: 0:00:10 lr: 0.000593 loss: 3.2209 (3.3808) grad_norm: 1.3224 (1.3196) time: 0.5100 [2021-03-26 03:36:53 swin_small_patch4_window7_224] INFO: Epoch: [132] [1240/1251] eta: 0:00:05 lr: 0.000593 loss: 3.3242 (3.3812) grad_norm: 1.2835 (1.3192) time: 0.5048 [2021-03-26 03:36:58 swin_small_patch4_window7_224] INFO: Epoch: [132] [1250/1251] eta: 0:00:00 lr: 0.000593 loss: 3.5226 (3.3812) grad_norm: 1.2647 (1.3186) time: 0.5045 [2021-03-26 03:37:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:47 loss: 1.1758 (1.1758) acc1: 70.3125 (70.3125) acc5: 92.1875 (92.1875) [2021-03-26 03:37:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 1.0026 (0.9842) acc1: 73.4375 (75.0000) acc5: 93.7500 (94.4602) [2021-03-26 03:37:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9954 (0.9956) acc1: 75.0000 (75.8929) acc5: 93.7500 (94.1964) [2021-03-26 03:37:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9107 (0.9538) acc1: 76.5625 (76.7137) acc5: 93.7500 (94.7077) [2021-03-26 03:37:15 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8464 (0.9427) acc1: 75.0000 (77.1723) acc5: 93.7500 (94.4360) [2021-03-26 03:37:16 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9844 (0.9510) acc1: 75.0000 (77.1200) acc5: 93.7500 (94.3360) [2021-03-26 03:37:22 swin_small_patch4_window7_224] INFO: * Acc@1 77.656 Acc@5 94.188 loss 0.944 [2021-03-26 03:37:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-26 03:37:22 swin_small_patch4_window7_224] INFO: Max accuracy: 77.66% [2021-03-26 03:37:26 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 0/1251] eta: 1:29:18 lr: 0.000593 loss: 3.6297 (3.6297) grad_norm: 1.2045 (1.2045) time: 4.2833 [2021-03-26 03:37:31 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 10/1251] eta: 0:17:49 lr: 0.000593 loss: 3.4986 (3.4324) grad_norm: 1.2557 (1.2955) time: 0.8615 [2021-03-26 03:37:37 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 20/1251] eta: 0:14:10 lr: 0.000593 loss: 3.1963 (3.2291) grad_norm: 1.2690 (1.3073) time: 0.5109 [2021-03-26 03:37:42 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 30/1251] eta: 0:12:52 lr: 0.000593 loss: 2.9713 (3.1834) grad_norm: 1.2492 (1.2932) time: 0.5067 [2021-03-26 03:37:47 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 40/1251] eta: 0:12:11 lr: 0.000592 loss: 3.3531 (3.2334) grad_norm: 1.2674 (1.2980) time: 0.5132 [2021-03-26 03:37:52 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 50/1251] eta: 0:11:42 lr: 0.000592 loss: 3.3531 (3.2414) grad_norm: 1.2674 (1.2931) time: 0.5102 [2021-03-26 03:37:57 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 60/1251] eta: 0:11:20 lr: 0.000592 loss: 3.2652 (3.2484) grad_norm: 1.2599 (1.2927) time: 0.5046 [2021-03-26 03:38:02 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 70/1251] eta: 0:11:02 lr: 0.000592 loss: 3.2749 (3.2313) grad_norm: 1.2960 (1.2997) time: 0.5000 [2021-03-26 03:38:07 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 80/1251] eta: 0:10:49 lr: 0.000592 loss: 3.3643 (3.2308) grad_norm: 1.3140 (1.3091) time: 0.5047 [2021-03-26 03:38:12 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 90/1251] eta: 0:10:38 lr: 0.000592 loss: 3.5234 (3.2524) grad_norm: 1.3310 (1.3127) time: 0.5102 [2021-03-26 03:38:17 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 100/1251] eta: 0:10:27 lr: 0.000592 loss: 3.5489 (3.2680) grad_norm: 1.3139 (1.3153) time: 0.5048 [2021-03-26 03:38:22 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 110/1251] eta: 0:10:18 lr: 0.000592 loss: 3.3896 (3.2791) grad_norm: 1.3313 (1.3222) time: 0.5069 [2021-03-26 03:38:27 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 120/1251] eta: 0:10:09 lr: 0.000592 loss: 3.5389 (3.3009) grad_norm: 1.4133 (1.3303) time: 0.5091 [2021-03-26 03:38:32 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 130/1251] eta: 0:10:01 lr: 0.000592 loss: 3.5389 (3.3068) grad_norm: 1.3651 (1.3299) time: 0.5081 [2021-03-26 03:38:37 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 140/1251] eta: 0:09:53 lr: 0.000592 loss: 3.4206 (3.3088) grad_norm: 1.2671 (1.3245) time: 0.5075 [2021-03-26 03:38:42 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 150/1251] eta: 0:09:46 lr: 0.000592 loss: 3.5121 (3.3267) grad_norm: 1.2672 (1.3204) time: 0.5028 [2021-03-26 03:38:48 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 160/1251] eta: 0:09:39 lr: 0.000592 loss: 3.5913 (3.3394) grad_norm: 1.2691 (1.3189) time: 0.5063 [2021-03-26 03:38:53 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 170/1251] eta: 0:09:32 lr: 0.000592 loss: 3.4509 (3.3405) grad_norm: 1.2530 (1.3187) time: 0.5083 [2021-03-26 03:38:58 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 180/1251] eta: 0:09:26 lr: 0.000592 loss: 3.3744 (3.3449) grad_norm: 1.2519 (1.3192) time: 0.5076 [2021-03-26 03:39:03 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 190/1251] eta: 0:09:18 lr: 0.000592 loss: 3.4435 (3.3523) grad_norm: 1.2519 (1.3175) time: 0.5022 [2021-03-26 03:39:08 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 200/1251] eta: 0:09:12 lr: 0.000592 loss: 3.4460 (3.3577) grad_norm: 1.2229 (1.3155) time: 0.4980 [2021-03-26 03:39:13 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 210/1251] eta: 0:09:06 lr: 0.000592 loss: 3.5205 (3.3625) grad_norm: 1.2792 (1.3160) time: 0.5047 [2021-03-26 03:39:18 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 220/1251] eta: 0:08:59 lr: 0.000592 loss: 3.5861 (3.3631) grad_norm: 1.3638 (1.3196) time: 0.5019 [2021-03-26 03:39:23 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 230/1251] eta: 0:08:53 lr: 0.000592 loss: 3.4230 (3.3610) grad_norm: 1.3495 (1.3193) time: 0.5008 [2021-03-26 03:39:28 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 240/1251] eta: 0:08:47 lr: 0.000592 loss: 3.4230 (3.3665) grad_norm: 1.2756 (1.3170) time: 0.5050 [2021-03-26 03:39:33 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 250/1251] eta: 0:08:41 lr: 0.000592 loss: 3.2862 (3.3660) grad_norm: 1.2756 (1.3192) time: 0.5061 [2021-03-26 03:39:38 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 260/1251] eta: 0:08:35 lr: 0.000592 loss: 3.2555 (3.3603) grad_norm: 1.3390 (1.3194) time: 0.5053 [2021-03-26 03:39:43 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 270/1251] eta: 0:08:29 lr: 0.000592 loss: 3.2555 (3.3590) grad_norm: 1.3142 (1.3191) time: 0.5011 [2021-03-26 03:39:48 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 280/1251] eta: 0:08:23 lr: 0.000592 loss: 3.2285 (3.3507) grad_norm: 1.3604 (1.3237) time: 0.4994 [2021-03-26 03:39:53 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 290/1251] eta: 0:08:18 lr: 0.000591 loss: 3.2750 (3.3507) grad_norm: 1.4162 (1.3236) time: 0.5022 [2021-03-26 03:39:58 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 300/1251] eta: 0:08:12 lr: 0.000591 loss: 3.2750 (3.3436) grad_norm: 1.2691 (1.3230) time: 0.5063 [2021-03-26 03:40:03 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 310/1251] eta: 0:08:07 lr: 0.000591 loss: 3.3252 (3.3479) grad_norm: 1.3145 (1.3243) time: 0.5079 [2021-03-26 03:40:08 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 320/1251] eta: 0:08:01 lr: 0.000591 loss: 3.5210 (3.3585) grad_norm: 1.4008 (1.3280) time: 0.5006 [2021-03-26 03:40:13 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 330/1251] eta: 0:07:55 lr: 0.000591 loss: 3.5210 (3.3583) grad_norm: 1.3531 (1.3280) time: 0.5011 [2021-03-26 03:40:18 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 340/1251] eta: 0:07:50 lr: 0.000591 loss: 3.4214 (3.3561) grad_norm: 1.2733 (1.3256) time: 0.5023 [2021-03-26 03:40:23 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 350/1251] eta: 0:07:45 lr: 0.000591 loss: 3.4141 (3.3630) grad_norm: 1.2075 (1.3228) time: 0.5058 [2021-03-26 03:40:28 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 360/1251] eta: 0:07:39 lr: 0.000591 loss: 3.4063 (3.3646) grad_norm: 1.2763 (1.3237) time: 0.5110 [2021-03-26 03:40:33 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 370/1251] eta: 0:07:34 lr: 0.000591 loss: 3.3548 (3.3598) grad_norm: 1.2897 (1.3235) time: 0.5031 [2021-03-26 03:40:38 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 380/1251] eta: 0:07:28 lr: 0.000591 loss: 3.5487 (3.3627) grad_norm: 1.2652 (1.3226) time: 0.4993 [2021-03-26 03:40:43 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 390/1251] eta: 0:07:22 lr: 0.000591 loss: 3.6074 (3.3670) grad_norm: 1.2498 (1.3207) time: 0.4959 [2021-03-26 03:40:48 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 400/1251] eta: 0:07:17 lr: 0.000591 loss: 3.4056 (3.3588) grad_norm: 1.2548 (1.3213) time: 0.4994 [2021-03-26 03:40:53 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 410/1251] eta: 0:07:12 lr: 0.000591 loss: 3.3915 (3.3640) grad_norm: 1.3300 (1.3222) time: 0.5049 [2021-03-26 03:40:58 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 420/1251] eta: 0:07:06 lr: 0.000591 loss: 3.2795 (3.3579) grad_norm: 1.2789 (1.3212) time: 0.5017 [2021-03-26 03:41:03 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 430/1251] eta: 0:07:01 lr: 0.000591 loss: 3.1080 (3.3539) grad_norm: 1.2789 (1.3212) time: 0.5035 [2021-03-26 03:41:09 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 440/1251] eta: 0:06:56 lr: 0.000591 loss: 3.3576 (3.3546) grad_norm: 1.2907 (1.3205) time: 0.5086 [2021-03-26 03:41:14 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 450/1251] eta: 0:06:51 lr: 0.000591 loss: 3.4050 (3.3573) grad_norm: 1.2921 (1.3201) time: 0.5045 [2021-03-26 03:41:19 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 460/1251] eta: 0:06:45 lr: 0.000591 loss: 3.6606 (3.3624) grad_norm: 1.2313 (1.3188) time: 0.5010 [2021-03-26 03:41:24 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 470/1251] eta: 0:06:40 lr: 0.000591 loss: 3.4885 (3.3641) grad_norm: 1.2130 (1.3168) time: 0.4988 [2021-03-26 03:41:29 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 480/1251] eta: 0:06:35 lr: 0.000591 loss: 3.2944 (3.3570) grad_norm: 1.2130 (1.3160) time: 0.5030 [2021-03-26 03:41:34 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 490/1251] eta: 0:06:29 lr: 0.000591 loss: 3.3694 (3.3585) grad_norm: 1.2712 (1.3165) time: 0.5097 [2021-03-26 03:41:39 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 500/1251] eta: 0:06:24 lr: 0.000591 loss: 3.4633 (3.3592) grad_norm: 1.2906 (1.3156) time: 0.5047 [2021-03-26 03:41:44 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 510/1251] eta: 0:06:19 lr: 0.000591 loss: 3.4633 (3.3614) grad_norm: 1.2081 (1.3143) time: 0.5033 [2021-03-26 03:41:49 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 520/1251] eta: 0:06:14 lr: 0.000591 loss: 3.5879 (3.3643) grad_norm: 1.2071 (1.3134) time: 0.5108 [2021-03-26 03:41:54 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 530/1251] eta: 0:06:09 lr: 0.000590 loss: 3.5272 (3.3647) grad_norm: 1.2585 (1.3132) time: 0.5091 [2021-03-26 03:41:59 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 540/1251] eta: 0:06:03 lr: 0.000590 loss: 3.3422 (3.3632) grad_norm: 1.2617 (1.3131) time: 0.5031 [2021-03-26 03:42:04 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 550/1251] eta: 0:05:59 lr: 0.000590 loss: 3.5065 (3.3675) grad_norm: 1.2632 (1.3137) time: 0.5186 [2021-03-26 03:42:09 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 560/1251] eta: 0:05:53 lr: 0.000590 loss: 3.5535 (3.3683) grad_norm: 1.2632 (1.3134) time: 0.5150 [2021-03-26 03:42:14 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 570/1251] eta: 0:05:48 lr: 0.000590 loss: 3.6515 (3.3735) grad_norm: 1.2700 (1.3137) time: 0.5008 [2021-03-26 03:42:19 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 580/1251] eta: 0:05:43 lr: 0.000590 loss: 3.6931 (3.3786) grad_norm: 1.2747 (1.3142) time: 0.5086 [2021-03-26 03:42:25 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 590/1251] eta: 0:05:38 lr: 0.000590 loss: 3.5266 (3.3737) grad_norm: 1.3369 (1.3151) time: 0.5121 [2021-03-26 03:42:30 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 600/1251] eta: 0:05:33 lr: 0.000590 loss: 3.2640 (3.3714) grad_norm: 1.3328 (1.3148) time: 0.5119 [2021-03-26 03:42:35 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 610/1251] eta: 0:05:28 lr: 0.000590 loss: 3.2340 (3.3668) grad_norm: 1.2608 (1.3143) time: 0.5095 [2021-03-26 03:42:40 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 620/1251] eta: 0:05:22 lr: 0.000590 loss: 3.0944 (3.3646) grad_norm: 1.2484 (1.3141) time: 0.5053 [2021-03-26 03:42:45 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 630/1251] eta: 0:05:17 lr: 0.000590 loss: 3.3545 (3.3632) grad_norm: 1.3128 (1.3150) time: 0.5082 [2021-03-26 03:42:50 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 640/1251] eta: 0:05:12 lr: 0.000590 loss: 3.3688 (3.3624) grad_norm: 1.3229 (1.3155) time: 0.5080 [2021-03-26 03:42:55 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 650/1251] eta: 0:05:07 lr: 0.000590 loss: 3.3688 (3.3615) grad_norm: 1.3396 (1.3154) time: 0.5032 [2021-03-26 03:43:00 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 660/1251] eta: 0:05:02 lr: 0.000590 loss: 3.4662 (3.3595) grad_norm: 1.2862 (1.3155) time: 0.5025 [2021-03-26 03:43:05 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 670/1251] eta: 0:04:56 lr: 0.000590 loss: 3.4904 (3.3597) grad_norm: 1.2512 (1.3149) time: 0.5033 [2021-03-26 03:43:10 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 680/1251] eta: 0:04:51 lr: 0.000590 loss: 3.3590 (3.3564) grad_norm: 1.2967 (1.3161) time: 0.5047 [2021-03-26 03:43:15 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 690/1251] eta: 0:04:46 lr: 0.000590 loss: 3.1739 (3.3546) grad_norm: 1.3996 (1.3173) time: 0.5092 [2021-03-26 03:43:20 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 700/1251] eta: 0:04:41 lr: 0.000590 loss: 3.1328 (3.3511) grad_norm: 1.3718 (1.3168) time: 0.5080 [2021-03-26 03:43:25 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 710/1251] eta: 0:04:36 lr: 0.000590 loss: 3.1939 (3.3511) grad_norm: 1.3084 (1.3172) time: 0.5059 [2021-03-26 03:43:30 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 720/1251] eta: 0:04:31 lr: 0.000590 loss: 3.3992 (3.3546) grad_norm: 1.3069 (1.3175) time: 0.5038 [2021-03-26 03:43:35 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 730/1251] eta: 0:04:26 lr: 0.000590 loss: 3.3992 (3.3559) grad_norm: 1.3361 (1.3188) time: 0.5034 [2021-03-26 03:43:41 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 740/1251] eta: 0:04:20 lr: 0.000590 loss: 3.3729 (3.3558) grad_norm: 1.3860 (1.3193) time: 0.5099 [2021-03-26 03:43:46 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 750/1251] eta: 0:04:15 lr: 0.000590 loss: 3.4225 (3.3577) grad_norm: 1.3841 (1.3196) time: 0.5104 [2021-03-26 03:43:51 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 760/1251] eta: 0:04:10 lr: 0.000590 loss: 3.5349 (3.3593) grad_norm: 1.3291 (1.3198) time: 0.5099 [2021-03-26 03:43:56 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 770/1251] eta: 0:04:05 lr: 0.000590 loss: 3.4219 (3.3587) grad_norm: 1.3259 (1.3196) time: 0.5149 [2021-03-26 03:44:01 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 780/1251] eta: 0:04:00 lr: 0.000589 loss: 3.1927 (3.3566) grad_norm: 1.2843 (1.3187) time: 0.5125 [2021-03-26 03:44:06 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 790/1251] eta: 0:03:55 lr: 0.000589 loss: 3.3298 (3.3576) grad_norm: 1.2587 (1.3181) time: 0.5065 [2021-03-26 03:44:11 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 800/1251] eta: 0:03:50 lr: 0.000589 loss: 3.4171 (3.3566) grad_norm: 1.2578 (1.3180) time: 0.5058 [2021-03-26 03:44:16 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 810/1251] eta: 0:03:45 lr: 0.000589 loss: 3.6219 (3.3590) grad_norm: 1.2388 (1.3182) time: 0.5030 [2021-03-26 03:44:21 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 820/1251] eta: 0:03:40 lr: 0.000589 loss: 3.6135 (3.3614) grad_norm: 1.3069 (1.3181) time: 0.5135 [2021-03-26 03:44:26 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 830/1251] eta: 0:03:34 lr: 0.000589 loss: 3.6135 (3.3624) grad_norm: 1.3005 (1.3184) time: 0.5131 [2021-03-26 03:44:31 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 840/1251] eta: 0:03:29 lr: 0.000589 loss: 3.3444 (3.3616) grad_norm: 1.2829 (1.3181) time: 0.4988 [2021-03-26 03:44:36 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 850/1251] eta: 0:03:24 lr: 0.000589 loss: 3.3444 (3.3607) grad_norm: 1.2691 (nan) time: 0.4997 [2021-03-26 03:44:42 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 860/1251] eta: 0:03:19 lr: 0.000589 loss: 3.2583 (3.3588) grad_norm: 1.2577 (nan) time: 0.5084 [2021-03-26 03:44:47 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 870/1251] eta: 0:03:14 lr: 0.000589 loss: 3.5601 (3.3621) grad_norm: 1.2498 (nan) time: 0.5106 [2021-03-26 03:44:52 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 880/1251] eta: 0:03:09 lr: 0.000589 loss: 3.4584 (3.3614) grad_norm: 1.3283 (nan) time: 0.5072 [2021-03-26 03:44:57 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 890/1251] eta: 0:03:04 lr: 0.000589 loss: 3.3641 (3.3584) grad_norm: 1.3145 (nan) time: 0.5045 [2021-03-26 03:45:02 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 900/1251] eta: 0:02:59 lr: 0.000589 loss: 3.2726 (3.3576) grad_norm: 1.2960 (nan) time: 0.4984 [2021-03-26 03:45:07 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 910/1251] eta: 0:02:53 lr: 0.000589 loss: 3.2675 (3.3562) grad_norm: 1.3292 (nan) time: 0.4959 [2021-03-26 03:45:12 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 920/1251] eta: 0:02:48 lr: 0.000589 loss: 3.2679 (3.3554) grad_norm: 1.2857 (nan) time: 0.5008 [2021-03-26 03:45:17 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 930/1251] eta: 0:02:43 lr: 0.000589 loss: 3.3578 (3.3554) grad_norm: 1.2535 (nan) time: 0.5077 [2021-03-26 03:45:22 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 940/1251] eta: 0:02:38 lr: 0.000589 loss: 3.0936 (3.3509) grad_norm: 1.2268 (nan) time: 0.5105 [2021-03-26 03:45:27 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 950/1251] eta: 0:02:33 lr: 0.000589 loss: 3.3144 (3.3513) grad_norm: 1.2574 (nan) time: 0.5073 [2021-03-26 03:45:32 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 960/1251] eta: 0:02:28 lr: 0.000589 loss: 3.5225 (3.3506) grad_norm: 1.2976 (nan) time: 0.5029 [2021-03-26 03:45:37 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 970/1251] eta: 0:02:23 lr: 0.000589 loss: 3.3253 (3.3498) grad_norm: 1.2989 (nan) time: 0.5036 [2021-03-26 03:45:42 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 980/1251] eta: 0:02:18 lr: 0.000589 loss: 3.4992 (3.3532) grad_norm: 1.3152 (nan) time: 0.5072 [2021-03-26 03:45:47 swin_small_patch4_window7_224] INFO: Epoch: [133] [ 990/1251] eta: 0:02:13 lr: 0.000589 loss: 3.5886 (3.3535) grad_norm: 1.4025 (nan) time: 0.5106 [2021-03-26 03:45:52 swin_small_patch4_window7_224] INFO: Epoch: [133] [1000/1251] eta: 0:02:07 lr: 0.000589 loss: 3.3780 (3.3537) grad_norm: 1.3126 (nan) time: 0.5123 [2021-03-26 03:45:57 swin_small_patch4_window7_224] INFO: Epoch: [133] [1010/1251] eta: 0:02:02 lr: 0.000589 loss: 3.3698 (3.3523) grad_norm: 1.2082 (nan) time: 0.5064 [2021-03-26 03:46:02 swin_small_patch4_window7_224] INFO: Epoch: [133] [1020/1251] eta: 0:01:57 lr: 0.000588 loss: 3.3879 (3.3529) grad_norm: 1.3416 (nan) time: 0.4986 [2021-03-26 03:46:07 swin_small_patch4_window7_224] INFO: Epoch: [133] [1030/1251] eta: 0:01:52 lr: 0.000588 loss: 3.4393 (3.3540) grad_norm: 1.3416 (nan) time: 0.5007 [2021-03-26 03:46:13 swin_small_patch4_window7_224] INFO: Epoch: [133] [1040/1251] eta: 0:01:47 lr: 0.000588 loss: 3.5444 (3.3556) grad_norm: 1.2685 (nan) time: 0.5102 [2021-03-26 03:46:18 swin_small_patch4_window7_224] INFO: Epoch: [133] [1050/1251] eta: 0:01:42 lr: 0.000588 loss: 3.5221 (3.3546) grad_norm: 1.2685 (nan) time: 0.5117 [2021-03-26 03:46:23 swin_small_patch4_window7_224] INFO: Epoch: [133] [1060/1251] eta: 0:01:37 lr: 0.000588 loss: 3.3524 (3.3552) grad_norm: 1.2818 (nan) time: 0.5080 [2021-03-26 03:46:28 swin_small_patch4_window7_224] INFO: Epoch: [133] [1070/1251] eta: 0:01:32 lr: 0.000588 loss: 3.4573 (3.3570) grad_norm: 1.3032 (nan) time: 0.5086 [2021-03-26 03:46:33 swin_small_patch4_window7_224] INFO: Epoch: [133] [1080/1251] eta: 0:01:27 lr: 0.000588 loss: 3.3799 (3.3554) grad_norm: 1.2714 (nan) time: 0.5044 [2021-03-26 03:46:38 swin_small_patch4_window7_224] INFO: Epoch: [133] [1090/1251] eta: 0:01:21 lr: 0.000588 loss: 3.0539 (3.3536) grad_norm: 1.2781 (nan) time: 0.4976 [2021-03-26 03:46:43 swin_small_patch4_window7_224] INFO: Epoch: [133] [1100/1251] eta: 0:01:16 lr: 0.000588 loss: 3.1337 (3.3541) grad_norm: 1.3223 (nan) time: 0.5042 [2021-03-26 03:46:48 swin_small_patch4_window7_224] INFO: Epoch: [133] [1110/1251] eta: 0:01:11 lr: 0.000588 loss: 3.4166 (3.3541) grad_norm: 1.3141 (nan) time: 0.5139 [2021-03-26 03:46:53 swin_small_patch4_window7_224] INFO: Epoch: [133] [1120/1251] eta: 0:01:06 lr: 0.000588 loss: 3.5460 (3.3549) grad_norm: 1.3038 (nan) time: 0.5064 [2021-03-26 03:46:58 swin_small_patch4_window7_224] INFO: Epoch: [133] [1130/1251] eta: 0:01:01 lr: 0.000588 loss: 3.5392 (3.3555) grad_norm: 1.2824 (nan) time: 0.4977 [2021-03-26 03:47:03 swin_small_patch4_window7_224] INFO: Epoch: [133] [1140/1251] eta: 0:00:56 lr: 0.000588 loss: 3.4372 (3.3548) grad_norm: 1.2871 (nan) time: 0.4990 [2021-03-26 03:47:08 swin_small_patch4_window7_224] INFO: Epoch: [133] [1150/1251] eta: 0:00:51 lr: 0.000588 loss: 3.4516 (3.3566) grad_norm: 1.2774 (nan) time: 0.5015 [2021-03-26 03:47:13 swin_small_patch4_window7_224] INFO: Epoch: [133] [1160/1251] eta: 0:00:46 lr: 0.000588 loss: 3.7232 (3.3583) grad_norm: 1.3209 (nan) time: 0.5043 [2021-03-26 03:47:18 swin_small_patch4_window7_224] INFO: Epoch: [133] [1170/1251] eta: 0:00:41 lr: 0.000588 loss: 3.5627 (3.3600) grad_norm: 1.3568 (nan) time: 0.5016 [2021-03-26 03:47:23 swin_small_patch4_window7_224] INFO: Epoch: [133] [1180/1251] eta: 0:00:36 lr: 0.000588 loss: 3.4587 (3.3578) grad_norm: 1.3141 (nan) time: 0.4999 [2021-03-26 03:47:28 swin_small_patch4_window7_224] INFO: Epoch: [133] [1190/1251] eta: 0:00:31 lr: 0.000588 loss: 3.1072 (3.3558) grad_norm: 1.2551 (nan) time: 0.5087 [2021-03-26 03:47:33 swin_small_patch4_window7_224] INFO: Epoch: [133] [1200/1251] eta: 0:00:25 lr: 0.000588 loss: 3.3883 (3.3565) grad_norm: 1.3034 (nan) time: 0.5090 [2021-03-26 03:47:38 swin_small_patch4_window7_224] INFO: Epoch: [133] [1210/1251] eta: 0:00:20 lr: 0.000588 loss: 3.5043 (3.3575) grad_norm: 1.3334 (nan) time: 0.5014 [2021-03-26 03:47:43 swin_small_patch4_window7_224] INFO: Epoch: [133] [1220/1251] eta: 0:00:15 lr: 0.000588 loss: 3.4476 (3.3575) grad_norm: 1.3158 (nan) time: 0.5006 [2021-03-26 03:47:48 swin_small_patch4_window7_224] INFO: Epoch: [133] [1230/1251] eta: 0:00:10 lr: 0.000588 loss: 3.2896 (3.3575) grad_norm: 1.3370 (nan) time: 0.5056 [2021-03-26 03:47:53 swin_small_patch4_window7_224] INFO: Epoch: [133] [1240/1251] eta: 0:00:05 lr: 0.000588 loss: 3.2896 (3.3570) grad_norm: 1.3551 (nan) time: 0.5076 [2021-03-26 03:47:59 swin_small_patch4_window7_224] INFO: Epoch: [133] [1250/1251] eta: 0:00:00 lr: 0.000588 loss: 3.2247 (3.3553) grad_norm: 1.3425 (nan) time: 0.5055 [2021-03-26 03:48:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.5834 (0.5834) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-26 03:48:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9123 (0.9461) acc1: 79.6875 (77.9830) acc5: 95.3125 (95.0284) [2021-03-26 03:48:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9898 (0.9942) acc1: 76.5625 (77.1577) acc5: 93.7500 (93.9732) [2021-03-26 03:48:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9887 (0.9685) acc1: 76.5625 (77.3185) acc5: 93.7500 (94.3044) [2021-03-26 03:48:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9184 (0.9495) acc1: 78.1250 (77.5534) acc5: 95.3125 (94.4360) [2021-03-26 03:48:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9202 (0.9460) acc1: 76.5625 (77.2800) acc5: 93.7500 (94.5280) [2021-03-26 03:48:25 swin_small_patch4_window7_224] INFO: * Acc@1 77.744 Acc@5 94.132 loss 0.943 [2021-03-26 03:48:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-26 03:48:25 swin_small_patch4_window7_224] INFO: Max accuracy: 77.74% [2021-03-26 03:48:29 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 0/1251] eta: 1:28:29 lr: 0.000588 loss: 3.2004 (3.2004) grad_norm: 1.1260 (1.1260) time: 4.2441 [2021-03-26 03:48:35 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 10/1251] eta: 0:17:45 lr: 0.000588 loss: 3.3342 (3.4006) grad_norm: 1.2446 (1.2668) time: 0.8589 [2021-03-26 03:48:40 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 20/1251] eta: 0:14:10 lr: 0.000587 loss: 3.3342 (3.3704) grad_norm: 1.2794 (1.3099) time: 0.5129 [2021-03-26 03:48:45 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 30/1251] eta: 0:12:49 lr: 0.000587 loss: 3.1582 (3.3206) grad_norm: 1.3625 (1.3516) time: 0.5051 [2021-03-26 03:48:50 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 40/1251] eta: 0:12:08 lr: 0.000587 loss: 3.3097 (3.3394) grad_norm: 1.3455 (1.3637) time: 0.5079 [2021-03-26 03:48:55 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 50/1251] eta: 0:11:40 lr: 0.000587 loss: 3.3139 (3.3390) grad_norm: 1.3116 (1.3574) time: 0.5096 [2021-03-26 03:49:00 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 60/1251] eta: 0:11:19 lr: 0.000587 loss: 3.3800 (3.3212) grad_norm: 1.3099 (1.3524) time: 0.5075 [2021-03-26 03:49:05 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 70/1251] eta: 0:11:00 lr: 0.000587 loss: 3.4667 (3.3241) grad_norm: 1.2963 (1.3416) time: 0.4986 [2021-03-26 03:49:10 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 80/1251] eta: 0:10:47 lr: 0.000587 loss: 3.4979 (3.3369) grad_norm: 1.2905 (1.3345) time: 0.4974 [2021-03-26 03:49:15 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 90/1251] eta: 0:10:36 lr: 0.000587 loss: 3.5182 (3.3328) grad_norm: 1.3595 (1.3431) time: 0.5102 [2021-03-26 03:49:20 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 100/1251] eta: 0:10:26 lr: 0.000587 loss: 3.3915 (3.3148) grad_norm: 1.3704 (1.3368) time: 0.5129 [2021-03-26 03:49:25 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 110/1251] eta: 0:10:17 lr: 0.000587 loss: 3.3046 (3.3197) grad_norm: 1.2889 (1.3345) time: 0.5069 [2021-03-26 03:49:30 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 120/1251] eta: 0:10:08 lr: 0.000587 loss: 3.4560 (3.3311) grad_norm: 1.3195 (1.3394) time: 0.5050 [2021-03-26 03:49:35 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 130/1251] eta: 0:09:59 lr: 0.000587 loss: 3.4560 (3.3338) grad_norm: 1.2753 (1.3356) time: 0.5027 [2021-03-26 03:49:40 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 140/1251] eta: 0:09:51 lr: 0.000587 loss: 3.5964 (3.3388) grad_norm: 1.2956 (1.3390) time: 0.4996 [2021-03-26 03:49:45 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 150/1251] eta: 0:09:44 lr: 0.000587 loss: 3.1795 (3.3276) grad_norm: 1.3139 (1.3348) time: 0.5016 [2021-03-26 03:49:50 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 160/1251] eta: 0:09:37 lr: 0.000587 loss: 3.1795 (3.3180) grad_norm: 1.2633 (1.3326) time: 0.5086 [2021-03-26 03:49:56 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 170/1251] eta: 0:09:31 lr: 0.000587 loss: 3.0678 (3.3034) grad_norm: 1.2807 (1.3359) time: 0.5141 [2021-03-26 03:50:01 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 180/1251] eta: 0:09:25 lr: 0.000587 loss: 2.9715 (3.2939) grad_norm: 1.3203 (1.3375) time: 0.5152 [2021-03-26 03:50:06 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 190/1251] eta: 0:09:18 lr: 0.000587 loss: 3.4121 (3.3068) grad_norm: 1.3134 (1.3375) time: 0.5083 [2021-03-26 03:50:11 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 200/1251] eta: 0:09:13 lr: 0.000587 loss: 3.4594 (3.3044) grad_norm: 1.3052 (1.3365) time: 0.5097 [2021-03-26 03:50:16 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 210/1251] eta: 0:09:06 lr: 0.000587 loss: 3.4914 (3.3187) grad_norm: 1.3013 (1.3367) time: 0.5080 [2021-03-26 03:50:21 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 220/1251] eta: 0:09:00 lr: 0.000587 loss: 3.4941 (3.3200) grad_norm: 1.3094 (1.3395) time: 0.4990 [2021-03-26 03:50:26 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 230/1251] eta: 0:08:53 lr: 0.000587 loss: 3.4458 (3.3167) grad_norm: 1.3502 (1.3414) time: 0.5016 [2021-03-26 03:50:31 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 240/1251] eta: 0:08:48 lr: 0.000587 loss: 3.2800 (3.3108) grad_norm: 1.4300 (1.3477) time: 0.5058 [2021-03-26 03:50:36 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 250/1251] eta: 0:08:42 lr: 0.000587 loss: 3.3492 (3.3180) grad_norm: 1.3084 (1.3443) time: 0.5127 [2021-03-26 03:50:41 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 260/1251] eta: 0:08:37 lr: 0.000586 loss: 3.6181 (3.3231) grad_norm: 1.2779 (1.3437) time: 0.5189 [2021-03-26 03:50:46 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 270/1251] eta: 0:08:31 lr: 0.000586 loss: 3.5926 (3.3251) grad_norm: 1.2611 (1.3392) time: 0.5106 [2021-03-26 03:50:51 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 280/1251] eta: 0:08:25 lr: 0.000586 loss: 3.4869 (3.3383) grad_norm: 1.2560 (1.3371) time: 0.5048 [2021-03-26 03:50:57 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 290/1251] eta: 0:08:19 lr: 0.000586 loss: 3.5859 (3.3490) grad_norm: 1.2593 (1.3356) time: 0.5070 [2021-03-26 03:51:02 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 300/1251] eta: 0:08:14 lr: 0.000586 loss: 3.5859 (3.3491) grad_norm: 1.3115 (1.3406) time: 0.5030 [2021-03-26 03:51:07 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 310/1251] eta: 0:08:08 lr: 0.000586 loss: 3.4068 (3.3424) grad_norm: 1.3954 (1.3410) time: 0.5017 [2021-03-26 03:51:12 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 320/1251] eta: 0:08:03 lr: 0.000586 loss: 3.1510 (3.3437) grad_norm: 1.3155 (1.3399) time: 0.5064 [2021-03-26 03:51:17 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 330/1251] eta: 0:07:57 lr: 0.000586 loss: 3.0338 (3.3317) grad_norm: 1.3547 (1.3409) time: 0.5079 [2021-03-26 03:51:22 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 340/1251] eta: 0:07:51 lr: 0.000586 loss: 3.0209 (3.3326) grad_norm: 1.3491 (1.3396) time: 0.5018 [2021-03-26 03:51:27 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 350/1251] eta: 0:07:46 lr: 0.000586 loss: 3.5396 (3.3331) grad_norm: 1.3117 (1.3413) time: 0.5037 [2021-03-26 03:51:32 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 360/1251] eta: 0:07:40 lr: 0.000586 loss: 3.3828 (3.3321) grad_norm: 1.3498 (1.3411) time: 0.5040 [2021-03-26 03:51:37 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 370/1251] eta: 0:07:35 lr: 0.000586 loss: 3.4513 (3.3356) grad_norm: 1.2965 (1.3401) time: 0.5037 [2021-03-26 03:51:42 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 380/1251] eta: 0:07:29 lr: 0.000586 loss: 3.4544 (3.3408) grad_norm: 1.2965 (1.3401) time: 0.5072 [2021-03-26 03:51:47 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 390/1251] eta: 0:07:24 lr: 0.000586 loss: 3.5395 (3.3448) grad_norm: 1.3576 (1.3403) time: 0.5038 [2021-03-26 03:51:52 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 400/1251] eta: 0:07:18 lr: 0.000586 loss: 3.6330 (3.3557) grad_norm: 1.3572 (1.3397) time: 0.5025 [2021-03-26 03:51:57 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 410/1251] eta: 0:07:13 lr: 0.000586 loss: 3.6482 (3.3591) grad_norm: 1.2637 (1.3401) time: 0.5039 [2021-03-26 03:52:02 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 420/1251] eta: 0:07:08 lr: 0.000586 loss: 3.2872 (3.3538) grad_norm: 1.2605 (1.3391) time: 0.5067 [2021-03-26 03:52:07 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 430/1251] eta: 0:07:02 lr: 0.000586 loss: 3.3449 (3.3551) grad_norm: 1.3272 (1.3395) time: 0.5072 [2021-03-26 03:52:12 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 440/1251] eta: 0:06:57 lr: 0.000586 loss: 3.3449 (3.3450) grad_norm: 1.3371 (1.3390) time: 0.5083 [2021-03-26 03:52:17 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 450/1251] eta: 0:06:52 lr: 0.000586 loss: 2.8263 (3.3362) grad_norm: 1.3371 (1.3401) time: 0.5118 [2021-03-26 03:52:23 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 460/1251] eta: 0:06:47 lr: 0.000586 loss: 3.2217 (3.3371) grad_norm: 1.3137 (1.3388) time: 0.5124 [2021-03-26 03:52:28 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 470/1251] eta: 0:06:42 lr: 0.000586 loss: 3.5987 (3.3428) grad_norm: 1.2554 (1.3381) time: 0.5124 [2021-03-26 03:52:33 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 480/1251] eta: 0:06:36 lr: 0.000586 loss: 3.6175 (3.3428) grad_norm: 1.2500 (1.3362) time: 0.5068 [2021-03-26 03:52:38 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 490/1251] eta: 0:06:31 lr: 0.000586 loss: 3.2406 (3.3413) grad_norm: 1.2646 (1.3353) time: 0.5016 [2021-03-26 03:52:43 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 500/1251] eta: 0:06:26 lr: 0.000586 loss: 3.5800 (3.3440) grad_norm: 1.3401 (1.3354) time: 0.5010 [2021-03-26 03:52:48 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 510/1251] eta: 0:06:20 lr: 0.000585 loss: 3.6472 (3.3478) grad_norm: 1.3196 (1.3347) time: 0.5002 [2021-03-26 03:52:53 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 520/1251] eta: 0:06:15 lr: 0.000585 loss: 3.5022 (3.3461) grad_norm: 1.3029 (1.3350) time: 0.4998 [2021-03-26 03:52:58 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 530/1251] eta: 0:06:10 lr: 0.000585 loss: 3.4217 (3.3480) grad_norm: 1.3648 (1.3356) time: 0.5014 [2021-03-26 03:53:03 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 540/1251] eta: 0:06:04 lr: 0.000585 loss: 3.5158 (3.3505) grad_norm: 1.3353 (1.3357) time: 0.5050 [2021-03-26 03:53:08 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 550/1251] eta: 0:05:59 lr: 0.000585 loss: 3.5847 (3.3558) grad_norm: 1.3088 (1.3366) time: 0.5150 [2021-03-26 03:53:13 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 560/1251] eta: 0:05:54 lr: 0.000585 loss: 3.4323 (3.3533) grad_norm: 1.3286 (1.3376) time: 0.5244 [2021-03-26 03:53:18 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 570/1251] eta: 0:05:49 lr: 0.000585 loss: 3.4852 (3.3564) grad_norm: 1.3233 (1.3372) time: 0.5168 [2021-03-26 03:53:23 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 580/1251] eta: 0:05:44 lr: 0.000585 loss: 3.4985 (3.3579) grad_norm: 1.3045 (1.3371) time: 0.5050 [2021-03-26 03:53:29 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 590/1251] eta: 0:05:39 lr: 0.000585 loss: 3.5147 (3.3592) grad_norm: 1.3169 (1.3374) time: 0.5091 [2021-03-26 03:53:34 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 600/1251] eta: 0:05:34 lr: 0.000585 loss: 3.3395 (3.3562) grad_norm: 1.3203 (1.3378) time: 0.5099 [2021-03-26 03:53:39 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 610/1251] eta: 0:05:28 lr: 0.000585 loss: 3.3015 (3.3578) grad_norm: 1.3393 (1.3386) time: 0.5068 [2021-03-26 03:53:44 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 620/1251] eta: 0:05:23 lr: 0.000585 loss: 3.6418 (3.3626) grad_norm: 1.3393 (1.3387) time: 0.5071 [2021-03-26 03:53:49 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 630/1251] eta: 0:05:18 lr: 0.000585 loss: 3.6418 (3.3635) grad_norm: 1.2810 (1.3375) time: 0.5028 [2021-03-26 03:53:54 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 640/1251] eta: 0:05:13 lr: 0.000585 loss: 3.5555 (3.3669) grad_norm: 1.2575 (1.3360) time: 0.5052 [2021-03-26 03:53:59 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 650/1251] eta: 0:05:08 lr: 0.000585 loss: 3.6079 (3.3706) grad_norm: 1.2738 (1.3358) time: 0.5043 [2021-03-26 03:54:04 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 660/1251] eta: 0:05:02 lr: 0.000585 loss: 3.5056 (3.3694) grad_norm: 1.2947 (1.3364) time: 0.4981 [2021-03-26 03:54:09 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 670/1251] eta: 0:04:57 lr: 0.000585 loss: 3.4839 (3.3709) grad_norm: 1.3156 (1.3364) time: 0.5014 [2021-03-26 03:54:14 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 680/1251] eta: 0:04:52 lr: 0.000585 loss: 3.5724 (3.3707) grad_norm: 1.3264 (1.3364) time: 0.5045 [2021-03-26 03:54:19 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 690/1251] eta: 0:04:47 lr: 0.000585 loss: 3.5807 (3.3691) grad_norm: 1.3376 (1.3360) time: 0.5040 [2021-03-26 03:54:24 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 700/1251] eta: 0:04:42 lr: 0.000585 loss: 3.1092 (3.3604) grad_norm: 1.3299 (1.3359) time: 0.5083 [2021-03-26 03:54:29 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 710/1251] eta: 0:04:36 lr: 0.000585 loss: 3.1092 (3.3585) grad_norm: 1.2733 (1.3344) time: 0.5079 [2021-03-26 03:54:34 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 720/1251] eta: 0:04:31 lr: 0.000585 loss: 3.2982 (3.3605) grad_norm: 1.2160 (1.3334) time: 0.5112 [2021-03-26 03:54:39 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 730/1251] eta: 0:04:26 lr: 0.000585 loss: 3.4474 (3.3608) grad_norm: 1.2965 (1.3331) time: 0.5185 [2021-03-26 03:54:45 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 740/1251] eta: 0:04:21 lr: 0.000585 loss: 3.4888 (3.3610) grad_norm: 1.3032 (1.3332) time: 0.5159 [2021-03-26 03:54:50 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 750/1251] eta: 0:04:16 lr: 0.000584 loss: 3.5370 (3.3627) grad_norm: 1.3184 (1.3339) time: 0.5144 [2021-03-26 03:54:55 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 760/1251] eta: 0:04:11 lr: 0.000584 loss: 3.2565 (3.3616) grad_norm: 1.3005 (1.3328) time: 0.5112 [2021-03-26 03:55:00 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 770/1251] eta: 0:04:06 lr: 0.000584 loss: 3.5164 (3.3640) grad_norm: 1.2694 (1.3330) time: 0.5091 [2021-03-26 03:55:05 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 780/1251] eta: 0:04:01 lr: 0.000584 loss: 3.5786 (3.3676) grad_norm: 1.2825 (1.3328) time: 0.5056 [2021-03-26 03:55:10 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 790/1251] eta: 0:03:56 lr: 0.000584 loss: 3.3890 (3.3667) grad_norm: 1.2825 (1.3323) time: 0.5088 [2021-03-26 03:55:15 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 800/1251] eta: 0:03:50 lr: 0.000584 loss: 3.2405 (3.3673) grad_norm: 1.2984 (1.3329) time: 0.5099 [2021-03-26 03:55:20 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 810/1251] eta: 0:03:45 lr: 0.000584 loss: 3.4550 (3.3699) grad_norm: 1.3538 (1.3329) time: 0.5053 [2021-03-26 03:55:25 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 820/1251] eta: 0:03:40 lr: 0.000584 loss: 3.4231 (3.3678) grad_norm: 1.3374 (1.3338) time: 0.5068 [2021-03-26 03:55:30 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 830/1251] eta: 0:03:35 lr: 0.000584 loss: 3.3667 (3.3692) grad_norm: 1.3282 (1.3337) time: 0.5091 [2021-03-26 03:55:35 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 840/1251] eta: 0:03:30 lr: 0.000584 loss: 3.5718 (3.3689) grad_norm: 1.2998 (1.3338) time: 0.5092 [2021-03-26 03:55:40 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 850/1251] eta: 0:03:25 lr: 0.000584 loss: 3.1855 (3.3689) grad_norm: 1.3783 (1.3349) time: 0.5024 [2021-03-26 03:55:46 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 860/1251] eta: 0:03:19 lr: 0.000584 loss: 3.3908 (3.3673) grad_norm: 1.2792 (1.3342) time: 0.5021 [2021-03-26 03:55:51 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 870/1251] eta: 0:03:14 lr: 0.000584 loss: 3.3608 (3.3678) grad_norm: 1.2658 (1.3334) time: 0.5025 [2021-03-26 03:55:56 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 880/1251] eta: 0:03:09 lr: 0.000584 loss: 3.3608 (3.3680) grad_norm: 1.2624 (1.3330) time: 0.5066 [2021-03-26 03:56:01 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 890/1251] eta: 0:03:04 lr: 0.000584 loss: 3.4954 (3.3683) grad_norm: 1.2897 (1.3333) time: 0.5054 [2021-03-26 03:56:06 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 900/1251] eta: 0:02:59 lr: 0.000584 loss: 3.5055 (3.3703) grad_norm: 1.3609 (1.3338) time: 0.4976 [2021-03-26 03:56:11 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 910/1251] eta: 0:02:54 lr: 0.000584 loss: 3.5332 (3.3710) grad_norm: 1.3364 (1.3336) time: 0.5059 [2021-03-26 03:56:16 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 920/1251] eta: 0:02:49 lr: 0.000584 loss: 3.3898 (3.3705) grad_norm: 1.3789 (1.3344) time: 0.5137 [2021-03-26 03:56:21 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 930/1251] eta: 0:02:44 lr: 0.000584 loss: 3.2395 (3.3689) grad_norm: 1.3789 (1.3344) time: 0.5127 [2021-03-26 03:56:26 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 940/1251] eta: 0:02:38 lr: 0.000584 loss: 3.4453 (3.3672) grad_norm: 1.2895 (1.3342) time: 0.5117 [2021-03-26 03:56:31 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 950/1251] eta: 0:02:33 lr: 0.000584 loss: 3.4677 (3.3663) grad_norm: 1.2822 (1.3343) time: 0.5051 [2021-03-26 03:56:36 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 960/1251] eta: 0:02:28 lr: 0.000584 loss: 3.4677 (3.3657) grad_norm: 1.2537 (1.3334) time: 0.5052 [2021-03-26 03:56:41 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 970/1251] eta: 0:02:23 lr: 0.000584 loss: 3.5215 (3.3679) grad_norm: 1.2548 (1.3325) time: 0.5083 [2021-03-26 03:56:46 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 980/1251] eta: 0:02:18 lr: 0.000584 loss: 3.4119 (3.3664) grad_norm: 1.2398 (1.3318) time: 0.5085 [2021-03-26 03:56:51 swin_small_patch4_window7_224] INFO: Epoch: [134] [ 990/1251] eta: 0:02:13 lr: 0.000584 loss: 3.0052 (3.3633) grad_norm: 1.2398 (1.3316) time: 0.5087 [2021-03-26 03:56:57 swin_small_patch4_window7_224] INFO: Epoch: [134] [1000/1251] eta: 0:02:08 lr: 0.000583 loss: 3.1143 (3.3631) grad_norm: 1.2969 (1.3313) time: 0.5125 [2021-03-26 03:57:02 swin_small_patch4_window7_224] INFO: Epoch: [134] [1010/1251] eta: 0:02:03 lr: 0.000583 loss: 3.4797 (3.3656) grad_norm: 1.2846 (1.3317) time: 0.5143 [2021-03-26 03:57:07 swin_small_patch4_window7_224] INFO: Epoch: [134] [1020/1251] eta: 0:01:58 lr: 0.000583 loss: 3.3856 (3.3646) grad_norm: 1.2794 (1.3309) time: 0.5091 [2021-03-26 03:57:12 swin_small_patch4_window7_224] INFO: Epoch: [134] [1030/1251] eta: 0:01:52 lr: 0.000583 loss: 3.3377 (3.3635) grad_norm: 1.2528 (1.3304) time: 0.5030 [2021-03-26 03:57:17 swin_small_patch4_window7_224] INFO: Epoch: [134] [1040/1251] eta: 0:01:47 lr: 0.000583 loss: 3.4186 (3.3652) grad_norm: 1.2977 (1.3306) time: 0.5005 [2021-03-26 03:57:22 swin_small_patch4_window7_224] INFO: Epoch: [134] [1050/1251] eta: 0:01:42 lr: 0.000583 loss: 3.4186 (3.3645) grad_norm: 1.3319 (1.3309) time: 0.5034 [2021-03-26 03:57:27 swin_small_patch4_window7_224] INFO: Epoch: [134] [1060/1251] eta: 0:01:37 lr: 0.000583 loss: 3.4758 (3.3648) grad_norm: 1.3319 (1.3309) time: 0.4971 [2021-03-26 03:57:32 swin_small_patch4_window7_224] INFO: Epoch: [134] [1070/1251] eta: 0:01:32 lr: 0.000583 loss: 3.5144 (3.3649) grad_norm: 1.3451 (1.3313) time: 0.4950 [2021-03-26 03:57:37 swin_small_patch4_window7_224] INFO: Epoch: [134] [1080/1251] eta: 0:01:27 lr: 0.000583 loss: 3.3926 (3.3631) grad_norm: 1.3451 (1.3312) time: 0.5019 [2021-03-26 03:57:42 swin_small_patch4_window7_224] INFO: Epoch: [134] [1090/1251] eta: 0:01:22 lr: 0.000583 loss: 3.3129 (3.3628) grad_norm: 1.3182 (1.3311) time: 0.5040 [2021-03-26 03:57:47 swin_small_patch4_window7_224] INFO: Epoch: [134] [1100/1251] eta: 0:01:17 lr: 0.000583 loss: 3.3730 (3.3641) grad_norm: 1.3712 (1.3321) time: 0.5029 [2021-03-26 03:57:52 swin_small_patch4_window7_224] INFO: Epoch: [134] [1110/1251] eta: 0:01:11 lr: 0.000583 loss: 3.5892 (3.3672) grad_norm: 1.3349 (1.3318) time: 0.5041 [2021-03-26 03:57:57 swin_small_patch4_window7_224] INFO: Epoch: [134] [1120/1251] eta: 0:01:06 lr: 0.000583 loss: 3.2918 (3.3656) grad_norm: 1.2527 (1.3313) time: 0.5041 [2021-03-26 03:58:02 swin_small_patch4_window7_224] INFO: Epoch: [134] [1130/1251] eta: 0:01:01 lr: 0.000583 loss: 3.1949 (3.3642) grad_norm: 1.2211 (1.3303) time: 0.5047 [2021-03-26 03:58:07 swin_small_patch4_window7_224] INFO: Epoch: [134] [1140/1251] eta: 0:00:56 lr: 0.000583 loss: 3.4331 (3.3662) grad_norm: 1.2311 (1.3304) time: 0.5024 [2021-03-26 03:58:12 swin_small_patch4_window7_224] INFO: Epoch: [134] [1150/1251] eta: 0:00:51 lr: 0.000583 loss: 3.6314 (3.3678) grad_norm: 1.3037 (1.3305) time: 0.4969 [2021-03-26 03:58:17 swin_small_patch4_window7_224] INFO: Epoch: [134] [1160/1251] eta: 0:00:46 lr: 0.000583 loss: 3.5505 (3.3665) grad_norm: 1.3337 (1.3311) time: 0.5013 [2021-03-26 03:58:22 swin_small_patch4_window7_224] INFO: Epoch: [134] [1170/1251] eta: 0:00:41 lr: 0.000583 loss: 3.4637 (3.3665) grad_norm: 1.3617 (1.3323) time: 0.5056 [2021-03-26 03:58:27 swin_small_patch4_window7_224] INFO: Epoch: [134] [1180/1251] eta: 0:00:36 lr: 0.000583 loss: 3.5210 (3.3675) grad_norm: 1.3588 (1.3325) time: 0.5061 [2021-03-26 03:58:32 swin_small_patch4_window7_224] INFO: Epoch: [134] [1190/1251] eta: 0:00:31 lr: 0.000583 loss: 3.4648 (3.3655) grad_norm: 1.3415 (1.3327) time: 0.5094 [2021-03-26 03:58:37 swin_small_patch4_window7_224] INFO: Epoch: [134] [1200/1251] eta: 0:00:25 lr: 0.000583 loss: 3.1709 (3.3662) grad_norm: 1.3114 (1.3322) time: 0.5067 [2021-03-26 03:58:42 swin_small_patch4_window7_224] INFO: Epoch: [134] [1210/1251] eta: 0:00:20 lr: 0.000583 loss: 3.5579 (3.3670) grad_norm: 1.2698 (1.3321) time: 0.5081 [2021-03-26 03:58:47 swin_small_patch4_window7_224] INFO: Epoch: [134] [1220/1251] eta: 0:00:15 lr: 0.000583 loss: 3.6079 (3.3681) grad_norm: 1.2522 (1.3317) time: 0.5052 [2021-03-26 03:58:53 swin_small_patch4_window7_224] INFO: Epoch: [134] [1230/1251] eta: 0:00:10 lr: 0.000583 loss: 3.6316 (3.3699) grad_norm: 1.2801 (1.3319) time: 0.5006 [2021-03-26 03:58:58 swin_small_patch4_window7_224] INFO: Epoch: [134] [1240/1251] eta: 0:00:05 lr: 0.000582 loss: 3.3297 (3.3676) grad_norm: 1.3792 (1.3321) time: 0.5073 [2021-03-26 03:59:03 swin_small_patch4_window7_224] INFO: Epoch: [134] [1250/1251] eta: 0:00:00 lr: 0.000582 loss: 3.1026 (3.3669) grad_norm: 1.2670 (1.3312) time: 0.5062 [2021-03-26 03:59:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 1.2595 (1.2595) acc1: 75.0000 (75.0000) acc5: 87.5000 (87.5000) [2021-03-26 03:59:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9884 (1.0090) acc1: 76.5625 (75.5682) acc5: 93.7500 (93.1818) [2021-03-26 03:59:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9884 (0.9922) acc1: 75.0000 (76.0417) acc5: 93.7500 (93.6012) [2021-03-26 03:59:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9067 (0.9617) acc1: 75.0000 (76.4617) acc5: 93.7500 (94.0020) [2021-03-26 03:59:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8638 (0.9546) acc1: 76.5625 (76.7912) acc5: 95.3125 (94.1311) [2021-03-26 03:59:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8519 (0.9393) acc1: 79.6875 (77.4080) acc5: 95.3125 (94.3680) [2021-03-26 03:59:24 swin_small_patch4_window7_224] INFO: * Acc@1 77.658 Acc@5 94.260 loss 0.933 [2021-03-26 03:59:24 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-26 03:59:24 swin_small_patch4_window7_224] INFO: Max accuracy: 77.74% [2021-03-26 03:59:28 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 0/1251] eta: 1:22:04 lr: 0.000582 loss: 3.7857 (3.7857) grad_norm: 1.3492 (1.3492) time: 3.9364 [2021-03-26 03:59:33 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 10/1251] eta: 0:17:27 lr: 0.000582 loss: 3.6276 (3.2338) grad_norm: 1.2683 (1.2874) time: 0.8445 [2021-03-26 03:59:38 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 20/1251] eta: 0:13:58 lr: 0.000582 loss: 3.4167 (3.3721) grad_norm: 1.2822 (1.3087) time: 0.5184 [2021-03-26 03:59:43 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 30/1251] eta: 0:12:43 lr: 0.000582 loss: 3.4032 (3.3378) grad_norm: 1.3588 (1.3372) time: 0.5048 [2021-03-26 03:59:48 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 40/1251] eta: 0:12:01 lr: 0.000582 loss: 3.3157 (3.3575) grad_norm: 1.3917 (1.3540) time: 0.5064 [2021-03-26 03:59:53 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 50/1251] eta: 0:11:35 lr: 0.000582 loss: 3.4348 (3.3727) grad_norm: 1.4002 (1.3535) time: 0.5076 [2021-03-26 03:59:58 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 60/1251] eta: 0:11:13 lr: 0.000582 loss: 3.5656 (3.4031) grad_norm: 1.3597 (1.3466) time: 0.5025 [2021-03-26 04:00:03 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 70/1251] eta: 0:10:58 lr: 0.000582 loss: 3.2660 (3.3538) grad_norm: 1.3182 (1.3422) time: 0.5034 [2021-03-26 04:00:08 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 80/1251] eta: 0:10:44 lr: 0.000582 loss: 3.3651 (3.3733) grad_norm: 1.2934 (1.3395) time: 0.5051 [2021-03-26 04:00:13 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 90/1251] eta: 0:10:32 lr: 0.000582 loss: 3.6020 (3.4014) grad_norm: 1.3028 (1.3393) time: 0.4972 [2021-03-26 04:00:18 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 100/1251] eta: 0:10:23 lr: 0.000582 loss: 3.5779 (3.4098) grad_norm: 1.3404 (1.3407) time: 0.5082 [2021-03-26 04:00:24 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 110/1251] eta: 0:10:16 lr: 0.000582 loss: 3.4648 (3.4040) grad_norm: 1.3577 (1.3429) time: 0.5222 [2021-03-26 04:00:29 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 120/1251] eta: 0:10:08 lr: 0.000582 loss: 3.3018 (3.4074) grad_norm: 1.3593 (1.3435) time: 0.5171 [2021-03-26 04:00:34 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 130/1251] eta: 0:10:01 lr: 0.000582 loss: 3.5837 (3.4169) grad_norm: 1.2884 (1.3408) time: 0.5154 [2021-03-26 04:00:39 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 140/1251] eta: 0:09:53 lr: 0.000582 loss: 3.4906 (3.4111) grad_norm: 1.2675 (1.3375) time: 0.5103 [2021-03-26 04:00:44 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 150/1251] eta: 0:09:45 lr: 0.000582 loss: 3.4906 (3.4130) grad_norm: 1.2482 (1.3347) time: 0.5002 [2021-03-26 04:00:49 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 160/1251] eta: 0:09:38 lr: 0.000582 loss: 3.6030 (3.4196) grad_norm: 1.3081 (1.3409) time: 0.5056 [2021-03-26 04:00:54 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 170/1251] eta: 0:09:31 lr: 0.000582 loss: 3.5502 (3.4258) grad_norm: 1.3546 (1.3387) time: 0.5082 [2021-03-26 04:00:59 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 180/1251] eta: 0:09:25 lr: 0.000582 loss: 3.5904 (3.4394) grad_norm: 1.2375 (1.3336) time: 0.5105 [2021-03-26 04:01:04 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 190/1251] eta: 0:09:18 lr: 0.000582 loss: 3.5913 (3.4484) grad_norm: 1.2248 (1.3323) time: 0.5073 [2021-03-26 04:01:09 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 200/1251] eta: 0:09:12 lr: 0.000582 loss: 3.5885 (3.4458) grad_norm: 1.3355 (1.3330) time: 0.5010 [2021-03-26 04:01:14 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 210/1251] eta: 0:09:06 lr: 0.000582 loss: 3.4607 (3.4352) grad_norm: 1.2756 (1.3316) time: 0.5071 [2021-03-26 04:01:19 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 220/1251] eta: 0:08:59 lr: 0.000582 loss: 3.4607 (3.4386) grad_norm: 1.3590 (1.3367) time: 0.5038 [2021-03-26 04:01:25 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 230/1251] eta: 0:08:53 lr: 0.000581 loss: 3.5537 (3.4337) grad_norm: 1.3785 (1.3353) time: 0.5026 [2021-03-26 04:01:30 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 240/1251] eta: 0:08:47 lr: 0.000581 loss: 3.4055 (3.4323) grad_norm: 1.3055 (1.3364) time: 0.5066 [2021-03-26 04:01:35 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 250/1251] eta: 0:08:42 lr: 0.000581 loss: 3.4444 (3.4326) grad_norm: 1.3128 (1.3349) time: 0.5058 [2021-03-26 04:01:40 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 260/1251] eta: 0:08:36 lr: 0.000581 loss: 3.4729 (3.4315) grad_norm: 1.3225 (1.3366) time: 0.5043 [2021-03-26 04:01:45 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 270/1251] eta: 0:08:30 lr: 0.000581 loss: 3.2336 (3.4228) grad_norm: 1.3356 (1.3361) time: 0.5009 [2021-03-26 04:01:50 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 280/1251] eta: 0:08:24 lr: 0.000581 loss: 3.1861 (3.4227) grad_norm: 1.3635 (1.3387) time: 0.4995 [2021-03-26 04:01:55 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 290/1251] eta: 0:08:18 lr: 0.000581 loss: 3.4944 (3.4233) grad_norm: 1.4433 (1.3449) time: 0.5079 [2021-03-26 04:02:00 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 300/1251] eta: 0:08:13 lr: 0.000581 loss: 3.3726 (3.4109) grad_norm: 1.3638 (1.3442) time: 0.5143 [2021-03-26 04:02:05 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 310/1251] eta: 0:08:08 lr: 0.000581 loss: 3.4534 (3.4152) grad_norm: 1.3019 (1.3410) time: 0.5129 [2021-03-26 04:02:10 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 320/1251] eta: 0:08:02 lr: 0.000581 loss: 3.5836 (3.4152) grad_norm: 1.2851 (1.3398) time: 0.5049 [2021-03-26 04:02:15 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 330/1251] eta: 0:07:56 lr: 0.000581 loss: 3.3238 (3.4186) grad_norm: 1.2851 (1.3369) time: 0.4983 [2021-03-26 04:02:20 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 340/1251] eta: 0:07:51 lr: 0.000581 loss: 3.2534 (3.4059) grad_norm: 1.2221 (1.3343) time: 0.5018 [2021-03-26 04:02:25 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 350/1251] eta: 0:07:45 lr: 0.000581 loss: 3.1703 (3.4018) grad_norm: 1.2455 (1.3327) time: 0.5068 [2021-03-26 04:02:30 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 360/1251] eta: 0:07:40 lr: 0.000581 loss: 3.2936 (3.3976) grad_norm: 1.2965 (1.3329) time: 0.5073 [2021-03-26 04:02:35 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 370/1251] eta: 0:07:35 lr: 0.000581 loss: 3.2664 (3.3976) grad_norm: 1.3078 (1.3310) time: 0.5077 [2021-03-26 04:02:40 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 380/1251] eta: 0:07:29 lr: 0.000581 loss: 3.2664 (3.3989) grad_norm: 1.2855 (1.3313) time: 0.5086 [2021-03-26 04:02:45 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 390/1251] eta: 0:07:23 lr: 0.000581 loss: 3.3327 (3.4000) grad_norm: 1.3469 (1.3326) time: 0.5003 [2021-03-26 04:02:50 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 400/1251] eta: 0:07:18 lr: 0.000581 loss: 3.3811 (3.4002) grad_norm: 1.3220 (1.3332) time: 0.4983 [2021-03-26 04:02:55 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 410/1251] eta: 0:07:13 lr: 0.000581 loss: 3.4886 (3.4009) grad_norm: 1.3184 (1.3332) time: 0.4995 [2021-03-26 04:03:00 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 420/1251] eta: 0:07:07 lr: 0.000581 loss: 3.3431 (3.3983) grad_norm: 1.3055 (1.3325) time: 0.5002 [2021-03-26 04:03:05 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 430/1251] eta: 0:07:02 lr: 0.000581 loss: 3.3633 (3.3985) grad_norm: 1.2970 (1.3319) time: 0.5045 [2021-03-26 04:03:10 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 440/1251] eta: 0:06:57 lr: 0.000581 loss: 3.4579 (3.4016) grad_norm: 1.2689 (1.3311) time: 0.5059 [2021-03-26 04:03:15 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 450/1251] eta: 0:06:51 lr: 0.000581 loss: 3.6256 (3.4033) grad_norm: 1.2538 (1.3296) time: 0.5000 [2021-03-26 04:03:20 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 460/1251] eta: 0:06:46 lr: 0.000581 loss: 3.5696 (3.4023) grad_norm: 1.2314 (1.3288) time: 0.4969 [2021-03-26 04:03:26 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 470/1251] eta: 0:06:40 lr: 0.000581 loss: 3.4995 (3.4019) grad_norm: 1.3110 (1.3293) time: 0.5035 [2021-03-26 04:03:31 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 480/1251] eta: 0:06:35 lr: 0.000580 loss: 3.5400 (3.4052) grad_norm: 1.3110 (1.3296) time: 0.5086 [2021-03-26 04:03:36 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 490/1251] eta: 0:06:30 lr: 0.000580 loss: 3.6141 (3.4083) grad_norm: 1.2981 (1.3305) time: 0.5054 [2021-03-26 04:03:41 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 500/1251] eta: 0:06:25 lr: 0.000580 loss: 3.4451 (3.4035) grad_norm: 1.3550 (1.3316) time: 0.5008 [2021-03-26 04:03:46 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 510/1251] eta: 0:06:19 lr: 0.000580 loss: 3.3176 (3.4031) grad_norm: 1.3666 (1.3330) time: 0.5045 [2021-03-26 04:03:51 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 520/1251] eta: 0:06:14 lr: 0.000580 loss: 3.6037 (3.4090) grad_norm: 1.3587 (1.3325) time: 0.5068 [2021-03-26 04:03:56 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 530/1251] eta: 0:06:09 lr: 0.000580 loss: 3.6071 (3.4044) grad_norm: 1.2722 (1.3307) time: 0.5038 [2021-03-26 04:04:01 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 540/1251] eta: 0:06:04 lr: 0.000580 loss: 3.5199 (3.4080) grad_norm: 1.2876 (1.3315) time: 0.5044 [2021-03-26 04:04:06 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 550/1251] eta: 0:05:59 lr: 0.000580 loss: 3.6533 (3.4108) grad_norm: 1.2888 (1.3306) time: 0.5183 [2021-03-26 04:04:11 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 560/1251] eta: 0:05:54 lr: 0.000580 loss: 3.5407 (3.4087) grad_norm: 1.2594 (1.3292) time: 0.5167 [2021-03-26 04:04:16 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 570/1251] eta: 0:05:48 lr: 0.000580 loss: 3.5307 (3.4076) grad_norm: 1.2696 (1.3282) time: 0.5103 [2021-03-26 04:04:21 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 580/1251] eta: 0:05:43 lr: 0.000580 loss: 3.3913 (3.4064) grad_norm: 1.2696 (1.3277) time: 0.5061 [2021-03-26 04:04:26 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 590/1251] eta: 0:05:38 lr: 0.000580 loss: 3.4054 (3.4055) grad_norm: 1.2648 (1.3276) time: 0.5031 [2021-03-26 04:04:32 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 600/1251] eta: 0:05:33 lr: 0.000580 loss: 3.4054 (3.4073) grad_norm: 1.3398 (1.3287) time: 0.5124 [2021-03-26 04:04:37 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 610/1251] eta: 0:05:28 lr: 0.000580 loss: 3.4826 (3.4090) grad_norm: 1.2990 (1.3276) time: 0.5105 [2021-03-26 04:04:42 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 620/1251] eta: 0:05:23 lr: 0.000580 loss: 3.5623 (3.4080) grad_norm: 1.2810 (1.3271) time: 0.5084 [2021-03-26 04:04:47 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 630/1251] eta: 0:05:17 lr: 0.000580 loss: 3.3504 (3.4046) grad_norm: 1.3314 (inf) time: 0.5045 [2021-03-26 04:04:52 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 640/1251] eta: 0:05:12 lr: 0.000580 loss: 3.3436 (3.4029) grad_norm: 1.3314 (inf) time: 0.5045 [2021-03-26 04:04:57 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 650/1251] eta: 0:05:07 lr: 0.000580 loss: 3.3545 (3.4024) grad_norm: 1.3385 (inf) time: 0.5077 [2021-03-26 04:05:02 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 660/1251] eta: 0:05:02 lr: 0.000580 loss: 3.4106 (3.4017) grad_norm: 1.3142 (inf) time: 0.5030 [2021-03-26 04:05:07 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 670/1251] eta: 0:04:57 lr: 0.000580 loss: 3.5080 (3.4027) grad_norm: 1.3102 (inf) time: 0.5020 [2021-03-26 04:05:12 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 680/1251] eta: 0:04:51 lr: 0.000580 loss: 3.3797 (3.4024) grad_norm: 1.3067 (inf) time: 0.5046 [2021-03-26 04:05:17 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 690/1251] eta: 0:04:46 lr: 0.000580 loss: 3.5090 (3.4046) grad_norm: 1.2520 (inf) time: 0.5075 [2021-03-26 04:05:22 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 700/1251] eta: 0:04:41 lr: 0.000580 loss: 3.4245 (3.4004) grad_norm: 1.2569 (inf) time: 0.5097 [2021-03-26 04:05:27 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 710/1251] eta: 0:04:36 lr: 0.000580 loss: 3.0967 (3.3993) grad_norm: 1.2531 (inf) time: 0.5032 [2021-03-26 04:05:32 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 720/1251] eta: 0:04:31 lr: 0.000579 loss: 3.4977 (3.4031) grad_norm: 1.3257 (inf) time: 0.4975 [2021-03-26 04:05:37 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 730/1251] eta: 0:04:26 lr: 0.000579 loss: 3.5273 (3.4015) grad_norm: 1.3257 (inf) time: 0.5023 [2021-03-26 04:05:43 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 740/1251] eta: 0:04:21 lr: 0.000579 loss: 3.1550 (3.3991) grad_norm: 1.2925 (inf) time: 0.5198 [2021-03-26 04:05:48 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 750/1251] eta: 0:04:16 lr: 0.000579 loss: 3.4830 (3.4026) grad_norm: 1.2672 (inf) time: 0.5196 [2021-03-26 04:05:53 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 760/1251] eta: 0:04:10 lr: 0.000579 loss: 3.6650 (3.4030) grad_norm: 1.2589 (inf) time: 0.5112 [2021-03-26 04:05:58 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 770/1251] eta: 0:04:05 lr: 0.000579 loss: 3.5879 (3.4029) grad_norm: 1.2897 (inf) time: 0.5088 [2021-03-26 04:06:03 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 780/1251] eta: 0:04:00 lr: 0.000579 loss: 3.5211 (3.4025) grad_norm: 1.3534 (inf) time: 0.5059 [2021-03-26 04:06:08 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 790/1251] eta: 0:03:55 lr: 0.000579 loss: 3.4980 (3.4008) grad_norm: 1.3731 (inf) time: 0.5096 [2021-03-26 04:06:13 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 800/1251] eta: 0:03:50 lr: 0.000579 loss: 3.5327 (3.4030) grad_norm: 1.3869 (inf) time: 0.5111 [2021-03-26 04:06:18 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 810/1251] eta: 0:03:45 lr: 0.000579 loss: 3.6699 (3.4064) grad_norm: 1.4263 (inf) time: 0.5133 [2021-03-26 04:06:23 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 820/1251] eta: 0:03:40 lr: 0.000579 loss: 3.3397 (3.4026) grad_norm: 1.3654 (inf) time: 0.5107 [2021-03-26 04:06:28 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 830/1251] eta: 0:03:35 lr: 0.000579 loss: 3.1389 (3.3996) grad_norm: 1.3654 (inf) time: 0.5062 [2021-03-26 04:06:33 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 840/1251] eta: 0:03:29 lr: 0.000579 loss: 3.1297 (3.3962) grad_norm: 1.3520 (inf) time: 0.5076 [2021-03-26 04:06:39 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 850/1251] eta: 0:03:24 lr: 0.000579 loss: 3.4410 (3.3983) grad_norm: 1.2939 (inf) time: 0.5101 [2021-03-26 04:06:44 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 860/1251] eta: 0:03:19 lr: 0.000579 loss: 3.5083 (3.3973) grad_norm: 1.2939 (inf) time: 0.5095 [2021-03-26 04:06:49 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 870/1251] eta: 0:03:14 lr: 0.000579 loss: 3.5233 (3.3969) grad_norm: 1.3802 (inf) time: 0.5065 [2021-03-26 04:06:54 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 880/1251] eta: 0:03:09 lr: 0.000579 loss: 3.3154 (3.3961) grad_norm: 1.4291 (inf) time: 0.5063 [2021-03-26 04:06:59 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 890/1251] eta: 0:03:04 lr: 0.000579 loss: 3.4042 (3.3961) grad_norm: 1.3736 (inf) time: 0.5050 [2021-03-26 04:07:04 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 900/1251] eta: 0:02:59 lr: 0.000579 loss: 3.4437 (3.3941) grad_norm: 1.3196 (inf) time: 0.5062 [2021-03-26 04:07:09 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 910/1251] eta: 0:02:54 lr: 0.000579 loss: 3.5498 (3.3951) grad_norm: 1.2744 (inf) time: 0.5065 [2021-03-26 04:07:14 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 920/1251] eta: 0:02:48 lr: 0.000579 loss: 3.4937 (3.3942) grad_norm: 1.2885 (inf) time: 0.5013 [2021-03-26 04:07:19 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 930/1251] eta: 0:02:43 lr: 0.000579 loss: 3.1727 (3.3915) grad_norm: 1.3422 (inf) time: 0.5037 [2021-03-26 04:07:24 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 940/1251] eta: 0:02:38 lr: 0.000579 loss: 3.2620 (3.3916) grad_norm: 1.3029 (inf) time: 0.5030 [2021-03-26 04:07:29 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 950/1251] eta: 0:02:33 lr: 0.000579 loss: 3.5274 (3.3928) grad_norm: 1.2907 (inf) time: 0.5042 [2021-03-26 04:07:34 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 960/1251] eta: 0:02:28 lr: 0.000579 loss: 3.5862 (3.3929) grad_norm: 1.3323 (inf) time: 0.5073 [2021-03-26 04:07:39 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 970/1251] eta: 0:02:23 lr: 0.000578 loss: 3.4405 (3.3900) grad_norm: 1.3497 (inf) time: 0.5025 [2021-03-26 04:07:44 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 980/1251] eta: 0:02:18 lr: 0.000578 loss: 3.4581 (3.3925) grad_norm: 1.3534 (inf) time: 0.5030 [2021-03-26 04:07:49 swin_small_patch4_window7_224] INFO: Epoch: [135] [ 990/1251] eta: 0:02:13 lr: 0.000578 loss: 3.6202 (3.3934) grad_norm: 1.3404 (inf) time: 0.5028 [2021-03-26 04:07:54 swin_small_patch4_window7_224] INFO: Epoch: [135] [1000/1251] eta: 0:02:07 lr: 0.000578 loss: 3.6179 (3.3936) grad_norm: 1.3207 (inf) time: 0.5012 [2021-03-26 04:07:59 swin_small_patch4_window7_224] INFO: Epoch: [135] [1010/1251] eta: 0:02:02 lr: 0.000578 loss: 3.3566 (3.3919) grad_norm: 1.3207 (inf) time: 0.5045 [2021-03-26 04:08:04 swin_small_patch4_window7_224] INFO: Epoch: [135] [1020/1251] eta: 0:01:57 lr: 0.000578 loss: 3.4412 (3.3932) grad_norm: 1.3309 (inf) time: 0.5030 [2021-03-26 04:08:09 swin_small_patch4_window7_224] INFO: Epoch: [135] [1030/1251] eta: 0:01:52 lr: 0.000578 loss: 3.4269 (3.3906) grad_norm: 1.2705 (inf) time: 0.4997 [2021-03-26 04:08:14 swin_small_patch4_window7_224] INFO: Epoch: [135] [1040/1251] eta: 0:01:47 lr: 0.000578 loss: 3.4269 (3.3901) grad_norm: 1.2758 (inf) time: 0.5024 [2021-03-26 04:08:20 swin_small_patch4_window7_224] INFO: Epoch: [135] [1050/1251] eta: 0:01:42 lr: 0.000578 loss: 3.5472 (3.3909) grad_norm: 1.2758 (inf) time: 0.5161 [2021-03-26 04:08:25 swin_small_patch4_window7_224] INFO: Epoch: [135] [1060/1251] eta: 0:01:37 lr: 0.000578 loss: 3.4661 (3.3917) grad_norm: 1.3183 (inf) time: 0.5130 [2021-03-26 04:08:30 swin_small_patch4_window7_224] INFO: Epoch: [135] [1070/1251] eta: 0:01:32 lr: 0.000578 loss: 3.4661 (3.3932) grad_norm: 1.3152 (inf) time: 0.5001 [2021-03-26 04:08:35 swin_small_patch4_window7_224] INFO: Epoch: [135] [1080/1251] eta: 0:01:27 lr: 0.000578 loss: 3.4051 (3.3914) grad_norm: 1.2988 (inf) time: 0.5042 [2021-03-26 04:08:40 swin_small_patch4_window7_224] INFO: Epoch: [135] [1090/1251] eta: 0:01:22 lr: 0.000578 loss: 3.3344 (3.3884) grad_norm: 1.2988 (inf) time: 0.5052 [2021-03-26 04:08:45 swin_small_patch4_window7_224] INFO: Epoch: [135] [1100/1251] eta: 0:01:16 lr: 0.000578 loss: 3.5732 (3.3904) grad_norm: 1.2866 (inf) time: 0.5020 [2021-03-26 04:08:50 swin_small_patch4_window7_224] INFO: Epoch: [135] [1110/1251] eta: 0:01:11 lr: 0.000578 loss: 3.5510 (3.3879) grad_norm: 1.3041 (inf) time: 0.5010 [2021-03-26 04:08:55 swin_small_patch4_window7_224] INFO: Epoch: [135] [1120/1251] eta: 0:01:06 lr: 0.000578 loss: 3.2109 (3.3869) grad_norm: 1.2693 (inf) time: 0.4964 [2021-03-26 04:09:00 swin_small_patch4_window7_224] INFO: Epoch: [135] [1130/1251] eta: 0:01:01 lr: 0.000578 loss: 3.3778 (3.3850) grad_norm: 1.2992 (inf) time: 0.5001 [2021-03-26 04:09:05 swin_small_patch4_window7_224] INFO: Epoch: [135] [1140/1251] eta: 0:00:56 lr: 0.000578 loss: 3.2965 (3.3854) grad_norm: 1.2988 (inf) time: 0.5095 [2021-03-26 04:09:10 swin_small_patch4_window7_224] INFO: Epoch: [135] [1150/1251] eta: 0:00:51 lr: 0.000578 loss: 3.4306 (3.3859) grad_norm: 1.2766 (inf) time: 0.5063 [2021-03-26 04:09:15 swin_small_patch4_window7_224] INFO: Epoch: [135] [1160/1251] eta: 0:00:46 lr: 0.000578 loss: 3.5756 (3.3865) grad_norm: 1.2754 (inf) time: 0.4991 [2021-03-26 04:09:20 swin_small_patch4_window7_224] INFO: Epoch: [135] [1170/1251] eta: 0:00:41 lr: 0.000578 loss: 3.4447 (3.3860) grad_norm: 1.3087 (inf) time: 0.5020 [2021-03-26 04:09:25 swin_small_patch4_window7_224] INFO: Epoch: [135] [1180/1251] eta: 0:00:36 lr: 0.000578 loss: 3.4115 (3.3852) grad_norm: 1.2157 (inf) time: 0.5029 [2021-03-26 04:09:30 swin_small_patch4_window7_224] INFO: Epoch: [135] [1190/1251] eta: 0:00:31 lr: 0.000578 loss: 3.3127 (3.3851) grad_norm: 1.2486 (inf) time: 0.4986 [2021-03-26 04:09:35 swin_small_patch4_window7_224] INFO: Epoch: [135] [1200/1251] eta: 0:00:25 lr: 0.000578 loss: 3.3718 (3.3850) grad_norm: 1.2964 (inf) time: 0.5019 [2021-03-26 04:09:40 swin_small_patch4_window7_224] INFO: Epoch: [135] [1210/1251] eta: 0:00:20 lr: 0.000577 loss: 3.3718 (3.3828) grad_norm: 1.3178 (inf) time: 0.5083 [2021-03-26 04:09:45 swin_small_patch4_window7_224] INFO: Epoch: [135] [1220/1251] eta: 0:00:15 lr: 0.000577 loss: 3.2790 (3.3823) grad_norm: 1.2587 (inf) time: 0.5085 [2021-03-26 04:09:50 swin_small_patch4_window7_224] INFO: Epoch: [135] [1230/1251] eta: 0:00:10 lr: 0.000577 loss: 3.2902 (3.3832) grad_norm: 1.2587 (inf) time: 0.5051 [2021-03-26 04:09:55 swin_small_patch4_window7_224] INFO: Epoch: [135] [1240/1251] eta: 0:00:05 lr: 0.000577 loss: 3.4012 (3.3832) grad_norm: 1.3863 (inf) time: 0.5030 [2021-03-26 04:10:00 swin_small_patch4_window7_224] INFO: Epoch: [135] [1250/1251] eta: 0:00:00 lr: 0.000577 loss: 3.5214 (3.3841) grad_norm: 1.3863 (inf) time: 0.5015 [2021-03-26 04:10:49 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 0.7119 (0.7119) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-26 04:10:50 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8588 (0.9209) acc1: 79.6875 (77.4148) acc5: 93.7500 (93.8920) [2021-03-26 04:10:51 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8588 (0.8880) acc1: 78.1250 (78.2738) acc5: 95.3125 (95.0893) [2021-03-26 04:10:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8704 (0.8796) acc1: 78.1250 (78.2762) acc5: 95.3125 (95.2117) [2021-03-26 04:10:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9276 (0.9201) acc1: 76.5625 (77.4390) acc5: 93.7500 (94.5884) [2021-03-26 04:10:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9895 (0.9380) acc1: 76.5625 (77.3120) acc5: 92.1875 (94.2400) [2021-03-26 04:11:02 swin_small_patch4_window7_224] INFO: * Acc@1 77.758 Acc@5 94.292 loss 0.931 [2021-03-26 04:11:02 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-26 04:11:02 swin_small_patch4_window7_224] INFO: Max accuracy: 77.76% [2021-03-26 04:11:06 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 0/1251] eta: 1:25:02 lr: 0.000577 loss: 3.3244 (3.3244) grad_norm: 1.4643 (1.4643) time: 4.0789 [2021-03-26 04:11:11 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 10/1251] eta: 0:17:35 lr: 0.000577 loss: 3.3164 (3.3037) grad_norm: 1.3740 (1.3839) time: 0.8501 [2021-03-26 04:11:16 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 20/1251] eta: 0:14:04 lr: 0.000577 loss: 3.3490 (3.3383) grad_norm: 1.3701 (1.3741) time: 0.5168 [2021-03-26 04:11:21 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 30/1251] eta: 0:12:46 lr: 0.000577 loss: 3.3999 (3.3789) grad_norm: 1.3701 (1.3997) time: 0.5049 [2021-03-26 04:11:26 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 40/1251] eta: 0:12:01 lr: 0.000577 loss: 3.4623 (3.3866) grad_norm: 1.3912 (1.3997) time: 0.4999 [2021-03-26 04:11:31 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 50/1251] eta: 0:11:33 lr: 0.000577 loss: 3.2475 (3.3547) grad_norm: 1.3598 (1.3887) time: 0.4991 [2021-03-26 04:11:37 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 60/1251] eta: 0:11:14 lr: 0.000577 loss: 3.2136 (3.3351) grad_norm: 1.2736 (1.3632) time: 0.5077 [2021-03-26 04:11:42 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 70/1251] eta: 0:10:59 lr: 0.000577 loss: 3.2847 (3.3093) grad_norm: 1.2552 (1.3593) time: 0.5119 [2021-03-26 04:11:47 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 80/1251] eta: 0:10:47 lr: 0.000577 loss: 3.3026 (3.3064) grad_norm: 1.2854 (1.3550) time: 0.5097 [2021-03-26 04:11:52 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 90/1251] eta: 0:10:36 lr: 0.000577 loss: 3.3784 (3.3236) grad_norm: 1.3393 (1.3551) time: 0.5108 [2021-03-26 04:11:57 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 100/1251] eta: 0:10:25 lr: 0.000577 loss: 3.5060 (3.3178) grad_norm: 1.2836 (1.3452) time: 0.5082 [2021-03-26 04:12:02 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 110/1251] eta: 0:10:17 lr: 0.000577 loss: 3.4335 (3.3256) grad_norm: 1.2467 (1.3413) time: 0.5093 [2021-03-26 04:12:07 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 120/1251] eta: 0:10:07 lr: 0.000577 loss: 3.5964 (3.3558) grad_norm: 1.3366 (1.3443) time: 0.5061 [2021-03-26 04:12:12 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 130/1251] eta: 0:09:59 lr: 0.000577 loss: 3.6104 (3.3669) grad_norm: 1.3461 (1.3424) time: 0.5021 [2021-03-26 04:12:17 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 140/1251] eta: 0:09:52 lr: 0.000577 loss: 3.4823 (3.3704) grad_norm: 1.3068 (1.3416) time: 0.5087 [2021-03-26 04:12:22 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 150/1251] eta: 0:09:45 lr: 0.000577 loss: 3.5762 (3.3900) grad_norm: 1.2776 (1.3397) time: 0.5075 [2021-03-26 04:12:27 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 160/1251] eta: 0:09:37 lr: 0.000577 loss: 3.5762 (3.3920) grad_norm: 1.2776 (1.3422) time: 0.5009 [2021-03-26 04:12:32 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 170/1251] eta: 0:09:31 lr: 0.000577 loss: 3.3338 (3.4073) grad_norm: 1.3783 (1.3479) time: 0.5043 [2021-03-26 04:12:37 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 180/1251] eta: 0:09:24 lr: 0.000577 loss: 3.6390 (3.4129) grad_norm: 1.4374 (1.3531) time: 0.5096 [2021-03-26 04:12:43 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 190/1251] eta: 0:09:18 lr: 0.000577 loss: 3.5603 (3.4097) grad_norm: 1.4299 (1.3559) time: 0.5122 [2021-03-26 04:12:48 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 200/1251] eta: 0:09:12 lr: 0.000576 loss: 3.3582 (3.4067) grad_norm: 1.4022 (1.3603) time: 0.5126 [2021-03-26 04:12:53 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 210/1251] eta: 0:09:05 lr: 0.000576 loss: 3.3812 (3.4056) grad_norm: 1.3939 (1.3607) time: 0.5030 [2021-03-26 04:12:58 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 220/1251] eta: 0:09:00 lr: 0.000576 loss: 3.5017 (3.4010) grad_norm: 1.2950 (1.3560) time: 0.5053 [2021-03-26 04:13:03 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 230/1251] eta: 0:08:54 lr: 0.000576 loss: 3.4682 (3.3953) grad_norm: 1.2850 (1.3540) time: 0.5088 [2021-03-26 04:13:08 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 240/1251] eta: 0:08:47 lr: 0.000576 loss: 3.4441 (3.3939) grad_norm: 1.2490 (1.3498) time: 0.5022 [2021-03-26 04:13:13 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 250/1251] eta: 0:08:42 lr: 0.000576 loss: 3.4575 (3.3935) grad_norm: 1.2327 (1.3474) time: 0.5049 [2021-03-26 04:13:18 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 260/1251] eta: 0:08:36 lr: 0.000576 loss: 3.5409 (3.3950) grad_norm: 1.2976 (1.3512) time: 0.5098 [2021-03-26 04:13:23 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 270/1251] eta: 0:08:30 lr: 0.000576 loss: 3.4901 (3.3994) grad_norm: 1.3218 (1.3519) time: 0.5090 [2021-03-26 04:13:28 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 280/1251] eta: 0:08:24 lr: 0.000576 loss: 3.2780 (3.3941) grad_norm: 1.2584 (1.3497) time: 0.5055 [2021-03-26 04:13:33 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 290/1251] eta: 0:08:19 lr: 0.000576 loss: 3.2780 (3.3946) grad_norm: 1.3237 (1.3509) time: 0.5015 [2021-03-26 04:13:38 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 300/1251] eta: 0:08:13 lr: 0.000576 loss: 3.4994 (3.3941) grad_norm: 1.4495 (1.3557) time: 0.5014 [2021-03-26 04:13:43 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 310/1251] eta: 0:08:08 lr: 0.000576 loss: 3.4994 (3.3975) grad_norm: 1.4613 (1.3576) time: 0.5109 [2021-03-26 04:13:48 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 320/1251] eta: 0:08:02 lr: 0.000576 loss: 3.5027 (3.4014) grad_norm: 1.3525 (1.3566) time: 0.5105 [2021-03-26 04:13:54 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 330/1251] eta: 0:07:57 lr: 0.000576 loss: 3.4298 (3.3958) grad_norm: 1.2625 (1.3542) time: 0.5098 [2021-03-26 04:13:59 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 340/1251] eta: 0:07:51 lr: 0.000576 loss: 3.4298 (3.3998) grad_norm: 1.3503 (1.3568) time: 0.5086 [2021-03-26 04:14:04 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 350/1251] eta: 0:07:46 lr: 0.000576 loss: 3.4013 (3.3960) grad_norm: 1.3317 (1.3551) time: 0.5023 [2021-03-26 04:14:09 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 360/1251] eta: 0:07:40 lr: 0.000576 loss: 3.4633 (3.4002) grad_norm: 1.3317 (1.3567) time: 0.5017 [2021-03-26 04:14:14 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 370/1251] eta: 0:07:35 lr: 0.000576 loss: 3.5573 (3.4013) grad_norm: 1.3747 (1.3563) time: 0.5018 [2021-03-26 04:14:19 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 380/1251] eta: 0:07:29 lr: 0.000576 loss: 3.3676 (3.4001) grad_norm: 1.3452 (1.3563) time: 0.5035 [2021-03-26 04:14:24 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 390/1251] eta: 0:07:24 lr: 0.000576 loss: 3.3676 (3.4012) grad_norm: 1.3922 (1.3594) time: 0.5024 [2021-03-26 04:14:29 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 400/1251] eta: 0:07:18 lr: 0.000576 loss: 3.2727 (3.3929) grad_norm: 1.4425 (1.3623) time: 0.5085 [2021-03-26 04:14:34 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 410/1251] eta: 0:07:13 lr: 0.000576 loss: 3.2178 (3.3895) grad_norm: 1.3684 (1.3619) time: 0.5133 [2021-03-26 04:14:39 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 420/1251] eta: 0:07:08 lr: 0.000576 loss: 3.5298 (3.3939) grad_norm: 1.3181 (1.3604) time: 0.5086 [2021-03-26 04:14:44 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 430/1251] eta: 0:07:02 lr: 0.000576 loss: 3.6713 (3.3938) grad_norm: 1.2827 (1.3591) time: 0.5047 [2021-03-26 04:14:49 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 440/1251] eta: 0:06:57 lr: 0.000576 loss: 3.6724 (3.3922) grad_norm: 1.3162 (nan) time: 0.5014 [2021-03-26 04:14:54 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 450/1251] eta: 0:06:52 lr: 0.000575 loss: 3.3503 (3.3892) grad_norm: 1.3327 (nan) time: 0.5029 [2021-03-26 04:14:59 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 460/1251] eta: 0:06:46 lr: 0.000575 loss: 3.4241 (3.3872) grad_norm: 1.3327 (nan) time: 0.5034 [2021-03-26 04:15:04 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 470/1251] eta: 0:06:41 lr: 0.000575 loss: 3.4956 (3.3920) grad_norm: 1.3475 (nan) time: 0.5012 [2021-03-26 04:15:09 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 480/1251] eta: 0:06:36 lr: 0.000575 loss: 3.3757 (3.3826) grad_norm: 1.3220 (nan) time: 0.5044 [2021-03-26 04:15:14 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 490/1251] eta: 0:06:30 lr: 0.000575 loss: 3.0976 (3.3803) grad_norm: 1.3087 (nan) time: 0.5033 [2021-03-26 04:15:19 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 500/1251] eta: 0:06:25 lr: 0.000575 loss: 3.5566 (3.3855) grad_norm: 1.3295 (nan) time: 0.5055 [2021-03-26 04:15:24 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 510/1251] eta: 0:06:20 lr: 0.000575 loss: 3.6501 (3.3871) grad_norm: 1.3014 (nan) time: 0.5065 [2021-03-26 04:15:29 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 520/1251] eta: 0:06:15 lr: 0.000575 loss: 3.4264 (3.3849) grad_norm: 1.3524 (nan) time: 0.5014 [2021-03-26 04:15:34 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 530/1251] eta: 0:06:09 lr: 0.000575 loss: 3.4264 (3.3864) grad_norm: 1.3796 (nan) time: 0.4979 [2021-03-26 04:15:39 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 540/1251] eta: 0:06:04 lr: 0.000575 loss: 3.6132 (3.3892) grad_norm: 1.3226 (nan) time: 0.5071 [2021-03-26 04:15:45 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 550/1251] eta: 0:05:59 lr: 0.000575 loss: 3.6624 (3.3919) grad_norm: 1.3072 (nan) time: 0.5211 [2021-03-26 04:15:50 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 560/1251] eta: 0:05:54 lr: 0.000575 loss: 3.5423 (3.3932) grad_norm: 1.3007 (nan) time: 0.5167 [2021-03-26 04:15:55 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 570/1251] eta: 0:05:49 lr: 0.000575 loss: 3.5345 (3.3920) grad_norm: 1.2515 (nan) time: 0.5108 [2021-03-26 04:16:00 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 580/1251] eta: 0:05:44 lr: 0.000575 loss: 3.4013 (3.3905) grad_norm: 1.2296 (nan) time: 0.5079 [2021-03-26 04:16:05 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 590/1251] eta: 0:05:38 lr: 0.000575 loss: 3.4038 (3.3917) grad_norm: 1.2901 (nan) time: 0.5027 [2021-03-26 04:16:10 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 600/1251] eta: 0:05:33 lr: 0.000575 loss: 3.5014 (3.3924) grad_norm: 1.3037 (nan) time: 0.4993 [2021-03-26 04:16:15 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 610/1251] eta: 0:05:28 lr: 0.000575 loss: 3.5967 (3.3921) grad_norm: 1.3339 (nan) time: 0.4984 [2021-03-26 04:16:20 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 620/1251] eta: 0:05:23 lr: 0.000575 loss: 3.2989 (3.3892) grad_norm: 1.3251 (nan) time: 0.5037 [2021-03-26 04:16:25 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 630/1251] eta: 0:05:17 lr: 0.000575 loss: 3.4992 (3.3917) grad_norm: 1.3251 (nan) time: 0.5044 [2021-03-26 04:16:30 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 640/1251] eta: 0:05:12 lr: 0.000575 loss: 3.5149 (3.3939) grad_norm: 1.3508 (nan) time: 0.5135 [2021-03-26 04:16:35 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 650/1251] eta: 0:05:07 lr: 0.000575 loss: 3.5026 (3.3921) grad_norm: 1.3908 (nan) time: 0.5173 [2021-03-26 04:16:41 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 660/1251] eta: 0:05:02 lr: 0.000575 loss: 3.5103 (3.3916) grad_norm: 1.2828 (nan) time: 0.5090 [2021-03-26 04:16:46 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 670/1251] eta: 0:04:57 lr: 0.000575 loss: 3.4517 (3.3897) grad_norm: 1.2603 (nan) time: 0.5088 [2021-03-26 04:16:51 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 680/1251] eta: 0:04:52 lr: 0.000575 loss: 3.5234 (3.3925) grad_norm: 1.3022 (nan) time: 0.5062 [2021-03-26 04:16:56 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 690/1251] eta: 0:04:47 lr: 0.000574 loss: 3.5655 (3.3941) grad_norm: 1.3463 (nan) time: 0.5086 [2021-03-26 04:17:01 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 700/1251] eta: 0:04:41 lr: 0.000574 loss: 3.5260 (3.3938) grad_norm: 1.3249 (nan) time: 0.5041 [2021-03-26 04:17:06 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 710/1251] eta: 0:04:36 lr: 0.000574 loss: 3.4233 (3.3919) grad_norm: 1.3082 (nan) time: 0.5012 [2021-03-26 04:17:11 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 720/1251] eta: 0:04:31 lr: 0.000574 loss: 3.5313 (3.3943) grad_norm: 1.3289 (nan) time: 0.5092 [2021-03-26 04:17:16 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 730/1251] eta: 0:04:26 lr: 0.000574 loss: 3.5228 (3.3929) grad_norm: 1.3436 (nan) time: 0.5110 [2021-03-26 04:17:21 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 740/1251] eta: 0:04:21 lr: 0.000574 loss: 3.5114 (3.3954) grad_norm: 1.3436 (nan) time: 0.5209 [2021-03-26 04:17:26 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 750/1251] eta: 0:04:16 lr: 0.000574 loss: 3.4735 (3.3933) grad_norm: 1.3326 (nan) time: 0.5211 [2021-03-26 04:17:31 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 760/1251] eta: 0:04:11 lr: 0.000574 loss: 3.2948 (3.3955) grad_norm: 1.3448 (nan) time: 0.5061 [2021-03-26 04:17:36 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 770/1251] eta: 0:04:05 lr: 0.000574 loss: 3.2948 (3.3943) grad_norm: 1.3407 (nan) time: 0.4967 [2021-03-26 04:17:41 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 780/1251] eta: 0:04:00 lr: 0.000574 loss: 3.3781 (3.3939) grad_norm: 1.2917 (nan) time: 0.4987 [2021-03-26 04:17:46 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 790/1251] eta: 0:03:55 lr: 0.000574 loss: 3.5742 (3.3948) grad_norm: 1.2619 (nan) time: 0.5034 [2021-03-26 04:17:51 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 800/1251] eta: 0:03:50 lr: 0.000574 loss: 3.3181 (3.3946) grad_norm: 1.2571 (nan) time: 0.5020 [2021-03-26 04:17:57 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 810/1251] eta: 0:03:45 lr: 0.000574 loss: 3.4086 (3.3941) grad_norm: 1.2981 (nan) time: 0.5075 [2021-03-26 04:18:02 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 820/1251] eta: 0:03:40 lr: 0.000574 loss: 3.4388 (3.3938) grad_norm: 1.2974 (nan) time: 0.5083 [2021-03-26 04:18:07 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 830/1251] eta: 0:03:35 lr: 0.000574 loss: 3.4264 (3.3952) grad_norm: 1.2651 (nan) time: 0.5144 [2021-03-26 04:18:12 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 840/1251] eta: 0:03:30 lr: 0.000574 loss: 3.5613 (3.3969) grad_norm: 1.2908 (nan) time: 0.5130 [2021-03-26 04:18:17 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 850/1251] eta: 0:03:24 lr: 0.000574 loss: 3.4179 (3.3960) grad_norm: 1.3922 (nan) time: 0.5012 [2021-03-26 04:18:22 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 860/1251] eta: 0:03:19 lr: 0.000574 loss: 3.3945 (3.3951) grad_norm: 1.3364 (nan) time: 0.5008 [2021-03-26 04:18:27 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 870/1251] eta: 0:03:14 lr: 0.000574 loss: 3.4246 (3.3933) grad_norm: 1.2876 (nan) time: 0.4999 [2021-03-26 04:18:32 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 880/1251] eta: 0:03:09 lr: 0.000574 loss: 3.3399 (3.3917) grad_norm: 1.2488 (nan) time: 0.5044 [2021-03-26 04:18:37 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 890/1251] eta: 0:03:04 lr: 0.000574 loss: 3.4615 (3.3915) grad_norm: 1.2994 (nan) time: 0.5067 [2021-03-26 04:18:42 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 900/1251] eta: 0:02:59 lr: 0.000574 loss: 3.3687 (3.3910) grad_norm: 1.3698 (nan) time: 0.5069 [2021-03-26 04:18:47 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 910/1251] eta: 0:02:54 lr: 0.000574 loss: 3.2897 (3.3878) grad_norm: 1.3128 (nan) time: 0.5070 [2021-03-26 04:18:52 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 920/1251] eta: 0:02:48 lr: 0.000574 loss: 3.3558 (3.3870) grad_norm: 1.2697 (nan) time: 0.5008 [2021-03-26 04:18:57 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 930/1251] eta: 0:02:43 lr: 0.000573 loss: 3.5359 (3.3867) grad_norm: 1.2903 (nan) time: 0.5069 [2021-03-26 04:19:02 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 940/1251] eta: 0:02:38 lr: 0.000573 loss: 3.1869 (3.3831) grad_norm: 1.3295 (nan) time: 0.5038 [2021-03-26 04:19:07 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 950/1251] eta: 0:02:33 lr: 0.000573 loss: 3.1869 (3.3817) grad_norm: 1.3938 (nan) time: 0.4997 [2021-03-26 04:19:12 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 960/1251] eta: 0:02:28 lr: 0.000573 loss: 3.3094 (3.3815) grad_norm: 1.3405 (nan) time: 0.5089 [2021-03-26 04:19:18 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 970/1251] eta: 0:02:23 lr: 0.000573 loss: 3.5437 (3.3837) grad_norm: 1.2923 (nan) time: 0.5075 [2021-03-26 04:19:23 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 980/1251] eta: 0:02:18 lr: 0.000573 loss: 3.4392 (3.3815) grad_norm: 1.2813 (nan) time: 0.5052 [2021-03-26 04:19:28 swin_small_patch4_window7_224] INFO: Epoch: [136] [ 990/1251] eta: 0:02:13 lr: 0.000573 loss: 3.1972 (3.3795) grad_norm: 1.3138 (nan) time: 0.5069 [2021-03-26 04:19:33 swin_small_patch4_window7_224] INFO: Epoch: [136] [1000/1251] eta: 0:02:08 lr: 0.000573 loss: 3.4801 (3.3798) grad_norm: 1.3376 (nan) time: 0.5097 [2021-03-26 04:19:38 swin_small_patch4_window7_224] INFO: Epoch: [136] [1010/1251] eta: 0:02:02 lr: 0.000573 loss: 3.5620 (3.3782) grad_norm: 1.3098 (nan) time: 0.5077 [2021-03-26 04:19:43 swin_small_patch4_window7_224] INFO: Epoch: [136] [1020/1251] eta: 0:01:57 lr: 0.000573 loss: 3.3933 (3.3799) grad_norm: 1.3224 (nan) time: 0.5073 [2021-03-26 04:19:48 swin_small_patch4_window7_224] INFO: Epoch: [136] [1030/1251] eta: 0:01:52 lr: 0.000573 loss: 3.3933 (3.3801) grad_norm: 1.3332 (nan) time: 0.5036 [2021-03-26 04:19:53 swin_small_patch4_window7_224] INFO: Epoch: [136] [1040/1251] eta: 0:01:47 lr: 0.000573 loss: 3.5379 (3.3826) grad_norm: 1.3332 (nan) time: 0.5044 [2021-03-26 04:19:58 swin_small_patch4_window7_224] INFO: Epoch: [136] [1050/1251] eta: 0:01:42 lr: 0.000573 loss: 3.5379 (3.3808) grad_norm: 1.3074 (nan) time: 0.5143 [2021-03-26 04:20:03 swin_small_patch4_window7_224] INFO: Epoch: [136] [1060/1251] eta: 0:01:37 lr: 0.000573 loss: 3.5364 (3.3831) grad_norm: 1.2926 (nan) time: 0.5088 [2021-03-26 04:20:08 swin_small_patch4_window7_224] INFO: Epoch: [136] [1070/1251] eta: 0:01:32 lr: 0.000573 loss: 3.5035 (3.3811) grad_norm: 1.2742 (nan) time: 0.5050 [2021-03-26 04:20:13 swin_small_patch4_window7_224] INFO: Epoch: [136] [1080/1251] eta: 0:01:27 lr: 0.000573 loss: 3.5191 (3.3832) grad_norm: 1.3197 (nan) time: 0.5071 [2021-03-26 04:20:18 swin_small_patch4_window7_224] INFO: Epoch: [136] [1090/1251] eta: 0:01:22 lr: 0.000573 loss: 3.6196 (3.3831) grad_norm: 1.4269 (nan) time: 0.5033 [2021-03-26 04:20:23 swin_small_patch4_window7_224] INFO: Epoch: [136] [1100/1251] eta: 0:01:16 lr: 0.000573 loss: 3.4730 (3.3814) grad_norm: 1.3283 (nan) time: 0.5048 [2021-03-26 04:20:28 swin_small_patch4_window7_224] INFO: Epoch: [136] [1110/1251] eta: 0:01:11 lr: 0.000573 loss: 3.2712 (3.3802) grad_norm: 1.2663 (nan) time: 0.4998 [2021-03-26 04:20:33 swin_small_patch4_window7_224] INFO: Epoch: [136] [1120/1251] eta: 0:01:06 lr: 0.000573 loss: 3.5226 (3.3813) grad_norm: 1.2945 (nan) time: 0.5002 [2021-03-26 04:20:38 swin_small_patch4_window7_224] INFO: Epoch: [136] [1130/1251] eta: 0:01:01 lr: 0.000573 loss: 3.5698 (3.3821) grad_norm: 1.3602 (nan) time: 0.5057 [2021-03-26 04:20:44 swin_small_patch4_window7_224] INFO: Epoch: [136] [1140/1251] eta: 0:00:56 lr: 0.000573 loss: 3.2387 (3.3811) grad_norm: 1.3358 (nan) time: 0.5100 [2021-03-26 04:20:49 swin_small_patch4_window7_224] INFO: Epoch: [136] [1150/1251] eta: 0:00:51 lr: 0.000573 loss: 3.4752 (3.3834) grad_norm: 1.2826 (nan) time: 0.5152 [2021-03-26 04:20:54 swin_small_patch4_window7_224] INFO: Epoch: [136] [1160/1251] eta: 0:00:46 lr: 0.000573 loss: 3.5549 (3.3823) grad_norm: 1.3235 (nan) time: 0.5051 [2021-03-26 04:20:59 swin_small_patch4_window7_224] INFO: Epoch: [136] [1170/1251] eta: 0:00:41 lr: 0.000573 loss: 3.3326 (3.3826) grad_norm: 1.3020 (nan) time: 0.5000 [2021-03-26 04:21:04 swin_small_patch4_window7_224] INFO: Epoch: [136] [1180/1251] eta: 0:00:36 lr: 0.000572 loss: 3.3580 (3.3821) grad_norm: 1.2722 (nan) time: 0.4989 [2021-03-26 04:21:09 swin_small_patch4_window7_224] INFO: Epoch: [136] [1190/1251] eta: 0:00:31 lr: 0.000572 loss: 3.3642 (3.3823) grad_norm: 1.3131 (nan) time: 0.4952 [2021-03-26 04:21:14 swin_small_patch4_window7_224] INFO: Epoch: [136] [1200/1251] eta: 0:00:25 lr: 0.000572 loss: 3.4402 (3.3818) grad_norm: 1.2960 (nan) time: 0.5003 [2021-03-26 04:21:19 swin_small_patch4_window7_224] INFO: Epoch: [136] [1210/1251] eta: 0:00:20 lr: 0.000572 loss: 3.3131 (3.3810) grad_norm: 1.3014 (nan) time: 0.4994 [2021-03-26 04:21:24 swin_small_patch4_window7_224] INFO: Epoch: [136] [1220/1251] eta: 0:00:15 lr: 0.000572 loss: 3.3097 (3.3807) grad_norm: 1.3817 (nan) time: 0.4998 [2021-03-26 04:21:29 swin_small_patch4_window7_224] INFO: Epoch: [136] [1230/1251] eta: 0:00:10 lr: 0.000572 loss: 3.4230 (3.3818) grad_norm: 1.3744 (nan) time: 0.5020 [2021-03-26 04:21:34 swin_small_patch4_window7_224] INFO: Epoch: [136] [1240/1251] eta: 0:00:05 lr: 0.000572 loss: 3.5146 (3.3837) grad_norm: 1.3744 (nan) time: 0.5022 [2021-03-26 04:21:39 swin_small_patch4_window7_224] INFO: Epoch: [136] [1250/1251] eta: 0:00:00 lr: 0.000572 loss: 3.5146 (3.3839) grad_norm: 1.3537 (nan) time: 0.4982 [2021-03-26 04:21:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 0.8328 (0.8328) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-26 04:21:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9084 (0.9050) acc1: 79.6875 (78.8352) acc5: 95.3125 (95.3125) [2021-03-26 04:21:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9635 (0.9417) acc1: 76.5625 (77.8274) acc5: 93.7500 (94.3452) [2021-03-26 04:21:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 1.0448 (0.9562) acc1: 75.0000 (77.6714) acc5: 93.7500 (94.0524) [2021-03-26 04:21:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9949 (0.9409) acc1: 78.1250 (77.7439) acc5: 93.7500 (94.2835) [2021-03-26 04:21:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8924 (0.9645) acc1: 73.4375 (77.0240) acc5: 93.7500 (93.9840) [2021-03-26 04:22:01 swin_small_patch4_window7_224] INFO: * Acc@1 77.628 Acc@5 94.232 loss 0.945 [2021-03-26 04:22:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.6% [2021-03-26 04:22:01 swin_small_patch4_window7_224] INFO: Max accuracy: 77.76% [2021-03-26 04:22:05 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 0/1251] eta: 1:26:08 lr: 0.000572 loss: 2.8405 (2.8405) grad_norm: 1.3079 (1.3079) time: 4.1316 [2021-03-26 04:22:10 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 10/1251] eta: 0:17:57 lr: 0.000572 loss: 3.4200 (3.4028) grad_norm: 1.4167 (1.3858) time: 0.8683 [2021-03-26 04:22:15 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 20/1251] eta: 0:14:19 lr: 0.000572 loss: 3.4712 (3.3308) grad_norm: 1.3297 (1.3562) time: 0.5268 [2021-03-26 04:22:20 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 30/1251] eta: 0:12:53 lr: 0.000572 loss: 3.3715 (3.2837) grad_norm: 1.3009 (1.3361) time: 0.5046 [2021-03-26 04:22:25 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 40/1251] eta: 0:12:08 lr: 0.000572 loss: 3.2857 (3.3094) grad_norm: 1.3319 (1.3500) time: 0.5004 [2021-03-26 04:22:30 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 50/1251] eta: 0:11:38 lr: 0.000572 loss: 3.2722 (3.3276) grad_norm: 1.3338 (1.3497) time: 0.5013 [2021-03-26 04:22:35 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 60/1251] eta: 0:11:15 lr: 0.000572 loss: 3.2722 (3.3200) grad_norm: 1.2917 (1.3403) time: 0.4970 [2021-03-26 04:22:40 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 70/1251] eta: 0:10:58 lr: 0.000572 loss: 3.2522 (3.3185) grad_norm: 1.2952 (1.3395) time: 0.4972 [2021-03-26 04:22:45 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 80/1251] eta: 0:10:45 lr: 0.000572 loss: 3.5087 (3.3502) grad_norm: 1.2993 (1.3356) time: 0.5022 [2021-03-26 04:22:50 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 90/1251] eta: 0:10:35 lr: 0.000572 loss: 3.6470 (3.3583) grad_norm: 1.2360 (1.3282) time: 0.5091 [2021-03-26 04:22:56 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 100/1251] eta: 0:10:25 lr: 0.000572 loss: 3.4982 (3.3625) grad_norm: 1.2360 (1.3254) time: 0.5117 [2021-03-26 04:23:01 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 110/1251] eta: 0:10:16 lr: 0.000572 loss: 3.5116 (3.3696) grad_norm: 1.3212 (1.3352) time: 0.5107 [2021-03-26 04:23:06 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 120/1251] eta: 0:10:08 lr: 0.000572 loss: 3.5116 (3.3891) grad_norm: 1.4031 (1.3398) time: 0.5109 [2021-03-26 04:23:11 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 130/1251] eta: 0:10:00 lr: 0.000572 loss: 3.3873 (3.3746) grad_norm: 1.4800 (1.3540) time: 0.5096 [2021-03-26 04:23:16 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 140/1251] eta: 0:09:52 lr: 0.000572 loss: 3.3330 (3.3809) grad_norm: 1.4404 (1.3533) time: 0.5018 [2021-03-26 04:23:21 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 150/1251] eta: 0:09:44 lr: 0.000572 loss: 3.4086 (3.3675) grad_norm: 1.3498 (1.3554) time: 0.4969 [2021-03-26 04:23:26 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 160/1251] eta: 0:09:37 lr: 0.000572 loss: 3.0321 (3.3593) grad_norm: 1.3643 (1.3609) time: 0.5010 [2021-03-26 04:23:31 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 170/1251] eta: 0:09:30 lr: 0.000571 loss: 3.3620 (3.3617) grad_norm: 1.3925 (1.3618) time: 0.5022 [2021-03-26 04:23:36 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 180/1251] eta: 0:09:23 lr: 0.000571 loss: 3.3620 (3.3624) grad_norm: 1.3744 (1.3628) time: 0.5049 [2021-03-26 04:23:41 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 190/1251] eta: 0:09:17 lr: 0.000571 loss: 3.4141 (3.3735) grad_norm: 1.4044 (1.3682) time: 0.5121 [2021-03-26 04:23:46 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 200/1251] eta: 0:09:11 lr: 0.000571 loss: 3.6914 (3.3798) grad_norm: 1.4564 (1.3717) time: 0.5093 [2021-03-26 04:23:51 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 210/1251] eta: 0:09:05 lr: 0.000571 loss: 3.6914 (3.3813) grad_norm: 1.3859 (1.3717) time: 0.5048 [2021-03-26 04:23:56 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 220/1251] eta: 0:08:59 lr: 0.000571 loss: 3.2618 (3.3732) grad_norm: 1.3859 (1.3731) time: 0.5119 [2021-03-26 04:24:01 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 230/1251] eta: 0:08:53 lr: 0.000571 loss: 3.0858 (3.3667) grad_norm: 1.2783 (1.3700) time: 0.5135 [2021-03-26 04:24:07 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 240/1251] eta: 0:08:48 lr: 0.000571 loss: 3.0463 (3.3587) grad_norm: 1.2608 (1.3659) time: 0.5113 [2021-03-26 04:24:12 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 250/1251] eta: 0:08:42 lr: 0.000571 loss: 3.0463 (3.3547) grad_norm: 1.2987 (1.3644) time: 0.5100 [2021-03-26 04:24:17 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 260/1251] eta: 0:08:36 lr: 0.000571 loss: 3.6981 (3.3700) grad_norm: 1.3421 (1.3637) time: 0.5046 [2021-03-26 04:24:22 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 270/1251] eta: 0:08:30 lr: 0.000571 loss: 3.5845 (3.3688) grad_norm: 1.3412 (1.3640) time: 0.4999 [2021-03-26 04:24:27 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 280/1251] eta: 0:08:24 lr: 0.000571 loss: 3.5044 (3.3691) grad_norm: 1.3491 (1.3686) time: 0.4969 [2021-03-26 04:24:32 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 290/1251] eta: 0:08:18 lr: 0.000571 loss: 3.6315 (3.3762) grad_norm: 1.4315 (1.3731) time: 0.4974 [2021-03-26 04:24:37 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 300/1251] eta: 0:08:12 lr: 0.000571 loss: 3.3860 (3.3697) grad_norm: 1.3798 (1.3719) time: 0.5011 [2021-03-26 04:24:42 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 310/1251] eta: 0:08:07 lr: 0.000571 loss: 3.1802 (3.3686) grad_norm: 1.3020 (1.3689) time: 0.5098 [2021-03-26 04:24:47 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 320/1251] eta: 0:08:01 lr: 0.000571 loss: 3.0093 (3.3571) grad_norm: 1.3107 (1.3695) time: 0.5107 [2021-03-26 04:24:52 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 330/1251] eta: 0:07:56 lr: 0.000571 loss: 3.0614 (3.3546) grad_norm: 1.3363 (1.3694) time: 0.5080 [2021-03-26 04:24:57 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 340/1251] eta: 0:07:51 lr: 0.000571 loss: 3.1109 (3.3477) grad_norm: 1.3491 (1.3696) time: 0.5109 [2021-03-26 04:25:02 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 350/1251] eta: 0:07:45 lr: 0.000571 loss: 3.3262 (3.3530) grad_norm: 1.2711 (1.3669) time: 0.5061 [2021-03-26 04:25:07 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 360/1251] eta: 0:07:40 lr: 0.000571 loss: 3.4709 (3.3498) grad_norm: 1.2382 (1.3653) time: 0.5016 [2021-03-26 04:25:12 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 370/1251] eta: 0:07:34 lr: 0.000571 loss: 3.2982 (3.3477) grad_norm: 1.3230 (1.3645) time: 0.5039 [2021-03-26 04:25:17 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 380/1251] eta: 0:07:29 lr: 0.000571 loss: 3.5225 (3.3479) grad_norm: 1.3177 (1.3618) time: 0.5060 [2021-03-26 04:25:22 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 390/1251] eta: 0:07:23 lr: 0.000571 loss: 3.4934 (3.3456) grad_norm: 1.3177 (1.3610) time: 0.5048 [2021-03-26 04:25:27 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 400/1251] eta: 0:07:18 lr: 0.000571 loss: 3.5468 (3.3559) grad_norm: 1.3144 (1.3587) time: 0.5076 [2021-03-26 04:25:33 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 410/1251] eta: 0:07:13 lr: 0.000570 loss: 3.5292 (3.3515) grad_norm: 1.3002 (1.3571) time: 0.5155 [2021-03-26 04:25:38 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 420/1251] eta: 0:07:08 lr: 0.000570 loss: 3.3377 (3.3518) grad_norm: 1.3237 (1.3567) time: 0.5143 [2021-03-26 04:25:43 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 430/1251] eta: 0:07:02 lr: 0.000570 loss: 3.4790 (3.3575) grad_norm: 1.3432 (1.3575) time: 0.5067 [2021-03-26 04:25:48 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 440/1251] eta: 0:06:57 lr: 0.000570 loss: 3.4024 (3.3527) grad_norm: 1.3618 (1.3568) time: 0.4971 [2021-03-26 04:25:53 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 450/1251] eta: 0:06:51 lr: 0.000570 loss: 3.2927 (3.3514) grad_norm: 1.3741 (1.3598) time: 0.4957 [2021-03-26 04:25:58 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 460/1251] eta: 0:06:46 lr: 0.000570 loss: 3.1954 (3.3505) grad_norm: 1.3734 (1.3593) time: 0.5046 [2021-03-26 04:26:03 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 470/1251] eta: 0:06:41 lr: 0.000570 loss: 3.4449 (3.3494) grad_norm: 1.3240 (1.3589) time: 0.5012 [2021-03-26 04:26:08 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 480/1251] eta: 0:06:36 lr: 0.000570 loss: 3.4911 (3.3480) grad_norm: 1.2939 (1.3591) time: 0.5017 [2021-03-26 04:26:13 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 490/1251] eta: 0:06:30 lr: 0.000570 loss: 3.6171 (3.3554) grad_norm: 1.2939 (1.3581) time: 0.5091 [2021-03-26 04:26:18 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 500/1251] eta: 0:06:25 lr: 0.000570 loss: 3.5803 (3.3553) grad_norm: 1.2885 (1.3573) time: 0.5093 [2021-03-26 04:26:23 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 510/1251] eta: 0:06:20 lr: 0.000570 loss: 3.3997 (3.3550) grad_norm: 1.3232 (1.3568) time: 0.5043 [2021-03-26 04:26:28 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 520/1251] eta: 0:06:15 lr: 0.000570 loss: 3.2178 (3.3475) grad_norm: 1.3232 (1.3565) time: 0.5035 [2021-03-26 04:26:33 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 530/1251] eta: 0:06:09 lr: 0.000570 loss: 3.2400 (3.3465) grad_norm: 1.3180 (1.3566) time: 0.5113 [2021-03-26 04:26:38 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 540/1251] eta: 0:06:04 lr: 0.000570 loss: 3.3014 (3.3432) grad_norm: 1.3271 (1.3569) time: 0.5085 [2021-03-26 04:26:43 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 550/1251] eta: 0:05:59 lr: 0.000570 loss: 3.2754 (3.3396) grad_norm: 1.3564 (1.3586) time: 0.5076 [2021-03-26 04:26:48 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 560/1251] eta: 0:05:54 lr: 0.000570 loss: 3.3678 (3.3392) grad_norm: 1.3770 (1.3586) time: 0.5134 [2021-03-26 04:26:54 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 570/1251] eta: 0:05:49 lr: 0.000570 loss: 3.2769 (3.3352) grad_norm: 1.3544 (1.3604) time: 0.5093 [2021-03-26 04:26:59 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 580/1251] eta: 0:05:44 lr: 0.000570 loss: 3.3831 (3.3391) grad_norm: 1.3816 (1.3607) time: 0.5080 [2021-03-26 04:27:04 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 590/1251] eta: 0:05:38 lr: 0.000570 loss: 3.4430 (3.3390) grad_norm: 1.3250 (1.3604) time: 0.5072 [2021-03-26 04:27:09 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 600/1251] eta: 0:05:33 lr: 0.000570 loss: 3.2982 (3.3398) grad_norm: 1.3735 (1.3615) time: 0.5043 [2021-03-26 04:27:14 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 610/1251] eta: 0:05:28 lr: 0.000570 loss: 3.3847 (3.3444) grad_norm: 1.2976 (1.3601) time: 0.5077 [2021-03-26 04:27:19 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 620/1251] eta: 0:05:23 lr: 0.000570 loss: 3.5234 (3.3458) grad_norm: 1.2976 (1.3607) time: 0.5099 [2021-03-26 04:27:24 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 630/1251] eta: 0:05:18 lr: 0.000570 loss: 3.5388 (3.3473) grad_norm: 1.3994 (1.3611) time: 0.5021 [2021-03-26 04:27:29 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 640/1251] eta: 0:05:12 lr: 0.000570 loss: 3.5388 (3.3465) grad_norm: 1.3622 (1.3606) time: 0.4965 [2021-03-26 04:27:34 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 650/1251] eta: 0:05:07 lr: 0.000570 loss: 3.2693 (3.3478) grad_norm: 1.3409 (1.3606) time: 0.5072 [2021-03-26 04:27:39 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 660/1251] eta: 0:05:02 lr: 0.000569 loss: 3.4849 (3.3486) grad_norm: 1.3522 (1.3610) time: 0.5127 [2021-03-26 04:27:44 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 670/1251] eta: 0:04:57 lr: 0.000569 loss: 3.5260 (3.3492) grad_norm: 1.3805 (1.3617) time: 0.5066 [2021-03-26 04:27:49 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 680/1251] eta: 0:04:52 lr: 0.000569 loss: 3.5239 (3.3485) grad_norm: 1.3358 (1.3615) time: 0.5047 [2021-03-26 04:27:54 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 690/1251] eta: 0:04:47 lr: 0.000569 loss: 3.3549 (3.3457) grad_norm: 1.3057 (1.3608) time: 0.5066 [2021-03-26 04:27:59 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 700/1251] eta: 0:04:41 lr: 0.000569 loss: 3.2672 (3.3455) grad_norm: 1.2717 (1.3602) time: 0.5078 [2021-03-26 04:28:04 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 710/1251] eta: 0:04:36 lr: 0.000569 loss: 3.1868 (3.3400) grad_norm: 1.3338 (1.3601) time: 0.5043 [2021-03-26 04:28:09 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 720/1251] eta: 0:04:31 lr: 0.000569 loss: 3.1045 (3.3401) grad_norm: 1.3156 (1.3590) time: 0.5002 [2021-03-26 04:28:14 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 730/1251] eta: 0:04:26 lr: 0.000569 loss: 3.4069 (3.3406) grad_norm: 1.3023 (1.3594) time: 0.5062 [2021-03-26 04:28:20 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 740/1251] eta: 0:04:21 lr: 0.000569 loss: 3.3301 (3.3389) grad_norm: 1.4017 (1.3603) time: 0.5196 [2021-03-26 04:28:25 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 750/1251] eta: 0:04:16 lr: 0.000569 loss: 3.1887 (3.3374) grad_norm: 1.3770 (1.3601) time: 0.5157 [2021-03-26 04:28:30 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 760/1251] eta: 0:04:11 lr: 0.000569 loss: 3.1671 (3.3352) grad_norm: 1.2988 (1.3595) time: 0.5078 [2021-03-26 04:28:35 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 770/1251] eta: 0:04:06 lr: 0.000569 loss: 3.1794 (3.3340) grad_norm: 1.3109 (1.3595) time: 0.5150 [2021-03-26 04:28:40 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 780/1251] eta: 0:04:00 lr: 0.000569 loss: 3.2069 (3.3338) grad_norm: 1.3436 (1.3591) time: 0.5157 [2021-03-26 04:28:45 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 790/1251] eta: 0:03:55 lr: 0.000569 loss: 3.4146 (3.3338) grad_norm: 1.2954 (1.3586) time: 0.5086 [2021-03-26 04:28:50 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 800/1251] eta: 0:03:50 lr: 0.000569 loss: 3.6897 (3.3382) grad_norm: 1.3695 (1.3605) time: 0.5068 [2021-03-26 04:28:55 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 810/1251] eta: 0:03:45 lr: 0.000569 loss: 3.6947 (3.3395) grad_norm: 1.3877 (1.3604) time: 0.5027 [2021-03-26 04:29:01 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 820/1251] eta: 0:03:40 lr: 0.000569 loss: 3.6445 (3.3401) grad_norm: 1.3312 (1.3605) time: 0.5069 [2021-03-26 04:29:06 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 830/1251] eta: 0:03:35 lr: 0.000569 loss: 3.1530 (3.3362) grad_norm: 1.3337 (1.3603) time: 0.5114 [2021-03-26 04:29:11 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 840/1251] eta: 0:03:30 lr: 0.000569 loss: 3.1530 (3.3359) grad_norm: 1.2786 (1.3590) time: 0.5113 [2021-03-26 04:29:16 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 850/1251] eta: 0:03:25 lr: 0.000569 loss: 3.5292 (3.3377) grad_norm: 1.2786 (1.3584) time: 0.5118 [2021-03-26 04:29:21 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 860/1251] eta: 0:03:19 lr: 0.000569 loss: 3.5292 (3.3383) grad_norm: 1.3501 (1.3583) time: 0.5116 [2021-03-26 04:29:26 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 870/1251] eta: 0:03:14 lr: 0.000569 loss: 3.2990 (3.3368) grad_norm: 1.3268 (1.3586) time: 0.5073 [2021-03-26 04:29:31 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 880/1251] eta: 0:03:09 lr: 0.000569 loss: 3.5652 (3.3405) grad_norm: 1.3512 (1.3595) time: 0.4992 [2021-03-26 04:29:36 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 890/1251] eta: 0:03:04 lr: 0.000569 loss: 3.5619 (3.3411) grad_norm: 1.3512 (1.3596) time: 0.4980 [2021-03-26 04:29:41 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 900/1251] eta: 0:02:59 lr: 0.000568 loss: 3.3432 (3.3412) grad_norm: 1.3676 (1.3603) time: 0.4974 [2021-03-26 04:29:46 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 910/1251] eta: 0:02:54 lr: 0.000568 loss: 3.5273 (3.3436) grad_norm: 1.3291 (1.3596) time: 0.5025 [2021-03-26 04:29:51 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 920/1251] eta: 0:02:49 lr: 0.000568 loss: 3.5037 (3.3417) grad_norm: 1.3105 (1.3590) time: 0.5051 [2021-03-26 04:29:56 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 930/1251] eta: 0:02:43 lr: 0.000568 loss: 3.4877 (3.3429) grad_norm: 1.3227 (1.3594) time: 0.5104 [2021-03-26 04:30:01 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 940/1251] eta: 0:02:38 lr: 0.000568 loss: 3.4877 (3.3425) grad_norm: 1.3501 (1.3603) time: 0.5148 [2021-03-26 04:30:06 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 950/1251] eta: 0:02:33 lr: 0.000568 loss: 3.4618 (3.3442) grad_norm: 1.3501 (1.3598) time: 0.5071 [2021-03-26 04:30:12 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 960/1251] eta: 0:02:28 lr: 0.000568 loss: 3.6343 (3.3480) grad_norm: 1.2843 (1.3593) time: 0.5092 [2021-03-26 04:30:17 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 970/1251] eta: 0:02:23 lr: 0.000568 loss: 3.6188 (3.3481) grad_norm: 1.3222 (1.3594) time: 0.5084 [2021-03-26 04:30:22 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 980/1251] eta: 0:02:18 lr: 0.000568 loss: 3.6460 (3.3526) grad_norm: 1.3962 (1.3601) time: 0.5014 [2021-03-26 04:30:27 swin_small_patch4_window7_224] INFO: Epoch: [137] [ 990/1251] eta: 0:02:13 lr: 0.000568 loss: 3.6669 (3.3544) grad_norm: 1.3821 (1.3601) time: 0.5012 [2021-03-26 04:30:32 swin_small_patch4_window7_224] INFO: Epoch: [137] [1000/1251] eta: 0:02:08 lr: 0.000568 loss: 3.4246 (3.3535) grad_norm: 1.3308 (1.3601) time: 0.5021 [2021-03-26 04:30:37 swin_small_patch4_window7_224] INFO: Epoch: [137] [1010/1251] eta: 0:02:02 lr: 0.000568 loss: 3.1423 (3.3510) grad_norm: 1.3144 (1.3596) time: 0.5050 [2021-03-26 04:30:42 swin_small_patch4_window7_224] INFO: Epoch: [137] [1020/1251] eta: 0:01:57 lr: 0.000568 loss: 3.3800 (3.3535) grad_norm: 1.3021 (1.3591) time: 0.5051 [2021-03-26 04:30:47 swin_small_patch4_window7_224] INFO: Epoch: [137] [1030/1251] eta: 0:01:52 lr: 0.000568 loss: 3.6046 (3.3546) grad_norm: 1.3123 (1.3590) time: 0.5036 [2021-03-26 04:30:52 swin_small_patch4_window7_224] INFO: Epoch: [137] [1040/1251] eta: 0:01:47 lr: 0.000568 loss: 3.4956 (3.3552) grad_norm: 1.3409 (1.3598) time: 0.5081 [2021-03-26 04:30:57 swin_small_patch4_window7_224] INFO: Epoch: [137] [1050/1251] eta: 0:01:42 lr: 0.000568 loss: 3.4400 (3.3549) grad_norm: 1.4098 (1.3600) time: 0.5100 [2021-03-26 04:31:02 swin_small_patch4_window7_224] INFO: Epoch: [137] [1060/1251] eta: 0:01:37 lr: 0.000568 loss: 3.4931 (3.3578) grad_norm: 1.3760 (1.3600) time: 0.5035 [2021-03-26 04:31:07 swin_small_patch4_window7_224] INFO: Epoch: [137] [1070/1251] eta: 0:01:32 lr: 0.000568 loss: 3.6905 (3.3599) grad_norm: 1.3524 (1.3602) time: 0.5054 [2021-03-26 04:31:12 swin_small_patch4_window7_224] INFO: Epoch: [137] [1080/1251] eta: 0:01:27 lr: 0.000568 loss: 3.4742 (3.3585) grad_norm: 1.4017 (1.3608) time: 0.5038 [2021-03-26 04:31:17 swin_small_patch4_window7_224] INFO: Epoch: [137] [1090/1251] eta: 0:01:22 lr: 0.000568 loss: 3.5960 (3.3616) grad_norm: 1.3952 (1.3606) time: 0.5029 [2021-03-26 04:31:22 swin_small_patch4_window7_224] INFO: Epoch: [137] [1100/1251] eta: 0:01:16 lr: 0.000568 loss: 3.6043 (3.3616) grad_norm: 1.2861 (1.3599) time: 0.5063 [2021-03-26 04:31:27 swin_small_patch4_window7_224] INFO: Epoch: [137] [1110/1251] eta: 0:01:11 lr: 0.000568 loss: 3.5831 (3.3633) grad_norm: 1.2768 (1.3593) time: 0.4996 [2021-03-26 04:31:32 swin_small_patch4_window7_224] INFO: Epoch: [137] [1120/1251] eta: 0:01:06 lr: 0.000568 loss: 3.6325 (3.3644) grad_norm: 1.3154 (1.3593) time: 0.4962 [2021-03-26 04:31:37 swin_small_patch4_window7_224] INFO: Epoch: [137] [1130/1251] eta: 0:01:01 lr: 0.000568 loss: 3.4787 (3.3639) grad_norm: 1.3402 (1.3592) time: 0.5100 [2021-03-26 04:31:42 swin_small_patch4_window7_224] INFO: Epoch: [137] [1140/1251] eta: 0:00:56 lr: 0.000567 loss: 3.1605 (3.3621) grad_norm: 1.3040 (1.3591) time: 0.5167 [2021-03-26 04:31:47 swin_small_patch4_window7_224] INFO: Epoch: [137] [1150/1251] eta: 0:00:51 lr: 0.000567 loss: 3.3409 (3.3616) grad_norm: 1.3204 (1.3592) time: 0.5046 [2021-03-26 04:31:52 swin_small_patch4_window7_224] INFO: Epoch: [137] [1160/1251] eta: 0:00:46 lr: 0.000567 loss: 3.4310 (3.3599) grad_norm: 1.3118 (1.3584) time: 0.4987 [2021-03-26 04:31:57 swin_small_patch4_window7_224] INFO: Epoch: [137] [1170/1251] eta: 0:00:41 lr: 0.000567 loss: 3.4310 (3.3602) grad_norm: 1.3055 (1.3585) time: 0.5060 [2021-03-26 04:32:03 swin_small_patch4_window7_224] INFO: Epoch: [137] [1180/1251] eta: 0:00:36 lr: 0.000567 loss: 3.3973 (3.3597) grad_norm: 1.3047 (1.3578) time: 0.5102 [2021-03-26 04:32:08 swin_small_patch4_window7_224] INFO: Epoch: [137] [1190/1251] eta: 0:00:31 lr: 0.000567 loss: 3.2499 (3.3579) grad_norm: 1.2593 (1.3574) time: 0.5114 [2021-03-26 04:32:13 swin_small_patch4_window7_224] INFO: Epoch: [137] [1200/1251] eta: 0:00:25 lr: 0.000567 loss: 3.2499 (3.3577) grad_norm: 1.2689 (1.3566) time: 0.5116 [2021-03-26 04:32:18 swin_small_patch4_window7_224] INFO: Epoch: [137] [1210/1251] eta: 0:00:20 lr: 0.000567 loss: 3.3414 (3.3568) grad_norm: 1.2508 (1.3559) time: 0.5026 [2021-03-26 04:32:23 swin_small_patch4_window7_224] INFO: Epoch: [137] [1220/1251] eta: 0:00:15 lr: 0.000567 loss: 3.3414 (3.3565) grad_norm: 1.2338 (1.3553) time: 0.4966 [2021-03-26 04:32:28 swin_small_patch4_window7_224] INFO: Epoch: [137] [1230/1251] eta: 0:00:10 lr: 0.000567 loss: 3.5826 (3.3593) grad_norm: 1.2338 (1.3551) time: 0.4957 [2021-03-26 04:32:33 swin_small_patch4_window7_224] INFO: Epoch: [137] [1240/1251] eta: 0:00:05 lr: 0.000567 loss: 3.5826 (3.3588) grad_norm: 1.3013 (1.3555) time: 0.4974 [2021-03-26 04:32:38 swin_small_patch4_window7_224] INFO: Epoch: [137] [1250/1251] eta: 0:00:00 lr: 0.000567 loss: 3.1831 (3.3576) grad_norm: 1.3755 (1.3558) time: 0.4953 [2021-03-26 04:32:46 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:58 loss: 0.9787 (0.9787) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 04:32:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9787 (0.9412) acc1: 78.1250 (77.9830) acc5: 95.3125 (94.3182) [2021-03-26 04:32:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9828 (0.9479) acc1: 78.1250 (77.9018) acc5: 93.7500 (94.4940) [2021-03-26 04:32:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9562 (0.9408) acc1: 78.1250 (78.1754) acc5: 95.3125 (94.6573) [2021-03-26 04:32:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9446 (0.9328) acc1: 78.1250 (78.4299) acc5: 93.7500 (94.5884) [2021-03-26 04:32:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9562 (0.9526) acc1: 78.1250 (77.5680) acc5: 93.7500 (94.4000) [2021-03-26 04:33:01 swin_small_patch4_window7_224] INFO: * Acc@1 77.750 Acc@5 94.250 loss 0.933 [2021-03-26 04:33:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-26 04:33:01 swin_small_patch4_window7_224] INFO: Max accuracy: 77.76% [2021-03-26 04:33:05 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 0/1251] eta: 1:30:31 lr: 0.000567 loss: 4.1890 (4.1890) grad_norm: 1.3142 (1.3142) time: 4.3420 [2021-03-26 04:33:11 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 10/1251] eta: 0:18:08 lr: 0.000567 loss: 3.2640 (3.2749) grad_norm: 1.3337 (1.3754) time: 0.8768 [2021-03-26 04:33:16 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 20/1251] eta: 0:14:23 lr: 0.000567 loss: 3.2988 (3.3566) grad_norm: 1.3337 (1.3655) time: 0.5192 [2021-03-26 04:33:21 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 30/1251] eta: 0:12:57 lr: 0.000567 loss: 3.4429 (3.2642) grad_norm: 1.3519 (1.3692) time: 0.5048 [2021-03-26 04:33:26 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 40/1251] eta: 0:12:14 lr: 0.000567 loss: 3.2633 (3.2789) grad_norm: 1.3997 (1.3815) time: 0.5079 [2021-03-26 04:33:31 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 50/1251] eta: 0:11:44 lr: 0.000567 loss: 3.4790 (3.2847) grad_norm: 1.3573 (1.3736) time: 0.5085 [2021-03-26 04:33:36 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 60/1251] eta: 0:11:25 lr: 0.000567 loss: 3.3293 (3.3166) grad_norm: 1.3559 (1.3759) time: 0.5100 [2021-03-26 04:33:41 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 70/1251] eta: 0:11:07 lr: 0.000567 loss: 3.5614 (3.3409) grad_norm: 1.3455 (1.3794) time: 0.5096 [2021-03-26 04:33:46 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 80/1251] eta: 0:10:52 lr: 0.000567 loss: 3.4545 (3.3498) grad_norm: 1.3530 (1.3795) time: 0.5027 [2021-03-26 04:33:51 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 90/1251] eta: 0:10:40 lr: 0.000567 loss: 3.3885 (3.3375) grad_norm: 1.3674 (1.3844) time: 0.5060 [2021-03-26 04:33:56 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 100/1251] eta: 0:10:30 lr: 0.000567 loss: 3.4265 (3.3533) grad_norm: 1.3880 (1.3827) time: 0.5076 [2021-03-26 04:34:01 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 110/1251] eta: 0:10:21 lr: 0.000567 loss: 3.5313 (3.3783) grad_norm: 1.3798 (1.3825) time: 0.5112 [2021-03-26 04:34:06 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 120/1251] eta: 0:10:12 lr: 0.000567 loss: 3.4420 (3.3641) grad_norm: 1.3798 (1.3862) time: 0.5101 [2021-03-26 04:34:12 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 130/1251] eta: 0:10:04 lr: 0.000567 loss: 3.3329 (3.3681) grad_norm: 1.3636 (1.3855) time: 0.5120 [2021-03-26 04:34:17 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 140/1251] eta: 0:09:56 lr: 0.000566 loss: 3.6357 (3.3803) grad_norm: 1.3715 (1.3858) time: 0.5119 [2021-03-26 04:34:22 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 150/1251] eta: 0:09:48 lr: 0.000566 loss: 3.6591 (3.3805) grad_norm: 1.3404 (1.3811) time: 0.5036 [2021-03-26 04:34:27 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 160/1251] eta: 0:09:41 lr: 0.000566 loss: 3.6830 (3.4015) grad_norm: 1.3051 (1.3801) time: 0.5027 [2021-03-26 04:34:32 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 170/1251] eta: 0:09:34 lr: 0.000566 loss: 3.6650 (3.3868) grad_norm: 1.2996 (1.3748) time: 0.5067 [2021-03-26 04:34:37 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 180/1251] eta: 0:09:27 lr: 0.000566 loss: 3.3758 (3.3879) grad_norm: 1.3533 (1.3771) time: 0.5090 [2021-03-26 04:34:42 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 190/1251] eta: 0:09:21 lr: 0.000566 loss: 3.3951 (3.3850) grad_norm: 1.3865 (1.3763) time: 0.5085 [2021-03-26 04:34:47 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 200/1251] eta: 0:09:15 lr: 0.000566 loss: 3.4571 (3.3850) grad_norm: 1.2949 (1.3721) time: 0.5167 [2021-03-26 04:34:52 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 210/1251] eta: 0:09:09 lr: 0.000566 loss: 3.5268 (3.3904) grad_norm: 1.2990 (1.3705) time: 0.5132 [2021-03-26 04:34:57 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 220/1251] eta: 0:09:02 lr: 0.000566 loss: 3.5388 (3.3919) grad_norm: 1.3239 (1.3699) time: 0.5024 [2021-03-26 04:35:02 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 230/1251] eta: 0:08:56 lr: 0.000566 loss: 3.5399 (3.3867) grad_norm: 1.3169 (1.3695) time: 0.5040 [2021-03-26 04:35:07 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 240/1251] eta: 0:08:50 lr: 0.000566 loss: 3.2788 (3.3839) grad_norm: 1.3165 (1.3653) time: 0.5019 [2021-03-26 04:35:12 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 250/1251] eta: 0:08:44 lr: 0.000566 loss: 3.0289 (3.3698) grad_norm: 1.3262 (1.3647) time: 0.5007 [2021-03-26 04:35:17 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 260/1251] eta: 0:08:38 lr: 0.000566 loss: 3.4607 (3.3826) grad_norm: 1.3456 (1.3628) time: 0.5069 [2021-03-26 04:35:22 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 270/1251] eta: 0:08:32 lr: 0.000566 loss: 3.6387 (3.3863) grad_norm: 1.3587 (1.3653) time: 0.5036 [2021-03-26 04:35:27 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 280/1251] eta: 0:08:26 lr: 0.000566 loss: 3.5380 (3.3843) grad_norm: 1.3506 (1.3636) time: 0.4999 [2021-03-26 04:35:33 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 290/1251] eta: 0:08:20 lr: 0.000566 loss: 3.3639 (3.3810) grad_norm: 1.3240 (1.3614) time: 0.5072 [2021-03-26 04:35:38 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 300/1251] eta: 0:08:14 lr: 0.000566 loss: 3.3501 (3.3710) grad_norm: 1.3451 (1.3610) time: 0.5075 [2021-03-26 04:35:43 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 310/1251] eta: 0:08:09 lr: 0.000566 loss: 3.2492 (3.3601) grad_norm: 1.3341 (1.3614) time: 0.5044 [2021-03-26 04:35:48 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 320/1251] eta: 0:08:03 lr: 0.000566 loss: 3.2578 (3.3577) grad_norm: 1.3363 (1.3631) time: 0.5040 [2021-03-26 04:35:53 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 330/1251] eta: 0:07:57 lr: 0.000566 loss: 3.0381 (3.3430) grad_norm: 1.3148 (1.3618) time: 0.5016 [2021-03-26 04:35:58 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 340/1251] eta: 0:07:52 lr: 0.000566 loss: 3.0381 (3.3430) grad_norm: 1.3093 (1.3603) time: 0.5020 [2021-03-26 04:36:03 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 350/1251] eta: 0:07:46 lr: 0.000566 loss: 3.4985 (3.3454) grad_norm: 1.3322 (1.3603) time: 0.5025 [2021-03-26 04:36:08 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 360/1251] eta: 0:07:41 lr: 0.000566 loss: 3.4632 (3.3438) grad_norm: 1.3309 (1.3595) time: 0.4996 [2021-03-26 04:36:13 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 370/1251] eta: 0:07:35 lr: 0.000566 loss: 3.2403 (3.3424) grad_norm: 1.3046 (1.3588) time: 0.4956 [2021-03-26 04:36:18 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 380/1251] eta: 0:07:29 lr: 0.000565 loss: 3.1706 (3.3389) grad_norm: 1.3021 (1.3582) time: 0.4978 [2021-03-26 04:36:23 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 390/1251] eta: 0:07:24 lr: 0.000565 loss: 3.1588 (3.3340) grad_norm: 1.4006 (1.3609) time: 0.5066 [2021-03-26 04:36:28 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 400/1251] eta: 0:07:19 lr: 0.000565 loss: 3.1826 (3.3325) grad_norm: 1.4099 (1.3605) time: 0.5100 [2021-03-26 04:36:33 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 410/1251] eta: 0:07:13 lr: 0.000565 loss: 3.1404 (3.3276) grad_norm: 1.3072 (1.3598) time: 0.5071 [2021-03-26 04:36:38 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 420/1251] eta: 0:07:08 lr: 0.000565 loss: 3.4095 (3.3296) grad_norm: 1.3023 (1.3610) time: 0.5058 [2021-03-26 04:36:43 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 430/1251] eta: 0:07:03 lr: 0.000565 loss: 3.4279 (3.3330) grad_norm: 1.3173 (1.3599) time: 0.5058 [2021-03-26 04:36:48 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 440/1251] eta: 0:06:57 lr: 0.000565 loss: 3.3795 (3.3333) grad_norm: 1.3136 (1.3582) time: 0.5051 [2021-03-26 04:36:53 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 450/1251] eta: 0:06:52 lr: 0.000565 loss: 3.3795 (3.3315) grad_norm: 1.2564 (1.3569) time: 0.5094 [2021-03-26 04:36:58 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 460/1251] eta: 0:06:47 lr: 0.000565 loss: 3.3580 (3.3308) grad_norm: 1.2697 (1.3552) time: 0.5129 [2021-03-26 04:37:03 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 470/1251] eta: 0:06:41 lr: 0.000565 loss: 3.4671 (3.3313) grad_norm: 1.3169 (1.3555) time: 0.5058 [2021-03-26 04:37:08 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 480/1251] eta: 0:06:36 lr: 0.000565 loss: 3.4286 (3.3321) grad_norm: 1.3864 (1.3570) time: 0.5039 [2021-03-26 04:37:14 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 490/1251] eta: 0:06:31 lr: 0.000565 loss: 3.3367 (3.3302) grad_norm: 1.3995 (1.3586) time: 0.5059 [2021-03-26 04:37:19 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 500/1251] eta: 0:06:26 lr: 0.000565 loss: 3.2948 (3.3293) grad_norm: 1.4005 (1.3596) time: 0.5059 [2021-03-26 04:37:24 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 510/1251] eta: 0:06:21 lr: 0.000565 loss: 3.6198 (3.3353) grad_norm: 1.3833 (1.3595) time: 0.5110 [2021-03-26 04:37:29 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 520/1251] eta: 0:06:15 lr: 0.000565 loss: 3.6100 (3.3354) grad_norm: 1.3651 (1.3580) time: 0.5074 [2021-03-26 04:37:34 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 530/1251] eta: 0:06:10 lr: 0.000565 loss: 3.5853 (3.3376) grad_norm: 1.2470 (1.3571) time: 0.5029 [2021-03-26 04:37:39 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 540/1251] eta: 0:06:05 lr: 0.000565 loss: 3.5853 (3.3424) grad_norm: 1.3259 (1.3574) time: 0.5071 [2021-03-26 04:37:44 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 550/1251] eta: 0:05:59 lr: 0.000565 loss: 3.3530 (3.3360) grad_norm: 1.3885 (1.3583) time: 0.5042 [2021-03-26 04:37:49 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 560/1251] eta: 0:05:54 lr: 0.000565 loss: 2.7610 (3.3296) grad_norm: 1.3422 (1.3580) time: 0.5059 [2021-03-26 04:37:54 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 570/1251] eta: 0:05:49 lr: 0.000565 loss: 3.1128 (3.3284) grad_norm: 1.3011 (1.3578) time: 0.5030 [2021-03-26 04:37:59 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 580/1251] eta: 0:05:44 lr: 0.000565 loss: 3.3059 (3.3244) grad_norm: 1.2921 (1.3571) time: 0.5012 [2021-03-26 04:38:04 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 590/1251] eta: 0:05:39 lr: 0.000565 loss: 2.6829 (3.3170) grad_norm: 1.3095 (1.3577) time: 0.5118 [2021-03-26 04:38:09 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 600/1251] eta: 0:05:33 lr: 0.000565 loss: 3.1566 (3.3185) grad_norm: 1.3314 (1.3570) time: 0.5055 [2021-03-26 04:38:14 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 610/1251] eta: 0:05:28 lr: 0.000565 loss: 3.4906 (3.3193) grad_norm: 1.3008 (1.3559) time: 0.5039 [2021-03-26 04:38:19 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 620/1251] eta: 0:05:23 lr: 0.000564 loss: 3.6075 (3.3235) grad_norm: 1.3058 (1.3559) time: 0.5111 [2021-03-26 04:38:24 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 630/1251] eta: 0:05:18 lr: 0.000564 loss: 3.3861 (3.3170) grad_norm: 1.3336 (1.3554) time: 0.5087 [2021-03-26 04:38:29 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 640/1251] eta: 0:05:13 lr: 0.000564 loss: 3.5337 (3.3228) grad_norm: 1.3286 (1.3555) time: 0.5048 [2021-03-26 04:38:35 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 650/1251] eta: 0:05:07 lr: 0.000564 loss: 3.6107 (3.3189) grad_norm: 1.3286 (1.3546) time: 0.5051 [2021-03-26 04:38:40 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 660/1251] eta: 0:05:02 lr: 0.000564 loss: 3.2690 (3.3208) grad_norm: 1.3140 (1.3551) time: 0.5018 [2021-03-26 04:38:45 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 670/1251] eta: 0:04:57 lr: 0.000564 loss: 3.4985 (3.3211) grad_norm: 1.4094 (1.3570) time: 0.5030 [2021-03-26 04:38:50 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 680/1251] eta: 0:04:52 lr: 0.000564 loss: 3.3313 (3.3203) grad_norm: 1.3659 (1.3573) time: 0.5064 [2021-03-26 04:38:55 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 690/1251] eta: 0:04:47 lr: 0.000564 loss: 3.5371 (3.3234) grad_norm: 1.3334 (1.3572) time: 0.5014 [2021-03-26 04:39:00 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 700/1251] eta: 0:04:41 lr: 0.000564 loss: 3.5019 (3.3246) grad_norm: 1.2628 (1.3559) time: 0.5034 [2021-03-26 04:39:05 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 710/1251] eta: 0:04:36 lr: 0.000564 loss: 3.4445 (3.3242) grad_norm: 1.2628 (1.3555) time: 0.5052 [2021-03-26 04:39:10 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 720/1251] eta: 0:04:31 lr: 0.000564 loss: 3.2454 (3.3215) grad_norm: 1.3527 (1.3560) time: 0.5024 [2021-03-26 04:39:15 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 730/1251] eta: 0:04:26 lr: 0.000564 loss: 3.2798 (3.3221) grad_norm: 1.3220 (1.3551) time: 0.5121 [2021-03-26 04:39:20 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 740/1251] eta: 0:04:21 lr: 0.000564 loss: 3.3588 (3.3205) grad_norm: 1.2947 (1.3548) time: 0.5113 [2021-03-26 04:39:25 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 750/1251] eta: 0:04:16 lr: 0.000564 loss: 3.2936 (3.3214) grad_norm: 1.2458 (1.3533) time: 0.5117 [2021-03-26 04:39:30 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 760/1251] eta: 0:04:11 lr: 0.000564 loss: 3.4039 (3.3219) grad_norm: 1.2608 (1.3524) time: 0.5075 [2021-03-26 04:39:35 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 770/1251] eta: 0:04:05 lr: 0.000564 loss: 3.4039 (3.3217) grad_norm: 1.2796 (1.3522) time: 0.4942 [2021-03-26 04:39:40 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 780/1251] eta: 0:04:00 lr: 0.000564 loss: 3.4521 (3.3250) grad_norm: 1.3243 (1.3525) time: 0.4964 [2021-03-26 04:39:45 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 790/1251] eta: 0:03:55 lr: 0.000564 loss: 3.4697 (3.3255) grad_norm: 1.3118 (1.3518) time: 0.5016 [2021-03-26 04:39:50 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 800/1251] eta: 0:03:50 lr: 0.000564 loss: 3.3914 (3.3255) grad_norm: 1.2971 (1.3513) time: 0.5071 [2021-03-26 04:39:55 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 810/1251] eta: 0:03:45 lr: 0.000564 loss: 3.4461 (3.3266) grad_norm: 1.2639 (1.3507) time: 0.5093 [2021-03-26 04:40:00 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 820/1251] eta: 0:03:40 lr: 0.000564 loss: 3.4951 (3.3283) grad_norm: 1.3224 (1.3510) time: 0.5047 [2021-03-26 04:40:05 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 830/1251] eta: 0:03:35 lr: 0.000564 loss: 3.4703 (3.3297) grad_norm: 1.3530 (1.3509) time: 0.5060 [2021-03-26 04:40:11 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 840/1251] eta: 0:03:29 lr: 0.000564 loss: 3.4703 (3.3313) grad_norm: 1.3389 (1.3512) time: 0.5101 [2021-03-26 04:40:16 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 850/1251] eta: 0:03:24 lr: 0.000564 loss: 3.6169 (3.3337) grad_norm: 1.3312 (1.3512) time: 0.5019 [2021-03-26 04:40:21 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 860/1251] eta: 0:03:19 lr: 0.000564 loss: 3.5385 (3.3337) grad_norm: 1.2852 (1.3507) time: 0.4990 [2021-03-26 04:40:26 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 870/1251] eta: 0:03:14 lr: 0.000563 loss: 3.3265 (3.3319) grad_norm: 1.2752 (1.3506) time: 0.5054 [2021-03-26 04:40:31 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 880/1251] eta: 0:03:09 lr: 0.000563 loss: 3.4671 (3.3364) grad_norm: 1.2831 (1.3504) time: 0.5101 [2021-03-26 04:40:36 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 890/1251] eta: 0:03:04 lr: 0.000563 loss: 3.7268 (3.3409) grad_norm: 1.3072 (1.3503) time: 0.5066 [2021-03-26 04:40:41 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 900/1251] eta: 0:02:59 lr: 0.000563 loss: 3.7030 (3.3383) grad_norm: 1.3466 (1.3508) time: 0.5048 [2021-03-26 04:40:46 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 910/1251] eta: 0:02:53 lr: 0.000563 loss: 3.0170 (3.3374) grad_norm: 1.3574 (1.3512) time: 0.5028 [2021-03-26 04:40:51 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 920/1251] eta: 0:02:48 lr: 0.000563 loss: 3.4965 (3.3405) grad_norm: 1.3392 (1.3511) time: 0.5002 [2021-03-26 04:40:56 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 930/1251] eta: 0:02:43 lr: 0.000563 loss: 3.4965 (3.3407) grad_norm: 1.3103 (1.3503) time: 0.5072 [2021-03-26 04:41:01 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 940/1251] eta: 0:02:38 lr: 0.000563 loss: 3.4607 (3.3415) grad_norm: 1.2581 (1.3500) time: 0.5154 [2021-03-26 04:41:06 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 950/1251] eta: 0:02:33 lr: 0.000563 loss: 3.6504 (3.3440) grad_norm: 1.2706 (1.3501) time: 0.5108 [2021-03-26 04:41:11 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 960/1251] eta: 0:02:28 lr: 0.000563 loss: 3.5022 (3.3429) grad_norm: 1.2965 (1.3501) time: 0.5049 [2021-03-26 04:41:16 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 970/1251] eta: 0:02:23 lr: 0.000563 loss: 3.2762 (3.3423) grad_norm: 1.3643 (1.3505) time: 0.5018 [2021-03-26 04:41:21 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 980/1251] eta: 0:02:18 lr: 0.000563 loss: 3.3483 (3.3428) grad_norm: 1.3608 (1.3503) time: 0.4996 [2021-03-26 04:41:26 swin_small_patch4_window7_224] INFO: Epoch: [138] [ 990/1251] eta: 0:02:13 lr: 0.000563 loss: 3.5069 (3.3435) grad_norm: 1.3047 (1.3500) time: 0.4997 [2021-03-26 04:41:31 swin_small_patch4_window7_224] INFO: Epoch: [138] [1000/1251] eta: 0:02:07 lr: 0.000563 loss: 3.5980 (3.3459) grad_norm: 1.3052 (1.3501) time: 0.5022 [2021-03-26 04:41:36 swin_small_patch4_window7_224] INFO: Epoch: [138] [1010/1251] eta: 0:02:02 lr: 0.000563 loss: 3.5980 (3.3478) grad_norm: 1.3238 (1.3503) time: 0.5070 [2021-03-26 04:41:41 swin_small_patch4_window7_224] INFO: Epoch: [138] [1020/1251] eta: 0:01:57 lr: 0.000563 loss: 3.5630 (3.3495) grad_norm: 1.3220 (1.3498) time: 0.5072 [2021-03-26 04:41:46 swin_small_patch4_window7_224] INFO: Epoch: [138] [1030/1251] eta: 0:01:52 lr: 0.000563 loss: 3.3989 (3.3493) grad_norm: 1.3183 (1.3495) time: 0.5007 [2021-03-26 04:41:51 swin_small_patch4_window7_224] INFO: Epoch: [138] [1040/1251] eta: 0:01:47 lr: 0.000563 loss: 3.3379 (3.3487) grad_norm: 1.2883 (1.3491) time: 0.5031 [2021-03-26 04:41:56 swin_small_patch4_window7_224] INFO: Epoch: [138] [1050/1251] eta: 0:01:42 lr: 0.000563 loss: 3.3147 (3.3462) grad_norm: 1.3274 (1.3495) time: 0.5044 [2021-03-26 04:42:01 swin_small_patch4_window7_224] INFO: Epoch: [138] [1060/1251] eta: 0:01:37 lr: 0.000563 loss: 3.2134 (3.3453) grad_norm: 1.3321 (1.3499) time: 0.4960 [2021-03-26 04:42:06 swin_small_patch4_window7_224] INFO: Epoch: [138] [1070/1251] eta: 0:01:32 lr: 0.000563 loss: 3.3401 (3.3462) grad_norm: 1.3219 (1.3495) time: 0.4978 [2021-03-26 04:42:12 swin_small_patch4_window7_224] INFO: Epoch: [138] [1080/1251] eta: 0:01:27 lr: 0.000563 loss: 3.3930 (3.3469) grad_norm: 1.3634 (1.3507) time: 0.5051 [2021-03-26 04:42:17 swin_small_patch4_window7_224] INFO: Epoch: [138] [1090/1251] eta: 0:01:21 lr: 0.000563 loss: 3.3607 (3.3467) grad_norm: 1.2935 (1.3500) time: 0.5086 [2021-03-26 04:42:22 swin_small_patch4_window7_224] INFO: Epoch: [138] [1100/1251] eta: 0:01:16 lr: 0.000563 loss: 3.4753 (3.3472) grad_norm: 1.3092 (1.3504) time: 0.5007 [2021-03-26 04:42:27 swin_small_patch4_window7_224] INFO: Epoch: [138] [1110/1251] eta: 0:01:11 lr: 0.000562 loss: 3.5228 (3.3490) grad_norm: 1.3734 (1.3508) time: 0.4958 [2021-03-26 04:42:32 swin_small_patch4_window7_224] INFO: Epoch: [138] [1120/1251] eta: 0:01:06 lr: 0.000562 loss: 3.5799 (3.3506) grad_norm: 1.3317 (1.3508) time: 0.5003 [2021-03-26 04:42:37 swin_small_patch4_window7_224] INFO: Epoch: [138] [1130/1251] eta: 0:01:01 lr: 0.000562 loss: 3.4234 (3.3502) grad_norm: 1.3144 (1.3507) time: 0.5050 [2021-03-26 04:42:42 swin_small_patch4_window7_224] INFO: Epoch: [138] [1140/1251] eta: 0:00:56 lr: 0.000562 loss: 3.3769 (3.3492) grad_norm: 1.2983 (1.3508) time: 0.5059 [2021-03-26 04:42:47 swin_small_patch4_window7_224] INFO: Epoch: [138] [1150/1251] eta: 0:00:51 lr: 0.000562 loss: 3.4867 (3.3507) grad_norm: 1.3219 (1.3505) time: 0.5014 [2021-03-26 04:42:52 swin_small_patch4_window7_224] INFO: Epoch: [138] [1160/1251] eta: 0:00:46 lr: 0.000562 loss: 3.1927 (3.3474) grad_norm: 1.3694 (1.3510) time: 0.4999 [2021-03-26 04:42:57 swin_small_patch4_window7_224] INFO: Epoch: [138] [1170/1251] eta: 0:00:41 lr: 0.000562 loss: 3.2786 (3.3481) grad_norm: 1.3944 (1.3516) time: 0.5016 [2021-03-26 04:43:02 swin_small_patch4_window7_224] INFO: Epoch: [138] [1180/1251] eta: 0:00:36 lr: 0.000562 loss: 3.4290 (3.3484) grad_norm: 1.3691 (1.3518) time: 0.5067 [2021-03-26 04:43:07 swin_small_patch4_window7_224] INFO: Epoch: [138] [1190/1251] eta: 0:00:31 lr: 0.000562 loss: 3.4290 (3.3473) grad_norm: 1.3782 (1.3523) time: 0.5047 [2021-03-26 04:43:12 swin_small_patch4_window7_224] INFO: Epoch: [138] [1200/1251] eta: 0:00:25 lr: 0.000562 loss: 3.2994 (3.3469) grad_norm: 1.3679 (1.3517) time: 0.5016 [2021-03-26 04:43:17 swin_small_patch4_window7_224] INFO: Epoch: [138] [1210/1251] eta: 0:00:20 lr: 0.000562 loss: 3.2930 (3.3486) grad_norm: 1.3679 (1.3524) time: 0.5052 [2021-03-26 04:43:22 swin_small_patch4_window7_224] INFO: Epoch: [138] [1220/1251] eta: 0:00:15 lr: 0.000562 loss: 3.6354 (3.3496) grad_norm: 1.4303 (1.3532) time: 0.5063 [2021-03-26 04:43:27 swin_small_patch4_window7_224] INFO: Epoch: [138] [1230/1251] eta: 0:00:10 lr: 0.000562 loss: 3.3966 (3.3502) grad_norm: 1.3871 (1.3529) time: 0.5051 [2021-03-26 04:43:32 swin_small_patch4_window7_224] INFO: Epoch: [138] [1240/1251] eta: 0:00:05 lr: 0.000562 loss: 3.3856 (3.3497) grad_norm: 1.2991 (1.3527) time: 0.5063 [2021-03-26 04:43:37 swin_small_patch4_window7_224] INFO: Epoch: [138] [1250/1251] eta: 0:00:00 lr: 0.000562 loss: 3.5117 (3.3516) grad_norm: 1.3948 (1.3534) time: 0.4989 [2021-03-26 04:43:43 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:53 loss: 1.1169 (1.1169) acc1: 75.0000 (75.0000) acc5: 90.6250 (90.6250) [2021-03-26 04:43:45 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 1.0770 (1.0422) acc1: 75.0000 (74.8580) acc5: 92.1875 (92.8977) [2021-03-26 04:43:47 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 1.0146 (1.0129) acc1: 75.0000 (75.3720) acc5: 93.7500 (93.3780) [2021-03-26 04:43:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9511 (0.9810) acc1: 76.5625 (76.2601) acc5: 93.7500 (93.8508) [2021-03-26 04:43:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9261 (0.9743) acc1: 78.1250 (76.5244) acc5: 95.3125 (94.2073) [2021-03-26 04:43:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9344 (0.9661) acc1: 78.1250 (76.8000) acc5: 95.3125 (94.4640) [2021-03-26 04:43:58 swin_small_patch4_window7_224] INFO: * Acc@1 77.770 Acc@5 94.274 loss 0.937 [2021-03-26 04:43:58 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.8% [2021-03-26 04:43:58 swin_small_patch4_window7_224] INFO: Max accuracy: 77.77% [2021-03-26 04:44:02 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 0/1251] eta: 1:26:57 lr: 0.000562 loss: 2.5301 (2.5301) grad_norm: 1.3123 (1.3123) time: 4.1708 [2021-03-26 04:44:08 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 10/1251] eta: 0:17:47 lr: 0.000562 loss: 3.1017 (3.0880) grad_norm: 1.3552 (1.3684) time: 0.8603 [2021-03-26 04:44:13 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 20/1251] eta: 0:14:03 lr: 0.000562 loss: 3.4823 (3.3394) grad_norm: 1.3627 (1.3886) time: 0.5108 [2021-03-26 04:44:18 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 30/1251] eta: 0:12:45 lr: 0.000562 loss: 3.5404 (3.3228) grad_norm: 1.3790 (1.3856) time: 0.4990 [2021-03-26 04:44:23 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 40/1251] eta: 0:12:09 lr: 0.000562 loss: 3.4009 (3.3509) grad_norm: 1.3124 (1.3705) time: 0.5163 [2021-03-26 04:44:28 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 50/1251] eta: 0:11:43 lr: 0.000562 loss: 3.1992 (3.2777) grad_norm: 1.3238 (1.3685) time: 0.5223 [2021-03-26 04:44:33 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 60/1251] eta: 0:11:23 lr: 0.000562 loss: 3.2957 (3.3154) grad_norm: 1.3518 (1.3670) time: 0.5136 [2021-03-26 04:44:38 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 70/1251] eta: 0:11:05 lr: 0.000562 loss: 3.4660 (3.2802) grad_norm: 1.3518 (1.3762) time: 0.5059 [2021-03-26 04:44:43 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 80/1251] eta: 0:10:51 lr: 0.000562 loss: 3.2916 (3.3160) grad_norm: 1.3341 (1.3709) time: 0.5035 [2021-03-26 04:44:48 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 90/1251] eta: 0:10:38 lr: 0.000562 loss: 3.2916 (3.2939) grad_norm: 1.3152 (1.3648) time: 0.5008 [2021-03-26 04:44:53 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 100/1251] eta: 0:10:26 lr: 0.000561 loss: 3.1980 (3.3080) grad_norm: 1.2851 (1.3590) time: 0.4977 [2021-03-26 04:44:58 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 110/1251] eta: 0:10:18 lr: 0.000561 loss: 3.5231 (3.3148) grad_norm: 1.2776 (1.3573) time: 0.5066 [2021-03-26 04:45:04 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 120/1251] eta: 0:10:09 lr: 0.000561 loss: 3.5439 (3.3351) grad_norm: 1.3217 (1.3552) time: 0.5112 [2021-03-26 04:45:09 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 130/1251] eta: 0:10:02 lr: 0.000561 loss: 3.4702 (3.3497) grad_norm: 1.3217 (1.3556) time: 0.5146 [2021-03-26 04:45:14 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 140/1251] eta: 0:09:54 lr: 0.000561 loss: 3.3159 (3.3458) grad_norm: 1.3131 (1.3608) time: 0.5104 [2021-03-26 04:45:19 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 150/1251] eta: 0:09:47 lr: 0.000561 loss: 3.4931 (3.3592) grad_norm: 1.3237 (1.3636) time: 0.5034 [2021-03-26 04:45:24 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 160/1251] eta: 0:09:39 lr: 0.000561 loss: 3.7096 (3.3599) grad_norm: 1.3237 (1.3598) time: 0.5063 [2021-03-26 04:45:29 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 170/1251] eta: 0:09:33 lr: 0.000561 loss: 3.4177 (3.3595) grad_norm: 1.3357 (1.3578) time: 0.5070 [2021-03-26 04:45:34 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 180/1251] eta: 0:09:26 lr: 0.000561 loss: 3.2820 (3.3504) grad_norm: 1.3382 (1.3570) time: 0.5119 [2021-03-26 04:45:39 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 190/1251] eta: 0:09:19 lr: 0.000561 loss: 3.2070 (3.3481) grad_norm: 1.3208 (1.3549) time: 0.5077 [2021-03-26 04:45:44 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 200/1251] eta: 0:09:13 lr: 0.000561 loss: 3.2208 (3.3470) grad_norm: 1.2970 (1.3573) time: 0.5065 [2021-03-26 04:45:49 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 210/1251] eta: 0:09:07 lr: 0.000561 loss: 3.4648 (3.3550) grad_norm: 1.3323 (1.3567) time: 0.5101 [2021-03-26 04:45:54 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 220/1251] eta: 0:09:01 lr: 0.000561 loss: 3.5058 (3.3492) grad_norm: 1.3323 (1.3575) time: 0.5076 [2021-03-26 04:45:59 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 230/1251] eta: 0:08:55 lr: 0.000561 loss: 3.5058 (3.3513) grad_norm: 1.2878 (1.3518) time: 0.5053 [2021-03-26 04:46:05 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 240/1251] eta: 0:08:49 lr: 0.000561 loss: 3.3927 (3.3489) grad_norm: 1.2503 (1.3522) time: 0.5041 [2021-03-26 04:46:10 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 250/1251] eta: 0:08:43 lr: 0.000561 loss: 3.3223 (3.3517) grad_norm: 1.2633 (1.3505) time: 0.5082 [2021-03-26 04:46:15 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 260/1251] eta: 0:08:37 lr: 0.000561 loss: 3.3126 (3.3478) grad_norm: 1.2688 (1.3496) time: 0.5091 [2021-03-26 04:46:20 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 270/1251] eta: 0:08:31 lr: 0.000561 loss: 3.4082 (3.3494) grad_norm: 1.3222 (1.3491) time: 0.5030 [2021-03-26 04:46:25 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 280/1251] eta: 0:08:25 lr: 0.000561 loss: 3.4382 (3.3434) grad_norm: 1.2933 (1.3484) time: 0.4990 [2021-03-26 04:46:30 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 290/1251] eta: 0:08:19 lr: 0.000561 loss: 3.2098 (3.3383) grad_norm: 1.3376 (1.3528) time: 0.5019 [2021-03-26 04:46:35 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 300/1251] eta: 0:08:14 lr: 0.000561 loss: 3.3903 (3.3423) grad_norm: 1.4152 (1.3540) time: 0.5027 [2021-03-26 04:46:40 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 310/1251] eta: 0:08:08 lr: 0.000561 loss: 3.4868 (3.3448) grad_norm: 1.3617 (1.3545) time: 0.5052 [2021-03-26 04:46:45 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 320/1251] eta: 0:08:03 lr: 0.000561 loss: 3.4963 (3.3516) grad_norm: 1.2926 (nan) time: 0.5097 [2021-03-26 04:46:50 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 330/1251] eta: 0:07:57 lr: 0.000561 loss: 3.4850 (3.3476) grad_norm: 1.2890 (nan) time: 0.5045 [2021-03-26 04:46:55 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 340/1251] eta: 0:07:51 lr: 0.000560 loss: 3.3222 (3.3437) grad_norm: 1.3007 (nan) time: 0.5014 [2021-03-26 04:47:00 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 350/1251] eta: 0:07:46 lr: 0.000560 loss: 3.2443 (3.3359) grad_norm: 1.3440 (nan) time: 0.4989 [2021-03-26 04:47:05 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 360/1251] eta: 0:07:40 lr: 0.000560 loss: 3.1251 (3.3373) grad_norm: 1.3351 (nan) time: 0.5030 [2021-03-26 04:47:10 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 370/1251] eta: 0:07:35 lr: 0.000560 loss: 3.5575 (3.3434) grad_norm: 1.3216 (nan) time: 0.5089 [2021-03-26 04:47:15 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 380/1251] eta: 0:07:29 lr: 0.000560 loss: 3.5575 (3.3494) grad_norm: 1.2389 (nan) time: 0.5047 [2021-03-26 04:47:20 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 390/1251] eta: 0:07:24 lr: 0.000560 loss: 3.4780 (3.3453) grad_norm: 1.3005 (nan) time: 0.5085 [2021-03-26 04:47:25 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 400/1251] eta: 0:07:19 lr: 0.000560 loss: 3.3861 (3.3490) grad_norm: 1.3386 (nan) time: 0.5130 [2021-03-26 04:47:30 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 410/1251] eta: 0:07:13 lr: 0.000560 loss: 3.4733 (3.3499) grad_norm: 1.2579 (nan) time: 0.5063 [2021-03-26 04:47:36 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 420/1251] eta: 0:07:08 lr: 0.000560 loss: 3.2491 (3.3480) grad_norm: 1.3012 (nan) time: 0.5053 [2021-03-26 04:47:41 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 430/1251] eta: 0:07:03 lr: 0.000560 loss: 3.5382 (3.3531) grad_norm: 1.3552 (nan) time: 0.5063 [2021-03-26 04:47:46 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 440/1251] eta: 0:06:57 lr: 0.000560 loss: 3.6475 (3.3552) grad_norm: 1.3552 (nan) time: 0.5020 [2021-03-26 04:47:51 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 450/1251] eta: 0:06:52 lr: 0.000560 loss: 3.4998 (3.3526) grad_norm: 1.3404 (nan) time: 0.5015 [2021-03-26 04:47:56 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 460/1251] eta: 0:06:47 lr: 0.000560 loss: 3.0124 (3.3507) grad_norm: 1.3262 (nan) time: 0.5038 [2021-03-26 04:48:01 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 470/1251] eta: 0:06:41 lr: 0.000560 loss: 3.1169 (3.3473) grad_norm: 1.3246 (nan) time: 0.5061 [2021-03-26 04:48:06 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 480/1251] eta: 0:06:36 lr: 0.000560 loss: 3.3577 (3.3479) grad_norm: 1.3031 (nan) time: 0.5014 [2021-03-26 04:48:11 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 490/1251] eta: 0:06:30 lr: 0.000560 loss: 3.3528 (3.3454) grad_norm: 1.3454 (nan) time: 0.4951 [2021-03-26 04:48:16 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 500/1251] eta: 0:06:25 lr: 0.000560 loss: 3.3074 (3.3475) grad_norm: 1.3687 (nan) time: 0.4943 [2021-03-26 04:48:21 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 510/1251] eta: 0:06:20 lr: 0.000560 loss: 3.1429 (3.3427) grad_norm: 1.3841 (nan) time: 0.5016 [2021-03-26 04:48:26 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 520/1251] eta: 0:06:14 lr: 0.000560 loss: 3.1429 (3.3453) grad_norm: 1.3954 (nan) time: 0.5032 [2021-03-26 04:48:31 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 530/1251] eta: 0:06:09 lr: 0.000560 loss: 3.4963 (3.3449) grad_norm: 1.3702 (nan) time: 0.4989 [2021-03-26 04:48:36 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 540/1251] eta: 0:06:04 lr: 0.000560 loss: 3.4597 (3.3472) grad_norm: 1.3013 (nan) time: 0.5020 [2021-03-26 04:48:41 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 550/1251] eta: 0:05:59 lr: 0.000560 loss: 3.4606 (3.3467) grad_norm: 1.2688 (nan) time: 0.5081 [2021-03-26 04:48:46 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 560/1251] eta: 0:05:53 lr: 0.000560 loss: 3.4606 (3.3490) grad_norm: 1.2639 (nan) time: 0.5025 [2021-03-26 04:48:51 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 570/1251] eta: 0:05:48 lr: 0.000560 loss: 3.3243 (3.3451) grad_norm: 1.3131 (nan) time: 0.4996 [2021-03-26 04:48:56 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 580/1251] eta: 0:05:43 lr: 0.000560 loss: 3.3243 (3.3470) grad_norm: 1.3406 (nan) time: 0.5010 [2021-03-26 04:49:01 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 590/1251] eta: 0:05:38 lr: 0.000559 loss: 3.4673 (3.3450) grad_norm: 1.3599 (nan) time: 0.5061 [2021-03-26 04:49:06 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 600/1251] eta: 0:05:33 lr: 0.000559 loss: 3.4673 (3.3476) grad_norm: 1.3193 (nan) time: 0.5086 [2021-03-26 04:49:11 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 610/1251] eta: 0:05:27 lr: 0.000559 loss: 3.4547 (3.3479) grad_norm: 1.3152 (nan) time: 0.5033 [2021-03-26 04:49:16 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 620/1251] eta: 0:05:22 lr: 0.000559 loss: 3.4455 (3.3489) grad_norm: 1.3152 (nan) time: 0.5074 [2021-03-26 04:49:21 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 630/1251] eta: 0:05:17 lr: 0.000559 loss: 3.3635 (3.3452) grad_norm: 1.3127 (nan) time: 0.5059 [2021-03-26 04:49:26 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 640/1251] eta: 0:05:12 lr: 0.000559 loss: 3.4838 (3.3472) grad_norm: 1.2865 (nan) time: 0.5042 [2021-03-26 04:49:31 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 650/1251] eta: 0:05:07 lr: 0.000559 loss: 3.4838 (3.3477) grad_norm: 1.2761 (nan) time: 0.5068 [2021-03-26 04:49:36 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 660/1251] eta: 0:05:02 lr: 0.000559 loss: 3.5311 (3.3492) grad_norm: 1.2816 (nan) time: 0.5067 [2021-03-26 04:49:41 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 670/1251] eta: 0:04:56 lr: 0.000559 loss: 3.4333 (3.3494) grad_norm: 1.3050 (nan) time: 0.5091 [2021-03-26 04:49:46 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 680/1251] eta: 0:04:51 lr: 0.000559 loss: 3.2212 (3.3500) grad_norm: 1.3050 (nan) time: 0.5039 [2021-03-26 04:49:52 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 690/1251] eta: 0:04:46 lr: 0.000559 loss: 3.4798 (3.3500) grad_norm: 1.3292 (nan) time: 0.5055 [2021-03-26 04:49:57 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 700/1251] eta: 0:04:41 lr: 0.000559 loss: 3.4856 (3.3515) grad_norm: 1.3315 (nan) time: 0.5091 [2021-03-26 04:50:02 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 710/1251] eta: 0:04:36 lr: 0.000559 loss: 3.4372 (3.3505) grad_norm: 1.3315 (nan) time: 0.5038 [2021-03-26 04:50:07 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 720/1251] eta: 0:04:31 lr: 0.000559 loss: 3.3129 (3.3476) grad_norm: 1.3422 (nan) time: 0.5020 [2021-03-26 04:50:12 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 730/1251] eta: 0:04:26 lr: 0.000559 loss: 3.4047 (3.3495) grad_norm: 1.3490 (nan) time: 0.5037 [2021-03-26 04:50:17 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 740/1251] eta: 0:04:21 lr: 0.000559 loss: 3.4689 (3.3478) grad_norm: 1.3490 (nan) time: 0.5155 [2021-03-26 04:50:22 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 750/1251] eta: 0:04:15 lr: 0.000559 loss: 3.4236 (3.3487) grad_norm: 1.4149 (nan) time: 0.5166 [2021-03-26 04:50:27 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 760/1251] eta: 0:04:10 lr: 0.000559 loss: 3.4723 (3.3466) grad_norm: 1.3701 (nan) time: 0.5131 [2021-03-26 04:50:32 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 770/1251] eta: 0:04:05 lr: 0.000559 loss: 3.3257 (3.3480) grad_norm: 1.3301 (nan) time: 0.5158 [2021-03-26 04:50:37 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 780/1251] eta: 0:04:00 lr: 0.000559 loss: 3.6236 (3.3494) grad_norm: 1.2711 (nan) time: 0.5103 [2021-03-26 04:50:43 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 790/1251] eta: 0:03:55 lr: 0.000559 loss: 3.3897 (3.3433) grad_norm: 1.2711 (nan) time: 0.5142 [2021-03-26 04:50:48 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 800/1251] eta: 0:03:50 lr: 0.000559 loss: 3.3879 (3.3441) grad_norm: 1.3491 (nan) time: 0.5169 [2021-03-26 04:50:53 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 810/1251] eta: 0:03:45 lr: 0.000559 loss: 3.4958 (3.3472) grad_norm: 1.3125 (nan) time: 0.5101 [2021-03-26 04:50:58 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 820/1251] eta: 0:03:40 lr: 0.000559 loss: 3.3906 (3.3451) grad_norm: 1.3062 (nan) time: 0.5095 [2021-03-26 04:51:03 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 830/1251] eta: 0:03:35 lr: 0.000558 loss: 3.2988 (3.3425) grad_norm: 1.4481 (nan) time: 0.5054 [2021-03-26 04:51:08 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 840/1251] eta: 0:03:29 lr: 0.000558 loss: 3.1963 (3.3399) grad_norm: 1.3857 (nan) time: 0.5033 [2021-03-26 04:51:13 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 850/1251] eta: 0:03:24 lr: 0.000558 loss: 3.1903 (3.3386) grad_norm: 1.3284 (nan) time: 0.5050 [2021-03-26 04:51:18 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 860/1251] eta: 0:03:19 lr: 0.000558 loss: 3.1536 (3.3370) grad_norm: 1.3035 (nan) time: 0.5023 [2021-03-26 04:51:23 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 870/1251] eta: 0:03:14 lr: 0.000558 loss: 3.4668 (3.3388) grad_norm: 1.2972 (nan) time: 0.5042 [2021-03-26 04:51:28 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 880/1251] eta: 0:03:09 lr: 0.000558 loss: 3.5613 (3.3396) grad_norm: 1.3377 (nan) time: 0.5073 [2021-03-26 04:51:33 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 890/1251] eta: 0:03:04 lr: 0.000558 loss: 3.5623 (3.3400) grad_norm: 1.3535 (nan) time: 0.5010 [2021-03-26 04:51:38 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 900/1251] eta: 0:02:59 lr: 0.000558 loss: 3.5183 (3.3416) grad_norm: 1.3120 (nan) time: 0.5058 [2021-03-26 04:51:43 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 910/1251] eta: 0:02:54 lr: 0.000558 loss: 3.5183 (3.3438) grad_norm: 1.2737 (nan) time: 0.5078 [2021-03-26 04:51:48 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 920/1251] eta: 0:02:48 lr: 0.000558 loss: 3.3550 (3.3432) grad_norm: 1.3199 (nan) time: 0.5061 [2021-03-26 04:51:53 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 930/1251] eta: 0:02:43 lr: 0.000558 loss: 3.1975 (3.3414) grad_norm: 1.3921 (nan) time: 0.5063 [2021-03-26 04:51:58 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 940/1251] eta: 0:02:38 lr: 0.000558 loss: 3.1627 (3.3389) grad_norm: 1.3447 (nan) time: 0.5019 [2021-03-26 04:52:04 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 950/1251] eta: 0:02:33 lr: 0.000558 loss: 3.4925 (3.3407) grad_norm: 1.3022 (nan) time: 0.5104 [2021-03-26 04:52:09 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 960/1251] eta: 0:02:28 lr: 0.000558 loss: 3.5141 (3.3413) grad_norm: 1.3395 (nan) time: 0.5100 [2021-03-26 04:52:14 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 970/1251] eta: 0:02:23 lr: 0.000558 loss: 3.1110 (3.3380) grad_norm: 1.3426 (nan) time: 0.5052 [2021-03-26 04:52:19 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 980/1251] eta: 0:02:18 lr: 0.000558 loss: 3.2036 (3.3395) grad_norm: 1.3097 (nan) time: 0.5067 [2021-03-26 04:52:24 swin_small_patch4_window7_224] INFO: Epoch: [139] [ 990/1251] eta: 0:02:13 lr: 0.000558 loss: 3.4387 (3.3364) grad_norm: 1.3713 (nan) time: 0.5082 [2021-03-26 04:52:29 swin_small_patch4_window7_224] INFO: Epoch: [139] [1000/1251] eta: 0:02:08 lr: 0.000558 loss: 3.4187 (3.3375) grad_norm: 1.3713 (nan) time: 0.5084 [2021-03-26 04:52:34 swin_small_patch4_window7_224] INFO: Epoch: [139] [1010/1251] eta: 0:02:02 lr: 0.000558 loss: 3.2504 (3.3357) grad_norm: 1.3568 (nan) time: 0.5045 [2021-03-26 04:52:39 swin_small_patch4_window7_224] INFO: Epoch: [139] [1020/1251] eta: 0:01:57 lr: 0.000558 loss: 3.2140 (3.3350) grad_norm: 1.3493 (nan) time: 0.5049 [2021-03-26 04:52:44 swin_small_patch4_window7_224] INFO: Epoch: [139] [1030/1251] eta: 0:01:52 lr: 0.000558 loss: 3.4696 (3.3368) grad_norm: 1.4077 (nan) time: 0.5061 [2021-03-26 04:52:49 swin_small_patch4_window7_224] INFO: Epoch: [139] [1040/1251] eta: 0:01:47 lr: 0.000558 loss: 3.4927 (3.3375) grad_norm: 1.4077 (nan) time: 0.5061 [2021-03-26 04:52:54 swin_small_patch4_window7_224] INFO: Epoch: [139] [1050/1251] eta: 0:01:42 lr: 0.000558 loss: 3.2787 (3.3335) grad_norm: 1.3542 (nan) time: 0.5073 [2021-03-26 04:52:59 swin_small_patch4_window7_224] INFO: Epoch: [139] [1060/1251] eta: 0:01:37 lr: 0.000558 loss: 3.2670 (3.3335) grad_norm: 1.3015 (nan) time: 0.5063 [2021-03-26 04:53:04 swin_small_patch4_window7_224] INFO: Epoch: [139] [1070/1251] eta: 0:01:32 lr: 0.000557 loss: 3.3983 (3.3329) grad_norm: 1.2253 (nan) time: 0.5096 [2021-03-26 04:53:09 swin_small_patch4_window7_224] INFO: Epoch: [139] [1080/1251] eta: 0:01:27 lr: 0.000557 loss: 3.4818 (3.3360) grad_norm: 1.2647 (nan) time: 0.5068 [2021-03-26 04:53:15 swin_small_patch4_window7_224] INFO: Epoch: [139] [1090/1251] eta: 0:01:22 lr: 0.000557 loss: 3.5073 (3.3352) grad_norm: 1.3062 (nan) time: 0.5035 [2021-03-26 04:53:20 swin_small_patch4_window7_224] INFO: Epoch: [139] [1100/1251] eta: 0:01:16 lr: 0.000557 loss: 3.3242 (3.3351) grad_norm: 1.3062 (nan) time: 0.5059 [2021-03-26 04:53:25 swin_small_patch4_window7_224] INFO: Epoch: [139] [1110/1251] eta: 0:01:11 lr: 0.000557 loss: 3.3385 (3.3349) grad_norm: 1.2564 (nan) time: 0.5054 [2021-03-26 04:53:30 swin_small_patch4_window7_224] INFO: Epoch: [139] [1120/1251] eta: 0:01:06 lr: 0.000557 loss: 3.3350 (3.3349) grad_norm: 1.2454 (nan) time: 0.5078 [2021-03-26 04:53:35 swin_small_patch4_window7_224] INFO: Epoch: [139] [1130/1251] eta: 0:01:01 lr: 0.000557 loss: 3.3487 (3.3341) grad_norm: 1.3558 (nan) time: 0.5075 [2021-03-26 04:53:40 swin_small_patch4_window7_224] INFO: Epoch: [139] [1140/1251] eta: 0:00:56 lr: 0.000557 loss: 3.0874 (3.3324) grad_norm: 1.3558 (nan) time: 0.4989 [2021-03-26 04:53:45 swin_small_patch4_window7_224] INFO: Epoch: [139] [1150/1251] eta: 0:00:51 lr: 0.000557 loss: 3.3381 (3.3354) grad_norm: 1.2893 (nan) time: 0.5002 [2021-03-26 04:53:50 swin_small_patch4_window7_224] INFO: Epoch: [139] [1160/1251] eta: 0:00:46 lr: 0.000557 loss: 3.5778 (3.3366) grad_norm: 1.3782 (nan) time: 0.5060 [2021-03-26 04:53:55 swin_small_patch4_window7_224] INFO: Epoch: [139] [1170/1251] eta: 0:00:41 lr: 0.000557 loss: 3.2492 (3.3351) grad_norm: 1.3369 (nan) time: 0.5033 [2021-03-26 04:54:00 swin_small_patch4_window7_224] INFO: Epoch: [139] [1180/1251] eta: 0:00:36 lr: 0.000557 loss: 3.3375 (3.3359) grad_norm: 1.3347 (nan) time: 0.5064 [2021-03-26 04:54:05 swin_small_patch4_window7_224] INFO: Epoch: [139] [1190/1251] eta: 0:00:31 lr: 0.000557 loss: 3.3796 (3.3319) grad_norm: 1.3222 (nan) time: 0.5045 [2021-03-26 04:54:10 swin_small_patch4_window7_224] INFO: Epoch: [139] [1200/1251] eta: 0:00:25 lr: 0.000557 loss: 3.3031 (3.3330) grad_norm: 1.3382 (nan) time: 0.5038 [2021-03-26 04:54:15 swin_small_patch4_window7_224] INFO: Epoch: [139] [1210/1251] eta: 0:00:20 lr: 0.000557 loss: 3.5256 (3.3348) grad_norm: 1.3701 (nan) time: 0.5040 [2021-03-26 04:54:20 swin_small_patch4_window7_224] INFO: Epoch: [139] [1220/1251] eta: 0:00:15 lr: 0.000557 loss: 3.5000 (3.3354) grad_norm: 1.3209 (nan) time: 0.4997 [2021-03-26 04:54:25 swin_small_patch4_window7_224] INFO: Epoch: [139] [1230/1251] eta: 0:00:10 lr: 0.000557 loss: 3.5000 (3.3372) grad_norm: 1.3390 (nan) time: 0.5048 [2021-03-26 04:54:30 swin_small_patch4_window7_224] INFO: Epoch: [139] [1240/1251] eta: 0:00:05 lr: 0.000557 loss: 3.5610 (3.3383) grad_norm: 1.3658 (nan) time: 0.5042 [2021-03-26 04:54:35 swin_small_patch4_window7_224] INFO: Epoch: [139] [1250/1251] eta: 0:00:00 lr: 0.000557 loss: 3.4763 (3.3386) grad_norm: 1.3414 (nan) time: 0.4966 [2021-03-26 04:54:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 1.0005 (1.0005) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-26 04:54:44 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 1.0005 (0.9373) acc1: 78.1250 (77.5568) acc5: 95.3125 (95.0284) [2021-03-26 04:54:47 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8377 (0.9260) acc1: 78.1250 (78.1250) acc5: 93.7500 (94.4940) [2021-03-26 04:54:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9959 (0.9685) acc1: 75.0000 (76.5625) acc5: 93.7500 (94.5060) [2021-03-26 04:54:51 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 1.0179 (0.9689) acc1: 73.4375 (76.4863) acc5: 95.3125 (94.3979) [2021-03-26 04:54:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8998 (0.9531) acc1: 78.1250 (76.9600) acc5: 95.3125 (94.5280) [2021-03-26 04:54:58 swin_small_patch4_window7_224] INFO: * Acc@1 77.892 Acc@5 94.312 loss 0.926 [2021-03-26 04:54:58 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.9% [2021-03-26 04:54:58 swin_small_patch4_window7_224] INFO: Max accuracy: 77.89% [2021-03-26 04:55:02 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 0/1251] eta: 1:24:01 lr: 0.000557 loss: 3.8738 (3.8738) grad_norm: 1.4119 (1.4119) time: 4.0300 [2021-03-26 04:55:07 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 10/1251] eta: 0:17:16 lr: 0.000557 loss: 3.4631 (3.4929) grad_norm: 1.4119 (1.4250) time: 0.8351 [2021-03-26 04:55:12 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 20/1251] eta: 0:13:59 lr: 0.000557 loss: 3.3175 (3.2918) grad_norm: 1.3118 (1.3427) time: 0.5149 [2021-03-26 04:55:17 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 30/1251] eta: 0:12:41 lr: 0.000557 loss: 3.3915 (3.3617) grad_norm: 1.2133 (1.3347) time: 0.5069 [2021-03-26 04:55:23 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 40/1251] eta: 0:12:00 lr: 0.000557 loss: 3.4727 (3.3529) grad_norm: 1.3376 (1.3451) time: 0.5041 [2021-03-26 04:55:28 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 50/1251] eta: 0:11:37 lr: 0.000557 loss: 3.4037 (3.3577) grad_norm: 1.3376 (1.3489) time: 0.5142 [2021-03-26 04:55:33 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 60/1251] eta: 0:11:18 lr: 0.000556 loss: 3.4991 (3.3953) grad_norm: 1.3181 (1.3599) time: 0.5181 [2021-03-26 04:55:38 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 70/1251] eta: 0:11:01 lr: 0.000556 loss: 3.4930 (3.3690) grad_norm: 1.3638 (1.3613) time: 0.5080 [2021-03-26 04:55:43 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 80/1251] eta: 0:10:48 lr: 0.000556 loss: 3.2372 (3.3503) grad_norm: 1.3425 (1.3568) time: 0.5042 [2021-03-26 04:55:48 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 90/1251] eta: 0:10:36 lr: 0.000556 loss: 3.4965 (3.3580) grad_norm: 1.3809 (1.3681) time: 0.5061 [2021-03-26 04:55:53 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 100/1251] eta: 0:10:26 lr: 0.000556 loss: 3.5423 (3.3752) grad_norm: 1.4578 (1.3818) time: 0.5047 [2021-03-26 04:55:58 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 110/1251] eta: 0:10:16 lr: 0.000556 loss: 3.4877 (3.3854) grad_norm: 1.4521 (1.3844) time: 0.5057 [2021-03-26 04:56:03 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 120/1251] eta: 0:10:08 lr: 0.000556 loss: 3.3797 (3.3808) grad_norm: 1.3692 (1.3918) time: 0.5058 [2021-03-26 04:56:08 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 130/1251] eta: 0:09:59 lr: 0.000556 loss: 3.1963 (3.3527) grad_norm: 1.4538 (1.3965) time: 0.5040 [2021-03-26 04:56:13 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 140/1251] eta: 0:09:51 lr: 0.000556 loss: 3.1730 (3.3529) grad_norm: 1.3205 (1.3881) time: 0.5012 [2021-03-26 04:56:18 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 150/1251] eta: 0:09:44 lr: 0.000556 loss: 3.3282 (3.3334) grad_norm: 1.3179 (1.3872) time: 0.5023 [2021-03-26 04:56:23 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 160/1251] eta: 0:09:37 lr: 0.000556 loss: 3.3813 (3.3368) grad_norm: 1.3392 (1.3843) time: 0.5069 [2021-03-26 04:56:28 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 170/1251] eta: 0:09:30 lr: 0.000556 loss: 3.4446 (3.3416) grad_norm: 1.3372 (1.3824) time: 0.5033 [2021-03-26 04:56:33 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 180/1251] eta: 0:09:23 lr: 0.000556 loss: 3.5194 (3.3530) grad_norm: 1.3321 (1.3823) time: 0.5017 [2021-03-26 04:56:39 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 190/1251] eta: 0:09:17 lr: 0.000556 loss: 3.5047 (3.3441) grad_norm: 1.2996 (1.3790) time: 0.5078 [2021-03-26 04:56:44 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 200/1251] eta: 0:09:11 lr: 0.000556 loss: 3.4682 (3.3537) grad_norm: 1.3166 (1.3774) time: 0.5072 [2021-03-26 04:56:49 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 210/1251] eta: 0:09:04 lr: 0.000556 loss: 3.4682 (3.3529) grad_norm: 1.3715 (1.3772) time: 0.5001 [2021-03-26 04:56:53 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 220/1251] eta: 0:08:57 lr: 0.000556 loss: 3.4946 (3.3655) grad_norm: 1.3382 (1.3739) time: 0.4958 [2021-03-26 04:56:59 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 230/1251] eta: 0:08:52 lr: 0.000556 loss: 3.5624 (3.3626) grad_norm: 1.2964 (1.3704) time: 0.5036 [2021-03-26 04:57:04 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 240/1251] eta: 0:08:46 lr: 0.000556 loss: 3.3319 (3.3483) grad_norm: 1.2885 (1.3662) time: 0.5067 [2021-03-26 04:57:09 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 250/1251] eta: 0:08:40 lr: 0.000556 loss: 3.1814 (3.3462) grad_norm: 1.3169 (1.3687) time: 0.5032 [2021-03-26 04:57:14 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 260/1251] eta: 0:08:34 lr: 0.000556 loss: 3.2367 (3.3447) grad_norm: 1.4239 (1.3726) time: 0.5062 [2021-03-26 04:57:19 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 270/1251] eta: 0:08:28 lr: 0.000556 loss: 3.3583 (3.3489) grad_norm: 1.4062 (1.3738) time: 0.5038 [2021-03-26 04:57:24 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 280/1251] eta: 0:08:23 lr: 0.000556 loss: 3.4289 (3.3480) grad_norm: 1.3598 (1.3745) time: 0.4998 [2021-03-26 04:57:29 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 290/1251] eta: 0:08:17 lr: 0.000556 loss: 3.4184 (3.3469) grad_norm: 1.3079 (1.3738) time: 0.5008 [2021-03-26 04:57:34 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 300/1251] eta: 0:08:11 lr: 0.000556 loss: 3.4633 (3.3490) grad_norm: 1.3397 (1.3734) time: 0.5021 [2021-03-26 04:57:39 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 310/1251] eta: 0:08:06 lr: 0.000555 loss: 3.4633 (3.3486) grad_norm: 1.3342 (1.3724) time: 0.5055 [2021-03-26 04:57:44 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 320/1251] eta: 0:08:00 lr: 0.000555 loss: 3.5840 (3.3567) grad_norm: 1.3018 (1.3720) time: 0.5031 [2021-03-26 04:57:49 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 330/1251] eta: 0:07:55 lr: 0.000555 loss: 3.5294 (3.3559) grad_norm: 1.3018 (1.3707) time: 0.5010 [2021-03-26 04:57:54 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 340/1251] eta: 0:07:49 lr: 0.000555 loss: 3.3738 (3.3487) grad_norm: 1.2905 (1.3688) time: 0.5007 [2021-03-26 04:57:59 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 350/1251] eta: 0:07:43 lr: 0.000555 loss: 3.4976 (3.3556) grad_norm: 1.2605 (1.3661) time: 0.4947 [2021-03-26 04:58:04 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 360/1251] eta: 0:07:38 lr: 0.000555 loss: 3.5595 (3.3573) grad_norm: 1.2626 (1.3648) time: 0.4967 [2021-03-26 04:58:09 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 370/1251] eta: 0:07:32 lr: 0.000555 loss: 3.6295 (3.3577) grad_norm: 1.2626 (1.3634) time: 0.5033 [2021-03-26 04:58:14 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 380/1251] eta: 0:07:27 lr: 0.000555 loss: 3.4868 (3.3583) grad_norm: 1.3390 (1.3644) time: 0.5022 [2021-03-26 04:58:19 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 390/1251] eta: 0:07:21 lr: 0.000555 loss: 3.4496 (3.3606) grad_norm: 1.3390 (1.3627) time: 0.5010 [2021-03-26 04:58:24 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 400/1251] eta: 0:07:16 lr: 0.000555 loss: 3.4092 (3.3611) grad_norm: 1.2982 (1.3629) time: 0.5041 [2021-03-26 04:58:29 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 410/1251] eta: 0:07:11 lr: 0.000555 loss: 3.4092 (3.3615) grad_norm: 1.4012 (1.3640) time: 0.5026 [2021-03-26 04:58:34 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 420/1251] eta: 0:07:05 lr: 0.000555 loss: 3.5369 (3.3634) grad_norm: 1.3133 (1.3621) time: 0.5027 [2021-03-26 04:58:39 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 430/1251] eta: 0:07:00 lr: 0.000555 loss: 3.6182 (3.3640) grad_norm: 1.2844 (1.3602) time: 0.5086 [2021-03-26 04:58:44 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 440/1251] eta: 0:06:55 lr: 0.000555 loss: 3.4056 (3.3629) grad_norm: 1.3040 (1.3606) time: 0.5123 [2021-03-26 04:58:49 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 450/1251] eta: 0:06:50 lr: 0.000555 loss: 3.2964 (3.3638) grad_norm: 1.3040 (1.3597) time: 0.5109 [2021-03-26 04:58:54 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 460/1251] eta: 0:06:45 lr: 0.000555 loss: 3.2964 (3.3604) grad_norm: 1.3142 (1.3609) time: 0.5072 [2021-03-26 04:58:59 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 470/1251] eta: 0:06:40 lr: 0.000555 loss: 3.4089 (3.3615) grad_norm: 1.3237 (1.3618) time: 0.5057 [2021-03-26 04:59:04 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 480/1251] eta: 0:06:34 lr: 0.000555 loss: 3.4984 (3.3659) grad_norm: 1.4673 (1.3644) time: 0.5011 [2021-03-26 04:59:09 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 490/1251] eta: 0:06:29 lr: 0.000555 loss: 3.5155 (3.3652) grad_norm: 1.3402 (1.3636) time: 0.4987 [2021-03-26 04:59:15 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 500/1251] eta: 0:06:24 lr: 0.000555 loss: 3.6303 (3.3678) grad_norm: 1.3157 (1.3628) time: 0.5053 [2021-03-26 04:59:20 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 510/1251] eta: 0:06:19 lr: 0.000555 loss: 3.5881 (3.3683) grad_norm: 1.3422 (1.3625) time: 0.5099 [2021-03-26 04:59:25 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 520/1251] eta: 0:06:13 lr: 0.000555 loss: 3.2652 (3.3683) grad_norm: 1.3422 (1.3621) time: 0.5092 [2021-03-26 04:59:30 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 530/1251] eta: 0:06:08 lr: 0.000555 loss: 3.4204 (3.3687) grad_norm: 1.3589 (1.3620) time: 0.5026 [2021-03-26 04:59:35 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 540/1251] eta: 0:06:03 lr: 0.000555 loss: 3.3976 (3.3625) grad_norm: 1.3232 (1.3604) time: 0.4992 [2021-03-26 04:59:40 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 550/1251] eta: 0:05:58 lr: 0.000554 loss: 3.2103 (3.3647) grad_norm: 1.3251 (1.3604) time: 0.5093 [2021-03-26 04:59:45 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 560/1251] eta: 0:05:53 lr: 0.000554 loss: 3.1942 (3.3592) grad_norm: 1.3359 (1.3600) time: 0.5125 [2021-03-26 04:59:50 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 570/1251] eta: 0:05:48 lr: 0.000554 loss: 3.1942 (3.3593) grad_norm: 1.2835 (1.3582) time: 0.5070 [2021-03-26 04:59:55 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 580/1251] eta: 0:05:42 lr: 0.000554 loss: 3.4203 (3.3618) grad_norm: 1.2835 (1.3579) time: 0.5025 [2021-03-26 05:00:00 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 590/1251] eta: 0:05:37 lr: 0.000554 loss: 3.6731 (3.3650) grad_norm: 1.3443 (1.3588) time: 0.5061 [2021-03-26 05:00:05 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 600/1251] eta: 0:05:32 lr: 0.000554 loss: 3.4485 (3.3608) grad_norm: 1.3530 (1.3589) time: 0.5168 [2021-03-26 05:00:10 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 610/1251] eta: 0:05:27 lr: 0.000554 loss: 3.2982 (3.3616) grad_norm: 1.2875 (1.3579) time: 0.5123 [2021-03-26 05:00:16 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 620/1251] eta: 0:05:22 lr: 0.000554 loss: 3.4238 (3.3612) grad_norm: 1.3082 (1.3577) time: 0.5081 [2021-03-26 05:00:21 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 630/1251] eta: 0:05:17 lr: 0.000554 loss: 3.4637 (3.3609) grad_norm: 1.3529 (1.3583) time: 0.5062 [2021-03-26 05:00:26 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 640/1251] eta: 0:05:12 lr: 0.000554 loss: 3.4966 (3.3644) grad_norm: 1.3718 (1.3582) time: 0.5033 [2021-03-26 05:00:31 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 650/1251] eta: 0:05:06 lr: 0.000554 loss: 3.4966 (3.3662) grad_norm: 1.3413 (1.3579) time: 0.5041 [2021-03-26 05:00:36 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 660/1251] eta: 0:05:01 lr: 0.000554 loss: 3.5349 (3.3688) grad_norm: 1.2708 (1.3571) time: 0.5016 [2021-03-26 05:00:41 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 670/1251] eta: 0:04:56 lr: 0.000554 loss: 3.5808 (3.3691) grad_norm: 1.3703 (1.3589) time: 0.5010 [2021-03-26 05:00:46 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 680/1251] eta: 0:04:51 lr: 0.000554 loss: 3.4326 (3.3689) grad_norm: 1.3603 (1.3576) time: 0.5028 [2021-03-26 05:00:51 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 690/1251] eta: 0:04:46 lr: 0.000554 loss: 3.2347 (3.3645) grad_norm: 1.2885 (1.3568) time: 0.5079 [2021-03-26 05:00:56 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 700/1251] eta: 0:04:41 lr: 0.000554 loss: 3.2299 (3.3647) grad_norm: 1.2919 (1.3558) time: 0.5065 [2021-03-26 05:01:01 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 710/1251] eta: 0:04:35 lr: 0.000554 loss: 3.5271 (3.3664) grad_norm: 1.2976 (1.3555) time: 0.5040 [2021-03-26 05:01:06 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 720/1251] eta: 0:04:30 lr: 0.000554 loss: 3.5271 (3.3651) grad_norm: 1.3302 (1.3557) time: 0.5058 [2021-03-26 05:01:11 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 730/1251] eta: 0:04:25 lr: 0.000554 loss: 3.6012 (3.3663) grad_norm: 1.3264 (1.3552) time: 0.5084 [2021-03-26 05:01:16 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 740/1251] eta: 0:04:20 lr: 0.000554 loss: 3.5900 (3.3658) grad_norm: 1.2646 (1.3546) time: 0.5181 [2021-03-26 05:01:21 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 750/1251] eta: 0:04:15 lr: 0.000554 loss: 3.4061 (3.3627) grad_norm: 1.2789 (1.3536) time: 0.5124 [2021-03-26 05:01:26 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 760/1251] eta: 0:04:10 lr: 0.000554 loss: 3.4063 (3.3630) grad_norm: 1.3237 (1.3535) time: 0.5034 [2021-03-26 05:01:31 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 770/1251] eta: 0:04:05 lr: 0.000554 loss: 3.4838 (3.3623) grad_norm: 1.3424 (1.3534) time: 0.5092 [2021-03-26 05:01:37 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 780/1251] eta: 0:04:00 lr: 0.000554 loss: 3.4664 (3.3616) grad_norm: 1.3424 (1.3537) time: 0.5068 [2021-03-26 05:01:42 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 790/1251] eta: 0:03:55 lr: 0.000553 loss: 3.0539 (3.3557) grad_norm: 1.3031 (1.3531) time: 0.5119 [2021-03-26 05:01:47 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 800/1251] eta: 0:03:50 lr: 0.000553 loss: 3.2604 (3.3575) grad_norm: 1.2821 (1.3531) time: 0.5232 [2021-03-26 05:01:52 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 810/1251] eta: 0:03:45 lr: 0.000553 loss: 3.4379 (3.3589) grad_norm: 1.3226 (1.3530) time: 0.5198 [2021-03-26 05:01:57 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 820/1251] eta: 0:03:39 lr: 0.000553 loss: 3.4286 (3.3583) grad_norm: 1.3084 (1.3531) time: 0.5046 [2021-03-26 05:02:02 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 830/1251] eta: 0:03:34 lr: 0.000553 loss: 3.4942 (3.3619) grad_norm: 1.3896 (1.3536) time: 0.4975 [2021-03-26 05:02:07 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 840/1251] eta: 0:03:29 lr: 0.000553 loss: 3.4740 (3.3620) grad_norm: 1.3759 (1.3535) time: 0.5045 [2021-03-26 05:02:12 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 850/1251] eta: 0:03:24 lr: 0.000553 loss: 3.2226 (3.3605) grad_norm: 1.3200 (1.3530) time: 0.5054 [2021-03-26 05:02:17 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 860/1251] eta: 0:03:19 lr: 0.000553 loss: 3.4295 (3.3609) grad_norm: 1.3200 (1.3526) time: 0.5029 [2021-03-26 05:02:22 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 870/1251] eta: 0:03:14 lr: 0.000553 loss: 3.4344 (3.3599) grad_norm: 1.3306 (1.3528) time: 0.5019 [2021-03-26 05:02:27 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 880/1251] eta: 0:03:09 lr: 0.000553 loss: 3.4445 (3.3604) grad_norm: 1.3479 (1.3531) time: 0.5027 [2021-03-26 05:02:32 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 890/1251] eta: 0:03:04 lr: 0.000553 loss: 3.4040 (3.3614) grad_norm: 1.3479 (1.3531) time: 0.5094 [2021-03-26 05:02:37 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 900/1251] eta: 0:02:58 lr: 0.000553 loss: 3.4563 (3.3620) grad_norm: 1.3692 (1.3538) time: 0.5081 [2021-03-26 05:02:43 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 910/1251] eta: 0:02:53 lr: 0.000553 loss: 3.4957 (3.3625) grad_norm: 1.4057 (1.3551) time: 0.5047 [2021-03-26 05:02:48 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 920/1251] eta: 0:02:48 lr: 0.000553 loss: 3.2798 (3.3598) grad_norm: 1.3510 (1.3556) time: 0.5028 [2021-03-26 05:02:53 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 930/1251] eta: 0:02:43 lr: 0.000553 loss: 3.2294 (3.3587) grad_norm: 1.3334 (1.3559) time: 0.5088 [2021-03-26 05:02:58 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 940/1251] eta: 0:02:38 lr: 0.000553 loss: 3.3648 (3.3565) grad_norm: 1.3137 (1.3558) time: 0.5067 [2021-03-26 05:03:03 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 950/1251] eta: 0:02:33 lr: 0.000553 loss: 3.3805 (3.3574) grad_norm: 1.3986 (1.3568) time: 0.4956 [2021-03-26 05:03:08 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 960/1251] eta: 0:02:28 lr: 0.000553 loss: 3.4942 (3.3607) grad_norm: 1.4076 (1.3570) time: 0.5019 [2021-03-26 05:03:13 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 970/1251] eta: 0:02:23 lr: 0.000553 loss: 3.4070 (3.3587) grad_norm: 1.3459 (1.3571) time: 0.5034 [2021-03-26 05:03:18 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 980/1251] eta: 0:02:17 lr: 0.000553 loss: 3.3188 (3.3586) grad_norm: 1.3366 (1.3568) time: 0.5066 [2021-03-26 05:03:23 swin_small_patch4_window7_224] INFO: Epoch: [140] [ 990/1251] eta: 0:02:12 lr: 0.000553 loss: 3.3553 (3.3585) grad_norm: 1.3366 (1.3567) time: 0.5118 [2021-03-26 05:03:28 swin_small_patch4_window7_224] INFO: Epoch: [140] [1000/1251] eta: 0:02:07 lr: 0.000553 loss: 3.4045 (3.3590) grad_norm: 1.2851 (1.3559) time: 0.5123 [2021-03-26 05:03:33 swin_small_patch4_window7_224] INFO: Epoch: [140] [1010/1251] eta: 0:02:02 lr: 0.000553 loss: 3.4360 (3.3598) grad_norm: 1.2786 (1.3555) time: 0.5100 [2021-03-26 05:03:38 swin_small_patch4_window7_224] INFO: Epoch: [140] [1020/1251] eta: 0:01:57 lr: 0.000553 loss: 3.3803 (3.3585) grad_norm: 1.3292 (1.3559) time: 0.5061 [2021-03-26 05:03:43 swin_small_patch4_window7_224] INFO: Epoch: [140] [1030/1251] eta: 0:01:52 lr: 0.000552 loss: 3.2784 (3.3573) grad_norm: 1.3739 (1.3560) time: 0.5028 [2021-03-26 05:03:48 swin_small_patch4_window7_224] INFO: Epoch: [140] [1040/1251] eta: 0:01:47 lr: 0.000552 loss: 3.1714 (3.3553) grad_norm: 1.3665 (1.3560) time: 0.5021 [2021-03-26 05:03:53 swin_small_patch4_window7_224] INFO: Epoch: [140] [1050/1251] eta: 0:01:42 lr: 0.000552 loss: 3.2892 (3.3546) grad_norm: 1.3728 (1.3565) time: 0.5035 [2021-03-26 05:03:58 swin_small_patch4_window7_224] INFO: Epoch: [140] [1060/1251] eta: 0:01:37 lr: 0.000552 loss: 3.3241 (3.3549) grad_norm: 1.3986 (1.3579) time: 0.5013 [2021-03-26 05:04:03 swin_small_patch4_window7_224] INFO: Epoch: [140] [1070/1251] eta: 0:01:32 lr: 0.000552 loss: 3.4998 (3.3567) grad_norm: 1.3785 (1.3578) time: 0.5003 [2021-03-26 05:04:08 swin_small_patch4_window7_224] INFO: Epoch: [140] [1080/1251] eta: 0:01:26 lr: 0.000552 loss: 3.5294 (3.3565) grad_norm: 1.3341 (1.3572) time: 0.4995 [2021-03-26 05:04:13 swin_small_patch4_window7_224] INFO: Epoch: [140] [1090/1251] eta: 0:01:21 lr: 0.000552 loss: 3.4893 (3.3548) grad_norm: 1.3423 (1.3576) time: 0.5012 [2021-03-26 05:04:19 swin_small_patch4_window7_224] INFO: Epoch: [140] [1100/1251] eta: 0:01:16 lr: 0.000552 loss: 3.4780 (3.3556) grad_norm: 1.2938 (1.3570) time: 0.5110 [2021-03-26 05:04:23 swin_small_patch4_window7_224] INFO: Epoch: [140] [1110/1251] eta: 0:01:11 lr: 0.000552 loss: 3.4780 (3.3572) grad_norm: 1.2938 (1.3571) time: 0.5088 [2021-03-26 05:04:29 swin_small_patch4_window7_224] INFO: Epoch: [140] [1120/1251] eta: 0:01:06 lr: 0.000552 loss: 3.2942 (3.3557) grad_norm: 1.3105 (1.3566) time: 0.5032 [2021-03-26 05:04:34 swin_small_patch4_window7_224] INFO: Epoch: [140] [1130/1251] eta: 0:01:01 lr: 0.000552 loss: 3.2942 (3.3572) grad_norm: 1.3058 (1.3567) time: 0.5076 [2021-03-26 05:04:39 swin_small_patch4_window7_224] INFO: Epoch: [140] [1140/1251] eta: 0:00:56 lr: 0.000552 loss: 3.6839 (3.3586) grad_norm: 1.4218 (1.3578) time: 0.5027 [2021-03-26 05:04:44 swin_small_patch4_window7_224] INFO: Epoch: [140] [1150/1251] eta: 0:00:51 lr: 0.000552 loss: 3.6528 (3.3596) grad_norm: 1.3702 (1.3574) time: 0.4971 [2021-03-26 05:04:49 swin_small_patch4_window7_224] INFO: Epoch: [140] [1160/1251] eta: 0:00:46 lr: 0.000552 loss: 3.5978 (3.3609) grad_norm: 1.3224 (1.3578) time: 0.5018 [2021-03-26 05:04:54 swin_small_patch4_window7_224] INFO: Epoch: [140] [1170/1251] eta: 0:00:41 lr: 0.000552 loss: 3.2925 (3.3584) grad_norm: 1.3459 (1.3579) time: 0.5126 [2021-03-26 05:04:59 swin_small_patch4_window7_224] INFO: Epoch: [140] [1180/1251] eta: 0:00:36 lr: 0.000552 loss: 3.4065 (3.3590) grad_norm: 1.3346 (1.3578) time: 0.5116 [2021-03-26 05:05:04 swin_small_patch4_window7_224] INFO: Epoch: [140] [1190/1251] eta: 0:00:31 lr: 0.000552 loss: 3.5071 (3.3599) grad_norm: 1.3377 (1.3579) time: 0.5174 [2021-03-26 05:05:09 swin_small_patch4_window7_224] INFO: Epoch: [140] [1200/1251] eta: 0:00:25 lr: 0.000552 loss: 3.6599 (3.3623) grad_norm: 1.3726 (1.3584) time: 0.5155 [2021-03-26 05:05:14 swin_small_patch4_window7_224] INFO: Epoch: [140] [1210/1251] eta: 0:00:20 lr: 0.000552 loss: 3.6695 (3.3640) grad_norm: 1.3317 (1.3581) time: 0.5032 [2021-03-26 05:05:19 swin_small_patch4_window7_224] INFO: Epoch: [140] [1220/1251] eta: 0:00:15 lr: 0.000552 loss: 3.6637 (3.3650) grad_norm: 1.3021 (1.3575) time: 0.5024 [2021-03-26 05:05:24 swin_small_patch4_window7_224] INFO: Epoch: [140] [1230/1251] eta: 0:00:10 lr: 0.000552 loss: 3.5649 (3.3665) grad_norm: 1.2713 (1.3568) time: 0.5012 [2021-03-26 05:05:29 swin_small_patch4_window7_224] INFO: Epoch: [140] [1240/1251] eta: 0:00:05 lr: 0.000552 loss: 3.5649 (3.3681) grad_norm: 1.2836 (1.3574) time: 0.5059 [2021-03-26 05:05:34 swin_small_patch4_window7_224] INFO: Epoch: [140] [1250/1251] eta: 0:00:00 lr: 0.000552 loss: 3.4489 (3.3685) grad_norm: 1.3640 (1.3575) time: 0.5003 [2021-03-26 05:06:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:18 loss: 1.0004 (1.0004) acc1: 81.2500 (81.2500) acc5: 92.1875 (92.1875) [2021-03-26 05:06:17 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8078 (0.9433) acc1: 78.1250 (78.5511) acc5: 95.3125 (93.8920) [2021-03-26 05:06:18 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8526 (0.9237) acc1: 76.5625 (77.3810) acc5: 95.3125 (94.7917) [2021-03-26 05:06:19 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.9280 (0.9455) acc1: 75.0000 (76.7137) acc5: 95.3125 (94.4556) [2021-03-26 05:06:20 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9280 (0.9345) acc1: 76.5625 (77.0960) acc5: 93.7500 (94.3216) [2021-03-26 05:06:21 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9058 (0.9360) acc1: 78.1250 (77.1200) acc5: 93.7500 (94.5600) [2021-03-26 05:06:29 swin_small_patch4_window7_224] INFO: * Acc@1 78.034 Acc@5 94.378 loss 0.929 [2021-03-26 05:06:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.0% [2021-03-26 05:06:29 swin_small_patch4_window7_224] INFO: Max accuracy: 78.03% [2021-03-26 05:06:33 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 0/1251] eta: 1:22:12 lr: 0.000552 loss: 2.5709 (2.5709) grad_norm: 1.4844 (1.4844) time: 3.9429 [2021-03-26 05:06:39 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 10/1251] eta: 0:17:47 lr: 0.000552 loss: 3.4209 (3.2125) grad_norm: 1.3182 (1.3459) time: 0.8598 [2021-03-26 05:06:44 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 20/1251] eta: 0:14:13 lr: 0.000552 loss: 3.4767 (3.3628) grad_norm: 1.3301 (1.3905) time: 0.5306 [2021-03-26 05:06:49 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 30/1251] eta: 0:12:49 lr: 0.000551 loss: 3.3986 (3.3130) grad_norm: 1.4204 (1.4145) time: 0.5034 [2021-03-26 05:06:54 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 40/1251] eta: 0:12:09 lr: 0.000551 loss: 3.3034 (3.3192) grad_norm: 1.3666 (1.4125) time: 0.5076 [2021-03-26 05:06:59 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 50/1251] eta: 0:11:40 lr: 0.000551 loss: 3.4646 (3.3336) grad_norm: 1.3666 (1.4106) time: 0.5118 [2021-03-26 05:07:04 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 60/1251] eta: 0:11:19 lr: 0.000551 loss: 3.4646 (3.3147) grad_norm: 1.3003 (1.3911) time: 0.5041 [2021-03-26 05:07:09 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 70/1251] eta: 0:11:02 lr: 0.000551 loss: 3.3554 (3.3066) grad_norm: 1.2848 (1.3840) time: 0.5021 [2021-03-26 05:07:14 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 80/1251] eta: 0:10:47 lr: 0.000551 loss: 2.8826 (3.2713) grad_norm: 1.2957 (1.3798) time: 0.4998 [2021-03-26 05:07:19 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 90/1251] eta: 0:10:36 lr: 0.000551 loss: 3.4001 (3.2897) grad_norm: 1.3673 (1.3832) time: 0.5029 [2021-03-26 05:07:24 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 100/1251] eta: 0:10:26 lr: 0.000551 loss: 3.4001 (3.2832) grad_norm: 1.3307 (1.3769) time: 0.5114 [2021-03-26 05:07:30 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 110/1251] eta: 0:10:17 lr: 0.000551 loss: 2.9671 (3.2593) grad_norm: 1.3079 (1.3759) time: 0.5111 [2021-03-26 05:07:35 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 120/1251] eta: 0:10:08 lr: 0.000551 loss: 3.1731 (3.2567) grad_norm: 1.3489 (1.3790) time: 0.5042 [2021-03-26 05:07:40 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 130/1251] eta: 0:10:01 lr: 0.000551 loss: 3.3230 (3.2643) grad_norm: 1.3387 (1.3775) time: 0.5097 [2021-03-26 05:07:45 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 140/1251] eta: 0:09:54 lr: 0.000551 loss: 3.2702 (3.2556) grad_norm: 1.3387 (1.3773) time: 0.5157 [2021-03-26 05:07:50 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 150/1251] eta: 0:09:46 lr: 0.000551 loss: 3.0640 (3.2387) grad_norm: 1.3248 (1.3716) time: 0.5092 [2021-03-26 05:07:55 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 160/1251] eta: 0:09:39 lr: 0.000551 loss: 3.0640 (3.2277) grad_norm: 1.3170 (1.3685) time: 0.5026 [2021-03-26 05:08:00 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 170/1251] eta: 0:09:31 lr: 0.000551 loss: 3.0577 (3.2073) grad_norm: 1.3436 (1.3692) time: 0.4996 [2021-03-26 05:08:05 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 180/1251] eta: 0:09:25 lr: 0.000551 loss: 3.3006 (3.2255) grad_norm: 1.3914 (1.3731) time: 0.5060 [2021-03-26 05:08:10 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 190/1251] eta: 0:09:18 lr: 0.000551 loss: 3.3543 (3.2176) grad_norm: 1.3914 (1.3724) time: 0.5084 [2021-03-26 05:08:15 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 200/1251] eta: 0:09:12 lr: 0.000551 loss: 3.2791 (3.2242) grad_norm: 1.3346 (1.3740) time: 0.5055 [2021-03-26 05:08:20 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 210/1251] eta: 0:09:06 lr: 0.000551 loss: 3.5464 (3.2355) grad_norm: 1.3346 (1.3760) time: 0.5068 [2021-03-26 05:08:25 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 220/1251] eta: 0:09:00 lr: 0.000551 loss: 3.5463 (3.2397) grad_norm: 1.3103 (1.3726) time: 0.5093 [2021-03-26 05:08:30 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 230/1251] eta: 0:08:54 lr: 0.000551 loss: 3.4228 (3.2352) grad_norm: 1.3014 (1.3696) time: 0.5075 [2021-03-26 05:08:36 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 240/1251] eta: 0:08:48 lr: 0.000551 loss: 3.4023 (3.2408) grad_norm: 1.3029 (1.3665) time: 0.5083 [2021-03-26 05:08:41 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 250/1251] eta: 0:08:42 lr: 0.000551 loss: 3.4191 (3.2447) grad_norm: 1.3029 (1.3679) time: 0.5075 [2021-03-26 05:08:46 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 260/1251] eta: 0:08:36 lr: 0.000551 loss: 3.2908 (3.2443) grad_norm: 1.3517 (1.3691) time: 0.5035 [2021-03-26 05:08:51 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 270/1251] eta: 0:08:30 lr: 0.000550 loss: 3.0046 (3.2349) grad_norm: 1.3485 (1.3678) time: 0.5043 [2021-03-26 05:08:56 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 280/1251] eta: 0:08:25 lr: 0.000550 loss: 3.4127 (3.2438) grad_norm: 1.3114 (1.3680) time: 0.5030 [2021-03-26 05:09:01 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 290/1251] eta: 0:08:19 lr: 0.000550 loss: 3.4596 (3.2418) grad_norm: 1.3167 (1.3662) time: 0.5004 [2021-03-26 05:09:06 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 300/1251] eta: 0:08:13 lr: 0.000550 loss: 3.3266 (3.2458) grad_norm: 1.3167 (1.3667) time: 0.5013 [2021-03-26 05:09:11 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 310/1251] eta: 0:08:08 lr: 0.000550 loss: 3.2504 (3.2409) grad_norm: 1.3426 (1.3667) time: 0.5088 [2021-03-26 05:09:16 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 320/1251] eta: 0:08:02 lr: 0.000550 loss: 2.9994 (3.2339) grad_norm: 1.3357 (1.3683) time: 0.5053 [2021-03-26 05:09:21 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 330/1251] eta: 0:07:56 lr: 0.000550 loss: 3.1275 (3.2321) grad_norm: 1.3150 (1.3669) time: 0.5004 [2021-03-26 05:09:26 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 340/1251] eta: 0:07:51 lr: 0.000550 loss: 3.2996 (3.2353) grad_norm: 1.3041 (1.3668) time: 0.5029 [2021-03-26 05:09:31 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 350/1251] eta: 0:07:45 lr: 0.000550 loss: 3.3871 (3.2427) grad_norm: 1.3819 (1.3687) time: 0.5023 [2021-03-26 05:09:36 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 360/1251] eta: 0:07:40 lr: 0.000550 loss: 3.4534 (3.2442) grad_norm: 1.3567 (1.3673) time: 0.5109 [2021-03-26 05:09:41 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 370/1251] eta: 0:07:35 lr: 0.000550 loss: 3.4534 (3.2444) grad_norm: 1.3538 (1.3678) time: 0.5118 [2021-03-26 05:09:46 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 380/1251] eta: 0:07:29 lr: 0.000550 loss: 3.2289 (3.2437) grad_norm: 1.3751 (1.3689) time: 0.5014 [2021-03-26 05:09:51 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 390/1251] eta: 0:07:23 lr: 0.000550 loss: 3.2740 (3.2481) grad_norm: 1.3192 (1.3690) time: 0.4998 [2021-03-26 05:09:56 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 400/1251] eta: 0:07:18 lr: 0.000550 loss: 3.3515 (3.2499) grad_norm: 1.2896 (1.3694) time: 0.5013 [2021-03-26 05:10:01 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 410/1251] eta: 0:07:13 lr: 0.000550 loss: 3.3995 (3.2552) grad_norm: 1.3639 (1.3704) time: 0.5042 [2021-03-26 05:10:06 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 420/1251] eta: 0:07:07 lr: 0.000550 loss: 3.3413 (3.2572) grad_norm: 1.3639 (1.3692) time: 0.5037 [2021-03-26 05:10:11 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 430/1251] eta: 0:07:02 lr: 0.000550 loss: 3.2900 (3.2585) grad_norm: 1.2944 (1.3683) time: 0.5010 [2021-03-26 05:10:16 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 440/1251] eta: 0:06:56 lr: 0.000550 loss: 3.1225 (3.2544) grad_norm: 1.2900 (1.3669) time: 0.4985 [2021-03-26 05:10:21 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 450/1251] eta: 0:06:51 lr: 0.000550 loss: 3.1225 (3.2542) grad_norm: 1.2900 (1.3664) time: 0.4987 [2021-03-26 05:10:26 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 460/1251] eta: 0:06:46 lr: 0.000550 loss: 3.3881 (3.2580) grad_norm: 1.2760 (1.3654) time: 0.5026 [2021-03-26 05:10:31 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 470/1251] eta: 0:06:40 lr: 0.000550 loss: 3.4315 (3.2593) grad_norm: 1.2755 (1.3662) time: 0.5041 [2021-03-26 05:10:36 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 480/1251] eta: 0:06:35 lr: 0.000550 loss: 3.3701 (3.2606) grad_norm: 1.3795 (1.3674) time: 0.4990 [2021-03-26 05:10:41 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 490/1251] eta: 0:06:30 lr: 0.000550 loss: 3.3701 (3.2658) grad_norm: 1.4369 (1.3689) time: 0.4983 [2021-03-26 05:10:46 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 500/1251] eta: 0:06:25 lr: 0.000550 loss: 3.3042 (3.2621) grad_norm: 1.4035 (1.3684) time: 0.5090 [2021-03-26 05:10:51 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 510/1251] eta: 0:06:19 lr: 0.000549 loss: 3.3019 (3.2659) grad_norm: 1.3189 (1.3674) time: 0.5055 [2021-03-26 05:10:56 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 520/1251] eta: 0:06:14 lr: 0.000549 loss: 3.5143 (3.2707) grad_norm: 1.2871 (1.3661) time: 0.4960 [2021-03-26 05:11:01 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 530/1251] eta: 0:06:09 lr: 0.000549 loss: 3.5651 (3.2708) grad_norm: 1.3050 (1.3663) time: 0.4983 [2021-03-26 05:11:06 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 540/1251] eta: 0:06:03 lr: 0.000549 loss: 3.4506 (3.2741) grad_norm: 1.3374 (1.3659) time: 0.5056 [2021-03-26 05:11:12 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 550/1251] eta: 0:05:59 lr: 0.000549 loss: 3.3204 (3.2731) grad_norm: 1.3374 (1.3665) time: 0.5240 [2021-03-26 05:11:17 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 560/1251] eta: 0:05:54 lr: 0.000549 loss: 3.6077 (3.2779) grad_norm: 1.2999 (1.3654) time: 0.5303 [2021-03-26 05:11:22 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 570/1251] eta: 0:05:48 lr: 0.000549 loss: 3.5741 (3.2778) grad_norm: 1.3105 (1.3660) time: 0.5137 [2021-03-26 05:11:27 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 580/1251] eta: 0:05:43 lr: 0.000549 loss: 3.2472 (3.2783) grad_norm: 1.3863 (1.3675) time: 0.5010 [2021-03-26 05:11:32 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 590/1251] eta: 0:05:38 lr: 0.000549 loss: 3.3340 (3.2804) grad_norm: 1.3863 (1.3681) time: 0.5016 [2021-03-26 05:11:37 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 600/1251] eta: 0:05:33 lr: 0.000549 loss: 3.3250 (3.2799) grad_norm: 1.3709 (1.3680) time: 0.5087 [2021-03-26 05:11:42 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 610/1251] eta: 0:05:28 lr: 0.000549 loss: 3.2490 (3.2808) grad_norm: 1.4153 (1.3698) time: 0.5089 [2021-03-26 05:11:47 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 620/1251] eta: 0:05:22 lr: 0.000549 loss: 3.2643 (3.2798) grad_norm: 1.4153 (1.3691) time: 0.5068 [2021-03-26 05:11:52 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 630/1251] eta: 0:05:17 lr: 0.000549 loss: 3.5318 (3.2854) grad_norm: 1.2747 (1.3688) time: 0.5009 [2021-03-26 05:11:57 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 640/1251] eta: 0:05:12 lr: 0.000549 loss: 3.6312 (3.2881) grad_norm: 1.3293 (1.3682) time: 0.4971 [2021-03-26 05:12:02 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 650/1251] eta: 0:05:07 lr: 0.000549 loss: 3.4913 (3.2905) grad_norm: 1.3254 (1.3677) time: 0.5030 [2021-03-26 05:12:07 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 660/1251] eta: 0:05:02 lr: 0.000549 loss: 3.3933 (3.2923) grad_norm: 1.3632 (1.3685) time: 0.5034 [2021-03-26 05:12:12 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 670/1251] eta: 0:04:56 lr: 0.000549 loss: 3.4288 (3.2946) grad_norm: 1.3632 (1.3688) time: 0.4986 [2021-03-26 05:12:17 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 680/1251] eta: 0:04:51 lr: 0.000549 loss: 3.3919 (3.2924) grad_norm: 1.3770 (1.3705) time: 0.5029 [2021-03-26 05:12:23 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 690/1251] eta: 0:04:46 lr: 0.000549 loss: 3.1825 (3.2932) grad_norm: 1.3803 (1.3713) time: 0.5081 [2021-03-26 05:12:28 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 700/1251] eta: 0:04:41 lr: 0.000549 loss: 3.3433 (3.2921) grad_norm: 1.3729 (1.3721) time: 0.5072 [2021-03-26 05:12:33 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 710/1251] eta: 0:04:36 lr: 0.000549 loss: 3.3234 (3.2928) grad_norm: 1.3648 (1.3717) time: 0.5051 [2021-03-26 05:12:38 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 720/1251] eta: 0:04:31 lr: 0.000549 loss: 3.4490 (3.2946) grad_norm: 1.3648 (1.3720) time: 0.5048 [2021-03-26 05:12:43 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 730/1251] eta: 0:04:26 lr: 0.000549 loss: 3.3546 (3.2933) grad_norm: 1.3351 (1.3720) time: 0.5090 [2021-03-26 05:12:48 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 740/1251] eta: 0:04:21 lr: 0.000549 loss: 3.3916 (3.2958) grad_norm: 1.3852 (1.3734) time: 0.5317 [2021-03-26 05:12:54 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 750/1251] eta: 0:04:16 lr: 0.000548 loss: 3.5785 (3.2963) grad_norm: 1.4033 (1.3730) time: 0.5422 [2021-03-26 05:12:59 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 760/1251] eta: 0:04:11 lr: 0.000548 loss: 3.5283 (3.2984) grad_norm: 1.3349 (1.3727) time: 0.5170 [2021-03-26 05:13:04 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 770/1251] eta: 0:04:05 lr: 0.000548 loss: 3.3662 (3.2996) grad_norm: 1.2821 (1.3715) time: 0.5045 [2021-03-26 05:13:09 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 780/1251] eta: 0:04:00 lr: 0.000548 loss: 3.3662 (3.2986) grad_norm: 1.2688 (1.3709) time: 0.5039 [2021-03-26 05:13:14 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 790/1251] eta: 0:03:55 lr: 0.000548 loss: 3.2512 (3.2964) grad_norm: 1.3173 (1.3711) time: 0.5029 [2021-03-26 05:13:19 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 800/1251] eta: 0:03:50 lr: 0.000548 loss: 3.1616 (3.2937) grad_norm: 1.3753 (1.3710) time: 0.5031 [2021-03-26 05:13:24 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 810/1251] eta: 0:03:45 lr: 0.000548 loss: 3.4449 (3.2980) grad_norm: 1.3099 (1.3708) time: 0.5011 [2021-03-26 05:13:29 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 820/1251] eta: 0:03:40 lr: 0.000548 loss: 3.5166 (3.2997) grad_norm: 1.2859 (1.3698) time: 0.4985 [2021-03-26 05:13:34 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 830/1251] eta: 0:03:34 lr: 0.000548 loss: 3.4072 (3.3007) grad_norm: 1.2770 (1.3691) time: 0.4996 [2021-03-26 05:13:39 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 840/1251] eta: 0:03:29 lr: 0.000548 loss: 3.5864 (3.3058) grad_norm: 1.2739 (1.3686) time: 0.5004 [2021-03-26 05:13:44 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 850/1251] eta: 0:03:24 lr: 0.000548 loss: 3.6915 (3.3090) grad_norm: 1.3662 (1.3703) time: 0.5028 [2021-03-26 05:13:49 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 860/1251] eta: 0:03:19 lr: 0.000548 loss: 3.4818 (3.3089) grad_norm: 1.4736 (1.3708) time: 0.5075 [2021-03-26 05:13:54 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 870/1251] eta: 0:03:14 lr: 0.000548 loss: 3.0786 (3.3069) grad_norm: 1.4028 (1.3712) time: 0.5137 [2021-03-26 05:13:59 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 880/1251] eta: 0:03:09 lr: 0.000548 loss: 3.0786 (3.3052) grad_norm: 1.3249 (1.3710) time: 0.5171 [2021-03-26 05:14:04 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 890/1251] eta: 0:03:04 lr: 0.000548 loss: 3.2922 (3.3087) grad_norm: 1.3249 (1.3710) time: 0.5071 [2021-03-26 05:14:09 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 900/1251] eta: 0:02:59 lr: 0.000548 loss: 3.4566 (3.3109) grad_norm: 1.3036 (1.3706) time: 0.4998 [2021-03-26 05:14:14 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 910/1251] eta: 0:02:53 lr: 0.000548 loss: 3.4093 (3.3096) grad_norm: 1.2754 (1.3699) time: 0.4986 [2021-03-26 05:14:19 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 920/1251] eta: 0:02:48 lr: 0.000548 loss: 3.4321 (3.3104) grad_norm: 1.3381 (1.3699) time: 0.4999 [2021-03-26 05:14:24 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 930/1251] eta: 0:02:43 lr: 0.000548 loss: 3.4692 (3.3130) grad_norm: 1.3193 (1.3692) time: 0.5037 [2021-03-26 05:14:30 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 940/1251] eta: 0:02:38 lr: 0.000548 loss: 3.4692 (3.3127) grad_norm: 1.3594 (1.3698) time: 0.5101 [2021-03-26 05:14:35 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 950/1251] eta: 0:02:33 lr: 0.000548 loss: 3.3899 (3.3141) grad_norm: 1.3739 (1.3699) time: 0.5100 [2021-03-26 05:14:40 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 960/1251] eta: 0:02:28 lr: 0.000548 loss: 3.2811 (3.3121) grad_norm: 1.3727 (1.3708) time: 0.5019 [2021-03-26 05:14:45 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 970/1251] eta: 0:02:23 lr: 0.000548 loss: 3.3628 (3.3150) grad_norm: 1.3035 (1.3698) time: 0.5002 [2021-03-26 05:14:50 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 980/1251] eta: 0:02:18 lr: 0.000548 loss: 3.5692 (3.3168) grad_norm: 1.3031 (1.3697) time: 0.5002 [2021-03-26 05:14:55 swin_small_patch4_window7_224] INFO: Epoch: [141] [ 990/1251] eta: 0:02:13 lr: 0.000547 loss: 3.6699 (3.3201) grad_norm: 1.4004 (1.3712) time: 0.5028 [2021-03-26 05:15:00 swin_small_patch4_window7_224] INFO: Epoch: [141] [1000/1251] eta: 0:02:07 lr: 0.000547 loss: 3.6722 (3.3204) grad_norm: 1.4992 (1.3719) time: 0.5080 [2021-03-26 05:15:05 swin_small_patch4_window7_224] INFO: Epoch: [141] [1010/1251] eta: 0:02:02 lr: 0.000547 loss: 3.5427 (3.3230) grad_norm: 1.3855 (1.3720) time: 0.5060 [2021-03-26 05:15:10 swin_small_patch4_window7_224] INFO: Epoch: [141] [1020/1251] eta: 0:01:57 lr: 0.000547 loss: 3.6551 (3.3261) grad_norm: 1.3716 (1.3725) time: 0.4990 [2021-03-26 05:15:15 swin_small_patch4_window7_224] INFO: Epoch: [141] [1030/1251] eta: 0:01:52 lr: 0.000547 loss: 3.6746 (3.3272) grad_norm: 1.3530 (1.3724) time: 0.5003 [2021-03-26 05:15:20 swin_small_patch4_window7_224] INFO: Epoch: [141] [1040/1251] eta: 0:01:47 lr: 0.000547 loss: 3.6315 (3.3269) grad_norm: 1.3131 (1.3714) time: 0.5050 [2021-03-26 05:15:25 swin_small_patch4_window7_224] INFO: Epoch: [141] [1050/1251] eta: 0:01:42 lr: 0.000547 loss: 3.6704 (3.3305) grad_norm: 1.3131 (1.3712) time: 0.5084 [2021-03-26 05:15:30 swin_small_patch4_window7_224] INFO: Epoch: [141] [1060/1251] eta: 0:01:37 lr: 0.000547 loss: 3.6704 (3.3328) grad_norm: 1.3801 (1.3721) time: 0.5078 [2021-03-26 05:15:35 swin_small_patch4_window7_224] INFO: Epoch: [141] [1070/1251] eta: 0:01:32 lr: 0.000547 loss: 3.6063 (3.3345) grad_norm: 1.4068 (1.3721) time: 0.5065 [2021-03-26 05:15:40 swin_small_patch4_window7_224] INFO: Epoch: [141] [1080/1251] eta: 0:01:27 lr: 0.000547 loss: 3.6335 (3.3360) grad_norm: 1.3585 (1.3720) time: 0.5039 [2021-03-26 05:15:45 swin_small_patch4_window7_224] INFO: Epoch: [141] [1090/1251] eta: 0:01:21 lr: 0.000547 loss: 3.4454 (3.3358) grad_norm: 1.2791 (1.3711) time: 0.5017 [2021-03-26 05:15:50 swin_small_patch4_window7_224] INFO: Epoch: [141] [1100/1251] eta: 0:01:16 lr: 0.000547 loss: 3.3291 (3.3353) grad_norm: 1.2789 (1.3708) time: 0.5078 [2021-03-26 05:15:55 swin_small_patch4_window7_224] INFO: Epoch: [141] [1110/1251] eta: 0:01:11 lr: 0.000547 loss: 3.4706 (3.3372) grad_norm: 1.3263 (1.3710) time: 0.5049 [2021-03-26 05:16:00 swin_small_patch4_window7_224] INFO: Epoch: [141] [1120/1251] eta: 0:01:06 lr: 0.000547 loss: 3.5106 (3.3382) grad_norm: 1.3918 (1.3720) time: 0.5005 [2021-03-26 05:16:05 swin_small_patch4_window7_224] INFO: Epoch: [141] [1130/1251] eta: 0:01:01 lr: 0.000547 loss: 3.5983 (3.3392) grad_norm: 1.3691 (1.3720) time: 0.4995 [2021-03-26 05:16:10 swin_small_patch4_window7_224] INFO: Epoch: [141] [1140/1251] eta: 0:00:56 lr: 0.000547 loss: 3.6977 (3.3418) grad_norm: 1.3634 (1.3725) time: 0.5053 [2021-03-26 05:16:15 swin_small_patch4_window7_224] INFO: Epoch: [141] [1150/1251] eta: 0:00:51 lr: 0.000547 loss: 3.6977 (3.3435) grad_norm: 1.3939 (1.3733) time: 0.5079 [2021-03-26 05:16:20 swin_small_patch4_window7_224] INFO: Epoch: [141] [1160/1251] eta: 0:00:46 lr: 0.000547 loss: 3.4031 (3.3428) grad_norm: 1.3686 (1.3735) time: 0.5048 [2021-03-26 05:16:26 swin_small_patch4_window7_224] INFO: Epoch: [141] [1170/1251] eta: 0:00:41 lr: 0.000547 loss: 3.3815 (3.3430) grad_norm: 1.3908 (1.3740) time: 0.5079 [2021-03-26 05:16:31 swin_small_patch4_window7_224] INFO: Epoch: [141] [1180/1251] eta: 0:00:36 lr: 0.000547 loss: 3.3815 (3.3430) grad_norm: 1.4032 (1.3753) time: 0.5024 [2021-03-26 05:16:35 swin_small_patch4_window7_224] INFO: Epoch: [141] [1190/1251] eta: 0:00:31 lr: 0.000547 loss: 3.4447 (3.3438) grad_norm: 1.4032 (1.3755) time: 0.4970 [2021-03-26 05:16:41 swin_small_patch4_window7_224] INFO: Epoch: [141] [1200/1251] eta: 0:00:25 lr: 0.000547 loss: 3.3467 (3.3433) grad_norm: 1.4053 (1.3762) time: 0.4997 [2021-03-26 05:16:46 swin_small_patch4_window7_224] INFO: Epoch: [141] [1210/1251] eta: 0:00:20 lr: 0.000547 loss: 3.2060 (3.3424) grad_norm: 1.4367 (1.3773) time: 0.5015 [2021-03-26 05:16:51 swin_small_patch4_window7_224] INFO: Epoch: [141] [1220/1251] eta: 0:00:15 lr: 0.000547 loss: 3.2060 (3.3422) grad_norm: 1.4044 (1.3777) time: 0.5024 [2021-03-26 05:16:56 swin_small_patch4_window7_224] INFO: Epoch: [141] [1230/1251] eta: 0:00:10 lr: 0.000547 loss: 3.4173 (3.3435) grad_norm: 1.3801 (1.3779) time: 0.5019 [2021-03-26 05:17:01 swin_small_patch4_window7_224] INFO: Epoch: [141] [1240/1251] eta: 0:00:05 lr: 0.000546 loss: 3.5407 (3.3452) grad_norm: 1.3351 (1.3777) time: 0.5005 [2021-03-26 05:17:06 swin_small_patch4_window7_224] INFO: Epoch: [141] [1250/1251] eta: 0:00:00 lr: 0.000546 loss: 3.5407 (3.3463) grad_norm: 1.3518 (1.3784) time: 0.5017 [2021-03-26 05:17:14 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:47 loss: 0.9392 (0.9392) acc1: 73.4375 (73.4375) acc5: 95.3125 (95.3125) [2021-03-26 05:17:17 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9240 (0.8817) acc1: 79.6875 (78.4091) acc5: 95.3125 (95.1705) [2021-03-26 05:17:19 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9240 (0.9360) acc1: 79.6875 (77.2321) acc5: 95.3125 (94.7917) [2021-03-26 05:17:21 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9683 (0.9795) acc1: 76.5625 (76.5121) acc5: 93.7500 (93.9516) [2021-03-26 05:17:23 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9643 (0.9761) acc1: 76.5625 (76.4482) acc5: 95.3125 (94.3598) [2021-03-26 05:17:24 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8876 (0.9523) acc1: 78.1250 (76.8960) acc5: 95.3125 (94.6880) [2021-03-26 05:17:29 swin_small_patch4_window7_224] INFO: * Acc@1 77.662 Acc@5 94.410 loss 0.936 [2021-03-26 05:17:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 77.7% [2021-03-26 05:17:29 swin_small_patch4_window7_224] INFO: Max accuracy: 78.03% [2021-03-26 05:17:34 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 0/1251] eta: 1:35:10 lr: 0.000546 loss: 2.6082 (2.6082) grad_norm: 1.1809 (1.1809) time: 4.5644 [2021-03-26 05:17:39 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 10/1251] eta: 0:17:59 lr: 0.000546 loss: 3.1842 (3.1426) grad_norm: 1.3123 (1.2959) time: 0.8695 [2021-03-26 05:17:44 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 20/1251] eta: 0:14:17 lr: 0.000546 loss: 3.2790 (3.1900) grad_norm: 1.3123 (1.3147) time: 0.5029 [2021-03-26 05:17:49 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 30/1251] eta: 0:12:59 lr: 0.000546 loss: 3.3543 (3.2444) grad_norm: 1.3372 (1.3458) time: 0.5116 [2021-03-26 05:17:54 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 40/1251] eta: 0:12:14 lr: 0.000546 loss: 3.3450 (3.2515) grad_norm: 1.3530 (1.3424) time: 0.5126 [2021-03-26 05:17:59 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 50/1251] eta: 0:11:43 lr: 0.000546 loss: 3.5795 (3.3464) grad_norm: 1.3530 (1.3520) time: 0.5031 [2021-03-26 05:18:04 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 60/1251] eta: 0:11:22 lr: 0.000546 loss: 3.5795 (3.3419) grad_norm: 1.3873 (1.3615) time: 0.5049 [2021-03-26 05:18:09 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 70/1251] eta: 0:11:05 lr: 0.000546 loss: 3.3530 (3.3448) grad_norm: 1.4098 (1.3763) time: 0.5076 [2021-03-26 05:18:14 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 80/1251] eta: 0:10:52 lr: 0.000546 loss: 3.3530 (3.3163) grad_norm: 1.3717 (1.3819) time: 0.5074 [2021-03-26 05:18:19 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 90/1251] eta: 0:10:40 lr: 0.000546 loss: 3.3561 (3.3243) grad_norm: 1.3893 (1.3834) time: 0.5103 [2021-03-26 05:18:25 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 100/1251] eta: 0:10:29 lr: 0.000546 loss: 3.6156 (3.3396) grad_norm: 1.4041 (1.3834) time: 0.5080 [2021-03-26 05:18:30 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 110/1251] eta: 0:10:19 lr: 0.000546 loss: 3.5169 (3.3515) grad_norm: 1.3567 (1.3784) time: 0.5037 [2021-03-26 05:18:34 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 120/1251] eta: 0:10:09 lr: 0.000546 loss: 3.5169 (3.3681) grad_norm: 1.3258 (1.3755) time: 0.4976 [2021-03-26 05:18:40 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 130/1251] eta: 0:10:01 lr: 0.000546 loss: 3.2220 (3.3337) grad_norm: 1.3331 (1.3753) time: 0.5019 [2021-03-26 05:18:45 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 140/1251] eta: 0:09:53 lr: 0.000546 loss: 3.1665 (3.3271) grad_norm: 1.3802 (1.3801) time: 0.5037 [2021-03-26 05:18:49 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 150/1251] eta: 0:09:44 lr: 0.000546 loss: 3.3616 (3.3266) grad_norm: 1.3741 (1.3776) time: 0.4935 [2021-03-26 05:18:54 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 160/1251] eta: 0:09:37 lr: 0.000546 loss: 3.3616 (3.3296) grad_norm: 1.2942 (1.3767) time: 0.4951 [2021-03-26 05:19:00 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 170/1251] eta: 0:09:30 lr: 0.000546 loss: 3.3597 (3.3289) grad_norm: 1.2730 (1.3739) time: 0.5034 [2021-03-26 05:19:04 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 180/1251] eta: 0:09:23 lr: 0.000546 loss: 3.0403 (3.3024) grad_norm: 1.2552 (1.3685) time: 0.5002 [2021-03-26 05:19:10 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 190/1251] eta: 0:09:17 lr: 0.000546 loss: 2.8791 (3.2953) grad_norm: 1.3158 (1.3676) time: 0.5003 [2021-03-26 05:19:15 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 200/1251] eta: 0:09:11 lr: 0.000546 loss: 3.3764 (3.3015) grad_norm: 1.3589 (1.3683) time: 0.5118 [2021-03-26 05:19:20 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 210/1251] eta: 0:09:05 lr: 0.000546 loss: 3.4495 (3.3034) grad_norm: 1.3652 (1.3716) time: 0.5098 [2021-03-26 05:19:25 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 220/1251] eta: 0:08:59 lr: 0.000546 loss: 3.3685 (3.3061) grad_norm: 1.3467 (1.3715) time: 0.5052 [2021-03-26 05:19:30 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 230/1251] eta: 0:08:52 lr: 0.000545 loss: 3.2852 (3.3022) grad_norm: 1.3681 (1.3732) time: 0.5005 [2021-03-26 05:19:35 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 240/1251] eta: 0:08:46 lr: 0.000545 loss: 3.2501 (3.3021) grad_norm: 1.3681 (1.3741) time: 0.4980 [2021-03-26 05:19:40 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 250/1251] eta: 0:08:40 lr: 0.000545 loss: 3.3638 (3.3105) grad_norm: 1.3367 (1.3743) time: 0.5081 [2021-03-26 05:19:45 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 260/1251] eta: 0:08:34 lr: 0.000545 loss: 3.5775 (3.3204) grad_norm: 1.3301 (1.3725) time: 0.5050 [2021-03-26 05:19:50 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 270/1251] eta: 0:08:28 lr: 0.000545 loss: 3.5923 (3.3184) grad_norm: 1.3385 (1.3731) time: 0.4974 [2021-03-26 05:19:55 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 280/1251] eta: 0:08:23 lr: 0.000545 loss: 3.5729 (3.3176) grad_norm: 1.3385 (1.3717) time: 0.4996 [2021-03-26 05:20:00 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 290/1251] eta: 0:08:17 lr: 0.000545 loss: 3.3816 (3.3199) grad_norm: 1.2688 (1.3693) time: 0.4988 [2021-03-26 05:20:05 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 300/1251] eta: 0:08:11 lr: 0.000545 loss: 3.3816 (3.3209) grad_norm: 1.3049 (1.3697) time: 0.4986 [2021-03-26 05:20:10 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 310/1251] eta: 0:08:06 lr: 0.000545 loss: 3.3044 (3.3141) grad_norm: 1.3971 (1.3711) time: 0.5032 [2021-03-26 05:20:15 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 320/1251] eta: 0:08:00 lr: 0.000545 loss: 3.3044 (3.3131) grad_norm: 1.4273 (1.3742) time: 0.5089 [2021-03-26 05:20:20 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 330/1251] eta: 0:07:55 lr: 0.000545 loss: 3.3605 (3.3097) grad_norm: 1.3778 (1.3727) time: 0.5070 [2021-03-26 05:20:25 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 340/1251] eta: 0:07:49 lr: 0.000545 loss: 3.3490 (3.3081) grad_norm: 1.3056 (1.3703) time: 0.5032 [2021-03-26 05:20:30 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 350/1251] eta: 0:07:44 lr: 0.000545 loss: 3.2902 (3.3098) grad_norm: 1.3056 (1.3687) time: 0.5007 [2021-03-26 05:20:35 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 360/1251] eta: 0:07:38 lr: 0.000545 loss: 3.5571 (3.3117) grad_norm: 1.3424 (1.3717) time: 0.5015 [2021-03-26 05:20:40 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 370/1251] eta: 0:07:33 lr: 0.000545 loss: 3.6010 (3.3113) grad_norm: 1.3840 (1.3703) time: 0.5033 [2021-03-26 05:20:45 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 380/1251] eta: 0:07:27 lr: 0.000545 loss: 3.4929 (3.3105) grad_norm: 1.3325 (1.3716) time: 0.5045 [2021-03-26 05:20:50 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 390/1251] eta: 0:07:22 lr: 0.000545 loss: 3.4929 (3.3125) grad_norm: 1.3418 (1.3718) time: 0.5068 [2021-03-26 05:20:55 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 400/1251] eta: 0:07:17 lr: 0.000545 loss: 3.5122 (3.3123) grad_norm: 1.3949 (1.3717) time: 0.5026 [2021-03-26 05:21:00 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 410/1251] eta: 0:07:11 lr: 0.000545 loss: 3.4842 (3.3146) grad_norm: 1.3670 (1.3733) time: 0.4981 [2021-03-26 05:21:05 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 420/1251] eta: 0:07:06 lr: 0.000545 loss: 3.4631 (3.3146) grad_norm: 1.3304 (1.3719) time: 0.5019 [2021-03-26 05:21:10 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 430/1251] eta: 0:07:01 lr: 0.000545 loss: 3.4031 (3.3117) grad_norm: 1.3095 (1.3709) time: 0.5121 [2021-03-26 05:21:16 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 440/1251] eta: 0:06:56 lr: 0.000545 loss: 3.2655 (3.3097) grad_norm: 1.3616 (1.3738) time: 0.5097 [2021-03-26 05:21:21 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 450/1251] eta: 0:06:50 lr: 0.000545 loss: 3.1410 (3.3036) grad_norm: 1.4500 (1.3762) time: 0.5038 [2021-03-26 05:21:26 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 460/1251] eta: 0:06:45 lr: 0.000545 loss: 3.3873 (3.3062) grad_norm: 1.4625 (1.3783) time: 0.5017 [2021-03-26 05:21:31 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 470/1251] eta: 0:06:40 lr: 0.000544 loss: 3.5254 (3.3087) grad_norm: 1.3899 (1.3786) time: 0.5006 [2021-03-26 05:21:36 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 480/1251] eta: 0:06:34 lr: 0.000544 loss: 3.5134 (3.3100) grad_norm: 1.3899 (1.3796) time: 0.5017 [2021-03-26 05:21:41 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 490/1251] eta: 0:06:29 lr: 0.000544 loss: 3.3252 (3.3108) grad_norm: 1.3856 (inf) time: 0.4997 [2021-03-26 05:21:46 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 500/1251] eta: 0:06:24 lr: 0.000544 loss: 3.3252 (3.3109) grad_norm: 1.3781 (inf) time: 0.4987 [2021-03-26 05:21:51 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 510/1251] eta: 0:06:18 lr: 0.000544 loss: 3.1979 (3.3081) grad_norm: 1.4217 (inf) time: 0.5032 [2021-03-26 05:21:56 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 520/1251] eta: 0:06:13 lr: 0.000544 loss: 2.9801 (3.3069) grad_norm: 1.4024 (inf) time: 0.5069 [2021-03-26 05:22:01 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 530/1251] eta: 0:06:08 lr: 0.000544 loss: 3.1773 (3.3055) grad_norm: 1.3611 (inf) time: 0.5042 [2021-03-26 05:22:06 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 540/1251] eta: 0:06:03 lr: 0.000544 loss: 3.1028 (3.3009) grad_norm: 1.3302 (inf) time: 0.5079 [2021-03-26 05:22:11 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 550/1251] eta: 0:05:58 lr: 0.000544 loss: 3.2359 (3.3052) grad_norm: 1.2969 (inf) time: 0.5254 [2021-03-26 05:22:16 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 560/1251] eta: 0:05:53 lr: 0.000544 loss: 3.5285 (3.3074) grad_norm: 1.3335 (inf) time: 0.5231 [2021-03-26 05:22:21 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 570/1251] eta: 0:05:48 lr: 0.000544 loss: 3.4893 (3.3069) grad_norm: 1.3289 (inf) time: 0.5073 [2021-03-26 05:22:26 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 580/1251] eta: 0:05:43 lr: 0.000544 loss: 3.4893 (3.3135) grad_norm: 1.3832 (inf) time: 0.5060 [2021-03-26 05:22:32 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 590/1251] eta: 0:05:38 lr: 0.000544 loss: 3.5610 (3.3110) grad_norm: 1.4333 (inf) time: 0.5092 [2021-03-26 05:22:37 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 600/1251] eta: 0:05:32 lr: 0.000544 loss: 3.2964 (3.3107) grad_norm: 1.3347 (inf) time: 0.5074 [2021-03-26 05:22:42 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 610/1251] eta: 0:05:27 lr: 0.000544 loss: 3.2964 (3.3115) grad_norm: 1.2946 (inf) time: 0.5097 [2021-03-26 05:22:47 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 620/1251] eta: 0:05:22 lr: 0.000544 loss: 3.4882 (3.3119) grad_norm: 1.3414 (inf) time: 0.5123 [2021-03-26 05:22:52 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 630/1251] eta: 0:05:17 lr: 0.000544 loss: 3.5376 (3.3125) grad_norm: 1.3053 (inf) time: 0.5057 [2021-03-26 05:22:57 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 640/1251] eta: 0:05:12 lr: 0.000544 loss: 3.4473 (3.3135) grad_norm: 1.3305 (inf) time: 0.5016 [2021-03-26 05:23:02 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 650/1251] eta: 0:05:06 lr: 0.000544 loss: 3.1977 (3.3117) grad_norm: 1.4865 (inf) time: 0.4988 [2021-03-26 05:23:07 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 660/1251] eta: 0:05:01 lr: 0.000544 loss: 3.4113 (3.3119) grad_norm: 1.4387 (inf) time: 0.4981 [2021-03-26 05:23:12 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 670/1251] eta: 0:04:56 lr: 0.000544 loss: 3.4920 (3.3130) grad_norm: 1.3154 (inf) time: 0.5029 [2021-03-26 05:23:17 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 680/1251] eta: 0:04:51 lr: 0.000544 loss: 3.4588 (3.3135) grad_norm: 1.3265 (inf) time: 0.5104 [2021-03-26 05:23:22 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 690/1251] eta: 0:04:46 lr: 0.000544 loss: 3.1632 (3.3090) grad_norm: 1.4391 (inf) time: 0.5074 [2021-03-26 05:23:27 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 700/1251] eta: 0:04:41 lr: 0.000544 loss: 3.1841 (3.3115) grad_norm: 1.3769 (inf) time: 0.5009 [2021-03-26 05:23:32 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 710/1251] eta: 0:04:35 lr: 0.000543 loss: 3.2824 (3.3102) grad_norm: 1.4026 (inf) time: 0.4982 [2021-03-26 05:23:37 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 720/1251] eta: 0:04:30 lr: 0.000543 loss: 3.4174 (3.3149) grad_norm: 1.4026 (inf) time: 0.5007 [2021-03-26 05:23:42 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 730/1251] eta: 0:04:25 lr: 0.000543 loss: 3.4530 (3.3140) grad_norm: 1.3508 (inf) time: 0.5132 [2021-03-26 05:23:48 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 740/1251] eta: 0:04:20 lr: 0.000543 loss: 3.1573 (3.3119) grad_norm: 1.3113 (inf) time: 0.5266 [2021-03-26 05:23:53 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 750/1251] eta: 0:04:15 lr: 0.000543 loss: 3.3584 (3.3146) grad_norm: 1.3147 (inf) time: 0.5263 [2021-03-26 05:23:58 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 760/1251] eta: 0:04:10 lr: 0.000543 loss: 3.2774 (3.3144) grad_norm: 1.3469 (inf) time: 0.5112 [2021-03-26 05:24:03 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 770/1251] eta: 0:04:05 lr: 0.000543 loss: 3.3382 (3.3152) grad_norm: 1.3347 (inf) time: 0.5096 [2021-03-26 05:24:08 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 780/1251] eta: 0:04:00 lr: 0.000543 loss: 3.3652 (3.3161) grad_norm: 1.2882 (inf) time: 0.5107 [2021-03-26 05:24:13 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 790/1251] eta: 0:03:55 lr: 0.000543 loss: 3.4302 (3.3177) grad_norm: 1.3111 (inf) time: 0.5084 [2021-03-26 05:24:18 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 800/1251] eta: 0:03:50 lr: 0.000543 loss: 3.4302 (3.3166) grad_norm: 1.3509 (inf) time: 0.5102 [2021-03-26 05:24:23 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 810/1251] eta: 0:03:45 lr: 0.000543 loss: 3.2902 (3.3145) grad_norm: 1.3346 (inf) time: 0.5101 [2021-03-26 05:24:28 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 820/1251] eta: 0:03:40 lr: 0.000543 loss: 3.2209 (3.3131) grad_norm: 1.2920 (inf) time: 0.5083 [2021-03-26 05:24:34 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 830/1251] eta: 0:03:34 lr: 0.000543 loss: 3.2423 (3.3132) grad_norm: 1.3164 (inf) time: 0.5061 [2021-03-26 05:24:39 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 840/1251] eta: 0:03:29 lr: 0.000543 loss: 3.3393 (3.3142) grad_norm: 1.3344 (inf) time: 0.5094 [2021-03-26 05:24:44 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 850/1251] eta: 0:03:24 lr: 0.000543 loss: 3.4830 (3.3172) grad_norm: 1.3930 (inf) time: 0.5105 [2021-03-26 05:24:49 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 860/1251] eta: 0:03:19 lr: 0.000543 loss: 3.5172 (3.3180) grad_norm: 1.3930 (inf) time: 0.5064 [2021-03-26 05:24:54 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 870/1251] eta: 0:03:14 lr: 0.000543 loss: 3.5172 (3.3221) grad_norm: 1.3448 (inf) time: 0.5112 [2021-03-26 05:24:59 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 880/1251] eta: 0:03:09 lr: 0.000543 loss: 3.6634 (3.3238) grad_norm: 1.3279 (inf) time: 0.5083 [2021-03-26 05:25:04 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 890/1251] eta: 0:03:04 lr: 0.000543 loss: 3.3913 (3.3236) grad_norm: 1.3825 (inf) time: 0.5021 [2021-03-26 05:25:09 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 900/1251] eta: 0:02:59 lr: 0.000543 loss: 3.3910 (3.3250) grad_norm: 1.3825 (inf) time: 0.5065 [2021-03-26 05:25:14 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 910/1251] eta: 0:02:53 lr: 0.000543 loss: 3.5052 (3.3268) grad_norm: 1.3159 (inf) time: 0.5004 [2021-03-26 05:25:19 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 920/1251] eta: 0:02:48 lr: 0.000543 loss: 3.5452 (3.3284) grad_norm: 1.3531 (inf) time: 0.4947 [2021-03-26 05:25:24 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 930/1251] eta: 0:02:43 lr: 0.000543 loss: 3.5452 (3.3297) grad_norm: 1.3719 (inf) time: 0.4956 [2021-03-26 05:25:29 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 940/1251] eta: 0:02:38 lr: 0.000543 loss: 3.2730 (3.3274) grad_norm: 1.4392 (inf) time: 0.5091 [2021-03-26 05:25:34 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 950/1251] eta: 0:02:33 lr: 0.000542 loss: 3.2730 (3.3291) grad_norm: 1.3079 (inf) time: 0.5074 [2021-03-26 05:25:39 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 960/1251] eta: 0:02:28 lr: 0.000542 loss: 3.4588 (3.3297) grad_norm: 1.3010 (inf) time: 0.4989 [2021-03-26 05:25:44 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 970/1251] eta: 0:02:23 lr: 0.000542 loss: 3.4209 (3.3319) grad_norm: 1.3722 (inf) time: 0.5057 [2021-03-26 05:25:49 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 980/1251] eta: 0:02:18 lr: 0.000542 loss: 3.4360 (3.3319) grad_norm: 1.4221 (inf) time: 0.5040 [2021-03-26 05:25:54 swin_small_patch4_window7_224] INFO: Epoch: [142] [ 990/1251] eta: 0:02:12 lr: 0.000542 loss: 3.4324 (3.3324) grad_norm: 1.4090 (inf) time: 0.5055 [2021-03-26 05:25:59 swin_small_patch4_window7_224] INFO: Epoch: [142] [1000/1251] eta: 0:02:07 lr: 0.000542 loss: 3.4324 (3.3323) grad_norm: 1.3855 (inf) time: 0.5081 [2021-03-26 05:26:04 swin_small_patch4_window7_224] INFO: Epoch: [142] [1010/1251] eta: 0:02:02 lr: 0.000542 loss: 3.4686 (3.3341) grad_norm: 1.3485 (inf) time: 0.5071 [2021-03-26 05:26:10 swin_small_patch4_window7_224] INFO: Epoch: [142] [1020/1251] eta: 0:01:57 lr: 0.000542 loss: 3.5646 (3.3348) grad_norm: 1.2606 (inf) time: 0.5084 [2021-03-26 05:26:15 swin_small_patch4_window7_224] INFO: Epoch: [142] [1030/1251] eta: 0:01:52 lr: 0.000542 loss: 3.2462 (3.3325) grad_norm: 1.2672 (inf) time: 0.5047 [2021-03-26 05:26:20 swin_small_patch4_window7_224] INFO: Epoch: [142] [1040/1251] eta: 0:01:47 lr: 0.000542 loss: 3.1195 (3.3327) grad_norm: 1.3776 (inf) time: 0.5049 [2021-03-26 05:26:25 swin_small_patch4_window7_224] INFO: Epoch: [142] [1050/1251] eta: 0:01:42 lr: 0.000542 loss: 3.3901 (3.3325) grad_norm: 1.4007 (inf) time: 0.5045 [2021-03-26 05:26:30 swin_small_patch4_window7_224] INFO: Epoch: [142] [1060/1251] eta: 0:01:37 lr: 0.000542 loss: 3.3374 (3.3305) grad_norm: 1.3930 (inf) time: 0.4977 [2021-03-26 05:26:35 swin_small_patch4_window7_224] INFO: Epoch: [142] [1070/1251] eta: 0:01:32 lr: 0.000542 loss: 3.4407 (3.3323) grad_norm: 1.3930 (inf) time: 0.5036 [2021-03-26 05:26:40 swin_small_patch4_window7_224] INFO: Epoch: [142] [1080/1251] eta: 0:01:27 lr: 0.000542 loss: 3.4407 (3.3305) grad_norm: 1.3859 (inf) time: 0.5031 [2021-03-26 05:26:45 swin_small_patch4_window7_224] INFO: Epoch: [142] [1090/1251] eta: 0:01:21 lr: 0.000542 loss: 3.3301 (3.3313) grad_norm: 1.3228 (inf) time: 0.4971 [2021-03-26 05:26:50 swin_small_patch4_window7_224] INFO: Epoch: [142] [1100/1251] eta: 0:01:16 lr: 0.000542 loss: 3.4348 (3.3318) grad_norm: 1.2718 (inf) time: 0.5014 [2021-03-26 05:26:55 swin_small_patch4_window7_224] INFO: Epoch: [142] [1110/1251] eta: 0:01:11 lr: 0.000542 loss: 3.2246 (3.3301) grad_norm: 1.3211 (inf) time: 0.5058 [2021-03-26 05:27:00 swin_small_patch4_window7_224] INFO: Epoch: [142] [1120/1251] eta: 0:01:06 lr: 0.000542 loss: 2.9017 (3.3271) grad_norm: 1.3544 (inf) time: 0.5076 [2021-03-26 05:27:05 swin_small_patch4_window7_224] INFO: Epoch: [142] [1130/1251] eta: 0:01:01 lr: 0.000542 loss: 2.8440 (3.3267) grad_norm: 1.3544 (inf) time: 0.5025 [2021-03-26 05:27:10 swin_small_patch4_window7_224] INFO: Epoch: [142] [1140/1251] eta: 0:00:56 lr: 0.000542 loss: 3.4351 (3.3277) grad_norm: 1.3390 (inf) time: 0.5010 [2021-03-26 05:27:15 swin_small_patch4_window7_224] INFO: Epoch: [142] [1150/1251] eta: 0:00:51 lr: 0.000542 loss: 3.4570 (3.3285) grad_norm: 1.3179 (inf) time: 0.5085 [2021-03-26 05:27:20 swin_small_patch4_window7_224] INFO: Epoch: [142] [1160/1251] eta: 0:00:46 lr: 0.000542 loss: 3.4570 (3.3289) grad_norm: 1.3376 (inf) time: 0.5105 [2021-03-26 05:27:25 swin_small_patch4_window7_224] INFO: Epoch: [142] [1170/1251] eta: 0:00:41 lr: 0.000542 loss: 3.4406 (3.3300) grad_norm: 1.3429 (inf) time: 0.5079 [2021-03-26 05:27:30 swin_small_patch4_window7_224] INFO: Epoch: [142] [1180/1251] eta: 0:00:36 lr: 0.000542 loss: 3.3356 (3.3297) grad_norm: 1.3429 (inf) time: 0.5121 [2021-03-26 05:27:35 swin_small_patch4_window7_224] INFO: Epoch: [142] [1190/1251] eta: 0:00:31 lr: 0.000542 loss: 3.4541 (3.3312) grad_norm: 1.3275 (inf) time: 0.5119 [2021-03-26 05:27:41 swin_small_patch4_window7_224] INFO: Epoch: [142] [1200/1251] eta: 0:00:25 lr: 0.000541 loss: 3.4224 (3.3284) grad_norm: 1.3261 (inf) time: 0.5088 [2021-03-26 05:27:46 swin_small_patch4_window7_224] INFO: Epoch: [142] [1210/1251] eta: 0:00:20 lr: 0.000541 loss: 3.2904 (3.3288) grad_norm: 1.3760 (inf) time: 0.5060 [2021-03-26 05:27:51 swin_small_patch4_window7_224] INFO: Epoch: [142] [1220/1251] eta: 0:00:15 lr: 0.000541 loss: 3.3383 (3.3276) grad_norm: 1.3961 (inf) time: 0.5042 [2021-03-26 05:27:56 swin_small_patch4_window7_224] INFO: Epoch: [142] [1230/1251] eta: 0:00:10 lr: 0.000541 loss: 3.2449 (3.3273) grad_norm: 1.2856 (inf) time: 0.5011 [2021-03-26 05:28:01 swin_small_patch4_window7_224] INFO: Epoch: [142] [1240/1251] eta: 0:00:05 lr: 0.000541 loss: 3.3471 (3.3272) grad_norm: 1.2925 (inf) time: 0.4994 [2021-03-26 05:28:06 swin_small_patch4_window7_224] INFO: Epoch: [142] [1250/1251] eta: 0:00:00 lr: 0.000541 loss: 3.4404 (3.3282) grad_norm: 1.3847 (inf) time: 0.4978 [2021-03-26 05:28:15 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:45 loss: 0.7951 (0.7951) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 05:28:17 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8408 (0.8713) acc1: 81.2500 (80.2557) acc5: 93.7500 (94.6023) [2021-03-26 05:28:19 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9271 (0.9345) acc1: 78.1250 (78.2738) acc5: 93.7500 (94.0476) [2021-03-26 05:28:22 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 1.0159 (0.9581) acc1: 75.0000 (77.6210) acc5: 93.7500 (94.1532) [2021-03-26 05:28:23 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9884 (0.9658) acc1: 76.5625 (77.5152) acc5: 93.7500 (94.4360) [2021-03-26 05:28:24 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 1.0071 (0.9626) acc1: 75.4717 (77.6000) acc5: 93.7500 (94.4960) [2021-03-26 05:28:29 swin_small_patch4_window7_224] INFO: * Acc@1 78.060 Acc@5 94.416 loss 0.936 [2021-03-26 05:28:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.1% [2021-03-26 05:28:29 swin_small_patch4_window7_224] INFO: Max accuracy: 78.06% [2021-03-26 05:28:33 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 0/1251] eta: 1:29:59 lr: 0.000541 loss: 3.0251 (3.0251) grad_norm: 1.5055 (1.5055) time: 4.3164 [2021-03-26 05:28:38 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 10/1251] eta: 0:17:36 lr: 0.000541 loss: 3.5702 (3.4078) grad_norm: 1.5541 (1.5067) time: 0.8513 [2021-03-26 05:28:43 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 20/1251] eta: 0:14:07 lr: 0.000541 loss: 3.4803 (3.4042) grad_norm: 1.4086 (1.4346) time: 0.5075 [2021-03-26 05:28:48 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 30/1251] eta: 0:12:48 lr: 0.000541 loss: 3.4640 (3.3708) grad_norm: 1.3380 (1.4316) time: 0.5072 [2021-03-26 05:28:53 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 40/1251] eta: 0:12:07 lr: 0.000541 loss: 3.2577 (3.3047) grad_norm: 1.3372 (1.4187) time: 0.5079 [2021-03-26 05:28:58 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 50/1251] eta: 0:11:42 lr: 0.000541 loss: 3.3864 (3.3336) grad_norm: 1.3372 (1.4116) time: 0.5169 [2021-03-26 05:29:03 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 60/1251] eta: 0:11:21 lr: 0.000541 loss: 3.5707 (3.3442) grad_norm: 1.3581 (1.3988) time: 0.5130 [2021-03-26 05:29:09 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 70/1251] eta: 0:11:04 lr: 0.000541 loss: 3.4762 (3.3517) grad_norm: 1.3022 (1.3887) time: 0.5051 [2021-03-26 05:29:14 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 80/1251] eta: 0:10:51 lr: 0.000541 loss: 3.5035 (3.3755) grad_norm: 1.3545 (1.3890) time: 0.5090 [2021-03-26 05:29:19 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 90/1251] eta: 0:10:38 lr: 0.000541 loss: 3.5757 (3.3689) grad_norm: 1.3452 (1.3837) time: 0.5067 [2021-03-26 05:29:24 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 100/1251] eta: 0:10:29 lr: 0.000541 loss: 3.4446 (3.3728) grad_norm: 1.3354 (1.3840) time: 0.5077 [2021-03-26 05:29:29 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 110/1251] eta: 0:10:19 lr: 0.000541 loss: 3.3613 (3.3571) grad_norm: 1.3678 (1.3825) time: 0.5081 [2021-03-26 05:29:34 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 120/1251] eta: 0:10:10 lr: 0.000541 loss: 3.3602 (3.3708) grad_norm: 1.4171 (1.3869) time: 0.5026 [2021-03-26 05:29:39 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 130/1251] eta: 0:10:01 lr: 0.000541 loss: 3.4903 (3.3637) grad_norm: 1.4139 (1.3906) time: 0.5028 [2021-03-26 05:29:44 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 140/1251] eta: 0:09:54 lr: 0.000541 loss: 3.3074 (3.3528) grad_norm: 1.3341 (1.3874) time: 0.5083 [2021-03-26 05:29:49 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 150/1251] eta: 0:09:46 lr: 0.000541 loss: 3.3717 (3.3534) grad_norm: 1.3293 (1.3851) time: 0.5085 [2021-03-26 05:29:54 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 160/1251] eta: 0:09:39 lr: 0.000541 loss: 3.5841 (3.3668) grad_norm: 1.3893 (1.3925) time: 0.5052 [2021-03-26 05:29:59 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 170/1251] eta: 0:09:32 lr: 0.000541 loss: 3.5234 (3.3602) grad_norm: 1.4019 (1.3910) time: 0.5064 [2021-03-26 05:30:04 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 180/1251] eta: 0:09:26 lr: 0.000541 loss: 3.4861 (3.3676) grad_norm: 1.3772 (1.3940) time: 0.5139 [2021-03-26 05:30:10 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 190/1251] eta: 0:09:20 lr: 0.000540 loss: 3.6534 (3.3821) grad_norm: 1.4623 (1.3977) time: 0.5143 [2021-03-26 05:30:15 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 200/1251] eta: 0:09:14 lr: 0.000540 loss: 3.5520 (3.3777) grad_norm: 1.4554 (1.3996) time: 0.5092 [2021-03-26 05:30:20 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 210/1251] eta: 0:09:07 lr: 0.000540 loss: 3.4095 (3.3777) grad_norm: 1.4320 (1.4023) time: 0.5070 [2021-03-26 05:30:25 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 220/1251] eta: 0:09:01 lr: 0.000540 loss: 3.2615 (3.3681) grad_norm: 1.3820 (1.4018) time: 0.5073 [2021-03-26 05:30:30 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 230/1251] eta: 0:08:55 lr: 0.000540 loss: 3.3271 (3.3700) grad_norm: 1.3625 (1.4011) time: 0.5119 [2021-03-26 05:30:35 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 240/1251] eta: 0:08:49 lr: 0.000540 loss: 3.2994 (3.3647) grad_norm: 1.3569 (1.4004) time: 0.5087 [2021-03-26 05:30:40 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 250/1251] eta: 0:08:44 lr: 0.000540 loss: 3.3285 (3.3714) grad_norm: 1.4001 (1.4034) time: 0.5086 [2021-03-26 05:30:45 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 260/1251] eta: 0:08:38 lr: 0.000540 loss: 3.3108 (3.3608) grad_norm: 1.4370 (1.4039) time: 0.5084 [2021-03-26 05:30:50 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 270/1251] eta: 0:08:32 lr: 0.000540 loss: 2.9492 (3.3553) grad_norm: 1.3596 (1.4033) time: 0.5048 [2021-03-26 05:30:55 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 280/1251] eta: 0:08:26 lr: 0.000540 loss: 3.1667 (3.3520) grad_norm: 1.3598 (1.4030) time: 0.5031 [2021-03-26 05:31:00 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 290/1251] eta: 0:08:20 lr: 0.000540 loss: 3.1848 (3.3492) grad_norm: 1.3532 (1.4002) time: 0.5038 [2021-03-26 05:31:05 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 300/1251] eta: 0:08:15 lr: 0.000540 loss: 3.1848 (3.3464) grad_norm: 1.2954 (1.3969) time: 0.5080 [2021-03-26 05:31:10 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 310/1251] eta: 0:08:09 lr: 0.000540 loss: 3.4396 (3.3499) grad_norm: 1.3050 (1.3958) time: 0.5071 [2021-03-26 05:31:15 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 320/1251] eta: 0:08:03 lr: 0.000540 loss: 3.5670 (3.3551) grad_norm: 1.4205 (1.3969) time: 0.4993 [2021-03-26 05:31:20 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 330/1251] eta: 0:07:57 lr: 0.000540 loss: 3.6671 (3.3522) grad_norm: 1.4498 (1.3989) time: 0.4998 [2021-03-26 05:31:25 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 340/1251] eta: 0:07:52 lr: 0.000540 loss: 3.3122 (3.3511) grad_norm: 1.4036 (1.3988) time: 0.5041 [2021-03-26 05:31:30 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 350/1251] eta: 0:07:46 lr: 0.000540 loss: 3.2866 (3.3411) grad_norm: 1.4032 (1.3988) time: 0.5054 [2021-03-26 05:31:36 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 360/1251] eta: 0:07:41 lr: 0.000540 loss: 3.0880 (3.3352) grad_norm: 1.4065 (1.3987) time: 0.5044 [2021-03-26 05:31:41 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 370/1251] eta: 0:07:35 lr: 0.000540 loss: 3.2176 (3.3333) grad_norm: 1.3287 (1.3978) time: 0.5072 [2021-03-26 05:31:46 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 380/1251] eta: 0:07:30 lr: 0.000540 loss: 3.3516 (3.3344) grad_norm: 1.3388 (1.3975) time: 0.5097 [2021-03-26 05:31:51 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 390/1251] eta: 0:07:25 lr: 0.000540 loss: 3.5645 (3.3343) grad_norm: 1.3661 (1.3974) time: 0.5059 [2021-03-26 05:31:56 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 400/1251] eta: 0:07:19 lr: 0.000540 loss: 3.5645 (3.3369) grad_norm: 1.3661 (1.3964) time: 0.5050 [2021-03-26 05:32:01 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 410/1251] eta: 0:07:14 lr: 0.000540 loss: 3.4578 (3.3359) grad_norm: 1.3263 (1.3966) time: 0.5031 [2021-03-26 05:32:06 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 420/1251] eta: 0:07:08 lr: 0.000540 loss: 3.4578 (3.3346) grad_norm: 1.3080 (1.3949) time: 0.4990 [2021-03-26 05:32:11 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 430/1251] eta: 0:07:03 lr: 0.000539 loss: 3.1696 (3.3267) grad_norm: 1.3475 (1.3952) time: 0.5018 [2021-03-26 05:32:16 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 440/1251] eta: 0:06:57 lr: 0.000539 loss: 3.1696 (3.3231) grad_norm: 1.3543 (1.3944) time: 0.5020 [2021-03-26 05:32:21 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 450/1251] eta: 0:06:52 lr: 0.000539 loss: 3.3456 (3.3217) grad_norm: 1.3426 (1.3931) time: 0.5041 [2021-03-26 05:32:26 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 460/1251] eta: 0:06:47 lr: 0.000539 loss: 3.4186 (3.3244) grad_norm: 1.3549 (1.3938) time: 0.5110 [2021-03-26 05:32:31 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 470/1251] eta: 0:06:41 lr: 0.000539 loss: 3.3063 (3.3187) grad_norm: 1.3362 (1.3922) time: 0.5063 [2021-03-26 05:32:36 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 480/1251] eta: 0:06:36 lr: 0.000539 loss: 3.2313 (3.3195) grad_norm: 1.3274 (1.3920) time: 0.5004 [2021-03-26 05:32:41 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 490/1251] eta: 0:06:31 lr: 0.000539 loss: 3.1205 (3.3139) grad_norm: 1.3601 (1.3924) time: 0.5011 [2021-03-26 05:32:46 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 500/1251] eta: 0:06:25 lr: 0.000539 loss: 3.2192 (3.3127) grad_norm: 1.3721 (1.3928) time: 0.5046 [2021-03-26 05:32:51 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 510/1251] eta: 0:06:20 lr: 0.000539 loss: 3.2192 (3.3116) grad_norm: 1.3660 (1.3917) time: 0.5051 [2021-03-26 05:32:56 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 520/1251] eta: 0:06:15 lr: 0.000539 loss: 3.2724 (3.3105) grad_norm: 1.3256 (1.3905) time: 0.5058 [2021-03-26 05:33:01 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 530/1251] eta: 0:06:10 lr: 0.000539 loss: 3.3894 (3.3115) grad_norm: 1.3748 (1.3922) time: 0.5024 [2021-03-26 05:33:06 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 540/1251] eta: 0:06:04 lr: 0.000539 loss: 3.3894 (3.3113) grad_norm: 1.3948 (1.3909) time: 0.5045 [2021-03-26 05:33:12 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 550/1251] eta: 0:06:00 lr: 0.000539 loss: 3.5913 (3.3166) grad_norm: 1.3168 (1.3903) time: 0.5197 [2021-03-26 05:33:17 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 560/1251] eta: 0:05:54 lr: 0.000539 loss: 3.6933 (3.3198) grad_norm: 1.3107 (1.3884) time: 0.5240 [2021-03-26 05:33:22 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 570/1251] eta: 0:05:49 lr: 0.000539 loss: 3.6508 (3.3258) grad_norm: 1.3056 (1.3907) time: 0.5162 [2021-03-26 05:33:27 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 580/1251] eta: 0:05:44 lr: 0.000539 loss: 3.4755 (3.3235) grad_norm: 1.3853 (1.3932) time: 0.5058 [2021-03-26 05:33:32 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 590/1251] eta: 0:05:39 lr: 0.000539 loss: 3.2376 (3.3232) grad_norm: 1.4173 (1.3942) time: 0.5030 [2021-03-26 05:33:37 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 600/1251] eta: 0:05:34 lr: 0.000539 loss: 3.2376 (3.3192) grad_norm: 1.4172 (1.3953) time: 0.5099 [2021-03-26 05:33:42 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 610/1251] eta: 0:05:28 lr: 0.000539 loss: 3.2292 (3.3198) grad_norm: 1.3912 (1.3943) time: 0.5084 [2021-03-26 05:33:47 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 620/1251] eta: 0:05:23 lr: 0.000539 loss: 3.1537 (3.3151) grad_norm: 1.3190 (1.3937) time: 0.5056 [2021-03-26 05:33:52 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 630/1251] eta: 0:05:18 lr: 0.000539 loss: 3.1243 (3.3122) grad_norm: 1.2968 (1.3937) time: 0.5103 [2021-03-26 05:33:57 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 640/1251] eta: 0:05:13 lr: 0.000539 loss: 3.1662 (3.3117) grad_norm: 1.2976 (1.3932) time: 0.5087 [2021-03-26 05:34:02 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 650/1251] eta: 0:05:08 lr: 0.000539 loss: 3.3339 (3.3113) grad_norm: 1.3638 (1.3931) time: 0.5027 [2021-03-26 05:34:08 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 660/1251] eta: 0:05:02 lr: 0.000539 loss: 3.4877 (3.3152) grad_norm: 1.3649 (1.3927) time: 0.5017 [2021-03-26 05:34:13 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 670/1251] eta: 0:04:57 lr: 0.000538 loss: 3.5166 (3.3152) grad_norm: 1.3638 (1.3923) time: 0.5063 [2021-03-26 05:34:18 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 680/1251] eta: 0:04:52 lr: 0.000538 loss: 3.4136 (3.3161) grad_norm: 1.4089 (1.3937) time: 0.5097 [2021-03-26 05:34:23 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 690/1251] eta: 0:04:47 lr: 0.000538 loss: 3.4319 (3.3148) grad_norm: 1.4480 (1.3932) time: 0.5038 [2021-03-26 05:34:28 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 700/1251] eta: 0:04:42 lr: 0.000538 loss: 3.3044 (3.3127) grad_norm: 1.3224 (1.3927) time: 0.5011 [2021-03-26 05:34:33 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 710/1251] eta: 0:04:37 lr: 0.000538 loss: 3.2200 (3.3122) grad_norm: 1.3537 (1.3936) time: 0.5086 [2021-03-26 05:34:38 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 720/1251] eta: 0:04:31 lr: 0.000538 loss: 2.9801 (3.3084) grad_norm: 1.4427 (1.3945) time: 0.5091 [2021-03-26 05:34:43 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 730/1251] eta: 0:04:26 lr: 0.000538 loss: 3.1514 (3.3079) grad_norm: 1.4657 (1.3963) time: 0.5144 [2021-03-26 05:34:49 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 740/1251] eta: 0:04:21 lr: 0.000538 loss: 3.2384 (3.3086) grad_norm: 1.4258 (1.3963) time: 0.5329 [2021-03-26 05:34:54 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 750/1251] eta: 0:04:16 lr: 0.000538 loss: 3.1221 (3.3063) grad_norm: 1.4006 (1.3962) time: 0.5253 [2021-03-26 05:34:59 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 760/1251] eta: 0:04:11 lr: 0.000538 loss: 3.3115 (3.3061) grad_norm: 1.4006 (1.3965) time: 0.5077 [2021-03-26 05:35:04 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 770/1251] eta: 0:04:06 lr: 0.000538 loss: 3.4378 (3.3078) grad_norm: 1.3470 (1.3963) time: 0.5059 [2021-03-26 05:35:09 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 780/1251] eta: 0:04:01 lr: 0.000538 loss: 3.3229 (3.3026) grad_norm: 1.4176 (1.3972) time: 0.5088 [2021-03-26 05:35:14 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 790/1251] eta: 0:03:56 lr: 0.000538 loss: 3.1217 (3.3015) grad_norm: 1.3864 (1.3972) time: 0.5114 [2021-03-26 05:35:19 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 800/1251] eta: 0:03:51 lr: 0.000538 loss: 3.3819 (3.3015) grad_norm: 1.3822 (1.3973) time: 0.5059 [2021-03-26 05:35:24 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 810/1251] eta: 0:03:45 lr: 0.000538 loss: 3.3898 (3.3032) grad_norm: 1.3822 (1.3976) time: 0.5067 [2021-03-26 05:35:29 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 820/1251] eta: 0:03:40 lr: 0.000538 loss: 3.3898 (3.3037) grad_norm: 1.4182 (1.3980) time: 0.5044 [2021-03-26 05:35:34 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 830/1251] eta: 0:03:35 lr: 0.000538 loss: 3.4745 (3.3043) grad_norm: 1.4182 (1.3982) time: 0.5001 [2021-03-26 05:35:39 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 840/1251] eta: 0:03:30 lr: 0.000538 loss: 3.4333 (3.3049) grad_norm: 1.3608 (1.3981) time: 0.5077 [2021-03-26 05:35:44 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 850/1251] eta: 0:03:25 lr: 0.000538 loss: 3.3900 (3.3064) grad_norm: 1.3594 (1.3976) time: 0.5131 [2021-03-26 05:35:49 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 860/1251] eta: 0:03:20 lr: 0.000538 loss: 3.3900 (3.3065) grad_norm: 1.3497 (1.3974) time: 0.5058 [2021-03-26 05:35:55 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 870/1251] eta: 0:03:15 lr: 0.000538 loss: 3.3352 (3.3071) grad_norm: 1.3563 (1.3974) time: 0.5039 [2021-03-26 05:35:59 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 880/1251] eta: 0:03:09 lr: 0.000538 loss: 3.4680 (3.3088) grad_norm: 1.3563 (1.3968) time: 0.5034 [2021-03-26 05:36:04 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 890/1251] eta: 0:03:04 lr: 0.000538 loss: 3.4442 (3.3087) grad_norm: 1.4049 (1.3971) time: 0.4967 [2021-03-26 05:36:09 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 900/1251] eta: 0:02:59 lr: 0.000538 loss: 3.4024 (3.3063) grad_norm: 1.4272 (1.3977) time: 0.4986 [2021-03-26 05:36:14 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 910/1251] eta: 0:02:54 lr: 0.000537 loss: 3.4059 (3.3068) grad_norm: 1.4066 (1.3980) time: 0.5016 [2021-03-26 05:36:20 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 920/1251] eta: 0:02:49 lr: 0.000537 loss: 3.4059 (3.3057) grad_norm: 1.3724 (1.3980) time: 0.5047 [2021-03-26 05:36:25 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 930/1251] eta: 0:02:44 lr: 0.000537 loss: 3.4669 (3.3084) grad_norm: 1.3886 (1.3984) time: 0.5144 [2021-03-26 05:36:30 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 940/1251] eta: 0:02:39 lr: 0.000537 loss: 3.6229 (3.3087) grad_norm: 1.4146 (1.3986) time: 0.5147 [2021-03-26 05:36:35 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 950/1251] eta: 0:02:33 lr: 0.000537 loss: 3.4038 (3.3090) grad_norm: 1.4146 (1.3991) time: 0.5019 [2021-03-26 05:36:40 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 960/1251] eta: 0:02:28 lr: 0.000537 loss: 3.5624 (3.3117) grad_norm: 1.3847 (1.3986) time: 0.5020 [2021-03-26 05:36:45 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 970/1251] eta: 0:02:23 lr: 0.000537 loss: 3.3889 (3.3094) grad_norm: 1.3733 (1.3991) time: 0.5092 [2021-03-26 05:36:50 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 980/1251] eta: 0:02:18 lr: 0.000537 loss: 2.9394 (3.3089) grad_norm: 1.4590 (1.4003) time: 0.5093 [2021-03-26 05:36:55 swin_small_patch4_window7_224] INFO: Epoch: [143] [ 990/1251] eta: 0:02:13 lr: 0.000537 loss: 3.4718 (3.3087) grad_norm: 1.3927 (1.3996) time: 0.5069 [2021-03-26 05:37:00 swin_small_patch4_window7_224] INFO: Epoch: [143] [1000/1251] eta: 0:02:08 lr: 0.000537 loss: 3.2825 (3.3058) grad_norm: 1.3189 (1.3987) time: 0.5087 [2021-03-26 05:37:05 swin_small_patch4_window7_224] INFO: Epoch: [143] [1010/1251] eta: 0:02:03 lr: 0.000537 loss: 3.2825 (3.3051) grad_norm: 1.3198 (1.3982) time: 0.5085 [2021-03-26 05:37:10 swin_small_patch4_window7_224] INFO: Epoch: [143] [1020/1251] eta: 0:01:58 lr: 0.000537 loss: 3.3149 (3.3037) grad_norm: 1.3327 (1.3978) time: 0.5050 [2021-03-26 05:37:15 swin_small_patch4_window7_224] INFO: Epoch: [143] [1030/1251] eta: 0:01:52 lr: 0.000537 loss: 3.3489 (3.3056) grad_norm: 1.3560 (1.3974) time: 0.5009 [2021-03-26 05:37:20 swin_small_patch4_window7_224] INFO: Epoch: [143] [1040/1251] eta: 0:01:47 lr: 0.000537 loss: 3.3184 (3.3019) grad_norm: 1.3927 (1.3987) time: 0.4973 [2021-03-26 05:37:25 swin_small_patch4_window7_224] INFO: Epoch: [143] [1050/1251] eta: 0:01:42 lr: 0.000537 loss: 2.9927 (3.3005) grad_norm: 1.4102 (1.3991) time: 0.4994 [2021-03-26 05:37:30 swin_small_patch4_window7_224] INFO: Epoch: [143] [1060/1251] eta: 0:01:37 lr: 0.000537 loss: 3.1499 (3.3005) grad_norm: 1.3674 (1.3987) time: 0.4999 [2021-03-26 05:37:35 swin_small_patch4_window7_224] INFO: Epoch: [143] [1070/1251] eta: 0:01:32 lr: 0.000537 loss: 3.4737 (3.3023) grad_norm: 1.3295 (1.3990) time: 0.5018 [2021-03-26 05:37:40 swin_small_patch4_window7_224] INFO: Epoch: [143] [1080/1251] eta: 0:01:27 lr: 0.000537 loss: 3.4737 (3.3018) grad_norm: 1.3345 (1.3983) time: 0.5043 [2021-03-26 05:37:45 swin_small_patch4_window7_224] INFO: Epoch: [143] [1090/1251] eta: 0:01:22 lr: 0.000537 loss: 3.3157 (3.3023) grad_norm: 1.3259 (1.3976) time: 0.5037 [2021-03-26 05:37:51 swin_small_patch4_window7_224] INFO: Epoch: [143] [1100/1251] eta: 0:01:17 lr: 0.000537 loss: 3.3875 (3.3030) grad_norm: 1.3303 (1.3977) time: 0.5063 [2021-03-26 05:37:56 swin_small_patch4_window7_224] INFO: Epoch: [143] [1110/1251] eta: 0:01:11 lr: 0.000537 loss: 3.5108 (3.3056) grad_norm: 1.3312 (1.3972) time: 0.5095 [2021-03-26 05:38:01 swin_small_patch4_window7_224] INFO: Epoch: [143] [1120/1251] eta: 0:01:06 lr: 0.000537 loss: 3.4619 (3.3036) grad_norm: 1.3354 (1.3970) time: 0.5124 [2021-03-26 05:38:06 swin_small_patch4_window7_224] INFO: Epoch: [143] [1130/1251] eta: 0:01:01 lr: 0.000537 loss: 3.2912 (3.3043) grad_norm: 1.3900 (1.3979) time: 0.5075 [2021-03-26 05:38:11 swin_small_patch4_window7_224] INFO: Epoch: [143] [1140/1251] eta: 0:00:56 lr: 0.000537 loss: 3.4300 (3.3056) grad_norm: 1.4324 (1.3978) time: 0.5014 [2021-03-26 05:38:16 swin_small_patch4_window7_224] INFO: Epoch: [143] [1150/1251] eta: 0:00:51 lr: 0.000536 loss: 3.4300 (3.3053) grad_norm: 1.4097 (1.3986) time: 0.5041 [2021-03-26 05:38:21 swin_small_patch4_window7_224] INFO: Epoch: [143] [1160/1251] eta: 0:00:46 lr: 0.000536 loss: 3.1274 (3.3048) grad_norm: 1.4337 (1.3992) time: 0.5067 [2021-03-26 05:38:26 swin_small_patch4_window7_224] INFO: Epoch: [143] [1170/1251] eta: 0:00:41 lr: 0.000536 loss: 3.3895 (3.3066) grad_norm: 1.4293 (1.3995) time: 0.5034 [2021-03-26 05:38:31 swin_small_patch4_window7_224] INFO: Epoch: [143] [1180/1251] eta: 0:00:36 lr: 0.000536 loss: 3.5173 (3.3080) grad_norm: 1.4244 (1.4000) time: 0.5075 [2021-03-26 05:38:36 swin_small_patch4_window7_224] INFO: Epoch: [143] [1190/1251] eta: 0:00:31 lr: 0.000536 loss: 3.4298 (3.3086) grad_norm: 1.3844 (1.3998) time: 0.5132 [2021-03-26 05:38:41 swin_small_patch4_window7_224] INFO: Epoch: [143] [1200/1251] eta: 0:00:26 lr: 0.000536 loss: 3.5074 (3.3106) grad_norm: 1.3586 (1.3995) time: 0.5031 [2021-03-26 05:38:46 swin_small_patch4_window7_224] INFO: Epoch: [143] [1210/1251] eta: 0:00:20 lr: 0.000536 loss: 3.4652 (3.3096) grad_norm: 1.3769 (1.3995) time: 0.5016 [2021-03-26 05:38:51 swin_small_patch4_window7_224] INFO: Epoch: [143] [1220/1251] eta: 0:00:15 lr: 0.000536 loss: 3.4511 (3.3117) grad_norm: 1.3038 (1.3990) time: 0.5088 [2021-03-26 05:38:56 swin_small_patch4_window7_224] INFO: Epoch: [143] [1230/1251] eta: 0:00:10 lr: 0.000536 loss: 3.4524 (3.3116) grad_norm: 1.3047 (1.3987) time: 0.5020 [2021-03-26 05:39:01 swin_small_patch4_window7_224] INFO: Epoch: [143] [1240/1251] eta: 0:00:05 lr: 0.000536 loss: 3.4577 (3.3130) grad_norm: 1.3693 (1.3987) time: 0.5034 [2021-03-26 05:39:07 swin_small_patch4_window7_224] INFO: Epoch: [143] [1250/1251] eta: 0:00:00 lr: 0.000536 loss: 3.4029 (3.3134) grad_norm: 1.3720 (1.3985) time: 0.5108 [2021-03-26 05:39:14 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 1.0652 (1.0652) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-26 05:39:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:23 loss: 0.8152 (0.8753) acc1: 81.2500 (79.4034) acc5: 95.3125 (95.3125) [2021-03-26 05:39:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9097 (0.9051) acc1: 78.1250 (78.9435) acc5: 93.7500 (95.0149) [2021-03-26 05:39:22 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9490 (0.9242) acc1: 78.1250 (78.3266) acc5: 93.7500 (94.9093) [2021-03-26 05:39:23 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9614 (0.9255) acc1: 76.5625 (77.9726) acc5: 93.7500 (94.6646) [2021-03-26 05:39:24 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9614 (0.9458) acc1: 76.5625 (77.4720) acc5: 93.7500 (94.4640) [2021-03-26 05:39:31 swin_small_patch4_window7_224] INFO: * Acc@1 78.194 Acc@5 94.446 loss 0.934 [2021-03-26 05:39:31 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.2% [2021-03-26 05:39:31 swin_small_patch4_window7_224] INFO: Max accuracy: 78.19% [2021-03-26 05:39:35 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 0/1251] eta: 1:28:03 lr: 0.000536 loss: 3.2537 (3.2537) grad_norm: 1.2940 (1.2940) time: 4.2233 [2021-03-26 05:39:40 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 10/1251] eta: 0:17:53 lr: 0.000536 loss: 3.3333 (3.2452) grad_norm: 1.3666 (1.3844) time: 0.8654 [2021-03-26 05:39:45 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 20/1251] eta: 0:14:12 lr: 0.000536 loss: 3.3333 (3.2151) grad_norm: 1.3406 (1.4087) time: 0.5160 [2021-03-26 05:39:51 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 30/1251] eta: 0:12:51 lr: 0.000536 loss: 3.1557 (3.1748) grad_norm: 1.3166 (1.3974) time: 0.5036 [2021-03-26 05:39:56 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 40/1251] eta: 0:12:09 lr: 0.000536 loss: 2.9204 (3.1541) grad_norm: 1.3326 (1.4055) time: 0.5082 [2021-03-26 05:40:01 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 50/1251] eta: 0:11:39 lr: 0.000536 loss: 3.3600 (3.1684) grad_norm: 1.3741 (1.4158) time: 0.5047 [2021-03-26 05:40:06 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 60/1251] eta: 0:11:18 lr: 0.000536 loss: 3.4607 (3.2530) grad_norm: 1.3890 (1.4099) time: 0.5029 [2021-03-26 05:40:11 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 70/1251] eta: 0:11:00 lr: 0.000536 loss: 3.5633 (3.2747) grad_norm: 1.3849 (1.4074) time: 0.5012 [2021-03-26 05:40:16 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 80/1251] eta: 0:10:46 lr: 0.000536 loss: 3.3572 (3.2806) grad_norm: 1.3904 (1.4071) time: 0.4990 [2021-03-26 05:40:21 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 90/1251] eta: 0:10:34 lr: 0.000536 loss: 3.0804 (3.2573) grad_norm: 1.4127 (1.4378) time: 0.5028 [2021-03-26 05:40:26 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 100/1251] eta: 0:10:25 lr: 0.000536 loss: 3.5713 (3.2993) grad_norm: 1.4127 (1.4379) time: 0.5056 [2021-03-26 05:40:31 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 110/1251] eta: 0:10:15 lr: 0.000536 loss: 3.6116 (3.3115) grad_norm: 1.4092 (1.4513) time: 0.5070 [2021-03-26 05:40:36 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 120/1251] eta: 0:10:08 lr: 0.000536 loss: 3.3171 (3.3004) grad_norm: 1.4833 (1.4591) time: 0.5108 [2021-03-26 05:40:41 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 130/1251] eta: 0:10:00 lr: 0.000536 loss: 3.3171 (3.3154) grad_norm: 1.4580 (1.4612) time: 0.5130 [2021-03-26 05:40:46 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 140/1251] eta: 0:09:53 lr: 0.000536 loss: 3.3071 (3.3042) grad_norm: 1.4445 (1.4603) time: 0.5116 [2021-03-26 05:40:51 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 150/1251] eta: 0:09:46 lr: 0.000535 loss: 3.1037 (3.2933) grad_norm: 1.4445 (1.4602) time: 0.5132 [2021-03-26 05:40:56 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 160/1251] eta: 0:09:39 lr: 0.000535 loss: 3.3664 (3.2938) grad_norm: 1.3446 (1.4505) time: 0.5090 [2021-03-26 05:41:02 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 170/1251] eta: 0:09:32 lr: 0.000535 loss: 3.2632 (3.2878) grad_norm: 1.3266 (1.4460) time: 0.5088 [2021-03-26 05:41:07 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 180/1251] eta: 0:09:26 lr: 0.000535 loss: 3.1571 (3.2732) grad_norm: 1.4247 (1.4495) time: 0.5109 [2021-03-26 05:41:12 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 190/1251] eta: 0:09:19 lr: 0.000535 loss: 3.2462 (3.2850) grad_norm: 1.3420 (1.4440) time: 0.5061 [2021-03-26 05:41:17 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 200/1251] eta: 0:09:13 lr: 0.000535 loss: 3.3749 (3.2841) grad_norm: 1.3420 (1.4426) time: 0.5076 [2021-03-26 05:41:22 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 210/1251] eta: 0:09:07 lr: 0.000535 loss: 3.2565 (3.2756) grad_norm: 1.3974 (1.4442) time: 0.5076 [2021-03-26 05:41:27 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 220/1251] eta: 0:09:00 lr: 0.000535 loss: 3.4053 (3.2862) grad_norm: 1.4483 (1.4444) time: 0.5019 [2021-03-26 05:41:32 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 230/1251] eta: 0:08:54 lr: 0.000535 loss: 3.4053 (3.2862) grad_norm: 1.4483 (1.4436) time: 0.5006 [2021-03-26 05:41:37 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 240/1251] eta: 0:08:48 lr: 0.000535 loss: 3.3189 (3.2876) grad_norm: 1.4306 (1.4425) time: 0.5017 [2021-03-26 05:41:42 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 250/1251] eta: 0:08:42 lr: 0.000535 loss: 3.4284 (3.2909) grad_norm: 1.3994 (1.4452) time: 0.5025 [2021-03-26 05:41:47 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 260/1251] eta: 0:08:36 lr: 0.000535 loss: 3.3926 (3.2896) grad_norm: 1.4398 (1.4501) time: 0.5058 [2021-03-26 05:41:52 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 270/1251] eta: 0:08:30 lr: 0.000535 loss: 3.3926 (3.2917) grad_norm: 1.4398 (1.4486) time: 0.5071 [2021-03-26 05:41:57 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 280/1251] eta: 0:08:24 lr: 0.000535 loss: 3.3093 (3.2904) grad_norm: 1.4359 (1.4491) time: 0.5001 [2021-03-26 05:42:02 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 290/1251] eta: 0:08:19 lr: 0.000535 loss: 3.1842 (3.2867) grad_norm: 1.3947 (1.4458) time: 0.5013 [2021-03-26 05:42:07 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 300/1251] eta: 0:08:13 lr: 0.000535 loss: 3.1869 (3.2917) grad_norm: 1.2923 (1.4414) time: 0.5064 [2021-03-26 05:42:12 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 310/1251] eta: 0:08:08 lr: 0.000535 loss: 3.4473 (3.2928) grad_norm: 1.3395 (1.4416) time: 0.5196 [2021-03-26 05:42:18 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 320/1251] eta: 0:08:03 lr: 0.000535 loss: 3.4473 (3.2943) grad_norm: 1.4350 (1.4408) time: 0.5193 [2021-03-26 05:42:23 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 330/1251] eta: 0:07:57 lr: 0.000535 loss: 3.4105 (3.2934) grad_norm: 1.3379 (1.4368) time: 0.5068 [2021-03-26 05:42:28 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 340/1251] eta: 0:07:52 lr: 0.000535 loss: 3.3477 (3.2988) grad_norm: 1.3354 (1.4364) time: 0.5084 [2021-03-26 05:42:33 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 350/1251] eta: 0:07:46 lr: 0.000535 loss: 3.4466 (3.3047) grad_norm: 1.4437 (1.4381) time: 0.5055 [2021-03-26 05:42:38 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 360/1251] eta: 0:07:41 lr: 0.000535 loss: 3.3695 (3.3055) grad_norm: 1.4222 (1.4371) time: 0.5050 [2021-03-26 05:42:43 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 370/1251] eta: 0:07:35 lr: 0.000535 loss: 3.2322 (3.3058) grad_norm: 1.3626 (1.4350) time: 0.5033 [2021-03-26 05:42:48 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 380/1251] eta: 0:07:30 lr: 0.000535 loss: 3.4218 (3.3087) grad_norm: 1.3256 (1.4321) time: 0.5053 [2021-03-26 05:42:53 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 390/1251] eta: 0:07:24 lr: 0.000534 loss: 3.5164 (3.3118) grad_norm: 1.3354 (1.4311) time: 0.5077 [2021-03-26 05:42:58 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 400/1251] eta: 0:07:19 lr: 0.000534 loss: 3.5182 (3.3102) grad_norm: 1.4192 (1.4312) time: 0.5027 [2021-03-26 05:43:03 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 410/1251] eta: 0:07:13 lr: 0.000534 loss: 3.5471 (3.3165) grad_norm: 1.4342 (1.4311) time: 0.5025 [2021-03-26 05:43:08 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 420/1251] eta: 0:07:08 lr: 0.000534 loss: 3.4641 (3.3150) grad_norm: 1.3655 (1.4295) time: 0.5088 [2021-03-26 05:43:13 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 430/1251] eta: 0:07:03 lr: 0.000534 loss: 3.4029 (3.3140) grad_norm: 1.3655 (1.4292) time: 0.5074 [2021-03-26 05:43:18 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 440/1251] eta: 0:06:57 lr: 0.000534 loss: 3.4281 (3.3144) grad_norm: 1.4205 (1.4293) time: 0.5033 [2021-03-26 05:43:23 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 450/1251] eta: 0:06:52 lr: 0.000534 loss: 3.3331 (3.3130) grad_norm: 1.3869 (1.4289) time: 0.5070 [2021-03-26 05:43:28 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 460/1251] eta: 0:06:47 lr: 0.000534 loss: 3.0824 (3.3095) grad_norm: 1.3928 (1.4286) time: 0.4996 [2021-03-26 05:43:33 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 470/1251] eta: 0:06:41 lr: 0.000534 loss: 3.0824 (3.3039) grad_norm: 1.4031 (1.4277) time: 0.4994 [2021-03-26 05:43:38 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 480/1251] eta: 0:06:36 lr: 0.000534 loss: 3.1388 (3.2981) grad_norm: 1.3262 (1.4254) time: 0.5034 [2021-03-26 05:43:43 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 490/1251] eta: 0:06:31 lr: 0.000534 loss: 3.3349 (3.3031) grad_norm: 1.3595 (1.4252) time: 0.5023 [2021-03-26 05:43:48 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 500/1251] eta: 0:06:25 lr: 0.000534 loss: 3.3349 (3.3003) grad_norm: 1.3801 (1.4252) time: 0.5082 [2021-03-26 05:43:54 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 510/1251] eta: 0:06:20 lr: 0.000534 loss: 3.4187 (3.3045) grad_norm: 1.3986 (1.4257) time: 0.5107 [2021-03-26 05:43:59 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 520/1251] eta: 0:06:15 lr: 0.000534 loss: 3.5505 (3.3066) grad_norm: 1.3771 (1.4249) time: 0.5096 [2021-03-26 05:44:04 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 530/1251] eta: 0:06:10 lr: 0.000534 loss: 3.5505 (3.3096) grad_norm: 1.3669 (1.4255) time: 0.5112 [2021-03-26 05:44:09 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 540/1251] eta: 0:06:05 lr: 0.000534 loss: 3.3924 (3.3113) grad_norm: 1.3780 (1.4255) time: 0.5113 [2021-03-26 05:44:14 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 550/1251] eta: 0:06:00 lr: 0.000534 loss: 3.3700 (3.3108) grad_norm: 1.3703 (1.4244) time: 0.5125 [2021-03-26 05:44:19 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 560/1251] eta: 0:05:54 lr: 0.000534 loss: 3.3867 (3.3153) grad_norm: 1.3442 (1.4232) time: 0.5161 [2021-03-26 05:44:24 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 570/1251] eta: 0:05:49 lr: 0.000534 loss: 3.4782 (3.3181) grad_norm: 1.3318 (1.4222) time: 0.5089 [2021-03-26 05:44:29 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 580/1251] eta: 0:05:44 lr: 0.000534 loss: 3.4066 (3.3193) grad_norm: 1.3206 (1.4202) time: 0.4993 [2021-03-26 05:44:34 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 590/1251] eta: 0:05:39 lr: 0.000534 loss: 3.3989 (3.3188) grad_norm: 1.2843 (1.4185) time: 0.5036 [2021-03-26 05:44:39 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 600/1251] eta: 0:05:33 lr: 0.000534 loss: 3.4121 (3.3191) grad_norm: 1.3493 (1.4190) time: 0.5031 [2021-03-26 05:44:44 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 610/1251] eta: 0:05:28 lr: 0.000534 loss: 3.1021 (3.3130) grad_norm: 1.4480 (1.4184) time: 0.5033 [2021-03-26 05:44:49 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 620/1251] eta: 0:05:23 lr: 0.000534 loss: 3.0300 (3.3113) grad_norm: 1.3344 (1.4180) time: 0.5099 [2021-03-26 05:44:55 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 630/1251] eta: 0:05:18 lr: 0.000533 loss: 3.4484 (3.3157) grad_norm: 1.3344 (1.4172) time: 0.5072 [2021-03-26 05:45:00 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 640/1251] eta: 0:05:13 lr: 0.000533 loss: 3.4484 (3.3108) grad_norm: 1.3890 (1.4168) time: 0.5075 [2021-03-26 05:45:05 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 650/1251] eta: 0:05:07 lr: 0.000533 loss: 3.2765 (3.3113) grad_norm: 1.3752 (1.4159) time: 0.5066 [2021-03-26 05:45:10 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 660/1251] eta: 0:05:02 lr: 0.000533 loss: 3.3265 (3.3093) grad_norm: 1.3752 (1.4174) time: 0.5009 [2021-03-26 05:45:15 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 670/1251] eta: 0:04:57 lr: 0.000533 loss: 3.3813 (3.3096) grad_norm: 1.4719 (1.4183) time: 0.5023 [2021-03-26 05:45:20 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 680/1251] eta: 0:04:52 lr: 0.000533 loss: 3.1556 (3.3045) grad_norm: 1.4054 (1.4178) time: 0.4999 [2021-03-26 05:45:25 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 690/1251] eta: 0:04:47 lr: 0.000533 loss: 3.3356 (3.3072) grad_norm: 1.3500 (1.4172) time: 0.4987 [2021-03-26 05:45:30 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 700/1251] eta: 0:04:41 lr: 0.000533 loss: 3.3248 (3.3058) grad_norm: 1.3515 (1.4166) time: 0.5000 [2021-03-26 05:45:35 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 710/1251] eta: 0:04:36 lr: 0.000533 loss: 3.1817 (3.3062) grad_norm: 1.3515 (1.4164) time: 0.5040 [2021-03-26 05:45:40 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 720/1251] eta: 0:04:31 lr: 0.000533 loss: 3.1817 (3.3050) grad_norm: 1.3896 (1.4171) time: 0.5175 [2021-03-26 05:45:45 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 730/1251] eta: 0:04:26 lr: 0.000533 loss: 3.3944 (3.3039) grad_norm: 1.4489 (1.4175) time: 0.5267 [2021-03-26 05:45:51 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 740/1251] eta: 0:04:21 lr: 0.000533 loss: 3.2435 (3.3023) grad_norm: 1.4150 (1.4176) time: 0.5255 [2021-03-26 05:45:56 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 750/1251] eta: 0:04:16 lr: 0.000533 loss: 3.2435 (3.3034) grad_norm: 1.3863 (1.4166) time: 0.5153 [2021-03-26 05:46:01 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 760/1251] eta: 0:04:11 lr: 0.000533 loss: 3.5006 (3.3056) grad_norm: 1.3949 (1.4171) time: 0.5144 [2021-03-26 05:46:06 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 770/1251] eta: 0:04:06 lr: 0.000533 loss: 3.5246 (3.3073) grad_norm: 1.3961 (1.4160) time: 0.5092 [2021-03-26 05:46:11 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 780/1251] eta: 0:04:01 lr: 0.000533 loss: 3.4038 (3.3070) grad_norm: 1.3389 (1.4169) time: 0.4993 [2021-03-26 05:46:16 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 790/1251] eta: 0:03:55 lr: 0.000533 loss: 3.4038 (3.3091) grad_norm: 1.3572 (1.4166) time: 0.5067 [2021-03-26 05:46:21 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 800/1251] eta: 0:03:50 lr: 0.000533 loss: 3.5460 (3.3136) grad_norm: 1.3453 (1.4157) time: 0.5120 [2021-03-26 05:46:26 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 810/1251] eta: 0:03:45 lr: 0.000533 loss: 3.4114 (3.3119) grad_norm: 1.3335 (1.4144) time: 0.5049 [2021-03-26 05:46:31 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 820/1251] eta: 0:03:40 lr: 0.000533 loss: 3.3473 (3.3122) grad_norm: 1.3021 (1.4140) time: 0.5058 [2021-03-26 05:46:36 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 830/1251] eta: 0:03:35 lr: 0.000533 loss: 3.4650 (3.3127) grad_norm: 1.3376 (1.4136) time: 0.5055 [2021-03-26 05:46:41 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 840/1251] eta: 0:03:30 lr: 0.000533 loss: 3.4216 (3.3124) grad_norm: 1.3376 (1.4134) time: 0.4995 [2021-03-26 05:46:46 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 850/1251] eta: 0:03:25 lr: 0.000533 loss: 3.3843 (3.3117) grad_norm: 1.4535 (1.4149) time: 0.5094 [2021-03-26 05:46:51 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 860/1251] eta: 0:03:19 lr: 0.000533 loss: 3.4140 (3.3135) grad_norm: 1.4896 (1.4159) time: 0.5097 [2021-03-26 05:46:56 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 870/1251] eta: 0:03:14 lr: 0.000532 loss: 3.5096 (3.3147) grad_norm: 1.4478 (1.4157) time: 0.5034 [2021-03-26 05:47:01 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 880/1251] eta: 0:03:09 lr: 0.000532 loss: 3.3151 (3.3123) grad_norm: 1.4478 (1.4169) time: 0.5051 [2021-03-26 05:47:06 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 890/1251] eta: 0:03:04 lr: 0.000532 loss: 3.4791 (3.3137) grad_norm: 1.4437 (1.4169) time: 0.5002 [2021-03-26 05:47:11 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 900/1251] eta: 0:02:59 lr: 0.000532 loss: 3.5112 (3.3150) grad_norm: 1.3205 (1.4153) time: 0.4994 [2021-03-26 05:47:17 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 910/1251] eta: 0:02:54 lr: 0.000532 loss: 3.3423 (3.3150) grad_norm: 1.3323 (1.4157) time: 0.5107 [2021-03-26 05:47:22 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 920/1251] eta: 0:02:49 lr: 0.000532 loss: 3.4942 (3.3168) grad_norm: 1.4290 (1.4160) time: 0.5146 [2021-03-26 05:47:27 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 930/1251] eta: 0:02:44 lr: 0.000532 loss: 3.5687 (3.3180) grad_norm: 1.4620 (1.4176) time: 0.5093 [2021-03-26 05:47:32 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 940/1251] eta: 0:02:38 lr: 0.000532 loss: 3.3739 (3.3186) grad_norm: 1.4110 (1.4177) time: 0.5121 [2021-03-26 05:47:37 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 950/1251] eta: 0:02:33 lr: 0.000532 loss: 3.3744 (3.3193) grad_norm: 1.3806 (1.4175) time: 0.5104 [2021-03-26 05:47:42 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 960/1251] eta: 0:02:28 lr: 0.000532 loss: 3.3215 (3.3162) grad_norm: 1.3789 (1.4172) time: 0.5056 [2021-03-26 05:47:47 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 970/1251] eta: 0:02:23 lr: 0.000532 loss: 3.1847 (3.3153) grad_norm: 1.3528 (1.4172) time: 0.5007 [2021-03-26 05:47:52 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 980/1251] eta: 0:02:18 lr: 0.000532 loss: 3.1778 (3.3141) grad_norm: 1.3361 (1.4169) time: 0.5009 [2021-03-26 05:47:57 swin_small_patch4_window7_224] INFO: Epoch: [144] [ 990/1251] eta: 0:02:13 lr: 0.000532 loss: 3.1636 (3.3123) grad_norm: 1.4007 (1.4174) time: 0.5026 [2021-03-26 05:48:02 swin_small_patch4_window7_224] INFO: Epoch: [144] [1000/1251] eta: 0:02:08 lr: 0.000532 loss: 3.1951 (3.3122) grad_norm: 1.4615 (1.4182) time: 0.5029 [2021-03-26 05:48:07 swin_small_patch4_window7_224] INFO: Epoch: [144] [1010/1251] eta: 0:02:03 lr: 0.000532 loss: 3.3419 (3.3125) grad_norm: 1.4462 (1.4183) time: 0.5022 [2021-03-26 05:48:12 swin_small_patch4_window7_224] INFO: Epoch: [144] [1020/1251] eta: 0:01:57 lr: 0.000532 loss: 3.1504 (3.3088) grad_norm: 1.3785 (1.4177) time: 0.4959 [2021-03-26 05:48:17 swin_small_patch4_window7_224] INFO: Epoch: [144] [1030/1251] eta: 0:01:52 lr: 0.000532 loss: 3.1504 (3.3097) grad_norm: 1.3056 (1.4175) time: 0.4990 [2021-03-26 05:48:22 swin_small_patch4_window7_224] INFO: Epoch: [144] [1040/1251] eta: 0:01:47 lr: 0.000532 loss: 3.3433 (3.3084) grad_norm: 1.4234 (1.4178) time: 0.5022 [2021-03-26 05:48:27 swin_small_patch4_window7_224] INFO: Epoch: [144] [1050/1251] eta: 0:01:42 lr: 0.000532 loss: 3.4609 (3.3100) grad_norm: 1.4600 (1.4180) time: 0.5106 [2021-03-26 05:48:33 swin_small_patch4_window7_224] INFO: Epoch: [144] [1060/1251] eta: 0:01:37 lr: 0.000532 loss: 3.5262 (3.3131) grad_norm: 1.4600 (1.4181) time: 0.5231 [2021-03-26 05:48:38 swin_small_patch4_window7_224] INFO: Epoch: [144] [1070/1251] eta: 0:01:32 lr: 0.000532 loss: 3.5397 (3.3147) grad_norm: 1.4348 (1.4189) time: 0.5141 [2021-03-26 05:48:43 swin_small_patch4_window7_224] INFO: Epoch: [144] [1080/1251] eta: 0:01:27 lr: 0.000532 loss: 3.3805 (3.3159) grad_norm: 1.4348 (1.4194) time: 0.5057 [2021-03-26 05:48:48 swin_small_patch4_window7_224] INFO: Epoch: [144] [1090/1251] eta: 0:01:22 lr: 0.000532 loss: 3.4691 (3.3168) grad_norm: 1.4031 (1.4190) time: 0.5063 [2021-03-26 05:48:53 swin_small_patch4_window7_224] INFO: Epoch: [144] [1100/1251] eta: 0:01:17 lr: 0.000532 loss: 3.2049 (3.3149) grad_norm: 1.3437 (1.4185) time: 0.5035 [2021-03-26 05:48:58 swin_small_patch4_window7_224] INFO: Epoch: [144] [1110/1251] eta: 0:01:11 lr: 0.000531 loss: 3.3177 (3.3143) grad_norm: 1.3249 (1.4185) time: 0.5031 [2021-03-26 05:49:03 swin_small_patch4_window7_224] INFO: Epoch: [144] [1120/1251] eta: 0:01:06 lr: 0.000531 loss: 3.3619 (3.3128) grad_norm: 1.3249 (1.4180) time: 0.5027 [2021-03-26 05:49:08 swin_small_patch4_window7_224] INFO: Epoch: [144] [1130/1251] eta: 0:01:01 lr: 0.000531 loss: 3.1681 (3.3136) grad_norm: 1.3665 (1.4183) time: 0.5029 [2021-03-26 05:49:13 swin_small_patch4_window7_224] INFO: Epoch: [144] [1140/1251] eta: 0:00:56 lr: 0.000531 loss: 3.3730 (3.3143) grad_norm: 1.3969 (1.4184) time: 0.5020 [2021-03-26 05:49:18 swin_small_patch4_window7_224] INFO: Epoch: [144] [1150/1251] eta: 0:00:51 lr: 0.000531 loss: 3.3730 (3.3137) grad_norm: 1.3678 (1.4176) time: 0.5049 [2021-03-26 05:49:23 swin_small_patch4_window7_224] INFO: Epoch: [144] [1160/1251] eta: 0:00:46 lr: 0.000531 loss: 3.6103 (3.3164) grad_norm: 1.4665 (1.4181) time: 0.5089 [2021-03-26 05:49:28 swin_small_patch4_window7_224] INFO: Epoch: [144] [1170/1251] eta: 0:00:41 lr: 0.000531 loss: 3.5792 (3.3161) grad_norm: 1.3581 (1.4176) time: 0.5098 [2021-03-26 05:49:33 swin_small_patch4_window7_224] INFO: Epoch: [144] [1180/1251] eta: 0:00:36 lr: 0.000531 loss: 3.4463 (3.3172) grad_norm: 1.3581 (1.4176) time: 0.5077 [2021-03-26 05:49:38 swin_small_patch4_window7_224] INFO: Epoch: [144] [1190/1251] eta: 0:00:31 lr: 0.000531 loss: 3.5748 (3.3202) grad_norm: 1.4400 (1.4179) time: 0.5018 [2021-03-26 05:49:43 swin_small_patch4_window7_224] INFO: Epoch: [144] [1200/1251] eta: 0:00:25 lr: 0.000531 loss: 3.5475 (3.3199) grad_norm: 1.4290 (1.4178) time: 0.5021 [2021-03-26 05:49:48 swin_small_patch4_window7_224] INFO: Epoch: [144] [1210/1251] eta: 0:00:20 lr: 0.000531 loss: 3.3918 (3.3204) grad_norm: 1.4091 (1.4181) time: 0.5062 [2021-03-26 05:49:53 swin_small_patch4_window7_224] INFO: Epoch: [144] [1220/1251] eta: 0:00:15 lr: 0.000531 loss: 3.3918 (3.3209) grad_norm: 1.3726 (1.4184) time: 0.5090 [2021-03-26 05:49:58 swin_small_patch4_window7_224] INFO: Epoch: [144] [1230/1251] eta: 0:00:10 lr: 0.000531 loss: 3.1301 (3.3201) grad_norm: 1.4846 (1.4191) time: 0.5057 [2021-03-26 05:50:03 swin_small_patch4_window7_224] INFO: Epoch: [144] [1240/1251] eta: 0:00:05 lr: 0.000531 loss: 3.1206 (3.3205) grad_norm: 1.3933 (1.4186) time: 0.4990 [2021-03-26 05:50:08 swin_small_patch4_window7_224] INFO: Epoch: [144] [1250/1251] eta: 0:00:00 lr: 0.000531 loss: 3.2632 (3.3194) grad_norm: 1.3395 (1.4181) time: 0.4943 [2021-03-26 05:50:15 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:01 loss: 1.2252 (1.2252) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.7500) [2021-03-26 05:50:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.9657 (0.9585) acc1: 76.5625 (77.4148) acc5: 95.3125 (95.1705) [2021-03-26 05:50:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9264 (0.9388) acc1: 78.1250 (77.5298) acc5: 95.3125 (95.0149) [2021-03-26 05:50:22 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9494 (0.9544) acc1: 76.5625 (77.3690) acc5: 93.7500 (94.7581) [2021-03-26 05:50:24 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9494 (0.9454) acc1: 76.5625 (77.6677) acc5: 93.7500 (94.7027) [2021-03-26 05:50:25 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9127 (0.9480) acc1: 78.1250 (77.6320) acc5: 93.7500 (94.7200) [2021-03-26 05:50:31 swin_small_patch4_window7_224] INFO: * Acc@1 78.150 Acc@5 94.424 loss 0.935 [2021-03-26 05:50:31 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.2% [2021-03-26 05:50:31 swin_small_patch4_window7_224] INFO: Max accuracy: 78.19% [2021-03-26 05:50:35 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 0/1251] eta: 1:25:45 lr: 0.000531 loss: 2.5620 (2.5620) grad_norm: 1.5340 (1.5340) time: 4.1129 [2021-03-26 05:50:40 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 10/1251] eta: 0:17:36 lr: 0.000531 loss: 3.3646 (3.2415) grad_norm: 1.4655 (1.4751) time: 0.8512 [2021-03-26 05:50:45 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 20/1251] eta: 0:14:04 lr: 0.000531 loss: 3.3646 (3.3029) grad_norm: 1.4404 (1.4785) time: 0.5151 [2021-03-26 05:50:50 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 30/1251] eta: 0:12:48 lr: 0.000531 loss: 3.3545 (3.2316) grad_norm: 1.3761 (1.4594) time: 0.5069 [2021-03-26 05:50:56 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 40/1251] eta: 0:12:11 lr: 0.000531 loss: 3.2149 (3.2191) grad_norm: 1.3865 (1.4460) time: 0.5176 [2021-03-26 05:51:01 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 50/1251] eta: 0:11:42 lr: 0.000531 loss: 3.2046 (3.2411) grad_norm: 1.3685 (1.4468) time: 0.5174 [2021-03-26 05:51:06 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 60/1251] eta: 0:11:20 lr: 0.000531 loss: 3.1514 (3.2144) grad_norm: 1.3909 (1.4356) time: 0.5052 [2021-03-26 05:51:11 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 70/1251] eta: 0:11:03 lr: 0.000531 loss: 3.4115 (3.2534) grad_norm: 1.3978 (1.4303) time: 0.5026 [2021-03-26 05:51:16 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 80/1251] eta: 0:10:51 lr: 0.000531 loss: 3.5569 (3.2620) grad_norm: 1.3623 (1.4385) time: 0.5089 [2021-03-26 05:51:21 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 90/1251] eta: 0:10:39 lr: 0.000531 loss: 3.5011 (3.2755) grad_norm: 1.3405 (1.4285) time: 0.5122 [2021-03-26 05:51:26 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 100/1251] eta: 0:10:28 lr: 0.000530 loss: 3.4115 (3.2726) grad_norm: 1.3736 (1.4325) time: 0.5072 [2021-03-26 05:51:31 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 110/1251] eta: 0:10:20 lr: 0.000530 loss: 3.3828 (3.2771) grad_norm: 1.3459 (1.4227) time: 0.5120 [2021-03-26 05:51:36 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 120/1251] eta: 0:10:11 lr: 0.000530 loss: 3.4909 (3.2944) grad_norm: 1.3079 (1.4156) time: 0.5107 [2021-03-26 05:51:41 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 130/1251] eta: 0:10:02 lr: 0.000530 loss: 3.5224 (3.3010) grad_norm: 1.3467 (1.4103) time: 0.5021 [2021-03-26 05:51:46 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 140/1251] eta: 0:09:54 lr: 0.000530 loss: 3.4450 (3.3052) grad_norm: 1.3505 (1.4127) time: 0.5027 [2021-03-26 05:51:51 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 150/1251] eta: 0:09:47 lr: 0.000530 loss: 3.6197 (3.3272) grad_norm: 1.4021 (1.4122) time: 0.5061 [2021-03-26 05:51:57 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 160/1251] eta: 0:09:40 lr: 0.000530 loss: 3.6197 (3.3313) grad_norm: 1.4368 (1.4152) time: 0.5108 [2021-03-26 05:52:02 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 170/1251] eta: 0:09:33 lr: 0.000530 loss: 3.5030 (3.3412) grad_norm: 1.4368 (1.4218) time: 0.5101 [2021-03-26 05:52:07 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 180/1251] eta: 0:09:26 lr: 0.000530 loss: 3.4666 (3.3400) grad_norm: 1.3626 (1.4189) time: 0.5014 [2021-03-26 05:52:12 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 190/1251] eta: 0:09:19 lr: 0.000530 loss: 3.4109 (3.3307) grad_norm: 1.3317 (1.4136) time: 0.4948 [2021-03-26 05:52:17 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 200/1251] eta: 0:09:12 lr: 0.000530 loss: 3.4109 (3.3290) grad_norm: 1.3660 (1.4169) time: 0.4981 [2021-03-26 05:52:22 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 210/1251] eta: 0:09:06 lr: 0.000530 loss: 3.3838 (3.3372) grad_norm: 1.4193 (1.4158) time: 0.5046 [2021-03-26 05:52:27 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 220/1251] eta: 0:09:00 lr: 0.000530 loss: 3.3838 (3.3275) grad_norm: 1.3024 (1.4126) time: 0.5080 [2021-03-26 05:52:32 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 230/1251] eta: 0:08:54 lr: 0.000530 loss: 3.3713 (3.3339) grad_norm: 1.3432 (1.4127) time: 0.5065 [2021-03-26 05:52:37 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 240/1251] eta: 0:08:48 lr: 0.000530 loss: 3.3713 (3.3333) grad_norm: 1.3628 (1.4105) time: 0.5046 [2021-03-26 05:52:42 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 250/1251] eta: 0:08:42 lr: 0.000530 loss: 3.2424 (3.3255) grad_norm: 1.3543 (1.4084) time: 0.5058 [2021-03-26 05:52:47 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 260/1251] eta: 0:08:37 lr: 0.000530 loss: 3.2905 (3.3210) grad_norm: 1.3383 (1.4078) time: 0.5127 [2021-03-26 05:52:52 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 270/1251] eta: 0:08:31 lr: 0.000530 loss: 3.4694 (3.3247) grad_norm: 1.3906 (1.4108) time: 0.5128 [2021-03-26 05:52:57 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 280/1251] eta: 0:08:25 lr: 0.000530 loss: 3.4807 (3.3334) grad_norm: 1.3495 (1.4083) time: 0.5043 [2021-03-26 05:53:02 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 290/1251] eta: 0:08:19 lr: 0.000530 loss: 3.4807 (3.3325) grad_norm: 1.3187 (1.4073) time: 0.5017 [2021-03-26 05:53:07 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 300/1251] eta: 0:08:14 lr: 0.000530 loss: 3.5942 (3.3445) grad_norm: 1.3488 (1.4061) time: 0.5051 [2021-03-26 05:53:12 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 310/1251] eta: 0:08:08 lr: 0.000530 loss: 3.5547 (3.3326) grad_norm: 1.3513 (1.4059) time: 0.5110 [2021-03-26 05:53:17 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 320/1251] eta: 0:08:02 lr: 0.000530 loss: 3.3042 (3.3289) grad_norm: 1.3943 (1.4113) time: 0.5062 [2021-03-26 05:53:22 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 330/1251] eta: 0:07:57 lr: 0.000530 loss: 3.3583 (3.3300) grad_norm: 1.4388 (1.4115) time: 0.5059 [2021-03-26 05:53:27 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 340/1251] eta: 0:07:51 lr: 0.000529 loss: 3.3514 (3.3264) grad_norm: 1.4147 (1.4136) time: 0.5055 [2021-03-26 05:53:33 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 350/1251] eta: 0:07:46 lr: 0.000529 loss: 3.3504 (3.3287) grad_norm: 1.3687 (1.4141) time: 0.5004 [2021-03-26 05:53:38 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 360/1251] eta: 0:07:40 lr: 0.000529 loss: 3.3504 (3.3250) grad_norm: 1.4312 (1.4155) time: 0.5052 [2021-03-26 05:53:43 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 370/1251] eta: 0:07:35 lr: 0.000529 loss: 3.3756 (3.3272) grad_norm: 1.4312 (1.4179) time: 0.5063 [2021-03-26 05:53:48 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 380/1251] eta: 0:07:30 lr: 0.000529 loss: 3.4131 (3.3287) grad_norm: 1.4547 (1.4188) time: 0.5078 [2021-03-26 05:53:53 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 390/1251] eta: 0:07:24 lr: 0.000529 loss: 3.4147 (3.3343) grad_norm: 1.3721 (1.4175) time: 0.5107 [2021-03-26 05:53:58 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 400/1251] eta: 0:07:19 lr: 0.000529 loss: 3.5536 (3.3351) grad_norm: 1.3117 (1.4179) time: 0.5052 [2021-03-26 05:54:03 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 410/1251] eta: 0:07:13 lr: 0.000529 loss: 3.3825 (3.3324) grad_norm: 1.3064 (1.4153) time: 0.5012 [2021-03-26 05:54:08 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 420/1251] eta: 0:07:08 lr: 0.000529 loss: 3.2257 (3.3310) grad_norm: 1.3424 (1.4143) time: 0.5039 [2021-03-26 05:54:13 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 430/1251] eta: 0:07:03 lr: 0.000529 loss: 3.4279 (3.3341) grad_norm: 1.3498 (1.4142) time: 0.5103 [2021-03-26 05:54:18 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 440/1251] eta: 0:06:58 lr: 0.000529 loss: 3.2971 (3.3280) grad_norm: 1.3510 (1.4129) time: 0.5143 [2021-03-26 05:54:23 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 450/1251] eta: 0:06:52 lr: 0.000529 loss: 3.1543 (3.3224) grad_norm: 1.3510 (1.4128) time: 0.5096 [2021-03-26 05:54:28 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 460/1251] eta: 0:06:47 lr: 0.000529 loss: 3.3503 (3.3210) grad_norm: 1.3401 (1.4138) time: 0.5046 [2021-03-26 05:54:33 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 470/1251] eta: 0:06:42 lr: 0.000529 loss: 3.3728 (3.3202) grad_norm: 1.3412 (1.4134) time: 0.5048 [2021-03-26 05:54:38 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 480/1251] eta: 0:06:36 lr: 0.000529 loss: 3.3952 (3.3166) grad_norm: 1.3398 (1.4123) time: 0.5047 [2021-03-26 05:54:44 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 490/1251] eta: 0:06:31 lr: 0.000529 loss: 3.1831 (3.3131) grad_norm: 1.3894 (1.4131) time: 0.5058 [2021-03-26 05:54:48 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 500/1251] eta: 0:06:26 lr: 0.000529 loss: 3.1831 (3.3121) grad_norm: 1.3926 (1.4121) time: 0.5015 [2021-03-26 05:54:53 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 510/1251] eta: 0:06:20 lr: 0.000529 loss: 3.3744 (3.3097) grad_norm: 1.3671 (1.4116) time: 0.4986 [2021-03-26 05:54:59 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 520/1251] eta: 0:06:15 lr: 0.000529 loss: 3.4325 (3.3133) grad_norm: 1.3379 (1.4108) time: 0.5054 [2021-03-26 05:55:04 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 530/1251] eta: 0:06:10 lr: 0.000529 loss: 3.6098 (3.3217) grad_norm: 1.3398 (1.4103) time: 0.5059 [2021-03-26 05:55:09 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 540/1251] eta: 0:06:05 lr: 0.000529 loss: 3.5407 (3.3218) grad_norm: 1.4025 (1.4103) time: 0.5071 [2021-03-26 05:55:14 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 550/1251] eta: 0:06:00 lr: 0.000529 loss: 3.3954 (3.3221) grad_norm: 1.3973 (1.4101) time: 0.5168 [2021-03-26 05:55:19 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 560/1251] eta: 0:05:54 lr: 0.000529 loss: 3.3017 (3.3175) grad_norm: 1.3807 (1.4105) time: 0.5153 [2021-03-26 05:55:24 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 570/1251] eta: 0:05:49 lr: 0.000529 loss: 3.3652 (3.3208) grad_norm: 1.4016 (1.4109) time: 0.5048 [2021-03-26 05:55:29 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 580/1251] eta: 0:05:44 lr: 0.000529 loss: 3.3652 (3.3176) grad_norm: 1.3635 (1.4101) time: 0.5007 [2021-03-26 05:55:34 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 590/1251] eta: 0:05:39 lr: 0.000528 loss: 3.2493 (3.3165) grad_norm: 1.3346 (1.4092) time: 0.5034 [2021-03-26 05:55:39 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 600/1251] eta: 0:05:33 lr: 0.000528 loss: 3.4728 (3.3202) grad_norm: 1.4088 (1.4096) time: 0.5057 [2021-03-26 05:55:44 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 610/1251] eta: 0:05:28 lr: 0.000528 loss: 3.4728 (3.3214) grad_norm: 1.4217 (1.4091) time: 0.5058 [2021-03-26 05:55:49 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 620/1251] eta: 0:05:23 lr: 0.000528 loss: 3.3602 (3.3201) grad_norm: 1.3506 (1.4081) time: 0.5029 [2021-03-26 05:55:54 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 630/1251] eta: 0:05:18 lr: 0.000528 loss: 3.3692 (3.3221) grad_norm: 1.3100 (1.4073) time: 0.4992 [2021-03-26 05:55:59 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 640/1251] eta: 0:05:13 lr: 0.000528 loss: 3.5245 (3.3212) grad_norm: 1.3100 (1.4062) time: 0.5087 [2021-03-26 05:56:04 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 650/1251] eta: 0:05:07 lr: 0.000528 loss: 3.3343 (3.3232) grad_norm: 1.3236 (1.4049) time: 0.5086 [2021-03-26 05:56:09 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 660/1251] eta: 0:05:02 lr: 0.000528 loss: 3.4151 (3.3234) grad_norm: 1.3416 (1.4043) time: 0.5036 [2021-03-26 05:56:15 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 670/1251] eta: 0:04:57 lr: 0.000528 loss: 3.4151 (3.3213) grad_norm: 1.3350 (1.4034) time: 0.5054 [2021-03-26 05:56:20 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 680/1251] eta: 0:04:52 lr: 0.000528 loss: 3.1734 (3.3197) grad_norm: 1.3297 (1.4024) time: 0.5064 [2021-03-26 05:56:25 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 690/1251] eta: 0:04:47 lr: 0.000528 loss: 3.3549 (3.3234) grad_norm: 1.3918 (1.4033) time: 0.5094 [2021-03-26 05:56:30 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 700/1251] eta: 0:04:41 lr: 0.000528 loss: 3.3549 (3.3214) grad_norm: 1.4283 (1.4030) time: 0.5050 [2021-03-26 05:56:35 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 710/1251] eta: 0:04:36 lr: 0.000528 loss: 3.3520 (3.3203) grad_norm: 1.4341 (1.4048) time: 0.5055 [2021-03-26 05:56:40 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 720/1251] eta: 0:04:31 lr: 0.000528 loss: 3.3981 (3.3189) grad_norm: 1.4128 (1.4043) time: 0.5048 [2021-03-26 05:56:45 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 730/1251] eta: 0:04:26 lr: 0.000528 loss: 3.2921 (3.3176) grad_norm: 1.4011 (1.4056) time: 0.4994 [2021-03-26 05:56:50 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 740/1251] eta: 0:04:21 lr: 0.000528 loss: 3.0377 (3.3159) grad_norm: 1.4726 (1.4064) time: 0.5168 [2021-03-26 05:56:55 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 750/1251] eta: 0:04:16 lr: 0.000528 loss: 3.4919 (3.3176) grad_norm: 1.3912 (1.4065) time: 0.5161 [2021-03-26 05:57:00 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 760/1251] eta: 0:04:11 lr: 0.000528 loss: 3.4919 (3.3162) grad_norm: 1.4367 (1.4075) time: 0.4995 [2021-03-26 05:57:05 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 770/1251] eta: 0:04:05 lr: 0.000528 loss: 3.3589 (3.3165) grad_norm: 1.4583 (1.4095) time: 0.4991 [2021-03-26 05:57:10 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 780/1251] eta: 0:04:00 lr: 0.000528 loss: 3.5044 (3.3210) grad_norm: 1.4583 (1.4094) time: 0.4971 [2021-03-26 05:57:15 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 790/1251] eta: 0:03:55 lr: 0.000528 loss: 3.3166 (3.3194) grad_norm: 1.3699 (1.4096) time: 0.5106 [2021-03-26 05:57:20 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 800/1251] eta: 0:03:50 lr: 0.000528 loss: 3.3166 (3.3201) grad_norm: 1.3476 (1.4094) time: 0.5113 [2021-03-26 05:57:25 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 810/1251] eta: 0:03:45 lr: 0.000528 loss: 3.3785 (3.3220) grad_norm: 1.3206 (1.4087) time: 0.5052 [2021-03-26 05:57:31 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 820/1251] eta: 0:03:40 lr: 0.000528 loss: 3.2631 (3.3193) grad_norm: 1.3235 (1.4080) time: 0.5102 [2021-03-26 05:57:36 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 830/1251] eta: 0:03:35 lr: 0.000527 loss: 3.2412 (3.3187) grad_norm: 1.3551 (1.4085) time: 0.5112 [2021-03-26 05:57:41 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 840/1251] eta: 0:03:30 lr: 0.000527 loss: 3.4606 (3.3194) grad_norm: 1.3633 (1.4086) time: 0.5105 [2021-03-26 05:57:46 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 850/1251] eta: 0:03:24 lr: 0.000527 loss: 3.4606 (3.3199) grad_norm: 1.3964 (1.4083) time: 0.5124 [2021-03-26 05:57:51 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 860/1251] eta: 0:03:19 lr: 0.000527 loss: 3.3245 (3.3177) grad_norm: 1.4274 (1.4090) time: 0.5089 [2021-03-26 05:57:56 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 870/1251] eta: 0:03:14 lr: 0.000527 loss: 3.0161 (3.3154) grad_norm: 1.4069 (1.4085) time: 0.4996 [2021-03-26 05:58:01 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 880/1251] eta: 0:03:09 lr: 0.000527 loss: 3.3047 (3.3169) grad_norm: 1.3295 (1.4071) time: 0.4991 [2021-03-26 05:58:06 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 890/1251] eta: 0:03:04 lr: 0.000527 loss: 3.3289 (3.3161) grad_norm: 1.2944 (1.4060) time: 0.4979 [2021-03-26 05:58:11 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 900/1251] eta: 0:02:59 lr: 0.000527 loss: 3.4125 (3.3172) grad_norm: 1.3370 (1.4055) time: 0.4984 [2021-03-26 05:58:16 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 910/1251] eta: 0:02:54 lr: 0.000527 loss: 3.4125 (3.3177) grad_norm: 1.3830 (1.4053) time: 0.5016 [2021-03-26 05:58:21 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 920/1251] eta: 0:02:48 lr: 0.000527 loss: 3.3853 (3.3185) grad_norm: 1.4116 (1.4063) time: 0.5018 [2021-03-26 05:58:26 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 930/1251] eta: 0:02:43 lr: 0.000527 loss: 3.3824 (3.3174) grad_norm: 1.4621 (1.4066) time: 0.4992 [2021-03-26 05:58:31 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 940/1251] eta: 0:02:38 lr: 0.000527 loss: 3.3824 (3.3172) grad_norm: 1.3838 (1.4067) time: 0.4990 [2021-03-26 05:58:36 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 950/1251] eta: 0:02:33 lr: 0.000527 loss: 3.4450 (3.3176) grad_norm: 1.3642 (1.4067) time: 0.5016 [2021-03-26 05:58:41 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 960/1251] eta: 0:02:28 lr: 0.000527 loss: 3.3109 (3.3159) grad_norm: 1.4171 (1.4076) time: 0.5010 [2021-03-26 05:58:46 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 970/1251] eta: 0:02:23 lr: 0.000527 loss: 3.3697 (3.3158) grad_norm: 1.4361 (1.4085) time: 0.5013 [2021-03-26 05:58:51 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 980/1251] eta: 0:02:18 lr: 0.000527 loss: 3.3697 (3.3162) grad_norm: 1.4137 (1.4086) time: 0.5019 [2021-03-26 05:58:56 swin_small_patch4_window7_224] INFO: Epoch: [145] [ 990/1251] eta: 0:02:13 lr: 0.000527 loss: 3.3662 (3.3153) grad_norm: 1.3445 (1.4079) time: 0.5091 [2021-03-26 05:59:01 swin_small_patch4_window7_224] INFO: Epoch: [145] [1000/1251] eta: 0:02:07 lr: 0.000527 loss: 3.4098 (3.3159) grad_norm: 1.3817 (1.4084) time: 0.5142 [2021-03-26 05:59:06 swin_small_patch4_window7_224] INFO: Epoch: [145] [1010/1251] eta: 0:02:02 lr: 0.000527 loss: 3.4742 (3.3158) grad_norm: 1.3924 (1.4081) time: 0.5107 [2021-03-26 05:59:11 swin_small_patch4_window7_224] INFO: Epoch: [145] [1020/1251] eta: 0:01:57 lr: 0.000527 loss: 3.3194 (3.3134) grad_norm: 1.3421 (1.4084) time: 0.5110 [2021-03-26 05:59:16 swin_small_patch4_window7_224] INFO: Epoch: [145] [1030/1251] eta: 0:01:52 lr: 0.000527 loss: 3.2368 (3.3126) grad_norm: 1.3365 (1.4078) time: 0.5055 [2021-03-26 05:59:22 swin_small_patch4_window7_224] INFO: Epoch: [145] [1040/1251] eta: 0:01:47 lr: 0.000527 loss: 3.2199 (3.3125) grad_norm: 1.3119 (1.4068) time: 0.5045 [2021-03-26 05:59:27 swin_small_patch4_window7_224] INFO: Epoch: [145] [1050/1251] eta: 0:01:42 lr: 0.000527 loss: 3.2129 (3.3100) grad_norm: 1.3563 (1.4070) time: 0.5149 [2021-03-26 05:59:32 swin_small_patch4_window7_224] INFO: Epoch: [145] [1060/1251] eta: 0:01:37 lr: 0.000527 loss: 3.2829 (3.3103) grad_norm: 1.3780 (1.4075) time: 0.5115 [2021-03-26 05:59:37 swin_small_patch4_window7_224] INFO: Epoch: [145] [1070/1251] eta: 0:01:32 lr: 0.000526 loss: 3.3061 (3.3104) grad_norm: 1.3871 (1.4075) time: 0.5002 [2021-03-26 05:59:42 swin_small_patch4_window7_224] INFO: Epoch: [145] [1080/1251] eta: 0:01:27 lr: 0.000526 loss: 3.4136 (3.3108) grad_norm: 1.3823 (1.4074) time: 0.4992 [2021-03-26 05:59:47 swin_small_patch4_window7_224] INFO: Epoch: [145] [1090/1251] eta: 0:01:22 lr: 0.000526 loss: 3.4449 (3.3110) grad_norm: 1.3280 (1.4068) time: 0.4994 [2021-03-26 05:59:52 swin_small_patch4_window7_224] INFO: Epoch: [145] [1100/1251] eta: 0:01:16 lr: 0.000526 loss: 3.4958 (3.3125) grad_norm: 1.3373 (1.4067) time: 0.4991 [2021-03-26 05:59:57 swin_small_patch4_window7_224] INFO: Epoch: [145] [1110/1251] eta: 0:01:11 lr: 0.000526 loss: 3.5738 (3.3147) grad_norm: 1.3593 (1.4066) time: 0.5068 [2021-03-26 06:00:02 swin_small_patch4_window7_224] INFO: Epoch: [145] [1120/1251] eta: 0:01:06 lr: 0.000526 loss: 3.5691 (3.3155) grad_norm: 1.3720 (1.4062) time: 0.5102 [2021-03-26 06:00:07 swin_small_patch4_window7_224] INFO: Epoch: [145] [1130/1251] eta: 0:01:01 lr: 0.000526 loss: 3.2604 (3.3155) grad_norm: 1.3763 (1.4068) time: 0.5056 [2021-03-26 06:00:12 swin_small_patch4_window7_224] INFO: Epoch: [145] [1140/1251] eta: 0:00:56 lr: 0.000526 loss: 3.2394 (3.3155) grad_norm: 1.4500 (1.4068) time: 0.5082 [2021-03-26 06:00:17 swin_small_patch4_window7_224] INFO: Epoch: [145] [1150/1251] eta: 0:00:51 lr: 0.000526 loss: 3.1084 (3.3133) grad_norm: 1.4162 (1.4072) time: 0.5121 [2021-03-26 06:00:22 swin_small_patch4_window7_224] INFO: Epoch: [145] [1160/1251] eta: 0:00:46 lr: 0.000526 loss: 3.5237 (3.3143) grad_norm: 1.3911 (1.4070) time: 0.5095 [2021-03-26 06:00:27 swin_small_patch4_window7_224] INFO: Epoch: [145] [1170/1251] eta: 0:00:41 lr: 0.000526 loss: 3.5966 (3.3161) grad_norm: 1.3061 (1.4065) time: 0.5081 [2021-03-26 06:00:33 swin_small_patch4_window7_224] INFO: Epoch: [145] [1180/1251] eta: 0:00:36 lr: 0.000526 loss: 3.5810 (3.3175) grad_norm: 1.3369 (1.4063) time: 0.5124 [2021-03-26 06:00:38 swin_small_patch4_window7_224] INFO: Epoch: [145] [1190/1251] eta: 0:00:31 lr: 0.000526 loss: 3.4666 (3.3172) grad_norm: 1.4125 (1.4068) time: 0.5060 [2021-03-26 06:00:43 swin_small_patch4_window7_224] INFO: Epoch: [145] [1200/1251] eta: 0:00:25 lr: 0.000526 loss: 3.5817 (3.3194) grad_norm: 1.4198 (1.4074) time: 0.5008 [2021-03-26 06:00:48 swin_small_patch4_window7_224] INFO: Epoch: [145] [1210/1251] eta: 0:00:20 lr: 0.000526 loss: 3.5459 (3.3190) grad_norm: 1.4150 (1.4072) time: 0.5073 [2021-03-26 06:00:53 swin_small_patch4_window7_224] INFO: Epoch: [145] [1220/1251] eta: 0:00:15 lr: 0.000526 loss: 3.2421 (3.3187) grad_norm: 1.3649 (1.4068) time: 0.5044 [2021-03-26 06:00:58 swin_small_patch4_window7_224] INFO: Epoch: [145] [1230/1251] eta: 0:00:10 lr: 0.000526 loss: 3.3879 (3.3193) grad_norm: 1.3511 (1.4067) time: 0.4990 [2021-03-26 06:01:03 swin_small_patch4_window7_224] INFO: Epoch: [145] [1240/1251] eta: 0:00:05 lr: 0.000526 loss: 3.5110 (3.3206) grad_norm: 1.2999 (1.4057) time: 0.5020 [2021-03-26 06:01:08 swin_small_patch4_window7_224] INFO: Epoch: [145] [1250/1251] eta: 0:00:00 lr: 0.000526 loss: 3.4184 (3.3205) grad_norm: 1.2915 (1.4054) time: 0.5022 [2021-03-26 06:01:51 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.6506 (0.6506) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-26 06:01:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.9205 (0.9496) acc1: 76.5625 (77.2727) acc5: 93.7500 (93.8920) [2021-03-26 06:01:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.9205 (0.9373) acc1: 78.1250 (77.6042) acc5: 93.7500 (93.6756) [2021-03-26 06:01:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9346 (0.9320) acc1: 78.1250 (77.1169) acc5: 93.7500 (94.2036) [2021-03-26 06:01:55 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.9346 (0.9316) acc1: 76.5625 (77.2485) acc5: 93.7500 (94.1311) [2021-03-26 06:01:56 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8546 (0.9271) acc1: 78.1250 (77.4400) acc5: 95.3125 (94.4320) [2021-03-26 06:02:03 swin_small_patch4_window7_224] INFO: * Acc@1 78.190 Acc@5 94.366 loss 0.914 [2021-03-26 06:02:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.2% [2021-03-26 06:02:03 swin_small_patch4_window7_224] INFO: Max accuracy: 78.19% [2021-03-26 06:02:07 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 0/1251] eta: 1:30:14 lr: 0.000526 loss: 4.0386 (4.0386) grad_norm: 1.4329 (1.4329) time: 4.3285 [2021-03-26 06:02:12 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 10/1251] eta: 0:17:40 lr: 0.000526 loss: 3.4406 (3.4381) grad_norm: 1.3421 (1.4051) time: 0.8543 [2021-03-26 06:02:17 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 20/1251] eta: 0:14:08 lr: 0.000526 loss: 3.4030 (3.3013) grad_norm: 1.3150 (1.3325) time: 0.5073 [2021-03-26 06:02:22 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 30/1251] eta: 0:12:51 lr: 0.000526 loss: 3.1092 (3.2905) grad_norm: 1.1995 (1.3166) time: 0.5095 [2021-03-26 06:02:27 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 40/1251] eta: 0:12:08 lr: 0.000526 loss: 3.1475 (3.2325) grad_norm: 1.2824 (1.3340) time: 0.5091 [2021-03-26 06:02:32 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 50/1251] eta: 0:11:37 lr: 0.000526 loss: 3.1475 (3.2235) grad_norm: 1.3583 (1.3460) time: 0.5026 [2021-03-26 06:02:38 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 60/1251] eta: 0:11:16 lr: 0.000525 loss: 3.0784 (3.1801) grad_norm: 1.3816 (1.3605) time: 0.5003 [2021-03-26 06:02:43 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 70/1251] eta: 0:11:02 lr: 0.000525 loss: 3.1081 (3.1893) grad_norm: 1.3529 (1.3566) time: 0.5082 [2021-03-26 06:02:48 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 80/1251] eta: 0:10:48 lr: 0.000525 loss: 3.1921 (3.1786) grad_norm: 1.3398 (1.3605) time: 0.5094 [2021-03-26 06:02:53 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 90/1251] eta: 0:10:35 lr: 0.000525 loss: 3.1590 (3.1857) grad_norm: 1.3390 (1.3589) time: 0.5019 [2021-03-26 06:02:58 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 100/1251] eta: 0:10:24 lr: 0.000525 loss: 3.4528 (3.2096) grad_norm: 1.3650 (1.3685) time: 0.4993 [2021-03-26 06:03:03 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 110/1251] eta: 0:10:14 lr: 0.000525 loss: 3.5079 (3.2028) grad_norm: 1.4137 (1.3694) time: 0.4990 [2021-03-26 06:03:08 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 120/1251] eta: 0:10:06 lr: 0.000525 loss: 3.0879 (3.1992) grad_norm: 1.3903 (1.3801) time: 0.5024 [2021-03-26 06:03:13 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 130/1251] eta: 0:09:59 lr: 0.000525 loss: 3.0879 (3.1876) grad_norm: 1.4084 (1.3852) time: 0.5136 [2021-03-26 06:03:18 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 140/1251] eta: 0:09:51 lr: 0.000525 loss: 3.2845 (3.2144) grad_norm: 1.4341 (1.3907) time: 0.5108 [2021-03-26 06:03:23 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 150/1251] eta: 0:09:44 lr: 0.000525 loss: 3.3422 (3.2148) grad_norm: 1.4658 (1.3963) time: 0.5024 [2021-03-26 06:03:28 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 160/1251] eta: 0:09:37 lr: 0.000525 loss: 3.2159 (3.2222) grad_norm: 1.4676 (1.4023) time: 0.5080 [2021-03-26 06:03:33 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 170/1251] eta: 0:09:31 lr: 0.000525 loss: 3.3696 (3.2224) grad_norm: 1.4331 (1.4021) time: 0.5138 [2021-03-26 06:03:38 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 180/1251] eta: 0:09:24 lr: 0.000525 loss: 3.5482 (3.2414) grad_norm: 1.3737 (1.3977) time: 0.5070 [2021-03-26 06:03:43 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 190/1251] eta: 0:09:17 lr: 0.000525 loss: 3.5482 (3.2454) grad_norm: 1.3233 (1.3946) time: 0.5017 [2021-03-26 06:03:48 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 200/1251] eta: 0:09:11 lr: 0.000525 loss: 3.2686 (3.2412) grad_norm: 1.3642 (1.3959) time: 0.5064 [2021-03-26 06:03:54 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 210/1251] eta: 0:09:06 lr: 0.000525 loss: 3.4114 (3.2582) grad_norm: 1.4201 (1.4060) time: 0.5124 [2021-03-26 06:03:59 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 220/1251] eta: 0:08:59 lr: 0.000525 loss: 3.4114 (3.2533) grad_norm: 1.4601 (nan) time: 0.5050 [2021-03-26 06:04:04 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 230/1251] eta: 0:08:53 lr: 0.000525 loss: 3.4667 (3.2641) grad_norm: 1.3957 (nan) time: 0.5044 [2021-03-26 06:04:09 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 240/1251] eta: 0:08:47 lr: 0.000525 loss: 3.5567 (3.2604) grad_norm: 1.3690 (nan) time: 0.5044 [2021-03-26 06:04:14 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 250/1251] eta: 0:08:41 lr: 0.000525 loss: 3.2778 (3.2658) grad_norm: 1.3296 (nan) time: 0.4985 [2021-03-26 06:04:19 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 260/1251] eta: 0:08:35 lr: 0.000525 loss: 3.4277 (3.2676) grad_norm: 1.3242 (nan) time: 0.5036 [2021-03-26 06:04:24 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 270/1251] eta: 0:08:29 lr: 0.000525 loss: 3.4995 (3.2725) grad_norm: 1.3363 (nan) time: 0.5020 [2021-03-26 06:04:29 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 280/1251] eta: 0:08:23 lr: 0.000525 loss: 3.2314 (3.2629) grad_norm: 1.3999 (nan) time: 0.5012 [2021-03-26 06:04:34 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 290/1251] eta: 0:08:18 lr: 0.000525 loss: 3.0779 (3.2605) grad_norm: 1.4171 (nan) time: 0.5002 [2021-03-26 06:04:39 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 300/1251] eta: 0:08:12 lr: 0.000524 loss: 3.2392 (3.2634) grad_norm: 1.3570 (nan) time: 0.5031 [2021-03-26 06:04:44 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 310/1251] eta: 0:08:06 lr: 0.000524 loss: 3.4884 (3.2706) grad_norm: 1.3719 (nan) time: 0.5068 [2021-03-26 06:04:49 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 320/1251] eta: 0:08:01 lr: 0.000524 loss: 3.3773 (3.2705) grad_norm: 1.4814 (nan) time: 0.5108 [2021-03-26 06:04:54 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 330/1251] eta: 0:07:56 lr: 0.000524 loss: 3.2728 (3.2727) grad_norm: 1.4223 (nan) time: 0.5105 [2021-03-26 06:04:59 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 340/1251] eta: 0:07:50 lr: 0.000524 loss: 3.4346 (3.2713) grad_norm: 1.3529 (nan) time: 0.5029 [2021-03-26 06:05:04 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 350/1251] eta: 0:07:45 lr: 0.000524 loss: 3.4352 (3.2732) grad_norm: 1.4235 (nan) time: 0.5002 [2021-03-26 06:05:09 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 360/1251] eta: 0:07:39 lr: 0.000524 loss: 3.4352 (3.2768) grad_norm: 1.4111 (nan) time: 0.5027 [2021-03-26 06:05:14 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 370/1251] eta: 0:07:34 lr: 0.000524 loss: 3.4283 (3.2783) grad_norm: 1.3726 (nan) time: 0.5116 [2021-03-26 06:05:19 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 380/1251] eta: 0:07:29 lr: 0.000524 loss: 3.4420 (3.2803) grad_norm: 1.3726 (nan) time: 0.5132 [2021-03-26 06:05:24 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 390/1251] eta: 0:07:23 lr: 0.000524 loss: 3.1741 (3.2756) grad_norm: 1.3350 (nan) time: 0.5061 [2021-03-26 06:05:29 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 400/1251] eta: 0:07:18 lr: 0.000524 loss: 3.2054 (3.2800) grad_norm: 1.3493 (nan) time: 0.5065 [2021-03-26 06:05:35 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 410/1251] eta: 0:07:13 lr: 0.000524 loss: 3.0492 (3.2714) grad_norm: 1.3734 (nan) time: 0.5116 [2021-03-26 06:05:40 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 420/1251] eta: 0:07:08 lr: 0.000524 loss: 3.3104 (3.2789) grad_norm: 1.3171 (nan) time: 0.5149 [2021-03-26 06:05:45 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 430/1251] eta: 0:07:03 lr: 0.000524 loss: 3.3661 (3.2752) grad_norm: 1.3604 (nan) time: 0.5172 [2021-03-26 06:05:50 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 440/1251] eta: 0:06:57 lr: 0.000524 loss: 3.2915 (3.2783) grad_norm: 1.3965 (nan) time: 0.5111 [2021-03-26 06:05:55 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 450/1251] eta: 0:06:52 lr: 0.000524 loss: 3.2915 (3.2807) grad_norm: 1.4385 (nan) time: 0.5039 [2021-03-26 06:06:00 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 460/1251] eta: 0:06:46 lr: 0.000524 loss: 3.2763 (3.2821) grad_norm: 1.4215 (nan) time: 0.4977 [2021-03-26 06:06:05 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 470/1251] eta: 0:06:41 lr: 0.000524 loss: 3.2763 (3.2837) grad_norm: 1.3369 (nan) time: 0.4947 [2021-03-26 06:06:10 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 480/1251] eta: 0:06:36 lr: 0.000524 loss: 3.4851 (3.2918) grad_norm: 1.3369 (nan) time: 0.5036 [2021-03-26 06:06:15 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 490/1251] eta: 0:06:30 lr: 0.000524 loss: 3.5936 (3.2914) grad_norm: 1.3911 (nan) time: 0.5071 [2021-03-26 06:06:20 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 500/1251] eta: 0:06:25 lr: 0.000524 loss: 3.5080 (3.2933) grad_norm: 1.3911 (nan) time: 0.5031 [2021-03-26 06:06:25 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 510/1251] eta: 0:06:20 lr: 0.000524 loss: 3.3612 (3.2909) grad_norm: 1.3221 (nan) time: 0.5049 [2021-03-26 06:06:30 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 520/1251] eta: 0:06:15 lr: 0.000524 loss: 3.2636 (3.2898) grad_norm: 1.3264 (nan) time: 0.5060 [2021-03-26 06:06:35 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 530/1251] eta: 0:06:09 lr: 0.000524 loss: 3.3045 (3.2890) grad_norm: 1.3753 (nan) time: 0.5065 [2021-03-26 06:06:41 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 540/1251] eta: 0:06:04 lr: 0.000523 loss: 3.3045 (3.2917) grad_norm: 1.3936 (nan) time: 0.5139 [2021-03-26 06:06:46 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 550/1251] eta: 0:05:59 lr: 0.000523 loss: 3.2891 (3.2905) grad_norm: 1.3575 (nan) time: 0.5227 [2021-03-26 06:06:51 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 560/1251] eta: 0:05:54 lr: 0.000523 loss: 3.3177 (3.2908) grad_norm: 1.3535 (nan) time: 0.5175 [2021-03-26 06:06:56 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 570/1251] eta: 0:05:49 lr: 0.000523 loss: 3.3065 (3.2874) grad_norm: 1.3281 (nan) time: 0.5054 [2021-03-26 06:07:01 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 580/1251] eta: 0:05:44 lr: 0.000523 loss: 3.3065 (3.2884) grad_norm: 1.3520 (nan) time: 0.5068 [2021-03-26 06:07:06 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 590/1251] eta: 0:05:39 lr: 0.000523 loss: 3.3486 (3.2876) grad_norm: 1.3821 (nan) time: 0.5078 [2021-03-26 06:07:11 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 600/1251] eta: 0:05:33 lr: 0.000523 loss: 3.3808 (3.2911) grad_norm: 1.4333 (nan) time: 0.5035 [2021-03-26 06:07:16 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 610/1251] eta: 0:05:28 lr: 0.000523 loss: 3.3274 (3.2852) grad_norm: 1.4569 (nan) time: 0.5063 [2021-03-26 06:07:21 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 620/1251] eta: 0:05:23 lr: 0.000523 loss: 2.9727 (3.2845) grad_norm: 1.4201 (nan) time: 0.5102 [2021-03-26 06:07:26 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 630/1251] eta: 0:05:18 lr: 0.000523 loss: 3.1074 (3.2842) grad_norm: 1.3793 (nan) time: 0.5045 [2021-03-26 06:07:31 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 640/1251] eta: 0:05:13 lr: 0.000523 loss: 3.3914 (3.2872) grad_norm: 1.4255 (nan) time: 0.5023 [2021-03-26 06:07:36 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 650/1251] eta: 0:05:07 lr: 0.000523 loss: 3.4968 (3.2904) grad_norm: 1.4090 (nan) time: 0.5036 [2021-03-26 06:07:41 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 660/1251] eta: 0:05:02 lr: 0.000523 loss: 3.5872 (3.2935) grad_norm: 1.3907 (nan) time: 0.5048 [2021-03-26 06:07:47 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 670/1251] eta: 0:04:57 lr: 0.000523 loss: 3.5344 (3.2953) grad_norm: 1.4218 (nan) time: 0.5068 [2021-03-26 06:07:52 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 680/1251] eta: 0:04:52 lr: 0.000523 loss: 3.1993 (3.2901) grad_norm: 1.3940 (nan) time: 0.5043 [2021-03-26 06:07:57 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 690/1251] eta: 0:04:47 lr: 0.000523 loss: 3.1861 (3.2897) grad_norm: 1.3718 (nan) time: 0.5039 [2021-03-26 06:08:02 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 700/1251] eta: 0:04:41 lr: 0.000523 loss: 3.5010 (3.2912) grad_norm: 1.3841 (nan) time: 0.5037 [2021-03-26 06:08:07 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 710/1251] eta: 0:04:36 lr: 0.000523 loss: 3.3781 (3.2909) grad_norm: 1.3923 (nan) time: 0.5010 [2021-03-26 06:08:12 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 720/1251] eta: 0:04:31 lr: 0.000523 loss: 3.1345 (3.2893) grad_norm: 1.3812 (nan) time: 0.5048 [2021-03-26 06:08:17 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 730/1251] eta: 0:04:26 lr: 0.000523 loss: 3.2509 (3.2907) grad_norm: 1.3699 (nan) time: 0.5119 [2021-03-26 06:08:22 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 740/1251] eta: 0:04:21 lr: 0.000523 loss: 3.4980 (3.2930) grad_norm: 1.3395 (nan) time: 0.5192 [2021-03-26 06:08:27 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 750/1251] eta: 0:04:16 lr: 0.000523 loss: 3.4211 (3.2919) grad_norm: 1.3190 (nan) time: 0.5181 [2021-03-26 06:08:32 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 760/1251] eta: 0:04:11 lr: 0.000523 loss: 3.2306 (3.2908) grad_norm: 1.3190 (nan) time: 0.5147 [2021-03-26 06:08:37 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 770/1251] eta: 0:04:06 lr: 0.000523 loss: 3.4567 (3.2930) grad_norm: 1.3943 (nan) time: 0.5078 [2021-03-26 06:08:42 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 780/1251] eta: 0:04:00 lr: 0.000522 loss: 3.4567 (3.2933) grad_norm: 1.4017 (nan) time: 0.5019 [2021-03-26 06:08:47 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 790/1251] eta: 0:03:55 lr: 0.000522 loss: 3.3323 (3.2933) grad_norm: 1.3700 (nan) time: 0.5048 [2021-03-26 06:08:53 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 800/1251] eta: 0:03:50 lr: 0.000522 loss: 3.3760 (3.2924) grad_norm: 1.3013 (nan) time: 0.5073 [2021-03-26 06:08:58 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 810/1251] eta: 0:03:45 lr: 0.000522 loss: 3.2636 (3.2912) grad_norm: 1.3593 (nan) time: 0.5100 [2021-03-26 06:09:03 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 820/1251] eta: 0:03:40 lr: 0.000522 loss: 3.2269 (3.2907) grad_norm: 1.3907 (nan) time: 0.5086 [2021-03-26 06:09:08 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 830/1251] eta: 0:03:35 lr: 0.000522 loss: 3.2932 (3.2901) grad_norm: 1.3443 (nan) time: 0.5025 [2021-03-26 06:09:13 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 840/1251] eta: 0:03:30 lr: 0.000522 loss: 3.0847 (3.2878) grad_norm: 1.3386 (nan) time: 0.5026 [2021-03-26 06:09:18 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 850/1251] eta: 0:03:24 lr: 0.000522 loss: 3.3933 (3.2902) grad_norm: 1.3703 (nan) time: 0.5096 [2021-03-26 06:09:23 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 860/1251] eta: 0:03:19 lr: 0.000522 loss: 3.5818 (3.2915) grad_norm: 1.3935 (nan) time: 0.5111 [2021-03-26 06:09:28 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 870/1251] eta: 0:03:14 lr: 0.000522 loss: 3.3732 (3.2922) grad_norm: 1.3935 (nan) time: 0.5107 [2021-03-26 06:09:33 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 880/1251] eta: 0:03:09 lr: 0.000522 loss: 3.4065 (3.2938) grad_norm: 1.3843 (nan) time: 0.5010 [2021-03-26 06:09:38 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 890/1251] eta: 0:03:04 lr: 0.000522 loss: 3.4213 (3.2935) grad_norm: 1.3798 (nan) time: 0.4994 [2021-03-26 06:09:43 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 900/1251] eta: 0:02:59 lr: 0.000522 loss: 3.4213 (3.2945) grad_norm: 1.3498 (nan) time: 0.5098 [2021-03-26 06:09:48 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 910/1251] eta: 0:02:54 lr: 0.000522 loss: 3.4784 (3.2961) grad_norm: 1.3404 (nan) time: 0.5149 [2021-03-26 06:09:53 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 920/1251] eta: 0:02:49 lr: 0.000522 loss: 3.4784 (3.2969) grad_norm: 1.4098 (nan) time: 0.5055 [2021-03-26 06:09:58 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 930/1251] eta: 0:02:43 lr: 0.000522 loss: 3.3164 (3.2954) grad_norm: 1.3982 (nan) time: 0.5001 [2021-03-26 06:10:03 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 940/1251] eta: 0:02:38 lr: 0.000522 loss: 3.3164 (3.2953) grad_norm: 1.3814 (nan) time: 0.5035 [2021-03-26 06:10:09 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 950/1251] eta: 0:02:33 lr: 0.000522 loss: 3.3830 (3.2948) grad_norm: 1.3744 (nan) time: 0.5101 [2021-03-26 06:10:14 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 960/1251] eta: 0:02:28 lr: 0.000522 loss: 3.4208 (3.2953) grad_norm: 1.3721 (nan) time: 0.5086 [2021-03-26 06:10:19 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 970/1251] eta: 0:02:23 lr: 0.000522 loss: 3.4199 (3.2959) grad_norm: 1.4011 (nan) time: 0.5022 [2021-03-26 06:10:24 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 980/1251] eta: 0:02:18 lr: 0.000522 loss: 3.4623 (3.2967) grad_norm: 1.3814 (nan) time: 0.5069 [2021-03-26 06:10:29 swin_small_patch4_window7_224] INFO: Epoch: [146] [ 990/1251] eta: 0:02:13 lr: 0.000522 loss: 3.5140 (3.2958) grad_norm: 1.3440 (nan) time: 0.5059 [2021-03-26 06:10:34 swin_small_patch4_window7_224] INFO: Epoch: [146] [1000/1251] eta: 0:02:08 lr: 0.000522 loss: 3.5140 (3.2981) grad_norm: 1.3498 (nan) time: 0.5092 [2021-03-26 06:10:39 swin_small_patch4_window7_224] INFO: Epoch: [146] [1010/1251] eta: 0:02:02 lr: 0.000522 loss: 3.4554 (3.2973) grad_norm: 1.3531 (nan) time: 0.5052 [2021-03-26 06:10:44 swin_small_patch4_window7_224] INFO: Epoch: [146] [1020/1251] eta: 0:01:57 lr: 0.000522 loss: 3.4564 (3.2982) grad_norm: 1.3725 (nan) time: 0.5014 [2021-03-26 06:10:49 swin_small_patch4_window7_224] INFO: Epoch: [146] [1030/1251] eta: 0:01:52 lr: 0.000521 loss: 3.3976 (3.2987) grad_norm: 1.3700 (nan) time: 0.5056 [2021-03-26 06:10:54 swin_small_patch4_window7_224] INFO: Epoch: [146] [1040/1251] eta: 0:01:47 lr: 0.000521 loss: 3.3715 (3.2984) grad_norm: 1.3761 (nan) time: 0.5014 [2021-03-26 06:10:59 swin_small_patch4_window7_224] INFO: Epoch: [146] [1050/1251] eta: 0:01:42 lr: 0.000521 loss: 3.3692 (3.2990) grad_norm: 1.3865 (nan) time: 0.4997 [2021-03-26 06:11:04 swin_small_patch4_window7_224] INFO: Epoch: [146] [1060/1251] eta: 0:01:37 lr: 0.000521 loss: 3.5563 (3.3011) grad_norm: 1.3836 (nan) time: 0.5055 [2021-03-26 06:11:09 swin_small_patch4_window7_224] INFO: Epoch: [146] [1070/1251] eta: 0:01:32 lr: 0.000521 loss: 3.3787 (3.2981) grad_norm: 1.4095 (nan) time: 0.5109 [2021-03-26 06:11:14 swin_small_patch4_window7_224] INFO: Epoch: [146] [1080/1251] eta: 0:01:27 lr: 0.000521 loss: 3.1280 (3.2976) grad_norm: 1.4377 (nan) time: 0.5098 [2021-03-26 06:11:19 swin_small_patch4_window7_224] INFO: Epoch: [146] [1090/1251] eta: 0:01:22 lr: 0.000521 loss: 3.4411 (3.3005) grad_norm: 1.4500 (nan) time: 0.5035 [2021-03-26 06:11:24 swin_small_patch4_window7_224] INFO: Epoch: [146] [1100/1251] eta: 0:01:16 lr: 0.000521 loss: 3.4894 (3.2985) grad_norm: 1.3583 (nan) time: 0.5017 [2021-03-26 06:11:29 swin_small_patch4_window7_224] INFO: Epoch: [146] [1110/1251] eta: 0:01:11 lr: 0.000521 loss: 3.2667 (3.2993) grad_norm: 1.3777 (nan) time: 0.5028 [2021-03-26 06:11:35 swin_small_patch4_window7_224] INFO: Epoch: [146] [1120/1251] eta: 0:01:06 lr: 0.000521 loss: 3.4112 (3.2980) grad_norm: 1.3644 (nan) time: 0.5063 [2021-03-26 06:11:40 swin_small_patch4_window7_224] INFO: Epoch: [146] [1130/1251] eta: 0:01:01 lr: 0.000521 loss: 3.2350 (3.2991) grad_norm: 1.2869 (nan) time: 0.5112 [2021-03-26 06:11:45 swin_small_patch4_window7_224] INFO: Epoch: [146] [1140/1251] eta: 0:00:56 lr: 0.000521 loss: 3.3418 (3.3003) grad_norm: 1.3467 (nan) time: 0.5071 [2021-03-26 06:11:50 swin_small_patch4_window7_224] INFO: Epoch: [146] [1150/1251] eta: 0:00:51 lr: 0.000521 loss: 3.3418 (3.3000) grad_norm: 1.4281 (nan) time: 0.5016 [2021-03-26 06:11:55 swin_small_patch4_window7_224] INFO: Epoch: [146] [1160/1251] eta: 0:00:46 lr: 0.000521 loss: 3.2845 (3.2993) grad_norm: 1.3432 (nan) time: 0.5037 [2021-03-26 06:12:00 swin_small_patch4_window7_224] INFO: Epoch: [146] [1170/1251] eta: 0:00:41 lr: 0.000521 loss: 3.6065 (3.3013) grad_norm: 1.3943 (nan) time: 0.5087 [2021-03-26 06:12:05 swin_small_patch4_window7_224] INFO: Epoch: [146] [1180/1251] eta: 0:00:36 lr: 0.000521 loss: 3.5099 (3.3013) grad_norm: 1.3776 (nan) time: 0.5061 [2021-03-26 06:12:10 swin_small_patch4_window7_224] INFO: Epoch: [146] [1190/1251] eta: 0:00:31 lr: 0.000521 loss: 3.1929 (3.3013) grad_norm: 1.3889 (nan) time: 0.5054 [2021-03-26 06:12:15 swin_small_patch4_window7_224] INFO: Epoch: [146] [1200/1251] eta: 0:00:25 lr: 0.000521 loss: 3.1658 (3.3000) grad_norm: 1.4536 (nan) time: 0.5048 [2021-03-26 06:12:20 swin_small_patch4_window7_224] INFO: Epoch: [146] [1210/1251] eta: 0:00:20 lr: 0.000521 loss: 3.3906 (3.3008) grad_norm: 1.3676 (nan) time: 0.5007 [2021-03-26 06:12:25 swin_small_patch4_window7_224] INFO: Epoch: [146] [1220/1251] eta: 0:00:15 lr: 0.000521 loss: 3.4294 (3.3014) grad_norm: 1.3559 (nan) time: 0.4980 [2021-03-26 06:12:30 swin_small_patch4_window7_224] INFO: Epoch: [146] [1230/1251] eta: 0:00:10 lr: 0.000521 loss: 3.3881 (3.3009) grad_norm: 1.3729 (nan) time: 0.5017 [2021-03-26 06:12:35 swin_small_patch4_window7_224] INFO: Epoch: [146] [1240/1251] eta: 0:00:05 lr: 0.000521 loss: 3.3584 (3.3007) grad_norm: 1.3624 (nan) time: 0.4999 [2021-03-26 06:12:40 swin_small_patch4_window7_224] INFO: Epoch: [146] [1250/1251] eta: 0:00:00 lr: 0.000521 loss: 3.3200 (3.3000) grad_norm: 1.3508 (nan) time: 0.4961 [2021-03-26 06:12:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:48 loss: 0.8508 (0.8508) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 06:12:51 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8641 (0.8820) acc1: 79.6875 (78.9773) acc5: 95.3125 (94.7443) [2021-03-26 06:12:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8641 (0.8952) acc1: 78.1250 (78.1250) acc5: 95.3125 (94.8661) [2021-03-26 06:12:55 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8976 (0.8992) acc1: 78.1250 (78.4274) acc5: 93.7500 (94.7581) [2021-03-26 06:12:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8976 (0.9207) acc1: 78.1250 (77.6296) acc5: 93.7500 (94.7409) [2021-03-26 06:12:58 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8886 (0.9195) acc1: 78.1250 (77.7280) acc5: 95.3125 (94.7520) [2021-03-26 06:13:04 swin_small_patch4_window7_224] INFO: * Acc@1 78.262 Acc@5 94.430 loss 0.917 [2021-03-26 06:13:04 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.3% [2021-03-26 06:13:04 swin_small_patch4_window7_224] INFO: Max accuracy: 78.26% [2021-03-26 06:13:09 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 0/1251] eta: 1:32:12 lr: 0.000521 loss: 3.2661 (3.2661) grad_norm: 1.4901 (1.4901) time: 4.4224 [2021-03-26 06:13:14 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 10/1251] eta: 0:17:43 lr: 0.000521 loss: 3.2661 (3.0816) grad_norm: 1.4435 (1.4285) time: 0.8571 [2021-03-26 06:13:19 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 20/1251] eta: 0:14:08 lr: 0.000520 loss: 3.3062 (3.1811) grad_norm: 1.4065 (1.4122) time: 0.5024 [2021-03-26 06:13:24 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 30/1251] eta: 0:12:47 lr: 0.000520 loss: 3.3895 (3.2166) grad_norm: 1.3824 (1.4065) time: 0.5031 [2021-03-26 06:13:29 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 40/1251] eta: 0:12:08 lr: 0.000520 loss: 3.2647 (3.2077) grad_norm: 1.4365 (1.4206) time: 0.5098 [2021-03-26 06:13:34 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 50/1251] eta: 0:11:42 lr: 0.000520 loss: 3.2352 (3.2102) grad_norm: 1.4147 (1.4148) time: 0.5167 [2021-03-26 06:13:39 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 60/1251] eta: 0:11:22 lr: 0.000520 loss: 3.1765 (3.1856) grad_norm: 1.3398 (1.4016) time: 0.5143 [2021-03-26 06:13:44 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 70/1251] eta: 0:11:04 lr: 0.000520 loss: 3.3456 (3.2368) grad_norm: 1.3386 (1.3973) time: 0.5064 [2021-03-26 06:13:49 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 80/1251] eta: 0:10:49 lr: 0.000520 loss: 3.5366 (3.2535) grad_norm: 1.3702 (1.3927) time: 0.4986 [2021-03-26 06:13:54 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 90/1251] eta: 0:10:37 lr: 0.000520 loss: 3.4777 (3.2548) grad_norm: 1.3452 (1.3930) time: 0.5011 [2021-03-26 06:13:59 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 100/1251] eta: 0:10:26 lr: 0.000520 loss: 3.4444 (3.2909) grad_norm: 1.3362 (1.4000) time: 0.5041 [2021-03-26 06:14:04 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 110/1251] eta: 0:10:17 lr: 0.000520 loss: 3.4113 (3.2805) grad_norm: 1.3286 (1.3950) time: 0.5053 [2021-03-26 06:14:10 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 120/1251] eta: 0:10:09 lr: 0.000520 loss: 3.2112 (3.2611) grad_norm: 1.3286 (1.3959) time: 0.5078 [2021-03-26 06:14:15 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 130/1251] eta: 0:10:02 lr: 0.000520 loss: 3.1433 (3.2643) grad_norm: 1.3862 (1.3950) time: 0.5146 [2021-03-26 06:14:20 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 140/1251] eta: 0:09:54 lr: 0.000520 loss: 3.1386 (3.2539) grad_norm: 1.4326 (1.4007) time: 0.5169 [2021-03-26 06:14:25 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 150/1251] eta: 0:09:47 lr: 0.000520 loss: 3.0194 (3.2437) grad_norm: 1.4388 (1.4025) time: 0.5112 [2021-03-26 06:14:30 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 160/1251] eta: 0:09:40 lr: 0.000520 loss: 3.2991 (3.2586) grad_norm: 1.4388 (1.4078) time: 0.5047 [2021-03-26 06:14:35 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 170/1251] eta: 0:09:32 lr: 0.000520 loss: 3.4190 (3.2741) grad_norm: 1.4845 (1.4091) time: 0.4999 [2021-03-26 06:14:40 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 180/1251] eta: 0:09:26 lr: 0.000520 loss: 3.4370 (3.2830) grad_norm: 1.3012 (1.4080) time: 0.5107 [2021-03-26 06:14:45 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 190/1251] eta: 0:09:19 lr: 0.000520 loss: 3.4888 (3.2891) grad_norm: 1.3897 (1.4078) time: 0.5087 [2021-03-26 06:14:50 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 200/1251] eta: 0:09:13 lr: 0.000520 loss: 3.3899 (3.2787) grad_norm: 1.3534 (1.4016) time: 0.4984 [2021-03-26 06:14:55 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 210/1251] eta: 0:09:06 lr: 0.000520 loss: 3.2942 (3.2777) grad_norm: 1.3359 (1.4024) time: 0.5006 [2021-03-26 06:15:00 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 220/1251] eta: 0:09:00 lr: 0.000520 loss: 3.2610 (3.2678) grad_norm: 1.3706 (1.4036) time: 0.5009 [2021-03-26 06:15:05 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 230/1251] eta: 0:08:53 lr: 0.000520 loss: 3.3514 (3.2786) grad_norm: 1.4085 (1.4088) time: 0.5007 [2021-03-26 06:15:10 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 240/1251] eta: 0:08:48 lr: 0.000520 loss: 3.4856 (3.2842) grad_norm: 1.4348 (1.4125) time: 0.5056 [2021-03-26 06:15:15 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 250/1251] eta: 0:08:42 lr: 0.000520 loss: 3.4856 (3.2871) grad_norm: 1.4253 (1.4117) time: 0.5147 [2021-03-26 06:15:21 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 260/1251] eta: 0:08:37 lr: 0.000519 loss: 3.1982 (3.2783) grad_norm: 1.3375 (1.4103) time: 0.5135 [2021-03-26 06:15:26 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 270/1251] eta: 0:08:31 lr: 0.000519 loss: 3.1985 (3.2805) grad_norm: 1.3921 (1.4115) time: 0.5044 [2021-03-26 06:15:31 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 280/1251] eta: 0:08:25 lr: 0.000519 loss: 3.0142 (3.2667) grad_norm: 1.4769 (1.4135) time: 0.5004 [2021-03-26 06:15:36 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 290/1251] eta: 0:08:19 lr: 0.000519 loss: 3.0142 (3.2671) grad_norm: 1.4098 (1.4130) time: 0.5031 [2021-03-26 06:15:41 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 300/1251] eta: 0:08:13 lr: 0.000519 loss: 3.4767 (3.2751) grad_norm: 1.4308 (1.4149) time: 0.5038 [2021-03-26 06:15:46 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 310/1251] eta: 0:08:07 lr: 0.000519 loss: 3.5611 (3.2804) grad_norm: 1.4197 (1.4126) time: 0.4998 [2021-03-26 06:15:51 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 320/1251] eta: 0:08:02 lr: 0.000519 loss: 3.4305 (3.2760) grad_norm: 1.3415 (1.4124) time: 0.4988 [2021-03-26 06:15:56 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 330/1251] eta: 0:07:56 lr: 0.000519 loss: 3.1639 (3.2709) grad_norm: 1.4228 (1.4144) time: 0.5021 [2021-03-26 06:16:01 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 340/1251] eta: 0:07:51 lr: 0.000519 loss: 3.1965 (3.2677) grad_norm: 1.4592 (1.4182) time: 0.5054 [2021-03-26 06:16:06 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 350/1251] eta: 0:07:45 lr: 0.000519 loss: 3.1350 (3.2644) grad_norm: 1.5118 (1.4215) time: 0.5078 [2021-03-26 06:16:11 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 360/1251] eta: 0:07:40 lr: 0.000519 loss: 3.3120 (3.2679) grad_norm: 1.4757 (1.4230) time: 0.5036 [2021-03-26 06:16:16 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 370/1251] eta: 0:07:34 lr: 0.000519 loss: 3.3100 (3.2634) grad_norm: 1.4485 (1.4239) time: 0.5025 [2021-03-26 06:16:21 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 380/1251] eta: 0:07:29 lr: 0.000519 loss: 3.2541 (3.2680) grad_norm: 1.3903 (1.4231) time: 0.5045 [2021-03-26 06:16:26 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 390/1251] eta: 0:07:23 lr: 0.000519 loss: 3.2501 (3.2623) grad_norm: 1.3527 (1.4226) time: 0.5020 [2021-03-26 06:16:31 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 400/1251] eta: 0:07:18 lr: 0.000519 loss: 3.2081 (3.2610) grad_norm: 1.3550 (1.4219) time: 0.4969 [2021-03-26 06:16:36 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 410/1251] eta: 0:07:12 lr: 0.000519 loss: 3.4454 (3.2639) grad_norm: 1.3764 (1.4211) time: 0.4975 [2021-03-26 06:16:41 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 420/1251] eta: 0:07:07 lr: 0.000519 loss: 3.5661 (3.2718) grad_norm: 1.4516 (1.4227) time: 0.5074 [2021-03-26 06:16:46 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 430/1251] eta: 0:07:02 lr: 0.000519 loss: 3.6904 (3.2793) grad_norm: 1.4541 (1.4231) time: 0.5070 [2021-03-26 06:16:51 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 440/1251] eta: 0:06:57 lr: 0.000519 loss: 3.6770 (3.2862) grad_norm: 1.4368 (1.4236) time: 0.5090 [2021-03-26 06:16:56 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 450/1251] eta: 0:06:51 lr: 0.000519 loss: 3.5811 (3.2872) grad_norm: 1.4751 (1.4243) time: 0.5062 [2021-03-26 06:17:01 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 460/1251] eta: 0:06:46 lr: 0.000519 loss: 3.4508 (3.2924) grad_norm: 1.4183 (1.4241) time: 0.4988 [2021-03-26 06:17:06 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 470/1251] eta: 0:06:40 lr: 0.000519 loss: 3.4064 (3.2884) grad_norm: 1.4146 (1.4239) time: 0.4975 [2021-03-26 06:17:11 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 480/1251] eta: 0:06:35 lr: 0.000519 loss: 3.0688 (3.2845) grad_norm: 1.4163 (1.4247) time: 0.5012 [2021-03-26 06:17:16 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 490/1251] eta: 0:06:30 lr: 0.000519 loss: 3.0688 (3.2858) grad_norm: 1.4139 (1.4242) time: 0.5066 [2021-03-26 06:17:21 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 500/1251] eta: 0:06:25 lr: 0.000518 loss: 3.2748 (3.2834) grad_norm: 1.4013 (1.4249) time: 0.5059 [2021-03-26 06:17:26 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 510/1251] eta: 0:06:19 lr: 0.000518 loss: 3.3303 (3.2866) grad_norm: 1.3606 (1.4228) time: 0.5057 [2021-03-26 06:17:31 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 520/1251] eta: 0:06:14 lr: 0.000518 loss: 3.6139 (3.2841) grad_norm: 1.3310 (1.4228) time: 0.5064 [2021-03-26 06:17:36 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 530/1251] eta: 0:06:09 lr: 0.000518 loss: 3.5114 (3.2826) grad_norm: 1.2716 (1.4206) time: 0.5017 [2021-03-26 06:17:42 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 540/1251] eta: 0:06:04 lr: 0.000518 loss: 3.3487 (3.2822) grad_norm: 1.3079 (1.4194) time: 0.5039 [2021-03-26 06:17:47 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 550/1251] eta: 0:05:59 lr: 0.000518 loss: 3.4211 (3.2838) grad_norm: 1.3694 (1.4207) time: 0.5159 [2021-03-26 06:17:52 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 560/1251] eta: 0:05:53 lr: 0.000518 loss: 3.5476 (3.2895) grad_norm: 1.4805 (1.4204) time: 0.5104 [2021-03-26 06:17:57 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 570/1251] eta: 0:05:48 lr: 0.000518 loss: 3.5192 (3.2892) grad_norm: 1.4741 (1.4218) time: 0.5016 [2021-03-26 06:18:02 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 580/1251] eta: 0:05:43 lr: 0.000518 loss: 3.1169 (3.2874) grad_norm: 1.4235 (1.4223) time: 0.5019 [2021-03-26 06:18:07 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 590/1251] eta: 0:05:38 lr: 0.000518 loss: 3.4207 (3.2888) grad_norm: 1.4157 (1.4217) time: 0.5060 [2021-03-26 06:18:12 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 600/1251] eta: 0:05:33 lr: 0.000518 loss: 3.3597 (3.2888) grad_norm: 1.3630 (1.4214) time: 0.5078 [2021-03-26 06:18:17 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 610/1251] eta: 0:05:27 lr: 0.000518 loss: 3.2653 (3.2889) grad_norm: 1.3076 (1.4196) time: 0.5079 [2021-03-26 06:18:22 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 620/1251] eta: 0:05:22 lr: 0.000518 loss: 3.3771 (3.2916) grad_norm: 1.3496 (1.4199) time: 0.5087 [2021-03-26 06:18:27 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 630/1251] eta: 0:05:17 lr: 0.000518 loss: 3.6080 (3.2944) grad_norm: 1.4065 (1.4209) time: 0.5110 [2021-03-26 06:18:32 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 640/1251] eta: 0:05:12 lr: 0.000518 loss: 3.3783 (3.2943) grad_norm: 1.4064 (1.4212) time: 0.5082 [2021-03-26 06:18:37 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 650/1251] eta: 0:05:07 lr: 0.000518 loss: 3.1481 (3.2889) grad_norm: 1.4436 (1.4224) time: 0.5008 [2021-03-26 06:18:42 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 660/1251] eta: 0:05:02 lr: 0.000518 loss: 3.1697 (3.2908) grad_norm: 1.4360 (1.4220) time: 0.4986 [2021-03-26 06:18:47 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 670/1251] eta: 0:04:56 lr: 0.000518 loss: 3.5691 (3.2934) grad_norm: 1.3536 (1.4224) time: 0.5039 [2021-03-26 06:18:52 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 680/1251] eta: 0:04:51 lr: 0.000518 loss: 3.1205 (3.2899) grad_norm: 1.4061 (1.4227) time: 0.5060 [2021-03-26 06:18:57 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 690/1251] eta: 0:04:46 lr: 0.000518 loss: 2.8871 (3.2865) grad_norm: 1.4061 (1.4223) time: 0.5049 [2021-03-26 06:19:02 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 700/1251] eta: 0:04:41 lr: 0.000518 loss: 3.2491 (3.2859) grad_norm: 1.3236 (1.4207) time: 0.5054 [2021-03-26 06:19:08 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 710/1251] eta: 0:04:36 lr: 0.000518 loss: 3.2496 (3.2856) grad_norm: 1.3194 (1.4196) time: 0.5065 [2021-03-26 06:19:13 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 720/1251] eta: 0:04:31 lr: 0.000518 loss: 3.3794 (3.2876) grad_norm: 1.3715 (1.4191) time: 0.5069 [2021-03-26 06:19:18 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 730/1251] eta: 0:04:25 lr: 0.000518 loss: 3.5197 (3.2878) grad_norm: 1.3798 (1.4200) time: 0.5039 [2021-03-26 06:19:23 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 740/1251] eta: 0:04:21 lr: 0.000517 loss: 3.5860 (3.2920) grad_norm: 1.3977 (1.4200) time: 0.5198 [2021-03-26 06:19:28 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 750/1251] eta: 0:04:15 lr: 0.000517 loss: 3.5876 (3.2958) grad_norm: 1.4200 (1.4200) time: 0.5199 [2021-03-26 06:19:33 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 760/1251] eta: 0:04:10 lr: 0.000517 loss: 3.5532 (3.2969) grad_norm: 1.4058 (1.4195) time: 0.5039 [2021-03-26 06:19:38 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 770/1251] eta: 0:04:05 lr: 0.000517 loss: 3.4603 (3.2974) grad_norm: 1.3920 (1.4191) time: 0.5078 [2021-03-26 06:19:43 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 780/1251] eta: 0:04:00 lr: 0.000517 loss: 3.5847 (3.2980) grad_norm: 1.4299 (1.4201) time: 0.5088 [2021-03-26 06:19:48 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 790/1251] eta: 0:03:55 lr: 0.000517 loss: 3.3192 (3.2993) grad_norm: 1.4285 (1.4193) time: 0.5066 [2021-03-26 06:19:54 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 800/1251] eta: 0:03:50 lr: 0.000517 loss: 3.2838 (3.2986) grad_norm: 1.3269 (1.4191) time: 0.5108 [2021-03-26 06:19:59 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 810/1251] eta: 0:03:45 lr: 0.000517 loss: 3.4307 (3.3008) grad_norm: 1.4488 (1.4197) time: 0.5085 [2021-03-26 06:20:04 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 820/1251] eta: 0:03:40 lr: 0.000517 loss: 3.5422 (3.3049) grad_norm: 1.3879 (1.4187) time: 0.5064 [2021-03-26 06:20:09 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 830/1251] eta: 0:03:34 lr: 0.000517 loss: 3.5344 (3.3035) grad_norm: 1.3560 (1.4183) time: 0.5101 [2021-03-26 06:20:14 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 840/1251] eta: 0:03:29 lr: 0.000517 loss: 3.5654 (3.3062) grad_norm: 1.2861 (1.4167) time: 0.5053 [2021-03-26 06:20:19 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 850/1251] eta: 0:03:24 lr: 0.000517 loss: 3.5640 (3.3068) grad_norm: 1.3033 (1.4167) time: 0.4992 [2021-03-26 06:20:24 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 860/1251] eta: 0:03:19 lr: 0.000517 loss: 3.5469 (3.3087) grad_norm: 1.3683 (1.4160) time: 0.5032 [2021-03-26 06:20:29 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 870/1251] eta: 0:03:14 lr: 0.000517 loss: 3.4252 (3.3075) grad_norm: 1.3761 (1.4161) time: 0.5105 [2021-03-26 06:20:34 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 880/1251] eta: 0:03:09 lr: 0.000517 loss: 3.4770 (3.3103) grad_norm: 1.3719 (1.4149) time: 0.5070 [2021-03-26 06:20:39 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 890/1251] eta: 0:03:04 lr: 0.000517 loss: 3.5293 (3.3096) grad_norm: 1.3353 (1.4145) time: 0.5072 [2021-03-26 06:20:44 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 900/1251] eta: 0:02:59 lr: 0.000517 loss: 3.2138 (3.3088) grad_norm: 1.3897 (1.4139) time: 0.5107 [2021-03-26 06:20:49 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 910/1251] eta: 0:02:53 lr: 0.000517 loss: 3.1178 (3.3061) grad_norm: 1.3589 (1.4137) time: 0.5067 [2021-03-26 06:20:54 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 920/1251] eta: 0:02:48 lr: 0.000517 loss: 3.3316 (3.3048) grad_norm: 1.3465 (1.4129) time: 0.5118 [2021-03-26 06:21:00 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 930/1251] eta: 0:02:43 lr: 0.000517 loss: 3.3316 (3.3045) grad_norm: 1.3952 (1.4133) time: 0.5148 [2021-03-26 06:21:05 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 940/1251] eta: 0:02:38 lr: 0.000517 loss: 3.3150 (3.3039) grad_norm: 1.4604 (1.4136) time: 0.5065 [2021-03-26 06:21:10 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 950/1251] eta: 0:02:33 lr: 0.000517 loss: 3.3235 (3.3032) grad_norm: 1.4472 (1.4146) time: 0.5034 [2021-03-26 06:21:15 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 960/1251] eta: 0:02:28 lr: 0.000517 loss: 3.1284 (3.2986) grad_norm: 1.4951 (1.4153) time: 0.5083 [2021-03-26 06:21:20 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 970/1251] eta: 0:02:23 lr: 0.000517 loss: 2.8609 (3.2976) grad_norm: 1.4951 (1.4155) time: 0.5123 [2021-03-26 06:21:25 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 980/1251] eta: 0:02:18 lr: 0.000516 loss: 3.3930 (3.2969) grad_norm: 1.4714 (1.4161) time: 0.5152 [2021-03-26 06:21:30 swin_small_patch4_window7_224] INFO: Epoch: [147] [ 990/1251] eta: 0:02:13 lr: 0.000516 loss: 3.4162 (3.2994) grad_norm: 1.4714 (1.4168) time: 0.5233 [2021-03-26 06:21:35 swin_small_patch4_window7_224] INFO: Epoch: [147] [1000/1251] eta: 0:02:08 lr: 0.000516 loss: 3.4954 (3.2997) grad_norm: 1.4942 (1.4178) time: 0.5123 [2021-03-26 06:21:40 swin_small_patch4_window7_224] INFO: Epoch: [147] [1010/1251] eta: 0:02:02 lr: 0.000516 loss: 3.4842 (3.3015) grad_norm: 1.4464 (1.4181) time: 0.5013 [2021-03-26 06:21:45 swin_small_patch4_window7_224] INFO: Epoch: [147] [1020/1251] eta: 0:01:57 lr: 0.000516 loss: 3.4303 (3.3018) grad_norm: 1.4181 (1.4183) time: 0.5071 [2021-03-26 06:21:50 swin_small_patch4_window7_224] INFO: Epoch: [147] [1030/1251] eta: 0:01:52 lr: 0.000516 loss: 3.4303 (3.3025) grad_norm: 1.3819 (1.4180) time: 0.5042 [2021-03-26 06:21:56 swin_small_patch4_window7_224] INFO: Epoch: [147] [1040/1251] eta: 0:01:47 lr: 0.000516 loss: 3.4110 (3.3015) grad_norm: 1.4023 (1.4184) time: 0.5056 [2021-03-26 06:22:01 swin_small_patch4_window7_224] INFO: Epoch: [147] [1050/1251] eta: 0:01:42 lr: 0.000516 loss: 3.2889 (3.3012) grad_norm: 1.4095 (1.4184) time: 0.5105 [2021-03-26 06:22:06 swin_small_patch4_window7_224] INFO: Epoch: [147] [1060/1251] eta: 0:01:37 lr: 0.000516 loss: 3.2071 (3.2987) grad_norm: 1.3391 (1.4179) time: 0.5049 [2021-03-26 06:22:11 swin_small_patch4_window7_224] INFO: Epoch: [147] [1070/1251] eta: 0:01:32 lr: 0.000516 loss: 3.1867 (3.2995) grad_norm: 1.3132 (1.4173) time: 0.5053 [2021-03-26 06:22:16 swin_small_patch4_window7_224] INFO: Epoch: [147] [1080/1251] eta: 0:01:27 lr: 0.000516 loss: 3.3685 (3.2987) grad_norm: 1.3271 (1.4173) time: 0.5147 [2021-03-26 06:22:21 swin_small_patch4_window7_224] INFO: Epoch: [147] [1090/1251] eta: 0:01:22 lr: 0.000516 loss: 3.4214 (3.2991) grad_norm: 1.4451 (1.4176) time: 0.5122 [2021-03-26 06:22:26 swin_small_patch4_window7_224] INFO: Epoch: [147] [1100/1251] eta: 0:01:17 lr: 0.000516 loss: 3.4949 (3.3001) grad_norm: 1.4461 (1.4184) time: 0.5043 [2021-03-26 06:22:31 swin_small_patch4_window7_224] INFO: Epoch: [147] [1110/1251] eta: 0:01:11 lr: 0.000516 loss: 3.3508 (3.3001) grad_norm: 1.4461 (1.4185) time: 0.5034 [2021-03-26 06:22:36 swin_small_patch4_window7_224] INFO: Epoch: [147] [1120/1251] eta: 0:01:06 lr: 0.000516 loss: 3.1733 (3.2997) grad_norm: 1.4149 (1.4183) time: 0.5088 [2021-03-26 06:22:41 swin_small_patch4_window7_224] INFO: Epoch: [147] [1130/1251] eta: 0:01:01 lr: 0.000516 loss: 3.1733 (3.2982) grad_norm: 1.3347 (1.4175) time: 0.5119 [2021-03-26 06:22:46 swin_small_patch4_window7_224] INFO: Epoch: [147] [1140/1251] eta: 0:00:56 lr: 0.000516 loss: 3.3509 (3.2975) grad_norm: 1.3172 (1.4171) time: 0.5070 [2021-03-26 06:22:51 swin_small_patch4_window7_224] INFO: Epoch: [147] [1150/1251] eta: 0:00:51 lr: 0.000516 loss: 3.3509 (3.2989) grad_norm: 1.3451 (1.4169) time: 0.5053 [2021-03-26 06:22:57 swin_small_patch4_window7_224] INFO: Epoch: [147] [1160/1251] eta: 0:00:46 lr: 0.000516 loss: 3.5678 (3.3004) grad_norm: 1.4044 (1.4172) time: 0.5089 [2021-03-26 06:23:02 swin_small_patch4_window7_224] INFO: Epoch: [147] [1170/1251] eta: 0:00:41 lr: 0.000516 loss: 3.5736 (3.3030) grad_norm: 1.3895 (1.4169) time: 0.5071 [2021-03-26 06:23:07 swin_small_patch4_window7_224] INFO: Epoch: [147] [1180/1251] eta: 0:00:36 lr: 0.000516 loss: 3.4251 (3.3031) grad_norm: 1.3895 (1.4168) time: 0.5031 [2021-03-26 06:23:12 swin_small_patch4_window7_224] INFO: Epoch: [147] [1190/1251] eta: 0:00:31 lr: 0.000516 loss: 3.3325 (3.3024) grad_norm: 1.3996 (1.4166) time: 0.5085 [2021-03-26 06:23:17 swin_small_patch4_window7_224] INFO: Epoch: [147] [1200/1251] eta: 0:00:25 lr: 0.000516 loss: 3.2142 (3.3013) grad_norm: 1.4429 (1.4175) time: 0.5104 [2021-03-26 06:23:22 swin_small_patch4_window7_224] INFO: Epoch: [147] [1210/1251] eta: 0:00:20 lr: 0.000516 loss: 3.4851 (3.3014) grad_norm: 1.4581 (1.4182) time: 0.5096 [2021-03-26 06:23:27 swin_small_patch4_window7_224] INFO: Epoch: [147] [1220/1251] eta: 0:00:15 lr: 0.000515 loss: 3.4851 (3.3022) grad_norm: 1.4283 (1.4184) time: 0.5082 [2021-03-26 06:23:32 swin_small_patch4_window7_224] INFO: Epoch: [147] [1230/1251] eta: 0:00:10 lr: 0.000515 loss: 3.2901 (3.3011) grad_norm: 1.4208 (1.4187) time: 0.5067 [2021-03-26 06:23:37 swin_small_patch4_window7_224] INFO: Epoch: [147] [1240/1251] eta: 0:00:05 lr: 0.000515 loss: 3.3570 (3.3020) grad_norm: 1.3838 (1.4184) time: 0.5079 [2021-03-26 06:23:42 swin_small_patch4_window7_224] INFO: Epoch: [147] [1250/1251] eta: 0:00:00 lr: 0.000515 loss: 3.4346 (3.3030) grad_norm: 1.3830 (1.4185) time: 0.4999 [2021-03-26 06:23:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:20 loss: 1.0722 (1.0722) acc1: 71.8750 (71.8750) acc5: 92.1875 (92.1875) [2021-03-26 06:23:51 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8919 (0.9077) acc1: 76.5625 (76.8466) acc5: 92.1875 (93.6080) [2021-03-26 06:23:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8769 (0.9422) acc1: 76.5625 (76.4881) acc5: 93.7500 (93.6012) [2021-03-26 06:23:55 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9635 (0.9495) acc1: 78.1250 (76.6633) acc5: 93.7500 (93.7500) [2021-03-26 06:23:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9402 (0.9496) acc1: 78.1250 (76.7912) acc5: 93.7500 (93.9024) [2021-03-26 06:23:58 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9036 (0.9411) acc1: 78.1250 (76.8640) acc5: 95.3125 (94.2720) [2021-03-26 06:24:04 swin_small_patch4_window7_224] INFO: * Acc@1 78.166 Acc@5 94.460 loss 0.929 [2021-03-26 06:24:04 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.2% [2021-03-26 06:24:04 swin_small_patch4_window7_224] INFO: Max accuracy: 78.26% [2021-03-26 06:24:08 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 0/1251] eta: 1:28:45 lr: 0.000515 loss: 3.4419 (3.4419) grad_norm: 1.6095 (1.6095) time: 4.2571 [2021-03-26 06:24:13 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 10/1251] eta: 0:17:42 lr: 0.000515 loss: 3.4749 (3.5228) grad_norm: 1.3977 (1.4118) time: 0.8564 [2021-03-26 06:24:18 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 20/1251] eta: 0:14:05 lr: 0.000515 loss: 3.4749 (3.4891) grad_norm: 1.3162 (1.3630) time: 0.5083 [2021-03-26 06:24:23 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 30/1251] eta: 0:12:46 lr: 0.000515 loss: 3.4512 (3.4443) grad_norm: 1.3771 (1.4104) time: 0.5020 [2021-03-26 06:24:28 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 40/1251] eta: 0:12:05 lr: 0.000515 loss: 3.5785 (3.4550) grad_norm: 1.4656 (1.4129) time: 0.5074 [2021-03-26 06:24:34 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 50/1251] eta: 0:11:40 lr: 0.000515 loss: 3.4247 (3.4286) grad_norm: 1.3688 (1.4033) time: 0.5137 [2021-03-26 06:24:39 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 60/1251] eta: 0:11:22 lr: 0.000515 loss: 3.2308 (3.4048) grad_norm: 1.3951 (1.4085) time: 0.5185 [2021-03-26 06:24:44 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 70/1251] eta: 0:11:03 lr: 0.000515 loss: 3.2054 (3.3859) grad_norm: 1.3951 (1.4038) time: 0.5076 [2021-03-26 06:24:49 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 80/1251] eta: 0:10:48 lr: 0.000515 loss: 3.2358 (3.3765) grad_norm: 1.3543 (1.3987) time: 0.4969 [2021-03-26 06:24:54 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 90/1251] eta: 0:10:37 lr: 0.000515 loss: 3.2358 (3.3801) grad_norm: 1.3558 (1.3944) time: 0.5033 [2021-03-26 06:24:59 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 100/1251] eta: 0:10:26 lr: 0.000515 loss: 3.1672 (3.3504) grad_norm: 1.3681 (1.3895) time: 0.5055 [2021-03-26 06:25:04 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 110/1251] eta: 0:10:17 lr: 0.000515 loss: 3.0708 (3.3438) grad_norm: 1.3599 (1.3894) time: 0.5050 [2021-03-26 06:25:09 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 120/1251] eta: 0:10:07 lr: 0.000515 loss: 3.4144 (3.3423) grad_norm: 1.3237 (1.3846) time: 0.5024 [2021-03-26 06:25:14 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 130/1251] eta: 0:09:59 lr: 0.000515 loss: 3.4498 (3.3488) grad_norm: 1.2869 (1.3801) time: 0.5023 [2021-03-26 06:25:19 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 140/1251] eta: 0:09:52 lr: 0.000515 loss: 3.3621 (3.3378) grad_norm: 1.2827 (1.3796) time: 0.5102 [2021-03-26 06:25:24 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 150/1251] eta: 0:09:45 lr: 0.000515 loss: 3.1667 (3.3124) grad_norm: 1.4156 (1.3889) time: 0.5124 [2021-03-26 06:25:29 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 160/1251] eta: 0:09:39 lr: 0.000515 loss: 3.1071 (3.2899) grad_norm: 1.4486 (1.3902) time: 0.5103 [2021-03-26 06:25:34 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 170/1251] eta: 0:09:32 lr: 0.000515 loss: 3.1193 (3.2838) grad_norm: 1.3817 (1.3928) time: 0.5114 [2021-03-26 06:25:40 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 180/1251] eta: 0:09:26 lr: 0.000515 loss: 3.3934 (3.2917) grad_norm: 1.3817 (1.3982) time: 0.5138 [2021-03-26 06:25:45 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 190/1251] eta: 0:09:20 lr: 0.000515 loss: 3.3948 (3.2920) grad_norm: 1.4527 (1.4023) time: 0.5158 [2021-03-26 06:25:50 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 200/1251] eta: 0:09:14 lr: 0.000515 loss: 3.3527 (3.2881) grad_norm: 1.4058 (1.4005) time: 0.5144 [2021-03-26 06:25:55 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 210/1251] eta: 0:09:07 lr: 0.000514 loss: 3.3633 (3.2875) grad_norm: 1.3352 (1.4008) time: 0.5022 [2021-03-26 06:26:00 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 220/1251] eta: 0:09:00 lr: 0.000514 loss: 3.4688 (3.2935) grad_norm: 1.3150 (1.3986) time: 0.4959 [2021-03-26 06:26:05 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 230/1251] eta: 0:08:54 lr: 0.000514 loss: 3.2061 (3.2884) grad_norm: 1.3521 (1.3993) time: 0.5016 [2021-03-26 06:26:10 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 240/1251] eta: 0:08:48 lr: 0.000514 loss: 3.1246 (3.2757) grad_norm: 1.3574 (1.3975) time: 0.5063 [2021-03-26 06:26:15 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 250/1251] eta: 0:08:43 lr: 0.000514 loss: 3.1790 (3.2796) grad_norm: 1.3419 (1.3981) time: 0.5146 [2021-03-26 06:26:20 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 260/1251] eta: 0:08:37 lr: 0.000514 loss: 3.5413 (3.2900) grad_norm: 1.3514 (1.3974) time: 0.5135 [2021-03-26 06:26:25 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 270/1251] eta: 0:08:31 lr: 0.000514 loss: 3.3291 (3.2885) grad_norm: 1.3798 (1.3986) time: 0.5027 [2021-03-26 06:26:30 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 280/1251] eta: 0:08:25 lr: 0.000514 loss: 3.1772 (3.2825) grad_norm: 1.3906 (1.4003) time: 0.4995 [2021-03-26 06:26:35 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 290/1251] eta: 0:08:20 lr: 0.000514 loss: 3.3537 (3.2896) grad_norm: 1.4148 (1.4025) time: 0.5063 [2021-03-26 06:26:40 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 300/1251] eta: 0:08:14 lr: 0.000514 loss: 3.4816 (3.2834) grad_norm: 1.4238 (1.4030) time: 0.5090 [2021-03-26 06:26:45 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 310/1251] eta: 0:08:08 lr: 0.000514 loss: 3.4756 (3.2881) grad_norm: 1.4009 (1.4035) time: 0.5037 [2021-03-26 06:26:51 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 320/1251] eta: 0:08:03 lr: 0.000514 loss: 3.5300 (3.2919) grad_norm: 1.3548 (1.4035) time: 0.5081 [2021-03-26 06:26:56 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 330/1251] eta: 0:07:57 lr: 0.000514 loss: 3.5300 (3.2981) grad_norm: 1.3883 (1.4058) time: 0.5079 [2021-03-26 06:27:01 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 340/1251] eta: 0:07:52 lr: 0.000514 loss: 3.2139 (3.2933) grad_norm: 1.4202 (1.4064) time: 0.5049 [2021-03-26 06:27:06 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 350/1251] eta: 0:07:46 lr: 0.000514 loss: 3.3260 (3.2973) grad_norm: 1.3795 (1.4051) time: 0.5060 [2021-03-26 06:27:11 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 360/1251] eta: 0:07:41 lr: 0.000514 loss: 3.4320 (3.2926) grad_norm: 1.3795 (1.4089) time: 0.5053 [2021-03-26 06:27:16 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 370/1251] eta: 0:07:36 lr: 0.000514 loss: 3.1514 (3.2857) grad_norm: 1.4235 (1.4091) time: 0.5130 [2021-03-26 06:27:21 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 380/1251] eta: 0:07:30 lr: 0.000514 loss: 3.3040 (3.2952) grad_norm: 1.4160 (1.4107) time: 0.5096 [2021-03-26 06:27:26 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 390/1251] eta: 0:07:25 lr: 0.000514 loss: 3.4582 (3.2941) grad_norm: 1.3891 (1.4110) time: 0.5017 [2021-03-26 06:27:31 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 400/1251] eta: 0:07:19 lr: 0.000514 loss: 3.3812 (3.2949) grad_norm: 1.4457 (1.4128) time: 0.5034 [2021-03-26 06:27:36 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 410/1251] eta: 0:07:14 lr: 0.000514 loss: 3.2938 (3.2887) grad_norm: 1.3840 (1.4123) time: 0.5094 [2021-03-26 06:27:41 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 420/1251] eta: 0:07:08 lr: 0.000514 loss: 3.1623 (3.2869) grad_norm: 1.3761 (1.4118) time: 0.5066 [2021-03-26 06:27:46 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 430/1251] eta: 0:07:03 lr: 0.000514 loss: 3.3328 (3.2873) grad_norm: 1.3988 (1.4133) time: 0.4989 [2021-03-26 06:27:51 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 440/1251] eta: 0:06:58 lr: 0.000514 loss: 3.3447 (3.2894) grad_norm: 1.3988 (1.4127) time: 0.5042 [2021-03-26 06:27:56 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 450/1251] eta: 0:06:52 lr: 0.000514 loss: 3.1231 (3.2839) grad_norm: 1.3213 (1.4110) time: 0.5055 [2021-03-26 06:28:01 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 460/1251] eta: 0:06:47 lr: 0.000513 loss: 3.2754 (3.2866) grad_norm: 1.3319 (1.4103) time: 0.5073 [2021-03-26 06:28:06 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 470/1251] eta: 0:06:42 lr: 0.000513 loss: 3.5490 (3.2900) grad_norm: 1.3470 (1.4107) time: 0.5102 [2021-03-26 06:28:12 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 480/1251] eta: 0:06:37 lr: 0.000513 loss: 3.6073 (3.2930) grad_norm: 1.3524 (1.4099) time: 0.5109 [2021-03-26 06:28:17 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 490/1251] eta: 0:06:31 lr: 0.000513 loss: 3.4239 (3.2903) grad_norm: 1.3509 (1.4096) time: 0.5086 [2021-03-26 06:28:22 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 500/1251] eta: 0:06:26 lr: 0.000513 loss: 3.2063 (3.2906) grad_norm: 1.3844 (1.4127) time: 0.5036 [2021-03-26 06:28:27 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 510/1251] eta: 0:06:21 lr: 0.000513 loss: 3.4316 (3.2920) grad_norm: 1.3917 (1.4132) time: 0.5033 [2021-03-26 06:28:32 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 520/1251] eta: 0:06:15 lr: 0.000513 loss: 3.4856 (3.2966) grad_norm: 1.3521 (1.4117) time: 0.5038 [2021-03-26 06:28:37 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 530/1251] eta: 0:06:10 lr: 0.000513 loss: 3.5600 (3.2985) grad_norm: 1.3577 (1.4116) time: 0.4997 [2021-03-26 06:28:42 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 540/1251] eta: 0:06:05 lr: 0.000513 loss: 3.4416 (3.2993) grad_norm: 1.4030 (1.4120) time: 0.5032 [2021-03-26 06:28:47 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 550/1251] eta: 0:06:00 lr: 0.000513 loss: 3.4065 (3.2975) grad_norm: 1.4030 (1.4123) time: 0.5119 [2021-03-26 06:28:52 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 560/1251] eta: 0:05:54 lr: 0.000513 loss: 3.5487 (3.3023) grad_norm: 1.3669 (1.4120) time: 0.5053 [2021-03-26 06:28:57 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 570/1251] eta: 0:05:49 lr: 0.000513 loss: 3.5728 (3.3048) grad_norm: 1.4216 (1.4132) time: 0.5000 [2021-03-26 06:29:02 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 580/1251] eta: 0:05:44 lr: 0.000513 loss: 3.5963 (3.3116) grad_norm: 1.3901 (1.4118) time: 0.5074 [2021-03-26 06:29:07 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 590/1251] eta: 0:05:39 lr: 0.000513 loss: 3.4981 (3.3083) grad_norm: 1.3366 (1.4112) time: 0.5154 [2021-03-26 06:29:12 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 600/1251] eta: 0:05:34 lr: 0.000513 loss: 3.3224 (3.3095) grad_norm: 1.3841 (1.4112) time: 0.5105 [2021-03-26 06:29:17 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 610/1251] eta: 0:05:28 lr: 0.000513 loss: 3.4650 (3.3091) grad_norm: 1.4232 (1.4105) time: 0.5067 [2021-03-26 06:29:22 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 620/1251] eta: 0:05:23 lr: 0.000513 loss: 3.4350 (3.3072) grad_norm: 1.3564 (1.4104) time: 0.5088 [2021-03-26 06:29:28 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 630/1251] eta: 0:05:18 lr: 0.000513 loss: 3.0739 (3.3057) grad_norm: 1.4225 (1.4115) time: 0.5046 [2021-03-26 06:29:33 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 640/1251] eta: 0:05:13 lr: 0.000513 loss: 3.1897 (3.3043) grad_norm: 1.4225 (1.4115) time: 0.5041 [2021-03-26 06:29:38 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 650/1251] eta: 0:05:08 lr: 0.000513 loss: 3.5824 (3.3101) grad_norm: 1.4130 (1.4114) time: 0.5078 [2021-03-26 06:29:43 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 660/1251] eta: 0:05:02 lr: 0.000513 loss: 3.5072 (3.3073) grad_norm: 1.3634 (1.4107) time: 0.5083 [2021-03-26 06:29:48 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 670/1251] eta: 0:04:57 lr: 0.000513 loss: 3.3405 (3.3053) grad_norm: 1.3634 (1.4104) time: 0.5043 [2021-03-26 06:29:53 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 680/1251] eta: 0:04:52 lr: 0.000513 loss: 3.4726 (3.3088) grad_norm: 1.3760 (1.4101) time: 0.5033 [2021-03-26 06:29:58 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 690/1251] eta: 0:04:47 lr: 0.000513 loss: 3.6031 (3.3094) grad_norm: 1.3570 (1.4101) time: 0.5090 [2021-03-26 06:30:03 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 700/1251] eta: 0:04:42 lr: 0.000512 loss: 3.5020 (3.3100) grad_norm: 1.3713 (1.4102) time: 0.5095 [2021-03-26 06:30:08 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 710/1251] eta: 0:04:37 lr: 0.000512 loss: 3.5020 (3.3084) grad_norm: 1.3590 (1.4097) time: 0.5048 [2021-03-26 06:30:13 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 720/1251] eta: 0:04:31 lr: 0.000512 loss: 3.4634 (3.3114) grad_norm: 1.3956 (1.4103) time: 0.5105 [2021-03-26 06:30:18 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 730/1251] eta: 0:04:26 lr: 0.000512 loss: 3.4474 (3.3098) grad_norm: 1.3795 (1.4091) time: 0.5117 [2021-03-26 06:30:23 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 740/1251] eta: 0:04:21 lr: 0.000512 loss: 2.9733 (3.3071) grad_norm: 1.3649 (1.4084) time: 0.5098 [2021-03-26 06:30:29 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 750/1251] eta: 0:04:16 lr: 0.000512 loss: 3.3552 (3.3074) grad_norm: 1.3759 (1.4086) time: 0.5118 [2021-03-26 06:30:34 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 760/1251] eta: 0:04:11 lr: 0.000512 loss: 3.4742 (3.3070) grad_norm: 1.3781 (1.4090) time: 0.5057 [2021-03-26 06:30:39 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 770/1251] eta: 0:04:06 lr: 0.000512 loss: 3.2560 (3.3059) grad_norm: 1.3729 (1.4086) time: 0.5021 [2021-03-26 06:30:44 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 780/1251] eta: 0:04:00 lr: 0.000512 loss: 3.0673 (3.3029) grad_norm: 1.3440 (1.4076) time: 0.5007 [2021-03-26 06:30:49 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 790/1251] eta: 0:03:55 lr: 0.000512 loss: 3.2367 (3.3051) grad_norm: 1.4059 (1.4085) time: 0.5099 [2021-03-26 06:30:54 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 800/1251] eta: 0:03:50 lr: 0.000512 loss: 3.3309 (3.3032) grad_norm: 1.4697 (1.4101) time: 0.5203 [2021-03-26 06:30:59 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 810/1251] eta: 0:03:45 lr: 0.000512 loss: 3.4259 (3.3047) grad_norm: 1.4451 (1.4104) time: 0.5149 [2021-03-26 06:31:04 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 820/1251] eta: 0:03:40 lr: 0.000512 loss: 3.4453 (3.3059) grad_norm: 1.3854 (1.4103) time: 0.5070 [2021-03-26 06:31:09 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 830/1251] eta: 0:03:35 lr: 0.000512 loss: 3.5334 (3.3085) grad_norm: 1.3551 (1.4098) time: 0.5047 [2021-03-26 06:31:14 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 840/1251] eta: 0:03:30 lr: 0.000512 loss: 3.5334 (3.3088) grad_norm: 1.3701 (1.4104) time: 0.5049 [2021-03-26 06:31:19 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 850/1251] eta: 0:03:25 lr: 0.000512 loss: 3.3159 (3.3086) grad_norm: 1.4305 (1.4106) time: 0.5083 [2021-03-26 06:31:24 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 860/1251] eta: 0:03:19 lr: 0.000512 loss: 3.4632 (3.3125) grad_norm: 1.3861 (1.4100) time: 0.5058 [2021-03-26 06:31:29 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 870/1251] eta: 0:03:14 lr: 0.000512 loss: 3.5639 (3.3118) grad_norm: 1.3846 (1.4104) time: 0.5020 [2021-03-26 06:31:34 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 880/1251] eta: 0:03:09 lr: 0.000512 loss: 3.3814 (3.3121) grad_norm: 1.4121 (1.4103) time: 0.5055 [2021-03-26 06:31:40 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 890/1251] eta: 0:03:04 lr: 0.000512 loss: 3.3265 (3.3116) grad_norm: 1.3666 (1.4104) time: 0.5067 [2021-03-26 06:31:45 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 900/1251] eta: 0:02:59 lr: 0.000512 loss: 3.2989 (3.3102) grad_norm: 1.3064 (1.4092) time: 0.5045 [2021-03-26 06:31:50 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 910/1251] eta: 0:02:54 lr: 0.000512 loss: 3.2989 (3.3110) grad_norm: 1.3178 (1.4090) time: 0.5094 [2021-03-26 06:31:55 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 920/1251] eta: 0:02:49 lr: 0.000512 loss: 3.2339 (3.3072) grad_norm: 1.4214 (1.4092) time: 0.5121 [2021-03-26 06:32:00 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 930/1251] eta: 0:02:44 lr: 0.000512 loss: 3.2133 (3.3071) grad_norm: 1.3891 (1.4092) time: 0.5111 [2021-03-26 06:32:05 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 940/1251] eta: 0:02:38 lr: 0.000511 loss: 3.3596 (3.3083) grad_norm: 1.3645 (1.4088) time: 0.5112 [2021-03-26 06:32:10 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 950/1251] eta: 0:02:33 lr: 0.000511 loss: 3.2997 (3.3069) grad_norm: 1.3993 (1.4091) time: 0.5013 [2021-03-26 06:32:15 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 960/1251] eta: 0:02:28 lr: 0.000511 loss: 3.2485 (3.3077) grad_norm: 1.4176 (1.4090) time: 0.4978 [2021-03-26 06:32:20 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 970/1251] eta: 0:02:23 lr: 0.000511 loss: 3.4308 (3.3101) grad_norm: 1.3384 (1.4088) time: 0.5018 [2021-03-26 06:32:25 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 980/1251] eta: 0:02:18 lr: 0.000511 loss: 3.5046 (3.3119) grad_norm: 1.2945 (1.4089) time: 0.5024 [2021-03-26 06:32:30 swin_small_patch4_window7_224] INFO: Epoch: [148] [ 990/1251] eta: 0:02:13 lr: 0.000511 loss: 3.4880 (3.3109) grad_norm: 1.3976 (1.4095) time: 0.5082 [2021-03-26 06:32:35 swin_small_patch4_window7_224] INFO: Epoch: [148] [1000/1251] eta: 0:02:08 lr: 0.000511 loss: 3.3481 (3.3107) grad_norm: 1.3976 (1.4097) time: 0.5101 [2021-03-26 06:32:40 swin_small_patch4_window7_224] INFO: Epoch: [148] [1010/1251] eta: 0:02:03 lr: 0.000511 loss: 3.4994 (3.3123) grad_norm: 1.3959 (1.4099) time: 0.5057 [2021-03-26 06:32:45 swin_small_patch4_window7_224] INFO: Epoch: [148] [1020/1251] eta: 0:01:57 lr: 0.000511 loss: 3.4551 (3.3122) grad_norm: 1.3551 (1.4093) time: 0.5083 [2021-03-26 06:32:50 swin_small_patch4_window7_224] INFO: Epoch: [148] [1030/1251] eta: 0:01:52 lr: 0.000511 loss: 3.4964 (3.3141) grad_norm: 1.3551 (1.4098) time: 0.5087 [2021-03-26 06:32:56 swin_small_patch4_window7_224] INFO: Epoch: [148] [1040/1251] eta: 0:01:47 lr: 0.000511 loss: 3.6163 (3.3159) grad_norm: 1.4320 (1.4098) time: 0.5105 [2021-03-26 06:33:01 swin_small_patch4_window7_224] INFO: Epoch: [148] [1050/1251] eta: 0:01:42 lr: 0.000511 loss: 3.4200 (3.3145) grad_norm: 1.3897 (1.4092) time: 0.5071 [2021-03-26 06:33:06 swin_small_patch4_window7_224] INFO: Epoch: [148] [1060/1251] eta: 0:01:37 lr: 0.000511 loss: 3.2347 (3.3153) grad_norm: 1.3204 (1.4093) time: 0.4969 [2021-03-26 06:33:11 swin_small_patch4_window7_224] INFO: Epoch: [148] [1070/1251] eta: 0:01:32 lr: 0.000511 loss: 3.3904 (3.3148) grad_norm: 1.3630 (1.4090) time: 0.5015 [2021-03-26 06:33:16 swin_small_patch4_window7_224] INFO: Epoch: [148] [1080/1251] eta: 0:01:27 lr: 0.000511 loss: 3.4903 (3.3150) grad_norm: 1.4157 (1.4098) time: 0.5026 [2021-03-26 06:33:21 swin_small_patch4_window7_224] INFO: Epoch: [148] [1090/1251] eta: 0:01:22 lr: 0.000511 loss: 3.5280 (3.3158) grad_norm: 1.4465 (1.4107) time: 0.4953 [2021-03-26 06:33:26 swin_small_patch4_window7_224] INFO: Epoch: [148] [1100/1251] eta: 0:01:17 lr: 0.000511 loss: 3.3314 (3.3134) grad_norm: 1.4224 (1.4107) time: 0.4964 [2021-03-26 06:33:31 swin_small_patch4_window7_224] INFO: Epoch: [148] [1110/1251] eta: 0:01:11 lr: 0.000511 loss: 3.2602 (3.3146) grad_norm: 1.4042 (1.4102) time: 0.5006 [2021-03-26 06:33:36 swin_small_patch4_window7_224] INFO: Epoch: [148] [1120/1251] eta: 0:01:06 lr: 0.000511 loss: 3.4537 (3.3150) grad_norm: 1.4045 (1.4106) time: 0.5048 [2021-03-26 06:33:41 swin_small_patch4_window7_224] INFO: Epoch: [148] [1130/1251] eta: 0:01:01 lr: 0.000511 loss: 3.4214 (3.3161) grad_norm: 1.3962 (1.4102) time: 0.5041 [2021-03-26 06:33:46 swin_small_patch4_window7_224] INFO: Epoch: [148] [1140/1251] eta: 0:00:56 lr: 0.000511 loss: 3.4214 (3.3149) grad_norm: 1.3703 (1.4100) time: 0.5033 [2021-03-26 06:33:51 swin_small_patch4_window7_224] INFO: Epoch: [148] [1150/1251] eta: 0:00:51 lr: 0.000511 loss: 3.2414 (3.3110) grad_norm: 1.3702 (1.4094) time: 0.5050 [2021-03-26 06:33:56 swin_small_patch4_window7_224] INFO: Epoch: [148] [1160/1251] eta: 0:00:46 lr: 0.000511 loss: 3.2414 (3.3112) grad_norm: 1.3360 (1.4096) time: 0.5016 [2021-03-26 06:34:01 swin_small_patch4_window7_224] INFO: Epoch: [148] [1170/1251] eta: 0:00:41 lr: 0.000511 loss: 3.3635 (3.3109) grad_norm: 1.3693 (1.4094) time: 0.5025 [2021-03-26 06:34:06 swin_small_patch4_window7_224] INFO: Epoch: [148] [1180/1251] eta: 0:00:36 lr: 0.000510 loss: 3.3876 (3.3123) grad_norm: 1.3693 (1.4091) time: 0.5045 [2021-03-26 06:34:11 swin_small_patch4_window7_224] INFO: Epoch: [148] [1190/1251] eta: 0:00:31 lr: 0.000510 loss: 3.6291 (3.3139) grad_norm: 1.3408 (1.4089) time: 0.5045 [2021-03-26 06:34:16 swin_small_patch4_window7_224] INFO: Epoch: [148] [1200/1251] eta: 0:00:25 lr: 0.000510 loss: 3.4878 (3.3151) grad_norm: 1.3374 (1.4086) time: 0.5029 [2021-03-26 06:34:21 swin_small_patch4_window7_224] INFO: Epoch: [148] [1210/1251] eta: 0:00:20 lr: 0.000510 loss: 3.4230 (3.3156) grad_norm: 1.3374 (1.4085) time: 0.5033 [2021-03-26 06:34:26 swin_small_patch4_window7_224] INFO: Epoch: [148] [1220/1251] eta: 0:00:15 lr: 0.000510 loss: 3.3931 (3.3162) grad_norm: 1.3658 (1.4083) time: 0.5075 [2021-03-26 06:34:31 swin_small_patch4_window7_224] INFO: Epoch: [148] [1230/1251] eta: 0:00:10 lr: 0.000510 loss: 3.3482 (3.3165) grad_norm: 1.3957 (1.4086) time: 0.5069 [2021-03-26 06:34:36 swin_small_patch4_window7_224] INFO: Epoch: [148] [1240/1251] eta: 0:00:05 lr: 0.000510 loss: 3.2263 (3.3146) grad_norm: 1.4405 (1.4099) time: 0.5039 [2021-03-26 06:34:41 swin_small_patch4_window7_224] INFO: Epoch: [148] [1250/1251] eta: 0:00:00 lr: 0.000510 loss: 3.1829 (3.3137) grad_norm: 1.4353 (1.4099) time: 0.5000 [2021-03-26 06:34:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:31 loss: 0.9880 (0.9880) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-26 06:34:49 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9709 (0.9693) acc1: 76.5625 (76.8466) acc5: 93.7500 (94.4602) [2021-03-26 06:34:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9199 (0.9479) acc1: 76.5625 (77.6042) acc5: 95.3125 (94.7173) [2021-03-26 06:34:56 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8819 (0.9151) acc1: 79.6875 (78.1250) acc5: 95.3125 (94.8085) [2021-03-26 06:34:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8999 (0.9342) acc1: 78.1250 (77.3628) acc5: 93.7500 (94.6265) [2021-03-26 06:34:58 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9411 (0.9434) acc1: 76.5625 (77.4720) acc5: 93.7500 (94.5280) [2021-03-26 06:35:05 swin_small_patch4_window7_224] INFO: * Acc@1 78.344 Acc@5 94.336 loss 0.922 [2021-03-26 06:35:05 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.3% [2021-03-26 06:35:05 swin_small_patch4_window7_224] INFO: Max accuracy: 78.34% [2021-03-26 06:35:09 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 0/1251] eta: 1:23:49 lr: 0.000510 loss: 3.7130 (3.7130) grad_norm: 1.5019 (1.5019) time: 4.0205 [2021-03-26 06:35:14 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 10/1251] eta: 0:17:38 lr: 0.000510 loss: 3.2572 (3.1393) grad_norm: 1.4293 (1.3894) time: 0.8531 [2021-03-26 06:35:19 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 20/1251] eta: 0:14:04 lr: 0.000510 loss: 3.2046 (3.1854) grad_norm: 1.3560 (1.3666) time: 0.5194 [2021-03-26 06:35:24 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 30/1251] eta: 0:12:50 lr: 0.000510 loss: 3.3119 (3.2224) grad_norm: 1.3707 (1.3876) time: 0.5094 [2021-03-26 06:35:29 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 40/1251] eta: 0:12:10 lr: 0.000510 loss: 3.3457 (3.2220) grad_norm: 1.4092 (1.3924) time: 0.5162 [2021-03-26 06:35:34 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 50/1251] eta: 0:11:41 lr: 0.000510 loss: 3.3664 (3.2473) grad_norm: 1.3974 (1.4039) time: 0.5118 [2021-03-26 06:35:40 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 60/1251] eta: 0:11:20 lr: 0.000510 loss: 3.3684 (3.2723) grad_norm: 1.4305 (1.4118) time: 0.5062 [2021-03-26 06:35:45 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 70/1251] eta: 0:11:04 lr: 0.000510 loss: 3.2705 (3.2870) grad_norm: 1.4606 (1.4361) time: 0.5071 [2021-03-26 06:35:50 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 80/1251] eta: 0:10:48 lr: 0.000510 loss: 3.5383 (3.2885) grad_norm: 1.5330 (1.4578) time: 0.5016 [2021-03-26 06:35:55 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 90/1251] eta: 0:10:37 lr: 0.000510 loss: 3.5062 (3.2962) grad_norm: 1.4927 (1.4556) time: 0.5012 [2021-03-26 06:36:00 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 100/1251] eta: 0:10:27 lr: 0.000510 loss: 3.5062 (3.3040) grad_norm: 1.4472 (1.4514) time: 0.5092 [2021-03-26 06:36:05 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 110/1251] eta: 0:10:18 lr: 0.000510 loss: 3.3713 (3.3091) grad_norm: 1.4203 (1.4552) time: 0.5108 [2021-03-26 06:36:10 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 120/1251] eta: 0:10:09 lr: 0.000510 loss: 3.3938 (3.3182) grad_norm: 1.4504 (1.4594) time: 0.5071 [2021-03-26 06:36:15 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 130/1251] eta: 0:10:00 lr: 0.000510 loss: 3.3938 (3.2977) grad_norm: 1.5076 (1.4610) time: 0.4987 [2021-03-26 06:36:20 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 140/1251] eta: 0:09:52 lr: 0.000510 loss: 3.3820 (3.3075) grad_norm: 1.4218 (1.4589) time: 0.5016 [2021-03-26 06:36:25 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 150/1251] eta: 0:09:45 lr: 0.000510 loss: 3.4464 (3.2989) grad_norm: 1.3962 (1.4547) time: 0.5046 [2021-03-26 06:36:30 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 160/1251] eta: 0:09:37 lr: 0.000510 loss: 3.2749 (3.3025) grad_norm: 1.3644 (inf) time: 0.4997 [2021-03-26 06:36:35 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 170/1251] eta: 0:09:30 lr: 0.000509 loss: 3.2749 (3.3025) grad_norm: 1.3854 (inf) time: 0.5030 [2021-03-26 06:36:40 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 180/1251] eta: 0:09:25 lr: 0.000509 loss: 3.1231 (3.2909) grad_norm: 1.4328 (inf) time: 0.5135 [2021-03-26 06:36:45 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 190/1251] eta: 0:09:19 lr: 0.000509 loss: 3.1953 (3.3018) grad_norm: 1.4240 (inf) time: 0.5166 [2021-03-26 06:36:50 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 200/1251] eta: 0:09:12 lr: 0.000509 loss: 3.2861 (3.3003) grad_norm: 1.4137 (inf) time: 0.5086 [2021-03-26 06:36:55 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 210/1251] eta: 0:09:06 lr: 0.000509 loss: 3.1163 (3.2951) grad_norm: 1.4320 (inf) time: 0.5010 [2021-03-26 06:37:00 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 220/1251] eta: 0:09:00 lr: 0.000509 loss: 3.1249 (3.2913) grad_norm: 1.4511 (inf) time: 0.5045 [2021-03-26 06:37:05 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 230/1251] eta: 0:08:54 lr: 0.000509 loss: 3.2637 (3.2929) grad_norm: 1.4594 (inf) time: 0.5074 [2021-03-26 06:37:11 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 240/1251] eta: 0:08:47 lr: 0.000509 loss: 3.5312 (3.3107) grad_norm: 1.4295 (inf) time: 0.5038 [2021-03-26 06:37:16 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 250/1251] eta: 0:08:42 lr: 0.000509 loss: 3.5834 (3.3220) grad_norm: 1.3951 (inf) time: 0.5050 [2021-03-26 06:37:21 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 260/1251] eta: 0:08:35 lr: 0.000509 loss: 3.4828 (3.3173) grad_norm: 1.4337 (inf) time: 0.5020 [2021-03-26 06:37:26 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 270/1251] eta: 0:08:30 lr: 0.000509 loss: 3.3774 (3.3205) grad_norm: 1.4349 (inf) time: 0.5035 [2021-03-26 06:37:31 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 280/1251] eta: 0:08:24 lr: 0.000509 loss: 3.3774 (3.3127) grad_norm: 1.3883 (inf) time: 0.5108 [2021-03-26 06:37:36 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 290/1251] eta: 0:08:19 lr: 0.000509 loss: 3.3382 (3.3147) grad_norm: 1.3715 (inf) time: 0.5083 [2021-03-26 06:37:41 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 300/1251] eta: 0:08:13 lr: 0.000509 loss: 3.4560 (3.3164) grad_norm: 1.3715 (inf) time: 0.5016 [2021-03-26 06:37:46 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 310/1251] eta: 0:08:07 lr: 0.000509 loss: 3.5407 (3.3193) grad_norm: 1.3453 (inf) time: 0.4979 [2021-03-26 06:37:51 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 320/1251] eta: 0:08:02 lr: 0.000509 loss: 3.5407 (3.3168) grad_norm: 1.4205 (inf) time: 0.5037 [2021-03-26 06:37:56 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 330/1251] eta: 0:07:56 lr: 0.000509 loss: 3.1818 (3.3148) grad_norm: 1.4170 (inf) time: 0.5070 [2021-03-26 06:38:01 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 340/1251] eta: 0:07:50 lr: 0.000509 loss: 3.4032 (3.3137) grad_norm: 1.4051 (inf) time: 0.4994 [2021-03-26 06:38:06 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 350/1251] eta: 0:07:45 lr: 0.000509 loss: 3.4415 (3.3155) grad_norm: 1.3658 (inf) time: 0.5023 [2021-03-26 06:38:11 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 360/1251] eta: 0:07:39 lr: 0.000509 loss: 3.4678 (3.3162) grad_norm: 1.4070 (inf) time: 0.5033 [2021-03-26 06:38:16 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 370/1251] eta: 0:07:34 lr: 0.000509 loss: 3.5049 (3.3214) grad_norm: 1.3924 (inf) time: 0.5015 [2021-03-26 06:38:21 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 380/1251] eta: 0:07:29 lr: 0.000509 loss: 3.5218 (3.3213) grad_norm: 1.3427 (inf) time: 0.5122 [2021-03-26 06:38:26 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 390/1251] eta: 0:07:23 lr: 0.000509 loss: 3.2760 (3.3193) grad_norm: 1.3423 (inf) time: 0.5119 [2021-03-26 06:38:31 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 400/1251] eta: 0:07:18 lr: 0.000509 loss: 3.2796 (3.3222) grad_norm: 1.3304 (inf) time: 0.5059 [2021-03-26 06:38:36 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 410/1251] eta: 0:07:13 lr: 0.000508 loss: 3.5354 (3.3258) grad_norm: 1.3790 (inf) time: 0.5049 [2021-03-26 06:38:41 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 420/1251] eta: 0:07:07 lr: 0.000508 loss: 3.3486 (3.3191) grad_norm: 1.3882 (inf) time: 0.5056 [2021-03-26 06:38:46 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 430/1251] eta: 0:07:02 lr: 0.000508 loss: 3.4509 (3.3249) grad_norm: 1.4050 (inf) time: 0.5025 [2021-03-26 06:38:52 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 440/1251] eta: 0:06:57 lr: 0.000508 loss: 3.6030 (3.3287) grad_norm: 1.3889 (inf) time: 0.5036 [2021-03-26 06:38:56 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 450/1251] eta: 0:06:51 lr: 0.000508 loss: 3.3640 (3.3267) grad_norm: 1.3869 (inf) time: 0.5035 [2021-03-26 06:39:01 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 460/1251] eta: 0:06:46 lr: 0.000508 loss: 3.3640 (3.3257) grad_norm: 1.3778 (inf) time: 0.4984 [2021-03-26 06:39:07 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 470/1251] eta: 0:06:40 lr: 0.000508 loss: 3.4968 (3.3286) grad_norm: 1.3713 (inf) time: 0.5010 [2021-03-26 06:39:11 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 480/1251] eta: 0:06:35 lr: 0.000508 loss: 3.4968 (3.3286) grad_norm: 1.3920 (inf) time: 0.5001 [2021-03-26 06:39:16 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 490/1251] eta: 0:06:30 lr: 0.000508 loss: 3.3044 (3.3236) grad_norm: 1.3961 (inf) time: 0.4991 [2021-03-26 06:39:22 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 500/1251] eta: 0:06:25 lr: 0.000508 loss: 3.4281 (3.3267) grad_norm: 1.3860 (inf) time: 0.5060 [2021-03-26 06:39:27 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 510/1251] eta: 0:06:19 lr: 0.000508 loss: 3.5530 (3.3265) grad_norm: 1.3961 (inf) time: 0.5103 [2021-03-26 06:39:32 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 520/1251] eta: 0:06:14 lr: 0.000508 loss: 3.4995 (3.3228) grad_norm: 1.4457 (inf) time: 0.5044 [2021-03-26 06:39:37 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 530/1251] eta: 0:06:09 lr: 0.000508 loss: 3.1567 (3.3179) grad_norm: 1.4633 (inf) time: 0.5036 [2021-03-26 06:39:42 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 540/1251] eta: 0:06:04 lr: 0.000508 loss: 3.3135 (3.3207) grad_norm: 1.4176 (inf) time: 0.5035 [2021-03-26 06:39:47 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 550/1251] eta: 0:05:59 lr: 0.000508 loss: 3.4159 (3.3220) grad_norm: 1.3498 (inf) time: 0.5119 [2021-03-26 06:39:52 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 560/1251] eta: 0:05:53 lr: 0.000508 loss: 3.5140 (3.3234) grad_norm: 1.3498 (inf) time: 0.5151 [2021-03-26 06:39:57 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 570/1251] eta: 0:05:48 lr: 0.000508 loss: 3.3435 (3.3216) grad_norm: 1.3200 (inf) time: 0.5071 [2021-03-26 06:40:02 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 580/1251] eta: 0:05:43 lr: 0.000508 loss: 3.3268 (3.3216) grad_norm: 1.3966 (inf) time: 0.5057 [2021-03-26 06:40:07 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 590/1251] eta: 0:05:38 lr: 0.000508 loss: 3.4201 (3.3220) grad_norm: 1.4105 (inf) time: 0.5119 [2021-03-26 06:40:12 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 600/1251] eta: 0:05:33 lr: 0.000508 loss: 3.3591 (3.3197) grad_norm: 1.4047 (inf) time: 0.5112 [2021-03-26 06:40:17 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 610/1251] eta: 0:05:28 lr: 0.000508 loss: 3.3608 (3.3193) grad_norm: 1.4504 (inf) time: 0.5012 [2021-03-26 06:40:23 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 620/1251] eta: 0:05:22 lr: 0.000508 loss: 3.4432 (3.3205) grad_norm: 1.4504 (inf) time: 0.5039 [2021-03-26 06:40:28 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 630/1251] eta: 0:05:17 lr: 0.000508 loss: 3.4432 (3.3205) grad_norm: 1.4247 (inf) time: 0.5036 [2021-03-26 06:40:32 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 640/1251] eta: 0:05:12 lr: 0.000508 loss: 3.3138 (3.3214) grad_norm: 1.4586 (inf) time: 0.4967 [2021-03-26 06:40:37 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 650/1251] eta: 0:05:07 lr: 0.000507 loss: 3.2346 (3.3189) grad_norm: 1.4276 (inf) time: 0.4967 [2021-03-26 06:40:43 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 660/1251] eta: 0:05:02 lr: 0.000507 loss: 3.1504 (3.3169) grad_norm: 1.3659 (inf) time: 0.5053 [2021-03-26 06:40:48 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 670/1251] eta: 0:04:56 lr: 0.000507 loss: 3.2787 (3.3201) grad_norm: 1.4188 (inf) time: 0.5073 [2021-03-26 06:40:53 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 680/1251] eta: 0:04:51 lr: 0.000507 loss: 3.3599 (3.3194) grad_norm: 1.4188 (inf) time: 0.5031 [2021-03-26 06:40:58 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 690/1251] eta: 0:04:46 lr: 0.000507 loss: 3.3172 (3.3175) grad_norm: 1.4032 (inf) time: 0.5014 [2021-03-26 06:41:03 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 700/1251] eta: 0:04:41 lr: 0.000507 loss: 3.3053 (3.3134) grad_norm: 1.4310 (inf) time: 0.5034 [2021-03-26 06:41:08 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 710/1251] eta: 0:04:36 lr: 0.000507 loss: 3.0276 (3.3111) grad_norm: 1.4310 (inf) time: 0.5069 [2021-03-26 06:41:13 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 720/1251] eta: 0:04:31 lr: 0.000507 loss: 3.2015 (3.3108) grad_norm: 1.3424 (inf) time: 0.5073 [2021-03-26 06:41:18 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 730/1251] eta: 0:04:26 lr: 0.000507 loss: 3.2934 (3.3085) grad_norm: 1.4032 (inf) time: 0.5112 [2021-03-26 06:41:23 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 740/1251] eta: 0:04:21 lr: 0.000507 loss: 3.3081 (3.3069) grad_norm: 1.4771 (inf) time: 0.5204 [2021-03-26 06:41:28 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 750/1251] eta: 0:04:15 lr: 0.000507 loss: 3.1761 (3.3057) grad_norm: 1.4515 (inf) time: 0.5195 [2021-03-26 06:41:34 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 760/1251] eta: 0:04:10 lr: 0.000507 loss: 3.1761 (3.3062) grad_norm: 1.4188 (inf) time: 0.5131 [2021-03-26 06:41:39 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 770/1251] eta: 0:04:05 lr: 0.000507 loss: 3.1373 (3.3021) grad_norm: 1.3368 (inf) time: 0.5176 [2021-03-26 06:41:44 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 780/1251] eta: 0:04:00 lr: 0.000507 loss: 3.2306 (3.3009) grad_norm: 1.3368 (inf) time: 0.5263 [2021-03-26 06:41:49 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 790/1251] eta: 0:03:55 lr: 0.000507 loss: 3.3107 (3.2997) grad_norm: 1.3827 (inf) time: 0.5184 [2021-03-26 06:41:54 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 800/1251] eta: 0:03:50 lr: 0.000507 loss: 3.1595 (3.2961) grad_norm: 1.4406 (inf) time: 0.5064 [2021-03-26 06:41:59 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 810/1251] eta: 0:03:45 lr: 0.000507 loss: 3.1595 (3.2949) grad_norm: 1.4012 (inf) time: 0.5024 [2021-03-26 06:42:04 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 820/1251] eta: 0:03:40 lr: 0.000507 loss: 3.4606 (3.2933) grad_norm: 1.4012 (inf) time: 0.5013 [2021-03-26 06:42:09 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 830/1251] eta: 0:03:35 lr: 0.000507 loss: 3.4606 (3.2932) grad_norm: 1.3788 (inf) time: 0.5060 [2021-03-26 06:42:14 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 840/1251] eta: 0:03:29 lr: 0.000507 loss: 3.4714 (3.2953) grad_norm: 1.4392 (inf) time: 0.5038 [2021-03-26 06:42:19 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 850/1251] eta: 0:03:24 lr: 0.000507 loss: 3.4582 (3.2945) grad_norm: 1.4452 (inf) time: 0.5068 [2021-03-26 06:42:24 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 860/1251] eta: 0:03:19 lr: 0.000507 loss: 3.3780 (3.2911) grad_norm: 1.4347 (inf) time: 0.5078 [2021-03-26 06:42:30 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 870/1251] eta: 0:03:14 lr: 0.000507 loss: 3.2479 (3.2919) grad_norm: 1.4160 (inf) time: 0.5056 [2021-03-26 06:42:35 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 880/1251] eta: 0:03:09 lr: 0.000507 loss: 3.2479 (3.2902) grad_norm: 1.3214 (inf) time: 0.5035 [2021-03-26 06:42:40 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 890/1251] eta: 0:03:04 lr: 0.000506 loss: 3.4407 (3.2934) grad_norm: 1.3543 (inf) time: 0.5010 [2021-03-26 06:42:45 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 900/1251] eta: 0:02:59 lr: 0.000506 loss: 3.6012 (3.2954) grad_norm: 1.3925 (inf) time: 0.5021 [2021-03-26 06:42:50 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 910/1251] eta: 0:02:53 lr: 0.000506 loss: 3.6319 (3.2982) grad_norm: 1.3873 (inf) time: 0.4985 [2021-03-26 06:42:55 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 920/1251] eta: 0:02:48 lr: 0.000506 loss: 3.6226 (3.2983) grad_norm: 1.3851 (inf) time: 0.4982 [2021-03-26 06:43:00 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 930/1251] eta: 0:02:43 lr: 0.000506 loss: 3.4154 (3.2968) grad_norm: 1.3647 (inf) time: 0.5114 [2021-03-26 06:43:05 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 940/1251] eta: 0:02:38 lr: 0.000506 loss: 3.6312 (3.2999) grad_norm: 1.3585 (inf) time: 0.5140 [2021-03-26 06:43:10 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 950/1251] eta: 0:02:33 lr: 0.000506 loss: 3.6916 (3.3027) grad_norm: 1.4107 (inf) time: 0.4999 [2021-03-26 06:43:15 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 960/1251] eta: 0:02:28 lr: 0.000506 loss: 3.6196 (3.3047) grad_norm: 1.4362 (inf) time: 0.4958 [2021-03-26 06:43:20 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 970/1251] eta: 0:02:23 lr: 0.000506 loss: 3.4749 (3.3041) grad_norm: 1.3357 (inf) time: 0.5028 [2021-03-26 06:43:25 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 980/1251] eta: 0:02:18 lr: 0.000506 loss: 3.3145 (3.3045) grad_norm: 1.3262 (inf) time: 0.5035 [2021-03-26 06:43:30 swin_small_patch4_window7_224] INFO: Epoch: [149] [ 990/1251] eta: 0:02:13 lr: 0.000506 loss: 3.2723 (3.3049) grad_norm: 1.3597 (inf) time: 0.5120 [2021-03-26 06:43:35 swin_small_patch4_window7_224] INFO: Epoch: [149] [1000/1251] eta: 0:02:07 lr: 0.000506 loss: 3.2779 (3.3053) grad_norm: 1.4835 (inf) time: 0.5189 [2021-03-26 06:43:40 swin_small_patch4_window7_224] INFO: Epoch: [149] [1010/1251] eta: 0:02:02 lr: 0.000506 loss: 3.3428 (3.3047) grad_norm: 1.4414 (inf) time: 0.5097 [2021-03-26 06:43:45 swin_small_patch4_window7_224] INFO: Epoch: [149] [1020/1251] eta: 0:01:57 lr: 0.000506 loss: 3.5567 (3.3066) grad_norm: 1.3545 (inf) time: 0.5043 [2021-03-26 06:43:50 swin_small_patch4_window7_224] INFO: Epoch: [149] [1030/1251] eta: 0:01:52 lr: 0.000506 loss: 3.5567 (3.3082) grad_norm: 1.3092 (inf) time: 0.4971 [2021-03-26 06:43:55 swin_small_patch4_window7_224] INFO: Epoch: [149] [1040/1251] eta: 0:01:47 lr: 0.000506 loss: 3.4430 (3.3067) grad_norm: 1.4507 (inf) time: 0.5001 [2021-03-26 06:44:00 swin_small_patch4_window7_224] INFO: Epoch: [149] [1050/1251] eta: 0:01:42 lr: 0.000506 loss: 2.9430 (3.3033) grad_norm: 1.5059 (inf) time: 0.5046 [2021-03-26 06:44:05 swin_small_patch4_window7_224] INFO: Epoch: [149] [1060/1251] eta: 0:01:37 lr: 0.000506 loss: 3.0386 (3.3032) grad_norm: 1.4069 (inf) time: 0.5056 [2021-03-26 06:44:11 swin_small_patch4_window7_224] INFO: Epoch: [149] [1070/1251] eta: 0:01:32 lr: 0.000506 loss: 3.4768 (3.3023) grad_norm: 1.3468 (inf) time: 0.5119 [2021-03-26 06:44:16 swin_small_patch4_window7_224] INFO: Epoch: [149] [1080/1251] eta: 0:01:27 lr: 0.000506 loss: 3.2888 (3.3013) grad_norm: 1.3466 (inf) time: 0.5063 [2021-03-26 06:44:21 swin_small_patch4_window7_224] INFO: Epoch: [149] [1090/1251] eta: 0:01:22 lr: 0.000506 loss: 3.3431 (3.3022) grad_norm: 1.3605 (inf) time: 0.5008 [2021-03-26 06:44:26 swin_small_patch4_window7_224] INFO: Epoch: [149] [1100/1251] eta: 0:01:16 lr: 0.000506 loss: 3.3935 (3.3031) grad_norm: 1.3605 (inf) time: 0.4999 [2021-03-26 06:44:31 swin_small_patch4_window7_224] INFO: Epoch: [149] [1110/1251] eta: 0:01:11 lr: 0.000506 loss: 3.4206 (3.3026) grad_norm: 1.3432 (inf) time: 0.4990 [2021-03-26 06:44:36 swin_small_patch4_window7_224] INFO: Epoch: [149] [1120/1251] eta: 0:01:06 lr: 0.000506 loss: 3.2054 (3.3005) grad_norm: 1.3315 (inf) time: 0.5061 [2021-03-26 06:44:41 swin_small_patch4_window7_224] INFO: Epoch: [149] [1130/1251] eta: 0:01:01 lr: 0.000506 loss: 3.2725 (3.3024) grad_norm: 1.3382 (inf) time: 0.5070 [2021-03-26 06:44:46 swin_small_patch4_window7_224] INFO: Epoch: [149] [1140/1251] eta: 0:00:56 lr: 0.000505 loss: 3.4866 (3.3025) grad_norm: 1.4117 (nan) time: 0.4992 [2021-03-26 06:44:51 swin_small_patch4_window7_224] INFO: Epoch: [149] [1150/1251] eta: 0:00:51 lr: 0.000505 loss: 3.3506 (3.3046) grad_norm: 1.4356 (nan) time: 0.5009 [2021-03-26 06:44:56 swin_small_patch4_window7_224] INFO: Epoch: [149] [1160/1251] eta: 0:00:46 lr: 0.000505 loss: 3.4431 (3.3055) grad_norm: 1.3819 (nan) time: 0.5065 [2021-03-26 06:45:01 swin_small_patch4_window7_224] INFO: Epoch: [149] [1170/1251] eta: 0:00:41 lr: 0.000505 loss: 3.4823 (3.3065) grad_norm: 1.3882 (nan) time: 0.5035 [2021-03-26 06:45:06 swin_small_patch4_window7_224] INFO: Epoch: [149] [1180/1251] eta: 0:00:36 lr: 0.000505 loss: 3.2914 (3.3029) grad_norm: 1.4804 (nan) time: 0.5001 [2021-03-26 06:45:11 swin_small_patch4_window7_224] INFO: Epoch: [149] [1190/1251] eta: 0:00:31 lr: 0.000505 loss: 2.8844 (3.3022) grad_norm: 1.5093 (nan) time: 0.5021 [2021-03-26 06:45:16 swin_small_patch4_window7_224] INFO: Epoch: [149] [1200/1251] eta: 0:00:25 lr: 0.000505 loss: 3.2617 (3.3012) grad_norm: 1.5093 (nan) time: 0.5045 [2021-03-26 06:45:21 swin_small_patch4_window7_224] INFO: Epoch: [149] [1210/1251] eta: 0:00:20 lr: 0.000505 loss: 3.2658 (3.3009) grad_norm: 1.5122 (nan) time: 0.5058 [2021-03-26 06:45:26 swin_small_patch4_window7_224] INFO: Epoch: [149] [1220/1251] eta: 0:00:15 lr: 0.000505 loss: 3.5099 (3.3021) grad_norm: 1.3964 (nan) time: 0.5078 [2021-03-26 06:45:31 swin_small_patch4_window7_224] INFO: Epoch: [149] [1230/1251] eta: 0:00:10 lr: 0.000505 loss: 3.6092 (3.3023) grad_norm: 1.3496 (nan) time: 0.5032 [2021-03-26 06:45:36 swin_small_patch4_window7_224] INFO: Epoch: [149] [1240/1251] eta: 0:00:05 lr: 0.000505 loss: 3.0650 (3.2998) grad_norm: 1.4064 (nan) time: 0.5040 [2021-03-26 06:45:41 swin_small_patch4_window7_224] INFO: Epoch: [149] [1250/1251] eta: 0:00:00 lr: 0.000505 loss: 3.2104 (3.3000) grad_norm: 1.4499 (nan) time: 0.5067 [2021-03-26 06:45:51 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:51 loss: 0.8867 (0.8867) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-26 06:45:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8964 (0.9230) acc1: 78.1250 (78.5511) acc5: 95.3125 (94.3182) [2021-03-26 06:45:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8964 (0.9656) acc1: 76.5625 (77.0833) acc5: 93.7500 (93.8988) [2021-03-26 06:45:58 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8728 (0.9377) acc1: 76.5625 (77.5202) acc5: 95.3125 (94.2540) [2021-03-26 06:45:59 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8855 (0.9292) acc1: 76.5625 (77.3247) acc5: 95.3125 (94.3979) [2021-03-26 06:46:00 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9095 (0.9350) acc1: 76.5625 (77.3120) acc5: 94.3396 (94.5280) [2021-03-26 06:46:06 swin_small_patch4_window7_224] INFO: * Acc@1 78.206 Acc@5 94.448 loss 0.920 [2021-03-26 06:46:06 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.2% [2021-03-26 06:46:06 swin_small_patch4_window7_224] INFO: Max accuracy: 78.34% [2021-03-26 06:46:10 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 0/1251] eta: 1:22:24 lr: 0.000505 loss: 3.4971 (3.4971) grad_norm: 1.1256 (1.1256) time: 3.9528 [2021-03-26 06:46:15 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 10/1251] eta: 0:17:25 lr: 0.000505 loss: 3.4655 (3.3175) grad_norm: 1.3874 (1.3767) time: 0.8423 [2021-03-26 06:46:20 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 20/1251] eta: 0:14:03 lr: 0.000505 loss: 3.3777 (3.2853) grad_norm: 1.3874 (1.3918) time: 0.5215 [2021-03-26 06:46:25 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 30/1251] eta: 0:12:46 lr: 0.000505 loss: 3.3259 (3.2413) grad_norm: 1.4333 (1.4484) time: 0.5103 [2021-03-26 06:46:30 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 40/1251] eta: 0:12:03 lr: 0.000505 loss: 3.3707 (3.3110) grad_norm: 1.4583 (1.4487) time: 0.5053 [2021-03-26 06:46:35 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 50/1251] eta: 0:11:34 lr: 0.000505 loss: 3.5783 (3.3593) grad_norm: 1.4377 (1.4444) time: 0.5003 [2021-03-26 06:46:40 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 60/1251] eta: 0:11:15 lr: 0.000505 loss: 3.5848 (3.3898) grad_norm: 1.4005 (1.4345) time: 0.5042 [2021-03-26 06:46:45 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 70/1251] eta: 0:10:58 lr: 0.000505 loss: 3.6382 (3.3967) grad_norm: 1.4005 (1.4406) time: 0.5040 [2021-03-26 06:46:50 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 80/1251] eta: 0:10:44 lr: 0.000505 loss: 3.3871 (3.3738) grad_norm: 1.4107 (1.4387) time: 0.5018 [2021-03-26 06:46:56 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 90/1251] eta: 0:10:33 lr: 0.000505 loss: 3.4639 (3.3785) grad_norm: 1.4274 (1.4404) time: 0.5051 [2021-03-26 06:47:01 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 100/1251] eta: 0:10:23 lr: 0.000505 loss: 3.3695 (3.3524) grad_norm: 1.5076 (1.4534) time: 0.5059 [2021-03-26 06:47:06 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 110/1251] eta: 0:10:17 lr: 0.000505 loss: 3.1457 (3.3380) grad_norm: 1.5076 (1.4576) time: 0.5199 [2021-03-26 06:47:11 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 120/1251] eta: 0:10:07 lr: 0.000505 loss: 3.2634 (3.3373) grad_norm: 1.4800 (1.4606) time: 0.5150 [2021-03-26 06:47:16 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 130/1251] eta: 0:09:59 lr: 0.000504 loss: 3.0848 (3.3085) grad_norm: 1.4460 (1.4566) time: 0.5016 [2021-03-26 06:47:21 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 140/1251] eta: 0:09:51 lr: 0.000504 loss: 3.0677 (3.3117) grad_norm: 1.3422 (1.4513) time: 0.5004 [2021-03-26 06:47:26 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 150/1251] eta: 0:09:43 lr: 0.000504 loss: 3.3419 (3.3059) grad_norm: 1.3777 (1.4484) time: 0.4948 [2021-03-26 06:47:31 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 160/1251] eta: 0:09:36 lr: 0.000504 loss: 3.3262 (3.3080) grad_norm: 1.4303 (1.4563) time: 0.4984 [2021-03-26 06:47:36 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 170/1251] eta: 0:09:29 lr: 0.000504 loss: 3.3729 (3.3156) grad_norm: 1.4743 (1.4559) time: 0.5065 [2021-03-26 06:47:41 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 180/1251] eta: 0:09:23 lr: 0.000504 loss: 3.5320 (3.3250) grad_norm: 1.5073 (1.4712) time: 0.5145 [2021-03-26 06:47:46 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 190/1251] eta: 0:09:17 lr: 0.000504 loss: 3.4871 (3.3248) grad_norm: 1.4914 (1.4674) time: 0.5080 [2021-03-26 06:47:51 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 200/1251] eta: 0:09:11 lr: 0.000504 loss: 3.4199 (3.3230) grad_norm: 1.4193 (1.4675) time: 0.5085 [2021-03-26 06:47:56 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 210/1251] eta: 0:09:04 lr: 0.000504 loss: 3.3316 (3.3231) grad_norm: 1.5035 (1.4736) time: 0.5087 [2021-03-26 06:48:01 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 220/1251] eta: 0:08:58 lr: 0.000504 loss: 3.3998 (3.3276) grad_norm: 1.5233 (1.4767) time: 0.4995 [2021-03-26 06:48:06 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 230/1251] eta: 0:08:52 lr: 0.000504 loss: 3.3796 (3.3214) grad_norm: 1.4758 (1.4754) time: 0.5061 [2021-03-26 06:48:11 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 240/1251] eta: 0:08:46 lr: 0.000504 loss: 3.0409 (3.3036) grad_norm: 1.3884 (1.4709) time: 0.5080 [2021-03-26 06:48:16 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 250/1251] eta: 0:08:40 lr: 0.000504 loss: 2.9872 (3.2964) grad_norm: 1.3260 (1.4667) time: 0.5014 [2021-03-26 06:48:22 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 260/1251] eta: 0:08:34 lr: 0.000504 loss: 3.1896 (3.2955) grad_norm: 1.4326 (1.4680) time: 0.5007 [2021-03-26 06:48:27 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 270/1251] eta: 0:08:29 lr: 0.000504 loss: 3.3247 (3.2944) grad_norm: 1.4326 (1.4654) time: 0.5054 [2021-03-26 06:48:32 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 280/1251] eta: 0:08:23 lr: 0.000504 loss: 3.4289 (3.2921) grad_norm: 1.4542 (1.4669) time: 0.5082 [2021-03-26 06:48:37 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 290/1251] eta: 0:08:18 lr: 0.000504 loss: 3.1757 (3.2894) grad_norm: 1.4558 (1.4654) time: 0.5080 [2021-03-26 06:48:42 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 300/1251] eta: 0:08:12 lr: 0.000504 loss: 2.9872 (3.2804) grad_norm: 1.3935 (1.4619) time: 0.5025 [2021-03-26 06:48:47 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 310/1251] eta: 0:08:06 lr: 0.000504 loss: 3.3375 (3.2835) grad_norm: 1.4196 (1.4617) time: 0.5021 [2021-03-26 06:48:52 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 320/1251] eta: 0:08:01 lr: 0.000504 loss: 3.4843 (3.2883) grad_norm: 1.4175 (1.4592) time: 0.5079 [2021-03-26 06:48:57 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 330/1251] eta: 0:07:55 lr: 0.000504 loss: 3.4632 (3.2928) grad_norm: 1.4084 (1.4577) time: 0.5035 [2021-03-26 06:49:02 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 340/1251] eta: 0:07:50 lr: 0.000504 loss: 3.3904 (3.2899) grad_norm: 1.4230 (1.4579) time: 0.4966 [2021-03-26 06:49:07 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 350/1251] eta: 0:07:44 lr: 0.000504 loss: 3.3904 (3.2931) grad_norm: 1.3998 (1.4559) time: 0.5004 [2021-03-26 06:49:12 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 360/1251] eta: 0:07:39 lr: 0.000504 loss: 3.4654 (3.2873) grad_norm: 1.3998 (1.4559) time: 0.5067 [2021-03-26 06:49:17 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 370/1251] eta: 0:07:33 lr: 0.000503 loss: 3.0929 (3.2817) grad_norm: 1.4632 (1.4556) time: 0.5085 [2021-03-26 06:49:22 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 380/1251] eta: 0:07:28 lr: 0.000503 loss: 3.0170 (3.2741) grad_norm: 1.4654 (1.4596) time: 0.5086 [2021-03-26 06:49:27 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 390/1251] eta: 0:07:23 lr: 0.000503 loss: 3.3249 (3.2761) grad_norm: 1.4611 (1.4605) time: 0.5076 [2021-03-26 06:49:32 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 400/1251] eta: 0:07:18 lr: 0.000503 loss: 3.3383 (3.2749) grad_norm: 1.4302 (1.4596) time: 0.5081 [2021-03-26 06:49:37 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 410/1251] eta: 0:07:12 lr: 0.000503 loss: 3.3007 (3.2762) grad_norm: 1.3782 (1.4575) time: 0.5083 [2021-03-26 06:49:42 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 420/1251] eta: 0:07:07 lr: 0.000503 loss: 3.2032 (3.2697) grad_norm: 1.3782 (1.4587) time: 0.5083 [2021-03-26 06:49:48 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 430/1251] eta: 0:07:02 lr: 0.000503 loss: 3.2778 (3.2713) grad_norm: 1.4158 (1.4585) time: 0.5104 [2021-03-26 06:49:53 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 440/1251] eta: 0:06:56 lr: 0.000503 loss: 3.3195 (3.2712) grad_norm: 1.3756 (1.4579) time: 0.5059 [2021-03-26 06:49:58 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 450/1251] eta: 0:06:51 lr: 0.000503 loss: 3.2115 (3.2703) grad_norm: 1.3954 (1.4569) time: 0.5037 [2021-03-26 06:50:03 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 460/1251] eta: 0:06:46 lr: 0.000503 loss: 3.0659 (3.2614) grad_norm: 1.3954 (1.4558) time: 0.5069 [2021-03-26 06:50:08 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 470/1251] eta: 0:06:41 lr: 0.000503 loss: 2.9534 (3.2586) grad_norm: 1.3388 (1.4524) time: 0.5043 [2021-03-26 06:50:13 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 480/1251] eta: 0:06:35 lr: 0.000503 loss: 3.0420 (3.2537) grad_norm: 1.3507 (1.4526) time: 0.5088 [2021-03-26 06:50:18 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 490/1251] eta: 0:06:30 lr: 0.000503 loss: 3.0420 (3.2540) grad_norm: 1.3713 (1.4507) time: 0.5074 [2021-03-26 06:50:23 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 500/1251] eta: 0:06:25 lr: 0.000503 loss: 3.1285 (3.2495) grad_norm: 1.3840 (1.4516) time: 0.5029 [2021-03-26 06:50:28 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 510/1251] eta: 0:06:20 lr: 0.000503 loss: 3.0937 (3.2495) grad_norm: 1.4389 (1.4509) time: 0.5044 [2021-03-26 06:50:33 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 520/1251] eta: 0:06:14 lr: 0.000503 loss: 3.1766 (3.2482) grad_norm: 1.4152 (1.4510) time: 0.5078 [2021-03-26 06:50:38 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 530/1251] eta: 0:06:09 lr: 0.000503 loss: 3.2316 (3.2508) grad_norm: 1.4465 (1.4534) time: 0.5153 [2021-03-26 06:50:43 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 540/1251] eta: 0:06:04 lr: 0.000503 loss: 3.4810 (3.2533) grad_norm: 1.5032 (1.4536) time: 0.5154 [2021-03-26 06:50:49 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 550/1251] eta: 0:05:59 lr: 0.000503 loss: 3.4810 (3.2554) grad_norm: 1.4455 (1.4539) time: 0.5193 [2021-03-26 06:50:54 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 560/1251] eta: 0:05:54 lr: 0.000503 loss: 3.4546 (3.2590) grad_norm: 1.4455 (1.4541) time: 0.5161 [2021-03-26 06:50:59 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 570/1251] eta: 0:05:49 lr: 0.000503 loss: 3.5011 (3.2618) grad_norm: 1.3920 (1.4526) time: 0.5123 [2021-03-26 06:51:04 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 580/1251] eta: 0:05:44 lr: 0.000503 loss: 3.5011 (3.2634) grad_norm: 1.3642 (1.4507) time: 0.5124 [2021-03-26 06:51:09 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 590/1251] eta: 0:05:39 lr: 0.000503 loss: 3.2500 (3.2570) grad_norm: 1.3782 (1.4512) time: 0.5058 [2021-03-26 06:51:14 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 600/1251] eta: 0:05:33 lr: 0.000503 loss: 3.0901 (3.2581) grad_norm: 1.3782 (1.4498) time: 0.5105 [2021-03-26 06:51:19 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 610/1251] eta: 0:05:28 lr: 0.000502 loss: 3.5011 (3.2594) grad_norm: 1.3852 (1.4493) time: 0.5129 [2021-03-26 06:51:24 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 620/1251] eta: 0:05:23 lr: 0.000502 loss: 3.1421 (3.2575) grad_norm: 1.4105 (1.4483) time: 0.5039 [2021-03-26 06:51:29 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 630/1251] eta: 0:05:18 lr: 0.000502 loss: 3.1307 (3.2583) grad_norm: 1.4341 (1.4490) time: 0.5028 [2021-03-26 06:51:34 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 640/1251] eta: 0:05:13 lr: 0.000502 loss: 3.4077 (3.2598) grad_norm: 1.4501 (1.4484) time: 0.5055 [2021-03-26 06:51:40 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 650/1251] eta: 0:05:07 lr: 0.000502 loss: 3.4857 (3.2644) grad_norm: 1.3811 (1.4473) time: 0.5089 [2021-03-26 06:51:45 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 660/1251] eta: 0:05:02 lr: 0.000502 loss: 3.4375 (3.2640) grad_norm: 1.3544 (1.4468) time: 0.5101 [2021-03-26 06:51:50 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 670/1251] eta: 0:04:57 lr: 0.000502 loss: 3.4310 (3.2647) grad_norm: 1.4389 (1.4471) time: 0.5061 [2021-03-26 06:51:55 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 680/1251] eta: 0:04:52 lr: 0.000502 loss: 3.4662 (3.2678) grad_norm: 1.4426 (1.4491) time: 0.5058 [2021-03-26 06:52:00 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 690/1251] eta: 0:04:47 lr: 0.000502 loss: 3.3255 (3.2663) grad_norm: 1.4351 (1.4487) time: 0.5061 [2021-03-26 06:52:05 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 700/1251] eta: 0:04:42 lr: 0.000502 loss: 3.0872 (3.2667) grad_norm: 1.4308 (1.4497) time: 0.5059 [2021-03-26 06:52:10 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 710/1251] eta: 0:04:36 lr: 0.000502 loss: 3.4911 (3.2714) grad_norm: 1.4308 (1.4500) time: 0.5033 [2021-03-26 06:52:15 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 720/1251] eta: 0:04:31 lr: 0.000502 loss: 3.4757 (3.2706) grad_norm: 1.3833 (1.4497) time: 0.5039 [2021-03-26 06:52:20 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 730/1251] eta: 0:04:26 lr: 0.000502 loss: 3.1707 (3.2701) grad_norm: 1.4095 (1.4495) time: 0.5092 [2021-03-26 06:52:25 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 740/1251] eta: 0:04:21 lr: 0.000502 loss: 3.3815 (3.2711) grad_norm: 1.4575 (1.4506) time: 0.5184 [2021-03-26 06:52:30 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 750/1251] eta: 0:04:16 lr: 0.000502 loss: 3.4484 (3.2718) grad_norm: 1.5052 (1.4510) time: 0.5179 [2021-03-26 06:52:36 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 760/1251] eta: 0:04:11 lr: 0.000502 loss: 3.3657 (3.2733) grad_norm: 1.4416 (1.4499) time: 0.5107 [2021-03-26 06:52:41 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 770/1251] eta: 0:04:06 lr: 0.000502 loss: 3.2460 (3.2721) grad_norm: 1.3990 (1.4519) time: 0.5075 [2021-03-26 06:52:46 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 780/1251] eta: 0:04:01 lr: 0.000502 loss: 3.2663 (3.2741) grad_norm: 1.4683 (1.4529) time: 0.5072 [2021-03-26 06:52:51 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 790/1251] eta: 0:03:55 lr: 0.000502 loss: 3.3599 (3.2743) grad_norm: 1.4428 (1.4529) time: 0.5072 [2021-03-26 06:52:56 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 800/1251] eta: 0:03:50 lr: 0.000502 loss: 3.3599 (3.2738) grad_norm: 1.4320 (1.4526) time: 0.5081 [2021-03-26 06:53:01 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 810/1251] eta: 0:03:45 lr: 0.000502 loss: 3.4824 (3.2767) grad_norm: 1.4324 (1.4527) time: 0.5066 [2021-03-26 06:53:06 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 820/1251] eta: 0:03:40 lr: 0.000502 loss: 3.5152 (3.2798) grad_norm: 1.4324 (1.4521) time: 0.5032 [2021-03-26 06:53:11 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 830/1251] eta: 0:03:35 lr: 0.000502 loss: 3.3633 (3.2740) grad_norm: 1.4141 (1.4518) time: 0.5067 [2021-03-26 06:53:16 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 840/1251] eta: 0:03:30 lr: 0.000502 loss: 2.8080 (3.2729) grad_norm: 1.4630 (1.4517) time: 0.5057 [2021-03-26 06:53:21 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 850/1251] eta: 0:03:25 lr: 0.000501 loss: 3.2874 (3.2736) grad_norm: 1.4630 (1.4530) time: 0.5161 [2021-03-26 06:53:27 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 860/1251] eta: 0:03:20 lr: 0.000501 loss: 3.3457 (3.2751) grad_norm: 1.4618 (1.4527) time: 0.5284 [2021-03-26 06:53:32 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 870/1251] eta: 0:03:14 lr: 0.000501 loss: 3.3751 (3.2745) grad_norm: 1.4011 (1.4531) time: 0.5161 [2021-03-26 06:53:37 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 880/1251] eta: 0:03:09 lr: 0.000501 loss: 3.2685 (3.2735) grad_norm: 1.3762 (1.4527) time: 0.5023 [2021-03-26 06:53:42 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 890/1251] eta: 0:03:04 lr: 0.000501 loss: 3.2685 (3.2749) grad_norm: 1.4277 (1.4532) time: 0.5047 [2021-03-26 06:53:47 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 900/1251] eta: 0:02:59 lr: 0.000501 loss: 3.4356 (3.2775) grad_norm: 1.5131 (1.4545) time: 0.5107 [2021-03-26 06:53:52 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 910/1251] eta: 0:02:54 lr: 0.000501 loss: 3.3933 (3.2761) grad_norm: 1.4580 (1.4541) time: 0.5077 [2021-03-26 06:53:57 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 920/1251] eta: 0:02:49 lr: 0.000501 loss: 3.1775 (3.2752) grad_norm: 1.4355 (1.4546) time: 0.5059 [2021-03-26 06:54:02 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 930/1251] eta: 0:02:44 lr: 0.000501 loss: 3.5146 (3.2781) grad_norm: 1.4400 (1.4542) time: 0.5065 [2021-03-26 06:54:07 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 940/1251] eta: 0:02:39 lr: 0.000501 loss: 3.6353 (3.2791) grad_norm: 1.3890 (1.4537) time: 0.5083 [2021-03-26 06:54:12 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 950/1251] eta: 0:02:33 lr: 0.000501 loss: 3.2237 (3.2782) grad_norm: 1.3674 (1.4528) time: 0.5064 [2021-03-26 06:54:17 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 960/1251] eta: 0:02:28 lr: 0.000501 loss: 3.2237 (3.2783) grad_norm: 1.3208 (1.4513) time: 0.5041 [2021-03-26 06:54:22 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 970/1251] eta: 0:02:23 lr: 0.000501 loss: 3.2389 (3.2773) grad_norm: 1.3613 (1.4512) time: 0.5068 [2021-03-26 06:54:27 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 980/1251] eta: 0:02:18 lr: 0.000501 loss: 3.3875 (3.2788) grad_norm: 1.4359 (1.4506) time: 0.5012 [2021-03-26 06:54:32 swin_small_patch4_window7_224] INFO: Epoch: [150] [ 990/1251] eta: 0:02:13 lr: 0.000501 loss: 3.3198 (3.2778) grad_norm: 1.4057 (1.4505) time: 0.4996 [2021-03-26 06:54:37 swin_small_patch4_window7_224] INFO: Epoch: [150] [1000/1251] eta: 0:02:08 lr: 0.000501 loss: 3.2943 (3.2794) grad_norm: 1.4108 (1.4501) time: 0.5043 [2021-03-26 06:54:42 swin_small_patch4_window7_224] INFO: Epoch: [150] [1010/1251] eta: 0:02:03 lr: 0.000501 loss: 3.4041 (3.2801) grad_norm: 1.4164 (1.4501) time: 0.5068 [2021-03-26 06:54:48 swin_small_patch4_window7_224] INFO: Epoch: [150] [1020/1251] eta: 0:01:57 lr: 0.000501 loss: 3.2795 (3.2789) grad_norm: 1.3841 (1.4498) time: 0.5077 [2021-03-26 06:54:53 swin_small_patch4_window7_224] INFO: Epoch: [150] [1030/1251] eta: 0:01:52 lr: 0.000501 loss: 3.4898 (3.2811) grad_norm: 1.3974 (1.4505) time: 0.5032 [2021-03-26 06:54:58 swin_small_patch4_window7_224] INFO: Epoch: [150] [1040/1251] eta: 0:01:47 lr: 0.000501 loss: 3.3599 (3.2797) grad_norm: 1.4765 (1.4506) time: 0.4997 [2021-03-26 06:55:03 swin_small_patch4_window7_224] INFO: Epoch: [150] [1050/1251] eta: 0:01:42 lr: 0.000501 loss: 3.3169 (3.2809) grad_norm: 1.4135 (1.4504) time: 0.5104 [2021-03-26 06:55:08 swin_small_patch4_window7_224] INFO: Epoch: [150] [1060/1251] eta: 0:01:37 lr: 0.000501 loss: 3.6222 (3.2843) grad_norm: 1.3840 (1.4509) time: 0.5127 [2021-03-26 06:55:13 swin_small_patch4_window7_224] INFO: Epoch: [150] [1070/1251] eta: 0:01:32 lr: 0.000501 loss: 3.4886 (3.2844) grad_norm: 1.3944 (1.4502) time: 0.5058 [2021-03-26 06:55:18 swin_small_patch4_window7_224] INFO: Epoch: [150] [1080/1251] eta: 0:01:27 lr: 0.000501 loss: 3.3876 (3.2849) grad_norm: 1.3944 (1.4497) time: 0.5064 [2021-03-26 06:55:23 swin_small_patch4_window7_224] INFO: Epoch: [150] [1090/1251] eta: 0:01:22 lr: 0.000500 loss: 3.4006 (3.2851) grad_norm: 1.3255 (1.4485) time: 0.5078 [2021-03-26 06:55:28 swin_small_patch4_window7_224] INFO: Epoch: [150] [1100/1251] eta: 0:01:17 lr: 0.000500 loss: 3.4841 (3.2869) grad_norm: 1.3049 (1.4478) time: 0.5052 [2021-03-26 06:55:33 swin_small_patch4_window7_224] INFO: Epoch: [150] [1110/1251] eta: 0:01:11 lr: 0.000500 loss: 3.2511 (3.2822) grad_norm: 1.3519 (1.4478) time: 0.4982 [2021-03-26 06:55:38 swin_small_patch4_window7_224] INFO: Epoch: [150] [1120/1251] eta: 0:01:06 lr: 0.000500 loss: 3.1763 (3.2815) grad_norm: 1.4218 (1.4482) time: 0.4943 [2021-03-26 06:55:43 swin_small_patch4_window7_224] INFO: Epoch: [150] [1130/1251] eta: 0:01:01 lr: 0.000500 loss: 3.3709 (3.2803) grad_norm: 1.4218 (1.4481) time: 0.5040 [2021-03-26 06:55:48 swin_small_patch4_window7_224] INFO: Epoch: [150] [1140/1251] eta: 0:00:56 lr: 0.000500 loss: 3.2501 (3.2783) grad_norm: 1.3883 (1.4478) time: 0.5104 [2021-03-26 06:55:53 swin_small_patch4_window7_224] INFO: Epoch: [150] [1150/1251] eta: 0:00:51 lr: 0.000500 loss: 3.1447 (3.2772) grad_norm: 1.4293 (1.4480) time: 0.5054 [2021-03-26 06:55:58 swin_small_patch4_window7_224] INFO: Epoch: [150] [1160/1251] eta: 0:00:46 lr: 0.000500 loss: 3.1660 (3.2760) grad_norm: 1.4443 (1.4477) time: 0.5053 [2021-03-26 06:56:03 swin_small_patch4_window7_224] INFO: Epoch: [150] [1170/1251] eta: 0:00:41 lr: 0.000500 loss: 3.4212 (3.2768) grad_norm: 1.4140 (1.4475) time: 0.5033 [2021-03-26 06:56:08 swin_small_patch4_window7_224] INFO: Epoch: [150] [1180/1251] eta: 0:00:36 lr: 0.000500 loss: 3.6083 (3.2792) grad_norm: 1.3564 (1.4469) time: 0.5006 [2021-03-26 06:56:13 swin_small_patch4_window7_224] INFO: Epoch: [150] [1190/1251] eta: 0:00:31 lr: 0.000500 loss: 3.5297 (3.2806) grad_norm: 1.3156 (1.4462) time: 0.5024 [2021-03-26 06:56:18 swin_small_patch4_window7_224] INFO: Epoch: [150] [1200/1251] eta: 0:00:26 lr: 0.000500 loss: 3.3832 (3.2807) grad_norm: 1.3427 (1.4462) time: 0.5070 [2021-03-26 06:56:23 swin_small_patch4_window7_224] INFO: Epoch: [150] [1210/1251] eta: 0:00:20 lr: 0.000500 loss: 3.2151 (3.2802) grad_norm: 1.4544 (1.4465) time: 0.5069 [2021-03-26 06:56:28 swin_small_patch4_window7_224] INFO: Epoch: [150] [1220/1251] eta: 0:00:15 lr: 0.000500 loss: 3.4230 (3.2820) grad_norm: 1.3854 (1.4458) time: 0.5029 [2021-03-26 06:56:33 swin_small_patch4_window7_224] INFO: Epoch: [150] [1230/1251] eta: 0:00:10 lr: 0.000500 loss: 3.4258 (3.2804) grad_norm: 1.3585 (1.4454) time: 0.4979 [2021-03-26 06:56:38 swin_small_patch4_window7_224] INFO: Epoch: [150] [1240/1251] eta: 0:00:05 lr: 0.000500 loss: 3.4293 (3.2825) grad_norm: 1.3693 (1.4449) time: 0.4979 [2021-03-26 06:56:44 swin_small_patch4_window7_224] INFO: Epoch: [150] [1250/1251] eta: 0:00:00 lr: 0.000500 loss: 3.4015 (3.2805) grad_norm: 1.3756 (1.4450) time: 0.5066 [2021-03-26 06:57:26 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:13 loss: 1.1686 (1.1686) acc1: 65.6250 (65.6250) acc5: 96.8750 (96.8750) [2021-03-26 06:57:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9665 (0.9664) acc1: 76.5625 (76.7045) acc5: 93.7500 (93.7500) [2021-03-26 06:57:28 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9638 (0.9797) acc1: 76.5625 (75.8185) acc5: 93.7500 (93.8988) [2021-03-26 06:57:29 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9398 (0.9485) acc1: 76.5625 (76.8145) acc5: 92.1875 (93.8508) [2021-03-26 06:57:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8586 (0.9241) acc1: 78.1250 (77.3247) acc5: 95.3125 (94.4741) [2021-03-26 06:57:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8614 (0.9166) acc1: 76.5625 (77.6000) acc5: 95.3125 (94.3680) [2021-03-26 06:57:38 swin_small_patch4_window7_224] INFO: * Acc@1 78.400 Acc@5 94.584 loss 0.905 [2021-03-26 06:57:38 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-26 06:57:38 swin_small_patch4_window7_224] INFO: Max accuracy: 78.40% [2021-03-26 06:57:42 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 0/1251] eta: 1:28:44 lr: 0.000500 loss: 3.6278 (3.6278) grad_norm: 1.5351 (1.5351) time: 4.2563 [2021-03-26 06:57:48 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 10/1251] eta: 0:17:46 lr: 0.000500 loss: 3.4522 (3.3126) grad_norm: 1.4384 (1.4405) time: 0.8590 [2021-03-26 06:57:53 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 20/1251] eta: 0:14:17 lr: 0.000500 loss: 3.3742 (3.3205) grad_norm: 1.4001 (1.4250) time: 0.5182 [2021-03-26 06:57:58 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 30/1251] eta: 0:12:56 lr: 0.000500 loss: 3.3980 (3.3019) grad_norm: 1.3632 (1.4229) time: 0.5129 [2021-03-26 06:58:03 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 40/1251] eta: 0:12:14 lr: 0.000500 loss: 3.4410 (3.2826) grad_norm: 1.4003 (1.4222) time: 0.5130 [2021-03-26 06:58:08 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 50/1251] eta: 0:11:44 lr: 0.000500 loss: 3.1990 (3.2648) grad_norm: 1.4534 (1.4339) time: 0.5107 [2021-03-26 06:58:13 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 60/1251] eta: 0:11:22 lr: 0.000500 loss: 3.4275 (3.2905) grad_norm: 1.4429 (1.4288) time: 0.5034 [2021-03-26 06:58:18 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 70/1251] eta: 0:11:04 lr: 0.000500 loss: 3.4375 (3.2932) grad_norm: 1.3328 (1.4185) time: 0.5004 [2021-03-26 06:58:23 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 80/1251] eta: 0:10:50 lr: 0.000499 loss: 3.2763 (3.3035) grad_norm: 1.4602 (1.4325) time: 0.5011 [2021-03-26 06:58:28 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 90/1251] eta: 0:10:38 lr: 0.000499 loss: 3.4104 (3.3231) grad_norm: 1.4858 (1.4343) time: 0.5063 [2021-03-26 06:58:33 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 100/1251] eta: 0:10:28 lr: 0.000499 loss: 3.4104 (3.3211) grad_norm: 1.4748 (1.4409) time: 0.5079 [2021-03-26 06:58:38 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 110/1251] eta: 0:10:19 lr: 0.000499 loss: 3.3706 (3.3293) grad_norm: 1.4627 (1.4425) time: 0.5099 [2021-03-26 06:58:43 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 120/1251] eta: 0:10:10 lr: 0.000499 loss: 3.5685 (3.3449) grad_norm: 1.4323 (1.4431) time: 0.5071 [2021-03-26 06:58:49 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 130/1251] eta: 0:10:02 lr: 0.000499 loss: 3.6123 (3.3601) grad_norm: 1.4046 (1.4398) time: 0.5055 [2021-03-26 06:58:54 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 140/1251] eta: 0:09:54 lr: 0.000499 loss: 3.5800 (3.3698) grad_norm: 1.3624 (1.4370) time: 0.5071 [2021-03-26 06:58:59 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 150/1251] eta: 0:09:46 lr: 0.000499 loss: 3.3712 (3.3523) grad_norm: 1.3784 (1.4424) time: 0.5039 [2021-03-26 06:59:04 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 160/1251] eta: 0:09:38 lr: 0.000499 loss: 3.2907 (3.3517) grad_norm: 1.4792 (1.4468) time: 0.4988 [2021-03-26 06:59:09 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 170/1251] eta: 0:09:31 lr: 0.000499 loss: 3.3625 (3.3432) grad_norm: 1.4361 (1.4482) time: 0.4980 [2021-03-26 06:59:14 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 180/1251] eta: 0:09:25 lr: 0.000499 loss: 3.2855 (3.3361) grad_norm: 1.4011 (1.4447) time: 0.5060 [2021-03-26 06:59:19 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 190/1251] eta: 0:09:19 lr: 0.000499 loss: 3.2317 (3.3261) grad_norm: 1.4097 (1.4495) time: 0.5177 [2021-03-26 06:59:24 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 200/1251] eta: 0:09:13 lr: 0.000499 loss: 3.2764 (3.3242) grad_norm: 1.4400 (1.4493) time: 0.5212 [2021-03-26 06:59:29 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 210/1251] eta: 0:09:07 lr: 0.000499 loss: 3.3765 (3.3246) grad_norm: 1.3886 (1.4441) time: 0.5095 [2021-03-26 06:59:34 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 220/1251] eta: 0:09:01 lr: 0.000499 loss: 3.3240 (3.3264) grad_norm: 1.3917 (1.4473) time: 0.5025 [2021-03-26 06:59:39 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 230/1251] eta: 0:08:55 lr: 0.000499 loss: 3.3611 (3.3311) grad_norm: 1.4377 (1.4492) time: 0.5088 [2021-03-26 06:59:44 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 240/1251] eta: 0:08:49 lr: 0.000499 loss: 3.4103 (3.3349) grad_norm: 1.4238 (1.4476) time: 0.5142 [2021-03-26 06:59:50 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 250/1251] eta: 0:08:43 lr: 0.000499 loss: 3.5400 (3.3406) grad_norm: 1.4086 (1.4485) time: 0.5104 [2021-03-26 06:59:55 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 260/1251] eta: 0:08:37 lr: 0.000499 loss: 3.5550 (3.3463) grad_norm: 1.4086 (1.4459) time: 0.5040 [2021-03-26 07:00:00 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 270/1251] eta: 0:08:31 lr: 0.000499 loss: 3.2690 (3.3381) grad_norm: 1.3615 (1.4446) time: 0.5031 [2021-03-26 07:00:05 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 280/1251] eta: 0:08:25 lr: 0.000499 loss: 3.0622 (3.3264) grad_norm: 1.3588 (1.4422) time: 0.5035 [2021-03-26 07:00:10 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 290/1251] eta: 0:08:19 lr: 0.000499 loss: 3.2372 (3.3234) grad_norm: 1.4236 (1.4434) time: 0.4988 [2021-03-26 07:00:15 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 300/1251] eta: 0:08:14 lr: 0.000499 loss: 3.4044 (3.3234) grad_norm: 1.4786 (1.4454) time: 0.5041 [2021-03-26 07:00:20 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 310/1251] eta: 0:08:08 lr: 0.000499 loss: 3.4044 (3.3212) grad_norm: 1.3809 (1.4413) time: 0.5058 [2021-03-26 07:00:25 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 320/1251] eta: 0:08:03 lr: 0.000498 loss: 3.3056 (3.3211) grad_norm: 1.3495 (1.4422) time: 0.5064 [2021-03-26 07:00:30 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 330/1251] eta: 0:07:57 lr: 0.000498 loss: 3.2816 (3.3192) grad_norm: 1.3947 (1.4404) time: 0.5083 [2021-03-26 07:00:35 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 340/1251] eta: 0:07:52 lr: 0.000498 loss: 3.3721 (3.3255) grad_norm: 1.3966 (1.4413) time: 0.5028 [2021-03-26 07:00:40 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 350/1251] eta: 0:07:46 lr: 0.000498 loss: 3.3984 (3.3225) grad_norm: 1.4622 (1.4440) time: 0.5046 [2021-03-26 07:00:45 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 360/1251] eta: 0:07:40 lr: 0.000498 loss: 3.3930 (3.3245) grad_norm: 1.4987 (1.4449) time: 0.5044 [2021-03-26 07:00:50 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 370/1251] eta: 0:07:35 lr: 0.000498 loss: 3.2886 (3.3259) grad_norm: 1.4944 (1.4456) time: 0.5038 [2021-03-26 07:00:55 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 380/1251] eta: 0:07:30 lr: 0.000498 loss: 3.3340 (3.3258) grad_norm: 1.4236 (1.4448) time: 0.5075 [2021-03-26 07:01:00 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 390/1251] eta: 0:07:24 lr: 0.000498 loss: 3.3326 (3.3261) grad_norm: 1.3501 (1.4422) time: 0.5091 [2021-03-26 07:01:05 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 400/1251] eta: 0:07:19 lr: 0.000498 loss: 3.3181 (3.3262) grad_norm: 1.3789 (1.4426) time: 0.5038 [2021-03-26 07:01:10 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 410/1251] eta: 0:07:13 lr: 0.000498 loss: 3.3202 (3.3258) grad_norm: 1.3985 (1.4403) time: 0.5010 [2021-03-26 07:01:15 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 420/1251] eta: 0:07:08 lr: 0.000498 loss: 3.2830 (3.3215) grad_norm: 1.4103 (1.4418) time: 0.5012 [2021-03-26 07:01:20 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 430/1251] eta: 0:07:03 lr: 0.000498 loss: 3.1356 (3.3186) grad_norm: 1.4790 (1.4436) time: 0.5102 [2021-03-26 07:01:26 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 440/1251] eta: 0:06:58 lr: 0.000498 loss: 3.4983 (3.3211) grad_norm: 1.4375 (1.4431) time: 0.5189 [2021-03-26 07:01:31 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 450/1251] eta: 0:06:52 lr: 0.000498 loss: 3.3807 (3.3171) grad_norm: 1.3869 (1.4414) time: 0.5086 [2021-03-26 07:01:36 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 460/1251] eta: 0:06:47 lr: 0.000498 loss: 3.2700 (3.3139) grad_norm: 1.3826 (1.4407) time: 0.4989 [2021-03-26 07:01:41 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 470/1251] eta: 0:06:41 lr: 0.000498 loss: 3.3684 (3.3137) grad_norm: 1.3954 (1.4404) time: 0.5009 [2021-03-26 07:01:46 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 480/1251] eta: 0:06:36 lr: 0.000498 loss: 3.2474 (3.3111) grad_norm: 1.3592 (1.4391) time: 0.5063 [2021-03-26 07:01:51 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 490/1251] eta: 0:06:31 lr: 0.000498 loss: 3.1845 (3.3061) grad_norm: 1.3592 (1.4382) time: 0.5034 [2021-03-26 07:01:56 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 500/1251] eta: 0:06:26 lr: 0.000498 loss: 3.6150 (3.3135) grad_norm: 1.3629 (1.4376) time: 0.5029 [2021-03-26 07:02:01 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 510/1251] eta: 0:06:20 lr: 0.000498 loss: 3.6218 (3.3149) grad_norm: 1.3742 (1.4374) time: 0.5056 [2021-03-26 07:02:06 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 520/1251] eta: 0:06:15 lr: 0.000498 loss: 3.4201 (3.3155) grad_norm: 1.3963 (1.4357) time: 0.5062 [2021-03-26 07:02:11 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 530/1251] eta: 0:06:10 lr: 0.000498 loss: 3.3864 (3.3180) grad_norm: 1.3548 (1.4365) time: 0.5067 [2021-03-26 07:02:16 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 540/1251] eta: 0:06:05 lr: 0.000498 loss: 3.4700 (3.3208) grad_norm: 1.4260 (1.4375) time: 0.5078 [2021-03-26 07:02:21 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 550/1251] eta: 0:06:00 lr: 0.000498 loss: 3.4935 (3.3218) grad_norm: 1.4206 (1.4371) time: 0.5180 [2021-03-26 07:02:26 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 560/1251] eta: 0:05:54 lr: 0.000497 loss: 3.3863 (3.3196) grad_norm: 1.4203 (1.4369) time: 0.5185 [2021-03-26 07:02:32 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 570/1251] eta: 0:05:49 lr: 0.000497 loss: 3.3508 (3.3204) grad_norm: 1.4141 (1.4361) time: 0.5082 [2021-03-26 07:02:37 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 580/1251] eta: 0:05:44 lr: 0.000497 loss: 3.3425 (3.3203) grad_norm: 1.3961 (1.4357) time: 0.5050 [2021-03-26 07:02:42 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 590/1251] eta: 0:05:39 lr: 0.000497 loss: 3.3078 (3.3192) grad_norm: 1.4249 (1.4360) time: 0.5103 [2021-03-26 07:02:47 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 600/1251] eta: 0:05:34 lr: 0.000497 loss: 3.4617 (3.3174) grad_norm: 1.4271 (1.4366) time: 0.5169 [2021-03-26 07:02:52 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 610/1251] eta: 0:05:29 lr: 0.000497 loss: 3.4723 (3.3203) grad_norm: 1.4215 (1.4371) time: 0.5137 [2021-03-26 07:02:57 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 620/1251] eta: 0:05:23 lr: 0.000497 loss: 3.4228 (3.3189) grad_norm: 1.4215 (1.4372) time: 0.5106 [2021-03-26 07:03:02 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 630/1251] eta: 0:05:18 lr: 0.000497 loss: 3.4060 (3.3172) grad_norm: 1.4214 (1.4376) time: 0.5104 [2021-03-26 07:03:07 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 640/1251] eta: 0:05:13 lr: 0.000497 loss: 3.0496 (3.3142) grad_norm: 1.4289 (1.4385) time: 0.5079 [2021-03-26 07:03:12 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 650/1251] eta: 0:05:08 lr: 0.000497 loss: 3.1177 (3.3143) grad_norm: 1.4295 (1.4386) time: 0.5096 [2021-03-26 07:03:17 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 660/1251] eta: 0:05:03 lr: 0.000497 loss: 3.2810 (3.3137) grad_norm: 1.4344 (1.4391) time: 0.5055 [2021-03-26 07:03:23 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 670/1251] eta: 0:04:58 lr: 0.000497 loss: 3.2810 (3.3139) grad_norm: 1.4432 (1.4397) time: 0.5053 [2021-03-26 07:03:28 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 680/1251] eta: 0:04:52 lr: 0.000497 loss: 3.4455 (3.3141) grad_norm: 1.4125 (1.4389) time: 0.5060 [2021-03-26 07:03:33 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 690/1251] eta: 0:04:47 lr: 0.000497 loss: 3.5016 (3.3132) grad_norm: 1.4254 (1.4398) time: 0.4978 [2021-03-26 07:03:38 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 700/1251] eta: 0:04:42 lr: 0.000497 loss: 3.3909 (3.3099) grad_norm: 1.4506 (1.4403) time: 0.5003 [2021-03-26 07:03:43 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 710/1251] eta: 0:04:37 lr: 0.000497 loss: 3.3758 (3.3111) grad_norm: 1.4277 (1.4407) time: 0.5054 [2021-03-26 07:03:48 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 720/1251] eta: 0:04:32 lr: 0.000497 loss: 3.3186 (3.3110) grad_norm: 1.4265 (1.4408) time: 0.5055 [2021-03-26 07:03:53 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 730/1251] eta: 0:04:26 lr: 0.000497 loss: 3.4692 (3.3142) grad_norm: 1.4141 (1.4411) time: 0.5071 [2021-03-26 07:03:58 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 740/1251] eta: 0:04:21 lr: 0.000497 loss: 3.5156 (3.3163) grad_norm: 1.4612 (1.4416) time: 0.5180 [2021-03-26 07:04:03 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 750/1251] eta: 0:04:16 lr: 0.000497 loss: 3.5022 (3.3161) grad_norm: 1.4192 (1.4412) time: 0.5264 [2021-03-26 07:04:08 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 760/1251] eta: 0:04:11 lr: 0.000497 loss: 3.3126 (3.3167) grad_norm: 1.4138 (1.4416) time: 0.5177 [2021-03-26 07:04:14 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 770/1251] eta: 0:04:06 lr: 0.000497 loss: 3.4294 (3.3185) grad_norm: 1.4001 (1.4413) time: 0.5105 [2021-03-26 07:04:19 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 780/1251] eta: 0:04:01 lr: 0.000497 loss: 3.5198 (3.3200) grad_norm: 1.3983 (1.4406) time: 0.5070 [2021-03-26 07:04:24 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 790/1251] eta: 0:03:56 lr: 0.000497 loss: 3.5220 (3.3181) grad_norm: 1.4121 (1.4409) time: 0.5032 [2021-03-26 07:04:29 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 800/1251] eta: 0:03:50 lr: 0.000497 loss: 3.4631 (3.3199) grad_norm: 1.4131 (1.4407) time: 0.5019 [2021-03-26 07:04:34 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 810/1251] eta: 0:03:45 lr: 0.000496 loss: 3.5281 (3.3207) grad_norm: 1.4859 (1.4418) time: 0.4990 [2021-03-26 07:04:39 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 820/1251] eta: 0:03:40 lr: 0.000496 loss: 3.5281 (3.3215) grad_norm: 1.4864 (1.4421) time: 0.4975 [2021-03-26 07:04:44 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 830/1251] eta: 0:03:35 lr: 0.000496 loss: 3.4336 (3.3226) grad_norm: 1.4559 (1.4423) time: 0.4987 [2021-03-26 07:04:49 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 840/1251] eta: 0:03:30 lr: 0.000496 loss: 3.4336 (3.3219) grad_norm: 1.3948 (1.4429) time: 0.5036 [2021-03-26 07:04:54 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 850/1251] eta: 0:03:25 lr: 0.000496 loss: 3.0250 (3.3183) grad_norm: 1.3917 (1.4424) time: 0.5079 [2021-03-26 07:04:59 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 860/1251] eta: 0:03:19 lr: 0.000496 loss: 3.3144 (3.3208) grad_norm: 1.4735 (1.4437) time: 0.5063 [2021-03-26 07:05:04 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 870/1251] eta: 0:03:14 lr: 0.000496 loss: 3.5831 (3.3212) grad_norm: 1.4778 (1.4437) time: 0.5086 [2021-03-26 07:05:09 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 880/1251] eta: 0:03:09 lr: 0.000496 loss: 3.5966 (3.3252) grad_norm: 1.4707 (1.4447) time: 0.5043 [2021-03-26 07:05:14 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 890/1251] eta: 0:03:04 lr: 0.000496 loss: 3.5778 (3.3247) grad_norm: 1.4740 (1.4444) time: 0.4946 [2021-03-26 07:05:19 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 900/1251] eta: 0:02:59 lr: 0.000496 loss: 3.2256 (3.3237) grad_norm: 1.4147 (1.4445) time: 0.5007 [2021-03-26 07:05:24 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 910/1251] eta: 0:02:54 lr: 0.000496 loss: 3.2938 (3.3224) grad_norm: 1.4259 (1.4449) time: 0.5043 [2021-03-26 07:05:29 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 920/1251] eta: 0:02:49 lr: 0.000496 loss: 3.5055 (3.3235) grad_norm: 1.4354 (1.4455) time: 0.5031 [2021-03-26 07:05:34 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 930/1251] eta: 0:02:44 lr: 0.000496 loss: 3.4952 (3.3236) grad_norm: 1.4480 (1.4458) time: 0.5088 [2021-03-26 07:05:39 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 940/1251] eta: 0:02:38 lr: 0.000496 loss: 3.3079 (3.3229) grad_norm: 1.4048 (1.4457) time: 0.5147 [2021-03-26 07:05:44 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 950/1251] eta: 0:02:33 lr: 0.000496 loss: 3.3567 (3.3233) grad_norm: 1.3694 (1.4450) time: 0.5085 [2021-03-26 07:05:49 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 960/1251] eta: 0:02:28 lr: 0.000496 loss: 3.3567 (3.3224) grad_norm: 1.3751 (1.4447) time: 0.4982 [2021-03-26 07:05:54 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 970/1251] eta: 0:02:23 lr: 0.000496 loss: 3.2249 (3.3210) grad_norm: 1.3544 (1.4435) time: 0.5102 [2021-03-26 07:05:59 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 980/1251] eta: 0:02:18 lr: 0.000496 loss: 3.0951 (3.3190) grad_norm: 1.3707 (1.4437) time: 0.5120 [2021-03-26 07:06:05 swin_small_patch4_window7_224] INFO: Epoch: [151] [ 990/1251] eta: 0:02:13 lr: 0.000496 loss: 3.2776 (3.3188) grad_norm: 1.4027 (1.4436) time: 0.5092 [2021-03-26 07:06:10 swin_small_patch4_window7_224] INFO: Epoch: [151] [1000/1251] eta: 0:02:08 lr: 0.000496 loss: 3.4476 (3.3202) grad_norm: 1.4027 (1.4441) time: 0.5108 [2021-03-26 07:06:15 swin_small_patch4_window7_224] INFO: Epoch: [151] [1010/1251] eta: 0:02:03 lr: 0.000496 loss: 3.5327 (3.3231) grad_norm: 1.4383 (1.4442) time: 0.5042 [2021-03-26 07:06:20 swin_small_patch4_window7_224] INFO: Epoch: [151] [1020/1251] eta: 0:01:57 lr: 0.000496 loss: 3.5961 (3.3245) grad_norm: 1.4219 (1.4440) time: 0.5065 [2021-03-26 07:06:25 swin_small_patch4_window7_224] INFO: Epoch: [151] [1030/1251] eta: 0:01:52 lr: 0.000496 loss: 3.5302 (3.3257) grad_norm: 1.4457 (1.4446) time: 0.5038 [2021-03-26 07:06:30 swin_small_patch4_window7_224] INFO: Epoch: [151] [1040/1251] eta: 0:01:47 lr: 0.000496 loss: 3.4998 (3.3278) grad_norm: 1.4948 (1.4454) time: 0.5012 [2021-03-26 07:06:35 swin_small_patch4_window7_224] INFO: Epoch: [151] [1050/1251] eta: 0:01:42 lr: 0.000495 loss: 3.4824 (3.3271) grad_norm: 1.4026 (1.4451) time: 0.5045 [2021-03-26 07:06:40 swin_small_patch4_window7_224] INFO: Epoch: [151] [1060/1251] eta: 0:01:37 lr: 0.000495 loss: 3.0300 (3.3242) grad_norm: 1.4026 (1.4454) time: 0.5030 [2021-03-26 07:06:45 swin_small_patch4_window7_224] INFO: Epoch: [151] [1070/1251] eta: 0:01:32 lr: 0.000495 loss: 3.4338 (3.3256) grad_norm: 1.3911 (1.4448) time: 0.5059 [2021-03-26 07:06:50 swin_small_patch4_window7_224] INFO: Epoch: [151] [1080/1251] eta: 0:01:27 lr: 0.000495 loss: 3.6218 (3.3265) grad_norm: 1.3783 (1.4458) time: 0.5060 [2021-03-26 07:06:55 swin_small_patch4_window7_224] INFO: Epoch: [151] [1090/1251] eta: 0:01:22 lr: 0.000495 loss: 3.3355 (3.3263) grad_norm: 1.4085 (1.4454) time: 0.5004 [2021-03-26 07:07:00 swin_small_patch4_window7_224] INFO: Epoch: [151] [1100/1251] eta: 0:01:17 lr: 0.000495 loss: 3.3355 (3.3267) grad_norm: 1.4284 (1.4456) time: 0.5034 [2021-03-26 07:07:05 swin_small_patch4_window7_224] INFO: Epoch: [151] [1110/1251] eta: 0:01:11 lr: 0.000495 loss: 3.4831 (3.3284) grad_norm: 1.4499 (1.4458) time: 0.5037 [2021-03-26 07:07:10 swin_small_patch4_window7_224] INFO: Epoch: [151] [1120/1251] eta: 0:01:06 lr: 0.000495 loss: 3.5819 (3.3304) grad_norm: 1.4322 (1.4458) time: 0.5047 [2021-03-26 07:07:15 swin_small_patch4_window7_224] INFO: Epoch: [151] [1130/1251] eta: 0:01:01 lr: 0.000495 loss: 3.3763 (3.3264) grad_norm: 1.4231 (1.4456) time: 0.5070 [2021-03-26 07:07:20 swin_small_patch4_window7_224] INFO: Epoch: [151] [1140/1251] eta: 0:00:56 lr: 0.000495 loss: 3.2458 (3.3261) grad_norm: 1.3431 (1.4445) time: 0.5045 [2021-03-26 07:07:25 swin_small_patch4_window7_224] INFO: Epoch: [151] [1150/1251] eta: 0:00:51 lr: 0.000495 loss: 3.3688 (3.3246) grad_norm: 1.3431 (1.4440) time: 0.4995 [2021-03-26 07:07:30 swin_small_patch4_window7_224] INFO: Epoch: [151] [1160/1251] eta: 0:00:46 lr: 0.000495 loss: 3.3004 (3.3249) grad_norm: 1.4011 (1.4439) time: 0.4988 [2021-03-26 07:07:35 swin_small_patch4_window7_224] INFO: Epoch: [151] [1170/1251] eta: 0:00:41 lr: 0.000495 loss: 3.4948 (3.3259) grad_norm: 1.4100 (1.4437) time: 0.5079 [2021-03-26 07:07:40 swin_small_patch4_window7_224] INFO: Epoch: [151] [1180/1251] eta: 0:00:36 lr: 0.000495 loss: 3.5569 (3.3279) grad_norm: 1.4198 (1.4437) time: 0.5140 [2021-03-26 07:07:46 swin_small_patch4_window7_224] INFO: Epoch: [151] [1190/1251] eta: 0:00:31 lr: 0.000495 loss: 3.5678 (3.3295) grad_norm: 1.4176 (1.4434) time: 0.5109 [2021-03-26 07:07:51 swin_small_patch4_window7_224] INFO: Epoch: [151] [1200/1251] eta: 0:00:25 lr: 0.000495 loss: 3.4666 (3.3292) grad_norm: 1.3860 (inf) time: 0.5025 [2021-03-26 07:07:56 swin_small_patch4_window7_224] INFO: Epoch: [151] [1210/1251] eta: 0:00:20 lr: 0.000495 loss: 3.4080 (3.3282) grad_norm: 1.3530 (inf) time: 0.5006 [2021-03-26 07:08:01 swin_small_patch4_window7_224] INFO: Epoch: [151] [1220/1251] eta: 0:00:15 lr: 0.000495 loss: 3.3766 (3.3280) grad_norm: 1.3394 (inf) time: 0.5009 [2021-03-26 07:08:06 swin_small_patch4_window7_224] INFO: Epoch: [151] [1230/1251] eta: 0:00:10 lr: 0.000495 loss: 3.3766 (3.3284) grad_norm: 1.3733 (inf) time: 0.5001 [2021-03-26 07:08:11 swin_small_patch4_window7_224] INFO: Epoch: [151] [1240/1251] eta: 0:00:05 lr: 0.000495 loss: 3.4760 (3.3302) grad_norm: 1.3733 (inf) time: 0.5000 [2021-03-26 07:08:16 swin_small_patch4_window7_224] INFO: Epoch: [151] [1250/1251] eta: 0:00:00 lr: 0.000495 loss: 3.4112 (3.3307) grad_norm: 1.3961 (inf) time: 0.5011 [2021-03-26 07:08:24 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:38 loss: 0.8817 (0.8817) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-26 07:08:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9008 (0.9496) acc1: 78.1250 (79.5455) acc5: 95.3125 (95.0284) [2021-03-26 07:08:29 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8903 (0.9346) acc1: 76.5625 (78.8690) acc5: 95.3125 (94.6429) [2021-03-26 07:08:31 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8695 (0.9244) acc1: 76.5625 (78.1754) acc5: 93.7500 (94.7581) [2021-03-26 07:08:33 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9106 (0.9325) acc1: 78.1250 (78.2012) acc5: 93.7500 (94.4741) [2021-03-26 07:08:34 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9106 (0.9381) acc1: 78.1250 (78.0160) acc5: 93.7500 (94.4640) [2021-03-26 07:08:41 swin_small_patch4_window7_224] INFO: * Acc@1 78.092 Acc@5 94.512 loss 0.925 [2021-03-26 07:08:41 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.1% [2021-03-26 07:08:41 swin_small_patch4_window7_224] INFO: Max accuracy: 78.40% [2021-03-26 07:08:45 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 0/1251] eta: 1:29:11 lr: 0.000495 loss: 3.7952 (3.7952) grad_norm: 1.2559 (1.2559) time: 4.2779 [2021-03-26 07:08:50 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 10/1251] eta: 0:17:27 lr: 0.000495 loss: 3.5329 (3.4394) grad_norm: 1.4242 (1.4251) time: 0.8440 [2021-03-26 07:08:55 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 20/1251] eta: 0:13:58 lr: 0.000495 loss: 3.2981 (3.2996) grad_norm: 1.4521 (1.4383) time: 0.5014 [2021-03-26 07:09:00 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 30/1251] eta: 0:12:45 lr: 0.000495 loss: 3.1013 (3.2489) grad_norm: 1.4572 (1.4463) time: 0.5072 [2021-03-26 07:09:05 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 40/1251] eta: 0:12:00 lr: 0.000494 loss: 3.1546 (3.2393) grad_norm: 1.4592 (1.4476) time: 0.5041 [2021-03-26 07:09:10 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 50/1251] eta: 0:11:31 lr: 0.000494 loss: 3.4836 (3.3090) grad_norm: 1.4592 (1.4524) time: 0.4977 [2021-03-26 07:09:15 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 60/1251] eta: 0:11:11 lr: 0.000494 loss: 3.5170 (3.2969) grad_norm: 1.4400 (1.4586) time: 0.5004 [2021-03-26 07:09:20 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 70/1251] eta: 0:10:56 lr: 0.000494 loss: 3.3784 (3.2931) grad_norm: 1.4449 (1.4705) time: 0.5054 [2021-03-26 07:09:25 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 80/1251] eta: 0:10:44 lr: 0.000494 loss: 3.2887 (3.3005) grad_norm: 1.5490 (1.4892) time: 0.5090 [2021-03-26 07:09:30 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 90/1251] eta: 0:10:33 lr: 0.000494 loss: 3.2512 (3.2857) grad_norm: 1.5387 (1.4978) time: 0.5064 [2021-03-26 07:09:35 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 100/1251] eta: 0:10:22 lr: 0.000494 loss: 3.1773 (3.2823) grad_norm: 1.4413 (1.4970) time: 0.5037 [2021-03-26 07:09:40 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 110/1251] eta: 0:10:13 lr: 0.000494 loss: 3.3588 (3.2745) grad_norm: 1.4442 (1.4937) time: 0.5049 [2021-03-26 07:09:45 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 120/1251] eta: 0:10:05 lr: 0.000494 loss: 3.2324 (3.2657) grad_norm: 1.3384 (1.4776) time: 0.5064 [2021-03-26 07:09:51 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 130/1251] eta: 0:09:58 lr: 0.000494 loss: 3.3374 (3.2795) grad_norm: 1.3212 (1.4708) time: 0.5136 [2021-03-26 07:09:56 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 140/1251] eta: 0:09:51 lr: 0.000494 loss: 3.5796 (3.2907) grad_norm: 1.4031 (1.4694) time: 0.5144 [2021-03-26 07:10:01 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 150/1251] eta: 0:09:44 lr: 0.000494 loss: 3.3216 (3.2854) grad_norm: 1.4464 (1.4742) time: 0.5081 [2021-03-26 07:10:06 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 160/1251] eta: 0:09:37 lr: 0.000494 loss: 3.1787 (3.2808) grad_norm: 1.4616 (1.4719) time: 0.5056 [2021-03-26 07:10:11 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 170/1251] eta: 0:09:30 lr: 0.000494 loss: 3.4110 (3.2838) grad_norm: 1.3996 (1.4668) time: 0.5022 [2021-03-26 07:10:16 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 180/1251] eta: 0:09:24 lr: 0.000494 loss: 3.4323 (3.2864) grad_norm: 1.3652 (1.4646) time: 0.5113 [2021-03-26 07:10:21 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 190/1251] eta: 0:09:17 lr: 0.000494 loss: 3.4648 (3.3010) grad_norm: 1.4922 (1.4705) time: 0.5094 [2021-03-26 07:10:26 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 200/1251] eta: 0:09:11 lr: 0.000494 loss: 3.4635 (3.2928) grad_norm: 1.5040 (1.4716) time: 0.5025 [2021-03-26 07:10:31 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 210/1251] eta: 0:09:05 lr: 0.000494 loss: 3.0758 (3.2860) grad_norm: 1.4933 (1.4706) time: 0.5056 [2021-03-26 07:10:36 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 220/1251] eta: 0:08:58 lr: 0.000494 loss: 3.1434 (3.2784) grad_norm: 1.3281 (1.4634) time: 0.5022 [2021-03-26 07:10:41 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 230/1251] eta: 0:08:53 lr: 0.000494 loss: 3.1434 (3.2712) grad_norm: 1.3484 (1.4632) time: 0.5065 [2021-03-26 07:10:46 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 240/1251] eta: 0:08:47 lr: 0.000494 loss: 3.4422 (3.2787) grad_norm: 1.4158 (1.4625) time: 0.5093 [2021-03-26 07:10:52 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 250/1251] eta: 0:08:41 lr: 0.000494 loss: 3.4624 (3.2775) grad_norm: 1.4109 (1.4600) time: 0.5106 [2021-03-26 07:10:57 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 260/1251] eta: 0:08:35 lr: 0.000494 loss: 3.3069 (3.2772) grad_norm: 1.3802 (1.4561) time: 0.5061 [2021-03-26 07:11:02 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 270/1251] eta: 0:08:30 lr: 0.000494 loss: 3.2810 (3.2783) grad_norm: 1.3496 (1.4551) time: 0.5028 [2021-03-26 07:11:07 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 280/1251] eta: 0:08:24 lr: 0.000493 loss: 3.4783 (3.2847) grad_norm: 1.4004 (1.4535) time: 0.5074 [2021-03-26 07:11:12 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 290/1251] eta: 0:08:18 lr: 0.000493 loss: 3.4710 (3.2874) grad_norm: 1.3636 (1.4514) time: 0.5017 [2021-03-26 07:11:17 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 300/1251] eta: 0:08:12 lr: 0.000493 loss: 3.4695 (3.2910) grad_norm: 1.4029 (1.4549) time: 0.5033 [2021-03-26 07:11:22 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 310/1251] eta: 0:08:07 lr: 0.000493 loss: 3.5150 (3.2926) grad_norm: 1.4245 (1.4524) time: 0.5104 [2021-03-26 07:11:27 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 320/1251] eta: 0:08:02 lr: 0.000493 loss: 3.5150 (3.2961) grad_norm: 1.3787 (1.4515) time: 0.5120 [2021-03-26 07:11:32 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 330/1251] eta: 0:07:56 lr: 0.000493 loss: 3.4143 (3.2939) grad_norm: 1.4298 (1.4511) time: 0.5147 [2021-03-26 07:11:37 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 340/1251] eta: 0:07:51 lr: 0.000493 loss: 3.3983 (3.2968) grad_norm: 1.4356 (1.4535) time: 0.5091 [2021-03-26 07:11:42 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 350/1251] eta: 0:07:46 lr: 0.000493 loss: 3.3983 (3.2973) grad_norm: 1.4257 (1.4524) time: 0.5160 [2021-03-26 07:11:48 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 360/1251] eta: 0:07:41 lr: 0.000493 loss: 3.2233 (3.2902) grad_norm: 1.3808 (1.4519) time: 0.5228 [2021-03-26 07:11:53 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 370/1251] eta: 0:07:35 lr: 0.000493 loss: 3.3123 (3.2890) grad_norm: 1.4249 (1.4553) time: 0.5066 [2021-03-26 07:11:58 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 380/1251] eta: 0:07:30 lr: 0.000493 loss: 3.0379 (3.2875) grad_norm: 1.5061 (1.4557) time: 0.4987 [2021-03-26 07:12:03 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 390/1251] eta: 0:07:24 lr: 0.000493 loss: 3.1368 (3.2873) grad_norm: 1.4006 (1.4574) time: 0.4974 [2021-03-26 07:12:08 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 400/1251] eta: 0:07:19 lr: 0.000493 loss: 3.5240 (3.2912) grad_norm: 1.4652 (1.4595) time: 0.4996 [2021-03-26 07:12:13 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 410/1251] eta: 0:07:13 lr: 0.000493 loss: 3.4415 (3.2900) grad_norm: 1.4905 (1.4613) time: 0.5022 [2021-03-26 07:12:18 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 420/1251] eta: 0:07:08 lr: 0.000493 loss: 3.1687 (3.2906) grad_norm: 1.4881 (1.4628) time: 0.5045 [2021-03-26 07:12:23 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 430/1251] eta: 0:07:03 lr: 0.000493 loss: 3.3103 (3.2882) grad_norm: 1.5104 (1.4633) time: 0.5106 [2021-03-26 07:12:28 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 440/1251] eta: 0:06:57 lr: 0.000493 loss: 3.0644 (3.2804) grad_norm: 1.4301 (1.4622) time: 0.5079 [2021-03-26 07:12:33 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 450/1251] eta: 0:06:52 lr: 0.000493 loss: 3.0644 (3.2787) grad_norm: 1.4301 (1.4641) time: 0.4988 [2021-03-26 07:12:38 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 460/1251] eta: 0:06:46 lr: 0.000493 loss: 3.2367 (3.2773) grad_norm: 1.4711 (1.4658) time: 0.5024 [2021-03-26 07:12:43 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 470/1251] eta: 0:06:41 lr: 0.000493 loss: 3.3085 (3.2783) grad_norm: 1.4490 (1.4652) time: 0.5070 [2021-03-26 07:12:48 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 480/1251] eta: 0:06:36 lr: 0.000493 loss: 3.3241 (3.2784) grad_norm: 1.4566 (1.4652) time: 0.5063 [2021-03-26 07:12:53 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 490/1251] eta: 0:06:31 lr: 0.000493 loss: 3.4081 (3.2827) grad_norm: 1.4578 (1.4650) time: 0.5041 [2021-03-26 07:12:58 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 500/1251] eta: 0:06:25 lr: 0.000493 loss: 3.5742 (3.2870) grad_norm: 1.4353 (1.4634) time: 0.5041 [2021-03-26 07:13:03 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 510/1251] eta: 0:06:20 lr: 0.000493 loss: 3.3658 (3.2848) grad_norm: 1.4297 (1.4632) time: 0.5084 [2021-03-26 07:13:08 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 520/1251] eta: 0:06:15 lr: 0.000492 loss: 3.1669 (3.2805) grad_norm: 1.4297 (1.4624) time: 0.5087 [2021-03-26 07:13:13 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 530/1251] eta: 0:06:10 lr: 0.000492 loss: 3.3544 (3.2822) grad_norm: 1.4236 (1.4623) time: 0.5075 [2021-03-26 07:13:18 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 540/1251] eta: 0:06:05 lr: 0.000492 loss: 3.5105 (3.2874) grad_norm: 1.4637 (1.4630) time: 0.5095 [2021-03-26 07:13:24 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 550/1251] eta: 0:06:00 lr: 0.000492 loss: 3.4886 (3.2851) grad_norm: 1.4729 (1.4626) time: 0.5194 [2021-03-26 07:13:29 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 560/1251] eta: 0:05:54 lr: 0.000492 loss: 3.2445 (3.2866) grad_norm: 1.4251 (1.4627) time: 0.5148 [2021-03-26 07:13:34 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 570/1251] eta: 0:05:49 lr: 0.000492 loss: 3.2550 (3.2859) grad_norm: 1.4436 (1.4633) time: 0.5043 [2021-03-26 07:13:39 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 580/1251] eta: 0:05:44 lr: 0.000492 loss: 3.2254 (3.2830) grad_norm: 1.4541 (1.4625) time: 0.5071 [2021-03-26 07:13:44 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 590/1251] eta: 0:05:39 lr: 0.000492 loss: 2.9335 (3.2782) grad_norm: 1.3962 (1.4619) time: 0.5083 [2021-03-26 07:13:49 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 600/1251] eta: 0:05:33 lr: 0.000492 loss: 3.1556 (3.2748) grad_norm: 1.4101 (1.4628) time: 0.5084 [2021-03-26 07:13:54 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 610/1251] eta: 0:05:28 lr: 0.000492 loss: 3.1790 (3.2768) grad_norm: 1.5234 (1.4645) time: 0.5088 [2021-03-26 07:13:59 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 620/1251] eta: 0:05:23 lr: 0.000492 loss: 3.3441 (3.2780) grad_norm: 1.4453 (1.4634) time: 0.4993 [2021-03-26 07:14:04 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 630/1251] eta: 0:05:18 lr: 0.000492 loss: 3.3004 (3.2751) grad_norm: 1.3927 (1.4631) time: 0.4956 [2021-03-26 07:14:09 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 640/1251] eta: 0:05:12 lr: 0.000492 loss: 3.3215 (3.2765) grad_norm: 1.4033 (1.4610) time: 0.4997 [2021-03-26 07:14:14 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 650/1251] eta: 0:05:07 lr: 0.000492 loss: 3.5331 (3.2771) grad_norm: 1.3972 (1.4615) time: 0.5036 [2021-03-26 07:14:19 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 660/1251] eta: 0:05:02 lr: 0.000492 loss: 3.1875 (3.2771) grad_norm: 1.4215 (1.4610) time: 0.5092 [2021-03-26 07:14:24 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 670/1251] eta: 0:04:57 lr: 0.000492 loss: 3.3650 (3.2798) grad_norm: 1.3937 (1.4610) time: 0.5072 [2021-03-26 07:14:29 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 680/1251] eta: 0:04:52 lr: 0.000492 loss: 3.4571 (3.2801) grad_norm: 1.3869 (1.4605) time: 0.5084 [2021-03-26 07:14:34 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 690/1251] eta: 0:04:47 lr: 0.000492 loss: 3.2624 (3.2797) grad_norm: 1.4387 (1.4610) time: 0.5057 [2021-03-26 07:14:39 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 700/1251] eta: 0:04:41 lr: 0.000492 loss: 3.2140 (3.2804) grad_norm: 1.4559 (1.4608) time: 0.5011 [2021-03-26 07:14:44 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 710/1251] eta: 0:04:36 lr: 0.000492 loss: 3.3775 (3.2801) grad_norm: 1.4415 (1.4605) time: 0.5030 [2021-03-26 07:14:50 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 720/1251] eta: 0:04:31 lr: 0.000492 loss: 3.3452 (3.2808) grad_norm: 1.4072 (1.4600) time: 0.5016 [2021-03-26 07:14:55 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 730/1251] eta: 0:04:26 lr: 0.000492 loss: 3.3452 (3.2821) grad_norm: 1.4831 (1.4619) time: 0.5118 [2021-03-26 07:15:00 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 740/1251] eta: 0:04:21 lr: 0.000492 loss: 3.3216 (3.2813) grad_norm: 1.5351 (1.4629) time: 0.5232 [2021-03-26 07:15:05 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 750/1251] eta: 0:04:16 lr: 0.000492 loss: 3.3216 (3.2808) grad_norm: 1.4663 (1.4622) time: 0.5151 [2021-03-26 07:15:10 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 760/1251] eta: 0:04:11 lr: 0.000491 loss: 3.4323 (3.2815) grad_norm: 1.3847 (1.4613) time: 0.5073 [2021-03-26 07:15:15 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 770/1251] eta: 0:04:06 lr: 0.000491 loss: 3.4991 (3.2838) grad_norm: 1.3927 (1.4618) time: 0.5055 [2021-03-26 07:15:20 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 780/1251] eta: 0:04:00 lr: 0.000491 loss: 3.5058 (3.2873) grad_norm: 1.5016 (1.4622) time: 0.5023 [2021-03-26 07:15:25 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 790/1251] eta: 0:03:55 lr: 0.000491 loss: 3.4183 (3.2832) grad_norm: 1.4561 (1.4622) time: 0.5044 [2021-03-26 07:15:30 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 800/1251] eta: 0:03:50 lr: 0.000491 loss: 3.0290 (3.2815) grad_norm: 1.3992 (1.4611) time: 0.5051 [2021-03-26 07:15:35 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 810/1251] eta: 0:03:45 lr: 0.000491 loss: 3.2231 (3.2824) grad_norm: 1.3584 (1.4606) time: 0.5031 [2021-03-26 07:15:40 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 820/1251] eta: 0:03:40 lr: 0.000491 loss: 3.4252 (3.2831) grad_norm: 1.3836 (1.4598) time: 0.5009 [2021-03-26 07:15:45 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 830/1251] eta: 0:03:35 lr: 0.000491 loss: 3.3391 (3.2831) grad_norm: 1.3836 (1.4594) time: 0.4964 [2021-03-26 07:15:50 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 840/1251] eta: 0:03:29 lr: 0.000491 loss: 3.6370 (3.2882) grad_norm: 1.3858 (1.4587) time: 0.5044 [2021-03-26 07:15:55 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 850/1251] eta: 0:03:24 lr: 0.000491 loss: 3.5776 (3.2882) grad_norm: 1.4161 (1.4586) time: 0.5102 [2021-03-26 07:16:00 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 860/1251] eta: 0:03:19 lr: 0.000491 loss: 3.5018 (3.2916) grad_norm: 1.4581 (1.4584) time: 0.5040 [2021-03-26 07:16:05 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 870/1251] eta: 0:03:14 lr: 0.000491 loss: 3.3803 (3.2910) grad_norm: 1.4615 (1.4590) time: 0.4991 [2021-03-26 07:16:11 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 880/1251] eta: 0:03:09 lr: 0.000491 loss: 3.3487 (3.2923) grad_norm: 1.4615 (1.4589) time: 0.5076 [2021-03-26 07:16:16 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 890/1251] eta: 0:03:04 lr: 0.000491 loss: 3.3808 (3.2941) grad_norm: 1.4662 (1.4584) time: 0.5110 [2021-03-26 07:16:21 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 900/1251] eta: 0:02:59 lr: 0.000491 loss: 3.3256 (3.2940) grad_norm: 1.4662 (1.4579) time: 0.5014 [2021-03-26 07:16:26 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 910/1251] eta: 0:02:54 lr: 0.000491 loss: 3.1276 (3.2932) grad_norm: 1.3823 (1.4575) time: 0.5010 [2021-03-26 07:16:31 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 920/1251] eta: 0:02:48 lr: 0.000491 loss: 3.5525 (3.2949) grad_norm: 1.4138 (1.4579) time: 0.5101 [2021-03-26 07:16:36 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 930/1251] eta: 0:02:43 lr: 0.000491 loss: 3.5694 (3.2969) grad_norm: 1.4618 (1.4582) time: 0.5119 [2021-03-26 07:16:41 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 940/1251] eta: 0:02:38 lr: 0.000491 loss: 3.2461 (3.2960) grad_norm: 1.4536 (1.4584) time: 0.5058 [2021-03-26 07:16:46 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 950/1251] eta: 0:02:33 lr: 0.000491 loss: 3.1984 (3.2967) grad_norm: 1.4803 (1.4599) time: 0.5046 [2021-03-26 07:16:51 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 960/1251] eta: 0:02:28 lr: 0.000491 loss: 3.5288 (3.2968) grad_norm: 1.5181 (1.4600) time: 0.4994 [2021-03-26 07:16:56 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 970/1251] eta: 0:02:23 lr: 0.000491 loss: 3.4474 (3.2967) grad_norm: 1.4240 (1.4600) time: 0.4973 [2021-03-26 07:17:01 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 980/1251] eta: 0:02:18 lr: 0.000491 loss: 3.4955 (3.2998) grad_norm: 1.4126 (1.4601) time: 0.4994 [2021-03-26 07:17:06 swin_small_patch4_window7_224] INFO: Epoch: [152] [ 990/1251] eta: 0:02:13 lr: 0.000491 loss: 3.4672 (3.3006) grad_norm: 1.4273 (1.4603) time: 0.5073 [2021-03-26 07:17:11 swin_small_patch4_window7_224] INFO: Epoch: [152] [1000/1251] eta: 0:02:07 lr: 0.000490 loss: 3.3614 (3.3006) grad_norm: 1.4264 (1.4601) time: 0.5066 [2021-03-26 07:17:16 swin_small_patch4_window7_224] INFO: Epoch: [152] [1010/1251] eta: 0:02:02 lr: 0.000490 loss: 3.3731 (3.3000) grad_norm: 1.3656 (1.4592) time: 0.5011 [2021-03-26 07:17:21 swin_small_patch4_window7_224] INFO: Epoch: [152] [1020/1251] eta: 0:01:57 lr: 0.000490 loss: 3.1477 (3.2964) grad_norm: 1.3399 (1.4586) time: 0.5022 [2021-03-26 07:17:26 swin_small_patch4_window7_224] INFO: Epoch: [152] [1030/1251] eta: 0:01:52 lr: 0.000490 loss: 2.8973 (3.2938) grad_norm: 1.4340 (1.4599) time: 0.5037 [2021-03-26 07:17:31 swin_small_patch4_window7_224] INFO: Epoch: [152] [1040/1251] eta: 0:01:47 lr: 0.000490 loss: 3.1732 (3.2925) grad_norm: 1.4302 (1.4595) time: 0.5067 [2021-03-26 07:17:36 swin_small_patch4_window7_224] INFO: Epoch: [152] [1050/1251] eta: 0:01:42 lr: 0.000490 loss: 3.0962 (3.2898) grad_norm: 1.3807 (1.4590) time: 0.5097 [2021-03-26 07:17:42 swin_small_patch4_window7_224] INFO: Epoch: [152] [1060/1251] eta: 0:01:37 lr: 0.000490 loss: 3.2320 (3.2905) grad_norm: 1.3862 (1.4585) time: 0.5109 [2021-03-26 07:17:47 swin_small_patch4_window7_224] INFO: Epoch: [152] [1070/1251] eta: 0:01:32 lr: 0.000490 loss: 3.3568 (3.2917) grad_norm: 1.4090 (1.4586) time: 0.5125 [2021-03-26 07:17:52 swin_small_patch4_window7_224] INFO: Epoch: [152] [1080/1251] eta: 0:01:27 lr: 0.000490 loss: 3.6030 (3.2957) grad_norm: 1.5144 (1.4586) time: 0.5117 [2021-03-26 07:17:57 swin_small_patch4_window7_224] INFO: Epoch: [152] [1090/1251] eta: 0:01:22 lr: 0.000490 loss: 3.4848 (3.2953) grad_norm: 1.3930 (1.4580) time: 0.5142 [2021-03-26 07:18:02 swin_small_patch4_window7_224] INFO: Epoch: [152] [1100/1251] eta: 0:01:16 lr: 0.000490 loss: 3.4727 (3.2953) grad_norm: 1.3657 (1.4575) time: 0.5129 [2021-03-26 07:18:07 swin_small_patch4_window7_224] INFO: Epoch: [152] [1110/1251] eta: 0:01:11 lr: 0.000490 loss: 3.5444 (3.2981) grad_norm: 1.4331 (1.4579) time: 0.5059 [2021-03-26 07:18:12 swin_small_patch4_window7_224] INFO: Epoch: [152] [1120/1251] eta: 0:01:06 lr: 0.000490 loss: 3.5508 (3.2990) grad_norm: 1.4742 (1.4582) time: 0.5094 [2021-03-26 07:18:17 swin_small_patch4_window7_224] INFO: Epoch: [152] [1130/1251] eta: 0:01:01 lr: 0.000490 loss: 3.1896 (3.2991) grad_norm: 1.4553 (1.4581) time: 0.5089 [2021-03-26 07:18:22 swin_small_patch4_window7_224] INFO: Epoch: [152] [1140/1251] eta: 0:00:56 lr: 0.000490 loss: 3.1857 (3.2970) grad_norm: 1.4331 (1.4582) time: 0.5054 [2021-03-26 07:18:27 swin_small_patch4_window7_224] INFO: Epoch: [152] [1150/1251] eta: 0:00:51 lr: 0.000490 loss: 3.4134 (3.2975) grad_norm: 1.4331 (1.4580) time: 0.5062 [2021-03-26 07:18:32 swin_small_patch4_window7_224] INFO: Epoch: [152] [1160/1251] eta: 0:00:46 lr: 0.000490 loss: 3.4606 (3.2991) grad_norm: 1.4646 (1.4583) time: 0.5091 [2021-03-26 07:18:38 swin_small_patch4_window7_224] INFO: Epoch: [152] [1170/1251] eta: 0:00:41 lr: 0.000490 loss: 3.4606 (3.3010) grad_norm: 1.4006 (1.4579) time: 0.5091 [2021-03-26 07:18:42 swin_small_patch4_window7_224] INFO: Epoch: [152] [1180/1251] eta: 0:00:36 lr: 0.000490 loss: 3.4460 (3.3016) grad_norm: 1.3734 (1.4576) time: 0.4998 [2021-03-26 07:18:48 swin_small_patch4_window7_224] INFO: Epoch: [152] [1190/1251] eta: 0:00:31 lr: 0.000490 loss: 3.3473 (3.3004) grad_norm: 1.3734 (1.4576) time: 0.5008 [2021-03-26 07:18:53 swin_small_patch4_window7_224] INFO: Epoch: [152] [1200/1251] eta: 0:00:25 lr: 0.000490 loss: 3.3692 (3.3018) grad_norm: 1.4025 (1.4572) time: 0.5087 [2021-03-26 07:18:58 swin_small_patch4_window7_224] INFO: Epoch: [152] [1210/1251] eta: 0:00:20 lr: 0.000490 loss: 3.4864 (3.3037) grad_norm: 1.4165 (1.4569) time: 0.5104 [2021-03-26 07:19:03 swin_small_patch4_window7_224] INFO: Epoch: [152] [1220/1251] eta: 0:00:15 lr: 0.000490 loss: 3.3968 (3.3038) grad_norm: 1.4165 (1.4563) time: 0.5099 [2021-03-26 07:19:08 swin_small_patch4_window7_224] INFO: Epoch: [152] [1230/1251] eta: 0:00:10 lr: 0.000490 loss: 3.3292 (3.3039) grad_norm: 1.3813 (1.4566) time: 0.5058 [2021-03-26 07:19:13 swin_small_patch4_window7_224] INFO: Epoch: [152] [1240/1251] eta: 0:00:05 lr: 0.000489 loss: 3.5033 (3.3055) grad_norm: 1.4276 (1.4564) time: 0.5041 [2021-03-26 07:19:18 swin_small_patch4_window7_224] INFO: Epoch: [152] [1250/1251] eta: 0:00:00 lr: 0.000489 loss: 3.1128 (3.3026) grad_norm: 1.4433 (1.4562) time: 0.5030 [2021-03-26 07:19:23 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.8766 (0.8766) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-26 07:19:26 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9183 (0.9089) acc1: 78.1250 (77.6989) acc5: 93.7500 (94.4602) [2021-03-26 07:19:28 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8807 (0.8880) acc1: 78.1250 (77.9762) acc5: 93.7500 (94.8661) [2021-03-26 07:19:30 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8300 (0.8984) acc1: 78.1250 (77.9738) acc5: 93.7500 (94.4556) [2021-03-26 07:19:32 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8853 (0.8981) acc1: 78.1250 (77.8582) acc5: 95.3125 (94.5122) [2021-03-26 07:19:33 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9039 (0.9051) acc1: 78.1250 (77.8240) acc5: 95.3125 (94.3040) [2021-03-26 07:19:41 swin_small_patch4_window7_224] INFO: * Acc@1 78.556 Acc@5 94.518 loss 0.894 [2021-03-26 07:19:41 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.6% [2021-03-26 07:19:41 swin_small_patch4_window7_224] INFO: Max accuracy: 78.56% [2021-03-26 07:19:46 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 0/1251] eta: 1:29:51 lr: 0.000489 loss: 2.8091 (2.8091) grad_norm: 1.4971 (1.4971) time: 4.3094 [2021-03-26 07:19:51 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 10/1251] eta: 0:17:39 lr: 0.000489 loss: 2.8084 (2.7943) grad_norm: 1.4710 (1.5087) time: 0.8540 [2021-03-26 07:19:56 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 20/1251] eta: 0:14:10 lr: 0.000489 loss: 3.0832 (2.9400) grad_norm: 1.4905 (1.5429) time: 0.5100 [2021-03-26 07:20:01 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 30/1251] eta: 0:12:59 lr: 0.000489 loss: 3.1075 (3.0116) grad_norm: 1.4726 (1.5158) time: 0.5194 [2021-03-26 07:20:06 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 40/1251] eta: 0:12:15 lr: 0.000489 loss: 3.3365 (3.0700) grad_norm: 1.4637 (1.5183) time: 0.5197 [2021-03-26 07:20:11 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 50/1251] eta: 0:11:44 lr: 0.000489 loss: 3.3526 (3.0865) grad_norm: 1.4795 (1.5172) time: 0.5076 [2021-03-26 07:20:16 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 60/1251] eta: 0:11:22 lr: 0.000489 loss: 3.4899 (3.1448) grad_norm: 1.4372 (1.5110) time: 0.5023 [2021-03-26 07:20:21 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 70/1251] eta: 0:11:05 lr: 0.000489 loss: 3.4899 (3.1721) grad_norm: 1.4313 (1.4936) time: 0.5049 [2021-03-26 07:20:26 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 80/1251] eta: 0:10:51 lr: 0.000489 loss: 3.4443 (3.2126) grad_norm: 1.3768 (1.4840) time: 0.5072 [2021-03-26 07:20:31 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 90/1251] eta: 0:10:38 lr: 0.000489 loss: 3.4386 (3.2098) grad_norm: 1.3882 (1.4820) time: 0.5024 [2021-03-26 07:20:37 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 100/1251] eta: 0:10:29 lr: 0.000489 loss: 3.2715 (3.1999) grad_norm: 1.4356 (1.4734) time: 0.5073 [2021-03-26 07:20:42 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 110/1251] eta: 0:10:21 lr: 0.000489 loss: 3.2798 (3.2039) grad_norm: 1.4219 (1.4696) time: 0.5183 [2021-03-26 07:20:47 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 120/1251] eta: 0:10:12 lr: 0.000489 loss: 3.3019 (3.2013) grad_norm: 1.4703 (1.4754) time: 0.5153 [2021-03-26 07:20:52 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 130/1251] eta: 0:10:06 lr: 0.000489 loss: 3.2917 (3.1999) grad_norm: 1.4938 (1.4780) time: 0.5187 [2021-03-26 07:20:57 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 140/1251] eta: 0:09:56 lr: 0.000489 loss: 3.1659 (3.2031) grad_norm: 1.4765 (1.4759) time: 0.5101 [2021-03-26 07:21:02 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 150/1251] eta: 0:09:48 lr: 0.000489 loss: 3.5392 (3.2292) grad_norm: 1.4741 (1.4784) time: 0.4974 [2021-03-26 07:21:07 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 160/1251] eta: 0:09:41 lr: 0.000489 loss: 3.5305 (3.2178) grad_norm: 1.5093 (1.4801) time: 0.4999 [2021-03-26 07:21:12 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 170/1251] eta: 0:09:33 lr: 0.000489 loss: 3.2200 (3.2139) grad_norm: 1.5116 (1.4801) time: 0.5001 [2021-03-26 07:21:17 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 180/1251] eta: 0:09:27 lr: 0.000489 loss: 3.4029 (3.2289) grad_norm: 1.4629 (1.4788) time: 0.5092 [2021-03-26 07:21:22 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 190/1251] eta: 0:09:21 lr: 0.000489 loss: 3.4756 (3.2352) grad_norm: 1.4629 (1.4799) time: 0.5127 [2021-03-26 07:21:27 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 200/1251] eta: 0:09:14 lr: 0.000489 loss: 3.2009 (3.2197) grad_norm: 1.4580 (1.4779) time: 0.5051 [2021-03-26 07:21:32 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 210/1251] eta: 0:09:07 lr: 0.000489 loss: 3.0636 (3.2195) grad_norm: 1.4857 (1.4801) time: 0.5019 [2021-03-26 07:21:37 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 220/1251] eta: 0:09:01 lr: 0.000489 loss: 3.2793 (3.2225) grad_norm: 1.4581 (1.4800) time: 0.5015 [2021-03-26 07:21:42 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 230/1251] eta: 0:08:55 lr: 0.000488 loss: 3.2793 (3.2226) grad_norm: 1.4222 (1.4785) time: 0.4997 [2021-03-26 07:21:48 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 240/1251] eta: 0:08:49 lr: 0.000488 loss: 3.3967 (3.2345) grad_norm: 1.4857 (1.4830) time: 0.5068 [2021-03-26 07:21:53 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 250/1251] eta: 0:08:43 lr: 0.000488 loss: 3.4688 (3.2414) grad_norm: 1.4275 (1.4788) time: 0.5091 [2021-03-26 07:21:58 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 260/1251] eta: 0:08:38 lr: 0.000488 loss: 3.4250 (3.2507) grad_norm: 1.3842 (1.4775) time: 0.5128 [2021-03-26 07:22:03 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 270/1251] eta: 0:08:32 lr: 0.000488 loss: 3.4250 (3.2499) grad_norm: 1.4140 (1.4741) time: 0.5153 [2021-03-26 07:22:08 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 280/1251] eta: 0:08:26 lr: 0.000488 loss: 3.4254 (3.2548) grad_norm: 1.4216 (1.4766) time: 0.5086 [2021-03-26 07:22:13 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 290/1251] eta: 0:08:20 lr: 0.000488 loss: 3.1899 (3.2469) grad_norm: 1.4596 (1.4747) time: 0.5039 [2021-03-26 07:22:18 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 300/1251] eta: 0:08:15 lr: 0.000488 loss: 3.1899 (3.2522) grad_norm: 1.3833 (1.4731) time: 0.5045 [2021-03-26 07:22:23 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 310/1251] eta: 0:08:09 lr: 0.000488 loss: 3.3178 (3.2461) grad_norm: 1.4073 (1.4729) time: 0.5129 [2021-03-26 07:22:28 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 320/1251] eta: 0:08:04 lr: 0.000488 loss: 3.1379 (3.2463) grad_norm: 1.4335 (1.4722) time: 0.5113 [2021-03-26 07:22:33 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 330/1251] eta: 0:07:58 lr: 0.000488 loss: 3.3624 (3.2481) grad_norm: 1.4942 (1.4751) time: 0.5010 [2021-03-26 07:22:38 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 340/1251] eta: 0:07:52 lr: 0.000488 loss: 3.3629 (3.2530) grad_norm: 1.5047 (1.4744) time: 0.5040 [2021-03-26 07:22:43 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 350/1251] eta: 0:07:47 lr: 0.000488 loss: 3.4407 (3.2503) grad_norm: 1.3947 (1.4714) time: 0.5058 [2021-03-26 07:22:48 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 360/1251] eta: 0:07:41 lr: 0.000488 loss: 3.2032 (3.2478) grad_norm: 1.3527 (1.4684) time: 0.5029 [2021-03-26 07:22:53 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 370/1251] eta: 0:07:36 lr: 0.000488 loss: 3.2154 (3.2488) grad_norm: 1.3608 (1.4680) time: 0.5032 [2021-03-26 07:22:58 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 380/1251] eta: 0:07:30 lr: 0.000488 loss: 3.3005 (3.2485) grad_norm: 1.4240 (1.4673) time: 0.5028 [2021-03-26 07:23:04 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 390/1251] eta: 0:07:25 lr: 0.000488 loss: 3.3005 (3.2525) grad_norm: 1.3852 (1.4657) time: 0.5054 [2021-03-26 07:23:09 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 400/1251] eta: 0:07:19 lr: 0.000488 loss: 3.3835 (3.2556) grad_norm: 1.3685 (1.4641) time: 0.5050 [2021-03-26 07:23:14 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 410/1251] eta: 0:07:14 lr: 0.000488 loss: 3.4997 (3.2599) grad_norm: 1.4595 (1.4656) time: 0.5008 [2021-03-26 07:23:19 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 420/1251] eta: 0:07:08 lr: 0.000488 loss: 3.4941 (3.2642) grad_norm: 1.4712 (1.4666) time: 0.5011 [2021-03-26 07:23:24 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 430/1251] eta: 0:07:03 lr: 0.000488 loss: 3.2973 (3.2609) grad_norm: 1.3956 (1.4645) time: 0.5023 [2021-03-26 07:23:29 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 440/1251] eta: 0:06:57 lr: 0.000488 loss: 3.1429 (3.2573) grad_norm: 1.3817 (1.4641) time: 0.5012 [2021-03-26 07:23:34 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 450/1251] eta: 0:06:52 lr: 0.000488 loss: 3.3080 (3.2624) grad_norm: 1.5254 (1.4663) time: 0.5105 [2021-03-26 07:23:39 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 460/1251] eta: 0:06:47 lr: 0.000488 loss: 3.5197 (3.2633) grad_norm: 1.5245 (1.4665) time: 0.5060 [2021-03-26 07:23:44 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 470/1251] eta: 0:06:42 lr: 0.000488 loss: 3.4064 (3.2635) grad_norm: 1.4404 (1.4654) time: 0.4990 [2021-03-26 07:23:49 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 480/1251] eta: 0:06:36 lr: 0.000487 loss: 3.3840 (3.2613) grad_norm: 1.3750 (1.4641) time: 0.5035 [2021-03-26 07:23:54 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 490/1251] eta: 0:06:31 lr: 0.000487 loss: 3.3881 (3.2618) grad_norm: 1.4799 (1.4653) time: 0.5022 [2021-03-26 07:23:59 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 500/1251] eta: 0:06:25 lr: 0.000487 loss: 3.1740 (3.2593) grad_norm: 1.4404 (1.4657) time: 0.5010 [2021-03-26 07:24:04 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 510/1251] eta: 0:06:20 lr: 0.000487 loss: 3.2000 (3.2602) grad_norm: 1.3970 (1.4670) time: 0.4986 [2021-03-26 07:24:09 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 520/1251] eta: 0:06:15 lr: 0.000487 loss: 3.3491 (3.2586) grad_norm: 1.4633 (1.4680) time: 0.5019 [2021-03-26 07:24:14 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 530/1251] eta: 0:06:10 lr: 0.000487 loss: 3.3491 (3.2586) grad_norm: 1.3920 (1.4666) time: 0.5082 [2021-03-26 07:24:19 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 540/1251] eta: 0:06:04 lr: 0.000487 loss: 3.3757 (3.2599) grad_norm: 1.3672 (1.4665) time: 0.5080 [2021-03-26 07:24:24 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 550/1251] eta: 0:05:59 lr: 0.000487 loss: 3.3421 (3.2625) grad_norm: 1.4196 (1.4662) time: 0.5144 [2021-03-26 07:24:29 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 560/1251] eta: 0:05:54 lr: 0.000487 loss: 3.3421 (3.2635) grad_norm: 1.4210 (1.4657) time: 0.5134 [2021-03-26 07:24:34 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 570/1251] eta: 0:05:49 lr: 0.000487 loss: 3.4374 (3.2690) grad_norm: 1.4166 (1.4651) time: 0.5078 [2021-03-26 07:24:40 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 580/1251] eta: 0:05:44 lr: 0.000487 loss: 3.3664 (3.2642) grad_norm: 1.3869 (1.4647) time: 0.5133 [2021-03-26 07:24:45 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 590/1251] eta: 0:05:39 lr: 0.000487 loss: 3.2143 (3.2661) grad_norm: 1.3169 (1.4636) time: 0.5112 [2021-03-26 07:24:50 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 600/1251] eta: 0:05:33 lr: 0.000487 loss: 3.6246 (3.2709) grad_norm: 1.3535 (1.4634) time: 0.4999 [2021-03-26 07:24:55 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 610/1251] eta: 0:05:28 lr: 0.000487 loss: 3.4427 (3.2684) grad_norm: 1.3535 (1.4619) time: 0.4957 [2021-03-26 07:25:00 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 620/1251] eta: 0:05:23 lr: 0.000487 loss: 3.3908 (3.2709) grad_norm: 1.3719 (1.4604) time: 0.5040 [2021-03-26 07:25:05 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 630/1251] eta: 0:05:18 lr: 0.000487 loss: 3.4128 (3.2723) grad_norm: 1.4465 (1.4615) time: 0.5072 [2021-03-26 07:25:10 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 640/1251] eta: 0:05:13 lr: 0.000487 loss: 3.4128 (3.2750) grad_norm: 1.4375 (1.4602) time: 0.5102 [2021-03-26 07:25:15 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 650/1251] eta: 0:05:07 lr: 0.000487 loss: 3.2588 (3.2716) grad_norm: 1.4035 (1.4594) time: 0.5122 [2021-03-26 07:25:20 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 660/1251] eta: 0:05:02 lr: 0.000487 loss: 3.2588 (3.2732) grad_norm: 1.4237 (1.4586) time: 0.5050 [2021-03-26 07:25:25 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 670/1251] eta: 0:04:57 lr: 0.000487 loss: 3.2340 (3.2666) grad_norm: 1.3898 (1.4582) time: 0.5071 [2021-03-26 07:25:30 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 680/1251] eta: 0:04:52 lr: 0.000487 loss: 3.0885 (3.2660) grad_norm: 1.3942 (1.4580) time: 0.5170 [2021-03-26 07:25:35 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 690/1251] eta: 0:04:47 lr: 0.000487 loss: 3.2613 (3.2637) grad_norm: 1.4407 (1.4589) time: 0.5145 [2021-03-26 07:25:40 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 700/1251] eta: 0:04:42 lr: 0.000487 loss: 3.2911 (3.2633) grad_norm: 1.4407 (1.4587) time: 0.5018 [2021-03-26 07:25:45 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 710/1251] eta: 0:04:36 lr: 0.000487 loss: 3.1730 (3.2607) grad_norm: 1.4378 (1.4591) time: 0.4968 [2021-03-26 07:25:50 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 720/1251] eta: 0:04:31 lr: 0.000486 loss: 3.3378 (3.2622) grad_norm: 1.5545 (1.4625) time: 0.4980 [2021-03-26 07:25:56 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 730/1251] eta: 0:04:26 lr: 0.000486 loss: 3.4206 (3.2643) grad_norm: 1.5137 (1.4630) time: 0.5094 [2021-03-26 07:26:01 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 740/1251] eta: 0:04:21 lr: 0.000486 loss: 3.4670 (3.2675) grad_norm: 1.4922 (1.4642) time: 0.5201 [2021-03-26 07:26:06 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 750/1251] eta: 0:04:16 lr: 0.000486 loss: 3.5458 (3.2707) grad_norm: 1.5315 (1.4648) time: 0.5118 [2021-03-26 07:26:11 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 760/1251] eta: 0:04:11 lr: 0.000486 loss: 3.4472 (3.2719) grad_norm: 1.5279 (1.4652) time: 0.5002 [2021-03-26 07:26:16 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 770/1251] eta: 0:04:06 lr: 0.000486 loss: 3.3914 (3.2713) grad_norm: 1.4978 (1.4661) time: 0.5011 [2021-03-26 07:26:21 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 780/1251] eta: 0:04:00 lr: 0.000486 loss: 3.3994 (3.2725) grad_norm: 1.5585 (1.4677) time: 0.5109 [2021-03-26 07:26:26 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 790/1251] eta: 0:03:55 lr: 0.000486 loss: 3.4019 (3.2715) grad_norm: 1.5209 (1.4670) time: 0.5072 [2021-03-26 07:26:31 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 800/1251] eta: 0:03:50 lr: 0.000486 loss: 3.3257 (3.2718) grad_norm: 1.3752 (1.4663) time: 0.4963 [2021-03-26 07:26:36 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 810/1251] eta: 0:03:45 lr: 0.000486 loss: 3.3937 (3.2723) grad_norm: 1.3924 (1.4668) time: 0.4978 [2021-03-26 07:26:41 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 820/1251] eta: 0:03:40 lr: 0.000486 loss: 3.3946 (3.2724) grad_norm: 1.4148 (1.4674) time: 0.4997 [2021-03-26 07:26:46 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 830/1251] eta: 0:03:35 lr: 0.000486 loss: 3.3966 (3.2725) grad_norm: 1.4148 (1.4661) time: 0.5018 [2021-03-26 07:26:51 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 840/1251] eta: 0:03:29 lr: 0.000486 loss: 3.3072 (3.2717) grad_norm: 1.3604 (1.4654) time: 0.5104 [2021-03-26 07:26:56 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 850/1251] eta: 0:03:24 lr: 0.000486 loss: 3.3355 (3.2727) grad_norm: 1.4138 (1.4653) time: 0.5088 [2021-03-26 07:27:01 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 860/1251] eta: 0:03:19 lr: 0.000486 loss: 3.3355 (3.2688) grad_norm: 1.4138 (1.4651) time: 0.5015 [2021-03-26 07:27:06 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 870/1251] eta: 0:03:14 lr: 0.000486 loss: 3.1753 (3.2703) grad_norm: 1.4724 (1.4660) time: 0.5072 [2021-03-26 07:27:11 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 880/1251] eta: 0:03:09 lr: 0.000486 loss: 3.1753 (3.2671) grad_norm: 1.4966 (1.4662) time: 0.5139 [2021-03-26 07:27:16 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 890/1251] eta: 0:03:04 lr: 0.000486 loss: 2.7547 (3.2645) grad_norm: 1.4595 (1.4660) time: 0.5095 [2021-03-26 07:27:22 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 900/1251] eta: 0:02:59 lr: 0.000486 loss: 3.3308 (3.2686) grad_norm: 1.4364 (1.4664) time: 0.5047 [2021-03-26 07:27:27 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 910/1251] eta: 0:02:54 lr: 0.000486 loss: 3.4213 (3.2690) grad_norm: 1.4752 (1.4669) time: 0.5061 [2021-03-26 07:27:32 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 920/1251] eta: 0:02:49 lr: 0.000486 loss: 3.4213 (3.2705) grad_norm: 1.4752 (1.4667) time: 0.5105 [2021-03-26 07:27:37 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 930/1251] eta: 0:02:43 lr: 0.000486 loss: 3.5387 (3.2718) grad_norm: 1.4203 (1.4676) time: 0.5135 [2021-03-26 07:27:42 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 940/1251] eta: 0:02:38 lr: 0.000486 loss: 3.5446 (3.2751) grad_norm: 1.3960 (1.4679) time: 0.5088 [2021-03-26 07:27:47 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 950/1251] eta: 0:02:33 lr: 0.000486 loss: 3.5168 (3.2758) grad_norm: 1.4812 (1.4684) time: 0.5045 [2021-03-26 07:27:52 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 960/1251] eta: 0:02:28 lr: 0.000485 loss: 3.1631 (3.2755) grad_norm: 1.4790 (1.4680) time: 0.5077 [2021-03-26 07:27:57 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 970/1251] eta: 0:02:23 lr: 0.000485 loss: 3.2662 (3.2761) grad_norm: 1.4038 (1.4674) time: 0.5066 [2021-03-26 07:28:02 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 980/1251] eta: 0:02:18 lr: 0.000485 loss: 3.5766 (3.2785) grad_norm: 1.3881 (1.4669) time: 0.4989 [2021-03-26 07:28:07 swin_small_patch4_window7_224] INFO: Epoch: [153] [ 990/1251] eta: 0:02:13 lr: 0.000485 loss: 3.5766 (3.2782) grad_norm: 1.3766 (1.4664) time: 0.4979 [2021-03-26 07:28:12 swin_small_patch4_window7_224] INFO: Epoch: [153] [1000/1251] eta: 0:02:08 lr: 0.000485 loss: 3.2143 (3.2768) grad_norm: 1.3957 (1.4657) time: 0.5078 [2021-03-26 07:28:17 swin_small_patch4_window7_224] INFO: Epoch: [153] [1010/1251] eta: 0:02:02 lr: 0.000485 loss: 3.2273 (3.2764) grad_norm: 1.4381 (1.4662) time: 0.5073 [2021-03-26 07:28:22 swin_small_patch4_window7_224] INFO: Epoch: [153] [1020/1251] eta: 0:01:57 lr: 0.000485 loss: 3.3530 (3.2787) grad_norm: 1.4381 (1.4656) time: 0.5000 [2021-03-26 07:28:27 swin_small_patch4_window7_224] INFO: Epoch: [153] [1030/1251] eta: 0:01:52 lr: 0.000485 loss: 3.6206 (3.2815) grad_norm: 1.4136 (1.4652) time: 0.4999 [2021-03-26 07:28:32 swin_small_patch4_window7_224] INFO: Epoch: [153] [1040/1251] eta: 0:01:47 lr: 0.000485 loss: 3.6206 (3.2824) grad_norm: 1.5018 (1.4660) time: 0.5005 [2021-03-26 07:28:37 swin_small_patch4_window7_224] INFO: Epoch: [153] [1050/1251] eta: 0:01:42 lr: 0.000485 loss: 3.4141 (3.2837) grad_norm: 1.4829 (1.4659) time: 0.5078 [2021-03-26 07:28:42 swin_small_patch4_window7_224] INFO: Epoch: [153] [1060/1251] eta: 0:01:37 lr: 0.000485 loss: 3.3385 (3.2858) grad_norm: 1.4402 (1.4655) time: 0.5087 [2021-03-26 07:28:48 swin_small_patch4_window7_224] INFO: Epoch: [153] [1070/1251] eta: 0:01:32 lr: 0.000485 loss: 3.3606 (3.2870) grad_norm: 1.3764 (1.4647) time: 0.5078 [2021-03-26 07:28:53 swin_small_patch4_window7_224] INFO: Epoch: [153] [1080/1251] eta: 0:01:27 lr: 0.000485 loss: 3.3121 (3.2837) grad_norm: 1.3884 (1.4644) time: 0.5054 [2021-03-26 07:28:58 swin_small_patch4_window7_224] INFO: Epoch: [153] [1090/1251] eta: 0:01:22 lr: 0.000485 loss: 3.1782 (3.2829) grad_norm: 1.4098 (1.4643) time: 0.5027 [2021-03-26 07:29:03 swin_small_patch4_window7_224] INFO: Epoch: [153] [1100/1251] eta: 0:01:16 lr: 0.000485 loss: 3.2283 (3.2831) grad_norm: 1.4690 (1.4651) time: 0.5044 [2021-03-26 07:29:08 swin_small_patch4_window7_224] INFO: Epoch: [153] [1110/1251] eta: 0:01:11 lr: 0.000485 loss: 3.1681 (3.2817) grad_norm: 1.4272 (1.4646) time: 0.5017 [2021-03-26 07:29:13 swin_small_patch4_window7_224] INFO: Epoch: [153] [1120/1251] eta: 0:01:06 lr: 0.000485 loss: 3.1283 (3.2823) grad_norm: 1.4272 (1.4650) time: 0.4988 [2021-03-26 07:29:18 swin_small_patch4_window7_224] INFO: Epoch: [153] [1130/1251] eta: 0:01:01 lr: 0.000485 loss: 3.4921 (3.2828) grad_norm: 1.4794 (1.4651) time: 0.4981 [2021-03-26 07:29:23 swin_small_patch4_window7_224] INFO: Epoch: [153] [1140/1251] eta: 0:00:56 lr: 0.000485 loss: 3.2625 (3.2821) grad_norm: 1.4468 (1.4652) time: 0.5001 [2021-03-26 07:29:28 swin_small_patch4_window7_224] INFO: Epoch: [153] [1150/1251] eta: 0:00:51 lr: 0.000485 loss: 3.3464 (3.2823) grad_norm: 1.4524 (1.4653) time: 0.5001 [2021-03-26 07:29:33 swin_small_patch4_window7_224] INFO: Epoch: [153] [1160/1251] eta: 0:00:46 lr: 0.000485 loss: 3.0915 (3.2790) grad_norm: 1.4151 (1.4651) time: 0.5009 [2021-03-26 07:29:38 swin_small_patch4_window7_224] INFO: Epoch: [153] [1170/1251] eta: 0:00:41 lr: 0.000485 loss: 3.0915 (3.2769) grad_norm: 1.3961 (1.4649) time: 0.5047 [2021-03-26 07:29:43 swin_small_patch4_window7_224] INFO: Epoch: [153] [1180/1251] eta: 0:00:36 lr: 0.000485 loss: 3.2262 (3.2765) grad_norm: 1.4061 (1.4646) time: 0.5051 [2021-03-26 07:29:48 swin_small_patch4_window7_224] INFO: Epoch: [153] [1190/1251] eta: 0:00:31 lr: 0.000485 loss: 3.2928 (3.2765) grad_norm: 1.4037 (1.4640) time: 0.5042 [2021-03-26 07:29:53 swin_small_patch4_window7_224] INFO: Epoch: [153] [1200/1251] eta: 0:00:25 lr: 0.000484 loss: 3.3309 (3.2766) grad_norm: 1.3825 (1.4638) time: 0.5145 [2021-03-26 07:29:58 swin_small_patch4_window7_224] INFO: Epoch: [153] [1210/1251] eta: 0:00:20 lr: 0.000484 loss: 3.3811 (3.2777) grad_norm: 1.4886 (1.4649) time: 0.5199 [2021-03-26 07:30:03 swin_small_patch4_window7_224] INFO: Epoch: [153] [1220/1251] eta: 0:00:15 lr: 0.000484 loss: 3.4702 (3.2805) grad_norm: 1.5145 (1.4650) time: 0.5095 [2021-03-26 07:30:08 swin_small_patch4_window7_224] INFO: Epoch: [153] [1230/1251] eta: 0:00:10 lr: 0.000484 loss: 3.4702 (3.2806) grad_norm: 1.4103 (1.4645) time: 0.5041 [2021-03-26 07:30:13 swin_small_patch4_window7_224] INFO: Epoch: [153] [1240/1251] eta: 0:00:05 lr: 0.000484 loss: 3.4137 (3.2812) grad_norm: 1.3939 (1.4641) time: 0.5035 [2021-03-26 07:30:18 swin_small_patch4_window7_224] INFO: Epoch: [153] [1250/1251] eta: 0:00:00 lr: 0.000484 loss: 3.4239 (3.2825) grad_norm: 1.4644 (1.4644) time: 0.5009 [2021-03-26 07:30:26 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:31 loss: 0.8225 (0.8225) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 07:30:29 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8586 (0.8560) acc1: 78.1250 (79.9716) acc5: 95.3125 (95.1705) [2021-03-26 07:30:31 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8590 (0.8756) acc1: 78.1250 (79.0179) acc5: 95.3125 (95.1637) [2021-03-26 07:30:33 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8635 (0.8953) acc1: 76.5625 (78.9315) acc5: 95.3125 (94.8589) [2021-03-26 07:30:35 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9484 (0.9234) acc1: 76.5625 (77.7820) acc5: 93.7500 (94.5503) [2021-03-26 07:30:36 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9791 (0.9280) acc1: 75.0000 (77.5680) acc5: 95.3125 (94.6240) [2021-03-26 07:30:42 swin_small_patch4_window7_224] INFO: * Acc@1 78.382 Acc@5 94.514 loss 0.912 [2021-03-26 07:30:42 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-26 07:30:42 swin_small_patch4_window7_224] INFO: Max accuracy: 78.56% [2021-03-26 07:30:47 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 0/1251] eta: 1:28:38 lr: 0.000484 loss: 2.9127 (2.9127) grad_norm: 1.4806 (1.4806) time: 4.2516 [2021-03-26 07:30:52 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 10/1251] eta: 0:18:02 lr: 0.000484 loss: 3.5336 (3.1030) grad_norm: 1.4471 (1.4101) time: 0.8724 [2021-03-26 07:30:57 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 20/1251] eta: 0:14:25 lr: 0.000484 loss: 3.5336 (3.1302) grad_norm: 1.4471 (1.4338) time: 0.5258 [2021-03-26 07:31:02 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 30/1251] eta: 0:13:05 lr: 0.000484 loss: 3.1317 (3.0680) grad_norm: 1.4743 (1.4552) time: 0.5174 [2021-03-26 07:31:07 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 40/1251] eta: 0:12:16 lr: 0.000484 loss: 3.1390 (3.1036) grad_norm: 1.4743 (1.4569) time: 0.5082 [2021-03-26 07:31:12 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 50/1251] eta: 0:11:46 lr: 0.000484 loss: 3.1125 (3.1250) grad_norm: 1.4370 (1.4464) time: 0.5036 [2021-03-26 07:31:17 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 60/1251] eta: 0:11:25 lr: 0.000484 loss: 3.3421 (3.1591) grad_norm: 1.4435 (1.4508) time: 0.5079 [2021-03-26 07:31:22 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 70/1251] eta: 0:11:06 lr: 0.000484 loss: 3.3451 (3.1746) grad_norm: 1.4435 (1.4501) time: 0.5040 [2021-03-26 07:31:27 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 80/1251] eta: 0:10:51 lr: 0.000484 loss: 3.2724 (3.1853) grad_norm: 1.3915 (1.4532) time: 0.4977 [2021-03-26 07:31:32 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 90/1251] eta: 0:10:37 lr: 0.000484 loss: 3.4462 (3.2177) grad_norm: 1.4745 (1.4625) time: 0.4948 [2021-03-26 07:31:37 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 100/1251] eta: 0:10:26 lr: 0.000484 loss: 3.2570 (3.2058) grad_norm: 1.5021 (1.4699) time: 0.4971 [2021-03-26 07:31:43 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 110/1251] eta: 0:10:18 lr: 0.000484 loss: 3.2546 (3.2074) grad_norm: 1.4133 (1.4662) time: 0.5091 [2021-03-26 07:31:48 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 120/1251] eta: 0:10:09 lr: 0.000484 loss: 3.4525 (3.2297) grad_norm: 1.3932 (1.4712) time: 0.5101 [2021-03-26 07:31:53 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 130/1251] eta: 0:10:02 lr: 0.000484 loss: 3.5179 (3.2439) grad_norm: 1.4281 (1.4659) time: 0.5126 [2021-03-26 07:31:58 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 140/1251] eta: 0:09:54 lr: 0.000484 loss: 3.5024 (3.2490) grad_norm: 1.4195 (1.4603) time: 0.5120 [2021-03-26 07:32:03 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 150/1251] eta: 0:09:46 lr: 0.000484 loss: 3.5574 (3.2553) grad_norm: 1.4121 (1.4581) time: 0.4999 [2021-03-26 07:32:08 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 160/1251] eta: 0:09:39 lr: 0.000484 loss: 3.4796 (3.2623) grad_norm: 1.3858 (1.4527) time: 0.5054 [2021-03-26 07:32:13 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 170/1251] eta: 0:09:32 lr: 0.000484 loss: 3.5309 (3.2723) grad_norm: 1.4130 (1.4521) time: 0.5096 [2021-03-26 07:32:18 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 180/1251] eta: 0:09:25 lr: 0.000484 loss: 3.5309 (3.2742) grad_norm: 1.5045 (1.4547) time: 0.5026 [2021-03-26 07:32:23 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 190/1251] eta: 0:09:19 lr: 0.000483 loss: 3.4429 (3.2755) grad_norm: 1.5127 (1.4603) time: 0.5046 [2021-03-26 07:32:28 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 200/1251] eta: 0:09:13 lr: 0.000483 loss: 3.4429 (3.2828) grad_norm: 1.4230 (1.4550) time: 0.5158 [2021-03-26 07:32:33 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 210/1251] eta: 0:09:07 lr: 0.000483 loss: 3.2762 (3.2705) grad_norm: 1.4149 (1.4540) time: 0.5166 [2021-03-26 07:32:38 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 220/1251] eta: 0:09:01 lr: 0.000483 loss: 3.1581 (3.2735) grad_norm: 1.4159 (1.4522) time: 0.5053 [2021-03-26 07:32:44 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 230/1251] eta: 0:08:55 lr: 0.000483 loss: 3.1719 (3.2696) grad_norm: 1.4305 (1.4538) time: 0.5072 [2021-03-26 07:32:49 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 240/1251] eta: 0:08:49 lr: 0.000483 loss: 3.2991 (3.2704) grad_norm: 1.4857 (1.4567) time: 0.5118 [2021-03-26 07:32:54 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 250/1251] eta: 0:08:43 lr: 0.000483 loss: 3.3996 (3.2723) grad_norm: 1.4495 (1.4564) time: 0.5072 [2021-03-26 07:32:59 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 260/1251] eta: 0:08:37 lr: 0.000483 loss: 3.3843 (3.2703) grad_norm: 1.4830 (1.4610) time: 0.5038 [2021-03-26 07:33:04 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 270/1251] eta: 0:08:31 lr: 0.000483 loss: 3.2804 (3.2679) grad_norm: 1.4685 (1.4616) time: 0.5002 [2021-03-26 07:33:09 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 280/1251] eta: 0:08:25 lr: 0.000483 loss: 3.1614 (3.2613) grad_norm: 1.4354 (1.4595) time: 0.5014 [2021-03-26 07:33:14 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 290/1251] eta: 0:08:19 lr: 0.000483 loss: 3.1846 (3.2570) grad_norm: 1.3800 (1.4582) time: 0.4992 [2021-03-26 07:33:19 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 300/1251] eta: 0:08:13 lr: 0.000483 loss: 3.2371 (3.2588) grad_norm: 1.3442 (1.4570) time: 0.4996 [2021-03-26 07:33:24 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 310/1251] eta: 0:08:08 lr: 0.000483 loss: 3.2413 (3.2572) grad_norm: 1.4645 (1.4580) time: 0.5065 [2021-03-26 07:33:29 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 320/1251] eta: 0:08:03 lr: 0.000483 loss: 3.1185 (3.2503) grad_norm: 1.3723 (1.4573) time: 0.5117 [2021-03-26 07:33:34 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 330/1251] eta: 0:07:57 lr: 0.000483 loss: 3.2365 (3.2539) grad_norm: 1.3859 (1.4598) time: 0.5083 [2021-03-26 07:33:39 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 340/1251] eta: 0:07:52 lr: 0.000483 loss: 3.4600 (3.2578) grad_norm: 1.4900 (1.4603) time: 0.5065 [2021-03-26 07:33:44 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 350/1251] eta: 0:07:46 lr: 0.000483 loss: 3.3742 (3.2532) grad_norm: 1.4317 (1.4590) time: 0.5035 [2021-03-26 07:33:49 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 360/1251] eta: 0:07:40 lr: 0.000483 loss: 3.2868 (3.2529) grad_norm: 1.4415 (1.4595) time: 0.4953 [2021-03-26 07:33:54 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 370/1251] eta: 0:07:35 lr: 0.000483 loss: 3.3131 (3.2540) grad_norm: 1.4857 (1.4602) time: 0.5008 [2021-03-26 07:33:59 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 380/1251] eta: 0:07:29 lr: 0.000483 loss: 3.3726 (3.2588) grad_norm: 1.4034 (1.4589) time: 0.5085 [2021-03-26 07:34:04 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 390/1251] eta: 0:07:24 lr: 0.000483 loss: 3.5230 (3.2656) grad_norm: 1.3835 (1.4580) time: 0.5016 [2021-03-26 07:34:09 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 400/1251] eta: 0:07:18 lr: 0.000483 loss: 3.4024 (3.2642) grad_norm: 1.3849 (1.4593) time: 0.4964 [2021-03-26 07:34:14 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 410/1251] eta: 0:07:13 lr: 0.000483 loss: 3.3359 (3.2651) grad_norm: 1.4339 (1.4589) time: 0.5015 [2021-03-26 07:34:19 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 420/1251] eta: 0:07:07 lr: 0.000483 loss: 3.3359 (3.2605) grad_norm: 1.3946 (1.4578) time: 0.5052 [2021-03-26 07:34:24 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 430/1251] eta: 0:07:02 lr: 0.000482 loss: 3.4223 (3.2648) grad_norm: 1.3663 (1.4554) time: 0.5041 [2021-03-26 07:34:29 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 440/1251] eta: 0:06:57 lr: 0.000482 loss: 3.3816 (3.2646) grad_norm: 1.3306 (1.4519) time: 0.5024 [2021-03-26 07:34:34 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 450/1251] eta: 0:06:51 lr: 0.000482 loss: 3.4253 (3.2705) grad_norm: 1.3679 (1.4521) time: 0.5060 [2021-03-26 07:34:39 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 460/1251] eta: 0:06:46 lr: 0.000482 loss: 3.2871 (3.2653) grad_norm: 1.4175 (1.4516) time: 0.5053 [2021-03-26 07:34:44 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 470/1251] eta: 0:06:41 lr: 0.000482 loss: 3.2871 (3.2705) grad_norm: 1.3663 (1.4507) time: 0.5033 [2021-03-26 07:34:49 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 480/1251] eta: 0:06:35 lr: 0.000482 loss: 3.3884 (3.2660) grad_norm: 1.4280 (1.4518) time: 0.5027 [2021-03-26 07:34:55 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 490/1251] eta: 0:06:30 lr: 0.000482 loss: 2.9312 (3.2651) grad_norm: 1.4935 (1.4520) time: 0.5017 [2021-03-26 07:35:00 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 500/1251] eta: 0:06:25 lr: 0.000482 loss: 3.1217 (3.2613) grad_norm: 1.4935 (1.4534) time: 0.5032 [2021-03-26 07:35:05 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 510/1251] eta: 0:06:20 lr: 0.000482 loss: 3.2493 (3.2588) grad_norm: 1.5147 (1.4548) time: 0.5072 [2021-03-26 07:35:10 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 520/1251] eta: 0:06:15 lr: 0.000482 loss: 3.2645 (3.2619) grad_norm: 1.4353 (1.4534) time: 0.5126 [2021-03-26 07:35:15 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 530/1251] eta: 0:06:09 lr: 0.000482 loss: 3.4347 (3.2616) grad_norm: 1.4401 (1.4551) time: 0.5073 [2021-03-26 07:35:20 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 540/1251] eta: 0:06:04 lr: 0.000482 loss: 3.1434 (3.2609) grad_norm: 1.4845 (1.4557) time: 0.5084 [2021-03-26 07:35:25 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 550/1251] eta: 0:05:59 lr: 0.000482 loss: 3.2377 (3.2610) grad_norm: 1.4747 (1.4564) time: 0.5153 [2021-03-26 07:35:30 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 560/1251] eta: 0:05:54 lr: 0.000482 loss: 3.4600 (3.2640) grad_norm: 1.4748 (1.4565) time: 0.5117 [2021-03-26 07:35:35 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 570/1251] eta: 0:05:49 lr: 0.000482 loss: 3.1442 (3.2572) grad_norm: 1.4763 (1.4570) time: 0.5087 [2021-03-26 07:35:40 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 580/1251] eta: 0:05:44 lr: 0.000482 loss: 3.1575 (3.2609) grad_norm: 1.4978 (1.4591) time: 0.5095 [2021-03-26 07:35:46 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 590/1251] eta: 0:05:38 lr: 0.000482 loss: 3.4810 (3.2634) grad_norm: 1.5250 (1.4603) time: 0.5117 [2021-03-26 07:35:51 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 600/1251] eta: 0:05:33 lr: 0.000482 loss: 3.3107 (3.2607) grad_norm: 1.4768 (1.4605) time: 0.5069 [2021-03-26 07:35:56 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 610/1251] eta: 0:05:28 lr: 0.000482 loss: 3.1486 (3.2589) grad_norm: 1.4349 (1.4605) time: 0.5002 [2021-03-26 07:36:01 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 620/1251] eta: 0:05:23 lr: 0.000482 loss: 3.4236 (3.2622) grad_norm: 1.4125 (1.4618) time: 0.4984 [2021-03-26 07:36:06 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 630/1251] eta: 0:05:17 lr: 0.000482 loss: 3.5484 (3.2631) grad_norm: 1.4050 (1.4621) time: 0.5009 [2021-03-26 07:36:11 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 640/1251] eta: 0:05:12 lr: 0.000482 loss: 3.4443 (3.2647) grad_norm: 1.4098 (1.4611) time: 0.5057 [2021-03-26 07:36:16 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 650/1251] eta: 0:05:07 lr: 0.000482 loss: 3.5504 (3.2681) grad_norm: 1.4209 (1.4604) time: 0.5051 [2021-03-26 07:36:21 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 660/1251] eta: 0:05:02 lr: 0.000482 loss: 3.3838 (3.2655) grad_norm: 1.4733 (1.4619) time: 0.5028 [2021-03-26 07:36:26 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 670/1251] eta: 0:04:57 lr: 0.000481 loss: 3.0077 (3.2624) grad_norm: 1.5047 (1.4627) time: 0.5035 [2021-03-26 07:36:31 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 680/1251] eta: 0:04:51 lr: 0.000481 loss: 3.1435 (3.2617) grad_norm: 1.4572 (1.4624) time: 0.5022 [2021-03-26 07:36:36 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 690/1251] eta: 0:04:46 lr: 0.000481 loss: 3.3929 (3.2671) grad_norm: 1.4313 (1.4627) time: 0.5065 [2021-03-26 07:36:41 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 700/1251] eta: 0:04:41 lr: 0.000481 loss: 3.6555 (3.2696) grad_norm: 1.4383 (1.4624) time: 0.5093 [2021-03-26 07:36:46 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 710/1251] eta: 0:04:36 lr: 0.000481 loss: 3.5579 (3.2708) grad_norm: 1.3981 (1.4621) time: 0.5147 [2021-03-26 07:36:51 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 720/1251] eta: 0:04:31 lr: 0.000481 loss: 3.5598 (3.2736) grad_norm: 1.4494 (1.4623) time: 0.5138 [2021-03-26 07:36:56 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 730/1251] eta: 0:04:26 lr: 0.000481 loss: 3.5187 (3.2751) grad_norm: 1.4876 (1.4628) time: 0.5099 [2021-03-26 07:37:02 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 740/1251] eta: 0:04:21 lr: 0.000481 loss: 3.0912 (3.2712) grad_norm: 1.4732 (1.4636) time: 0.5143 [2021-03-26 07:37:07 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 750/1251] eta: 0:04:16 lr: 0.000481 loss: 3.0912 (3.2718) grad_norm: 1.4699 (1.4637) time: 0.5115 [2021-03-26 07:37:12 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 760/1251] eta: 0:04:11 lr: 0.000481 loss: 3.3214 (3.2700) grad_norm: 1.4699 (1.4643) time: 0.5083 [2021-03-26 07:37:17 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 770/1251] eta: 0:04:05 lr: 0.000481 loss: 3.1226 (3.2712) grad_norm: 1.4688 (1.4644) time: 0.5086 [2021-03-26 07:37:22 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 780/1251] eta: 0:04:00 lr: 0.000481 loss: 3.4940 (3.2698) grad_norm: 1.4142 (1.4643) time: 0.5094 [2021-03-26 07:37:27 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 790/1251] eta: 0:03:55 lr: 0.000481 loss: 2.9375 (3.2666) grad_norm: 1.3915 (1.4636) time: 0.5048 [2021-03-26 07:37:32 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 800/1251] eta: 0:03:50 lr: 0.000481 loss: 3.5226 (3.2703) grad_norm: 1.4221 (1.4634) time: 0.5093 [2021-03-26 07:37:37 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 810/1251] eta: 0:03:45 lr: 0.000481 loss: 3.6285 (3.2717) grad_norm: 1.4374 (1.4638) time: 0.5083 [2021-03-26 07:37:42 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 820/1251] eta: 0:03:40 lr: 0.000481 loss: 3.2160 (3.2704) grad_norm: 1.4749 (1.4641) time: 0.5019 [2021-03-26 07:37:47 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 830/1251] eta: 0:03:35 lr: 0.000481 loss: 3.3119 (3.2708) grad_norm: 1.4753 (1.4644) time: 0.5050 [2021-03-26 07:37:52 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 840/1251] eta: 0:03:29 lr: 0.000481 loss: 3.3119 (3.2690) grad_norm: 1.3715 (1.4638) time: 0.5044 [2021-03-26 07:37:57 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 850/1251] eta: 0:03:24 lr: 0.000481 loss: 3.3513 (3.2705) grad_norm: 1.3715 (1.4629) time: 0.5084 [2021-03-26 07:38:02 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 860/1251] eta: 0:03:19 lr: 0.000481 loss: 3.1439 (3.2677) grad_norm: 1.3821 (1.4626) time: 0.5152 [2021-03-26 07:38:08 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 870/1251] eta: 0:03:14 lr: 0.000481 loss: 2.9793 (3.2671) grad_norm: 1.4402 (1.4628) time: 0.5125 [2021-03-26 07:38:13 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 880/1251] eta: 0:03:09 lr: 0.000481 loss: 3.2477 (3.2686) grad_norm: 1.4649 (1.4636) time: 0.5100 [2021-03-26 07:38:18 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 890/1251] eta: 0:03:04 lr: 0.000481 loss: 3.3103 (3.2669) grad_norm: 1.4722 (1.4639) time: 0.5036 [2021-03-26 07:38:23 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 900/1251] eta: 0:02:59 lr: 0.000481 loss: 3.2216 (3.2639) grad_norm: 1.4989 (1.4645) time: 0.4984 [2021-03-26 07:38:28 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 910/1251] eta: 0:02:54 lr: 0.000481 loss: 2.9168 (3.2612) grad_norm: 1.4986 (1.4642) time: 0.5014 [2021-03-26 07:38:33 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 920/1251] eta: 0:02:48 lr: 0.000480 loss: 3.0591 (3.2613) grad_norm: 1.5388 (1.4652) time: 0.5050 [2021-03-26 07:38:38 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 930/1251] eta: 0:02:43 lr: 0.000480 loss: 3.3310 (3.2611) grad_norm: 1.5199 (1.4649) time: 0.5093 [2021-03-26 07:38:43 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 940/1251] eta: 0:02:38 lr: 0.000480 loss: 3.5323 (3.2654) grad_norm: 1.5114 (1.4661) time: 0.5115 [2021-03-26 07:38:48 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 950/1251] eta: 0:02:33 lr: 0.000480 loss: 3.4143 (3.2637) grad_norm: 1.5412 (1.4669) time: 0.5099 [2021-03-26 07:38:53 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 960/1251] eta: 0:02:28 lr: 0.000480 loss: 3.2382 (3.2649) grad_norm: 1.4828 (1.4668) time: 0.5036 [2021-03-26 07:38:58 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 970/1251] eta: 0:02:23 lr: 0.000480 loss: 3.3407 (3.2652) grad_norm: 1.4290 (1.4669) time: 0.5002 [2021-03-26 07:39:03 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 980/1251] eta: 0:02:18 lr: 0.000480 loss: 3.2529 (3.2651) grad_norm: 1.4290 (1.4667) time: 0.5003 [2021-03-26 07:39:08 swin_small_patch4_window7_224] INFO: Epoch: [154] [ 990/1251] eta: 0:02:13 lr: 0.000480 loss: 2.9409 (3.2616) grad_norm: 1.4096 (1.4655) time: 0.5043 [2021-03-26 07:39:13 swin_small_patch4_window7_224] INFO: Epoch: [154] [1000/1251] eta: 0:02:08 lr: 0.000480 loss: 3.0412 (3.2620) grad_norm: 1.3882 (1.4654) time: 0.5071 [2021-03-26 07:39:18 swin_small_patch4_window7_224] INFO: Epoch: [154] [1010/1251] eta: 0:02:02 lr: 0.000480 loss: 3.4316 (3.2611) grad_norm: 1.4740 (1.4659) time: 0.5058 [2021-03-26 07:39:23 swin_small_patch4_window7_224] INFO: Epoch: [154] [1020/1251] eta: 0:01:57 lr: 0.000480 loss: 3.4628 (3.2627) grad_norm: 1.4237 (1.4655) time: 0.5064 [2021-03-26 07:39:28 swin_small_patch4_window7_224] INFO: Epoch: [154] [1030/1251] eta: 0:01:52 lr: 0.000480 loss: 3.4042 (3.2627) grad_norm: 1.4237 (1.4657) time: 0.5044 [2021-03-26 07:39:33 swin_small_patch4_window7_224] INFO: Epoch: [154] [1040/1251] eta: 0:01:47 lr: 0.000480 loss: 3.3171 (3.2638) grad_norm: 1.5158 (1.4660) time: 0.5046 [2021-03-26 07:39:39 swin_small_patch4_window7_224] INFO: Epoch: [154] [1050/1251] eta: 0:01:42 lr: 0.000480 loss: 3.2808 (3.2629) grad_norm: 1.4468 (1.4658) time: 0.5117 [2021-03-26 07:39:44 swin_small_patch4_window7_224] INFO: Epoch: [154] [1060/1251] eta: 0:01:37 lr: 0.000480 loss: 3.2919 (3.2658) grad_norm: 1.4225 (1.4656) time: 0.5067 [2021-03-26 07:39:49 swin_small_patch4_window7_224] INFO: Epoch: [154] [1070/1251] eta: 0:01:32 lr: 0.000480 loss: 3.5596 (3.2669) grad_norm: 1.4072 (1.4654) time: 0.5049 [2021-03-26 07:39:54 swin_small_patch4_window7_224] INFO: Epoch: [154] [1080/1251] eta: 0:01:27 lr: 0.000480 loss: 3.3693 (3.2656) grad_norm: 1.4395 (1.4655) time: 0.5125 [2021-03-26 07:39:59 swin_small_patch4_window7_224] INFO: Epoch: [154] [1090/1251] eta: 0:01:22 lr: 0.000480 loss: 3.2415 (3.2652) grad_norm: 1.4420 (1.4654) time: 0.5095 [2021-03-26 07:40:04 swin_small_patch4_window7_224] INFO: Epoch: [154] [1100/1251] eta: 0:01:16 lr: 0.000480 loss: 3.3850 (3.2648) grad_norm: 1.4420 (1.4655) time: 0.5040 [2021-03-26 07:40:09 swin_small_patch4_window7_224] INFO: Epoch: [154] [1110/1251] eta: 0:01:11 lr: 0.000480 loss: 3.4492 (3.2650) grad_norm: 1.4769 (1.4659) time: 0.5021 [2021-03-26 07:40:14 swin_small_patch4_window7_224] INFO: Epoch: [154] [1120/1251] eta: 0:01:06 lr: 0.000480 loss: 3.4414 (3.2644) grad_norm: 1.4232 (1.4655) time: 0.5032 [2021-03-26 07:40:19 swin_small_patch4_window7_224] INFO: Epoch: [154] [1130/1251] eta: 0:01:01 lr: 0.000480 loss: 3.4307 (3.2641) grad_norm: 1.4019 (1.4660) time: 0.5079 [2021-03-26 07:40:24 swin_small_patch4_window7_224] INFO: Epoch: [154] [1140/1251] eta: 0:00:56 lr: 0.000480 loss: 3.4307 (3.2655) grad_norm: 1.3730 (1.4652) time: 0.5049 [2021-03-26 07:40:29 swin_small_patch4_window7_224] INFO: Epoch: [154] [1150/1251] eta: 0:00:51 lr: 0.000480 loss: 3.3816 (3.2669) grad_norm: 1.4006 (1.4653) time: 0.4990 [2021-03-26 07:40:34 swin_small_patch4_window7_224] INFO: Epoch: [154] [1160/1251] eta: 0:00:46 lr: 0.000479 loss: 3.2789 (3.2672) grad_norm: 1.4243 (1.4646) time: 0.5018 [2021-03-26 07:40:39 swin_small_patch4_window7_224] INFO: Epoch: [154] [1170/1251] eta: 0:00:41 lr: 0.000479 loss: 3.4573 (3.2695) grad_norm: 1.4463 (1.4661) time: 0.5087 [2021-03-26 07:40:44 swin_small_patch4_window7_224] INFO: Epoch: [154] [1180/1251] eta: 0:00:36 lr: 0.000479 loss: 3.5490 (3.2691) grad_norm: 1.5306 (1.4663) time: 0.5097 [2021-03-26 07:40:49 swin_small_patch4_window7_224] INFO: Epoch: [154] [1190/1251] eta: 0:00:31 lr: 0.000479 loss: 3.2078 (3.2683) grad_norm: 1.4544 (1.4661) time: 0.5072 [2021-03-26 07:40:54 swin_small_patch4_window7_224] INFO: Epoch: [154] [1200/1251] eta: 0:00:25 lr: 0.000479 loss: 3.1554 (3.2683) grad_norm: 1.4899 (1.4670) time: 0.5039 [2021-03-26 07:40:59 swin_small_patch4_window7_224] INFO: Epoch: [154] [1210/1251] eta: 0:00:20 lr: 0.000479 loss: 3.0259 (3.2659) grad_norm: 1.4868 (1.4673) time: 0.5011 [2021-03-26 07:41:04 swin_small_patch4_window7_224] INFO: Epoch: [154] [1220/1251] eta: 0:00:15 lr: 0.000479 loss: 3.2675 (3.2654) grad_norm: 1.3995 (1.4668) time: 0.5027 [2021-03-26 07:41:10 swin_small_patch4_window7_224] INFO: Epoch: [154] [1230/1251] eta: 0:00:10 lr: 0.000479 loss: 3.3783 (3.2667) grad_norm: 1.3755 (1.4670) time: 0.5043 [2021-03-26 07:41:14 swin_small_patch4_window7_224] INFO: Epoch: [154] [1240/1251] eta: 0:00:05 lr: 0.000479 loss: 3.3590 (3.2682) grad_norm: 1.4852 (1.4670) time: 0.4997 [2021-03-26 07:41:19 swin_small_patch4_window7_224] INFO: Epoch: [154] [1250/1251] eta: 0:00:00 lr: 0.000479 loss: 3.4376 (3.2706) grad_norm: 1.4615 (1.4670) time: 0.4897 [2021-03-26 07:41:27 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 1.1008 (1.1008) acc1: 79.6875 (79.6875) acc5: 92.1875 (92.1875) [2021-03-26 07:41:31 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8951 (0.9793) acc1: 78.1250 (77.9830) acc5: 95.3125 (94.4602) [2021-03-26 07:41:33 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8512 (0.9573) acc1: 78.1250 (77.6786) acc5: 95.3125 (95.2381) [2021-03-26 07:41:35 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8314 (0.9247) acc1: 78.1250 (78.1754) acc5: 95.3125 (95.6149) [2021-03-26 07:41:37 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9098 (0.9363) acc1: 76.5625 (77.7439) acc5: 95.3125 (95.1601) [2021-03-26 07:41:38 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9098 (0.9290) acc1: 76.5625 (77.9520) acc5: 94.3396 (95.1360) [2021-03-26 07:41:46 swin_small_patch4_window7_224] INFO: * Acc@1 78.446 Acc@5 94.604 loss 0.929 [2021-03-26 07:41:46 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-26 07:41:46 swin_small_patch4_window7_224] INFO: Max accuracy: 78.56% [2021-03-26 07:41:50 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 0/1251] eta: 1:28:20 lr: 0.000479 loss: 3.6064 (3.6064) grad_norm: 1.3814 (1.3814) time: 4.2367 [2021-03-26 07:41:55 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 10/1251] eta: 0:17:33 lr: 0.000479 loss: 3.4038 (3.2977) grad_norm: 1.4706 (1.4889) time: 0.8488 [2021-03-26 07:42:00 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 20/1251] eta: 0:14:01 lr: 0.000479 loss: 3.4025 (3.3195) grad_norm: 1.4463 (1.4613) time: 0.5057 [2021-03-26 07:42:05 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 30/1251] eta: 0:12:46 lr: 0.000479 loss: 3.2941 (3.2992) grad_norm: 1.4197 (1.4422) time: 0.5058 [2021-03-26 07:42:10 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 40/1251] eta: 0:12:02 lr: 0.000479 loss: 3.3586 (3.3247) grad_norm: 1.4003 (1.4404) time: 0.5057 [2021-03-26 07:42:16 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 50/1251] eta: 0:11:36 lr: 0.000479 loss: 3.4542 (3.3306) grad_norm: 1.4003 (1.4353) time: 0.5068 [2021-03-26 07:42:21 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 60/1251] eta: 0:11:15 lr: 0.000479 loss: 3.3503 (3.3300) grad_norm: 1.4316 (1.4462) time: 0.5076 [2021-03-26 07:42:26 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 70/1251] eta: 0:11:02 lr: 0.000479 loss: 3.2166 (3.2907) grad_norm: 1.4316 (1.4550) time: 0.5128 [2021-03-26 07:42:31 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 80/1251] eta: 0:10:49 lr: 0.000479 loss: 3.0903 (3.2530) grad_norm: 1.4483 (1.4633) time: 0.5150 [2021-03-26 07:42:36 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 90/1251] eta: 0:10:37 lr: 0.000479 loss: 3.1341 (3.2562) grad_norm: 1.4816 (1.4599) time: 0.5057 [2021-03-26 07:42:41 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 100/1251] eta: 0:10:26 lr: 0.000479 loss: 3.3149 (3.2439) grad_norm: 1.4853 (1.4661) time: 0.5007 [2021-03-26 07:42:46 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 110/1251] eta: 0:10:16 lr: 0.000479 loss: 3.0898 (3.2450) grad_norm: 1.5069 (1.4675) time: 0.5020 [2021-03-26 07:42:51 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 120/1251] eta: 0:10:07 lr: 0.000479 loss: 3.1673 (3.2433) grad_norm: 1.4320 (1.4617) time: 0.5052 [2021-03-26 07:42:56 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 130/1251] eta: 0:10:00 lr: 0.000479 loss: 3.3850 (3.2503) grad_norm: 1.4139 (1.4579) time: 0.5060 [2021-03-26 07:43:01 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 140/1251] eta: 0:09:52 lr: 0.000479 loss: 3.3850 (3.2454) grad_norm: 1.3967 (1.4566) time: 0.5080 [2021-03-26 07:43:06 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 150/1251] eta: 0:09:44 lr: 0.000478 loss: 3.4543 (3.2659) grad_norm: 1.4356 (1.4600) time: 0.5033 [2021-03-26 07:43:11 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 160/1251] eta: 0:09:37 lr: 0.000478 loss: 3.5236 (3.2771) grad_norm: 1.4312 (1.4588) time: 0.5046 [2021-03-26 07:43:16 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 170/1251] eta: 0:09:31 lr: 0.000478 loss: 3.3383 (3.2861) grad_norm: 1.4022 (1.4587) time: 0.5117 [2021-03-26 07:43:22 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 180/1251] eta: 0:09:25 lr: 0.000478 loss: 3.3097 (3.2689) grad_norm: 1.4325 (1.4567) time: 0.5108 [2021-03-26 07:43:27 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 190/1251] eta: 0:09:18 lr: 0.000478 loss: 3.3152 (3.2776) grad_norm: 1.4320 (1.4573) time: 0.5088 [2021-03-26 07:43:32 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 200/1251] eta: 0:09:12 lr: 0.000478 loss: 3.3152 (3.2664) grad_norm: 1.5039 (1.4620) time: 0.5085 [2021-03-26 07:43:37 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 210/1251] eta: 0:09:05 lr: 0.000478 loss: 3.1010 (3.2523) grad_norm: 1.5156 (1.4651) time: 0.5026 [2021-03-26 07:43:42 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 220/1251] eta: 0:08:59 lr: 0.000478 loss: 3.1405 (3.2520) grad_norm: 1.4152 (1.4655) time: 0.4972 [2021-03-26 07:43:47 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 230/1251] eta: 0:08:53 lr: 0.000478 loss: 3.3456 (3.2540) grad_norm: 1.4974 (1.4730) time: 0.4992 [2021-03-26 07:43:52 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 240/1251] eta: 0:08:46 lr: 0.000478 loss: 3.2388 (3.2517) grad_norm: 1.5119 (1.4733) time: 0.4974 [2021-03-26 07:43:57 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 250/1251] eta: 0:08:41 lr: 0.000478 loss: 3.4379 (3.2555) grad_norm: 1.4928 (1.4751) time: 0.5012 [2021-03-26 07:44:02 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 260/1251] eta: 0:08:35 lr: 0.000478 loss: 3.4379 (3.2539) grad_norm: 1.4549 (1.4736) time: 0.5161 [2021-03-26 07:44:07 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 270/1251] eta: 0:08:30 lr: 0.000478 loss: 3.5086 (3.2618) grad_norm: 1.4235 (1.4710) time: 0.5172 [2021-03-26 07:44:12 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 280/1251] eta: 0:08:24 lr: 0.000478 loss: 3.3383 (3.2616) grad_norm: 1.4175 (1.4697) time: 0.5078 [2021-03-26 07:44:17 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 290/1251] eta: 0:08:18 lr: 0.000478 loss: 3.4416 (3.2720) grad_norm: 1.4084 (1.4677) time: 0.5047 [2021-03-26 07:44:22 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 300/1251] eta: 0:08:13 lr: 0.000478 loss: 3.5865 (3.2736) grad_norm: 1.3887 (1.4664) time: 0.5002 [2021-03-26 07:44:27 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 310/1251] eta: 0:08:07 lr: 0.000478 loss: 3.3374 (3.2743) grad_norm: 1.4486 (1.4662) time: 0.4946 [2021-03-26 07:44:32 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 320/1251] eta: 0:08:02 lr: 0.000478 loss: 3.2902 (3.2756) grad_norm: 1.4615 (1.4690) time: 0.5096 [2021-03-26 07:44:37 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 330/1251] eta: 0:07:56 lr: 0.000478 loss: 3.2974 (3.2740) grad_norm: 1.4737 (1.4700) time: 0.5093 [2021-03-26 07:44:42 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 340/1251] eta: 0:07:50 lr: 0.000478 loss: 3.2974 (3.2726) grad_norm: 1.4470 (1.4706) time: 0.4966 [2021-03-26 07:44:47 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 350/1251] eta: 0:07:45 lr: 0.000478 loss: 3.2515 (3.2758) grad_norm: 1.5369 (1.4751) time: 0.5099 [2021-03-26 07:44:52 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 360/1251] eta: 0:07:39 lr: 0.000478 loss: 3.2197 (3.2692) grad_norm: 1.5809 (1.4778) time: 0.5085 [2021-03-26 07:44:57 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 370/1251] eta: 0:07:34 lr: 0.000478 loss: 3.3001 (3.2722) grad_norm: 1.5484 (1.4776) time: 0.5012 [2021-03-26 07:45:03 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 380/1251] eta: 0:07:29 lr: 0.000478 loss: 3.3043 (3.2688) grad_norm: 1.5889 (1.4825) time: 0.5050 [2021-03-26 07:45:08 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 390/1251] eta: 0:07:23 lr: 0.000477 loss: 3.3043 (3.2719) grad_norm: 1.5907 (1.4833) time: 0.5012 [2021-03-26 07:45:13 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 400/1251] eta: 0:07:18 lr: 0.000477 loss: 3.2574 (3.2671) grad_norm: 1.5226 (1.4844) time: 0.4994 [2021-03-26 07:45:18 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 410/1251] eta: 0:07:12 lr: 0.000477 loss: 3.1212 (3.2688) grad_norm: 1.5806 (1.4874) time: 0.5029 [2021-03-26 07:45:23 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 420/1251] eta: 0:07:07 lr: 0.000477 loss: 3.3182 (3.2685) grad_norm: 1.5472 (1.4869) time: 0.5068 [2021-03-26 07:45:28 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 430/1251] eta: 0:07:01 lr: 0.000477 loss: 3.3104 (3.2681) grad_norm: 1.4277 (inf) time: 0.5026 [2021-03-26 07:45:33 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 440/1251] eta: 0:06:56 lr: 0.000477 loss: 3.3104 (3.2696) grad_norm: 1.5265 (inf) time: 0.4971 [2021-03-26 07:45:38 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 450/1251] eta: 0:06:51 lr: 0.000477 loss: 3.0365 (3.2620) grad_norm: 1.5247 (inf) time: 0.4997 [2021-03-26 07:45:43 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 460/1251] eta: 0:06:45 lr: 0.000477 loss: 3.0082 (3.2600) grad_norm: 1.4502 (inf) time: 0.5049 [2021-03-26 07:45:48 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 470/1251] eta: 0:06:40 lr: 0.000477 loss: 3.2145 (3.2666) grad_norm: 1.5168 (inf) time: 0.5095 [2021-03-26 07:45:53 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 480/1251] eta: 0:06:35 lr: 0.000477 loss: 3.2145 (3.2625) grad_norm: 1.5242 (inf) time: 0.5060 [2021-03-26 07:45:58 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 490/1251] eta: 0:06:30 lr: 0.000477 loss: 3.4387 (3.2691) grad_norm: 1.4970 (inf) time: 0.4981 [2021-03-26 07:46:03 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 500/1251] eta: 0:06:24 lr: 0.000477 loss: 3.4387 (3.2693) grad_norm: 1.4040 (inf) time: 0.4977 [2021-03-26 07:46:08 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 510/1251] eta: 0:06:19 lr: 0.000477 loss: 3.3384 (3.2699) grad_norm: 1.3832 (inf) time: 0.5069 [2021-03-26 07:46:13 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 520/1251] eta: 0:06:14 lr: 0.000477 loss: 3.3384 (3.2687) grad_norm: 1.3957 (inf) time: 0.5033 [2021-03-26 07:46:18 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 530/1251] eta: 0:06:08 lr: 0.000477 loss: 3.1957 (3.2607) grad_norm: 1.3941 (inf) time: 0.4948 [2021-03-26 07:46:23 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 540/1251] eta: 0:06:03 lr: 0.000477 loss: 3.3157 (3.2641) grad_norm: 1.3797 (inf) time: 0.4980 [2021-03-26 07:46:28 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 550/1251] eta: 0:05:58 lr: 0.000477 loss: 3.3157 (3.2611) grad_norm: 1.4289 (inf) time: 0.5147 [2021-03-26 07:46:33 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 560/1251] eta: 0:05:53 lr: 0.000477 loss: 3.0887 (3.2609) grad_norm: 1.4751 (inf) time: 0.5124 [2021-03-26 07:46:38 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 570/1251] eta: 0:05:48 lr: 0.000477 loss: 3.2728 (3.2578) grad_norm: 1.5237 (inf) time: 0.5042 [2021-03-26 07:46:43 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 580/1251] eta: 0:05:43 lr: 0.000477 loss: 3.3738 (3.2611) grad_norm: 1.4591 (inf) time: 0.5090 [2021-03-26 07:46:48 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 590/1251] eta: 0:05:37 lr: 0.000477 loss: 3.5892 (3.2641) grad_norm: 1.4754 (inf) time: 0.5051 [2021-03-26 07:46:53 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 600/1251] eta: 0:05:32 lr: 0.000477 loss: 3.4662 (3.2667) grad_norm: 1.4754 (inf) time: 0.5037 [2021-03-26 07:46:58 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 610/1251] eta: 0:05:27 lr: 0.000477 loss: 3.4850 (3.2702) grad_norm: 1.4181 (inf) time: 0.5082 [2021-03-26 07:47:04 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 620/1251] eta: 0:05:22 lr: 0.000477 loss: 3.4320 (3.2678) grad_norm: 1.3979 (inf) time: 0.5142 [2021-03-26 07:47:09 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 630/1251] eta: 0:05:17 lr: 0.000476 loss: 2.9969 (3.2664) grad_norm: 1.4406 (inf) time: 0.5085 [2021-03-26 07:47:14 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 640/1251] eta: 0:05:12 lr: 0.000476 loss: 3.3862 (3.2676) grad_norm: 1.4944 (inf) time: 0.5078 [2021-03-26 07:47:19 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 650/1251] eta: 0:05:07 lr: 0.000476 loss: 3.3817 (3.2657) grad_norm: 1.4611 (inf) time: 0.5050 [2021-03-26 07:47:24 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 660/1251] eta: 0:05:01 lr: 0.000476 loss: 3.3817 (3.2650) grad_norm: 1.4611 (inf) time: 0.5019 [2021-03-26 07:47:29 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 670/1251] eta: 0:04:56 lr: 0.000476 loss: 3.4456 (3.2661) grad_norm: 1.4528 (inf) time: 0.5015 [2021-03-26 07:47:34 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 680/1251] eta: 0:04:51 lr: 0.000476 loss: 3.4606 (3.2700) grad_norm: 1.4147 (inf) time: 0.4995 [2021-03-26 07:47:39 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 690/1251] eta: 0:04:46 lr: 0.000476 loss: 3.4928 (3.2715) grad_norm: 1.4322 (inf) time: 0.5046 [2021-03-26 07:47:44 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 700/1251] eta: 0:04:41 lr: 0.000476 loss: 3.6282 (3.2748) grad_norm: 1.4603 (inf) time: 0.5012 [2021-03-26 07:47:49 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 710/1251] eta: 0:04:36 lr: 0.000476 loss: 3.3781 (3.2752) grad_norm: 1.4632 (inf) time: 0.5044 [2021-03-26 07:47:54 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 720/1251] eta: 0:04:30 lr: 0.000476 loss: 3.4445 (3.2776) grad_norm: 1.4089 (inf) time: 0.5108 [2021-03-26 07:47:59 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 730/1251] eta: 0:04:25 lr: 0.000476 loss: 3.6434 (3.2814) grad_norm: 1.3984 (inf) time: 0.5144 [2021-03-26 07:48:04 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 740/1251] eta: 0:04:20 lr: 0.000476 loss: 3.5519 (3.2820) grad_norm: 1.4955 (inf) time: 0.5219 [2021-03-26 07:48:09 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 750/1251] eta: 0:04:15 lr: 0.000476 loss: 3.3768 (3.2813) grad_norm: 1.4955 (inf) time: 0.5101 [2021-03-26 07:48:15 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 760/1251] eta: 0:04:10 lr: 0.000476 loss: 3.3697 (3.2833) grad_norm: 1.4037 (inf) time: 0.5032 [2021-03-26 07:48:20 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 770/1251] eta: 0:04:05 lr: 0.000476 loss: 3.3193 (3.2797) grad_norm: 1.4922 (inf) time: 0.5085 [2021-03-26 07:48:25 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 780/1251] eta: 0:04:00 lr: 0.000476 loss: 3.3193 (3.2796) grad_norm: 1.5094 (inf) time: 0.5066 [2021-03-26 07:48:30 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 790/1251] eta: 0:03:55 lr: 0.000476 loss: 3.3982 (3.2802) grad_norm: 1.4189 (inf) time: 0.5041 [2021-03-26 07:48:35 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 800/1251] eta: 0:03:50 lr: 0.000476 loss: 3.3899 (3.2822) grad_norm: 1.4006 (inf) time: 0.5083 [2021-03-26 07:48:40 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 810/1251] eta: 0:03:45 lr: 0.000476 loss: 3.4541 (3.2821) grad_norm: 1.4044 (inf) time: 0.5129 [2021-03-26 07:48:45 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 820/1251] eta: 0:03:39 lr: 0.000476 loss: 3.5182 (3.2836) grad_norm: 1.3835 (inf) time: 0.5079 [2021-03-26 07:48:50 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 830/1251] eta: 0:03:34 lr: 0.000476 loss: 3.5267 (3.2868) grad_norm: 1.4568 (inf) time: 0.5080 [2021-03-26 07:48:55 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 840/1251] eta: 0:03:29 lr: 0.000476 loss: 3.6028 (3.2878) grad_norm: 1.4922 (inf) time: 0.5088 [2021-03-26 07:49:00 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 850/1251] eta: 0:03:24 lr: 0.000476 loss: 3.5573 (3.2878) grad_norm: 1.4480 (inf) time: 0.5066 [2021-03-26 07:49:05 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 860/1251] eta: 0:03:19 lr: 0.000476 loss: 3.4255 (3.2872) grad_norm: 1.4452 (inf) time: 0.5080 [2021-03-26 07:49:11 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 870/1251] eta: 0:03:14 lr: 0.000475 loss: 3.4077 (3.2869) grad_norm: 1.4452 (inf) time: 0.5119 [2021-03-26 07:49:16 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 880/1251] eta: 0:03:09 lr: 0.000475 loss: 3.4077 (3.2883) grad_norm: 1.4714 (inf) time: 0.5124 [2021-03-26 07:49:21 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 890/1251] eta: 0:03:04 lr: 0.000475 loss: 3.4919 (3.2899) grad_norm: 1.5187 (inf) time: 0.5046 [2021-03-26 07:49:26 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 900/1251] eta: 0:02:58 lr: 0.000475 loss: 3.5743 (3.2904) grad_norm: 1.4350 (inf) time: 0.4980 [2021-03-26 07:49:31 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 910/1251] eta: 0:02:53 lr: 0.000475 loss: 3.3624 (3.2886) grad_norm: 1.4165 (inf) time: 0.5049 [2021-03-26 07:49:36 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 920/1251] eta: 0:02:48 lr: 0.000475 loss: 3.0457 (3.2866) grad_norm: 1.3917 (inf) time: 0.5114 [2021-03-26 07:49:41 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 930/1251] eta: 0:02:43 lr: 0.000475 loss: 3.1459 (3.2864) grad_norm: 1.3907 (inf) time: 0.5128 [2021-03-26 07:49:46 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 940/1251] eta: 0:02:38 lr: 0.000475 loss: 3.3369 (3.2872) grad_norm: 1.4409 (inf) time: 0.5079 [2021-03-26 07:49:51 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 950/1251] eta: 0:02:33 lr: 0.000475 loss: 3.3168 (3.2872) grad_norm: 1.5993 (inf) time: 0.5022 [2021-03-26 07:49:56 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 960/1251] eta: 0:02:28 lr: 0.000475 loss: 3.3168 (3.2884) grad_norm: 1.5900 (inf) time: 0.5065 [2021-03-26 07:50:01 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 970/1251] eta: 0:02:23 lr: 0.000475 loss: 3.3232 (3.2857) grad_norm: 1.3893 (inf) time: 0.5084 [2021-03-26 07:50:06 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 980/1251] eta: 0:02:18 lr: 0.000475 loss: 3.3687 (3.2864) grad_norm: 1.4538 (inf) time: 0.5058 [2021-03-26 07:50:11 swin_small_patch4_window7_224] INFO: Epoch: [155] [ 990/1251] eta: 0:02:13 lr: 0.000475 loss: 3.5658 (3.2878) grad_norm: 1.5768 (inf) time: 0.5030 [2021-03-26 07:50:16 swin_small_patch4_window7_224] INFO: Epoch: [155] [1000/1251] eta: 0:02:07 lr: 0.000475 loss: 3.6325 (3.2906) grad_norm: 1.5282 (inf) time: 0.5064 [2021-03-26 07:50:21 swin_small_patch4_window7_224] INFO: Epoch: [155] [1010/1251] eta: 0:02:02 lr: 0.000475 loss: 3.6077 (3.2901) grad_norm: 1.4547 (inf) time: 0.5083 [2021-03-26 07:50:27 swin_small_patch4_window7_224] INFO: Epoch: [155] [1020/1251] eta: 0:01:57 lr: 0.000475 loss: 3.2809 (3.2909) grad_norm: 1.4657 (inf) time: 0.5087 [2021-03-26 07:50:32 swin_small_patch4_window7_224] INFO: Epoch: [155] [1030/1251] eta: 0:01:52 lr: 0.000475 loss: 3.4631 (3.2944) grad_norm: 1.5289 (inf) time: 0.5037 [2021-03-26 07:50:37 swin_small_patch4_window7_224] INFO: Epoch: [155] [1040/1251] eta: 0:01:47 lr: 0.000475 loss: 3.6263 (3.2962) grad_norm: 1.5509 (inf) time: 0.4988 [2021-03-26 07:50:42 swin_small_patch4_window7_224] INFO: Epoch: [155] [1050/1251] eta: 0:01:42 lr: 0.000475 loss: 3.3165 (3.2959) grad_norm: 1.4867 (inf) time: 0.4995 [2021-03-26 07:50:47 swin_small_patch4_window7_224] INFO: Epoch: [155] [1060/1251] eta: 0:01:37 lr: 0.000475 loss: 3.2348 (3.2948) grad_norm: 1.4388 (inf) time: 0.5020 [2021-03-26 07:50:52 swin_small_patch4_window7_224] INFO: Epoch: [155] [1070/1251] eta: 0:01:32 lr: 0.000475 loss: 3.3146 (3.2957) grad_norm: 1.5291 (inf) time: 0.5024 [2021-03-26 07:50:57 swin_small_patch4_window7_224] INFO: Epoch: [155] [1080/1251] eta: 0:01:27 lr: 0.000475 loss: 3.3474 (3.2947) grad_norm: 1.5164 (inf) time: 0.5010 [2021-03-26 07:51:02 swin_small_patch4_window7_224] INFO: Epoch: [155] [1090/1251] eta: 0:01:21 lr: 0.000475 loss: 3.4747 (3.2951) grad_norm: 1.4773 (inf) time: 0.5089 [2021-03-26 07:51:07 swin_small_patch4_window7_224] INFO: Epoch: [155] [1100/1251] eta: 0:01:16 lr: 0.000475 loss: 3.2397 (3.2931) grad_norm: 1.4161 (inf) time: 0.5071 [2021-03-26 07:51:12 swin_small_patch4_window7_224] INFO: Epoch: [155] [1110/1251] eta: 0:01:11 lr: 0.000475 loss: 3.2632 (3.2924) grad_norm: 1.5188 (inf) time: 0.5016 [2021-03-26 07:51:17 swin_small_patch4_window7_224] INFO: Epoch: [155] [1120/1251] eta: 0:01:06 lr: 0.000474 loss: 3.3067 (3.2903) grad_norm: 1.5899 (inf) time: 0.5063 [2021-03-26 07:51:22 swin_small_patch4_window7_224] INFO: Epoch: [155] [1130/1251] eta: 0:01:01 lr: 0.000474 loss: 3.1116 (3.2896) grad_norm: 1.5534 (inf) time: 0.5073 [2021-03-26 07:51:27 swin_small_patch4_window7_224] INFO: Epoch: [155] [1140/1251] eta: 0:00:56 lr: 0.000474 loss: 3.4079 (3.2917) grad_norm: 1.5004 (inf) time: 0.5062 [2021-03-26 07:51:32 swin_small_patch4_window7_224] INFO: Epoch: [155] [1150/1251] eta: 0:00:51 lr: 0.000474 loss: 3.3038 (3.2901) grad_norm: 1.4254 (inf) time: 0.5056 [2021-03-26 07:51:37 swin_small_patch4_window7_224] INFO: Epoch: [155] [1160/1251] eta: 0:00:46 lr: 0.000474 loss: 3.3038 (3.2915) grad_norm: 1.4185 (inf) time: 0.4999 [2021-03-26 07:51:42 swin_small_patch4_window7_224] INFO: Epoch: [155] [1170/1251] eta: 0:00:41 lr: 0.000474 loss: 3.3383 (3.2902) grad_norm: 1.4624 (inf) time: 0.5033 [2021-03-26 07:51:47 swin_small_patch4_window7_224] INFO: Epoch: [155] [1180/1251] eta: 0:00:36 lr: 0.000474 loss: 3.2984 (3.2895) grad_norm: 1.4624 (inf) time: 0.5066 [2021-03-26 07:51:52 swin_small_patch4_window7_224] INFO: Epoch: [155] [1190/1251] eta: 0:00:31 lr: 0.000474 loss: 3.4319 (3.2922) grad_norm: 1.4212 (inf) time: 0.5005 [2021-03-26 07:51:57 swin_small_patch4_window7_224] INFO: Epoch: [155] [1200/1251] eta: 0:00:25 lr: 0.000474 loss: 3.3905 (3.2919) grad_norm: 1.4473 (inf) time: 0.5029 [2021-03-26 07:52:02 swin_small_patch4_window7_224] INFO: Epoch: [155] [1210/1251] eta: 0:00:20 lr: 0.000474 loss: 3.1288 (3.2897) grad_norm: 1.4737 (inf) time: 0.5044 [2021-03-26 07:52:07 swin_small_patch4_window7_224] INFO: Epoch: [155] [1220/1251] eta: 0:00:15 lr: 0.000474 loss: 2.8064 (3.2871) grad_norm: 1.4555 (inf) time: 0.5023 [2021-03-26 07:52:12 swin_small_patch4_window7_224] INFO: Epoch: [155] [1230/1251] eta: 0:00:10 lr: 0.000474 loss: 3.0355 (3.2865) grad_norm: 1.4954 (inf) time: 0.4970 [2021-03-26 07:52:17 swin_small_patch4_window7_224] INFO: Epoch: [155] [1240/1251] eta: 0:00:05 lr: 0.000474 loss: 3.2695 (3.2859) grad_norm: 1.5405 (inf) time: 0.4944 [2021-03-26 07:52:22 swin_small_patch4_window7_224] INFO: Epoch: [155] [1250/1251] eta: 0:00:00 lr: 0.000474 loss: 3.3840 (3.2867) grad_norm: 1.4519 (inf) time: 0.5029 [2021-03-26 07:53:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 1.1135 (1.1135) acc1: 67.1875 (67.1875) acc5: 96.8750 (96.8750) [2021-03-26 07:53:08 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.9808 (0.9607) acc1: 75.0000 (75.2841) acc5: 95.3125 (95.0284) [2021-03-26 07:53:09 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9571 (0.9639) acc1: 76.5625 (76.4881) acc5: 93.7500 (94.6429) [2021-03-26 07:53:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9418 (0.9361) acc1: 78.1250 (77.2177) acc5: 95.3125 (94.9597) [2021-03-26 07:53:11 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8208 (0.9172) acc1: 78.1250 (77.1341) acc5: 95.3125 (95.0457) [2021-03-26 07:53:12 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8208 (0.9024) acc1: 76.5625 (77.2480) acc5: 95.3125 (95.2320) [2021-03-26 07:53:18 swin_small_patch4_window7_224] INFO: * Acc@1 78.448 Acc@5 94.678 loss 0.898 [2021-03-26 07:53:18 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.4% [2021-03-26 07:53:18 swin_small_patch4_window7_224] INFO: Max accuracy: 78.56% [2021-03-26 07:53:22 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 0/1251] eta: 1:33:20 lr: 0.000474 loss: 3.5061 (3.5061) grad_norm: 1.9299 (1.9299) time: 4.4765 [2021-03-26 07:53:28 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 10/1251] eta: 0:18:10 lr: 0.000474 loss: 3.5198 (3.4936) grad_norm: 1.3755 (1.4595) time: 0.8785 [2021-03-26 07:53:33 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 20/1251] eta: 0:14:17 lr: 0.000474 loss: 3.4838 (3.4060) grad_norm: 1.4411 (1.4653) time: 0.5072 [2021-03-26 07:53:38 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 30/1251] eta: 0:12:53 lr: 0.000474 loss: 3.3409 (3.4018) grad_norm: 1.4770 (1.4808) time: 0.4987 [2021-03-26 07:53:43 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 40/1251] eta: 0:12:10 lr: 0.000474 loss: 3.4610 (3.4067) grad_norm: 1.4658 (1.4870) time: 0.5051 [2021-03-26 07:53:48 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 50/1251] eta: 0:11:39 lr: 0.000474 loss: 3.4550 (3.3730) grad_norm: 1.4490 (1.4854) time: 0.5043 [2021-03-26 07:53:53 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 60/1251] eta: 0:11:19 lr: 0.000474 loss: 3.2778 (3.3164) grad_norm: 1.4502 (1.4839) time: 0.5042 [2021-03-26 07:53:58 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 70/1251] eta: 0:11:01 lr: 0.000474 loss: 3.3048 (3.3150) grad_norm: 1.4702 (1.4798) time: 0.5037 [2021-03-26 07:54:03 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 80/1251] eta: 0:10:47 lr: 0.000474 loss: 3.1840 (3.2776) grad_norm: 1.4702 (1.4759) time: 0.4991 [2021-03-26 07:54:08 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 90/1251] eta: 0:10:37 lr: 0.000474 loss: 3.4596 (3.3105) grad_norm: 1.4634 (1.4699) time: 0.5080 [2021-03-26 07:54:13 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 100/1251] eta: 0:10:26 lr: 0.000474 loss: 3.5015 (3.3350) grad_norm: 1.4634 (1.4753) time: 0.5094 [2021-03-26 07:54:18 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 110/1251] eta: 0:10:18 lr: 0.000473 loss: 3.7495 (3.3644) grad_norm: 1.5478 (1.4865) time: 0.5083 [2021-03-26 07:54:23 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 120/1251] eta: 0:10:09 lr: 0.000473 loss: 3.5843 (3.3467) grad_norm: 1.5375 (1.4870) time: 0.5106 [2021-03-26 07:54:28 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 130/1251] eta: 0:10:00 lr: 0.000473 loss: 3.3242 (3.3344) grad_norm: 1.4568 (1.4815) time: 0.5054 [2021-03-26 07:54:33 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 140/1251] eta: 0:09:53 lr: 0.000473 loss: 3.3242 (3.3305) grad_norm: 1.4205 (1.4793) time: 0.5043 [2021-03-26 07:54:38 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 150/1251] eta: 0:09:46 lr: 0.000473 loss: 3.1600 (3.3242) grad_norm: 1.4153 (1.4734) time: 0.5089 [2021-03-26 07:54:43 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 160/1251] eta: 0:09:39 lr: 0.000473 loss: 3.2424 (3.3156) grad_norm: 1.4153 (1.4779) time: 0.5095 [2021-03-26 07:54:48 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 170/1251] eta: 0:09:32 lr: 0.000473 loss: 3.1244 (3.3041) grad_norm: 1.4516 (1.4775) time: 0.5042 [2021-03-26 07:54:54 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 180/1251] eta: 0:09:25 lr: 0.000473 loss: 3.4557 (3.3153) grad_norm: 1.4270 (1.4741) time: 0.5073 [2021-03-26 07:54:59 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 190/1251] eta: 0:09:19 lr: 0.000473 loss: 3.3583 (3.3029) grad_norm: 1.3906 (1.4723) time: 0.5150 [2021-03-26 07:55:04 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 200/1251] eta: 0:09:13 lr: 0.000473 loss: 3.0338 (3.2910) grad_norm: 1.4582 (1.4749) time: 0.5090 [2021-03-26 07:55:09 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 210/1251] eta: 0:09:06 lr: 0.000473 loss: 3.2850 (3.2929) grad_norm: 1.4582 (1.4782) time: 0.5009 [2021-03-26 07:55:14 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 220/1251] eta: 0:09:00 lr: 0.000473 loss: 3.3071 (3.2900) grad_norm: 1.4458 (1.4764) time: 0.4987 [2021-03-26 07:55:19 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 230/1251] eta: 0:08:54 lr: 0.000473 loss: 3.0290 (3.2759) grad_norm: 1.4310 (1.4778) time: 0.5040 [2021-03-26 07:55:24 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 240/1251] eta: 0:08:48 lr: 0.000473 loss: 3.0481 (3.2783) grad_norm: 1.4829 (1.4815) time: 0.5091 [2021-03-26 07:55:29 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 250/1251] eta: 0:08:42 lr: 0.000473 loss: 3.2189 (3.2659) grad_norm: 1.4277 (1.4790) time: 0.5012 [2021-03-26 07:55:34 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 260/1251] eta: 0:08:36 lr: 0.000473 loss: 3.1417 (3.2599) grad_norm: 1.4634 (1.4820) time: 0.5023 [2021-03-26 07:55:39 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 270/1251] eta: 0:08:30 lr: 0.000473 loss: 3.2283 (3.2703) grad_norm: 1.5234 (1.4880) time: 0.5093 [2021-03-26 07:55:44 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 280/1251] eta: 0:08:24 lr: 0.000473 loss: 3.5986 (3.2697) grad_norm: 1.5023 (1.4877) time: 0.5073 [2021-03-26 07:55:49 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 290/1251] eta: 0:08:19 lr: 0.000473 loss: 3.3370 (3.2642) grad_norm: 1.5016 (1.4893) time: 0.5101 [2021-03-26 07:55:54 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 300/1251] eta: 0:08:13 lr: 0.000473 loss: 3.5147 (3.2730) grad_norm: 1.4972 (1.4882) time: 0.5075 [2021-03-26 07:55:59 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 310/1251] eta: 0:08:08 lr: 0.000473 loss: 3.4894 (3.2726) grad_norm: 1.4912 (1.4899) time: 0.5082 [2021-03-26 07:56:05 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 320/1251] eta: 0:08:03 lr: 0.000473 loss: 3.4113 (3.2788) grad_norm: 1.5116 (1.4900) time: 0.5123 [2021-03-26 07:56:10 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 330/1251] eta: 0:07:57 lr: 0.000473 loss: 3.3430 (3.2775) grad_norm: 1.4627 (1.4892) time: 0.5058 [2021-03-26 07:56:15 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 340/1251] eta: 0:07:52 lr: 0.000473 loss: 3.3755 (3.2778) grad_norm: 1.4828 (1.4900) time: 0.5076 [2021-03-26 07:56:20 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 350/1251] eta: 0:07:46 lr: 0.000472 loss: 3.2589 (3.2686) grad_norm: 1.4828 (1.4882) time: 0.5113 [2021-03-26 07:56:25 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 360/1251] eta: 0:07:41 lr: 0.000472 loss: 3.1552 (3.2687) grad_norm: 1.4544 (1.4880) time: 0.5092 [2021-03-26 07:56:30 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 370/1251] eta: 0:07:35 lr: 0.000472 loss: 3.2740 (3.2709) grad_norm: 1.4598 (1.4894) time: 0.5061 [2021-03-26 07:56:35 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 380/1251] eta: 0:07:30 lr: 0.000472 loss: 3.3110 (3.2721) grad_norm: 1.4803 (1.4910) time: 0.5048 [2021-03-26 07:56:40 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 390/1251] eta: 0:07:25 lr: 0.000472 loss: 3.1512 (3.2658) grad_norm: 1.5509 (1.4933) time: 0.5110 [2021-03-26 07:56:45 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 400/1251] eta: 0:07:19 lr: 0.000472 loss: 3.2669 (3.2685) grad_norm: 1.5554 (1.4962) time: 0.5053 [2021-03-26 07:56:50 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 410/1251] eta: 0:07:14 lr: 0.000472 loss: 3.5313 (3.2720) grad_norm: 1.5554 (1.4952) time: 0.4982 [2021-03-26 07:56:55 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 420/1251] eta: 0:07:08 lr: 0.000472 loss: 3.4617 (3.2776) grad_norm: 1.5120 (1.4958) time: 0.5019 [2021-03-26 07:57:00 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 430/1251] eta: 0:07:03 lr: 0.000472 loss: 3.4617 (3.2805) grad_norm: 1.5120 (1.4958) time: 0.4979 [2021-03-26 07:57:05 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 440/1251] eta: 0:06:57 lr: 0.000472 loss: 3.5035 (3.2847) grad_norm: 1.4681 (1.4966) time: 0.5019 [2021-03-26 07:57:10 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 450/1251] eta: 0:06:52 lr: 0.000472 loss: 3.5633 (3.2899) grad_norm: 1.4616 (1.4966) time: 0.5074 [2021-03-26 07:57:15 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 460/1251] eta: 0:06:46 lr: 0.000472 loss: 3.5373 (3.2870) grad_norm: 1.4576 (1.4961) time: 0.5014 [2021-03-26 07:57:20 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 470/1251] eta: 0:06:41 lr: 0.000472 loss: 3.3463 (3.2860) grad_norm: 1.5435 (1.4974) time: 0.5008 [2021-03-26 07:57:25 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 480/1251] eta: 0:06:36 lr: 0.000472 loss: 3.1558 (3.2839) grad_norm: 1.5396 (1.4976) time: 0.5014 [2021-03-26 07:57:30 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 490/1251] eta: 0:06:30 lr: 0.000472 loss: 3.0791 (3.2808) grad_norm: 1.4719 (1.4969) time: 0.4969 [2021-03-26 07:57:35 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 500/1251] eta: 0:06:25 lr: 0.000472 loss: 3.1563 (3.2745) grad_norm: 1.4841 (1.4976) time: 0.5032 [2021-03-26 07:57:40 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 510/1251] eta: 0:06:20 lr: 0.000472 loss: 3.0609 (3.2716) grad_norm: 1.4771 (1.4969) time: 0.5074 [2021-03-26 07:57:45 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 520/1251] eta: 0:06:15 lr: 0.000472 loss: 3.0738 (3.2731) grad_norm: 1.4574 (1.4964) time: 0.5023 [2021-03-26 07:57:50 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 530/1251] eta: 0:06:09 lr: 0.000472 loss: 3.1795 (3.2712) grad_norm: 1.3781 (1.4944) time: 0.5041 [2021-03-26 07:57:56 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 540/1251] eta: 0:06:04 lr: 0.000472 loss: 3.2703 (3.2699) grad_norm: 1.3781 (1.4925) time: 0.5079 [2021-03-26 07:58:01 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 550/1251] eta: 0:05:59 lr: 0.000472 loss: 3.3040 (3.2720) grad_norm: 1.4144 (1.4927) time: 0.5136 [2021-03-26 07:58:06 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 560/1251] eta: 0:05:54 lr: 0.000472 loss: 3.3152 (3.2694) grad_norm: 1.4518 (1.4924) time: 0.5165 [2021-03-26 07:58:11 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 570/1251] eta: 0:05:49 lr: 0.000472 loss: 3.3152 (3.2680) grad_norm: 1.4200 (1.4922) time: 0.5060 [2021-03-26 07:58:16 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 580/1251] eta: 0:05:43 lr: 0.000472 loss: 3.4348 (3.2702) grad_norm: 1.3948 (1.4914) time: 0.4976 [2021-03-26 07:58:21 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 590/1251] eta: 0:05:38 lr: 0.000471 loss: 3.4804 (3.2720) grad_norm: 1.4836 (1.4925) time: 0.5027 [2021-03-26 07:58:26 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 600/1251] eta: 0:05:33 lr: 0.000471 loss: 3.3299 (3.2722) grad_norm: 1.4271 (1.4908) time: 0.5102 [2021-03-26 07:58:31 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 610/1251] eta: 0:05:28 lr: 0.000471 loss: 3.2134 (3.2718) grad_norm: 1.4084 (1.4898) time: 0.5061 [2021-03-26 07:58:36 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 620/1251] eta: 0:05:23 lr: 0.000471 loss: 3.2860 (3.2708) grad_norm: 1.4084 (1.4885) time: 0.5034 [2021-03-26 07:58:41 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 630/1251] eta: 0:05:17 lr: 0.000471 loss: 3.3266 (3.2702) grad_norm: 1.4804 (1.4895) time: 0.5048 [2021-03-26 07:58:46 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 640/1251] eta: 0:05:12 lr: 0.000471 loss: 3.0906 (3.2645) grad_norm: 1.4804 (1.4898) time: 0.5023 [2021-03-26 07:58:51 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 650/1251] eta: 0:05:07 lr: 0.000471 loss: 3.2616 (3.2675) grad_norm: 1.4486 (1.4892) time: 0.5079 [2021-03-26 07:58:56 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 660/1251] eta: 0:05:02 lr: 0.000471 loss: 3.1895 (3.2651) grad_norm: 1.4630 (1.4891) time: 0.5084 [2021-03-26 07:59:01 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 670/1251] eta: 0:04:57 lr: 0.000471 loss: 3.1810 (3.2665) grad_norm: 1.4630 (1.4887) time: 0.5047 [2021-03-26 07:59:06 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 680/1251] eta: 0:04:52 lr: 0.000471 loss: 3.3128 (3.2659) grad_norm: 1.4777 (1.4894) time: 0.5074 [2021-03-26 07:59:11 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 690/1251] eta: 0:04:46 lr: 0.000471 loss: 3.3144 (3.2705) grad_norm: 1.4042 (1.4872) time: 0.5048 [2021-03-26 07:59:16 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 700/1251] eta: 0:04:41 lr: 0.000471 loss: 3.2148 (3.2692) grad_norm: 1.3492 (1.4864) time: 0.4986 [2021-03-26 07:59:21 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 710/1251] eta: 0:04:36 lr: 0.000471 loss: 3.2148 (3.2702) grad_norm: 1.4186 (1.4871) time: 0.5005 [2021-03-26 07:59:26 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 720/1251] eta: 0:04:31 lr: 0.000471 loss: 3.2490 (3.2689) grad_norm: 1.5237 (1.4881) time: 0.5020 [2021-03-26 07:59:31 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 730/1251] eta: 0:04:26 lr: 0.000471 loss: 3.2391 (3.2703) grad_norm: 1.4796 (1.4875) time: 0.5001 [2021-03-26 07:59:37 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 740/1251] eta: 0:04:21 lr: 0.000471 loss: 3.4180 (3.2708) grad_norm: 1.4381 (1.4873) time: 0.5188 [2021-03-26 07:59:42 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 750/1251] eta: 0:04:16 lr: 0.000471 loss: 3.4513 (3.2743) grad_norm: 1.4448 (1.4871) time: 0.5358 [2021-03-26 07:59:47 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 760/1251] eta: 0:04:11 lr: 0.000471 loss: 3.6396 (3.2776) grad_norm: 1.4513 (1.4877) time: 0.5294 [2021-03-26 07:59:52 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 770/1251] eta: 0:04:06 lr: 0.000471 loss: 3.1476 (3.2735) grad_norm: 1.4898 (1.4881) time: 0.5141 [2021-03-26 07:59:58 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 780/1251] eta: 0:04:00 lr: 0.000471 loss: 2.9592 (3.2729) grad_norm: 1.4898 (1.4882) time: 0.5053 [2021-03-26 08:00:03 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 790/1251] eta: 0:03:55 lr: 0.000471 loss: 3.3389 (3.2728) grad_norm: 1.4885 (1.4881) time: 0.5056 [2021-03-26 08:00:08 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 800/1251] eta: 0:03:50 lr: 0.000471 loss: 3.3389 (3.2722) grad_norm: 1.4534 (1.4869) time: 0.5067 [2021-03-26 08:00:13 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 810/1251] eta: 0:03:45 lr: 0.000471 loss: 3.2916 (3.2724) grad_norm: 1.4004 (1.4859) time: 0.5057 [2021-03-26 08:00:18 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 820/1251] eta: 0:03:40 lr: 0.000471 loss: 3.1739 (3.2717) grad_norm: 1.4498 (1.4864) time: 0.5026 [2021-03-26 08:00:23 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 830/1251] eta: 0:03:35 lr: 0.000470 loss: 3.3993 (3.2737) grad_norm: 1.5431 (1.4869) time: 0.5022 [2021-03-26 08:00:28 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 840/1251] eta: 0:03:30 lr: 0.000470 loss: 3.3993 (3.2749) grad_norm: 1.5254 (1.4874) time: 0.5088 [2021-03-26 08:00:33 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 850/1251] eta: 0:03:24 lr: 0.000470 loss: 3.4699 (3.2786) grad_norm: 1.4557 (1.4873) time: 0.5071 [2021-03-26 08:00:38 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 860/1251] eta: 0:03:19 lr: 0.000470 loss: 3.6675 (3.2823) grad_norm: 1.4714 (1.4881) time: 0.5041 [2021-03-26 08:00:43 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 870/1251] eta: 0:03:14 lr: 0.000470 loss: 3.5547 (3.2823) grad_norm: 1.4904 (1.4889) time: 0.5098 [2021-03-26 08:00:48 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 880/1251] eta: 0:03:09 lr: 0.000470 loss: 3.3016 (3.2826) grad_norm: 1.4726 (1.4887) time: 0.5121 [2021-03-26 08:00:53 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 890/1251] eta: 0:03:04 lr: 0.000470 loss: 3.3016 (3.2821) grad_norm: 1.4479 (1.4888) time: 0.5081 [2021-03-26 08:00:58 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 900/1251] eta: 0:02:59 lr: 0.000470 loss: 3.3357 (3.2828) grad_norm: 1.3816 (1.4883) time: 0.5077 [2021-03-26 08:01:03 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 910/1251] eta: 0:02:54 lr: 0.000470 loss: 3.4844 (3.2859) grad_norm: 1.4653 (1.4902) time: 0.5031 [2021-03-26 08:01:08 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 920/1251] eta: 0:02:49 lr: 0.000470 loss: 3.6544 (3.2889) grad_norm: 1.5363 (1.4905) time: 0.4964 [2021-03-26 08:01:13 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 930/1251] eta: 0:02:43 lr: 0.000470 loss: 3.6172 (3.2903) grad_norm: 1.5245 (1.4911) time: 0.5050 [2021-03-26 08:01:19 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 940/1251] eta: 0:02:38 lr: 0.000470 loss: 3.3974 (3.2891) grad_norm: 1.4732 (1.4909) time: 0.5146 [2021-03-26 08:01:24 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 950/1251] eta: 0:02:33 lr: 0.000470 loss: 3.1679 (3.2881) grad_norm: 1.4570 (1.4908) time: 0.5141 [2021-03-26 08:01:29 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 960/1251] eta: 0:02:28 lr: 0.000470 loss: 3.3772 (3.2877) grad_norm: 1.5201 (1.4911) time: 0.5027 [2021-03-26 08:01:34 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 970/1251] eta: 0:02:23 lr: 0.000470 loss: 3.3348 (3.2868) grad_norm: 1.5209 (1.4916) time: 0.4982 [2021-03-26 08:01:39 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 980/1251] eta: 0:02:18 lr: 0.000470 loss: 3.2950 (3.2847) grad_norm: 1.5076 (1.4920) time: 0.5039 [2021-03-26 08:01:44 swin_small_patch4_window7_224] INFO: Epoch: [156] [ 990/1251] eta: 0:02:13 lr: 0.000470 loss: 3.3934 (3.2862) grad_norm: 1.4621 (1.4915) time: 0.5005 [2021-03-26 08:01:49 swin_small_patch4_window7_224] INFO: Epoch: [156] [1000/1251] eta: 0:02:08 lr: 0.000470 loss: 3.4136 (3.2866) grad_norm: 1.4621 (1.4922) time: 0.4988 [2021-03-26 08:01:54 swin_small_patch4_window7_224] INFO: Epoch: [156] [1010/1251] eta: 0:02:02 lr: 0.000470 loss: 3.2592 (3.2859) grad_norm: 1.5118 (1.4932) time: 0.5010 [2021-03-26 08:01:59 swin_small_patch4_window7_224] INFO: Epoch: [156] [1020/1251] eta: 0:01:57 lr: 0.000470 loss: 3.2684 (3.2861) grad_norm: 1.4941 (1.4928) time: 0.5021 [2021-03-26 08:02:04 swin_small_patch4_window7_224] INFO: Epoch: [156] [1030/1251] eta: 0:01:52 lr: 0.000470 loss: 3.2939 (3.2859) grad_norm: 1.4546 (1.4929) time: 0.5059 [2021-03-26 08:02:09 swin_small_patch4_window7_224] INFO: Epoch: [156] [1040/1251] eta: 0:01:47 lr: 0.000470 loss: 3.3025 (3.2871) grad_norm: 1.4916 (1.4926) time: 0.5062 [2021-03-26 08:02:14 swin_small_patch4_window7_224] INFO: Epoch: [156] [1050/1251] eta: 0:01:42 lr: 0.000470 loss: 3.2831 (3.2874) grad_norm: 1.4547 (1.4919) time: 0.5094 [2021-03-26 08:02:19 swin_small_patch4_window7_224] INFO: Epoch: [156] [1060/1251] eta: 0:01:37 lr: 0.000470 loss: 3.4098 (3.2884) grad_norm: 1.4012 (1.4914) time: 0.5101 [2021-03-26 08:02:24 swin_small_patch4_window7_224] INFO: Epoch: [156] [1070/1251] eta: 0:01:32 lr: 0.000469 loss: 3.4259 (3.2884) grad_norm: 1.4012 (1.4912) time: 0.5093 [2021-03-26 08:02:29 swin_small_patch4_window7_224] INFO: Epoch: [156] [1080/1251] eta: 0:01:27 lr: 0.000469 loss: 3.2640 (3.2874) grad_norm: 1.4606 (1.4911) time: 0.5111 [2021-03-26 08:02:34 swin_small_patch4_window7_224] INFO: Epoch: [156] [1090/1251] eta: 0:01:22 lr: 0.000469 loss: 3.2640 (3.2860) grad_norm: 1.4518 (1.4906) time: 0.5096 [2021-03-26 08:02:39 swin_small_patch4_window7_224] INFO: Epoch: [156] [1100/1251] eta: 0:01:16 lr: 0.000469 loss: 3.3323 (3.2864) grad_norm: 1.4181 (1.4902) time: 0.5057 [2021-03-26 08:02:44 swin_small_patch4_window7_224] INFO: Epoch: [156] [1110/1251] eta: 0:01:11 lr: 0.000469 loss: 3.3451 (3.2856) grad_norm: 1.4746 (1.4906) time: 0.4981 [2021-03-26 08:02:49 swin_small_patch4_window7_224] INFO: Epoch: [156] [1120/1251] eta: 0:01:06 lr: 0.000469 loss: 2.8495 (3.2816) grad_norm: 1.4637 (1.4900) time: 0.4916 [2021-03-26 08:02:54 swin_small_patch4_window7_224] INFO: Epoch: [156] [1130/1251] eta: 0:01:01 lr: 0.000469 loss: 3.1351 (3.2812) grad_norm: 1.4504 (1.4897) time: 0.5006 [2021-03-26 08:02:59 swin_small_patch4_window7_224] INFO: Epoch: [156] [1140/1251] eta: 0:00:56 lr: 0.000469 loss: 3.3483 (3.2817) grad_norm: 1.4147 (1.4897) time: 0.5078 [2021-03-26 08:03:04 swin_small_patch4_window7_224] INFO: Epoch: [156] [1150/1251] eta: 0:00:51 lr: 0.000469 loss: 3.3483 (3.2813) grad_norm: 1.3940 (1.4897) time: 0.5033 [2021-03-26 08:03:10 swin_small_patch4_window7_224] INFO: Epoch: [156] [1160/1251] eta: 0:00:46 lr: 0.000469 loss: 3.3928 (3.2831) grad_norm: 1.4382 (1.4898) time: 0.5029 [2021-03-26 08:03:15 swin_small_patch4_window7_224] INFO: Epoch: [156] [1170/1251] eta: 0:00:41 lr: 0.000469 loss: 3.4857 (3.2841) grad_norm: 1.4813 (1.4906) time: 0.5026 [2021-03-26 08:03:20 swin_small_patch4_window7_224] INFO: Epoch: [156] [1180/1251] eta: 0:00:36 lr: 0.000469 loss: 3.4448 (3.2841) grad_norm: 1.5937 (1.4919) time: 0.5040 [2021-03-26 08:03:25 swin_small_patch4_window7_224] INFO: Epoch: [156] [1190/1251] eta: 0:00:31 lr: 0.000469 loss: 3.4669 (3.2844) grad_norm: 1.5779 (1.4922) time: 0.5056 [2021-03-26 08:03:30 swin_small_patch4_window7_224] INFO: Epoch: [156] [1200/1251] eta: 0:00:25 lr: 0.000469 loss: 3.5238 (3.2854) grad_norm: 1.4640 (1.4918) time: 0.4998 [2021-03-26 08:03:35 swin_small_patch4_window7_224] INFO: Epoch: [156] [1210/1251] eta: 0:00:20 lr: 0.000469 loss: 3.4871 (3.2855) grad_norm: 1.4340 (1.4916) time: 0.5000 [2021-03-26 08:03:40 swin_small_patch4_window7_224] INFO: Epoch: [156] [1220/1251] eta: 0:00:15 lr: 0.000469 loss: 3.5758 (3.2873) grad_norm: 1.4462 (1.4915) time: 0.5043 [2021-03-26 08:03:45 swin_small_patch4_window7_224] INFO: Epoch: [156] [1230/1251] eta: 0:00:10 lr: 0.000469 loss: 3.5230 (3.2885) grad_norm: 1.4587 (1.4910) time: 0.5042 [2021-03-26 08:03:50 swin_small_patch4_window7_224] INFO: Epoch: [156] [1240/1251] eta: 0:00:05 lr: 0.000469 loss: 3.3448 (3.2881) grad_norm: 1.4534 (1.4905) time: 0.4991 [2021-03-26 08:03:55 swin_small_patch4_window7_224] INFO: Epoch: [156] [1250/1251] eta: 0:00:00 lr: 0.000469 loss: 3.3448 (3.2882) grad_norm: 1.4156 (1.4897) time: 0.4957 [2021-03-26 08:04:01 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:31 loss: 0.9852 (0.9852) acc1: 68.7500 (68.7500) acc5: 90.6250 (90.6250) [2021-03-26 08:04:04 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8955 (0.8777) acc1: 79.6875 (78.8352) acc5: 96.8750 (95.4545) [2021-03-26 08:04:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7985 (0.8864) acc1: 79.6875 (78.8690) acc5: 95.3125 (94.8661) [2021-03-26 08:04:09 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8843 (0.9023) acc1: 78.1250 (78.6794) acc5: 95.3125 (94.7581) [2021-03-26 08:04:10 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8872 (0.9085) acc1: 78.1250 (78.6585) acc5: 95.3125 (94.7027) [2021-03-26 08:04:11 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8872 (0.9091) acc1: 76.5625 (78.7840) acc5: 93.7500 (94.6240) [2021-03-26 08:04:16 swin_small_patch4_window7_224] INFO: * Acc@1 78.574 Acc@5 94.578 loss 0.896 [2021-03-26 08:04:16 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.6% [2021-03-26 08:04:16 swin_small_patch4_window7_224] INFO: Max accuracy: 78.57% [2021-03-26 08:04:21 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 0/1251] eta: 1:33:36 lr: 0.000469 loss: 2.5342 (2.5342) grad_norm: 1.4196 (1.4196) time: 4.4893 [2021-03-26 08:04:26 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 10/1251] eta: 0:18:04 lr: 0.000469 loss: 3.3072 (3.2108) grad_norm: 1.5540 (1.5375) time: 0.8738 [2021-03-26 08:04:31 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 20/1251] eta: 0:14:18 lr: 0.000469 loss: 3.3676 (3.3555) grad_norm: 1.5841 (1.5584) time: 0.5079 [2021-03-26 08:04:36 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 30/1251] eta: 0:12:57 lr: 0.000469 loss: 3.4269 (3.3251) grad_norm: 1.5363 (1.5437) time: 0.5069 [2021-03-26 08:04:41 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 40/1251] eta: 0:12:10 lr: 0.000469 loss: 3.3979 (3.3258) grad_norm: 1.4976 (1.5272) time: 0.5043 [2021-03-26 08:04:46 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 50/1251] eta: 0:11:40 lr: 0.000469 loss: 3.3979 (3.3246) grad_norm: 1.5026 (1.5203) time: 0.5007 [2021-03-26 08:04:51 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 60/1251] eta: 0:11:20 lr: 0.000468 loss: 3.4471 (3.3543) grad_norm: 1.5183 (1.5242) time: 0.5064 [2021-03-26 08:04:56 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 70/1251] eta: 0:11:02 lr: 0.000468 loss: 3.3678 (3.3154) grad_norm: 1.4393 (1.5185) time: 0.5043 [2021-03-26 08:05:01 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 80/1251] eta: 0:10:48 lr: 0.000468 loss: 3.3063 (3.3286) grad_norm: 1.4176 (1.5186) time: 0.5005 [2021-03-26 08:05:06 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 90/1251] eta: 0:10:37 lr: 0.000468 loss: 3.4277 (3.3213) grad_norm: 1.4384 (1.5145) time: 0.5076 [2021-03-26 08:05:11 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 100/1251] eta: 0:10:26 lr: 0.000468 loss: 3.2154 (3.2885) grad_norm: 1.4384 (1.5216) time: 0.5048 [2021-03-26 08:05:17 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 110/1251] eta: 0:10:18 lr: 0.000468 loss: 2.9741 (3.2761) grad_norm: 1.4653 (1.5110) time: 0.5061 [2021-03-26 08:05:22 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 120/1251] eta: 0:10:09 lr: 0.000468 loss: 2.9741 (3.2644) grad_norm: 1.4413 (1.5093) time: 0.5096 [2021-03-26 08:05:27 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 130/1251] eta: 0:10:01 lr: 0.000468 loss: 3.1552 (3.2682) grad_norm: 1.4747 (1.5056) time: 0.5082 [2021-03-26 08:05:32 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 140/1251] eta: 0:09:52 lr: 0.000468 loss: 3.1627 (3.2631) grad_norm: 1.4349 (1.5000) time: 0.5044 [2021-03-26 08:05:37 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 150/1251] eta: 0:09:44 lr: 0.000468 loss: 3.2541 (3.2683) grad_norm: 1.4306 (1.4999) time: 0.4949 [2021-03-26 08:05:42 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 160/1251] eta: 0:09:37 lr: 0.000468 loss: 3.2871 (3.2667) grad_norm: 1.4544 (1.4980) time: 0.4995 [2021-03-26 08:05:47 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 170/1251] eta: 0:09:30 lr: 0.000468 loss: 3.3935 (3.2708) grad_norm: 1.5036 (1.5009) time: 0.5034 [2021-03-26 08:05:52 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 180/1251] eta: 0:09:23 lr: 0.000468 loss: 3.4239 (3.2709) grad_norm: 1.4503 (1.5000) time: 0.4972 [2021-03-26 08:05:57 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 190/1251] eta: 0:09:16 lr: 0.000468 loss: 3.3898 (3.2649) grad_norm: 1.4747 (1.5044) time: 0.4962 [2021-03-26 08:06:02 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 200/1251] eta: 0:09:10 lr: 0.000468 loss: 3.4759 (3.2797) grad_norm: 1.5436 (1.5059) time: 0.5065 [2021-03-26 08:06:07 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 210/1251] eta: 0:09:04 lr: 0.000468 loss: 3.4905 (3.2850) grad_norm: 1.4666 (1.5055) time: 0.5061 [2021-03-26 08:06:12 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 220/1251] eta: 0:08:58 lr: 0.000468 loss: 3.5298 (3.2987) grad_norm: 1.4511 (1.5059) time: 0.5041 [2021-03-26 08:06:17 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 230/1251] eta: 0:08:51 lr: 0.000468 loss: 3.4654 (3.2905) grad_norm: 1.5323 (1.5055) time: 0.5015 [2021-03-26 08:06:22 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 240/1251] eta: 0:08:46 lr: 0.000468 loss: 3.2122 (3.2943) grad_norm: 1.4896 (1.5087) time: 0.5047 [2021-03-26 08:06:27 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 250/1251] eta: 0:08:40 lr: 0.000468 loss: 3.4539 (3.3008) grad_norm: 1.5319 (1.5097) time: 0.5040 [2021-03-26 08:06:32 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 260/1251] eta: 0:08:33 lr: 0.000468 loss: 3.4462 (3.2938) grad_norm: 1.5137 (1.5090) time: 0.4926 [2021-03-26 08:06:37 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 270/1251] eta: 0:08:28 lr: 0.000468 loss: 3.2185 (3.2953) grad_norm: 1.5103 (1.5093) time: 0.5017 [2021-03-26 08:06:42 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 280/1251] eta: 0:08:23 lr: 0.000468 loss: 3.3577 (3.2965) grad_norm: 1.4906 (1.5090) time: 0.5118 [2021-03-26 08:06:47 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 290/1251] eta: 0:08:17 lr: 0.000468 loss: 3.2640 (3.2961) grad_norm: 1.5011 (1.5105) time: 0.5069 [2021-03-26 08:06:52 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 300/1251] eta: 0:08:11 lr: 0.000468 loss: 3.2074 (3.2882) grad_norm: 1.4776 (inf) time: 0.4984 [2021-03-26 08:06:57 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 310/1251] eta: 0:08:06 lr: 0.000467 loss: 3.0307 (3.2814) grad_norm: 1.4843 (inf) time: 0.5036 [2021-03-26 08:07:02 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 320/1251] eta: 0:08:00 lr: 0.000467 loss: 3.3327 (3.2850) grad_norm: 1.5080 (inf) time: 0.5051 [2021-03-26 08:07:07 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 330/1251] eta: 0:07:54 lr: 0.000467 loss: 3.3359 (3.2833) grad_norm: 1.5080 (inf) time: 0.5004 [2021-03-26 08:07:12 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 340/1251] eta: 0:07:49 lr: 0.000467 loss: 3.4581 (3.2827) grad_norm: 1.4498 (inf) time: 0.5001 [2021-03-26 08:07:17 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 350/1251] eta: 0:07:43 lr: 0.000467 loss: 3.5045 (3.2888) grad_norm: 1.4762 (inf) time: 0.4994 [2021-03-26 08:07:22 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 360/1251] eta: 0:07:38 lr: 0.000467 loss: 3.4985 (3.2884) grad_norm: 1.4762 (inf) time: 0.4964 [2021-03-26 08:07:27 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 370/1251] eta: 0:07:32 lr: 0.000467 loss: 3.2906 (3.2819) grad_norm: 1.4354 (inf) time: 0.4960 [2021-03-26 08:07:32 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 380/1251] eta: 0:07:27 lr: 0.000467 loss: 3.3365 (3.2849) grad_norm: 1.4874 (inf) time: 0.5002 [2021-03-26 08:07:37 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 390/1251] eta: 0:07:21 lr: 0.000467 loss: 3.5473 (3.2891) grad_norm: 1.4788 (inf) time: 0.5034 [2021-03-26 08:07:42 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 400/1251] eta: 0:07:16 lr: 0.000467 loss: 3.3467 (3.2886) grad_norm: 1.4604 (inf) time: 0.5044 [2021-03-26 08:07:47 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 410/1251] eta: 0:07:11 lr: 0.000467 loss: 3.2455 (3.2842) grad_norm: 1.4168 (inf) time: 0.5057 [2021-03-26 08:07:52 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 420/1251] eta: 0:07:06 lr: 0.000467 loss: 3.2118 (3.2897) grad_norm: 1.4168 (inf) time: 0.5080 [2021-03-26 08:07:58 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 430/1251] eta: 0:07:00 lr: 0.000467 loss: 3.4383 (3.2864) grad_norm: 1.5058 (inf) time: 0.5109 [2021-03-26 08:08:03 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 440/1251] eta: 0:06:55 lr: 0.000467 loss: 3.1487 (3.2777) grad_norm: 1.5246 (inf) time: 0.5073 [2021-03-26 08:08:08 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 450/1251] eta: 0:06:50 lr: 0.000467 loss: 3.0238 (3.2716) grad_norm: 1.5282 (inf) time: 0.5021 [2021-03-26 08:08:13 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 460/1251] eta: 0:06:45 lr: 0.000467 loss: 3.0811 (3.2728) grad_norm: 1.4538 (inf) time: 0.5067 [2021-03-26 08:08:18 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 470/1251] eta: 0:06:39 lr: 0.000467 loss: 3.3337 (3.2765) grad_norm: 1.4294 (inf) time: 0.5078 [2021-03-26 08:08:23 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 480/1251] eta: 0:06:34 lr: 0.000467 loss: 3.3337 (3.2753) grad_norm: 1.5317 (inf) time: 0.5018 [2021-03-26 08:08:28 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 490/1251] eta: 0:06:29 lr: 0.000467 loss: 3.3045 (3.2753) grad_norm: 1.5138 (inf) time: 0.5027 [2021-03-26 08:08:33 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 500/1251] eta: 0:06:24 lr: 0.000467 loss: 3.1913 (3.2751) grad_norm: 1.5077 (inf) time: 0.5043 [2021-03-26 08:08:38 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 510/1251] eta: 0:06:18 lr: 0.000467 loss: 3.2027 (3.2740) grad_norm: 1.5854 (inf) time: 0.5022 [2021-03-26 08:08:43 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 520/1251] eta: 0:06:13 lr: 0.000467 loss: 3.3950 (3.2765) grad_norm: 1.5095 (inf) time: 0.5052 [2021-03-26 08:08:48 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 530/1251] eta: 0:06:08 lr: 0.000467 loss: 3.2296 (3.2722) grad_norm: 1.4598 (inf) time: 0.5049 [2021-03-26 08:08:53 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 540/1251] eta: 0:06:03 lr: 0.000467 loss: 3.0902 (3.2696) grad_norm: 1.5127 (inf) time: 0.5089 [2021-03-26 08:08:58 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 550/1251] eta: 0:05:58 lr: 0.000466 loss: 3.1844 (3.2726) grad_norm: 1.5565 (inf) time: 0.5161 [2021-03-26 08:09:03 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 560/1251] eta: 0:05:53 lr: 0.000466 loss: 3.5890 (3.2758) grad_norm: 1.5800 (inf) time: 0.5167 [2021-03-26 08:09:08 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 570/1251] eta: 0:05:48 lr: 0.000466 loss: 3.4855 (3.2780) grad_norm: 1.5836 (inf) time: 0.5069 [2021-03-26 08:09:13 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 580/1251] eta: 0:05:42 lr: 0.000466 loss: 3.3653 (3.2758) grad_norm: 1.5566 (inf) time: 0.5005 [2021-03-26 08:09:19 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 590/1251] eta: 0:05:37 lr: 0.000466 loss: 3.1886 (3.2749) grad_norm: 1.4746 (inf) time: 0.5075 [2021-03-26 08:09:24 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 600/1251] eta: 0:05:32 lr: 0.000466 loss: 3.3025 (3.2767) grad_norm: 1.5223 (inf) time: 0.5089 [2021-03-26 08:09:29 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 610/1251] eta: 0:05:27 lr: 0.000466 loss: 3.3025 (3.2776) grad_norm: 1.4768 (inf) time: 0.5017 [2021-03-26 08:09:34 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 620/1251] eta: 0:05:22 lr: 0.000466 loss: 3.2857 (3.2748) grad_norm: 1.5157 (inf) time: 0.5055 [2021-03-26 08:09:39 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 630/1251] eta: 0:05:17 lr: 0.000466 loss: 3.4390 (3.2789) grad_norm: 1.5256 (inf) time: 0.5066 [2021-03-26 08:09:44 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 640/1251] eta: 0:05:11 lr: 0.000466 loss: 3.3718 (3.2760) grad_norm: 1.5256 (inf) time: 0.4998 [2021-03-26 08:09:49 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 650/1251] eta: 0:05:06 lr: 0.000466 loss: 3.1647 (3.2758) grad_norm: 1.5047 (inf) time: 0.5060 [2021-03-26 08:09:54 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 660/1251] eta: 0:05:01 lr: 0.000466 loss: 3.2691 (3.2776) grad_norm: 1.4949 (inf) time: 0.5050 [2021-03-26 08:09:59 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 670/1251] eta: 0:04:56 lr: 0.000466 loss: 3.2756 (3.2770) grad_norm: 1.5254 (inf) time: 0.5000 [2021-03-26 08:10:04 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 680/1251] eta: 0:04:51 lr: 0.000466 loss: 3.2756 (3.2779) grad_norm: 1.5246 (inf) time: 0.5019 [2021-03-26 08:10:09 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 690/1251] eta: 0:04:46 lr: 0.000466 loss: 3.4232 (3.2818) grad_norm: 1.5352 (inf) time: 0.5012 [2021-03-26 08:10:14 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 700/1251] eta: 0:04:40 lr: 0.000466 loss: 3.3511 (3.2800) grad_norm: 1.5399 (inf) time: 0.5057 [2021-03-26 08:10:19 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 710/1251] eta: 0:04:35 lr: 0.000466 loss: 3.0012 (3.2759) grad_norm: 1.4964 (inf) time: 0.5087 [2021-03-26 08:10:24 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 720/1251] eta: 0:04:30 lr: 0.000466 loss: 3.4717 (3.2795) grad_norm: 1.4836 (inf) time: 0.4988 [2021-03-26 08:10:29 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 730/1251] eta: 0:04:25 lr: 0.000466 loss: 3.4595 (3.2792) grad_norm: 1.4468 (inf) time: 0.5006 [2021-03-26 08:10:34 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 740/1251] eta: 0:04:20 lr: 0.000466 loss: 3.1889 (3.2791) grad_norm: 1.4468 (inf) time: 0.5159 [2021-03-26 08:10:39 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 750/1251] eta: 0:04:15 lr: 0.000466 loss: 3.2908 (3.2795) grad_norm: 1.5137 (inf) time: 0.5190 [2021-03-26 08:10:44 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 760/1251] eta: 0:04:10 lr: 0.000466 loss: 3.3601 (3.2799) grad_norm: 1.5137 (inf) time: 0.5087 [2021-03-26 08:10:50 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 770/1251] eta: 0:04:05 lr: 0.000466 loss: 3.4263 (3.2803) grad_norm: 1.4912 (inf) time: 0.5092 [2021-03-26 08:10:55 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 780/1251] eta: 0:04:00 lr: 0.000466 loss: 3.4459 (3.2833) grad_norm: 1.4525 (inf) time: 0.5101 [2021-03-26 08:11:00 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 790/1251] eta: 0:03:54 lr: 0.000465 loss: 3.1373 (3.2778) grad_norm: 1.4525 (inf) time: 0.5038 [2021-03-26 08:11:05 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 800/1251] eta: 0:03:49 lr: 0.000465 loss: 2.9398 (3.2754) grad_norm: 1.5259 (inf) time: 0.5051 [2021-03-26 08:11:10 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 810/1251] eta: 0:03:44 lr: 0.000465 loss: 3.1177 (3.2757) grad_norm: 1.5130 (inf) time: 0.5059 [2021-03-26 08:11:15 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 820/1251] eta: 0:03:39 lr: 0.000465 loss: 3.5284 (3.2788) grad_norm: 1.5062 (inf) time: 0.5089 [2021-03-26 08:11:20 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 830/1251] eta: 0:03:34 lr: 0.000465 loss: 3.3662 (3.2780) grad_norm: 1.4118 (inf) time: 0.5114 [2021-03-26 08:11:25 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 840/1251] eta: 0:03:29 lr: 0.000465 loss: 3.1765 (3.2770) grad_norm: 1.4126 (inf) time: 0.5096 [2021-03-26 08:11:30 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 850/1251] eta: 0:03:24 lr: 0.000465 loss: 3.5326 (3.2794) grad_norm: 1.4985 (inf) time: 0.5049 [2021-03-26 08:11:35 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 860/1251] eta: 0:03:19 lr: 0.000465 loss: 3.4592 (3.2792) grad_norm: 1.5498 (inf) time: 0.5086 [2021-03-26 08:11:40 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 870/1251] eta: 0:03:14 lr: 0.000465 loss: 3.4459 (3.2807) grad_norm: 1.5508 (inf) time: 0.5094 [2021-03-26 08:11:45 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 880/1251] eta: 0:03:09 lr: 0.000465 loss: 3.5131 (3.2828) grad_norm: 1.4967 (inf) time: 0.5057 [2021-03-26 08:11:50 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 890/1251] eta: 0:03:03 lr: 0.000465 loss: 3.3179 (3.2822) grad_norm: 1.3960 (inf) time: 0.5054 [2021-03-26 08:11:56 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 900/1251] eta: 0:02:58 lr: 0.000465 loss: 3.3492 (3.2839) grad_norm: 1.4375 (inf) time: 0.5041 [2021-03-26 08:12:01 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 910/1251] eta: 0:02:53 lr: 0.000465 loss: 3.4053 (3.2835) grad_norm: 1.4375 (inf) time: 0.5030 [2021-03-26 08:12:06 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 920/1251] eta: 0:02:48 lr: 0.000465 loss: 3.4053 (3.2851) grad_norm: 1.4475 (inf) time: 0.5006 [2021-03-26 08:12:11 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 930/1251] eta: 0:02:43 lr: 0.000465 loss: 3.3992 (3.2825) grad_norm: 1.4698 (inf) time: 0.5031 [2021-03-26 08:12:16 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 940/1251] eta: 0:02:38 lr: 0.000465 loss: 3.2320 (3.2825) grad_norm: 1.4945 (inf) time: 0.5079 [2021-03-26 08:12:21 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 950/1251] eta: 0:02:33 lr: 0.000465 loss: 3.3050 (3.2836) grad_norm: 1.4732 (inf) time: 0.5132 [2021-03-26 08:12:26 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 960/1251] eta: 0:02:28 lr: 0.000465 loss: 3.4148 (3.2821) grad_norm: 1.5193 (inf) time: 0.5121 [2021-03-26 08:12:31 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 970/1251] eta: 0:02:23 lr: 0.000465 loss: 3.1972 (3.2788) grad_norm: 1.5260 (inf) time: 0.5062 [2021-03-26 08:12:36 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 980/1251] eta: 0:02:17 lr: 0.000465 loss: 3.1972 (3.2775) grad_norm: 1.4956 (inf) time: 0.5046 [2021-03-26 08:12:41 swin_small_patch4_window7_224] INFO: Epoch: [157] [ 990/1251] eta: 0:02:12 lr: 0.000465 loss: 3.2514 (3.2767) grad_norm: 1.5131 (inf) time: 0.5092 [2021-03-26 08:12:46 swin_small_patch4_window7_224] INFO: Epoch: [157] [1000/1251] eta: 0:02:07 lr: 0.000465 loss: 3.4956 (3.2784) grad_norm: 1.4932 (inf) time: 0.5060 [2021-03-26 08:12:51 swin_small_patch4_window7_224] INFO: Epoch: [157] [1010/1251] eta: 0:02:02 lr: 0.000465 loss: 3.5164 (3.2786) grad_norm: 1.4401 (inf) time: 0.5040 [2021-03-26 08:12:56 swin_small_patch4_window7_224] INFO: Epoch: [157] [1020/1251] eta: 0:01:57 lr: 0.000465 loss: 3.5192 (3.2782) grad_norm: 1.4243 (inf) time: 0.5024 [2021-03-26 08:13:01 swin_small_patch4_window7_224] INFO: Epoch: [157] [1030/1251] eta: 0:01:52 lr: 0.000464 loss: 3.3872 (3.2764) grad_norm: 1.4413 (inf) time: 0.4985 [2021-03-26 08:13:06 swin_small_patch4_window7_224] INFO: Epoch: [157] [1040/1251] eta: 0:01:47 lr: 0.000464 loss: 3.2732 (3.2768) grad_norm: 1.5032 (inf) time: 0.5022 [2021-03-26 08:13:11 swin_small_patch4_window7_224] INFO: Epoch: [157] [1050/1251] eta: 0:01:42 lr: 0.000464 loss: 3.4170 (3.2775) grad_norm: 1.5532 (inf) time: 0.5065 [2021-03-26 08:13:16 swin_small_patch4_window7_224] INFO: Epoch: [157] [1060/1251] eta: 0:01:37 lr: 0.000464 loss: 3.3054 (3.2768) grad_norm: 1.5769 (inf) time: 0.5113 [2021-03-26 08:13:22 swin_small_patch4_window7_224] INFO: Epoch: [157] [1070/1251] eta: 0:01:32 lr: 0.000464 loss: 3.2346 (3.2756) grad_norm: 1.5520 (inf) time: 0.5083 [2021-03-26 08:13:27 swin_small_patch4_window7_224] INFO: Epoch: [157] [1080/1251] eta: 0:01:26 lr: 0.000464 loss: 3.1022 (3.2743) grad_norm: 1.4771 (inf) time: 0.5032 [2021-03-26 08:13:32 swin_small_patch4_window7_224] INFO: Epoch: [157] [1090/1251] eta: 0:01:21 lr: 0.000464 loss: 3.0644 (3.2731) grad_norm: 1.5235 (inf) time: 0.5002 [2021-03-26 08:13:37 swin_small_patch4_window7_224] INFO: Epoch: [157] [1100/1251] eta: 0:01:16 lr: 0.000464 loss: 3.2485 (3.2728) grad_norm: 1.4741 (inf) time: 0.5022 [2021-03-26 08:13:42 swin_small_patch4_window7_224] INFO: Epoch: [157] [1110/1251] eta: 0:01:11 lr: 0.000464 loss: 3.1046 (3.2705) grad_norm: 1.4177 (inf) time: 0.5060 [2021-03-26 08:13:47 swin_small_patch4_window7_224] INFO: Epoch: [157] [1120/1251] eta: 0:01:06 lr: 0.000464 loss: 3.0771 (3.2704) grad_norm: 1.4463 (inf) time: 0.5051 [2021-03-26 08:13:52 swin_small_patch4_window7_224] INFO: Epoch: [157] [1130/1251] eta: 0:01:01 lr: 0.000464 loss: 3.2694 (3.2708) grad_norm: 1.5169 (inf) time: 0.5003 [2021-03-26 08:13:57 swin_small_patch4_window7_224] INFO: Epoch: [157] [1140/1251] eta: 0:00:56 lr: 0.000464 loss: 3.5281 (3.2727) grad_norm: 1.5116 (inf) time: 0.5041 [2021-03-26 08:14:02 swin_small_patch4_window7_224] INFO: Epoch: [157] [1150/1251] eta: 0:00:51 lr: 0.000464 loss: 3.4025 (3.2727) grad_norm: 1.4301 (inf) time: 0.5095 [2021-03-26 08:14:07 swin_small_patch4_window7_224] INFO: Epoch: [157] [1160/1251] eta: 0:00:46 lr: 0.000464 loss: 3.1808 (3.2726) grad_norm: 1.4335 (inf) time: 0.5107 [2021-03-26 08:14:12 swin_small_patch4_window7_224] INFO: Epoch: [157] [1170/1251] eta: 0:00:41 lr: 0.000464 loss: 3.3652 (3.2735) grad_norm: 1.4335 (inf) time: 0.5105 [2021-03-26 08:14:17 swin_small_patch4_window7_224] INFO: Epoch: [157] [1180/1251] eta: 0:00:36 lr: 0.000464 loss: 3.3021 (3.2733) grad_norm: 1.4263 (inf) time: 0.5132 [2021-03-26 08:14:22 swin_small_patch4_window7_224] INFO: Epoch: [157] [1190/1251] eta: 0:00:31 lr: 0.000464 loss: 3.2317 (3.2725) grad_norm: 1.4308 (inf) time: 0.5139 [2021-03-26 08:14:27 swin_small_patch4_window7_224] INFO: Epoch: [157] [1200/1251] eta: 0:00:25 lr: 0.000464 loss: 3.2989 (3.2725) grad_norm: 1.4024 (inf) time: 0.5053 [2021-03-26 08:14:32 swin_small_patch4_window7_224] INFO: Epoch: [157] [1210/1251] eta: 0:00:20 lr: 0.000464 loss: 3.4692 (3.2733) grad_norm: 1.4530 (inf) time: 0.5066 [2021-03-26 08:14:38 swin_small_patch4_window7_224] INFO: Epoch: [157] [1220/1251] eta: 0:00:15 lr: 0.000464 loss: 3.4819 (3.2738) grad_norm: 1.4996 (inf) time: 0.5095 [2021-03-26 08:14:43 swin_small_patch4_window7_224] INFO: Epoch: [157] [1230/1251] eta: 0:00:10 lr: 0.000464 loss: 3.4425 (3.2722) grad_norm: 1.4625 (inf) time: 0.5045 [2021-03-26 08:14:48 swin_small_patch4_window7_224] INFO: Epoch: [157] [1240/1251] eta: 0:00:05 lr: 0.000464 loss: 3.2246 (3.2705) grad_norm: 1.4122 (inf) time: 0.5019 [2021-03-26 08:14:53 swin_small_patch4_window7_224] INFO: Epoch: [157] [1250/1251] eta: 0:00:00 lr: 0.000464 loss: 2.9959 (3.2695) grad_norm: 1.5521 (inf) time: 0.5018 [2021-03-26 08:15:02 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:01 loss: 0.9125 (0.9125) acc1: 73.4375 (73.4375) acc5: 92.1875 (92.1875) [2021-03-26 08:15:04 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9125 (0.8936) acc1: 78.1250 (77.9830) acc5: 95.3125 (94.1761) [2021-03-26 08:15:07 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8743 (0.9225) acc1: 78.1250 (78.1994) acc5: 93.7500 (94.1220) [2021-03-26 08:15:09 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8762 (0.9125) acc1: 78.1250 (78.0242) acc5: 95.3125 (94.7581) [2021-03-26 08:15:10 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8846 (0.9013) acc1: 78.1250 (78.2774) acc5: 95.3125 (94.9695) [2021-03-26 08:15:11 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8883 (0.9054) acc1: 78.1250 (78.1120) acc5: 95.3125 (94.9120) [2021-03-26 08:15:21 swin_small_patch4_window7_224] INFO: * Acc@1 78.728 Acc@5 94.670 loss 0.896 [2021-03-26 08:15:21 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.7% [2021-03-26 08:15:21 swin_small_patch4_window7_224] INFO: Max accuracy: 78.73% [2021-03-26 08:15:26 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 0/1251] eta: 1:39:16 lr: 0.000464 loss: 2.4193 (2.4193) grad_norm: 1.3631 (1.3631) time: 4.7614 [2021-03-26 08:15:31 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 10/1251] eta: 0:18:27 lr: 0.000464 loss: 3.2984 (3.2848) grad_norm: 1.5455 (1.5121) time: 0.8923 [2021-03-26 08:15:36 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 20/1251] eta: 0:14:33 lr: 0.000463 loss: 3.2591 (3.1785) grad_norm: 1.3633 (1.4386) time: 0.5072 [2021-03-26 08:15:41 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 30/1251] eta: 0:13:07 lr: 0.000463 loss: 3.1269 (3.2133) grad_norm: 1.3633 (1.4276) time: 0.5085 [2021-03-26 08:15:46 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 40/1251] eta: 0:12:19 lr: 0.000463 loss: 3.2295 (3.2478) grad_norm: 1.4126 (1.4299) time: 0.5060 [2021-03-26 08:15:51 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 50/1251] eta: 0:11:47 lr: 0.000463 loss: 3.3639 (3.2526) grad_norm: 1.4233 (1.4382) time: 0.5031 [2021-03-26 08:15:56 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 60/1251] eta: 0:11:24 lr: 0.000463 loss: 3.3639 (3.2810) grad_norm: 1.5592 (1.4611) time: 0.5017 [2021-03-26 08:16:01 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 70/1251] eta: 0:11:06 lr: 0.000463 loss: 3.4915 (3.2955) grad_norm: 1.5593 (1.4732) time: 0.5011 [2021-03-26 08:16:06 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 80/1251] eta: 0:10:53 lr: 0.000463 loss: 3.4467 (3.3113) grad_norm: 1.5338 (1.4944) time: 0.5081 [2021-03-26 08:16:11 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 90/1251] eta: 0:10:40 lr: 0.000463 loss: 3.4467 (3.2995) grad_norm: 1.4655 (1.4894) time: 0.5074 [2021-03-26 08:16:16 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 100/1251] eta: 0:10:28 lr: 0.000463 loss: 3.4815 (3.3097) grad_norm: 1.4655 (1.4914) time: 0.4983 [2021-03-26 08:16:21 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 110/1251] eta: 0:10:18 lr: 0.000463 loss: 3.4815 (3.3269) grad_norm: 1.5269 (1.4944) time: 0.4957 [2021-03-26 08:16:26 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 120/1251] eta: 0:10:09 lr: 0.000463 loss: 3.2447 (3.3069) grad_norm: 1.5179 (1.4952) time: 0.4990 [2021-03-26 08:16:32 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 130/1251] eta: 0:10:02 lr: 0.000463 loss: 3.2546 (3.3057) grad_norm: 1.5163 (1.5041) time: 0.5149 [2021-03-26 08:16:37 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 140/1251] eta: 0:09:54 lr: 0.000463 loss: 3.3333 (3.3022) grad_norm: 1.5163 (1.5046) time: 0.5164 [2021-03-26 08:16:42 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 150/1251] eta: 0:09:47 lr: 0.000463 loss: 3.3364 (3.3020) grad_norm: 1.4831 (1.5012) time: 0.5074 [2021-03-26 08:16:47 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 160/1251] eta: 0:09:40 lr: 0.000463 loss: 3.4694 (3.3092) grad_norm: 1.4831 (1.5003) time: 0.5064 [2021-03-26 08:16:52 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 170/1251] eta: 0:09:33 lr: 0.000463 loss: 3.4424 (3.3113) grad_norm: 1.5374 (1.5063) time: 0.5034 [2021-03-26 08:16:57 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 180/1251] eta: 0:09:26 lr: 0.000463 loss: 3.2622 (3.2958) grad_norm: 1.5495 (1.5098) time: 0.5094 [2021-03-26 08:17:02 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 190/1251] eta: 0:09:20 lr: 0.000463 loss: 3.3765 (3.3084) grad_norm: 1.4712 (1.5069) time: 0.5088 [2021-03-26 08:17:07 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 200/1251] eta: 0:09:13 lr: 0.000463 loss: 3.4483 (3.3000) grad_norm: 1.4534 (1.5086) time: 0.5039 [2021-03-26 08:17:12 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 210/1251] eta: 0:09:07 lr: 0.000463 loss: 3.3393 (3.3066) grad_norm: 1.5349 (1.5102) time: 0.5054 [2021-03-26 08:17:17 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 220/1251] eta: 0:09:00 lr: 0.000463 loss: 3.3393 (3.2955) grad_norm: 1.5037 (1.5098) time: 0.5025 [2021-03-26 08:17:22 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 230/1251] eta: 0:08:54 lr: 0.000463 loss: 3.0372 (3.2825) grad_norm: 1.5010 (1.5115) time: 0.5020 [2021-03-26 08:17:27 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 240/1251] eta: 0:08:48 lr: 0.000463 loss: 3.1458 (3.2797) grad_norm: 1.4732 (1.5082) time: 0.5056 [2021-03-26 08:17:32 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 250/1251] eta: 0:08:43 lr: 0.000463 loss: 3.3241 (3.2855) grad_norm: 1.4190 (1.5066) time: 0.5100 [2021-03-26 08:17:37 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 260/1251] eta: 0:08:36 lr: 0.000463 loss: 3.3977 (3.2836) grad_norm: 1.3779 (1.5024) time: 0.5048 [2021-03-26 08:17:42 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 270/1251] eta: 0:08:30 lr: 0.000462 loss: 3.4166 (3.2855) grad_norm: 1.4025 (1.5040) time: 0.4985 [2021-03-26 08:17:47 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 280/1251] eta: 0:08:25 lr: 0.000462 loss: 3.3488 (3.2827) grad_norm: 1.5286 (1.5040) time: 0.5025 [2021-03-26 08:17:52 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 290/1251] eta: 0:08:19 lr: 0.000462 loss: 3.1301 (3.2756) grad_norm: 1.3905 (1.5017) time: 0.5039 [2021-03-26 08:17:58 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 300/1251] eta: 0:08:13 lr: 0.000462 loss: 3.1017 (3.2694) grad_norm: 1.3856 (1.4995) time: 0.5038 [2021-03-26 08:18:03 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 310/1251] eta: 0:08:08 lr: 0.000462 loss: 3.1458 (3.2703) grad_norm: 1.4812 (1.5001) time: 0.5057 [2021-03-26 08:18:08 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 320/1251] eta: 0:08:02 lr: 0.000462 loss: 3.2182 (3.2643) grad_norm: 1.4831 (1.4995) time: 0.5096 [2021-03-26 08:18:13 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 330/1251] eta: 0:07:57 lr: 0.000462 loss: 3.2157 (3.2637) grad_norm: 1.4458 (1.4973) time: 0.5078 [2021-03-26 08:18:18 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 340/1251] eta: 0:07:51 lr: 0.000462 loss: 3.2972 (3.2664) grad_norm: 1.4507 (1.4962) time: 0.5057 [2021-03-26 08:18:23 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 350/1251] eta: 0:07:46 lr: 0.000462 loss: 3.5229 (3.2707) grad_norm: 1.4680 (1.4962) time: 0.5075 [2021-03-26 08:18:28 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 360/1251] eta: 0:07:40 lr: 0.000462 loss: 3.5229 (3.2720) grad_norm: 1.4088 (1.4942) time: 0.5041 [2021-03-26 08:18:33 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 370/1251] eta: 0:07:35 lr: 0.000462 loss: 3.2772 (3.2720) grad_norm: 1.3971 (1.4929) time: 0.5009 [2021-03-26 08:18:38 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 380/1251] eta: 0:07:29 lr: 0.000462 loss: 3.0438 (3.2627) grad_norm: 1.4184 (1.4909) time: 0.4987 [2021-03-26 08:18:43 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 390/1251] eta: 0:07:23 lr: 0.000462 loss: 3.2162 (3.2684) grad_norm: 1.4265 (1.4923) time: 0.4981 [2021-03-26 08:18:48 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 400/1251] eta: 0:07:18 lr: 0.000462 loss: 3.4625 (3.2711) grad_norm: 1.5342 (1.4920) time: 0.4975 [2021-03-26 08:18:53 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 410/1251] eta: 0:07:12 lr: 0.000462 loss: 3.3012 (3.2681) grad_norm: 1.4546 (1.4915) time: 0.4980 [2021-03-26 08:18:58 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 420/1251] eta: 0:07:07 lr: 0.000462 loss: 3.2237 (3.2634) grad_norm: 1.4542 (1.4911) time: 0.5030 [2021-03-26 08:19:03 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 430/1251] eta: 0:07:02 lr: 0.000462 loss: 3.2205 (3.2625) grad_norm: 1.5048 (1.4931) time: 0.5087 [2021-03-26 08:19:08 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 440/1251] eta: 0:06:57 lr: 0.000462 loss: 3.4546 (3.2647) grad_norm: 1.5797 (1.4942) time: 0.5128 [2021-03-26 08:19:13 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 450/1251] eta: 0:06:52 lr: 0.000462 loss: 3.4432 (3.2628) grad_norm: 1.5900 (1.4980) time: 0.5119 [2021-03-26 08:19:18 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 460/1251] eta: 0:06:46 lr: 0.000462 loss: 3.4122 (3.2649) grad_norm: 1.5467 (1.4981) time: 0.5096 [2021-03-26 08:19:23 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 470/1251] eta: 0:06:41 lr: 0.000462 loss: 3.4110 (3.2646) grad_norm: 1.4911 (1.4979) time: 0.5057 [2021-03-26 08:19:28 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 480/1251] eta: 0:06:36 lr: 0.000462 loss: 3.4110 (3.2725) grad_norm: 1.4739 (1.4985) time: 0.5001 [2021-03-26 08:19:33 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 490/1251] eta: 0:06:30 lr: 0.000462 loss: 3.5486 (3.2729) grad_norm: 1.5293 (1.4992) time: 0.5031 [2021-03-26 08:19:39 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 500/1251] eta: 0:06:25 lr: 0.000462 loss: 3.3276 (3.2746) grad_norm: 1.5293 (1.5007) time: 0.5079 [2021-03-26 08:19:44 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 510/1251] eta: 0:06:20 lr: 0.000461 loss: 3.3276 (3.2716) grad_norm: 1.4758 (1.5009) time: 0.5073 [2021-03-26 08:19:49 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 520/1251] eta: 0:06:15 lr: 0.000461 loss: 3.2902 (3.2691) grad_norm: 1.4663 (1.5006) time: 0.5069 [2021-03-26 08:19:54 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 530/1251] eta: 0:06:10 lr: 0.000461 loss: 3.2902 (3.2695) grad_norm: 1.4520 (1.5002) time: 0.5114 [2021-03-26 08:19:59 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 540/1251] eta: 0:06:04 lr: 0.000461 loss: 3.3023 (3.2681) grad_norm: 1.4697 (1.5008) time: 0.5136 [2021-03-26 08:20:04 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 550/1251] eta: 0:05:59 lr: 0.000461 loss: 3.4007 (3.2723) grad_norm: 1.5017 (1.5005) time: 0.5108 [2021-03-26 08:20:09 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 560/1251] eta: 0:05:54 lr: 0.000461 loss: 3.5473 (3.2726) grad_norm: 1.5037 (1.5019) time: 0.5082 [2021-03-26 08:20:14 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 570/1251] eta: 0:05:49 lr: 0.000461 loss: 3.3730 (3.2752) grad_norm: 1.5874 (1.5022) time: 0.5047 [2021-03-26 08:20:19 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 580/1251] eta: 0:05:43 lr: 0.000461 loss: 3.4521 (3.2790) grad_norm: 1.5062 (1.5032) time: 0.5009 [2021-03-26 08:20:24 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 590/1251] eta: 0:05:38 lr: 0.000461 loss: 3.4521 (3.2803) grad_norm: 1.4930 (1.5043) time: 0.4976 [2021-03-26 08:20:29 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 600/1251] eta: 0:05:33 lr: 0.000461 loss: 3.4518 (3.2838) grad_norm: 1.5561 (1.5076) time: 0.5002 [2021-03-26 08:20:34 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 610/1251] eta: 0:05:28 lr: 0.000461 loss: 3.5622 (3.2870) grad_norm: 1.5697 (1.5090) time: 0.5055 [2021-03-26 08:20:39 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 620/1251] eta: 0:05:23 lr: 0.000461 loss: 3.3765 (3.2888) grad_norm: 1.5697 (1.5099) time: 0.5093 [2021-03-26 08:20:44 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 630/1251] eta: 0:05:18 lr: 0.000461 loss: 3.4472 (3.2910) grad_norm: 1.5316 (1.5102) time: 0.5130 [2021-03-26 08:20:50 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 640/1251] eta: 0:05:12 lr: 0.000461 loss: 3.5645 (3.2935) grad_norm: 1.5255 (1.5111) time: 0.5115 [2021-03-26 08:20:55 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 650/1251] eta: 0:05:07 lr: 0.000461 loss: 3.5645 (3.2990) grad_norm: 1.5604 (1.5122) time: 0.5061 [2021-03-26 08:21:00 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 660/1251] eta: 0:05:02 lr: 0.000461 loss: 3.5178 (3.2971) grad_norm: 1.5904 (1.5140) time: 0.5006 [2021-03-26 08:21:05 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 670/1251] eta: 0:04:57 lr: 0.000461 loss: 3.4031 (3.2967) grad_norm: 1.4698 (1.5133) time: 0.4989 [2021-03-26 08:21:10 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 680/1251] eta: 0:04:52 lr: 0.000461 loss: 3.4238 (3.2955) grad_norm: 1.4582 (1.5141) time: 0.5018 [2021-03-26 08:21:15 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 690/1251] eta: 0:04:46 lr: 0.000461 loss: 3.1566 (3.2966) grad_norm: 1.4654 (1.5158) time: 0.5016 [2021-03-26 08:21:20 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 700/1251] eta: 0:04:41 lr: 0.000461 loss: 3.1252 (3.2954) grad_norm: 1.5180 (1.5157) time: 0.4969 [2021-03-26 08:21:25 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 710/1251] eta: 0:04:36 lr: 0.000461 loss: 3.2520 (3.2955) grad_norm: 1.5180 (1.5157) time: 0.4986 [2021-03-26 08:21:30 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 720/1251] eta: 0:04:31 lr: 0.000461 loss: 3.2605 (3.2930) grad_norm: 1.3861 (1.5137) time: 0.5074 [2021-03-26 08:21:35 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 730/1251] eta: 0:04:26 lr: 0.000461 loss: 3.2605 (3.2931) grad_norm: 1.3835 (1.5135) time: 0.5153 [2021-03-26 08:21:40 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 740/1251] eta: 0:04:21 lr: 0.000461 loss: 3.1638 (3.2900) grad_norm: 1.4832 (1.5140) time: 0.5147 [2021-03-26 08:21:45 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 750/1251] eta: 0:04:16 lr: 0.000460 loss: 2.9558 (3.2870) grad_norm: 1.4060 (1.5126) time: 0.5232 [2021-03-26 08:21:50 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 760/1251] eta: 0:04:11 lr: 0.000460 loss: 3.2667 (3.2874) grad_norm: 1.4305 (1.5128) time: 0.5188 [2021-03-26 08:21:55 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 770/1251] eta: 0:04:05 lr: 0.000460 loss: 3.3285 (3.2870) grad_norm: 1.4848 (1.5137) time: 0.5019 [2021-03-26 08:22:00 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 780/1251] eta: 0:04:00 lr: 0.000460 loss: 3.3285 (3.2886) grad_norm: 1.5523 (1.5146) time: 0.5026 [2021-03-26 08:22:05 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 790/1251] eta: 0:03:55 lr: 0.000460 loss: 3.5372 (3.2913) grad_norm: 1.5246 (1.5150) time: 0.5040 [2021-03-26 08:22:10 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 800/1251] eta: 0:03:50 lr: 0.000460 loss: 3.3583 (3.2910) grad_norm: 1.5003 (1.5150) time: 0.4988 [2021-03-26 08:22:15 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 810/1251] eta: 0:03:45 lr: 0.000460 loss: 3.0948 (3.2863) grad_norm: 1.5378 (1.5158) time: 0.4995 [2021-03-26 08:22:21 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 820/1251] eta: 0:03:40 lr: 0.000460 loss: 3.2581 (3.2894) grad_norm: 1.5518 (1.5157) time: 0.5101 [2021-03-26 08:22:26 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 830/1251] eta: 0:03:34 lr: 0.000460 loss: 3.5542 (3.2899) grad_norm: 1.5167 (1.5162) time: 0.5071 [2021-03-26 08:22:31 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 840/1251] eta: 0:03:29 lr: 0.000460 loss: 3.5211 (3.2915) grad_norm: 1.5167 (1.5157) time: 0.5040 [2021-03-26 08:22:36 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 850/1251] eta: 0:03:24 lr: 0.000460 loss: 3.5253 (3.2920) grad_norm: 1.4501 (1.5154) time: 0.5081 [2021-03-26 08:22:41 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 860/1251] eta: 0:03:19 lr: 0.000460 loss: 3.5824 (3.2914) grad_norm: 1.4618 (1.5151) time: 0.5055 [2021-03-26 08:22:46 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 870/1251] eta: 0:03:14 lr: 0.000460 loss: 3.6140 (3.2941) grad_norm: 1.5280 (1.5155) time: 0.5057 [2021-03-26 08:22:51 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 880/1251] eta: 0:03:09 lr: 0.000460 loss: 3.3544 (3.2934) grad_norm: 1.4866 (1.5153) time: 0.5099 [2021-03-26 08:22:56 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 890/1251] eta: 0:03:04 lr: 0.000460 loss: 3.3544 (3.2933) grad_norm: 1.4570 (1.5147) time: 0.5073 [2021-03-26 08:23:01 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 900/1251] eta: 0:02:59 lr: 0.000460 loss: 3.5000 (3.2933) grad_norm: 1.4287 (1.5141) time: 0.5064 [2021-03-26 08:23:06 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 910/1251] eta: 0:02:53 lr: 0.000460 loss: 3.4898 (3.2922) grad_norm: 1.4114 (1.5133) time: 0.5015 [2021-03-26 08:23:11 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 920/1251] eta: 0:02:48 lr: 0.000460 loss: 3.4360 (3.2908) grad_norm: 1.4487 (1.5130) time: 0.5066 [2021-03-26 08:23:16 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 930/1251] eta: 0:02:43 lr: 0.000460 loss: 3.3688 (3.2908) grad_norm: 1.4882 (1.5132) time: 0.5145 [2021-03-26 08:23:22 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 940/1251] eta: 0:02:38 lr: 0.000460 loss: 3.3688 (3.2916) grad_norm: 1.5650 (1.5144) time: 0.5135 [2021-03-26 08:23:27 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 950/1251] eta: 0:02:33 lr: 0.000460 loss: 3.4390 (3.2918) grad_norm: 1.4675 (1.5138) time: 0.5099 [2021-03-26 08:23:32 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 960/1251] eta: 0:02:28 lr: 0.000460 loss: 3.4691 (3.2934) grad_norm: 1.4267 (1.5125) time: 0.5033 [2021-03-26 08:23:37 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 970/1251] eta: 0:02:23 lr: 0.000460 loss: 3.4798 (3.2917) grad_norm: 1.4249 (1.5121) time: 0.5030 [2021-03-26 08:23:42 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 980/1251] eta: 0:02:18 lr: 0.000460 loss: 3.0377 (3.2902) grad_norm: 1.4324 (1.5119) time: 0.5007 [2021-03-26 08:23:47 swin_small_patch4_window7_224] INFO: Epoch: [158] [ 990/1251] eta: 0:02:13 lr: 0.000459 loss: 3.3163 (3.2927) grad_norm: 1.4984 (1.5131) time: 0.5095 [2021-03-26 08:23:52 swin_small_patch4_window7_224] INFO: Epoch: [158] [1000/1251] eta: 0:02:08 lr: 0.000459 loss: 3.5811 (3.2953) grad_norm: 1.5664 (1.5137) time: 0.5139 [2021-03-26 08:23:57 swin_small_patch4_window7_224] INFO: Epoch: [158] [1010/1251] eta: 0:02:02 lr: 0.000459 loss: 3.5728 (3.2969) grad_norm: 1.5664 (1.5142) time: 0.5064 [2021-03-26 08:24:02 swin_small_patch4_window7_224] INFO: Epoch: [158] [1020/1251] eta: 0:01:57 lr: 0.000459 loss: 3.2900 (3.2934) grad_norm: 1.5131 (1.5142) time: 0.5039 [2021-03-26 08:24:07 swin_small_patch4_window7_224] INFO: Epoch: [158] [1030/1251] eta: 0:01:52 lr: 0.000459 loss: 3.2900 (3.2949) grad_norm: 1.4866 (1.5130) time: 0.5015 [2021-03-26 08:24:12 swin_small_patch4_window7_224] INFO: Epoch: [158] [1040/1251] eta: 0:01:47 lr: 0.000459 loss: 3.4160 (3.2945) grad_norm: 1.3858 (1.5122) time: 0.5019 [2021-03-26 08:24:17 swin_small_patch4_window7_224] INFO: Epoch: [158] [1050/1251] eta: 0:01:42 lr: 0.000459 loss: 3.0356 (3.2902) grad_norm: 1.4240 (1.5117) time: 0.5049 [2021-03-26 08:24:22 swin_small_patch4_window7_224] INFO: Epoch: [158] [1060/1251] eta: 0:01:37 lr: 0.000459 loss: 3.1059 (3.2915) grad_norm: 1.5188 (1.5119) time: 0.5032 [2021-03-26 08:24:27 swin_small_patch4_window7_224] INFO: Epoch: [158] [1070/1251] eta: 0:01:32 lr: 0.000459 loss: 3.4064 (3.2906) grad_norm: 1.4749 (nan) time: 0.5060 [2021-03-26 08:24:32 swin_small_patch4_window7_224] INFO: Epoch: [158] [1080/1251] eta: 0:01:27 lr: 0.000459 loss: 3.4008 (3.2914) grad_norm: 1.4497 (nan) time: 0.5058 [2021-03-26 08:24:37 swin_small_patch4_window7_224] INFO: Epoch: [158] [1090/1251] eta: 0:01:22 lr: 0.000459 loss: 3.3851 (3.2920) grad_norm: 1.5051 (nan) time: 0.5054 [2021-03-26 08:24:42 swin_small_patch4_window7_224] INFO: Epoch: [158] [1100/1251] eta: 0:01:16 lr: 0.000459 loss: 3.4232 (3.2938) grad_norm: 1.5790 (nan) time: 0.5053 [2021-03-26 08:24:47 swin_small_patch4_window7_224] INFO: Epoch: [158] [1110/1251] eta: 0:01:11 lr: 0.000459 loss: 3.5912 (3.2960) grad_norm: 1.5109 (nan) time: 0.5049 [2021-03-26 08:24:52 swin_small_patch4_window7_224] INFO: Epoch: [158] [1120/1251] eta: 0:01:06 lr: 0.000459 loss: 3.3873 (3.2965) grad_norm: 1.4872 (nan) time: 0.5032 [2021-03-26 08:24:57 swin_small_patch4_window7_224] INFO: Epoch: [158] [1130/1251] eta: 0:01:01 lr: 0.000459 loss: 3.2045 (3.2948) grad_norm: 1.4881 (nan) time: 0.5025 [2021-03-26 08:25:02 swin_small_patch4_window7_224] INFO: Epoch: [158] [1140/1251] eta: 0:00:56 lr: 0.000459 loss: 3.0239 (3.2905) grad_norm: 1.4420 (nan) time: 0.5034 [2021-03-26 08:25:08 swin_small_patch4_window7_224] INFO: Epoch: [158] [1150/1251] eta: 0:00:51 lr: 0.000459 loss: 3.0436 (3.2911) grad_norm: 1.4961 (nan) time: 0.5048 [2021-03-26 08:25:13 swin_small_patch4_window7_224] INFO: Epoch: [158] [1160/1251] eta: 0:00:46 lr: 0.000459 loss: 3.3243 (3.2907) grad_norm: 1.5998 (nan) time: 0.5053 [2021-03-26 08:25:18 swin_small_patch4_window7_224] INFO: Epoch: [158] [1170/1251] eta: 0:00:41 lr: 0.000459 loss: 3.2677 (3.2910) grad_norm: 1.5261 (nan) time: 0.5023 [2021-03-26 08:25:23 swin_small_patch4_window7_224] INFO: Epoch: [158] [1180/1251] eta: 0:00:36 lr: 0.000459 loss: 3.3400 (3.2915) grad_norm: 1.4720 (nan) time: 0.5144 [2021-03-26 08:25:28 swin_small_patch4_window7_224] INFO: Epoch: [158] [1190/1251] eta: 0:00:31 lr: 0.000459 loss: 3.1944 (3.2902) grad_norm: 1.5184 (nan) time: 0.5180 [2021-03-26 08:25:33 swin_small_patch4_window7_224] INFO: Epoch: [158] [1200/1251] eta: 0:00:25 lr: 0.000459 loss: 3.1984 (3.2918) grad_norm: 1.4704 (nan) time: 0.5047 [2021-03-26 08:25:38 swin_small_patch4_window7_224] INFO: Epoch: [158] [1210/1251] eta: 0:00:20 lr: 0.000459 loss: 3.4369 (3.2915) grad_norm: 1.4235 (nan) time: 0.4986 [2021-03-26 08:25:43 swin_small_patch4_window7_224] INFO: Epoch: [158] [1220/1251] eta: 0:00:15 lr: 0.000459 loss: 3.2166 (3.2898) grad_norm: 1.4606 (nan) time: 0.5011 [2021-03-26 08:25:48 swin_small_patch4_window7_224] INFO: Epoch: [158] [1230/1251] eta: 0:00:10 lr: 0.000459 loss: 3.2783 (3.2895) grad_norm: 1.5512 (nan) time: 0.5066 [2021-03-26 08:25:53 swin_small_patch4_window7_224] INFO: Epoch: [158] [1240/1251] eta: 0:00:05 lr: 0.000458 loss: 3.4658 (3.2889) grad_norm: 1.5096 (nan) time: 0.5042 [2021-03-26 08:25:58 swin_small_patch4_window7_224] INFO: Epoch: [158] [1250/1251] eta: 0:00:00 lr: 0.000458 loss: 3.2974 (3.2888) grad_norm: 1.5096 (nan) time: 0.5005 [2021-03-26 08:26:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 0.8487 (0.8487) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-26 08:26:10 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.9411 (0.9267) acc1: 76.5625 (77.6989) acc5: 93.7500 (95.0284) [2021-03-26 08:26:12 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9411 (0.9189) acc1: 78.1250 (77.6042) acc5: 95.3125 (95.5357) [2021-03-26 08:26:14 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.9417 (0.9436) acc1: 79.6875 (77.8730) acc5: 95.3125 (94.8589) [2021-03-26 08:26:16 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9761 (0.9436) acc1: 78.1250 (77.7439) acc5: 95.3125 (94.7409) [2021-03-26 08:26:17 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8010 (0.9238) acc1: 79.6875 (78.4320) acc5: 95.3125 (94.7520) [2021-03-26 08:26:26 swin_small_patch4_window7_224] INFO: * Acc@1 78.810 Acc@5 94.600 loss 0.904 [2021-03-26 08:26:26 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-26 08:26:26 swin_small_patch4_window7_224] INFO: Max accuracy: 78.81% [2021-03-26 08:26:29 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 0/1251] eta: 1:22:22 lr: 0.000458 loss: 3.6922 (3.6922) grad_norm: 1.4709 (1.4709) time: 3.9506 [2021-03-26 08:26:35 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 10/1251] eta: 0:17:20 lr: 0.000458 loss: 3.4048 (3.4156) grad_norm: 1.6090 (1.6147) time: 0.8382 [2021-03-26 08:26:40 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 20/1251] eta: 0:13:53 lr: 0.000458 loss: 3.4170 (3.4280) grad_norm: 1.5390 (1.5508) time: 0.5131 [2021-03-26 08:26:45 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 30/1251] eta: 0:12:41 lr: 0.000458 loss: 3.4170 (3.2886) grad_norm: 1.4497 (1.5189) time: 0.5057 [2021-03-26 08:26:50 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 40/1251] eta: 0:12:04 lr: 0.000458 loss: 3.1024 (3.2894) grad_norm: 1.5047 (1.5460) time: 0.5159 [2021-03-26 08:26:55 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 50/1251] eta: 0:11:35 lr: 0.000458 loss: 3.4185 (3.3239) grad_norm: 1.5047 (1.5310) time: 0.5102 [2021-03-26 08:27:00 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 60/1251] eta: 0:11:14 lr: 0.000458 loss: 3.4185 (3.3177) grad_norm: 1.4372 (1.5282) time: 0.5017 [2021-03-26 08:27:05 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 70/1251] eta: 0:10:59 lr: 0.000458 loss: 3.2775 (3.3109) grad_norm: 1.5492 (1.5376) time: 0.5047 [2021-03-26 08:27:10 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 80/1251] eta: 0:10:45 lr: 0.000458 loss: 3.1494 (3.2840) grad_norm: 1.5077 (1.5271) time: 0.5025 [2021-03-26 08:27:15 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 90/1251] eta: 0:10:34 lr: 0.000458 loss: 3.3026 (3.2736) grad_norm: 1.4776 (1.5322) time: 0.5068 [2021-03-26 08:27:20 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 100/1251] eta: 0:10:25 lr: 0.000458 loss: 3.2947 (3.2757) grad_norm: 1.4834 (1.5243) time: 0.5142 [2021-03-26 08:27:25 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 110/1251] eta: 0:10:16 lr: 0.000458 loss: 3.3271 (3.2878) grad_norm: 1.4854 (1.5270) time: 0.5084 [2021-03-26 08:27:30 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 120/1251] eta: 0:10:06 lr: 0.000458 loss: 3.3271 (3.2667) grad_norm: 1.4566 (1.5180) time: 0.4998 [2021-03-26 08:27:35 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 130/1251] eta: 0:09:58 lr: 0.000458 loss: 3.1412 (3.2550) grad_norm: 1.4391 (1.5176) time: 0.4989 [2021-03-26 08:27:40 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 140/1251] eta: 0:09:50 lr: 0.000458 loss: 3.1438 (3.2410) grad_norm: 1.4833 (1.5152) time: 0.5009 [2021-03-26 08:27:45 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 150/1251] eta: 0:09:42 lr: 0.000458 loss: 3.1860 (3.2362) grad_norm: 1.4716 (1.5161) time: 0.5013 [2021-03-26 08:27:51 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 160/1251] eta: 0:09:36 lr: 0.000458 loss: 3.4284 (3.2573) grad_norm: 1.5184 (1.5207) time: 0.5056 [2021-03-26 08:27:56 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 170/1251] eta: 0:09:29 lr: 0.000458 loss: 3.3143 (3.2441) grad_norm: 1.5273 (1.5189) time: 0.5100 [2021-03-26 08:28:01 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 180/1251] eta: 0:09:24 lr: 0.000458 loss: 3.1776 (3.2357) grad_norm: 1.4376 (1.5157) time: 0.5154 [2021-03-26 08:28:06 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 190/1251] eta: 0:09:18 lr: 0.000458 loss: 3.3635 (3.2419) grad_norm: 1.4376 (1.5165) time: 0.5179 [2021-03-26 08:28:11 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 200/1251] eta: 0:09:11 lr: 0.000458 loss: 3.3649 (3.2467) grad_norm: 1.5035 (1.5159) time: 0.5069 [2021-03-26 08:28:16 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 210/1251] eta: 0:09:05 lr: 0.000458 loss: 3.1450 (3.2279) grad_norm: 1.4890 (1.5142) time: 0.5043 [2021-03-26 08:28:21 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 220/1251] eta: 0:08:59 lr: 0.000458 loss: 3.2580 (3.2354) grad_norm: 1.4890 (1.5163) time: 0.5071 [2021-03-26 08:28:26 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 230/1251] eta: 0:08:53 lr: 0.000457 loss: 3.4823 (3.2429) grad_norm: 1.4913 (1.5178) time: 0.5038 [2021-03-26 08:28:31 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 240/1251] eta: 0:08:47 lr: 0.000457 loss: 3.3419 (3.2453) grad_norm: 1.4895 (1.5206) time: 0.5019 [2021-03-26 08:28:36 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 250/1251] eta: 0:08:41 lr: 0.000457 loss: 3.3230 (3.2469) grad_norm: 1.5151 (1.5188) time: 0.5010 [2021-03-26 08:28:41 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 260/1251] eta: 0:08:35 lr: 0.000457 loss: 3.0200 (3.2330) grad_norm: 1.4625 (1.5156) time: 0.5054 [2021-03-26 08:28:46 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 270/1251] eta: 0:08:29 lr: 0.000457 loss: 3.1866 (3.2406) grad_norm: 1.4398 (1.5142) time: 0.5006 [2021-03-26 08:28:51 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 280/1251] eta: 0:08:23 lr: 0.000457 loss: 3.4794 (3.2465) grad_norm: 1.4454 (1.5133) time: 0.4968 [2021-03-26 08:28:56 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 290/1251] eta: 0:08:18 lr: 0.000457 loss: 3.4544 (3.2532) grad_norm: 1.4010 (1.5102) time: 0.5082 [2021-03-26 08:29:01 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 300/1251] eta: 0:08:12 lr: 0.000457 loss: 3.5130 (3.2621) grad_norm: 1.4490 (1.5126) time: 0.5092 [2021-03-26 08:29:07 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 310/1251] eta: 0:08:07 lr: 0.000457 loss: 3.5536 (3.2695) grad_norm: 1.5546 (1.5134) time: 0.5048 [2021-03-26 08:29:12 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 320/1251] eta: 0:08:01 lr: 0.000457 loss: 3.4412 (3.2730) grad_norm: 1.5528 (1.5146) time: 0.5069 [2021-03-26 08:29:17 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 330/1251] eta: 0:07:55 lr: 0.000457 loss: 3.4144 (3.2790) grad_norm: 1.5693 (1.5149) time: 0.5050 [2021-03-26 08:29:22 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 340/1251] eta: 0:07:50 lr: 0.000457 loss: 3.2624 (3.2715) grad_norm: 1.4350 (1.5122) time: 0.5064 [2021-03-26 08:29:27 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 350/1251] eta: 0:07:45 lr: 0.000457 loss: 3.2367 (3.2724) grad_norm: 1.4264 (1.5103) time: 0.5075 [2021-03-26 08:29:32 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 360/1251] eta: 0:07:39 lr: 0.000457 loss: 3.3797 (3.2661) grad_norm: 1.4754 (1.5106) time: 0.4992 [2021-03-26 08:29:37 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 370/1251] eta: 0:07:34 lr: 0.000457 loss: 2.9093 (3.2528) grad_norm: 1.4794 (1.5096) time: 0.5024 [2021-03-26 08:29:42 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 380/1251] eta: 0:07:28 lr: 0.000457 loss: 2.9093 (3.2526) grad_norm: 1.4137 (1.5067) time: 0.5047 [2021-03-26 08:29:47 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 390/1251] eta: 0:07:23 lr: 0.000457 loss: 3.4300 (3.2521) grad_norm: 1.4137 (1.5051) time: 0.5017 [2021-03-26 08:29:52 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 400/1251] eta: 0:07:17 lr: 0.000457 loss: 3.3466 (3.2518) grad_norm: 1.4471 (1.5040) time: 0.5078 [2021-03-26 08:29:57 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 410/1251] eta: 0:07:12 lr: 0.000457 loss: 3.2152 (3.2496) grad_norm: 1.3966 (1.5013) time: 0.5056 [2021-03-26 08:30:02 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 420/1251] eta: 0:07:07 lr: 0.000457 loss: 3.2835 (3.2541) grad_norm: 1.4443 (1.5016) time: 0.5026 [2021-03-26 08:30:07 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 430/1251] eta: 0:07:01 lr: 0.000457 loss: 3.1455 (3.2450) grad_norm: 1.4625 (1.5023) time: 0.5048 [2021-03-26 08:30:12 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 440/1251] eta: 0:06:56 lr: 0.000457 loss: 3.0099 (3.2424) grad_norm: 1.4587 (1.5019) time: 0.5026 [2021-03-26 08:30:17 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 450/1251] eta: 0:06:51 lr: 0.000457 loss: 3.1816 (3.2422) grad_norm: 1.4036 (1.5024) time: 0.5066 [2021-03-26 08:30:22 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 460/1251] eta: 0:06:46 lr: 0.000457 loss: 3.2278 (3.2425) grad_norm: 1.4919 (1.5028) time: 0.5092 [2021-03-26 08:30:27 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 470/1251] eta: 0:06:40 lr: 0.000456 loss: 3.1403 (3.2400) grad_norm: 1.5375 (1.5051) time: 0.5052 [2021-03-26 08:30:32 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 480/1251] eta: 0:06:35 lr: 0.000456 loss: 2.9501 (3.2371) grad_norm: 1.5375 (1.5094) time: 0.5062 [2021-03-26 08:30:37 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 490/1251] eta: 0:06:30 lr: 0.000456 loss: 3.2723 (3.2401) grad_norm: 1.5633 (1.5114) time: 0.5018 [2021-03-26 08:30:42 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 500/1251] eta: 0:06:25 lr: 0.000456 loss: 3.1943 (3.2325) grad_norm: 1.5397 (1.5110) time: 0.5031 [2021-03-26 08:30:47 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 510/1251] eta: 0:06:19 lr: 0.000456 loss: 2.8748 (3.2302) grad_norm: 1.4620 (1.5107) time: 0.5045 [2021-03-26 08:30:52 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 520/1251] eta: 0:06:14 lr: 0.000456 loss: 3.1127 (3.2269) grad_norm: 1.4939 (1.5107) time: 0.4989 [2021-03-26 08:30:57 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 530/1251] eta: 0:06:09 lr: 0.000456 loss: 3.1596 (3.2312) grad_norm: 1.4994 (1.5094) time: 0.4990 [2021-03-26 08:31:02 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 540/1251] eta: 0:06:03 lr: 0.000456 loss: 3.4588 (3.2366) grad_norm: 1.4782 (1.5103) time: 0.5006 [2021-03-26 08:31:08 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 550/1251] eta: 0:05:58 lr: 0.000456 loss: 3.5031 (3.2359) grad_norm: 1.5230 (1.5125) time: 0.5128 [2021-03-26 08:31:13 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 560/1251] eta: 0:05:54 lr: 0.000456 loss: 3.0799 (3.2310) grad_norm: 1.5261 (1.5124) time: 0.5296 [2021-03-26 08:31:18 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 570/1251] eta: 0:05:48 lr: 0.000456 loss: 3.0840 (3.2336) grad_norm: 1.5134 (1.5129) time: 0.5157 [2021-03-26 08:31:23 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 580/1251] eta: 0:05:43 lr: 0.000456 loss: 3.3130 (3.2325) grad_norm: 1.4770 (1.5120) time: 0.5007 [2021-03-26 08:31:28 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 590/1251] eta: 0:05:38 lr: 0.000456 loss: 3.3450 (3.2340) grad_norm: 1.4378 (1.5123) time: 0.5132 [2021-03-26 08:31:33 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 600/1251] eta: 0:05:33 lr: 0.000456 loss: 3.4142 (3.2342) grad_norm: 1.4739 (1.5118) time: 0.5102 [2021-03-26 08:31:38 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 610/1251] eta: 0:05:27 lr: 0.000456 loss: 3.0441 (3.2335) grad_norm: 1.4695 (1.5107) time: 0.4946 [2021-03-26 08:31:43 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 620/1251] eta: 0:05:22 lr: 0.000456 loss: 3.2065 (3.2335) grad_norm: 1.5038 (1.5115) time: 0.4955 [2021-03-26 08:31:48 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 630/1251] eta: 0:05:17 lr: 0.000456 loss: 3.2886 (3.2345) grad_norm: 1.5038 (1.5104) time: 0.5005 [2021-03-26 08:31:53 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 640/1251] eta: 0:05:12 lr: 0.000456 loss: 3.2886 (3.2346) grad_norm: 1.4898 (1.5118) time: 0.4998 [2021-03-26 08:31:58 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 650/1251] eta: 0:05:07 lr: 0.000456 loss: 3.4731 (3.2386) grad_norm: 1.6063 (1.5135) time: 0.5104 [2021-03-26 08:32:04 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 660/1251] eta: 0:05:02 lr: 0.000456 loss: 3.3401 (3.2329) grad_norm: 1.5760 (1.5131) time: 0.5166 [2021-03-26 08:32:08 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 670/1251] eta: 0:04:56 lr: 0.000456 loss: 3.0142 (3.2344) grad_norm: 1.5650 (1.5143) time: 0.5035 [2021-03-26 08:32:13 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 680/1251] eta: 0:04:51 lr: 0.000456 loss: 3.3473 (3.2373) grad_norm: 1.5888 (1.5156) time: 0.4982 [2021-03-26 08:32:19 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 690/1251] eta: 0:04:46 lr: 0.000456 loss: 3.3078 (3.2358) grad_norm: 1.5720 (1.5162) time: 0.5021 [2021-03-26 08:32:23 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 700/1251] eta: 0:04:41 lr: 0.000456 loss: 3.3299 (3.2403) grad_norm: 1.4792 (1.5163) time: 0.4978 [2021-03-26 08:32:29 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 710/1251] eta: 0:04:36 lr: 0.000455 loss: 3.4850 (3.2430) grad_norm: 1.4792 (1.5169) time: 0.4994 [2021-03-26 08:32:33 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 720/1251] eta: 0:04:30 lr: 0.000455 loss: 3.4479 (3.2419) grad_norm: 1.5558 (1.5185) time: 0.5020 [2021-03-26 08:32:39 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 730/1251] eta: 0:04:25 lr: 0.000455 loss: 3.2591 (3.2420) grad_norm: 1.5558 (1.5188) time: 0.5087 [2021-03-26 08:32:44 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 740/1251] eta: 0:04:20 lr: 0.000455 loss: 3.2702 (3.2451) grad_norm: 1.4647 (1.5176) time: 0.5281 [2021-03-26 08:32:49 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 750/1251] eta: 0:04:15 lr: 0.000455 loss: 3.4902 (3.2489) grad_norm: 1.4046 (1.5164) time: 0.5235 [2021-03-26 08:32:54 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 760/1251] eta: 0:04:10 lr: 0.000455 loss: 3.4885 (3.2491) grad_norm: 1.4652 (1.5159) time: 0.5105 [2021-03-26 08:32:59 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 770/1251] eta: 0:04:05 lr: 0.000455 loss: 3.3093 (3.2487) grad_norm: 1.4954 (1.5174) time: 0.5159 [2021-03-26 08:33:05 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 780/1251] eta: 0:04:00 lr: 0.000455 loss: 3.4602 (3.2508) grad_norm: 1.5640 (1.5176) time: 0.5142 [2021-03-26 08:33:10 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 790/1251] eta: 0:03:55 lr: 0.000455 loss: 3.3359 (3.2483) grad_norm: 1.4217 (1.5180) time: 0.5110 [2021-03-26 08:33:15 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 800/1251] eta: 0:03:50 lr: 0.000455 loss: 3.2644 (3.2494) grad_norm: 1.5450 (1.5192) time: 0.5137 [2021-03-26 08:33:20 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 810/1251] eta: 0:03:45 lr: 0.000455 loss: 3.5887 (3.2518) grad_norm: 1.5470 (1.5190) time: 0.5098 [2021-03-26 08:33:25 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 820/1251] eta: 0:03:40 lr: 0.000455 loss: 3.3621 (3.2475) grad_norm: 1.4574 (1.5175) time: 0.5094 [2021-03-26 08:33:30 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 830/1251] eta: 0:03:35 lr: 0.000455 loss: 3.0867 (3.2481) grad_norm: 1.4460 (1.5171) time: 0.5072 [2021-03-26 08:33:35 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 840/1251] eta: 0:03:29 lr: 0.000455 loss: 3.3920 (3.2490) grad_norm: 1.4443 (1.5157) time: 0.5131 [2021-03-26 08:33:40 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 850/1251] eta: 0:03:24 lr: 0.000455 loss: 3.2913 (3.2472) grad_norm: 1.4038 (1.5151) time: 0.5149 [2021-03-26 08:33:45 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 860/1251] eta: 0:03:19 lr: 0.000455 loss: 3.3131 (3.2488) grad_norm: 1.5083 (1.5158) time: 0.5068 [2021-03-26 08:33:51 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 870/1251] eta: 0:03:14 lr: 0.000455 loss: 3.4525 (3.2489) grad_norm: 1.6313 (1.5173) time: 0.5094 [2021-03-26 08:33:56 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 880/1251] eta: 0:03:09 lr: 0.000455 loss: 3.4525 (3.2508) grad_norm: 1.6278 (1.5180) time: 0.5083 [2021-03-26 08:34:01 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 890/1251] eta: 0:03:04 lr: 0.000455 loss: 3.4578 (3.2524) grad_norm: 1.4321 (1.5172) time: 0.5047 [2021-03-26 08:34:06 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 900/1251] eta: 0:02:59 lr: 0.000455 loss: 3.3293 (3.2545) grad_norm: 1.4141 (1.5162) time: 0.5047 [2021-03-26 08:34:11 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 910/1251] eta: 0:02:54 lr: 0.000455 loss: 3.3293 (3.2557) grad_norm: 1.4377 (1.5162) time: 0.5061 [2021-03-26 08:34:16 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 920/1251] eta: 0:02:48 lr: 0.000455 loss: 3.2301 (3.2553) grad_norm: 1.4603 (1.5177) time: 0.5090 [2021-03-26 08:34:21 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 930/1251] eta: 0:02:43 lr: 0.000455 loss: 3.3167 (3.2559) grad_norm: 1.5807 (1.5181) time: 0.5097 [2021-03-26 08:34:26 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 940/1251] eta: 0:02:38 lr: 0.000455 loss: 3.3167 (3.2547) grad_norm: 1.5185 (1.5179) time: 0.5116 [2021-03-26 08:34:31 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 950/1251] eta: 0:02:33 lr: 0.000454 loss: 3.1480 (3.2532) grad_norm: 1.4787 (1.5174) time: 0.5060 [2021-03-26 08:34:36 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 960/1251] eta: 0:02:28 lr: 0.000454 loss: 3.3183 (3.2556) grad_norm: 1.4796 (1.5171) time: 0.4985 [2021-03-26 08:34:41 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 970/1251] eta: 0:02:23 lr: 0.000454 loss: 3.5759 (3.2579) grad_norm: 1.3871 (1.5157) time: 0.5020 [2021-03-26 08:34:46 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 980/1251] eta: 0:02:18 lr: 0.000454 loss: 3.4391 (3.2572) grad_norm: 1.3800 (1.5153) time: 0.5032 [2021-03-26 08:34:51 swin_small_patch4_window7_224] INFO: Epoch: [159] [ 990/1251] eta: 0:02:13 lr: 0.000454 loss: 3.3821 (3.2580) grad_norm: 1.4301 (1.5149) time: 0.5022 [2021-03-26 08:34:56 swin_small_patch4_window7_224] INFO: Epoch: [159] [1000/1251] eta: 0:02:08 lr: 0.000454 loss: 3.3821 (3.2581) grad_norm: 1.4194 (1.5144) time: 0.5046 [2021-03-26 08:35:01 swin_small_patch4_window7_224] INFO: Epoch: [159] [1010/1251] eta: 0:02:02 lr: 0.000454 loss: 3.2157 (3.2571) grad_norm: 1.4958 (1.5150) time: 0.5030 [2021-03-26 08:35:06 swin_small_patch4_window7_224] INFO: Epoch: [159] [1020/1251] eta: 0:01:57 lr: 0.000454 loss: 3.2885 (3.2568) grad_norm: 1.5429 (1.5152) time: 0.4988 [2021-03-26 08:35:11 swin_small_patch4_window7_224] INFO: Epoch: [159] [1030/1251] eta: 0:01:52 lr: 0.000454 loss: 3.3634 (3.2573) grad_norm: 1.4649 (1.5151) time: 0.4957 [2021-03-26 08:35:16 swin_small_patch4_window7_224] INFO: Epoch: [159] [1040/1251] eta: 0:01:47 lr: 0.000454 loss: 3.5037 (3.2571) grad_norm: 1.4042 (1.5146) time: 0.4995 [2021-03-26 08:35:21 swin_small_patch4_window7_224] INFO: Epoch: [159] [1050/1251] eta: 0:01:42 lr: 0.000454 loss: 3.1633 (3.2556) grad_norm: 1.4042 (1.5135) time: 0.5082 [2021-03-26 08:35:26 swin_small_patch4_window7_224] INFO: Epoch: [159] [1060/1251] eta: 0:01:37 lr: 0.000454 loss: 3.2529 (3.2562) grad_norm: 1.4280 (1.5133) time: 0.5018 [2021-03-26 08:35:31 swin_small_patch4_window7_224] INFO: Epoch: [159] [1070/1251] eta: 0:01:32 lr: 0.000454 loss: 3.4824 (3.2569) grad_norm: 1.4527 (1.5126) time: 0.4988 [2021-03-26 08:35:36 swin_small_patch4_window7_224] INFO: Epoch: [159] [1080/1251] eta: 0:01:27 lr: 0.000454 loss: 3.5924 (3.2609) grad_norm: 1.4438 (1.5120) time: 0.5011 [2021-03-26 08:35:41 swin_small_patch4_window7_224] INFO: Epoch: [159] [1090/1251] eta: 0:01:21 lr: 0.000454 loss: 3.5420 (3.2614) grad_norm: 1.4579 (1.5119) time: 0.5001 [2021-03-26 08:35:46 swin_small_patch4_window7_224] INFO: Epoch: [159] [1100/1251] eta: 0:01:16 lr: 0.000454 loss: 3.2108 (3.2614) grad_norm: 1.4378 (1.5110) time: 0.4964 [2021-03-26 08:35:51 swin_small_patch4_window7_224] INFO: Epoch: [159] [1110/1251] eta: 0:01:11 lr: 0.000454 loss: 3.3176 (3.2611) grad_norm: 1.4378 (1.5111) time: 0.5048 [2021-03-26 08:35:56 swin_small_patch4_window7_224] INFO: Epoch: [159] [1120/1251] eta: 0:01:06 lr: 0.000454 loss: 3.3163 (3.2611) grad_norm: 1.5424 (1.5113) time: 0.5115 [2021-03-26 08:36:02 swin_small_patch4_window7_224] INFO: Epoch: [159] [1130/1251] eta: 0:01:01 lr: 0.000454 loss: 3.3163 (3.2616) grad_norm: 1.4879 (1.5110) time: 0.5077 [2021-03-26 08:36:07 swin_small_patch4_window7_224] INFO: Epoch: [159] [1140/1251] eta: 0:00:56 lr: 0.000454 loss: 3.5021 (3.2610) grad_norm: 1.5122 (1.5110) time: 0.5073 [2021-03-26 08:36:12 swin_small_patch4_window7_224] INFO: Epoch: [159] [1150/1251] eta: 0:00:51 lr: 0.000454 loss: 3.3138 (3.2606) grad_norm: 1.4930 (1.5105) time: 0.5047 [2021-03-26 08:36:17 swin_small_patch4_window7_224] INFO: Epoch: [159] [1160/1251] eta: 0:00:46 lr: 0.000454 loss: 3.4524 (3.2611) grad_norm: 1.4930 (1.5113) time: 0.5054 [2021-03-26 08:36:22 swin_small_patch4_window7_224] INFO: Epoch: [159] [1170/1251] eta: 0:00:41 lr: 0.000454 loss: 3.4179 (3.2617) grad_norm: 1.5770 (1.5119) time: 0.5011 [2021-03-26 08:36:27 swin_small_patch4_window7_224] INFO: Epoch: [159] [1180/1251] eta: 0:00:36 lr: 0.000454 loss: 3.3282 (3.2613) grad_norm: 1.6335 (1.5126) time: 0.4970 [2021-03-26 08:36:32 swin_small_patch4_window7_224] INFO: Epoch: [159] [1190/1251] eta: 0:00:31 lr: 0.000454 loss: 3.2001 (3.2602) grad_norm: 1.6218 (1.5137) time: 0.5033 [2021-03-26 08:36:37 swin_small_patch4_window7_224] INFO: Epoch: [159] [1200/1251] eta: 0:00:25 lr: 0.000453 loss: 3.1802 (3.2602) grad_norm: 1.6001 (1.5135) time: 0.5060 [2021-03-26 08:36:42 swin_small_patch4_window7_224] INFO: Epoch: [159] [1210/1251] eta: 0:00:20 lr: 0.000453 loss: 3.1737 (3.2591) grad_norm: 1.5155 (1.5144) time: 0.5001 [2021-03-26 08:36:47 swin_small_patch4_window7_224] INFO: Epoch: [159] [1220/1251] eta: 0:00:15 lr: 0.000453 loss: 3.4360 (3.2608) grad_norm: 1.5765 (1.5153) time: 0.5037 [2021-03-26 08:36:52 swin_small_patch4_window7_224] INFO: Epoch: [159] [1230/1251] eta: 0:00:10 lr: 0.000453 loss: 3.4360 (3.2603) grad_norm: 1.4994 (1.5156) time: 0.5073 [2021-03-26 08:36:57 swin_small_patch4_window7_224] INFO: Epoch: [159] [1240/1251] eta: 0:00:05 lr: 0.000453 loss: 3.4676 (3.2612) grad_norm: 1.4556 (1.5153) time: 0.4991 [2021-03-26 08:37:02 swin_small_patch4_window7_224] INFO: Epoch: [159] [1250/1251] eta: 0:00:00 lr: 0.000453 loss: 3.4445 (3.2607) grad_norm: 1.4755 (1.5154) time: 0.4976 [2021-03-26 08:37:13 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:03:36 loss: 1.0709 (1.0709) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-26 08:37:15 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:24 loss: 0.8804 (0.8917) acc1: 78.1250 (77.5568) acc5: 95.3125 (95.1705) [2021-03-26 08:37:17 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.9023 (0.9250) acc1: 76.5625 (77.0089) acc5: 95.3125 (94.6429) [2021-03-26 08:37:19 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8869 (0.9000) acc1: 76.5625 (77.4194) acc5: 95.3125 (95.0101) [2021-03-26 08:37:20 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8869 (0.8917) acc1: 76.5625 (78.0488) acc5: 95.3125 (95.1220) [2021-03-26 08:37:21 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8869 (0.8908) acc1: 79.6875 (78.3040) acc5: 95.3125 (95.1360) [2021-03-26 08:37:29 swin_small_patch4_window7_224] INFO: * Acc@1 78.772 Acc@5 94.680 loss 0.885 [2021-03-26 08:37:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-26 08:37:29 swin_small_patch4_window7_224] INFO: Max accuracy: 78.81% [2021-03-26 08:37:33 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 0/1251] eta: 1:25:53 lr: 0.000453 loss: 3.5207 (3.5207) grad_norm: 1.5829 (1.5829) time: 4.1194 [2021-03-26 08:37:39 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 10/1251] eta: 0:17:48 lr: 0.000453 loss: 3.2084 (3.0762) grad_norm: 1.5206 (1.5168) time: 0.8612 [2021-03-26 08:37:44 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 20/1251] eta: 0:14:05 lr: 0.000453 loss: 3.3060 (3.2433) grad_norm: 1.5139 (1.5228) time: 0.5148 [2021-03-26 08:37:49 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 30/1251] eta: 0:12:46 lr: 0.000453 loss: 3.3482 (3.2624) grad_norm: 1.5048 (1.5282) time: 0.4997 [2021-03-26 08:37:54 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 40/1251] eta: 0:12:07 lr: 0.000453 loss: 3.3242 (3.2983) grad_norm: 1.4809 (1.5240) time: 0.5099 [2021-03-26 08:37:59 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 50/1251] eta: 0:11:37 lr: 0.000453 loss: 3.3325 (3.2924) grad_norm: 1.4617 (1.5079) time: 0.5080 [2021-03-26 08:38:04 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 60/1251] eta: 0:11:17 lr: 0.000453 loss: 3.3540 (3.3398) grad_norm: 1.4312 (1.4956) time: 0.5035 [2021-03-26 08:38:09 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 70/1251] eta: 0:10:59 lr: 0.000453 loss: 3.3204 (3.2806) grad_norm: 1.4656 (1.5020) time: 0.5008 [2021-03-26 08:38:14 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 80/1251] eta: 0:10:45 lr: 0.000453 loss: 2.9077 (3.2666) grad_norm: 1.5096 (1.5020) time: 0.4967 [2021-03-26 08:38:19 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 90/1251] eta: 0:10:33 lr: 0.000453 loss: 3.0515 (3.2517) grad_norm: 1.5367 (1.5075) time: 0.5021 [2021-03-26 08:38:24 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 100/1251] eta: 0:10:24 lr: 0.000453 loss: 3.1737 (3.2614) grad_norm: 1.5290 (1.5102) time: 0.5072 [2021-03-26 08:38:29 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 110/1251] eta: 0:10:15 lr: 0.000453 loss: 3.2240 (3.2536) grad_norm: 1.5290 (1.5189) time: 0.5117 [2021-03-26 08:38:34 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 120/1251] eta: 0:10:07 lr: 0.000453 loss: 3.2142 (3.2430) grad_norm: 1.5325 (1.5188) time: 0.5111 [2021-03-26 08:38:39 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 130/1251] eta: 0:10:00 lr: 0.000453 loss: 3.1441 (3.2422) grad_norm: 1.4917 (1.5137) time: 0.5153 [2021-03-26 08:38:44 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 140/1251] eta: 0:09:52 lr: 0.000453 loss: 3.1441 (3.2244) grad_norm: 1.4210 (1.5173) time: 0.5114 [2021-03-26 08:38:49 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 150/1251] eta: 0:09:45 lr: 0.000453 loss: 3.2003 (3.2296) grad_norm: 1.4835 (1.5216) time: 0.5006 [2021-03-26 08:38:54 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 160/1251] eta: 0:09:37 lr: 0.000453 loss: 3.3679 (3.2221) grad_norm: 1.5721 (1.5285) time: 0.5016 [2021-03-26 08:39:00 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 170/1251] eta: 0:09:30 lr: 0.000453 loss: 3.4730 (3.2437) grad_norm: 1.5683 (1.5322) time: 0.5037 [2021-03-26 08:39:05 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 180/1251] eta: 0:09:23 lr: 0.000453 loss: 3.6620 (3.2524) grad_norm: 1.5443 (1.5363) time: 0.5008 [2021-03-26 08:39:10 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 190/1251] eta: 0:09:17 lr: 0.000452 loss: 3.6291 (3.2622) grad_norm: 1.5533 (1.5385) time: 0.5006 [2021-03-26 08:39:15 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 200/1251] eta: 0:09:11 lr: 0.000452 loss: 3.3129 (3.2461) grad_norm: 1.5561 (1.5386) time: 0.5113 [2021-03-26 08:39:20 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 210/1251] eta: 0:09:05 lr: 0.000452 loss: 3.3129 (3.2522) grad_norm: 1.4544 (1.5338) time: 0.5097 [2021-03-26 08:39:25 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 220/1251] eta: 0:08:59 lr: 0.000452 loss: 3.3997 (3.2596) grad_norm: 1.4505 (1.5293) time: 0.5067 [2021-03-26 08:39:30 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 230/1251] eta: 0:08:52 lr: 0.000452 loss: 3.4016 (3.2640) grad_norm: 1.5130 (1.5397) time: 0.5036 [2021-03-26 08:39:35 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 240/1251] eta: 0:08:46 lr: 0.000452 loss: 3.4016 (3.2598) grad_norm: 1.5777 (1.5374) time: 0.4966 [2021-03-26 08:39:40 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 250/1251] eta: 0:08:41 lr: 0.000452 loss: 3.2449 (3.2568) grad_norm: 1.4351 (1.5325) time: 0.5037 [2021-03-26 08:39:45 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 260/1251] eta: 0:08:35 lr: 0.000452 loss: 3.0086 (3.2426) grad_norm: 1.3761 (1.5251) time: 0.5050 [2021-03-26 08:39:50 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 270/1251] eta: 0:08:29 lr: 0.000452 loss: 2.9563 (3.2334) grad_norm: 1.3941 (1.5218) time: 0.4995 [2021-03-26 08:39:55 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 280/1251] eta: 0:08:23 lr: 0.000452 loss: 3.1333 (3.2384) grad_norm: 1.4451 (1.5196) time: 0.4997 [2021-03-26 08:40:00 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 290/1251] eta: 0:08:17 lr: 0.000452 loss: 3.3269 (3.2362) grad_norm: 1.4997 (1.5208) time: 0.5015 [2021-03-26 08:40:05 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 300/1251] eta: 0:08:12 lr: 0.000452 loss: 3.0984 (3.2320) grad_norm: 1.5094 (1.5200) time: 0.5075 [2021-03-26 08:40:10 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 310/1251] eta: 0:08:06 lr: 0.000452 loss: 3.0897 (3.2294) grad_norm: 1.4424 (1.5192) time: 0.5034 [2021-03-26 08:40:15 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 320/1251] eta: 0:08:01 lr: 0.000452 loss: 3.3411 (3.2365) grad_norm: 1.4801 (1.5188) time: 0.5028 [2021-03-26 08:40:20 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 330/1251] eta: 0:07:55 lr: 0.000452 loss: 3.4100 (3.2365) grad_norm: 1.5137 (1.5185) time: 0.5064 [2021-03-26 08:40:25 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 340/1251] eta: 0:07:49 lr: 0.000452 loss: 3.4100 (3.2355) grad_norm: 1.4950 (1.5185) time: 0.4965 [2021-03-26 08:40:30 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 350/1251] eta: 0:07:44 lr: 0.000452 loss: 3.2854 (3.2342) grad_norm: 1.5868 (1.5223) time: 0.5001 [2021-03-26 08:40:35 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 360/1251] eta: 0:07:38 lr: 0.000452 loss: 3.2362 (3.2337) grad_norm: 1.6390 (1.5238) time: 0.5092 [2021-03-26 08:40:40 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 370/1251] eta: 0:07:33 lr: 0.000452 loss: 3.2022 (3.2285) grad_norm: 1.4906 (1.5240) time: 0.5071 [2021-03-26 08:40:45 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 380/1251] eta: 0:07:28 lr: 0.000452 loss: 3.2022 (3.2285) grad_norm: 1.4098 (1.5221) time: 0.5032 [2021-03-26 08:40:50 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 390/1251] eta: 0:07:22 lr: 0.000452 loss: 3.5509 (3.2319) grad_norm: 1.4925 (1.5233) time: 0.4987 [2021-03-26 08:40:55 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 400/1251] eta: 0:07:17 lr: 0.000452 loss: 3.3422 (3.2285) grad_norm: 1.5303 (1.5221) time: 0.4953 [2021-03-26 08:41:00 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 410/1251] eta: 0:07:11 lr: 0.000452 loss: 3.3422 (3.2305) grad_norm: 1.4589 (1.5207) time: 0.4970 [2021-03-26 08:41:05 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 420/1251] eta: 0:07:06 lr: 0.000452 loss: 3.5900 (3.2329) grad_norm: 1.4653 (1.5203) time: 0.5008 [2021-03-26 08:41:10 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 430/1251] eta: 0:07:00 lr: 0.000451 loss: 3.4955 (3.2372) grad_norm: 1.4653 (nan) time: 0.5023 [2021-03-26 08:41:15 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 440/1251] eta: 0:06:55 lr: 0.000451 loss: 3.3998 (3.2383) grad_norm: 1.4247 (nan) time: 0.5024 [2021-03-26 08:41:20 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 450/1251] eta: 0:06:50 lr: 0.000451 loss: 3.0003 (3.2297) grad_norm: 1.5132 (nan) time: 0.5025 [2021-03-26 08:41:25 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 460/1251] eta: 0:06:45 lr: 0.000451 loss: 2.8459 (3.2273) grad_norm: 1.4904 (nan) time: 0.5042 [2021-03-26 08:41:30 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 470/1251] eta: 0:06:39 lr: 0.000451 loss: 2.9874 (3.2230) grad_norm: 1.4791 (nan) time: 0.5028 [2021-03-26 08:41:35 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 480/1251] eta: 0:06:34 lr: 0.000451 loss: 3.2429 (3.2246) grad_norm: 1.4791 (nan) time: 0.5017 [2021-03-26 08:41:41 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 490/1251] eta: 0:06:29 lr: 0.000451 loss: 3.3197 (3.2228) grad_norm: 1.4783 (nan) time: 0.5083 [2021-03-26 08:41:46 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 500/1251] eta: 0:06:24 lr: 0.000451 loss: 3.1973 (3.2196) grad_norm: 1.4992 (nan) time: 0.5093 [2021-03-26 08:41:51 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 510/1251] eta: 0:06:18 lr: 0.000451 loss: 3.3244 (3.2234) grad_norm: 1.5832 (nan) time: 0.5027 [2021-03-26 08:41:56 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 520/1251] eta: 0:06:13 lr: 0.000451 loss: 3.3534 (3.2235) grad_norm: 1.5471 (nan) time: 0.5018 [2021-03-26 08:42:01 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 530/1251] eta: 0:06:08 lr: 0.000451 loss: 3.2103 (3.2241) grad_norm: 1.5146 (nan) time: 0.5042 [2021-03-26 08:42:06 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 540/1251] eta: 0:06:03 lr: 0.000451 loss: 3.3680 (3.2248) grad_norm: 1.5364 (nan) time: 0.5090 [2021-03-26 08:42:11 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 550/1251] eta: 0:05:58 lr: 0.000451 loss: 3.2299 (3.2209) grad_norm: 1.5285 (nan) time: 0.5227 [2021-03-26 08:42:16 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 560/1251] eta: 0:05:53 lr: 0.000451 loss: 3.2299 (3.2254) grad_norm: 1.4869 (nan) time: 0.5210 [2021-03-26 08:42:21 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 570/1251] eta: 0:05:48 lr: 0.000451 loss: 3.1160 (3.2194) grad_norm: 1.5519 (nan) time: 0.5135 [2021-03-26 08:42:27 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 580/1251] eta: 0:05:43 lr: 0.000451 loss: 2.9865 (3.2223) grad_norm: 1.5629 (nan) time: 0.5139 [2021-03-26 08:42:32 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 590/1251] eta: 0:05:38 lr: 0.000451 loss: 3.4244 (3.2261) grad_norm: 1.5722 (nan) time: 0.5202 [2021-03-26 08:42:37 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 600/1251] eta: 0:05:33 lr: 0.000451 loss: 3.2993 (3.2285) grad_norm: 1.5509 (nan) time: 0.5140 [2021-03-26 08:42:42 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 610/1251] eta: 0:05:27 lr: 0.000451 loss: 3.2558 (3.2266) grad_norm: 1.5043 (nan) time: 0.4984 [2021-03-26 08:42:47 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 620/1251] eta: 0:05:22 lr: 0.000451 loss: 3.1782 (3.2270) grad_norm: 1.5082 (nan) time: 0.5063 [2021-03-26 08:42:52 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 630/1251] eta: 0:05:17 lr: 0.000451 loss: 3.1782 (3.2252) grad_norm: 1.5067 (nan) time: 0.5127 [2021-03-26 08:42:57 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 640/1251] eta: 0:05:12 lr: 0.000451 loss: 3.2875 (3.2251) grad_norm: 1.5600 (nan) time: 0.5099 [2021-03-26 08:43:02 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 650/1251] eta: 0:05:07 lr: 0.000451 loss: 3.4289 (3.2287) grad_norm: 1.5153 (nan) time: 0.5051 [2021-03-26 08:43:07 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 660/1251] eta: 0:05:02 lr: 0.000451 loss: 3.3990 (3.2254) grad_norm: 1.4937 (nan) time: 0.5043 [2021-03-26 08:43:12 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 670/1251] eta: 0:04:56 lr: 0.000450 loss: 3.3326 (3.2282) grad_norm: 1.5032 (nan) time: 0.5043 [2021-03-26 08:43:17 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 680/1251] eta: 0:04:51 lr: 0.000450 loss: 3.4807 (3.2294) grad_norm: 1.5032 (nan) time: 0.5059 [2021-03-26 08:43:22 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 690/1251] eta: 0:04:46 lr: 0.000450 loss: 3.0894 (3.2255) grad_norm: 1.5223 (nan) time: 0.5080 [2021-03-26 08:43:27 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 700/1251] eta: 0:04:41 lr: 0.000450 loss: 3.1452 (3.2248) grad_norm: 1.5238 (nan) time: 0.5048 [2021-03-26 08:43:32 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 710/1251] eta: 0:04:36 lr: 0.000450 loss: 3.2171 (3.2209) grad_norm: 1.4941 (nan) time: 0.5011 [2021-03-26 08:43:38 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 720/1251] eta: 0:04:31 lr: 0.000450 loss: 3.3022 (3.2220) grad_norm: 1.4941 (nan) time: 0.5020 [2021-03-26 08:43:43 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 730/1251] eta: 0:04:26 lr: 0.000450 loss: 3.3220 (3.2213) grad_norm: 1.4216 (nan) time: 0.5112 [2021-03-26 08:43:48 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 740/1251] eta: 0:04:21 lr: 0.000450 loss: 3.2865 (3.2204) grad_norm: 1.3965 (nan) time: 0.5308 [2021-03-26 08:43:53 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 750/1251] eta: 0:04:16 lr: 0.000450 loss: 3.2152 (3.2205) grad_norm: 1.4285 (nan) time: 0.5325 [2021-03-26 08:43:59 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 760/1251] eta: 0:04:11 lr: 0.000450 loss: 3.3323 (3.2232) grad_norm: 1.4482 (nan) time: 0.5226 [2021-03-26 08:44:04 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 770/1251] eta: 0:04:05 lr: 0.000450 loss: 3.4371 (3.2244) grad_norm: 1.4521 (nan) time: 0.5154 [2021-03-26 08:44:09 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 780/1251] eta: 0:04:00 lr: 0.000450 loss: 3.2651 (3.2248) grad_norm: 1.4854 (nan) time: 0.5005 [2021-03-26 08:44:14 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 790/1251] eta: 0:03:55 lr: 0.000450 loss: 2.9637 (3.2214) grad_norm: 1.4760 (nan) time: 0.5024 [2021-03-26 08:44:19 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 800/1251] eta: 0:03:50 lr: 0.000450 loss: 3.2176 (3.2207) grad_norm: 1.5103 (nan) time: 0.5059 [2021-03-26 08:44:24 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 810/1251] eta: 0:03:45 lr: 0.000450 loss: 3.0475 (3.2186) grad_norm: 1.5081 (nan) time: 0.5015 [2021-03-26 08:44:29 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 820/1251] eta: 0:03:40 lr: 0.000450 loss: 3.2502 (3.2214) grad_norm: 1.4756 (nan) time: 0.5031 [2021-03-26 08:44:34 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 830/1251] eta: 0:03:35 lr: 0.000450 loss: 3.2502 (3.2201) grad_norm: 1.5881 (nan) time: 0.5087 [2021-03-26 08:44:39 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 840/1251] eta: 0:03:29 lr: 0.000450 loss: 3.1227 (3.2204) grad_norm: 1.5005 (nan) time: 0.5039 [2021-03-26 08:44:44 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 850/1251] eta: 0:03:24 lr: 0.000450 loss: 3.1797 (3.2183) grad_norm: 1.4749 (nan) time: 0.5012 [2021-03-26 08:44:49 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 860/1251] eta: 0:03:19 lr: 0.000450 loss: 3.1683 (3.2206) grad_norm: 1.4525 (nan) time: 0.5081 [2021-03-26 08:44:54 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 870/1251] eta: 0:03:14 lr: 0.000450 loss: 3.2258 (3.2208) grad_norm: 1.4558 (nan) time: 0.5107 [2021-03-26 08:44:59 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 880/1251] eta: 0:03:09 lr: 0.000450 loss: 3.3159 (3.2217) grad_norm: 1.4749 (nan) time: 0.5122 [2021-03-26 08:45:04 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 890/1251] eta: 0:03:04 lr: 0.000450 loss: 3.3876 (3.2224) grad_norm: 1.5271 (nan) time: 0.5153 [2021-03-26 08:45:10 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 900/1251] eta: 0:02:59 lr: 0.000450 loss: 3.4395 (3.2252) grad_norm: 1.5387 (nan) time: 0.5113 [2021-03-26 08:45:15 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 910/1251] eta: 0:02:54 lr: 0.000450 loss: 3.5377 (3.2256) grad_norm: 1.5058 (nan) time: 0.5047 [2021-03-26 08:45:20 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 920/1251] eta: 0:02:48 lr: 0.000449 loss: 3.2369 (3.2235) grad_norm: 1.5019 (nan) time: 0.5012 [2021-03-26 08:45:24 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 930/1251] eta: 0:02:43 lr: 0.000449 loss: 3.0421 (3.2221) grad_norm: 1.4715 (nan) time: 0.4962 [2021-03-26 08:45:29 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 940/1251] eta: 0:02:38 lr: 0.000449 loss: 3.1465 (3.2237) grad_norm: 1.4981 (nan) time: 0.4940 [2021-03-26 08:45:34 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 950/1251] eta: 0:02:33 lr: 0.000449 loss: 3.3433 (3.2263) grad_norm: 1.5974 (nan) time: 0.4958 [2021-03-26 08:45:40 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 960/1251] eta: 0:02:28 lr: 0.000449 loss: 3.2613 (3.2254) grad_norm: 1.5219 (nan) time: 0.5044 [2021-03-26 08:45:45 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 970/1251] eta: 0:02:23 lr: 0.000449 loss: 3.3757 (3.2278) grad_norm: 1.4471 (nan) time: 0.5103 [2021-03-26 08:45:50 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 980/1251] eta: 0:02:18 lr: 0.000449 loss: 3.3022 (3.2292) grad_norm: 1.4104 (nan) time: 0.5080 [2021-03-26 08:45:55 swin_small_patch4_window7_224] INFO: Epoch: [160] [ 990/1251] eta: 0:02:13 lr: 0.000449 loss: 3.2458 (3.2291) grad_norm: 1.4197 (nan) time: 0.5055 [2021-03-26 08:46:00 swin_small_patch4_window7_224] INFO: Epoch: [160] [1000/1251] eta: 0:02:07 lr: 0.000449 loss: 3.3648 (3.2300) grad_norm: 1.4528 (nan) time: 0.5030 [2021-03-26 08:46:05 swin_small_patch4_window7_224] INFO: Epoch: [160] [1010/1251] eta: 0:02:02 lr: 0.000449 loss: 3.4396 (3.2293) grad_norm: 1.5679 (nan) time: 0.5069 [2021-03-26 08:46:10 swin_small_patch4_window7_224] INFO: Epoch: [160] [1020/1251] eta: 0:01:57 lr: 0.000449 loss: 3.1829 (3.2270) grad_norm: 1.5071 (nan) time: 0.5034 [2021-03-26 08:46:15 swin_small_patch4_window7_224] INFO: Epoch: [160] [1030/1251] eta: 0:01:52 lr: 0.000449 loss: 3.1829 (3.2257) grad_norm: 1.4809 (nan) time: 0.5025 [2021-03-26 08:46:20 swin_small_patch4_window7_224] INFO: Epoch: [160] [1040/1251] eta: 0:01:47 lr: 0.000449 loss: 3.2453 (3.2264) grad_norm: 1.4926 (nan) time: 0.5102 [2021-03-26 08:46:25 swin_small_patch4_window7_224] INFO: Epoch: [160] [1050/1251] eta: 0:01:42 lr: 0.000449 loss: 3.2398 (3.2259) grad_norm: 1.5248 (nan) time: 0.5092 [2021-03-26 08:46:30 swin_small_patch4_window7_224] INFO: Epoch: [160] [1060/1251] eta: 0:01:37 lr: 0.000449 loss: 3.0885 (3.2236) grad_norm: 1.5034 (nan) time: 0.5046 [2021-03-26 08:46:35 swin_small_patch4_window7_224] INFO: Epoch: [160] [1070/1251] eta: 0:01:32 lr: 0.000449 loss: 2.9452 (3.2214) grad_norm: 1.4490 (nan) time: 0.5053 [2021-03-26 08:46:40 swin_small_patch4_window7_224] INFO: Epoch: [160] [1080/1251] eta: 0:01:27 lr: 0.000449 loss: 3.0852 (3.2227) grad_norm: 1.4324 (nan) time: 0.5078 [2021-03-26 08:46:45 swin_small_patch4_window7_224] INFO: Epoch: [160] [1090/1251] eta: 0:01:22 lr: 0.000449 loss: 3.4075 (3.2218) grad_norm: 1.4862 (nan) time: 0.5037 [2021-03-26 08:46:50 swin_small_patch4_window7_224] INFO: Epoch: [160] [1100/1251] eta: 0:01:16 lr: 0.000449 loss: 3.3399 (3.2223) grad_norm: 1.4862 (nan) time: 0.5030 [2021-03-26 08:46:55 swin_small_patch4_window7_224] INFO: Epoch: [160] [1110/1251] eta: 0:01:11 lr: 0.000449 loss: 3.4497 (3.2229) grad_norm: 1.4759 (nan) time: 0.5012 [2021-03-26 08:47:00 swin_small_patch4_window7_224] INFO: Epoch: [160] [1120/1251] eta: 0:01:06 lr: 0.000449 loss: 3.4107 (3.2233) grad_norm: 1.4449 (nan) time: 0.5066 [2021-03-26 08:47:06 swin_small_patch4_window7_224] INFO: Epoch: [160] [1130/1251] eta: 0:01:01 lr: 0.000449 loss: 3.3334 (3.2249) grad_norm: 1.4774 (nan) time: 0.5113 [2021-03-26 08:47:11 swin_small_patch4_window7_224] INFO: Epoch: [160] [1140/1251] eta: 0:00:56 lr: 0.000449 loss: 3.3369 (3.2266) grad_norm: 1.5318 (nan) time: 0.5094 [2021-03-26 08:47:16 swin_small_patch4_window7_224] INFO: Epoch: [160] [1150/1251] eta: 0:00:51 lr: 0.000449 loss: 3.3117 (3.2251) grad_norm: 1.5210 (nan) time: 0.5012 [2021-03-26 08:47:21 swin_small_patch4_window7_224] INFO: Epoch: [160] [1160/1251] eta: 0:00:46 lr: 0.000448 loss: 3.0465 (3.2235) grad_norm: 1.4547 (nan) time: 0.4978 [2021-03-26 08:47:26 swin_small_patch4_window7_224] INFO: Epoch: [160] [1170/1251] eta: 0:00:41 lr: 0.000448 loss: 3.1135 (3.2233) grad_norm: 1.4962 (nan) time: 0.5031 [2021-03-26 08:47:31 swin_small_patch4_window7_224] INFO: Epoch: [160] [1180/1251] eta: 0:00:36 lr: 0.000448 loss: 3.1654 (3.2233) grad_norm: 1.5180 (nan) time: 0.5041 [2021-03-26 08:47:36 swin_small_patch4_window7_224] INFO: Epoch: [160] [1190/1251] eta: 0:00:31 lr: 0.000448 loss: 3.2879 (3.2244) grad_norm: 1.4971 (nan) time: 0.5032 [2021-03-26 08:47:41 swin_small_patch4_window7_224] INFO: Epoch: [160] [1200/1251] eta: 0:00:25 lr: 0.000448 loss: 3.3284 (3.2260) grad_norm: 1.4175 (nan) time: 0.5062 [2021-03-26 08:47:46 swin_small_patch4_window7_224] INFO: Epoch: [160] [1210/1251] eta: 0:00:20 lr: 0.000448 loss: 3.3284 (3.2242) grad_norm: 1.4243 (nan) time: 0.5105 [2021-03-26 08:47:51 swin_small_patch4_window7_224] INFO: Epoch: [160] [1220/1251] eta: 0:00:15 lr: 0.000448 loss: 3.2491 (3.2248) grad_norm: 1.4470 (nan) time: 0.5069 [2021-03-26 08:47:56 swin_small_patch4_window7_224] INFO: Epoch: [160] [1230/1251] eta: 0:00:10 lr: 0.000448 loss: 3.2491 (3.2223) grad_norm: 1.4764 (nan) time: 0.5029 [2021-03-26 08:48:01 swin_small_patch4_window7_224] INFO: Epoch: [160] [1240/1251] eta: 0:00:05 lr: 0.000448 loss: 2.7180 (3.2187) grad_norm: 1.4083 (nan) time: 0.5051 [2021-03-26 08:48:06 swin_small_patch4_window7_224] INFO: Epoch: [160] [1250/1251] eta: 0:00:00 lr: 0.000448 loss: 2.9068 (3.2179) grad_norm: 1.3809 (nan) time: 0.5010 [2021-03-26 08:48:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 1.1633 (1.1633) acc1: 70.3125 (70.3125) acc5: 93.7500 (93.7500) [2021-03-26 08:48:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 1.0371 (0.9471) acc1: 78.1250 (76.7045) acc5: 95.3125 (94.7443) [2021-03-26 08:48:54 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.8931 (0.9162) acc1: 79.6875 (77.8274) acc5: 95.3125 (95.5357) [2021-03-26 08:48:55 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8689 (0.9003) acc1: 79.6875 (78.2762) acc5: 95.3125 (95.3125) [2021-03-26 08:48:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8823 (0.9062) acc1: 76.5625 (77.7439) acc5: 93.7500 (95.1982) [2021-03-26 08:48:57 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8866 (0.9042) acc1: 75.4717 (77.7920) acc5: 95.3125 (95.1360) [2021-03-26 08:49:08 swin_small_patch4_window7_224] INFO: * Acc@1 78.630 Acc@5 94.678 loss 0.897 [2021-03-26 08:49:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.6% [2021-03-26 08:49:08 swin_small_patch4_window7_224] INFO: Max accuracy: 78.81% [2021-03-26 08:49:12 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 0/1251] eta: 1:25:36 lr: 0.000448 loss: 3.4398 (3.4398) grad_norm: 1.6118 (1.6118) time: 4.1061 [2021-03-26 08:49:17 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 10/1251] eta: 0:17:43 lr: 0.000448 loss: 3.3950 (3.1555) grad_norm: 1.4798 (1.5059) time: 0.8569 [2021-03-26 08:49:22 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 20/1251] eta: 0:14:07 lr: 0.000448 loss: 3.4551 (3.2906) grad_norm: 1.4917 (1.4973) time: 0.5174 [2021-03-26 08:49:27 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 30/1251] eta: 0:12:50 lr: 0.000448 loss: 3.3127 (3.2376) grad_norm: 1.5078 (1.5277) time: 0.5066 [2021-03-26 08:49:32 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 40/1251] eta: 0:12:05 lr: 0.000448 loss: 3.2820 (3.2098) grad_norm: 1.5313 (1.5532) time: 0.5059 [2021-03-26 08:49:37 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 50/1251] eta: 0:11:40 lr: 0.000448 loss: 3.4072 (3.2093) grad_norm: 1.5315 (1.5554) time: 0.5089 [2021-03-26 08:49:42 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 60/1251] eta: 0:11:17 lr: 0.000448 loss: 3.1499 (3.1986) grad_norm: 1.4975 (1.5478) time: 0.5057 [2021-03-26 08:49:47 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 70/1251] eta: 0:11:00 lr: 0.000448 loss: 3.1499 (3.2109) grad_norm: 1.4903 (1.5533) time: 0.4989 [2021-03-26 08:49:52 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 80/1251] eta: 0:10:48 lr: 0.000448 loss: 3.1612 (3.1907) grad_norm: 1.4903 (1.5402) time: 0.5069 [2021-03-26 08:49:57 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 90/1251] eta: 0:10:35 lr: 0.000448 loss: 3.0917 (3.1857) grad_norm: 1.4270 (1.5362) time: 0.5046 [2021-03-26 08:50:02 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 100/1251] eta: 0:10:24 lr: 0.000448 loss: 3.0670 (3.1787) grad_norm: 1.5569 (1.5430) time: 0.4971 [2021-03-26 08:50:08 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 110/1251] eta: 0:10:15 lr: 0.000448 loss: 3.1739 (3.1805) grad_norm: 1.6067 (1.5500) time: 0.5029 [2021-03-26 08:50:13 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 120/1251] eta: 0:10:06 lr: 0.000448 loss: 3.0608 (3.1706) grad_norm: 1.6066 (1.5528) time: 0.5085 [2021-03-26 08:50:18 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 130/1251] eta: 0:09:58 lr: 0.000448 loss: 3.1469 (3.1779) grad_norm: 1.5997 (1.5550) time: 0.5042 [2021-03-26 08:50:23 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 140/1251] eta: 0:09:50 lr: 0.000448 loss: 3.1469 (3.1693) grad_norm: 1.5884 (1.5580) time: 0.5021 [2021-03-26 08:50:28 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 150/1251] eta: 0:09:43 lr: 0.000447 loss: 3.1663 (3.1822) grad_norm: 1.4650 (1.5519) time: 0.5045 [2021-03-26 08:50:33 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 160/1251] eta: 0:09:36 lr: 0.000447 loss: 3.1767 (3.1870) grad_norm: 1.4697 (1.5482) time: 0.5062 [2021-03-26 08:50:38 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 170/1251] eta: 0:09:29 lr: 0.000447 loss: 3.3813 (3.1904) grad_norm: 1.5021 (1.5487) time: 0.5033 [2021-03-26 08:50:43 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 180/1251] eta: 0:09:23 lr: 0.000447 loss: 3.4089 (3.1905) grad_norm: 1.5021 (1.5480) time: 0.5076 [2021-03-26 08:50:48 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 190/1251] eta: 0:09:17 lr: 0.000447 loss: 3.0500 (3.1833) grad_norm: 1.5281 (1.5472) time: 0.5117 [2021-03-26 08:50:53 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 200/1251] eta: 0:09:11 lr: 0.000447 loss: 3.0500 (3.1835) grad_norm: 1.5310 (1.5518) time: 0.5131 [2021-03-26 08:50:58 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 210/1251] eta: 0:09:05 lr: 0.000447 loss: 3.2170 (3.1898) grad_norm: 1.5652 (1.5525) time: 0.5129 [2021-03-26 08:51:03 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 220/1251] eta: 0:08:59 lr: 0.000447 loss: 3.2237 (3.1865) grad_norm: 1.5284 (1.5500) time: 0.5035 [2021-03-26 08:51:08 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 230/1251] eta: 0:08:53 lr: 0.000447 loss: 3.1714 (3.1856) grad_norm: 1.4952 (1.5481) time: 0.5032 [2021-03-26 08:51:13 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 240/1251] eta: 0:08:47 lr: 0.000447 loss: 3.2920 (3.1976) grad_norm: 1.4787 (1.5444) time: 0.5045 [2021-03-26 08:51:18 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 250/1251] eta: 0:08:41 lr: 0.000447 loss: 3.2920 (3.2023) grad_norm: 1.4569 (1.5399) time: 0.5066 [2021-03-26 08:51:23 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 260/1251] eta: 0:08:35 lr: 0.000447 loss: 3.5086 (3.2110) grad_norm: 1.4321 (1.5369) time: 0.5060 [2021-03-26 08:51:28 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 270/1251] eta: 0:08:29 lr: 0.000447 loss: 3.5086 (3.2173) grad_norm: 1.4841 (1.5373) time: 0.5011 [2021-03-26 08:51:34 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 280/1251] eta: 0:08:23 lr: 0.000447 loss: 3.2816 (3.2163) grad_norm: 1.4544 (1.5351) time: 0.5014 [2021-03-26 08:51:39 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 290/1251] eta: 0:08:18 lr: 0.000447 loss: 3.0362 (3.2072) grad_norm: 1.5131 (1.5367) time: 0.5035 [2021-03-26 08:51:44 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 300/1251] eta: 0:08:12 lr: 0.000447 loss: 2.9994 (3.2046) grad_norm: 1.5462 (1.5357) time: 0.5035 [2021-03-26 08:51:49 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 310/1251] eta: 0:08:06 lr: 0.000447 loss: 3.4096 (3.2116) grad_norm: 1.4803 (1.5348) time: 0.4992 [2021-03-26 08:51:54 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 320/1251] eta: 0:08:00 lr: 0.000447 loss: 3.3674 (3.2097) grad_norm: 1.4760 (1.5318) time: 0.4971 [2021-03-26 08:51:58 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 330/1251] eta: 0:07:55 lr: 0.000447 loss: 3.2475 (3.2118) grad_norm: 1.4230 (1.5304) time: 0.4951 [2021-03-26 08:52:04 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 340/1251] eta: 0:07:49 lr: 0.000447 loss: 3.4285 (3.2175) grad_norm: 1.4474 (1.5267) time: 0.4992 [2021-03-26 08:52:09 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 350/1251] eta: 0:07:44 lr: 0.000447 loss: 3.5629 (3.2242) grad_norm: 1.3840 (1.5243) time: 0.5043 [2021-03-26 08:52:14 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 360/1251] eta: 0:07:38 lr: 0.000447 loss: 3.3416 (3.2204) grad_norm: 1.4702 (1.5232) time: 0.5008 [2021-03-26 08:52:18 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 370/1251] eta: 0:07:33 lr: 0.000447 loss: 3.1899 (3.2218) grad_norm: 1.4272 (1.5197) time: 0.4971 [2021-03-26 08:52:24 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 380/1251] eta: 0:07:27 lr: 0.000447 loss: 3.3162 (3.2254) grad_norm: 1.4297 (1.5212) time: 0.5000 [2021-03-26 08:52:29 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 390/1251] eta: 0:07:22 lr: 0.000447 loss: 3.3205 (3.2296) grad_norm: 1.5861 (1.5241) time: 0.5033 [2021-03-26 08:52:34 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 400/1251] eta: 0:07:16 lr: 0.000446 loss: 3.5105 (3.2370) grad_norm: 1.5700 (1.5253) time: 0.5004 [2021-03-26 08:52:39 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 410/1251] eta: 0:07:11 lr: 0.000446 loss: 3.5105 (3.2419) grad_norm: 1.5482 (1.5253) time: 0.5018 [2021-03-26 08:52:44 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 420/1251] eta: 0:07:06 lr: 0.000446 loss: 3.3949 (3.2444) grad_norm: 1.4551 (1.5242) time: 0.5014 [2021-03-26 08:52:49 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 430/1251] eta: 0:07:00 lr: 0.000446 loss: 3.2153 (3.2402) grad_norm: 1.4573 (1.5246) time: 0.5010 [2021-03-26 08:52:54 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 440/1251] eta: 0:06:55 lr: 0.000446 loss: 3.1191 (3.2410) grad_norm: 1.4932 (1.5247) time: 0.5031 [2021-03-26 08:52:59 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 450/1251] eta: 0:06:50 lr: 0.000446 loss: 3.3477 (3.2476) grad_norm: 1.5078 (1.5244) time: 0.5089 [2021-03-26 08:53:04 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 460/1251] eta: 0:06:45 lr: 0.000446 loss: 3.3156 (3.2457) grad_norm: 1.5071 (1.5253) time: 0.5087 [2021-03-26 08:53:09 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 470/1251] eta: 0:06:39 lr: 0.000446 loss: 3.1755 (3.2493) grad_norm: 1.5071 (1.5239) time: 0.5030 [2021-03-26 08:53:14 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 480/1251] eta: 0:06:34 lr: 0.000446 loss: 3.1748 (3.2430) grad_norm: 1.5202 (1.5245) time: 0.5086 [2021-03-26 08:53:19 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 490/1251] eta: 0:06:29 lr: 0.000446 loss: 3.1332 (3.2420) grad_norm: 1.5088 (1.5246) time: 0.5053 [2021-03-26 08:53:24 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 500/1251] eta: 0:06:24 lr: 0.000446 loss: 3.2226 (3.2411) grad_norm: 1.4841 (1.5242) time: 0.5016 [2021-03-26 08:53:29 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 510/1251] eta: 0:06:18 lr: 0.000446 loss: 3.3122 (3.2418) grad_norm: 1.5170 (1.5262) time: 0.5037 [2021-03-26 08:53:34 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 520/1251] eta: 0:06:13 lr: 0.000446 loss: 3.3122 (3.2375) grad_norm: 1.6573 (1.5290) time: 0.5016 [2021-03-26 08:53:39 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 530/1251] eta: 0:06:08 lr: 0.000446 loss: 3.3780 (3.2407) grad_norm: 1.5765 (1.5295) time: 0.4984 [2021-03-26 08:53:44 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 540/1251] eta: 0:06:03 lr: 0.000446 loss: 3.3702 (3.2379) grad_norm: 1.5253 (1.5295) time: 0.5002 [2021-03-26 08:53:49 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 550/1251] eta: 0:05:58 lr: 0.000446 loss: 3.3180 (3.2409) grad_norm: 1.4898 (1.5286) time: 0.5185 [2021-03-26 08:53:54 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 560/1251] eta: 0:05:53 lr: 0.000446 loss: 3.3180 (3.2395) grad_norm: 1.4908 (1.5307) time: 0.5196 [2021-03-26 08:54:00 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 570/1251] eta: 0:05:47 lr: 0.000446 loss: 3.1464 (3.2357) grad_norm: 1.5843 (1.5314) time: 0.5059 [2021-03-26 08:54:05 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 580/1251] eta: 0:05:42 lr: 0.000446 loss: 3.3739 (3.2361) grad_norm: 1.5543 (1.5314) time: 0.5097 [2021-03-26 08:54:10 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 590/1251] eta: 0:05:37 lr: 0.000446 loss: 3.4707 (3.2397) grad_norm: 1.5680 (1.5362) time: 0.5108 [2021-03-26 08:54:15 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 600/1251] eta: 0:05:32 lr: 0.000446 loss: 3.3678 (3.2370) grad_norm: 1.5430 (1.5360) time: 0.5088 [2021-03-26 08:54:20 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 610/1251] eta: 0:05:27 lr: 0.000446 loss: 3.2263 (3.2364) grad_norm: 1.5333 (1.5373) time: 0.5102 [2021-03-26 08:54:25 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 620/1251] eta: 0:05:22 lr: 0.000446 loss: 3.3643 (3.2410) grad_norm: 1.5742 (1.5371) time: 0.5092 [2021-03-26 08:54:30 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 630/1251] eta: 0:05:17 lr: 0.000446 loss: 3.5234 (3.2426) grad_norm: 1.5218 (1.5365) time: 0.5061 [2021-03-26 08:54:35 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 640/1251] eta: 0:05:12 lr: 0.000445 loss: 3.3666 (3.2395) grad_norm: 1.4642 (1.5361) time: 0.5050 [2021-03-26 08:54:40 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 650/1251] eta: 0:05:06 lr: 0.000445 loss: 3.3940 (3.2424) grad_norm: 1.4604 (1.5354) time: 0.5069 [2021-03-26 08:54:45 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 660/1251] eta: 0:05:01 lr: 0.000445 loss: 3.3844 (3.2427) grad_norm: 1.4305 (1.5348) time: 0.5065 [2021-03-26 08:54:50 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 670/1251] eta: 0:04:56 lr: 0.000445 loss: 3.3269 (3.2427) grad_norm: 1.4465 (1.5344) time: 0.5002 [2021-03-26 08:54:55 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 680/1251] eta: 0:04:51 lr: 0.000445 loss: 3.2833 (3.2414) grad_norm: 1.4836 (1.5344) time: 0.5006 [2021-03-26 08:55:00 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 690/1251] eta: 0:04:46 lr: 0.000445 loss: 3.2613 (3.2413) grad_norm: 1.4716 (1.5337) time: 0.5030 [2021-03-26 08:55:05 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 700/1251] eta: 0:04:41 lr: 0.000445 loss: 3.2243 (3.2416) grad_norm: 1.4936 (1.5336) time: 0.5027 [2021-03-26 08:55:10 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 710/1251] eta: 0:04:35 lr: 0.000445 loss: 3.1785 (3.2405) grad_norm: 1.5184 (1.5337) time: 0.5055 [2021-03-26 08:55:15 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 720/1251] eta: 0:04:30 lr: 0.000445 loss: 3.4533 (3.2443) grad_norm: 1.5095 (1.5342) time: 0.5073 [2021-03-26 08:55:21 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 730/1251] eta: 0:04:25 lr: 0.000445 loss: 3.3151 (3.2438) grad_norm: 1.4371 (1.5326) time: 0.5176 [2021-03-26 08:55:26 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 740/1251] eta: 0:04:21 lr: 0.000445 loss: 3.3073 (3.2459) grad_norm: 1.4246 (1.5323) time: 0.5391 [2021-03-26 08:55:31 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 750/1251] eta: 0:04:15 lr: 0.000445 loss: 3.3184 (3.2453) grad_norm: 1.4940 (1.5314) time: 0.5321 [2021-03-26 08:55:36 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 760/1251] eta: 0:04:10 lr: 0.000445 loss: 3.3187 (3.2445) grad_norm: 1.5051 (1.5311) time: 0.5101 [2021-03-26 08:55:42 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 770/1251] eta: 0:04:05 lr: 0.000445 loss: 3.2635 (3.2449) grad_norm: 1.5051 (1.5304) time: 0.5115 [2021-03-26 08:55:47 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 780/1251] eta: 0:04:00 lr: 0.000445 loss: 3.2635 (3.2448) grad_norm: 1.5244 (1.5311) time: 0.5071 [2021-03-26 08:55:52 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 790/1251] eta: 0:03:55 lr: 0.000445 loss: 3.4518 (3.2481) grad_norm: 1.5626 (1.5330) time: 0.5006 [2021-03-26 08:55:57 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 800/1251] eta: 0:03:50 lr: 0.000445 loss: 3.5618 (3.2494) grad_norm: 1.6679 (1.5355) time: 0.5088 [2021-03-26 08:56:02 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 810/1251] eta: 0:03:45 lr: 0.000445 loss: 3.4957 (3.2504) grad_norm: 1.6126 (1.5356) time: 0.5095 [2021-03-26 08:56:07 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 820/1251] eta: 0:03:40 lr: 0.000445 loss: 3.3595 (3.2506) grad_norm: 1.5265 (1.5353) time: 0.5107 [2021-03-26 08:56:12 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 830/1251] eta: 0:03:34 lr: 0.000445 loss: 3.2529 (3.2472) grad_norm: 1.4574 (1.5348) time: 0.5108 [2021-03-26 08:56:17 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 840/1251] eta: 0:03:29 lr: 0.000445 loss: 2.9515 (3.2444) grad_norm: 1.5280 (1.5350) time: 0.5061 [2021-03-26 08:56:22 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 850/1251] eta: 0:03:24 lr: 0.000445 loss: 3.6337 (3.2502) grad_norm: 1.5550 (1.5344) time: 0.5066 [2021-03-26 08:56:27 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 860/1251] eta: 0:03:19 lr: 0.000445 loss: 3.7564 (3.2523) grad_norm: 1.5019 (1.5346) time: 0.5008 [2021-03-26 08:56:32 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 870/1251] eta: 0:03:14 lr: 0.000445 loss: 3.5133 (3.2531) grad_norm: 1.5188 (1.5349) time: 0.5012 [2021-03-26 08:56:37 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 880/1251] eta: 0:03:09 lr: 0.000444 loss: 3.1586 (3.2502) grad_norm: 1.5940 (1.5356) time: 0.5038 [2021-03-26 08:56:42 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 890/1251] eta: 0:03:04 lr: 0.000444 loss: 3.2046 (3.2512) grad_norm: 1.6134 (1.5362) time: 0.4983 [2021-03-26 08:56:47 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 900/1251] eta: 0:02:58 lr: 0.000444 loss: 3.4693 (3.2539) grad_norm: 1.5668 (1.5360) time: 0.4984 [2021-03-26 08:56:52 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 910/1251] eta: 0:02:53 lr: 0.000444 loss: 3.4162 (3.2546) grad_norm: 1.5304 (1.5360) time: 0.5067 [2021-03-26 08:56:58 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 920/1251] eta: 0:02:48 lr: 0.000444 loss: 3.2891 (3.2563) grad_norm: 1.5430 (1.5371) time: 0.5143 [2021-03-26 08:57:03 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 930/1251] eta: 0:02:43 lr: 0.000444 loss: 3.2089 (3.2551) grad_norm: 1.4622 (1.5367) time: 0.5134 [2021-03-26 08:57:08 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 940/1251] eta: 0:02:38 lr: 0.000444 loss: 3.3572 (3.2549) grad_norm: 1.4936 (1.5374) time: 0.5085 [2021-03-26 08:57:13 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 950/1251] eta: 0:02:33 lr: 0.000444 loss: 3.3690 (3.2563) grad_norm: 1.4936 (1.5364) time: 0.5105 [2021-03-26 08:57:18 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 960/1251] eta: 0:02:28 lr: 0.000444 loss: 3.5206 (3.2567) grad_norm: 1.3950 (1.5362) time: 0.5088 [2021-03-26 08:57:23 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 970/1251] eta: 0:02:23 lr: 0.000444 loss: 3.5206 (3.2594) grad_norm: 1.5269 (1.5362) time: 0.5046 [2021-03-26 08:57:28 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 980/1251] eta: 0:02:18 lr: 0.000444 loss: 3.5300 (3.2613) grad_norm: 1.5257 (1.5359) time: 0.5071 [2021-03-26 08:57:33 swin_small_patch4_window7_224] INFO: Epoch: [161] [ 990/1251] eta: 0:02:13 lr: 0.000444 loss: 3.4015 (3.2613) grad_norm: 1.5181 (1.5360) time: 0.5045 [2021-03-26 08:57:38 swin_small_patch4_window7_224] INFO: Epoch: [161] [1000/1251] eta: 0:02:07 lr: 0.000444 loss: 3.4015 (3.2613) grad_norm: 1.5799 (1.5382) time: 0.5054 [2021-03-26 08:57:43 swin_small_patch4_window7_224] INFO: Epoch: [161] [1010/1251] eta: 0:02:02 lr: 0.000444 loss: 3.4240 (3.2611) grad_norm: 1.5971 (1.5374) time: 0.5075 [2021-03-26 08:57:48 swin_small_patch4_window7_224] INFO: Epoch: [161] [1020/1251] eta: 0:01:57 lr: 0.000444 loss: 3.1831 (3.2609) grad_norm: 1.6052 (1.5388) time: 0.5034 [2021-03-26 08:57:53 swin_small_patch4_window7_224] INFO: Epoch: [161] [1030/1251] eta: 0:01:52 lr: 0.000444 loss: 3.3042 (3.2602) grad_norm: 1.6012 (1.5388) time: 0.5001 [2021-03-26 08:57:58 swin_small_patch4_window7_224] INFO: Epoch: [161] [1040/1251] eta: 0:01:47 lr: 0.000444 loss: 3.3687 (3.2609) grad_norm: 1.5324 (1.5388) time: 0.4968 [2021-03-26 08:58:03 swin_small_patch4_window7_224] INFO: Epoch: [161] [1050/1251] eta: 0:01:42 lr: 0.000444 loss: 3.5851 (3.2621) grad_norm: 1.4603 (1.5382) time: 0.4947 [2021-03-26 08:58:08 swin_small_patch4_window7_224] INFO: Epoch: [161] [1060/1251] eta: 0:01:37 lr: 0.000444 loss: 3.3042 (3.2604) grad_norm: 1.4261 (1.5376) time: 0.4989 [2021-03-26 08:58:13 swin_small_patch4_window7_224] INFO: Epoch: [161] [1070/1251] eta: 0:01:32 lr: 0.000444 loss: 3.0717 (3.2579) grad_norm: 1.5333 (1.5380) time: 0.5070 [2021-03-26 08:58:18 swin_small_patch4_window7_224] INFO: Epoch: [161] [1080/1251] eta: 0:01:27 lr: 0.000444 loss: 3.1382 (3.2574) grad_norm: 1.5574 (1.5388) time: 0.5050 [2021-03-26 08:58:23 swin_small_patch4_window7_224] INFO: Epoch: [161] [1090/1251] eta: 0:01:21 lr: 0.000444 loss: 3.3031 (3.2589) grad_norm: 1.6514 (1.5398) time: 0.5058 [2021-03-26 08:58:28 swin_small_patch4_window7_224] INFO: Epoch: [161] [1100/1251] eta: 0:01:16 lr: 0.000444 loss: 3.4578 (3.2592) grad_norm: 1.6583 (1.5403) time: 0.5123 [2021-03-26 08:58:33 swin_small_patch4_window7_224] INFO: Epoch: [161] [1110/1251] eta: 0:01:11 lr: 0.000444 loss: 3.1508 (3.2573) grad_norm: 1.5372 (1.5402) time: 0.5038 [2021-03-26 08:58:38 swin_small_patch4_window7_224] INFO: Epoch: [161] [1120/1251] eta: 0:01:06 lr: 0.000443 loss: 3.0543 (3.2587) grad_norm: 1.5532 (1.5404) time: 0.4950 [2021-03-26 08:58:43 swin_small_patch4_window7_224] INFO: Epoch: [161] [1130/1251] eta: 0:01:01 lr: 0.000443 loss: 3.4270 (3.2587) grad_norm: 1.5825 (1.5408) time: 0.4998 [2021-03-26 08:58:48 swin_small_patch4_window7_224] INFO: Epoch: [161] [1140/1251] eta: 0:00:56 lr: 0.000443 loss: 3.4304 (3.2602) grad_norm: 1.6124 (1.5417) time: 0.5037 [2021-03-26 08:58:53 swin_small_patch4_window7_224] INFO: Epoch: [161] [1150/1251] eta: 0:00:51 lr: 0.000443 loss: 3.5098 (3.2603) grad_norm: 1.4833 (1.5410) time: 0.5044 [2021-03-26 08:58:59 swin_small_patch4_window7_224] INFO: Epoch: [161] [1160/1251] eta: 0:00:46 lr: 0.000443 loss: 3.3673 (3.2606) grad_norm: 1.4993 (1.5426) time: 0.5025 [2021-03-26 08:59:03 swin_small_patch4_window7_224] INFO: Epoch: [161] [1170/1251] eta: 0:00:41 lr: 0.000443 loss: 3.1895 (3.2596) grad_norm: 1.5192 (1.5418) time: 0.4974 [2021-03-26 08:59:08 swin_small_patch4_window7_224] INFO: Epoch: [161] [1180/1251] eta: 0:00:36 lr: 0.000443 loss: 3.1086 (3.2590) grad_norm: 1.4861 (1.5418) time: 0.4966 [2021-03-26 08:59:14 swin_small_patch4_window7_224] INFO: Epoch: [161] [1190/1251] eta: 0:00:31 lr: 0.000443 loss: 3.1652 (3.2589) grad_norm: 1.4923 (1.5411) time: 0.5121 [2021-03-26 08:59:19 swin_small_patch4_window7_224] INFO: Epoch: [161] [1200/1251] eta: 0:00:25 lr: 0.000443 loss: 3.3353 (3.2593) grad_norm: 1.4666 (1.5406) time: 0.5127 [2021-03-26 08:59:24 swin_small_patch4_window7_224] INFO: Epoch: [161] [1210/1251] eta: 0:00:20 lr: 0.000443 loss: 3.3137 (3.2571) grad_norm: 1.4016 (1.5397) time: 0.5004 [2021-03-26 08:59:29 swin_small_patch4_window7_224] INFO: Epoch: [161] [1220/1251] eta: 0:00:15 lr: 0.000443 loss: 3.0522 (3.2558) grad_norm: 1.4719 (1.5396) time: 0.5052 [2021-03-26 08:59:34 swin_small_patch4_window7_224] INFO: Epoch: [161] [1230/1251] eta: 0:00:10 lr: 0.000443 loss: 3.5481 (3.2590) grad_norm: 1.5187 (1.5398) time: 0.5066 [2021-03-26 08:59:39 swin_small_patch4_window7_224] INFO: Epoch: [161] [1240/1251] eta: 0:00:05 lr: 0.000443 loss: 3.6083 (3.2614) grad_norm: 1.4552 (1.5391) time: 0.4996 [2021-03-26 08:59:44 swin_small_patch4_window7_224] INFO: Epoch: [161] [1250/1251] eta: 0:00:00 lr: 0.000443 loss: 3.5347 (3.2619) grad_norm: 1.4528 (1.5394) time: 0.4984 [2021-03-26 08:59:56 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:48 loss: 0.8949 (0.8949) acc1: 75.0000 (75.0000) acc5: 95.3125 (95.3125) [2021-03-26 08:59:59 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9087 (0.8675) acc1: 79.6875 (78.6932) acc5: 95.3125 (96.0227) [2021-03-26 09:00:01 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.9087 (0.9170) acc1: 79.6875 (77.6042) acc5: 95.3125 (95.0149) [2021-03-26 09:00:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9330 (0.9278) acc1: 78.1250 (78.1250) acc5: 93.7500 (94.6573) [2021-03-26 09:00:05 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9331 (0.9201) acc1: 79.6875 (78.4680) acc5: 93.7500 (94.7409) [2021-03-26 09:00:06 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8328 (0.9062) acc1: 79.6875 (78.5280) acc5: 95.3125 (95.1040) [2021-03-26 09:00:18 swin_small_patch4_window7_224] INFO: * Acc@1 78.916 Acc@5 94.780 loss 0.899 [2021-03-26 09:00:18 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.9% [2021-03-26 09:00:18 swin_small_patch4_window7_224] INFO: Max accuracy: 78.92% [2021-03-26 09:00:22 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 0/1251] eta: 1:26:02 lr: 0.000443 loss: 2.8070 (2.8070) grad_norm: 1.6226 (1.6226) time: 4.1271 [2021-03-26 09:00:27 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 10/1251] eta: 0:17:42 lr: 0.000443 loss: 3.0064 (3.1549) grad_norm: 1.5819 (1.5488) time: 0.8560 [2021-03-26 09:00:32 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 20/1251] eta: 0:14:08 lr: 0.000443 loss: 3.2429 (3.2037) grad_norm: 1.4694 (1.5698) time: 0.5173 [2021-03-26 09:00:37 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 30/1251] eta: 0:12:44 lr: 0.000443 loss: 3.3920 (3.2320) grad_norm: 1.5494 (1.5789) time: 0.4996 [2021-03-26 09:00:42 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 40/1251] eta: 0:12:05 lr: 0.000443 loss: 3.4022 (3.2240) grad_norm: 1.5325 (1.5527) time: 0.5047 [2021-03-26 09:00:47 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 50/1251] eta: 0:11:36 lr: 0.000443 loss: 3.3121 (3.2244) grad_norm: 1.4723 (1.5390) time: 0.5091 [2021-03-26 09:00:52 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 60/1251] eta: 0:11:15 lr: 0.000443 loss: 3.2924 (3.2143) grad_norm: 1.4911 (1.5366) time: 0.5018 [2021-03-26 09:00:57 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 70/1251] eta: 0:10:59 lr: 0.000443 loss: 3.2163 (3.2050) grad_norm: 1.4693 (1.5218) time: 0.5043 [2021-03-26 09:01:02 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 80/1251] eta: 0:10:45 lr: 0.000443 loss: 2.8659 (3.1586) grad_norm: 1.4688 (1.5202) time: 0.5018 [2021-03-26 09:01:07 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 90/1251] eta: 0:10:32 lr: 0.000443 loss: 3.0874 (3.1830) grad_norm: 1.4982 (1.5186) time: 0.4967 [2021-03-26 09:01:12 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 100/1251] eta: 0:10:22 lr: 0.000443 loss: 3.4121 (3.2009) grad_norm: 1.4730 (1.5179) time: 0.5008 [2021-03-26 09:01:17 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 110/1251] eta: 0:10:14 lr: 0.000443 loss: 3.3892 (3.2221) grad_norm: 1.5294 (1.5192) time: 0.5101 [2021-03-26 09:01:23 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 120/1251] eta: 0:10:06 lr: 0.000442 loss: 3.2887 (3.2151) grad_norm: 1.5046 (1.5132) time: 0.5126 [2021-03-26 09:01:28 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 130/1251] eta: 0:09:58 lr: 0.000442 loss: 3.4171 (3.2284) grad_norm: 1.3750 (1.5100) time: 0.5065 [2021-03-26 09:01:33 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 140/1251] eta: 0:09:51 lr: 0.000442 loss: 3.4523 (3.2354) grad_norm: 1.4258 (1.5075) time: 0.5061 [2021-03-26 09:01:38 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 150/1251] eta: 0:09:44 lr: 0.000442 loss: 3.2647 (3.2322) grad_norm: 1.4382 (1.5062) time: 0.5079 [2021-03-26 09:01:43 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 160/1251] eta: 0:09:36 lr: 0.000442 loss: 3.1175 (3.2304) grad_norm: 1.5522 (1.5114) time: 0.5023 [2021-03-26 09:01:48 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 170/1251] eta: 0:09:29 lr: 0.000442 loss: 3.1430 (3.2278) grad_norm: 1.5910 (1.5172) time: 0.4987 [2021-03-26 09:01:53 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 180/1251] eta: 0:09:23 lr: 0.000442 loss: 3.3712 (3.2307) grad_norm: 1.5660 (1.5201) time: 0.5038 [2021-03-26 09:01:58 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 190/1251] eta: 0:09:17 lr: 0.000442 loss: 3.5047 (3.2343) grad_norm: 1.5422 (1.5217) time: 0.5132 [2021-03-26 09:02:03 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 200/1251] eta: 0:09:11 lr: 0.000442 loss: 3.2375 (3.2297) grad_norm: 1.5475 (1.5244) time: 0.5170 [2021-03-26 09:02:08 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 210/1251] eta: 0:09:05 lr: 0.000442 loss: 3.0096 (3.2156) grad_norm: 1.5017 (1.5249) time: 0.5084 [2021-03-26 09:02:13 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 220/1251] eta: 0:08:59 lr: 0.000442 loss: 3.0079 (3.2143) grad_norm: 1.5017 (1.5254) time: 0.5035 [2021-03-26 09:02:18 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 230/1251] eta: 0:08:52 lr: 0.000442 loss: 3.2994 (3.2212) grad_norm: 1.5497 (1.5263) time: 0.5032 [2021-03-26 09:02:23 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 240/1251] eta: 0:08:46 lr: 0.000442 loss: 3.2854 (3.2206) grad_norm: 1.4892 (1.5231) time: 0.4994 [2021-03-26 09:02:28 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 250/1251] eta: 0:08:41 lr: 0.000442 loss: 3.2738 (3.2263) grad_norm: 1.4706 (1.5228) time: 0.5042 [2021-03-26 09:02:33 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 260/1251] eta: 0:08:35 lr: 0.000442 loss: 3.1485 (3.2162) grad_norm: 1.4941 (1.5242) time: 0.5101 [2021-03-26 09:02:38 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 270/1251] eta: 0:08:29 lr: 0.000442 loss: 3.0395 (3.2176) grad_norm: 1.4286 (1.5234) time: 0.5092 [2021-03-26 09:02:44 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 280/1251] eta: 0:08:24 lr: 0.000442 loss: 3.1958 (3.2146) grad_norm: 1.4799 (1.5250) time: 0.5064 [2021-03-26 09:02:49 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 290/1251] eta: 0:08:18 lr: 0.000442 loss: 3.3034 (3.2182) grad_norm: 1.5859 (1.5274) time: 0.5070 [2021-03-26 09:02:54 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 300/1251] eta: 0:08:13 lr: 0.000442 loss: 3.3482 (3.2255) grad_norm: 1.6042 (1.5310) time: 0.5113 [2021-03-26 09:02:59 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 310/1251] eta: 0:08:07 lr: 0.000442 loss: 3.5484 (3.2341) grad_norm: 1.6183 (1.5348) time: 0.5107 [2021-03-26 09:03:04 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 320/1251] eta: 0:08:02 lr: 0.000442 loss: 3.2031 (3.2286) grad_norm: 1.6183 (1.5393) time: 0.5084 [2021-03-26 09:03:09 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 330/1251] eta: 0:07:56 lr: 0.000442 loss: 3.2278 (3.2327) grad_norm: 1.5829 (1.5402) time: 0.5104 [2021-03-26 09:03:14 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 340/1251] eta: 0:07:51 lr: 0.000442 loss: 3.3647 (3.2285) grad_norm: 1.5252 (1.5404) time: 0.5124 [2021-03-26 09:03:19 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 350/1251] eta: 0:07:45 lr: 0.000442 loss: 3.2543 (3.2296) grad_norm: 1.4787 (1.5396) time: 0.5066 [2021-03-26 09:03:24 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 360/1251] eta: 0:07:40 lr: 0.000441 loss: 3.3198 (3.2276) grad_norm: 1.4806 (1.5400) time: 0.5030 [2021-03-26 09:03:29 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 370/1251] eta: 0:07:35 lr: 0.000441 loss: 3.3198 (3.2314) grad_norm: 1.5222 (1.5379) time: 0.5056 [2021-03-26 09:03:34 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 380/1251] eta: 0:07:29 lr: 0.000441 loss: 3.4954 (3.2364) grad_norm: 1.4784 (1.5394) time: 0.5055 [2021-03-26 09:03:39 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 390/1251] eta: 0:07:24 lr: 0.000441 loss: 3.2540 (3.2313) grad_norm: 1.4609 (1.5370) time: 0.5038 [2021-03-26 09:03:44 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 400/1251] eta: 0:07:18 lr: 0.000441 loss: 3.2237 (3.2335) grad_norm: 1.4552 (1.5372) time: 0.5000 [2021-03-26 09:03:49 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 410/1251] eta: 0:07:13 lr: 0.000441 loss: 3.1927 (3.2316) grad_norm: 1.4416 (1.5373) time: 0.4974 [2021-03-26 09:03:54 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 420/1251] eta: 0:07:07 lr: 0.000441 loss: 3.2906 (3.2378) grad_norm: 1.4416 (1.5367) time: 0.4982 [2021-03-26 09:03:59 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 430/1251] eta: 0:07:02 lr: 0.000441 loss: 3.4094 (3.2394) grad_norm: 1.4386 (1.5354) time: 0.4975 [2021-03-26 09:04:04 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 440/1251] eta: 0:06:56 lr: 0.000441 loss: 3.4094 (3.2429) grad_norm: 1.5479 (1.5365) time: 0.5013 [2021-03-26 09:04:09 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 450/1251] eta: 0:06:51 lr: 0.000441 loss: 3.3637 (3.2448) grad_norm: 1.5623 (1.5376) time: 0.5012 [2021-03-26 09:04:14 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 460/1251] eta: 0:06:46 lr: 0.000441 loss: 3.1266 (3.2373) grad_norm: 1.4886 (1.5363) time: 0.5029 [2021-03-26 09:04:19 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 470/1251] eta: 0:06:40 lr: 0.000441 loss: 3.2495 (3.2389) grad_norm: 1.4834 (1.5366) time: 0.5077 [2021-03-26 09:04:24 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 480/1251] eta: 0:06:35 lr: 0.000441 loss: 3.3464 (3.2376) grad_norm: 1.5092 (1.5379) time: 0.5037 [2021-03-26 09:04:30 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 490/1251] eta: 0:06:30 lr: 0.000441 loss: 3.3059 (3.2390) grad_norm: 1.5144 (1.5386) time: 0.5020 [2021-03-26 09:04:35 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 500/1251] eta: 0:06:25 lr: 0.000441 loss: 3.3391 (3.2425) grad_norm: 1.5144 (1.5380) time: 0.5028 [2021-03-26 09:04:40 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 510/1251] eta: 0:06:20 lr: 0.000441 loss: 3.3233 (3.2449) grad_norm: 1.5293 (1.5396) time: 0.5110 [2021-03-26 09:04:45 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 520/1251] eta: 0:06:14 lr: 0.000441 loss: 3.4711 (3.2494) grad_norm: 1.5591 (1.5406) time: 0.5100 [2021-03-26 09:04:50 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 530/1251] eta: 0:06:09 lr: 0.000441 loss: 3.4748 (3.2526) grad_norm: 1.5756 (1.5416) time: 0.4985 [2021-03-26 09:04:55 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 540/1251] eta: 0:06:04 lr: 0.000441 loss: 3.3646 (3.2565) grad_norm: 1.5756 (1.5425) time: 0.4993 [2021-03-26 09:05:00 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 550/1251] eta: 0:05:59 lr: 0.000441 loss: 3.3646 (3.2572) grad_norm: 1.5471 (1.5418) time: 0.5162 [2021-03-26 09:05:05 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 560/1251] eta: 0:05:54 lr: 0.000441 loss: 3.2525 (3.2545) grad_norm: 1.5415 (1.5420) time: 0.5189 [2021-03-26 09:05:10 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 570/1251] eta: 0:05:48 lr: 0.000441 loss: 3.1428 (3.2554) grad_norm: 1.5015 (1.5409) time: 0.5075 [2021-03-26 09:05:15 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 580/1251] eta: 0:05:43 lr: 0.000441 loss: 3.2135 (3.2533) grad_norm: 1.5009 (1.5407) time: 0.5061 [2021-03-26 09:05:20 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 590/1251] eta: 0:05:38 lr: 0.000441 loss: 3.2725 (3.2531) grad_norm: 1.5269 (1.5418) time: 0.5103 [2021-03-26 09:05:25 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 600/1251] eta: 0:05:33 lr: 0.000440 loss: 3.2725 (3.2509) grad_norm: 1.5681 (1.5418) time: 0.5088 [2021-03-26 09:05:30 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 610/1251] eta: 0:05:28 lr: 0.000440 loss: 3.0627 (3.2493) grad_norm: 1.5467 (1.5418) time: 0.4991 [2021-03-26 09:05:35 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 620/1251] eta: 0:05:22 lr: 0.000440 loss: 3.1245 (3.2518) grad_norm: 1.5467 (1.5421) time: 0.5012 [2021-03-26 09:05:40 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 630/1251] eta: 0:05:17 lr: 0.000440 loss: 3.2477 (3.2491) grad_norm: 1.5629 (1.5430) time: 0.5042 [2021-03-26 09:05:45 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 640/1251] eta: 0:05:12 lr: 0.000440 loss: 3.2477 (3.2493) grad_norm: 1.5340 (1.5427) time: 0.4997 [2021-03-26 09:05:50 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 650/1251] eta: 0:05:07 lr: 0.000440 loss: 3.4612 (3.2520) grad_norm: 1.5298 (1.5428) time: 0.4999 [2021-03-26 09:05:56 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 660/1251] eta: 0:05:02 lr: 0.000440 loss: 3.3702 (3.2505) grad_norm: 1.4954 (1.5430) time: 0.5058 [2021-03-26 09:06:01 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 670/1251] eta: 0:04:56 lr: 0.000440 loss: 3.3769 (3.2497) grad_norm: 1.5425 (1.5518) time: 0.5097 [2021-03-26 09:06:06 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 680/1251] eta: 0:04:51 lr: 0.000440 loss: 3.3039 (3.2494) grad_norm: 1.5311 (1.5509) time: 0.5068 [2021-03-26 09:06:11 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 690/1251] eta: 0:04:46 lr: 0.000440 loss: 3.2176 (3.2502) grad_norm: 1.5311 (1.5578) time: 0.5093 [2021-03-26 09:06:16 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 700/1251] eta: 0:04:41 lr: 0.000440 loss: 3.4333 (3.2524) grad_norm: 1.7157 (1.5611) time: 0.5143 [2021-03-26 09:06:21 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 710/1251] eta: 0:04:36 lr: 0.000440 loss: 3.4790 (3.2531) grad_norm: 1.6792 (1.5623) time: 0.5062 [2021-03-26 09:06:26 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 720/1251] eta: 0:04:31 lr: 0.000440 loss: 3.4892 (3.2583) grad_norm: 1.6464 (1.5630) time: 0.4972 [2021-03-26 09:06:31 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 730/1251] eta: 0:04:25 lr: 0.000440 loss: 3.4755 (3.2534) grad_norm: 1.4806 (1.5622) time: 0.4954 [2021-03-26 09:06:36 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 740/1251] eta: 0:04:21 lr: 0.000440 loss: 3.0624 (3.2549) grad_norm: 1.4852 (1.5620) time: 0.5250 [2021-03-26 09:06:41 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 750/1251] eta: 0:04:16 lr: 0.000440 loss: 3.2183 (3.2521) grad_norm: 1.5410 (1.5626) time: 0.5299 [2021-03-26 09:06:46 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 760/1251] eta: 0:04:10 lr: 0.000440 loss: 3.2571 (3.2537) grad_norm: 1.5450 (1.5634) time: 0.5019 [2021-03-26 09:06:52 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 770/1251] eta: 0:04:05 lr: 0.000440 loss: 3.4677 (3.2546) grad_norm: 1.5575 (1.5647) time: 0.5017 [2021-03-26 09:06:57 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 780/1251] eta: 0:04:00 lr: 0.000440 loss: 3.3891 (3.2557) grad_norm: 1.5858 (1.5654) time: 0.5124 [2021-03-26 09:07:02 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 790/1251] eta: 0:03:55 lr: 0.000440 loss: 3.3229 (3.2553) grad_norm: 1.4928 (1.5652) time: 0.5179 [2021-03-26 09:07:07 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 800/1251] eta: 0:03:50 lr: 0.000440 loss: 3.2341 (3.2538) grad_norm: 1.4902 (1.5657) time: 0.5089 [2021-03-26 09:07:12 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 810/1251] eta: 0:03:45 lr: 0.000440 loss: 3.3951 (3.2567) grad_norm: 1.5159 (1.5652) time: 0.5035 [2021-03-26 09:07:17 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 820/1251] eta: 0:03:40 lr: 0.000440 loss: 3.4772 (3.2582) grad_norm: 1.5033 (1.5646) time: 0.5028 [2021-03-26 09:07:22 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 830/1251] eta: 0:03:34 lr: 0.000440 loss: 3.3201 (3.2566) grad_norm: 1.5037 (1.5638) time: 0.5012 [2021-03-26 09:07:27 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 840/1251] eta: 0:03:29 lr: 0.000440 loss: 3.1731 (3.2544) grad_norm: 1.5383 (1.5638) time: 0.5001 [2021-03-26 09:07:32 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 850/1251] eta: 0:03:24 lr: 0.000439 loss: 3.2486 (3.2539) grad_norm: 1.5418 (1.5644) time: 0.5026 [2021-03-26 09:07:37 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 860/1251] eta: 0:03:19 lr: 0.000439 loss: 3.4351 (3.2568) grad_norm: 1.5007 (1.5640) time: 0.5063 [2021-03-26 09:07:42 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 870/1251] eta: 0:03:14 lr: 0.000439 loss: 3.4595 (3.2574) grad_norm: 1.5660 (1.5651) time: 0.5088 [2021-03-26 09:07:47 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 880/1251] eta: 0:03:09 lr: 0.000439 loss: 3.3363 (3.2547) grad_norm: 1.5705 (1.5646) time: 0.5137 [2021-03-26 09:07:52 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 890/1251] eta: 0:03:04 lr: 0.000439 loss: 3.2932 (3.2542) grad_norm: 1.4825 (1.5640) time: 0.5052 [2021-03-26 09:07:57 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 900/1251] eta: 0:02:59 lr: 0.000439 loss: 3.2206 (3.2530) grad_norm: 1.4593 (1.5626) time: 0.4971 [2021-03-26 09:08:02 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 910/1251] eta: 0:02:53 lr: 0.000439 loss: 3.2426 (3.2549) grad_norm: 1.4578 (1.5622) time: 0.5011 [2021-03-26 09:08:07 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 920/1251] eta: 0:02:48 lr: 0.000439 loss: 3.3402 (3.2550) grad_norm: 1.5264 (1.5621) time: 0.5040 [2021-03-26 09:08:12 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 930/1251] eta: 0:02:43 lr: 0.000439 loss: 3.2672 (3.2553) grad_norm: 1.5108 (1.5614) time: 0.5058 [2021-03-26 09:08:18 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 940/1251] eta: 0:02:38 lr: 0.000439 loss: 3.2293 (3.2553) grad_norm: 1.4616 (1.5605) time: 0.5050 [2021-03-26 09:08:23 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 950/1251] eta: 0:02:33 lr: 0.000439 loss: 3.1998 (3.2541) grad_norm: 1.4634 (1.5602) time: 0.5071 [2021-03-26 09:08:28 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 960/1251] eta: 0:02:28 lr: 0.000439 loss: 3.1998 (3.2532) grad_norm: 1.5632 (1.5604) time: 0.5098 [2021-03-26 09:08:33 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 970/1251] eta: 0:02:23 lr: 0.000439 loss: 3.3507 (3.2538) grad_norm: 1.5401 (1.5600) time: 0.5053 [2021-03-26 09:08:38 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 980/1251] eta: 0:02:18 lr: 0.000439 loss: 3.4305 (3.2510) grad_norm: 1.4923 (1.5598) time: 0.5021 [2021-03-26 09:08:43 swin_small_patch4_window7_224] INFO: Epoch: [162] [ 990/1251] eta: 0:02:13 lr: 0.000439 loss: 3.2302 (3.2517) grad_norm: 1.5190 (1.5602) time: 0.5005 [2021-03-26 09:08:48 swin_small_patch4_window7_224] INFO: Epoch: [162] [1000/1251] eta: 0:02:07 lr: 0.000439 loss: 3.4470 (3.2518) grad_norm: 1.5489 (1.5604) time: 0.5043 [2021-03-26 09:08:53 swin_small_patch4_window7_224] INFO: Epoch: [162] [1010/1251] eta: 0:02:02 lr: 0.000439 loss: 3.3536 (3.2535) grad_norm: 1.5398 (1.5600) time: 0.5085 [2021-03-26 09:08:58 swin_small_patch4_window7_224] INFO: Epoch: [162] [1020/1251] eta: 0:01:57 lr: 0.000439 loss: 3.2823 (3.2537) grad_norm: 1.5509 (1.5609) time: 0.5083 [2021-03-26 09:09:03 swin_small_patch4_window7_224] INFO: Epoch: [162] [1030/1251] eta: 0:01:52 lr: 0.000439 loss: 3.2823 (3.2545) grad_norm: 1.5464 (1.5609) time: 0.5081 [2021-03-26 09:09:08 swin_small_patch4_window7_224] INFO: Epoch: [162] [1040/1251] eta: 0:01:47 lr: 0.000439 loss: 3.5637 (3.2564) grad_norm: 1.4911 (1.5605) time: 0.5001 [2021-03-26 09:09:13 swin_small_patch4_window7_224] INFO: Epoch: [162] [1050/1251] eta: 0:01:42 lr: 0.000439 loss: 3.5301 (3.2572) grad_norm: 1.4711 (1.5601) time: 0.5039 [2021-03-26 09:09:18 swin_small_patch4_window7_224] INFO: Epoch: [162] [1060/1251] eta: 0:01:37 lr: 0.000439 loss: 3.3751 (3.2560) grad_norm: 1.4324 (1.5589) time: 0.5138 [2021-03-26 09:09:23 swin_small_patch4_window7_224] INFO: Epoch: [162] [1070/1251] eta: 0:01:32 lr: 0.000439 loss: 3.4266 (3.2570) grad_norm: 1.4658 (1.5592) time: 0.5090 [2021-03-26 09:09:28 swin_small_patch4_window7_224] INFO: Epoch: [162] [1080/1251] eta: 0:01:27 lr: 0.000439 loss: 3.4165 (3.2574) grad_norm: 1.5644 (1.5592) time: 0.5011 [2021-03-26 09:09:33 swin_small_patch4_window7_224] INFO: Epoch: [162] [1090/1251] eta: 0:01:21 lr: 0.000438 loss: 3.2962 (3.2568) grad_norm: 1.5773 (1.5593) time: 0.5000 [2021-03-26 09:09:38 swin_small_patch4_window7_224] INFO: Epoch: [162] [1100/1251] eta: 0:01:16 lr: 0.000438 loss: 3.2090 (3.2568) grad_norm: 1.5264 (1.5588) time: 0.5004 [2021-03-26 09:09:43 swin_small_patch4_window7_224] INFO: Epoch: [162] [1110/1251] eta: 0:01:11 lr: 0.000438 loss: 3.1907 (3.2541) grad_norm: 1.5189 (1.5592) time: 0.4981 [2021-03-26 09:09:48 swin_small_patch4_window7_224] INFO: Epoch: [162] [1120/1251] eta: 0:01:06 lr: 0.000438 loss: 3.2849 (3.2559) grad_norm: 1.4970 (1.5584) time: 0.4991 [2021-03-26 09:09:53 swin_small_patch4_window7_224] INFO: Epoch: [162] [1130/1251] eta: 0:01:01 lr: 0.000438 loss: 3.4494 (3.2552) grad_norm: 1.4425 (1.5581) time: 0.5057 [2021-03-26 09:09:59 swin_small_patch4_window7_224] INFO: Epoch: [162] [1140/1251] eta: 0:00:56 lr: 0.000438 loss: 3.4494 (3.2572) grad_norm: 1.5258 (1.5581) time: 0.5115 [2021-03-26 09:10:04 swin_small_patch4_window7_224] INFO: Epoch: [162] [1150/1251] eta: 0:00:51 lr: 0.000438 loss: 3.6116 (3.2579) grad_norm: 1.5258 (1.5581) time: 0.5065 [2021-03-26 09:10:09 swin_small_patch4_window7_224] INFO: Epoch: [162] [1160/1251] eta: 0:00:46 lr: 0.000438 loss: 3.5646 (3.2598) grad_norm: 1.5694 (1.5584) time: 0.4967 [2021-03-26 09:10:14 swin_small_patch4_window7_224] INFO: Epoch: [162] [1170/1251] eta: 0:00:41 lr: 0.000438 loss: 3.6449 (3.2635) grad_norm: 1.5683 (1.5584) time: 0.5010 [2021-03-26 09:10:19 swin_small_patch4_window7_224] INFO: Epoch: [162] [1180/1251] eta: 0:00:36 lr: 0.000438 loss: 3.5653 (3.2641) grad_norm: 1.5683 (1.5593) time: 0.5038 [2021-03-26 09:10:24 swin_small_patch4_window7_224] INFO: Epoch: [162] [1190/1251] eta: 0:00:31 lr: 0.000438 loss: 3.4490 (3.2661) grad_norm: 1.5603 (1.5591) time: 0.4976 [2021-03-26 09:10:28 swin_small_patch4_window7_224] INFO: Epoch: [162] [1200/1251] eta: 0:00:25 lr: 0.000438 loss: 3.4490 (3.2675) grad_norm: 1.4979 (1.5589) time: 0.4943 [2021-03-26 09:10:33 swin_small_patch4_window7_224] INFO: Epoch: [162] [1210/1251] eta: 0:00:20 lr: 0.000438 loss: 3.2624 (3.2667) grad_norm: 1.4786 (1.5582) time: 0.4961 [2021-03-26 09:10:39 swin_small_patch4_window7_224] INFO: Epoch: [162] [1220/1251] eta: 0:00:15 lr: 0.000438 loss: 3.2616 (3.2660) grad_norm: 1.4496 (1.5571) time: 0.5021 [2021-03-26 09:10:44 swin_small_patch4_window7_224] INFO: Epoch: [162] [1230/1251] eta: 0:00:10 lr: 0.000438 loss: 3.3323 (3.2639) grad_norm: 1.4496 (1.5566) time: 0.5028 [2021-03-26 09:10:49 swin_small_patch4_window7_224] INFO: Epoch: [162] [1240/1251] eta: 0:00:05 lr: 0.000438 loss: 3.3323 (3.2640) grad_norm: 1.5156 (1.5561) time: 0.5008 [2021-03-26 09:10:54 swin_small_patch4_window7_224] INFO: Epoch: [162] [1250/1251] eta: 0:00:00 lr: 0.000438 loss: 3.6001 (3.2662) grad_norm: 1.4914 (1.5555) time: 0.4995 [2021-03-26 09:11:03 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:08 loss: 1.0039 (1.0039) acc1: 71.8750 (71.8750) acc5: 90.6250 (90.6250) [2021-03-26 09:11:05 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9113 (0.9589) acc1: 79.6875 (76.9886) acc5: 93.7500 (93.8920) [2021-03-26 09:11:07 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8280 (0.9013) acc1: 79.6875 (78.1250) acc5: 95.3125 (94.8661) [2021-03-26 09:11:11 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8502 (0.9074) acc1: 79.6875 (78.5282) acc5: 95.3125 (94.6069) [2021-03-26 09:11:12 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8502 (0.8879) acc1: 78.1250 (78.5442) acc5: 96.8750 (95.0838) [2021-03-26 09:11:13 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8273 (0.9039) acc1: 76.5625 (78.0480) acc5: 96.8750 (94.9440) [2021-03-26 09:11:20 swin_small_patch4_window7_224] INFO: * Acc@1 78.920 Acc@5 94.772 loss 0.891 [2021-03-26 09:11:20 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.9% [2021-03-26 09:11:20 swin_small_patch4_window7_224] INFO: Max accuracy: 78.92% [2021-03-26 09:11:25 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 0/1251] eta: 1:28:24 lr: 0.000438 loss: 3.7417 (3.7417) grad_norm: 1.4474 (1.4474) time: 4.2404 [2021-03-26 09:11:30 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 10/1251] eta: 0:17:22 lr: 0.000438 loss: 3.1045 (3.2583) grad_norm: 1.4701 (1.4869) time: 0.8399 [2021-03-26 09:11:35 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 20/1251] eta: 0:14:02 lr: 0.000438 loss: 3.3988 (3.3671) grad_norm: 1.5722 (1.5840) time: 0.5064 [2021-03-26 09:11:40 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 30/1251] eta: 0:12:43 lr: 0.000438 loss: 3.4838 (3.3310) grad_norm: 1.6004 (1.5892) time: 0.5078 [2021-03-26 09:11:45 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 40/1251] eta: 0:12:03 lr: 0.000438 loss: 3.4614 (3.3426) grad_norm: 1.5465 (1.5716) time: 0.5065 [2021-03-26 09:11:50 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 50/1251] eta: 0:11:34 lr: 0.000438 loss: 3.4156 (3.3245) grad_norm: 1.5170 (1.5658) time: 0.5051 [2021-03-26 09:11:55 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 60/1251] eta: 0:11:13 lr: 0.000438 loss: 3.3493 (3.3265) grad_norm: 1.4901 (1.5522) time: 0.5002 [2021-03-26 09:12:00 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 70/1251] eta: 0:10:56 lr: 0.000438 loss: 3.4631 (3.3389) grad_norm: 1.4582 (1.5437) time: 0.4981 [2021-03-26 09:12:05 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 80/1251] eta: 0:10:42 lr: 0.000437 loss: 3.1329 (3.3143) grad_norm: 1.4685 (1.5360) time: 0.4979 [2021-03-26 09:12:10 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 90/1251] eta: 0:10:31 lr: 0.000437 loss: 3.1329 (3.3008) grad_norm: 1.4793 (1.5337) time: 0.5017 [2021-03-26 09:12:15 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 100/1251] eta: 0:10:20 lr: 0.000437 loss: 3.2481 (3.2931) grad_norm: 1.4846 (1.5340) time: 0.5004 [2021-03-26 09:12:20 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 110/1251] eta: 0:10:11 lr: 0.000437 loss: 3.2887 (3.2924) grad_norm: 1.6049 (1.5462) time: 0.4997 [2021-03-26 09:12:25 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 120/1251] eta: 0:10:03 lr: 0.000437 loss: 3.3010 (3.2852) grad_norm: 1.6002 (1.5454) time: 0.5029 [2021-03-26 09:12:30 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 130/1251] eta: 0:09:55 lr: 0.000437 loss: 3.4610 (3.2953) grad_norm: 1.5330 (1.5459) time: 0.5068 [2021-03-26 09:12:35 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 140/1251] eta: 0:09:48 lr: 0.000437 loss: 3.4518 (3.2938) grad_norm: 1.5108 (1.5458) time: 0.5091 [2021-03-26 09:12:40 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 150/1251] eta: 0:09:41 lr: 0.000437 loss: 3.3803 (3.2953) grad_norm: 1.5108 (1.5518) time: 0.5076 [2021-03-26 09:12:45 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 160/1251] eta: 0:09:35 lr: 0.000437 loss: 3.2823 (3.2838) grad_norm: 1.4697 (1.5479) time: 0.5073 [2021-03-26 09:12:51 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 170/1251] eta: 0:09:29 lr: 0.000437 loss: 3.1123 (3.2668) grad_norm: 1.5189 (1.5546) time: 0.5132 [2021-03-26 09:12:56 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 180/1251] eta: 0:09:23 lr: 0.000437 loss: 3.2778 (3.2714) grad_norm: 1.5660 (1.5550) time: 0.5173 [2021-03-26 09:13:01 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 190/1251] eta: 0:09:17 lr: 0.000437 loss: 3.3150 (3.2669) grad_norm: 1.5335 (1.5533) time: 0.5131 [2021-03-26 09:13:06 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 200/1251] eta: 0:09:10 lr: 0.000437 loss: 3.3150 (3.2783) grad_norm: 1.5078 (1.5528) time: 0.5081 [2021-03-26 09:13:11 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 210/1251] eta: 0:09:04 lr: 0.000437 loss: 3.3537 (3.2796) grad_norm: 1.4871 (1.5530) time: 0.5042 [2021-03-26 09:13:16 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 220/1251] eta: 0:08:58 lr: 0.000437 loss: 3.4243 (3.2766) grad_norm: 1.4911 (1.5523) time: 0.5029 [2021-03-26 09:13:21 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 230/1251] eta: 0:08:52 lr: 0.000437 loss: 3.1293 (3.2737) grad_norm: 1.5076 (1.5516) time: 0.5036 [2021-03-26 09:13:26 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 240/1251] eta: 0:08:47 lr: 0.000437 loss: 3.3385 (3.2815) grad_norm: 1.5280 (1.5525) time: 0.5152 [2021-03-26 09:13:31 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 250/1251] eta: 0:08:41 lr: 0.000437 loss: 3.3580 (3.2893) grad_norm: 1.4484 (1.5487) time: 0.5148 [2021-03-26 09:13:36 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 260/1251] eta: 0:08:35 lr: 0.000437 loss: 3.3450 (3.2848) grad_norm: 1.4571 (1.5502) time: 0.5055 [2021-03-26 09:13:41 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 270/1251] eta: 0:08:29 lr: 0.000437 loss: 3.3479 (3.2865) grad_norm: 1.5332 (1.5496) time: 0.5028 [2021-03-26 09:13:46 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 280/1251] eta: 0:08:24 lr: 0.000437 loss: 3.3479 (3.2829) grad_norm: 1.5332 (1.5488) time: 0.5016 [2021-03-26 09:13:51 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 290/1251] eta: 0:08:18 lr: 0.000437 loss: 3.2086 (3.2701) grad_norm: 1.4382 (1.5454) time: 0.5040 [2021-03-26 09:13:56 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 300/1251] eta: 0:08:12 lr: 0.000437 loss: 2.9111 (3.2652) grad_norm: 1.4382 (1.5425) time: 0.5026 [2021-03-26 09:14:01 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 310/1251] eta: 0:08:06 lr: 0.000437 loss: 3.3500 (3.2733) grad_norm: 1.4632 (1.5394) time: 0.5012 [2021-03-26 09:14:06 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 320/1251] eta: 0:08:01 lr: 0.000437 loss: 3.4711 (3.2826) grad_norm: 1.4671 (1.5379) time: 0.5029 [2021-03-26 09:14:11 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 330/1251] eta: 0:07:55 lr: 0.000436 loss: 3.5043 (3.2865) grad_norm: 1.5387 (1.5399) time: 0.5016 [2021-03-26 09:14:16 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 340/1251] eta: 0:07:50 lr: 0.000436 loss: 3.3300 (3.2812) grad_norm: 1.5410 (1.5417) time: 0.4983 [2021-03-26 09:14:22 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 350/1251] eta: 0:07:44 lr: 0.000436 loss: 3.1655 (3.2776) grad_norm: 1.4930 (1.5408) time: 0.5093 [2021-03-26 09:14:27 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 360/1251] eta: 0:07:39 lr: 0.000436 loss: 3.2156 (3.2786) grad_norm: 1.4962 (1.5418) time: 0.5127 [2021-03-26 09:14:32 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 370/1251] eta: 0:07:33 lr: 0.000436 loss: 3.3968 (3.2790) grad_norm: 1.5384 (1.5407) time: 0.5009 [2021-03-26 09:14:37 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 380/1251] eta: 0:07:28 lr: 0.000436 loss: 3.4368 (3.2835) grad_norm: 1.5384 (1.5419) time: 0.4993 [2021-03-26 09:14:42 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 390/1251] eta: 0:07:22 lr: 0.000436 loss: 3.3516 (3.2820) grad_norm: 1.5474 (1.5421) time: 0.4982 [2021-03-26 09:14:47 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 400/1251] eta: 0:07:17 lr: 0.000436 loss: 3.3516 (3.2841) grad_norm: 1.5474 (1.5442) time: 0.5008 [2021-03-26 09:14:52 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 410/1251] eta: 0:07:12 lr: 0.000436 loss: 3.3452 (3.2835) grad_norm: 1.5594 (1.5435) time: 0.5052 [2021-03-26 09:14:57 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 420/1251] eta: 0:07:06 lr: 0.000436 loss: 3.2133 (3.2793) grad_norm: 1.4797 (1.5432) time: 0.5028 [2021-03-26 09:15:02 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 430/1251] eta: 0:07:01 lr: 0.000436 loss: 3.2764 (3.2752) grad_norm: 1.4972 (1.5456) time: 0.5067 [2021-03-26 09:15:07 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 440/1251] eta: 0:06:56 lr: 0.000436 loss: 3.2060 (3.2697) grad_norm: 1.6138 (1.5469) time: 0.5058 [2021-03-26 09:15:12 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 450/1251] eta: 0:06:51 lr: 0.000436 loss: 3.4004 (3.2747) grad_norm: 1.5565 (1.5464) time: 0.5029 [2021-03-26 09:15:17 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 460/1251] eta: 0:06:45 lr: 0.000436 loss: 3.4962 (3.2798) grad_norm: 1.4149 (1.5440) time: 0.5018 [2021-03-26 09:15:22 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 470/1251] eta: 0:06:40 lr: 0.000436 loss: 3.3980 (3.2701) grad_norm: 1.5002 (1.5459) time: 0.5009 [2021-03-26 09:15:27 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 480/1251] eta: 0:06:34 lr: 0.000436 loss: 3.3667 (3.2715) grad_norm: 1.5406 (1.5474) time: 0.4998 [2021-03-26 09:15:32 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 490/1251] eta: 0:06:29 lr: 0.000436 loss: 3.3667 (3.2693) grad_norm: 1.5349 (1.5463) time: 0.4963 [2021-03-26 09:15:37 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 500/1251] eta: 0:06:24 lr: 0.000436 loss: 3.3241 (3.2698) grad_norm: 1.4784 (1.5455) time: 0.4935 [2021-03-26 09:15:42 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 510/1251] eta: 0:06:19 lr: 0.000436 loss: 3.3321 (3.2710) grad_norm: 1.4967 (1.5450) time: 0.5034 [2021-03-26 09:15:47 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 520/1251] eta: 0:06:13 lr: 0.000436 loss: 3.3120 (3.2698) grad_norm: 1.4967 (1.5439) time: 0.5093 [2021-03-26 09:15:52 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 530/1251] eta: 0:06:08 lr: 0.000436 loss: 3.3868 (3.2754) grad_norm: 1.5004 (1.5439) time: 0.5021 [2021-03-26 09:15:57 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 540/1251] eta: 0:06:03 lr: 0.000436 loss: 3.4236 (3.2767) grad_norm: 1.5273 (1.5435) time: 0.5046 [2021-03-26 09:16:02 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 550/1251] eta: 0:05:58 lr: 0.000436 loss: 3.3701 (3.2780) grad_norm: 1.5273 (1.5442) time: 0.5175 [2021-03-26 09:16:07 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 560/1251] eta: 0:05:53 lr: 0.000436 loss: 3.1835 (3.2772) grad_norm: 1.5829 (1.5461) time: 0.5162 [2021-03-26 09:16:13 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 570/1251] eta: 0:05:48 lr: 0.000435 loss: 3.1835 (3.2760) grad_norm: 1.5530 (1.5464) time: 0.5073 [2021-03-26 09:16:18 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 580/1251] eta: 0:05:43 lr: 0.000435 loss: 3.1650 (3.2744) grad_norm: 1.5807 (1.5483) time: 0.5193 [2021-03-26 09:16:23 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 590/1251] eta: 0:05:38 lr: 0.000435 loss: 3.1214 (3.2729) grad_norm: 1.6910 (1.5516) time: 0.5211 [2021-03-26 09:16:28 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 600/1251] eta: 0:05:32 lr: 0.000435 loss: 3.3038 (3.2737) grad_norm: 1.6035 (1.5513) time: 0.5071 [2021-03-26 09:16:33 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 610/1251] eta: 0:05:27 lr: 0.000435 loss: 3.3450 (3.2739) grad_norm: 1.4835 (1.5502) time: 0.4999 [2021-03-26 09:16:38 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 620/1251] eta: 0:05:22 lr: 0.000435 loss: 2.9871 (3.2684) grad_norm: 1.4487 (1.5487) time: 0.5020 [2021-03-26 09:16:43 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 630/1251] eta: 0:05:17 lr: 0.000435 loss: 3.3550 (3.2711) grad_norm: 1.4453 (1.5480) time: 0.5011 [2021-03-26 09:16:48 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 640/1251] eta: 0:05:12 lr: 0.000435 loss: 3.3951 (3.2724) grad_norm: 1.5146 (1.5482) time: 0.4981 [2021-03-26 09:16:53 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 650/1251] eta: 0:05:06 lr: 0.000435 loss: 3.2906 (3.2709) grad_norm: 1.5698 (1.5492) time: 0.5004 [2021-03-26 09:16:58 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 660/1251] eta: 0:05:01 lr: 0.000435 loss: 3.4020 (3.2742) grad_norm: 1.5698 (1.5492) time: 0.5039 [2021-03-26 09:17:03 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 670/1251] eta: 0:04:56 lr: 0.000435 loss: 3.4052 (3.2727) grad_norm: 1.4835 (1.5482) time: 0.5013 [2021-03-26 09:17:08 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 680/1251] eta: 0:04:51 lr: 0.000435 loss: 3.2414 (3.2724) grad_norm: 1.4937 (1.5485) time: 0.5009 [2021-03-26 09:17:13 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 690/1251] eta: 0:04:46 lr: 0.000435 loss: 3.3426 (3.2689) grad_norm: 1.4881 (1.5486) time: 0.5047 [2021-03-26 09:17:18 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 700/1251] eta: 0:04:41 lr: 0.000435 loss: 3.2719 (3.2698) grad_norm: 1.4881 (1.5481) time: 0.5007 [2021-03-26 09:17:23 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 710/1251] eta: 0:04:35 lr: 0.000435 loss: 3.1620 (3.2637) grad_norm: 1.4925 (1.5472) time: 0.4985 [2021-03-26 09:17:28 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 720/1251] eta: 0:04:30 lr: 0.000435 loss: 3.0964 (3.2635) grad_norm: 1.5414 (1.5474) time: 0.5087 [2021-03-26 09:17:33 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 730/1251] eta: 0:04:25 lr: 0.000435 loss: 3.3521 (3.2634) grad_norm: 1.5414 (1.5466) time: 0.5122 [2021-03-26 09:17:39 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 740/1251] eta: 0:04:20 lr: 0.000435 loss: 3.2103 (3.2633) grad_norm: 1.5088 (1.5466) time: 0.5333 [2021-03-26 09:17:44 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 750/1251] eta: 0:04:15 lr: 0.000435 loss: 3.1890 (3.2632) grad_norm: 1.5088 (1.5459) time: 0.5352 [2021-03-26 09:17:49 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 760/1251] eta: 0:04:10 lr: 0.000435 loss: 3.3605 (3.2654) grad_norm: 1.4924 (1.5473) time: 0.5030 [2021-03-26 09:17:54 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 770/1251] eta: 0:04:05 lr: 0.000435 loss: 3.2720 (3.2647) grad_norm: 1.5271 (1.5476) time: 0.5038 [2021-03-26 09:17:59 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 780/1251] eta: 0:04:00 lr: 0.000435 loss: 3.1641 (3.2643) grad_norm: 1.5606 (1.5481) time: 0.5128 [2021-03-26 09:18:04 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 790/1251] eta: 0:03:55 lr: 0.000435 loss: 3.1935 (3.2619) grad_norm: 1.5870 (1.5484) time: 0.5079 [2021-03-26 09:18:09 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 800/1251] eta: 0:03:50 lr: 0.000435 loss: 3.1408 (3.2598) grad_norm: 1.6112 (1.5495) time: 0.5054 [2021-03-26 09:18:14 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 810/1251] eta: 0:03:45 lr: 0.000434 loss: 3.2201 (3.2588) grad_norm: 1.5363 (1.5490) time: 0.5086 [2021-03-26 09:18:19 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 820/1251] eta: 0:03:39 lr: 0.000434 loss: 3.4156 (3.2607) grad_norm: 1.4978 (1.5482) time: 0.5035 [2021-03-26 09:18:24 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 830/1251] eta: 0:03:34 lr: 0.000434 loss: 3.5492 (3.2632) grad_norm: 1.5010 (1.5479) time: 0.4983 [2021-03-26 09:18:29 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 840/1251] eta: 0:03:29 lr: 0.000434 loss: 3.3897 (3.2623) grad_norm: 1.5094 (1.5476) time: 0.4980 [2021-03-26 09:18:34 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 850/1251] eta: 0:03:24 lr: 0.000434 loss: 3.3897 (3.2641) grad_norm: 1.5214 (1.5476) time: 0.5006 [2021-03-26 09:18:39 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 860/1251] eta: 0:03:19 lr: 0.000434 loss: 3.4807 (3.2657) grad_norm: 1.5019 (1.5480) time: 0.5013 [2021-03-26 09:18:44 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 870/1251] eta: 0:03:14 lr: 0.000434 loss: 3.4981 (3.2674) grad_norm: 1.5739 (1.5485) time: 0.5020 [2021-03-26 09:18:50 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 880/1251] eta: 0:03:09 lr: 0.000434 loss: 3.6442 (3.2667) grad_norm: 1.5786 (1.5497) time: 0.5047 [2021-03-26 09:18:55 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 890/1251] eta: 0:03:03 lr: 0.000434 loss: 3.3181 (3.2646) grad_norm: 1.5645 (1.5502) time: 0.5056 [2021-03-26 09:19:00 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 900/1251] eta: 0:02:58 lr: 0.000434 loss: 3.0692 (3.2632) grad_norm: 1.4806 (1.5495) time: 0.5065 [2021-03-26 09:19:05 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 910/1251] eta: 0:02:53 lr: 0.000434 loss: 3.0750 (3.2624) grad_norm: 1.4308 (1.5483) time: 0.5069 [2021-03-26 09:19:10 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 920/1251] eta: 0:02:48 lr: 0.000434 loss: 3.4867 (3.2650) grad_norm: 1.4411 (1.5469) time: 0.5070 [2021-03-26 09:19:15 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 930/1251] eta: 0:02:43 lr: 0.000434 loss: 3.5140 (3.2652) grad_norm: 1.4614 (1.5463) time: 0.5056 [2021-03-26 09:19:20 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 940/1251] eta: 0:02:38 lr: 0.000434 loss: 3.3301 (3.2637) grad_norm: 1.4825 (1.5462) time: 0.5077 [2021-03-26 09:19:25 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 950/1251] eta: 0:02:33 lr: 0.000434 loss: 3.3196 (3.2647) grad_norm: 1.5159 (1.5461) time: 0.5035 [2021-03-26 09:19:30 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 960/1251] eta: 0:02:28 lr: 0.000434 loss: 3.3370 (3.2637) grad_norm: 1.4914 (1.5460) time: 0.4975 [2021-03-26 09:19:35 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 970/1251] eta: 0:02:23 lr: 0.000434 loss: 3.2975 (3.2637) grad_norm: 1.4698 (1.5466) time: 0.4995 [2021-03-26 09:19:40 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 980/1251] eta: 0:02:17 lr: 0.000434 loss: 3.3362 (3.2658) grad_norm: 1.4698 (1.5462) time: 0.5077 [2021-03-26 09:19:45 swin_small_patch4_window7_224] INFO: Epoch: [163] [ 990/1251] eta: 0:02:12 lr: 0.000434 loss: 3.3299 (3.2657) grad_norm: 1.5474 (1.5463) time: 0.5055 [2021-03-26 09:19:50 swin_small_patch4_window7_224] INFO: Epoch: [163] [1000/1251] eta: 0:02:07 lr: 0.000434 loss: 3.2450 (3.2647) grad_norm: 1.5671 (1.5463) time: 0.5048 [2021-03-26 09:19:55 swin_small_patch4_window7_224] INFO: Epoch: [163] [1010/1251] eta: 0:02:02 lr: 0.000434 loss: 3.0918 (3.2622) grad_norm: 1.4662 (1.5455) time: 0.5107 [2021-03-26 09:20:00 swin_small_patch4_window7_224] INFO: Epoch: [163] [1020/1251] eta: 0:01:57 lr: 0.000434 loss: 3.0918 (3.2611) grad_norm: 1.4662 (1.5448) time: 0.5057 [2021-03-26 09:20:05 swin_small_patch4_window7_224] INFO: Epoch: [163] [1030/1251] eta: 0:01:52 lr: 0.000434 loss: 3.1499 (3.2618) grad_norm: 1.5169 (1.5451) time: 0.5098 [2021-03-26 09:20:10 swin_small_patch4_window7_224] INFO: Epoch: [163] [1040/1251] eta: 0:01:47 lr: 0.000434 loss: 3.3855 (3.2633) grad_norm: 1.5406 (1.5448) time: 0.5100 [2021-03-26 09:20:15 swin_small_patch4_window7_224] INFO: Epoch: [163] [1050/1251] eta: 0:01:42 lr: 0.000434 loss: 3.3855 (3.2628) grad_norm: 1.5777 (1.5457) time: 0.5016 [2021-03-26 09:20:21 swin_small_patch4_window7_224] INFO: Epoch: [163] [1060/1251] eta: 0:01:37 lr: 0.000433 loss: 3.2928 (3.2624) grad_norm: 1.5842 (1.5455) time: 0.5034 [2021-03-26 09:20:26 swin_small_patch4_window7_224] INFO: Epoch: [163] [1070/1251] eta: 0:01:32 lr: 0.000433 loss: 3.1793 (3.2609) grad_norm: 1.4465 (1.5450) time: 0.5081 [2021-03-26 09:20:31 swin_small_patch4_window7_224] INFO: Epoch: [163] [1080/1251] eta: 0:01:27 lr: 0.000433 loss: 3.0904 (3.2583) grad_norm: 1.4667 (1.5449) time: 0.5058 [2021-03-26 09:20:36 swin_small_patch4_window7_224] INFO: Epoch: [163] [1090/1251] eta: 0:01:21 lr: 0.000433 loss: 3.0050 (3.2566) grad_norm: 1.5261 (1.5447) time: 0.5009 [2021-03-26 09:20:41 swin_small_patch4_window7_224] INFO: Epoch: [163] [1100/1251] eta: 0:01:16 lr: 0.000433 loss: 3.3939 (3.2602) grad_norm: 1.5301 (1.5450) time: 0.4990 [2021-03-26 09:20:46 swin_small_patch4_window7_224] INFO: Epoch: [163] [1110/1251] eta: 0:01:11 lr: 0.000433 loss: 3.6164 (3.2624) grad_norm: 1.5288 (1.5449) time: 0.4978 [2021-03-26 09:20:51 swin_small_patch4_window7_224] INFO: Epoch: [163] [1120/1251] eta: 0:01:06 lr: 0.000433 loss: 3.4495 (3.2612) grad_norm: 1.4856 (1.5450) time: 0.4995 [2021-03-26 09:20:56 swin_small_patch4_window7_224] INFO: Epoch: [163] [1130/1251] eta: 0:01:01 lr: 0.000433 loss: 3.3180 (3.2621) grad_norm: 1.5238 (1.5451) time: 0.5028 [2021-03-26 09:21:01 swin_small_patch4_window7_224] INFO: Epoch: [163] [1140/1251] eta: 0:00:56 lr: 0.000433 loss: 3.4280 (3.2608) grad_norm: 1.5175 (1.5445) time: 0.5040 [2021-03-26 09:21:06 swin_small_patch4_window7_224] INFO: Epoch: [163] [1150/1251] eta: 0:00:51 lr: 0.000433 loss: 3.0682 (3.2601) grad_norm: 1.5009 (1.5445) time: 0.5049 [2021-03-26 09:21:11 swin_small_patch4_window7_224] INFO: Epoch: [163] [1160/1251] eta: 0:00:46 lr: 0.000433 loss: 3.0304 (3.2587) grad_norm: 1.5541 (1.5447) time: 0.4998 [2021-03-26 09:21:16 swin_small_patch4_window7_224] INFO: Epoch: [163] [1170/1251] eta: 0:00:41 lr: 0.000433 loss: 3.2352 (3.2590) grad_norm: 1.5487 (1.5448) time: 0.5081 [2021-03-26 09:21:21 swin_small_patch4_window7_224] INFO: Epoch: [163] [1180/1251] eta: 0:00:36 lr: 0.000433 loss: 3.3446 (3.2579) grad_norm: 1.5155 (1.5450) time: 0.5189 [2021-03-26 09:21:26 swin_small_patch4_window7_224] INFO: Epoch: [163] [1190/1251] eta: 0:00:31 lr: 0.000433 loss: 3.4328 (3.2583) grad_norm: 1.5580 (1.5453) time: 0.5157 [2021-03-26 09:21:31 swin_small_patch4_window7_224] INFO: Epoch: [163] [1200/1251] eta: 0:00:25 lr: 0.000433 loss: 3.4328 (3.2585) grad_norm: 1.5246 (1.5447) time: 0.5097 [2021-03-26 09:21:36 swin_small_patch4_window7_224] INFO: Epoch: [163] [1210/1251] eta: 0:00:20 lr: 0.000433 loss: 3.2529 (3.2587) grad_norm: 1.4960 (1.5447) time: 0.5067 [2021-03-26 09:21:41 swin_small_patch4_window7_224] INFO: Epoch: [163] [1220/1251] eta: 0:00:15 lr: 0.000433 loss: 3.4766 (3.2598) grad_norm: 1.5202 (1.5448) time: 0.5050 [2021-03-26 09:21:46 swin_small_patch4_window7_224] INFO: Epoch: [163] [1230/1251] eta: 0:00:10 lr: 0.000433 loss: 3.4722 (3.2588) grad_norm: 1.5303 (1.5454) time: 0.4974 [2021-03-26 09:21:51 swin_small_patch4_window7_224] INFO: Epoch: [163] [1240/1251] eta: 0:00:05 lr: 0.000433 loss: 3.0968 (3.2574) grad_norm: 1.5432 (1.5449) time: 0.4918 [2021-03-26 09:21:56 swin_small_patch4_window7_224] INFO: Epoch: [163] [1250/1251] eta: 0:00:00 lr: 0.000433 loss: 3.2330 (3.2586) grad_norm: 1.5381 (1.5464) time: 0.4898 [2021-03-26 09:22:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 0.9194 (0.9194) acc1: 75.0000 (75.0000) acc5: 93.7500 (93.7500) [2021-03-26 09:22:07 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9194 (0.9444) acc1: 76.5625 (78.2670) acc5: 93.7500 (94.8864) [2021-03-26 09:22:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8800 (0.9144) acc1: 76.5625 (77.6786) acc5: 95.3125 (95.1637) [2021-03-26 09:22:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8884 (0.9065) acc1: 75.0000 (77.6210) acc5: 95.3125 (95.1109) [2021-03-26 09:22:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8982 (0.9090) acc1: 78.1250 (77.7058) acc5: 93.7500 (94.6265) [2021-03-26 09:22:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8291 (0.8994) acc1: 79.6875 (78.3040) acc5: 93.7500 (94.6240) [2021-03-26 09:22:23 swin_small_patch4_window7_224] INFO: * Acc@1 78.978 Acc@5 94.700 loss 0.894 [2021-03-26 09:22:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.0% [2021-03-26 09:22:23 swin_small_patch4_window7_224] INFO: Max accuracy: 78.98% [2021-03-26 09:22:27 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 0/1251] eta: 1:24:20 lr: 0.000433 loss: 3.3843 (3.3843) grad_norm: 1.5941 (1.5941) time: 4.0454 [2021-03-26 09:22:32 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 10/1251] eta: 0:17:31 lr: 0.000433 loss: 3.4750 (3.4012) grad_norm: 1.5941 (1.5918) time: 0.8474 [2021-03-26 09:22:37 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 20/1251] eta: 0:14:04 lr: 0.000433 loss: 3.4750 (3.4448) grad_norm: 1.5280 (1.5767) time: 0.5184 [2021-03-26 09:22:42 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 30/1251] eta: 0:12:43 lr: 0.000433 loss: 3.3823 (3.4114) grad_norm: 1.5170 (1.5532) time: 0.5034 [2021-03-26 09:22:47 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 40/1251] eta: 0:12:01 lr: 0.000433 loss: 3.2769 (3.3341) grad_norm: 1.5099 (1.5538) time: 0.5010 [2021-03-26 09:22:52 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 50/1251] eta: 0:11:34 lr: 0.000432 loss: 3.1495 (3.3618) grad_norm: 1.5371 (1.5697) time: 0.5043 [2021-03-26 09:22:57 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 60/1251] eta: 0:11:11 lr: 0.000432 loss: 3.3301 (3.3258) grad_norm: 1.6130 (1.5750) time: 0.4981 [2021-03-26 09:23:02 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 70/1251] eta: 0:10:54 lr: 0.000432 loss: 3.5096 (3.3524) grad_norm: 1.5806 (1.5782) time: 0.4933 [2021-03-26 09:23:07 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 80/1251] eta: 0:10:41 lr: 0.000432 loss: 3.4668 (3.3543) grad_norm: 1.5727 (1.5806) time: 0.4997 [2021-03-26 09:23:12 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 90/1251] eta: 0:10:30 lr: 0.000432 loss: 3.3131 (3.3558) grad_norm: 1.5009 (1.5658) time: 0.5020 [2021-03-26 09:23:17 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 100/1251] eta: 0:10:20 lr: 0.000432 loss: 3.2957 (3.3387) grad_norm: 1.4863 (1.5673) time: 0.5027 [2021-03-26 09:23:22 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 110/1251] eta: 0:10:11 lr: 0.000432 loss: 3.3035 (3.3302) grad_norm: 1.4863 (1.5641) time: 0.5073 [2021-03-26 09:23:27 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 120/1251] eta: 0:10:03 lr: 0.000432 loss: 3.3035 (3.3181) grad_norm: 1.4763 (1.5638) time: 0.5041 [2021-03-26 09:23:33 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 130/1251] eta: 0:09:56 lr: 0.000432 loss: 3.2414 (3.3075) grad_norm: 1.5941 (1.5642) time: 0.5103 [2021-03-26 09:23:38 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 140/1251] eta: 0:09:49 lr: 0.000432 loss: 3.3124 (3.3025) grad_norm: 1.5155 (1.5584) time: 0.5173 [2021-03-26 09:23:43 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 150/1251] eta: 0:09:42 lr: 0.000432 loss: 3.3625 (3.3108) grad_norm: 1.4963 (1.5634) time: 0.5106 [2021-03-26 09:23:48 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 160/1251] eta: 0:09:35 lr: 0.000432 loss: 3.3995 (3.3127) grad_norm: 1.6224 (1.5686) time: 0.5044 [2021-03-26 09:23:53 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 170/1251] eta: 0:09:29 lr: 0.000432 loss: 3.3962 (3.3120) grad_norm: 1.5992 (1.5680) time: 0.5031 [2021-03-26 09:23:58 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 180/1251] eta: 0:09:23 lr: 0.000432 loss: 3.2061 (3.3046) grad_norm: 1.6113 (1.5707) time: 0.5135 [2021-03-26 09:24:03 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 190/1251] eta: 0:09:16 lr: 0.000432 loss: 3.2061 (3.2986) grad_norm: 1.6351 (1.5695) time: 0.5119 [2021-03-26 09:24:08 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 200/1251] eta: 0:09:11 lr: 0.000432 loss: 3.3990 (3.2943) grad_norm: 1.5373 (1.5664) time: 0.5119 [2021-03-26 09:24:13 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 210/1251] eta: 0:09:05 lr: 0.000432 loss: 3.5114 (3.3060) grad_norm: 1.5630 (1.5676) time: 0.5151 [2021-03-26 09:24:18 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 220/1251] eta: 0:08:58 lr: 0.000432 loss: 3.3958 (3.2997) grad_norm: 1.5702 (1.5647) time: 0.5031 [2021-03-26 09:24:23 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 230/1251] eta: 0:08:53 lr: 0.000432 loss: 3.3579 (3.3015) grad_norm: 1.5231 (1.5630) time: 0.5021 [2021-03-26 09:24:28 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 240/1251] eta: 0:08:47 lr: 0.000432 loss: 3.3266 (3.2899) grad_norm: 1.5327 (1.5632) time: 0.5050 [2021-03-26 09:24:33 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 250/1251] eta: 0:08:40 lr: 0.000432 loss: 3.2356 (3.2858) grad_norm: 1.5474 (1.5625) time: 0.5018 [2021-03-26 09:24:39 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 260/1251] eta: 0:08:35 lr: 0.000432 loss: 3.1218 (3.2853) grad_norm: 1.4866 (1.5603) time: 0.5013 [2021-03-26 09:24:44 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 270/1251] eta: 0:08:29 lr: 0.000432 loss: 2.9008 (3.2713) grad_norm: 1.5194 (1.5597) time: 0.5024 [2021-03-26 09:24:49 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 280/1251] eta: 0:08:23 lr: 0.000432 loss: 3.2129 (3.2703) grad_norm: 1.4643 (1.5580) time: 0.5036 [2021-03-26 09:24:54 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 290/1251] eta: 0:08:18 lr: 0.000432 loss: 3.2129 (3.2631) grad_norm: 1.5325 (1.5611) time: 0.5100 [2021-03-26 09:24:59 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 300/1251] eta: 0:08:12 lr: 0.000431 loss: 3.0264 (3.2616) grad_norm: 1.6024 (1.5598) time: 0.5107 [2021-03-26 09:25:04 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 310/1251] eta: 0:08:06 lr: 0.000431 loss: 3.2362 (3.2628) grad_norm: 1.4614 (1.5569) time: 0.5020 [2021-03-26 09:25:09 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 320/1251] eta: 0:08:01 lr: 0.000431 loss: 3.2075 (3.2584) grad_norm: 1.4589 (1.5551) time: 0.5034 [2021-03-26 09:25:14 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 330/1251] eta: 0:07:55 lr: 0.000431 loss: 3.2135 (3.2640) grad_norm: 1.4950 (1.5534) time: 0.5016 [2021-03-26 09:25:19 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 340/1251] eta: 0:07:50 lr: 0.000431 loss: 3.1686 (3.2618) grad_norm: 1.5093 (1.5530) time: 0.5025 [2021-03-26 09:25:24 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 350/1251] eta: 0:07:44 lr: 0.000431 loss: 3.2168 (3.2670) grad_norm: 1.5622 (1.5555) time: 0.5094 [2021-03-26 09:25:29 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 360/1251] eta: 0:07:39 lr: 0.000431 loss: 3.2192 (3.2623) grad_norm: 1.5885 (1.5568) time: 0.5059 [2021-03-26 09:25:34 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 370/1251] eta: 0:07:33 lr: 0.000431 loss: 3.2214 (3.2607) grad_norm: 1.5097 (1.5555) time: 0.5007 [2021-03-26 09:25:39 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 380/1251] eta: 0:07:28 lr: 0.000431 loss: 3.2477 (3.2590) grad_norm: 1.5097 (1.5550) time: 0.5010 [2021-03-26 09:25:44 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 390/1251] eta: 0:07:23 lr: 0.000431 loss: 3.3487 (3.2609) grad_norm: 1.5094 (1.5538) time: 0.5043 [2021-03-26 09:25:49 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 400/1251] eta: 0:07:17 lr: 0.000431 loss: 3.5267 (3.2653) grad_norm: 1.5094 (1.5538) time: 0.5000 [2021-03-26 09:25:54 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 410/1251] eta: 0:07:12 lr: 0.000431 loss: 3.3422 (3.2639) grad_norm: 1.5338 (1.5557) time: 0.4964 [2021-03-26 09:25:59 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 420/1251] eta: 0:07:06 lr: 0.000431 loss: 3.3379 (3.2690) grad_norm: 1.5042 (1.5567) time: 0.5005 [2021-03-26 09:26:04 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 430/1251] eta: 0:07:01 lr: 0.000431 loss: 3.3605 (3.2659) grad_norm: 1.5290 (1.5576) time: 0.5078 [2021-03-26 09:26:09 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 440/1251] eta: 0:06:56 lr: 0.000431 loss: 3.1230 (3.2646) grad_norm: 1.5707 (1.5596) time: 0.5052 [2021-03-26 09:26:14 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 450/1251] eta: 0:06:51 lr: 0.000431 loss: 3.3413 (3.2659) grad_norm: 1.5444 (1.5575) time: 0.5048 [2021-03-26 09:26:19 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 460/1251] eta: 0:06:45 lr: 0.000431 loss: 3.4008 (3.2689) grad_norm: 1.4864 (1.5564) time: 0.5059 [2021-03-26 09:26:24 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 470/1251] eta: 0:06:40 lr: 0.000431 loss: 3.4836 (3.2655) grad_norm: 1.5137 (1.5576) time: 0.5044 [2021-03-26 09:26:29 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 480/1251] eta: 0:06:35 lr: 0.000431 loss: 3.1632 (3.2626) grad_norm: 1.5809 (1.5584) time: 0.5065 [2021-03-26 09:26:35 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 490/1251] eta: 0:06:30 lr: 0.000431 loss: 3.1483 (3.2568) grad_norm: 1.5456 (1.5578) time: 0.5084 [2021-03-26 09:26:40 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 500/1251] eta: 0:06:24 lr: 0.000431 loss: 3.1620 (3.2578) grad_norm: 1.5028 (nan) time: 0.5024 [2021-03-26 09:26:45 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 510/1251] eta: 0:06:19 lr: 0.000431 loss: 3.2775 (3.2524) grad_norm: 1.5084 (nan) time: 0.5014 [2021-03-26 09:26:50 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 520/1251] eta: 0:06:14 lr: 0.000431 loss: 3.2630 (3.2523) grad_norm: 1.5503 (nan) time: 0.5036 [2021-03-26 09:26:55 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 530/1251] eta: 0:06:08 lr: 0.000431 loss: 3.3588 (3.2500) grad_norm: 1.5545 (nan) time: 0.4977 [2021-03-26 09:27:00 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 540/1251] eta: 0:06:03 lr: 0.000430 loss: 3.3588 (3.2522) grad_norm: 1.4711 (nan) time: 0.5023 [2021-03-26 09:27:05 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 550/1251] eta: 0:05:58 lr: 0.000430 loss: 3.4595 (3.2563) grad_norm: 1.4868 (nan) time: 0.5213 [2021-03-26 09:27:10 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 560/1251] eta: 0:05:53 lr: 0.000430 loss: 3.4595 (3.2567) grad_norm: 1.5105 (nan) time: 0.5141 [2021-03-26 09:27:15 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 570/1251] eta: 0:05:48 lr: 0.000430 loss: 3.3707 (3.2553) grad_norm: 1.6172 (nan) time: 0.4975 [2021-03-26 09:27:20 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 580/1251] eta: 0:05:43 lr: 0.000430 loss: 3.3707 (3.2553) grad_norm: 1.5559 (nan) time: 0.5017 [2021-03-26 09:27:25 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 590/1251] eta: 0:05:37 lr: 0.000430 loss: 3.4809 (3.2568) grad_norm: 1.5287 (nan) time: 0.4979 [2021-03-26 09:27:30 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 600/1251] eta: 0:05:32 lr: 0.000430 loss: 3.5765 (3.2611) grad_norm: 1.5268 (nan) time: 0.4977 [2021-03-26 09:27:35 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 610/1251] eta: 0:05:27 lr: 0.000430 loss: 3.3806 (3.2600) grad_norm: 1.4970 (nan) time: 0.5039 [2021-03-26 09:27:40 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 620/1251] eta: 0:05:22 lr: 0.000430 loss: 3.2233 (3.2606) grad_norm: 1.5320 (nan) time: 0.5052 [2021-03-26 09:27:45 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 630/1251] eta: 0:05:17 lr: 0.000430 loss: 3.2233 (3.2590) grad_norm: 1.5320 (nan) time: 0.5043 [2021-03-26 09:27:50 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 640/1251] eta: 0:05:11 lr: 0.000430 loss: 3.3041 (3.2612) grad_norm: 1.5421 (nan) time: 0.5047 [2021-03-26 09:27:55 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 650/1251] eta: 0:05:06 lr: 0.000430 loss: 3.4633 (3.2645) grad_norm: 1.5573 (nan) time: 0.5006 [2021-03-26 09:28:00 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 660/1251] eta: 0:05:01 lr: 0.000430 loss: 3.2930 (3.2641) grad_norm: 1.5055 (nan) time: 0.4979 [2021-03-26 09:28:05 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 670/1251] eta: 0:04:56 lr: 0.000430 loss: 3.4100 (3.2669) grad_norm: 1.5055 (nan) time: 0.5024 [2021-03-26 09:28:10 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 680/1251] eta: 0:04:51 lr: 0.000430 loss: 3.2942 (3.2626) grad_norm: 1.5103 (nan) time: 0.5063 [2021-03-26 09:28:15 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 690/1251] eta: 0:04:46 lr: 0.000430 loss: 3.0909 (3.2638) grad_norm: 1.5347 (nan) time: 0.5036 [2021-03-26 09:28:20 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 700/1251] eta: 0:04:40 lr: 0.000430 loss: 3.2866 (3.2636) grad_norm: 1.4344 (nan) time: 0.4987 [2021-03-26 09:28:25 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 710/1251] eta: 0:04:35 lr: 0.000430 loss: 3.2866 (3.2646) grad_norm: 1.4972 (nan) time: 0.5013 [2021-03-26 09:28:30 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 720/1251] eta: 0:04:30 lr: 0.000430 loss: 3.3685 (3.2648) grad_norm: 1.5721 (nan) time: 0.4991 [2021-03-26 09:28:35 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 730/1251] eta: 0:04:25 lr: 0.000430 loss: 3.3786 (3.2668) grad_norm: 1.5107 (nan) time: 0.5060 [2021-03-26 09:28:41 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 740/1251] eta: 0:04:20 lr: 0.000430 loss: 3.3786 (3.2678) grad_norm: 1.4317 (nan) time: 0.5305 [2021-03-26 09:28:46 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 750/1251] eta: 0:04:15 lr: 0.000430 loss: 3.4226 (3.2720) grad_norm: 1.4961 (nan) time: 0.5264 [2021-03-26 09:28:51 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 760/1251] eta: 0:04:10 lr: 0.000430 loss: 3.4522 (3.2715) grad_norm: 1.5255 (nan) time: 0.5021 [2021-03-26 09:28:56 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 770/1251] eta: 0:04:05 lr: 0.000430 loss: 3.3889 (3.2722) grad_norm: 1.5057 (nan) time: 0.4962 [2021-03-26 09:29:01 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 780/1251] eta: 0:04:00 lr: 0.000429 loss: 3.3379 (3.2703) grad_norm: 1.5197 (nan) time: 0.5043 [2021-03-26 09:29:06 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 790/1251] eta: 0:03:54 lr: 0.000429 loss: 3.1434 (3.2685) grad_norm: 1.5469 (nan) time: 0.5063 [2021-03-26 09:29:11 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 800/1251] eta: 0:03:49 lr: 0.000429 loss: 3.4414 (3.2706) grad_norm: 1.5000 (nan) time: 0.5071 [2021-03-26 09:29:16 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 810/1251] eta: 0:03:44 lr: 0.000429 loss: 3.4813 (3.2708) grad_norm: 1.5117 (nan) time: 0.5068 [2021-03-26 09:29:21 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 820/1251] eta: 0:03:39 lr: 0.000429 loss: 3.3575 (3.2680) grad_norm: 1.6059 (nan) time: 0.5053 [2021-03-26 09:29:26 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 830/1251] eta: 0:03:34 lr: 0.000429 loss: 3.2982 (3.2681) grad_norm: 1.5828 (nan) time: 0.5064 [2021-03-26 09:29:31 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 840/1251] eta: 0:03:29 lr: 0.000429 loss: 3.4151 (3.2699) grad_norm: 1.5828 (nan) time: 0.5092 [2021-03-26 09:29:36 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 850/1251] eta: 0:03:24 lr: 0.000429 loss: 3.3245 (3.2701) grad_norm: 1.5631 (nan) time: 0.5119 [2021-03-26 09:29:41 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 860/1251] eta: 0:03:19 lr: 0.000429 loss: 3.3027 (3.2707) grad_norm: 1.5577 (nan) time: 0.5054 [2021-03-26 09:29:47 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 870/1251] eta: 0:03:14 lr: 0.000429 loss: 3.3759 (3.2705) grad_norm: 1.5013 (nan) time: 0.5059 [2021-03-26 09:29:52 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 880/1251] eta: 0:03:08 lr: 0.000429 loss: 3.3861 (3.2719) grad_norm: 1.5091 (nan) time: 0.5103 [2021-03-26 09:29:57 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 890/1251] eta: 0:03:03 lr: 0.000429 loss: 3.4887 (3.2730) grad_norm: 1.5849 (nan) time: 0.5068 [2021-03-26 09:30:02 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 900/1251] eta: 0:02:58 lr: 0.000429 loss: 3.4539 (3.2750) grad_norm: 1.5018 (nan) time: 0.4991 [2021-03-26 09:30:07 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 910/1251] eta: 0:02:53 lr: 0.000429 loss: 3.4539 (3.2738) grad_norm: 1.5206 (nan) time: 0.4975 [2021-03-26 09:30:12 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 920/1251] eta: 0:02:48 lr: 0.000429 loss: 3.4317 (3.2745) grad_norm: 1.5206 (nan) time: 0.5044 [2021-03-26 09:30:17 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 930/1251] eta: 0:02:43 lr: 0.000429 loss: 3.4317 (3.2759) grad_norm: 1.5564 (nan) time: 0.5101 [2021-03-26 09:30:22 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 940/1251] eta: 0:02:38 lr: 0.000429 loss: 3.4175 (3.2766) grad_norm: 1.5545 (nan) time: 0.5182 [2021-03-26 09:30:27 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 950/1251] eta: 0:02:33 lr: 0.000429 loss: 3.2181 (3.2753) grad_norm: 1.5097 (nan) time: 0.5082 [2021-03-26 09:30:32 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 960/1251] eta: 0:02:28 lr: 0.000429 loss: 3.1188 (3.2741) grad_norm: 1.5643 (nan) time: 0.4940 [2021-03-26 09:30:37 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 970/1251] eta: 0:02:22 lr: 0.000429 loss: 3.1595 (3.2761) grad_norm: 1.5643 (nan) time: 0.4971 [2021-03-26 09:30:42 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 980/1251] eta: 0:02:17 lr: 0.000429 loss: 3.2844 (3.2742) grad_norm: 1.4993 (nan) time: 0.4973 [2021-03-26 09:30:47 swin_small_patch4_window7_224] INFO: Epoch: [164] [ 990/1251] eta: 0:02:12 lr: 0.000429 loss: 3.1365 (3.2736) grad_norm: 1.5352 (nan) time: 0.4955 [2021-03-26 09:30:52 swin_small_patch4_window7_224] INFO: Epoch: [164] [1000/1251] eta: 0:02:07 lr: 0.000429 loss: 3.0561 (3.2707) grad_norm: 1.5575 (nan) time: 0.4965 [2021-03-26 09:30:57 swin_small_patch4_window7_224] INFO: Epoch: [164] [1010/1251] eta: 0:02:02 lr: 0.000429 loss: 2.9509 (3.2682) grad_norm: 1.5166 (nan) time: 0.4985 [2021-03-26 09:31:02 swin_small_patch4_window7_224] INFO: Epoch: [164] [1020/1251] eta: 0:01:57 lr: 0.000429 loss: 3.3000 (3.2708) grad_norm: 1.5956 (nan) time: 0.4977 [2021-03-26 09:31:07 swin_small_patch4_window7_224] INFO: Epoch: [164] [1030/1251] eta: 0:01:52 lr: 0.000428 loss: 3.5701 (3.2708) grad_norm: 1.6211 (nan) time: 0.5036 [2021-03-26 09:31:12 swin_small_patch4_window7_224] INFO: Epoch: [164] [1040/1251] eta: 0:01:47 lr: 0.000428 loss: 3.3824 (3.2705) grad_norm: 1.5921 (nan) time: 0.5097 [2021-03-26 09:31:17 swin_small_patch4_window7_224] INFO: Epoch: [164] [1050/1251] eta: 0:01:42 lr: 0.000428 loss: 3.2551 (3.2700) grad_norm: 1.5921 (nan) time: 0.5073 [2021-03-26 09:31:22 swin_small_patch4_window7_224] INFO: Epoch: [164] [1060/1251] eta: 0:01:37 lr: 0.000428 loss: 3.3163 (3.2715) grad_norm: 1.5809 (nan) time: 0.5063 [2021-03-26 09:31:27 swin_small_patch4_window7_224] INFO: Epoch: [164] [1070/1251] eta: 0:01:31 lr: 0.000428 loss: 3.4825 (3.2722) grad_norm: 1.6019 (nan) time: 0.5122 [2021-03-26 09:31:32 swin_small_patch4_window7_224] INFO: Epoch: [164] [1080/1251] eta: 0:01:26 lr: 0.000428 loss: 3.2415 (3.2707) grad_norm: 1.6019 (nan) time: 0.5096 [2021-03-26 09:31:37 swin_small_patch4_window7_224] INFO: Epoch: [164] [1090/1251] eta: 0:01:21 lr: 0.000428 loss: 2.9750 (3.2681) grad_norm: 1.5296 (nan) time: 0.5041 [2021-03-26 09:31:43 swin_small_patch4_window7_224] INFO: Epoch: [164] [1100/1251] eta: 0:01:16 lr: 0.000428 loss: 3.2483 (3.2676) grad_norm: 1.4422 (nan) time: 0.5079 [2021-03-26 09:31:48 swin_small_patch4_window7_224] INFO: Epoch: [164] [1110/1251] eta: 0:01:11 lr: 0.000428 loss: 3.2535 (3.2678) grad_norm: 1.4657 (nan) time: 0.5081 [2021-03-26 09:31:53 swin_small_patch4_window7_224] INFO: Epoch: [164] [1120/1251] eta: 0:01:06 lr: 0.000428 loss: 3.3125 (3.2683) grad_norm: 1.5236 (nan) time: 0.5079 [2021-03-26 09:31:58 swin_small_patch4_window7_224] INFO: Epoch: [164] [1130/1251] eta: 0:01:01 lr: 0.000428 loss: 3.5217 (3.2712) grad_norm: 1.5278 (nan) time: 0.5018 [2021-03-26 09:32:03 swin_small_patch4_window7_224] INFO: Epoch: [164] [1140/1251] eta: 0:00:56 lr: 0.000428 loss: 3.2866 (3.2698) grad_norm: 1.5278 (nan) time: 0.5006 [2021-03-26 09:32:08 swin_small_patch4_window7_224] INFO: Epoch: [164] [1150/1251] eta: 0:00:51 lr: 0.000428 loss: 3.1706 (3.2716) grad_norm: 1.4448 (nan) time: 0.5040 [2021-03-26 09:32:13 swin_small_patch4_window7_224] INFO: Epoch: [164] [1160/1251] eta: 0:00:46 lr: 0.000428 loss: 3.5163 (3.2704) grad_norm: 1.4850 (nan) time: 0.5041 [2021-03-26 09:32:18 swin_small_patch4_window7_224] INFO: Epoch: [164] [1170/1251] eta: 0:00:41 lr: 0.000428 loss: 3.2368 (3.2699) grad_norm: 1.5954 (nan) time: 0.5061 [2021-03-26 09:32:23 swin_small_patch4_window7_224] INFO: Epoch: [164] [1180/1251] eta: 0:00:36 lr: 0.000428 loss: 3.2368 (3.2689) grad_norm: 1.6045 (nan) time: 0.5063 [2021-03-26 09:32:28 swin_small_patch4_window7_224] INFO: Epoch: [164] [1190/1251] eta: 0:00:30 lr: 0.000428 loss: 3.2733 (3.2684) grad_norm: 1.5457 (nan) time: 0.5053 [2021-03-26 09:32:33 swin_small_patch4_window7_224] INFO: Epoch: [164] [1200/1251] eta: 0:00:25 lr: 0.000428 loss: 3.3721 (3.2681) grad_norm: 1.5548 (nan) time: 0.5024 [2021-03-26 09:32:38 swin_small_patch4_window7_224] INFO: Epoch: [164] [1210/1251] eta: 0:00:20 lr: 0.000428 loss: 3.5037 (3.2711) grad_norm: 1.5548 (nan) time: 0.5009 [2021-03-26 09:32:43 swin_small_patch4_window7_224] INFO: Epoch: [164] [1220/1251] eta: 0:00:15 lr: 0.000428 loss: 3.4300 (3.2718) grad_norm: 1.5843 (nan) time: 0.5003 [2021-03-26 09:32:48 swin_small_patch4_window7_224] INFO: Epoch: [164] [1230/1251] eta: 0:00:10 lr: 0.000428 loss: 3.4300 (3.2739) grad_norm: 1.6380 (nan) time: 0.5016 [2021-03-26 09:32:53 swin_small_patch4_window7_224] INFO: Epoch: [164] [1240/1251] eta: 0:00:05 lr: 0.000428 loss: 3.4090 (3.2733) grad_norm: 1.5981 (nan) time: 0.4977 [2021-03-26 09:32:58 swin_small_patch4_window7_224] INFO: Epoch: [164] [1250/1251] eta: 0:00:00 lr: 0.000428 loss: 3.3136 (3.2722) grad_norm: 1.5073 (nan) time: 0.4921 [2021-03-26 09:33:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:59 loss: 0.8826 (0.8826) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-26 09:33:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:22 loss: 0.8826 (1.0003) acc1: 78.1250 (76.4205) acc5: 93.7500 (92.8977) [2021-03-26 09:33:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.9032 (0.9591) acc1: 76.5625 (77.0089) acc5: 93.7500 (93.5268) [2021-03-26 09:33:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8735 (0.9182) acc1: 76.5625 (77.6210) acc5: 95.3125 (94.1028) [2021-03-26 09:33:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8382 (0.9072) acc1: 78.1250 (77.7439) acc5: 95.3125 (94.3979) [2021-03-26 09:33:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8395 (0.9017) acc1: 78.1250 (77.8240) acc5: 96.8750 (94.9120) [2021-03-26 09:33:23 swin_small_patch4_window7_224] INFO: * Acc@1 78.842 Acc@5 94.874 loss 0.886 [2021-03-26 09:33:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 78.8% [2021-03-26 09:33:23 swin_small_patch4_window7_224] INFO: Max accuracy: 78.98% [2021-03-26 09:33:27 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 0/1251] eta: 1:24:36 lr: 0.000428 loss: 3.0461 (3.0461) grad_norm: 1.6162 (1.6162) time: 4.0577 [2021-03-26 09:33:32 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 10/1251] eta: 0:17:36 lr: 0.000428 loss: 3.2396 (3.1946) grad_norm: 1.5348 (1.5694) time: 0.8515 [2021-03-26 09:33:37 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 20/1251] eta: 0:14:02 lr: 0.000427 loss: 3.2396 (3.1629) grad_norm: 1.5348 (1.5834) time: 0.5155 [2021-03-26 09:33:42 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 30/1251] eta: 0:12:45 lr: 0.000427 loss: 3.3734 (3.2532) grad_norm: 1.5202 (1.5501) time: 0.5035 [2021-03-26 09:33:47 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 40/1251] eta: 0:12:05 lr: 0.000427 loss: 3.3217 (3.2187) grad_norm: 1.4545 (1.5421) time: 0.5106 [2021-03-26 09:33:52 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 50/1251] eta: 0:11:36 lr: 0.000427 loss: 3.2688 (3.2115) grad_norm: 1.4891 (1.5322) time: 0.5063 [2021-03-26 09:33:57 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 60/1251] eta: 0:11:17 lr: 0.000427 loss: 3.3100 (3.2261) grad_norm: 1.5056 (1.5398) time: 0.5059 [2021-03-26 09:34:02 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 70/1251] eta: 0:11:00 lr: 0.000427 loss: 3.4582 (3.2631) grad_norm: 1.5230 (1.5467) time: 0.5078 [2021-03-26 09:34:08 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 80/1251] eta: 0:10:49 lr: 0.000427 loss: 3.5250 (3.2848) grad_norm: 1.5565 (1.5610) time: 0.5108 [2021-03-26 09:34:13 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 90/1251] eta: 0:10:38 lr: 0.000427 loss: 3.4112 (3.2787) grad_norm: 1.5124 (1.5551) time: 0.5179 [2021-03-26 09:34:18 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 100/1251] eta: 0:10:27 lr: 0.000427 loss: 3.5230 (3.2946) grad_norm: 1.5081 (1.5544) time: 0.5074 [2021-03-26 09:34:23 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 110/1251] eta: 0:10:18 lr: 0.000427 loss: 3.2723 (3.2834) grad_norm: 1.5061 (1.5480) time: 0.5061 [2021-03-26 09:34:28 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 120/1251] eta: 0:10:09 lr: 0.000427 loss: 3.1061 (3.2637) grad_norm: 1.4978 (1.5521) time: 0.5096 [2021-03-26 09:34:33 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 130/1251] eta: 0:10:00 lr: 0.000427 loss: 3.0935 (3.2560) grad_norm: 1.5048 (1.5472) time: 0.5015 [2021-03-26 09:34:38 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 140/1251] eta: 0:09:53 lr: 0.000427 loss: 3.3779 (3.2496) grad_norm: 1.4735 (1.5442) time: 0.5004 [2021-03-26 09:34:43 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 150/1251] eta: 0:09:45 lr: 0.000427 loss: 3.3779 (3.2513) grad_norm: 1.5451 (1.5451) time: 0.5041 [2021-03-26 09:34:48 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 160/1251] eta: 0:09:38 lr: 0.000427 loss: 3.1863 (3.2459) grad_norm: 1.5664 (1.5482) time: 0.5048 [2021-03-26 09:34:53 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 170/1251] eta: 0:09:31 lr: 0.000427 loss: 3.2906 (3.2524) grad_norm: 1.5264 (1.5449) time: 0.5025 [2021-03-26 09:34:58 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 180/1251] eta: 0:09:25 lr: 0.000427 loss: 3.2906 (3.2501) grad_norm: 1.4657 (1.5429) time: 0.5083 [2021-03-26 09:35:03 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 190/1251] eta: 0:09:17 lr: 0.000427 loss: 3.2817 (3.2449) grad_norm: 1.5053 (1.5473) time: 0.5041 [2021-03-26 09:35:08 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 200/1251] eta: 0:09:11 lr: 0.000427 loss: 3.3718 (3.2550) grad_norm: 1.5912 (1.5506) time: 0.4951 [2021-03-26 09:35:13 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 210/1251] eta: 0:09:05 lr: 0.000427 loss: 3.4031 (3.2599) grad_norm: 1.5912 (1.5536) time: 0.5025 [2021-03-26 09:35:18 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 220/1251] eta: 0:08:59 lr: 0.000427 loss: 3.2850 (3.2545) grad_norm: 1.5614 (1.5559) time: 0.5138 [2021-03-26 09:35:24 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 230/1251] eta: 0:08:53 lr: 0.000427 loss: 3.3077 (3.2620) grad_norm: 1.5411 (1.5619) time: 0.5145 [2021-03-26 09:35:29 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 240/1251] eta: 0:08:47 lr: 0.000427 loss: 3.1967 (3.2566) grad_norm: 1.5522 (1.5614) time: 0.5047 [2021-03-26 09:35:34 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 250/1251] eta: 0:08:41 lr: 0.000427 loss: 3.1368 (3.2596) grad_norm: 1.5177 (1.5605) time: 0.5047 [2021-03-26 09:35:39 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 260/1251] eta: 0:08:36 lr: 0.000427 loss: 3.3067 (3.2645) grad_norm: 1.5137 (1.5590) time: 0.5101 [2021-03-26 09:35:44 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 270/1251] eta: 0:08:30 lr: 0.000426 loss: 3.5420 (3.2626) grad_norm: 1.5020 (1.5558) time: 0.5066 [2021-03-26 09:35:49 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 280/1251] eta: 0:08:24 lr: 0.000426 loss: 3.1218 (3.2605) grad_norm: 1.4863 (1.5561) time: 0.4998 [2021-03-26 09:35:54 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 290/1251] eta: 0:08:18 lr: 0.000426 loss: 3.1480 (3.2630) grad_norm: 1.5250 (1.5569) time: 0.5008 [2021-03-26 09:35:59 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 300/1251] eta: 0:08:13 lr: 0.000426 loss: 3.3462 (3.2576) grad_norm: 1.5587 (1.5564) time: 0.5055 [2021-03-26 09:36:04 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 310/1251] eta: 0:08:07 lr: 0.000426 loss: 3.4059 (3.2615) grad_norm: 1.5422 (1.5559) time: 0.5041 [2021-03-26 09:36:09 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 320/1251] eta: 0:08:01 lr: 0.000426 loss: 3.4059 (3.2574) grad_norm: 1.4954 (1.5558) time: 0.5011 [2021-03-26 09:36:14 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 330/1251] eta: 0:07:56 lr: 0.000426 loss: 3.2000 (3.2534) grad_norm: 1.4895 (1.5529) time: 0.4987 [2021-03-26 09:36:19 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 340/1251] eta: 0:07:50 lr: 0.000426 loss: 3.3115 (3.2568) grad_norm: 1.4515 (1.5516) time: 0.4979 [2021-03-26 09:36:24 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 350/1251] eta: 0:07:45 lr: 0.000426 loss: 3.2512 (3.2517) grad_norm: 1.4837 (1.5511) time: 0.5063 [2021-03-26 09:36:29 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 360/1251] eta: 0:07:39 lr: 0.000426 loss: 3.1858 (3.2533) grad_norm: 1.4837 (1.5500) time: 0.5060 [2021-03-26 09:36:34 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 370/1251] eta: 0:07:34 lr: 0.000426 loss: 3.1858 (3.2472) grad_norm: 1.5342 (1.5506) time: 0.5027 [2021-03-26 09:36:39 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 380/1251] eta: 0:07:28 lr: 0.000426 loss: 3.0932 (3.2443) grad_norm: 1.6251 (1.5546) time: 0.5026 [2021-03-26 09:36:44 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 390/1251] eta: 0:07:23 lr: 0.000426 loss: 3.4351 (3.2536) grad_norm: 1.6393 (1.5572) time: 0.5042 [2021-03-26 09:36:49 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 400/1251] eta: 0:07:17 lr: 0.000426 loss: 3.4724 (3.2560) grad_norm: 1.6393 (1.5599) time: 0.5033 [2021-03-26 09:36:54 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 410/1251] eta: 0:07:12 lr: 0.000426 loss: 3.4485 (3.2596) grad_norm: 1.5578 (1.5592) time: 0.5083 [2021-03-26 09:36:59 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 420/1251] eta: 0:07:07 lr: 0.000426 loss: 3.3876 (3.2589) grad_norm: 1.5326 (1.5594) time: 0.5080 [2021-03-26 09:37:04 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 430/1251] eta: 0:07:02 lr: 0.000426 loss: 3.3345 (3.2592) grad_norm: 1.4598 (1.5573) time: 0.5033 [2021-03-26 09:37:09 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 440/1251] eta: 0:06:56 lr: 0.000426 loss: 3.2726 (3.2535) grad_norm: 1.3713 (1.5575) time: 0.5021 [2021-03-26 09:37:14 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 450/1251] eta: 0:06:51 lr: 0.000426 loss: 3.3292 (3.2575) grad_norm: 1.5825 (1.5571) time: 0.4953 [2021-03-26 09:37:19 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 460/1251] eta: 0:06:45 lr: 0.000426 loss: 3.3292 (3.2567) grad_norm: 1.5103 (1.5568) time: 0.5016 [2021-03-26 09:37:24 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 470/1251] eta: 0:06:40 lr: 0.000426 loss: 3.3422 (3.2580) grad_norm: 1.5465 (1.5576) time: 0.5085 [2021-03-26 09:37:29 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 480/1251] eta: 0:06:35 lr: 0.000426 loss: 3.3619 (3.2566) grad_norm: 1.5011 (1.5571) time: 0.5057 [2021-03-26 09:37:35 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 490/1251] eta: 0:06:30 lr: 0.000426 loss: 3.3477 (3.2617) grad_norm: 1.5379 (1.5571) time: 0.5046 [2021-03-26 09:37:40 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 500/1251] eta: 0:06:25 lr: 0.000426 loss: 3.3459 (3.2625) grad_norm: 1.5306 (1.5576) time: 0.5096 [2021-03-26 09:37:45 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 510/1251] eta: 0:06:19 lr: 0.000425 loss: 3.2048 (3.2610) grad_norm: 1.5196 (1.5581) time: 0.5094 [2021-03-26 09:37:50 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 520/1251] eta: 0:06:14 lr: 0.000425 loss: 3.1789 (3.2610) grad_norm: 1.6571 (1.5607) time: 0.5082 [2021-03-26 09:37:55 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 530/1251] eta: 0:06:09 lr: 0.000425 loss: 3.1789 (3.2588) grad_norm: 1.6563 (1.5625) time: 0.5048 [2021-03-26 09:38:00 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 540/1251] eta: 0:06:04 lr: 0.000425 loss: 3.4744 (3.2615) grad_norm: 1.6276 (1.5638) time: 0.5084 [2021-03-26 09:38:05 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 550/1251] eta: 0:05:59 lr: 0.000425 loss: 3.4519 (3.2609) grad_norm: 1.5863 (1.5637) time: 0.5198 [2021-03-26 09:38:10 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 560/1251] eta: 0:05:54 lr: 0.000425 loss: 3.3635 (3.2591) grad_norm: 1.5710 (1.5633) time: 0.5139 [2021-03-26 09:38:15 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 570/1251] eta: 0:05:48 lr: 0.000425 loss: 3.2633 (3.2613) grad_norm: 1.5811 (1.5659) time: 0.5079 [2021-03-26 09:38:20 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 580/1251] eta: 0:05:43 lr: 0.000425 loss: 3.3819 (3.2577) grad_norm: 1.5298 (1.5655) time: 0.5097 [2021-03-26 09:38:26 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 590/1251] eta: 0:05:38 lr: 0.000425 loss: 3.3673 (3.2587) grad_norm: 1.5114 (1.5659) time: 0.5092 [2021-03-26 09:38:31 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 600/1251] eta: 0:05:33 lr: 0.000425 loss: 3.4346 (3.2606) grad_norm: 1.5489 (1.5670) time: 0.5066 [2021-03-26 09:38:36 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 610/1251] eta: 0:05:28 lr: 0.000425 loss: 3.4265 (3.2610) grad_norm: 1.5656 (1.5674) time: 0.5045 [2021-03-26 09:38:41 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 620/1251] eta: 0:05:22 lr: 0.000425 loss: 3.2073 (3.2581) grad_norm: 1.5250 (1.5671) time: 0.5028 [2021-03-26 09:38:46 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 630/1251] eta: 0:05:17 lr: 0.000425 loss: 3.2073 (3.2588) grad_norm: 1.5045 (1.5710) time: 0.5044 [2021-03-26 09:38:51 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 640/1251] eta: 0:05:12 lr: 0.000425 loss: 3.3886 (3.2587) grad_norm: 1.5635 (1.5725) time: 0.5078 [2021-03-26 09:38:56 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 650/1251] eta: 0:05:07 lr: 0.000425 loss: 3.3581 (3.2585) grad_norm: 1.5481 (1.5724) time: 0.5097 [2021-03-26 09:39:01 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 660/1251] eta: 0:05:02 lr: 0.000425 loss: 3.5024 (3.2632) grad_norm: 1.5068 (1.5721) time: 0.5088 [2021-03-26 09:39:06 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 670/1251] eta: 0:04:57 lr: 0.000425 loss: 3.5481 (3.2658) grad_norm: 1.5631 (1.5723) time: 0.5060 [2021-03-26 09:39:11 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 680/1251] eta: 0:04:52 lr: 0.000425 loss: 3.4300 (3.2676) grad_norm: 1.5458 (1.5719) time: 0.5076 [2021-03-26 09:39:16 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 690/1251] eta: 0:04:46 lr: 0.000425 loss: 3.2398 (3.2664) grad_norm: 1.5295 (1.5716) time: 0.5055 [2021-03-26 09:39:21 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 700/1251] eta: 0:04:41 lr: 0.000425 loss: 3.3511 (3.2698) grad_norm: 1.5432 (1.5721) time: 0.5078 [2021-03-26 09:39:26 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 710/1251] eta: 0:04:36 lr: 0.000425 loss: 3.5672 (3.2733) grad_norm: 1.5424 (1.5724) time: 0.5055 [2021-03-26 09:39:31 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 720/1251] eta: 0:04:31 lr: 0.000425 loss: 3.2242 (3.2702) grad_norm: 1.6002 (1.5731) time: 0.4997 [2021-03-26 09:39:37 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 730/1251] eta: 0:04:26 lr: 0.000425 loss: 3.1988 (3.2699) grad_norm: 1.5673 (1.5725) time: 0.5118 [2021-03-26 09:39:42 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 740/1251] eta: 0:04:21 lr: 0.000425 loss: 3.2235 (3.2684) grad_norm: 1.5277 (1.5715) time: 0.5185 [2021-03-26 09:39:47 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 750/1251] eta: 0:04:16 lr: 0.000424 loss: 3.2492 (3.2698) grad_norm: 1.5236 (1.5715) time: 0.5142 [2021-03-26 09:39:52 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 760/1251] eta: 0:04:11 lr: 0.000424 loss: 3.3364 (3.2679) grad_norm: 1.6177 (1.5730) time: 0.5083 [2021-03-26 09:39:57 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 770/1251] eta: 0:04:05 lr: 0.000424 loss: 3.3234 (3.2682) grad_norm: 1.5935 (1.5722) time: 0.5088 [2021-03-26 09:40:02 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 780/1251] eta: 0:04:00 lr: 0.000424 loss: 3.3727 (3.2686) grad_norm: 1.5169 (1.5723) time: 0.5142 [2021-03-26 09:40:07 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 790/1251] eta: 0:03:55 lr: 0.000424 loss: 3.3084 (3.2692) grad_norm: 1.5169 (1.5727) time: 0.5100 [2021-03-26 09:40:12 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 800/1251] eta: 0:03:50 lr: 0.000424 loss: 3.3843 (3.2681) grad_norm: 1.4434 (1.5712) time: 0.5077 [2021-03-26 09:40:17 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 810/1251] eta: 0:03:45 lr: 0.000424 loss: 3.1912 (3.2683) grad_norm: 1.4872 (1.5723) time: 0.5062 [2021-03-26 09:40:22 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 820/1251] eta: 0:03:40 lr: 0.000424 loss: 3.2685 (3.2687) grad_norm: 1.5803 (1.5727) time: 0.5049 [2021-03-26 09:40:28 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 830/1251] eta: 0:03:35 lr: 0.000424 loss: 3.2704 (3.2687) grad_norm: 1.5058 (1.5719) time: 0.5101 [2021-03-26 09:40:33 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 840/1251] eta: 0:03:30 lr: 0.000424 loss: 3.0242 (3.2655) grad_norm: 1.4499 (1.5713) time: 0.5076 [2021-03-26 09:40:38 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 850/1251] eta: 0:03:24 lr: 0.000424 loss: 3.2134 (3.2655) grad_norm: 1.5201 (1.5717) time: 0.5022 [2021-03-26 09:40:43 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 860/1251] eta: 0:03:19 lr: 0.000424 loss: 3.2384 (3.2644) grad_norm: 1.5394 (1.5711) time: 0.5067 [2021-03-26 09:40:48 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 870/1251] eta: 0:03:14 lr: 0.000424 loss: 3.2340 (3.2633) grad_norm: 1.5394 (1.5701) time: 0.5058 [2021-03-26 09:40:53 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 880/1251] eta: 0:03:09 lr: 0.000424 loss: 3.3061 (3.2651) grad_norm: 1.5525 (1.5704) time: 0.5010 [2021-03-26 09:40:58 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 890/1251] eta: 0:03:04 lr: 0.000424 loss: 3.2699 (3.2615) grad_norm: 1.4898 (1.5696) time: 0.4988 [2021-03-26 09:41:03 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 900/1251] eta: 0:02:59 lr: 0.000424 loss: 3.1387 (3.2611) grad_norm: 1.5460 (1.5699) time: 0.5027 [2021-03-26 09:41:08 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 910/1251] eta: 0:02:54 lr: 0.000424 loss: 3.1387 (3.2585) grad_norm: 1.5498 (1.5693) time: 0.5074 [2021-03-26 09:41:13 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 920/1251] eta: 0:02:48 lr: 0.000424 loss: 3.1655 (3.2587) grad_norm: 1.4927 (1.5696) time: 0.5090 [2021-03-26 09:41:18 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 930/1251] eta: 0:02:43 lr: 0.000424 loss: 3.3221 (3.2577) grad_norm: 1.4810 (1.5696) time: 0.5062 [2021-03-26 09:41:23 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 940/1251] eta: 0:02:38 lr: 0.000424 loss: 3.0270 (3.2537) grad_norm: 1.5306 (1.5702) time: 0.5041 [2021-03-26 09:41:28 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 950/1251] eta: 0:02:33 lr: 0.000424 loss: 3.1526 (3.2531) grad_norm: 1.5958 (1.5713) time: 0.5086 [2021-03-26 09:41:33 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 960/1251] eta: 0:02:28 lr: 0.000424 loss: 3.2267 (3.2534) grad_norm: 1.7002 (1.5733) time: 0.5049 [2021-03-26 09:41:38 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 970/1251] eta: 0:02:23 lr: 0.000424 loss: 3.3698 (3.2531) grad_norm: 1.6901 (1.5738) time: 0.5090 [2021-03-26 09:41:43 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 980/1251] eta: 0:02:18 lr: 0.000424 loss: 3.0021 (3.2503) grad_norm: 1.5004 (1.5725) time: 0.5088 [2021-03-26 09:41:48 swin_small_patch4_window7_224] INFO: Epoch: [165] [ 990/1251] eta: 0:02:13 lr: 0.000424 loss: 3.1325 (3.2506) grad_norm: 1.4588 (1.5714) time: 0.5035 [2021-03-26 09:41:54 swin_small_patch4_window7_224] INFO: Epoch: [165] [1000/1251] eta: 0:02:08 lr: 0.000423 loss: 3.4601 (3.2530) grad_norm: 1.4983 (1.5712) time: 0.5101 [2021-03-26 09:41:59 swin_small_patch4_window7_224] INFO: Epoch: [165] [1010/1251] eta: 0:02:02 lr: 0.000423 loss: 3.5658 (3.2547) grad_norm: 1.4898 (1.5712) time: 0.5068 [2021-03-26 09:42:04 swin_small_patch4_window7_224] INFO: Epoch: [165] [1020/1251] eta: 0:01:57 lr: 0.000423 loss: 3.4516 (3.2570) grad_norm: 1.5564 (1.5721) time: 0.5041 [2021-03-26 09:42:09 swin_small_patch4_window7_224] INFO: Epoch: [165] [1030/1251] eta: 0:01:52 lr: 0.000423 loss: 3.3414 (3.2561) grad_norm: 1.5564 (1.5719) time: 0.5062 [2021-03-26 09:42:14 swin_small_patch4_window7_224] INFO: Epoch: [165] [1040/1251] eta: 0:01:47 lr: 0.000423 loss: 3.1221 (3.2528) grad_norm: 1.4845 (1.5710) time: 0.5112 [2021-03-26 09:42:19 swin_small_patch4_window7_224] INFO: Epoch: [165] [1050/1251] eta: 0:01:42 lr: 0.000423 loss: 3.1795 (3.2538) grad_norm: 1.4358 (1.5703) time: 0.5121 [2021-03-26 09:42:24 swin_small_patch4_window7_224] INFO: Epoch: [165] [1060/1251] eta: 0:01:37 lr: 0.000423 loss: 3.1795 (3.2502) grad_norm: 1.5195 (1.5699) time: 0.5045 [2021-03-26 09:42:29 swin_small_patch4_window7_224] INFO: Epoch: [165] [1070/1251] eta: 0:01:32 lr: 0.000423 loss: 3.0181 (3.2486) grad_norm: 1.5902 (1.5711) time: 0.5073 [2021-03-26 09:42:34 swin_small_patch4_window7_224] INFO: Epoch: [165] [1080/1251] eta: 0:01:27 lr: 0.000423 loss: 3.0398 (3.2461) grad_norm: 1.6378 (1.5711) time: 0.5057 [2021-03-26 09:42:39 swin_small_patch4_window7_224] INFO: Epoch: [165] [1090/1251] eta: 0:01:22 lr: 0.000423 loss: 3.0398 (3.2458) grad_norm: 1.5174 (1.5704) time: 0.5037 [2021-03-26 09:42:44 swin_small_patch4_window7_224] INFO: Epoch: [165] [1100/1251] eta: 0:01:16 lr: 0.000423 loss: 3.1756 (3.2471) grad_norm: 1.5085 (1.5701) time: 0.5079 [2021-03-26 09:42:49 swin_small_patch4_window7_224] INFO: Epoch: [165] [1110/1251] eta: 0:01:11 lr: 0.000423 loss: 3.3226 (3.2476) grad_norm: 1.5136 (1.5707) time: 0.5078 [2021-03-26 09:42:54 swin_small_patch4_window7_224] INFO: Epoch: [165] [1120/1251] eta: 0:01:06 lr: 0.000423 loss: 3.4709 (3.2483) grad_norm: 1.5774 (1.5708) time: 0.5088 [2021-03-26 09:42:59 swin_small_patch4_window7_224] INFO: Epoch: [165] [1130/1251] eta: 0:01:01 lr: 0.000423 loss: 3.3423 (3.2473) grad_norm: 1.5618 (1.5708) time: 0.5057 [2021-03-26 09:43:04 swin_small_patch4_window7_224] INFO: Epoch: [165] [1140/1251] eta: 0:00:56 lr: 0.000423 loss: 3.2066 (3.2474) grad_norm: 1.5974 (1.5712) time: 0.5000 [2021-03-26 09:43:09 swin_small_patch4_window7_224] INFO: Epoch: [165] [1150/1251] eta: 0:00:51 lr: 0.000423 loss: 3.2337 (3.2484) grad_norm: 1.5173 (1.5705) time: 0.5022 [2021-03-26 09:43:15 swin_small_patch4_window7_224] INFO: Epoch: [165] [1160/1251] eta: 0:00:46 lr: 0.000423 loss: 3.2648 (3.2478) grad_norm: 1.4868 (1.5700) time: 0.5087 [2021-03-26 09:43:20 swin_small_patch4_window7_224] INFO: Epoch: [165] [1170/1251] eta: 0:00:41 lr: 0.000423 loss: 3.2648 (3.2470) grad_norm: 1.4868 (1.5689) time: 0.5027 [2021-03-26 09:43:25 swin_small_patch4_window7_224] INFO: Epoch: [165] [1180/1251] eta: 0:00:36 lr: 0.000423 loss: 3.3667 (3.2475) grad_norm: 1.5200 (1.5693) time: 0.4970 [2021-03-26 09:43:30 swin_small_patch4_window7_224] INFO: Epoch: [165] [1190/1251] eta: 0:00:31 lr: 0.000423 loss: 3.4582 (3.2493) grad_norm: 1.5200 (1.5687) time: 0.4997 [2021-03-26 09:43:35 swin_small_patch4_window7_224] INFO: Epoch: [165] [1200/1251] eta: 0:00:25 lr: 0.000423 loss: 3.4582 (3.2518) grad_norm: 1.4643 (1.5682) time: 0.5028 [2021-03-26 09:43:40 swin_small_patch4_window7_224] INFO: Epoch: [165] [1210/1251] eta: 0:00:20 lr: 0.000423 loss: 3.4534 (3.2532) grad_norm: 1.4664 (1.5677) time: 0.5070 [2021-03-26 09:43:45 swin_small_patch4_window7_224] INFO: Epoch: [165] [1220/1251] eta: 0:00:15 lr: 0.000423 loss: 3.3347 (3.2523) grad_norm: 1.5014 (1.5673) time: 0.5044 [2021-03-26 09:43:50 swin_small_patch4_window7_224] INFO: Epoch: [165] [1230/1251] eta: 0:00:10 lr: 0.000423 loss: 3.0470 (3.2502) grad_norm: 1.5014 (1.5667) time: 0.4987 [2021-03-26 09:43:55 swin_small_patch4_window7_224] INFO: Epoch: [165] [1240/1251] eta: 0:00:05 lr: 0.000422 loss: 2.9371 (3.2480) grad_norm: 1.5306 (1.5667) time: 0.5021 [2021-03-26 09:44:00 swin_small_patch4_window7_224] INFO: Epoch: [165] [1250/1251] eta: 0:00:00 lr: 0.000422 loss: 3.0491 (3.2481) grad_norm: 1.5608 (1.5667) time: 0.5053 [2021-03-26 09:44:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.9292 (0.9292) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-26 09:44:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.8388 (0.8223) acc1: 78.1250 (78.5511) acc5: 95.3125 (95.5966) [2021-03-26 09:44:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.8466 (0.8698) acc1: 79.6875 (78.7202) acc5: 95.3125 (95.0149) [2021-03-26 09:44:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8687 (0.8628) acc1: 81.2500 (79.3851) acc5: 95.3125 (95.1109) [2021-03-26 09:44:50 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8687 (0.8854) acc1: 79.6875 (78.6585) acc5: 95.3125 (95.0076) [2021-03-26 09:44:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9217 (0.9013) acc1: 78.1250 (78.1120) acc5: 95.3125 (94.8800) [2021-03-26 09:45:00 swin_small_patch4_window7_224] INFO: * Acc@1 79.070 Acc@5 94.950 loss 0.895 [2021-03-26 09:45:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-26 09:45:00 swin_small_patch4_window7_224] INFO: Max accuracy: 79.07% [2021-03-26 09:45:04 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 0/1251] eta: 1:25:53 lr: 0.000422 loss: 3.7601 (3.7601) grad_norm: 1.4884 (1.4884) time: 4.1196 [2021-03-26 09:45:09 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 10/1251] eta: 0:17:48 lr: 0.000422 loss: 3.1763 (3.1484) grad_norm: 1.5644 (1.5885) time: 0.8608 [2021-03-26 09:45:14 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 20/1251] eta: 0:14:06 lr: 0.000422 loss: 3.1772 (3.2191) grad_norm: 1.5034 (1.5470) time: 0.5162 [2021-03-26 09:45:19 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 30/1251] eta: 0:12:48 lr: 0.000422 loss: 3.1772 (3.1435) grad_norm: 1.4765 (1.5281) time: 0.5018 [2021-03-26 09:45:25 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 40/1251] eta: 0:12:09 lr: 0.000422 loss: 3.2212 (3.2077) grad_norm: 1.4553 (1.5113) time: 0.5125 [2021-03-26 09:45:30 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 50/1251] eta: 0:11:40 lr: 0.000422 loss: 3.4632 (3.2254) grad_norm: 1.5346 (1.5328) time: 0.5120 [2021-03-26 09:45:35 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 60/1251] eta: 0:11:18 lr: 0.000422 loss: 3.1920 (3.2170) grad_norm: 1.5346 (1.5268) time: 0.5018 [2021-03-26 09:45:40 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 70/1251] eta: 0:11:02 lr: 0.000422 loss: 3.2386 (3.2421) grad_norm: 1.5408 (1.5399) time: 0.5046 [2021-03-26 09:45:45 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 80/1251] eta: 0:10:49 lr: 0.000422 loss: 3.5457 (3.2815) grad_norm: 1.5443 (1.5426) time: 0.5107 [2021-03-26 09:45:50 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 90/1251] eta: 0:10:38 lr: 0.000422 loss: 3.4499 (3.2832) grad_norm: 1.5116 (1.5386) time: 0.5085 [2021-03-26 09:45:55 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 100/1251] eta: 0:10:27 lr: 0.000422 loss: 3.4477 (3.2842) grad_norm: 1.4742 (1.5364) time: 0.5043 [2021-03-26 09:46:00 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 110/1251] eta: 0:10:17 lr: 0.000422 loss: 3.2323 (3.2550) grad_norm: 1.4992 (1.5456) time: 0.5040 [2021-03-26 09:46:05 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 120/1251] eta: 0:10:09 lr: 0.000422 loss: 3.2323 (3.2619) grad_norm: 1.5795 (1.5525) time: 0.5087 [2021-03-26 09:46:10 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 130/1251] eta: 0:10:01 lr: 0.000422 loss: 3.3004 (3.2510) grad_norm: 1.6740 (1.5692) time: 0.5090 [2021-03-26 09:46:15 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 140/1251] eta: 0:09:52 lr: 0.000422 loss: 3.3582 (3.2594) grad_norm: 1.5821 (1.5646) time: 0.5009 [2021-03-26 09:46:20 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 150/1251] eta: 0:09:45 lr: 0.000422 loss: 3.1540 (3.2437) grad_norm: 1.5611 (1.5683) time: 0.5023 [2021-03-26 09:46:25 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 160/1251] eta: 0:09:38 lr: 0.000422 loss: 3.0667 (3.2315) grad_norm: 1.5611 (1.5701) time: 0.5095 [2021-03-26 09:46:30 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 170/1251] eta: 0:09:31 lr: 0.000422 loss: 3.1162 (3.2331) grad_norm: 1.5281 (1.5710) time: 0.5025 [2021-03-26 09:46:35 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 180/1251] eta: 0:09:24 lr: 0.000422 loss: 3.0568 (3.2149) grad_norm: 1.5422 (1.5703) time: 0.5009 [2021-03-26 09:46:41 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 190/1251] eta: 0:09:18 lr: 0.000422 loss: 2.9683 (3.2130) grad_norm: 1.5529 (1.5706) time: 0.5106 [2021-03-26 09:46:46 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 200/1251] eta: 0:09:12 lr: 0.000422 loss: 3.2214 (3.2224) grad_norm: 1.5919 (1.5730) time: 0.5156 [2021-03-26 09:46:51 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 210/1251] eta: 0:09:06 lr: 0.000422 loss: 3.2082 (3.2146) grad_norm: 1.6433 (1.5757) time: 0.5104 [2021-03-26 09:46:56 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 220/1251] eta: 0:09:00 lr: 0.000422 loss: 3.1673 (3.2123) grad_norm: 1.6372 (1.5759) time: 0.5007 [2021-03-26 09:47:01 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 230/1251] eta: 0:08:54 lr: 0.000422 loss: 3.2022 (3.2125) grad_norm: 1.5561 (1.5750) time: 0.5043 [2021-03-26 09:47:06 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 240/1251] eta: 0:08:47 lr: 0.000421 loss: 3.1641 (3.2138) grad_norm: 1.4480 (1.5722) time: 0.5050 [2021-03-26 09:47:11 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 250/1251] eta: 0:08:41 lr: 0.000421 loss: 3.1269 (3.2076) grad_norm: 1.6129 (1.5745) time: 0.5008 [2021-03-26 09:47:16 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 260/1251] eta: 0:08:36 lr: 0.000421 loss: 3.3468 (3.2121) grad_norm: 1.6134 (1.5764) time: 0.5056 [2021-03-26 09:47:21 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 270/1251] eta: 0:08:30 lr: 0.000421 loss: 3.3524 (3.2125) grad_norm: 1.6188 (1.5808) time: 0.5078 [2021-03-26 09:47:26 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 280/1251] eta: 0:08:24 lr: 0.000421 loss: 3.3126 (3.2180) grad_norm: 1.5880 (1.5800) time: 0.5076 [2021-03-26 09:47:31 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 290/1251] eta: 0:08:18 lr: 0.000421 loss: 3.2413 (3.2145) grad_norm: 1.5707 (1.5785) time: 0.5024 [2021-03-26 09:47:36 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 300/1251] eta: 0:08:13 lr: 0.000421 loss: 3.2291 (3.2229) grad_norm: 1.5178 (1.5768) time: 0.4966 [2021-03-26 09:47:41 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 310/1251] eta: 0:08:07 lr: 0.000421 loss: 3.4519 (3.2282) grad_norm: 1.5053 (1.5764) time: 0.5023 [2021-03-26 09:47:46 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 320/1251] eta: 0:08:02 lr: 0.000421 loss: 3.2823 (3.2207) grad_norm: 1.4996 (1.5741) time: 0.5071 [2021-03-26 09:47:51 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 330/1251] eta: 0:07:56 lr: 0.000421 loss: 3.2847 (3.2303) grad_norm: 1.5188 (1.5745) time: 0.5062 [2021-03-26 09:47:56 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 340/1251] eta: 0:07:51 lr: 0.000421 loss: 3.4760 (3.2298) grad_norm: 1.5393 (1.5756) time: 0.5064 [2021-03-26 09:48:01 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 350/1251] eta: 0:07:45 lr: 0.000421 loss: 3.4760 (3.2348) grad_norm: 1.5749 (1.5775) time: 0.4989 [2021-03-26 09:48:06 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 360/1251] eta: 0:07:39 lr: 0.000421 loss: 3.4358 (3.2306) grad_norm: 1.6123 (1.5772) time: 0.4994 [2021-03-26 09:48:11 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 370/1251] eta: 0:07:34 lr: 0.000421 loss: 3.3497 (3.2323) grad_norm: 1.5372 (1.5744) time: 0.5057 [2021-03-26 09:48:16 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 380/1251] eta: 0:07:28 lr: 0.000421 loss: 3.1655 (3.2247) grad_norm: 1.4771 (1.5752) time: 0.5013 [2021-03-26 09:48:21 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 390/1251] eta: 0:07:23 lr: 0.000421 loss: 3.1384 (3.2295) grad_norm: 1.5411 (1.5741) time: 0.4988 [2021-03-26 09:48:26 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 400/1251] eta: 0:07:18 lr: 0.000421 loss: 3.1929 (3.2281) grad_norm: 1.5640 (1.5748) time: 0.5038 [2021-03-26 09:48:32 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 410/1251] eta: 0:07:12 lr: 0.000421 loss: 3.1872 (3.2260) grad_norm: 1.5026 (1.5746) time: 0.5100 [2021-03-26 09:48:37 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 420/1251] eta: 0:07:07 lr: 0.000421 loss: 3.2759 (3.2303) grad_norm: 1.5197 (1.5740) time: 0.5070 [2021-03-26 09:48:42 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 430/1251] eta: 0:07:02 lr: 0.000421 loss: 3.2767 (3.2295) grad_norm: 1.5883 (1.5764) time: 0.5071 [2021-03-26 09:48:47 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 440/1251] eta: 0:06:56 lr: 0.000421 loss: 3.2767 (3.2300) grad_norm: 1.5885 (1.5761) time: 0.5081 [2021-03-26 09:48:52 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 450/1251] eta: 0:06:51 lr: 0.000421 loss: 3.2249 (3.2245) grad_norm: 1.5195 (1.5743) time: 0.5020 [2021-03-26 09:48:57 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 460/1251] eta: 0:06:46 lr: 0.000421 loss: 3.2739 (3.2311) grad_norm: 1.5359 (1.5749) time: 0.5017 [2021-03-26 09:49:02 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 470/1251] eta: 0:06:41 lr: 0.000421 loss: 3.4040 (3.2303) grad_norm: 1.5990 (1.5758) time: 0.5063 [2021-03-26 09:49:07 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 480/1251] eta: 0:06:35 lr: 0.000420 loss: 3.3321 (3.2279) grad_norm: 1.5990 (1.5752) time: 0.5028 [2021-03-26 09:49:12 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 490/1251] eta: 0:06:30 lr: 0.000420 loss: 3.2692 (3.2286) grad_norm: 1.5531 (1.5750) time: 0.4997 [2021-03-26 09:49:17 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 500/1251] eta: 0:06:25 lr: 0.000420 loss: 3.2170 (3.2273) grad_norm: 1.5531 (1.5742) time: 0.5021 [2021-03-26 09:49:22 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 510/1251] eta: 0:06:19 lr: 0.000420 loss: 3.3356 (3.2316) grad_norm: 1.5119 (1.5746) time: 0.5020 [2021-03-26 09:49:27 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 520/1251] eta: 0:06:14 lr: 0.000420 loss: 3.4376 (3.2324) grad_norm: 1.4917 (1.5742) time: 0.4994 [2021-03-26 09:49:32 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 530/1251] eta: 0:06:09 lr: 0.000420 loss: 3.1642 (3.2338) grad_norm: 1.5004 (1.5740) time: 0.5078 [2021-03-26 09:49:37 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 540/1251] eta: 0:06:04 lr: 0.000420 loss: 3.1892 (3.2313) grad_norm: 1.5279 (1.5735) time: 0.5108 [2021-03-26 09:49:42 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 550/1251] eta: 0:05:59 lr: 0.000420 loss: 3.2252 (3.2278) grad_norm: 1.5747 (1.5740) time: 0.5146 [2021-03-26 09:49:47 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 560/1251] eta: 0:05:53 lr: 0.000420 loss: 3.3176 (3.2326) grad_norm: 1.5747 (1.5750) time: 0.5119 [2021-03-26 09:49:52 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 570/1251] eta: 0:05:48 lr: 0.000420 loss: 3.4805 (3.2316) grad_norm: 1.5596 (1.5770) time: 0.5066 [2021-03-26 09:49:58 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 580/1251] eta: 0:05:43 lr: 0.000420 loss: 3.2612 (3.2310) grad_norm: 1.5099 (1.5764) time: 0.5113 [2021-03-26 09:50:03 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 590/1251] eta: 0:05:38 lr: 0.000420 loss: 3.2859 (3.2311) grad_norm: 1.5028 (1.5765) time: 0.5054 [2021-03-26 09:50:08 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 600/1251] eta: 0:05:33 lr: 0.000420 loss: 3.1498 (3.2300) grad_norm: 1.5811 (1.5771) time: 0.5071 [2021-03-26 09:50:13 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 610/1251] eta: 0:05:28 lr: 0.000420 loss: 3.1568 (3.2282) grad_norm: 1.5335 (1.5758) time: 0.5048 [2021-03-26 09:50:18 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 620/1251] eta: 0:05:22 lr: 0.000420 loss: 3.2121 (3.2286) grad_norm: 1.4841 (1.5757) time: 0.5033 [2021-03-26 09:50:23 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 630/1251] eta: 0:05:17 lr: 0.000420 loss: 3.4495 (3.2304) grad_norm: 1.4835 (1.5743) time: 0.5037 [2021-03-26 09:50:28 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 640/1251] eta: 0:05:12 lr: 0.000420 loss: 3.3257 (3.2296) grad_norm: 1.4574 (1.5734) time: 0.5023 [2021-03-26 09:50:33 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 650/1251] eta: 0:05:07 lr: 0.000420 loss: 3.3074 (3.2286) grad_norm: 1.4358 (1.5718) time: 0.5031 [2021-03-26 09:50:38 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 660/1251] eta: 0:05:01 lr: 0.000420 loss: 3.3441 (3.2290) grad_norm: 1.5133 (1.5719) time: 0.4981 [2021-03-26 09:50:43 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 670/1251] eta: 0:04:56 lr: 0.000420 loss: 3.3485 (3.2307) grad_norm: 1.6296 (1.5729) time: 0.5021 [2021-03-26 09:50:48 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 680/1251] eta: 0:04:51 lr: 0.000420 loss: 3.3334 (3.2280) grad_norm: 1.6880 (nan) time: 0.5069 [2021-03-26 09:50:53 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 690/1251] eta: 0:04:46 lr: 0.000420 loss: 3.3872 (3.2317) grad_norm: 1.6661 (nan) time: 0.5057 [2021-03-26 09:50:58 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 700/1251] eta: 0:04:41 lr: 0.000420 loss: 3.5164 (3.2341) grad_norm: 1.5909 (nan) time: 0.5007 [2021-03-26 09:51:03 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 710/1251] eta: 0:04:36 lr: 0.000420 loss: 3.2380 (3.2303) grad_norm: 1.6423 (nan) time: 0.4958 [2021-03-26 09:51:08 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 720/1251] eta: 0:04:30 lr: 0.000420 loss: 3.3059 (3.2339) grad_norm: 1.5976 (nan) time: 0.4955 [2021-03-26 09:51:13 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 730/1251] eta: 0:04:25 lr: 0.000419 loss: 3.3059 (3.2321) grad_norm: 1.4991 (nan) time: 0.5079 [2021-03-26 09:51:18 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 740/1251] eta: 0:04:20 lr: 0.000419 loss: 3.2325 (3.2321) grad_norm: 1.5698 (nan) time: 0.5233 [2021-03-26 09:51:24 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 750/1251] eta: 0:04:15 lr: 0.000419 loss: 3.2946 (3.2323) grad_norm: 1.5649 (nan) time: 0.5247 [2021-03-26 09:51:29 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 760/1251] eta: 0:04:10 lr: 0.000419 loss: 3.3464 (3.2332) grad_norm: 1.5298 (nan) time: 0.5157 [2021-03-26 09:51:34 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 770/1251] eta: 0:04:05 lr: 0.000419 loss: 3.2292 (3.2315) grad_norm: 1.5302 (nan) time: 0.5046 [2021-03-26 09:51:39 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 780/1251] eta: 0:04:00 lr: 0.000419 loss: 3.2297 (3.2325) grad_norm: 1.5858 (nan) time: 0.4997 [2021-03-26 09:51:44 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 790/1251] eta: 0:03:55 lr: 0.000419 loss: 3.2456 (3.2296) grad_norm: 1.6076 (nan) time: 0.4997 [2021-03-26 09:51:49 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 800/1251] eta: 0:03:50 lr: 0.000419 loss: 3.1274 (3.2286) grad_norm: 1.5822 (nan) time: 0.5047 [2021-03-26 09:51:54 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 810/1251] eta: 0:03:44 lr: 0.000419 loss: 3.1274 (3.2268) grad_norm: 1.6516 (nan) time: 0.5027 [2021-03-26 09:51:59 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 820/1251] eta: 0:03:39 lr: 0.000419 loss: 3.0795 (3.2239) grad_norm: 1.4884 (nan) time: 0.5034 [2021-03-26 09:52:04 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 830/1251] eta: 0:03:34 lr: 0.000419 loss: 3.2786 (3.2256) grad_norm: 1.4663 (nan) time: 0.5055 [2021-03-26 09:52:09 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 840/1251] eta: 0:03:29 lr: 0.000419 loss: 3.3711 (3.2244) grad_norm: 1.4708 (nan) time: 0.5030 [2021-03-26 09:52:14 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 850/1251] eta: 0:03:24 lr: 0.000419 loss: 3.1720 (3.2238) grad_norm: 1.5821 (nan) time: 0.5043 [2021-03-26 09:52:19 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 860/1251] eta: 0:03:19 lr: 0.000419 loss: 3.2818 (3.2251) grad_norm: 1.6153 (nan) time: 0.5070 [2021-03-26 09:52:24 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 870/1251] eta: 0:03:14 lr: 0.000419 loss: 3.3695 (3.2257) grad_norm: 1.5040 (nan) time: 0.5085 [2021-03-26 09:52:29 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 880/1251] eta: 0:03:09 lr: 0.000419 loss: 3.2832 (3.2269) grad_norm: 1.4690 (nan) time: 0.5154 [2021-03-26 09:52:34 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 890/1251] eta: 0:03:04 lr: 0.000419 loss: 3.2252 (3.2255) grad_norm: 1.4690 (nan) time: 0.5122 [2021-03-26 09:52:39 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 900/1251] eta: 0:02:58 lr: 0.000419 loss: 3.2252 (3.2259) grad_norm: 1.5524 (nan) time: 0.4998 [2021-03-26 09:52:44 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 910/1251] eta: 0:02:53 lr: 0.000419 loss: 3.4235 (3.2286) grad_norm: 1.5524 (nan) time: 0.5020 [2021-03-26 09:52:50 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 920/1251] eta: 0:02:48 lr: 0.000419 loss: 3.3891 (3.2283) grad_norm: 1.5645 (nan) time: 0.5112 [2021-03-26 09:52:54 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 930/1251] eta: 0:02:43 lr: 0.000419 loss: 3.3349 (3.2302) grad_norm: 1.5698 (nan) time: 0.5039 [2021-03-26 09:53:00 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 940/1251] eta: 0:02:38 lr: 0.000419 loss: 3.3494 (3.2304) grad_norm: 1.5257 (nan) time: 0.5041 [2021-03-26 09:53:05 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 950/1251] eta: 0:02:33 lr: 0.000419 loss: 3.4523 (3.2330) grad_norm: 1.4609 (nan) time: 0.5090 [2021-03-26 09:53:10 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 960/1251] eta: 0:02:28 lr: 0.000419 loss: 3.4476 (3.2334) grad_norm: 1.4640 (nan) time: 0.5033 [2021-03-26 09:53:15 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 970/1251] eta: 0:02:23 lr: 0.000418 loss: 3.3207 (3.2332) grad_norm: 1.5647 (nan) time: 0.5040 [2021-03-26 09:53:20 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 980/1251] eta: 0:02:18 lr: 0.000418 loss: 3.3054 (3.2313) grad_norm: 1.5834 (nan) time: 0.5079 [2021-03-26 09:53:25 swin_small_patch4_window7_224] INFO: Epoch: [166] [ 990/1251] eta: 0:02:12 lr: 0.000418 loss: 3.2350 (3.2298) grad_norm: 1.5765 (nan) time: 0.5035 [2021-03-26 09:53:30 swin_small_patch4_window7_224] INFO: Epoch: [166] [1000/1251] eta: 0:02:07 lr: 0.000418 loss: 3.4409 (3.2343) grad_norm: 1.5095 (nan) time: 0.4989 [2021-03-26 09:53:35 swin_small_patch4_window7_224] INFO: Epoch: [166] [1010/1251] eta: 0:02:02 lr: 0.000418 loss: 3.5196 (3.2336) grad_norm: 1.4692 (nan) time: 0.5068 [2021-03-26 09:53:40 swin_small_patch4_window7_224] INFO: Epoch: [166] [1020/1251] eta: 0:01:57 lr: 0.000418 loss: 3.1602 (3.2312) grad_norm: 1.4659 (nan) time: 0.5076 [2021-03-26 09:53:45 swin_small_patch4_window7_224] INFO: Epoch: [166] [1030/1251] eta: 0:01:52 lr: 0.000418 loss: 3.2570 (3.2314) grad_norm: 1.4925 (nan) time: 0.5047 [2021-03-26 09:53:50 swin_small_patch4_window7_224] INFO: Epoch: [166] [1040/1251] eta: 0:01:47 lr: 0.000418 loss: 3.2489 (3.2298) grad_norm: 1.5276 (nan) time: 0.5026 [2021-03-26 09:53:55 swin_small_patch4_window7_224] INFO: Epoch: [166] [1050/1251] eta: 0:01:42 lr: 0.000418 loss: 3.0635 (3.2279) grad_norm: 1.5807 (nan) time: 0.4986 [2021-03-26 09:54:00 swin_small_patch4_window7_224] INFO: Epoch: [166] [1060/1251] eta: 0:01:37 lr: 0.000418 loss: 3.2215 (3.2304) grad_norm: 1.5931 (nan) time: 0.5008 [2021-03-26 09:54:05 swin_small_patch4_window7_224] INFO: Epoch: [166] [1070/1251] eta: 0:01:32 lr: 0.000418 loss: 3.3936 (3.2313) grad_norm: 1.5361 (nan) time: 0.5043 [2021-03-26 09:54:10 swin_small_patch4_window7_224] INFO: Epoch: [166] [1080/1251] eta: 0:01:26 lr: 0.000418 loss: 3.2362 (3.2312) grad_norm: 1.5361 (nan) time: 0.5007 [2021-03-26 09:54:15 swin_small_patch4_window7_224] INFO: Epoch: [166] [1090/1251] eta: 0:01:21 lr: 0.000418 loss: 3.3129 (3.2309) grad_norm: 1.4939 (nan) time: 0.5004 [2021-03-26 09:54:20 swin_small_patch4_window7_224] INFO: Epoch: [166] [1100/1251] eta: 0:01:16 lr: 0.000418 loss: 3.3258 (3.2313) grad_norm: 1.4880 (nan) time: 0.5016 [2021-03-26 09:54:25 swin_small_patch4_window7_224] INFO: Epoch: [166] [1110/1251] eta: 0:01:11 lr: 0.000418 loss: 3.3773 (3.2337) grad_norm: 1.6039 (nan) time: 0.5013 [2021-03-26 09:54:30 swin_small_patch4_window7_224] INFO: Epoch: [166] [1120/1251] eta: 0:01:06 lr: 0.000418 loss: 3.4656 (3.2341) grad_norm: 1.6039 (nan) time: 0.5019 [2021-03-26 09:54:35 swin_small_patch4_window7_224] INFO: Epoch: [166] [1130/1251] eta: 0:01:01 lr: 0.000418 loss: 3.2289 (3.2343) grad_norm: 1.5630 (nan) time: 0.4982 [2021-03-26 09:54:40 swin_small_patch4_window7_224] INFO: Epoch: [166] [1140/1251] eta: 0:00:56 lr: 0.000418 loss: 3.4290 (3.2351) grad_norm: 1.5154 (nan) time: 0.5026 [2021-03-26 09:54:45 swin_small_patch4_window7_224] INFO: Epoch: [166] [1150/1251] eta: 0:00:51 lr: 0.000418 loss: 3.4125 (3.2351) grad_norm: 1.5650 (nan) time: 0.5035 [2021-03-26 09:54:50 swin_small_patch4_window7_224] INFO: Epoch: [166] [1160/1251] eta: 0:00:46 lr: 0.000418 loss: 3.3151 (3.2371) grad_norm: 1.5990 (nan) time: 0.5011 [2021-03-26 09:54:55 swin_small_patch4_window7_224] INFO: Epoch: [166] [1170/1251] eta: 0:00:41 lr: 0.000418 loss: 3.5106 (3.2391) grad_norm: 1.5419 (nan) time: 0.5021 [2021-03-26 09:55:00 swin_small_patch4_window7_224] INFO: Epoch: [166] [1180/1251] eta: 0:00:36 lr: 0.000418 loss: 3.5187 (3.2409) grad_norm: 1.5307 (nan) time: 0.5033 [2021-03-26 09:55:05 swin_small_patch4_window7_224] INFO: Epoch: [166] [1190/1251] eta: 0:00:30 lr: 0.000418 loss: 3.3919 (3.2396) grad_norm: 1.5720 (nan) time: 0.5050 [2021-03-26 09:55:10 swin_small_patch4_window7_224] INFO: Epoch: [166] [1200/1251] eta: 0:00:25 lr: 0.000418 loss: 3.3271 (3.2410) grad_norm: 1.5720 (nan) time: 0.5047 [2021-03-26 09:55:16 swin_small_patch4_window7_224] INFO: Epoch: [166] [1210/1251] eta: 0:00:20 lr: 0.000418 loss: 3.4156 (3.2429) grad_norm: 1.4902 (nan) time: 0.5093 [2021-03-26 09:55:21 swin_small_patch4_window7_224] INFO: Epoch: [166] [1220/1251] eta: 0:00:15 lr: 0.000417 loss: 3.2945 (3.2431) grad_norm: 1.5314 (nan) time: 0.5068 [2021-03-26 09:55:26 swin_small_patch4_window7_224] INFO: Epoch: [166] [1230/1251] eta: 0:00:10 lr: 0.000417 loss: 3.2951 (3.2449) grad_norm: 1.5312 (nan) time: 0.5026 [2021-03-26 09:55:31 swin_small_patch4_window7_224] INFO: Epoch: [166] [1240/1251] eta: 0:00:05 lr: 0.000417 loss: 3.4884 (3.2450) grad_norm: 1.4926 (nan) time: 0.5058 [2021-03-26 09:55:36 swin_small_patch4_window7_224] INFO: Epoch: [166] [1250/1251] eta: 0:00:00 lr: 0.000417 loss: 2.9994 (3.2437) grad_norm: 1.4914 (nan) time: 0.5059 [2021-03-26 09:55:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:42 loss: 0.8754 (0.8754) acc1: 82.8125 (82.8125) acc5: 93.7500 (93.7500) [2021-03-26 09:55:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8513 (0.8796) acc1: 81.2500 (79.6875) acc5: 95.3125 (94.7443) [2021-03-26 09:55:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8420 (0.8868) acc1: 79.6875 (79.1667) acc5: 95.3125 (95.0893) [2021-03-26 09:55:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8720 (0.8924) acc1: 76.5625 (78.5282) acc5: 93.7500 (94.7581) [2021-03-26 09:55:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8961 (0.8981) acc1: 76.5625 (78.3537) acc5: 93.7500 (94.7790) [2021-03-26 09:55:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8950 (0.8924) acc1: 79.6875 (78.3680) acc5: 95.3125 (94.7200) [2021-03-26 09:56:04 swin_small_patch4_window7_224] INFO: * Acc@1 79.154 Acc@5 94.806 loss 0.884 [2021-03-26 09:56:04 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.2% [2021-03-26 09:56:04 swin_small_patch4_window7_224] INFO: Max accuracy: 79.15% [2021-03-26 09:56:08 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 0/1251] eta: 1:25:25 lr: 0.000417 loss: 3.8181 (3.8181) grad_norm: 1.4628 (1.4628) time: 4.0968 [2021-03-26 09:56:13 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 10/1251] eta: 0:17:31 lr: 0.000417 loss: 3.4775 (3.2591) grad_norm: 1.5802 (1.6148) time: 0.8469 [2021-03-26 09:56:19 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 20/1251] eta: 0:14:11 lr: 0.000417 loss: 2.9484 (3.1634) grad_norm: 1.5585 (1.5904) time: 0.5211 [2021-03-26 09:56:24 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 30/1251] eta: 0:12:47 lr: 0.000417 loss: 2.9243 (3.1107) grad_norm: 1.5006 (1.5498) time: 0.5086 [2021-03-26 09:56:29 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 40/1251] eta: 0:12:03 lr: 0.000417 loss: 3.2982 (3.1612) grad_norm: 1.4980 (1.5431) time: 0.4995 [2021-03-26 09:56:33 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 50/1251] eta: 0:11:33 lr: 0.000417 loss: 3.3586 (3.2082) grad_norm: 1.5354 (1.5423) time: 0.4991 [2021-03-26 09:56:39 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 60/1251] eta: 0:11:13 lr: 0.000417 loss: 3.3586 (3.2166) grad_norm: 1.5192 (1.5383) time: 0.4987 [2021-03-26 09:56:44 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 70/1251] eta: 0:10:57 lr: 0.000417 loss: 3.2096 (3.1924) grad_norm: 1.4488 (1.5265) time: 0.5029 [2021-03-26 09:56:49 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 80/1251] eta: 0:10:44 lr: 0.000417 loss: 3.1575 (3.2014) grad_norm: 1.4055 (1.5214) time: 0.5037 [2021-03-26 09:56:54 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 90/1251] eta: 0:10:33 lr: 0.000417 loss: 3.2284 (3.2087) grad_norm: 1.5082 (1.5384) time: 0.5065 [2021-03-26 09:56:59 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 100/1251] eta: 0:10:22 lr: 0.000417 loss: 3.4250 (3.2286) grad_norm: 1.6826 (1.6351) time: 0.5012 [2021-03-26 09:57:04 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 110/1251] eta: 0:10:13 lr: 0.000417 loss: 3.3651 (3.2280) grad_norm: 1.6473 (1.6311) time: 0.5003 [2021-03-26 09:57:09 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 120/1251] eta: 0:10:04 lr: 0.000417 loss: 3.3445 (3.2456) grad_norm: 1.5215 (1.6215) time: 0.5059 [2021-03-26 09:57:14 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 130/1251] eta: 0:09:58 lr: 0.000417 loss: 3.3908 (3.2549) grad_norm: 1.5711 (1.6239) time: 0.5147 [2021-03-26 09:57:19 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 140/1251] eta: 0:09:51 lr: 0.000417 loss: 3.6329 (3.2746) grad_norm: 1.6707 (1.6316) time: 0.5165 [2021-03-26 09:57:24 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 150/1251] eta: 0:09:43 lr: 0.000417 loss: 3.3480 (3.2641) grad_norm: 1.6220 (1.6314) time: 0.5028 [2021-03-26 09:57:29 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 160/1251] eta: 0:09:36 lr: 0.000417 loss: 3.3480 (3.2812) grad_norm: 1.5462 (1.6348) time: 0.4987 [2021-03-26 09:57:34 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 170/1251] eta: 0:09:28 lr: 0.000417 loss: 3.4739 (3.2935) grad_norm: 1.6295 (1.6374) time: 0.4970 [2021-03-26 09:57:39 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 180/1251] eta: 0:09:22 lr: 0.000417 loss: 3.3020 (3.2863) grad_norm: 1.6499 (1.6381) time: 0.5069 [2021-03-26 09:57:44 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 190/1251] eta: 0:09:16 lr: 0.000417 loss: 3.2849 (3.2953) grad_norm: 1.5751 (1.6330) time: 0.5129 [2021-03-26 09:57:49 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 200/1251] eta: 0:09:10 lr: 0.000417 loss: 3.5928 (3.3041) grad_norm: 1.5172 (1.6293) time: 0.5089 [2021-03-26 09:57:54 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 210/1251] eta: 0:09:03 lr: 0.000416 loss: 3.5917 (3.3098) grad_norm: 1.5788 (1.6273) time: 0.5022 [2021-03-26 09:57:59 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 220/1251] eta: 0:08:57 lr: 0.000416 loss: 3.4987 (3.3106) grad_norm: 1.5793 (1.6282) time: 0.4986 [2021-03-26 09:58:04 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 230/1251] eta: 0:08:51 lr: 0.000416 loss: 3.4245 (3.3099) grad_norm: 1.5883 (1.6274) time: 0.5034 [2021-03-26 09:58:09 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 240/1251] eta: 0:08:45 lr: 0.000416 loss: 3.4245 (3.3158) grad_norm: 1.5713 (1.6244) time: 0.5021 [2021-03-26 09:58:14 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 250/1251] eta: 0:08:39 lr: 0.000416 loss: 3.3198 (3.3050) grad_norm: 1.5492 (1.6223) time: 0.4973 [2021-03-26 09:58:19 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 260/1251] eta: 0:08:33 lr: 0.000416 loss: 3.0751 (3.2996) grad_norm: 1.5933 (1.6222) time: 0.4989 [2021-03-26 09:58:24 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 270/1251] eta: 0:08:28 lr: 0.000416 loss: 3.4552 (3.3029) grad_norm: 1.5933 (1.6225) time: 0.5070 [2021-03-26 09:58:30 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 280/1251] eta: 0:08:22 lr: 0.000416 loss: 3.3259 (3.3008) grad_norm: 1.5501 (1.6184) time: 0.5075 [2021-03-26 09:58:35 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 290/1251] eta: 0:08:16 lr: 0.000416 loss: 3.1470 (3.2934) grad_norm: 1.5035 (1.6152) time: 0.5041 [2021-03-26 09:58:40 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 300/1251] eta: 0:08:11 lr: 0.000416 loss: 3.1594 (3.2936) grad_norm: 1.4996 (1.6133) time: 0.5111 [2021-03-26 09:58:45 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 310/1251] eta: 0:08:06 lr: 0.000416 loss: 3.2402 (3.2829) grad_norm: 1.5870 (1.6157) time: 0.5107 [2021-03-26 09:58:50 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 320/1251] eta: 0:08:01 lr: 0.000416 loss: 2.7364 (3.2706) grad_norm: 1.6480 (1.6161) time: 0.5179 [2021-03-26 09:58:55 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 330/1251] eta: 0:07:55 lr: 0.000416 loss: 2.8007 (3.2666) grad_norm: 1.5655 (1.6157) time: 0.5162 [2021-03-26 09:59:00 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 340/1251] eta: 0:07:50 lr: 0.000416 loss: 3.3278 (3.2693) grad_norm: 1.5655 (1.6143) time: 0.4988 [2021-03-26 09:59:05 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 350/1251] eta: 0:07:44 lr: 0.000416 loss: 3.2962 (3.2691) grad_norm: 1.4819 (1.6105) time: 0.4963 [2021-03-26 09:59:10 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 360/1251] eta: 0:07:38 lr: 0.000416 loss: 3.3089 (3.2705) grad_norm: 1.4724 (1.6071) time: 0.4975 [2021-03-26 09:59:15 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 370/1251] eta: 0:07:33 lr: 0.000416 loss: 3.3996 (3.2683) grad_norm: 1.4980 (1.6046) time: 0.5010 [2021-03-26 09:59:20 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 380/1251] eta: 0:07:28 lr: 0.000416 loss: 3.1441 (3.2666) grad_norm: 1.4831 (1.6034) time: 0.5076 [2021-03-26 09:59:25 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 390/1251] eta: 0:07:22 lr: 0.000416 loss: 3.2003 (3.2634) grad_norm: 1.4595 (1.6011) time: 0.5083 [2021-03-26 09:59:30 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 400/1251] eta: 0:07:17 lr: 0.000416 loss: 3.2349 (3.2625) grad_norm: 1.4926 (1.6011) time: 0.5004 [2021-03-26 09:59:35 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 410/1251] eta: 0:07:11 lr: 0.000416 loss: 3.2721 (3.2649) grad_norm: 1.5932 (1.6010) time: 0.4968 [2021-03-26 09:59:40 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 420/1251] eta: 0:07:06 lr: 0.000416 loss: 3.2233 (3.2617) grad_norm: 1.5712 (1.6003) time: 0.4987 [2021-03-26 09:59:45 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 430/1251] eta: 0:07:01 lr: 0.000416 loss: 3.0905 (3.2559) grad_norm: 1.5712 (1.6008) time: 0.4998 [2021-03-26 09:59:50 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 440/1251] eta: 0:06:55 lr: 0.000416 loss: 3.1942 (3.2580) grad_norm: 1.6115 (1.6014) time: 0.4982 [2021-03-26 09:59:55 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 450/1251] eta: 0:06:50 lr: 0.000416 loss: 3.3544 (3.2612) grad_norm: 1.5715 (1.6008) time: 0.4995 [2021-03-26 10:00:00 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 460/1251] eta: 0:06:45 lr: 0.000415 loss: 3.3966 (3.2636) grad_norm: 1.5526 (1.5994) time: 0.5003 [2021-03-26 10:00:05 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 470/1251] eta: 0:06:39 lr: 0.000415 loss: 3.3526 (3.2595) grad_norm: 1.5138 (1.5997) time: 0.5025 [2021-03-26 10:00:10 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 480/1251] eta: 0:06:34 lr: 0.000415 loss: 3.3855 (3.2626) grad_norm: 1.5991 (1.6008) time: 0.5012 [2021-03-26 10:00:15 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 490/1251] eta: 0:06:29 lr: 0.000415 loss: 3.4355 (3.2627) grad_norm: 1.6880 (1.6036) time: 0.4981 [2021-03-26 10:00:20 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 500/1251] eta: 0:06:23 lr: 0.000415 loss: 3.3041 (3.2610) grad_norm: 1.5877 (1.6021) time: 0.5016 [2021-03-26 10:00:25 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 510/1251] eta: 0:06:18 lr: 0.000415 loss: 3.3691 (3.2635) grad_norm: 1.5347 (1.6010) time: 0.5132 [2021-03-26 10:00:30 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 520/1251] eta: 0:06:13 lr: 0.000415 loss: 3.5467 (3.2667) grad_norm: 1.4913 (1.5986) time: 0.5100 [2021-03-26 10:00:35 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 530/1251] eta: 0:06:08 lr: 0.000415 loss: 3.4420 (3.2662) grad_norm: 1.5119 (1.5975) time: 0.4974 [2021-03-26 10:00:40 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 540/1251] eta: 0:06:03 lr: 0.000415 loss: 3.2568 (3.2643) grad_norm: 1.5236 (1.5967) time: 0.5009 [2021-03-26 10:00:46 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 550/1251] eta: 0:05:58 lr: 0.000415 loss: 3.3470 (3.2631) grad_norm: 1.5007 (1.5949) time: 0.5183 [2021-03-26 10:00:51 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 560/1251] eta: 0:05:53 lr: 0.000415 loss: 3.3597 (3.2626) grad_norm: 1.4870 (1.5945) time: 0.5206 [2021-03-26 10:00:56 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 570/1251] eta: 0:05:48 lr: 0.000415 loss: 3.2053 (3.2608) grad_norm: 1.5534 (1.5943) time: 0.5076 [2021-03-26 10:01:01 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 580/1251] eta: 0:05:42 lr: 0.000415 loss: 3.3433 (3.2629) grad_norm: 1.5234 (1.5924) time: 0.5030 [2021-03-26 10:01:06 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 590/1251] eta: 0:05:37 lr: 0.000415 loss: 3.3433 (3.2647) grad_norm: 1.4534 (1.5908) time: 0.5018 [2021-03-26 10:01:11 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 600/1251] eta: 0:05:32 lr: 0.000415 loss: 3.3014 (3.2664) grad_norm: 1.4370 (1.5904) time: 0.5064 [2021-03-26 10:01:16 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 610/1251] eta: 0:05:27 lr: 0.000415 loss: 3.4370 (3.2667) grad_norm: 1.4906 (1.5907) time: 0.5070 [2021-03-26 10:01:21 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 620/1251] eta: 0:05:22 lr: 0.000415 loss: 3.3758 (3.2642) grad_norm: 1.4824 (1.5888) time: 0.4978 [2021-03-26 10:01:26 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 630/1251] eta: 0:05:16 lr: 0.000415 loss: 3.3153 (3.2657) grad_norm: 1.4800 (1.5883) time: 0.4981 [2021-03-26 10:01:31 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 640/1251] eta: 0:05:11 lr: 0.000415 loss: 3.3410 (3.2659) grad_norm: 1.5438 (1.5897) time: 0.5042 [2021-03-26 10:01:36 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 650/1251] eta: 0:05:06 lr: 0.000415 loss: 3.5343 (3.2702) grad_norm: 1.6029 (1.5893) time: 0.5055 [2021-03-26 10:01:41 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 660/1251] eta: 0:05:01 lr: 0.000415 loss: 3.5535 (3.2687) grad_norm: 1.5800 (1.5895) time: 0.5101 [2021-03-26 10:01:46 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 670/1251] eta: 0:04:56 lr: 0.000415 loss: 3.4327 (3.2683) grad_norm: 1.5330 (1.5880) time: 0.5088 [2021-03-26 10:01:51 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 680/1251] eta: 0:04:51 lr: 0.000415 loss: 3.3707 (3.2678) grad_norm: 1.4668 (1.5872) time: 0.5078 [2021-03-26 10:01:56 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 690/1251] eta: 0:04:46 lr: 0.000415 loss: 3.3981 (3.2696) grad_norm: 1.4668 (1.5867) time: 0.5057 [2021-03-26 10:02:02 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 700/1251] eta: 0:04:40 lr: 0.000414 loss: 3.4866 (3.2685) grad_norm: 1.4714 (1.5860) time: 0.5064 [2021-03-26 10:02:07 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 710/1251] eta: 0:04:35 lr: 0.000414 loss: 2.7554 (3.2630) grad_norm: 1.4503 (1.5841) time: 0.5049 [2021-03-26 10:02:12 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 720/1251] eta: 0:04:30 lr: 0.000414 loss: 3.0870 (3.2628) grad_norm: 1.5107 (1.5839) time: 0.4978 [2021-03-26 10:02:17 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 730/1251] eta: 0:04:25 lr: 0.000414 loss: 3.0005 (3.2573) grad_norm: 1.5488 (1.5831) time: 0.5068 [2021-03-26 10:02:22 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 740/1251] eta: 0:04:20 lr: 0.000414 loss: 3.0013 (3.2560) grad_norm: 1.5488 (1.5829) time: 0.5283 [2021-03-26 10:02:27 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 750/1251] eta: 0:04:15 lr: 0.000414 loss: 3.2626 (3.2563) grad_norm: 1.6172 (1.5838) time: 0.5232 [2021-03-26 10:02:32 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 760/1251] eta: 0:04:10 lr: 0.000414 loss: 3.2730 (3.2582) grad_norm: 1.6110 (1.5833) time: 0.5079 [2021-03-26 10:02:37 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 770/1251] eta: 0:04:05 lr: 0.000414 loss: 3.6461 (3.2631) grad_norm: 1.4643 (1.5821) time: 0.5101 [2021-03-26 10:02:42 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 780/1251] eta: 0:04:00 lr: 0.000414 loss: 3.5374 (3.2631) grad_norm: 1.5039 (1.5823) time: 0.5051 [2021-03-26 10:02:47 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 790/1251] eta: 0:03:54 lr: 0.000414 loss: 3.3734 (3.2630) grad_norm: 1.5055 (1.5812) time: 0.4980 [2021-03-26 10:02:52 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 800/1251] eta: 0:03:49 lr: 0.000414 loss: 3.3399 (3.2627) grad_norm: 1.5055 (1.5804) time: 0.4971 [2021-03-26 10:02:57 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 810/1251] eta: 0:03:44 lr: 0.000414 loss: 3.2966 (3.2602) grad_norm: 1.5446 (1.5810) time: 0.5000 [2021-03-26 10:03:02 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 820/1251] eta: 0:03:39 lr: 0.000414 loss: 3.2335 (3.2602) grad_norm: 1.5739 (1.5800) time: 0.5016 [2021-03-26 10:03:07 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 830/1251] eta: 0:03:34 lr: 0.000414 loss: 2.9773 (3.2561) grad_norm: 1.5394 (1.5794) time: 0.4968 [2021-03-26 10:03:12 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 840/1251] eta: 0:03:29 lr: 0.000414 loss: 3.1250 (3.2574) grad_norm: 1.5466 (1.5793) time: 0.4996 [2021-03-26 10:03:17 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 850/1251] eta: 0:03:24 lr: 0.000414 loss: 3.4943 (3.2593) grad_norm: 1.5937 (1.5797) time: 0.5071 [2021-03-26 10:03:22 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 860/1251] eta: 0:03:19 lr: 0.000414 loss: 3.4020 (3.2594) grad_norm: 1.5701 (1.5802) time: 0.5020 [2021-03-26 10:03:28 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 870/1251] eta: 0:03:13 lr: 0.000414 loss: 3.3681 (3.2592) grad_norm: 1.5815 (1.5806) time: 0.5053 [2021-03-26 10:03:33 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 880/1251] eta: 0:03:08 lr: 0.000414 loss: 3.3681 (3.2593) grad_norm: 1.5607 (1.5804) time: 0.5057 [2021-03-26 10:03:38 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 890/1251] eta: 0:03:03 lr: 0.000414 loss: 3.1187 (3.2572) grad_norm: 1.5607 (1.5819) time: 0.4979 [2021-03-26 10:03:43 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 900/1251] eta: 0:02:58 lr: 0.000414 loss: 3.1187 (3.2549) grad_norm: 1.4853 (1.5810) time: 0.5031 [2021-03-26 10:03:48 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 910/1251] eta: 0:02:53 lr: 0.000414 loss: 3.4345 (3.2576) grad_norm: 1.4807 (1.5800) time: 0.5049 [2021-03-26 10:03:53 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 920/1251] eta: 0:02:48 lr: 0.000414 loss: 3.4540 (3.2562) grad_norm: 1.4747 (1.5787) time: 0.5048 [2021-03-26 10:03:58 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 930/1251] eta: 0:02:43 lr: 0.000414 loss: 3.2000 (3.2553) grad_norm: 1.5128 (1.5789) time: 0.5155 [2021-03-26 10:04:03 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 940/1251] eta: 0:02:38 lr: 0.000414 loss: 3.2000 (3.2544) grad_norm: 1.5529 (1.5777) time: 0.5161 [2021-03-26 10:04:08 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 950/1251] eta: 0:02:33 lr: 0.000413 loss: 3.3452 (3.2541) grad_norm: 1.4963 (1.5774) time: 0.5135 [2021-03-26 10:04:13 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 960/1251] eta: 0:02:28 lr: 0.000413 loss: 3.3562 (3.2544) grad_norm: 1.5244 (1.5768) time: 0.5138 [2021-03-26 10:04:18 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 970/1251] eta: 0:02:23 lr: 0.000413 loss: 3.4758 (3.2574) grad_norm: 1.5377 (1.5767) time: 0.5061 [2021-03-26 10:04:23 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 980/1251] eta: 0:02:17 lr: 0.000413 loss: 3.3838 (3.2564) grad_norm: 1.5709 (1.5768) time: 0.5020 [2021-03-26 10:04:28 swin_small_patch4_window7_224] INFO: Epoch: [167] [ 990/1251] eta: 0:02:12 lr: 0.000413 loss: 3.3296 (3.2563) grad_norm: 1.5591 (1.5765) time: 0.4985 [2021-03-26 10:04:33 swin_small_patch4_window7_224] INFO: Epoch: [167] [1000/1251] eta: 0:02:07 lr: 0.000413 loss: 3.3296 (3.2548) grad_norm: 1.5598 (1.5764) time: 0.4992 [2021-03-26 10:04:38 swin_small_patch4_window7_224] INFO: Epoch: [167] [1010/1251] eta: 0:02:02 lr: 0.000413 loss: 3.3995 (3.2542) grad_norm: 1.5598 (1.5767) time: 0.5035 [2021-03-26 10:04:43 swin_small_patch4_window7_224] INFO: Epoch: [167] [1020/1251] eta: 0:01:57 lr: 0.000413 loss: 3.1320 (3.2495) grad_norm: 1.5222 (1.5761) time: 0.5041 [2021-03-26 10:04:48 swin_small_patch4_window7_224] INFO: Epoch: [167] [1030/1251] eta: 0:01:52 lr: 0.000413 loss: 2.9226 (3.2491) grad_norm: 1.5113 (1.5774) time: 0.5020 [2021-03-26 10:04:53 swin_small_patch4_window7_224] INFO: Epoch: [167] [1040/1251] eta: 0:01:47 lr: 0.000413 loss: 3.2698 (3.2506) grad_norm: 1.5526 (1.5777) time: 0.5014 [2021-03-26 10:04:59 swin_small_patch4_window7_224] INFO: Epoch: [167] [1050/1251] eta: 0:01:42 lr: 0.000413 loss: 3.3704 (3.2495) grad_norm: 1.5924 (1.5780) time: 0.5080 [2021-03-26 10:05:04 swin_small_patch4_window7_224] INFO: Epoch: [167] [1060/1251] eta: 0:01:37 lr: 0.000413 loss: 3.3017 (3.2480) grad_norm: 1.6086 (1.5782) time: 0.5078 [2021-03-26 10:05:09 swin_small_patch4_window7_224] INFO: Epoch: [167] [1070/1251] eta: 0:01:32 lr: 0.000413 loss: 3.2752 (3.2477) grad_norm: 1.5947 (1.5781) time: 0.5061 [2021-03-26 10:05:14 swin_small_patch4_window7_224] INFO: Epoch: [167] [1080/1251] eta: 0:01:26 lr: 0.000413 loss: 3.4109 (3.2490) grad_norm: 1.5032 (1.5782) time: 0.5070 [2021-03-26 10:05:19 swin_small_patch4_window7_224] INFO: Epoch: [167] [1090/1251] eta: 0:01:21 lr: 0.000413 loss: 3.4109 (3.2475) grad_norm: 1.4863 (1.5770) time: 0.5054 [2021-03-26 10:05:24 swin_small_patch4_window7_224] INFO: Epoch: [167] [1100/1251] eta: 0:01:16 lr: 0.000413 loss: 3.1564 (3.2478) grad_norm: 1.5055 (1.5770) time: 0.5046 [2021-03-26 10:05:29 swin_small_patch4_window7_224] INFO: Epoch: [167] [1110/1251] eta: 0:01:11 lr: 0.000413 loss: 3.2970 (3.2478) grad_norm: 1.5600 (1.5774) time: 0.5082 [2021-03-26 10:05:34 swin_small_patch4_window7_224] INFO: Epoch: [167] [1120/1251] eta: 0:01:06 lr: 0.000413 loss: 3.2949 (3.2473) grad_norm: 1.5564 (1.5770) time: 0.5050 [2021-03-26 10:05:39 swin_small_patch4_window7_224] INFO: Epoch: [167] [1130/1251] eta: 0:01:01 lr: 0.000413 loss: 3.2317 (3.2458) grad_norm: 1.4965 (1.5766) time: 0.4938 [2021-03-26 10:05:44 swin_small_patch4_window7_224] INFO: Epoch: [167] [1140/1251] eta: 0:00:56 lr: 0.000413 loss: 3.2953 (3.2480) grad_norm: 1.4670 (1.5760) time: 0.4951 [2021-03-26 10:05:49 swin_small_patch4_window7_224] INFO: Epoch: [167] [1150/1251] eta: 0:00:51 lr: 0.000413 loss: 3.4440 (3.2475) grad_norm: 1.4670 (1.5753) time: 0.5013 [2021-03-26 10:05:54 swin_small_patch4_window7_224] INFO: Epoch: [167] [1160/1251] eta: 0:00:46 lr: 0.000413 loss: 3.2043 (3.2465) grad_norm: 1.5288 (1.5757) time: 0.5024 [2021-03-26 10:05:59 swin_small_patch4_window7_224] INFO: Epoch: [167] [1170/1251] eta: 0:00:41 lr: 0.000413 loss: 3.1275 (3.2447) grad_norm: 1.5580 (1.5761) time: 0.5018 [2021-03-26 10:06:04 swin_small_patch4_window7_224] INFO: Epoch: [167] [1180/1251] eta: 0:00:36 lr: 0.000413 loss: 3.2572 (3.2447) grad_norm: 1.5567 (1.5759) time: 0.5017 [2021-03-26 10:06:09 swin_small_patch4_window7_224] INFO: Epoch: [167] [1190/1251] eta: 0:00:30 lr: 0.000412 loss: 3.1912 (3.2441) grad_norm: 1.5493 (1.5761) time: 0.5028 [2021-03-26 10:06:14 swin_small_patch4_window7_224] INFO: Epoch: [167] [1200/1251] eta: 0:00:25 lr: 0.000412 loss: 3.2123 (3.2446) grad_norm: 1.5633 (1.5758) time: 0.5049 [2021-03-26 10:06:19 swin_small_patch4_window7_224] INFO: Epoch: [167] [1210/1251] eta: 0:00:20 lr: 0.000412 loss: 3.0078 (3.2416) grad_norm: 1.5718 (1.5757) time: 0.5053 [2021-03-26 10:06:24 swin_small_patch4_window7_224] INFO: Epoch: [167] [1220/1251] eta: 0:00:15 lr: 0.000412 loss: 3.0773 (3.2418) grad_norm: 1.5183 (1.5751) time: 0.5063 [2021-03-26 10:06:29 swin_small_patch4_window7_224] INFO: Epoch: [167] [1230/1251] eta: 0:00:10 lr: 0.000412 loss: 3.1882 (3.2409) grad_norm: 1.5959 (1.5767) time: 0.5084 [2021-03-26 10:06:34 swin_small_patch4_window7_224] INFO: Epoch: [167] [1240/1251] eta: 0:00:05 lr: 0.000412 loss: 3.4143 (3.2426) grad_norm: 1.6504 (1.5771) time: 0.5029 [2021-03-26 10:06:39 swin_small_patch4_window7_224] INFO: Epoch: [167] [1250/1251] eta: 0:00:00 lr: 0.000412 loss: 3.3461 (3.2411) grad_norm: 1.5606 (1.5771) time: 0.4953 [2021-03-26 10:06:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:31 loss: 0.5757 (0.5757) acc1: 85.9375 (85.9375) acc5: 100.0000 (100.0000) [2021-03-26 10:06:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8990 (0.9040) acc1: 78.1250 (77.8409) acc5: 95.3125 (94.8864) [2021-03-26 10:06:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8990 (0.9219) acc1: 78.1250 (77.8274) acc5: 92.1875 (94.3452) [2021-03-26 10:06:58 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8023 (0.8817) acc1: 79.6875 (79.0323) acc5: 95.3125 (94.9093) [2021-03-26 10:06:59 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8182 (0.8916) acc1: 79.6875 (78.6204) acc5: 95.3125 (94.8171) [2021-03-26 10:07:00 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8596 (0.8952) acc1: 79.6875 (78.5600) acc5: 95.3125 (94.7520) [2021-03-26 10:07:09 swin_small_patch4_window7_224] INFO: * Acc@1 79.088 Acc@5 94.744 loss 0.875 [2021-03-26 10:07:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-26 10:07:09 swin_small_patch4_window7_224] INFO: Max accuracy: 79.15% [2021-03-26 10:07:13 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 0/1251] eta: 1:27:10 lr: 0.000412 loss: 3.8400 (3.8400) grad_norm: 1.4406 (1.4406) time: 4.1812 [2021-03-26 10:07:18 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 10/1251] eta: 0:17:27 lr: 0.000412 loss: 3.3649 (3.2654) grad_norm: 1.4406 (1.5139) time: 0.8442 [2021-03-26 10:07:23 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 20/1251] eta: 0:14:03 lr: 0.000412 loss: 3.3310 (3.2166) grad_norm: 1.5009 (1.5066) time: 0.5107 [2021-03-26 10:07:28 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 30/1251] eta: 0:12:44 lr: 0.000412 loss: 3.3310 (3.1900) grad_norm: 1.5009 (1.5106) time: 0.5056 [2021-03-26 10:07:33 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 40/1251] eta: 0:12:05 lr: 0.000412 loss: 3.3800 (3.2109) grad_norm: 1.5270 (1.5266) time: 0.5081 [2021-03-26 10:07:39 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 50/1251] eta: 0:11:40 lr: 0.000412 loss: 3.3994 (3.2461) grad_norm: 1.5485 (1.5419) time: 0.5182 [2021-03-26 10:07:44 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 60/1251] eta: 0:11:19 lr: 0.000412 loss: 3.3478 (3.2433) grad_norm: 1.6172 (1.5550) time: 0.5120 [2021-03-26 10:07:49 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 70/1251] eta: 0:11:02 lr: 0.000412 loss: 3.4754 (3.2613) grad_norm: 1.5717 (1.5560) time: 0.5025 [2021-03-26 10:07:54 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 80/1251] eta: 0:10:49 lr: 0.000412 loss: 3.3949 (3.2466) grad_norm: 1.4842 (1.5425) time: 0.5072 [2021-03-26 10:07:59 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 90/1251] eta: 0:10:37 lr: 0.000412 loss: 3.3158 (3.2474) grad_norm: 1.4955 (1.5489) time: 0.5070 [2021-03-26 10:08:04 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 100/1251] eta: 0:10:25 lr: 0.000412 loss: 3.4337 (3.2820) grad_norm: 1.4973 (1.5508) time: 0.4957 [2021-03-26 10:08:09 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 110/1251] eta: 0:10:15 lr: 0.000412 loss: 3.4337 (3.2686) grad_norm: 1.4599 (1.5423) time: 0.4939 [2021-03-26 10:08:14 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 120/1251] eta: 0:10:06 lr: 0.000412 loss: 3.1734 (3.2450) grad_norm: 1.4818 (1.5517) time: 0.5005 [2021-03-26 10:08:19 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 130/1251] eta: 0:09:58 lr: 0.000412 loss: 3.1734 (3.2380) grad_norm: 1.5332 (1.5504) time: 0.5048 [2021-03-26 10:08:24 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 140/1251] eta: 0:09:50 lr: 0.000412 loss: 3.1961 (3.2367) grad_norm: 1.5426 (1.5524) time: 0.5041 [2021-03-26 10:08:29 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 150/1251] eta: 0:09:44 lr: 0.000412 loss: 2.9288 (3.2106) grad_norm: 1.5885 (1.5574) time: 0.5120 [2021-03-26 10:08:34 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 160/1251] eta: 0:09:37 lr: 0.000412 loss: 2.7193 (3.2043) grad_norm: 1.6277 (1.5643) time: 0.5148 [2021-03-26 10:08:39 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 170/1251] eta: 0:09:31 lr: 0.000412 loss: 3.3347 (3.2066) grad_norm: 1.6006 (1.5643) time: 0.5153 [2021-03-26 10:08:45 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 180/1251] eta: 0:09:25 lr: 0.000412 loss: 3.3839 (3.2203) grad_norm: 1.5370 (1.5650) time: 0.5184 [2021-03-26 10:08:50 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 190/1251] eta: 0:09:18 lr: 0.000411 loss: 3.0884 (3.1983) grad_norm: 1.5370 (1.5625) time: 0.5059 [2021-03-26 10:08:55 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 200/1251] eta: 0:09:12 lr: 0.000411 loss: 2.9982 (3.2054) grad_norm: 1.4993 (1.5601) time: 0.5048 [2021-03-26 10:09:00 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 210/1251] eta: 0:09:06 lr: 0.000411 loss: 3.1376 (3.1948) grad_norm: 1.4876 (1.5554) time: 0.5057 [2021-03-26 10:09:05 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 220/1251] eta: 0:08:59 lr: 0.000411 loss: 3.1020 (3.1910) grad_norm: 1.4761 (1.5555) time: 0.5016 [2021-03-26 10:09:10 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 230/1251] eta: 0:08:54 lr: 0.000411 loss: 3.1792 (3.1933) grad_norm: 1.4557 (1.5491) time: 0.5077 [2021-03-26 10:09:15 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 240/1251] eta: 0:08:48 lr: 0.000411 loss: 3.2800 (3.1997) grad_norm: 1.4325 (1.5496) time: 0.5094 [2021-03-26 10:09:20 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 250/1251] eta: 0:08:42 lr: 0.000411 loss: 3.4109 (3.2021) grad_norm: 1.5898 (1.5524) time: 0.5104 [2021-03-26 10:09:25 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 260/1251] eta: 0:08:36 lr: 0.000411 loss: 3.3415 (3.2024) grad_norm: 1.5722 (1.5550) time: 0.5115 [2021-03-26 10:09:30 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 270/1251] eta: 0:08:30 lr: 0.000411 loss: 3.2294 (3.1981) grad_norm: 1.5552 (1.5571) time: 0.5031 [2021-03-26 10:09:35 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 280/1251] eta: 0:08:25 lr: 0.000411 loss: 3.2111 (3.1970) grad_norm: 1.4969 (1.5564) time: 0.5000 [2021-03-26 10:09:40 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 290/1251] eta: 0:08:19 lr: 0.000411 loss: 3.2111 (3.1987) grad_norm: 1.5469 (1.5580) time: 0.5003 [2021-03-26 10:09:45 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 300/1251] eta: 0:08:13 lr: 0.000411 loss: 3.1065 (3.1911) grad_norm: 1.5292 (1.5574) time: 0.4988 [2021-03-26 10:09:50 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 310/1251] eta: 0:08:07 lr: 0.000411 loss: 3.2453 (3.2050) grad_norm: 1.5348 (1.5587) time: 0.4989 [2021-03-26 10:09:55 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 320/1251] eta: 0:08:01 lr: 0.000411 loss: 3.4665 (3.2035) grad_norm: 1.5315 (1.5575) time: 0.5009 [2021-03-26 10:10:00 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 330/1251] eta: 0:07:56 lr: 0.000411 loss: 3.3583 (3.2037) grad_norm: 1.5127 (1.5573) time: 0.5026 [2021-03-26 10:10:05 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 340/1251] eta: 0:07:50 lr: 0.000411 loss: 3.2623 (3.2078) grad_norm: 1.5363 (1.5593) time: 0.5051 [2021-03-26 10:10:10 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 350/1251] eta: 0:07:45 lr: 0.000411 loss: 3.2145 (3.2073) grad_norm: 1.5360 (1.5598) time: 0.5073 [2021-03-26 10:10:15 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 360/1251] eta: 0:07:39 lr: 0.000411 loss: 3.0357 (3.1996) grad_norm: 1.5720 (1.5607) time: 0.5015 [2021-03-26 10:10:20 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 370/1251] eta: 0:07:34 lr: 0.000411 loss: 3.0705 (3.2001) grad_norm: 1.5254 (1.5597) time: 0.4994 [2021-03-26 10:10:25 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 380/1251] eta: 0:07:28 lr: 0.000411 loss: 3.2454 (3.1990) grad_norm: 1.5415 (1.5616) time: 0.5031 [2021-03-26 10:10:30 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 390/1251] eta: 0:07:23 lr: 0.000411 loss: 3.1606 (3.1999) grad_norm: 1.6194 (1.5641) time: 0.5044 [2021-03-26 10:10:35 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 400/1251] eta: 0:07:17 lr: 0.000411 loss: 3.3022 (3.2055) grad_norm: 1.5822 (1.5640) time: 0.5005 [2021-03-26 10:10:40 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 410/1251] eta: 0:07:12 lr: 0.000411 loss: 3.4519 (3.2094) grad_norm: 1.5301 (1.5618) time: 0.5017 [2021-03-26 10:10:45 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 420/1251] eta: 0:07:07 lr: 0.000411 loss: 3.1296 (3.2035) grad_norm: 1.5301 (1.5616) time: 0.5010 [2021-03-26 10:10:50 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 430/1251] eta: 0:07:01 lr: 0.000410 loss: 2.9569 (3.2010) grad_norm: 1.5279 (1.5619) time: 0.5015 [2021-03-26 10:10:56 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 440/1251] eta: 0:06:56 lr: 0.000410 loss: 3.1541 (3.2009) grad_norm: 1.5279 (1.5632) time: 0.5107 [2021-03-26 10:11:01 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 450/1251] eta: 0:06:51 lr: 0.000410 loss: 3.2545 (3.2013) grad_norm: 1.5016 (1.5615) time: 0.5074 [2021-03-26 10:11:06 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 460/1251] eta: 0:06:45 lr: 0.000410 loss: 3.3876 (3.2054) grad_norm: 1.5016 (1.5634) time: 0.4987 [2021-03-26 10:11:11 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 470/1251] eta: 0:06:40 lr: 0.000410 loss: 3.3523 (3.2083) grad_norm: 1.4877 (1.5612) time: 0.5004 [2021-03-26 10:11:16 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 480/1251] eta: 0:06:35 lr: 0.000410 loss: 3.1360 (3.2060) grad_norm: 1.4715 (1.5609) time: 0.5055 [2021-03-26 10:11:21 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 490/1251] eta: 0:06:30 lr: 0.000410 loss: 3.1194 (3.2044) grad_norm: 1.5178 (1.5606) time: 0.5017 [2021-03-26 10:11:26 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 500/1251] eta: 0:06:24 lr: 0.000410 loss: 3.2831 (3.2024) grad_norm: 1.5376 (1.5604) time: 0.4992 [2021-03-26 10:11:31 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 510/1251] eta: 0:06:19 lr: 0.000410 loss: 3.2831 (3.2056) grad_norm: 1.5395 (1.5610) time: 0.5034 [2021-03-26 10:11:36 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 520/1251] eta: 0:06:14 lr: 0.000410 loss: 3.0993 (3.1996) grad_norm: 1.5094 (1.5598) time: 0.5007 [2021-03-26 10:11:41 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 530/1251] eta: 0:06:09 lr: 0.000410 loss: 2.7681 (3.1949) grad_norm: 1.5437 (1.5622) time: 0.5035 [2021-03-26 10:11:46 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 540/1251] eta: 0:06:03 lr: 0.000410 loss: 2.8230 (3.1895) grad_norm: 1.5724 (1.5621) time: 0.5138 [2021-03-26 10:11:51 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 550/1251] eta: 0:05:59 lr: 0.000410 loss: 3.1310 (3.1929) grad_norm: 1.5653 (1.5624) time: 0.5308 [2021-03-26 10:11:56 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 560/1251] eta: 0:05:54 lr: 0.000410 loss: 3.5495 (3.1968) grad_norm: 1.5653 (1.5636) time: 0.5267 [2021-03-26 10:12:01 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 570/1251] eta: 0:05:48 lr: 0.000410 loss: 3.4261 (3.1972) grad_norm: 1.5395 (1.5642) time: 0.5065 [2021-03-26 10:12:06 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 580/1251] eta: 0:05:43 lr: 0.000410 loss: 3.4145 (3.2011) grad_norm: 1.5710 (1.5653) time: 0.5014 [2021-03-26 10:12:12 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 590/1251] eta: 0:05:38 lr: 0.000410 loss: 3.3765 (3.2023) grad_norm: 1.5303 (1.5647) time: 0.5116 [2021-03-26 10:12:17 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 600/1251] eta: 0:05:33 lr: 0.000410 loss: 3.4470 (3.2041) grad_norm: 1.5083 (1.5654) time: 0.5219 [2021-03-26 10:12:22 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 610/1251] eta: 0:05:28 lr: 0.000410 loss: 3.4685 (3.2031) grad_norm: 1.5575 (1.5654) time: 0.5158 [2021-03-26 10:12:27 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 620/1251] eta: 0:05:23 lr: 0.000410 loss: 3.1623 (3.2038) grad_norm: 1.5520 (1.5654) time: 0.5099 [2021-03-26 10:12:32 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 630/1251] eta: 0:05:18 lr: 0.000410 loss: 3.1388 (3.2020) grad_norm: 1.5341 (1.5654) time: 0.5065 [2021-03-26 10:12:37 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 640/1251] eta: 0:05:12 lr: 0.000410 loss: 3.1438 (3.2012) grad_norm: 1.4478 (1.5632) time: 0.5050 [2021-03-26 10:12:42 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 650/1251] eta: 0:05:07 lr: 0.000410 loss: 3.3492 (3.1997) grad_norm: 1.4567 (1.5645) time: 0.4998 [2021-03-26 10:12:47 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 660/1251] eta: 0:05:02 lr: 0.000410 loss: 3.4288 (3.2017) grad_norm: 1.5934 (1.5655) time: 0.5003 [2021-03-26 10:12:52 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 670/1251] eta: 0:04:57 lr: 0.000410 loss: 3.1908 (3.2006) grad_norm: 1.5817 (1.5653) time: 0.5062 [2021-03-26 10:12:57 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 680/1251] eta: 0:04:52 lr: 0.000409 loss: 3.1908 (3.2018) grad_norm: 1.4740 (1.5635) time: 0.5051 [2021-03-26 10:13:02 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 690/1251] eta: 0:04:46 lr: 0.000409 loss: 3.2792 (3.2032) grad_norm: 1.4712 (1.5631) time: 0.5019 [2021-03-26 10:13:07 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 700/1251] eta: 0:04:41 lr: 0.000409 loss: 3.2508 (3.1988) grad_norm: 1.5787 (1.5639) time: 0.4982 [2021-03-26 10:13:12 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 710/1251] eta: 0:04:36 lr: 0.000409 loss: 3.1010 (3.2002) grad_norm: 1.5823 (1.5630) time: 0.5026 [2021-03-26 10:13:18 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 720/1251] eta: 0:04:31 lr: 0.000409 loss: 3.3017 (3.2029) grad_norm: 1.5079 (1.5637) time: 0.5106 [2021-03-26 10:13:23 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 730/1251] eta: 0:04:26 lr: 0.000409 loss: 3.4068 (3.2055) grad_norm: 1.5615 (1.5638) time: 0.5087 [2021-03-26 10:13:28 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 740/1251] eta: 0:04:21 lr: 0.000409 loss: 3.3505 (3.2057) grad_norm: 1.5492 (1.5627) time: 0.5231 [2021-03-26 10:13:33 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 750/1251] eta: 0:04:16 lr: 0.000409 loss: 3.0860 (3.2036) grad_norm: 1.4881 (1.5630) time: 0.5252 [2021-03-26 10:13:38 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 760/1251] eta: 0:04:11 lr: 0.000409 loss: 2.7876 (3.2005) grad_norm: 1.5353 (1.5635) time: 0.5126 [2021-03-26 10:13:43 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 770/1251] eta: 0:04:05 lr: 0.000409 loss: 3.1149 (3.2021) grad_norm: 1.5353 (1.5633) time: 0.5105 [2021-03-26 10:13:48 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 780/1251] eta: 0:04:00 lr: 0.000409 loss: 3.3530 (3.2034) grad_norm: 1.5461 (1.5638) time: 0.5067 [2021-03-26 10:13:53 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 790/1251] eta: 0:03:55 lr: 0.000409 loss: 3.3639 (3.2047) grad_norm: 1.5649 (1.5639) time: 0.5090 [2021-03-26 10:13:59 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 800/1251] eta: 0:03:50 lr: 0.000409 loss: 3.3639 (3.2068) grad_norm: 1.5308 (1.5632) time: 0.5232 [2021-03-26 10:14:04 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 810/1251] eta: 0:03:45 lr: 0.000409 loss: 3.4578 (3.2100) grad_norm: 1.4775 (1.5629) time: 0.5236 [2021-03-26 10:14:09 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 820/1251] eta: 0:03:40 lr: 0.000409 loss: 3.4082 (3.2131) grad_norm: 1.5855 (1.5639) time: 0.5032 [2021-03-26 10:14:14 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 830/1251] eta: 0:03:35 lr: 0.000409 loss: 3.5437 (3.2185) grad_norm: 1.6497 (1.5653) time: 0.5030 [2021-03-26 10:14:19 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 840/1251] eta: 0:03:30 lr: 0.000409 loss: 3.5553 (3.2220) grad_norm: 1.5569 (1.5651) time: 0.5091 [2021-03-26 10:14:24 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 850/1251] eta: 0:03:25 lr: 0.000409 loss: 3.3515 (3.2234) grad_norm: 1.5504 (1.5650) time: 0.5072 [2021-03-26 10:14:29 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 860/1251] eta: 0:03:19 lr: 0.000409 loss: 3.3278 (3.2257) grad_norm: 1.5570 (1.5649) time: 0.5043 [2021-03-26 10:14:34 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 870/1251] eta: 0:03:14 lr: 0.000409 loss: 3.4730 (3.2252) grad_norm: 1.5392 (1.5652) time: 0.5043 [2021-03-26 10:14:39 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 880/1251] eta: 0:03:09 lr: 0.000409 loss: 3.2721 (3.2266) grad_norm: 1.5400 (1.5648) time: 0.5070 [2021-03-26 10:14:45 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 890/1251] eta: 0:03:04 lr: 0.000409 loss: 3.3095 (3.2264) grad_norm: 1.5735 (1.5654) time: 0.5127 [2021-03-26 10:14:50 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 900/1251] eta: 0:02:59 lr: 0.000409 loss: 3.2842 (3.2255) grad_norm: 1.5466 (1.5660) time: 0.5085 [2021-03-26 10:14:55 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 910/1251] eta: 0:02:54 lr: 0.000409 loss: 3.1846 (3.2250) grad_norm: 1.4771 (1.5652) time: 0.5089 [2021-03-26 10:15:00 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 920/1251] eta: 0:02:49 lr: 0.000409 loss: 3.2769 (3.2251) grad_norm: 1.4771 (1.5658) time: 0.5128 [2021-03-26 10:15:05 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 930/1251] eta: 0:02:44 lr: 0.000408 loss: 3.2769 (3.2229) grad_norm: 1.6089 (1.5664) time: 0.5008 [2021-03-26 10:15:10 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 940/1251] eta: 0:02:38 lr: 0.000408 loss: 2.8769 (3.2209) grad_norm: 1.5816 (1.5666) time: 0.5050 [2021-03-26 10:15:15 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 950/1251] eta: 0:02:33 lr: 0.000408 loss: 3.3785 (3.2225) grad_norm: 1.5651 (1.5681) time: 0.5127 [2021-03-26 10:15:20 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 960/1251] eta: 0:02:28 lr: 0.000408 loss: 3.4190 (3.2247) grad_norm: 1.5567 (1.5680) time: 0.5139 [2021-03-26 10:15:25 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 970/1251] eta: 0:02:23 lr: 0.000408 loss: 3.4360 (3.2263) grad_norm: 1.5540 (1.5681) time: 0.5139 [2021-03-26 10:15:30 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 980/1251] eta: 0:02:18 lr: 0.000408 loss: 3.5068 (3.2289) grad_norm: 1.4991 (1.5671) time: 0.5073 [2021-03-26 10:15:35 swin_small_patch4_window7_224] INFO: Epoch: [168] [ 990/1251] eta: 0:02:13 lr: 0.000408 loss: 3.5239 (3.2279) grad_norm: 1.5003 (1.5668) time: 0.5078 [2021-03-26 10:15:40 swin_small_patch4_window7_224] INFO: Epoch: [168] [1000/1251] eta: 0:02:08 lr: 0.000408 loss: 3.1281 (3.2282) grad_norm: 1.5372 (1.5672) time: 0.5072 [2021-03-26 10:15:46 swin_small_patch4_window7_224] INFO: Epoch: [168] [1010/1251] eta: 0:02:03 lr: 0.000408 loss: 3.0831 (3.2256) grad_norm: 1.5521 (1.5674) time: 0.5072 [2021-03-26 10:15:51 swin_small_patch4_window7_224] INFO: Epoch: [168] [1020/1251] eta: 0:01:57 lr: 0.000408 loss: 3.1841 (3.2260) grad_norm: 1.6272 (1.5689) time: 0.5037 [2021-03-26 10:15:56 swin_small_patch4_window7_224] INFO: Epoch: [168] [1030/1251] eta: 0:01:52 lr: 0.000408 loss: 3.3347 (3.2257) grad_norm: 1.6100 (1.5693) time: 0.5017 [2021-03-26 10:16:01 swin_small_patch4_window7_224] INFO: Epoch: [168] [1040/1251] eta: 0:01:47 lr: 0.000408 loss: 3.2341 (3.2264) grad_norm: 1.5791 (1.5698) time: 0.5015 [2021-03-26 10:16:06 swin_small_patch4_window7_224] INFO: Epoch: [168] [1050/1251] eta: 0:01:42 lr: 0.000408 loss: 3.4585 (3.2297) grad_norm: 1.5762 (1.5698) time: 0.4996 [2021-03-26 10:16:11 swin_small_patch4_window7_224] INFO: Epoch: [168] [1060/1251] eta: 0:01:37 lr: 0.000408 loss: 3.6875 (3.2330) grad_norm: 1.5452 (1.5705) time: 0.4977 [2021-03-26 10:16:16 swin_small_patch4_window7_224] INFO: Epoch: [168] [1070/1251] eta: 0:01:32 lr: 0.000408 loss: 3.6562 (3.2332) grad_norm: 1.5109 (1.5701) time: 0.4993 [2021-03-26 10:16:21 swin_small_patch4_window7_224] INFO: Epoch: [168] [1080/1251] eta: 0:01:27 lr: 0.000408 loss: 3.4386 (3.2345) grad_norm: 1.5285 (1.5701) time: 0.5052 [2021-03-26 10:16:26 swin_small_patch4_window7_224] INFO: Epoch: [168] [1090/1251] eta: 0:01:22 lr: 0.000408 loss: 3.0738 (3.2333) grad_norm: 1.5696 (1.5700) time: 0.4974 [2021-03-26 10:16:31 swin_small_patch4_window7_224] INFO: Epoch: [168] [1100/1251] eta: 0:01:17 lr: 0.000408 loss: 2.7885 (3.2288) grad_norm: 1.5723 (1.5709) time: 0.4944 [2021-03-26 10:16:36 swin_small_patch4_window7_224] INFO: Epoch: [168] [1110/1251] eta: 0:01:11 lr: 0.000408 loss: 2.5202 (3.2237) grad_norm: 1.6024 (1.5710) time: 0.5015 [2021-03-26 10:16:41 swin_small_patch4_window7_224] INFO: Epoch: [168] [1120/1251] eta: 0:01:06 lr: 0.000408 loss: 2.9210 (3.2242) grad_norm: 1.5763 (1.5708) time: 0.5012 [2021-03-26 10:16:46 swin_small_patch4_window7_224] INFO: Epoch: [168] [1130/1251] eta: 0:01:01 lr: 0.000408 loss: 3.2563 (3.2224) grad_norm: 1.5388 (1.5706) time: 0.4973 [2021-03-26 10:16:51 swin_small_patch4_window7_224] INFO: Epoch: [168] [1140/1251] eta: 0:00:56 lr: 0.000408 loss: 3.1685 (3.2218) grad_norm: 1.5653 (1.5708) time: 0.4988 [2021-03-26 10:16:56 swin_small_patch4_window7_224] INFO: Epoch: [168] [1150/1251] eta: 0:00:51 lr: 0.000408 loss: 3.2823 (3.2208) grad_norm: 1.5653 (1.5707) time: 0.5020 [2021-03-26 10:17:01 swin_small_patch4_window7_224] INFO: Epoch: [168] [1160/1251] eta: 0:00:46 lr: 0.000408 loss: 3.1096 (3.2185) grad_norm: 1.4903 (1.5700) time: 0.5021 [2021-03-26 10:17:06 swin_small_patch4_window7_224] INFO: Epoch: [168] [1170/1251] eta: 0:00:41 lr: 0.000407 loss: 2.9961 (3.2180) grad_norm: 1.4773 (1.5696) time: 0.5044 [2021-03-26 10:17:11 swin_small_patch4_window7_224] INFO: Epoch: [168] [1180/1251] eta: 0:00:36 lr: 0.000407 loss: 2.9961 (3.2143) grad_norm: 1.4773 (1.5692) time: 0.5071 [2021-03-26 10:17:16 swin_small_patch4_window7_224] INFO: Epoch: [168] [1190/1251] eta: 0:00:31 lr: 0.000407 loss: 2.8970 (3.2134) grad_norm: 1.5138 (1.5691) time: 0.5042 [2021-03-26 10:17:21 swin_small_patch4_window7_224] INFO: Epoch: [168] [1200/1251] eta: 0:00:25 lr: 0.000407 loss: 3.2987 (3.2136) grad_norm: 1.5263 (1.5692) time: 0.5003 [2021-03-26 10:17:26 swin_small_patch4_window7_224] INFO: Epoch: [168] [1210/1251] eta: 0:00:20 lr: 0.000407 loss: 3.2987 (3.2135) grad_norm: 1.6155 (1.5698) time: 0.5018 [2021-03-26 10:17:31 swin_small_patch4_window7_224] INFO: Epoch: [168] [1220/1251] eta: 0:00:15 lr: 0.000407 loss: 3.2622 (3.2150) grad_norm: 1.6155 (1.5700) time: 0.5052 [2021-03-26 10:17:36 swin_small_patch4_window7_224] INFO: Epoch: [168] [1230/1251] eta: 0:00:10 lr: 0.000407 loss: 3.3470 (3.2161) grad_norm: 1.5540 (1.5696) time: 0.5034 [2021-03-26 10:17:41 swin_small_patch4_window7_224] INFO: Epoch: [168] [1240/1251] eta: 0:00:05 lr: 0.000407 loss: 3.3703 (3.2172) grad_norm: 1.5540 (1.5699) time: 0.5051 [2021-03-26 10:17:46 swin_small_patch4_window7_224] INFO: Epoch: [168] [1250/1251] eta: 0:00:00 lr: 0.000407 loss: 3.1527 (3.2177) grad_norm: 1.6082 (1.5700) time: 0.5084 [2021-03-26 10:17:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:18 loss: 0.8991 (0.8991) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 10:17:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8991 (0.9186) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.0284) [2021-03-26 10:18:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8396 (0.8931) acc1: 78.1250 (78.1994) acc5: 95.3125 (95.3125) [2021-03-26 10:18:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8384 (0.8615) acc1: 78.1250 (78.6290) acc5: 96.8750 (95.7661) [2021-03-26 10:18:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8398 (0.8765) acc1: 78.1250 (78.5442) acc5: 95.3125 (95.5412) [2021-03-26 10:18:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8360 (0.8733) acc1: 79.2453 (78.4960) acc5: 95.3125 (95.5840) [2021-03-26 10:18:13 swin_small_patch4_window7_224] INFO: * Acc@1 79.224 Acc@5 94.960 loss 0.863 [2021-03-26 10:18:13 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.2% [2021-03-26 10:18:13 swin_small_patch4_window7_224] INFO: Max accuracy: 79.22% [2021-03-26 10:18:17 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 0/1251] eta: 1:28:23 lr: 0.000407 loss: 3.4385 (3.4385) grad_norm: 1.6525 (1.6525) time: 4.2392 [2021-03-26 10:18:22 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 10/1251] eta: 0:17:47 lr: 0.000407 loss: 2.9155 (2.8528) grad_norm: 1.5799 (1.5784) time: 0.8598 [2021-03-26 10:18:27 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 20/1251] eta: 0:14:10 lr: 0.000407 loss: 2.9155 (2.9277) grad_norm: 1.5182 (1.5792) time: 0.5132 [2021-03-26 10:18:33 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 30/1251] eta: 0:12:51 lr: 0.000407 loss: 3.1853 (2.9898) grad_norm: 1.5182 (1.5599) time: 0.5068 [2021-03-26 10:18:38 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 40/1251] eta: 0:12:10 lr: 0.000407 loss: 3.1209 (2.9847) grad_norm: 1.5412 (1.5831) time: 0.5118 [2021-03-26 10:18:43 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 50/1251] eta: 0:11:42 lr: 0.000407 loss: 3.1209 (3.0445) grad_norm: 1.5731 (1.6006) time: 0.5128 [2021-03-26 10:18:48 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 60/1251] eta: 0:11:21 lr: 0.000407 loss: 3.0684 (3.0130) grad_norm: 1.5272 (1.5878) time: 0.5083 [2021-03-26 10:18:53 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 70/1251] eta: 0:11:04 lr: 0.000407 loss: 3.0024 (3.0571) grad_norm: 1.4888 (1.5853) time: 0.5060 [2021-03-26 10:18:58 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 80/1251] eta: 0:10:50 lr: 0.000407 loss: 3.2314 (3.0620) grad_norm: 1.5307 (1.5873) time: 0.5055 [2021-03-26 10:19:03 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 90/1251] eta: 0:10:39 lr: 0.000407 loss: 3.3096 (3.1079) grad_norm: 1.5370 (1.5825) time: 0.5061 [2021-03-26 10:19:08 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 100/1251] eta: 0:10:29 lr: 0.000407 loss: 3.4273 (3.1261) grad_norm: 1.5370 (1.5832) time: 0.5090 [2021-03-26 10:19:13 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 110/1251] eta: 0:10:19 lr: 0.000407 loss: 3.3708 (3.1392) grad_norm: 1.5845 (1.5856) time: 0.5074 [2021-03-26 10:19:18 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 120/1251] eta: 0:10:11 lr: 0.000407 loss: 3.3081 (3.1417) grad_norm: 1.5650 (1.5874) time: 0.5103 [2021-03-26 10:19:23 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 130/1251] eta: 0:10:03 lr: 0.000407 loss: 3.2347 (3.1433) grad_norm: 1.5637 (1.5869) time: 0.5151 [2021-03-26 10:19:28 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 140/1251] eta: 0:09:54 lr: 0.000407 loss: 3.3624 (3.1590) grad_norm: 1.5215 (1.5819) time: 0.5043 [2021-03-26 10:19:33 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 150/1251] eta: 0:09:47 lr: 0.000407 loss: 3.2711 (3.1552) grad_norm: 1.4394 (1.5747) time: 0.4986 [2021-03-26 10:19:38 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 160/1251] eta: 0:09:39 lr: 0.000407 loss: 3.2204 (3.1565) grad_norm: 1.4743 (1.5729) time: 0.5001 [2021-03-26 10:19:44 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 170/1251] eta: 0:09:32 lr: 0.000406 loss: 3.2211 (3.1609) grad_norm: 1.5917 (1.5825) time: 0.5031 [2021-03-26 10:19:49 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 180/1251] eta: 0:09:26 lr: 0.000406 loss: 3.2382 (3.1611) grad_norm: 1.6119 (1.5817) time: 0.5123 [2021-03-26 10:19:54 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 190/1251] eta: 0:09:19 lr: 0.000406 loss: 3.2446 (3.1675) grad_norm: 1.6017 (1.5843) time: 0.5108 [2021-03-26 10:19:59 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 200/1251] eta: 0:09:14 lr: 0.000406 loss: 3.2677 (3.1578) grad_norm: 1.5978 (1.5839) time: 0.5130 [2021-03-26 10:20:04 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 210/1251] eta: 0:09:07 lr: 0.000406 loss: 3.2677 (3.1644) grad_norm: 1.5740 (1.5839) time: 0.5111 [2021-03-26 10:20:09 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 220/1251] eta: 0:09:00 lr: 0.000406 loss: 3.4382 (3.1784) grad_norm: 1.5448 (1.5808) time: 0.4952 [2021-03-26 10:20:14 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 230/1251] eta: 0:08:54 lr: 0.000406 loss: 3.4286 (3.1869) grad_norm: 1.4915 (1.5790) time: 0.4970 [2021-03-26 10:20:19 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 240/1251] eta: 0:08:48 lr: 0.000406 loss: 3.3323 (3.1838) grad_norm: 1.5929 (1.5847) time: 0.5051 [2021-03-26 10:20:24 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 250/1251] eta: 0:08:42 lr: 0.000406 loss: 3.2521 (3.1857) grad_norm: 1.5631 (1.5818) time: 0.5063 [2021-03-26 10:20:29 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 260/1251] eta: 0:08:36 lr: 0.000406 loss: 3.0448 (3.1783) grad_norm: 1.5367 (1.5817) time: 0.5023 [2021-03-26 10:20:34 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 270/1251] eta: 0:08:30 lr: 0.000406 loss: 3.1763 (3.1818) grad_norm: 1.5636 (1.5818) time: 0.4976 [2021-03-26 10:20:39 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 280/1251] eta: 0:08:24 lr: 0.000406 loss: 3.2395 (3.1851) grad_norm: 1.5949 (1.5833) time: 0.5010 [2021-03-26 10:20:44 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 290/1251] eta: 0:08:19 lr: 0.000406 loss: 3.3243 (3.1872) grad_norm: 1.6057 (1.5826) time: 0.5067 [2021-03-26 10:20:49 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 300/1251] eta: 0:08:13 lr: 0.000406 loss: 3.3243 (3.1901) grad_norm: 1.5471 (1.5804) time: 0.5071 [2021-03-26 10:20:54 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 310/1251] eta: 0:08:07 lr: 0.000406 loss: 3.2719 (3.1864) grad_norm: 1.4931 (1.5789) time: 0.5033 [2021-03-26 10:20:59 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 320/1251] eta: 0:08:02 lr: 0.000406 loss: 3.1461 (3.1880) grad_norm: 1.5359 (1.5815) time: 0.5089 [2021-03-26 10:21:04 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 330/1251] eta: 0:07:56 lr: 0.000406 loss: 3.1322 (3.1887) grad_norm: 1.4619 (1.5788) time: 0.5087 [2021-03-26 10:21:09 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 340/1251] eta: 0:07:51 lr: 0.000406 loss: 3.1322 (3.1922) grad_norm: 1.4577 (1.5779) time: 0.5049 [2021-03-26 10:21:15 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 350/1251] eta: 0:07:46 lr: 0.000406 loss: 3.1781 (3.1893) grad_norm: 1.4994 (1.5762) time: 0.5083 [2021-03-26 10:21:20 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 360/1251] eta: 0:07:40 lr: 0.000406 loss: 3.2402 (3.1963) grad_norm: 1.5234 (1.5763) time: 0.5038 [2021-03-26 10:21:25 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 370/1251] eta: 0:07:34 lr: 0.000406 loss: 3.4384 (3.1998) grad_norm: 1.5063 (1.5749) time: 0.4990 [2021-03-26 10:21:30 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 380/1251] eta: 0:07:29 lr: 0.000406 loss: 3.3498 (3.2013) grad_norm: 1.5393 (1.5761) time: 0.4989 [2021-03-26 10:21:35 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 390/1251] eta: 0:07:23 lr: 0.000406 loss: 3.3498 (3.2081) grad_norm: 1.5463 (1.5748) time: 0.5007 [2021-03-26 10:21:40 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 400/1251] eta: 0:07:18 lr: 0.000406 loss: 3.0606 (3.1989) grad_norm: 1.5311 (1.5797) time: 0.5060 [2021-03-26 10:21:45 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 410/1251] eta: 0:07:13 lr: 0.000405 loss: 2.9782 (3.2007) grad_norm: 1.5068 (1.5776) time: 0.5070 [2021-03-26 10:21:50 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 420/1251] eta: 0:07:07 lr: 0.000405 loss: 3.3151 (3.1985) grad_norm: 1.4761 (1.5768) time: 0.5065 [2021-03-26 10:21:55 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 430/1251] eta: 0:07:02 lr: 0.000405 loss: 3.3366 (3.2031) grad_norm: 1.5762 (1.5770) time: 0.5090 [2021-03-26 10:22:00 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 440/1251] eta: 0:06:57 lr: 0.000405 loss: 3.4291 (3.2063) grad_norm: 1.6232 (1.5784) time: 0.5082 [2021-03-26 10:22:05 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 450/1251] eta: 0:06:52 lr: 0.000405 loss: 3.4425 (3.2068) grad_norm: 1.5400 (1.5783) time: 0.5059 [2021-03-26 10:22:10 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 460/1251] eta: 0:06:46 lr: 0.000405 loss: 3.3229 (3.2053) grad_norm: 1.5482 (1.5785) time: 0.5041 [2021-03-26 10:22:15 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 470/1251] eta: 0:06:41 lr: 0.000405 loss: 3.4667 (3.2098) grad_norm: 1.6104 (1.5802) time: 0.5024 [2021-03-26 10:22:20 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 480/1251] eta: 0:06:36 lr: 0.000405 loss: 3.4725 (3.2130) grad_norm: 1.5575 (1.5797) time: 0.5058 [2021-03-26 10:22:25 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 490/1251] eta: 0:06:31 lr: 0.000405 loss: 3.2737 (3.2124) grad_norm: 1.5215 (1.5783) time: 0.5114 [2021-03-26 10:22:30 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 500/1251] eta: 0:06:25 lr: 0.000405 loss: 3.2865 (3.2140) grad_norm: 1.4806 (1.5771) time: 0.5077 [2021-03-26 10:22:35 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 510/1251] eta: 0:06:20 lr: 0.000405 loss: 3.2865 (3.2175) grad_norm: 1.4768 (1.5757) time: 0.5033 [2021-03-26 10:22:40 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 520/1251] eta: 0:06:15 lr: 0.000405 loss: 3.1501 (3.2182) grad_norm: 1.5152 (1.5760) time: 0.5012 [2021-03-26 10:22:45 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 530/1251] eta: 0:06:09 lr: 0.000405 loss: 3.2225 (3.2201) grad_norm: 1.5665 (1.5757) time: 0.5036 [2021-03-26 10:22:51 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 540/1251] eta: 0:06:04 lr: 0.000405 loss: 3.4913 (3.2245) grad_norm: 1.6015 (1.5784) time: 0.5126 [2021-03-26 10:22:56 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 550/1251] eta: 0:05:59 lr: 0.000405 loss: 3.3612 (3.2226) grad_norm: 1.6507 (1.5789) time: 0.5231 [2021-03-26 10:23:01 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 560/1251] eta: 0:05:54 lr: 0.000405 loss: 3.0300 (3.2217) grad_norm: 1.5826 (1.5777) time: 0.5188 [2021-03-26 10:23:06 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 570/1251] eta: 0:05:49 lr: 0.000405 loss: 3.5831 (3.2305) grad_norm: 1.5980 (1.5797) time: 0.5034 [2021-03-26 10:23:11 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 580/1251] eta: 0:05:44 lr: 0.000405 loss: 3.6188 (3.2337) grad_norm: 1.6167 (1.5795) time: 0.4998 [2021-03-26 10:23:16 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 590/1251] eta: 0:05:39 lr: 0.000405 loss: 3.4300 (3.2357) grad_norm: 1.6171 (1.5808) time: 0.5083 [2021-03-26 10:23:21 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 600/1251] eta: 0:05:33 lr: 0.000405 loss: 3.3714 (3.2349) grad_norm: 1.6397 (1.5806) time: 0.5098 [2021-03-26 10:23:26 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 610/1251] eta: 0:05:28 lr: 0.000405 loss: 3.4011 (3.2393) grad_norm: 1.5175 (1.5801) time: 0.5007 [2021-03-26 10:23:31 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 620/1251] eta: 0:05:23 lr: 0.000405 loss: 3.4089 (3.2382) grad_norm: 1.5956 (1.5806) time: 0.5015 [2021-03-26 10:23:36 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 630/1251] eta: 0:05:18 lr: 0.000405 loss: 2.9171 (3.2328) grad_norm: 1.6070 (1.5818) time: 0.5019 [2021-03-26 10:23:41 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 640/1251] eta: 0:05:12 lr: 0.000405 loss: 3.1766 (3.2345) grad_norm: 1.5829 (1.5811) time: 0.5033 [2021-03-26 10:23:46 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 650/1251] eta: 0:05:07 lr: 0.000405 loss: 3.3628 (3.2356) grad_norm: 1.4757 (1.5797) time: 0.5042 [2021-03-26 10:23:51 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 660/1251] eta: 0:05:02 lr: 0.000404 loss: 3.3812 (3.2324) grad_norm: 1.4757 (1.5796) time: 0.4975 [2021-03-26 10:23:56 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 670/1251] eta: 0:04:57 lr: 0.000404 loss: 3.3812 (3.2336) grad_norm: 1.6619 (1.5833) time: 0.4958 [2021-03-26 10:24:01 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 680/1251] eta: 0:04:52 lr: 0.000404 loss: 3.3626 (3.2341) grad_norm: 1.6706 (1.5836) time: 0.5068 [2021-03-26 10:24:06 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 690/1251] eta: 0:04:46 lr: 0.000404 loss: 3.2863 (3.2362) grad_norm: 1.5819 (1.5833) time: 0.5132 [2021-03-26 10:24:11 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 700/1251] eta: 0:04:41 lr: 0.000404 loss: 3.3997 (3.2387) grad_norm: 1.5593 (1.5833) time: 0.5060 [2021-03-26 10:24:17 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 710/1251] eta: 0:04:36 lr: 0.000404 loss: 3.4055 (3.2392) grad_norm: 1.5869 (1.5852) time: 0.5076 [2021-03-26 10:24:22 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 720/1251] eta: 0:04:31 lr: 0.000404 loss: 3.3864 (3.2395) grad_norm: 1.7280 (1.5868) time: 0.5110 [2021-03-26 10:24:27 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 730/1251] eta: 0:04:26 lr: 0.000404 loss: 3.2091 (3.2390) grad_norm: 1.6078 (1.5870) time: 0.5166 [2021-03-26 10:24:32 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 740/1251] eta: 0:04:21 lr: 0.000404 loss: 3.3088 (3.2404) grad_norm: 1.5806 (1.5880) time: 0.5231 [2021-03-26 10:24:37 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 750/1251] eta: 0:04:16 lr: 0.000404 loss: 3.3341 (3.2404) grad_norm: 1.5256 (1.5871) time: 0.5205 [2021-03-26 10:24:43 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 760/1251] eta: 0:04:11 lr: 0.000404 loss: 3.3347 (3.2395) grad_norm: 1.4654 (1.5867) time: 0.5199 [2021-03-26 10:24:48 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 770/1251] eta: 0:04:06 lr: 0.000404 loss: 3.2873 (3.2402) grad_norm: 1.4980 (1.5857) time: 0.5126 [2021-03-26 10:24:53 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 780/1251] eta: 0:04:01 lr: 0.000404 loss: 3.2711 (3.2409) grad_norm: 1.4818 (1.5850) time: 0.5068 [2021-03-26 10:24:58 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 790/1251] eta: 0:03:55 lr: 0.000404 loss: 3.1410 (3.2394) grad_norm: 1.5192 (1.5845) time: 0.5133 [2021-03-26 10:25:03 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 800/1251] eta: 0:03:50 lr: 0.000404 loss: 3.1508 (3.2404) grad_norm: 1.5192 (1.5841) time: 0.5133 [2021-03-26 10:25:08 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 810/1251] eta: 0:03:45 lr: 0.000404 loss: 3.1695 (3.2376) grad_norm: 1.4985 (1.5836) time: 0.5098 [2021-03-26 10:25:13 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 820/1251] eta: 0:03:40 lr: 0.000404 loss: 3.1849 (3.2377) grad_norm: 1.5251 (1.5836) time: 0.5040 [2021-03-26 10:25:18 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 830/1251] eta: 0:03:35 lr: 0.000404 loss: 3.2281 (3.2362) grad_norm: 1.5565 (1.5836) time: 0.5006 [2021-03-26 10:25:23 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 840/1251] eta: 0:03:30 lr: 0.000404 loss: 3.2336 (3.2362) grad_norm: 1.6100 (1.5840) time: 0.5073 [2021-03-26 10:25:28 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 850/1251] eta: 0:03:25 lr: 0.000404 loss: 3.3427 (3.2363) grad_norm: 1.6156 (1.5841) time: 0.5067 [2021-03-26 10:25:33 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 860/1251] eta: 0:03:19 lr: 0.000404 loss: 3.3758 (3.2370) grad_norm: 1.5919 (1.5849) time: 0.4994 [2021-03-26 10:25:38 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 870/1251] eta: 0:03:14 lr: 0.000404 loss: 3.2181 (3.2371) grad_norm: 1.5911 (1.5849) time: 0.5068 [2021-03-26 10:25:44 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 880/1251] eta: 0:03:09 lr: 0.000404 loss: 3.1381 (3.2357) grad_norm: 1.5048 (1.5846) time: 0.5172 [2021-03-26 10:25:49 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 890/1251] eta: 0:03:04 lr: 0.000404 loss: 3.1130 (3.2353) grad_norm: 1.4891 (1.5837) time: 0.5113 [2021-03-26 10:25:54 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 900/1251] eta: 0:02:59 lr: 0.000404 loss: 3.0990 (3.2346) grad_norm: 1.5193 (1.5837) time: 0.4997 [2021-03-26 10:25:59 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 910/1251] eta: 0:02:54 lr: 0.000403 loss: 3.1709 (3.2335) grad_norm: 1.5763 (1.5841) time: 0.4979 [2021-03-26 10:26:04 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 920/1251] eta: 0:02:49 lr: 0.000403 loss: 3.2659 (3.2348) grad_norm: 1.5969 (1.5849) time: 0.5014 [2021-03-26 10:26:09 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 930/1251] eta: 0:02:44 lr: 0.000403 loss: 3.4090 (3.2355) grad_norm: 1.5556 (1.5850) time: 0.5077 [2021-03-26 10:26:14 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 940/1251] eta: 0:02:38 lr: 0.000403 loss: 3.1733 (3.2341) grad_norm: 1.5267 (1.5844) time: 0.5125 [2021-03-26 10:26:19 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 950/1251] eta: 0:02:33 lr: 0.000403 loss: 3.2212 (3.2347) grad_norm: 1.5124 (1.5838) time: 0.5119 [2021-03-26 10:26:24 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 960/1251] eta: 0:02:28 lr: 0.000403 loss: 3.4884 (3.2366) grad_norm: 1.5786 (1.5840) time: 0.5115 [2021-03-26 10:26:29 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 970/1251] eta: 0:02:23 lr: 0.000403 loss: 3.5063 (3.2375) grad_norm: 1.5870 (1.5840) time: 0.5088 [2021-03-26 10:26:34 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 980/1251] eta: 0:02:18 lr: 0.000403 loss: 3.4827 (3.2395) grad_norm: 1.5705 (1.5837) time: 0.5032 [2021-03-26 10:26:39 swin_small_patch4_window7_224] INFO: Epoch: [169] [ 990/1251] eta: 0:02:13 lr: 0.000403 loss: 3.4024 (3.2415) grad_norm: 1.5012 (1.5834) time: 0.5001 [2021-03-26 10:26:44 swin_small_patch4_window7_224] INFO: Epoch: [169] [1000/1251] eta: 0:02:08 lr: 0.000403 loss: 3.3215 (3.2427) grad_norm: 1.6045 (1.5847) time: 0.5049 [2021-03-26 10:26:49 swin_small_patch4_window7_224] INFO: Epoch: [169] [1010/1251] eta: 0:02:03 lr: 0.000403 loss: 3.2494 (3.2406) grad_norm: 1.6045 (1.5848) time: 0.5034 [2021-03-26 10:26:54 swin_small_patch4_window7_224] INFO: Epoch: [169] [1020/1251] eta: 0:01:57 lr: 0.000403 loss: 3.4326 (3.2429) grad_norm: 1.5550 (1.5845) time: 0.4993 [2021-03-26 10:26:59 swin_small_patch4_window7_224] INFO: Epoch: [169] [1030/1251] eta: 0:01:52 lr: 0.000403 loss: 3.3867 (3.2426) grad_norm: 1.5513 (1.5842) time: 0.5032 [2021-03-26 10:27:04 swin_small_patch4_window7_224] INFO: Epoch: [169] [1040/1251] eta: 0:01:47 lr: 0.000403 loss: 3.2216 (3.2430) grad_norm: 1.5342 (1.5843) time: 0.5015 [2021-03-26 10:27:09 swin_small_patch4_window7_224] INFO: Epoch: [169] [1050/1251] eta: 0:01:42 lr: 0.000403 loss: 3.3684 (3.2441) grad_norm: 1.6320 (1.5855) time: 0.4997 [2021-03-26 10:27:14 swin_small_patch4_window7_224] INFO: Epoch: [169] [1060/1251] eta: 0:01:37 lr: 0.000403 loss: 3.2552 (3.2403) grad_norm: 1.6517 (1.5855) time: 0.5042 [2021-03-26 10:27:19 swin_small_patch4_window7_224] INFO: Epoch: [169] [1070/1251] eta: 0:01:32 lr: 0.000403 loss: 3.3559 (3.2425) grad_norm: 1.5705 (1.5856) time: 0.5050 [2021-03-26 10:27:24 swin_small_patch4_window7_224] INFO: Epoch: [169] [1080/1251] eta: 0:01:27 lr: 0.000403 loss: 3.3907 (3.2428) grad_norm: 1.5133 (1.5850) time: 0.5036 [2021-03-26 10:27:29 swin_small_patch4_window7_224] INFO: Epoch: [169] [1090/1251] eta: 0:01:22 lr: 0.000403 loss: 3.3201 (3.2429) grad_norm: 1.5077 (1.5850) time: 0.4996 [2021-03-26 10:27:34 swin_small_patch4_window7_224] INFO: Epoch: [169] [1100/1251] eta: 0:01:16 lr: 0.000403 loss: 3.3165 (3.2415) grad_norm: 1.5401 (1.5854) time: 0.5010 [2021-03-26 10:27:40 swin_small_patch4_window7_224] INFO: Epoch: [169] [1110/1251] eta: 0:01:11 lr: 0.000403 loss: 3.2250 (3.2407) grad_norm: 1.5956 (1.5856) time: 0.5072 [2021-03-26 10:27:45 swin_small_patch4_window7_224] INFO: Epoch: [169] [1120/1251] eta: 0:01:06 lr: 0.000403 loss: 3.2830 (3.2416) grad_norm: 1.5535 (1.5847) time: 0.5044 [2021-03-26 10:27:50 swin_small_patch4_window7_224] INFO: Epoch: [169] [1130/1251] eta: 0:01:01 lr: 0.000403 loss: 3.3222 (3.2422) grad_norm: 1.5036 (1.5845) time: 0.5022 [2021-03-26 10:27:55 swin_small_patch4_window7_224] INFO: Epoch: [169] [1140/1251] eta: 0:00:56 lr: 0.000403 loss: 3.3365 (3.2437) grad_norm: 1.5022 (1.5839) time: 0.4993 [2021-03-26 10:28:00 swin_small_patch4_window7_224] INFO: Epoch: [169] [1150/1251] eta: 0:00:51 lr: 0.000402 loss: 3.3670 (3.2440) grad_norm: 1.5023 (1.5837) time: 0.5022 [2021-03-26 10:28:05 swin_small_patch4_window7_224] INFO: Epoch: [169] [1160/1251] eta: 0:00:46 lr: 0.000402 loss: 3.3670 (3.2449) grad_norm: 1.5023 (1.5832) time: 0.5009 [2021-03-26 10:28:10 swin_small_patch4_window7_224] INFO: Epoch: [169] [1170/1251] eta: 0:00:41 lr: 0.000402 loss: 3.1271 (3.2424) grad_norm: 1.4612 (1.5828) time: 0.4942 [2021-03-26 10:28:14 swin_small_patch4_window7_224] INFO: Epoch: [169] [1180/1251] eta: 0:00:36 lr: 0.000402 loss: 3.0982 (3.2431) grad_norm: 1.5044 (1.5824) time: 0.4966 [2021-03-26 10:28:19 swin_small_patch4_window7_224] INFO: Epoch: [169] [1190/1251] eta: 0:00:31 lr: 0.000402 loss: 3.2620 (3.2433) grad_norm: 1.5044 (1.5821) time: 0.4957 [2021-03-26 10:28:24 swin_small_patch4_window7_224] INFO: Epoch: [169] [1200/1251] eta: 0:00:25 lr: 0.000402 loss: 3.2075 (3.2410) grad_norm: 1.4881 (1.5815) time: 0.5002 [2021-03-26 10:28:30 swin_small_patch4_window7_224] INFO: Epoch: [169] [1210/1251] eta: 0:00:20 lr: 0.000402 loss: 2.6269 (3.2370) grad_norm: 1.5064 (1.5813) time: 0.5063 [2021-03-26 10:28:35 swin_small_patch4_window7_224] INFO: Epoch: [169] [1220/1251] eta: 0:00:15 lr: 0.000402 loss: 3.2364 (3.2380) grad_norm: 1.5572 (1.5813) time: 0.5017 [2021-03-26 10:28:40 swin_small_patch4_window7_224] INFO: Epoch: [169] [1230/1251] eta: 0:00:10 lr: 0.000402 loss: 3.5350 (3.2419) grad_norm: 1.5954 (1.5815) time: 0.5013 [2021-03-26 10:28:45 swin_small_patch4_window7_224] INFO: Epoch: [169] [1240/1251] eta: 0:00:05 lr: 0.000402 loss: 3.3983 (3.2410) grad_norm: 1.5235 (1.5811) time: 0.5069 [2021-03-26 10:28:50 swin_small_patch4_window7_224] INFO: Epoch: [169] [1250/1251] eta: 0:00:00 lr: 0.000402 loss: 3.3983 (3.2431) grad_norm: 1.5234 (1.5813) time: 0.5050 [2021-03-26 10:28:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:40 loss: 0.9601 (0.9601) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.1875) [2021-03-26 10:29:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9341 (0.8964) acc1: 78.1250 (78.1250) acc5: 95.3125 (94.8864) [2021-03-26 10:29:03 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8728 (0.8994) acc1: 79.6875 (78.7946) acc5: 95.3125 (94.7917) [2021-03-26 10:29:06 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8452 (0.8884) acc1: 79.6875 (78.6794) acc5: 95.3125 (94.8589) [2021-03-26 10:29:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8452 (0.8858) acc1: 78.1250 (78.1631) acc5: 95.3125 (94.9314) [2021-03-26 10:29:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8542 (0.8949) acc1: 78.1250 (78.2080) acc5: 95.3125 (94.9120) [2021-03-26 10:29:18 swin_small_patch4_window7_224] INFO: * Acc@1 79.074 Acc@5 94.838 loss 0.876 [2021-03-26 10:29:18 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-26 10:29:18 swin_small_patch4_window7_224] INFO: Max accuracy: 79.22% [2021-03-26 10:29:22 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 0/1251] eta: 1:27:59 lr: 0.000402 loss: 2.9734 (2.9734) grad_norm: 1.4874 (1.4874) time: 4.2205 [2021-03-26 10:29:27 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 10/1251] eta: 0:17:34 lr: 0.000402 loss: 2.9734 (2.9783) grad_norm: 1.5790 (1.5625) time: 0.8498 [2021-03-26 10:29:32 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 20/1251] eta: 0:14:09 lr: 0.000402 loss: 3.0922 (3.0411) grad_norm: 1.5443 (1.5335) time: 0.5133 [2021-03-26 10:29:37 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 30/1251] eta: 0:12:50 lr: 0.000402 loss: 3.1819 (3.1066) grad_norm: 1.4986 (1.5325) time: 0.5106 [2021-03-26 10:29:42 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 40/1251] eta: 0:12:08 lr: 0.000402 loss: 3.3933 (3.1751) grad_norm: 1.5530 (1.5491) time: 0.5094 [2021-03-26 10:29:48 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 50/1251] eta: 0:11:42 lr: 0.000402 loss: 3.3440 (3.1790) grad_norm: 1.6235 (1.5827) time: 0.5143 [2021-03-26 10:29:53 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 60/1251] eta: 0:11:22 lr: 0.000402 loss: 3.2630 (3.1734) grad_norm: 1.5724 (1.5749) time: 0.5135 [2021-03-26 10:29:58 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 70/1251] eta: 0:11:04 lr: 0.000402 loss: 3.3371 (3.2059) grad_norm: 1.5724 (1.5848) time: 0.5051 [2021-03-26 10:30:03 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 80/1251] eta: 0:10:50 lr: 0.000402 loss: 3.4451 (3.2185) grad_norm: 1.6507 (1.5989) time: 0.5015 [2021-03-26 10:30:08 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 90/1251] eta: 0:10:39 lr: 0.000402 loss: 3.1572 (3.2126) grad_norm: 1.6271 (1.5985) time: 0.5090 [2021-03-26 10:30:13 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 100/1251] eta: 0:10:29 lr: 0.000402 loss: 3.1436 (3.2124) grad_norm: 1.5503 (1.5977) time: 0.5121 [2021-03-26 10:30:18 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 110/1251] eta: 0:10:19 lr: 0.000402 loss: 3.3634 (3.2289) grad_norm: 1.5269 (1.5981) time: 0.5056 [2021-03-26 10:30:23 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 120/1251] eta: 0:10:10 lr: 0.000402 loss: 3.3904 (3.2371) grad_norm: 1.5271 (1.5969) time: 0.5047 [2021-03-26 10:30:28 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 130/1251] eta: 0:10:03 lr: 0.000402 loss: 3.2560 (3.2262) grad_norm: 1.5403 (1.5988) time: 0.5119 [2021-03-26 10:30:33 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 140/1251] eta: 0:09:53 lr: 0.000402 loss: 3.1314 (3.2213) grad_norm: 1.5660 (nan) time: 0.5014 [2021-03-26 10:30:38 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 150/1251] eta: 0:09:45 lr: 0.000401 loss: 3.2070 (3.2315) grad_norm: 1.5838 (nan) time: 0.4917 [2021-03-26 10:30:43 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 160/1251] eta: 0:09:38 lr: 0.000401 loss: 3.2018 (3.2285) grad_norm: 1.6250 (nan) time: 0.5016 [2021-03-26 10:30:48 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 170/1251] eta: 0:09:31 lr: 0.000401 loss: 3.1253 (3.2265) grad_norm: 1.6087 (nan) time: 0.5022 [2021-03-26 10:30:53 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 180/1251] eta: 0:09:25 lr: 0.000401 loss: 3.3407 (3.2354) grad_norm: 1.5125 (nan) time: 0.5073 [2021-03-26 10:30:58 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 190/1251] eta: 0:09:18 lr: 0.000401 loss: 3.3295 (3.2409) grad_norm: 1.6164 (nan) time: 0.5092 [2021-03-26 10:31:03 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 200/1251] eta: 0:09:12 lr: 0.000401 loss: 3.2125 (3.2244) grad_norm: 1.5634 (nan) time: 0.5043 [2021-03-26 10:31:08 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 210/1251] eta: 0:09:05 lr: 0.000401 loss: 2.8498 (3.2223) grad_norm: 1.5634 (nan) time: 0.5063 [2021-03-26 10:31:14 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 220/1251] eta: 0:09:00 lr: 0.000401 loss: 3.0685 (3.2164) grad_norm: 1.6429 (nan) time: 0.5096 [2021-03-26 10:31:19 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 230/1251] eta: 0:08:54 lr: 0.000401 loss: 3.2392 (3.2246) grad_norm: 1.5629 (nan) time: 0.5082 [2021-03-26 10:31:24 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 240/1251] eta: 0:08:47 lr: 0.000401 loss: 3.2714 (3.2165) grad_norm: 1.5282 (nan) time: 0.5016 [2021-03-26 10:31:29 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 250/1251] eta: 0:08:42 lr: 0.000401 loss: 3.2005 (3.2165) grad_norm: 1.6098 (nan) time: 0.5044 [2021-03-26 10:31:34 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 260/1251] eta: 0:08:36 lr: 0.000401 loss: 3.3110 (3.2180) grad_norm: 1.6435 (nan) time: 0.5084 [2021-03-26 10:31:39 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 270/1251] eta: 0:08:30 lr: 0.000401 loss: 3.3354 (3.2116) grad_norm: 1.5721 (nan) time: 0.5073 [2021-03-26 10:31:44 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 280/1251] eta: 0:08:24 lr: 0.000401 loss: 3.3398 (3.2129) grad_norm: 1.5544 (nan) time: 0.5009 [2021-03-26 10:31:49 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 290/1251] eta: 0:08:18 lr: 0.000401 loss: 3.3398 (3.2129) grad_norm: 1.5911 (nan) time: 0.4978 [2021-03-26 10:31:54 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 300/1251] eta: 0:08:12 lr: 0.000401 loss: 3.3943 (3.2197) grad_norm: 1.6226 (nan) time: 0.5006 [2021-03-26 10:31:59 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 310/1251] eta: 0:08:07 lr: 0.000401 loss: 3.3488 (3.2143) grad_norm: 1.5939 (nan) time: 0.5024 [2021-03-26 10:32:04 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 320/1251] eta: 0:08:01 lr: 0.000401 loss: 3.1799 (3.2122) grad_norm: 1.5357 (nan) time: 0.5072 [2021-03-26 10:32:09 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 330/1251] eta: 0:07:56 lr: 0.000401 loss: 3.2311 (3.2114) grad_norm: 1.5832 (nan) time: 0.5068 [2021-03-26 10:32:14 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 340/1251] eta: 0:07:50 lr: 0.000401 loss: 3.1670 (3.2090) grad_norm: 1.6032 (nan) time: 0.5030 [2021-03-26 10:32:19 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 350/1251] eta: 0:07:45 lr: 0.000401 loss: 3.2666 (3.2145) grad_norm: 1.6032 (nan) time: 0.5029 [2021-03-26 10:32:24 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 360/1251] eta: 0:07:39 lr: 0.000401 loss: 3.4162 (3.2153) grad_norm: 1.5992 (nan) time: 0.5053 [2021-03-26 10:32:29 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 370/1251] eta: 0:07:34 lr: 0.000401 loss: 3.2926 (3.2091) grad_norm: 1.5286 (nan) time: 0.5028 [2021-03-26 10:32:34 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 380/1251] eta: 0:07:28 lr: 0.000401 loss: 3.1539 (3.2125) grad_norm: 1.5500 (nan) time: 0.5032 [2021-03-26 10:32:39 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 390/1251] eta: 0:07:23 lr: 0.000401 loss: 3.1885 (3.2127) grad_norm: 1.6198 (nan) time: 0.5118 [2021-03-26 10:32:44 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 400/1251] eta: 0:07:18 lr: 0.000400 loss: 3.1885 (3.2130) grad_norm: 1.6117 (nan) time: 0.5088 [2021-03-26 10:32:49 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 410/1251] eta: 0:07:13 lr: 0.000400 loss: 3.2676 (3.2162) grad_norm: 1.6043 (nan) time: 0.5059 [2021-03-26 10:32:55 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 420/1251] eta: 0:07:07 lr: 0.000400 loss: 3.2676 (3.2172) grad_norm: 1.5578 (nan) time: 0.5096 [2021-03-26 10:33:00 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 430/1251] eta: 0:07:02 lr: 0.000400 loss: 3.3458 (3.2183) grad_norm: 1.5842 (nan) time: 0.5072 [2021-03-26 10:33:05 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 440/1251] eta: 0:06:57 lr: 0.000400 loss: 3.2327 (3.2164) grad_norm: 1.6505 (nan) time: 0.5026 [2021-03-26 10:33:10 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 450/1251] eta: 0:06:51 lr: 0.000400 loss: 3.1021 (3.2100) grad_norm: 1.5589 (nan) time: 0.5029 [2021-03-26 10:33:15 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 460/1251] eta: 0:06:46 lr: 0.000400 loss: 3.1163 (3.2117) grad_norm: 1.5589 (nan) time: 0.5079 [2021-03-26 10:33:20 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 470/1251] eta: 0:06:41 lr: 0.000400 loss: 3.4561 (3.2131) grad_norm: 1.5958 (nan) time: 0.5106 [2021-03-26 10:33:25 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 480/1251] eta: 0:06:36 lr: 0.000400 loss: 3.4561 (3.2131) grad_norm: 1.5952 (nan) time: 0.5076 [2021-03-26 10:33:30 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 490/1251] eta: 0:06:30 lr: 0.000400 loss: 2.9798 (3.2082) grad_norm: 1.5952 (nan) time: 0.5058 [2021-03-26 10:33:35 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 500/1251] eta: 0:06:25 lr: 0.000400 loss: 3.3036 (3.2126) grad_norm: 1.5911 (nan) time: 0.5058 [2021-03-26 10:33:40 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 510/1251] eta: 0:06:20 lr: 0.000400 loss: 3.3107 (3.2086) grad_norm: 1.5503 (nan) time: 0.5019 [2021-03-26 10:33:45 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 520/1251] eta: 0:06:14 lr: 0.000400 loss: 3.1997 (3.2075) grad_norm: 1.6345 (nan) time: 0.4986 [2021-03-26 10:33:50 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 530/1251] eta: 0:06:09 lr: 0.000400 loss: 3.2678 (3.2094) grad_norm: 1.5967 (nan) time: 0.5017 [2021-03-26 10:33:55 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 540/1251] eta: 0:06:04 lr: 0.000400 loss: 3.1946 (3.2088) grad_norm: 1.4947 (nan) time: 0.5055 [2021-03-26 10:34:00 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 550/1251] eta: 0:05:59 lr: 0.000400 loss: 3.3593 (3.2112) grad_norm: 1.6189 (nan) time: 0.5141 [2021-03-26 10:34:05 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 560/1251] eta: 0:05:54 lr: 0.000400 loss: 3.3593 (3.2101) grad_norm: 1.6257 (nan) time: 0.5160 [2021-03-26 10:34:10 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 570/1251] eta: 0:05:49 lr: 0.000400 loss: 3.1640 (3.2098) grad_norm: 1.6005 (nan) time: 0.5040 [2021-03-26 10:34:16 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 580/1251] eta: 0:05:43 lr: 0.000400 loss: 3.4935 (3.2131) grad_norm: 1.5620 (nan) time: 0.5066 [2021-03-26 10:34:21 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 590/1251] eta: 0:05:38 lr: 0.000400 loss: 3.4118 (3.2120) grad_norm: 1.6077 (nan) time: 0.5091 [2021-03-26 10:34:26 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 600/1251] eta: 0:05:33 lr: 0.000400 loss: 3.1840 (3.2109) grad_norm: 1.6317 (nan) time: 0.5055 [2021-03-26 10:34:31 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 610/1251] eta: 0:05:28 lr: 0.000400 loss: 3.1840 (3.2106) grad_norm: 1.5425 (nan) time: 0.5024 [2021-03-26 10:34:36 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 620/1251] eta: 0:05:22 lr: 0.000400 loss: 3.1659 (3.2092) grad_norm: 1.5586 (nan) time: 0.4985 [2021-03-26 10:34:41 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 630/1251] eta: 0:05:17 lr: 0.000400 loss: 3.0789 (3.2058) grad_norm: 1.5665 (nan) time: 0.5049 [2021-03-26 10:34:46 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 640/1251] eta: 0:05:12 lr: 0.000399 loss: 3.1452 (3.2059) grad_norm: 1.5680 (nan) time: 0.5112 [2021-03-26 10:34:51 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 650/1251] eta: 0:05:07 lr: 0.000399 loss: 3.1801 (3.2041) grad_norm: 1.6470 (nan) time: 0.5051 [2021-03-26 10:34:56 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 660/1251] eta: 0:05:02 lr: 0.000399 loss: 3.2358 (3.2077) grad_norm: 1.5040 (nan) time: 0.4994 [2021-03-26 10:35:01 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 670/1251] eta: 0:04:57 lr: 0.000399 loss: 3.1613 (3.2064) grad_norm: 1.6134 (nan) time: 0.5032 [2021-03-26 10:35:06 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 680/1251] eta: 0:04:51 lr: 0.000399 loss: 3.2401 (3.2085) grad_norm: 1.6046 (nan) time: 0.5042 [2021-03-26 10:35:11 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 690/1251] eta: 0:04:46 lr: 0.000399 loss: 3.3599 (3.2111) grad_norm: 1.5406 (nan) time: 0.5029 [2021-03-26 10:35:16 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 700/1251] eta: 0:04:41 lr: 0.000399 loss: 3.3280 (3.2120) grad_norm: 1.5321 (nan) time: 0.5033 [2021-03-26 10:35:21 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 710/1251] eta: 0:04:36 lr: 0.000399 loss: 3.3116 (3.2108) grad_norm: 1.5100 (nan) time: 0.5060 [2021-03-26 10:35:26 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 720/1251] eta: 0:04:31 lr: 0.000399 loss: 3.3054 (3.2102) grad_norm: 1.5879 (nan) time: 0.5025 [2021-03-26 10:35:31 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 730/1251] eta: 0:04:26 lr: 0.000399 loss: 3.4708 (3.2138) grad_norm: 1.5783 (nan) time: 0.5060 [2021-03-26 10:35:37 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 740/1251] eta: 0:04:21 lr: 0.000399 loss: 3.5972 (3.2169) grad_norm: 1.5367 (nan) time: 0.5291 [2021-03-26 10:35:42 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 750/1251] eta: 0:04:16 lr: 0.000399 loss: 3.4378 (3.2172) grad_norm: 1.5117 (nan) time: 0.5231 [2021-03-26 10:35:47 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 760/1251] eta: 0:04:10 lr: 0.000399 loss: 3.3875 (3.2207) grad_norm: 1.5726 (nan) time: 0.5019 [2021-03-26 10:35:52 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 770/1251] eta: 0:04:05 lr: 0.000399 loss: 3.3977 (3.2180) grad_norm: 1.6509 (nan) time: 0.5016 [2021-03-26 10:35:57 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 780/1251] eta: 0:04:00 lr: 0.000399 loss: 3.2762 (3.2174) grad_norm: 1.5859 (nan) time: 0.5012 [2021-03-26 10:36:02 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 790/1251] eta: 0:03:55 lr: 0.000399 loss: 3.2762 (3.2155) grad_norm: 1.5724 (nan) time: 0.5086 [2021-03-26 10:36:07 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 800/1251] eta: 0:03:50 lr: 0.000399 loss: 3.2160 (3.2169) grad_norm: 1.6199 (nan) time: 0.5127 [2021-03-26 10:36:12 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 810/1251] eta: 0:03:45 lr: 0.000399 loss: 3.4693 (3.2195) grad_norm: 1.5950 (nan) time: 0.5049 [2021-03-26 10:36:17 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 820/1251] eta: 0:03:40 lr: 0.000399 loss: 3.4693 (3.2224) grad_norm: 1.5950 (nan) time: 0.5065 [2021-03-26 10:36:22 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 830/1251] eta: 0:03:34 lr: 0.000399 loss: 3.4671 (3.2237) grad_norm: 1.6323 (nan) time: 0.5091 [2021-03-26 10:36:27 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 840/1251] eta: 0:03:29 lr: 0.000399 loss: 3.3813 (3.2263) grad_norm: 1.6560 (nan) time: 0.5043 [2021-03-26 10:36:32 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 850/1251] eta: 0:03:24 lr: 0.000399 loss: 3.2641 (3.2263) grad_norm: 1.6732 (nan) time: 0.5006 [2021-03-26 10:36:37 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 860/1251] eta: 0:03:19 lr: 0.000399 loss: 3.2641 (3.2263) grad_norm: 1.5650 (nan) time: 0.5010 [2021-03-26 10:36:42 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 870/1251] eta: 0:03:14 lr: 0.000399 loss: 3.3546 (3.2281) grad_norm: 1.5262 (nan) time: 0.5044 [2021-03-26 10:36:47 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 880/1251] eta: 0:03:09 lr: 0.000399 loss: 3.1074 (3.2258) grad_norm: 1.5699 (nan) time: 0.5057 [2021-03-26 10:36:52 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 890/1251] eta: 0:03:04 lr: 0.000398 loss: 3.1061 (3.2257) grad_norm: 1.5944 (nan) time: 0.5056 [2021-03-26 10:36:57 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 900/1251] eta: 0:02:59 lr: 0.000398 loss: 3.4382 (3.2275) grad_norm: 1.5944 (nan) time: 0.5048 [2021-03-26 10:37:02 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 910/1251] eta: 0:02:53 lr: 0.000398 loss: 3.4323 (3.2280) grad_norm: 1.5769 (nan) time: 0.5028 [2021-03-26 10:37:07 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 920/1251] eta: 0:02:48 lr: 0.000398 loss: 3.2582 (3.2270) grad_norm: 1.5890 (nan) time: 0.5024 [2021-03-26 10:37:13 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 930/1251] eta: 0:02:43 lr: 0.000398 loss: 3.2054 (3.2256) grad_norm: 1.5973 (nan) time: 0.5046 [2021-03-26 10:37:18 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 940/1251] eta: 0:02:38 lr: 0.000398 loss: 3.3284 (3.2252) grad_norm: 1.6682 (nan) time: 0.5020 [2021-03-26 10:37:23 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 950/1251] eta: 0:02:33 lr: 0.000398 loss: 3.3482 (3.2263) grad_norm: 1.6829 (nan) time: 0.4995 [2021-03-26 10:37:28 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 960/1251] eta: 0:02:28 lr: 0.000398 loss: 3.4507 (3.2278) grad_norm: 1.6621 (nan) time: 0.5080 [2021-03-26 10:37:33 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 970/1251] eta: 0:02:23 lr: 0.000398 loss: 3.4507 (3.2279) grad_norm: 1.7346 (nan) time: 0.5104 [2021-03-26 10:37:38 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 980/1251] eta: 0:02:18 lr: 0.000398 loss: 3.3267 (3.2278) grad_norm: 1.5602 (nan) time: 0.5030 [2021-03-26 10:37:43 swin_small_patch4_window7_224] INFO: Epoch: [170] [ 990/1251] eta: 0:02:13 lr: 0.000398 loss: 3.1129 (3.2243) grad_norm: 1.5208 (nan) time: 0.5103 [2021-03-26 10:37:48 swin_small_patch4_window7_224] INFO: Epoch: [170] [1000/1251] eta: 0:02:07 lr: 0.000398 loss: 2.9357 (3.2229) grad_norm: 1.5480 (nan) time: 0.5150 [2021-03-26 10:37:53 swin_small_patch4_window7_224] INFO: Epoch: [170] [1010/1251] eta: 0:02:02 lr: 0.000398 loss: 3.2047 (3.2242) grad_norm: 1.5816 (nan) time: 0.5077 [2021-03-26 10:37:58 swin_small_patch4_window7_224] INFO: Epoch: [170] [1020/1251] eta: 0:01:57 lr: 0.000398 loss: 3.4813 (3.2239) grad_norm: 1.5816 (nan) time: 0.5052 [2021-03-26 10:38:03 swin_small_patch4_window7_224] INFO: Epoch: [170] [1030/1251] eta: 0:01:52 lr: 0.000398 loss: 3.2976 (3.2207) grad_norm: 1.5626 (nan) time: 0.5051 [2021-03-26 10:38:08 swin_small_patch4_window7_224] INFO: Epoch: [170] [1040/1251] eta: 0:01:47 lr: 0.000398 loss: 3.2298 (3.2214) grad_norm: 1.5960 (nan) time: 0.5045 [2021-03-26 10:38:13 swin_small_patch4_window7_224] INFO: Epoch: [170] [1050/1251] eta: 0:01:42 lr: 0.000398 loss: 3.0393 (3.2199) grad_norm: 1.5578 (nan) time: 0.5044 [2021-03-26 10:38:18 swin_small_patch4_window7_224] INFO: Epoch: [170] [1060/1251] eta: 0:01:37 lr: 0.000398 loss: 2.9091 (3.2191) grad_norm: 1.5964 (nan) time: 0.5062 [2021-03-26 10:38:23 swin_small_patch4_window7_224] INFO: Epoch: [170] [1070/1251] eta: 0:01:32 lr: 0.000398 loss: 2.9944 (3.2183) grad_norm: 1.6563 (nan) time: 0.5071 [2021-03-26 10:38:29 swin_small_patch4_window7_224] INFO: Epoch: [170] [1080/1251] eta: 0:01:27 lr: 0.000398 loss: 2.9944 (3.2170) grad_norm: 1.5863 (nan) time: 0.5077 [2021-03-26 10:38:34 swin_small_patch4_window7_224] INFO: Epoch: [170] [1090/1251] eta: 0:01:22 lr: 0.000398 loss: 3.2895 (3.2173) grad_norm: 1.5622 (nan) time: 0.5031 [2021-03-26 10:38:39 swin_small_patch4_window7_224] INFO: Epoch: [170] [1100/1251] eta: 0:01:16 lr: 0.000398 loss: 3.4128 (3.2176) grad_norm: 1.6095 (nan) time: 0.5038 [2021-03-26 10:38:44 swin_small_patch4_window7_224] INFO: Epoch: [170] [1110/1251] eta: 0:01:11 lr: 0.000398 loss: 3.2883 (3.2177) grad_norm: 1.6247 (nan) time: 0.5052 [2021-03-26 10:38:49 swin_small_patch4_window7_224] INFO: Epoch: [170] [1120/1251] eta: 0:01:06 lr: 0.000398 loss: 3.2807 (3.2183) grad_norm: 1.5771 (nan) time: 0.5006 [2021-03-26 10:38:54 swin_small_patch4_window7_224] INFO: Epoch: [170] [1130/1251] eta: 0:01:01 lr: 0.000398 loss: 3.1932 (3.2162) grad_norm: 1.5197 (nan) time: 0.4977 [2021-03-26 10:38:59 swin_small_patch4_window7_224] INFO: Epoch: [170] [1140/1251] eta: 0:00:56 lr: 0.000397 loss: 3.0623 (3.2140) grad_norm: 1.6304 (nan) time: 0.4956 [2021-03-26 10:39:04 swin_small_patch4_window7_224] INFO: Epoch: [170] [1150/1251] eta: 0:00:51 lr: 0.000397 loss: 3.0753 (3.2149) grad_norm: 1.6075 (nan) time: 0.5039 [2021-03-26 10:39:09 swin_small_patch4_window7_224] INFO: Epoch: [170] [1160/1251] eta: 0:00:46 lr: 0.000397 loss: 3.4863 (3.2170) grad_norm: 1.5509 (nan) time: 0.5035 [2021-03-26 10:39:14 swin_small_patch4_window7_224] INFO: Epoch: [170] [1170/1251] eta: 0:00:41 lr: 0.000397 loss: 3.4313 (3.2178) grad_norm: 1.5509 (nan) time: 0.4982 [2021-03-26 10:39:19 swin_small_patch4_window7_224] INFO: Epoch: [170] [1180/1251] eta: 0:00:36 lr: 0.000397 loss: 3.3017 (3.2187) grad_norm: 1.5452 (nan) time: 0.5055 [2021-03-26 10:39:24 swin_small_patch4_window7_224] INFO: Epoch: [170] [1190/1251] eta: 0:00:31 lr: 0.000397 loss: 3.2694 (3.2193) grad_norm: 1.6044 (nan) time: 0.5052 [2021-03-26 10:39:29 swin_small_patch4_window7_224] INFO: Epoch: [170] [1200/1251] eta: 0:00:25 lr: 0.000397 loss: 3.3614 (3.2205) grad_norm: 1.6059 (nan) time: 0.4999 [2021-03-26 10:39:34 swin_small_patch4_window7_224] INFO: Epoch: [170] [1210/1251] eta: 0:00:20 lr: 0.000397 loss: 3.3614 (3.2192) grad_norm: 1.5492 (nan) time: 0.4959 [2021-03-26 10:39:39 swin_small_patch4_window7_224] INFO: Epoch: [170] [1220/1251] eta: 0:00:15 lr: 0.000397 loss: 3.1868 (3.2180) grad_norm: 1.5884 (nan) time: 0.4992 [2021-03-26 10:39:44 swin_small_patch4_window7_224] INFO: Epoch: [170] [1230/1251] eta: 0:00:10 lr: 0.000397 loss: 3.2797 (3.2168) grad_norm: 1.5869 (nan) time: 0.5095 [2021-03-26 10:39:49 swin_small_patch4_window7_224] INFO: Epoch: [170] [1240/1251] eta: 0:00:05 lr: 0.000397 loss: 3.2647 (3.2165) grad_norm: 1.5842 (nan) time: 0.5045 [2021-03-26 10:39:54 swin_small_patch4_window7_224] INFO: Epoch: [170] [1250/1251] eta: 0:00:00 lr: 0.000397 loss: 3.3358 (3.2175) grad_norm: 1.5942 (nan) time: 0.4922 [2021-03-26 10:40:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.8483 (0.8483) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-26 10:40:42 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7983 (0.8916) acc1: 78.1250 (77.4148) acc5: 95.3125 (94.3182) [2021-03-26 10:40:43 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.9964 (0.9630) acc1: 76.5625 (76.0417) acc5: 93.7500 (93.6012) [2021-03-26 10:40:44 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.9931 (0.9357) acc1: 76.5625 (76.8145) acc5: 93.7500 (94.2540) [2021-03-26 10:40:45 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7810 (0.9083) acc1: 79.6875 (77.7820) acc5: 95.3125 (94.5884) [2021-03-26 10:40:46 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7741 (0.8870) acc1: 81.2500 (78.4640) acc5: 96.8750 (94.8160) [2021-03-26 10:40:54 swin_small_patch4_window7_224] INFO: * Acc@1 79.398 Acc@5 94.946 loss 0.877 [2021-03-26 10:40:54 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.4% [2021-03-26 10:40:54 swin_small_patch4_window7_224] INFO: Max accuracy: 79.40% [2021-03-26 10:40:59 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 0/1251] eta: 1:24:52 lr: 0.000397 loss: 3.9713 (3.9713) grad_norm: 1.7134 (1.7134) time: 4.0704 [2021-03-26 10:41:04 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 10/1251] eta: 0:17:25 lr: 0.000397 loss: 2.8215 (3.0203) grad_norm: 1.5284 (1.5422) time: 0.8424 [2021-03-26 10:41:09 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 20/1251] eta: 0:13:53 lr: 0.000397 loss: 2.9414 (3.1018) grad_norm: 1.5272 (1.5425) time: 0.5075 [2021-03-26 10:41:14 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 30/1251] eta: 0:12:37 lr: 0.000397 loss: 3.2942 (3.1845) grad_norm: 1.5487 (1.5632) time: 0.4979 [2021-03-26 10:41:19 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 40/1251] eta: 0:12:00 lr: 0.000397 loss: 3.2750 (3.0967) grad_norm: 1.6159 (1.5942) time: 0.5082 [2021-03-26 10:41:24 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 50/1251] eta: 0:11:33 lr: 0.000397 loss: 3.2750 (3.1379) grad_norm: 1.6461 (1.6172) time: 0.5109 [2021-03-26 10:41:29 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 60/1251] eta: 0:11:12 lr: 0.000397 loss: 3.2973 (3.1248) grad_norm: 1.7300 (1.6524) time: 0.5031 [2021-03-26 10:41:34 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 70/1251] eta: 0:10:55 lr: 0.000397 loss: 3.1088 (3.1095) grad_norm: 1.6991 (1.6499) time: 0.4995 [2021-03-26 10:41:39 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 80/1251] eta: 0:10:43 lr: 0.000397 loss: 3.1035 (3.1091) grad_norm: 1.5479 (1.6409) time: 0.5043 [2021-03-26 10:41:44 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 90/1251] eta: 0:10:32 lr: 0.000397 loss: 3.2739 (3.1270) grad_norm: 1.5604 (1.6383) time: 0.5075 [2021-03-26 10:41:49 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 100/1251] eta: 0:10:23 lr: 0.000397 loss: 3.3471 (3.1449) grad_norm: 1.5494 (1.6299) time: 0.5095 [2021-03-26 10:41:54 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 110/1251] eta: 0:10:14 lr: 0.000397 loss: 3.3471 (3.1521) grad_norm: 1.6040 (1.6320) time: 0.5106 [2021-03-26 10:41:59 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 120/1251] eta: 0:10:05 lr: 0.000397 loss: 3.3286 (3.1692) grad_norm: 1.6084 (1.6308) time: 0.5024 [2021-03-26 10:42:04 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 130/1251] eta: 0:09:56 lr: 0.000396 loss: 3.3286 (3.1600) grad_norm: 1.5508 (1.6297) time: 0.4970 [2021-03-26 10:42:09 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 140/1251] eta: 0:09:49 lr: 0.000396 loss: 3.4483 (3.1876) grad_norm: 1.5508 (1.6278) time: 0.5009 [2021-03-26 10:42:14 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 150/1251] eta: 0:09:42 lr: 0.000396 loss: 3.4801 (3.2012) grad_norm: 1.6953 (1.6357) time: 0.5076 [2021-03-26 10:42:19 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 160/1251] eta: 0:09:35 lr: 0.000396 loss: 3.3782 (3.1984) grad_norm: 1.6675 (1.6332) time: 0.5097 [2021-03-26 10:42:25 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 170/1251] eta: 0:09:29 lr: 0.000396 loss: 3.0073 (3.1869) grad_norm: 1.5728 (1.6333) time: 0.5098 [2021-03-26 10:42:30 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 180/1251] eta: 0:09:22 lr: 0.000396 loss: 3.1348 (3.1898) grad_norm: 1.5232 (1.6278) time: 0.5069 [2021-03-26 10:42:35 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 190/1251] eta: 0:09:16 lr: 0.000396 loss: 3.1999 (3.1967) grad_norm: 1.5221 (1.6249) time: 0.5070 [2021-03-26 10:42:40 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 200/1251] eta: 0:09:10 lr: 0.000396 loss: 3.2391 (3.1938) grad_norm: 1.5754 (1.6241) time: 0.5079 [2021-03-26 10:42:45 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 210/1251] eta: 0:09:04 lr: 0.000396 loss: 3.2391 (3.1879) grad_norm: 1.5434 (1.6200) time: 0.5045 [2021-03-26 10:42:50 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 220/1251] eta: 0:08:57 lr: 0.000396 loss: 3.2721 (3.1967) grad_norm: 1.5579 (1.6178) time: 0.5004 [2021-03-26 10:42:55 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 230/1251] eta: 0:08:51 lr: 0.000396 loss: 3.2337 (3.1896) grad_norm: 1.5643 (1.6149) time: 0.5001 [2021-03-26 10:43:00 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 240/1251] eta: 0:08:45 lr: 0.000396 loss: 3.1835 (3.1936) grad_norm: 1.5361 (1.6128) time: 0.5036 [2021-03-26 10:43:05 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 250/1251] eta: 0:08:39 lr: 0.000396 loss: 3.3445 (3.1955) grad_norm: 1.6111 (1.6179) time: 0.5012 [2021-03-26 10:43:10 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 260/1251] eta: 0:08:33 lr: 0.000396 loss: 3.3445 (3.1962) grad_norm: 1.6111 (1.6144) time: 0.4987 [2021-03-26 10:43:15 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 270/1251] eta: 0:08:27 lr: 0.000396 loss: 3.3705 (3.1964) grad_norm: 1.4905 (1.6127) time: 0.4973 [2021-03-26 10:43:20 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 280/1251] eta: 0:08:22 lr: 0.000396 loss: 3.0635 (3.1877) grad_norm: 1.6600 (1.6201) time: 0.4979 [2021-03-26 10:43:25 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 290/1251] eta: 0:08:16 lr: 0.000396 loss: 2.9397 (3.1793) grad_norm: 1.6775 (1.6194) time: 0.4992 [2021-03-26 10:43:30 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 300/1251] eta: 0:08:10 lr: 0.000396 loss: 2.9539 (3.1743) grad_norm: 1.5266 (1.6169) time: 0.4985 [2021-03-26 10:43:35 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 310/1251] eta: 0:08:05 lr: 0.000396 loss: 3.3252 (3.1779) grad_norm: 1.5266 (1.6143) time: 0.5031 [2021-03-26 10:43:40 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 320/1251] eta: 0:07:59 lr: 0.000396 loss: 3.3365 (3.1757) grad_norm: 1.5428 (1.6131) time: 0.5049 [2021-03-26 10:43:45 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 330/1251] eta: 0:07:54 lr: 0.000396 loss: 3.3448 (3.1858) grad_norm: 1.5543 (1.6127) time: 0.5016 [2021-03-26 10:43:50 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 340/1251] eta: 0:07:48 lr: 0.000396 loss: 3.3536 (3.1794) grad_norm: 1.5726 (1.6118) time: 0.5062 [2021-03-26 10:43:55 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 350/1251] eta: 0:07:43 lr: 0.000396 loss: 3.3536 (3.1815) grad_norm: 1.5618 (1.6107) time: 0.5069 [2021-03-26 10:44:00 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 360/1251] eta: 0:07:37 lr: 0.000396 loss: 3.3580 (3.1837) grad_norm: 1.5695 (1.6116) time: 0.5008 [2021-03-26 10:44:05 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 370/1251] eta: 0:07:32 lr: 0.000396 loss: 3.1835 (3.1815) grad_norm: 1.5364 (1.6106) time: 0.5065 [2021-03-26 10:44:10 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 380/1251] eta: 0:07:27 lr: 0.000395 loss: 3.2060 (3.1852) grad_norm: 1.5214 (1.6110) time: 0.5097 [2021-03-26 10:44:15 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 390/1251] eta: 0:07:21 lr: 0.000395 loss: 3.3369 (3.1870) grad_norm: 1.5425 (1.6106) time: 0.5031 [2021-03-26 10:44:20 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 400/1251] eta: 0:07:16 lr: 0.000395 loss: 3.3369 (3.1908) grad_norm: 1.5573 (1.6096) time: 0.5055 [2021-03-26 10:44:25 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 410/1251] eta: 0:07:11 lr: 0.000395 loss: 3.2815 (3.1892) grad_norm: 1.5573 (1.6088) time: 0.5016 [2021-03-26 10:44:30 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 420/1251] eta: 0:07:05 lr: 0.000395 loss: 3.1964 (3.1934) grad_norm: 1.5365 (1.6079) time: 0.4936 [2021-03-26 10:44:35 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 430/1251] eta: 0:07:00 lr: 0.000395 loss: 3.2552 (3.1915) grad_norm: 1.5002 (1.6059) time: 0.4966 [2021-03-26 10:44:40 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 440/1251] eta: 0:06:54 lr: 0.000395 loss: 3.1486 (3.1868) grad_norm: 1.5184 (1.6058) time: 0.4949 [2021-03-26 10:44:45 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 450/1251] eta: 0:06:49 lr: 0.000395 loss: 3.1889 (3.1867) grad_norm: 1.5973 (1.6056) time: 0.4925 [2021-03-26 10:44:50 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 460/1251] eta: 0:06:44 lr: 0.000395 loss: 3.3121 (3.1890) grad_norm: 1.5151 (1.6038) time: 0.4980 [2021-03-26 10:44:55 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 470/1251] eta: 0:06:38 lr: 0.000395 loss: 3.2885 (3.1850) grad_norm: 1.4951 (1.6019) time: 0.4987 [2021-03-26 10:45:00 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 480/1251] eta: 0:06:33 lr: 0.000395 loss: 3.3791 (3.1915) grad_norm: 1.5373 (1.6023) time: 0.5020 [2021-03-26 10:45:05 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 490/1251] eta: 0:06:28 lr: 0.000395 loss: 3.3986 (3.1949) grad_norm: 1.5133 (1.6012) time: 0.5029 [2021-03-26 10:45:10 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 500/1251] eta: 0:06:23 lr: 0.000395 loss: 3.1658 (3.1901) grad_norm: 1.5651 (1.6015) time: 0.4980 [2021-03-26 10:45:15 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 510/1251] eta: 0:06:17 lr: 0.000395 loss: 3.1796 (3.1924) grad_norm: 1.5651 (1.6009) time: 0.5041 [2021-03-26 10:45:20 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 520/1251] eta: 0:06:12 lr: 0.000395 loss: 3.4518 (3.1979) grad_norm: 1.6380 (1.6039) time: 0.5036 [2021-03-26 10:45:25 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 530/1251] eta: 0:06:07 lr: 0.000395 loss: 3.4952 (3.2020) grad_norm: 1.7301 (1.6050) time: 0.5092 [2021-03-26 10:45:30 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 540/1251] eta: 0:06:02 lr: 0.000395 loss: 3.2979 (3.1976) grad_norm: 1.6134 (1.6054) time: 0.5158 [2021-03-26 10:45:36 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 550/1251] eta: 0:05:57 lr: 0.000395 loss: 3.4653 (3.2038) grad_norm: 1.5679 (1.6053) time: 0.5169 [2021-03-26 10:45:41 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 560/1251] eta: 0:05:52 lr: 0.000395 loss: 3.4662 (3.2022) grad_norm: 1.5546 (1.6076) time: 0.5197 [2021-03-26 10:45:46 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 570/1251] eta: 0:05:47 lr: 0.000395 loss: 3.1706 (3.1995) grad_norm: 1.5890 (1.6077) time: 0.5110 [2021-03-26 10:45:51 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 580/1251] eta: 0:05:42 lr: 0.000395 loss: 2.9881 (3.1985) grad_norm: 1.6238 (1.6080) time: 0.5035 [2021-03-26 10:45:56 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 590/1251] eta: 0:05:37 lr: 0.000395 loss: 3.1386 (3.2018) grad_norm: 1.6220 (1.6092) time: 0.5038 [2021-03-26 10:46:01 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 600/1251] eta: 0:05:31 lr: 0.000395 loss: 3.4637 (3.2035) grad_norm: 1.5954 (1.6098) time: 0.5008 [2021-03-26 10:46:06 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 610/1251] eta: 0:05:26 lr: 0.000395 loss: 3.2018 (3.2000) grad_norm: 1.6123 (1.6129) time: 0.4956 [2021-03-26 10:46:11 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 620/1251] eta: 0:05:21 lr: 0.000395 loss: 3.1906 (3.2009) grad_norm: 1.6512 (1.6139) time: 0.5056 [2021-03-26 10:46:16 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 630/1251] eta: 0:05:16 lr: 0.000394 loss: 3.3891 (3.2026) grad_norm: 1.6412 (1.6134) time: 0.5051 [2021-03-26 10:46:21 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 640/1251] eta: 0:05:11 lr: 0.000394 loss: 3.4028 (3.2013) grad_norm: 1.5831 (1.6124) time: 0.5006 [2021-03-26 10:46:26 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 650/1251] eta: 0:05:06 lr: 0.000394 loss: 3.2966 (3.2036) grad_norm: 1.5820 (1.6120) time: 0.5058 [2021-03-26 10:46:31 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 660/1251] eta: 0:05:00 lr: 0.000394 loss: 3.2760 (3.2047) grad_norm: 1.6065 (1.6134) time: 0.5043 [2021-03-26 10:46:36 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 670/1251] eta: 0:04:55 lr: 0.000394 loss: 3.3196 (3.2076) grad_norm: 1.6282 (1.6135) time: 0.5029 [2021-03-26 10:46:41 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 680/1251] eta: 0:04:50 lr: 0.000394 loss: 3.5029 (3.2117) grad_norm: 1.6181 (1.6133) time: 0.5024 [2021-03-26 10:46:46 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 690/1251] eta: 0:04:45 lr: 0.000394 loss: 3.3808 (3.2119) grad_norm: 1.6181 (1.6135) time: 0.5014 [2021-03-26 10:46:51 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 700/1251] eta: 0:04:40 lr: 0.000394 loss: 3.2677 (3.2104) grad_norm: 1.5887 (1.6136) time: 0.5067 [2021-03-26 10:46:56 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 710/1251] eta: 0:04:35 lr: 0.000394 loss: 3.2431 (3.2108) grad_norm: 1.5753 (1.6130) time: 0.5065 [2021-03-26 10:47:01 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 720/1251] eta: 0:04:30 lr: 0.000394 loss: 3.2431 (3.2122) grad_norm: 1.5784 (1.6135) time: 0.4985 [2021-03-26 10:47:06 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 730/1251] eta: 0:04:25 lr: 0.000394 loss: 3.0917 (3.2104) grad_norm: 1.6211 (1.6132) time: 0.5038 [2021-03-26 10:47:12 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 740/1251] eta: 0:04:20 lr: 0.000394 loss: 3.1665 (3.2113) grad_norm: 1.6267 (1.6142) time: 0.5299 [2021-03-26 10:47:17 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 750/1251] eta: 0:04:15 lr: 0.000394 loss: 3.4172 (3.2131) grad_norm: 1.6267 (1.6143) time: 0.5344 [2021-03-26 10:47:22 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 760/1251] eta: 0:04:09 lr: 0.000394 loss: 3.3154 (3.2101) grad_norm: 1.6113 (1.6143) time: 0.5053 [2021-03-26 10:47:27 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 770/1251] eta: 0:04:04 lr: 0.000394 loss: 3.2991 (3.2105) grad_norm: 1.4941 (1.6127) time: 0.4948 [2021-03-26 10:47:32 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 780/1251] eta: 0:03:59 lr: 0.000394 loss: 3.2848 (3.2093) grad_norm: 1.4941 (1.6123) time: 0.4972 [2021-03-26 10:47:37 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 790/1251] eta: 0:03:54 lr: 0.000394 loss: 3.2795 (3.2081) grad_norm: 1.6239 (1.6123) time: 0.5002 [2021-03-26 10:47:42 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 800/1251] eta: 0:03:49 lr: 0.000394 loss: 3.2795 (3.2102) grad_norm: 1.6400 (1.6132) time: 0.5019 [2021-03-26 10:47:47 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 810/1251] eta: 0:03:44 lr: 0.000394 loss: 3.1647 (3.2078) grad_norm: 1.5747 (1.6120) time: 0.5046 [2021-03-26 10:47:52 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 820/1251] eta: 0:03:39 lr: 0.000394 loss: 3.3354 (3.2110) grad_norm: 1.4687 (1.6108) time: 0.5078 [2021-03-26 10:47:57 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 830/1251] eta: 0:03:34 lr: 0.000394 loss: 3.4657 (3.2129) grad_norm: 1.5342 (1.6106) time: 0.5020 [2021-03-26 10:48:02 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 840/1251] eta: 0:03:28 lr: 0.000394 loss: 3.3641 (3.2150) grad_norm: 1.6007 (1.6105) time: 0.5001 [2021-03-26 10:48:07 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 850/1251] eta: 0:03:23 lr: 0.000394 loss: 3.4506 (3.2174) grad_norm: 1.5637 (1.6106) time: 0.5038 [2021-03-26 10:48:12 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 860/1251] eta: 0:03:18 lr: 0.000394 loss: 3.1911 (3.2143) grad_norm: 1.5112 (1.6093) time: 0.5079 [2021-03-26 10:48:17 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 870/1251] eta: 0:03:13 lr: 0.000394 loss: 2.7638 (3.2093) grad_norm: 1.5488 (1.6091) time: 0.5061 [2021-03-26 10:48:22 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 880/1251] eta: 0:03:08 lr: 0.000393 loss: 3.1126 (3.2110) grad_norm: 1.5632 (1.6085) time: 0.5030 [2021-03-26 10:48:27 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 890/1251] eta: 0:03:03 lr: 0.000393 loss: 3.5336 (3.2147) grad_norm: 1.5981 (1.6093) time: 0.5057 [2021-03-26 10:48:33 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 900/1251] eta: 0:02:58 lr: 0.000393 loss: 3.4878 (3.2154) grad_norm: 1.6194 (1.6103) time: 0.5048 [2021-03-26 10:48:38 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 910/1251] eta: 0:02:53 lr: 0.000393 loss: 3.2500 (3.2137) grad_norm: 1.6493 (1.6109) time: 0.5016 [2021-03-26 10:48:43 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 920/1251] eta: 0:02:48 lr: 0.000393 loss: 3.3567 (3.2140) grad_norm: 1.5668 (1.6108) time: 0.5010 [2021-03-26 10:48:48 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 930/1251] eta: 0:02:43 lr: 0.000393 loss: 3.2443 (3.2098) grad_norm: 1.5668 (1.6109) time: 0.5121 [2021-03-26 10:48:53 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 940/1251] eta: 0:02:38 lr: 0.000393 loss: 3.2263 (3.2124) grad_norm: 1.6178 (1.6114) time: 0.5109 [2021-03-26 10:48:58 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 950/1251] eta: 0:02:32 lr: 0.000393 loss: 3.5039 (3.2140) grad_norm: 1.6155 (1.6117) time: 0.5009 [2021-03-26 10:49:03 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 960/1251] eta: 0:02:27 lr: 0.000393 loss: 3.4083 (3.2150) grad_norm: 1.5981 (1.6118) time: 0.5020 [2021-03-26 10:49:08 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 970/1251] eta: 0:02:22 lr: 0.000393 loss: 3.2742 (3.2136) grad_norm: 1.5633 (1.6115) time: 0.5060 [2021-03-26 10:49:13 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 980/1251] eta: 0:02:17 lr: 0.000393 loss: 3.2113 (3.2137) grad_norm: 1.5497 (1.6109) time: 0.5088 [2021-03-26 10:49:18 swin_small_patch4_window7_224] INFO: Epoch: [171] [ 990/1251] eta: 0:02:12 lr: 0.000393 loss: 3.2113 (3.2140) grad_norm: 1.4858 (1.6102) time: 0.5031 [2021-03-26 10:49:23 swin_small_patch4_window7_224] INFO: Epoch: [171] [1000/1251] eta: 0:02:07 lr: 0.000393 loss: 3.0504 (3.2124) grad_norm: 1.5290 (1.6101) time: 0.5008 [2021-03-26 10:49:28 swin_small_patch4_window7_224] INFO: Epoch: [171] [1010/1251] eta: 0:02:02 lr: 0.000393 loss: 3.1516 (3.2133) grad_norm: 1.5927 (1.6114) time: 0.5045 [2021-03-26 10:49:33 swin_small_patch4_window7_224] INFO: Epoch: [171] [1020/1251] eta: 0:01:57 lr: 0.000393 loss: 3.3443 (3.2139) grad_norm: 1.5829 (1.6117) time: 0.5048 [2021-03-26 10:49:38 swin_small_patch4_window7_224] INFO: Epoch: [171] [1030/1251] eta: 0:01:52 lr: 0.000393 loss: 3.2989 (3.2119) grad_norm: 1.5401 (1.6114) time: 0.4974 [2021-03-26 10:49:43 swin_small_patch4_window7_224] INFO: Epoch: [171] [1040/1251] eta: 0:01:47 lr: 0.000393 loss: 3.3057 (3.2134) grad_norm: 1.6503 (1.6118) time: 0.4993 [2021-03-26 10:49:48 swin_small_patch4_window7_224] INFO: Epoch: [171] [1050/1251] eta: 0:01:42 lr: 0.000393 loss: 3.3181 (3.2133) grad_norm: 1.6365 (1.6120) time: 0.5096 [2021-03-26 10:49:53 swin_small_patch4_window7_224] INFO: Epoch: [171] [1060/1251] eta: 0:01:36 lr: 0.000393 loss: 3.2966 (3.2148) grad_norm: 1.6065 (1.6119) time: 0.5067 [2021-03-26 10:49:58 swin_small_patch4_window7_224] INFO: Epoch: [171] [1070/1251] eta: 0:01:31 lr: 0.000393 loss: 3.2322 (3.2132) grad_norm: 1.5474 (1.6115) time: 0.4991 [2021-03-26 10:50:03 swin_small_patch4_window7_224] INFO: Epoch: [171] [1080/1251] eta: 0:01:26 lr: 0.000393 loss: 3.0482 (3.2120) grad_norm: 1.5051 (1.6105) time: 0.5031 [2021-03-26 10:50:08 swin_small_patch4_window7_224] INFO: Epoch: [171] [1090/1251] eta: 0:01:21 lr: 0.000393 loss: 3.3008 (3.2144) grad_norm: 1.5180 (1.6102) time: 0.5075 [2021-03-26 10:50:13 swin_small_patch4_window7_224] INFO: Epoch: [171] [1100/1251] eta: 0:01:16 lr: 0.000393 loss: 3.3772 (3.2134) grad_norm: 1.6052 (1.6107) time: 0.5007 [2021-03-26 10:50:18 swin_small_patch4_window7_224] INFO: Epoch: [171] [1110/1251] eta: 0:01:11 lr: 0.000393 loss: 3.3392 (3.2151) grad_norm: 1.5491 (1.6096) time: 0.4981 [2021-03-26 10:50:23 swin_small_patch4_window7_224] INFO: Epoch: [171] [1120/1251] eta: 0:01:06 lr: 0.000392 loss: 3.4702 (3.2163) grad_norm: 1.4686 (1.6090) time: 0.5016 [2021-03-26 10:50:29 swin_small_patch4_window7_224] INFO: Epoch: [171] [1130/1251] eta: 0:01:01 lr: 0.000392 loss: 3.3049 (3.2141) grad_norm: 1.6045 (1.6095) time: 0.5097 [2021-03-26 10:50:34 swin_small_patch4_window7_224] INFO: Epoch: [171] [1140/1251] eta: 0:00:56 lr: 0.000392 loss: 3.2972 (3.2156) grad_norm: 1.6106 (1.6093) time: 0.5101 [2021-03-26 10:50:39 swin_small_patch4_window7_224] INFO: Epoch: [171] [1150/1251] eta: 0:00:51 lr: 0.000392 loss: 3.4952 (3.2187) grad_norm: 1.6026 (1.6092) time: 0.5004 [2021-03-26 10:50:44 swin_small_patch4_window7_224] INFO: Epoch: [171] [1160/1251] eta: 0:00:46 lr: 0.000392 loss: 3.4526 (3.2201) grad_norm: 1.6233 (1.6094) time: 0.4979 [2021-03-26 10:50:49 swin_small_patch4_window7_224] INFO: Epoch: [171] [1170/1251] eta: 0:00:41 lr: 0.000392 loss: 3.2416 (3.2171) grad_norm: 1.5768 (1.6089) time: 0.5022 [2021-03-26 10:50:54 swin_small_patch4_window7_224] INFO: Epoch: [171] [1180/1251] eta: 0:00:36 lr: 0.000392 loss: 3.0225 (3.2162) grad_norm: 1.5990 (1.6091) time: 0.5059 [2021-03-26 10:50:59 swin_small_patch4_window7_224] INFO: Epoch: [171] [1190/1251] eta: 0:00:30 lr: 0.000392 loss: 3.3906 (3.2163) grad_norm: 1.6149 (1.6105) time: 0.5059 [2021-03-26 10:51:04 swin_small_patch4_window7_224] INFO: Epoch: [171] [1200/1251] eta: 0:00:25 lr: 0.000392 loss: 3.3952 (3.2166) grad_norm: 1.5829 (1.6110) time: 0.5028 [2021-03-26 10:51:09 swin_small_patch4_window7_224] INFO: Epoch: [171] [1210/1251] eta: 0:00:20 lr: 0.000392 loss: 3.3553 (3.2184) grad_norm: 1.6342 (1.6121) time: 0.5005 [2021-03-26 10:51:14 swin_small_patch4_window7_224] INFO: Epoch: [171] [1220/1251] eta: 0:00:15 lr: 0.000392 loss: 3.2917 (3.2190) grad_norm: 1.6305 (1.6119) time: 0.5061 [2021-03-26 10:51:19 swin_small_patch4_window7_224] INFO: Epoch: [171] [1230/1251] eta: 0:00:10 lr: 0.000392 loss: 3.0810 (3.2191) grad_norm: 1.6277 (1.6125) time: 0.5099 [2021-03-26 10:51:24 swin_small_patch4_window7_224] INFO: Epoch: [171] [1240/1251] eta: 0:00:05 lr: 0.000392 loss: 3.1802 (3.2184) grad_norm: 1.5611 (1.6124) time: 0.5089 [2021-03-26 10:51:29 swin_small_patch4_window7_224] INFO: Epoch: [171] [1250/1251] eta: 0:00:00 lr: 0.000392 loss: 3.4021 (3.2175) grad_norm: 1.6269 (1.6135) time: 0.5097 [2021-03-26 10:51:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:44 loss: 0.6287 (0.6287) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-26 10:51:40 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9103 (0.9533) acc1: 76.5625 (76.8466) acc5: 95.3125 (94.8864) [2021-03-26 10:51:42 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8357 (0.9147) acc1: 76.5625 (77.1577) acc5: 95.3125 (95.0893) [2021-03-26 10:51:44 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8163 (0.8681) acc1: 78.1250 (78.3770) acc5: 95.3125 (95.2117) [2021-03-26 10:51:46 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8373 (0.8716) acc1: 79.6875 (78.6585) acc5: 95.3125 (95.2744) [2021-03-26 10:51:47 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9071 (0.8821) acc1: 78.1250 (78.6240) acc5: 95.3125 (95.2960) [2021-03-26 10:51:55 swin_small_patch4_window7_224] INFO: * Acc@1 79.212 Acc@5 94.898 loss 0.878 [2021-03-26 10:51:55 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.2% [2021-03-26 10:51:55 swin_small_patch4_window7_224] INFO: Max accuracy: 79.40% [2021-03-26 10:51:59 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 0/1251] eta: 1:33:31 lr: 0.000392 loss: 2.1995 (2.1995) grad_norm: 1.8798 (1.8798) time: 4.4859 [2021-03-26 10:52:04 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 10/1251] eta: 0:18:03 lr: 0.000392 loss: 3.4984 (3.2883) grad_norm: 1.6840 (1.7041) time: 0.8732 [2021-03-26 10:52:09 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 20/1251] eta: 0:14:19 lr: 0.000392 loss: 3.4170 (3.2159) grad_norm: 1.6291 (1.6496) time: 0.5087 [2021-03-26 10:52:14 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 30/1251] eta: 0:12:54 lr: 0.000392 loss: 3.2132 (3.1385) grad_norm: 1.5948 (1.6360) time: 0.5031 [2021-03-26 10:52:19 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 40/1251] eta: 0:12:13 lr: 0.000392 loss: 3.2132 (3.1447) grad_norm: 1.5867 (1.6308) time: 0.5090 [2021-03-26 10:52:24 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 50/1251] eta: 0:11:42 lr: 0.000392 loss: 3.2998 (3.1606) grad_norm: 1.5623 (1.6388) time: 0.5084 [2021-03-26 10:52:29 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 60/1251] eta: 0:11:21 lr: 0.000392 loss: 3.2945 (3.1587) grad_norm: 1.5693 (1.6411) time: 0.5027 [2021-03-26 10:52:34 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 70/1251] eta: 0:11:03 lr: 0.000392 loss: 3.2786 (3.1718) grad_norm: 1.6564 (1.6529) time: 0.5028 [2021-03-26 10:52:40 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 80/1251] eta: 0:10:50 lr: 0.000392 loss: 3.0061 (3.1493) grad_norm: 1.7047 (1.6554) time: 0.5045 [2021-03-26 10:52:45 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 90/1251] eta: 0:10:38 lr: 0.000392 loss: 2.9440 (3.1401) grad_norm: 1.5175 (1.6426) time: 0.5093 [2021-03-26 10:52:50 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 100/1251] eta: 0:10:27 lr: 0.000392 loss: 2.9427 (3.1280) grad_norm: 1.5083 (1.6489) time: 0.5056 [2021-03-26 10:52:55 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 110/1251] eta: 0:10:18 lr: 0.000392 loss: 3.1406 (3.1279) grad_norm: 1.6555 (1.6490) time: 0.5058 [2021-03-26 10:53:00 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 120/1251] eta: 0:10:09 lr: 0.000391 loss: 3.2777 (3.1368) grad_norm: 1.6050 (1.6434) time: 0.5075 [2021-03-26 10:53:05 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 130/1251] eta: 0:10:01 lr: 0.000391 loss: 3.4094 (3.1431) grad_norm: 1.5294 (1.6353) time: 0.5023 [2021-03-26 10:53:10 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 140/1251] eta: 0:09:52 lr: 0.000391 loss: 3.2468 (3.1535) grad_norm: 1.5294 (1.6342) time: 0.4984 [2021-03-26 10:53:15 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 150/1251] eta: 0:09:45 lr: 0.000391 loss: 3.1984 (3.1474) grad_norm: 1.6758 (1.6364) time: 0.4999 [2021-03-26 10:53:20 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 160/1251] eta: 0:09:37 lr: 0.000391 loss: 3.2282 (3.1437) grad_norm: 1.5695 (1.6295) time: 0.5033 [2021-03-26 10:53:25 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 170/1251] eta: 0:09:30 lr: 0.000391 loss: 3.1451 (3.1425) grad_norm: 1.5500 (1.6252) time: 0.5024 [2021-03-26 10:53:30 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 180/1251] eta: 0:09:24 lr: 0.000391 loss: 2.9961 (3.1319) grad_norm: 1.5667 (1.6273) time: 0.5082 [2021-03-26 10:53:35 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 190/1251] eta: 0:09:17 lr: 0.000391 loss: 3.0555 (3.1369) grad_norm: 1.6019 (1.6259) time: 0.5054 [2021-03-26 10:53:40 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 200/1251] eta: 0:09:12 lr: 0.000391 loss: 3.1066 (3.1351) grad_norm: 1.5537 (1.6238) time: 0.5076 [2021-03-26 10:53:45 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 210/1251] eta: 0:09:05 lr: 0.000391 loss: 3.1066 (3.1410) grad_norm: 1.6322 (1.6279) time: 0.5128 [2021-03-26 10:53:50 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 220/1251] eta: 0:08:59 lr: 0.000391 loss: 3.0659 (3.1342) grad_norm: 1.6213 (1.6287) time: 0.5008 [2021-03-26 10:53:55 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 230/1251] eta: 0:08:53 lr: 0.000391 loss: 3.1425 (3.1373) grad_norm: 1.5738 (1.6271) time: 0.4982 [2021-03-26 10:54:00 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 240/1251] eta: 0:08:46 lr: 0.000391 loss: 3.3744 (3.1440) grad_norm: 1.5738 (1.6260) time: 0.5002 [2021-03-26 10:54:05 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 250/1251] eta: 0:08:41 lr: 0.000391 loss: 3.4003 (3.1368) grad_norm: 1.6144 (1.6255) time: 0.5043 [2021-03-26 10:54:10 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 260/1251] eta: 0:08:35 lr: 0.000391 loss: 3.3322 (3.1418) grad_norm: 1.5638 (1.6221) time: 0.5058 [2021-03-26 10:54:15 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 270/1251] eta: 0:08:29 lr: 0.000391 loss: 3.3429 (3.1510) grad_norm: 1.5638 (1.6225) time: 0.5011 [2021-03-26 10:54:20 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 280/1251] eta: 0:08:23 lr: 0.000391 loss: 3.2726 (3.1443) grad_norm: 1.5961 (1.6243) time: 0.5039 [2021-03-26 10:54:25 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 290/1251] eta: 0:08:18 lr: 0.000391 loss: 3.3239 (3.1562) grad_norm: 1.5792 (1.6231) time: 0.5041 [2021-03-26 10:54:30 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 300/1251] eta: 0:08:12 lr: 0.000391 loss: 3.4062 (3.1637) grad_norm: 1.5792 (1.6247) time: 0.5000 [2021-03-26 10:54:36 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 310/1251] eta: 0:08:06 lr: 0.000391 loss: 3.4140 (3.1730) grad_norm: 1.5729 (1.6230) time: 0.5062 [2021-03-26 10:54:41 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 320/1251] eta: 0:08:01 lr: 0.000391 loss: 3.4286 (3.1749) grad_norm: 1.4975 (1.6205) time: 0.5075 [2021-03-26 10:54:46 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 330/1251] eta: 0:07:55 lr: 0.000391 loss: 3.2463 (3.1731) grad_norm: 1.5373 (1.6192) time: 0.5017 [2021-03-26 10:54:51 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 340/1251] eta: 0:07:50 lr: 0.000391 loss: 3.2008 (3.1676) grad_norm: 1.5373 (1.6174) time: 0.5022 [2021-03-26 10:54:56 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 350/1251] eta: 0:07:44 lr: 0.000391 loss: 2.9776 (3.1647) grad_norm: 1.5460 (1.6180) time: 0.4988 [2021-03-26 10:55:01 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 360/1251] eta: 0:07:39 lr: 0.000391 loss: 3.2667 (3.1681) grad_norm: 1.7448 (1.6242) time: 0.5005 [2021-03-26 10:55:06 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 370/1251] eta: 0:07:33 lr: 0.000390 loss: 3.2965 (3.1656) grad_norm: 1.7448 (1.6259) time: 0.5095 [2021-03-26 10:55:11 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 380/1251] eta: 0:07:28 lr: 0.000390 loss: 2.7976 (3.1573) grad_norm: 1.6245 (1.6259) time: 0.5081 [2021-03-26 10:55:16 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 390/1251] eta: 0:07:23 lr: 0.000390 loss: 2.9802 (3.1574) grad_norm: 1.6209 (nan) time: 0.5065 [2021-03-26 10:55:21 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 400/1251] eta: 0:07:17 lr: 0.000390 loss: 3.3025 (3.1639) grad_norm: 1.6309 (nan) time: 0.5087 [2021-03-26 10:55:26 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 410/1251] eta: 0:07:12 lr: 0.000390 loss: 3.4742 (3.1703) grad_norm: 1.6404 (nan) time: 0.5025 [2021-03-26 10:55:31 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 420/1251] eta: 0:07:06 lr: 0.000390 loss: 3.4119 (3.1714) grad_norm: 1.6426 (nan) time: 0.4977 [2021-03-26 10:55:36 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 430/1251] eta: 0:07:01 lr: 0.000390 loss: 3.1257 (3.1703) grad_norm: 1.7030 (nan) time: 0.5015 [2021-03-26 10:55:41 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 440/1251] eta: 0:06:56 lr: 0.000390 loss: 3.1257 (3.1696) grad_norm: 1.7090 (nan) time: 0.5024 [2021-03-26 10:55:46 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 450/1251] eta: 0:06:50 lr: 0.000390 loss: 3.1663 (3.1707) grad_norm: 1.6105 (nan) time: 0.5037 [2021-03-26 10:55:51 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 460/1251] eta: 0:06:45 lr: 0.000390 loss: 3.0583 (3.1657) grad_norm: 1.5602 (nan) time: 0.5015 [2021-03-26 10:55:56 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 470/1251] eta: 0:06:40 lr: 0.000390 loss: 3.0007 (3.1630) grad_norm: 1.5372 (nan) time: 0.4969 [2021-03-26 10:56:01 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 480/1251] eta: 0:06:34 lr: 0.000390 loss: 3.1757 (3.1663) grad_norm: 1.5147 (nan) time: 0.4998 [2021-03-26 10:56:06 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 490/1251] eta: 0:06:29 lr: 0.000390 loss: 3.1939 (3.1662) grad_norm: 1.6267 (nan) time: 0.5055 [2021-03-26 10:56:11 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 500/1251] eta: 0:06:24 lr: 0.000390 loss: 3.4412 (3.1705) grad_norm: 1.6551 (nan) time: 0.5046 [2021-03-26 10:56:16 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 510/1251] eta: 0:06:19 lr: 0.000390 loss: 3.4412 (3.1727) grad_norm: 1.6135 (nan) time: 0.5068 [2021-03-26 10:56:21 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 520/1251] eta: 0:06:14 lr: 0.000390 loss: 3.1286 (3.1692) grad_norm: 1.6135 (nan) time: 0.5077 [2021-03-26 10:56:26 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 530/1251] eta: 0:06:08 lr: 0.000390 loss: 3.2270 (3.1678) grad_norm: 1.6716 (nan) time: 0.5032 [2021-03-26 10:56:31 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 540/1251] eta: 0:06:03 lr: 0.000390 loss: 3.4208 (3.1711) grad_norm: 1.6918 (nan) time: 0.5079 [2021-03-26 10:56:37 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 550/1251] eta: 0:05:58 lr: 0.000390 loss: 3.4692 (3.1730) grad_norm: 1.6965 (nan) time: 0.5137 [2021-03-26 10:56:42 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 560/1251] eta: 0:05:53 lr: 0.000390 loss: 3.2211 (3.1716) grad_norm: 1.6645 (nan) time: 0.5108 [2021-03-26 10:56:47 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 570/1251] eta: 0:05:48 lr: 0.000390 loss: 3.2178 (3.1760) grad_norm: 1.6170 (nan) time: 0.5026 [2021-03-26 10:56:52 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 580/1251] eta: 0:05:43 lr: 0.000390 loss: 3.3714 (3.1786) grad_norm: 1.6132 (nan) time: 0.5031 [2021-03-26 10:56:57 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 590/1251] eta: 0:05:37 lr: 0.000390 loss: 3.3247 (3.1786) grad_norm: 1.6541 (nan) time: 0.5088 [2021-03-26 10:57:02 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 600/1251] eta: 0:05:32 lr: 0.000390 loss: 3.2432 (3.1803) grad_norm: 1.6753 (nan) time: 0.5124 [2021-03-26 10:57:07 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 610/1251] eta: 0:05:27 lr: 0.000390 loss: 3.2816 (3.1812) grad_norm: 1.6527 (nan) time: 0.5102 [2021-03-26 10:57:12 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 620/1251] eta: 0:05:22 lr: 0.000389 loss: 3.3455 (3.1829) grad_norm: 1.5725 (nan) time: 0.5050 [2021-03-26 10:57:17 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 630/1251] eta: 0:05:17 lr: 0.000389 loss: 3.1628 (3.1835) grad_norm: 1.6023 (nan) time: 0.5057 [2021-03-26 10:57:22 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 640/1251] eta: 0:05:12 lr: 0.000389 loss: 3.2531 (3.1855) grad_norm: 1.6796 (nan) time: 0.5033 [2021-03-26 10:57:27 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 650/1251] eta: 0:05:07 lr: 0.000389 loss: 3.5003 (3.1885) grad_norm: 1.6626 (nan) time: 0.5064 [2021-03-26 10:57:32 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 660/1251] eta: 0:05:01 lr: 0.000389 loss: 3.1577 (3.1844) grad_norm: 1.5735 (nan) time: 0.5080 [2021-03-26 10:57:37 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 670/1251] eta: 0:04:56 lr: 0.000389 loss: 3.2195 (3.1857) grad_norm: 1.4898 (nan) time: 0.5067 [2021-03-26 10:57:42 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 680/1251] eta: 0:04:51 lr: 0.000389 loss: 3.2324 (3.1834) grad_norm: 1.5422 (nan) time: 0.5055 [2021-03-26 10:57:47 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 690/1251] eta: 0:04:46 lr: 0.000389 loss: 3.0791 (3.1849) grad_norm: 1.6254 (nan) time: 0.4986 [2021-03-26 10:57:52 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 700/1251] eta: 0:04:41 lr: 0.000389 loss: 3.0791 (3.1855) grad_norm: 1.5985 (nan) time: 0.4964 [2021-03-26 10:57:57 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 710/1251] eta: 0:04:35 lr: 0.000389 loss: 3.0780 (3.1838) grad_norm: 1.6482 (nan) time: 0.4990 [2021-03-26 10:58:02 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 720/1251] eta: 0:04:30 lr: 0.000389 loss: 3.2926 (3.1870) grad_norm: 1.6575 (nan) time: 0.4992 [2021-03-26 10:58:07 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 730/1251] eta: 0:04:25 lr: 0.000389 loss: 3.4227 (3.1886) grad_norm: 1.6048 (nan) time: 0.5074 [2021-03-26 10:58:13 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 740/1251] eta: 0:04:20 lr: 0.000389 loss: 3.3160 (3.1871) grad_norm: 1.6654 (nan) time: 0.5196 [2021-03-26 10:58:18 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 750/1251] eta: 0:04:15 lr: 0.000389 loss: 3.3957 (3.1929) grad_norm: 1.6654 (nan) time: 0.5243 [2021-03-26 10:58:23 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 760/1251] eta: 0:04:10 lr: 0.000389 loss: 3.5183 (3.1909) grad_norm: 1.6154 (nan) time: 0.5138 [2021-03-26 10:58:28 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 770/1251] eta: 0:04:05 lr: 0.000389 loss: 3.5183 (3.1962) grad_norm: 1.5246 (nan) time: 0.5000 [2021-03-26 10:58:33 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 780/1251] eta: 0:04:00 lr: 0.000389 loss: 3.4935 (3.1977) grad_norm: 1.5483 (nan) time: 0.5054 [2021-03-26 10:58:38 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 790/1251] eta: 0:03:55 lr: 0.000389 loss: 3.2758 (3.1961) grad_norm: 1.5232 (nan) time: 0.5128 [2021-03-26 10:58:43 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 800/1251] eta: 0:03:50 lr: 0.000389 loss: 3.0519 (3.1947) grad_norm: 1.6169 (nan) time: 0.5052 [2021-03-26 10:58:48 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 810/1251] eta: 0:03:44 lr: 0.000389 loss: 3.2840 (3.1934) grad_norm: 1.6274 (nan) time: 0.4994 [2021-03-26 10:58:53 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 820/1251] eta: 0:03:39 lr: 0.000389 loss: 3.1492 (3.1924) grad_norm: 1.6001 (nan) time: 0.5004 [2021-03-26 10:58:58 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 830/1251] eta: 0:03:34 lr: 0.000389 loss: 3.1325 (3.1916) grad_norm: 1.6109 (nan) time: 0.5029 [2021-03-26 10:59:03 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 840/1251] eta: 0:03:29 lr: 0.000389 loss: 3.1747 (3.1912) grad_norm: 1.6168 (nan) time: 0.5030 [2021-03-26 10:59:08 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 850/1251] eta: 0:03:24 lr: 0.000389 loss: 3.1747 (3.1898) grad_norm: 1.6128 (nan) time: 0.4996 [2021-03-26 10:59:13 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 860/1251] eta: 0:03:19 lr: 0.000388 loss: 3.3504 (3.1918) grad_norm: 1.6145 (nan) time: 0.5081 [2021-03-26 10:59:18 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 870/1251] eta: 0:03:14 lr: 0.000388 loss: 3.3920 (3.1936) grad_norm: 1.7354 (nan) time: 0.5067 [2021-03-26 10:59:23 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 880/1251] eta: 0:03:08 lr: 0.000388 loss: 3.5403 (3.1976) grad_norm: 1.6734 (nan) time: 0.4962 [2021-03-26 10:59:28 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 890/1251] eta: 0:03:03 lr: 0.000388 loss: 3.2137 (3.1937) grad_norm: 1.5608 (nan) time: 0.5000 [2021-03-26 10:59:33 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 900/1251] eta: 0:02:58 lr: 0.000388 loss: 3.1969 (3.1952) grad_norm: 1.6987 (nan) time: 0.5016 [2021-03-26 10:59:39 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 910/1251] eta: 0:02:53 lr: 0.000388 loss: 3.4385 (3.1975) grad_norm: 1.6987 (nan) time: 0.5045 [2021-03-26 10:59:44 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 920/1251] eta: 0:02:48 lr: 0.000388 loss: 3.4169 (3.1952) grad_norm: 1.6142 (nan) time: 0.5094 [2021-03-26 10:59:49 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 930/1251] eta: 0:02:43 lr: 0.000388 loss: 3.3452 (3.1963) grad_norm: 1.6264 (nan) time: 0.5101 [2021-03-26 10:59:54 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 940/1251] eta: 0:02:38 lr: 0.000388 loss: 3.3980 (3.1968) grad_norm: 1.5948 (nan) time: 0.5172 [2021-03-26 10:59:59 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 950/1251] eta: 0:02:33 lr: 0.000388 loss: 3.3651 (3.1962) grad_norm: 1.6036 (nan) time: 0.5133 [2021-03-26 11:00:04 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 960/1251] eta: 0:02:28 lr: 0.000388 loss: 3.2113 (3.1958) grad_norm: 1.6077 (nan) time: 0.5077 [2021-03-26 11:00:09 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 970/1251] eta: 0:02:23 lr: 0.000388 loss: 3.2113 (3.1968) grad_norm: 1.6947 (nan) time: 0.5053 [2021-03-26 11:00:14 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 980/1251] eta: 0:02:17 lr: 0.000388 loss: 3.1868 (3.1968) grad_norm: 1.6074 (nan) time: 0.4996 [2021-03-26 11:00:19 swin_small_patch4_window7_224] INFO: Epoch: [172] [ 990/1251] eta: 0:02:12 lr: 0.000388 loss: 3.3200 (3.1981) grad_norm: 1.5808 (nan) time: 0.4996 [2021-03-26 11:00:24 swin_small_patch4_window7_224] INFO: Epoch: [172] [1000/1251] eta: 0:02:07 lr: 0.000388 loss: 3.3441 (3.1981) grad_norm: 1.5640 (nan) time: 0.5075 [2021-03-26 11:00:29 swin_small_patch4_window7_224] INFO: Epoch: [172] [1010/1251] eta: 0:02:02 lr: 0.000388 loss: 3.2966 (3.1995) grad_norm: 1.5656 (nan) time: 0.5066 [2021-03-26 11:00:34 swin_small_patch4_window7_224] INFO: Epoch: [172] [1020/1251] eta: 0:01:57 lr: 0.000388 loss: 3.1683 (3.1982) grad_norm: 1.6371 (nan) time: 0.5041 [2021-03-26 11:00:39 swin_small_patch4_window7_224] INFO: Epoch: [172] [1030/1251] eta: 0:01:52 lr: 0.000388 loss: 3.3215 (3.2001) grad_norm: 1.6376 (nan) time: 0.5103 [2021-03-26 11:00:44 swin_small_patch4_window7_224] INFO: Epoch: [172] [1040/1251] eta: 0:01:47 lr: 0.000388 loss: 3.3877 (3.1988) grad_norm: 1.6707 (nan) time: 0.5057 [2021-03-26 11:00:50 swin_small_patch4_window7_224] INFO: Epoch: [172] [1050/1251] eta: 0:01:42 lr: 0.000388 loss: 3.3237 (3.2006) grad_norm: 1.7663 (nan) time: 0.5077 [2021-03-26 11:00:55 swin_small_patch4_window7_224] INFO: Epoch: [172] [1060/1251] eta: 0:01:37 lr: 0.000388 loss: 3.3583 (3.2006) grad_norm: 1.6727 (nan) time: 0.5106 [2021-03-26 11:01:00 swin_small_patch4_window7_224] INFO: Epoch: [172] [1070/1251] eta: 0:01:32 lr: 0.000388 loss: 3.2030 (3.1997) grad_norm: 1.5977 (nan) time: 0.5003 [2021-03-26 11:01:05 swin_small_patch4_window7_224] INFO: Epoch: [172] [1080/1251] eta: 0:01:26 lr: 0.000388 loss: 3.2444 (3.2005) grad_norm: 1.5993 (nan) time: 0.4972 [2021-03-26 11:01:10 swin_small_patch4_window7_224] INFO: Epoch: [172] [1090/1251] eta: 0:01:21 lr: 0.000388 loss: 3.1311 (3.1996) grad_norm: 1.6064 (nan) time: 0.4977 [2021-03-26 11:01:15 swin_small_patch4_window7_224] INFO: Epoch: [172] [1100/1251] eta: 0:01:16 lr: 0.000388 loss: 3.1273 (3.1999) grad_norm: 1.5858 (nan) time: 0.5015 [2021-03-26 11:01:20 swin_small_patch4_window7_224] INFO: Epoch: [172] [1110/1251] eta: 0:01:11 lr: 0.000387 loss: 3.4186 (3.2005) grad_norm: 1.5518 (nan) time: 0.5065 [2021-03-26 11:01:25 swin_small_patch4_window7_224] INFO: Epoch: [172] [1120/1251] eta: 0:01:06 lr: 0.000387 loss: 3.2761 (3.1997) grad_norm: 1.6068 (nan) time: 0.5057 [2021-03-26 11:01:30 swin_small_patch4_window7_224] INFO: Epoch: [172] [1130/1251] eta: 0:01:01 lr: 0.000387 loss: 3.1385 (3.1983) grad_norm: 1.5869 (nan) time: 0.5022 [2021-03-26 11:01:35 swin_small_patch4_window7_224] INFO: Epoch: [172] [1140/1251] eta: 0:00:56 lr: 0.000387 loss: 3.3275 (3.1993) grad_norm: 1.5459 (nan) time: 0.4968 [2021-03-26 11:01:40 swin_small_patch4_window7_224] INFO: Epoch: [172] [1150/1251] eta: 0:00:51 lr: 0.000387 loss: 3.3477 (3.1987) grad_norm: 1.5729 (nan) time: 0.4961 [2021-03-26 11:01:45 swin_small_patch4_window7_224] INFO: Epoch: [172] [1160/1251] eta: 0:00:46 lr: 0.000387 loss: 3.2716 (3.2008) grad_norm: 1.5729 (nan) time: 0.4962 [2021-03-26 11:01:50 swin_small_patch4_window7_224] INFO: Epoch: [172] [1170/1251] eta: 0:00:41 lr: 0.000387 loss: 3.2273 (3.2004) grad_norm: 1.5569 (nan) time: 0.5021 [2021-03-26 11:01:55 swin_small_patch4_window7_224] INFO: Epoch: [172] [1180/1251] eta: 0:00:36 lr: 0.000387 loss: 3.1780 (3.1978) grad_norm: 1.5703 (nan) time: 0.5057 [2021-03-26 11:02:00 swin_small_patch4_window7_224] INFO: Epoch: [172] [1190/1251] eta: 0:00:30 lr: 0.000387 loss: 3.0271 (3.1975) grad_norm: 1.5951 (nan) time: 0.5026 [2021-03-26 11:02:05 swin_small_patch4_window7_224] INFO: Epoch: [172] [1200/1251] eta: 0:00:25 lr: 0.000387 loss: 3.3217 (3.1995) grad_norm: 1.5931 (nan) time: 0.5027 [2021-03-26 11:02:10 swin_small_patch4_window7_224] INFO: Epoch: [172] [1210/1251] eta: 0:00:20 lr: 0.000387 loss: 3.3945 (3.1989) grad_norm: 1.5992 (nan) time: 0.5052 [2021-03-26 11:02:15 swin_small_patch4_window7_224] INFO: Epoch: [172] [1220/1251] eta: 0:00:15 lr: 0.000387 loss: 3.3594 (3.1999) grad_norm: 1.6193 (nan) time: 0.5006 [2021-03-26 11:02:20 swin_small_patch4_window7_224] INFO: Epoch: [172] [1230/1251] eta: 0:00:10 lr: 0.000387 loss: 3.2783 (3.2004) grad_norm: 1.6193 (nan) time: 0.4982 [2021-03-26 11:02:25 swin_small_patch4_window7_224] INFO: Epoch: [172] [1240/1251] eta: 0:00:05 lr: 0.000387 loss: 3.2989 (3.2013) grad_norm: 1.5910 (nan) time: 0.5041 [2021-03-26 11:02:30 swin_small_patch4_window7_224] INFO: Epoch: [172] [1250/1251] eta: 0:00:00 lr: 0.000387 loss: 3.0191 (3.1998) grad_norm: 1.5599 (nan) time: 0.5065 [2021-03-26 11:02:40 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:03:32 loss: 1.0620 (1.0620) acc1: 73.4375 (73.4375) acc5: 96.8750 (96.8750) [2021-03-26 11:02:42 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:23 loss: 0.7927 (0.8580) acc1: 81.2500 (78.4091) acc5: 95.3125 (94.7443) [2021-03-26 11:02:44 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.8559 (0.8933) acc1: 78.1250 (78.2738) acc5: 95.3125 (94.6429) [2021-03-26 11:02:46 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8652 (0.8760) acc1: 78.1250 (78.8306) acc5: 93.7500 (94.8085) [2021-03-26 11:02:47 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8652 (0.8746) acc1: 78.1250 (78.7729) acc5: 95.3125 (94.9695) [2021-03-26 11:02:48 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8878 (0.8874) acc1: 76.5625 (78.1120) acc5: 95.3125 (95.0400) [2021-03-26 11:02:57 swin_small_patch4_window7_224] INFO: * Acc@1 79.130 Acc@5 94.932 loss 0.878 [2021-03-26 11:02:57 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.1% [2021-03-26 11:02:57 swin_small_patch4_window7_224] INFO: Max accuracy: 79.40% [2021-03-26 11:03:01 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 0/1251] eta: 1:24:09 lr: 0.000387 loss: 3.5691 (3.5691) grad_norm: 1.7400 (1.7400) time: 4.0367 [2021-03-26 11:03:06 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 10/1251] eta: 0:17:38 lr: 0.000387 loss: 3.1168 (3.1251) grad_norm: 1.6828 (1.6826) time: 0.8528 [2021-03-26 11:03:11 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 20/1251] eta: 0:14:01 lr: 0.000387 loss: 3.1088 (3.1247) grad_norm: 1.6232 (1.6390) time: 0.5157 [2021-03-26 11:03:16 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 30/1251] eta: 0:12:40 lr: 0.000387 loss: 3.1884 (3.2059) grad_norm: 1.5990 (1.6566) time: 0.4960 [2021-03-26 11:03:22 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 40/1251] eta: 0:12:05 lr: 0.000387 loss: 3.2070 (3.1837) grad_norm: 1.7372 (1.7130) time: 0.5105 [2021-03-26 11:03:27 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 50/1251] eta: 0:11:37 lr: 0.000387 loss: 3.2070 (3.2009) grad_norm: 1.6708 (1.7076) time: 0.5149 [2021-03-26 11:03:32 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 60/1251] eta: 0:11:15 lr: 0.000387 loss: 3.3233 (3.1613) grad_norm: 1.6009 (1.6990) time: 0.5025 [2021-03-26 11:03:37 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 70/1251] eta: 0:10:59 lr: 0.000387 loss: 3.3870 (3.1925) grad_norm: 1.6540 (1.7101) time: 0.5015 [2021-03-26 11:03:42 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 80/1251] eta: 0:10:46 lr: 0.000387 loss: 3.4450 (3.2085) grad_norm: 1.7075 (1.7056) time: 0.5045 [2021-03-26 11:03:47 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 90/1251] eta: 0:10:35 lr: 0.000387 loss: 3.4138 (3.2153) grad_norm: 1.6910 (1.7050) time: 0.5085 [2021-03-26 11:03:52 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 100/1251] eta: 0:10:25 lr: 0.000387 loss: 3.0776 (3.1795) grad_norm: 1.6400 (1.6939) time: 0.5104 [2021-03-26 11:03:57 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 110/1251] eta: 0:10:17 lr: 0.000386 loss: 3.0259 (3.1903) grad_norm: 1.5663 (1.6856) time: 0.5130 [2021-03-26 11:04:02 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 120/1251] eta: 0:10:08 lr: 0.000386 loss: 3.1222 (3.1787) grad_norm: 1.5248 (1.6731) time: 0.5077 [2021-03-26 11:04:07 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 130/1251] eta: 0:10:00 lr: 0.000386 loss: 3.2548 (3.1996) grad_norm: 1.5247 (1.6649) time: 0.5042 [2021-03-26 11:04:12 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 140/1251] eta: 0:09:52 lr: 0.000386 loss: 3.3300 (3.2040) grad_norm: 1.5320 (1.6573) time: 0.5049 [2021-03-26 11:04:17 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 150/1251] eta: 0:09:46 lr: 0.000386 loss: 3.2509 (3.2013) grad_norm: 1.5340 (1.6512) time: 0.5155 [2021-03-26 11:04:23 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 160/1251] eta: 0:09:39 lr: 0.000386 loss: 3.1053 (3.1969) grad_norm: 1.6184 (1.6475) time: 0.5169 [2021-03-26 11:04:28 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 170/1251] eta: 0:09:32 lr: 0.000386 loss: 3.1245 (3.1892) grad_norm: 1.5529 (1.6435) time: 0.5067 [2021-03-26 11:04:33 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 180/1251] eta: 0:09:25 lr: 0.000386 loss: 3.2892 (3.2030) grad_norm: 1.5685 (1.6428) time: 0.5072 [2021-03-26 11:04:38 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 190/1251] eta: 0:09:19 lr: 0.000386 loss: 3.6178 (3.2134) grad_norm: 1.6088 (1.6417) time: 0.5056 [2021-03-26 11:04:43 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 200/1251] eta: 0:09:12 lr: 0.000386 loss: 3.4539 (3.2161) grad_norm: 1.5880 (1.6373) time: 0.5036 [2021-03-26 11:04:48 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 210/1251] eta: 0:09:06 lr: 0.000386 loss: 3.4483 (3.2318) grad_norm: 1.5953 (1.6358) time: 0.5027 [2021-03-26 11:04:53 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 220/1251] eta: 0:09:00 lr: 0.000386 loss: 3.3787 (3.2284) grad_norm: 1.6153 (1.6357) time: 0.5028 [2021-03-26 11:04:58 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 230/1251] eta: 0:08:54 lr: 0.000386 loss: 3.1570 (3.2330) grad_norm: 1.5917 (1.6315) time: 0.5036 [2021-03-26 11:05:03 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 240/1251] eta: 0:08:48 lr: 0.000386 loss: 3.4100 (3.2315) grad_norm: 1.5526 (1.6329) time: 0.5092 [2021-03-26 11:05:08 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 250/1251] eta: 0:08:42 lr: 0.000386 loss: 3.4285 (3.2393) grad_norm: 1.6138 (1.6328) time: 0.5075 [2021-03-26 11:05:13 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 260/1251] eta: 0:08:36 lr: 0.000386 loss: 3.3321 (3.2337) grad_norm: 1.5214 (1.6290) time: 0.5013 [2021-03-26 11:05:18 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 270/1251] eta: 0:08:30 lr: 0.000386 loss: 3.3894 (3.2397) grad_norm: 1.5583 (1.6273) time: 0.5044 [2021-03-26 11:05:23 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 280/1251] eta: 0:08:24 lr: 0.000386 loss: 3.3894 (3.2341) grad_norm: 1.6148 (1.6276) time: 0.5043 [2021-03-26 11:05:28 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 290/1251] eta: 0:08:18 lr: 0.000386 loss: 3.0173 (3.2245) grad_norm: 1.6441 (1.6287) time: 0.5015 [2021-03-26 11:05:33 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 300/1251] eta: 0:08:12 lr: 0.000386 loss: 3.1694 (3.2312) grad_norm: 1.6702 (1.6331) time: 0.4971 [2021-03-26 11:05:38 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 310/1251] eta: 0:08:07 lr: 0.000386 loss: 3.2581 (3.2274) grad_norm: 1.7611 (1.6375) time: 0.5020 [2021-03-26 11:05:43 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 320/1251] eta: 0:08:02 lr: 0.000386 loss: 3.3073 (3.2324) grad_norm: 1.5622 (1.6349) time: 0.5109 [2021-03-26 11:05:48 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 330/1251] eta: 0:07:56 lr: 0.000386 loss: 3.3969 (3.2325) grad_norm: 1.5368 (1.6341) time: 0.5032 [2021-03-26 11:05:53 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 340/1251] eta: 0:07:50 lr: 0.000386 loss: 3.4769 (3.2364) grad_norm: 1.6359 (1.6359) time: 0.4976 [2021-03-26 11:05:58 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 350/1251] eta: 0:07:45 lr: 0.000386 loss: 3.4947 (3.2390) grad_norm: 1.6614 (1.6363) time: 0.5007 [2021-03-26 11:06:03 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 360/1251] eta: 0:07:39 lr: 0.000385 loss: 3.0994 (3.2259) grad_norm: 1.6017 (1.6353) time: 0.5024 [2021-03-26 11:06:08 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 370/1251] eta: 0:07:34 lr: 0.000385 loss: 3.0311 (3.2250) grad_norm: 1.5914 (1.6353) time: 0.5006 [2021-03-26 11:06:13 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 380/1251] eta: 0:07:28 lr: 0.000385 loss: 3.0927 (3.2183) grad_norm: 1.6278 (1.6369) time: 0.4983 [2021-03-26 11:06:18 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 390/1251] eta: 0:07:23 lr: 0.000385 loss: 3.0315 (3.2191) grad_norm: 1.6368 (1.6368) time: 0.5005 [2021-03-26 11:06:23 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 400/1251] eta: 0:07:17 lr: 0.000385 loss: 3.3075 (3.2212) grad_norm: 1.5637 (1.6358) time: 0.5024 [2021-03-26 11:06:28 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 410/1251] eta: 0:07:12 lr: 0.000385 loss: 3.3543 (3.2245) grad_norm: 1.6663 (1.6402) time: 0.4983 [2021-03-26 11:06:33 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 420/1251] eta: 0:07:07 lr: 0.000385 loss: 3.4195 (3.2241) grad_norm: 1.7160 (1.6416) time: 0.5050 [2021-03-26 11:06:39 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 430/1251] eta: 0:07:01 lr: 0.000385 loss: 3.2183 (3.2239) grad_norm: 1.6238 (1.6404) time: 0.5132 [2021-03-26 11:06:44 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 440/1251] eta: 0:06:56 lr: 0.000385 loss: 3.1778 (3.2233) grad_norm: 1.5912 (1.6386) time: 0.5060 [2021-03-26 11:06:49 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 450/1251] eta: 0:06:51 lr: 0.000385 loss: 3.2545 (3.2243) grad_norm: 1.5912 (1.6389) time: 0.5043 [2021-03-26 11:06:54 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 460/1251] eta: 0:06:45 lr: 0.000385 loss: 3.1634 (3.2202) grad_norm: 1.5731 (1.6371) time: 0.5017 [2021-03-26 11:06:59 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 470/1251] eta: 0:06:40 lr: 0.000385 loss: 3.1417 (3.2190) grad_norm: 1.5231 (1.6344) time: 0.4956 [2021-03-26 11:07:04 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 480/1251] eta: 0:06:35 lr: 0.000385 loss: 3.2277 (3.2174) grad_norm: 1.5231 (1.6335) time: 0.5010 [2021-03-26 11:07:09 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 490/1251] eta: 0:06:30 lr: 0.000385 loss: 3.2387 (3.2191) grad_norm: 1.5585 (1.6350) time: 0.5105 [2021-03-26 11:07:14 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 500/1251] eta: 0:06:24 lr: 0.000385 loss: 3.2387 (3.2206) grad_norm: 1.5386 (1.6345) time: 0.5098 [2021-03-26 11:07:19 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 510/1251] eta: 0:06:19 lr: 0.000385 loss: 3.3009 (3.2226) grad_norm: 1.6584 (1.6361) time: 0.5032 [2021-03-26 11:07:24 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 520/1251] eta: 0:06:14 lr: 0.000385 loss: 3.3742 (3.2226) grad_norm: 1.6868 (1.6361) time: 0.5062 [2021-03-26 11:07:29 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 530/1251] eta: 0:06:09 lr: 0.000385 loss: 3.1539 (3.2220) grad_norm: 1.6400 (1.6365) time: 0.5041 [2021-03-26 11:07:34 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 540/1251] eta: 0:06:03 lr: 0.000385 loss: 3.0802 (3.2196) grad_norm: 1.6100 (1.6352) time: 0.5039 [2021-03-26 11:07:39 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 550/1251] eta: 0:05:58 lr: 0.000385 loss: 3.3450 (3.2219) grad_norm: 1.5867 (1.6346) time: 0.5128 [2021-03-26 11:07:44 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 560/1251] eta: 0:05:53 lr: 0.000385 loss: 3.3450 (3.2214) grad_norm: 1.5710 (1.6329) time: 0.5083 [2021-03-26 11:07:49 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 570/1251] eta: 0:05:48 lr: 0.000385 loss: 3.2023 (3.2235) grad_norm: 1.6427 (1.6336) time: 0.5014 [2021-03-26 11:07:54 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 580/1251] eta: 0:05:43 lr: 0.000385 loss: 3.5102 (3.2273) grad_norm: 1.6801 (1.6340) time: 0.5038 [2021-03-26 11:07:59 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 590/1251] eta: 0:05:38 lr: 0.000385 loss: 3.4228 (3.2285) grad_norm: 1.5722 (1.6328) time: 0.5091 [2021-03-26 11:08:04 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 600/1251] eta: 0:05:32 lr: 0.000385 loss: 3.1724 (3.2260) grad_norm: 1.5722 (1.6341) time: 0.5107 [2021-03-26 11:08:09 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 610/1251] eta: 0:05:27 lr: 0.000384 loss: 3.0988 (3.2274) grad_norm: 1.6169 (1.6335) time: 0.5047 [2021-03-26 11:08:14 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 620/1251] eta: 0:05:22 lr: 0.000384 loss: 3.4372 (3.2294) grad_norm: 1.6251 (1.6356) time: 0.4997 [2021-03-26 11:08:20 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 630/1251] eta: 0:05:17 lr: 0.000384 loss: 3.4889 (3.2306) grad_norm: 1.7232 (1.6363) time: 0.5035 [2021-03-26 11:08:25 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 640/1251] eta: 0:05:12 lr: 0.000384 loss: 3.4889 (3.2332) grad_norm: 1.6560 (1.6363) time: 0.5046 [2021-03-26 11:08:30 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 650/1251] eta: 0:05:06 lr: 0.000384 loss: 3.4506 (3.2342) grad_norm: 1.6560 (1.6355) time: 0.4987 [2021-03-26 11:08:35 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 660/1251] eta: 0:05:01 lr: 0.000384 loss: 3.2858 (3.2318) grad_norm: 1.5515 (1.6365) time: 0.5015 [2021-03-26 11:08:40 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 670/1251] eta: 0:04:56 lr: 0.000384 loss: 3.2858 (3.2341) grad_norm: 1.5515 (1.6391) time: 0.5040 [2021-03-26 11:08:45 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 680/1251] eta: 0:04:51 lr: 0.000384 loss: 3.2799 (3.2327) grad_norm: 1.5422 (1.6383) time: 0.4977 [2021-03-26 11:08:50 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 690/1251] eta: 0:04:46 lr: 0.000384 loss: 3.2712 (3.2340) grad_norm: 1.6035 (1.6386) time: 0.5022 [2021-03-26 11:08:55 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 700/1251] eta: 0:04:40 lr: 0.000384 loss: 3.3809 (3.2338) grad_norm: 1.6769 (nan) time: 0.5004 [2021-03-26 11:09:00 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 710/1251] eta: 0:04:35 lr: 0.000384 loss: 3.2562 (3.2323) grad_norm: 1.5873 (nan) time: 0.5037 [2021-03-26 11:09:05 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 720/1251] eta: 0:04:30 lr: 0.000384 loss: 3.2947 (3.2341) grad_norm: 1.5685 (nan) time: 0.5067 [2021-03-26 11:09:10 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 730/1251] eta: 0:04:25 lr: 0.000384 loss: 3.2947 (3.2297) grad_norm: 1.5966 (nan) time: 0.5064 [2021-03-26 11:09:15 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 740/1251] eta: 0:04:20 lr: 0.000384 loss: 3.2811 (3.2285) grad_norm: 1.5834 (nan) time: 0.5195 [2021-03-26 11:09:20 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 750/1251] eta: 0:04:15 lr: 0.000384 loss: 3.3635 (3.2279) grad_norm: 1.6045 (nan) time: 0.5092 [2021-03-26 11:09:25 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 760/1251] eta: 0:04:10 lr: 0.000384 loss: 3.2357 (3.2258) grad_norm: 1.6504 (nan) time: 0.4999 [2021-03-26 11:09:30 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 770/1251] eta: 0:04:05 lr: 0.000384 loss: 3.1159 (3.2244) grad_norm: 1.6504 (nan) time: 0.5016 [2021-03-26 11:09:35 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 780/1251] eta: 0:04:00 lr: 0.000384 loss: 3.1953 (3.2274) grad_norm: 1.6226 (nan) time: 0.5045 [2021-03-26 11:09:40 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 790/1251] eta: 0:03:55 lr: 0.000384 loss: 3.1903 (3.2239) grad_norm: 1.6226 (nan) time: 0.5142 [2021-03-26 11:09:45 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 800/1251] eta: 0:03:49 lr: 0.000384 loss: 3.1960 (3.2246) grad_norm: 1.5616 (nan) time: 0.5151 [2021-03-26 11:09:50 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 810/1251] eta: 0:03:44 lr: 0.000384 loss: 3.3761 (3.2240) grad_norm: 1.5616 (nan) time: 0.5057 [2021-03-26 11:09:56 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 820/1251] eta: 0:03:39 lr: 0.000384 loss: 3.4337 (3.2258) grad_norm: 1.5883 (nan) time: 0.5047 [2021-03-26 11:10:01 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 830/1251] eta: 0:03:34 lr: 0.000384 loss: 3.4616 (3.2282) grad_norm: 1.5883 (nan) time: 0.5067 [2021-03-26 11:10:06 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 840/1251] eta: 0:03:29 lr: 0.000384 loss: 3.5272 (3.2297) grad_norm: 1.6051 (nan) time: 0.5029 [2021-03-26 11:10:11 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 850/1251] eta: 0:03:24 lr: 0.000384 loss: 3.4757 (3.2334) grad_norm: 1.6006 (nan) time: 0.5052 [2021-03-26 11:10:16 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 860/1251] eta: 0:03:19 lr: 0.000383 loss: 3.4639 (3.2331) grad_norm: 1.6072 (nan) time: 0.5071 [2021-03-26 11:10:21 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 870/1251] eta: 0:03:14 lr: 0.000383 loss: 3.2361 (3.2327) grad_norm: 1.5553 (nan) time: 0.5150 [2021-03-26 11:10:26 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 880/1251] eta: 0:03:09 lr: 0.000383 loss: 3.2362 (3.2328) grad_norm: 1.5503 (nan) time: 0.5129 [2021-03-26 11:10:31 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 890/1251] eta: 0:03:03 lr: 0.000383 loss: 3.3225 (3.2327) grad_norm: 1.6056 (nan) time: 0.5012 [2021-03-26 11:10:36 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 900/1251] eta: 0:02:58 lr: 0.000383 loss: 3.3515 (3.2335) grad_norm: 1.5667 (nan) time: 0.5065 [2021-03-26 11:10:41 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 910/1251] eta: 0:02:53 lr: 0.000383 loss: 3.2480 (3.2339) grad_norm: 1.5691 (nan) time: 0.5124 [2021-03-26 11:10:46 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 920/1251] eta: 0:02:48 lr: 0.000383 loss: 3.2474 (3.2341) grad_norm: 1.5812 (nan) time: 0.5035 [2021-03-26 11:10:51 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 930/1251] eta: 0:02:43 lr: 0.000383 loss: 3.3164 (3.2354) grad_norm: 1.6392 (nan) time: 0.5052 [2021-03-26 11:10:56 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 940/1251] eta: 0:02:38 lr: 0.000383 loss: 3.4974 (3.2387) grad_norm: 1.6639 (nan) time: 0.5100 [2021-03-26 11:11:02 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 950/1251] eta: 0:02:33 lr: 0.000383 loss: 3.6150 (3.2406) grad_norm: 1.5820 (nan) time: 0.5044 [2021-03-26 11:11:07 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 960/1251] eta: 0:02:28 lr: 0.000383 loss: 3.5436 (3.2398) grad_norm: 1.5926 (nan) time: 0.5087 [2021-03-26 11:11:12 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 970/1251] eta: 0:02:23 lr: 0.000383 loss: 3.2496 (3.2404) grad_norm: 1.5926 (nan) time: 0.5086 [2021-03-26 11:11:17 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 980/1251] eta: 0:02:17 lr: 0.000383 loss: 3.3379 (3.2395) grad_norm: 1.5568 (nan) time: 0.5009 [2021-03-26 11:11:22 swin_small_patch4_window7_224] INFO: Epoch: [173] [ 990/1251] eta: 0:02:12 lr: 0.000383 loss: 3.0879 (3.2384) grad_norm: 1.6247 (nan) time: 0.5029 [2021-03-26 11:11:27 swin_small_patch4_window7_224] INFO: Epoch: [173] [1000/1251] eta: 0:02:07 lr: 0.000383 loss: 3.2028 (3.2412) grad_norm: 1.6053 (nan) time: 0.5068 [2021-03-26 11:11:32 swin_small_patch4_window7_224] INFO: Epoch: [173] [1010/1251] eta: 0:02:02 lr: 0.000383 loss: 3.5181 (3.2418) grad_norm: 1.5779 (nan) time: 0.5020 [2021-03-26 11:11:37 swin_small_patch4_window7_224] INFO: Epoch: [173] [1020/1251] eta: 0:01:57 lr: 0.000383 loss: 3.4392 (3.2423) grad_norm: 1.5690 (nan) time: 0.4990 [2021-03-26 11:11:42 swin_small_patch4_window7_224] INFO: Epoch: [173] [1030/1251] eta: 0:01:52 lr: 0.000383 loss: 3.3862 (3.2416) grad_norm: 1.5705 (nan) time: 0.5022 [2021-03-26 11:11:47 swin_small_patch4_window7_224] INFO: Epoch: [173] [1040/1251] eta: 0:01:47 lr: 0.000383 loss: 3.1346 (3.2411) grad_norm: 1.6207 (nan) time: 0.5014 [2021-03-26 11:11:52 swin_small_patch4_window7_224] INFO: Epoch: [173] [1050/1251] eta: 0:01:42 lr: 0.000383 loss: 3.1147 (3.2399) grad_norm: 1.6505 (nan) time: 0.5109 [2021-03-26 11:11:57 swin_small_patch4_window7_224] INFO: Epoch: [173] [1060/1251] eta: 0:01:37 lr: 0.000383 loss: 3.1147 (3.2388) grad_norm: 1.5867 (nan) time: 0.5216 [2021-03-26 11:12:02 swin_small_patch4_window7_224] INFO: Epoch: [173] [1070/1251] eta: 0:01:32 lr: 0.000383 loss: 3.1213 (3.2383) grad_norm: 1.5667 (nan) time: 0.5069 [2021-03-26 11:12:07 swin_small_patch4_window7_224] INFO: Epoch: [173] [1080/1251] eta: 0:01:27 lr: 0.000383 loss: 3.2132 (3.2377) grad_norm: 1.6627 (nan) time: 0.5001 [2021-03-26 11:12:12 swin_small_patch4_window7_224] INFO: Epoch: [173] [1090/1251] eta: 0:01:21 lr: 0.000383 loss: 3.2555 (3.2383) grad_norm: 1.6530 (nan) time: 0.5016 [2021-03-26 11:12:17 swin_small_patch4_window7_224] INFO: Epoch: [173] [1100/1251] eta: 0:01:16 lr: 0.000383 loss: 3.2024 (3.2358) grad_norm: 1.6530 (nan) time: 0.4969 [2021-03-26 11:12:22 swin_small_patch4_window7_224] INFO: Epoch: [173] [1110/1251] eta: 0:01:11 lr: 0.000382 loss: 3.2744 (3.2352) grad_norm: 1.6446 (nan) time: 0.5027 [2021-03-26 11:12:27 swin_small_patch4_window7_224] INFO: Epoch: [173] [1120/1251] eta: 0:01:06 lr: 0.000382 loss: 3.3003 (3.2340) grad_norm: 1.6073 (nan) time: 0.5100 [2021-03-26 11:12:32 swin_small_patch4_window7_224] INFO: Epoch: [173] [1130/1251] eta: 0:01:01 lr: 0.000382 loss: 3.2154 (3.2323) grad_norm: 1.6073 (nan) time: 0.5067 [2021-03-26 11:12:38 swin_small_patch4_window7_224] INFO: Epoch: [173] [1140/1251] eta: 0:00:56 lr: 0.000382 loss: 3.2373 (3.2341) grad_norm: 1.6062 (nan) time: 0.5048 [2021-03-26 11:12:42 swin_small_patch4_window7_224] INFO: Epoch: [173] [1150/1251] eta: 0:00:51 lr: 0.000382 loss: 3.3675 (3.2345) grad_norm: 1.5702 (nan) time: 0.5014 [2021-03-26 11:12:47 swin_small_patch4_window7_224] INFO: Epoch: [173] [1160/1251] eta: 0:00:46 lr: 0.000382 loss: 3.2333 (3.2318) grad_norm: 1.5878 (nan) time: 0.4964 [2021-03-26 11:12:52 swin_small_patch4_window7_224] INFO: Epoch: [173] [1170/1251] eta: 0:00:41 lr: 0.000382 loss: 3.1332 (3.2324) grad_norm: 1.6249 (nan) time: 0.4985 [2021-03-26 11:12:58 swin_small_patch4_window7_224] INFO: Epoch: [173] [1180/1251] eta: 0:00:36 lr: 0.000382 loss: 3.2263 (3.2310) grad_norm: 1.6452 (nan) time: 0.5087 [2021-03-26 11:13:03 swin_small_patch4_window7_224] INFO: Epoch: [173] [1190/1251] eta: 0:00:31 lr: 0.000382 loss: 3.3308 (3.2345) grad_norm: 1.6452 (nan) time: 0.5127 [2021-03-26 11:13:08 swin_small_patch4_window7_224] INFO: Epoch: [173] [1200/1251] eta: 0:00:25 lr: 0.000382 loss: 3.5590 (3.2345) grad_norm: 1.6540 (nan) time: 0.5029 [2021-03-26 11:13:13 swin_small_patch4_window7_224] INFO: Epoch: [173] [1210/1251] eta: 0:00:20 lr: 0.000382 loss: 3.1396 (3.2333) grad_norm: 1.6614 (nan) time: 0.4969 [2021-03-26 11:13:18 swin_small_patch4_window7_224] INFO: Epoch: [173] [1220/1251] eta: 0:00:15 lr: 0.000382 loss: 3.3268 (3.2340) grad_norm: 1.6508 (nan) time: 0.5001 [2021-03-26 11:13:23 swin_small_patch4_window7_224] INFO: Epoch: [173] [1230/1251] eta: 0:00:10 lr: 0.000382 loss: 3.4060 (3.2354) grad_norm: 1.6283 (nan) time: 0.5021 [2021-03-26 11:13:28 swin_small_patch4_window7_224] INFO: Epoch: [173] [1240/1251] eta: 0:00:05 lr: 0.000382 loss: 3.4289 (3.2357) grad_norm: 1.5650 (nan) time: 0.5052 [2021-03-26 11:13:33 swin_small_patch4_window7_224] INFO: Epoch: [173] [1250/1251] eta: 0:00:00 lr: 0.000382 loss: 3.4648 (3.2368) grad_norm: 1.5650 (nan) time: 0.5085 [2021-03-26 11:13:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:52 loss: 0.9154 (0.9154) acc1: 82.8125 (82.8125) acc5: 92.1875 (92.1875) [2021-03-26 11:13:43 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7896 (0.7978) acc1: 79.6875 (81.1080) acc5: 96.8750 (96.4489) [2021-03-26 11:13:46 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8043 (0.8453) acc1: 78.1250 (79.8363) acc5: 96.8750 (95.4613) [2021-03-26 11:13:47 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8170 (0.8375) acc1: 79.6875 (80.2923) acc5: 93.7500 (95.4133) [2021-03-26 11:13:49 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8114 (0.8442) acc1: 81.2500 (79.8780) acc5: 93.7500 (95.0457) [2021-03-26 11:13:50 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9400 (0.8719) acc1: 78.1250 (78.9440) acc5: 93.7500 (94.9760) [2021-03-26 11:14:01 swin_small_patch4_window7_224] INFO: * Acc@1 79.544 Acc@5 94.978 loss 0.857 [2021-03-26 11:14:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-26 11:14:01 swin_small_patch4_window7_224] INFO: Max accuracy: 79.54% [2021-03-26 11:14:05 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 0/1251] eta: 1:28:45 lr: 0.000382 loss: 2.7271 (2.7271) grad_norm: 1.4974 (1.4974) time: 4.2566 [2021-03-26 11:14:10 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 10/1251] eta: 0:17:53 lr: 0.000382 loss: 3.4030 (3.3101) grad_norm: 1.5611 (1.6040) time: 0.8646 [2021-03-26 11:14:15 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 20/1251] eta: 0:14:11 lr: 0.000382 loss: 3.3268 (3.1551) grad_norm: 1.6439 (1.6551) time: 0.5131 [2021-03-26 11:14:20 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 30/1251] eta: 0:12:50 lr: 0.000382 loss: 3.1271 (3.1860) grad_norm: 1.5980 (1.6263) time: 0.5029 [2021-03-26 11:14:25 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 40/1251] eta: 0:12:06 lr: 0.000382 loss: 3.4109 (3.2277) grad_norm: 1.5193 (1.6104) time: 0.5041 [2021-03-26 11:14:30 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 50/1251] eta: 0:11:38 lr: 0.000382 loss: 3.3184 (3.2307) grad_norm: 1.5193 (1.5987) time: 0.5045 [2021-03-26 11:14:35 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 60/1251] eta: 0:11:16 lr: 0.000382 loss: 3.1150 (3.1598) grad_norm: 1.5027 (1.5899) time: 0.5037 [2021-03-26 11:14:40 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 70/1251] eta: 0:11:00 lr: 0.000382 loss: 2.8388 (3.1227) grad_norm: 1.5175 (1.6010) time: 0.5026 [2021-03-26 11:14:45 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 80/1251] eta: 0:10:47 lr: 0.000382 loss: 3.0137 (3.1471) grad_norm: 1.5928 (1.6076) time: 0.5059 [2021-03-26 11:14:51 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 90/1251] eta: 0:10:37 lr: 0.000382 loss: 3.2317 (3.1497) grad_norm: 1.5564 (1.6000) time: 0.5133 [2021-03-26 11:14:56 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 100/1251] eta: 0:10:27 lr: 0.000381 loss: 3.2317 (3.1615) grad_norm: 1.5186 (1.5978) time: 0.5114 [2021-03-26 11:15:01 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 110/1251] eta: 0:10:18 lr: 0.000381 loss: 3.2466 (3.1589) grad_norm: 1.5186 (1.5944) time: 0.5086 [2021-03-26 11:15:06 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 120/1251] eta: 0:10:10 lr: 0.000381 loss: 3.1936 (3.1565) grad_norm: 1.5111 (1.5930) time: 0.5151 [2021-03-26 11:15:11 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 130/1251] eta: 0:10:02 lr: 0.000381 loss: 3.2883 (3.1616) grad_norm: 1.5462 (1.5941) time: 0.5122 [2021-03-26 11:15:16 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 140/1251] eta: 0:09:53 lr: 0.000381 loss: 3.3089 (3.1661) grad_norm: 1.6068 (1.6004) time: 0.5025 [2021-03-26 11:15:21 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 150/1251] eta: 0:09:46 lr: 0.000381 loss: 3.3089 (3.1671) grad_norm: 1.5711 (1.5979) time: 0.5024 [2021-03-26 11:15:26 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 160/1251] eta: 0:09:39 lr: 0.000381 loss: 3.4022 (3.1787) grad_norm: 1.5169 (1.5963) time: 0.5042 [2021-03-26 11:15:31 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 170/1251] eta: 0:09:32 lr: 0.000381 loss: 3.3840 (3.1883) grad_norm: 1.5713 (1.5968) time: 0.5059 [2021-03-26 11:15:36 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 180/1251] eta: 0:09:26 lr: 0.000381 loss: 3.2900 (3.1893) grad_norm: 1.5499 (1.5969) time: 0.5133 [2021-03-26 11:15:41 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 190/1251] eta: 0:09:19 lr: 0.000381 loss: 3.2900 (3.1862) grad_norm: 1.5605 (1.6014) time: 0.5067 [2021-03-26 11:15:46 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 200/1251] eta: 0:09:12 lr: 0.000381 loss: 3.3198 (3.1924) grad_norm: 1.6930 (1.6056) time: 0.5001 [2021-03-26 11:15:51 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 210/1251] eta: 0:09:06 lr: 0.000381 loss: 3.4193 (3.2082) grad_norm: 1.6784 (1.6093) time: 0.5038 [2021-03-26 11:15:56 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 220/1251] eta: 0:09:00 lr: 0.000381 loss: 3.3417 (3.2078) grad_norm: 1.6079 (1.6088) time: 0.5031 [2021-03-26 11:16:02 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 230/1251] eta: 0:08:54 lr: 0.000381 loss: 3.1083 (3.1904) grad_norm: 1.5542 (1.6039) time: 0.5064 [2021-03-26 11:16:07 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 240/1251] eta: 0:08:48 lr: 0.000381 loss: 3.2061 (3.1993) grad_norm: 1.5507 (1.6031) time: 0.5102 [2021-03-26 11:16:12 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 250/1251] eta: 0:08:42 lr: 0.000381 loss: 3.4361 (3.2067) grad_norm: 1.5860 (1.6029) time: 0.5080 [2021-03-26 11:16:17 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 260/1251] eta: 0:08:36 lr: 0.000381 loss: 3.3817 (3.2069) grad_norm: 1.5908 (1.6044) time: 0.5027 [2021-03-26 11:16:22 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 270/1251] eta: 0:08:30 lr: 0.000381 loss: 3.3817 (3.2082) grad_norm: 1.5771 (1.6046) time: 0.4995 [2021-03-26 11:16:27 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 280/1251] eta: 0:08:24 lr: 0.000381 loss: 3.3906 (3.2073) grad_norm: 1.5902 (1.6073) time: 0.5039 [2021-03-26 11:16:32 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 290/1251] eta: 0:08:18 lr: 0.000381 loss: 3.3086 (3.2097) grad_norm: 1.5902 (1.6077) time: 0.5009 [2021-03-26 11:16:37 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 300/1251] eta: 0:08:13 lr: 0.000381 loss: 3.1602 (3.2032) grad_norm: 1.6246 (1.6096) time: 0.5009 [2021-03-26 11:16:42 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 310/1251] eta: 0:08:08 lr: 0.000381 loss: 3.3256 (3.2078) grad_norm: 1.6289 (1.6103) time: 0.5110 [2021-03-26 11:16:47 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 320/1251] eta: 0:08:02 lr: 0.000381 loss: 3.3256 (3.2057) grad_norm: 1.6444 (1.6143) time: 0.5107 [2021-03-26 11:16:52 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 330/1251] eta: 0:07:56 lr: 0.000381 loss: 3.4025 (3.2145) grad_norm: 1.6513 (1.6164) time: 0.5064 [2021-03-26 11:16:57 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 340/1251] eta: 0:07:51 lr: 0.000381 loss: 3.4475 (3.2140) grad_norm: 1.6184 (1.6160) time: 0.5016 [2021-03-26 11:17:02 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 350/1251] eta: 0:07:45 lr: 0.000380 loss: 3.2753 (3.2109) grad_norm: 1.6254 (1.6174) time: 0.5018 [2021-03-26 11:17:07 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 360/1251] eta: 0:07:40 lr: 0.000380 loss: 3.3697 (3.2101) grad_norm: 1.6654 (1.6188) time: 0.5056 [2021-03-26 11:17:12 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 370/1251] eta: 0:07:35 lr: 0.000380 loss: 3.1823 (3.2101) grad_norm: 1.5875 (1.6171) time: 0.5105 [2021-03-26 11:17:17 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 380/1251] eta: 0:07:29 lr: 0.000380 loss: 3.1823 (3.2096) grad_norm: 1.6383 (1.6206) time: 0.5115 [2021-03-26 11:17:22 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 390/1251] eta: 0:07:24 lr: 0.000380 loss: 3.3604 (3.2149) grad_norm: 1.6383 (1.6205) time: 0.5064 [2021-03-26 11:17:28 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 400/1251] eta: 0:07:19 lr: 0.000380 loss: 3.3604 (3.2186) grad_norm: 1.5908 (1.6206) time: 0.5096 [2021-03-26 11:17:33 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 410/1251] eta: 0:07:13 lr: 0.000380 loss: 3.4034 (3.2234) grad_norm: 1.5461 (1.6188) time: 0.5128 [2021-03-26 11:17:38 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 420/1251] eta: 0:07:08 lr: 0.000380 loss: 3.2749 (3.2183) grad_norm: 1.5461 (1.6186) time: 0.5064 [2021-03-26 11:17:43 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 430/1251] eta: 0:07:03 lr: 0.000380 loss: 3.3077 (3.2227) grad_norm: 1.6590 (1.6217) time: 0.5109 [2021-03-26 11:17:48 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 440/1251] eta: 0:06:58 lr: 0.000380 loss: 3.4365 (3.2243) grad_norm: 1.5929 (1.6203) time: 0.5181 [2021-03-26 11:17:53 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 450/1251] eta: 0:06:52 lr: 0.000380 loss: 3.3783 (3.2260) grad_norm: 1.5551 (1.6196) time: 0.5086 [2021-03-26 11:17:58 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 460/1251] eta: 0:06:47 lr: 0.000380 loss: 3.4471 (3.2292) grad_norm: 1.6111 (1.6200) time: 0.5024 [2021-03-26 11:18:03 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 470/1251] eta: 0:06:42 lr: 0.000380 loss: 3.4690 (3.2328) grad_norm: 1.6547 (1.6210) time: 0.5002 [2021-03-26 11:18:08 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 480/1251] eta: 0:06:36 lr: 0.000380 loss: 3.4690 (3.2355) grad_norm: 1.6876 (1.6234) time: 0.4960 [2021-03-26 11:18:13 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 490/1251] eta: 0:06:31 lr: 0.000380 loss: 3.2310 (3.2334) grad_norm: 1.6562 (1.6220) time: 0.4936 [2021-03-26 11:18:18 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 500/1251] eta: 0:06:25 lr: 0.000380 loss: 3.2310 (3.2321) grad_norm: 1.5198 (1.6214) time: 0.4997 [2021-03-26 11:18:23 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 510/1251] eta: 0:06:20 lr: 0.000380 loss: 3.3304 (3.2320) grad_norm: 1.5294 (1.6208) time: 0.5050 [2021-03-26 11:18:28 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 520/1251] eta: 0:06:15 lr: 0.000380 loss: 3.3304 (3.2287) grad_norm: 1.5792 (1.6208) time: 0.5047 [2021-03-26 11:18:33 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 530/1251] eta: 0:06:10 lr: 0.000380 loss: 2.9194 (3.2244) grad_norm: 1.5792 (1.6202) time: 0.5063 [2021-03-26 11:18:38 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 540/1251] eta: 0:06:04 lr: 0.000380 loss: 3.0816 (3.2273) grad_norm: 1.5680 (1.6203) time: 0.5125 [2021-03-26 11:18:44 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 550/1251] eta: 0:05:59 lr: 0.000380 loss: 3.1789 (3.2242) grad_norm: 1.6145 (1.6223) time: 0.5181 [2021-03-26 11:18:49 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 560/1251] eta: 0:05:54 lr: 0.000380 loss: 3.1944 (3.2221) grad_norm: 1.6133 (1.6210) time: 0.5187 [2021-03-26 11:18:54 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 570/1251] eta: 0:05:49 lr: 0.000380 loss: 3.2580 (3.2232) grad_norm: 1.4908 (1.6186) time: 0.5098 [2021-03-26 11:18:59 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 580/1251] eta: 0:05:44 lr: 0.000380 loss: 3.3130 (3.2217) grad_norm: 1.5169 (1.6186) time: 0.5006 [2021-03-26 11:19:04 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 590/1251] eta: 0:05:39 lr: 0.000380 loss: 3.3130 (3.2210) grad_norm: 1.5820 (1.6188) time: 0.5056 [2021-03-26 11:19:09 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 600/1251] eta: 0:05:33 lr: 0.000379 loss: 3.3039 (3.2199) grad_norm: 1.5914 (1.6187) time: 0.5074 [2021-03-26 11:19:14 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 610/1251] eta: 0:05:28 lr: 0.000379 loss: 3.2917 (3.2162) grad_norm: 1.6017 (1.6185) time: 0.5004 [2021-03-26 11:19:19 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 620/1251] eta: 0:05:23 lr: 0.000379 loss: 3.3041 (3.2188) grad_norm: 1.6017 (1.6178) time: 0.4972 [2021-03-26 11:19:24 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 630/1251] eta: 0:05:18 lr: 0.000379 loss: 3.3206 (3.2213) grad_norm: 1.5897 (1.6180) time: 0.5027 [2021-03-26 11:19:29 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 640/1251] eta: 0:05:12 lr: 0.000379 loss: 3.1486 (3.2183) grad_norm: 1.6745 (1.6186) time: 0.5015 [2021-03-26 11:19:34 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 650/1251] eta: 0:05:07 lr: 0.000379 loss: 3.1646 (3.2175) grad_norm: 1.6267 (1.6184) time: 0.4954 [2021-03-26 11:19:39 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 660/1251] eta: 0:05:02 lr: 0.000379 loss: 3.1758 (3.2177) grad_norm: 1.5380 (1.6174) time: 0.4993 [2021-03-26 11:19:44 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 670/1251] eta: 0:04:57 lr: 0.000379 loss: 3.2795 (3.2180) grad_norm: 1.5375 (1.6163) time: 0.5050 [2021-03-26 11:19:49 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 680/1251] eta: 0:04:52 lr: 0.000379 loss: 3.2795 (3.2177) grad_norm: 1.5264 (1.6151) time: 0.5061 [2021-03-26 11:19:54 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 690/1251] eta: 0:04:46 lr: 0.000379 loss: 3.2070 (3.2184) grad_norm: 1.5532 (1.6158) time: 0.5081 [2021-03-26 11:19:59 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 700/1251] eta: 0:04:41 lr: 0.000379 loss: 3.1026 (3.2154) grad_norm: 1.6523 (1.6170) time: 0.5091 [2021-03-26 11:20:04 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 710/1251] eta: 0:04:36 lr: 0.000379 loss: 3.2404 (3.2137) grad_norm: 1.6527 (1.6177) time: 0.5075 [2021-03-26 11:20:09 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 720/1251] eta: 0:04:31 lr: 0.000379 loss: 3.1134 (3.2088) grad_norm: 1.6280 (1.6176) time: 0.5122 [2021-03-26 11:20:15 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 730/1251] eta: 0:04:26 lr: 0.000379 loss: 2.8609 (3.2070) grad_norm: 1.6025 (1.6172) time: 0.5183 [2021-03-26 11:20:20 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 740/1251] eta: 0:04:21 lr: 0.000379 loss: 3.2572 (3.2064) grad_norm: 1.4968 (1.6173) time: 0.5229 [2021-03-26 11:20:25 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 750/1251] eta: 0:04:16 lr: 0.000379 loss: 3.3888 (3.2098) grad_norm: 1.5122 (1.6167) time: 0.5229 [2021-03-26 11:20:30 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 760/1251] eta: 0:04:11 lr: 0.000379 loss: 3.3888 (3.2084) grad_norm: 1.5174 (1.6172) time: 0.5107 [2021-03-26 11:20:35 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 770/1251] eta: 0:04:06 lr: 0.000379 loss: 3.1241 (3.2089) grad_norm: 1.5263 (1.6164) time: 0.5042 [2021-03-26 11:20:40 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 780/1251] eta: 0:04:00 lr: 0.000379 loss: 3.2240 (3.2058) grad_norm: 1.5306 (1.6157) time: 0.5081 [2021-03-26 11:20:45 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 790/1251] eta: 0:03:55 lr: 0.000379 loss: 3.2531 (3.2082) grad_norm: 1.5306 (1.6150) time: 0.5032 [2021-03-26 11:20:50 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 800/1251] eta: 0:03:50 lr: 0.000379 loss: 3.3068 (3.2071) grad_norm: 1.5352 (1.6146) time: 0.5017 [2021-03-26 11:20:55 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 810/1251] eta: 0:03:45 lr: 0.000379 loss: 3.3068 (3.2088) grad_norm: 1.5710 (1.6152) time: 0.5062 [2021-03-26 11:21:00 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 820/1251] eta: 0:03:40 lr: 0.000379 loss: 3.5107 (3.2107) grad_norm: 1.6089 (1.6144) time: 0.5021 [2021-03-26 11:21:05 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 830/1251] eta: 0:03:35 lr: 0.000379 loss: 3.4669 (3.2111) grad_norm: 1.5775 (1.6134) time: 0.5020 [2021-03-26 11:21:10 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 840/1251] eta: 0:03:30 lr: 0.000379 loss: 3.2480 (3.2112) grad_norm: 1.6004 (1.6135) time: 0.5027 [2021-03-26 11:21:15 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 850/1251] eta: 0:03:24 lr: 0.000378 loss: 3.1799 (3.2098) grad_norm: 1.6314 (1.6144) time: 0.5004 [2021-03-26 11:21:21 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 860/1251] eta: 0:03:19 lr: 0.000378 loss: 3.1799 (3.2104) grad_norm: 1.6086 (1.6140) time: 0.5045 [2021-03-26 11:21:26 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 870/1251] eta: 0:03:14 lr: 0.000378 loss: 3.0065 (3.2085) grad_norm: 1.6086 (1.6147) time: 0.5108 [2021-03-26 11:21:31 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 880/1251] eta: 0:03:09 lr: 0.000378 loss: 3.3925 (3.2115) grad_norm: 1.6294 (1.6142) time: 0.5080 [2021-03-26 11:21:36 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 890/1251] eta: 0:03:04 lr: 0.000378 loss: 3.4953 (3.2134) grad_norm: 1.5758 (1.6139) time: 0.5018 [2021-03-26 11:21:41 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 900/1251] eta: 0:02:59 lr: 0.000378 loss: 3.4204 (3.2146) grad_norm: 1.5737 (1.6133) time: 0.5054 [2021-03-26 11:21:46 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 910/1251] eta: 0:02:54 lr: 0.000378 loss: 3.4204 (3.2147) grad_norm: 1.5919 (1.6144) time: 0.5126 [2021-03-26 11:21:51 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 920/1251] eta: 0:02:49 lr: 0.000378 loss: 3.4900 (3.2160) grad_norm: 1.5919 (1.6140) time: 0.5145 [2021-03-26 11:21:56 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 930/1251] eta: 0:02:43 lr: 0.000378 loss: 3.1776 (3.2131) grad_norm: 1.5749 (1.6139) time: 0.5111 [2021-03-26 11:22:01 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 940/1251] eta: 0:02:38 lr: 0.000378 loss: 3.1574 (3.2128) grad_norm: 1.5687 (1.6143) time: 0.5073 [2021-03-26 11:22:06 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 950/1251] eta: 0:02:33 lr: 0.000378 loss: 3.3298 (3.2147) grad_norm: 1.5380 (1.6141) time: 0.5039 [2021-03-26 11:22:11 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 960/1251] eta: 0:02:28 lr: 0.000378 loss: 3.4100 (3.2159) grad_norm: 1.5972 (1.6148) time: 0.5033 [2021-03-26 11:22:16 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 970/1251] eta: 0:02:23 lr: 0.000378 loss: 3.3314 (3.2151) grad_norm: 1.6227 (1.6153) time: 0.5080 [2021-03-26 11:22:22 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 980/1251] eta: 0:02:18 lr: 0.000378 loss: 3.2192 (3.2125) grad_norm: 1.5922 (1.6157) time: 0.5138 [2021-03-26 11:22:27 swin_small_patch4_window7_224] INFO: Epoch: [174] [ 990/1251] eta: 0:02:13 lr: 0.000378 loss: 3.2192 (3.2124) grad_norm: 1.5759 (1.6154) time: 0.5200 [2021-03-26 11:22:32 swin_small_patch4_window7_224] INFO: Epoch: [174] [1000/1251] eta: 0:02:08 lr: 0.000378 loss: 3.0304 (3.2083) grad_norm: 1.5535 (1.6152) time: 0.5090 [2021-03-26 11:22:37 swin_small_patch4_window7_224] INFO: Epoch: [174] [1010/1251] eta: 0:02:03 lr: 0.000378 loss: 3.0304 (3.2099) grad_norm: 1.6533 (1.6160) time: 0.4967 [2021-03-26 11:22:42 swin_small_patch4_window7_224] INFO: Epoch: [174] [1020/1251] eta: 0:01:57 lr: 0.000378 loss: 3.2572 (3.2073) grad_norm: 1.6062 (1.6158) time: 0.5001 [2021-03-26 11:22:47 swin_small_patch4_window7_224] INFO: Epoch: [174] [1030/1251] eta: 0:01:52 lr: 0.000378 loss: 3.2572 (3.2091) grad_norm: 1.5781 (1.6168) time: 0.5033 [2021-03-26 11:22:52 swin_small_patch4_window7_224] INFO: Epoch: [174] [1040/1251] eta: 0:01:47 lr: 0.000378 loss: 3.3194 (3.2098) grad_norm: 1.5951 (1.6167) time: 0.5024 [2021-03-26 11:22:57 swin_small_patch4_window7_224] INFO: Epoch: [174] [1050/1251] eta: 0:01:42 lr: 0.000378 loss: 3.0590 (3.2084) grad_norm: 1.5902 (1.6168) time: 0.5004 [2021-03-26 11:23:02 swin_small_patch4_window7_224] INFO: Epoch: [174] [1060/1251] eta: 0:01:37 lr: 0.000378 loss: 3.0976 (3.2096) grad_norm: 1.6113 (1.6176) time: 0.5096 [2021-03-26 11:23:07 swin_small_patch4_window7_224] INFO: Epoch: [174] [1070/1251] eta: 0:01:32 lr: 0.000378 loss: 3.3195 (3.2075) grad_norm: 1.5888 (1.6179) time: 0.5090 [2021-03-26 11:23:12 swin_small_patch4_window7_224] INFO: Epoch: [174] [1080/1251] eta: 0:01:27 lr: 0.000378 loss: 3.2590 (3.2073) grad_norm: 1.5815 (1.6179) time: 0.5011 [2021-03-26 11:23:17 swin_small_patch4_window7_224] INFO: Epoch: [174] [1090/1251] eta: 0:01:22 lr: 0.000378 loss: 3.3153 (3.2085) grad_norm: 1.6010 (1.6184) time: 0.5052 [2021-03-26 11:23:22 swin_small_patch4_window7_224] INFO: Epoch: [174] [1100/1251] eta: 0:01:16 lr: 0.000377 loss: 3.1860 (3.2072) grad_norm: 1.6562 (1.6202) time: 0.5059 [2021-03-26 11:23:27 swin_small_patch4_window7_224] INFO: Epoch: [174] [1110/1251] eta: 0:01:11 lr: 0.000377 loss: 3.1941 (3.2080) grad_norm: 1.5919 (1.6190) time: 0.5039 [2021-03-26 11:23:32 swin_small_patch4_window7_224] INFO: Epoch: [174] [1120/1251] eta: 0:01:06 lr: 0.000377 loss: 3.3166 (3.2096) grad_norm: 1.5007 (1.6183) time: 0.5047 [2021-03-26 11:23:37 swin_small_patch4_window7_224] INFO: Epoch: [174] [1130/1251] eta: 0:01:01 lr: 0.000377 loss: 3.3554 (3.2108) grad_norm: 1.5185 (1.6180) time: 0.5035 [2021-03-26 11:23:42 swin_small_patch4_window7_224] INFO: Epoch: [174] [1140/1251] eta: 0:00:56 lr: 0.000377 loss: 3.3903 (3.2103) grad_norm: 1.5790 (1.6179) time: 0.5039 [2021-03-26 11:23:47 swin_small_patch4_window7_224] INFO: Epoch: [174] [1150/1251] eta: 0:00:51 lr: 0.000377 loss: 3.3646 (3.2114) grad_norm: 1.5698 (1.6173) time: 0.5035 [2021-03-26 11:23:52 swin_small_patch4_window7_224] INFO: Epoch: [174] [1160/1251] eta: 0:00:46 lr: 0.000377 loss: 3.4311 (3.2134) grad_norm: 1.5534 (1.6172) time: 0.5002 [2021-03-26 11:23:57 swin_small_patch4_window7_224] INFO: Epoch: [174] [1170/1251] eta: 0:00:41 lr: 0.000377 loss: 3.4208 (3.2120) grad_norm: 1.6802 (1.6182) time: 0.5052 [2021-03-26 11:24:03 swin_small_patch4_window7_224] INFO: Epoch: [174] [1180/1251] eta: 0:00:36 lr: 0.000377 loss: 3.0501 (3.2090) grad_norm: 1.6486 (1.6180) time: 0.5129 [2021-03-26 11:24:08 swin_small_patch4_window7_224] INFO: Epoch: [174] [1190/1251] eta: 0:00:31 lr: 0.000377 loss: 3.0991 (3.2083) grad_norm: 1.5943 (1.6181) time: 0.5118 [2021-03-26 11:24:13 swin_small_patch4_window7_224] INFO: Epoch: [174] [1200/1251] eta: 0:00:25 lr: 0.000377 loss: 3.3245 (3.2082) grad_norm: 1.5950 (1.6191) time: 0.5053 [2021-03-26 11:24:18 swin_small_patch4_window7_224] INFO: Epoch: [174] [1210/1251] eta: 0:00:20 lr: 0.000377 loss: 3.3672 (3.2091) grad_norm: 1.6854 (1.6196) time: 0.5002 [2021-03-26 11:24:23 swin_small_patch4_window7_224] INFO: Epoch: [174] [1220/1251] eta: 0:00:15 lr: 0.000377 loss: 3.3951 (3.2088) grad_norm: 1.6704 (1.6200) time: 0.5004 [2021-03-26 11:24:28 swin_small_patch4_window7_224] INFO: Epoch: [174] [1230/1251] eta: 0:00:10 lr: 0.000377 loss: 3.3858 (3.2101) grad_norm: 1.5709 (1.6193) time: 0.5052 [2021-03-26 11:24:33 swin_small_patch4_window7_224] INFO: Epoch: [174] [1240/1251] eta: 0:00:05 lr: 0.000377 loss: 3.2988 (3.2086) grad_norm: 1.5709 (1.6188) time: 0.5048 [2021-03-26 11:24:38 swin_small_patch4_window7_224] INFO: Epoch: [174] [1250/1251] eta: 0:00:00 lr: 0.000377 loss: 3.1758 (3.2092) grad_norm: 1.6392 (1.6205) time: 0.4982 [2021-03-26 11:24:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:44 loss: 0.7544 (0.7544) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-26 11:24:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.9664 (0.9358) acc1: 76.5625 (78.2670) acc5: 95.3125 (94.7443) [2021-03-26 11:24:54 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9097 (0.8782) acc1: 78.1250 (79.5387) acc5: 95.3125 (94.8661) [2021-03-26 11:24:56 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8931 (0.8968) acc1: 78.1250 (78.7802) acc5: 95.3125 (94.8085) [2021-03-26 11:24:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9295 (0.8942) acc1: 78.1250 (78.7729) acc5: 95.3125 (94.8171) [2021-03-26 11:24:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8061 (0.8959) acc1: 79.6875 (78.8800) acc5: 95.3125 (94.7840) [2021-03-26 11:25:09 swin_small_patch4_window7_224] INFO: * Acc@1 79.446 Acc@5 94.950 loss 0.873 [2021-03-26 11:25:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.4% [2021-03-26 11:25:09 swin_small_patch4_window7_224] INFO: Max accuracy: 79.54% [2021-03-26 11:25:13 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 0/1251] eta: 1:30:58 lr: 0.000377 loss: 3.8185 (3.8185) grad_norm: 1.8373 (1.8373) time: 4.3630 [2021-03-26 11:25:18 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 10/1251] eta: 0:17:45 lr: 0.000377 loss: 3.4426 (3.2798) grad_norm: 1.6079 (1.6746) time: 0.8588 [2021-03-26 11:25:23 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 20/1251] eta: 0:14:04 lr: 0.000377 loss: 3.3240 (3.1583) grad_norm: 1.5590 (1.6191) time: 0.5023 [2021-03-26 11:25:28 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 30/1251] eta: 0:12:45 lr: 0.000377 loss: 3.3062 (3.2037) grad_norm: 1.4839 (1.5678) time: 0.4993 [2021-03-26 11:25:33 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 40/1251] eta: 0:12:05 lr: 0.000377 loss: 3.2889 (3.1823) grad_norm: 1.5226 (1.5906) time: 0.5069 [2021-03-26 11:25:38 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 50/1251] eta: 0:11:37 lr: 0.000377 loss: 3.1841 (3.1720) grad_norm: 1.6268 (1.5931) time: 0.5092 [2021-03-26 11:25:43 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 60/1251] eta: 0:11:16 lr: 0.000377 loss: 3.2689 (3.1966) grad_norm: 1.6158 (1.5996) time: 0.5059 [2021-03-26 11:25:48 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 70/1251] eta: 0:11:01 lr: 0.000377 loss: 3.3296 (3.2143) grad_norm: 1.6788 (1.6239) time: 0.5073 [2021-03-26 11:25:53 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 80/1251] eta: 0:10:47 lr: 0.000377 loss: 3.2671 (3.1782) grad_norm: 1.6478 (1.6228) time: 0.5048 [2021-03-26 11:25:58 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 90/1251] eta: 0:10:36 lr: 0.000377 loss: 3.3111 (3.2043) grad_norm: 1.6360 (1.6188) time: 0.5065 [2021-03-26 11:26:04 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 100/1251] eta: 0:10:26 lr: 0.000376 loss: 3.4824 (3.2368) grad_norm: 1.6026 (1.6159) time: 0.5109 [2021-03-26 11:26:09 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 110/1251] eta: 0:10:18 lr: 0.000376 loss: 3.3631 (3.2225) grad_norm: 1.6186 (1.6174) time: 0.5144 [2021-03-26 11:26:14 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 120/1251] eta: 0:10:09 lr: 0.000376 loss: 3.1855 (3.2179) grad_norm: 1.6077 (1.6150) time: 0.5096 [2021-03-26 11:26:19 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 130/1251] eta: 0:10:02 lr: 0.000376 loss: 3.1854 (3.2093) grad_norm: 1.5705 (1.6144) time: 0.5122 [2021-03-26 11:26:24 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 140/1251] eta: 0:09:54 lr: 0.000376 loss: 2.9060 (3.1860) grad_norm: 1.6713 (inf) time: 0.5134 [2021-03-26 11:26:29 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 150/1251] eta: 0:09:47 lr: 0.000376 loss: 3.0761 (3.1932) grad_norm: 1.7148 (inf) time: 0.5083 [2021-03-26 11:26:34 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 160/1251] eta: 0:09:40 lr: 0.000376 loss: 3.2478 (3.1972) grad_norm: 1.6516 (inf) time: 0.5085 [2021-03-26 11:26:39 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 170/1251] eta: 0:09:32 lr: 0.000376 loss: 3.1657 (3.2009) grad_norm: 1.6464 (inf) time: 0.5009 [2021-03-26 11:26:44 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 180/1251] eta: 0:09:26 lr: 0.000376 loss: 3.3881 (3.2093) grad_norm: 1.6580 (inf) time: 0.5023 [2021-03-26 11:26:49 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 190/1251] eta: 0:09:18 lr: 0.000376 loss: 3.0257 (3.1876) grad_norm: 1.6138 (inf) time: 0.5011 [2021-03-26 11:26:54 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 200/1251] eta: 0:09:11 lr: 0.000376 loss: 2.9866 (3.1899) grad_norm: 1.5894 (inf) time: 0.4945 [2021-03-26 11:26:59 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 210/1251] eta: 0:09:05 lr: 0.000376 loss: 3.3477 (3.1953) grad_norm: 1.6251 (inf) time: 0.4991 [2021-03-26 11:27:04 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 220/1251] eta: 0:08:59 lr: 0.000376 loss: 3.1612 (3.1870) grad_norm: 1.5959 (inf) time: 0.5059 [2021-03-26 11:27:09 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 230/1251] eta: 0:08:53 lr: 0.000376 loss: 3.0780 (3.1797) grad_norm: 1.6180 (inf) time: 0.5075 [2021-03-26 11:27:14 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 240/1251] eta: 0:08:47 lr: 0.000376 loss: 3.0780 (3.1770) grad_norm: 1.6795 (inf) time: 0.5085 [2021-03-26 11:27:19 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 250/1251] eta: 0:08:41 lr: 0.000376 loss: 2.9359 (3.1712) grad_norm: 1.6641 (inf) time: 0.5016 [2021-03-26 11:27:24 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 260/1251] eta: 0:08:35 lr: 0.000376 loss: 2.9665 (3.1708) grad_norm: 1.7019 (inf) time: 0.4971 [2021-03-26 11:27:29 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 270/1251] eta: 0:08:30 lr: 0.000376 loss: 3.4253 (3.1732) grad_norm: 1.7374 (inf) time: 0.5048 [2021-03-26 11:27:35 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 280/1251] eta: 0:08:24 lr: 0.000376 loss: 3.5233 (3.1903) grad_norm: 1.5733 (inf) time: 0.5065 [2021-03-26 11:27:39 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 290/1251] eta: 0:08:18 lr: 0.000376 loss: 3.1396 (3.1785) grad_norm: 1.5158 (inf) time: 0.5002 [2021-03-26 11:27:45 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 300/1251] eta: 0:08:12 lr: 0.000376 loss: 3.1934 (3.1893) grad_norm: 1.5158 (inf) time: 0.5012 [2021-03-26 11:27:50 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 310/1251] eta: 0:08:07 lr: 0.000376 loss: 3.3997 (3.1891) grad_norm: 1.5432 (inf) time: 0.5051 [2021-03-26 11:27:55 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 320/1251] eta: 0:08:01 lr: 0.000376 loss: 3.2338 (3.1894) grad_norm: 1.5781 (inf) time: 0.5021 [2021-03-26 11:28:00 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 330/1251] eta: 0:07:55 lr: 0.000376 loss: 3.2488 (3.1872) grad_norm: 1.5675 (inf) time: 0.4971 [2021-03-26 11:28:05 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 340/1251] eta: 0:07:50 lr: 0.000376 loss: 3.1599 (3.1791) grad_norm: 1.5396 (inf) time: 0.4992 [2021-03-26 11:28:10 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 350/1251] eta: 0:07:44 lr: 0.000375 loss: 3.1611 (3.1821) grad_norm: 1.6041 (inf) time: 0.5041 [2021-03-26 11:28:15 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 360/1251] eta: 0:07:39 lr: 0.000375 loss: 3.1611 (3.1733) grad_norm: 1.6296 (inf) time: 0.5011 [2021-03-26 11:28:20 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 370/1251] eta: 0:07:33 lr: 0.000375 loss: 2.9460 (3.1714) grad_norm: 1.6867 (inf) time: 0.4989 [2021-03-26 11:28:25 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 380/1251] eta: 0:07:28 lr: 0.000375 loss: 3.0303 (3.1673) grad_norm: 1.6550 (inf) time: 0.4999 [2021-03-26 11:28:30 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 390/1251] eta: 0:07:22 lr: 0.000375 loss: 3.3071 (3.1723) grad_norm: 1.5932 (inf) time: 0.4974 [2021-03-26 11:28:35 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 400/1251] eta: 0:07:17 lr: 0.000375 loss: 3.4011 (3.1704) grad_norm: 1.6344 (inf) time: 0.5041 [2021-03-26 11:28:40 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 410/1251] eta: 0:07:11 lr: 0.000375 loss: 3.0312 (3.1701) grad_norm: 1.6523 (inf) time: 0.5076 [2021-03-26 11:28:45 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 420/1251] eta: 0:07:06 lr: 0.000375 loss: 3.3471 (3.1754) grad_norm: 1.7015 (inf) time: 0.5000 [2021-03-26 11:28:50 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 430/1251] eta: 0:07:01 lr: 0.000375 loss: 3.3921 (3.1782) grad_norm: 1.6682 (inf) time: 0.5002 [2021-03-26 11:28:55 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 440/1251] eta: 0:06:55 lr: 0.000375 loss: 3.1648 (3.1759) grad_norm: 1.6069 (inf) time: 0.5027 [2021-03-26 11:29:00 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 450/1251] eta: 0:06:50 lr: 0.000375 loss: 3.1573 (3.1775) grad_norm: 1.6072 (inf) time: 0.5005 [2021-03-26 11:29:05 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 460/1251] eta: 0:06:45 lr: 0.000375 loss: 3.2746 (3.1802) grad_norm: 1.6072 (inf) time: 0.4995 [2021-03-26 11:29:10 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 470/1251] eta: 0:06:39 lr: 0.000375 loss: 3.3674 (3.1861) grad_norm: 1.6494 (inf) time: 0.5003 [2021-03-26 11:29:15 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 480/1251] eta: 0:06:34 lr: 0.000375 loss: 3.5525 (3.1901) grad_norm: 1.6264 (inf) time: 0.5035 [2021-03-26 11:29:20 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 490/1251] eta: 0:06:29 lr: 0.000375 loss: 3.0191 (3.1800) grad_norm: 1.6037 (inf) time: 0.5044 [2021-03-26 11:29:25 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 500/1251] eta: 0:06:24 lr: 0.000375 loss: 3.0756 (3.1829) grad_norm: 1.5611 (inf) time: 0.5041 [2021-03-26 11:29:30 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 510/1251] eta: 0:06:18 lr: 0.000375 loss: 3.1690 (3.1767) grad_norm: 1.5672 (inf) time: 0.4997 [2021-03-26 11:29:35 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 520/1251] eta: 0:06:13 lr: 0.000375 loss: 3.2257 (3.1786) grad_norm: 1.6852 (inf) time: 0.4977 [2021-03-26 11:29:40 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 530/1251] eta: 0:06:08 lr: 0.000375 loss: 3.2450 (3.1783) grad_norm: 1.6852 (inf) time: 0.5020 [2021-03-26 11:29:45 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 540/1251] eta: 0:06:03 lr: 0.000375 loss: 3.4366 (3.1843) grad_norm: 1.6548 (inf) time: 0.5011 [2021-03-26 11:29:50 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 550/1251] eta: 0:05:58 lr: 0.000375 loss: 3.4366 (3.1863) grad_norm: 1.6825 (inf) time: 0.5145 [2021-03-26 11:29:55 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 560/1251] eta: 0:05:53 lr: 0.000375 loss: 3.4097 (3.1863) grad_norm: 1.6825 (inf) time: 0.5197 [2021-03-26 11:30:00 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 570/1251] eta: 0:05:47 lr: 0.000375 loss: 3.3763 (3.1878) grad_norm: 1.5076 (inf) time: 0.5046 [2021-03-26 11:30:05 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 580/1251] eta: 0:05:42 lr: 0.000375 loss: 3.3538 (3.1918) grad_norm: 1.5577 (inf) time: 0.5034 [2021-03-26 11:30:10 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 590/1251] eta: 0:05:37 lr: 0.000375 loss: 3.5209 (3.1974) grad_norm: 1.6312 (inf) time: 0.5076 [2021-03-26 11:30:15 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 600/1251] eta: 0:05:32 lr: 0.000374 loss: 3.3381 (3.1958) grad_norm: 1.6337 (inf) time: 0.5047 [2021-03-26 11:30:21 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 610/1251] eta: 0:05:27 lr: 0.000374 loss: 3.2382 (3.1954) grad_norm: 1.5825 (inf) time: 0.5037 [2021-03-26 11:30:26 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 620/1251] eta: 0:05:22 lr: 0.000374 loss: 3.4027 (3.1983) grad_norm: 1.6065 (inf) time: 0.5074 [2021-03-26 11:30:31 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 630/1251] eta: 0:05:16 lr: 0.000374 loss: 3.2046 (3.1950) grad_norm: 1.6078 (inf) time: 0.5085 [2021-03-26 11:30:36 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 640/1251] eta: 0:05:11 lr: 0.000374 loss: 3.2038 (3.1960) grad_norm: 1.5812 (inf) time: 0.5074 [2021-03-26 11:30:41 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 650/1251] eta: 0:05:06 lr: 0.000374 loss: 3.2659 (3.1953) grad_norm: 1.5608 (inf) time: 0.5097 [2021-03-26 11:30:46 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 660/1251] eta: 0:05:01 lr: 0.000374 loss: 3.0856 (3.1927) grad_norm: 1.5987 (inf) time: 0.5069 [2021-03-26 11:30:51 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 670/1251] eta: 0:04:56 lr: 0.000374 loss: 3.1137 (3.1921) grad_norm: 1.6679 (inf) time: 0.4987 [2021-03-26 11:30:56 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 680/1251] eta: 0:04:51 lr: 0.000374 loss: 3.4812 (3.1943) grad_norm: 1.5389 (inf) time: 0.5121 [2021-03-26 11:31:01 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 690/1251] eta: 0:04:46 lr: 0.000374 loss: 3.4004 (3.1951) grad_norm: 1.5389 (inf) time: 0.5160 [2021-03-26 11:31:06 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 700/1251] eta: 0:04:40 lr: 0.000374 loss: 3.2090 (3.1911) grad_norm: 1.6159 (inf) time: 0.5010 [2021-03-26 11:31:11 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 710/1251] eta: 0:04:35 lr: 0.000374 loss: 3.1666 (3.1889) grad_norm: 1.5598 (inf) time: 0.4998 [2021-03-26 11:31:16 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 720/1251] eta: 0:04:30 lr: 0.000374 loss: 3.1350 (3.1888) grad_norm: 1.6160 (inf) time: 0.5024 [2021-03-26 11:31:21 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 730/1251] eta: 0:04:25 lr: 0.000374 loss: 3.1350 (3.1876) grad_norm: 1.6160 (inf) time: 0.5092 [2021-03-26 11:31:27 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 740/1251] eta: 0:04:20 lr: 0.000374 loss: 3.2708 (3.1876) grad_norm: 1.5531 (inf) time: 0.5155 [2021-03-26 11:31:32 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 750/1251] eta: 0:04:15 lr: 0.000374 loss: 3.3987 (3.1902) grad_norm: 1.5671 (inf) time: 0.5196 [2021-03-26 11:31:37 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 760/1251] eta: 0:04:10 lr: 0.000374 loss: 3.2433 (3.1893) grad_norm: 1.6203 (inf) time: 0.5107 [2021-03-26 11:31:42 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 770/1251] eta: 0:04:05 lr: 0.000374 loss: 2.9909 (3.1867) grad_norm: 1.6399 (inf) time: 0.5034 [2021-03-26 11:31:47 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 780/1251] eta: 0:04:00 lr: 0.000374 loss: 3.0611 (3.1884) grad_norm: 1.6247 (inf) time: 0.5053 [2021-03-26 11:31:52 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 790/1251] eta: 0:03:55 lr: 0.000374 loss: 3.2521 (3.1876) grad_norm: 1.6214 (inf) time: 0.5110 [2021-03-26 11:31:57 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 800/1251] eta: 0:03:49 lr: 0.000374 loss: 3.2818 (3.1886) grad_norm: 1.5584 (inf) time: 0.5126 [2021-03-26 11:32:02 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 810/1251] eta: 0:03:44 lr: 0.000374 loss: 3.3191 (3.1861) grad_norm: 1.5584 (inf) time: 0.5039 [2021-03-26 11:32:07 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 820/1251] eta: 0:03:39 lr: 0.000374 loss: 3.3207 (3.1870) grad_norm: 1.5734 (inf) time: 0.5021 [2021-03-26 11:32:12 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 830/1251] eta: 0:03:34 lr: 0.000374 loss: 3.3402 (3.1875) grad_norm: 1.6634 (inf) time: 0.5073 [2021-03-26 11:32:17 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 840/1251] eta: 0:03:29 lr: 0.000374 loss: 3.1424 (3.1838) grad_norm: 1.6581 (inf) time: 0.5076 [2021-03-26 11:32:22 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 850/1251] eta: 0:03:24 lr: 0.000373 loss: 3.0193 (3.1836) grad_norm: 1.5671 (inf) time: 0.5101 [2021-03-26 11:32:28 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 860/1251] eta: 0:03:19 lr: 0.000373 loss: 3.3101 (3.1862) grad_norm: 1.5671 (inf) time: 0.5118 [2021-03-26 11:32:33 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 870/1251] eta: 0:03:14 lr: 0.000373 loss: 3.2965 (3.1856) grad_norm: 1.5890 (inf) time: 0.5175 [2021-03-26 11:32:38 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 880/1251] eta: 0:03:09 lr: 0.000373 loss: 3.2965 (3.1860) grad_norm: 1.5417 (inf) time: 0.5177 [2021-03-26 11:32:43 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 890/1251] eta: 0:03:04 lr: 0.000373 loss: 3.3541 (3.1865) grad_norm: 1.5223 (inf) time: 0.5068 [2021-03-26 11:32:48 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 900/1251] eta: 0:02:58 lr: 0.000373 loss: 3.2864 (3.1855) grad_norm: 1.5796 (inf) time: 0.5090 [2021-03-26 11:32:53 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 910/1251] eta: 0:02:53 lr: 0.000373 loss: 3.0462 (3.1837) grad_norm: 1.5796 (inf) time: 0.5072 [2021-03-26 11:32:58 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 920/1251] eta: 0:02:48 lr: 0.000373 loss: 3.1642 (3.1840) grad_norm: 1.6303 (inf) time: 0.5080 [2021-03-26 11:33:03 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 930/1251] eta: 0:02:43 lr: 0.000373 loss: 3.2020 (3.1835) grad_norm: 1.5817 (inf) time: 0.5083 [2021-03-26 11:33:08 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 940/1251] eta: 0:02:38 lr: 0.000373 loss: 3.0983 (3.1829) grad_norm: 1.6170 (inf) time: 0.5091 [2021-03-26 11:33:13 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 950/1251] eta: 0:02:33 lr: 0.000373 loss: 2.9807 (3.1812) grad_norm: 1.6303 (inf) time: 0.5084 [2021-03-26 11:33:19 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 960/1251] eta: 0:02:28 lr: 0.000373 loss: 2.9815 (3.1788) grad_norm: 1.6067 (inf) time: 0.5049 [2021-03-26 11:33:24 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 970/1251] eta: 0:02:23 lr: 0.000373 loss: 3.1703 (3.1789) grad_norm: 1.5634 (inf) time: 0.5039 [2021-03-26 11:33:29 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 980/1251] eta: 0:02:18 lr: 0.000373 loss: 3.3463 (3.1794) grad_norm: 1.5147 (inf) time: 0.5016 [2021-03-26 11:33:34 swin_small_patch4_window7_224] INFO: Epoch: [175] [ 990/1251] eta: 0:02:12 lr: 0.000373 loss: 3.3074 (3.1779) grad_norm: 1.5325 (inf) time: 0.5029 [2021-03-26 11:33:39 swin_small_patch4_window7_224] INFO: Epoch: [175] [1000/1251] eta: 0:02:07 lr: 0.000373 loss: 3.0435 (3.1765) grad_norm: 1.5368 (inf) time: 0.5017 [2021-03-26 11:33:44 swin_small_patch4_window7_224] INFO: Epoch: [175] [1010/1251] eta: 0:02:02 lr: 0.000373 loss: 3.2917 (3.1777) grad_norm: 1.5368 (inf) time: 0.5009 [2021-03-26 11:33:49 swin_small_patch4_window7_224] INFO: Epoch: [175] [1020/1251] eta: 0:01:57 lr: 0.000373 loss: 3.4270 (3.1801) grad_norm: 1.6084 (inf) time: 0.4971 [2021-03-26 11:33:54 swin_small_patch4_window7_224] INFO: Epoch: [175] [1030/1251] eta: 0:01:52 lr: 0.000373 loss: 3.2890 (3.1794) grad_norm: 1.6281 (inf) time: 0.4966 [2021-03-26 11:33:59 swin_small_patch4_window7_224] INFO: Epoch: [175] [1040/1251] eta: 0:01:47 lr: 0.000373 loss: 3.1466 (3.1767) grad_norm: 1.5890 (inf) time: 0.5011 [2021-03-26 11:34:04 swin_small_patch4_window7_224] INFO: Epoch: [175] [1050/1251] eta: 0:01:42 lr: 0.000373 loss: 3.0687 (3.1748) grad_norm: 1.5268 (inf) time: 0.5066 [2021-03-26 11:34:09 swin_small_patch4_window7_224] INFO: Epoch: [175] [1060/1251] eta: 0:01:37 lr: 0.000373 loss: 3.0687 (3.1758) grad_norm: 1.5741 (inf) time: 0.5038 [2021-03-26 11:34:14 swin_small_patch4_window7_224] INFO: Epoch: [175] [1070/1251] eta: 0:01:32 lr: 0.000373 loss: 3.3270 (3.1759) grad_norm: 1.5415 (inf) time: 0.5012 [2021-03-26 11:34:19 swin_small_patch4_window7_224] INFO: Epoch: [175] [1080/1251] eta: 0:01:26 lr: 0.000373 loss: 3.0275 (3.1753) grad_norm: 1.5906 (inf) time: 0.5017 [2021-03-26 11:34:24 swin_small_patch4_window7_224] INFO: Epoch: [175] [1090/1251] eta: 0:01:21 lr: 0.000373 loss: 3.4586 (3.1783) grad_norm: 1.5906 (inf) time: 0.5025 [2021-03-26 11:34:29 swin_small_patch4_window7_224] INFO: Epoch: [175] [1100/1251] eta: 0:01:16 lr: 0.000372 loss: 3.4096 (3.1791) grad_norm: 1.5875 (inf) time: 0.5076 [2021-03-26 11:34:34 swin_small_patch4_window7_224] INFO: Epoch: [175] [1110/1251] eta: 0:01:11 lr: 0.000372 loss: 3.3429 (3.1799) grad_norm: 1.5909 (inf) time: 0.5063 [2021-03-26 11:34:39 swin_small_patch4_window7_224] INFO: Epoch: [175] [1120/1251] eta: 0:01:06 lr: 0.000372 loss: 3.2403 (3.1799) grad_norm: 1.6083 (inf) time: 0.5069 [2021-03-26 11:34:44 swin_small_patch4_window7_224] INFO: Epoch: [175] [1130/1251] eta: 0:01:01 lr: 0.000372 loss: 3.2403 (3.1808) grad_norm: 1.6810 (inf) time: 0.5035 [2021-03-26 11:34:49 swin_small_patch4_window7_224] INFO: Epoch: [175] [1140/1251] eta: 0:00:56 lr: 0.000372 loss: 3.1959 (3.1808) grad_norm: 1.6620 (inf) time: 0.5023 [2021-03-26 11:34:54 swin_small_patch4_window7_224] INFO: Epoch: [175] [1150/1251] eta: 0:00:51 lr: 0.000372 loss: 3.1598 (3.1801) grad_norm: 1.6592 (inf) time: 0.5074 [2021-03-26 11:34:59 swin_small_patch4_window7_224] INFO: Epoch: [175] [1160/1251] eta: 0:00:46 lr: 0.000372 loss: 3.1433 (3.1782) grad_norm: 1.6793 (inf) time: 0.5025 [2021-03-26 11:35:04 swin_small_patch4_window7_224] INFO: Epoch: [175] [1170/1251] eta: 0:00:41 lr: 0.000372 loss: 2.8617 (3.1768) grad_norm: 1.6281 (inf) time: 0.4994 [2021-03-26 11:35:09 swin_small_patch4_window7_224] INFO: Epoch: [175] [1180/1251] eta: 0:00:36 lr: 0.000372 loss: 3.1606 (3.1764) grad_norm: 1.6080 (inf) time: 0.5078 [2021-03-26 11:35:14 swin_small_patch4_window7_224] INFO: Epoch: [175] [1190/1251] eta: 0:00:31 lr: 0.000372 loss: 3.1606 (3.1769) grad_norm: 1.6636 (inf) time: 0.5098 [2021-03-26 11:35:19 swin_small_patch4_window7_224] INFO: Epoch: [175] [1200/1251] eta: 0:00:25 lr: 0.000372 loss: 3.1858 (3.1775) grad_norm: 1.6636 (inf) time: 0.5050 [2021-03-26 11:35:24 swin_small_patch4_window7_224] INFO: Epoch: [175] [1210/1251] eta: 0:00:20 lr: 0.000372 loss: 3.1741 (3.1751) grad_norm: 1.5445 (inf) time: 0.5012 [2021-03-26 11:35:29 swin_small_patch4_window7_224] INFO: Epoch: [175] [1220/1251] eta: 0:00:15 lr: 0.000372 loss: 2.8890 (3.1748) grad_norm: 1.5382 (inf) time: 0.4983 [2021-03-26 11:35:34 swin_small_patch4_window7_224] INFO: Epoch: [175] [1230/1251] eta: 0:00:10 lr: 0.000372 loss: 3.3829 (3.1761) grad_norm: 1.5454 (inf) time: 0.4971 [2021-03-26 11:35:39 swin_small_patch4_window7_224] INFO: Epoch: [175] [1240/1251] eta: 0:00:05 lr: 0.000372 loss: 3.3829 (3.1748) grad_norm: 1.5622 (inf) time: 0.5003 [2021-03-26 11:35:44 swin_small_patch4_window7_224] INFO: Epoch: [175] [1250/1251] eta: 0:00:00 lr: 0.000372 loss: 3.1262 (3.1763) grad_norm: 1.6492 (inf) time: 0.5045 [2021-03-26 11:36:34 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.6784 (0.6784) acc1: 84.3750 (84.3750) acc5: 98.4375 (98.4375) [2021-03-26 11:36:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8963 (0.8452) acc1: 79.6875 (80.3977) acc5: 95.3125 (95.1705) [2021-03-26 11:36:37 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.9198 (0.8715) acc1: 78.1250 (79.2411) acc5: 95.3125 (95.4613) [2021-03-26 11:36:38 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8305 (0.8654) acc1: 78.1250 (79.6371) acc5: 95.3125 (95.0605) [2021-03-26 11:36:39 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8495 (0.8724) acc1: 79.6875 (79.3445) acc5: 95.3125 (95.0838) [2021-03-26 11:36:40 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8676 (0.8772) acc1: 78.1250 (79.0720) acc5: 95.3125 (95.1040) [2021-03-26 11:36:47 swin_small_patch4_window7_224] INFO: * Acc@1 79.364 Acc@5 95.044 loss 0.869 [2021-03-26 11:36:47 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.4% [2021-03-26 11:36:47 swin_small_patch4_window7_224] INFO: Max accuracy: 79.54% [2021-03-26 11:36:51 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 0/1251] eta: 1:24:57 lr: 0.000372 loss: 3.2647 (3.2647) grad_norm: 1.5712 (1.5712) time: 4.0749 [2021-03-26 11:36:57 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 10/1251] eta: 0:17:44 lr: 0.000372 loss: 3.2647 (3.0797) grad_norm: 1.5982 (1.6429) time: 0.8574 [2021-03-26 11:37:02 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 20/1251] eta: 0:14:09 lr: 0.000372 loss: 3.2277 (3.1514) grad_norm: 1.6131 (1.6788) time: 0.5207 [2021-03-26 11:37:07 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 30/1251] eta: 0:12:55 lr: 0.000372 loss: 3.1925 (3.0749) grad_norm: 1.6297 (1.6854) time: 0.5123 [2021-03-26 11:37:12 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 40/1251] eta: 0:12:10 lr: 0.000372 loss: 3.2440 (3.1593) grad_norm: 1.7230 (1.6896) time: 0.5123 [2021-03-26 11:37:17 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 50/1251] eta: 0:11:45 lr: 0.000372 loss: 3.3311 (3.1898) grad_norm: 1.6409 (1.6864) time: 0.5133 [2021-03-26 11:37:22 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 60/1251] eta: 0:11:24 lr: 0.000372 loss: 3.2253 (3.1743) grad_norm: 1.5699 (1.6712) time: 0.5157 [2021-03-26 11:37:27 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 70/1251] eta: 0:11:06 lr: 0.000372 loss: 3.2253 (3.2007) grad_norm: 1.6024 (1.6671) time: 0.5064 [2021-03-26 11:37:33 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 80/1251] eta: 0:10:52 lr: 0.000372 loss: 3.3232 (3.2047) grad_norm: 1.6915 (1.6719) time: 0.5058 [2021-03-26 11:37:38 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 90/1251] eta: 0:10:40 lr: 0.000372 loss: 3.2141 (3.1907) grad_norm: 1.6780 (1.6747) time: 0.5058 [2021-03-26 11:37:43 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 100/1251] eta: 0:10:29 lr: 0.000371 loss: 3.2249 (3.2010) grad_norm: 1.6722 (1.6789) time: 0.5044 [2021-03-26 11:37:48 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 110/1251] eta: 0:10:21 lr: 0.000371 loss: 3.2249 (3.1798) grad_norm: 1.6701 (1.6828) time: 0.5123 [2021-03-26 11:37:53 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 120/1251] eta: 0:10:12 lr: 0.000371 loss: 2.9820 (3.1704) grad_norm: 1.6298 (1.6735) time: 0.5148 [2021-03-26 11:37:58 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 130/1251] eta: 0:10:04 lr: 0.000371 loss: 3.3133 (3.1892) grad_norm: 1.6088 (1.6725) time: 0.5105 [2021-03-26 11:38:03 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 140/1251] eta: 0:09:56 lr: 0.000371 loss: 3.3133 (3.1895) grad_norm: 1.6637 (1.6739) time: 0.5059 [2021-03-26 11:38:08 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 150/1251] eta: 0:09:48 lr: 0.000371 loss: 3.1039 (3.1771) grad_norm: 1.6869 (1.6770) time: 0.5014 [2021-03-26 11:38:13 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 160/1251] eta: 0:09:40 lr: 0.000371 loss: 3.0668 (3.1642) grad_norm: 1.6466 (1.6700) time: 0.5007 [2021-03-26 11:38:18 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 170/1251] eta: 0:09:33 lr: 0.000371 loss: 3.0668 (3.1620) grad_norm: 1.6037 (1.6683) time: 0.5024 [2021-03-26 11:38:23 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 180/1251] eta: 0:09:26 lr: 0.000371 loss: 3.3757 (3.1634) grad_norm: 1.6132 (1.6705) time: 0.5033 [2021-03-26 11:38:28 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 190/1251] eta: 0:09:20 lr: 0.000371 loss: 3.3511 (3.1665) grad_norm: 1.6303 (1.6734) time: 0.5117 [2021-03-26 11:38:33 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 200/1251] eta: 0:09:14 lr: 0.000371 loss: 3.2289 (3.1643) grad_norm: 1.6344 (1.6712) time: 0.5165 [2021-03-26 11:38:38 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 210/1251] eta: 0:09:07 lr: 0.000371 loss: 3.1242 (3.1661) grad_norm: 1.6415 (1.6714) time: 0.5059 [2021-03-26 11:38:43 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 220/1251] eta: 0:09:01 lr: 0.000371 loss: 3.1242 (3.1630) grad_norm: 1.6521 (1.6728) time: 0.4999 [2021-03-26 11:38:49 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 230/1251] eta: 0:08:55 lr: 0.000371 loss: 3.2687 (3.1693) grad_norm: 1.7216 (1.6756) time: 0.5085 [2021-03-26 11:38:54 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 240/1251] eta: 0:08:49 lr: 0.000371 loss: 3.1253 (3.1574) grad_norm: 1.6237 (1.6719) time: 0.5115 [2021-03-26 11:38:59 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 250/1251] eta: 0:08:44 lr: 0.000371 loss: 2.9437 (3.1545) grad_norm: 1.6241 (1.6730) time: 0.5114 [2021-03-26 11:39:04 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 260/1251] eta: 0:08:38 lr: 0.000371 loss: 3.3179 (3.1638) grad_norm: 1.6804 (1.6750) time: 0.5115 [2021-03-26 11:39:09 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 270/1251] eta: 0:08:32 lr: 0.000371 loss: 3.3619 (3.1766) grad_norm: 1.6331 (1.6694) time: 0.5072 [2021-03-26 11:39:14 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 280/1251] eta: 0:08:26 lr: 0.000371 loss: 3.4070 (3.1829) grad_norm: 1.5884 (1.6721) time: 0.5042 [2021-03-26 11:39:19 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 290/1251] eta: 0:08:20 lr: 0.000371 loss: 3.3078 (3.1813) grad_norm: 1.6354 (1.6702) time: 0.4973 [2021-03-26 11:39:24 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 300/1251] eta: 0:08:14 lr: 0.000371 loss: 3.0688 (3.1720) grad_norm: 1.5980 (1.6679) time: 0.5006 [2021-03-26 11:39:29 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 310/1251] eta: 0:08:09 lr: 0.000371 loss: 3.1176 (3.1701) grad_norm: 1.6640 (1.6722) time: 0.5076 [2021-03-26 11:39:34 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 320/1251] eta: 0:08:03 lr: 0.000371 loss: 3.4734 (3.1827) grad_norm: 1.7630 (1.6768) time: 0.5022 [2021-03-26 11:39:39 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 330/1251] eta: 0:07:57 lr: 0.000371 loss: 3.4927 (3.1779) grad_norm: 1.8005 (1.6800) time: 0.4984 [2021-03-26 11:39:44 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 340/1251] eta: 0:07:52 lr: 0.000371 loss: 3.2967 (3.1846) grad_norm: 1.6556 (1.6772) time: 0.5051 [2021-03-26 11:39:49 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 350/1251] eta: 0:07:47 lr: 0.000370 loss: 3.2904 (3.1866) grad_norm: 1.5538 (1.6747) time: 0.5160 [2021-03-26 11:39:54 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 360/1251] eta: 0:07:41 lr: 0.000370 loss: 3.3629 (3.1906) grad_norm: 1.6459 (1.6775) time: 0.5141 [2021-03-26 11:40:00 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 370/1251] eta: 0:07:36 lr: 0.000370 loss: 3.5575 (3.1978) grad_norm: 1.7813 (1.6821) time: 0.5105 [2021-03-26 11:40:05 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 380/1251] eta: 0:07:31 lr: 0.000370 loss: 3.3119 (3.1938) grad_norm: 1.6550 (1.6798) time: 0.5113 [2021-03-26 11:40:10 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 390/1251] eta: 0:07:25 lr: 0.000370 loss: 3.3119 (3.1969) grad_norm: 1.6003 (1.6771) time: 0.5047 [2021-03-26 11:40:15 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 400/1251] eta: 0:07:19 lr: 0.000370 loss: 3.4079 (3.1952) grad_norm: 1.6033 (1.6790) time: 0.4993 [2021-03-26 11:40:20 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 410/1251] eta: 0:07:14 lr: 0.000370 loss: 3.1166 (3.1945) grad_norm: 1.6504 (1.6793) time: 0.4986 [2021-03-26 11:40:25 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 420/1251] eta: 0:07:09 lr: 0.000370 loss: 3.1619 (3.1964) grad_norm: 1.6467 (1.6802) time: 0.5106 [2021-03-26 11:40:30 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 430/1251] eta: 0:07:03 lr: 0.000370 loss: 3.2246 (3.1969) grad_norm: 1.6460 (1.6789) time: 0.5136 [2021-03-26 11:40:35 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 440/1251] eta: 0:06:58 lr: 0.000370 loss: 3.2455 (3.1999) grad_norm: 1.5765 (1.6784) time: 0.5085 [2021-03-26 11:40:40 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 450/1251] eta: 0:06:53 lr: 0.000370 loss: 3.4861 (3.2050) grad_norm: 1.5863 (1.6765) time: 0.5080 [2021-03-26 11:40:45 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 460/1251] eta: 0:06:47 lr: 0.000370 loss: 3.3443 (3.2027) grad_norm: 1.6265 (1.6768) time: 0.5009 [2021-03-26 11:40:50 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 470/1251] eta: 0:06:42 lr: 0.000370 loss: 3.2832 (3.2065) grad_norm: 1.6369 (1.6776) time: 0.4987 [2021-03-26 11:40:55 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 480/1251] eta: 0:06:37 lr: 0.000370 loss: 3.2259 (3.2052) grad_norm: 1.6527 (1.6783) time: 0.5038 [2021-03-26 11:41:00 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 490/1251] eta: 0:06:31 lr: 0.000370 loss: 3.3057 (3.2098) grad_norm: 1.6648 (1.6785) time: 0.5046 [2021-03-26 11:41:05 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 500/1251] eta: 0:06:26 lr: 0.000370 loss: 3.3832 (3.2109) grad_norm: 1.6271 (1.6790) time: 0.5049 [2021-03-26 11:41:10 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 510/1251] eta: 0:06:21 lr: 0.000370 loss: 2.9247 (3.2021) grad_norm: 1.5848 (1.6770) time: 0.5053 [2021-03-26 11:41:15 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 520/1251] eta: 0:06:15 lr: 0.000370 loss: 2.6327 (3.1972) grad_norm: 1.5741 (1.6768) time: 0.5027 [2021-03-26 11:41:20 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 530/1251] eta: 0:06:10 lr: 0.000370 loss: 3.1711 (3.1976) grad_norm: 1.6674 (1.6790) time: 0.5034 [2021-03-26 11:41:25 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 540/1251] eta: 0:06:05 lr: 0.000370 loss: 3.4311 (3.2053) grad_norm: 1.7124 (1.6803) time: 0.5066 [2021-03-26 11:41:31 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 550/1251] eta: 0:06:00 lr: 0.000370 loss: 3.5005 (3.2076) grad_norm: 1.6687 (1.6798) time: 0.5163 [2021-03-26 11:41:36 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 560/1251] eta: 0:05:55 lr: 0.000370 loss: 2.9894 (3.2041) grad_norm: 1.6367 (1.6803) time: 0.5223 [2021-03-26 11:41:41 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 570/1251] eta: 0:05:50 lr: 0.000370 loss: 3.1517 (3.2032) grad_norm: 1.5581 (1.6790) time: 0.5189 [2021-03-26 11:41:46 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 580/1251] eta: 0:05:44 lr: 0.000370 loss: 3.3495 (3.2019) grad_norm: 1.5956 (1.6794) time: 0.5085 [2021-03-26 11:41:51 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 590/1251] eta: 0:05:39 lr: 0.000370 loss: 3.3194 (3.2003) grad_norm: 1.7316 (1.6805) time: 0.5047 [2021-03-26 11:41:56 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 600/1251] eta: 0:05:34 lr: 0.000369 loss: 3.3194 (3.2019) grad_norm: 1.6523 (1.6810) time: 0.5095 [2021-03-26 11:42:01 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 610/1251] eta: 0:05:29 lr: 0.000369 loss: 3.0708 (3.1979) grad_norm: 1.5915 (1.6800) time: 0.5065 [2021-03-26 11:42:06 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 620/1251] eta: 0:05:23 lr: 0.000369 loss: 2.8799 (3.1943) grad_norm: 1.6257 (1.6796) time: 0.5013 [2021-03-26 11:42:11 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 630/1251] eta: 0:05:18 lr: 0.000369 loss: 3.0155 (3.1934) grad_norm: 1.6247 (1.6782) time: 0.4964 [2021-03-26 11:42:16 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 640/1251] eta: 0:05:13 lr: 0.000369 loss: 3.2962 (3.1903) grad_norm: 1.6160 (1.6781) time: 0.5014 [2021-03-26 11:42:21 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 650/1251] eta: 0:05:08 lr: 0.000369 loss: 3.4300 (3.1973) grad_norm: 1.6500 (1.6783) time: 0.5098 [2021-03-26 11:42:26 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 660/1251] eta: 0:05:03 lr: 0.000369 loss: 3.4785 (3.1976) grad_norm: 1.6509 (1.6774) time: 0.5047 [2021-03-26 11:42:32 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 670/1251] eta: 0:04:57 lr: 0.000369 loss: 3.1228 (3.1953) grad_norm: 1.6452 (1.6766) time: 0.5031 [2021-03-26 11:42:37 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 680/1251] eta: 0:04:52 lr: 0.000369 loss: 3.2100 (3.1962) grad_norm: 1.6452 (1.6769) time: 0.5056 [2021-03-26 11:42:42 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 690/1251] eta: 0:04:47 lr: 0.000369 loss: 3.4049 (3.1984) grad_norm: 1.6849 (1.6769) time: 0.5004 [2021-03-26 11:42:47 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 700/1251] eta: 0:04:42 lr: 0.000369 loss: 3.2945 (3.1944) grad_norm: 1.6733 (1.6765) time: 0.4981 [2021-03-26 11:42:52 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 710/1251] eta: 0:04:37 lr: 0.000369 loss: 2.9856 (3.1940) grad_norm: 1.6223 (1.6756) time: 0.5086 [2021-03-26 11:42:57 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 720/1251] eta: 0:04:31 lr: 0.000369 loss: 3.3752 (3.1958) grad_norm: 1.6835 (1.6769) time: 0.5065 [2021-03-26 11:43:02 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 730/1251] eta: 0:04:26 lr: 0.000369 loss: 3.3708 (3.1955) grad_norm: 1.7939 (1.6772) time: 0.4996 [2021-03-26 11:43:07 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 740/1251] eta: 0:04:21 lr: 0.000369 loss: 3.2536 (3.1958) grad_norm: 1.7039 (1.6778) time: 0.5189 [2021-03-26 11:43:12 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 750/1251] eta: 0:04:16 lr: 0.000369 loss: 3.1885 (3.1957) grad_norm: 1.6393 (1.6770) time: 0.5252 [2021-03-26 11:43:17 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 760/1251] eta: 0:04:11 lr: 0.000369 loss: 3.1885 (3.1959) grad_norm: 1.6274 (1.6771) time: 0.5074 [2021-03-26 11:43:22 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 770/1251] eta: 0:04:06 lr: 0.000369 loss: 3.1299 (3.1946) grad_norm: 1.6650 (1.6771) time: 0.5042 [2021-03-26 11:43:27 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 780/1251] eta: 0:04:01 lr: 0.000369 loss: 3.1672 (3.1941) grad_norm: 1.6728 (1.6777) time: 0.5028 [2021-03-26 11:43:32 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 790/1251] eta: 0:03:55 lr: 0.000369 loss: 3.1672 (3.1915) grad_norm: 1.6204 (1.6762) time: 0.5001 [2021-03-26 11:43:37 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 800/1251] eta: 0:03:50 lr: 0.000369 loss: 3.3757 (3.1944) grad_norm: 1.6204 (1.6759) time: 0.5066 [2021-03-26 11:43:42 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 810/1251] eta: 0:03:45 lr: 0.000369 loss: 3.3757 (3.1910) grad_norm: 1.6214 (1.6748) time: 0.5066 [2021-03-26 11:43:48 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 820/1251] eta: 0:03:40 lr: 0.000369 loss: 3.1421 (3.1913) grad_norm: 1.6242 (1.6758) time: 0.5095 [2021-03-26 11:43:53 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 830/1251] eta: 0:03:35 lr: 0.000369 loss: 3.1421 (3.1910) grad_norm: 1.7244 (1.6757) time: 0.5119 [2021-03-26 11:43:58 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 840/1251] eta: 0:03:30 lr: 0.000369 loss: 3.0099 (3.1873) grad_norm: 1.6001 (1.6747) time: 0.5065 [2021-03-26 11:44:03 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 850/1251] eta: 0:03:25 lr: 0.000368 loss: 2.7567 (3.1839) grad_norm: 1.6126 (1.6754) time: 0.5086 [2021-03-26 11:44:08 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 860/1251] eta: 0:03:19 lr: 0.000368 loss: 3.2604 (3.1869) grad_norm: 1.6126 (1.6744) time: 0.5056 [2021-03-26 11:44:13 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 870/1251] eta: 0:03:14 lr: 0.000368 loss: 3.3646 (3.1862) grad_norm: 1.5890 (1.6743) time: 0.4985 [2021-03-26 11:44:18 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 880/1251] eta: 0:03:09 lr: 0.000368 loss: 3.4405 (3.1873) grad_norm: 1.5890 (1.6742) time: 0.4995 [2021-03-26 11:44:23 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 890/1251] eta: 0:03:04 lr: 0.000368 loss: 3.3981 (3.1873) grad_norm: 1.5803 (1.6733) time: 0.5018 [2021-03-26 11:44:28 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 900/1251] eta: 0:02:59 lr: 0.000368 loss: 3.1345 (3.1861) grad_norm: 1.5812 (1.6722) time: 0.5020 [2021-03-26 11:44:33 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 910/1251] eta: 0:02:54 lr: 0.000368 loss: 3.1883 (3.1851) grad_norm: 1.6306 (1.6735) time: 0.5055 [2021-03-26 11:44:38 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 920/1251] eta: 0:02:49 lr: 0.000368 loss: 3.3880 (3.1878) grad_norm: 1.6708 (1.6727) time: 0.5105 [2021-03-26 11:44:43 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 930/1251] eta: 0:02:43 lr: 0.000368 loss: 3.3532 (3.1863) grad_norm: 1.5239 (1.6716) time: 0.5064 [2021-03-26 11:44:48 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 940/1251] eta: 0:02:38 lr: 0.000368 loss: 3.1448 (3.1883) grad_norm: 1.5899 (1.6715) time: 0.5080 [2021-03-26 11:44:53 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 950/1251] eta: 0:02:33 lr: 0.000368 loss: 3.1884 (3.1886) grad_norm: 1.6881 (1.6727) time: 0.5056 [2021-03-26 11:44:58 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 960/1251] eta: 0:02:28 lr: 0.000368 loss: 3.0960 (3.1871) grad_norm: 1.6401 (1.6718) time: 0.5025 [2021-03-26 11:45:03 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 970/1251] eta: 0:02:23 lr: 0.000368 loss: 3.3182 (3.1888) grad_norm: 1.5707 (1.6708) time: 0.5111 [2021-03-26 11:45:09 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 980/1251] eta: 0:02:18 lr: 0.000368 loss: 3.3013 (3.1864) grad_norm: 1.6011 (1.6707) time: 0.5120 [2021-03-26 11:45:14 swin_small_patch4_window7_224] INFO: Epoch: [176] [ 990/1251] eta: 0:02:13 lr: 0.000368 loss: 3.0482 (3.1874) grad_norm: 1.6318 (1.6711) time: 0.5100 [2021-03-26 11:45:19 swin_small_patch4_window7_224] INFO: Epoch: [176] [1000/1251] eta: 0:02:08 lr: 0.000368 loss: 3.3286 (3.1873) grad_norm: 1.6896 (1.6727) time: 0.5067 [2021-03-26 11:45:24 swin_small_patch4_window7_224] INFO: Epoch: [176] [1010/1251] eta: 0:02:03 lr: 0.000368 loss: 3.3286 (3.1881) grad_norm: 1.7550 (1.6736) time: 0.4999 [2021-03-26 11:45:29 swin_small_patch4_window7_224] INFO: Epoch: [176] [1020/1251] eta: 0:01:57 lr: 0.000368 loss: 3.2608 (3.1882) grad_norm: 1.6604 (1.6740) time: 0.4978 [2021-03-26 11:45:34 swin_small_patch4_window7_224] INFO: Epoch: [176] [1030/1251] eta: 0:01:52 lr: 0.000368 loss: 3.2570 (3.1895) grad_norm: 1.6585 (1.6744) time: 0.5049 [2021-03-26 11:45:39 swin_small_patch4_window7_224] INFO: Epoch: [176] [1040/1251] eta: 0:01:47 lr: 0.000368 loss: 3.3542 (3.1893) grad_norm: 1.6877 (1.6750) time: 0.5090 [2021-03-26 11:45:44 swin_small_patch4_window7_224] INFO: Epoch: [176] [1050/1251] eta: 0:01:42 lr: 0.000368 loss: 3.2793 (3.1902) grad_norm: 1.6662 (1.6747) time: 0.5109 [2021-03-26 11:45:49 swin_small_patch4_window7_224] INFO: Epoch: [176] [1060/1251] eta: 0:01:37 lr: 0.000368 loss: 3.2552 (3.1900) grad_norm: 1.6196 (1.6740) time: 0.5151 [2021-03-26 11:45:54 swin_small_patch4_window7_224] INFO: Epoch: [176] [1070/1251] eta: 0:01:32 lr: 0.000368 loss: 3.1585 (3.1889) grad_norm: 1.6057 (1.6736) time: 0.5061 [2021-03-26 11:45:59 swin_small_patch4_window7_224] INFO: Epoch: [176] [1080/1251] eta: 0:01:27 lr: 0.000368 loss: 3.2700 (3.1899) grad_norm: 1.6538 (1.6743) time: 0.4993 [2021-03-26 11:46:04 swin_small_patch4_window7_224] INFO: Epoch: [176] [1090/1251] eta: 0:01:22 lr: 0.000368 loss: 3.2940 (3.1906) grad_norm: 1.6453 (1.6732) time: 0.5021 [2021-03-26 11:46:09 swin_small_patch4_window7_224] INFO: Epoch: [176] [1100/1251] eta: 0:01:17 lr: 0.000368 loss: 3.2716 (3.1896) grad_norm: 1.5943 (1.6732) time: 0.5071 [2021-03-26 11:46:14 swin_small_patch4_window7_224] INFO: Epoch: [176] [1110/1251] eta: 0:01:11 lr: 0.000367 loss: 3.1881 (3.1911) grad_norm: 1.5807 (1.6727) time: 0.5113 [2021-03-26 11:46:19 swin_small_patch4_window7_224] INFO: Epoch: [176] [1120/1251] eta: 0:01:06 lr: 0.000367 loss: 3.2621 (3.1901) grad_norm: 1.5584 (1.6723) time: 0.5071 [2021-03-26 11:46:24 swin_small_patch4_window7_224] INFO: Epoch: [176] [1130/1251] eta: 0:01:01 lr: 0.000367 loss: 3.3906 (3.1917) grad_norm: 1.5952 (1.6724) time: 0.5035 [2021-03-26 11:46:29 swin_small_patch4_window7_224] INFO: Epoch: [176] [1140/1251] eta: 0:00:56 lr: 0.000367 loss: 3.4177 (3.1924) grad_norm: 1.5952 (1.6713) time: 0.5009 [2021-03-26 11:46:34 swin_small_patch4_window7_224] INFO: Epoch: [176] [1150/1251] eta: 0:00:51 lr: 0.000367 loss: 3.1431 (3.1904) grad_norm: 1.5636 (1.6714) time: 0.4975 [2021-03-26 11:46:40 swin_small_patch4_window7_224] INFO: Epoch: [176] [1160/1251] eta: 0:00:46 lr: 0.000367 loss: 2.8952 (3.1878) grad_norm: 1.6473 (1.6725) time: 0.5059 [2021-03-26 11:46:45 swin_small_patch4_window7_224] INFO: Epoch: [176] [1170/1251] eta: 0:00:41 lr: 0.000367 loss: 3.2319 (3.1894) grad_norm: 1.6604 (1.6720) time: 0.5066 [2021-03-26 11:46:50 swin_small_patch4_window7_224] INFO: Epoch: [176] [1180/1251] eta: 0:00:36 lr: 0.000367 loss: 3.1980 (3.1893) grad_norm: 1.5665 (1.6710) time: 0.5032 [2021-03-26 11:46:55 swin_small_patch4_window7_224] INFO: Epoch: [176] [1190/1251] eta: 0:00:31 lr: 0.000367 loss: 2.9819 (3.1874) grad_norm: 1.5149 (1.6699) time: 0.5063 [2021-03-26 11:47:00 swin_small_patch4_window7_224] INFO: Epoch: [176] [1200/1251] eta: 0:00:25 lr: 0.000367 loss: 3.1049 (3.1875) grad_norm: 1.5487 (1.6697) time: 0.5069 [2021-03-26 11:47:05 swin_small_patch4_window7_224] INFO: Epoch: [176] [1210/1251] eta: 0:00:20 lr: 0.000367 loss: 3.1943 (3.1869) grad_norm: 1.6280 (1.6698) time: 0.5063 [2021-03-26 11:47:10 swin_small_patch4_window7_224] INFO: Epoch: [176] [1220/1251] eta: 0:00:15 lr: 0.000367 loss: 3.5920 (3.1893) grad_norm: 1.6919 (1.6701) time: 0.5067 [2021-03-26 11:47:15 swin_small_patch4_window7_224] INFO: Epoch: [176] [1230/1251] eta: 0:00:10 lr: 0.000367 loss: 3.5029 (3.1904) grad_norm: 1.6391 (1.6701) time: 0.5049 [2021-03-26 11:47:20 swin_small_patch4_window7_224] INFO: Epoch: [176] [1240/1251] eta: 0:00:05 lr: 0.000367 loss: 3.2602 (3.1891) grad_norm: 1.6279 (1.6706) time: 0.5060 [2021-03-26 11:47:25 swin_small_patch4_window7_224] INFO: Epoch: [176] [1250/1251] eta: 0:00:00 lr: 0.000367 loss: 3.1045 (3.1890) grad_norm: 1.6186 (1.6704) time: 0.5113 [2021-03-26 11:47:33 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 1.0710 (1.0710) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-26 11:47:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9425 (0.9480) acc1: 76.5625 (77.4148) acc5: 93.7500 (93.8920) [2021-03-26 11:47:39 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8754 (0.9252) acc1: 78.1250 (77.5298) acc5: 93.7500 (94.1964) [2021-03-26 11:47:41 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8578 (0.8949) acc1: 78.1250 (78.1754) acc5: 95.3125 (94.7077) [2021-03-26 11:47:42 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8285 (0.8789) acc1: 81.2500 (78.9634) acc5: 95.3125 (94.7027) [2021-03-26 11:47:43 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8443 (0.8759) acc1: 81.2500 (78.6560) acc5: 95.3125 (94.9760) [2021-03-26 11:47:52 swin_small_patch4_window7_224] INFO: * Acc@1 79.544 Acc@5 95.056 loss 0.864 [2021-03-26 11:47:52 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-26 11:47:52 swin_small_patch4_window7_224] INFO: Max accuracy: 79.54% [2021-03-26 11:47:56 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 0/1251] eta: 1:32:13 lr: 0.000367 loss: 3.4880 (3.4880) grad_norm: 2.0086 (2.0086) time: 4.4233 [2021-03-26 11:48:02 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 10/1251] eta: 0:17:55 lr: 0.000367 loss: 3.0814 (3.0400) grad_norm: 1.7200 (1.7022) time: 0.8667 [2021-03-26 11:48:07 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 20/1251] eta: 0:14:22 lr: 0.000367 loss: 3.1296 (3.1302) grad_norm: 1.6909 (1.6903) time: 0.5141 [2021-03-26 11:48:12 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 30/1251] eta: 0:12:57 lr: 0.000367 loss: 3.1296 (3.1216) grad_norm: 1.6992 (1.7084) time: 0.5100 [2021-03-26 11:48:17 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 40/1251] eta: 0:12:11 lr: 0.000367 loss: 3.1771 (3.1287) grad_norm: 1.6634 (1.6915) time: 0.5034 [2021-03-26 11:48:22 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 50/1251] eta: 0:11:44 lr: 0.000367 loss: 3.1771 (3.1128) grad_norm: 1.6634 (1.6990) time: 0.5081 [2021-03-26 11:48:27 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 60/1251] eta: 0:11:23 lr: 0.000367 loss: 3.1194 (3.1380) grad_norm: 1.6846 (1.6904) time: 0.5123 [2021-03-26 11:48:32 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 70/1251] eta: 0:11:07 lr: 0.000367 loss: 3.2937 (3.1330) grad_norm: 1.6818 (1.7011) time: 0.5113 [2021-03-26 11:48:37 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 80/1251] eta: 0:10:54 lr: 0.000367 loss: 3.2910 (3.1646) grad_norm: 1.7667 (1.7093) time: 0.5117 [2021-03-26 11:48:42 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 90/1251] eta: 0:10:40 lr: 0.000367 loss: 3.2624 (3.1733) grad_norm: 1.6608 (1.6971) time: 0.5052 [2021-03-26 11:48:47 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 100/1251] eta: 0:10:30 lr: 0.000367 loss: 2.9861 (3.1466) grad_norm: 1.6251 (1.6926) time: 0.5023 [2021-03-26 11:48:52 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 110/1251] eta: 0:10:19 lr: 0.000366 loss: 2.9769 (3.1499) grad_norm: 1.5455 (1.6779) time: 0.5039 [2021-03-26 11:48:57 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 120/1251] eta: 0:10:11 lr: 0.000366 loss: 3.2756 (3.1411) grad_norm: 1.5602 (1.6744) time: 0.5059 [2021-03-26 11:49:03 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 130/1251] eta: 0:10:03 lr: 0.000366 loss: 3.2438 (3.1439) grad_norm: 1.6268 (1.6739) time: 0.5135 [2021-03-26 11:49:08 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 140/1251] eta: 0:09:54 lr: 0.000366 loss: 3.1462 (3.1360) grad_norm: 1.6716 (1.6760) time: 0.5047 [2021-03-26 11:49:13 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 150/1251] eta: 0:09:47 lr: 0.000366 loss: 3.2352 (3.1461) grad_norm: 1.6914 (1.6750) time: 0.4997 [2021-03-26 11:49:18 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 160/1251] eta: 0:09:39 lr: 0.000366 loss: 3.2842 (3.1374) grad_norm: 1.6956 (1.6781) time: 0.5011 [2021-03-26 11:49:23 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 170/1251] eta: 0:09:33 lr: 0.000366 loss: 3.4139 (3.1485) grad_norm: 1.6345 (1.6773) time: 0.5075 [2021-03-26 11:49:28 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 180/1251] eta: 0:09:27 lr: 0.000366 loss: 3.4541 (3.1586) grad_norm: 1.5906 (1.6742) time: 0.5170 [2021-03-26 11:49:33 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 190/1251] eta: 0:09:20 lr: 0.000366 loss: 3.2452 (3.1562) grad_norm: 1.5834 (1.6710) time: 0.5089 [2021-03-26 11:49:38 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 200/1251] eta: 0:09:14 lr: 0.000366 loss: 3.1846 (3.1599) grad_norm: 1.5834 (1.6665) time: 0.5067 [2021-03-26 11:49:43 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 210/1251] eta: 0:09:07 lr: 0.000366 loss: 3.4035 (3.1728) grad_norm: 1.5375 (1.6633) time: 0.5087 [2021-03-26 11:49:48 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 220/1251] eta: 0:09:01 lr: 0.000366 loss: 3.4307 (3.1839) grad_norm: 1.5229 (1.6601) time: 0.5034 [2021-03-26 11:49:53 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 230/1251] eta: 0:08:55 lr: 0.000366 loss: 3.2902 (3.1949) grad_norm: 1.5157 (1.6546) time: 0.5079 [2021-03-26 11:49:58 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 240/1251] eta: 0:08:49 lr: 0.000366 loss: 3.3512 (3.1994) grad_norm: 1.5157 (1.6532) time: 0.5117 [2021-03-26 11:50:04 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 250/1251] eta: 0:08:44 lr: 0.000366 loss: 3.4843 (3.1986) grad_norm: 1.5843 (1.6512) time: 0.5102 [2021-03-26 11:50:09 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 260/1251] eta: 0:08:38 lr: 0.000366 loss: 3.5429 (3.2051) grad_norm: 1.5843 (1.6479) time: 0.5096 [2021-03-26 11:50:14 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 270/1251] eta: 0:08:32 lr: 0.000366 loss: 3.3800 (3.2020) grad_norm: 1.5163 (1.6422) time: 0.5065 [2021-03-26 11:50:19 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 280/1251] eta: 0:08:26 lr: 0.000366 loss: 3.1761 (3.1955) grad_norm: 1.5785 (1.6448) time: 0.5007 [2021-03-26 11:50:24 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 290/1251] eta: 0:08:20 lr: 0.000366 loss: 3.3414 (3.1983) grad_norm: 1.6537 (1.6471) time: 0.4981 [2021-03-26 11:50:29 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 300/1251] eta: 0:08:14 lr: 0.000366 loss: 3.4128 (3.2070) grad_norm: 1.6336 (1.6474) time: 0.5047 [2021-03-26 11:50:34 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 310/1251] eta: 0:08:09 lr: 0.000366 loss: 3.3322 (3.1891) grad_norm: 1.6268 (1.6466) time: 0.5106 [2021-03-26 11:50:39 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 320/1251] eta: 0:08:03 lr: 0.000366 loss: 3.0238 (3.1888) grad_norm: 1.5534 (1.6432) time: 0.5104 [2021-03-26 11:50:44 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 330/1251] eta: 0:07:58 lr: 0.000366 loss: 3.1302 (3.1834) grad_norm: 1.5534 (1.6420) time: 0.5066 [2021-03-26 11:50:49 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 340/1251] eta: 0:07:52 lr: 0.000366 loss: 3.2753 (3.1879) grad_norm: 1.5742 (1.6404) time: 0.5038 [2021-03-26 11:50:54 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 350/1251] eta: 0:07:46 lr: 0.000366 loss: 3.2020 (3.1820) grad_norm: 1.6163 (1.6400) time: 0.5010 [2021-03-26 11:50:59 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 360/1251] eta: 0:07:41 lr: 0.000365 loss: 3.1271 (3.1790) grad_norm: 1.6019 (1.6389) time: 0.4998 [2021-03-26 11:51:04 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 370/1251] eta: 0:07:35 lr: 0.000365 loss: 3.1542 (3.1766) grad_norm: 1.6083 (1.6402) time: 0.5064 [2021-03-26 11:51:09 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 380/1251] eta: 0:07:30 lr: 0.000365 loss: 2.9910 (3.1724) grad_norm: 1.6126 (1.6382) time: 0.5089 [2021-03-26 11:51:14 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 390/1251] eta: 0:07:25 lr: 0.000365 loss: 3.1962 (3.1749) grad_norm: 1.5995 (1.6399) time: 0.5062 [2021-03-26 11:51:19 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 400/1251] eta: 0:07:19 lr: 0.000365 loss: 3.0899 (3.1693) grad_norm: 1.6127 (1.6378) time: 0.5049 [2021-03-26 11:51:24 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 410/1251] eta: 0:07:14 lr: 0.000365 loss: 3.0681 (3.1688) grad_norm: 1.6127 (1.6383) time: 0.5067 [2021-03-26 11:51:29 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 420/1251] eta: 0:07:08 lr: 0.000365 loss: 3.2217 (3.1669) grad_norm: 1.6156 (1.6374) time: 0.5081 [2021-03-26 11:51:34 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 430/1251] eta: 0:07:03 lr: 0.000365 loss: 3.2722 (3.1700) grad_norm: 1.6235 (1.6394) time: 0.5040 [2021-03-26 11:51:40 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 440/1251] eta: 0:06:58 lr: 0.000365 loss: 3.4711 (3.1731) grad_norm: 1.6507 (1.6379) time: 0.5050 [2021-03-26 11:51:45 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 450/1251] eta: 0:06:52 lr: 0.000365 loss: 3.2816 (3.1724) grad_norm: 1.5863 (1.6382) time: 0.5073 [2021-03-26 11:51:50 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 460/1251] eta: 0:06:47 lr: 0.000365 loss: 3.0178 (3.1648) grad_norm: 1.5968 (1.6376) time: 0.5037 [2021-03-26 11:51:55 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 470/1251] eta: 0:06:42 lr: 0.000365 loss: 3.0178 (3.1617) grad_norm: 1.6551 (1.6397) time: 0.5014 [2021-03-26 11:52:00 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 480/1251] eta: 0:06:36 lr: 0.000365 loss: 3.1257 (3.1613) grad_norm: 1.6826 (1.6413) time: 0.5008 [2021-03-26 11:52:05 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 490/1251] eta: 0:06:31 lr: 0.000365 loss: 3.3203 (3.1613) grad_norm: 1.6689 (1.6423) time: 0.5004 [2021-03-26 11:52:10 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 500/1251] eta: 0:06:26 lr: 0.000365 loss: 3.3102 (3.1609) grad_norm: 1.6540 (1.6435) time: 0.5019 [2021-03-26 11:52:15 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 510/1251] eta: 0:06:20 lr: 0.000365 loss: 3.3613 (3.1662) grad_norm: 1.6579 (1.6444) time: 0.4995 [2021-03-26 11:52:20 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 520/1251] eta: 0:06:15 lr: 0.000365 loss: 3.4049 (3.1712) grad_norm: 1.7354 (1.6464) time: 0.4994 [2021-03-26 11:52:25 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 530/1251] eta: 0:06:10 lr: 0.000365 loss: 3.4163 (3.1729) grad_norm: 1.6897 (1.6451) time: 0.5041 [2021-03-26 11:52:30 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 540/1251] eta: 0:06:05 lr: 0.000365 loss: 3.3713 (3.1736) grad_norm: 1.6128 (1.6446) time: 0.5098 [2021-03-26 11:52:35 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 550/1251] eta: 0:05:59 lr: 0.000365 loss: 3.4340 (3.1788) grad_norm: 1.5664 (1.6432) time: 0.5142 [2021-03-26 11:52:40 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 560/1251] eta: 0:05:54 lr: 0.000365 loss: 3.4792 (3.1801) grad_norm: 1.5664 (1.6424) time: 0.5155 [2021-03-26 11:52:45 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 570/1251] eta: 0:05:49 lr: 0.000365 loss: 3.4157 (3.1828) grad_norm: 1.6491 (1.6436) time: 0.5111 [2021-03-26 11:52:50 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 580/1251] eta: 0:05:44 lr: 0.000365 loss: 3.4644 (3.1892) grad_norm: 1.7260 (1.6452) time: 0.5070 [2021-03-26 11:52:55 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 590/1251] eta: 0:05:39 lr: 0.000365 loss: 3.3629 (3.1905) grad_norm: 1.6472 (1.6439) time: 0.5012 [2021-03-26 11:53:00 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 600/1251] eta: 0:05:33 lr: 0.000365 loss: 3.3298 (3.1933) grad_norm: 1.6219 (1.6464) time: 0.4994 [2021-03-26 11:53:05 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 610/1251] eta: 0:05:28 lr: 0.000364 loss: 3.1408 (3.1884) grad_norm: 1.6885 (1.6475) time: 0.5086 [2021-03-26 11:53:10 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 620/1251] eta: 0:05:23 lr: 0.000364 loss: 3.3563 (3.1937) grad_norm: 1.7222 (1.6491) time: 0.5066 [2021-03-26 11:53:15 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 630/1251] eta: 0:05:18 lr: 0.000364 loss: 3.5317 (3.1978) grad_norm: 1.6881 (1.6498) time: 0.4978 [2021-03-26 11:53:20 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 640/1251] eta: 0:05:12 lr: 0.000364 loss: 3.4902 (3.2008) grad_norm: 1.6185 (1.6491) time: 0.5000 [2021-03-26 11:53:25 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 650/1251] eta: 0:05:07 lr: 0.000364 loss: 3.4687 (3.2048) grad_norm: 1.5637 (1.6496) time: 0.5038 [2021-03-26 11:53:30 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 660/1251] eta: 0:05:02 lr: 0.000364 loss: 3.3206 (3.2030) grad_norm: 1.6244 (1.6497) time: 0.5008 [2021-03-26 11:53:36 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 670/1251] eta: 0:04:57 lr: 0.000364 loss: 3.1227 (3.2020) grad_norm: 1.6072 (1.6495) time: 0.5026 [2021-03-26 11:53:41 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 680/1251] eta: 0:04:52 lr: 0.000364 loss: 3.0981 (3.1999) grad_norm: 1.7055 (1.6504) time: 0.5059 [2021-03-26 11:53:46 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 690/1251] eta: 0:04:46 lr: 0.000364 loss: 3.1196 (3.1999) grad_norm: 1.6632 (1.6504) time: 0.4994 [2021-03-26 11:53:50 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 700/1251] eta: 0:04:41 lr: 0.000364 loss: 3.2669 (3.2001) grad_norm: 1.6202 (1.6504) time: 0.4945 [2021-03-26 11:53:55 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 710/1251] eta: 0:04:36 lr: 0.000364 loss: 3.3525 (3.2031) grad_norm: 1.6202 (1.6504) time: 0.4968 [2021-03-26 11:54:01 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 720/1251] eta: 0:04:31 lr: 0.000364 loss: 3.4209 (3.2050) grad_norm: 1.5843 (1.6498) time: 0.5027 [2021-03-26 11:54:06 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 730/1251] eta: 0:04:26 lr: 0.000364 loss: 3.3067 (3.2025) grad_norm: 1.6360 (1.6502) time: 0.5104 [2021-03-26 11:54:11 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 740/1251] eta: 0:04:21 lr: 0.000364 loss: 3.2602 (3.2029) grad_norm: 1.6480 (1.6500) time: 0.5133 [2021-03-26 11:54:16 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 750/1251] eta: 0:04:15 lr: 0.000364 loss: 3.2829 (3.2007) grad_norm: 1.5895 (1.6493) time: 0.5110 [2021-03-26 11:54:21 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 760/1251] eta: 0:04:10 lr: 0.000364 loss: 3.1287 (3.1996) grad_norm: 1.6007 (1.6496) time: 0.5178 [2021-03-26 11:54:26 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 770/1251] eta: 0:04:05 lr: 0.000364 loss: 3.2435 (3.1991) grad_norm: 1.6475 (1.6498) time: 0.5126 [2021-03-26 11:54:31 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 780/1251] eta: 0:04:00 lr: 0.000364 loss: 3.0851 (3.1967) grad_norm: 1.6258 (1.6500) time: 0.5010 [2021-03-26 11:54:36 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 790/1251] eta: 0:03:55 lr: 0.000364 loss: 3.2098 (3.1980) grad_norm: 1.7131 (1.6518) time: 0.5039 [2021-03-26 11:54:41 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 800/1251] eta: 0:03:50 lr: 0.000364 loss: 3.3120 (3.1999) grad_norm: 1.6993 (1.6521) time: 0.5139 [2021-03-26 11:54:46 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 810/1251] eta: 0:03:45 lr: 0.000364 loss: 3.4465 (3.2011) grad_norm: 1.5787 (1.6519) time: 0.5125 [2021-03-26 11:54:52 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 820/1251] eta: 0:03:40 lr: 0.000364 loss: 3.4817 (3.1998) grad_norm: 1.6403 (1.6514) time: 0.5106 [2021-03-26 11:54:57 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 830/1251] eta: 0:03:35 lr: 0.000364 loss: 3.0696 (3.1972) grad_norm: 1.6057 (1.6511) time: 0.5212 [2021-03-26 11:55:02 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 840/1251] eta: 0:03:30 lr: 0.000364 loss: 3.0584 (3.1936) grad_norm: 1.6035 (1.6504) time: 0.5121 [2021-03-26 11:55:07 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 850/1251] eta: 0:03:24 lr: 0.000364 loss: 3.1186 (3.1931) grad_norm: 1.5204 (1.6490) time: 0.4990 [2021-03-26 11:55:12 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 860/1251] eta: 0:03:19 lr: 0.000363 loss: 3.1186 (3.1913) grad_norm: 1.5662 (1.6491) time: 0.5021 [2021-03-26 11:55:17 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 870/1251] eta: 0:03:14 lr: 0.000363 loss: 2.9987 (3.1917) grad_norm: 1.7323 (1.6506) time: 0.5103 [2021-03-26 11:55:22 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 880/1251] eta: 0:03:09 lr: 0.000363 loss: 3.4247 (3.1935) grad_norm: 1.8013 (1.6520) time: 0.5127 [2021-03-26 11:55:27 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 890/1251] eta: 0:03:04 lr: 0.000363 loss: 3.4035 (3.1946) grad_norm: 1.6502 (1.6517) time: 0.5113 [2021-03-26 11:55:32 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 900/1251] eta: 0:02:59 lr: 0.000363 loss: 3.2337 (3.1923) grad_norm: 1.6150 (1.6516) time: 0.5072 [2021-03-26 11:55:37 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 910/1251] eta: 0:02:54 lr: 0.000363 loss: 3.2452 (3.1958) grad_norm: 1.6423 (1.6519) time: 0.5024 [2021-03-26 11:55:42 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 920/1251] eta: 0:02:49 lr: 0.000363 loss: 3.3800 (3.1955) grad_norm: 1.6428 (1.6530) time: 0.5032 [2021-03-26 11:55:47 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 930/1251] eta: 0:02:43 lr: 0.000363 loss: 3.3693 (3.1968) grad_norm: 1.6937 (1.6535) time: 0.5009 [2021-03-26 11:55:53 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 940/1251] eta: 0:02:38 lr: 0.000363 loss: 3.3988 (3.1968) grad_norm: 1.6801 (1.6540) time: 0.5029 [2021-03-26 11:55:58 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 950/1251] eta: 0:02:33 lr: 0.000363 loss: 3.1864 (3.1932) grad_norm: 1.6606 (1.6537) time: 0.5089 [2021-03-26 11:56:03 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 960/1251] eta: 0:02:28 lr: 0.000363 loss: 3.0908 (3.1921) grad_norm: 1.6899 (1.6547) time: 0.5067 [2021-03-26 11:56:08 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 970/1251] eta: 0:02:23 lr: 0.000363 loss: 3.0485 (3.1916) grad_norm: 1.7451 (1.6567) time: 0.5062 [2021-03-26 11:56:13 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 980/1251] eta: 0:02:18 lr: 0.000363 loss: 2.9827 (3.1912) grad_norm: 1.6985 (1.6572) time: 0.5056 [2021-03-26 11:56:18 swin_small_patch4_window7_224] INFO: Epoch: [177] [ 990/1251] eta: 0:02:13 lr: 0.000363 loss: 3.3301 (3.1924) grad_norm: 1.6985 (1.6583) time: 0.5015 [2021-03-26 11:56:23 swin_small_patch4_window7_224] INFO: Epoch: [177] [1000/1251] eta: 0:02:08 lr: 0.000363 loss: 3.3826 (3.1924) grad_norm: 1.7515 (1.6597) time: 0.4981 [2021-03-26 11:56:28 swin_small_patch4_window7_224] INFO: Epoch: [177] [1010/1251] eta: 0:02:02 lr: 0.000363 loss: 3.1900 (3.1915) grad_norm: 1.6930 (1.6595) time: 0.5012 [2021-03-26 11:56:33 swin_small_patch4_window7_224] INFO: Epoch: [177] [1020/1251] eta: 0:01:57 lr: 0.000363 loss: 3.0582 (3.1891) grad_norm: 1.6563 (1.6597) time: 0.5047 [2021-03-26 11:56:38 swin_small_patch4_window7_224] INFO: Epoch: [177] [1030/1251] eta: 0:01:52 lr: 0.000363 loss: 3.0013 (3.1884) grad_norm: 1.6651 (1.6600) time: 0.5028 [2021-03-26 11:56:43 swin_small_patch4_window7_224] INFO: Epoch: [177] [1040/1251] eta: 0:01:47 lr: 0.000363 loss: 3.2537 (3.1899) grad_norm: 1.6036 (1.6587) time: 0.5032 [2021-03-26 11:56:48 swin_small_patch4_window7_224] INFO: Epoch: [177] [1050/1251] eta: 0:01:42 lr: 0.000363 loss: 3.2537 (3.1896) grad_norm: 1.5593 (1.6586) time: 0.5031 [2021-03-26 11:56:53 swin_small_patch4_window7_224] INFO: Epoch: [177] [1060/1251] eta: 0:01:37 lr: 0.000363 loss: 3.3084 (3.1911) grad_norm: 1.6107 (1.6583) time: 0.5060 [2021-03-26 11:56:58 swin_small_patch4_window7_224] INFO: Epoch: [177] [1070/1251] eta: 0:01:32 lr: 0.000363 loss: 3.2914 (3.1915) grad_norm: 1.6520 (1.6589) time: 0.5096 [2021-03-26 11:57:03 swin_small_patch4_window7_224] INFO: Epoch: [177] [1080/1251] eta: 0:01:27 lr: 0.000363 loss: 3.2028 (3.1917) grad_norm: 1.6647 (1.6588) time: 0.5042 [2021-03-26 11:57:08 swin_small_patch4_window7_224] INFO: Epoch: [177] [1090/1251] eta: 0:01:22 lr: 0.000363 loss: 3.3711 (3.1911) grad_norm: 1.6647 (1.6593) time: 0.4993 [2021-03-26 11:57:13 swin_small_patch4_window7_224] INFO: Epoch: [177] [1100/1251] eta: 0:01:16 lr: 0.000363 loss: 3.3180 (3.1909) grad_norm: 1.6715 (1.6599) time: 0.5033 [2021-03-26 11:57:18 swin_small_patch4_window7_224] INFO: Epoch: [177] [1110/1251] eta: 0:01:11 lr: 0.000362 loss: 3.2830 (3.1924) grad_norm: 1.6637 (1.6599) time: 0.5010 [2021-03-26 11:57:23 swin_small_patch4_window7_224] INFO: Epoch: [177] [1120/1251] eta: 0:01:06 lr: 0.000362 loss: 3.3330 (3.1911) grad_norm: 1.6150 (1.6592) time: 0.4960 [2021-03-26 11:57:28 swin_small_patch4_window7_224] INFO: Epoch: [177] [1130/1251] eta: 0:01:01 lr: 0.000362 loss: 3.2047 (3.1908) grad_norm: 1.5388 (1.6587) time: 0.4975 [2021-03-26 11:57:33 swin_small_patch4_window7_224] INFO: Epoch: [177] [1140/1251] eta: 0:00:56 lr: 0.000362 loss: 3.3790 (3.1920) grad_norm: 1.5553 (1.6583) time: 0.5022 [2021-03-26 11:57:38 swin_small_patch4_window7_224] INFO: Epoch: [177] [1150/1251] eta: 0:00:51 lr: 0.000362 loss: 3.2562 (3.1899) grad_norm: 1.5553 (1.6577) time: 0.5093 [2021-03-26 11:57:43 swin_small_patch4_window7_224] INFO: Epoch: [177] [1160/1251] eta: 0:00:46 lr: 0.000362 loss: 2.9926 (3.1906) grad_norm: 1.6746 (1.6584) time: 0.5057 [2021-03-26 11:57:48 swin_small_patch4_window7_224] INFO: Epoch: [177] [1170/1251] eta: 0:00:41 lr: 0.000362 loss: 3.1354 (3.1889) grad_norm: 1.6402 (1.6584) time: 0.5002 [2021-03-26 11:57:53 swin_small_patch4_window7_224] INFO: Epoch: [177] [1180/1251] eta: 0:00:36 lr: 0.000362 loss: 3.2245 (3.1889) grad_norm: 1.6402 (1.6590) time: 0.5025 [2021-03-26 11:57:58 swin_small_patch4_window7_224] INFO: Epoch: [177] [1190/1251] eta: 0:00:31 lr: 0.000362 loss: 3.2758 (3.1883) grad_norm: 1.6978 (1.6591) time: 0.5044 [2021-03-26 11:58:03 swin_small_patch4_window7_224] INFO: Epoch: [177] [1200/1251] eta: 0:00:25 lr: 0.000362 loss: 3.1709 (3.1878) grad_norm: 1.6581 (1.6592) time: 0.5005 [2021-03-26 11:58:08 swin_small_patch4_window7_224] INFO: Epoch: [177] [1210/1251] eta: 0:00:20 lr: 0.000362 loss: 3.0962 (3.1862) grad_norm: 1.6310 (1.6594) time: 0.4994 [2021-03-26 11:58:13 swin_small_patch4_window7_224] INFO: Epoch: [177] [1220/1251] eta: 0:00:15 lr: 0.000362 loss: 3.3985 (3.1890) grad_norm: 1.6266 (1.6591) time: 0.5023 [2021-03-26 11:58:18 swin_small_patch4_window7_224] INFO: Epoch: [177] [1230/1251] eta: 0:00:10 lr: 0.000362 loss: 3.4723 (3.1892) grad_norm: 1.6266 (1.6596) time: 0.5037 [2021-03-26 11:58:24 swin_small_patch4_window7_224] INFO: Epoch: [177] [1240/1251] eta: 0:00:05 lr: 0.000362 loss: 3.3119 (3.1894) grad_norm: 1.6029 (1.6589) time: 0.5076 [2021-03-26 11:58:29 swin_small_patch4_window7_224] INFO: Epoch: [177] [1250/1251] eta: 0:00:00 lr: 0.000362 loss: 3.0834 (3.1891) grad_norm: 1.5461 (1.6591) time: 0.5110 [2021-03-26 11:58:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:40 loss: 0.9194 (0.9194) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-26 11:58:42 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9194 (0.8934) acc1: 78.1250 (78.5511) acc5: 95.3125 (95.1705) [2021-03-26 11:58:44 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9220 (0.9130) acc1: 78.1250 (77.9762) acc5: 95.3125 (95.2381) [2021-03-26 11:58:46 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.9220 (0.8993) acc1: 78.1250 (78.2258) acc5: 95.3125 (95.3125) [2021-03-26 11:58:47 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8432 (0.8874) acc1: 79.6875 (78.6966) acc5: 95.3125 (95.1982) [2021-03-26 11:58:48 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8318 (0.8736) acc1: 79.6875 (78.8480) acc5: 95.3125 (95.3280) [2021-03-26 11:59:01 swin_small_patch4_window7_224] INFO: * Acc@1 79.454 Acc@5 94.970 loss 0.867 [2021-03-26 11:59:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-26 11:59:01 swin_small_patch4_window7_224] INFO: Max accuracy: 79.54% [2021-03-26 11:59:06 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 0/1251] eta: 1:30:32 lr: 0.000362 loss: 2.1427 (2.1427) grad_norm: 1.9382 (1.9382) time: 4.3427 [2021-03-26 11:59:11 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 10/1251] eta: 0:17:58 lr: 0.000362 loss: 3.3609 (3.1555) grad_norm: 1.7460 (1.7928) time: 0.8688 [2021-03-26 11:59:16 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 20/1251] eta: 0:14:16 lr: 0.000362 loss: 3.4639 (3.2285) grad_norm: 1.7233 (1.7818) time: 0.5137 [2021-03-26 11:59:21 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 30/1251] eta: 0:12:53 lr: 0.000362 loss: 3.3985 (3.2128) grad_norm: 1.7233 (1.7763) time: 0.5044 [2021-03-26 11:59:26 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 40/1251] eta: 0:12:09 lr: 0.000362 loss: 3.2391 (3.1879) grad_norm: 1.7148 (1.7801) time: 0.5046 [2021-03-26 11:59:31 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 50/1251] eta: 0:11:42 lr: 0.000362 loss: 3.2264 (3.1964) grad_norm: 1.7148 (1.7581) time: 0.5100 [2021-03-26 11:59:36 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 60/1251] eta: 0:11:23 lr: 0.000362 loss: 3.2264 (3.1826) grad_norm: 1.6556 (1.7414) time: 0.5141 [2021-03-26 11:59:41 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 70/1251] eta: 0:11:04 lr: 0.000362 loss: 3.2947 (3.1954) grad_norm: 1.6302 (1.7449) time: 0.5052 [2021-03-26 11:59:46 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 80/1251] eta: 0:10:50 lr: 0.000362 loss: 3.2410 (3.1904) grad_norm: 1.5869 (1.7419) time: 0.5008 [2021-03-26 11:59:51 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 90/1251] eta: 0:10:39 lr: 0.000362 loss: 3.1368 (3.2017) grad_norm: 1.5983 (1.7304) time: 0.5084 [2021-03-26 11:59:56 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 100/1251] eta: 0:10:29 lr: 0.000362 loss: 3.2697 (3.1925) grad_norm: 1.5983 (1.7178) time: 0.5096 [2021-03-26 12:00:02 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 110/1251] eta: 0:10:20 lr: 0.000361 loss: 3.2077 (3.1819) grad_norm: 1.6387 (1.7175) time: 0.5108 [2021-03-26 12:00:07 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 120/1251] eta: 0:10:10 lr: 0.000361 loss: 3.3684 (3.2077) grad_norm: 1.6956 (1.7225) time: 0.5050 [2021-03-26 12:00:12 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 130/1251] eta: 0:10:02 lr: 0.000361 loss: 3.4465 (3.2210) grad_norm: 1.8295 (1.7411) time: 0.5045 [2021-03-26 12:00:17 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 140/1251] eta: 0:09:54 lr: 0.000361 loss: 3.4255 (3.2186) grad_norm: 1.7741 (1.7406) time: 0.5080 [2021-03-26 12:00:22 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 150/1251] eta: 0:09:46 lr: 0.000361 loss: 3.2954 (3.2145) grad_norm: 1.6536 (1.7444) time: 0.5012 [2021-03-26 12:00:27 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 160/1251] eta: 0:09:39 lr: 0.000361 loss: 3.2954 (3.2134) grad_norm: 1.6536 (1.7378) time: 0.5021 [2021-03-26 12:00:32 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 170/1251] eta: 0:09:32 lr: 0.000361 loss: 3.2868 (3.2107) grad_norm: 1.6337 (1.7386) time: 0.5070 [2021-03-26 12:00:37 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 180/1251] eta: 0:09:26 lr: 0.000361 loss: 3.3711 (3.2185) grad_norm: 1.6856 (1.7359) time: 0.5095 [2021-03-26 12:00:42 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 190/1251] eta: 0:09:19 lr: 0.000361 loss: 3.2955 (3.2135) grad_norm: 1.6458 (1.7334) time: 0.5102 [2021-03-26 12:00:47 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 200/1251] eta: 0:09:13 lr: 0.000361 loss: 3.2115 (3.2138) grad_norm: 1.6175 (1.7283) time: 0.5111 [2021-03-26 12:00:52 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 210/1251] eta: 0:09:07 lr: 0.000361 loss: 3.2115 (3.2144) grad_norm: 1.6034 (1.7234) time: 0.5080 [2021-03-26 12:00:57 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 220/1251] eta: 0:09:01 lr: 0.000361 loss: 3.1687 (3.2026) grad_norm: 1.5880 (1.7205) time: 0.5079 [2021-03-26 12:01:02 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 230/1251] eta: 0:08:55 lr: 0.000361 loss: 3.1527 (3.2004) grad_norm: 1.5588 (1.7154) time: 0.5100 [2021-03-26 12:01:07 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 240/1251] eta: 0:08:49 lr: 0.000361 loss: 3.1527 (3.1926) grad_norm: 1.5535 (1.7122) time: 0.5048 [2021-03-26 12:01:12 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 250/1251] eta: 0:08:43 lr: 0.000361 loss: 3.1091 (3.1833) grad_norm: 1.7248 (1.7151) time: 0.5054 [2021-03-26 12:01:17 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 260/1251] eta: 0:08:37 lr: 0.000361 loss: 3.1645 (3.1806) grad_norm: 1.7161 (1.7187) time: 0.5035 [2021-03-26 12:01:22 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 270/1251] eta: 0:08:31 lr: 0.000361 loss: 3.3787 (3.1880) grad_norm: 1.6983 (1.7198) time: 0.4962 [2021-03-26 12:01:27 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 280/1251] eta: 0:08:25 lr: 0.000361 loss: 3.3074 (3.1848) grad_norm: 1.6955 (1.7183) time: 0.4962 [2021-03-26 12:01:33 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 290/1251] eta: 0:08:19 lr: 0.000361 loss: 3.2316 (3.1828) grad_norm: 1.5792 (1.7156) time: 0.5036 [2021-03-26 12:01:38 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 300/1251] eta: 0:08:13 lr: 0.000361 loss: 3.2567 (3.1888) grad_norm: 1.5820 (1.7124) time: 0.5086 [2021-03-26 12:01:43 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 310/1251] eta: 0:08:08 lr: 0.000361 loss: 3.3977 (3.1917) grad_norm: 1.5906 (1.7099) time: 0.5081 [2021-03-26 12:01:48 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 320/1251] eta: 0:08:02 lr: 0.000361 loss: 3.3194 (3.1947) grad_norm: 1.6437 (1.7132) time: 0.5091 [2021-03-26 12:01:53 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 330/1251] eta: 0:07:57 lr: 0.000361 loss: 3.3704 (3.2001) grad_norm: 1.7264 (1.7128) time: 0.5028 [2021-03-26 12:01:58 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 340/1251] eta: 0:07:51 lr: 0.000361 loss: 3.3941 (3.2053) grad_norm: 1.6140 (1.7106) time: 0.4989 [2021-03-26 12:02:03 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 350/1251] eta: 0:07:45 lr: 0.000361 loss: 3.2065 (3.1963) grad_norm: 1.6122 (1.7110) time: 0.5015 [2021-03-26 12:02:08 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 360/1251] eta: 0:07:40 lr: 0.000361 loss: 2.9172 (3.1952) grad_norm: 1.5654 (1.7072) time: 0.5015 [2021-03-26 12:02:13 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 370/1251] eta: 0:07:34 lr: 0.000360 loss: 2.9979 (3.1894) grad_norm: 1.5299 (1.7035) time: 0.5016 [2021-03-26 12:02:18 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 380/1251] eta: 0:07:29 lr: 0.000360 loss: 3.2637 (3.1922) grad_norm: 1.6227 (1.7013) time: 0.5023 [2021-03-26 12:02:23 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 390/1251] eta: 0:07:23 lr: 0.000360 loss: 3.0405 (3.1849) grad_norm: 1.6615 (1.7004) time: 0.5039 [2021-03-26 12:02:28 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 400/1251] eta: 0:07:18 lr: 0.000360 loss: 2.8765 (3.1860) grad_norm: 1.6709 (1.7000) time: 0.5052 [2021-03-26 12:02:33 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 410/1251] eta: 0:07:13 lr: 0.000360 loss: 3.3693 (3.1923) grad_norm: 1.6633 (1.6982) time: 0.5087 [2021-03-26 12:02:38 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 420/1251] eta: 0:07:07 lr: 0.000360 loss: 3.4126 (3.1951) grad_norm: 1.6133 (1.6972) time: 0.5068 [2021-03-26 12:02:43 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 430/1251] eta: 0:07:02 lr: 0.000360 loss: 3.0938 (3.1881) grad_norm: 1.6133 (1.6983) time: 0.5036 [2021-03-26 12:02:48 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 440/1251] eta: 0:06:57 lr: 0.000360 loss: 3.0907 (3.1880) grad_norm: 1.6454 (1.6977) time: 0.5020 [2021-03-26 12:02:53 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 450/1251] eta: 0:06:51 lr: 0.000360 loss: 3.3736 (3.1907) grad_norm: 1.6579 (1.6970) time: 0.4993 [2021-03-26 12:02:58 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 460/1251] eta: 0:06:46 lr: 0.000360 loss: 3.4530 (3.1966) grad_norm: 1.6647 (1.6975) time: 0.4999 [2021-03-26 12:03:03 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 470/1251] eta: 0:06:41 lr: 0.000360 loss: 3.4455 (3.1951) grad_norm: 1.7144 (1.6977) time: 0.5004 [2021-03-26 12:03:08 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 480/1251] eta: 0:06:35 lr: 0.000360 loss: 2.9697 (3.1904) grad_norm: 1.7037 (1.6966) time: 0.5001 [2021-03-26 12:03:13 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 490/1251] eta: 0:06:30 lr: 0.000360 loss: 2.8474 (3.1848) grad_norm: 1.6359 (1.6960) time: 0.5005 [2021-03-26 12:03:18 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 500/1251] eta: 0:06:24 lr: 0.000360 loss: 3.1822 (3.1859) grad_norm: 1.6483 (1.6959) time: 0.4989 [2021-03-26 12:03:23 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 510/1251] eta: 0:06:19 lr: 0.000360 loss: 3.2707 (3.1846) grad_norm: 1.6514 (1.6941) time: 0.4970 [2021-03-26 12:03:28 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 520/1251] eta: 0:06:14 lr: 0.000360 loss: 3.0795 (3.1822) grad_norm: 1.6548 (1.6934) time: 0.5047 [2021-03-26 12:03:33 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 530/1251] eta: 0:06:09 lr: 0.000360 loss: 3.2161 (3.1848) grad_norm: 1.5937 (1.6912) time: 0.5036 [2021-03-26 12:03:38 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 540/1251] eta: 0:06:03 lr: 0.000360 loss: 3.2350 (3.1858) grad_norm: 1.5937 (1.6920) time: 0.4985 [2021-03-26 12:03:43 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 550/1251] eta: 0:05:58 lr: 0.000360 loss: 3.3841 (3.1845) grad_norm: 1.6902 (1.6912) time: 0.5055 [2021-03-26 12:03:48 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 560/1251] eta: 0:05:53 lr: 0.000360 loss: 3.2722 (3.1805) grad_norm: 1.6439 (1.6910) time: 0.5115 [2021-03-26 12:03:54 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 570/1251] eta: 0:05:48 lr: 0.000360 loss: 3.2749 (3.1808) grad_norm: 1.6439 (1.6913) time: 0.5121 [2021-03-26 12:03:59 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 580/1251] eta: 0:05:43 lr: 0.000360 loss: 3.3482 (3.1807) grad_norm: 1.7591 (1.6920) time: 0.5105 [2021-03-26 12:04:04 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 590/1251] eta: 0:05:38 lr: 0.000360 loss: 3.3267 (3.1826) grad_norm: 1.7722 (1.6932) time: 0.5042 [2021-03-26 12:04:09 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 600/1251] eta: 0:05:32 lr: 0.000360 loss: 3.2850 (3.1820) grad_norm: 1.7909 (1.6957) time: 0.4985 [2021-03-26 12:04:14 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 610/1251] eta: 0:05:27 lr: 0.000360 loss: 3.4657 (3.1858) grad_norm: 1.7658 (1.6960) time: 0.5025 [2021-03-26 12:04:19 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 620/1251] eta: 0:05:22 lr: 0.000359 loss: 3.3971 (3.1852) grad_norm: 1.6827 (1.6965) time: 0.5067 [2021-03-26 12:04:24 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 630/1251] eta: 0:05:17 lr: 0.000359 loss: 3.2099 (3.1829) grad_norm: 1.7572 (1.6983) time: 0.5058 [2021-03-26 12:04:29 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 640/1251] eta: 0:05:12 lr: 0.000359 loss: 3.3262 (3.1828) grad_norm: 1.7572 (1.6998) time: 0.5079 [2021-03-26 12:04:34 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 650/1251] eta: 0:05:07 lr: 0.000359 loss: 3.3262 (3.1821) grad_norm: 1.6696 (1.6979) time: 0.5073 [2021-03-26 12:04:39 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 660/1251] eta: 0:05:01 lr: 0.000359 loss: 3.1254 (3.1797) grad_norm: 1.5949 (1.6978) time: 0.5062 [2021-03-26 12:04:44 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 670/1251] eta: 0:04:56 lr: 0.000359 loss: 3.3907 (3.1816) grad_norm: 1.6091 (1.6967) time: 0.5050 [2021-03-26 12:04:49 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 680/1251] eta: 0:04:51 lr: 0.000359 loss: 3.3546 (3.1828) grad_norm: 1.6140 (1.6965) time: 0.4995 [2021-03-26 12:04:54 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 690/1251] eta: 0:04:46 lr: 0.000359 loss: 3.3310 (3.1812) grad_norm: 1.6216 (1.6966) time: 0.4971 [2021-03-26 12:04:59 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 700/1251] eta: 0:04:41 lr: 0.000359 loss: 3.2242 (3.1817) grad_norm: 1.6125 (1.6953) time: 0.4985 [2021-03-26 12:05:04 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 710/1251] eta: 0:04:36 lr: 0.000359 loss: 3.3312 (3.1846) grad_norm: 1.6872 (1.6984) time: 0.5098 [2021-03-26 12:05:09 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 720/1251] eta: 0:04:30 lr: 0.000359 loss: 3.3915 (3.1857) grad_norm: 1.6982 (1.6977) time: 0.5121 [2021-03-26 12:05:14 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 730/1251] eta: 0:04:25 lr: 0.000359 loss: 3.3329 (3.1855) grad_norm: 1.6403 (1.6977) time: 0.5102 [2021-03-26 12:05:20 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 740/1251] eta: 0:04:20 lr: 0.000359 loss: 3.2443 (3.1839) grad_norm: 1.7043 (1.6976) time: 0.5147 [2021-03-26 12:05:25 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 750/1251] eta: 0:04:15 lr: 0.000359 loss: 3.2628 (3.1842) grad_norm: 1.7043 (1.6978) time: 0.5111 [2021-03-26 12:05:30 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 760/1251] eta: 0:04:10 lr: 0.000359 loss: 3.2778 (3.1867) grad_norm: 1.6828 (1.6989) time: 0.5142 [2021-03-26 12:05:35 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 770/1251] eta: 0:04:05 lr: 0.000359 loss: 3.4120 (3.1869) grad_norm: 1.6774 (1.6981) time: 0.5127 [2021-03-26 12:05:40 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 780/1251] eta: 0:04:00 lr: 0.000359 loss: 3.4120 (3.1897) grad_norm: 1.6265 (1.6975) time: 0.5004 [2021-03-26 12:05:45 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 790/1251] eta: 0:03:55 lr: 0.000359 loss: 3.3604 (3.1908) grad_norm: 1.6364 (1.6971) time: 0.5044 [2021-03-26 12:05:50 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 800/1251] eta: 0:03:50 lr: 0.000359 loss: 3.4209 (3.1929) grad_norm: 1.6991 (1.6978) time: 0.5093 [2021-03-26 12:05:55 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 810/1251] eta: 0:03:44 lr: 0.000359 loss: 3.2567 (3.1891) grad_norm: 1.6621 (1.6974) time: 0.5025 [2021-03-26 12:06:00 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 820/1251] eta: 0:03:39 lr: 0.000359 loss: 2.9982 (3.1894) grad_norm: 1.6142 (1.6975) time: 0.5009 [2021-03-26 12:06:05 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 830/1251] eta: 0:03:34 lr: 0.000359 loss: 3.3394 (3.1904) grad_norm: 1.6447 (1.6974) time: 0.5144 [2021-03-26 12:06:10 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 840/1251] eta: 0:03:29 lr: 0.000359 loss: 3.3657 (3.1927) grad_norm: 1.6850 (1.6966) time: 0.5136 [2021-03-26 12:06:16 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 850/1251] eta: 0:03:24 lr: 0.000359 loss: 3.3657 (3.1939) grad_norm: 1.6920 (1.6969) time: 0.5116 [2021-03-26 12:06:21 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 860/1251] eta: 0:03:19 lr: 0.000359 loss: 3.3867 (3.1958) grad_norm: 1.7377 (1.6985) time: 0.5146 [2021-03-26 12:06:26 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 870/1251] eta: 0:03:14 lr: 0.000358 loss: 3.3005 (3.1943) grad_norm: 1.7187 (1.6981) time: 0.5083 [2021-03-26 12:06:31 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 880/1251] eta: 0:03:09 lr: 0.000358 loss: 3.3083 (3.1974) grad_norm: 1.6441 (1.6982) time: 0.5060 [2021-03-26 12:06:36 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 890/1251] eta: 0:03:04 lr: 0.000358 loss: 3.3490 (3.1971) grad_norm: 1.6312 (1.6978) time: 0.5037 [2021-03-26 12:06:41 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 900/1251] eta: 0:02:59 lr: 0.000358 loss: 3.4249 (3.1998) grad_norm: 1.6275 (1.6974) time: 0.5065 [2021-03-26 12:06:46 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 910/1251] eta: 0:02:53 lr: 0.000358 loss: 3.1936 (3.1974) grad_norm: 1.5856 (1.6961) time: 0.5077 [2021-03-26 12:06:51 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 920/1251] eta: 0:02:48 lr: 0.000358 loss: 3.0928 (3.1947) grad_norm: 1.6186 (1.6957) time: 0.5055 [2021-03-26 12:06:56 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 930/1251] eta: 0:02:43 lr: 0.000358 loss: 2.6629 (3.1899) grad_norm: 1.6434 (1.6946) time: 0.5105 [2021-03-26 12:07:01 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 940/1251] eta: 0:02:38 lr: 0.000358 loss: 3.0737 (3.1908) grad_norm: 1.5695 (1.6947) time: 0.5072 [2021-03-26 12:07:06 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 950/1251] eta: 0:02:33 lr: 0.000358 loss: 3.3088 (3.1919) grad_norm: 1.6823 (1.6950) time: 0.5052 [2021-03-26 12:07:11 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 960/1251] eta: 0:02:28 lr: 0.000358 loss: 3.4029 (3.1944) grad_norm: 1.6700 (1.6944) time: 0.5099 [2021-03-26 12:07:16 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 970/1251] eta: 0:02:23 lr: 0.000358 loss: 3.3138 (3.1938) grad_norm: 1.6078 (1.6941) time: 0.5088 [2021-03-26 12:07:22 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 980/1251] eta: 0:02:18 lr: 0.000358 loss: 3.0074 (3.1914) grad_norm: 1.6686 (1.6941) time: 0.5090 [2021-03-26 12:07:27 swin_small_patch4_window7_224] INFO: Epoch: [178] [ 990/1251] eta: 0:02:13 lr: 0.000358 loss: 2.8123 (3.1884) grad_norm: 1.7011 (1.6941) time: 0.5077 [2021-03-26 12:07:32 swin_small_patch4_window7_224] INFO: Epoch: [178] [1000/1251] eta: 0:02:07 lr: 0.000358 loss: 3.0065 (3.1892) grad_norm: 1.7149 (1.6942) time: 0.5034 [2021-03-26 12:07:37 swin_small_patch4_window7_224] INFO: Epoch: [178] [1010/1251] eta: 0:02:02 lr: 0.000358 loss: 3.3659 (3.1908) grad_norm: 1.7336 (1.6953) time: 0.5021 [2021-03-26 12:07:42 swin_small_patch4_window7_224] INFO: Epoch: [178] [1020/1251] eta: 0:01:57 lr: 0.000358 loss: 3.2240 (3.1898) grad_norm: 1.6382 (1.6948) time: 0.5039 [2021-03-26 12:07:47 swin_small_patch4_window7_224] INFO: Epoch: [178] [1030/1251] eta: 0:01:52 lr: 0.000358 loss: 3.3278 (3.1916) grad_norm: 1.6280 (1.6950) time: 0.5067 [2021-03-26 12:07:52 swin_small_patch4_window7_224] INFO: Epoch: [178] [1040/1251] eta: 0:01:47 lr: 0.000358 loss: 3.3961 (3.1938) grad_norm: 1.7224 (1.6954) time: 0.5126 [2021-03-26 12:07:57 swin_small_patch4_window7_224] INFO: Epoch: [178] [1050/1251] eta: 0:01:42 lr: 0.000358 loss: 3.3785 (3.1952) grad_norm: 1.7508 (1.6960) time: 0.5092 [2021-03-26 12:08:02 swin_small_patch4_window7_224] INFO: Epoch: [178] [1060/1251] eta: 0:01:37 lr: 0.000358 loss: 3.3079 (3.1943) grad_norm: 1.7039 (1.6961) time: 0.5031 [2021-03-26 12:08:07 swin_small_patch4_window7_224] INFO: Epoch: [178] [1070/1251] eta: 0:01:32 lr: 0.000358 loss: 3.3243 (3.1936) grad_norm: 1.6666 (1.6956) time: 0.5058 [2021-03-26 12:08:12 swin_small_patch4_window7_224] INFO: Epoch: [178] [1080/1251] eta: 0:01:27 lr: 0.000358 loss: 3.3900 (3.1946) grad_norm: 1.6169 (1.6959) time: 0.5068 [2021-03-26 12:08:17 swin_small_patch4_window7_224] INFO: Epoch: [178] [1090/1251] eta: 0:01:22 lr: 0.000358 loss: 3.3421 (3.1932) grad_norm: 1.5866 (1.6952) time: 0.5044 [2021-03-26 12:08:22 swin_small_patch4_window7_224] INFO: Epoch: [178] [1100/1251] eta: 0:01:16 lr: 0.000358 loss: 3.4380 (3.1952) grad_norm: 1.5892 (1.6951) time: 0.5029 [2021-03-26 12:08:27 swin_small_patch4_window7_224] INFO: Epoch: [178] [1110/1251] eta: 0:01:11 lr: 0.000358 loss: 3.4380 (3.1952) grad_norm: 1.5834 (1.6946) time: 0.4969 [2021-03-26 12:08:32 swin_small_patch4_window7_224] INFO: Epoch: [178] [1120/1251] eta: 0:01:06 lr: 0.000357 loss: 3.0290 (3.1921) grad_norm: 1.5706 (1.6939) time: 0.4977 [2021-03-26 12:08:37 swin_small_patch4_window7_224] INFO: Epoch: [178] [1130/1251] eta: 0:01:01 lr: 0.000357 loss: 3.1546 (3.1926) grad_norm: 1.6283 (1.6938) time: 0.5048 [2021-03-26 12:08:42 swin_small_patch4_window7_224] INFO: Epoch: [178] [1140/1251] eta: 0:00:56 lr: 0.000357 loss: 3.2996 (3.1930) grad_norm: 1.7019 (1.6940) time: 0.5033 [2021-03-26 12:08:47 swin_small_patch4_window7_224] INFO: Epoch: [178] [1150/1251] eta: 0:00:51 lr: 0.000357 loss: 3.2859 (3.1933) grad_norm: 1.7072 (1.6945) time: 0.4969 [2021-03-26 12:08:52 swin_small_patch4_window7_224] INFO: Epoch: [178] [1160/1251] eta: 0:00:46 lr: 0.000357 loss: 3.2529 (3.1926) grad_norm: 1.6524 (1.6938) time: 0.4966 [2021-03-26 12:08:57 swin_small_patch4_window7_224] INFO: Epoch: [178] [1170/1251] eta: 0:00:41 lr: 0.000357 loss: 3.1021 (3.1906) grad_norm: 1.6375 (1.6941) time: 0.5000 [2021-03-26 12:09:02 swin_small_patch4_window7_224] INFO: Epoch: [178] [1180/1251] eta: 0:00:36 lr: 0.000357 loss: 3.1861 (3.1915) grad_norm: 1.6303 (1.6934) time: 0.4970 [2021-03-26 12:09:07 swin_small_patch4_window7_224] INFO: Epoch: [178] [1190/1251] eta: 0:00:31 lr: 0.000357 loss: 3.3783 (3.1924) grad_norm: 1.6303 (1.6935) time: 0.4997 [2021-03-26 12:09:12 swin_small_patch4_window7_224] INFO: Epoch: [178] [1200/1251] eta: 0:00:25 lr: 0.000357 loss: 3.2624 (3.1922) grad_norm: 1.8114 (1.6951) time: 0.5041 [2021-03-26 12:09:17 swin_small_patch4_window7_224] INFO: Epoch: [178] [1210/1251] eta: 0:00:20 lr: 0.000357 loss: 3.2349 (3.1909) grad_norm: 1.8496 (1.6969) time: 0.5009 [2021-03-26 12:09:22 swin_small_patch4_window7_224] INFO: Epoch: [178] [1220/1251] eta: 0:00:15 lr: 0.000357 loss: 3.3911 (3.1928) grad_norm: 1.7477 (1.6972) time: 0.4972 [2021-03-26 12:09:27 swin_small_patch4_window7_224] INFO: Epoch: [178] [1230/1251] eta: 0:00:10 lr: 0.000357 loss: 3.2962 (3.1900) grad_norm: 1.6709 (1.6970) time: 0.4965 [2021-03-26 12:09:32 swin_small_patch4_window7_224] INFO: Epoch: [178] [1240/1251] eta: 0:00:05 lr: 0.000357 loss: 3.1013 (3.1903) grad_norm: 1.7013 (1.6976) time: 0.4995 [2021-03-26 12:09:37 swin_small_patch4_window7_224] INFO: Epoch: [178] [1250/1251] eta: 0:00:00 lr: 0.000357 loss: 3.1677 (3.1891) grad_norm: 1.7267 (1.6984) time: 0.5007 [2021-03-26 12:09:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 1.0304 (1.0304) acc1: 81.2500 (81.2500) acc5: 90.6250 (90.6250) [2021-03-26 12:09:49 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8807 (0.8836) acc1: 81.2500 (79.9716) acc5: 93.7500 (94.3182) [2021-03-26 12:09:52 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8807 (0.8919) acc1: 79.6875 (79.3155) acc5: 93.7500 (94.7173) [2021-03-26 12:09:53 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9573 (0.9008) acc1: 76.5625 (78.6290) acc5: 96.8750 (95.2117) [2021-03-26 12:09:55 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9259 (0.9095) acc1: 76.5625 (78.0869) acc5: 95.3125 (95.0838) [2021-03-26 12:09:56 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8056 (0.8818) acc1: 76.5625 (78.7840) acc5: 95.3125 (95.1680) [2021-03-26 12:10:09 swin_small_patch4_window7_224] INFO: * Acc@1 79.548 Acc@5 94.980 loss 0.874 [2021-03-26 12:10:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-26 12:10:09 swin_small_patch4_window7_224] INFO: Max accuracy: 79.55% [2021-03-26 12:10:13 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 0/1251] eta: 1:27:38 lr: 0.000357 loss: 3.6930 (3.6930) grad_norm: 1.5405 (1.5405) time: 4.2033 [2021-03-26 12:10:19 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 10/1251] eta: 0:17:47 lr: 0.000357 loss: 3.6930 (3.4283) grad_norm: 1.6353 (1.6434) time: 0.8602 [2021-03-26 12:10:24 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 20/1251] eta: 0:14:08 lr: 0.000357 loss: 3.2427 (3.2858) grad_norm: 1.6353 (1.6593) time: 0.5134 [2021-03-26 12:10:29 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 30/1251] eta: 0:12:47 lr: 0.000357 loss: 3.3415 (3.2998) grad_norm: 1.6165 (1.6933) time: 0.5016 [2021-03-26 12:10:34 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 40/1251] eta: 0:12:02 lr: 0.000357 loss: 3.4370 (3.2951) grad_norm: 1.7186 (1.7400) time: 0.4993 [2021-03-26 12:10:39 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 50/1251] eta: 0:11:35 lr: 0.000357 loss: 3.2143 (3.2541) grad_norm: 1.6642 (1.7297) time: 0.5022 [2021-03-26 12:10:44 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 60/1251] eta: 0:11:15 lr: 0.000357 loss: 3.2143 (3.2360) grad_norm: 1.6204 (1.7102) time: 0.5081 [2021-03-26 12:10:49 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 70/1251] eta: 0:10:58 lr: 0.000357 loss: 3.3024 (3.2518) grad_norm: 1.6442 (1.7056) time: 0.5039 [2021-03-26 12:10:54 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 80/1251] eta: 0:10:45 lr: 0.000357 loss: 3.4705 (3.2517) grad_norm: 1.6674 (1.7021) time: 0.5022 [2021-03-26 12:10:59 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 90/1251] eta: 0:10:34 lr: 0.000357 loss: 3.4494 (3.2518) grad_norm: 1.6510 (1.6966) time: 0.5071 [2021-03-26 12:11:04 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 100/1251] eta: 0:10:23 lr: 0.000357 loss: 3.2119 (3.2191) grad_norm: 1.6178 (1.6861) time: 0.5032 [2021-03-26 12:11:09 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 110/1251] eta: 0:10:14 lr: 0.000357 loss: 3.1696 (3.2174) grad_norm: 1.6455 (1.6878) time: 0.5008 [2021-03-26 12:11:14 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 120/1251] eta: 0:10:06 lr: 0.000357 loss: 3.1696 (3.2139) grad_norm: 1.6904 (1.6851) time: 0.5075 [2021-03-26 12:11:19 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 130/1251] eta: 0:09:58 lr: 0.000356 loss: 3.1467 (3.2112) grad_norm: 1.6386 (1.6823) time: 0.5102 [2021-03-26 12:11:24 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 140/1251] eta: 0:09:50 lr: 0.000356 loss: 3.2532 (3.2155) grad_norm: 1.6807 (1.6919) time: 0.5034 [2021-03-26 12:11:29 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 150/1251] eta: 0:09:43 lr: 0.000356 loss: 3.3649 (3.2341) grad_norm: 1.7181 (1.6893) time: 0.4994 [2021-03-26 12:11:34 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 160/1251] eta: 0:09:36 lr: 0.000356 loss: 3.4297 (3.2347) grad_norm: 1.6615 (1.6961) time: 0.5046 [2021-03-26 12:11:40 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 170/1251] eta: 0:09:31 lr: 0.000356 loss: 3.2446 (3.2264) grad_norm: 1.7144 (1.6969) time: 0.5179 [2021-03-26 12:11:45 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 180/1251] eta: 0:09:23 lr: 0.000356 loss: 3.1887 (3.2247) grad_norm: 1.7150 (1.6998) time: 0.5130 [2021-03-26 12:11:50 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 190/1251] eta: 0:09:17 lr: 0.000356 loss: 3.0663 (3.2156) grad_norm: 1.6685 (1.6973) time: 0.5050 [2021-03-26 12:11:55 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 200/1251] eta: 0:09:11 lr: 0.000356 loss: 3.0978 (3.2206) grad_norm: 1.6097 (1.6916) time: 0.5081 [2021-03-26 12:12:00 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 210/1251] eta: 0:09:04 lr: 0.000356 loss: 3.3236 (3.2218) grad_norm: 1.6490 (1.6944) time: 0.5000 [2021-03-26 12:12:05 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 220/1251] eta: 0:08:58 lr: 0.000356 loss: 3.3661 (3.2276) grad_norm: 1.7528 (1.6932) time: 0.4991 [2021-03-26 12:12:10 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 230/1251] eta: 0:08:52 lr: 0.000356 loss: 3.3661 (3.2307) grad_norm: 1.6419 (1.6924) time: 0.5059 [2021-03-26 12:12:15 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 240/1251] eta: 0:08:46 lr: 0.000356 loss: 3.3255 (3.2211) grad_norm: 1.6626 (1.6928) time: 0.5072 [2021-03-26 12:12:20 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 250/1251] eta: 0:08:40 lr: 0.000356 loss: 3.2588 (3.2225) grad_norm: 1.6849 (1.6944) time: 0.5009 [2021-03-26 12:12:25 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 260/1251] eta: 0:08:34 lr: 0.000356 loss: 3.3668 (3.2246) grad_norm: 1.6512 (1.6927) time: 0.4975 [2021-03-26 12:12:30 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 270/1251] eta: 0:08:28 lr: 0.000356 loss: 3.0164 (3.2216) grad_norm: 1.7388 (1.6952) time: 0.4985 [2021-03-26 12:12:35 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 280/1251] eta: 0:08:22 lr: 0.000356 loss: 2.7877 (3.2097) grad_norm: 1.7682 (1.6950) time: 0.5011 [2021-03-26 12:12:40 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 290/1251] eta: 0:08:17 lr: 0.000356 loss: 3.2895 (3.2163) grad_norm: 1.6721 (1.6950) time: 0.5036 [2021-03-26 12:12:45 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 300/1251] eta: 0:08:11 lr: 0.000356 loss: 3.4781 (3.2155) grad_norm: 1.7022 (1.6978) time: 0.5018 [2021-03-26 12:12:50 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 310/1251] eta: 0:08:06 lr: 0.000356 loss: 3.2717 (3.2103) grad_norm: 1.7131 (1.6974) time: 0.5041 [2021-03-26 12:12:55 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 320/1251] eta: 0:08:00 lr: 0.000356 loss: 3.0956 (3.2114) grad_norm: 1.7390 (1.6978) time: 0.5093 [2021-03-26 12:13:00 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 330/1251] eta: 0:07:55 lr: 0.000356 loss: 3.1621 (3.2074) grad_norm: 1.6904 (1.6979) time: 0.5064 [2021-03-26 12:13:05 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 340/1251] eta: 0:07:49 lr: 0.000356 loss: 3.3995 (3.2135) grad_norm: 1.6480 (1.6975) time: 0.5011 [2021-03-26 12:13:10 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 350/1251] eta: 0:07:44 lr: 0.000356 loss: 3.3906 (3.2067) grad_norm: 1.5981 (1.6962) time: 0.5006 [2021-03-26 12:13:15 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 360/1251] eta: 0:07:38 lr: 0.000356 loss: 3.2189 (3.2067) grad_norm: 1.6526 (1.6935) time: 0.5015 [2021-03-26 12:13:20 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 370/1251] eta: 0:07:33 lr: 0.000356 loss: 3.2617 (3.2071) grad_norm: 1.6373 (1.6933) time: 0.5070 [2021-03-26 12:13:25 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 380/1251] eta: 0:07:28 lr: 0.000355 loss: 3.2388 (3.2005) grad_norm: 1.6373 (1.6919) time: 0.5071 [2021-03-26 12:13:30 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 390/1251] eta: 0:07:22 lr: 0.000355 loss: 3.2388 (3.2033) grad_norm: 1.5970 (1.6900) time: 0.5053 [2021-03-26 12:13:35 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 400/1251] eta: 0:07:17 lr: 0.000355 loss: 3.4174 (3.2008) grad_norm: 1.5565 (1.6883) time: 0.5060 [2021-03-26 12:13:40 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 410/1251] eta: 0:07:12 lr: 0.000355 loss: 3.1243 (3.2009) grad_norm: 1.6361 (1.6874) time: 0.5050 [2021-03-26 12:13:46 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 420/1251] eta: 0:07:06 lr: 0.000355 loss: 3.0777 (3.1996) grad_norm: 1.6615 (1.6919) time: 0.5055 [2021-03-26 12:13:51 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 430/1251] eta: 0:07:01 lr: 0.000355 loss: 3.2116 (3.2001) grad_norm: 1.6159 (1.6897) time: 0.5041 [2021-03-26 12:13:56 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 440/1251] eta: 0:06:56 lr: 0.000355 loss: 3.2829 (3.2014) grad_norm: 1.6215 (1.6900) time: 0.5041 [2021-03-26 12:14:01 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 450/1251] eta: 0:06:50 lr: 0.000355 loss: 3.2445 (3.2016) grad_norm: 1.6433 (1.6895) time: 0.5033 [2021-03-26 12:14:06 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 460/1251] eta: 0:06:45 lr: 0.000355 loss: 3.2445 (3.2034) grad_norm: 1.6092 (1.6885) time: 0.5006 [2021-03-26 12:14:11 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 470/1251] eta: 0:06:40 lr: 0.000355 loss: 3.2672 (3.2024) grad_norm: 1.6908 (1.6888) time: 0.5095 [2021-03-26 12:14:16 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 480/1251] eta: 0:06:35 lr: 0.000355 loss: 3.2734 (3.1982) grad_norm: 1.6767 (1.6886) time: 0.5117 [2021-03-26 12:14:21 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 490/1251] eta: 0:06:29 lr: 0.000355 loss: 3.2734 (3.1963) grad_norm: 1.6547 (1.6886) time: 0.5044 [2021-03-26 12:14:26 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 500/1251] eta: 0:06:24 lr: 0.000355 loss: 3.2908 (3.1961) grad_norm: 1.6152 (1.6876) time: 0.5034 [2021-03-26 12:14:31 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 510/1251] eta: 0:06:19 lr: 0.000355 loss: 3.4557 (3.1993) grad_norm: 1.6411 (1.6881) time: 0.5053 [2021-03-26 12:14:36 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 520/1251] eta: 0:06:14 lr: 0.000355 loss: 3.3528 (3.1988) grad_norm: 1.7132 (1.6894) time: 0.5042 [2021-03-26 12:14:41 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 530/1251] eta: 0:06:08 lr: 0.000355 loss: 3.3466 (3.1950) grad_norm: 1.6078 (1.6881) time: 0.5017 [2021-03-26 12:14:46 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 540/1251] eta: 0:06:03 lr: 0.000355 loss: 3.1265 (3.1919) grad_norm: 1.5561 (1.6867) time: 0.5089 [2021-03-26 12:14:51 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 550/1251] eta: 0:05:58 lr: 0.000355 loss: 3.1265 (3.1925) grad_norm: 1.5375 (1.6846) time: 0.5122 [2021-03-26 12:14:57 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 560/1251] eta: 0:05:53 lr: 0.000355 loss: 3.1930 (3.1924) grad_norm: 1.5164 (1.6841) time: 0.5195 [2021-03-26 12:15:02 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 570/1251] eta: 0:05:48 lr: 0.000355 loss: 3.3437 (3.1932) grad_norm: 1.6300 (1.6838) time: 0.5192 [2021-03-26 12:15:07 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 580/1251] eta: 0:05:43 lr: 0.000355 loss: 3.3437 (3.1948) grad_norm: 1.6564 (1.6859) time: 0.5068 [2021-03-26 12:15:12 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 590/1251] eta: 0:05:38 lr: 0.000355 loss: 3.2974 (3.1951) grad_norm: 1.6550 (1.6855) time: 0.5016 [2021-03-26 12:15:17 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 600/1251] eta: 0:05:32 lr: 0.000355 loss: 3.1667 (3.1934) grad_norm: 1.6323 (1.6854) time: 0.4998 [2021-03-26 12:15:22 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 610/1251] eta: 0:05:27 lr: 0.000355 loss: 3.4139 (3.1983) grad_norm: 1.6677 (1.6873) time: 0.5061 [2021-03-26 12:15:27 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 620/1251] eta: 0:05:22 lr: 0.000355 loss: 3.4139 (3.1968) grad_norm: 1.7023 (1.6871) time: 0.5092 [2021-03-26 12:15:32 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 630/1251] eta: 0:05:17 lr: 0.000354 loss: 3.2391 (3.1977) grad_norm: 1.7023 (1.6876) time: 0.5011 [2021-03-26 12:15:37 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 640/1251] eta: 0:05:12 lr: 0.000354 loss: 3.1512 (3.1968) grad_norm: 1.6361 (1.6866) time: 0.4977 [2021-03-26 12:15:42 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 650/1251] eta: 0:05:07 lr: 0.000354 loss: 3.1831 (3.1983) grad_norm: 1.5988 (1.6862) time: 0.5044 [2021-03-26 12:15:47 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 660/1251] eta: 0:05:01 lr: 0.000354 loss: 3.2117 (3.1979) grad_norm: 1.6132 (1.6863) time: 0.5061 [2021-03-26 12:15:52 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 670/1251] eta: 0:04:56 lr: 0.000354 loss: 3.2118 (3.1961) grad_norm: 1.6885 (1.6873) time: 0.5043 [2021-03-26 12:15:57 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 680/1251] eta: 0:04:51 lr: 0.000354 loss: 3.2433 (3.1965) grad_norm: 1.6038 (1.6861) time: 0.5058 [2021-03-26 12:16:02 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 690/1251] eta: 0:04:46 lr: 0.000354 loss: 3.2848 (3.1953) grad_norm: 1.6105 (1.6865) time: 0.5024 [2021-03-26 12:16:07 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 700/1251] eta: 0:04:41 lr: 0.000354 loss: 3.2973 (3.1962) grad_norm: 1.7010 (1.6864) time: 0.5133 [2021-03-26 12:16:12 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 710/1251] eta: 0:04:36 lr: 0.000354 loss: 3.1063 (3.1921) grad_norm: 1.6991 (1.6866) time: 0.5133 [2021-03-26 12:16:18 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 720/1251] eta: 0:04:31 lr: 0.000354 loss: 3.2273 (3.1920) grad_norm: 1.6907 (1.6875) time: 0.5068 [2021-03-26 12:16:23 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 730/1251] eta: 0:04:26 lr: 0.000354 loss: 3.4438 (3.1935) grad_norm: 1.7081 (1.6896) time: 0.5098 [2021-03-26 12:16:28 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 740/1251] eta: 0:04:21 lr: 0.000354 loss: 3.2371 (3.1931) grad_norm: 1.7081 (1.6895) time: 0.5184 [2021-03-26 12:16:33 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 750/1251] eta: 0:04:15 lr: 0.000354 loss: 3.1924 (3.1943) grad_norm: 1.6585 (1.6899) time: 0.5249 [2021-03-26 12:16:38 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 760/1251] eta: 0:04:10 lr: 0.000354 loss: 3.3441 (3.1967) grad_norm: 1.7250 (1.6910) time: 0.5109 [2021-03-26 12:16:43 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 770/1251] eta: 0:04:05 lr: 0.000354 loss: 3.3325 (3.1962) grad_norm: 1.7041 (1.6912) time: 0.5009 [2021-03-26 12:16:48 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 780/1251] eta: 0:04:00 lr: 0.000354 loss: 3.3325 (3.1974) grad_norm: 1.6533 (1.6910) time: 0.4994 [2021-03-26 12:16:53 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 790/1251] eta: 0:03:55 lr: 0.000354 loss: 3.2369 (3.1914) grad_norm: 1.6475 (1.6912) time: 0.5011 [2021-03-26 12:16:58 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 800/1251] eta: 0:03:50 lr: 0.000354 loss: 3.2369 (3.1932) grad_norm: 1.6210 (1.6911) time: 0.5031 [2021-03-26 12:17:03 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 810/1251] eta: 0:03:45 lr: 0.000354 loss: 3.3291 (3.1914) grad_norm: 1.6210 (1.6898) time: 0.5026 [2021-03-26 12:17:08 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 820/1251] eta: 0:03:39 lr: 0.000354 loss: 3.1365 (3.1914) grad_norm: 1.5626 (1.6891) time: 0.5026 [2021-03-26 12:17:13 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 830/1251] eta: 0:03:34 lr: 0.000354 loss: 3.2447 (3.1934) grad_norm: 1.6395 (1.6896) time: 0.5055 [2021-03-26 12:17:18 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 840/1251] eta: 0:03:29 lr: 0.000354 loss: 3.3221 (3.1916) grad_norm: 1.7095 (1.6899) time: 0.5092 [2021-03-26 12:17:23 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 850/1251] eta: 0:03:24 lr: 0.000354 loss: 3.2132 (3.1897) grad_norm: 1.6911 (1.6905) time: 0.5035 [2021-03-26 12:17:28 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 860/1251] eta: 0:03:19 lr: 0.000354 loss: 3.2070 (3.1887) grad_norm: 1.6474 (1.6897) time: 0.4966 [2021-03-26 12:17:34 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 870/1251] eta: 0:03:14 lr: 0.000354 loss: 2.9449 (3.1856) grad_norm: 1.6457 (1.6901) time: 0.5053 [2021-03-26 12:17:39 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 880/1251] eta: 0:03:09 lr: 0.000353 loss: 3.2056 (3.1874) grad_norm: 1.7288 (1.6910) time: 0.5085 [2021-03-26 12:17:44 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 890/1251] eta: 0:03:03 lr: 0.000353 loss: 3.5193 (3.1872) grad_norm: 1.6703 (1.6910) time: 0.5016 [2021-03-26 12:17:49 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 900/1251] eta: 0:02:58 lr: 0.000353 loss: 3.1887 (3.1851) grad_norm: 1.6640 (1.6917) time: 0.4991 [2021-03-26 12:17:54 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 910/1251] eta: 0:02:53 lr: 0.000353 loss: 3.2312 (3.1853) grad_norm: 1.6528 (1.6915) time: 0.5048 [2021-03-26 12:17:59 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 920/1251] eta: 0:02:48 lr: 0.000353 loss: 3.2312 (3.1842) grad_norm: 1.6446 (1.6911) time: 0.5090 [2021-03-26 12:18:04 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 930/1251] eta: 0:02:43 lr: 0.000353 loss: 3.1624 (3.1848) grad_norm: 1.6379 (1.6903) time: 0.5061 [2021-03-26 12:18:09 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 940/1251] eta: 0:02:38 lr: 0.000353 loss: 3.1411 (3.1816) grad_norm: 1.6219 (1.6895) time: 0.5087 [2021-03-26 12:18:14 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 950/1251] eta: 0:02:33 lr: 0.000353 loss: 3.1411 (3.1817) grad_norm: 1.5964 (nan) time: 0.5058 [2021-03-26 12:18:19 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 960/1251] eta: 0:02:28 lr: 0.000353 loss: 3.2858 (3.1823) grad_norm: 1.6974 (nan) time: 0.5041 [2021-03-26 12:18:24 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 970/1251] eta: 0:02:23 lr: 0.000353 loss: 3.5029 (3.1835) grad_norm: 1.7368 (nan) time: 0.5057 [2021-03-26 12:18:29 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 980/1251] eta: 0:02:18 lr: 0.000353 loss: 3.5183 (3.1862) grad_norm: 1.7708 (nan) time: 0.5053 [2021-03-26 12:18:34 swin_small_patch4_window7_224] INFO: Epoch: [179] [ 990/1251] eta: 0:02:12 lr: 0.000353 loss: 3.5461 (3.1888) grad_norm: 1.7030 (nan) time: 0.4994 [2021-03-26 12:18:39 swin_small_patch4_window7_224] INFO: Epoch: [179] [1000/1251] eta: 0:02:07 lr: 0.000353 loss: 3.3395 (3.1888) grad_norm: 1.6530 (nan) time: 0.5005 [2021-03-26 12:18:44 swin_small_patch4_window7_224] INFO: Epoch: [179] [1010/1251] eta: 0:02:02 lr: 0.000353 loss: 2.9333 (3.1859) grad_norm: 1.6727 (nan) time: 0.5064 [2021-03-26 12:18:49 swin_small_patch4_window7_224] INFO: Epoch: [179] [1020/1251] eta: 0:01:57 lr: 0.000353 loss: 2.9333 (3.1848) grad_norm: 1.6402 (nan) time: 0.5056 [2021-03-26 12:18:54 swin_small_patch4_window7_224] INFO: Epoch: [179] [1030/1251] eta: 0:01:52 lr: 0.000353 loss: 3.4036 (3.1865) grad_norm: 1.5862 (nan) time: 0.5084 [2021-03-26 12:18:59 swin_small_patch4_window7_224] INFO: Epoch: [179] [1040/1251] eta: 0:01:47 lr: 0.000353 loss: 3.1793 (3.1826) grad_norm: 1.6932 (nan) time: 0.5095 [2021-03-26 12:19:04 swin_small_patch4_window7_224] INFO: Epoch: [179] [1050/1251] eta: 0:01:42 lr: 0.000353 loss: 3.1780 (3.1832) grad_norm: 1.7055 (nan) time: 0.5077 [2021-03-26 12:19:10 swin_small_patch4_window7_224] INFO: Epoch: [179] [1060/1251] eta: 0:01:37 lr: 0.000353 loss: 3.3793 (3.1832) grad_norm: 1.6676 (nan) time: 0.5092 [2021-03-26 12:19:15 swin_small_patch4_window7_224] INFO: Epoch: [179] [1070/1251] eta: 0:01:32 lr: 0.000353 loss: 3.3042 (3.1839) grad_norm: 1.6676 (nan) time: 0.5129 [2021-03-26 12:19:20 swin_small_patch4_window7_224] INFO: Epoch: [179] [1080/1251] eta: 0:01:27 lr: 0.000353 loss: 3.2719 (3.1826) grad_norm: 1.6045 (nan) time: 0.5070 [2021-03-26 12:19:25 swin_small_patch4_window7_224] INFO: Epoch: [179] [1090/1251] eta: 0:01:21 lr: 0.000353 loss: 3.0418 (3.1819) grad_norm: 1.6489 (nan) time: 0.4996 [2021-03-26 12:19:30 swin_small_patch4_window7_224] INFO: Epoch: [179] [1100/1251] eta: 0:01:16 lr: 0.000353 loss: 3.2771 (3.1825) grad_norm: 1.6722 (nan) time: 0.5050 [2021-03-26 12:19:35 swin_small_patch4_window7_224] INFO: Epoch: [179] [1110/1251] eta: 0:01:11 lr: 0.000353 loss: 3.4215 (3.1834) grad_norm: 1.6802 (nan) time: 0.5111 [2021-03-26 12:19:40 swin_small_patch4_window7_224] INFO: Epoch: [179] [1120/1251] eta: 0:01:06 lr: 0.000353 loss: 3.4215 (3.1845) grad_norm: 1.6954 (nan) time: 0.5101 [2021-03-26 12:19:45 swin_small_patch4_window7_224] INFO: Epoch: [179] [1130/1251] eta: 0:01:01 lr: 0.000353 loss: 3.2447 (3.1833) grad_norm: 1.6954 (nan) time: 0.5063 [2021-03-26 12:19:50 swin_small_patch4_window7_224] INFO: Epoch: [179] [1140/1251] eta: 0:00:56 lr: 0.000352 loss: 3.1379 (3.1833) grad_norm: 1.7292 (nan) time: 0.5027 [2021-03-26 12:19:55 swin_small_patch4_window7_224] INFO: Epoch: [179] [1150/1251] eta: 0:00:51 lr: 0.000352 loss: 3.2202 (3.1842) grad_norm: 1.6139 (nan) time: 0.5004 [2021-03-26 12:20:00 swin_small_patch4_window7_224] INFO: Epoch: [179] [1160/1251] eta: 0:00:46 lr: 0.000352 loss: 3.2202 (3.1835) grad_norm: 1.6639 (nan) time: 0.5031 [2021-03-26 12:20:05 swin_small_patch4_window7_224] INFO: Epoch: [179] [1170/1251] eta: 0:00:41 lr: 0.000352 loss: 3.0973 (3.1818) grad_norm: 1.6818 (nan) time: 0.5073 [2021-03-26 12:20:10 swin_small_patch4_window7_224] INFO: Epoch: [179] [1180/1251] eta: 0:00:36 lr: 0.000352 loss: 2.9941 (3.1825) grad_norm: 1.7415 (nan) time: 0.5039 [2021-03-26 12:20:15 swin_small_patch4_window7_224] INFO: Epoch: [179] [1190/1251] eta: 0:00:31 lr: 0.000352 loss: 3.2271 (3.1831) grad_norm: 1.7990 (nan) time: 0.5031 [2021-03-26 12:20:20 swin_small_patch4_window7_224] INFO: Epoch: [179] [1200/1251] eta: 0:00:25 lr: 0.000352 loss: 3.3855 (3.1846) grad_norm: 1.8146 (nan) time: 0.5002 [2021-03-26 12:20:25 swin_small_patch4_window7_224] INFO: Epoch: [179] [1210/1251] eta: 0:00:20 lr: 0.000352 loss: 3.4286 (3.1837) grad_norm: 1.7309 (nan) time: 0.5052 [2021-03-26 12:20:30 swin_small_patch4_window7_224] INFO: Epoch: [179] [1220/1251] eta: 0:00:15 lr: 0.000352 loss: 3.4464 (3.1854) grad_norm: 1.6792 (nan) time: 0.5120 [2021-03-26 12:20:36 swin_small_patch4_window7_224] INFO: Epoch: [179] [1230/1251] eta: 0:00:10 lr: 0.000352 loss: 3.2470 (3.1828) grad_norm: 1.7205 (nan) time: 0.5105 [2021-03-26 12:20:41 swin_small_patch4_window7_224] INFO: Epoch: [179] [1240/1251] eta: 0:00:05 lr: 0.000352 loss: 2.9592 (3.1827) grad_norm: 1.6225 (nan) time: 0.5051 [2021-03-26 12:20:46 swin_small_patch4_window7_224] INFO: Epoch: [179] [1250/1251] eta: 0:00:00 lr: 0.000352 loss: 3.3881 (3.1839) grad_norm: 1.6831 (nan) time: 0.4952 [2021-03-26 12:20:55 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:36 loss: 0.8642 (0.8642) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-26 12:20:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.7914 (0.7963) acc1: 82.8125 (81.5341) acc5: 96.8750 (96.1648) [2021-03-26 12:21:01 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7914 (0.8278) acc1: 79.6875 (80.0595) acc5: 96.8750 (95.8333) [2021-03-26 12:21:03 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8582 (0.8555) acc1: 78.1250 (78.8810) acc5: 95.3125 (95.6149) [2021-03-26 12:21:05 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8837 (0.8696) acc1: 78.1250 (78.9634) acc5: 95.3125 (95.3125) [2021-03-26 12:21:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9238 (0.8752) acc1: 78.1250 (79.0080) acc5: 95.3125 (95.3280) [2021-03-26 12:21:17 swin_small_patch4_window7_224] INFO: * Acc@1 79.506 Acc@5 95.116 loss 0.865 [2021-03-26 12:21:17 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-26 12:21:17 swin_small_patch4_window7_224] INFO: Max accuracy: 79.55% [2021-03-26 12:21:21 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 0/1251] eta: 1:22:04 lr: 0.000352 loss: 3.4063 (3.4063) grad_norm: 1.6307 (1.6307) time: 3.9367 [2021-03-26 12:21:27 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 10/1251] eta: 0:17:46 lr: 0.000352 loss: 3.3835 (3.1961) grad_norm: 1.6009 (1.5956) time: 0.8591 [2021-03-26 12:21:32 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 20/1251] eta: 0:14:06 lr: 0.000352 loss: 3.3325 (3.1654) grad_norm: 1.5879 (1.6169) time: 0.5252 [2021-03-26 12:21:37 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 30/1251] eta: 0:12:50 lr: 0.000352 loss: 3.3427 (3.2273) grad_norm: 1.6967 (1.6826) time: 0.5058 [2021-03-26 12:21:42 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 40/1251] eta: 0:12:10 lr: 0.000352 loss: 3.5164 (3.2585) grad_norm: 1.7552 (1.7101) time: 0.5142 [2021-03-26 12:21:47 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 50/1251] eta: 0:11:42 lr: 0.000352 loss: 3.3488 (3.2144) grad_norm: 1.6637 (1.6845) time: 0.5140 [2021-03-26 12:21:52 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 60/1251] eta: 0:11:21 lr: 0.000352 loss: 3.0164 (3.1701) grad_norm: 1.5295 (1.6793) time: 0.5098 [2021-03-26 12:21:57 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 70/1251] eta: 0:11:04 lr: 0.000352 loss: 3.3322 (3.2075) grad_norm: 1.6322 (1.6813) time: 0.5049 [2021-03-26 12:22:02 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 80/1251] eta: 0:10:48 lr: 0.000352 loss: 3.4979 (3.2118) grad_norm: 1.6185 (1.6723) time: 0.4971 [2021-03-26 12:22:07 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 90/1251] eta: 0:10:38 lr: 0.000352 loss: 3.1713 (3.1788) grad_norm: 1.6652 (1.6891) time: 0.5049 [2021-03-26 12:22:12 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 100/1251] eta: 0:10:27 lr: 0.000352 loss: 3.1652 (3.1923) grad_norm: 1.7229 (1.7016) time: 0.5088 [2021-03-26 12:22:17 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 110/1251] eta: 0:10:18 lr: 0.000352 loss: 3.3066 (3.1866) grad_norm: 1.6939 (1.6973) time: 0.5076 [2021-03-26 12:22:22 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 120/1251] eta: 0:10:09 lr: 0.000352 loss: 3.1418 (3.1685) grad_norm: 1.6563 (1.6961) time: 0.5107 [2021-03-26 12:22:27 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 130/1251] eta: 0:10:01 lr: 0.000352 loss: 3.0812 (3.1600) grad_norm: 1.6521 (1.6919) time: 0.5020 [2021-03-26 12:22:32 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 140/1251] eta: 0:09:53 lr: 0.000351 loss: 3.1579 (3.1594) grad_norm: 1.6212 (1.6867) time: 0.5042 [2021-03-26 12:22:37 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 150/1251] eta: 0:09:45 lr: 0.000351 loss: 3.2883 (3.1556) grad_norm: 1.6335 (1.6842) time: 0.5063 [2021-03-26 12:22:42 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 160/1251] eta: 0:09:38 lr: 0.000351 loss: 3.2265 (3.1496) grad_norm: 1.6359 (1.6776) time: 0.4997 [2021-03-26 12:22:48 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 170/1251] eta: 0:09:31 lr: 0.000351 loss: 3.0226 (3.1590) grad_norm: 1.5279 (1.6694) time: 0.5039 [2021-03-26 12:22:53 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 180/1251] eta: 0:09:24 lr: 0.000351 loss: 3.2289 (3.1673) grad_norm: 1.5618 (1.6685) time: 0.5040 [2021-03-26 12:22:57 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 190/1251] eta: 0:09:17 lr: 0.000351 loss: 3.2424 (3.1683) grad_norm: 1.6879 (1.6668) time: 0.4979 [2021-03-26 12:23:02 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 200/1251] eta: 0:09:10 lr: 0.000351 loss: 3.3833 (3.1759) grad_norm: 1.5966 (1.6645) time: 0.4973 [2021-03-26 12:23:08 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 210/1251] eta: 0:09:04 lr: 0.000351 loss: 3.3041 (3.1650) grad_norm: 1.5919 (1.6603) time: 0.5009 [2021-03-26 12:23:13 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 220/1251] eta: 0:08:59 lr: 0.000351 loss: 3.2695 (3.1721) grad_norm: 1.6033 (1.6587) time: 0.5101 [2021-03-26 12:23:18 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 230/1251] eta: 0:08:52 lr: 0.000351 loss: 3.2522 (3.1711) grad_norm: 1.6812 (1.6599) time: 0.5086 [2021-03-26 12:23:23 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 240/1251] eta: 0:08:46 lr: 0.000351 loss: 2.9704 (3.1556) grad_norm: 1.6863 (1.6608) time: 0.5026 [2021-03-26 12:23:28 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 250/1251] eta: 0:08:41 lr: 0.000351 loss: 3.1787 (3.1602) grad_norm: 1.7181 (1.6626) time: 0.5056 [2021-03-26 12:23:33 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 260/1251] eta: 0:08:35 lr: 0.000351 loss: 3.2292 (3.1579) grad_norm: 1.6787 (1.6614) time: 0.5058 [2021-03-26 12:23:38 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 270/1251] eta: 0:08:29 lr: 0.000351 loss: 3.1791 (3.1549) grad_norm: 1.6815 (1.6631) time: 0.5042 [2021-03-26 12:23:43 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 280/1251] eta: 0:08:24 lr: 0.000351 loss: 3.1533 (3.1543) grad_norm: 1.7208 (1.6671) time: 0.5086 [2021-03-26 12:23:48 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 290/1251] eta: 0:08:18 lr: 0.000351 loss: 2.9888 (3.1482) grad_norm: 1.7435 (1.6678) time: 0.5055 [2021-03-26 12:23:53 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 300/1251] eta: 0:08:12 lr: 0.000351 loss: 2.9829 (3.1466) grad_norm: 1.6145 (1.6676) time: 0.5016 [2021-03-26 12:23:58 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 310/1251] eta: 0:08:07 lr: 0.000351 loss: 3.1277 (3.1449) grad_norm: 1.5966 (1.6682) time: 0.5048 [2021-03-26 12:24:03 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 320/1251] eta: 0:08:01 lr: 0.000351 loss: 2.7419 (3.1314) grad_norm: 1.6592 (1.6703) time: 0.5116 [2021-03-26 12:24:08 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 330/1251] eta: 0:07:56 lr: 0.000351 loss: 3.0428 (3.1387) grad_norm: 1.6592 (1.6689) time: 0.5100 [2021-03-26 12:24:13 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 340/1251] eta: 0:07:50 lr: 0.000351 loss: 3.3386 (3.1431) grad_norm: 1.5769 (1.6674) time: 0.5026 [2021-03-26 12:24:18 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 350/1251] eta: 0:07:45 lr: 0.000351 loss: 3.3147 (3.1486) grad_norm: 1.6613 (1.6682) time: 0.5012 [2021-03-26 12:24:23 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 360/1251] eta: 0:07:39 lr: 0.000351 loss: 3.3147 (3.1524) grad_norm: 1.6829 (1.6716) time: 0.5073 [2021-03-26 12:24:28 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 370/1251] eta: 0:07:34 lr: 0.000351 loss: 3.1909 (3.1497) grad_norm: 1.6190 (1.6708) time: 0.5080 [2021-03-26 12:24:34 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 380/1251] eta: 0:07:29 lr: 0.000351 loss: 3.1149 (3.1478) grad_norm: 1.6322 (1.6723) time: 0.5024 [2021-03-26 12:24:39 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 390/1251] eta: 0:07:23 lr: 0.000351 loss: 3.2945 (3.1510) grad_norm: 1.6322 (1.6705) time: 0.5054 [2021-03-26 12:24:44 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 400/1251] eta: 0:07:18 lr: 0.000350 loss: 3.4564 (3.1584) grad_norm: 1.6976 (1.6741) time: 0.5024 [2021-03-26 12:24:49 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 410/1251] eta: 0:07:12 lr: 0.000350 loss: 3.3341 (3.1540) grad_norm: 1.7255 (1.6736) time: 0.5007 [2021-03-26 12:24:54 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 420/1251] eta: 0:07:07 lr: 0.000350 loss: 3.0994 (3.1542) grad_norm: 1.6430 (1.6738) time: 0.5048 [2021-03-26 12:24:59 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 430/1251] eta: 0:07:02 lr: 0.000350 loss: 3.3739 (3.1551) grad_norm: 1.6655 (1.6796) time: 0.5038 [2021-03-26 12:25:04 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 440/1251] eta: 0:06:56 lr: 0.000350 loss: 3.2240 (3.1530) grad_norm: 1.6210 (1.6794) time: 0.5092 [2021-03-26 12:25:09 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 450/1251] eta: 0:06:51 lr: 0.000350 loss: 3.2439 (3.1574) grad_norm: 1.6548 (1.6808) time: 0.5116 [2021-03-26 12:25:14 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 460/1251] eta: 0:06:46 lr: 0.000350 loss: 3.3711 (3.1567) grad_norm: 1.7083 (1.6812) time: 0.5047 [2021-03-26 12:25:19 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 470/1251] eta: 0:06:40 lr: 0.000350 loss: 3.1838 (3.1520) grad_norm: 1.7375 (1.6834) time: 0.5007 [2021-03-26 12:25:24 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 480/1251] eta: 0:06:35 lr: 0.000350 loss: 3.2161 (3.1540) grad_norm: 1.7045 (1.6831) time: 0.5011 [2021-03-26 12:25:29 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 490/1251] eta: 0:06:30 lr: 0.000350 loss: 2.9122 (3.1531) grad_norm: 1.5683 (1.6819) time: 0.5023 [2021-03-26 12:25:34 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 500/1251] eta: 0:06:24 lr: 0.000350 loss: 2.8887 (3.1485) grad_norm: 1.6049 (1.6829) time: 0.4983 [2021-03-26 12:25:39 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 510/1251] eta: 0:06:19 lr: 0.000350 loss: 2.9008 (3.1506) grad_norm: 1.6911 (1.6825) time: 0.4977 [2021-03-26 12:25:44 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 520/1251] eta: 0:06:14 lr: 0.000350 loss: 3.1898 (3.1506) grad_norm: 1.6807 (1.6829) time: 0.5092 [2021-03-26 12:25:49 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 530/1251] eta: 0:06:09 lr: 0.000350 loss: 3.1459 (3.1511) grad_norm: 1.6336 (1.6816) time: 0.5140 [2021-03-26 12:25:54 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 540/1251] eta: 0:06:04 lr: 0.000350 loss: 3.2459 (3.1525) grad_norm: 1.6211 (1.6821) time: 0.5129 [2021-03-26 12:26:00 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 550/1251] eta: 0:05:59 lr: 0.000350 loss: 3.2668 (3.1550) grad_norm: 1.6169 (1.6819) time: 0.5253 [2021-03-26 12:26:05 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 560/1251] eta: 0:05:54 lr: 0.000350 loss: 3.3361 (3.1560) grad_norm: 1.6309 (1.6824) time: 0.5236 [2021-03-26 12:26:10 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 570/1251] eta: 0:05:49 lr: 0.000350 loss: 3.3538 (3.1571) grad_norm: 1.6683 (1.6834) time: 0.5075 [2021-03-26 12:26:15 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 580/1251] eta: 0:05:43 lr: 0.000350 loss: 3.3551 (3.1588) grad_norm: 1.6665 (1.6836) time: 0.5040 [2021-03-26 12:26:20 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 590/1251] eta: 0:05:38 lr: 0.000350 loss: 3.3860 (3.1604) grad_norm: 1.7067 (1.6847) time: 0.5112 [2021-03-26 12:26:25 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 600/1251] eta: 0:05:33 lr: 0.000350 loss: 3.3096 (3.1622) grad_norm: 1.6217 (1.6825) time: 0.5070 [2021-03-26 12:26:30 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 610/1251] eta: 0:05:28 lr: 0.000350 loss: 3.2519 (3.1623) grad_norm: 1.5680 (1.6825) time: 0.4998 [2021-03-26 12:26:35 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 620/1251] eta: 0:05:23 lr: 0.000350 loss: 3.1513 (3.1619) grad_norm: 1.6948 (1.6840) time: 0.5041 [2021-03-26 12:26:40 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 630/1251] eta: 0:05:17 lr: 0.000350 loss: 3.2950 (3.1626) grad_norm: 1.8161 (1.6859) time: 0.5047 [2021-03-26 12:26:45 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 640/1251] eta: 0:05:12 lr: 0.000350 loss: 3.3357 (3.1621) grad_norm: 1.7512 (1.6869) time: 0.5048 [2021-03-26 12:26:50 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 650/1251] eta: 0:05:07 lr: 0.000349 loss: 3.3365 (3.1628) grad_norm: 1.7316 (1.6887) time: 0.5093 [2021-03-26 12:26:55 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 660/1251] eta: 0:05:02 lr: 0.000349 loss: 3.2900 (3.1628) grad_norm: 1.7417 (1.6902) time: 0.5052 [2021-03-26 12:27:00 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 670/1251] eta: 0:04:57 lr: 0.000349 loss: 3.2257 (3.1631) grad_norm: 1.7146 (1.6903) time: 0.4997 [2021-03-26 12:27:05 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 680/1251] eta: 0:04:52 lr: 0.000349 loss: 3.2106 (3.1637) grad_norm: 1.7358 (1.6920) time: 0.5019 [2021-03-26 12:27:10 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 690/1251] eta: 0:04:46 lr: 0.000349 loss: 3.1971 (3.1654) grad_norm: 1.7886 (1.6939) time: 0.5019 [2021-03-26 12:27:16 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 700/1251] eta: 0:04:41 lr: 0.000349 loss: 3.2670 (3.1660) grad_norm: 1.6843 (1.6930) time: 0.5032 [2021-03-26 12:27:21 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 710/1251] eta: 0:04:36 lr: 0.000349 loss: 3.1496 (3.1644) grad_norm: 1.6916 (1.6939) time: 0.5020 [2021-03-26 12:27:26 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 720/1251] eta: 0:04:31 lr: 0.000349 loss: 3.2515 (3.1661) grad_norm: 1.7023 (1.6937) time: 0.5018 [2021-03-26 12:27:31 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 730/1251] eta: 0:04:26 lr: 0.000349 loss: 3.3209 (3.1638) grad_norm: 1.6922 (1.6933) time: 0.5028 [2021-03-26 12:27:36 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 740/1251] eta: 0:04:21 lr: 0.000349 loss: 3.1433 (3.1628) grad_norm: 1.7073 (1.6949) time: 0.5232 [2021-03-26 12:27:41 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 750/1251] eta: 0:04:16 lr: 0.000349 loss: 3.0794 (3.1617) grad_norm: 1.6804 (1.6948) time: 0.5312 [2021-03-26 12:27:46 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 760/1251] eta: 0:04:10 lr: 0.000349 loss: 3.1271 (3.1615) grad_norm: 1.6804 (1.6958) time: 0.5093 [2021-03-26 12:27:51 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 770/1251] eta: 0:04:05 lr: 0.000349 loss: 3.4280 (3.1660) grad_norm: 1.7105 (1.6959) time: 0.5062 [2021-03-26 12:27:56 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 780/1251] eta: 0:04:00 lr: 0.000349 loss: 3.5743 (3.1694) grad_norm: 1.6466 (1.6960) time: 0.5081 [2021-03-26 12:28:01 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 790/1251] eta: 0:03:55 lr: 0.000349 loss: 3.2857 (3.1691) grad_norm: 1.6337 (1.6972) time: 0.5013 [2021-03-26 12:28:06 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 800/1251] eta: 0:03:50 lr: 0.000349 loss: 3.1447 (3.1669) grad_norm: 1.6511 (1.6981) time: 0.5030 [2021-03-26 12:28:11 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 810/1251] eta: 0:03:45 lr: 0.000349 loss: 3.1988 (3.1687) grad_norm: 1.6511 (1.6973) time: 0.5043 [2021-03-26 12:28:17 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 820/1251] eta: 0:03:40 lr: 0.000349 loss: 3.3823 (3.1702) grad_norm: 1.6319 (1.6967) time: 0.5061 [2021-03-26 12:28:22 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 830/1251] eta: 0:03:35 lr: 0.000349 loss: 3.3553 (3.1706) grad_norm: 1.6634 (1.6970) time: 0.5080 [2021-03-26 12:28:27 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 840/1251] eta: 0:03:29 lr: 0.000349 loss: 3.0299 (3.1677) grad_norm: 1.6945 (1.6972) time: 0.5087 [2021-03-26 12:28:32 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 850/1251] eta: 0:03:24 lr: 0.000349 loss: 3.2744 (3.1702) grad_norm: 1.6080 (1.6966) time: 0.5147 [2021-03-26 12:28:37 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 860/1251] eta: 0:03:19 lr: 0.000349 loss: 3.2300 (3.1650) grad_norm: 1.6098 (1.6966) time: 0.5092 [2021-03-26 12:28:42 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 870/1251] eta: 0:03:14 lr: 0.000349 loss: 3.1940 (3.1647) grad_norm: 1.6933 (1.6968) time: 0.5048 [2021-03-26 12:28:47 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 880/1251] eta: 0:03:09 lr: 0.000349 loss: 3.4018 (3.1694) grad_norm: 1.6715 (1.6961) time: 0.5071 [2021-03-26 12:28:52 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 890/1251] eta: 0:03:04 lr: 0.000349 loss: 3.5139 (3.1706) grad_norm: 1.6028 (1.6955) time: 0.5024 [2021-03-26 12:28:57 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 900/1251] eta: 0:02:59 lr: 0.000348 loss: 3.4006 (3.1716) grad_norm: 1.6795 (1.6961) time: 0.5037 [2021-03-26 12:29:02 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 910/1251] eta: 0:02:54 lr: 0.000348 loss: 3.2858 (3.1725) grad_norm: 1.7252 (1.6967) time: 0.5075 [2021-03-26 12:29:07 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 920/1251] eta: 0:02:48 lr: 0.000348 loss: 3.3147 (3.1727) grad_norm: 1.6447 (1.6967) time: 0.5025 [2021-03-26 12:29:12 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 930/1251] eta: 0:02:43 lr: 0.000348 loss: 3.2093 (3.1708) grad_norm: 1.6054 (1.6953) time: 0.5042 [2021-03-26 12:29:17 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 940/1251] eta: 0:02:38 lr: 0.000348 loss: 3.2093 (3.1713) grad_norm: 1.6665 (1.6969) time: 0.5074 [2021-03-26 12:29:22 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 950/1251] eta: 0:02:33 lr: 0.000348 loss: 3.1014 (3.1671) grad_norm: 1.7900 (1.6988) time: 0.5037 [2021-03-26 12:29:27 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 960/1251] eta: 0:02:28 lr: 0.000348 loss: 3.1584 (3.1677) grad_norm: 1.7900 (1.6988) time: 0.5028 [2021-03-26 12:29:32 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 970/1251] eta: 0:02:23 lr: 0.000348 loss: 3.1971 (3.1664) grad_norm: 1.6985 (1.6994) time: 0.5053 [2021-03-26 12:29:38 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 980/1251] eta: 0:02:18 lr: 0.000348 loss: 3.1709 (3.1675) grad_norm: 1.7118 (1.7016) time: 0.5048 [2021-03-26 12:29:43 swin_small_patch4_window7_224] INFO: Epoch: [180] [ 990/1251] eta: 0:02:13 lr: 0.000348 loss: 3.2518 (3.1673) grad_norm: 1.7484 (1.7016) time: 0.5060 [2021-03-26 12:29:48 swin_small_patch4_window7_224] INFO: Epoch: [180] [1000/1251] eta: 0:02:07 lr: 0.000348 loss: 3.2446 (3.1652) grad_norm: 1.6177 (1.7019) time: 0.5033 [2021-03-26 12:29:53 swin_small_patch4_window7_224] INFO: Epoch: [180] [1010/1251] eta: 0:02:02 lr: 0.000348 loss: 3.2446 (3.1668) grad_norm: 1.6784 (1.7016) time: 0.5025 [2021-03-26 12:29:58 swin_small_patch4_window7_224] INFO: Epoch: [180] [1020/1251] eta: 0:01:57 lr: 0.000348 loss: 3.2373 (3.1663) grad_norm: 1.6849 (1.7027) time: 0.5035 [2021-03-26 12:30:03 swin_small_patch4_window7_224] INFO: Epoch: [180] [1030/1251] eta: 0:01:52 lr: 0.000348 loss: 3.2158 (3.1646) grad_norm: 1.6603 (1.7022) time: 0.5013 [2021-03-26 12:30:08 swin_small_patch4_window7_224] INFO: Epoch: [180] [1040/1251] eta: 0:01:47 lr: 0.000348 loss: 3.1555 (3.1644) grad_norm: 1.6105 (1.7019) time: 0.4990 [2021-03-26 12:30:13 swin_small_patch4_window7_224] INFO: Epoch: [180] [1050/1251] eta: 0:01:42 lr: 0.000348 loss: 3.2696 (3.1662) grad_norm: 1.6971 (1.7029) time: 0.4978 [2021-03-26 12:30:18 swin_small_patch4_window7_224] INFO: Epoch: [180] [1060/1251] eta: 0:01:37 lr: 0.000348 loss: 3.3661 (3.1679) grad_norm: 1.6971 (1.7027) time: 0.4982 [2021-03-26 12:30:23 swin_small_patch4_window7_224] INFO: Epoch: [180] [1070/1251] eta: 0:01:32 lr: 0.000348 loss: 3.3661 (3.1679) grad_norm: 1.6650 (1.7028) time: 0.5041 [2021-03-26 12:30:28 swin_small_patch4_window7_224] INFO: Epoch: [180] [1080/1251] eta: 0:01:27 lr: 0.000348 loss: 3.3248 (3.1680) grad_norm: 1.6388 (1.7016) time: 0.5051 [2021-03-26 12:30:33 swin_small_patch4_window7_224] INFO: Epoch: [180] [1090/1251] eta: 0:01:21 lr: 0.000348 loss: 3.2899 (3.1691) grad_norm: 1.6388 (1.7015) time: 0.5005 [2021-03-26 12:30:38 swin_small_patch4_window7_224] INFO: Epoch: [180] [1100/1251] eta: 0:01:16 lr: 0.000348 loss: 3.4402 (3.1715) grad_norm: 1.6794 (1.7020) time: 0.5000 [2021-03-26 12:30:43 swin_small_patch4_window7_224] INFO: Epoch: [180] [1110/1251] eta: 0:01:11 lr: 0.000348 loss: 3.4114 (3.1715) grad_norm: 1.7370 (1.7031) time: 0.5025 [2021-03-26 12:30:48 swin_small_patch4_window7_224] INFO: Epoch: [180] [1120/1251] eta: 0:01:06 lr: 0.000348 loss: 3.0403 (3.1693) grad_norm: 1.8130 (1.7047) time: 0.5055 [2021-03-26 12:30:53 swin_small_patch4_window7_224] INFO: Epoch: [180] [1130/1251] eta: 0:01:01 lr: 0.000348 loss: 3.0403 (3.1715) grad_norm: 1.6620 (1.7038) time: 0.5037 [2021-03-26 12:30:58 swin_small_patch4_window7_224] INFO: Epoch: [180] [1140/1251] eta: 0:00:56 lr: 0.000348 loss: 3.2656 (3.1718) grad_norm: 1.6338 (1.7035) time: 0.4982 [2021-03-26 12:31:03 swin_small_patch4_window7_224] INFO: Epoch: [180] [1150/1251] eta: 0:00:51 lr: 0.000348 loss: 3.1449 (3.1711) grad_norm: 1.6741 (1.7037) time: 0.4999 [2021-03-26 12:31:08 swin_small_patch4_window7_224] INFO: Epoch: [180] [1160/1251] eta: 0:00:46 lr: 0.000347 loss: 3.0616 (3.1706) grad_norm: 1.6628 (1.7039) time: 0.5075 [2021-03-26 12:31:13 swin_small_patch4_window7_224] INFO: Epoch: [180] [1170/1251] eta: 0:00:41 lr: 0.000347 loss: 3.2432 (3.1705) grad_norm: 1.6654 (1.7038) time: 0.5046 [2021-03-26 12:31:18 swin_small_patch4_window7_224] INFO: Epoch: [180] [1180/1251] eta: 0:00:36 lr: 0.000347 loss: 3.2110 (3.1705) grad_norm: 1.7315 (1.7044) time: 0.5066 [2021-03-26 12:31:23 swin_small_patch4_window7_224] INFO: Epoch: [180] [1190/1251] eta: 0:00:31 lr: 0.000347 loss: 3.1181 (3.1685) grad_norm: 1.7026 (1.7038) time: 0.5044 [2021-03-26 12:31:28 swin_small_patch4_window7_224] INFO: Epoch: [180] [1200/1251] eta: 0:00:25 lr: 0.000347 loss: 3.1297 (3.1703) grad_norm: 1.6290 (1.7040) time: 0.5000 [2021-03-26 12:31:33 swin_small_patch4_window7_224] INFO: Epoch: [180] [1210/1251] eta: 0:00:20 lr: 0.000347 loss: 3.2438 (3.1703) grad_norm: 1.6195 (1.7030) time: 0.5036 [2021-03-26 12:31:38 swin_small_patch4_window7_224] INFO: Epoch: [180] [1220/1251] eta: 0:00:15 lr: 0.000347 loss: 3.4099 (3.1726) grad_norm: 1.6357 (1.7028) time: 0.5002 [2021-03-26 12:31:43 swin_small_patch4_window7_224] INFO: Epoch: [180] [1230/1251] eta: 0:00:10 lr: 0.000347 loss: 3.4191 (3.1737) grad_norm: 1.6675 (1.7032) time: 0.5010 [2021-03-26 12:31:48 swin_small_patch4_window7_224] INFO: Epoch: [180] [1240/1251] eta: 0:00:05 lr: 0.000347 loss: 3.3747 (3.1757) grad_norm: 1.7211 (1.7033) time: 0.5072 [2021-03-26 12:31:53 swin_small_patch4_window7_224] INFO: Epoch: [180] [1250/1251] eta: 0:00:00 lr: 0.000347 loss: 3.4450 (3.1765) grad_norm: 1.6715 (1.7031) time: 0.5108 [2021-03-26 12:32:54 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.7678 (0.7678) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-26 12:32:55 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7678 (0.7594) acc1: 82.8125 (81.8182) acc5: 96.8750 (96.3068) [2021-03-26 12:32:56 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.8124 (0.7964) acc1: 79.6875 (81.0268) acc5: 95.3125 (95.9821) [2021-03-26 12:32:57 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8400 (0.8208) acc1: 78.1250 (80.4940) acc5: 95.3125 (95.6653) [2021-03-26 12:32:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8291 (0.8416) acc1: 78.1250 (79.5732) acc5: 95.3125 (95.4649) [2021-03-26 12:32:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9030 (0.8627) acc1: 76.5625 (78.9760) acc5: 93.7500 (95.0720) [2021-03-26 12:33:10 swin_small_patch4_window7_224] INFO: * Acc@1 79.650 Acc@5 94.996 loss 0.857 [2021-03-26 12:33:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.7% [2021-03-26 12:33:10 swin_small_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-26 12:33:15 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 0/1251] eta: 1:27:22 lr: 0.000347 loss: 3.7924 (3.7924) grad_norm: 1.7903 (1.7903) time: 4.1904 [2021-03-26 12:33:20 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 10/1251] eta: 0:17:43 lr: 0.000347 loss: 3.5803 (3.3497) grad_norm: 1.6889 (1.7030) time: 0.8570 [2021-03-26 12:33:25 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 20/1251] eta: 0:14:11 lr: 0.000347 loss: 3.5244 (3.3464) grad_norm: 1.6653 (1.7028) time: 0.5167 [2021-03-26 12:33:30 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 30/1251] eta: 0:12:54 lr: 0.000347 loss: 3.2854 (3.3265) grad_norm: 1.6608 (1.7262) time: 0.5114 [2021-03-26 12:33:35 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 40/1251] eta: 0:12:12 lr: 0.000347 loss: 3.2123 (3.2635) grad_norm: 1.6608 (1.7175) time: 0.5141 [2021-03-26 12:33:40 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 50/1251] eta: 0:11:44 lr: 0.000347 loss: 3.1934 (3.2735) grad_norm: 1.6225 (1.6963) time: 0.5125 [2021-03-26 12:33:45 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 60/1251] eta: 0:11:23 lr: 0.000347 loss: 3.3501 (3.2742) grad_norm: 1.5765 (1.6795) time: 0.5097 [2021-03-26 12:33:50 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 70/1251] eta: 0:11:04 lr: 0.000347 loss: 3.3547 (3.2982) grad_norm: 1.6561 (1.6968) time: 0.5012 [2021-03-26 12:33:55 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 80/1251] eta: 0:10:51 lr: 0.000347 loss: 3.3547 (3.2502) grad_norm: 1.7354 (1.7045) time: 0.5018 [2021-03-26 12:34:01 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 90/1251] eta: 0:10:39 lr: 0.000347 loss: 3.1616 (3.2586) grad_norm: 1.6936 (1.7084) time: 0.5084 [2021-03-26 12:34:05 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 100/1251] eta: 0:10:27 lr: 0.000347 loss: 3.2887 (3.2532) grad_norm: 1.6788 (1.7037) time: 0.5001 [2021-03-26 12:34:10 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 110/1251] eta: 0:10:17 lr: 0.000347 loss: 3.1017 (3.2379) grad_norm: 1.6350 (1.6973) time: 0.4973 [2021-03-26 12:34:16 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 120/1251] eta: 0:10:08 lr: 0.000347 loss: 3.1847 (3.2350) grad_norm: 1.5330 (1.6912) time: 0.5032 [2021-03-26 12:34:21 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 130/1251] eta: 0:10:00 lr: 0.000347 loss: 3.2319 (3.2276) grad_norm: 1.5895 (1.6850) time: 0.5074 [2021-03-26 12:34:26 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 140/1251] eta: 0:09:52 lr: 0.000347 loss: 3.2432 (3.2399) grad_norm: 1.5959 (1.6825) time: 0.5038 [2021-03-26 12:34:31 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 150/1251] eta: 0:09:45 lr: 0.000347 loss: 3.3607 (3.2441) grad_norm: 1.6123 (1.6848) time: 0.5056 [2021-03-26 12:34:36 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 160/1251] eta: 0:09:38 lr: 0.000346 loss: 3.3224 (3.2435) grad_norm: 1.6153 (1.6801) time: 0.5093 [2021-03-26 12:34:41 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 170/1251] eta: 0:09:31 lr: 0.000346 loss: 3.2257 (3.2403) grad_norm: 1.5862 (1.6753) time: 0.5051 [2021-03-26 12:34:46 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 180/1251] eta: 0:09:25 lr: 0.000346 loss: 3.3883 (3.2468) grad_norm: 1.5888 (1.6743) time: 0.5070 [2021-03-26 12:34:51 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 190/1251] eta: 0:09:18 lr: 0.000346 loss: 3.2923 (3.2414) grad_norm: 1.7513 (1.7348) time: 0.5056 [2021-03-26 12:34:56 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 200/1251] eta: 0:09:12 lr: 0.000346 loss: 3.2342 (3.2466) grad_norm: 1.6641 (1.7286) time: 0.5048 [2021-03-26 12:35:01 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 210/1251] eta: 0:09:05 lr: 0.000346 loss: 3.4158 (3.2489) grad_norm: 1.6241 (1.7283) time: 0.5063 [2021-03-26 12:35:06 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 220/1251] eta: 0:08:59 lr: 0.000346 loss: 3.3011 (3.2469) grad_norm: 1.6421 (1.7273) time: 0.5036 [2021-03-26 12:35:11 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 230/1251] eta: 0:08:53 lr: 0.000346 loss: 3.1296 (3.2324) grad_norm: 1.7346 (1.7296) time: 0.5087 [2021-03-26 12:35:16 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 240/1251] eta: 0:08:47 lr: 0.000346 loss: 2.9865 (3.2289) grad_norm: 1.7952 (1.7337) time: 0.5076 [2021-03-26 12:35:21 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 250/1251] eta: 0:08:41 lr: 0.000346 loss: 3.1104 (3.2250) grad_norm: 1.8711 (1.7385) time: 0.5019 [2021-03-26 12:35:26 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 260/1251] eta: 0:08:36 lr: 0.000346 loss: 3.1826 (3.2206) grad_norm: 1.7585 (1.7358) time: 0.5059 [2021-03-26 12:35:31 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 270/1251] eta: 0:08:30 lr: 0.000346 loss: 3.0383 (3.2179) grad_norm: 1.6266 (1.7336) time: 0.5069 [2021-03-26 12:35:36 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 280/1251] eta: 0:08:24 lr: 0.000346 loss: 3.1264 (3.2132) grad_norm: 1.6021 (1.7307) time: 0.5013 [2021-03-26 12:35:41 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 290/1251] eta: 0:08:18 lr: 0.000346 loss: 3.2198 (3.2156) grad_norm: 1.5947 (1.7286) time: 0.5012 [2021-03-26 12:35:46 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 300/1251] eta: 0:08:13 lr: 0.000346 loss: 3.2772 (3.2145) grad_norm: 1.7392 (1.7310) time: 0.5035 [2021-03-26 12:35:52 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 310/1251] eta: 0:08:07 lr: 0.000346 loss: 3.3290 (3.2138) grad_norm: 1.7084 (1.7289) time: 0.5027 [2021-03-26 12:35:57 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 320/1251] eta: 0:08:01 lr: 0.000346 loss: 3.1353 (3.2090) grad_norm: 1.6247 (1.7253) time: 0.5065 [2021-03-26 12:36:02 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 330/1251] eta: 0:07:56 lr: 0.000346 loss: 3.1329 (3.2061) grad_norm: 1.7062 (1.7261) time: 0.5096 [2021-03-26 12:36:07 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 340/1251] eta: 0:07:51 lr: 0.000346 loss: 3.1329 (3.2025) grad_norm: 1.7960 (1.7291) time: 0.5140 [2021-03-26 12:36:12 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 350/1251] eta: 0:07:45 lr: 0.000346 loss: 3.1092 (3.2016) grad_norm: 1.7183 (1.7274) time: 0.5123 [2021-03-26 12:36:17 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 360/1251] eta: 0:07:40 lr: 0.000346 loss: 3.1092 (3.1931) grad_norm: 1.7050 (1.7276) time: 0.5027 [2021-03-26 12:36:22 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 370/1251] eta: 0:07:34 lr: 0.000346 loss: 2.9929 (3.1894) grad_norm: 1.7050 (1.7259) time: 0.5032 [2021-03-26 12:36:27 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 380/1251] eta: 0:07:29 lr: 0.000346 loss: 3.2905 (3.1928) grad_norm: 1.6898 (1.7267) time: 0.5013 [2021-03-26 12:36:32 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 390/1251] eta: 0:07:23 lr: 0.000346 loss: 3.3992 (3.1892) grad_norm: 1.7099 (1.7262) time: 0.4935 [2021-03-26 12:36:37 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 400/1251] eta: 0:07:18 lr: 0.000346 loss: 3.1844 (3.1866) grad_norm: 1.7084 (1.7277) time: 0.4953 [2021-03-26 12:36:42 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 410/1251] eta: 0:07:12 lr: 0.000346 loss: 3.3600 (3.1912) grad_norm: 1.6616 (1.7264) time: 0.5007 [2021-03-26 12:36:47 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 420/1251] eta: 0:07:07 lr: 0.000345 loss: 3.3755 (3.1888) grad_norm: 1.7170 (1.7285) time: 0.4981 [2021-03-26 12:36:52 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 430/1251] eta: 0:07:01 lr: 0.000345 loss: 3.0804 (3.1841) grad_norm: 1.7360 (1.7295) time: 0.4963 [2021-03-26 12:36:57 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 440/1251] eta: 0:06:56 lr: 0.000345 loss: 3.1307 (3.1872) grad_norm: 1.7360 (1.7328) time: 0.4984 [2021-03-26 12:37:02 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 450/1251] eta: 0:06:50 lr: 0.000345 loss: 3.3163 (3.1894) grad_norm: 1.6847 (1.7310) time: 0.4966 [2021-03-26 12:37:07 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 460/1251] eta: 0:06:45 lr: 0.000345 loss: 3.3833 (3.1915) grad_norm: 1.6558 (1.7299) time: 0.4998 [2021-03-26 12:37:12 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 470/1251] eta: 0:06:40 lr: 0.000345 loss: 3.1614 (3.1902) grad_norm: 1.6708 (1.7289) time: 0.5034 [2021-03-26 12:37:17 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 480/1251] eta: 0:06:35 lr: 0.000345 loss: 3.3611 (3.1922) grad_norm: 1.6606 (1.7287) time: 0.5052 [2021-03-26 12:37:22 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 490/1251] eta: 0:06:29 lr: 0.000345 loss: 3.4867 (3.1941) grad_norm: 1.6833 (1.7289) time: 0.5034 [2021-03-26 12:37:27 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 500/1251] eta: 0:06:24 lr: 0.000345 loss: 3.3532 (3.1961) grad_norm: 1.7582 (1.7300) time: 0.5026 [2021-03-26 12:37:32 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 510/1251] eta: 0:06:19 lr: 0.000345 loss: 3.2331 (3.1952) grad_norm: 1.8017 (1.7337) time: 0.5013 [2021-03-26 12:37:37 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 520/1251] eta: 0:06:13 lr: 0.000345 loss: 3.2331 (3.1944) grad_norm: 1.7681 (1.7317) time: 0.4991 [2021-03-26 12:37:42 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 530/1251] eta: 0:06:08 lr: 0.000345 loss: 3.3602 (3.1968) grad_norm: 1.6284 (1.7308) time: 0.5016 [2021-03-26 12:37:47 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 540/1251] eta: 0:06:03 lr: 0.000345 loss: 3.4127 (3.2012) grad_norm: 1.6340 (1.7296) time: 0.5082 [2021-03-26 12:37:52 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 550/1251] eta: 0:05:58 lr: 0.000345 loss: 3.4127 (3.1976) grad_norm: 1.5931 (1.7268) time: 0.5218 [2021-03-26 12:37:58 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 560/1251] eta: 0:05:53 lr: 0.000345 loss: 3.0148 (3.1941) grad_norm: 1.6130 (1.7270) time: 0.5178 [2021-03-26 12:38:02 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 570/1251] eta: 0:05:48 lr: 0.000345 loss: 3.1328 (3.1934) grad_norm: 1.7274 (1.7269) time: 0.4992 [2021-03-26 12:38:07 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 580/1251] eta: 0:05:42 lr: 0.000345 loss: 3.1318 (3.1913) grad_norm: 1.7143 (1.7266) time: 0.4948 [2021-03-26 12:38:12 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 590/1251] eta: 0:05:37 lr: 0.000345 loss: 3.1199 (3.1907) grad_norm: 1.6409 (1.7251) time: 0.5039 [2021-03-26 12:38:18 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 600/1251] eta: 0:05:32 lr: 0.000345 loss: 3.3356 (3.1932) grad_norm: 1.5852 (1.7234) time: 0.5062 [2021-03-26 12:38:23 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 610/1251] eta: 0:05:27 lr: 0.000345 loss: 3.3915 (3.1933) grad_norm: 1.5916 (1.7225) time: 0.5016 [2021-03-26 12:38:28 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 620/1251] eta: 0:05:22 lr: 0.000345 loss: 3.2971 (3.1961) grad_norm: 1.6165 (1.7217) time: 0.4994 [2021-03-26 12:38:33 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 630/1251] eta: 0:05:16 lr: 0.000345 loss: 3.3986 (3.1978) grad_norm: 1.6775 (1.7220) time: 0.4981 [2021-03-26 12:38:38 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 640/1251] eta: 0:05:11 lr: 0.000345 loss: 3.2034 (3.1948) grad_norm: 1.6433 (1.7207) time: 0.5019 [2021-03-26 12:38:43 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 650/1251] eta: 0:05:06 lr: 0.000345 loss: 3.0340 (3.1917) grad_norm: 1.6433 (1.7207) time: 0.5035 [2021-03-26 12:38:48 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 660/1251] eta: 0:05:01 lr: 0.000345 loss: 3.2177 (3.1918) grad_norm: 1.7500 (1.7219) time: 0.5037 [2021-03-26 12:38:53 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 670/1251] eta: 0:04:56 lr: 0.000344 loss: 3.2177 (3.1936) grad_norm: 1.6931 (1.7210) time: 0.5048 [2021-03-26 12:38:58 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 680/1251] eta: 0:04:51 lr: 0.000344 loss: 3.3892 (3.1971) grad_norm: 1.6931 (1.7203) time: 0.5043 [2021-03-26 12:39:03 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 690/1251] eta: 0:04:45 lr: 0.000344 loss: 3.4247 (3.1965) grad_norm: 1.7003 (1.7204) time: 0.5035 [2021-03-26 12:39:08 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 700/1251] eta: 0:04:40 lr: 0.000344 loss: 3.2197 (3.1964) grad_norm: 1.6784 (1.7194) time: 0.4986 [2021-03-26 12:39:13 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 710/1251] eta: 0:04:35 lr: 0.000344 loss: 3.1953 (3.1965) grad_norm: 1.6784 (1.7201) time: 0.4961 [2021-03-26 12:39:18 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 720/1251] eta: 0:04:30 lr: 0.000344 loss: 3.0437 (3.1917) grad_norm: 1.6985 (1.7188) time: 0.4948 [2021-03-26 12:39:23 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 730/1251] eta: 0:04:25 lr: 0.000344 loss: 2.9341 (3.1910) grad_norm: 1.5657 (1.7168) time: 0.5042 [2021-03-26 12:39:28 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 740/1251] eta: 0:04:20 lr: 0.000344 loss: 3.0806 (3.1884) grad_norm: 1.5684 (1.7160) time: 0.5269 [2021-03-26 12:39:33 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 750/1251] eta: 0:04:15 lr: 0.000344 loss: 3.0352 (3.1868) grad_norm: 1.6417 (1.7160) time: 0.5272 [2021-03-26 12:39:38 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 760/1251] eta: 0:04:10 lr: 0.000344 loss: 2.9433 (3.1848) grad_norm: 1.6858 (1.7159) time: 0.5111 [2021-03-26 12:39:44 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 770/1251] eta: 0:04:05 lr: 0.000344 loss: 3.1986 (3.1861) grad_norm: 1.6972 (1.7162) time: 0.5123 [2021-03-26 12:39:49 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 780/1251] eta: 0:04:00 lr: 0.000344 loss: 3.2249 (3.1871) grad_norm: 1.6830 (1.7165) time: 0.5162 [2021-03-26 12:39:54 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 790/1251] eta: 0:03:55 lr: 0.000344 loss: 3.3352 (3.1876) grad_norm: 1.5865 (1.7148) time: 0.5113 [2021-03-26 12:39:59 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 800/1251] eta: 0:03:49 lr: 0.000344 loss: 3.3352 (3.1890) grad_norm: 1.5865 (1.7138) time: 0.5031 [2021-03-26 12:40:04 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 810/1251] eta: 0:03:44 lr: 0.000344 loss: 3.2383 (3.1886) grad_norm: 1.6712 (1.7136) time: 0.4992 [2021-03-26 12:40:09 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 820/1251] eta: 0:03:39 lr: 0.000344 loss: 3.1847 (3.1882) grad_norm: 1.6712 (1.7124) time: 0.4967 [2021-03-26 12:40:14 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 830/1251] eta: 0:03:34 lr: 0.000344 loss: 3.1601 (3.1862) grad_norm: 1.6217 (1.7120) time: 0.4936 [2021-03-26 12:40:19 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 840/1251] eta: 0:03:29 lr: 0.000344 loss: 3.2457 (3.1872) grad_norm: 1.6506 (1.7131) time: 0.4981 [2021-03-26 12:40:24 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 850/1251] eta: 0:03:24 lr: 0.000344 loss: 3.3434 (3.1871) grad_norm: 1.7000 (1.7140) time: 0.5025 [2021-03-26 12:40:29 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 860/1251] eta: 0:03:18 lr: 0.000344 loss: 3.1540 (3.1850) grad_norm: 1.6830 (1.7141) time: 0.5015 [2021-03-26 12:40:34 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 870/1251] eta: 0:03:13 lr: 0.000344 loss: 3.1540 (3.1873) grad_norm: 1.7933 (1.7156) time: 0.5038 [2021-03-26 12:40:39 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 880/1251] eta: 0:03:08 lr: 0.000344 loss: 3.1813 (3.1872) grad_norm: 1.8750 (1.7170) time: 0.5036 [2021-03-26 12:40:44 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 890/1251] eta: 0:03:03 lr: 0.000344 loss: 3.0894 (3.1859) grad_norm: 1.8254 (1.7174) time: 0.5056 [2021-03-26 12:40:49 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 900/1251] eta: 0:02:58 lr: 0.000344 loss: 3.0204 (3.1821) grad_norm: 1.7385 (1.7177) time: 0.5049 [2021-03-26 12:40:54 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 910/1251] eta: 0:02:53 lr: 0.000344 loss: 2.9234 (3.1797) grad_norm: 1.7150 (1.7184) time: 0.4961 [2021-03-26 12:40:59 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 920/1251] eta: 0:02:48 lr: 0.000344 loss: 3.1215 (3.1803) grad_norm: 1.7224 (1.7202) time: 0.5026 [2021-03-26 12:41:04 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 930/1251] eta: 0:02:43 lr: 0.000343 loss: 3.1215 (3.1769) grad_norm: 1.7090 (1.7200) time: 0.5037 [2021-03-26 12:41:09 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 940/1251] eta: 0:02:38 lr: 0.000343 loss: 2.9996 (3.1787) grad_norm: 1.6147 (1.7200) time: 0.5002 [2021-03-26 12:41:14 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 950/1251] eta: 0:02:33 lr: 0.000343 loss: 3.4580 (3.1809) grad_norm: 1.6430 (1.7202) time: 0.5044 [2021-03-26 12:41:19 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 960/1251] eta: 0:02:27 lr: 0.000343 loss: 3.4487 (3.1830) grad_norm: 1.6430 (1.7196) time: 0.5086 [2021-03-26 12:41:24 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 970/1251] eta: 0:02:22 lr: 0.000343 loss: 3.3265 (3.1833) grad_norm: 1.5734 (1.7182) time: 0.5140 [2021-03-26 12:41:29 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 980/1251] eta: 0:02:17 lr: 0.000343 loss: 3.1551 (3.1814) grad_norm: 1.5611 (1.7171) time: 0.5072 [2021-03-26 12:41:34 swin_small_patch4_window7_224] INFO: Epoch: [181] [ 990/1251] eta: 0:02:12 lr: 0.000343 loss: 3.1551 (3.1822) grad_norm: 1.6387 (1.7170) time: 0.5014 [2021-03-26 12:41:39 swin_small_patch4_window7_224] INFO: Epoch: [181] [1000/1251] eta: 0:02:07 lr: 0.000343 loss: 3.2865 (3.1805) grad_norm: 1.6778 (1.7163) time: 0.5030 [2021-03-26 12:41:44 swin_small_patch4_window7_224] INFO: Epoch: [181] [1010/1251] eta: 0:02:02 lr: 0.000343 loss: 3.0245 (3.1772) grad_norm: 1.6516 (1.7158) time: 0.5018 [2021-03-26 12:41:49 swin_small_patch4_window7_224] INFO: Epoch: [181] [1020/1251] eta: 0:01:57 lr: 0.000343 loss: 3.0643 (3.1783) grad_norm: 1.6743 (1.7160) time: 0.4986 [2021-03-26 12:41:54 swin_small_patch4_window7_224] INFO: Epoch: [181] [1030/1251] eta: 0:01:52 lr: 0.000343 loss: 3.3731 (3.1780) grad_norm: 1.7482 (1.7179) time: 0.5030 [2021-03-26 12:41:59 swin_small_patch4_window7_224] INFO: Epoch: [181] [1040/1251] eta: 0:01:47 lr: 0.000343 loss: 3.4224 (3.1790) grad_norm: 1.8563 (1.7196) time: 0.5034 [2021-03-26 12:42:04 swin_small_patch4_window7_224] INFO: Epoch: [181] [1050/1251] eta: 0:01:42 lr: 0.000343 loss: 3.4662 (3.1796) grad_norm: 1.7297 (1.7191) time: 0.4985 [2021-03-26 12:42:09 swin_small_patch4_window7_224] INFO: Epoch: [181] [1060/1251] eta: 0:01:36 lr: 0.000343 loss: 3.3636 (3.1810) grad_norm: 1.6885 (1.7192) time: 0.5011 [2021-03-26 12:42:14 swin_small_patch4_window7_224] INFO: Epoch: [181] [1070/1251] eta: 0:01:31 lr: 0.000343 loss: 3.3123 (3.1798) grad_norm: 1.6376 (1.7183) time: 0.5003 [2021-03-26 12:42:19 swin_small_patch4_window7_224] INFO: Epoch: [181] [1080/1251] eta: 0:01:26 lr: 0.000343 loss: 3.2542 (3.1790) grad_norm: 1.6411 (1.7184) time: 0.5023 [2021-03-26 12:42:24 swin_small_patch4_window7_224] INFO: Epoch: [181] [1090/1251] eta: 0:01:21 lr: 0.000343 loss: 3.3525 (3.1801) grad_norm: 1.6870 (1.7183) time: 0.5053 [2021-03-26 12:42:29 swin_small_patch4_window7_224] INFO: Epoch: [181] [1100/1251] eta: 0:01:16 lr: 0.000343 loss: 3.3934 (3.1816) grad_norm: 1.6870 (1.7179) time: 0.4987 [2021-03-26 12:42:34 swin_small_patch4_window7_224] INFO: Epoch: [181] [1110/1251] eta: 0:01:11 lr: 0.000343 loss: 3.3776 (3.1800) grad_norm: 1.6979 (1.7177) time: 0.4984 [2021-03-26 12:42:39 swin_small_patch4_window7_224] INFO: Epoch: [181] [1120/1251] eta: 0:01:06 lr: 0.000343 loss: 3.3442 (3.1818) grad_norm: 1.6989 (1.7175) time: 0.5024 [2021-03-26 12:42:44 swin_small_patch4_window7_224] INFO: Epoch: [181] [1130/1251] eta: 0:01:01 lr: 0.000343 loss: 3.2585 (3.1793) grad_norm: 1.7447 (1.7182) time: 0.4996 [2021-03-26 12:42:49 swin_small_patch4_window7_224] INFO: Epoch: [181] [1140/1251] eta: 0:00:56 lr: 0.000343 loss: 3.1627 (3.1802) grad_norm: 1.6982 (1.7177) time: 0.4996 [2021-03-26 12:42:54 swin_small_patch4_window7_224] INFO: Epoch: [181] [1150/1251] eta: 0:00:51 lr: 0.000343 loss: 3.3769 (3.1807) grad_norm: 1.6509 (1.7171) time: 0.4996 [2021-03-26 12:42:59 swin_small_patch4_window7_224] INFO: Epoch: [181] [1160/1251] eta: 0:00:46 lr: 0.000343 loss: 3.3769 (3.1827) grad_norm: 1.6502 (1.7183) time: 0.4988 [2021-03-26 12:43:04 swin_small_patch4_window7_224] INFO: Epoch: [181] [1170/1251] eta: 0:00:41 lr: 0.000343 loss: 3.3828 (3.1832) grad_norm: 1.6887 (1.7178) time: 0.4984 [2021-03-26 12:43:09 swin_small_patch4_window7_224] INFO: Epoch: [181] [1180/1251] eta: 0:00:36 lr: 0.000342 loss: 3.3448 (3.1830) grad_norm: 1.6822 (1.7182) time: 0.5005 [2021-03-26 12:43:15 swin_small_patch4_window7_224] INFO: Epoch: [181] [1190/1251] eta: 0:00:30 lr: 0.000342 loss: 3.3158 (3.1831) grad_norm: 1.6822 (1.7181) time: 0.5061 [2021-03-26 12:43:20 swin_small_patch4_window7_224] INFO: Epoch: [181] [1200/1251] eta: 0:00:25 lr: 0.000342 loss: 3.0755 (3.1826) grad_norm: 1.6089 (1.7174) time: 0.5052 [2021-03-26 12:43:25 swin_small_patch4_window7_224] INFO: Epoch: [181] [1210/1251] eta: 0:00:20 lr: 0.000342 loss: 2.9451 (3.1797) grad_norm: 1.6484 (1.7189) time: 0.5008 [2021-03-26 12:43:30 swin_small_patch4_window7_224] INFO: Epoch: [181] [1220/1251] eta: 0:00:15 lr: 0.000342 loss: 3.1173 (3.1803) grad_norm: 1.7298 (1.7186) time: 0.5023 [2021-03-26 12:43:35 swin_small_patch4_window7_224] INFO: Epoch: [181] [1230/1251] eta: 0:00:10 lr: 0.000342 loss: 3.3924 (3.1808) grad_norm: 1.6969 (1.7191) time: 0.5027 [2021-03-26 12:43:40 swin_small_patch4_window7_224] INFO: Epoch: [181] [1240/1251] eta: 0:00:05 lr: 0.000342 loss: 3.4047 (3.1815) grad_norm: 1.6975 (1.7190) time: 0.4999 [2021-03-26 12:43:45 swin_small_patch4_window7_224] INFO: Epoch: [181] [1250/1251] eta: 0:00:00 lr: 0.000342 loss: 3.2419 (3.1807) grad_norm: 1.7089 (1.7187) time: 0.5003 [2021-03-26 12:43:54 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 0.4451 (0.4451) acc1: 90.6250 (90.6250) acc5: 100.0000 (100.0000) [2021-03-26 12:43:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8249 (0.8284) acc1: 76.5625 (78.9773) acc5: 96.8750 (96.5909) [2021-03-26 12:43:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8289 (0.8827) acc1: 76.5625 (78.4226) acc5: 95.3125 (95.4613) [2021-03-26 12:44:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7820 (0.8390) acc1: 79.6875 (79.4859) acc5: 95.3125 (95.7661) [2021-03-26 12:44:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8186 (0.8700) acc1: 79.6875 (78.8491) acc5: 95.3125 (95.4649) [2021-03-26 12:44:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8646 (0.8702) acc1: 79.2453 (78.8480) acc5: 95.3125 (95.3600) [2021-03-26 12:44:14 swin_small_patch4_window7_224] INFO: * Acc@1 79.532 Acc@5 95.142 loss 0.860 [2021-03-26 12:44:14 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.5% [2021-03-26 12:44:14 swin_small_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-26 12:44:18 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 0/1251] eta: 1:26:21 lr: 0.000342 loss: 2.1336 (2.1336) grad_norm: 1.9961 (1.9961) time: 4.1416 [2021-03-26 12:44:23 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 10/1251] eta: 0:17:43 lr: 0.000342 loss: 2.9379 (2.8731) grad_norm: 1.7224 (1.7898) time: 0.8566 [2021-03-26 12:44:28 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 20/1251] eta: 0:14:04 lr: 0.000342 loss: 3.1814 (3.0897) grad_norm: 1.7224 (1.7757) time: 0.5134 [2021-03-26 12:44:33 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 30/1251] eta: 0:12:45 lr: 0.000342 loss: 3.2584 (3.1403) grad_norm: 1.6722 (1.7456) time: 0.5011 [2021-03-26 12:44:38 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 40/1251] eta: 0:12:05 lr: 0.000342 loss: 3.3917 (3.1772) grad_norm: 1.6005 (1.7186) time: 0.5076 [2021-03-26 12:44:43 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 50/1251] eta: 0:11:36 lr: 0.000342 loss: 3.2854 (3.1849) grad_norm: 1.6332 (1.7167) time: 0.5074 [2021-03-26 12:44:48 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 60/1251] eta: 0:11:16 lr: 0.000342 loss: 3.2528 (3.1610) grad_norm: 1.6701 (1.6977) time: 0.5033 [2021-03-26 12:44:53 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 70/1251] eta: 0:10:58 lr: 0.000342 loss: 2.9388 (3.1343) grad_norm: 1.6127 (1.6930) time: 0.4995 [2021-03-26 12:44:59 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 80/1251] eta: 0:10:46 lr: 0.000342 loss: 3.1372 (3.1553) grad_norm: 1.6975 (1.7012) time: 0.5037 [2021-03-26 12:45:04 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 90/1251] eta: 0:10:34 lr: 0.000342 loss: 3.2750 (3.1536) grad_norm: 1.7153 (1.6972) time: 0.5066 [2021-03-26 12:45:09 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 100/1251] eta: 0:10:22 lr: 0.000342 loss: 3.3276 (3.1687) grad_norm: 1.6015 (1.6933) time: 0.4977 [2021-03-26 12:45:14 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 110/1251] eta: 0:10:13 lr: 0.000342 loss: 3.4379 (3.1805) grad_norm: 1.6015 (1.6966) time: 0.4979 [2021-03-26 12:45:19 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 120/1251] eta: 0:10:05 lr: 0.000342 loss: 3.2078 (3.1712) grad_norm: 1.7425 (1.7034) time: 0.5077 [2021-03-26 12:45:24 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 130/1251] eta: 0:09:57 lr: 0.000342 loss: 3.2078 (3.1678) grad_norm: 1.7071 (1.7017) time: 0.5070 [2021-03-26 12:45:29 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 140/1251] eta: 0:09:49 lr: 0.000342 loss: 3.2456 (3.1694) grad_norm: 1.6604 (1.7004) time: 0.5018 [2021-03-26 12:45:34 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 150/1251] eta: 0:09:44 lr: 0.000342 loss: 3.1965 (3.1751) grad_norm: 1.6642 (1.7034) time: 0.5147 [2021-03-26 12:45:39 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 160/1251] eta: 0:09:37 lr: 0.000342 loss: 3.1965 (3.1598) grad_norm: 1.6528 (1.6998) time: 0.5158 [2021-03-26 12:45:44 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 170/1251] eta: 0:09:30 lr: 0.000342 loss: 3.2034 (3.1569) grad_norm: 1.6959 (1.7046) time: 0.5048 [2021-03-26 12:45:49 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 180/1251] eta: 0:09:23 lr: 0.000342 loss: 3.2072 (3.1566) grad_norm: 1.7358 (1.7138) time: 0.5076 [2021-03-26 12:45:54 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 190/1251] eta: 0:09:17 lr: 0.000341 loss: 3.3046 (3.1671) grad_norm: 1.7324 (1.7144) time: 0.5093 [2021-03-26 12:45:59 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 200/1251] eta: 0:09:11 lr: 0.000341 loss: 3.2927 (3.1619) grad_norm: 1.7280 (1.7162) time: 0.5073 [2021-03-26 12:46:04 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 210/1251] eta: 0:09:05 lr: 0.000341 loss: 3.0882 (3.1550) grad_norm: 1.6981 (1.7147) time: 0.5059 [2021-03-26 12:46:09 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 220/1251] eta: 0:08:58 lr: 0.000341 loss: 3.3981 (3.1711) grad_norm: 1.6424 (1.7118) time: 0.5035 [2021-03-26 12:46:14 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 230/1251] eta: 0:08:52 lr: 0.000341 loss: 3.3981 (3.1738) grad_norm: 1.6375 (1.7115) time: 0.5012 [2021-03-26 12:46:19 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 240/1251] eta: 0:08:46 lr: 0.000341 loss: 3.1935 (3.1600) grad_norm: 1.6923 (1.7117) time: 0.5019 [2021-03-26 12:46:24 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 250/1251] eta: 0:08:40 lr: 0.000341 loss: 3.0898 (3.1645) grad_norm: 1.7042 (1.7138) time: 0.5012 [2021-03-26 12:46:29 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 260/1251] eta: 0:08:34 lr: 0.000341 loss: 3.3576 (3.1737) grad_norm: 1.8208 (1.7216) time: 0.4980 [2021-03-26 12:46:34 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 270/1251] eta: 0:08:28 lr: 0.000341 loss: 3.2392 (3.1701) grad_norm: 1.8739 (1.7283) time: 0.5024 [2021-03-26 12:46:40 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 280/1251] eta: 0:08:23 lr: 0.000341 loss: 3.1026 (3.1606) grad_norm: 1.8370 (1.7315) time: 0.5068 [2021-03-26 12:46:45 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 290/1251] eta: 0:08:17 lr: 0.000341 loss: 3.2236 (3.1651) grad_norm: 1.6677 (1.7306) time: 0.5089 [2021-03-26 12:46:50 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 300/1251] eta: 0:08:12 lr: 0.000341 loss: 3.2236 (3.1676) grad_norm: 1.6555 (1.7337) time: 0.5095 [2021-03-26 12:46:55 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 310/1251] eta: 0:08:06 lr: 0.000341 loss: 3.2563 (3.1746) grad_norm: 1.7309 (1.7344) time: 0.5041 [2021-03-26 12:47:00 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 320/1251] eta: 0:08:01 lr: 0.000341 loss: 3.2928 (3.1782) grad_norm: 1.7978 (1.7379) time: 0.5058 [2021-03-26 12:47:05 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 330/1251] eta: 0:07:55 lr: 0.000341 loss: 3.2861 (3.1833) grad_norm: 1.7418 (1.7394) time: 0.5093 [2021-03-26 12:47:10 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 340/1251] eta: 0:07:50 lr: 0.000341 loss: 3.4393 (3.1899) grad_norm: 1.6923 (1.7397) time: 0.5102 [2021-03-26 12:47:15 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 350/1251] eta: 0:07:45 lr: 0.000341 loss: 3.4562 (3.1959) grad_norm: 1.6919 (1.7390) time: 0.5073 [2021-03-26 12:47:20 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 360/1251] eta: 0:07:39 lr: 0.000341 loss: 3.4562 (3.2042) grad_norm: 1.6368 (1.7366) time: 0.5052 [2021-03-26 12:47:25 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 370/1251] eta: 0:07:34 lr: 0.000341 loss: 3.3855 (3.2038) grad_norm: 1.5888 (1.7331) time: 0.5043 [2021-03-26 12:47:30 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 380/1251] eta: 0:07:28 lr: 0.000341 loss: 3.3820 (3.2059) grad_norm: 1.6393 (1.7317) time: 0.5011 [2021-03-26 12:47:35 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 390/1251] eta: 0:07:23 lr: 0.000341 loss: 3.3357 (3.2057) grad_norm: 1.6277 (1.7303) time: 0.4994 [2021-03-26 12:47:40 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 400/1251] eta: 0:07:17 lr: 0.000341 loss: 3.1546 (3.2009) grad_norm: 1.7552 (1.7320) time: 0.4951 [2021-03-26 12:47:45 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 410/1251] eta: 0:07:12 lr: 0.000341 loss: 3.0417 (3.1987) grad_norm: 1.7592 (1.7332) time: 0.4975 [2021-03-26 12:47:50 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 420/1251] eta: 0:07:06 lr: 0.000341 loss: 3.2864 (3.2016) grad_norm: 1.6038 (1.7299) time: 0.5042 [2021-03-26 12:47:55 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 430/1251] eta: 0:07:01 lr: 0.000341 loss: 3.1467 (3.1924) grad_norm: 1.5569 (1.7262) time: 0.5009 [2021-03-26 12:48:00 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 440/1251] eta: 0:06:55 lr: 0.000340 loss: 2.9783 (3.1920) grad_norm: 1.5924 (1.7248) time: 0.4953 [2021-03-26 12:48:05 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 450/1251] eta: 0:06:50 lr: 0.000340 loss: 3.1535 (3.1902) grad_norm: 1.6298 (1.7223) time: 0.4995 [2021-03-26 12:48:10 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 460/1251] eta: 0:06:45 lr: 0.000340 loss: 3.1706 (3.1874) grad_norm: 1.5790 (1.7197) time: 0.5066 [2021-03-26 12:48:15 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 470/1251] eta: 0:06:40 lr: 0.000340 loss: 3.3124 (3.1896) grad_norm: 1.5729 (1.7171) time: 0.5014 [2021-03-26 12:48:20 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 480/1251] eta: 0:06:34 lr: 0.000340 loss: 3.3124 (3.1880) grad_norm: 1.5888 (1.7149) time: 0.5030 [2021-03-26 12:48:25 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 490/1251] eta: 0:06:29 lr: 0.000340 loss: 3.0400 (3.1850) grad_norm: 1.7150 (1.7214) time: 0.5088 [2021-03-26 12:48:30 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 500/1251] eta: 0:06:24 lr: 0.000340 loss: 3.2075 (3.1871) grad_norm: 1.8357 (1.7240) time: 0.5051 [2021-03-26 12:48:35 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 510/1251] eta: 0:06:19 lr: 0.000340 loss: 3.3690 (3.1906) grad_norm: 1.7041 (1.7226) time: 0.5018 [2021-03-26 12:48:40 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 520/1251] eta: 0:06:13 lr: 0.000340 loss: 3.3823 (3.1917) grad_norm: 1.6357 (1.7219) time: 0.4983 [2021-03-26 12:48:45 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 530/1251] eta: 0:06:08 lr: 0.000340 loss: 3.2649 (3.1931) grad_norm: 1.6262 (1.7200) time: 0.5034 [2021-03-26 12:48:51 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 540/1251] eta: 0:06:03 lr: 0.000340 loss: 3.2649 (3.1912) grad_norm: 1.6505 (1.7202) time: 0.5070 [2021-03-26 12:48:56 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 550/1251] eta: 0:05:58 lr: 0.000340 loss: 3.2612 (3.1925) grad_norm: 1.6824 (1.7181) time: 0.5223 [2021-03-26 12:49:01 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 560/1251] eta: 0:05:53 lr: 0.000340 loss: 3.3145 (3.1930) grad_norm: 1.6165 (1.7198) time: 0.5222 [2021-03-26 12:49:06 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 570/1251] eta: 0:05:48 lr: 0.000340 loss: 3.3855 (3.1958) grad_norm: 1.5795 (1.7181) time: 0.5031 [2021-03-26 12:49:11 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 580/1251] eta: 0:05:43 lr: 0.000340 loss: 3.3755 (3.1982) grad_norm: 1.6347 (1.7175) time: 0.5047 [2021-03-26 12:49:16 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 590/1251] eta: 0:05:38 lr: 0.000340 loss: 3.1714 (3.1960) grad_norm: 1.6588 (1.7160) time: 0.5101 [2021-03-26 12:49:21 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 600/1251] eta: 0:05:32 lr: 0.000340 loss: 3.0433 (3.1934) grad_norm: 1.6387 (1.7154) time: 0.5066 [2021-03-26 12:49:26 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 610/1251] eta: 0:05:27 lr: 0.000340 loss: 3.2696 (3.1964) grad_norm: 1.6603 (1.7154) time: 0.5023 [2021-03-26 12:49:31 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 620/1251] eta: 0:05:22 lr: 0.000340 loss: 3.2527 (3.1927) grad_norm: 1.6635 (1.7167) time: 0.4971 [2021-03-26 12:49:36 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 630/1251] eta: 0:05:17 lr: 0.000340 loss: 3.2046 (3.1912) grad_norm: 1.6940 (1.7172) time: 0.4943 [2021-03-26 12:49:41 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 640/1251] eta: 0:05:11 lr: 0.000340 loss: 3.2046 (3.1917) grad_norm: 1.6847 (1.7171) time: 0.5021 [2021-03-26 12:49:46 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 650/1251] eta: 0:05:06 lr: 0.000340 loss: 3.1793 (3.1919) grad_norm: 1.6340 (1.7155) time: 0.5079 [2021-03-26 12:49:51 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 660/1251] eta: 0:05:01 lr: 0.000340 loss: 3.2745 (3.1929) grad_norm: 1.6347 (1.7157) time: 0.5087 [2021-03-26 12:49:56 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 670/1251] eta: 0:04:56 lr: 0.000340 loss: 3.4015 (3.1960) grad_norm: 1.7082 (1.7169) time: 0.5011 [2021-03-26 12:50:01 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 680/1251] eta: 0:04:51 lr: 0.000340 loss: 3.1256 (3.1952) grad_norm: 1.6882 (1.7157) time: 0.4971 [2021-03-26 12:50:06 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 690/1251] eta: 0:04:46 lr: 0.000340 loss: 3.1256 (3.1930) grad_norm: 1.6800 (1.7179) time: 0.5011 [2021-03-26 12:50:11 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 700/1251] eta: 0:04:40 lr: 0.000339 loss: 3.2192 (3.1926) grad_norm: 1.7680 (1.7175) time: 0.4971 [2021-03-26 12:50:16 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 710/1251] eta: 0:04:35 lr: 0.000339 loss: 3.1182 (3.1906) grad_norm: 1.6425 (1.7172) time: 0.4979 [2021-03-26 12:50:21 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 720/1251] eta: 0:04:30 lr: 0.000339 loss: 3.0902 (3.1899) grad_norm: 1.6824 (1.7168) time: 0.5020 [2021-03-26 12:50:27 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 730/1251] eta: 0:04:25 lr: 0.000339 loss: 3.1040 (3.1867) grad_norm: 1.6333 (1.7152) time: 0.5102 [2021-03-26 12:50:32 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 740/1251] eta: 0:04:20 lr: 0.000339 loss: 3.1040 (3.1839) grad_norm: 1.6330 (1.7140) time: 0.5279 [2021-03-26 12:50:37 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 750/1251] eta: 0:04:15 lr: 0.000339 loss: 3.1528 (3.1835) grad_norm: 1.6752 (1.7137) time: 0.5232 [2021-03-26 12:50:42 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 760/1251] eta: 0:04:10 lr: 0.000339 loss: 2.9906 (3.1794) grad_norm: 1.7317 (1.7141) time: 0.5059 [2021-03-26 12:50:47 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 770/1251] eta: 0:04:05 lr: 0.000339 loss: 2.8073 (3.1758) grad_norm: 1.7831 (1.7165) time: 0.5024 [2021-03-26 12:50:52 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 780/1251] eta: 0:04:00 lr: 0.000339 loss: 3.0232 (3.1761) grad_norm: 1.7538 (1.7166) time: 0.5041 [2021-03-26 12:50:57 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 790/1251] eta: 0:03:54 lr: 0.000339 loss: 3.0232 (3.1727) grad_norm: 1.6231 (1.7152) time: 0.5040 [2021-03-26 12:51:02 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 800/1251] eta: 0:03:49 lr: 0.000339 loss: 2.9749 (3.1714) grad_norm: 1.6114 (1.7140) time: 0.4967 [2021-03-26 12:51:07 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 810/1251] eta: 0:03:44 lr: 0.000339 loss: 2.9749 (3.1712) grad_norm: 1.6445 (1.7142) time: 0.4940 [2021-03-26 12:51:12 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 820/1251] eta: 0:03:39 lr: 0.000339 loss: 2.8954 (3.1687) grad_norm: 1.7032 (1.7142) time: 0.4951 [2021-03-26 12:51:17 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 830/1251] eta: 0:03:34 lr: 0.000339 loss: 3.0026 (3.1675) grad_norm: 1.6714 (1.7135) time: 0.4999 [2021-03-26 12:51:22 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 840/1251] eta: 0:03:29 lr: 0.000339 loss: 3.2375 (3.1689) grad_norm: 1.6349 (1.7131) time: 0.5033 [2021-03-26 12:51:27 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 850/1251] eta: 0:03:24 lr: 0.000339 loss: 3.1227 (3.1645) grad_norm: 1.7113 (1.7136) time: 0.5010 [2021-03-26 12:51:32 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 860/1251] eta: 0:03:18 lr: 0.000339 loss: 2.9919 (3.1641) grad_norm: 1.6452 (1.7125) time: 0.5060 [2021-03-26 12:51:37 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 870/1251] eta: 0:03:13 lr: 0.000339 loss: 3.3615 (3.1643) grad_norm: 1.5670 (1.7114) time: 0.5069 [2021-03-26 12:51:42 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 880/1251] eta: 0:03:08 lr: 0.000339 loss: 3.3857 (3.1642) grad_norm: 1.6500 (1.7129) time: 0.5028 [2021-03-26 12:51:47 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 890/1251] eta: 0:03:03 lr: 0.000339 loss: 3.1531 (3.1645) grad_norm: 1.6593 (1.7113) time: 0.5149 [2021-03-26 12:51:52 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 900/1251] eta: 0:02:58 lr: 0.000339 loss: 3.0645 (3.1633) grad_norm: 1.6215 (1.7114) time: 0.5124 [2021-03-26 12:51:57 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 910/1251] eta: 0:02:53 lr: 0.000339 loss: 3.2254 (3.1675) grad_norm: 1.6878 (1.7115) time: 0.4995 [2021-03-26 12:52:03 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 920/1251] eta: 0:02:48 lr: 0.000339 loss: 3.4016 (3.1658) grad_norm: 1.6878 (1.7116) time: 0.5103 [2021-03-26 12:52:08 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 930/1251] eta: 0:02:43 lr: 0.000339 loss: 3.1652 (3.1680) grad_norm: 1.6913 (1.7115) time: 0.5157 [2021-03-26 12:52:13 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 940/1251] eta: 0:02:38 lr: 0.000339 loss: 3.3931 (3.1701) grad_norm: 1.6868 (1.7118) time: 0.5101 [2021-03-26 12:52:18 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 950/1251] eta: 0:02:33 lr: 0.000338 loss: 3.3436 (3.1681) grad_norm: 1.7089 (1.7122) time: 0.5072 [2021-03-26 12:52:23 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 960/1251] eta: 0:02:28 lr: 0.000338 loss: 2.9937 (3.1680) grad_norm: 1.6903 (1.7115) time: 0.5059 [2021-03-26 12:52:28 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 970/1251] eta: 0:02:22 lr: 0.000338 loss: 3.2865 (3.1699) grad_norm: 1.6659 (1.7115) time: 0.5034 [2021-03-26 12:52:33 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 980/1251] eta: 0:02:17 lr: 0.000338 loss: 3.3532 (3.1694) grad_norm: 1.6415 (1.7109) time: 0.5018 [2021-03-26 12:52:38 swin_small_patch4_window7_224] INFO: Epoch: [182] [ 990/1251] eta: 0:02:12 lr: 0.000338 loss: 3.1953 (3.1677) grad_norm: 1.6171 (1.7100) time: 0.5025 [2021-03-26 12:52:43 swin_small_patch4_window7_224] INFO: Epoch: [182] [1000/1251] eta: 0:02:07 lr: 0.000338 loss: 3.2148 (3.1671) grad_norm: 1.6738 (1.7107) time: 0.5057 [2021-03-26 12:52:48 swin_small_patch4_window7_224] INFO: Epoch: [182] [1010/1251] eta: 0:02:02 lr: 0.000338 loss: 3.3633 (3.1691) grad_norm: 1.6897 (1.7111) time: 0.5031 [2021-03-26 12:52:53 swin_small_patch4_window7_224] INFO: Epoch: [182] [1020/1251] eta: 0:01:57 lr: 0.000338 loss: 3.3633 (3.1685) grad_norm: 1.6745 (1.7105) time: 0.5013 [2021-03-26 12:52:58 swin_small_patch4_window7_224] INFO: Epoch: [182] [1030/1251] eta: 0:01:52 lr: 0.000338 loss: 3.1609 (3.1679) grad_norm: 1.6983 (1.7116) time: 0.4984 [2021-03-26 12:53:03 swin_small_patch4_window7_224] INFO: Epoch: [182] [1040/1251] eta: 0:01:47 lr: 0.000338 loss: 3.2572 (3.1688) grad_norm: 1.7446 (1.7115) time: 0.4944 [2021-03-26 12:53:08 swin_small_patch4_window7_224] INFO: Epoch: [182] [1050/1251] eta: 0:01:42 lr: 0.000338 loss: 3.4839 (3.1706) grad_norm: 1.7885 (1.7123) time: 0.5022 [2021-03-26 12:53:13 swin_small_patch4_window7_224] INFO: Epoch: [182] [1060/1251] eta: 0:01:37 lr: 0.000338 loss: 3.4277 (3.1731) grad_norm: 1.7960 (1.7130) time: 0.5084 [2021-03-26 12:53:18 swin_small_patch4_window7_224] INFO: Epoch: [182] [1070/1251] eta: 0:01:31 lr: 0.000338 loss: 3.4277 (3.1759) grad_norm: 1.7842 (1.7138) time: 0.5061 [2021-03-26 12:53:23 swin_small_patch4_window7_224] INFO: Epoch: [182] [1080/1251] eta: 0:01:26 lr: 0.000338 loss: 3.4813 (3.1773) grad_norm: 1.7681 (1.7136) time: 0.5078 [2021-03-26 12:53:28 swin_small_patch4_window7_224] INFO: Epoch: [182] [1090/1251] eta: 0:01:21 lr: 0.000338 loss: 3.2535 (3.1769) grad_norm: 1.6500 (1.7128) time: 0.5116 [2021-03-26 12:53:33 swin_small_patch4_window7_224] INFO: Epoch: [182] [1100/1251] eta: 0:01:16 lr: 0.000338 loss: 3.1961 (3.1781) grad_norm: 1.6660 (1.7135) time: 0.5065 [2021-03-26 12:53:39 swin_small_patch4_window7_224] INFO: Epoch: [182] [1110/1251] eta: 0:01:11 lr: 0.000338 loss: 3.1744 (3.1757) grad_norm: 1.7456 (1.7137) time: 0.5036 [2021-03-26 12:53:44 swin_small_patch4_window7_224] INFO: Epoch: [182] [1120/1251] eta: 0:01:06 lr: 0.000338 loss: 3.1349 (3.1763) grad_norm: 1.7245 (1.7135) time: 0.5016 [2021-03-26 12:53:49 swin_small_patch4_window7_224] INFO: Epoch: [182] [1130/1251] eta: 0:01:01 lr: 0.000338 loss: 3.2289 (3.1756) grad_norm: 1.7245 (1.7135) time: 0.4978 [2021-03-26 12:53:53 swin_small_patch4_window7_224] INFO: Epoch: [182] [1140/1251] eta: 0:00:56 lr: 0.000338 loss: 3.1966 (3.1751) grad_norm: 1.6734 (1.7133) time: 0.4981 [2021-03-26 12:53:59 swin_small_patch4_window7_224] INFO: Epoch: [182] [1150/1251] eta: 0:00:51 lr: 0.000338 loss: 3.2821 (3.1763) grad_norm: 1.6734 (1.7139) time: 0.5015 [2021-03-26 12:54:04 swin_small_patch4_window7_224] INFO: Epoch: [182] [1160/1251] eta: 0:00:46 lr: 0.000338 loss: 3.3415 (3.1761) grad_norm: 1.6307 (1.7129) time: 0.5026 [2021-03-26 12:54:09 swin_small_patch4_window7_224] INFO: Epoch: [182] [1170/1251] eta: 0:00:41 lr: 0.000338 loss: 3.3406 (3.1772) grad_norm: 1.6252 (1.7132) time: 0.4976 [2021-03-26 12:54:14 swin_small_patch4_window7_224] INFO: Epoch: [182] [1180/1251] eta: 0:00:36 lr: 0.000338 loss: 3.2626 (3.1773) grad_norm: 1.6558 (1.7132) time: 0.4975 [2021-03-26 12:54:19 swin_small_patch4_window7_224] INFO: Epoch: [182] [1190/1251] eta: 0:00:30 lr: 0.000338 loss: 3.1992 (3.1761) grad_norm: 1.6390 (1.7124) time: 0.5049 [2021-03-26 12:54:24 swin_small_patch4_window7_224] INFO: Epoch: [182] [1200/1251] eta: 0:00:25 lr: 0.000338 loss: 3.1773 (3.1743) grad_norm: 1.6413 (1.7128) time: 0.5060 [2021-03-26 12:54:29 swin_small_patch4_window7_224] INFO: Epoch: [182] [1210/1251] eta: 0:00:20 lr: 0.000337 loss: 3.1328 (3.1726) grad_norm: 1.6440 (1.7125) time: 0.5033 [2021-03-26 12:54:34 swin_small_patch4_window7_224] INFO: Epoch: [182] [1220/1251] eta: 0:00:15 lr: 0.000337 loss: 3.1792 (3.1727) grad_norm: 1.6254 (1.7116) time: 0.5026 [2021-03-26 12:54:39 swin_small_patch4_window7_224] INFO: Epoch: [182] [1230/1251] eta: 0:00:10 lr: 0.000337 loss: 3.2574 (3.1731) grad_norm: 1.5955 (1.7109) time: 0.5021 [2021-03-26 12:54:44 swin_small_patch4_window7_224] INFO: Epoch: [182] [1240/1251] eta: 0:00:05 lr: 0.000337 loss: 3.2101 (3.1739) grad_norm: 1.6230 (1.7106) time: 0.5035 [2021-03-26 12:54:49 swin_small_patch4_window7_224] INFO: Epoch: [182] [1250/1251] eta: 0:00:00 lr: 0.000337 loss: 3.2101 (3.1735) grad_norm: 1.6230 (inf) time: 0.5001 [2021-03-26 12:54:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:14 loss: 0.6764 (0.6764) acc1: 84.3750 (84.3750) acc5: 98.4375 (98.4375) [2021-03-26 12:54:59 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8895 (0.8820) acc1: 76.5625 (76.9886) acc5: 96.8750 (95.8807) [2021-03-26 12:55:01 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8772 (0.8980) acc1: 76.5625 (77.4554) acc5: 95.3125 (95.3125) [2021-03-26 12:55:02 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.8303 (0.8764) acc1: 78.1250 (78.4778) acc5: 95.3125 (95.5645) [2021-03-26 12:55:04 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8158 (0.8714) acc1: 78.1250 (78.5061) acc5: 95.3125 (95.6555) [2021-03-26 12:55:05 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8225 (0.8625) acc1: 79.6875 (78.8160) acc5: 95.3125 (95.6160) [2021-03-26 12:55:15 swin_small_patch4_window7_224] INFO: * Acc@1 79.626 Acc@5 95.116 loss 0.854 [2021-03-26 12:55:15 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.6% [2021-03-26 12:55:15 swin_small_patch4_window7_224] INFO: Max accuracy: 79.65% [2021-03-26 12:55:19 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 0/1251] eta: 1:24:36 lr: 0.000337 loss: 3.1037 (3.1037) grad_norm: 2.0190 (2.0190) time: 4.0583 [2021-03-26 12:55:24 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 10/1251] eta: 0:17:25 lr: 0.000337 loss: 3.2003 (2.9977) grad_norm: 1.6762 (1.7007) time: 0.8423 [2021-03-26 12:55:29 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 20/1251] eta: 0:13:53 lr: 0.000337 loss: 3.2631 (3.1091) grad_norm: 1.6897 (1.7404) time: 0.5083 [2021-03-26 12:55:34 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 30/1251] eta: 0:12:37 lr: 0.000337 loss: 3.2471 (3.1143) grad_norm: 1.6933 (1.7445) time: 0.4989 [2021-03-26 12:55:39 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 40/1251] eta: 0:12:01 lr: 0.000337 loss: 3.2574 (3.1241) grad_norm: 1.7114 (1.7664) time: 0.5102 [2021-03-26 12:55:44 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 50/1251] eta: 0:11:32 lr: 0.000337 loss: 3.3087 (3.1279) grad_norm: 1.7114 (1.7593) time: 0.5088 [2021-03-26 12:55:49 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 60/1251] eta: 0:11:11 lr: 0.000337 loss: 3.2490 (3.1187) grad_norm: 1.7026 (1.7460) time: 0.4977 [2021-03-26 12:55:54 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 70/1251] eta: 0:10:55 lr: 0.000337 loss: 3.1084 (3.1162) grad_norm: 1.7325 (1.7549) time: 0.4996 [2021-03-26 12:55:59 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 80/1251] eta: 0:10:42 lr: 0.000337 loss: 3.0869 (3.0895) grad_norm: 1.7325 (1.7504) time: 0.5039 [2021-03-26 12:56:04 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 90/1251] eta: 0:10:30 lr: 0.000337 loss: 2.8864 (3.0818) grad_norm: 1.6904 (1.7376) time: 0.5011 [2021-03-26 12:56:09 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 100/1251] eta: 0:10:20 lr: 0.000337 loss: 3.0240 (3.0869) grad_norm: 1.7056 (1.7402) time: 0.4992 [2021-03-26 12:56:14 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 110/1251] eta: 0:10:12 lr: 0.000337 loss: 3.2682 (3.1097) grad_norm: 1.7426 (1.7467) time: 0.5095 [2021-03-26 12:56:19 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 120/1251] eta: 0:10:03 lr: 0.000337 loss: 3.5266 (3.1362) grad_norm: 1.7132 (1.7449) time: 0.5058 [2021-03-26 12:56:24 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 130/1251] eta: 0:09:55 lr: 0.000337 loss: 3.5589 (3.1421) grad_norm: 1.6899 (1.7511) time: 0.4979 [2021-03-26 12:56:29 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 140/1251] eta: 0:09:47 lr: 0.000337 loss: 3.5493 (3.1590) grad_norm: 1.7876 (1.7569) time: 0.5029 [2021-03-26 12:56:35 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 150/1251] eta: 0:09:40 lr: 0.000337 loss: 3.5493 (3.1700) grad_norm: 1.7493 (1.7541) time: 0.5044 [2021-03-26 12:56:39 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 160/1251] eta: 0:09:33 lr: 0.000337 loss: 3.3822 (3.1757) grad_norm: 1.6992 (1.7463) time: 0.4998 [2021-03-26 12:56:44 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 170/1251] eta: 0:09:26 lr: 0.000337 loss: 3.2500 (3.1798) grad_norm: 1.6701 (1.7414) time: 0.4961 [2021-03-26 12:56:49 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 180/1251] eta: 0:09:19 lr: 0.000337 loss: 3.2047 (3.1761) grad_norm: 1.7166 (1.7449) time: 0.4998 [2021-03-26 12:56:55 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 190/1251] eta: 0:09:14 lr: 0.000337 loss: 3.2047 (3.1810) grad_norm: 1.7166 (1.7420) time: 0.5111 [2021-03-26 12:57:00 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 200/1251] eta: 0:09:08 lr: 0.000337 loss: 3.2549 (3.1814) grad_norm: 1.6642 (1.7437) time: 0.5123 [2021-03-26 12:57:05 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 210/1251] eta: 0:09:02 lr: 0.000337 loss: 3.1241 (3.1741) grad_norm: 1.6266 (1.7366) time: 0.5027 [2021-03-26 12:57:10 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 220/1251] eta: 0:08:56 lr: 0.000336 loss: 3.3108 (3.1740) grad_norm: 1.6724 (1.7407) time: 0.5035 [2021-03-26 12:57:15 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 230/1251] eta: 0:08:50 lr: 0.000336 loss: 3.4032 (3.1843) grad_norm: 1.7491 (1.7436) time: 0.5038 [2021-03-26 12:57:20 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 240/1251] eta: 0:08:44 lr: 0.000336 loss: 3.4461 (3.1915) grad_norm: 1.7177 (1.7410) time: 0.5069 [2021-03-26 12:57:25 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 250/1251] eta: 0:08:38 lr: 0.000336 loss: 3.3621 (3.1953) grad_norm: 1.6359 (1.7387) time: 0.5046 [2021-03-26 12:57:30 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 260/1251] eta: 0:08:32 lr: 0.000336 loss: 3.2976 (3.1881) grad_norm: 1.6359 (1.7364) time: 0.4994 [2021-03-26 12:57:35 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 270/1251] eta: 0:08:27 lr: 0.000336 loss: 3.1277 (3.1857) grad_norm: 1.6589 (1.7364) time: 0.5113 [2021-03-26 12:57:40 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 280/1251] eta: 0:08:22 lr: 0.000336 loss: 3.1277 (3.1815) grad_norm: 1.7686 (1.7416) time: 0.5165 [2021-03-26 12:57:45 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 290/1251] eta: 0:08:16 lr: 0.000336 loss: 3.1198 (3.1783) grad_norm: 1.7709 (1.7406) time: 0.5062 [2021-03-26 12:57:50 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 300/1251] eta: 0:08:11 lr: 0.000336 loss: 3.2598 (3.1808) grad_norm: 1.7201 (1.7459) time: 0.5015 [2021-03-26 12:57:55 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 310/1251] eta: 0:08:05 lr: 0.000336 loss: 3.1097 (3.1765) grad_norm: 1.6917 (1.7417) time: 0.5071 [2021-03-26 12:58:00 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 320/1251] eta: 0:07:59 lr: 0.000336 loss: 3.1045 (3.1774) grad_norm: 1.6053 (1.7378) time: 0.5033 [2021-03-26 12:58:05 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 330/1251] eta: 0:07:54 lr: 0.000336 loss: 3.2200 (3.1748) grad_norm: 1.6504 (1.7386) time: 0.4988 [2021-03-26 12:58:10 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 340/1251] eta: 0:07:48 lr: 0.000336 loss: 3.1896 (3.1778) grad_norm: 1.7457 (1.7395) time: 0.5028 [2021-03-26 12:58:15 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 350/1251] eta: 0:07:43 lr: 0.000336 loss: 3.1675 (3.1698) grad_norm: 1.7277 (1.7379) time: 0.5032 [2021-03-26 12:58:20 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 360/1251] eta: 0:07:37 lr: 0.000336 loss: 3.2317 (3.1732) grad_norm: 1.6969 (1.7374) time: 0.4991 [2021-03-26 12:58:25 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 370/1251] eta: 0:07:32 lr: 0.000336 loss: 3.2630 (3.1742) grad_norm: 1.6517 (1.7355) time: 0.4994 [2021-03-26 12:58:30 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 380/1251] eta: 0:07:26 lr: 0.000336 loss: 3.3263 (3.1807) grad_norm: 1.6517 (1.7378) time: 0.5006 [2021-03-26 12:58:35 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 390/1251] eta: 0:07:21 lr: 0.000336 loss: 3.2640 (3.1758) grad_norm: 1.7862 (1.7375) time: 0.5011 [2021-03-26 12:58:41 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 400/1251] eta: 0:07:16 lr: 0.000336 loss: 3.1291 (3.1729) grad_norm: 1.7361 (1.7382) time: 0.5040 [2021-03-26 12:58:45 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 410/1251] eta: 0:07:10 lr: 0.000336 loss: 3.1035 (3.1687) grad_norm: 1.6750 (1.7357) time: 0.4970 [2021-03-26 12:58:51 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 420/1251] eta: 0:07:05 lr: 0.000336 loss: 3.0343 (3.1626) grad_norm: 1.7300 (1.7374) time: 0.5000 [2021-03-26 12:58:55 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 430/1251] eta: 0:07:00 lr: 0.000336 loss: 2.8906 (3.1568) grad_norm: 1.6982 (1.7356) time: 0.5007 [2021-03-26 12:59:00 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 440/1251] eta: 0:06:54 lr: 0.000336 loss: 2.9155 (3.1531) grad_norm: 1.6700 (1.7357) time: 0.4986 [2021-03-26 12:59:06 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 450/1251] eta: 0:06:49 lr: 0.000336 loss: 2.9890 (3.1498) grad_norm: 1.6720 (1.7342) time: 0.5049 [2021-03-26 12:59:11 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 460/1251] eta: 0:06:44 lr: 0.000336 loss: 3.0122 (3.1466) grad_norm: 1.6234 (1.7322) time: 0.5067 [2021-03-26 12:59:16 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 470/1251] eta: 0:06:39 lr: 0.000335 loss: 3.0866 (3.1475) grad_norm: 1.6234 (1.7325) time: 0.5085 [2021-03-26 12:59:21 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 480/1251] eta: 0:06:33 lr: 0.000335 loss: 3.1656 (3.1446) grad_norm: 1.6927 (1.7319) time: 0.5023 [2021-03-26 12:59:26 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 490/1251] eta: 0:06:28 lr: 0.000335 loss: 3.1656 (3.1442) grad_norm: 1.7354 (1.7328) time: 0.4995 [2021-03-26 12:59:31 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 500/1251] eta: 0:06:23 lr: 0.000335 loss: 3.2604 (3.1453) grad_norm: 1.7354 (1.7334) time: 0.5013 [2021-03-26 12:59:36 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 510/1251] eta: 0:06:18 lr: 0.000335 loss: 3.3365 (3.1487) grad_norm: 1.6295 (1.7312) time: 0.4967 [2021-03-26 12:59:41 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 520/1251] eta: 0:06:12 lr: 0.000335 loss: 3.4311 (3.1511) grad_norm: 1.6087 (1.7304) time: 0.4996 [2021-03-26 12:59:46 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 530/1251] eta: 0:06:07 lr: 0.000335 loss: 3.3660 (3.1452) grad_norm: 1.6390 (1.7301) time: 0.5041 [2021-03-26 12:59:51 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 540/1251] eta: 0:06:02 lr: 0.000335 loss: 3.2182 (3.1468) grad_norm: 1.6390 (1.7290) time: 0.5046 [2021-03-26 12:59:56 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 550/1251] eta: 0:05:57 lr: 0.000335 loss: 3.3216 (3.1495) grad_norm: 1.6602 (1.7277) time: 0.5062 [2021-03-26 13:00:01 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 560/1251] eta: 0:05:52 lr: 0.000335 loss: 3.1755 (3.1469) grad_norm: 1.6620 (1.7262) time: 0.4992 [2021-03-26 13:00:06 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 570/1251] eta: 0:05:46 lr: 0.000335 loss: 3.1755 (3.1505) grad_norm: 1.6733 (1.7262) time: 0.4949 [2021-03-26 13:00:11 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 580/1251] eta: 0:05:41 lr: 0.000335 loss: 3.2307 (3.1498) grad_norm: 1.6881 (1.7281) time: 0.4990 [2021-03-26 13:00:16 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 590/1251] eta: 0:05:36 lr: 0.000335 loss: 3.2791 (3.1506) grad_norm: 1.7556 (1.7291) time: 0.5083 [2021-03-26 13:00:21 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 600/1251] eta: 0:05:31 lr: 0.000335 loss: 3.3779 (3.1492) grad_norm: 1.7743 (1.7318) time: 0.5086 [2021-03-26 13:00:26 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 610/1251] eta: 0:05:26 lr: 0.000335 loss: 3.3130 (3.1511) grad_norm: 1.7192 (1.7320) time: 0.4989 [2021-03-26 13:00:31 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 620/1251] eta: 0:05:21 lr: 0.000335 loss: 3.1256 (3.1496) grad_norm: 1.7192 (1.7330) time: 0.4959 [2021-03-26 13:00:36 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 630/1251] eta: 0:05:15 lr: 0.000335 loss: 3.1154 (3.1492) grad_norm: 1.7538 (1.7337) time: 0.4980 [2021-03-26 13:00:41 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 640/1251] eta: 0:05:10 lr: 0.000335 loss: 3.1176 (3.1475) grad_norm: 1.7538 (1.7335) time: 0.5008 [2021-03-26 13:00:46 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 650/1251] eta: 0:05:05 lr: 0.000335 loss: 3.1579 (3.1463) grad_norm: 1.8136 (1.7356) time: 0.4990 [2021-03-26 13:00:51 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 660/1251] eta: 0:05:00 lr: 0.000335 loss: 3.2252 (3.1488) grad_norm: 1.7714 (1.7359) time: 0.4994 [2021-03-26 13:00:56 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 670/1251] eta: 0:04:55 lr: 0.000335 loss: 3.4598 (3.1526) grad_norm: 1.6817 (1.7357) time: 0.5004 [2021-03-26 13:01:01 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 680/1251] eta: 0:04:50 lr: 0.000335 loss: 3.3666 (3.1551) grad_norm: 1.6732 (1.7359) time: 0.5009 [2021-03-26 13:01:06 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 690/1251] eta: 0:04:45 lr: 0.000335 loss: 3.2171 (3.1570) grad_norm: 1.7278 (1.7373) time: 0.5078 [2021-03-26 13:01:11 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 700/1251] eta: 0:04:39 lr: 0.000335 loss: 3.3443 (3.1599) grad_norm: 1.7579 (1.7376) time: 0.5066 [2021-03-26 13:01:16 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 710/1251] eta: 0:04:34 lr: 0.000335 loss: 3.2247 (3.1585) grad_norm: 1.6933 (1.7372) time: 0.5059 [2021-03-26 13:01:21 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 720/1251] eta: 0:04:29 lr: 0.000335 loss: 3.1922 (3.1576) grad_norm: 1.6195 (1.7358) time: 0.5050 [2021-03-26 13:01:26 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 730/1251] eta: 0:04:24 lr: 0.000334 loss: 3.1922 (3.1580) grad_norm: 1.7410 (1.7370) time: 0.5031 [2021-03-26 13:01:31 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 740/1251] eta: 0:04:19 lr: 0.000334 loss: 3.4916 (3.1631) grad_norm: 1.7967 (1.7388) time: 0.5108 [2021-03-26 13:01:36 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 750/1251] eta: 0:04:14 lr: 0.000334 loss: 3.4055 (3.1619) grad_norm: 1.8262 (1.7400) time: 0.5134 [2021-03-26 13:01:42 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 760/1251] eta: 0:04:09 lr: 0.000334 loss: 2.9415 (3.1601) grad_norm: 1.7228 (1.7391) time: 0.5091 [2021-03-26 13:01:47 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 770/1251] eta: 0:04:04 lr: 0.000334 loss: 2.8840 (3.1571) grad_norm: 1.6282 (1.7392) time: 0.5061 [2021-03-26 13:01:52 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 780/1251] eta: 0:03:59 lr: 0.000334 loss: 2.8840 (3.1551) grad_norm: 1.6737 (1.7397) time: 0.5081 [2021-03-26 13:01:57 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 790/1251] eta: 0:03:54 lr: 0.000334 loss: 3.3510 (3.1567) grad_norm: 1.7130 (1.7396) time: 0.5113 [2021-03-26 13:02:02 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 800/1251] eta: 0:03:49 lr: 0.000334 loss: 3.3127 (3.1575) grad_norm: 1.6919 (1.7438) time: 0.5085 [2021-03-26 13:02:07 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 810/1251] eta: 0:03:44 lr: 0.000334 loss: 3.2402 (3.1580) grad_norm: 1.7684 (1.7443) time: 0.5080 [2021-03-26 13:02:12 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 820/1251] eta: 0:03:38 lr: 0.000334 loss: 3.1692 (3.1593) grad_norm: 1.7684 (1.7440) time: 0.5079 [2021-03-26 13:02:17 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 830/1251] eta: 0:03:33 lr: 0.000334 loss: 3.2135 (3.1612) grad_norm: 1.6817 (1.7438) time: 0.5015 [2021-03-26 13:02:22 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 840/1251] eta: 0:03:28 lr: 0.000334 loss: 3.2135 (3.1609) grad_norm: 1.6629 (1.7429) time: 0.4979 [2021-03-26 13:02:27 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 850/1251] eta: 0:03:23 lr: 0.000334 loss: 3.2309 (3.1613) grad_norm: 1.6629 (1.7442) time: 0.5015 [2021-03-26 13:02:32 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 860/1251] eta: 0:03:18 lr: 0.000334 loss: 3.1185 (3.1583) grad_norm: 1.6853 (1.7440) time: 0.5035 [2021-03-26 13:02:37 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 870/1251] eta: 0:03:13 lr: 0.000334 loss: 2.9960 (3.1581) grad_norm: 1.6867 (1.7444) time: 0.5017 [2021-03-26 13:02:42 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 880/1251] eta: 0:03:08 lr: 0.000334 loss: 3.1045 (3.1582) grad_norm: 1.8235 (1.7465) time: 0.5104 [2021-03-26 13:02:47 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 890/1251] eta: 0:03:03 lr: 0.000334 loss: 2.9827 (3.1571) grad_norm: 1.9023 (1.7486) time: 0.5128 [2021-03-26 13:02:52 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 900/1251] eta: 0:02:58 lr: 0.000334 loss: 3.1085 (3.1576) grad_norm: 1.8896 (1.7483) time: 0.5051 [2021-03-26 13:02:57 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 910/1251] eta: 0:02:53 lr: 0.000334 loss: 3.1085 (3.1547) grad_norm: 1.7459 (1.7495) time: 0.5044 [2021-03-26 13:03:03 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 920/1251] eta: 0:02:48 lr: 0.000334 loss: 3.1771 (3.1551) grad_norm: 1.7791 (1.7509) time: 0.5081 [2021-03-26 13:03:08 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 930/1251] eta: 0:02:42 lr: 0.000334 loss: 3.2728 (3.1557) grad_norm: 1.7342 (1.7514) time: 0.5107 [2021-03-26 13:03:13 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 940/1251] eta: 0:02:37 lr: 0.000334 loss: 3.2401 (3.1556) grad_norm: 1.7094 (1.7509) time: 0.5093 [2021-03-26 13:03:18 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 950/1251] eta: 0:02:32 lr: 0.000334 loss: 3.2581 (3.1552) grad_norm: 1.6542 (1.7508) time: 0.5083 [2021-03-26 13:03:23 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 960/1251] eta: 0:02:27 lr: 0.000334 loss: 3.3540 (3.1553) grad_norm: 1.6975 (1.7507) time: 0.5037 [2021-03-26 13:03:28 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 970/1251] eta: 0:02:22 lr: 0.000334 loss: 3.1600 (3.1565) grad_norm: 1.6875 (1.7508) time: 0.4971 [2021-03-26 13:03:33 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 980/1251] eta: 0:02:17 lr: 0.000334 loss: 3.1758 (3.1566) grad_norm: 1.6875 (1.7507) time: 0.4975 [2021-03-26 13:03:38 swin_small_patch4_window7_224] INFO: Epoch: [183] [ 990/1251] eta: 0:02:12 lr: 0.000333 loss: 3.2906 (3.1594) grad_norm: 1.7601 (1.7516) time: 0.5024 [2021-03-26 13:03:43 swin_small_patch4_window7_224] INFO: Epoch: [183] [1000/1251] eta: 0:02:07 lr: 0.000333 loss: 3.3095 (3.1586) grad_norm: 1.7084 (1.7508) time: 0.5017 [2021-03-26 13:03:48 swin_small_patch4_window7_224] INFO: Epoch: [183] [1010/1251] eta: 0:02:02 lr: 0.000333 loss: 3.2369 (3.1593) grad_norm: 1.7113 (1.7513) time: 0.5062 [2021-03-26 13:03:53 swin_small_patch4_window7_224] INFO: Epoch: [183] [1020/1251] eta: 0:01:57 lr: 0.000333 loss: 3.1397 (3.1590) grad_norm: 1.7957 (1.7516) time: 0.5090 [2021-03-26 13:03:58 swin_small_patch4_window7_224] INFO: Epoch: [183] [1030/1251] eta: 0:01:52 lr: 0.000333 loss: 3.1158 (3.1584) grad_norm: 1.7657 (1.7535) time: 0.5033 [2021-03-26 13:04:03 swin_small_patch4_window7_224] INFO: Epoch: [183] [1040/1251] eta: 0:01:47 lr: 0.000333 loss: 3.2864 (3.1589) grad_norm: 1.7521 (1.7541) time: 0.5060 [2021-03-26 13:04:08 swin_small_patch4_window7_224] INFO: Epoch: [183] [1050/1251] eta: 0:01:41 lr: 0.000333 loss: 3.3979 (3.1624) grad_norm: 1.7306 (1.7540) time: 0.5077 [2021-03-26 13:04:13 swin_small_patch4_window7_224] INFO: Epoch: [183] [1060/1251] eta: 0:01:36 lr: 0.000333 loss: 3.3979 (3.1615) grad_norm: 1.7186 (1.7550) time: 0.5033 [2021-03-26 13:04:18 swin_small_patch4_window7_224] INFO: Epoch: [183] [1070/1251] eta: 0:01:31 lr: 0.000333 loss: 3.0194 (3.1591) grad_norm: 1.6991 (1.7544) time: 0.5031 [2021-03-26 13:04:23 swin_small_patch4_window7_224] INFO: Epoch: [183] [1080/1251] eta: 0:01:26 lr: 0.000333 loss: 3.2524 (3.1599) grad_norm: 1.6755 (1.7540) time: 0.5042 [2021-03-26 13:04:28 swin_small_patch4_window7_224] INFO: Epoch: [183] [1090/1251] eta: 0:01:21 lr: 0.000333 loss: 3.3699 (3.1600) grad_norm: 1.7036 (1.7542) time: 0.5007 [2021-03-26 13:04:33 swin_small_patch4_window7_224] INFO: Epoch: [183] [1100/1251] eta: 0:01:16 lr: 0.000333 loss: 3.2038 (3.1595) grad_norm: 1.7274 (1.7552) time: 0.5056 [2021-03-26 13:04:39 swin_small_patch4_window7_224] INFO: Epoch: [183] [1110/1251] eta: 0:01:11 lr: 0.000333 loss: 3.0405 (3.1573) grad_norm: 1.7065 (1.7551) time: 0.5122 [2021-03-26 13:04:43 swin_small_patch4_window7_224] INFO: Epoch: [183] [1120/1251] eta: 0:01:06 lr: 0.000333 loss: 2.9658 (3.1558) grad_norm: 1.6906 (1.7546) time: 0.5018 [2021-03-26 13:04:48 swin_small_patch4_window7_224] INFO: Epoch: [183] [1130/1251] eta: 0:01:01 lr: 0.000333 loss: 3.1263 (3.1552) grad_norm: 1.6686 (1.7544) time: 0.4969 [2021-03-26 13:04:53 swin_small_patch4_window7_224] INFO: Epoch: [183] [1140/1251] eta: 0:00:56 lr: 0.000333 loss: 3.2998 (3.1544) grad_norm: 1.7432 (1.7550) time: 0.5002 [2021-03-26 13:04:59 swin_small_patch4_window7_224] INFO: Epoch: [183] [1150/1251] eta: 0:00:51 lr: 0.000333 loss: 3.2633 (3.1518) grad_norm: 1.6518 (1.7539) time: 0.5021 [2021-03-26 13:05:03 swin_small_patch4_window7_224] INFO: Epoch: [183] [1160/1251] eta: 0:00:46 lr: 0.000333 loss: 2.9824 (3.1521) grad_norm: 1.6139 (1.7537) time: 0.5020 [2021-03-26 13:05:08 swin_small_patch4_window7_224] INFO: Epoch: [183] [1170/1251] eta: 0:00:41 lr: 0.000333 loss: 3.3794 (3.1538) grad_norm: 1.6928 (1.7546) time: 0.4952 [2021-03-26 13:05:13 swin_small_patch4_window7_224] INFO: Epoch: [183] [1180/1251] eta: 0:00:35 lr: 0.000333 loss: 3.3180 (3.1520) grad_norm: 1.6884 (1.7556) time: 0.4964 [2021-03-26 13:05:18 swin_small_patch4_window7_224] INFO: Epoch: [183] [1190/1251] eta: 0:00:30 lr: 0.000333 loss: 3.0702 (3.1520) grad_norm: 1.8063 (1.7560) time: 0.5000 [2021-03-26 13:05:23 swin_small_patch4_window7_224] INFO: Epoch: [183] [1200/1251] eta: 0:00:25 lr: 0.000333 loss: 3.0074 (3.1500) grad_norm: 1.8178 (1.7568) time: 0.5020 [2021-03-26 13:05:29 swin_small_patch4_window7_224] INFO: Epoch: [183] [1210/1251] eta: 0:00:20 lr: 0.000333 loss: 2.8893 (3.1482) grad_norm: 1.7621 (1.7565) time: 0.5068 [2021-03-26 13:05:34 swin_small_patch4_window7_224] INFO: Epoch: [183] [1220/1251] eta: 0:00:15 lr: 0.000333 loss: 2.9218 (3.1471) grad_norm: 1.7221 (1.7558) time: 0.5087 [2021-03-26 13:05:39 swin_small_patch4_window7_224] INFO: Epoch: [183] [1230/1251] eta: 0:00:10 lr: 0.000333 loss: 3.3173 (3.1497) grad_norm: 1.7379 (1.7564) time: 0.5074 [2021-03-26 13:05:44 swin_small_patch4_window7_224] INFO: Epoch: [183] [1240/1251] eta: 0:00:05 lr: 0.000332 loss: 3.4825 (3.1500) grad_norm: 1.8067 (1.7569) time: 0.5082 [2021-03-26 13:05:49 swin_small_patch4_window7_224] INFO: Epoch: [183] [1250/1251] eta: 0:00:00 lr: 0.000332 loss: 3.4053 (3.1506) grad_norm: 1.6279 (1.7556) time: 0.4988 [2021-03-26 13:05:59 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:06 loss: 1.1752 (1.1752) acc1: 67.1875 (67.1875) acc5: 93.7500 (93.7500) [2021-03-26 13:06:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8436 (0.8026) acc1: 79.6875 (80.2557) acc5: 95.3125 (96.1648) [2021-03-26 13:06:04 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8209 (0.8178) acc1: 79.6875 (80.0595) acc5: 95.3125 (95.6845) [2021-03-26 13:06:06 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8076 (0.8227) acc1: 79.6875 (80.3427) acc5: 95.3125 (95.4637) [2021-03-26 13:06:08 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7993 (0.8170) acc1: 79.6875 (80.3354) acc5: 95.3125 (95.5412) [2021-03-26 13:06:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8860 (0.8476) acc1: 78.1250 (79.4560) acc5: 95.3125 (95.2640) [2021-03-26 13:06:19 swin_small_patch4_window7_224] INFO: * Acc@1 79.746 Acc@5 95.106 loss 0.841 [2021-03-26 13:06:19 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.7% [2021-03-26 13:06:19 swin_small_patch4_window7_224] INFO: Max accuracy: 79.75% [2021-03-26 13:06:23 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 0/1251] eta: 1:28:38 lr: 0.000332 loss: 2.2185 (2.2185) grad_norm: 1.6880 (1.6880) time: 4.2512 [2021-03-26 13:06:28 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 10/1251] eta: 0:17:45 lr: 0.000332 loss: 3.2047 (3.2130) grad_norm: 1.6583 (1.6837) time: 0.8585 [2021-03-26 13:06:34 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 20/1251] eta: 0:14:08 lr: 0.000332 loss: 3.3135 (3.2182) grad_norm: 1.6513 (1.6909) time: 0.5111 [2021-03-26 13:06:39 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 30/1251] eta: 0:12:48 lr: 0.000332 loss: 3.2283 (3.1495) grad_norm: 1.5981 (1.6842) time: 0.5032 [2021-03-26 13:06:44 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 40/1251] eta: 0:12:08 lr: 0.000332 loss: 3.0627 (3.1383) grad_norm: 1.5834 (1.6831) time: 0.5092 [2021-03-26 13:06:49 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 50/1251] eta: 0:11:36 lr: 0.000332 loss: 3.3548 (3.1547) grad_norm: 1.5870 (1.6721) time: 0.5038 [2021-03-26 13:06:54 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 60/1251] eta: 0:11:17 lr: 0.000332 loss: 3.2639 (3.1720) grad_norm: 1.6141 (1.6745) time: 0.5017 [2021-03-26 13:06:59 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 70/1251] eta: 0:11:02 lr: 0.000332 loss: 3.1601 (3.1443) grad_norm: 1.6740 (1.6771) time: 0.5119 [2021-03-26 13:07:04 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 80/1251] eta: 0:10:49 lr: 0.000332 loss: 3.1109 (3.1548) grad_norm: 1.6623 (1.6780) time: 0.5101 [2021-03-26 13:07:09 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 90/1251] eta: 0:10:37 lr: 0.000332 loss: 3.3164 (3.1520) grad_norm: 1.6623 (1.6882) time: 0.5088 [2021-03-26 13:07:14 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 100/1251] eta: 0:10:27 lr: 0.000332 loss: 3.1779 (3.1275) grad_norm: 1.7387 (1.6917) time: 0.5078 [2021-03-26 13:07:19 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 110/1251] eta: 0:10:18 lr: 0.000332 loss: 3.1779 (3.1364) grad_norm: 1.6867 (1.6910) time: 0.5087 [2021-03-26 13:07:24 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 120/1251] eta: 0:10:09 lr: 0.000332 loss: 3.2144 (3.1354) grad_norm: 1.7465 (1.6962) time: 0.5094 [2021-03-26 13:07:29 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 130/1251] eta: 0:10:01 lr: 0.000332 loss: 3.1585 (3.1215) grad_norm: 1.7303 (1.6947) time: 0.5064 [2021-03-26 13:07:35 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 140/1251] eta: 0:09:55 lr: 0.000332 loss: 3.0599 (3.1209) grad_norm: 1.6155 (1.6930) time: 0.5176 [2021-03-26 13:07:40 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 150/1251] eta: 0:09:47 lr: 0.000332 loss: 3.2964 (3.1261) grad_norm: 1.7928 (1.7052) time: 0.5160 [2021-03-26 13:07:45 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 160/1251] eta: 0:09:40 lr: 0.000332 loss: 3.2240 (3.1221) grad_norm: 1.7590 (1.7068) time: 0.5058 [2021-03-26 13:07:50 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 170/1251] eta: 0:09:34 lr: 0.000332 loss: 3.1009 (3.1259) grad_norm: 1.6885 (1.7081) time: 0.5132 [2021-03-26 13:07:55 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 180/1251] eta: 0:09:28 lr: 0.000332 loss: 3.3509 (3.1369) grad_norm: 1.6260 (1.7030) time: 0.5170 [2021-03-26 13:08:00 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 190/1251] eta: 0:09:21 lr: 0.000332 loss: 3.2507 (3.1378) grad_norm: 1.6260 (1.7035) time: 0.5122 [2021-03-26 13:08:05 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 200/1251] eta: 0:09:15 lr: 0.000332 loss: 3.2420 (3.1338) grad_norm: 1.7439 (1.7052) time: 0.5082 [2021-03-26 13:08:10 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 210/1251] eta: 0:09:08 lr: 0.000332 loss: 3.2976 (3.1475) grad_norm: 1.7648 (1.7092) time: 0.5023 [2021-03-26 13:08:15 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 220/1251] eta: 0:09:01 lr: 0.000332 loss: 3.3306 (3.1548) grad_norm: 1.8240 (1.7134) time: 0.4980 [2021-03-26 13:08:20 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 230/1251] eta: 0:08:55 lr: 0.000332 loss: 3.2600 (3.1549) grad_norm: 1.7268 (1.7157) time: 0.5032 [2021-03-26 13:08:25 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 240/1251] eta: 0:08:50 lr: 0.000332 loss: 3.2590 (3.1592) grad_norm: 1.7124 (1.7169) time: 0.5095 [2021-03-26 13:08:30 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 250/1251] eta: 0:08:43 lr: 0.000331 loss: 3.4149 (3.1685) grad_norm: 1.7208 (1.7165) time: 0.5059 [2021-03-26 13:08:36 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 260/1251] eta: 0:08:38 lr: 0.000331 loss: 3.3339 (3.1730) grad_norm: 1.6382 (1.7125) time: 0.5034 [2021-03-26 13:08:41 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 270/1251] eta: 0:08:32 lr: 0.000331 loss: 3.3339 (3.1749) grad_norm: 1.6686 (1.7127) time: 0.5091 [2021-03-26 13:08:46 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 280/1251] eta: 0:08:26 lr: 0.000331 loss: 3.2428 (3.1666) grad_norm: 1.6994 (1.7112) time: 0.5057 [2021-03-26 13:08:51 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 290/1251] eta: 0:08:20 lr: 0.000331 loss: 3.0084 (3.1624) grad_norm: 1.6684 (1.7117) time: 0.5039 [2021-03-26 13:08:56 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 300/1251] eta: 0:08:15 lr: 0.000331 loss: 3.2282 (3.1646) grad_norm: 1.7125 (1.7137) time: 0.5086 [2021-03-26 13:09:01 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 310/1251] eta: 0:08:09 lr: 0.000331 loss: 3.1476 (3.1600) grad_norm: 1.7275 (1.7209) time: 0.5086 [2021-03-26 13:09:06 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 320/1251] eta: 0:08:03 lr: 0.000331 loss: 3.0912 (3.1602) grad_norm: 1.7275 (1.7204) time: 0.5021 [2021-03-26 13:09:11 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 330/1251] eta: 0:07:57 lr: 0.000331 loss: 3.1486 (3.1615) grad_norm: 1.6845 (1.7200) time: 0.4983 [2021-03-26 13:09:16 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 340/1251] eta: 0:07:52 lr: 0.000331 loss: 3.1486 (3.1612) grad_norm: 1.6444 (1.7198) time: 0.4998 [2021-03-26 13:09:21 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 350/1251] eta: 0:07:46 lr: 0.000331 loss: 3.1849 (3.1571) grad_norm: 1.6783 (1.7193) time: 0.4977 [2021-03-26 13:09:26 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 360/1251] eta: 0:07:40 lr: 0.000331 loss: 3.0896 (3.1550) grad_norm: 1.6852 (1.7211) time: 0.5009 [2021-03-26 13:09:31 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 370/1251] eta: 0:07:35 lr: 0.000331 loss: 3.2596 (3.1588) grad_norm: 1.6735 (1.7193) time: 0.5065 [2021-03-26 13:09:36 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 380/1251] eta: 0:07:30 lr: 0.000331 loss: 3.2929 (3.1627) grad_norm: 1.7353 (1.7237) time: 0.5043 [2021-03-26 13:09:41 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 390/1251] eta: 0:07:24 lr: 0.000331 loss: 3.2929 (3.1680) grad_norm: 1.8305 (1.7274) time: 0.5017 [2021-03-26 13:09:46 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 400/1251] eta: 0:07:19 lr: 0.000331 loss: 3.3824 (3.1687) grad_norm: 1.6395 (1.7245) time: 0.5016 [2021-03-26 13:09:51 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 410/1251] eta: 0:07:13 lr: 0.000331 loss: 3.3311 (3.1707) grad_norm: 1.5536 (1.7216) time: 0.5007 [2021-03-26 13:09:56 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 420/1251] eta: 0:07:08 lr: 0.000331 loss: 3.4714 (3.1699) grad_norm: 1.6147 (1.7213) time: 0.5005 [2021-03-26 13:10:01 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 430/1251] eta: 0:07:02 lr: 0.000331 loss: 3.2608 (3.1666) grad_norm: 1.6745 (1.7223) time: 0.5055 [2021-03-26 13:10:06 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 440/1251] eta: 0:06:57 lr: 0.000331 loss: 3.2837 (3.1701) grad_norm: 1.7124 (1.7223) time: 0.5030 [2021-03-26 13:10:11 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 450/1251] eta: 0:06:51 lr: 0.000331 loss: 3.4587 (3.1731) grad_norm: 1.6888 (1.7217) time: 0.4969 [2021-03-26 13:10:16 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 460/1251] eta: 0:06:46 lr: 0.000331 loss: 3.4705 (3.1725) grad_norm: 1.6916 (1.7233) time: 0.5018 [2021-03-26 13:10:21 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 470/1251] eta: 0:06:41 lr: 0.000331 loss: 3.3127 (3.1713) grad_norm: 1.7174 (1.7229) time: 0.5013 [2021-03-26 13:10:26 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 480/1251] eta: 0:06:35 lr: 0.000331 loss: 3.4239 (3.1772) grad_norm: 1.7161 (1.7226) time: 0.5029 [2021-03-26 13:10:31 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 490/1251] eta: 0:06:30 lr: 0.000331 loss: 3.3791 (3.1762) grad_norm: 1.7640 (1.7247) time: 0.5071 [2021-03-26 13:10:36 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 500/1251] eta: 0:06:25 lr: 0.000331 loss: 3.2547 (3.1770) grad_norm: 1.7631 (1.7254) time: 0.4983 [2021-03-26 13:10:41 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 510/1251] eta: 0:06:20 lr: 0.000330 loss: 3.4456 (3.1830) grad_norm: 1.6950 (1.7253) time: 0.4992 [2021-03-26 13:10:46 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 520/1251] eta: 0:06:14 lr: 0.000330 loss: 3.4887 (3.1822) grad_norm: 1.6950 (1.7261) time: 0.5037 [2021-03-26 13:10:51 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 530/1251] eta: 0:06:09 lr: 0.000330 loss: 3.3122 (3.1829) grad_norm: 1.7088 (1.7268) time: 0.5015 [2021-03-26 13:10:56 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 540/1251] eta: 0:06:04 lr: 0.000330 loss: 3.4370 (3.1846) grad_norm: 1.7501 (1.7278) time: 0.5015 [2021-03-26 13:11:01 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 550/1251] eta: 0:05:59 lr: 0.000330 loss: 3.3059 (3.1843) grad_norm: 1.7286 (1.7282) time: 0.5115 [2021-03-26 13:11:06 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 560/1251] eta: 0:05:53 lr: 0.000330 loss: 3.2118 (3.1846) grad_norm: 1.7649 (1.7285) time: 0.5107 [2021-03-26 13:11:12 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 570/1251] eta: 0:05:48 lr: 0.000330 loss: 3.3077 (3.1858) grad_norm: 1.6894 (1.7283) time: 0.5032 [2021-03-26 13:11:16 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 580/1251] eta: 0:05:43 lr: 0.000330 loss: 3.2604 (3.1848) grad_norm: 1.6549 (1.7279) time: 0.4996 [2021-03-26 13:11:22 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 590/1251] eta: 0:05:38 lr: 0.000330 loss: 3.3756 (3.1866) grad_norm: 1.6549 (1.7276) time: 0.4992 [2021-03-26 13:11:27 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 600/1251] eta: 0:05:33 lr: 0.000330 loss: 3.3956 (3.1896) grad_norm: 1.6711 (1.7288) time: 0.5051 [2021-03-26 13:11:32 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 610/1251] eta: 0:05:27 lr: 0.000330 loss: 3.3296 (3.1905) grad_norm: 1.8638 (1.7307) time: 0.5003 [2021-03-26 13:11:37 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 620/1251] eta: 0:05:22 lr: 0.000330 loss: 3.1750 (3.1868) grad_norm: 1.6963 (1.7317) time: 0.4991 [2021-03-26 13:11:42 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 630/1251] eta: 0:05:17 lr: 0.000330 loss: 3.2204 (3.1890) grad_norm: 1.6567 (1.7312) time: 0.5037 [2021-03-26 13:11:47 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 640/1251] eta: 0:05:12 lr: 0.000330 loss: 3.4421 (3.1910) grad_norm: 1.7930 (1.7325) time: 0.5056 [2021-03-26 13:11:52 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 650/1251] eta: 0:05:06 lr: 0.000330 loss: 3.1667 (3.1890) grad_norm: 1.7834 (1.7332) time: 0.5005 [2021-03-26 13:11:57 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 660/1251] eta: 0:05:01 lr: 0.000330 loss: 2.9480 (3.1868) grad_norm: 1.7128 (1.7342) time: 0.4985 [2021-03-26 13:12:02 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 670/1251] eta: 0:04:56 lr: 0.000330 loss: 3.2356 (3.1898) grad_norm: 1.8030 (1.7356) time: 0.5017 [2021-03-26 13:12:07 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 680/1251] eta: 0:04:51 lr: 0.000330 loss: 3.3270 (3.1875) grad_norm: 1.8705 (1.7364) time: 0.5029 [2021-03-26 13:12:12 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 690/1251] eta: 0:04:46 lr: 0.000330 loss: 3.3281 (3.1901) grad_norm: 1.7151 (1.7375) time: 0.5059 [2021-03-26 13:12:17 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 700/1251] eta: 0:04:41 lr: 0.000330 loss: 3.3922 (3.1915) grad_norm: 1.7129 (1.7374) time: 0.5047 [2021-03-26 13:12:22 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 710/1251] eta: 0:04:35 lr: 0.000330 loss: 3.3922 (3.1911) grad_norm: 1.7117 (1.7383) time: 0.4962 [2021-03-26 13:12:27 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 720/1251] eta: 0:04:30 lr: 0.000330 loss: 2.8769 (3.1866) grad_norm: 1.7117 (1.7375) time: 0.4989 [2021-03-26 13:12:32 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 730/1251] eta: 0:04:25 lr: 0.000330 loss: 2.9698 (3.1863) grad_norm: 1.7082 (1.7387) time: 0.5069 [2021-03-26 13:12:37 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 740/1251] eta: 0:04:20 lr: 0.000330 loss: 3.4039 (3.1880) grad_norm: 1.7082 (1.7390) time: 0.5193 [2021-03-26 13:12:42 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 750/1251] eta: 0:04:15 lr: 0.000330 loss: 3.2459 (3.1868) grad_norm: 1.6967 (1.7389) time: 0.5198 [2021-03-26 13:12:47 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 760/1251] eta: 0:04:10 lr: 0.000330 loss: 3.3807 (3.1896) grad_norm: 1.6967 (1.7386) time: 0.5036 [2021-03-26 13:12:52 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 770/1251] eta: 0:04:05 lr: 0.000329 loss: 3.1494 (3.1869) grad_norm: 1.6463 (1.7388) time: 0.4964 [2021-03-26 13:12:57 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 780/1251] eta: 0:04:00 lr: 0.000329 loss: 2.9380 (3.1861) grad_norm: 1.6361 (1.7367) time: 0.5010 [2021-03-26 13:13:02 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 790/1251] eta: 0:03:55 lr: 0.000329 loss: 3.0681 (3.1840) grad_norm: 1.6437 (1.7371) time: 0.5108 [2021-03-26 13:13:07 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 800/1251] eta: 0:03:49 lr: 0.000329 loss: 3.4185 (3.1868) grad_norm: 1.7295 (1.7378) time: 0.5090 [2021-03-26 13:13:12 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 810/1251] eta: 0:03:44 lr: 0.000329 loss: 3.4484 (3.1857) grad_norm: 1.6937 (1.7370) time: 0.5022 [2021-03-26 13:13:18 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 820/1251] eta: 0:03:39 lr: 0.000329 loss: 2.9676 (3.1822) grad_norm: 1.6634 (1.7361) time: 0.5050 [2021-03-26 13:13:22 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 830/1251] eta: 0:03:34 lr: 0.000329 loss: 3.1143 (3.1822) grad_norm: 1.6772 (1.7357) time: 0.5001 [2021-03-26 13:13:28 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 840/1251] eta: 0:03:29 lr: 0.000329 loss: 3.3298 (3.1830) grad_norm: 1.7055 (nan) time: 0.4999 [2021-03-26 13:13:33 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 850/1251] eta: 0:03:24 lr: 0.000329 loss: 3.2997 (3.1827) grad_norm: 1.7799 (nan) time: 0.5049 [2021-03-26 13:13:38 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 860/1251] eta: 0:03:19 lr: 0.000329 loss: 2.9757 (3.1803) grad_norm: 1.7123 (nan) time: 0.5055 [2021-03-26 13:13:43 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 870/1251] eta: 0:03:14 lr: 0.000329 loss: 3.1451 (3.1807) grad_norm: 1.7352 (nan) time: 0.5080 [2021-03-26 13:13:48 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 880/1251] eta: 0:03:08 lr: 0.000329 loss: 3.2978 (3.1830) grad_norm: 1.7352 (nan) time: 0.5057 [2021-03-26 13:13:53 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 890/1251] eta: 0:03:03 lr: 0.000329 loss: 3.4200 (3.1853) grad_norm: 1.6848 (nan) time: 0.5076 [2021-03-26 13:13:58 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 900/1251] eta: 0:02:58 lr: 0.000329 loss: 3.4200 (3.1854) grad_norm: 1.7323 (nan) time: 0.5080 [2021-03-26 13:14:03 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 910/1251] eta: 0:02:53 lr: 0.000329 loss: 3.2874 (3.1862) grad_norm: 1.7085 (nan) time: 0.5089 [2021-03-26 13:14:08 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 920/1251] eta: 0:02:48 lr: 0.000329 loss: 3.1094 (3.1826) grad_norm: 1.7284 (nan) time: 0.5133 [2021-03-26 13:14:13 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 930/1251] eta: 0:02:43 lr: 0.000329 loss: 2.7733 (3.1803) grad_norm: 1.7234 (nan) time: 0.5124 [2021-03-26 13:14:18 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 940/1251] eta: 0:02:38 lr: 0.000329 loss: 3.2638 (3.1802) grad_norm: 1.6938 (nan) time: 0.5100 [2021-03-26 13:14:23 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 950/1251] eta: 0:02:33 lr: 0.000329 loss: 3.3425 (3.1807) grad_norm: 1.7534 (nan) time: 0.5086 [2021-03-26 13:14:29 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 960/1251] eta: 0:02:28 lr: 0.000329 loss: 3.2139 (3.1796) grad_norm: 1.6861 (nan) time: 0.5053 [2021-03-26 13:14:34 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 970/1251] eta: 0:02:23 lr: 0.000329 loss: 3.0075 (3.1779) grad_norm: 1.6861 (nan) time: 0.5036 [2021-03-26 13:14:39 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 980/1251] eta: 0:02:17 lr: 0.000329 loss: 3.0075 (3.1767) grad_norm: 1.6674 (nan) time: 0.5008 [2021-03-26 13:14:44 swin_small_patch4_window7_224] INFO: Epoch: [184] [ 990/1251] eta: 0:02:12 lr: 0.000329 loss: 3.1688 (3.1779) grad_norm: 1.7461 (nan) time: 0.4998 [2021-03-26 13:14:49 swin_small_patch4_window7_224] INFO: Epoch: [184] [1000/1251] eta: 0:02:07 lr: 0.000329 loss: 3.1688 (3.1763) grad_norm: 1.7721 (nan) time: 0.5022 [2021-03-26 13:14:54 swin_small_patch4_window7_224] INFO: Epoch: [184] [1010/1251] eta: 0:02:02 lr: 0.000329 loss: 3.0724 (3.1751) grad_norm: 1.6846 (nan) time: 0.5066 [2021-03-26 13:14:59 swin_small_patch4_window7_224] INFO: Epoch: [184] [1020/1251] eta: 0:01:57 lr: 0.000329 loss: 3.2218 (3.1742) grad_norm: 1.7016 (nan) time: 0.5085 [2021-03-26 13:15:04 swin_small_patch4_window7_224] INFO: Epoch: [184] [1030/1251] eta: 0:01:52 lr: 0.000328 loss: 3.3259 (3.1753) grad_norm: 1.7016 (nan) time: 0.5042 [2021-03-26 13:15:09 swin_small_patch4_window7_224] INFO: Epoch: [184] [1040/1251] eta: 0:01:47 lr: 0.000328 loss: 3.3259 (3.1768) grad_norm: 1.7002 (nan) time: 0.5051 [2021-03-26 13:15:14 swin_small_patch4_window7_224] INFO: Epoch: [184] [1050/1251] eta: 0:01:42 lr: 0.000328 loss: 3.3752 (3.1764) grad_norm: 1.6957 (nan) time: 0.5084 [2021-03-26 13:15:19 swin_small_patch4_window7_224] INFO: Epoch: [184] [1060/1251] eta: 0:01:37 lr: 0.000328 loss: 3.3180 (3.1772) grad_norm: 1.6528 (nan) time: 0.5069 [2021-03-26 13:15:24 swin_small_patch4_window7_224] INFO: Epoch: [184] [1070/1251] eta: 0:01:32 lr: 0.000328 loss: 3.2604 (3.1769) grad_norm: 1.7802 (nan) time: 0.5013 [2021-03-26 13:15:29 swin_small_patch4_window7_224] INFO: Epoch: [184] [1080/1251] eta: 0:01:26 lr: 0.000328 loss: 3.1974 (3.1777) grad_norm: 1.7071 (nan) time: 0.4967 [2021-03-26 13:15:34 swin_small_patch4_window7_224] INFO: Epoch: [184] [1090/1251] eta: 0:01:21 lr: 0.000328 loss: 3.1974 (3.1769) grad_norm: 1.6763 (nan) time: 0.4963 [2021-03-26 13:15:39 swin_small_patch4_window7_224] INFO: Epoch: [184] [1100/1251] eta: 0:01:16 lr: 0.000328 loss: 3.1361 (3.1763) grad_norm: 1.6763 (nan) time: 0.5005 [2021-03-26 13:15:44 swin_small_patch4_window7_224] INFO: Epoch: [184] [1110/1251] eta: 0:01:11 lr: 0.000328 loss: 3.1222 (3.1741) grad_norm: 1.7179 (nan) time: 0.5040 [2021-03-26 13:15:49 swin_small_patch4_window7_224] INFO: Epoch: [184] [1120/1251] eta: 0:01:06 lr: 0.000328 loss: 3.1454 (3.1732) grad_norm: 1.7179 (nan) time: 0.4980 [2021-03-26 13:15:54 swin_small_patch4_window7_224] INFO: Epoch: [184] [1130/1251] eta: 0:01:01 lr: 0.000328 loss: 3.1682 (3.1731) grad_norm: 1.7146 (nan) time: 0.4935 [2021-03-26 13:15:59 swin_small_patch4_window7_224] INFO: Epoch: [184] [1140/1251] eta: 0:00:56 lr: 0.000328 loss: 3.4039 (3.1741) grad_norm: 1.6679 (nan) time: 0.4935 [2021-03-26 13:16:04 swin_small_patch4_window7_224] INFO: Epoch: [184] [1150/1251] eta: 0:00:51 lr: 0.000328 loss: 3.1472 (3.1731) grad_norm: 1.6735 (nan) time: 0.5054 [2021-03-26 13:16:09 swin_small_patch4_window7_224] INFO: Epoch: [184] [1160/1251] eta: 0:00:46 lr: 0.000328 loss: 3.2152 (3.1753) grad_norm: 1.7534 (nan) time: 0.5130 [2021-03-26 13:16:14 swin_small_patch4_window7_224] INFO: Epoch: [184] [1170/1251] eta: 0:00:41 lr: 0.000328 loss: 3.3666 (3.1760) grad_norm: 1.7714 (nan) time: 0.5021 [2021-03-26 13:16:19 swin_small_patch4_window7_224] INFO: Epoch: [184] [1180/1251] eta: 0:00:36 lr: 0.000328 loss: 3.3594 (3.1779) grad_norm: 1.7714 (nan) time: 0.5007 [2021-03-26 13:16:24 swin_small_patch4_window7_224] INFO: Epoch: [184] [1190/1251] eta: 0:00:30 lr: 0.000328 loss: 3.3490 (3.1793) grad_norm: 1.7190 (nan) time: 0.5052 [2021-03-26 13:16:29 swin_small_patch4_window7_224] INFO: Epoch: [184] [1200/1251] eta: 0:00:25 lr: 0.000328 loss: 3.3252 (3.1801) grad_norm: 1.7156 (nan) time: 0.4984 [2021-03-26 13:16:34 swin_small_patch4_window7_224] INFO: Epoch: [184] [1210/1251] eta: 0:00:20 lr: 0.000328 loss: 3.3583 (3.1809) grad_norm: 1.7131 (nan) time: 0.4921 [2021-03-26 13:16:39 swin_small_patch4_window7_224] INFO: Epoch: [184] [1220/1251] eta: 0:00:15 lr: 0.000328 loss: 3.2253 (3.1804) grad_norm: 1.6545 (nan) time: 0.4973 [2021-03-26 13:16:44 swin_small_patch4_window7_224] INFO: Epoch: [184] [1230/1251] eta: 0:00:10 lr: 0.000328 loss: 3.0003 (3.1787) grad_norm: 1.6545 (nan) time: 0.5076 [2021-03-26 13:16:49 swin_small_patch4_window7_224] INFO: Epoch: [184] [1240/1251] eta: 0:00:05 lr: 0.000328 loss: 3.2634 (3.1782) grad_norm: 1.6702 (nan) time: 0.5093 [2021-03-26 13:16:54 swin_small_patch4_window7_224] INFO: Epoch: [184] [1250/1251] eta: 0:00:00 lr: 0.000328 loss: 3.3115 (3.1797) grad_norm: 1.6711 (nan) time: 0.4988 [2021-03-26 13:17:02 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 0.6574 (0.6574) acc1: 87.5000 (87.5000) acc5: 96.8750 (96.8750) [2021-03-26 13:17:05 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.9911 (0.9172) acc1: 75.0000 (77.9830) acc5: 93.7500 (95.0284) [2021-03-26 13:17:07 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.9513 (0.8874) acc1: 76.5625 (78.8690) acc5: 95.3125 (95.2381) [2021-03-26 13:17:09 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8002 (0.8340) acc1: 79.6875 (80.0403) acc5: 96.8750 (95.7661) [2021-03-26 13:17:11 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8422 (0.8597) acc1: 78.1250 (79.5351) acc5: 95.3125 (95.3125) [2021-03-26 13:17:12 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.9044 (0.8619) acc1: 78.1250 (79.4560) acc5: 93.7500 (95.2000) [2021-03-26 13:17:20 swin_small_patch4_window7_224] INFO: * Acc@1 79.830 Acc@5 95.056 loss 0.858 [2021-03-26 13:17:20 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.8% [2021-03-26 13:17:20 swin_small_patch4_window7_224] INFO: Max accuracy: 79.83% [2021-03-26 13:17:25 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 0/1251] eta: 1:30:09 lr: 0.000328 loss: 3.1200 (3.1200) grad_norm: 1.5393 (1.5393) time: 4.3244 [2021-03-26 13:17:30 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 10/1251] eta: 0:17:44 lr: 0.000328 loss: 3.2403 (3.1322) grad_norm: 1.7631 (1.8029) time: 0.8580 [2021-03-26 13:17:35 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 20/1251] eta: 0:14:06 lr: 0.000328 loss: 3.2403 (3.0455) grad_norm: 1.7177 (1.7500) time: 0.5060 [2021-03-26 13:17:40 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 30/1251] eta: 0:12:55 lr: 0.000327 loss: 3.2044 (3.0590) grad_norm: 1.6275 (1.7909) time: 0.5130 [2021-03-26 13:17:45 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 40/1251] eta: 0:12:09 lr: 0.000327 loss: 3.1039 (3.0675) grad_norm: 1.6543 (1.7532) time: 0.5127 [2021-03-26 13:17:50 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 50/1251] eta: 0:11:38 lr: 0.000327 loss: 3.0600 (3.0452) grad_norm: 1.6578 (1.7353) time: 0.4986 [2021-03-26 13:17:55 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 60/1251] eta: 0:11:16 lr: 0.000327 loss: 3.1601 (3.0632) grad_norm: 1.6815 (1.7540) time: 0.4964 [2021-03-26 13:18:00 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 70/1251] eta: 0:10:59 lr: 0.000327 loss: 3.2821 (3.0870) grad_norm: 1.6968 (1.7438) time: 0.4980 [2021-03-26 13:18:05 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 80/1251] eta: 0:10:45 lr: 0.000327 loss: 3.2851 (3.1068) grad_norm: 1.6931 (1.7418) time: 0.5014 [2021-03-26 13:18:10 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 90/1251] eta: 0:10:32 lr: 0.000327 loss: 3.2317 (3.0940) grad_norm: 1.6654 (1.7437) time: 0.4970 [2021-03-26 13:18:15 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 100/1251] eta: 0:10:21 lr: 0.000327 loss: 3.1339 (3.0939) grad_norm: 1.6310 (1.7319) time: 0.4961 [2021-03-26 13:18:20 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 110/1251] eta: 0:10:14 lr: 0.000327 loss: 3.1351 (3.0975) grad_norm: 1.6349 (1.7310) time: 0.5082 [2021-03-26 13:18:25 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 120/1251] eta: 0:10:06 lr: 0.000327 loss: 3.0409 (3.0963) grad_norm: 1.6452 (1.7271) time: 0.5153 [2021-03-26 13:18:30 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 130/1251] eta: 0:09:59 lr: 0.000327 loss: 3.1772 (3.1126) grad_norm: 1.6450 (1.7263) time: 0.5141 [2021-03-26 13:18:35 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 140/1251] eta: 0:09:50 lr: 0.000327 loss: 3.1772 (3.0906) grad_norm: 1.6469 (1.7296) time: 0.5055 [2021-03-26 13:18:40 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 150/1251] eta: 0:09:42 lr: 0.000327 loss: 3.1575 (3.0986) grad_norm: 1.7193 (1.7344) time: 0.4957 [2021-03-26 13:18:45 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 160/1251] eta: 0:09:35 lr: 0.000327 loss: 3.2247 (3.0956) grad_norm: 1.6645 (1.7290) time: 0.4957 [2021-03-26 13:18:50 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 170/1251] eta: 0:09:28 lr: 0.000327 loss: 3.2692 (3.1028) grad_norm: 1.6285 (1.7292) time: 0.4967 [2021-03-26 13:18:55 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 180/1251] eta: 0:09:20 lr: 0.000327 loss: 3.2995 (3.1165) grad_norm: 1.8680 (1.7324) time: 0.4928 [2021-03-26 13:19:00 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 190/1251] eta: 0:09:14 lr: 0.000327 loss: 3.2995 (3.1068) grad_norm: 1.7000 (1.7305) time: 0.5005 [2021-03-26 13:19:05 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 200/1251] eta: 0:09:09 lr: 0.000327 loss: 2.8012 (3.0840) grad_norm: 1.6869 (1.7305) time: 0.5161 [2021-03-26 13:19:10 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 210/1251] eta: 0:09:03 lr: 0.000327 loss: 2.9907 (3.0956) grad_norm: 1.6452 (1.7264) time: 0.5106 [2021-03-26 13:19:16 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 220/1251] eta: 0:08:57 lr: 0.000327 loss: 3.1998 (3.0904) grad_norm: 1.6926 (1.7272) time: 0.5081 [2021-03-26 13:19:21 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 230/1251] eta: 0:08:51 lr: 0.000327 loss: 3.0867 (3.0977) grad_norm: 1.7433 (1.7307) time: 0.5079 [2021-03-26 13:19:26 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 240/1251] eta: 0:08:45 lr: 0.000327 loss: 3.2423 (3.1064) grad_norm: 1.8063 (1.7353) time: 0.5032 [2021-03-26 13:19:31 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 250/1251] eta: 0:08:39 lr: 0.000327 loss: 3.4671 (3.1220) grad_norm: 1.7210 (1.7349) time: 0.4990 [2021-03-26 13:19:36 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 260/1251] eta: 0:08:33 lr: 0.000327 loss: 3.4007 (3.1233) grad_norm: 1.7045 (1.7378) time: 0.4944 [2021-03-26 13:19:41 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 270/1251] eta: 0:08:27 lr: 0.000327 loss: 3.2088 (3.1192) grad_norm: 1.7510 (1.7359) time: 0.5023 [2021-03-26 13:19:46 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 280/1251] eta: 0:08:22 lr: 0.000327 loss: 3.1541 (3.1145) grad_norm: 1.6536 (1.7332) time: 0.5050 [2021-03-26 13:19:51 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 290/1251] eta: 0:08:16 lr: 0.000326 loss: 3.2565 (3.1218) grad_norm: 1.6905 (1.7351) time: 0.5031 [2021-03-26 13:19:56 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 300/1251] eta: 0:08:11 lr: 0.000326 loss: 3.3098 (3.1192) grad_norm: 1.7524 (1.7358) time: 0.5082 [2021-03-26 13:20:01 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 310/1251] eta: 0:08:05 lr: 0.000326 loss: 3.0354 (3.1193) grad_norm: 1.7447 (1.7364) time: 0.5051 [2021-03-26 13:20:06 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 320/1251] eta: 0:07:59 lr: 0.000326 loss: 3.1892 (3.1155) grad_norm: 1.7447 (1.7370) time: 0.5009 [2021-03-26 13:20:11 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 330/1251] eta: 0:07:54 lr: 0.000326 loss: 3.1768 (3.1129) grad_norm: 1.7346 (1.7374) time: 0.5048 [2021-03-26 13:20:16 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 340/1251] eta: 0:07:49 lr: 0.000326 loss: 3.2887 (3.1188) grad_norm: 1.6866 (1.7395) time: 0.5050 [2021-03-26 13:20:21 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 350/1251] eta: 0:07:43 lr: 0.000326 loss: 3.3315 (3.1164) grad_norm: 1.7375 (1.7401) time: 0.5072 [2021-03-26 13:20:26 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 360/1251] eta: 0:07:38 lr: 0.000326 loss: 3.0090 (3.1130) grad_norm: 1.6772 (1.7384) time: 0.5007 [2021-03-26 13:20:31 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 370/1251] eta: 0:07:32 lr: 0.000326 loss: 3.0090 (3.1136) grad_norm: 1.6407 (1.7402) time: 0.5022 [2021-03-26 13:20:36 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 380/1251] eta: 0:07:27 lr: 0.000326 loss: 3.2430 (3.1213) grad_norm: 1.6457 (1.7392) time: 0.5063 [2021-03-26 13:20:41 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 390/1251] eta: 0:07:22 lr: 0.000326 loss: 3.4064 (3.1184) grad_norm: 1.7052 (1.7387) time: 0.5016 [2021-03-26 13:20:46 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 400/1251] eta: 0:07:16 lr: 0.000326 loss: 3.4064 (3.1235) grad_norm: 1.7156 (1.7393) time: 0.5001 [2021-03-26 13:20:51 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 410/1251] eta: 0:07:11 lr: 0.000326 loss: 3.3157 (3.1217) grad_norm: 1.7470 (1.7410) time: 0.5028 [2021-03-26 13:20:56 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 420/1251] eta: 0:07:05 lr: 0.000326 loss: 3.1145 (3.1184) grad_norm: 1.7175 (1.7403) time: 0.5009 [2021-03-26 13:21:01 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 430/1251] eta: 0:07:00 lr: 0.000326 loss: 3.0533 (3.1166) grad_norm: 1.7713 (1.7425) time: 0.5030 [2021-03-26 13:21:06 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 440/1251] eta: 0:06:55 lr: 0.000326 loss: 3.0533 (3.1185) grad_norm: 1.8299 (1.7444) time: 0.5077 [2021-03-26 13:21:11 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 450/1251] eta: 0:06:50 lr: 0.000326 loss: 3.3946 (3.1219) grad_norm: 1.7551 (1.7455) time: 0.5005 [2021-03-26 13:21:16 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 460/1251] eta: 0:06:44 lr: 0.000326 loss: 3.3012 (3.1210) grad_norm: 1.7072 (1.7452) time: 0.4951 [2021-03-26 13:21:21 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 470/1251] eta: 0:06:39 lr: 0.000326 loss: 3.3012 (3.1269) grad_norm: 1.6588 (1.7439) time: 0.4947 [2021-03-26 13:21:26 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 480/1251] eta: 0:06:33 lr: 0.000326 loss: 3.2895 (3.1280) grad_norm: 1.7576 (1.7453) time: 0.4973 [2021-03-26 13:21:31 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 490/1251] eta: 0:06:28 lr: 0.000326 loss: 3.0828 (3.1266) grad_norm: 1.7422 (1.7447) time: 0.4982 [2021-03-26 13:21:36 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 500/1251] eta: 0:06:23 lr: 0.000326 loss: 3.0828 (3.1272) grad_norm: 1.7451 (1.7501) time: 0.5042 [2021-03-26 13:21:41 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 510/1251] eta: 0:06:18 lr: 0.000326 loss: 3.2051 (3.1264) grad_norm: 1.7878 (1.7512) time: 0.5052 [2021-03-26 13:21:46 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 520/1251] eta: 0:06:13 lr: 0.000326 loss: 3.1630 (3.1240) grad_norm: 1.8655 (1.7549) time: 0.5032 [2021-03-26 13:21:51 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 530/1251] eta: 0:06:07 lr: 0.000326 loss: 3.1630 (3.1235) grad_norm: 1.7984 (1.7543) time: 0.5022 [2021-03-26 13:21:56 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 540/1251] eta: 0:06:02 lr: 0.000326 loss: 3.2252 (3.1244) grad_norm: 1.7332 (1.7548) time: 0.5064 [2021-03-26 13:22:02 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 550/1251] eta: 0:05:57 lr: 0.000325 loss: 3.1538 (3.1214) grad_norm: 1.6678 (1.7533) time: 0.5128 [2021-03-26 13:22:07 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 560/1251] eta: 0:05:52 lr: 0.000325 loss: 3.1538 (3.1206) grad_norm: 1.6589 (1.7528) time: 0.5075 [2021-03-26 13:22:12 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 570/1251] eta: 0:05:47 lr: 0.000325 loss: 3.2088 (3.1203) grad_norm: 1.6557 (1.7523) time: 0.5065 [2021-03-26 13:22:17 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 580/1251] eta: 0:05:42 lr: 0.000325 loss: 3.2349 (3.1220) grad_norm: 1.6880 (1.7522) time: 0.5069 [2021-03-26 13:22:22 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 590/1251] eta: 0:05:36 lr: 0.000325 loss: 3.3224 (3.1251) grad_norm: 1.7852 (1.7527) time: 0.5017 [2021-03-26 13:22:27 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 600/1251] eta: 0:05:31 lr: 0.000325 loss: 3.1736 (3.1258) grad_norm: 1.6970 (1.7522) time: 0.5023 [2021-03-26 13:22:32 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 610/1251] eta: 0:05:26 lr: 0.000325 loss: 3.1698 (3.1250) grad_norm: 1.6547 (1.7507) time: 0.5003 [2021-03-26 13:22:37 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 620/1251] eta: 0:05:21 lr: 0.000325 loss: 3.0144 (3.1266) grad_norm: 1.7146 (1.7518) time: 0.4981 [2021-03-26 13:22:42 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 630/1251] eta: 0:05:16 lr: 0.000325 loss: 3.0119 (3.1267) grad_norm: 1.6987 (1.7504) time: 0.5015 [2021-03-26 13:22:47 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 640/1251] eta: 0:05:11 lr: 0.000325 loss: 3.2363 (3.1290) grad_norm: 1.6816 (1.7502) time: 0.4991 [2021-03-26 13:22:52 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 650/1251] eta: 0:05:05 lr: 0.000325 loss: 3.3593 (3.1317) grad_norm: 1.7099 (1.7508) time: 0.4959 [2021-03-26 13:22:57 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 660/1251] eta: 0:05:00 lr: 0.000325 loss: 3.3680 (3.1324) grad_norm: 1.7365 (1.7521) time: 0.4957 [2021-03-26 13:23:02 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 670/1251] eta: 0:04:55 lr: 0.000325 loss: 3.3186 (3.1326) grad_norm: 1.7421 (1.7526) time: 0.4960 [2021-03-26 13:23:07 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 680/1251] eta: 0:04:50 lr: 0.000325 loss: 3.2932 (3.1354) grad_norm: 1.8707 (1.7554) time: 0.5011 [2021-03-26 13:23:12 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 690/1251] eta: 0:04:45 lr: 0.000325 loss: 3.4147 (3.1392) grad_norm: 1.8107 (1.7552) time: 0.5019 [2021-03-26 13:23:17 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 700/1251] eta: 0:04:39 lr: 0.000325 loss: 3.3381 (3.1410) grad_norm: 1.6634 (1.7540) time: 0.4954 [2021-03-26 13:23:22 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 710/1251] eta: 0:04:34 lr: 0.000325 loss: 3.3096 (3.1434) grad_norm: 1.6634 (1.7537) time: 0.4945 [2021-03-26 13:23:27 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 720/1251] eta: 0:04:29 lr: 0.000325 loss: 3.2118 (3.1418) grad_norm: 1.6963 (1.7545) time: 0.5013 [2021-03-26 13:23:32 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 730/1251] eta: 0:04:24 lr: 0.000325 loss: 3.1221 (3.1425) grad_norm: 1.6963 (1.7539) time: 0.5144 [2021-03-26 13:23:37 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 740/1251] eta: 0:04:19 lr: 0.000325 loss: 3.2204 (3.1441) grad_norm: 1.7274 (1.7546) time: 0.5169 [2021-03-26 13:23:42 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 750/1251] eta: 0:04:14 lr: 0.000325 loss: 3.4033 (3.1434) grad_norm: 1.7563 (1.7541) time: 0.5175 [2021-03-26 13:23:47 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 760/1251] eta: 0:04:09 lr: 0.000325 loss: 3.3939 (3.1460) grad_norm: 1.7563 (1.7545) time: 0.5177 [2021-03-26 13:23:53 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 770/1251] eta: 0:04:04 lr: 0.000325 loss: 3.4521 (3.1474) grad_norm: 1.7293 (1.7547) time: 0.5231 [2021-03-26 13:23:58 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 780/1251] eta: 0:03:59 lr: 0.000325 loss: 3.2657 (3.1476) grad_norm: 1.7221 (1.7569) time: 0.5194 [2021-03-26 13:24:03 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 790/1251] eta: 0:03:54 lr: 0.000325 loss: 3.1920 (3.1482) grad_norm: 1.8201 (1.7579) time: 0.5034 [2021-03-26 13:24:08 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 800/1251] eta: 0:03:49 lr: 0.000325 loss: 3.2922 (3.1502) grad_norm: 1.7537 (1.7585) time: 0.5033 [2021-03-26 13:24:13 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 810/1251] eta: 0:03:44 lr: 0.000324 loss: 3.3124 (3.1491) grad_norm: 1.8051 (1.7596) time: 0.5032 [2021-03-26 13:24:18 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 820/1251] eta: 0:03:39 lr: 0.000324 loss: 3.3681 (3.1524) grad_norm: 1.8161 (1.7600) time: 0.5079 [2021-03-26 13:24:23 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 830/1251] eta: 0:03:34 lr: 0.000324 loss: 3.4456 (3.1534) grad_norm: 1.7239 (1.7597) time: 0.5095 [2021-03-26 13:24:28 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 840/1251] eta: 0:03:28 lr: 0.000324 loss: 3.3013 (3.1548) grad_norm: 1.7077 (1.7590) time: 0.5023 [2021-03-26 13:24:33 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 850/1251] eta: 0:03:23 lr: 0.000324 loss: 3.3603 (3.1560) grad_norm: 1.7330 (1.7593) time: 0.5021 [2021-03-26 13:24:38 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 860/1251] eta: 0:03:18 lr: 0.000324 loss: 3.1977 (3.1538) grad_norm: 1.6925 (1.7594) time: 0.5027 [2021-03-26 13:24:43 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 870/1251] eta: 0:03:13 lr: 0.000324 loss: 3.0031 (3.1535) grad_norm: 1.7258 (1.7609) time: 0.5058 [2021-03-26 13:24:48 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 880/1251] eta: 0:03:08 lr: 0.000324 loss: 2.9224 (3.1509) grad_norm: 1.7258 (1.7609) time: 0.5159 [2021-03-26 13:24:53 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 890/1251] eta: 0:03:03 lr: 0.000324 loss: 2.9097 (3.1487) grad_norm: 1.7444 (1.7632) time: 0.5152 [2021-03-26 13:24:58 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 900/1251] eta: 0:02:58 lr: 0.000324 loss: 3.1569 (3.1493) grad_norm: 1.7463 (1.7631) time: 0.5018 [2021-03-26 13:25:03 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 910/1251] eta: 0:02:53 lr: 0.000324 loss: 3.1901 (3.1517) grad_norm: 1.8115 (1.7657) time: 0.4968 [2021-03-26 13:25:08 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 920/1251] eta: 0:02:48 lr: 0.000324 loss: 3.0936 (3.1487) grad_norm: 1.8857 (1.7663) time: 0.4997 [2021-03-26 13:25:13 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 930/1251] eta: 0:02:43 lr: 0.000324 loss: 3.0033 (3.1504) grad_norm: 1.7647 (1.7672) time: 0.4960 [2021-03-26 13:25:18 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 940/1251] eta: 0:02:37 lr: 0.000324 loss: 3.2049 (3.1485) grad_norm: 1.8342 (1.7684) time: 0.5028 [2021-03-26 13:25:23 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 950/1251] eta: 0:02:32 lr: 0.000324 loss: 3.0510 (3.1475) grad_norm: 1.8260 (1.7687) time: 0.5033 [2021-03-26 13:25:28 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 960/1251] eta: 0:02:27 lr: 0.000324 loss: 3.1101 (3.1472) grad_norm: 1.7343 (1.7681) time: 0.4985 [2021-03-26 13:25:33 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 970/1251] eta: 0:02:22 lr: 0.000324 loss: 3.1572 (3.1469) grad_norm: 1.6150 (1.7663) time: 0.5057 [2021-03-26 13:25:39 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 980/1251] eta: 0:02:17 lr: 0.000324 loss: 3.3011 (3.1490) grad_norm: 1.6667 (1.7664) time: 0.5064 [2021-03-26 13:25:44 swin_small_patch4_window7_224] INFO: Epoch: [185] [ 990/1251] eta: 0:02:12 lr: 0.000324 loss: 3.4664 (3.1529) grad_norm: 1.7262 (1.7660) time: 0.5018 [2021-03-26 13:25:49 swin_small_patch4_window7_224] INFO: Epoch: [185] [1000/1251] eta: 0:02:07 lr: 0.000324 loss: 3.4422 (3.1525) grad_norm: 1.7262 (1.7659) time: 0.5035 [2021-03-26 13:25:54 swin_small_patch4_window7_224] INFO: Epoch: [185] [1010/1251] eta: 0:02:02 lr: 0.000324 loss: 3.3708 (3.1542) grad_norm: 1.7628 (1.7668) time: 0.5096 [2021-03-26 13:25:59 swin_small_patch4_window7_224] INFO: Epoch: [185] [1020/1251] eta: 0:01:57 lr: 0.000324 loss: 3.3307 (3.1528) grad_norm: 1.7413 (1.7666) time: 0.5036 [2021-03-26 13:26:04 swin_small_patch4_window7_224] INFO: Epoch: [185] [1030/1251] eta: 0:01:52 lr: 0.000324 loss: 2.8785 (3.1493) grad_norm: 1.6424 (1.7652) time: 0.4963 [2021-03-26 13:26:09 swin_small_patch4_window7_224] INFO: Epoch: [185] [1040/1251] eta: 0:01:47 lr: 0.000324 loss: 2.8785 (3.1498) grad_norm: 1.6395 (1.7645) time: 0.5052 [2021-03-26 13:26:14 swin_small_patch4_window7_224] INFO: Epoch: [185] [1050/1251] eta: 0:01:42 lr: 0.000324 loss: 3.2924 (3.1517) grad_norm: 1.6860 (1.7639) time: 0.5106 [2021-03-26 13:26:19 swin_small_patch4_window7_224] INFO: Epoch: [185] [1060/1251] eta: 0:01:36 lr: 0.000324 loss: 3.3566 (3.1532) grad_norm: 1.6748 (1.7632) time: 0.5067 [2021-03-26 13:26:24 swin_small_patch4_window7_224] INFO: Epoch: [185] [1070/1251] eta: 0:01:31 lr: 0.000323 loss: 3.1983 (3.1516) grad_norm: 1.6748 (1.7622) time: 0.5001 [2021-03-26 13:26:29 swin_small_patch4_window7_224] INFO: Epoch: [185] [1080/1251] eta: 0:01:26 lr: 0.000323 loss: 3.1542 (3.1520) grad_norm: 1.6860 (1.7620) time: 0.4960 [2021-03-26 13:26:34 swin_small_patch4_window7_224] INFO: Epoch: [185] [1090/1251] eta: 0:01:21 lr: 0.000323 loss: 3.0989 (3.1511) grad_norm: 1.7277 (1.7625) time: 0.5019 [2021-03-26 13:26:39 swin_small_patch4_window7_224] INFO: Epoch: [185] [1100/1251] eta: 0:01:16 lr: 0.000323 loss: 2.9991 (3.1506) grad_norm: 1.6805 (1.7617) time: 0.4992 [2021-03-26 13:26:44 swin_small_patch4_window7_224] INFO: Epoch: [185] [1110/1251] eta: 0:01:11 lr: 0.000323 loss: 3.1769 (3.1498) grad_norm: 1.6668 (1.7608) time: 0.4959 [2021-03-26 13:26:49 swin_small_patch4_window7_224] INFO: Epoch: [185] [1120/1251] eta: 0:01:06 lr: 0.000323 loss: 3.3080 (3.1533) grad_norm: 1.6525 (1.7604) time: 0.4996 [2021-03-26 13:26:54 swin_small_patch4_window7_224] INFO: Epoch: [185] [1130/1251] eta: 0:01:01 lr: 0.000323 loss: 3.4762 (3.1534) grad_norm: 1.6380 (1.7606) time: 0.5037 [2021-03-26 13:26:59 swin_small_patch4_window7_224] INFO: Epoch: [185] [1140/1251] eta: 0:00:56 lr: 0.000323 loss: 3.1114 (3.1515) grad_norm: 1.8676 (1.7628) time: 0.5080 [2021-03-26 13:27:04 swin_small_patch4_window7_224] INFO: Epoch: [185] [1150/1251] eta: 0:00:51 lr: 0.000323 loss: 3.0656 (3.1502) grad_norm: 1.8790 (1.7641) time: 0.5037 [2021-03-26 13:27:09 swin_small_patch4_window7_224] INFO: Epoch: [185] [1160/1251] eta: 0:00:46 lr: 0.000323 loss: 3.0656 (3.1509) grad_norm: 1.7756 (1.7645) time: 0.5007 [2021-03-26 13:27:14 swin_small_patch4_window7_224] INFO: Epoch: [185] [1170/1251] eta: 0:00:41 lr: 0.000323 loss: 3.2840 (3.1522) grad_norm: 1.7725 (1.7640) time: 0.5045 [2021-03-26 13:27:19 swin_small_patch4_window7_224] INFO: Epoch: [185] [1180/1251] eta: 0:00:35 lr: 0.000323 loss: 3.2639 (3.1521) grad_norm: 1.7536 (1.7647) time: 0.4994 [2021-03-26 13:27:24 swin_small_patch4_window7_224] INFO: Epoch: [185] [1190/1251] eta: 0:00:30 lr: 0.000323 loss: 3.1865 (3.1510) grad_norm: 1.8001 (1.7648) time: 0.4956 [2021-03-26 13:27:29 swin_small_patch4_window7_224] INFO: Epoch: [185] [1200/1251] eta: 0:00:25 lr: 0.000323 loss: 3.1877 (3.1512) grad_norm: 1.7266 (1.7645) time: 0.4997 [2021-03-26 13:27:34 swin_small_patch4_window7_224] INFO: Epoch: [185] [1210/1251] eta: 0:00:20 lr: 0.000323 loss: 3.4797 (3.1549) grad_norm: 1.7434 (1.7647) time: 0.5015 [2021-03-26 13:27:39 swin_small_patch4_window7_224] INFO: Epoch: [185] [1220/1251] eta: 0:00:15 lr: 0.000323 loss: 3.4675 (3.1552) grad_norm: 1.7589 (1.7648) time: 0.5049 [2021-03-26 13:27:44 swin_small_patch4_window7_224] INFO: Epoch: [185] [1230/1251] eta: 0:00:10 lr: 0.000323 loss: 3.2642 (3.1559) grad_norm: 1.6989 (1.7640) time: 0.5015 [2021-03-26 13:27:49 swin_small_patch4_window7_224] INFO: Epoch: [185] [1240/1251] eta: 0:00:05 lr: 0.000323 loss: 3.2642 (3.1554) grad_norm: 1.6198 (1.7633) time: 0.4992 [2021-03-26 13:27:54 swin_small_patch4_window7_224] INFO: Epoch: [185] [1250/1251] eta: 0:00:00 lr: 0.000323 loss: 3.0781 (3.1542) grad_norm: 1.6765 (1.7636) time: 0.5014 [2021-03-26 13:28:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:11 loss: 1.0700 (1.0700) acc1: 71.8750 (71.8750) acc5: 93.7500 (93.7500) [2021-03-26 13:28:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8491 (0.8654) acc1: 79.6875 (79.1193) acc5: 95.3125 (95.4545) [2021-03-26 13:28:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8491 (0.8853) acc1: 78.1250 (78.5714) acc5: 93.7500 (94.8661) [2021-03-26 13:28:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8165 (0.8513) acc1: 79.6875 (79.3851) acc5: 96.8750 (95.6149) [2021-03-26 13:28:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7678 (0.8461) acc1: 79.6875 (79.3445) acc5: 96.8750 (95.5793) [2021-03-26 13:28:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8128 (0.8486) acc1: 77.3585 (79.4240) acc5: 95.3125 (95.4240) [2021-03-26 13:29:03 swin_small_patch4_window7_224] INFO: * Acc@1 80.016 Acc@5 95.182 loss 0.841 [2021-03-26 13:29:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.0% [2021-03-26 13:29:03 swin_small_patch4_window7_224] INFO: Max accuracy: 80.02% [2021-03-26 13:29:08 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 0/1251] eta: 1:27:39 lr: 0.000323 loss: 2.5149 (2.5149) grad_norm: 1.6658 (1.6658) time: 4.2041 [2021-03-26 13:29:13 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 10/1251] eta: 0:17:46 lr: 0.000323 loss: 3.4535 (3.2106) grad_norm: 1.6986 (1.7577) time: 0.8591 [2021-03-26 13:29:18 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 20/1251] eta: 0:14:08 lr: 0.000323 loss: 3.4174 (3.2626) grad_norm: 1.6981 (1.7297) time: 0.5138 [2021-03-26 13:29:23 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 30/1251] eta: 0:12:53 lr: 0.000323 loss: 3.2020 (3.1304) grad_norm: 1.6883 (1.7437) time: 0.5088 [2021-03-26 13:29:28 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 40/1251] eta: 0:12:06 lr: 0.000323 loss: 3.0492 (3.1139) grad_norm: 1.7154 (1.7307) time: 0.5060 [2021-03-26 13:29:33 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 50/1251] eta: 0:11:38 lr: 0.000323 loss: 3.0807 (3.1005) grad_norm: 1.7154 (1.7408) time: 0.5028 [2021-03-26 13:29:38 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 60/1251] eta: 0:11:19 lr: 0.000323 loss: 3.3091 (3.1396) grad_norm: 1.6846 (1.7299) time: 0.5095 [2021-03-26 13:29:43 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 70/1251] eta: 0:11:02 lr: 0.000323 loss: 3.4039 (3.1797) grad_norm: 1.6328 (1.7246) time: 0.5070 [2021-03-26 13:29:48 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 80/1251] eta: 0:10:50 lr: 0.000322 loss: 3.4400 (3.1878) grad_norm: 1.6343 (1.7220) time: 0.5088 [2021-03-26 13:29:53 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 90/1251] eta: 0:10:37 lr: 0.000322 loss: 3.4138 (3.1812) grad_norm: 1.6901 (1.7185) time: 0.5091 [2021-03-26 13:29:58 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 100/1251] eta: 0:10:27 lr: 0.000322 loss: 3.3662 (3.1810) grad_norm: 1.6901 (1.7228) time: 0.5066 [2021-03-26 13:30:03 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 110/1251] eta: 0:10:16 lr: 0.000322 loss: 3.3554 (3.1842) grad_norm: 1.6865 (1.7269) time: 0.5000 [2021-03-26 13:30:08 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 120/1251] eta: 0:10:07 lr: 0.000322 loss: 3.3193 (3.1846) grad_norm: 1.6865 (1.7222) time: 0.4933 [2021-03-26 13:30:13 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 130/1251] eta: 0:09:59 lr: 0.000322 loss: 3.3176 (3.1849) grad_norm: 1.6616 (1.7213) time: 0.4999 [2021-03-26 13:30:18 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 140/1251] eta: 0:09:50 lr: 0.000322 loss: 3.3176 (3.1759) grad_norm: 1.7002 (1.7233) time: 0.5014 [2021-03-26 13:30:24 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 150/1251] eta: 0:09:44 lr: 0.000322 loss: 3.3681 (3.1778) grad_norm: 1.7209 (1.7297) time: 0.5092 [2021-03-26 13:30:29 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 160/1251] eta: 0:09:37 lr: 0.000322 loss: 3.1567 (3.1725) grad_norm: 1.7142 (1.7302) time: 0.5128 [2021-03-26 13:30:34 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 170/1251] eta: 0:09:30 lr: 0.000322 loss: 3.0645 (3.1696) grad_norm: 1.6929 (1.7319) time: 0.5062 [2021-03-26 13:30:39 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 180/1251] eta: 0:09:25 lr: 0.000322 loss: 3.2325 (3.1678) grad_norm: 1.7774 (1.7410) time: 0.5158 [2021-03-26 13:30:44 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 190/1251] eta: 0:09:19 lr: 0.000322 loss: 3.0298 (3.1561) grad_norm: 1.7491 (1.7407) time: 0.5192 [2021-03-26 13:30:49 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 200/1251] eta: 0:09:12 lr: 0.000322 loss: 2.8867 (3.1441) grad_norm: 1.7491 (1.7465) time: 0.5050 [2021-03-26 13:30:54 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 210/1251] eta: 0:09:05 lr: 0.000322 loss: 3.0860 (3.1438) grad_norm: 1.7458 (1.7437) time: 0.4984 [2021-03-26 13:30:59 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 220/1251] eta: 0:09:00 lr: 0.000322 loss: 3.1248 (3.1351) grad_norm: 1.6392 (1.7422) time: 0.5045 [2021-03-26 13:31:04 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 230/1251] eta: 0:08:53 lr: 0.000322 loss: 3.3544 (3.1445) grad_norm: 1.6787 (1.7435) time: 0.5072 [2021-03-26 13:31:09 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 240/1251] eta: 0:08:47 lr: 0.000322 loss: 3.2188 (3.1386) grad_norm: 1.7083 (1.7441) time: 0.5019 [2021-03-26 13:31:14 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 250/1251] eta: 0:08:41 lr: 0.000322 loss: 3.2563 (3.1482) grad_norm: 1.7271 (1.7456) time: 0.5040 [2021-03-26 13:31:19 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 260/1251] eta: 0:08:36 lr: 0.000322 loss: 3.3835 (3.1568) grad_norm: 1.7333 (1.7438) time: 0.5052 [2021-03-26 13:31:24 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 270/1251] eta: 0:08:30 lr: 0.000322 loss: 3.1675 (3.1445) grad_norm: 1.6261 (1.7387) time: 0.5102 [2021-03-26 13:31:29 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 280/1251] eta: 0:08:24 lr: 0.000322 loss: 2.9641 (3.1526) grad_norm: 1.6742 (1.7399) time: 0.5104 [2021-03-26 13:31:34 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 290/1251] eta: 0:08:19 lr: 0.000322 loss: 3.1138 (3.1503) grad_norm: 1.7587 (1.7403) time: 0.5007 [2021-03-26 13:31:40 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 300/1251] eta: 0:08:13 lr: 0.000322 loss: 3.1138 (3.1500) grad_norm: 1.7547 (1.7402) time: 0.5043 [2021-03-26 13:31:45 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 310/1251] eta: 0:08:07 lr: 0.000322 loss: 3.2510 (3.1530) grad_norm: 1.7529 (1.7422) time: 0.5035 [2021-03-26 13:31:50 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 320/1251] eta: 0:08:01 lr: 0.000322 loss: 3.4024 (3.1586) grad_norm: 1.7061 (1.7412) time: 0.4977 [2021-03-26 13:31:55 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 330/1251] eta: 0:07:56 lr: 0.000322 loss: 3.4024 (3.1613) grad_norm: 1.7061 (1.7411) time: 0.5048 [2021-03-26 13:32:00 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 340/1251] eta: 0:07:51 lr: 0.000321 loss: 3.2803 (3.1604) grad_norm: 1.6735 (1.7378) time: 0.5115 [2021-03-26 13:32:05 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 350/1251] eta: 0:07:45 lr: 0.000321 loss: 3.2523 (3.1609) grad_norm: 1.5839 (1.7357) time: 0.5097 [2021-03-26 13:32:10 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 360/1251] eta: 0:07:40 lr: 0.000321 loss: 3.2353 (3.1634) grad_norm: 1.6581 (1.7355) time: 0.5071 [2021-03-26 13:32:15 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 370/1251] eta: 0:07:34 lr: 0.000321 loss: 3.2353 (3.1628) grad_norm: 1.7398 (1.7406) time: 0.5034 [2021-03-26 13:32:20 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 380/1251] eta: 0:07:29 lr: 0.000321 loss: 3.2372 (3.1638) grad_norm: 1.7398 (1.7428) time: 0.5027 [2021-03-26 13:32:25 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 390/1251] eta: 0:07:24 lr: 0.000321 loss: 3.2614 (3.1636) grad_norm: 1.7264 (1.7427) time: 0.5120 [2021-03-26 13:32:30 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 400/1251] eta: 0:07:18 lr: 0.000321 loss: 3.0543 (3.1585) grad_norm: 1.7377 (1.7438) time: 0.5098 [2021-03-26 13:32:35 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 410/1251] eta: 0:07:13 lr: 0.000321 loss: 2.9602 (3.1541) grad_norm: 1.8232 (1.7460) time: 0.4993 [2021-03-26 13:32:40 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 420/1251] eta: 0:07:07 lr: 0.000321 loss: 3.2418 (3.1570) grad_norm: 1.7854 (1.7449) time: 0.5016 [2021-03-26 13:32:45 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 430/1251] eta: 0:07:02 lr: 0.000321 loss: 3.2418 (3.1545) grad_norm: 1.7571 (1.7468) time: 0.5017 [2021-03-26 13:32:50 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 440/1251] eta: 0:06:57 lr: 0.000321 loss: 3.1046 (3.1549) grad_norm: 1.8187 (1.7497) time: 0.5047 [2021-03-26 13:32:55 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 450/1251] eta: 0:06:51 lr: 0.000321 loss: 3.1899 (3.1556) grad_norm: 1.7370 (1.7496) time: 0.5090 [2021-03-26 13:33:00 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 460/1251] eta: 0:06:46 lr: 0.000321 loss: 3.1661 (3.1549) grad_norm: 1.6578 (1.7471) time: 0.5012 [2021-03-26 13:33:05 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 470/1251] eta: 0:06:41 lr: 0.000321 loss: 3.1292 (3.1534) grad_norm: 1.6571 (1.7479) time: 0.4976 [2021-03-26 13:33:10 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 480/1251] eta: 0:06:35 lr: 0.000321 loss: 3.3318 (3.1555) grad_norm: 1.6908 (1.7467) time: 0.5058 [2021-03-26 13:33:15 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 490/1251] eta: 0:06:30 lr: 0.000321 loss: 3.3318 (3.1513) grad_norm: 1.6257 (1.7453) time: 0.5040 [2021-03-26 13:33:20 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 500/1251] eta: 0:06:25 lr: 0.000321 loss: 2.9433 (3.1486) grad_norm: 1.5979 (1.7442) time: 0.4968 [2021-03-26 13:33:25 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 510/1251] eta: 0:06:19 lr: 0.000321 loss: 3.2758 (3.1517) grad_norm: 1.6545 (1.7442) time: 0.4983 [2021-03-26 13:33:30 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 520/1251] eta: 0:06:14 lr: 0.000321 loss: 3.1179 (3.1460) grad_norm: 1.7165 (1.7431) time: 0.5022 [2021-03-26 13:33:35 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 530/1251] eta: 0:06:09 lr: 0.000321 loss: 3.2564 (3.1528) grad_norm: 1.7793 (1.7443) time: 0.5017 [2021-03-26 13:33:41 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 540/1251] eta: 0:06:04 lr: 0.000321 loss: 3.2564 (3.1509) grad_norm: 1.8136 (1.7486) time: 0.5057 [2021-03-26 13:33:46 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 550/1251] eta: 0:05:59 lr: 0.000321 loss: 3.1717 (3.1521) grad_norm: 1.6935 (1.7483) time: 0.5196 [2021-03-26 13:33:51 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 560/1251] eta: 0:05:54 lr: 0.000321 loss: 3.0877 (3.1467) grad_norm: 1.6843 (1.7478) time: 0.5169 [2021-03-26 13:33:56 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 570/1251] eta: 0:05:48 lr: 0.000321 loss: 3.1190 (3.1487) grad_norm: 1.7193 (1.7483) time: 0.5054 [2021-03-26 13:34:01 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 580/1251] eta: 0:05:43 lr: 0.000321 loss: 3.3910 (3.1529) grad_norm: 1.7545 (1.7478) time: 0.5063 [2021-03-26 13:34:06 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 590/1251] eta: 0:05:38 lr: 0.000321 loss: 3.2584 (3.1511) grad_norm: 1.7568 (1.7487) time: 0.5081 [2021-03-26 13:34:11 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 600/1251] eta: 0:05:33 lr: 0.000320 loss: 3.2344 (3.1532) grad_norm: 1.7568 (1.7483) time: 0.5033 [2021-03-26 13:34:16 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 610/1251] eta: 0:05:28 lr: 0.000320 loss: 3.2344 (3.1491) grad_norm: 1.7410 (1.7476) time: 0.5000 [2021-03-26 13:34:21 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 620/1251] eta: 0:05:22 lr: 0.000320 loss: 3.1032 (3.1486) grad_norm: 1.6989 (1.7481) time: 0.5040 [2021-03-26 13:34:26 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 630/1251] eta: 0:05:17 lr: 0.000320 loss: 3.1267 (3.1489) grad_norm: 1.7661 (1.7500) time: 0.5040 [2021-03-26 13:34:31 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 640/1251] eta: 0:05:12 lr: 0.000320 loss: 3.1267 (3.1485) grad_norm: 1.7708 (1.7500) time: 0.5052 [2021-03-26 13:34:36 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 650/1251] eta: 0:05:07 lr: 0.000320 loss: 3.0406 (3.1468) grad_norm: 1.7496 (1.7500) time: 0.5097 [2021-03-26 13:34:41 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 660/1251] eta: 0:05:02 lr: 0.000320 loss: 3.1868 (3.1466) grad_norm: 1.7046 (1.7489) time: 0.5116 [2021-03-26 13:34:47 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 670/1251] eta: 0:04:57 lr: 0.000320 loss: 3.1934 (3.1466) grad_norm: 1.6313 (1.7469) time: 0.5089 [2021-03-26 13:34:52 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 680/1251] eta: 0:04:51 lr: 0.000320 loss: 3.2615 (3.1497) grad_norm: 1.6771 (1.7473) time: 0.5028 [2021-03-26 13:34:57 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 690/1251] eta: 0:04:46 lr: 0.000320 loss: 3.4393 (3.1531) grad_norm: 1.8058 (1.7499) time: 0.5019 [2021-03-26 13:35:02 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 700/1251] eta: 0:04:41 lr: 0.000320 loss: 3.3618 (3.1524) grad_norm: 1.8058 (1.7506) time: 0.4997 [2021-03-26 13:35:07 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 710/1251] eta: 0:04:36 lr: 0.000320 loss: 3.4724 (3.1559) grad_norm: 1.7650 (inf) time: 0.4980 [2021-03-26 13:35:12 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 720/1251] eta: 0:04:31 lr: 0.000320 loss: 3.3822 (3.1562) grad_norm: 1.7650 (inf) time: 0.5031 [2021-03-26 13:35:17 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 730/1251] eta: 0:04:26 lr: 0.000320 loss: 3.2817 (3.1587) grad_norm: 1.7432 (inf) time: 0.5152 [2021-03-26 13:35:22 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 740/1251] eta: 0:04:21 lr: 0.000320 loss: 3.4225 (3.1602) grad_norm: 1.7557 (inf) time: 0.5194 [2021-03-26 13:35:27 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 750/1251] eta: 0:04:15 lr: 0.000320 loss: 3.3303 (3.1598) grad_norm: 1.6955 (inf) time: 0.5124 [2021-03-26 13:35:32 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 760/1251] eta: 0:04:10 lr: 0.000320 loss: 3.1045 (3.1593) grad_norm: 1.6585 (inf) time: 0.5081 [2021-03-26 13:35:37 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 770/1251] eta: 0:04:05 lr: 0.000320 loss: 3.1045 (3.1582) grad_norm: 1.7327 (inf) time: 0.5125 [2021-03-26 13:35:42 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 780/1251] eta: 0:04:00 lr: 0.000320 loss: 3.1386 (3.1589) grad_norm: 1.7310 (inf) time: 0.5119 [2021-03-26 13:35:47 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 790/1251] eta: 0:03:55 lr: 0.000320 loss: 3.2276 (3.1595) grad_norm: 1.7275 (inf) time: 0.5043 [2021-03-26 13:35:53 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 800/1251] eta: 0:03:50 lr: 0.000320 loss: 3.2109 (3.1583) grad_norm: 1.7275 (inf) time: 0.5048 [2021-03-26 13:35:58 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 810/1251] eta: 0:03:45 lr: 0.000320 loss: 2.9875 (3.1564) grad_norm: 1.7054 (inf) time: 0.5043 [2021-03-26 13:36:03 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 820/1251] eta: 0:03:40 lr: 0.000320 loss: 3.2142 (3.1591) grad_norm: 1.6661 (inf) time: 0.5025 [2021-03-26 13:36:08 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 830/1251] eta: 0:03:34 lr: 0.000320 loss: 3.4392 (3.1599) grad_norm: 1.6826 (inf) time: 0.5084 [2021-03-26 13:36:13 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 840/1251] eta: 0:03:29 lr: 0.000320 loss: 3.2974 (3.1594) grad_norm: 1.6656 (inf) time: 0.5048 [2021-03-26 13:36:18 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 850/1251] eta: 0:03:24 lr: 0.000320 loss: 2.9539 (3.1587) grad_norm: 1.7876 (nan) time: 0.4924 [2021-03-26 13:36:23 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 860/1251] eta: 0:03:19 lr: 0.000319 loss: 2.8600 (3.1568) grad_norm: 1.7965 (nan) time: 0.4947 [2021-03-26 13:36:28 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 870/1251] eta: 0:03:14 lr: 0.000319 loss: 3.1121 (3.1570) grad_norm: 1.7666 (nan) time: 0.5007 [2021-03-26 13:36:33 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 880/1251] eta: 0:03:09 lr: 0.000319 loss: 3.3158 (3.1588) grad_norm: 1.7629 (nan) time: 0.5002 [2021-03-26 13:36:38 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 890/1251] eta: 0:03:03 lr: 0.000319 loss: 3.3686 (3.1616) grad_norm: 1.7346 (nan) time: 0.5000 [2021-03-26 13:36:43 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 900/1251] eta: 0:02:58 lr: 0.000319 loss: 3.3067 (3.1630) grad_norm: 1.7685 (nan) time: 0.5062 [2021-03-26 13:36:48 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 910/1251] eta: 0:02:53 lr: 0.000319 loss: 3.2375 (3.1618) grad_norm: 1.7685 (nan) time: 0.5048 [2021-03-26 13:36:53 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 920/1251] eta: 0:02:48 lr: 0.000319 loss: 3.2375 (3.1611) grad_norm: 1.8143 (nan) time: 0.5082 [2021-03-26 13:36:58 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 930/1251] eta: 0:02:43 lr: 0.000319 loss: 3.2621 (3.1584) grad_norm: 1.7700 (nan) time: 0.5144 [2021-03-26 13:37:03 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 940/1251] eta: 0:02:38 lr: 0.000319 loss: 3.0455 (3.1576) grad_norm: 1.7348 (nan) time: 0.5097 [2021-03-26 13:37:08 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 950/1251] eta: 0:02:33 lr: 0.000319 loss: 3.0554 (3.1562) grad_norm: 1.6988 (nan) time: 0.5030 [2021-03-26 13:37:13 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 960/1251] eta: 0:02:28 lr: 0.000319 loss: 2.8418 (3.1531) grad_norm: 1.6771 (nan) time: 0.5000 [2021-03-26 13:37:18 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 970/1251] eta: 0:02:23 lr: 0.000319 loss: 2.8288 (3.1511) grad_norm: 1.6837 (nan) time: 0.5016 [2021-03-26 13:37:23 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 980/1251] eta: 0:02:18 lr: 0.000319 loss: 3.2200 (3.1541) grad_norm: 1.7731 (nan) time: 0.4998 [2021-03-26 13:37:28 swin_small_patch4_window7_224] INFO: Epoch: [186] [ 990/1251] eta: 0:02:12 lr: 0.000319 loss: 3.3037 (3.1565) grad_norm: 1.7056 (nan) time: 0.5064 [2021-03-26 13:37:33 swin_small_patch4_window7_224] INFO: Epoch: [186] [1000/1251] eta: 0:02:07 lr: 0.000319 loss: 3.1310 (3.1535) grad_norm: 1.7056 (nan) time: 0.5080 [2021-03-26 13:37:38 swin_small_patch4_window7_224] INFO: Epoch: [186] [1010/1251] eta: 0:02:02 lr: 0.000319 loss: 2.8541 (3.1514) grad_norm: 1.7796 (nan) time: 0.5044 [2021-03-26 13:37:43 swin_small_patch4_window7_224] INFO: Epoch: [186] [1020/1251] eta: 0:01:57 lr: 0.000319 loss: 2.8541 (3.1508) grad_norm: 1.7379 (nan) time: 0.5074 [2021-03-26 13:37:48 swin_small_patch4_window7_224] INFO: Epoch: [186] [1030/1251] eta: 0:01:52 lr: 0.000319 loss: 3.3397 (3.1519) grad_norm: 1.7315 (nan) time: 0.5065 [2021-03-26 13:37:54 swin_small_patch4_window7_224] INFO: Epoch: [186] [1040/1251] eta: 0:01:47 lr: 0.000319 loss: 3.1663 (3.1514) grad_norm: 1.6646 (nan) time: 0.5068 [2021-03-26 13:37:58 swin_small_patch4_window7_224] INFO: Epoch: [186] [1050/1251] eta: 0:01:42 lr: 0.000319 loss: 3.3541 (3.1538) grad_norm: 1.6900 (nan) time: 0.5026 [2021-03-26 13:38:04 swin_small_patch4_window7_224] INFO: Epoch: [186] [1060/1251] eta: 0:01:37 lr: 0.000319 loss: 3.2001 (3.1508) grad_norm: 1.7112 (nan) time: 0.5013 [2021-03-26 13:38:09 swin_small_patch4_window7_224] INFO: Epoch: [186] [1070/1251] eta: 0:01:32 lr: 0.000319 loss: 3.1499 (3.1507) grad_norm: 1.7051 (nan) time: 0.5120 [2021-03-26 13:38:14 swin_small_patch4_window7_224] INFO: Epoch: [186] [1080/1251] eta: 0:01:27 lr: 0.000319 loss: 3.1623 (3.1481) grad_norm: 1.7406 (nan) time: 0.5138 [2021-03-26 13:38:19 swin_small_patch4_window7_224] INFO: Epoch: [186] [1090/1251] eta: 0:01:21 lr: 0.000319 loss: 3.1485 (3.1474) grad_norm: 1.7085 (nan) time: 0.5109 [2021-03-26 13:38:24 swin_small_patch4_window7_224] INFO: Epoch: [186] [1100/1251] eta: 0:01:16 lr: 0.000319 loss: 3.2535 (3.1491) grad_norm: 1.6654 (nan) time: 0.5070 [2021-03-26 13:38:29 swin_small_patch4_window7_224] INFO: Epoch: [186] [1110/1251] eta: 0:01:11 lr: 0.000319 loss: 3.1418 (3.1458) grad_norm: 1.7142 (nan) time: 0.5004 [2021-03-26 13:38:34 swin_small_patch4_window7_224] INFO: Epoch: [186] [1120/1251] eta: 0:01:06 lr: 0.000318 loss: 2.9265 (3.1450) grad_norm: 1.7282 (nan) time: 0.5015 [2021-03-26 13:38:39 swin_small_patch4_window7_224] INFO: Epoch: [186] [1130/1251] eta: 0:01:01 lr: 0.000318 loss: 3.0696 (3.1449) grad_norm: 1.7257 (nan) time: 0.5102 [2021-03-26 13:38:44 swin_small_patch4_window7_224] INFO: Epoch: [186] [1140/1251] eta: 0:00:56 lr: 0.000318 loss: 3.3691 (3.1435) grad_norm: 1.7559 (nan) time: 0.5050 [2021-03-26 13:38:49 swin_small_patch4_window7_224] INFO: Epoch: [186] [1150/1251] eta: 0:00:51 lr: 0.000318 loss: 3.3691 (3.1458) grad_norm: 1.8325 (nan) time: 0.4966 [2021-03-26 13:38:54 swin_small_patch4_window7_224] INFO: Epoch: [186] [1160/1251] eta: 0:00:46 lr: 0.000318 loss: 3.3312 (3.1445) grad_norm: 1.7009 (nan) time: 0.5002 [2021-03-26 13:38:59 swin_small_patch4_window7_224] INFO: Epoch: [186] [1170/1251] eta: 0:00:41 lr: 0.000318 loss: 3.1660 (3.1442) grad_norm: 1.6766 (nan) time: 0.4992 [2021-03-26 13:39:04 swin_small_patch4_window7_224] INFO: Epoch: [186] [1180/1251] eta: 0:00:36 lr: 0.000318 loss: 3.2890 (3.1455) grad_norm: 1.7618 (nan) time: 0.5025 [2021-03-26 13:39:09 swin_small_patch4_window7_224] INFO: Epoch: [186] [1190/1251] eta: 0:00:31 lr: 0.000318 loss: 3.1091 (3.1422) grad_norm: 1.7758 (nan) time: 0.5122 [2021-03-26 13:39:14 swin_small_patch4_window7_224] INFO: Epoch: [186] [1200/1251] eta: 0:00:25 lr: 0.000318 loss: 2.9873 (3.1430) grad_norm: 1.7941 (nan) time: 0.5083 [2021-03-26 13:39:19 swin_small_patch4_window7_224] INFO: Epoch: [186] [1210/1251] eta: 0:00:20 lr: 0.000318 loss: 3.2685 (3.1439) grad_norm: 1.7732 (nan) time: 0.4974 [2021-03-26 13:39:24 swin_small_patch4_window7_224] INFO: Epoch: [186] [1220/1251] eta: 0:00:15 lr: 0.000318 loss: 3.2685 (3.1443) grad_norm: 1.8117 (nan) time: 0.4935 [2021-03-26 13:39:29 swin_small_patch4_window7_224] INFO: Epoch: [186] [1230/1251] eta: 0:00:10 lr: 0.000318 loss: 3.3254 (3.1456) grad_norm: 1.7895 (nan) time: 0.4981 [2021-03-26 13:39:34 swin_small_patch4_window7_224] INFO: Epoch: [186] [1240/1251] eta: 0:00:05 lr: 0.000318 loss: 3.4233 (3.1472) grad_norm: 1.7489 (nan) time: 0.5057 [2021-03-26 13:39:39 swin_small_patch4_window7_224] INFO: Epoch: [186] [1250/1251] eta: 0:00:00 lr: 0.000318 loss: 3.4233 (3.1478) grad_norm: 1.7748 (nan) time: 0.5081 [2021-03-26 13:39:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 0.8687 (0.8687) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-26 13:39:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8687 (0.8258) acc1: 75.0000 (77.9830) acc5: 96.8750 (96.0227) [2021-03-26 13:39:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8614 (0.8559) acc1: 76.5625 (77.3810) acc5: 95.3125 (95.6845) [2021-03-26 13:39:57 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8614 (0.8488) acc1: 78.1250 (77.9234) acc5: 95.3125 (95.8669) [2021-03-26 13:39:59 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8690 (0.8522) acc1: 79.6875 (78.2393) acc5: 95.3125 (95.7698) [2021-03-26 13:40:00 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8741 (0.8484) acc1: 79.6875 (78.7200) acc5: 95.3125 (95.6160) [2021-03-26 13:40:12 swin_small_patch4_window7_224] INFO: * Acc@1 79.892 Acc@5 95.244 loss 0.838 [2021-03-26 13:40:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.9% [2021-03-26 13:40:12 swin_small_patch4_window7_224] INFO: Max accuracy: 80.02% [2021-03-26 13:40:16 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 0/1251] eta: 1:34:23 lr: 0.000318 loss: 3.0029 (3.0029) grad_norm: 1.8546 (1.8546) time: 4.5274 [2021-03-26 13:40:22 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 10/1251] eta: 0:18:36 lr: 0.000318 loss: 3.1501 (3.0065) grad_norm: 1.6798 (1.7269) time: 0.8999 [2021-03-26 13:40:27 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 20/1251] eta: 0:14:33 lr: 0.000318 loss: 3.3193 (3.1224) grad_norm: 1.6798 (1.7656) time: 0.5189 [2021-03-26 13:40:32 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 30/1251] eta: 0:13:05 lr: 0.000318 loss: 3.2497 (3.1187) grad_norm: 1.7149 (1.7599) time: 0.5023 [2021-03-26 13:40:37 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 40/1251] eta: 0:12:16 lr: 0.000318 loss: 3.2497 (3.2065) grad_norm: 1.6981 (1.7364) time: 0.5024 [2021-03-26 13:40:42 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 50/1251] eta: 0:11:48 lr: 0.000318 loss: 3.4536 (3.2158) grad_norm: 1.7412 (1.7516) time: 0.5081 [2021-03-26 13:40:47 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 60/1251] eta: 0:11:27 lr: 0.000318 loss: 3.1909 (3.1907) grad_norm: 1.7530 (1.7495) time: 0.5142 [2021-03-26 13:40:52 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 70/1251] eta: 0:11:11 lr: 0.000318 loss: 3.0957 (3.1932) grad_norm: 1.8130 (1.7706) time: 0.5127 [2021-03-26 13:40:57 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 80/1251] eta: 0:10:56 lr: 0.000318 loss: 3.3432 (3.1674) grad_norm: 1.8147 (1.7732) time: 0.5091 [2021-03-26 13:41:02 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 90/1251] eta: 0:10:43 lr: 0.000318 loss: 3.1416 (3.1642) grad_norm: 1.7335 (1.7796) time: 0.5030 [2021-03-26 13:41:07 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 100/1251] eta: 0:10:32 lr: 0.000318 loss: 3.1222 (3.1543) grad_norm: 1.7331 (1.7748) time: 0.5036 [2021-03-26 13:41:13 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 110/1251] eta: 0:10:24 lr: 0.000318 loss: 2.9475 (3.1359) grad_norm: 1.7381 (1.7748) time: 0.5162 [2021-03-26 13:41:18 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 120/1251] eta: 0:10:14 lr: 0.000318 loss: 3.0841 (3.1287) grad_norm: 1.7685 (1.7866) time: 0.5138 [2021-03-26 13:41:23 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 130/1251] eta: 0:10:06 lr: 0.000317 loss: 3.1898 (3.1474) grad_norm: 1.7836 (1.7911) time: 0.5084 [2021-03-26 13:41:28 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 140/1251] eta: 0:09:57 lr: 0.000317 loss: 3.3339 (3.1503) grad_norm: 1.7924 (1.7952) time: 0.5060 [2021-03-26 13:41:33 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 150/1251] eta: 0:09:49 lr: 0.000317 loss: 3.2837 (3.1471) grad_norm: 1.9158 (1.8070) time: 0.4990 [2021-03-26 13:41:38 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 160/1251] eta: 0:09:42 lr: 0.000317 loss: 3.3175 (3.1582) grad_norm: 1.9098 (1.8188) time: 0.5070 [2021-03-26 13:41:43 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 170/1251] eta: 0:09:35 lr: 0.000317 loss: 3.4315 (3.1772) grad_norm: 1.8445 (1.8256) time: 0.5107 [2021-03-26 13:41:48 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 180/1251] eta: 0:09:30 lr: 0.000317 loss: 3.4681 (3.1792) grad_norm: 1.8170 (1.8256) time: 0.5155 [2021-03-26 13:41:53 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 190/1251] eta: 0:09:22 lr: 0.000317 loss: 2.9943 (3.1647) grad_norm: 1.7184 (1.8248) time: 0.5112 [2021-03-26 13:41:58 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 200/1251] eta: 0:09:16 lr: 0.000317 loss: 3.0729 (3.1736) grad_norm: 1.8107 (1.8257) time: 0.5064 [2021-03-26 13:42:04 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 210/1251] eta: 0:09:10 lr: 0.000317 loss: 3.1137 (3.1735) grad_norm: 1.7857 (1.8247) time: 0.5116 [2021-03-26 13:42:09 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 220/1251] eta: 0:09:03 lr: 0.000317 loss: 3.2113 (3.1790) grad_norm: 1.7674 (1.8265) time: 0.5056 [2021-03-26 13:42:14 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 230/1251] eta: 0:08:57 lr: 0.000317 loss: 3.3372 (3.1868) grad_norm: 1.8220 (1.8267) time: 0.5044 [2021-03-26 13:42:19 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 240/1251] eta: 0:08:51 lr: 0.000317 loss: 3.0834 (3.1815) grad_norm: 1.7908 (1.8242) time: 0.5049 [2021-03-26 13:42:24 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 250/1251] eta: 0:08:44 lr: 0.000317 loss: 3.2574 (3.1943) grad_norm: 1.7545 (1.8265) time: 0.4995 [2021-03-26 13:42:29 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 260/1251] eta: 0:08:38 lr: 0.000317 loss: 3.3458 (3.1948) grad_norm: 1.8329 (1.8294) time: 0.4995 [2021-03-26 13:42:34 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 270/1251] eta: 0:08:33 lr: 0.000317 loss: 3.2735 (3.1996) grad_norm: 1.8043 (1.8272) time: 0.5049 [2021-03-26 13:42:39 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 280/1251] eta: 0:08:27 lr: 0.000317 loss: 3.1150 (3.1951) grad_norm: 1.7345 (1.8275) time: 0.5048 [2021-03-26 13:42:44 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 290/1251] eta: 0:08:21 lr: 0.000317 loss: 3.1487 (3.1977) grad_norm: 1.8079 (1.8331) time: 0.5048 [2021-03-26 13:42:49 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 300/1251] eta: 0:08:15 lr: 0.000317 loss: 3.2279 (3.1961) grad_norm: 1.8720 (1.8373) time: 0.5091 [2021-03-26 13:42:54 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 310/1251] eta: 0:08:10 lr: 0.000317 loss: 3.0995 (3.1972) grad_norm: 1.8465 (1.8416) time: 0.5132 [2021-03-26 13:42:59 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 320/1251] eta: 0:08:04 lr: 0.000317 loss: 3.0995 (3.1903) grad_norm: 1.8007 (1.8383) time: 0.5056 [2021-03-26 13:43:04 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 330/1251] eta: 0:07:58 lr: 0.000317 loss: 3.1924 (3.1919) grad_norm: 1.7302 (1.8386) time: 0.4982 [2021-03-26 13:43:09 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 340/1251] eta: 0:07:53 lr: 0.000317 loss: 3.0626 (3.1820) grad_norm: 1.6925 (1.8368) time: 0.5020 [2021-03-26 13:43:14 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 350/1251] eta: 0:07:47 lr: 0.000317 loss: 2.8258 (3.1731) grad_norm: 1.6910 (1.8359) time: 0.5038 [2021-03-26 13:43:19 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 360/1251] eta: 0:07:42 lr: 0.000317 loss: 3.0648 (3.1695) grad_norm: 1.7590 (1.8356) time: 0.5089 [2021-03-26 13:43:24 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 370/1251] eta: 0:07:36 lr: 0.000317 loss: 3.0843 (3.1675) grad_norm: 1.7174 (1.8334) time: 0.5100 [2021-03-26 13:43:29 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 380/1251] eta: 0:07:31 lr: 0.000317 loss: 3.0843 (3.1669) grad_norm: 1.8274 (1.8348) time: 0.5006 [2021-03-26 13:43:34 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 390/1251] eta: 0:07:25 lr: 0.000316 loss: 3.2310 (3.1678) grad_norm: 1.8997 (1.8348) time: 0.4958 [2021-03-26 13:43:39 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 400/1251] eta: 0:07:19 lr: 0.000316 loss: 3.2411 (3.1675) grad_norm: 1.8035 (1.8343) time: 0.4973 [2021-03-26 13:43:44 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 410/1251] eta: 0:07:14 lr: 0.000316 loss: 2.9915 (3.1617) grad_norm: 1.7770 (1.8387) time: 0.4995 [2021-03-26 13:43:49 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 420/1251] eta: 0:07:08 lr: 0.000316 loss: 3.1109 (3.1681) grad_norm: 1.7770 (1.8397) time: 0.5005 [2021-03-26 13:43:54 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 430/1251] eta: 0:07:03 lr: 0.000316 loss: 3.3738 (3.1674) grad_norm: 1.7975 (1.8404) time: 0.5013 [2021-03-26 13:43:59 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 440/1251] eta: 0:06:57 lr: 0.000316 loss: 3.3851 (3.1758) grad_norm: 1.7822 (1.8388) time: 0.4988 [2021-03-26 13:44:04 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 450/1251] eta: 0:06:52 lr: 0.000316 loss: 3.5330 (3.1831) grad_norm: 1.7568 (1.8387) time: 0.5004 [2021-03-26 13:44:09 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 460/1251] eta: 0:06:47 lr: 0.000316 loss: 3.3469 (3.1817) grad_norm: 1.8189 (1.8390) time: 0.5086 [2021-03-26 13:44:15 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 470/1251] eta: 0:06:42 lr: 0.000316 loss: 3.3051 (3.1832) grad_norm: 1.8681 (1.8422) time: 0.5107 [2021-03-26 13:44:19 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 480/1251] eta: 0:06:36 lr: 0.000316 loss: 3.2276 (3.1828) grad_norm: 1.8019 (1.8436) time: 0.5035 [2021-03-26 13:44:24 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 490/1251] eta: 0:06:31 lr: 0.000316 loss: 2.9306 (3.1722) grad_norm: 1.7286 (1.8433) time: 0.4996 [2021-03-26 13:44:30 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 500/1251] eta: 0:06:26 lr: 0.000316 loss: 2.7807 (3.1699) grad_norm: 1.6713 (1.8407) time: 0.5089 [2021-03-26 13:44:35 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 510/1251] eta: 0:06:20 lr: 0.000316 loss: 3.1005 (3.1692) grad_norm: 1.7187 (1.8389) time: 0.5070 [2021-03-26 13:44:40 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 520/1251] eta: 0:06:15 lr: 0.000316 loss: 3.1322 (3.1659) grad_norm: 1.7519 (1.8394) time: 0.5019 [2021-03-26 13:44:45 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 530/1251] eta: 0:06:10 lr: 0.000316 loss: 3.3119 (3.1696) grad_norm: 1.7261 (1.8385) time: 0.5075 [2021-03-26 13:44:50 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 540/1251] eta: 0:06:05 lr: 0.000316 loss: 3.3501 (3.1705) grad_norm: 1.7065 (1.8373) time: 0.5064 [2021-03-26 13:44:55 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 550/1251] eta: 0:06:00 lr: 0.000316 loss: 3.3501 (3.1680) grad_norm: 1.6580 (1.8352) time: 0.5136 [2021-03-26 13:45:00 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 560/1251] eta: 0:05:54 lr: 0.000316 loss: 3.4174 (3.1716) grad_norm: 1.6816 (1.8332) time: 0.5201 [2021-03-26 13:45:05 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 570/1251] eta: 0:05:49 lr: 0.000316 loss: 3.4321 (3.1734) grad_norm: 1.7124 (1.8329) time: 0.5115 [2021-03-26 13:45:10 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 580/1251] eta: 0:05:44 lr: 0.000316 loss: 3.2484 (3.1724) grad_norm: 1.7786 (1.8314) time: 0.5041 [2021-03-26 13:45:15 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 590/1251] eta: 0:05:39 lr: 0.000316 loss: 3.2678 (3.1756) grad_norm: 1.7871 (1.8327) time: 0.5045 [2021-03-26 13:45:21 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 600/1251] eta: 0:05:34 lr: 0.000316 loss: 3.3716 (3.1775) grad_norm: 1.7689 (1.8304) time: 0.5120 [2021-03-26 13:45:26 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 610/1251] eta: 0:05:29 lr: 0.000316 loss: 3.2619 (3.1773) grad_norm: 1.6458 (1.8284) time: 0.5132 [2021-03-26 13:45:31 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 620/1251] eta: 0:05:23 lr: 0.000316 loss: 3.2505 (3.1736) grad_norm: 1.6518 (1.8269) time: 0.5064 [2021-03-26 13:45:36 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 630/1251] eta: 0:05:18 lr: 0.000316 loss: 2.9184 (3.1678) grad_norm: 1.6623 (1.8255) time: 0.5054 [2021-03-26 13:45:41 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 640/1251] eta: 0:05:13 lr: 0.000316 loss: 2.8804 (3.1658) grad_norm: 1.7419 (1.8247) time: 0.5068 [2021-03-26 13:45:46 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 650/1251] eta: 0:05:08 lr: 0.000315 loss: 3.1259 (3.1673) grad_norm: 1.7363 (1.8239) time: 0.5028 [2021-03-26 13:45:51 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 660/1251] eta: 0:05:03 lr: 0.000315 loss: 3.2547 (3.1687) grad_norm: 1.7113 (1.8225) time: 0.5066 [2021-03-26 13:45:56 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 670/1251] eta: 0:04:57 lr: 0.000315 loss: 3.2547 (3.1665) grad_norm: 1.7067 (1.8204) time: 0.5032 [2021-03-26 13:46:01 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 680/1251] eta: 0:04:52 lr: 0.000315 loss: 3.1441 (3.1655) grad_norm: 1.7425 (1.8208) time: 0.5030 [2021-03-26 13:46:06 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 690/1251] eta: 0:04:47 lr: 0.000315 loss: 3.1441 (3.1646) grad_norm: 1.8042 (1.8198) time: 0.5164 [2021-03-26 13:46:11 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 700/1251] eta: 0:04:42 lr: 0.000315 loss: 3.1404 (3.1608) grad_norm: 1.6740 (1.8182) time: 0.5147 [2021-03-26 13:46:16 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 710/1251] eta: 0:04:37 lr: 0.000315 loss: 2.8997 (3.1570) grad_norm: 1.7208 (1.8175) time: 0.5108 [2021-03-26 13:46:21 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 720/1251] eta: 0:04:32 lr: 0.000315 loss: 2.9227 (3.1547) grad_norm: 1.7500 (1.8165) time: 0.5084 [2021-03-26 13:46:27 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 730/1251] eta: 0:04:26 lr: 0.000315 loss: 3.1181 (3.1539) grad_norm: 1.7303 (1.8152) time: 0.5063 [2021-03-26 13:46:32 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 740/1251] eta: 0:04:21 lr: 0.000315 loss: 3.1961 (3.1545) grad_norm: 1.7303 (1.8141) time: 0.5138 [2021-03-26 13:46:37 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 750/1251] eta: 0:04:16 lr: 0.000315 loss: 3.1961 (3.1551) grad_norm: 1.6864 (1.8133) time: 0.5299 [2021-03-26 13:46:42 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 760/1251] eta: 0:04:11 lr: 0.000315 loss: 3.1286 (3.1526) grad_norm: 1.6864 (1.8125) time: 0.5225 [2021-03-26 13:46:47 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 770/1251] eta: 0:04:06 lr: 0.000315 loss: 3.1546 (3.1527) grad_norm: 1.6916 (1.8114) time: 0.5038 [2021-03-26 13:46:52 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 780/1251] eta: 0:04:01 lr: 0.000315 loss: 3.2983 (3.1513) grad_norm: 1.7439 (1.8115) time: 0.5042 [2021-03-26 13:46:57 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 790/1251] eta: 0:03:56 lr: 0.000315 loss: 2.9049 (3.1478) grad_norm: 1.7168 (1.8099) time: 0.5067 [2021-03-26 13:47:02 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 800/1251] eta: 0:03:51 lr: 0.000315 loss: 3.1081 (3.1481) grad_norm: 1.6764 (1.8087) time: 0.5067 [2021-03-26 13:47:07 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 810/1251] eta: 0:03:45 lr: 0.000315 loss: 3.1532 (3.1459) grad_norm: 1.6905 (1.8081) time: 0.5009 [2021-03-26 13:47:12 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 820/1251] eta: 0:03:40 lr: 0.000315 loss: 3.1211 (3.1462) grad_norm: 1.7592 (1.8097) time: 0.5007 [2021-03-26 13:47:17 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 830/1251] eta: 0:03:35 lr: 0.000315 loss: 3.1519 (3.1466) grad_norm: 1.8159 (1.8124) time: 0.5021 [2021-03-26 13:47:23 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 840/1251] eta: 0:03:30 lr: 0.000315 loss: 3.2086 (3.1470) grad_norm: 1.7564 (1.8117) time: 0.5018 [2021-03-26 13:47:28 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 850/1251] eta: 0:03:25 lr: 0.000315 loss: 3.0885 (3.1457) grad_norm: 1.7376 (1.8119) time: 0.5117 [2021-03-26 13:47:33 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 860/1251] eta: 0:03:20 lr: 0.000315 loss: 3.0756 (3.1451) grad_norm: 1.8541 (1.8129) time: 0.5126 [2021-03-26 13:47:38 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 870/1251] eta: 0:03:14 lr: 0.000315 loss: 2.8993 (3.1422) grad_norm: 1.8358 (1.8127) time: 0.5045 [2021-03-26 13:47:43 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 880/1251] eta: 0:03:09 lr: 0.000315 loss: 2.8993 (3.1427) grad_norm: 1.7504 (1.8123) time: 0.5065 [2021-03-26 13:47:48 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 890/1251] eta: 0:03:04 lr: 0.000315 loss: 2.8082 (3.1377) grad_norm: 1.7214 (1.8106) time: 0.5021 [2021-03-26 13:47:53 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 900/1251] eta: 0:02:59 lr: 0.000315 loss: 2.6705 (3.1355) grad_norm: 1.7214 (1.8106) time: 0.5005 [2021-03-26 13:47:58 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 910/1251] eta: 0:02:54 lr: 0.000314 loss: 3.0554 (3.1341) grad_norm: 1.7616 (1.8107) time: 0.5060 [2021-03-26 13:48:03 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 920/1251] eta: 0:02:49 lr: 0.000314 loss: 3.1663 (3.1351) grad_norm: 1.7550 (1.8096) time: 0.5101 [2021-03-26 13:48:08 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 930/1251] eta: 0:02:44 lr: 0.000314 loss: 3.2591 (3.1370) grad_norm: 1.7249 (1.8101) time: 0.5100 [2021-03-26 13:48:13 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 940/1251] eta: 0:02:39 lr: 0.000314 loss: 3.2591 (3.1377) grad_norm: 1.7395 (1.8122) time: 0.5089 [2021-03-26 13:48:18 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 950/1251] eta: 0:02:33 lr: 0.000314 loss: 3.0201 (3.1352) grad_norm: 1.9013 (1.8139) time: 0.5065 [2021-03-26 13:48:23 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 960/1251] eta: 0:02:28 lr: 0.000314 loss: 3.2135 (3.1371) grad_norm: 1.8705 (1.8139) time: 0.5029 [2021-03-26 13:48:28 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 970/1251] eta: 0:02:23 lr: 0.000314 loss: 3.3124 (3.1371) grad_norm: 1.7057 (1.8127) time: 0.5040 [2021-03-26 13:48:33 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 980/1251] eta: 0:02:18 lr: 0.000314 loss: 3.3074 (3.1387) grad_norm: 1.6986 (1.8126) time: 0.5058 [2021-03-26 13:48:39 swin_small_patch4_window7_224] INFO: Epoch: [187] [ 990/1251] eta: 0:02:13 lr: 0.000314 loss: 3.2796 (3.1402) grad_norm: 1.6707 (1.8113) time: 0.5089 [2021-03-26 13:48:44 swin_small_patch4_window7_224] INFO: Epoch: [187] [1000/1251] eta: 0:02:08 lr: 0.000314 loss: 3.3566 (3.1422) grad_norm: 1.6527 (1.8102) time: 0.5049 [2021-03-26 13:48:49 swin_small_patch4_window7_224] INFO: Epoch: [187] [1010/1251] eta: 0:02:03 lr: 0.000314 loss: 3.2532 (3.1413) grad_norm: 1.7012 (1.8107) time: 0.5018 [2021-03-26 13:48:54 swin_small_patch4_window7_224] INFO: Epoch: [187] [1020/1251] eta: 0:01:58 lr: 0.000314 loss: 3.1974 (3.1409) grad_norm: 1.8096 (1.8102) time: 0.5046 [2021-03-26 13:48:59 swin_small_patch4_window7_224] INFO: Epoch: [187] [1030/1251] eta: 0:01:52 lr: 0.000314 loss: 3.1974 (3.1418) grad_norm: 1.7589 (1.8105) time: 0.5009 [2021-03-26 13:49:04 swin_small_patch4_window7_224] INFO: Epoch: [187] [1040/1251] eta: 0:01:47 lr: 0.000314 loss: 3.0481 (3.1399) grad_norm: 1.7711 (1.8109) time: 0.5071 [2021-03-26 13:49:09 swin_small_patch4_window7_224] INFO: Epoch: [187] [1050/1251] eta: 0:01:42 lr: 0.000314 loss: 3.0123 (3.1392) grad_norm: 1.8481 (1.8115) time: 0.5153 [2021-03-26 13:49:14 swin_small_patch4_window7_224] INFO: Epoch: [187] [1060/1251] eta: 0:01:37 lr: 0.000314 loss: 3.2856 (3.1399) grad_norm: 1.6525 (1.8094) time: 0.5069 [2021-03-26 13:49:19 swin_small_patch4_window7_224] INFO: Epoch: [187] [1070/1251] eta: 0:01:32 lr: 0.000314 loss: 3.0298 (3.1376) grad_norm: 1.5936 (1.8080) time: 0.4978 [2021-03-26 13:49:24 swin_small_patch4_window7_224] INFO: Epoch: [187] [1080/1251] eta: 0:01:27 lr: 0.000314 loss: 3.1152 (3.1376) grad_norm: 1.6807 (1.8072) time: 0.4982 [2021-03-26 13:49:29 swin_small_patch4_window7_224] INFO: Epoch: [187] [1090/1251] eta: 0:01:22 lr: 0.000314 loss: 3.2507 (3.1383) grad_norm: 1.6448 (1.8061) time: 0.5040 [2021-03-26 13:49:34 swin_small_patch4_window7_224] INFO: Epoch: [187] [1100/1251] eta: 0:01:17 lr: 0.000314 loss: 3.1354 (3.1384) grad_norm: 1.6348 (1.8053) time: 0.5043 [2021-03-26 13:49:39 swin_small_patch4_window7_224] INFO: Epoch: [187] [1110/1251] eta: 0:01:11 lr: 0.000314 loss: 3.1203 (3.1383) grad_norm: 1.7814 (1.8061) time: 0.5021 [2021-03-26 13:49:44 swin_small_patch4_window7_224] INFO: Epoch: [187] [1120/1251] eta: 0:01:06 lr: 0.000314 loss: 3.2165 (3.1395) grad_norm: 1.8704 (1.8077) time: 0.4980 [2021-03-26 13:49:49 swin_small_patch4_window7_224] INFO: Epoch: [187] [1130/1251] eta: 0:01:01 lr: 0.000314 loss: 3.3626 (3.1404) grad_norm: 1.8395 (1.8076) time: 0.5000 [2021-03-26 13:49:54 swin_small_patch4_window7_224] INFO: Epoch: [187] [1140/1251] eta: 0:00:56 lr: 0.000314 loss: 3.2996 (3.1412) grad_norm: 1.7769 (1.8074) time: 0.5027 [2021-03-26 13:49:59 swin_small_patch4_window7_224] INFO: Epoch: [187] [1150/1251] eta: 0:00:51 lr: 0.000314 loss: 3.1873 (3.1400) grad_norm: 1.7489 (1.8071) time: 0.5013 [2021-03-26 13:50:04 swin_small_patch4_window7_224] INFO: Epoch: [187] [1160/1251] eta: 0:00:46 lr: 0.000314 loss: 3.3040 (3.1412) grad_norm: 1.7558 (1.8066) time: 0.4992 [2021-03-26 13:50:09 swin_small_patch4_window7_224] INFO: Epoch: [187] [1170/1251] eta: 0:00:41 lr: 0.000313 loss: 3.3040 (3.1403) grad_norm: 1.7558 (1.8063) time: 0.4998 [2021-03-26 13:50:14 swin_small_patch4_window7_224] INFO: Epoch: [187] [1180/1251] eta: 0:00:36 lr: 0.000313 loss: 3.2010 (3.1409) grad_norm: 1.6289 (1.8047) time: 0.5051 [2021-03-26 13:50:19 swin_small_patch4_window7_224] INFO: Epoch: [187] [1190/1251] eta: 0:00:31 lr: 0.000313 loss: 3.4355 (3.1426) grad_norm: 1.7181 (1.8055) time: 0.5014 [2021-03-26 13:50:24 swin_small_patch4_window7_224] INFO: Epoch: [187] [1200/1251] eta: 0:00:25 lr: 0.000313 loss: 3.4355 (3.1443) grad_norm: 1.7679 (1.8047) time: 0.4994 [2021-03-26 13:50:29 swin_small_patch4_window7_224] INFO: Epoch: [187] [1210/1251] eta: 0:00:20 lr: 0.000313 loss: 3.3025 (3.1456) grad_norm: 1.6734 (1.8049) time: 0.5022 [2021-03-26 13:50:34 swin_small_patch4_window7_224] INFO: Epoch: [187] [1220/1251] eta: 0:00:15 lr: 0.000313 loss: 3.1943 (3.1452) grad_norm: 1.7284 (1.8047) time: 0.5034 [2021-03-26 13:50:39 swin_small_patch4_window7_224] INFO: Epoch: [187] [1230/1251] eta: 0:00:10 lr: 0.000313 loss: 3.1538 (3.1449) grad_norm: 1.7259 (1.8046) time: 0.5064 [2021-03-26 13:50:44 swin_small_patch4_window7_224] INFO: Epoch: [187] [1240/1251] eta: 0:00:05 lr: 0.000313 loss: 3.0322 (3.1427) grad_norm: 1.7053 (1.8059) time: 0.5070 [2021-03-26 13:50:49 swin_small_patch4_window7_224] INFO: Epoch: [187] [1250/1251] eta: 0:00:00 lr: 0.000313 loss: 3.1983 (3.1422) grad_norm: 1.7068 (1.8056) time: 0.5071 [2021-03-26 13:50:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 0.5672 (0.5672) acc1: 84.3750 (84.3750) acc5: 100.0000 (100.0000) [2021-03-26 13:51:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8226 (0.7847) acc1: 81.2500 (80.3977) acc5: 95.3125 (95.3125) [2021-03-26 13:51:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8226 (0.8007) acc1: 78.1250 (79.5387) acc5: 95.3125 (95.5357) [2021-03-26 13:51:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8692 (0.8339) acc1: 76.5625 (78.6290) acc5: 95.3125 (95.3629) [2021-03-26 13:51:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9094 (0.8497) acc1: 75.0000 (78.5823) acc5: 93.7500 (95.0457) [2021-03-26 13:51:07 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8345 (0.8376) acc1: 79.6875 (79.0080) acc5: 95.3125 (95.2960) [2021-03-26 13:51:18 swin_small_patch4_window7_224] INFO: * Acc@1 80.074 Acc@5 95.246 loss 0.828 [2021-03-26 13:51:18 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-26 13:51:18 swin_small_patch4_window7_224] INFO: Max accuracy: 80.07% [2021-03-26 13:51:22 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 0/1251] eta: 1:25:38 lr: 0.000313 loss: 2.8462 (2.8462) grad_norm: 1.6126 (1.6126) time: 4.1073 [2021-03-26 13:51:27 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 10/1251] eta: 0:17:45 lr: 0.000313 loss: 3.4792 (3.2833) grad_norm: 1.6612 (1.6648) time: 0.8585 [2021-03-26 13:51:32 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 20/1251] eta: 0:14:10 lr: 0.000313 loss: 3.3753 (3.1486) grad_norm: 1.6612 (1.6905) time: 0.5200 [2021-03-26 13:51:37 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 30/1251] eta: 0:12:52 lr: 0.000313 loss: 3.2487 (3.1558) grad_norm: 1.6977 (1.7280) time: 0.5083 [2021-03-26 13:51:43 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 40/1251] eta: 0:12:15 lr: 0.000313 loss: 3.1246 (3.1180) grad_norm: 1.7838 (1.7458) time: 0.5203 [2021-03-26 13:51:48 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 50/1251] eta: 0:11:46 lr: 0.000313 loss: 3.1794 (3.1743) grad_norm: 1.7267 (1.7370) time: 0.5196 [2021-03-26 13:51:53 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 60/1251] eta: 0:11:24 lr: 0.000313 loss: 3.2196 (3.1633) grad_norm: 1.7288 (1.7606) time: 0.5063 [2021-03-26 13:51:58 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 70/1251] eta: 0:11:06 lr: 0.000313 loss: 3.0239 (3.1416) grad_norm: 1.7398 (1.7649) time: 0.5037 [2021-03-26 13:52:03 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 80/1251] eta: 0:10:54 lr: 0.000313 loss: 3.0238 (3.1253) grad_norm: 1.6910 (1.7587) time: 0.5112 [2021-03-26 13:52:08 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 90/1251] eta: 0:10:41 lr: 0.000313 loss: 3.1252 (3.1256) grad_norm: 1.6624 (1.7601) time: 0.5099 [2021-03-26 13:52:13 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 100/1251] eta: 0:10:30 lr: 0.000313 loss: 3.2096 (3.1231) grad_norm: 1.6723 (1.7655) time: 0.5040 [2021-03-26 13:52:18 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 110/1251] eta: 0:10:21 lr: 0.000313 loss: 3.2920 (3.1382) grad_norm: 1.6809 (1.7614) time: 0.5071 [2021-03-26 13:52:23 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 120/1251] eta: 0:10:11 lr: 0.000313 loss: 3.0956 (3.1250) grad_norm: 1.7615 (1.7837) time: 0.5054 [2021-03-26 13:52:28 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 130/1251] eta: 0:10:03 lr: 0.000313 loss: 3.0716 (3.1378) grad_norm: 1.8182 (1.7831) time: 0.5057 [2021-03-26 13:52:33 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 140/1251] eta: 0:09:55 lr: 0.000313 loss: 3.3240 (3.1378) grad_norm: 1.7575 (1.7806) time: 0.5054 [2021-03-26 13:52:38 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 150/1251] eta: 0:09:47 lr: 0.000313 loss: 3.3880 (3.1502) grad_norm: 1.7450 (1.7822) time: 0.5028 [2021-03-26 13:52:43 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 160/1251] eta: 0:09:40 lr: 0.000313 loss: 3.1711 (3.1380) grad_norm: 1.7450 (1.7818) time: 0.5049 [2021-03-26 13:52:48 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 170/1251] eta: 0:09:32 lr: 0.000313 loss: 3.3075 (3.1580) grad_norm: 1.7544 (1.7856) time: 0.5012 [2021-03-26 13:52:54 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 180/1251] eta: 0:09:26 lr: 0.000312 loss: 3.4435 (3.1605) grad_norm: 1.8041 (1.7875) time: 0.5015 [2021-03-26 13:52:58 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 190/1251] eta: 0:09:19 lr: 0.000312 loss: 3.0841 (3.1526) grad_norm: 1.7673 (1.7894) time: 0.5011 [2021-03-26 13:53:03 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 200/1251] eta: 0:09:12 lr: 0.000312 loss: 3.0729 (3.1526) grad_norm: 1.6807 (1.7835) time: 0.4982 [2021-03-26 13:53:08 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 210/1251] eta: 0:09:05 lr: 0.000312 loss: 3.1401 (3.1507) grad_norm: 1.6610 (1.7788) time: 0.5005 [2021-03-26 13:53:13 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 220/1251] eta: 0:08:59 lr: 0.000312 loss: 3.1591 (3.1575) grad_norm: 1.7143 (1.7772) time: 0.4983 [2021-03-26 13:53:19 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 230/1251] eta: 0:08:53 lr: 0.000312 loss: 3.2542 (3.1538) grad_norm: 1.7835 (1.7789) time: 0.5028 [2021-03-26 13:53:24 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 240/1251] eta: 0:08:47 lr: 0.000312 loss: 3.2542 (3.1574) grad_norm: 1.8123 (1.7864) time: 0.5114 [2021-03-26 13:53:29 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 250/1251] eta: 0:08:42 lr: 0.000312 loss: 3.3050 (3.1563) grad_norm: 1.8053 (1.7856) time: 0.5100 [2021-03-26 13:53:34 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 260/1251] eta: 0:08:35 lr: 0.000312 loss: 3.1240 (3.1542) grad_norm: 1.7464 (1.7895) time: 0.5015 [2021-03-26 13:53:39 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 270/1251] eta: 0:08:29 lr: 0.000312 loss: 2.9316 (3.1433) grad_norm: 1.7958 (1.7929) time: 0.4974 [2021-03-26 13:53:44 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 280/1251] eta: 0:08:23 lr: 0.000312 loss: 3.0201 (3.1416) grad_norm: 1.7821 (1.7889) time: 0.4960 [2021-03-26 13:53:49 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 290/1251] eta: 0:08:17 lr: 0.000312 loss: 3.0201 (3.1388) grad_norm: 1.8119 (1.7905) time: 0.4967 [2021-03-26 13:53:54 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 300/1251] eta: 0:08:12 lr: 0.000312 loss: 3.3307 (3.1481) grad_norm: 1.8180 (1.7884) time: 0.5002 [2021-03-26 13:53:59 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 310/1251] eta: 0:08:06 lr: 0.000312 loss: 3.3182 (3.1467) grad_norm: 1.7725 (1.7903) time: 0.4994 [2021-03-26 13:54:04 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 320/1251] eta: 0:08:01 lr: 0.000312 loss: 3.2209 (3.1428) grad_norm: 1.8380 (1.7910) time: 0.5053 [2021-03-26 13:54:09 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 330/1251] eta: 0:07:55 lr: 0.000312 loss: 3.2681 (3.1482) grad_norm: 1.7551 (1.7906) time: 0.5034 [2021-03-26 13:54:14 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 340/1251] eta: 0:07:49 lr: 0.000312 loss: 3.3148 (3.1483) grad_norm: 1.7290 (1.7920) time: 0.4945 [2021-03-26 13:54:19 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 350/1251] eta: 0:07:44 lr: 0.000312 loss: 3.2692 (3.1462) grad_norm: 1.7910 (1.7930) time: 0.4978 [2021-03-26 13:54:24 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 360/1251] eta: 0:07:38 lr: 0.000312 loss: 3.2853 (3.1491) grad_norm: 1.7830 (1.7988) time: 0.5009 [2021-03-26 13:54:29 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 370/1251] eta: 0:07:33 lr: 0.000312 loss: 3.3170 (3.1547) grad_norm: 1.7920 (1.8007) time: 0.4994 [2021-03-26 13:54:34 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 380/1251] eta: 0:07:27 lr: 0.000312 loss: 3.4281 (3.1585) grad_norm: 1.7869 (1.8008) time: 0.5017 [2021-03-26 13:54:39 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 390/1251] eta: 0:07:22 lr: 0.000312 loss: 3.3410 (3.1563) grad_norm: 1.7904 (1.8022) time: 0.5095 [2021-03-26 13:54:44 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 400/1251] eta: 0:07:17 lr: 0.000312 loss: 3.4106 (3.1663) grad_norm: 1.7540 (1.8009) time: 0.5084 [2021-03-26 13:54:49 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 410/1251] eta: 0:07:11 lr: 0.000312 loss: 3.5183 (3.1688) grad_norm: 1.7125 (1.7999) time: 0.4998 [2021-03-26 13:54:54 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 420/1251] eta: 0:07:06 lr: 0.000312 loss: 3.2617 (3.1714) grad_norm: 1.6923 (1.7992) time: 0.5028 [2021-03-26 13:54:59 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 430/1251] eta: 0:07:01 lr: 0.000312 loss: 3.3580 (3.1729) grad_norm: 1.6628 (1.7967) time: 0.5064 [2021-03-26 13:55:04 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 440/1251] eta: 0:06:55 lr: 0.000312 loss: 3.3745 (3.1755) grad_norm: 1.7362 (1.7997) time: 0.4979 [2021-03-26 13:55:09 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 450/1251] eta: 0:06:50 lr: 0.000311 loss: 3.2151 (3.1755) grad_norm: 1.7362 (1.7978) time: 0.4987 [2021-03-26 13:55:14 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 460/1251] eta: 0:06:44 lr: 0.000311 loss: 3.1627 (3.1735) grad_norm: 1.7410 (nan) time: 0.4986 [2021-03-26 13:55:19 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 470/1251] eta: 0:06:39 lr: 0.000311 loss: 2.9842 (3.1691) grad_norm: 1.7476 (nan) time: 0.4964 [2021-03-26 13:55:24 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 480/1251] eta: 0:06:34 lr: 0.000311 loss: 2.9842 (3.1619) grad_norm: 1.6892 (nan) time: 0.5022 [2021-03-26 13:55:29 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 490/1251] eta: 0:06:29 lr: 0.000311 loss: 3.0590 (3.1657) grad_norm: 1.7123 (nan) time: 0.5008 [2021-03-26 13:55:34 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 500/1251] eta: 0:06:23 lr: 0.000311 loss: 3.1825 (3.1640) grad_norm: 1.7899 (nan) time: 0.4981 [2021-03-26 13:55:39 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 510/1251] eta: 0:06:18 lr: 0.000311 loss: 3.0196 (3.1611) grad_norm: 1.7642 (nan) time: 0.4981 [2021-03-26 13:55:44 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 520/1251] eta: 0:06:13 lr: 0.000311 loss: 3.0196 (3.1596) grad_norm: 1.6613 (nan) time: 0.5040 [2021-03-26 13:55:49 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 530/1251] eta: 0:06:07 lr: 0.000311 loss: 3.1539 (3.1604) grad_norm: 1.6658 (nan) time: 0.5019 [2021-03-26 13:55:54 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 540/1251] eta: 0:06:02 lr: 0.000311 loss: 3.2848 (3.1605) grad_norm: 1.7857 (nan) time: 0.5012 [2021-03-26 13:55:59 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 550/1251] eta: 0:05:57 lr: 0.000311 loss: 3.0128 (3.1586) grad_norm: 1.7738 (nan) time: 0.5186 [2021-03-26 13:56:04 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 560/1251] eta: 0:05:52 lr: 0.000311 loss: 3.0128 (3.1582) grad_norm: 1.6594 (nan) time: 0.5179 [2021-03-26 13:56:09 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 570/1251] eta: 0:05:47 lr: 0.000311 loss: 3.1605 (3.1549) grad_norm: 1.6594 (nan) time: 0.5007 [2021-03-26 13:56:14 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 580/1251] eta: 0:05:42 lr: 0.000311 loss: 3.0684 (3.1558) grad_norm: 1.7819 (nan) time: 0.5049 [2021-03-26 13:56:20 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 590/1251] eta: 0:05:37 lr: 0.000311 loss: 3.1666 (3.1556) grad_norm: 1.7474 (nan) time: 0.5111 [2021-03-26 13:56:25 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 600/1251] eta: 0:05:32 lr: 0.000311 loss: 3.0366 (3.1515) grad_norm: 1.7474 (nan) time: 0.5056 [2021-03-26 13:56:30 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 610/1251] eta: 0:05:26 lr: 0.000311 loss: 3.0014 (3.1477) grad_norm: 1.8026 (nan) time: 0.5017 [2021-03-26 13:56:35 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 620/1251] eta: 0:05:21 lr: 0.000311 loss: 3.0020 (3.1461) grad_norm: 1.7067 (nan) time: 0.5016 [2021-03-26 13:56:40 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 630/1251] eta: 0:05:16 lr: 0.000311 loss: 3.0546 (3.1464) grad_norm: 1.7008 (nan) time: 0.5048 [2021-03-26 13:56:45 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 640/1251] eta: 0:05:11 lr: 0.000311 loss: 3.1005 (3.1470) grad_norm: 1.6991 (nan) time: 0.5039 [2021-03-26 13:56:50 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 650/1251] eta: 0:05:06 lr: 0.000311 loss: 3.2594 (3.1493) grad_norm: 1.6774 (nan) time: 0.4975 [2021-03-26 13:56:55 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 660/1251] eta: 0:05:01 lr: 0.000311 loss: 3.3404 (3.1533) grad_norm: 1.6959 (nan) time: 0.4982 [2021-03-26 13:57:00 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 670/1251] eta: 0:04:55 lr: 0.000311 loss: 3.1841 (3.1513) grad_norm: 1.7895 (nan) time: 0.5066 [2021-03-26 13:57:05 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 680/1251] eta: 0:04:50 lr: 0.000311 loss: 2.9147 (3.1504) grad_norm: 1.7895 (nan) time: 0.5036 [2021-03-26 13:57:10 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 690/1251] eta: 0:04:45 lr: 0.000311 loss: 3.2500 (3.1523) grad_norm: 1.8533 (nan) time: 0.4970 [2021-03-26 13:57:15 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 700/1251] eta: 0:04:40 lr: 0.000311 loss: 3.2729 (3.1526) grad_norm: 1.9742 (nan) time: 0.5060 [2021-03-26 13:57:20 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 710/1251] eta: 0:04:35 lr: 0.000310 loss: 3.2493 (3.1543) grad_norm: 1.9091 (nan) time: 0.5153 [2021-03-26 13:57:25 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 720/1251] eta: 0:04:30 lr: 0.000310 loss: 3.2063 (3.1529) grad_norm: 1.7990 (nan) time: 0.5071 [2021-03-26 13:57:30 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 730/1251] eta: 0:04:25 lr: 0.000310 loss: 3.1571 (3.1522) grad_norm: 1.7990 (nan) time: 0.5034 [2021-03-26 13:57:35 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 740/1251] eta: 0:04:20 lr: 0.000310 loss: 3.3291 (3.1521) grad_norm: 1.7648 (nan) time: 0.5142 [2021-03-26 13:57:40 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 750/1251] eta: 0:04:15 lr: 0.000310 loss: 3.3737 (3.1543) grad_norm: 1.8775 (nan) time: 0.5088 [2021-03-26 13:57:45 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 760/1251] eta: 0:04:09 lr: 0.000310 loss: 3.2382 (3.1518) grad_norm: 1.8824 (nan) time: 0.4974 [2021-03-26 13:57:50 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 770/1251] eta: 0:04:04 lr: 0.000310 loss: 3.2881 (3.1530) grad_norm: 1.8166 (nan) time: 0.5037 [2021-03-26 13:57:56 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 780/1251] eta: 0:03:59 lr: 0.000310 loss: 3.2400 (3.1531) grad_norm: 1.7934 (nan) time: 0.5123 [2021-03-26 13:58:01 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 790/1251] eta: 0:03:54 lr: 0.000310 loss: 3.2948 (3.1557) grad_norm: 1.7861 (nan) time: 0.5176 [2021-03-26 13:58:06 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 800/1251] eta: 0:03:49 lr: 0.000310 loss: 3.3462 (3.1553) grad_norm: 1.7629 (nan) time: 0.5142 [2021-03-26 13:58:11 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 810/1251] eta: 0:03:44 lr: 0.000310 loss: 3.1361 (3.1562) grad_norm: 1.7634 (nan) time: 0.5014 [2021-03-26 13:58:16 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 820/1251] eta: 0:03:39 lr: 0.000310 loss: 3.3272 (3.1557) grad_norm: 1.7634 (nan) time: 0.4962 [2021-03-26 13:58:21 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 830/1251] eta: 0:03:34 lr: 0.000310 loss: 3.0338 (3.1533) grad_norm: 1.7803 (nan) time: 0.5059 [2021-03-26 13:58:26 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 840/1251] eta: 0:03:29 lr: 0.000310 loss: 3.1730 (3.1553) grad_norm: 1.7829 (nan) time: 0.5090 [2021-03-26 13:58:31 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 850/1251] eta: 0:03:24 lr: 0.000310 loss: 3.1753 (3.1552) grad_norm: 1.7648 (nan) time: 0.5093 [2021-03-26 13:58:36 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 860/1251] eta: 0:03:18 lr: 0.000310 loss: 3.0815 (3.1552) grad_norm: 1.7636 (nan) time: 0.5073 [2021-03-26 13:58:41 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 870/1251] eta: 0:03:13 lr: 0.000310 loss: 3.2909 (3.1550) grad_norm: 1.7521 (nan) time: 0.5022 [2021-03-26 13:58:46 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 880/1251] eta: 0:03:08 lr: 0.000310 loss: 3.2825 (3.1548) grad_norm: 1.7521 (nan) time: 0.5034 [2021-03-26 13:58:51 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 890/1251] eta: 0:03:03 lr: 0.000310 loss: 3.1166 (3.1530) grad_norm: 1.9261 (nan) time: 0.5048 [2021-03-26 13:58:56 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 900/1251] eta: 0:02:58 lr: 0.000310 loss: 3.2788 (3.1547) grad_norm: 1.8012 (nan) time: 0.5050 [2021-03-26 13:59:01 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 910/1251] eta: 0:02:53 lr: 0.000310 loss: 3.3365 (3.1563) grad_norm: 1.8012 (nan) time: 0.5028 [2021-03-26 13:59:06 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 920/1251] eta: 0:02:48 lr: 0.000310 loss: 3.2307 (3.1545) grad_norm: 1.8678 (nan) time: 0.5022 [2021-03-26 13:59:11 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 930/1251] eta: 0:02:43 lr: 0.000310 loss: 3.1175 (3.1541) grad_norm: 1.7902 (nan) time: 0.5054 [2021-03-26 13:59:16 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 940/1251] eta: 0:02:38 lr: 0.000310 loss: 3.2257 (3.1547) grad_norm: 1.7902 (nan) time: 0.5039 [2021-03-26 13:59:21 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 950/1251] eta: 0:02:32 lr: 0.000310 loss: 3.1843 (3.1524) grad_norm: 1.7679 (nan) time: 0.4984 [2021-03-26 13:59:26 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 960/1251] eta: 0:02:27 lr: 0.000310 loss: 3.1043 (3.1517) grad_norm: 1.7679 (nan) time: 0.4995 [2021-03-26 13:59:31 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 970/1251] eta: 0:02:22 lr: 0.000309 loss: 3.2005 (3.1521) grad_norm: 1.7498 (nan) time: 0.5052 [2021-03-26 13:59:36 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 980/1251] eta: 0:02:17 lr: 0.000309 loss: 3.1121 (3.1503) grad_norm: 1.7408 (nan) time: 0.5002 [2021-03-26 13:59:41 swin_small_patch4_window7_224] INFO: Epoch: [188] [ 990/1251] eta: 0:02:12 lr: 0.000309 loss: 3.0307 (3.1493) grad_norm: 1.7222 (nan) time: 0.4965 [2021-03-26 13:59:46 swin_small_patch4_window7_224] INFO: Epoch: [188] [1000/1251] eta: 0:02:07 lr: 0.000309 loss: 3.2520 (3.1508) grad_norm: 1.7063 (nan) time: 0.5032 [2021-03-26 13:59:51 swin_small_patch4_window7_224] INFO: Epoch: [188] [1010/1251] eta: 0:02:02 lr: 0.000309 loss: 3.3329 (3.1515) grad_norm: 1.7553 (nan) time: 0.5034 [2021-03-26 13:59:56 swin_small_patch4_window7_224] INFO: Epoch: [188] [1020/1251] eta: 0:01:57 lr: 0.000309 loss: 3.1813 (3.1488) grad_norm: 1.8157 (nan) time: 0.4976 [2021-03-26 14:00:01 swin_small_patch4_window7_224] INFO: Epoch: [188] [1030/1251] eta: 0:01:52 lr: 0.000309 loss: 3.0764 (3.1487) grad_norm: 1.7438 (nan) time: 0.5006 [2021-03-26 14:00:06 swin_small_patch4_window7_224] INFO: Epoch: [188] [1040/1251] eta: 0:01:47 lr: 0.000309 loss: 3.2046 (3.1470) grad_norm: 1.7229 (nan) time: 0.5024 [2021-03-26 14:00:12 swin_small_patch4_window7_224] INFO: Epoch: [188] [1050/1251] eta: 0:01:42 lr: 0.000309 loss: 3.2180 (3.1470) grad_norm: 1.7666 (nan) time: 0.5066 [2021-03-26 14:00:17 swin_small_patch4_window7_224] INFO: Epoch: [188] [1060/1251] eta: 0:01:36 lr: 0.000309 loss: 3.1939 (3.1455) grad_norm: 1.7465 (nan) time: 0.5116 [2021-03-26 14:00:22 swin_small_patch4_window7_224] INFO: Epoch: [188] [1070/1251] eta: 0:01:31 lr: 0.000309 loss: 3.1939 (3.1457) grad_norm: 1.7351 (nan) time: 0.5076 [2021-03-26 14:00:27 swin_small_patch4_window7_224] INFO: Epoch: [188] [1080/1251] eta: 0:01:26 lr: 0.000309 loss: 3.3282 (3.1480) grad_norm: 1.7850 (nan) time: 0.5090 [2021-03-26 14:00:32 swin_small_patch4_window7_224] INFO: Epoch: [188] [1090/1251] eta: 0:01:21 lr: 0.000309 loss: 3.3021 (3.1470) grad_norm: 1.7994 (nan) time: 0.5048 [2021-03-26 14:00:37 swin_small_patch4_window7_224] INFO: Epoch: [188] [1100/1251] eta: 0:01:16 lr: 0.000309 loss: 3.2813 (3.1467) grad_norm: 1.7159 (nan) time: 0.4959 [2021-03-26 14:00:42 swin_small_patch4_window7_224] INFO: Epoch: [188] [1110/1251] eta: 0:01:11 lr: 0.000309 loss: 3.1986 (3.1456) grad_norm: 1.7453 (nan) time: 0.4960 [2021-03-26 14:00:47 swin_small_patch4_window7_224] INFO: Epoch: [188] [1120/1251] eta: 0:01:06 lr: 0.000309 loss: 3.3585 (3.1479) grad_norm: 1.7561 (nan) time: 0.5004 [2021-03-26 14:00:52 swin_small_patch4_window7_224] INFO: Epoch: [188] [1130/1251] eta: 0:01:01 lr: 0.000309 loss: 3.4516 (3.1488) grad_norm: 1.8523 (nan) time: 0.5083 [2021-03-26 14:00:57 swin_small_patch4_window7_224] INFO: Epoch: [188] [1140/1251] eta: 0:00:56 lr: 0.000309 loss: 3.2125 (3.1472) grad_norm: 1.8523 (nan) time: 0.5037 [2021-03-26 14:01:02 swin_small_patch4_window7_224] INFO: Epoch: [188] [1150/1251] eta: 0:00:51 lr: 0.000309 loss: 3.1916 (3.1472) grad_norm: 1.8462 (nan) time: 0.4948 [2021-03-26 14:01:07 swin_small_patch4_window7_224] INFO: Epoch: [188] [1160/1251] eta: 0:00:46 lr: 0.000309 loss: 3.2703 (3.1482) grad_norm: 1.8063 (nan) time: 0.4976 [2021-03-26 14:01:12 swin_small_patch4_window7_224] INFO: Epoch: [188] [1170/1251] eta: 0:00:41 lr: 0.000309 loss: 3.3550 (3.1483) grad_norm: 1.7649 (nan) time: 0.5014 [2021-03-26 14:01:17 swin_small_patch4_window7_224] INFO: Epoch: [188] [1180/1251] eta: 0:00:36 lr: 0.000309 loss: 3.2273 (3.1488) grad_norm: 1.8020 (nan) time: 0.5052 [2021-03-26 14:01:22 swin_small_patch4_window7_224] INFO: Epoch: [188] [1190/1251] eta: 0:00:30 lr: 0.000309 loss: 3.2273 (3.1485) grad_norm: 1.8090 (nan) time: 0.5048 [2021-03-26 14:01:27 swin_small_patch4_window7_224] INFO: Epoch: [188] [1200/1251] eta: 0:00:25 lr: 0.000309 loss: 3.1220 (3.1489) grad_norm: 1.7490 (nan) time: 0.5034 [2021-03-26 14:01:32 swin_small_patch4_window7_224] INFO: Epoch: [188] [1210/1251] eta: 0:00:20 lr: 0.000309 loss: 3.2524 (3.1500) grad_norm: 1.8698 (nan) time: 0.5036 [2021-03-26 14:01:37 swin_small_patch4_window7_224] INFO: Epoch: [188] [1220/1251] eta: 0:00:15 lr: 0.000309 loss: 3.2537 (3.1517) grad_norm: 1.8698 (nan) time: 0.5048 [2021-03-26 14:01:42 swin_small_patch4_window7_224] INFO: Epoch: [188] [1230/1251] eta: 0:00:10 lr: 0.000308 loss: 3.2927 (3.1503) grad_norm: 1.8095 (nan) time: 0.5036 [2021-03-26 14:01:47 swin_small_patch4_window7_224] INFO: Epoch: [188] [1240/1251] eta: 0:00:05 lr: 0.000308 loss: 3.2927 (3.1506) grad_norm: 1.8095 (nan) time: 0.5041 [2021-03-26 14:01:52 swin_small_patch4_window7_224] INFO: Epoch: [188] [1250/1251] eta: 0:00:00 lr: 0.000308 loss: 3.2899 (3.1512) grad_norm: 1.7478 (nan) time: 0.5023 [2021-03-26 14:02:02 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:50 loss: 0.8040 (0.8040) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-26 14:02:05 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8069 (0.8536) acc1: 78.1250 (78.4091) acc5: 95.3125 (95.5966) [2021-03-26 14:02:08 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.8094 (0.8602) acc1: 79.6875 (78.4226) acc5: 95.3125 (95.9077) [2021-03-26 14:02:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8581 (0.8564) acc1: 79.6875 (79.4355) acc5: 95.3125 (95.9173) [2021-03-26 14:02:12 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8739 (0.8608) acc1: 79.6875 (79.2683) acc5: 95.3125 (95.6555) [2021-03-26 14:02:13 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8446 (0.8557) acc1: 79.6875 (79.3280) acc5: 95.3125 (95.5200) [2021-03-26 14:02:22 swin_small_patch4_window7_224] INFO: * Acc@1 79.928 Acc@5 95.258 loss 0.845 [2021-03-26 14:02:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 79.9% [2021-03-26 14:02:22 swin_small_patch4_window7_224] INFO: Max accuracy: 80.07% [2021-03-26 14:02:27 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 0/1251] eta: 1:38:59 lr: 0.000308 loss: 2.8288 (2.8288) grad_norm: 1.5205 (1.5205) time: 4.7476 [2021-03-26 14:02:32 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 10/1251] eta: 0:18:28 lr: 0.000308 loss: 3.4268 (3.3449) grad_norm: 1.7141 (1.7494) time: 0.8932 [2021-03-26 14:02:37 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 20/1251] eta: 0:14:26 lr: 0.000308 loss: 3.4268 (3.3493) grad_norm: 1.7864 (2.0375) time: 0.5013 [2021-03-26 14:02:42 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 30/1251] eta: 0:13:02 lr: 0.000308 loss: 3.1703 (3.1600) grad_norm: 1.7864 (1.9657) time: 0.5017 [2021-03-26 14:02:47 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 40/1251] eta: 0:12:16 lr: 0.000308 loss: 2.6830 (3.1187) grad_norm: 1.6928 (1.9058) time: 0.5079 [2021-03-26 14:02:52 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 50/1251] eta: 0:11:43 lr: 0.000308 loss: 3.0325 (3.1036) grad_norm: 1.7633 (1.8836) time: 0.5018 [2021-03-26 14:02:57 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 60/1251] eta: 0:11:21 lr: 0.000308 loss: 3.1066 (3.1077) grad_norm: 1.7299 (1.8558) time: 0.4986 [2021-03-26 14:03:02 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 70/1251] eta: 0:11:03 lr: 0.000308 loss: 3.1066 (3.0891) grad_norm: 1.7795 (1.8544) time: 0.4991 [2021-03-26 14:03:07 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 80/1251] eta: 0:10:49 lr: 0.000308 loss: 3.2271 (3.0981) grad_norm: 1.8088 (1.8651) time: 0.4999 [2021-03-26 14:03:12 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 90/1251] eta: 0:10:35 lr: 0.000308 loss: 3.3314 (3.1138) grad_norm: 1.7218 (1.8526) time: 0.4967 [2021-03-26 14:03:17 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 100/1251] eta: 0:10:25 lr: 0.000308 loss: 3.4048 (3.1337) grad_norm: 1.7975 (1.8552) time: 0.4983 [2021-03-26 14:03:22 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 110/1251] eta: 0:10:16 lr: 0.000308 loss: 3.2416 (3.1203) grad_norm: 1.8014 (1.8961) time: 0.5105 [2021-03-26 14:03:27 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 120/1251] eta: 0:10:07 lr: 0.000308 loss: 3.2416 (3.1263) grad_norm: 1.8766 (1.8971) time: 0.5068 [2021-03-26 14:03:32 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 130/1251] eta: 0:10:00 lr: 0.000308 loss: 3.2878 (3.1222) grad_norm: 1.8216 (1.8945) time: 0.5066 [2021-03-26 14:03:37 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 140/1251] eta: 0:09:52 lr: 0.000308 loss: 3.1949 (3.1338) grad_norm: 1.8187 (1.8878) time: 0.5079 [2021-03-26 14:03:43 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 150/1251] eta: 0:09:45 lr: 0.000308 loss: 3.1949 (3.1488) grad_norm: 1.8187 (1.8846) time: 0.5050 [2021-03-26 14:03:48 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 160/1251] eta: 0:09:38 lr: 0.000308 loss: 3.2485 (3.1544) grad_norm: 1.7553 (1.8779) time: 0.5101 [2021-03-26 14:03:53 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 170/1251] eta: 0:09:31 lr: 0.000308 loss: 3.2745 (3.1508) grad_norm: 1.7553 (1.8780) time: 0.5077 [2021-03-26 14:03:58 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 180/1251] eta: 0:09:24 lr: 0.000308 loss: 3.2192 (3.1480) grad_norm: 1.7178 (1.8724) time: 0.5059 [2021-03-26 14:04:03 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 190/1251] eta: 0:09:18 lr: 0.000308 loss: 3.2192 (3.1504) grad_norm: 1.8090 (1.8736) time: 0.5080 [2021-03-26 14:04:08 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 200/1251] eta: 0:09:11 lr: 0.000308 loss: 3.2860 (3.1612) grad_norm: 1.7832 (1.8690) time: 0.5040 [2021-03-26 14:04:13 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 210/1251] eta: 0:09:05 lr: 0.000308 loss: 3.3269 (3.1533) grad_norm: 1.7630 (1.8702) time: 0.4997 [2021-03-26 14:04:18 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 220/1251] eta: 0:08:59 lr: 0.000308 loss: 3.2100 (3.1558) grad_norm: 1.7630 (1.8636) time: 0.5031 [2021-03-26 14:04:23 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 230/1251] eta: 0:08:53 lr: 0.000308 loss: 3.1263 (3.1566) grad_norm: 1.7121 (1.8580) time: 0.5056 [2021-03-26 14:04:28 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 240/1251] eta: 0:08:47 lr: 0.000307 loss: 3.1263 (3.1525) grad_norm: 1.7670 (1.8601) time: 0.5033 [2021-03-26 14:04:33 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 250/1251] eta: 0:08:41 lr: 0.000307 loss: 3.1915 (3.1554) grad_norm: 1.8369 (1.8589) time: 0.4997 [2021-03-26 14:04:38 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 260/1251] eta: 0:08:35 lr: 0.000307 loss: 3.1988 (3.1590) grad_norm: 1.8620 (1.8593) time: 0.5095 [2021-03-26 14:04:43 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 270/1251] eta: 0:08:30 lr: 0.000307 loss: 3.1988 (3.1579) grad_norm: 1.8225 (1.8619) time: 0.5145 [2021-03-26 14:04:48 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 280/1251] eta: 0:08:24 lr: 0.000307 loss: 3.0504 (3.1466) grad_norm: 1.8225 (1.8628) time: 0.5042 [2021-03-26 14:04:53 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 290/1251] eta: 0:08:18 lr: 0.000307 loss: 2.8758 (3.1416) grad_norm: 1.7947 (1.8575) time: 0.5005 [2021-03-26 14:04:58 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 300/1251] eta: 0:08:12 lr: 0.000307 loss: 2.8758 (3.1392) grad_norm: 1.7485 (1.8590) time: 0.4967 [2021-03-26 14:05:03 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 310/1251] eta: 0:08:07 lr: 0.000307 loss: 3.0173 (3.1353) grad_norm: 1.8422 (1.8593) time: 0.5003 [2021-03-26 14:05:08 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 320/1251] eta: 0:08:01 lr: 0.000307 loss: 3.0173 (3.1316) grad_norm: 1.7902 (1.8597) time: 0.5017 [2021-03-26 14:05:13 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 330/1251] eta: 0:07:55 lr: 0.000307 loss: 3.1605 (3.1363) grad_norm: 1.7665 (1.8573) time: 0.5020 [2021-03-26 14:05:18 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 340/1251] eta: 0:07:50 lr: 0.000307 loss: 3.2762 (3.1336) grad_norm: 1.7391 (1.8532) time: 0.5036 [2021-03-26 14:05:23 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 350/1251] eta: 0:07:44 lr: 0.000307 loss: 3.2031 (3.1286) grad_norm: 1.7391 (1.8526) time: 0.5044 [2021-03-26 14:05:28 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 360/1251] eta: 0:07:39 lr: 0.000307 loss: 3.2031 (3.1290) grad_norm: 1.7464 (1.8529) time: 0.5057 [2021-03-26 14:05:33 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 370/1251] eta: 0:07:33 lr: 0.000307 loss: 3.2272 (3.1301) grad_norm: 1.7980 (1.8582) time: 0.5034 [2021-03-26 14:05:38 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 380/1251] eta: 0:07:28 lr: 0.000307 loss: 2.9886 (3.1239) grad_norm: 1.8233 (1.8603) time: 0.5027 [2021-03-26 14:05:44 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 390/1251] eta: 0:07:23 lr: 0.000307 loss: 3.1730 (3.1324) grad_norm: 1.7734 (1.8608) time: 0.5021 [2021-03-26 14:05:49 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 400/1251] eta: 0:07:17 lr: 0.000307 loss: 3.1787 (3.1294) grad_norm: 1.7734 (1.8624) time: 0.5029 [2021-03-26 14:05:53 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 410/1251] eta: 0:07:12 lr: 0.000307 loss: 2.9441 (3.1243) grad_norm: 1.8177 (1.8612) time: 0.4992 [2021-03-26 14:05:59 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 420/1251] eta: 0:07:06 lr: 0.000307 loss: 2.9864 (3.1278) grad_norm: 1.8057 (1.8641) time: 0.5008 [2021-03-26 14:06:04 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 430/1251] eta: 0:07:01 lr: 0.000307 loss: 3.1650 (3.1229) grad_norm: 1.8656 (1.8663) time: 0.5029 [2021-03-26 14:06:09 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 440/1251] eta: 0:06:56 lr: 0.000307 loss: 3.0459 (3.1212) grad_norm: 1.8990 (1.8661) time: 0.5010 [2021-03-26 14:06:14 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 450/1251] eta: 0:06:50 lr: 0.000307 loss: 3.0197 (3.1182) grad_norm: 1.7880 (1.8653) time: 0.5062 [2021-03-26 14:06:19 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 460/1251] eta: 0:06:45 lr: 0.000307 loss: 3.0188 (3.1170) grad_norm: 1.7308 (1.8628) time: 0.5051 [2021-03-26 14:06:24 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 470/1251] eta: 0:06:40 lr: 0.000307 loss: 3.1864 (3.1175) grad_norm: 1.6837 (1.8609) time: 0.5067 [2021-03-26 14:06:29 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 480/1251] eta: 0:06:35 lr: 0.000307 loss: 3.0796 (3.1170) grad_norm: 1.8198 (1.8624) time: 0.5067 [2021-03-26 14:06:34 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 490/1251] eta: 0:06:29 lr: 0.000307 loss: 3.2360 (3.1205) grad_norm: 1.7839 (1.8605) time: 0.4966 [2021-03-26 14:06:39 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 500/1251] eta: 0:06:24 lr: 0.000307 loss: 3.1623 (3.1196) grad_norm: 1.7325 (1.8598) time: 0.4980 [2021-03-26 14:06:44 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 510/1251] eta: 0:06:19 lr: 0.000306 loss: 3.1623 (3.1236) grad_norm: 1.8282 (1.8592) time: 0.5013 [2021-03-26 14:06:49 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 520/1251] eta: 0:06:13 lr: 0.000306 loss: 3.3243 (3.1217) grad_norm: 1.8423 (1.8601) time: 0.5017 [2021-03-26 14:06:54 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 530/1251] eta: 0:06:08 lr: 0.000306 loss: 3.2626 (3.1216) grad_norm: 1.8638 (1.8609) time: 0.5015 [2021-03-26 14:06:59 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 540/1251] eta: 0:06:03 lr: 0.000306 loss: 3.3295 (3.1237) grad_norm: 1.8626 (1.8617) time: 0.5077 [2021-03-26 14:07:04 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 550/1251] eta: 0:05:58 lr: 0.000306 loss: 3.1781 (3.1216) grad_norm: 1.7994 (1.8596) time: 0.5175 [2021-03-26 14:07:09 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 560/1251] eta: 0:05:53 lr: 0.000306 loss: 3.0337 (3.1196) grad_norm: 1.7113 (1.8589) time: 0.5162 [2021-03-26 14:07:14 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 570/1251] eta: 0:05:48 lr: 0.000306 loss: 2.8705 (3.1143) grad_norm: 1.7855 (1.8566) time: 0.5036 [2021-03-26 14:07:19 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 580/1251] eta: 0:05:42 lr: 0.000306 loss: 2.8292 (3.1125) grad_norm: 1.6765 (1.8537) time: 0.4983 [2021-03-26 14:07:24 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 590/1251] eta: 0:05:37 lr: 0.000306 loss: 3.1228 (3.1124) grad_norm: 1.7059 (1.8543) time: 0.5031 [2021-03-26 14:07:29 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 600/1251] eta: 0:05:32 lr: 0.000306 loss: 3.2011 (3.1187) grad_norm: 1.8489 (1.8571) time: 0.4984 [2021-03-26 14:07:34 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 610/1251] eta: 0:05:27 lr: 0.000306 loss: 3.0010 (3.1128) grad_norm: 1.7872 (1.8574) time: 0.4950 [2021-03-26 14:07:39 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 620/1251] eta: 0:05:22 lr: 0.000306 loss: 2.9066 (3.1122) grad_norm: 1.7410 (1.8558) time: 0.5019 [2021-03-26 14:07:44 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 630/1251] eta: 0:05:16 lr: 0.000306 loss: 3.1431 (3.1104) grad_norm: 1.7420 (1.8554) time: 0.5020 [2021-03-26 14:07:49 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 640/1251] eta: 0:05:11 lr: 0.000306 loss: 3.1276 (3.1075) grad_norm: 1.6788 (1.8518) time: 0.5005 [2021-03-26 14:07:54 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 650/1251] eta: 0:05:06 lr: 0.000306 loss: 3.2648 (3.1112) grad_norm: 1.6375 (1.8504) time: 0.5053 [2021-03-26 14:07:59 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 660/1251] eta: 0:05:01 lr: 0.000306 loss: 3.2617 (3.1093) grad_norm: 1.7747 (1.8501) time: 0.5080 [2021-03-26 14:08:05 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 670/1251] eta: 0:04:56 lr: 0.000306 loss: 3.0987 (3.1071) grad_norm: 1.7747 (1.8492) time: 0.5140 [2021-03-26 14:08:10 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 680/1251] eta: 0:04:51 lr: 0.000306 loss: 3.1325 (3.1066) grad_norm: 1.8050 (1.8493) time: 0.5167 [2021-03-26 14:08:15 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 690/1251] eta: 0:04:46 lr: 0.000306 loss: 3.1892 (3.1071) grad_norm: 1.8152 (1.8486) time: 0.5079 [2021-03-26 14:08:20 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 700/1251] eta: 0:04:41 lr: 0.000306 loss: 3.3793 (3.1113) grad_norm: 1.8258 (1.8488) time: 0.5029 [2021-03-26 14:08:25 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 710/1251] eta: 0:04:35 lr: 0.000306 loss: 3.3793 (3.1126) grad_norm: 1.8257 (1.8484) time: 0.5031 [2021-03-26 14:08:30 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 720/1251] eta: 0:04:30 lr: 0.000306 loss: 3.3009 (3.1147) grad_norm: 1.7298 (1.8485) time: 0.5018 [2021-03-26 14:08:35 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 730/1251] eta: 0:04:25 lr: 0.000306 loss: 3.1993 (3.1128) grad_norm: 1.8436 (1.8512) time: 0.5058 [2021-03-26 14:08:40 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 740/1251] eta: 0:04:20 lr: 0.000306 loss: 3.1246 (3.1091) grad_norm: 1.8436 (1.8517) time: 0.5283 [2021-03-26 14:08:46 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 750/1251] eta: 0:04:15 lr: 0.000306 loss: 3.1006 (3.1095) grad_norm: 1.7661 (1.8515) time: 0.5267 [2021-03-26 14:08:51 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 760/1251] eta: 0:04:10 lr: 0.000306 loss: 3.1006 (3.1089) grad_norm: 1.7835 (1.8516) time: 0.5023 [2021-03-26 14:08:56 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 770/1251] eta: 0:04:05 lr: 0.000305 loss: 3.1881 (3.1103) grad_norm: 1.7674 (1.8507) time: 0.5030 [2021-03-26 14:09:01 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 780/1251] eta: 0:04:00 lr: 0.000305 loss: 3.3016 (3.1138) grad_norm: 1.7546 (1.8496) time: 0.5052 [2021-03-26 14:09:06 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 790/1251] eta: 0:03:55 lr: 0.000305 loss: 3.4064 (3.1163) grad_norm: 1.7053 (1.8484) time: 0.5046 [2021-03-26 14:09:11 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 800/1251] eta: 0:03:49 lr: 0.000305 loss: 3.3941 (3.1184) grad_norm: 1.6878 (1.8471) time: 0.5056 [2021-03-26 14:09:16 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 810/1251] eta: 0:03:44 lr: 0.000305 loss: 3.3149 (3.1149) grad_norm: 1.7353 (1.8458) time: 0.5061 [2021-03-26 14:09:21 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 820/1251] eta: 0:03:39 lr: 0.000305 loss: 3.0353 (3.1127) grad_norm: 1.7495 (1.8468) time: 0.5061 [2021-03-26 14:09:26 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 830/1251] eta: 0:03:34 lr: 0.000305 loss: 3.1585 (3.1145) grad_norm: 1.7687 (1.8469) time: 0.5038 [2021-03-26 14:09:31 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 840/1251] eta: 0:03:29 lr: 0.000305 loss: 3.2345 (3.1135) grad_norm: 1.7020 (1.8455) time: 0.5026 [2021-03-26 14:09:36 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 850/1251] eta: 0:03:24 lr: 0.000305 loss: 3.1079 (3.1122) grad_norm: 1.7891 (1.8459) time: 0.4991 [2021-03-26 14:09:41 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 860/1251] eta: 0:03:19 lr: 0.000305 loss: 3.1855 (3.1104) grad_norm: 1.8059 (1.8457) time: 0.5017 [2021-03-26 14:09:46 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 870/1251] eta: 0:03:14 lr: 0.000305 loss: 3.1126 (3.1113) grad_norm: 1.8045 (1.8459) time: 0.5013 [2021-03-26 14:09:51 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 880/1251] eta: 0:03:08 lr: 0.000305 loss: 3.0478 (3.1102) grad_norm: 1.8365 (1.8470) time: 0.5010 [2021-03-26 14:09:56 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 890/1251] eta: 0:03:03 lr: 0.000305 loss: 3.0475 (3.1109) grad_norm: 1.8565 (1.8466) time: 0.5067 [2021-03-26 14:10:01 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 900/1251] eta: 0:02:58 lr: 0.000305 loss: 3.0484 (3.1103) grad_norm: 1.7891 (1.8460) time: 0.5090 [2021-03-26 14:10:06 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 910/1251] eta: 0:02:53 lr: 0.000305 loss: 3.1238 (3.1099) grad_norm: 1.6935 (1.8444) time: 0.5083 [2021-03-26 14:10:11 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 920/1251] eta: 0:02:48 lr: 0.000305 loss: 3.2764 (3.1114) grad_norm: 1.7221 (1.8448) time: 0.5065 [2021-03-26 14:10:16 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 930/1251] eta: 0:02:43 lr: 0.000305 loss: 3.4161 (3.1137) grad_norm: 1.7680 (1.8431) time: 0.5101 [2021-03-26 14:10:21 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 940/1251] eta: 0:02:38 lr: 0.000305 loss: 3.3745 (3.1154) grad_norm: 1.6928 (1.8427) time: 0.5090 [2021-03-26 14:10:27 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 950/1251] eta: 0:02:33 lr: 0.000305 loss: 3.1528 (3.1127) grad_norm: 1.7299 (1.8422) time: 0.5054 [2021-03-26 14:10:32 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 960/1251] eta: 0:02:28 lr: 0.000305 loss: 3.1378 (3.1131) grad_norm: 1.7194 (1.8411) time: 0.5035 [2021-03-26 14:10:37 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 970/1251] eta: 0:02:23 lr: 0.000305 loss: 3.3344 (3.1137) grad_norm: 1.7194 (1.8407) time: 0.5008 [2021-03-26 14:10:42 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 980/1251] eta: 0:02:17 lr: 0.000305 loss: 3.3167 (3.1141) grad_norm: 1.7915 (1.8410) time: 0.5016 [2021-03-26 14:10:47 swin_small_patch4_window7_224] INFO: Epoch: [189] [ 990/1251] eta: 0:02:12 lr: 0.000305 loss: 3.3167 (3.1154) grad_norm: 1.7775 (1.8406) time: 0.4986 [2021-03-26 14:10:52 swin_small_patch4_window7_224] INFO: Epoch: [189] [1000/1251] eta: 0:02:07 lr: 0.000305 loss: 2.8394 (3.1117) grad_norm: 1.7775 (1.8412) time: 0.5020 [2021-03-26 14:10:57 swin_small_patch4_window7_224] INFO: Epoch: [189] [1010/1251] eta: 0:02:02 lr: 0.000305 loss: 2.8394 (3.1113) grad_norm: 1.7698 (1.8406) time: 0.5111 [2021-03-26 14:11:02 swin_small_patch4_window7_224] INFO: Epoch: [189] [1020/1251] eta: 0:01:57 lr: 0.000305 loss: 3.1779 (3.1114) grad_norm: 1.7989 (1.8413) time: 0.5126 [2021-03-26 14:11:07 swin_small_patch4_window7_224] INFO: Epoch: [189] [1030/1251] eta: 0:01:52 lr: 0.000305 loss: 3.1538 (3.1115) grad_norm: 1.8050 (1.8409) time: 0.5093 [2021-03-26 14:11:12 swin_small_patch4_window7_224] INFO: Epoch: [189] [1040/1251] eta: 0:01:47 lr: 0.000304 loss: 2.9299 (3.1076) grad_norm: 1.7860 (1.8407) time: 0.4997 [2021-03-26 14:11:17 swin_small_patch4_window7_224] INFO: Epoch: [189] [1050/1251] eta: 0:01:42 lr: 0.000304 loss: 2.7684 (3.1074) grad_norm: 1.8067 (1.8408) time: 0.5011 [2021-03-26 14:11:22 swin_small_patch4_window7_224] INFO: Epoch: [189] [1060/1251] eta: 0:01:37 lr: 0.000304 loss: 3.1618 (3.1069) grad_norm: 1.8224 (1.8417) time: 0.5050 [2021-03-26 14:11:27 swin_small_patch4_window7_224] INFO: Epoch: [189] [1070/1251] eta: 0:01:32 lr: 0.000304 loss: 3.2300 (3.1076) grad_norm: 1.7522 (1.8407) time: 0.5037 [2021-03-26 14:11:32 swin_small_patch4_window7_224] INFO: Epoch: [189] [1080/1251] eta: 0:01:26 lr: 0.000304 loss: 3.1976 (3.1065) grad_norm: 1.7555 (1.8403) time: 0.5059 [2021-03-26 14:11:37 swin_small_patch4_window7_224] INFO: Epoch: [189] [1090/1251] eta: 0:01:21 lr: 0.000304 loss: 2.9693 (3.1041) grad_norm: 1.7945 (1.8400) time: 0.5081 [2021-03-26 14:11:42 swin_small_patch4_window7_224] INFO: Epoch: [189] [1100/1251] eta: 0:01:16 lr: 0.000304 loss: 3.1054 (3.1065) grad_norm: 1.7224 (1.8386) time: 0.5019 [2021-03-26 14:11:47 swin_small_patch4_window7_224] INFO: Epoch: [189] [1110/1251] eta: 0:01:11 lr: 0.000304 loss: 3.1898 (3.1054) grad_norm: 1.7224 (1.8391) time: 0.4940 [2021-03-26 14:11:52 swin_small_patch4_window7_224] INFO: Epoch: [189] [1120/1251] eta: 0:01:06 lr: 0.000304 loss: 3.1926 (3.1058) grad_norm: 1.8644 (1.8390) time: 0.4925 [2021-03-26 14:11:57 swin_small_patch4_window7_224] INFO: Epoch: [189] [1130/1251] eta: 0:01:01 lr: 0.000304 loss: 3.2259 (3.1069) grad_norm: 1.8262 (1.8389) time: 0.4949 [2021-03-26 14:12:02 swin_small_patch4_window7_224] INFO: Epoch: [189] [1140/1251] eta: 0:00:56 lr: 0.000304 loss: 3.5223 (3.1102) grad_norm: 1.8262 (1.8386) time: 0.4979 [2021-03-26 14:12:07 swin_small_patch4_window7_224] INFO: Epoch: [189] [1150/1251] eta: 0:00:51 lr: 0.000304 loss: 3.5223 (3.1108) grad_norm: 1.7050 (1.8376) time: 0.4973 [2021-03-26 14:12:12 swin_small_patch4_window7_224] INFO: Epoch: [189] [1160/1251] eta: 0:00:46 lr: 0.000304 loss: 3.2285 (3.1110) grad_norm: 1.6984 (1.8373) time: 0.4975 [2021-03-26 14:12:17 swin_small_patch4_window7_224] INFO: Epoch: [189] [1170/1251] eta: 0:00:41 lr: 0.000304 loss: 3.1297 (3.1092) grad_norm: 1.8004 (1.8374) time: 0.4998 [2021-03-26 14:12:22 swin_small_patch4_window7_224] INFO: Epoch: [189] [1180/1251] eta: 0:00:36 lr: 0.000304 loss: 3.2439 (3.1111) grad_norm: 1.8004 (1.8377) time: 0.5067 [2021-03-26 14:12:27 swin_small_patch4_window7_224] INFO: Epoch: [189] [1190/1251] eta: 0:00:30 lr: 0.000304 loss: 3.3315 (3.1115) grad_norm: 1.8230 (1.8382) time: 0.5165 [2021-03-26 14:12:32 swin_small_patch4_window7_224] INFO: Epoch: [189] [1200/1251] eta: 0:00:25 lr: 0.000304 loss: 3.1832 (3.1107) grad_norm: 1.8021 (1.8376) time: 0.5114 [2021-03-26 14:12:37 swin_small_patch4_window7_224] INFO: Epoch: [189] [1210/1251] eta: 0:00:20 lr: 0.000304 loss: 3.2076 (3.1109) grad_norm: 1.7912 (1.8373) time: 0.5033 [2021-03-26 14:12:42 swin_small_patch4_window7_224] INFO: Epoch: [189] [1220/1251] eta: 0:00:15 lr: 0.000304 loss: 3.2943 (3.1125) grad_norm: 1.7765 (1.8375) time: 0.5108 [2021-03-26 14:12:48 swin_small_patch4_window7_224] INFO: Epoch: [189] [1230/1251] eta: 0:00:10 lr: 0.000304 loss: 3.0054 (3.1102) grad_norm: 1.7634 (1.8371) time: 0.5099 [2021-03-26 14:12:53 swin_small_patch4_window7_224] INFO: Epoch: [189] [1240/1251] eta: 0:00:05 lr: 0.000304 loss: 3.0054 (3.1119) grad_norm: 1.7782 (1.8367) time: 0.5042 [2021-03-26 14:12:58 swin_small_patch4_window7_224] INFO: Epoch: [189] [1250/1251] eta: 0:00:00 lr: 0.000304 loss: 3.3029 (3.1130) grad_norm: 1.8136 (1.8367) time: 0.5033 [2021-03-26 14:13:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:18 loss: 0.8838 (0.8838) acc1: 78.1250 (78.1250) acc5: 98.4375 (98.4375) [2021-03-26 14:13:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8838 (0.8553) acc1: 78.1250 (79.6875) acc5: 95.3125 (95.8807) [2021-03-26 14:13:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8383 (0.8618) acc1: 78.1250 (79.8363) acc5: 95.3125 (95.3125) [2021-03-26 14:13:13 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.9633 (0.8872) acc1: 78.1250 (79.0827) acc5: 93.7500 (95.3125) [2021-03-26 14:13:15 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8769 (0.8589) acc1: 79.6875 (79.7637) acc5: 95.3125 (95.4649) [2021-03-26 14:13:16 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8199 (0.8616) acc1: 78.1250 (79.4240) acc5: 95.3125 (95.2640) [2021-03-26 14:13:25 swin_small_patch4_window7_224] INFO: * Acc@1 80.066 Acc@5 95.218 loss 0.848 [2021-03-26 14:13:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-26 14:13:25 swin_small_patch4_window7_224] INFO: Max accuracy: 80.07% [2021-03-26 14:13:29 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 0/1251] eta: 1:27:47 lr: 0.000304 loss: 3.0637 (3.0637) grad_norm: 1.9575 (1.9575) time: 4.2102 [2021-03-26 14:13:34 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 10/1251] eta: 0:17:50 lr: 0.000304 loss: 2.9282 (3.0062) grad_norm: 1.8297 (1.8598) time: 0.8626 [2021-03-26 14:13:39 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 20/1251] eta: 0:14:08 lr: 0.000304 loss: 3.0848 (3.0854) grad_norm: 1.7808 (1.8113) time: 0.5135 [2021-03-26 14:13:44 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 30/1251] eta: 0:12:48 lr: 0.000304 loss: 3.2161 (3.0874) grad_norm: 1.7808 (1.8361) time: 0.5016 [2021-03-26 14:13:49 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 40/1251] eta: 0:12:04 lr: 0.000304 loss: 2.9698 (3.0645) grad_norm: 1.7381 (1.8013) time: 0.5026 [2021-03-26 14:13:54 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 50/1251] eta: 0:11:35 lr: 0.000303 loss: 3.0974 (3.1098) grad_norm: 1.7041 (1.7805) time: 0.5006 [2021-03-26 14:13:59 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 60/1251] eta: 0:11:15 lr: 0.000303 loss: 3.0974 (3.1001) grad_norm: 1.6961 (1.7679) time: 0.5023 [2021-03-26 14:14:04 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 70/1251] eta: 0:10:59 lr: 0.000303 loss: 2.9793 (3.0794) grad_norm: 1.7318 (1.7607) time: 0.5056 [2021-03-26 14:14:10 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 80/1251] eta: 0:10:46 lr: 0.000303 loss: 3.1763 (3.0957) grad_norm: 1.7474 (1.7631) time: 0.5075 [2021-03-26 14:14:15 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 90/1251] eta: 0:10:34 lr: 0.000303 loss: 3.2998 (3.1220) grad_norm: 1.8253 (1.7808) time: 0.5026 [2021-03-26 14:14:20 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 100/1251] eta: 0:10:23 lr: 0.000303 loss: 3.2347 (3.1155) grad_norm: 1.8131 (1.7768) time: 0.4993 [2021-03-26 14:14:25 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 110/1251] eta: 0:10:14 lr: 0.000303 loss: 3.2347 (3.1278) grad_norm: 1.7378 (1.7830) time: 0.5053 [2021-03-26 14:14:30 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 120/1251] eta: 0:10:05 lr: 0.000303 loss: 3.3547 (3.1257) grad_norm: 1.8214 (1.7859) time: 0.5028 [2021-03-26 14:14:35 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 130/1251] eta: 0:09:58 lr: 0.000303 loss: 3.3547 (3.1426) grad_norm: 1.7217 (1.7823) time: 0.5075 [2021-03-26 14:14:40 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 140/1251] eta: 0:09:50 lr: 0.000303 loss: 3.2574 (3.1379) grad_norm: 1.7049 (1.7752) time: 0.5088 [2021-03-26 14:14:45 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 150/1251] eta: 0:09:42 lr: 0.000303 loss: 3.1890 (3.1324) grad_norm: 1.7020 (1.7739) time: 0.4982 [2021-03-26 14:14:50 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 160/1251] eta: 0:09:35 lr: 0.000303 loss: 3.0113 (3.1239) grad_norm: 1.8194 (1.7907) time: 0.5000 [2021-03-26 14:14:55 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 170/1251] eta: 0:09:29 lr: 0.000303 loss: 3.0823 (3.1294) grad_norm: 1.9393 (1.8033) time: 0.5053 [2021-03-26 14:15:00 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 180/1251] eta: 0:09:22 lr: 0.000303 loss: 3.1490 (3.1248) grad_norm: 1.8988 (1.8059) time: 0.5088 [2021-03-26 14:15:05 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 190/1251] eta: 0:09:16 lr: 0.000303 loss: 3.3952 (3.1327) grad_norm: 1.8439 (1.8083) time: 0.5113 [2021-03-26 14:15:10 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 200/1251] eta: 0:09:11 lr: 0.000303 loss: 3.3200 (3.1389) grad_norm: 1.8711 (1.8097) time: 0.5162 [2021-03-26 14:15:15 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 210/1251] eta: 0:09:05 lr: 0.000303 loss: 3.2545 (3.1382) grad_norm: 1.8272 (1.8094) time: 0.5113 [2021-03-26 14:15:20 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 220/1251] eta: 0:08:58 lr: 0.000303 loss: 3.0449 (3.1335) grad_norm: 1.8272 (1.8097) time: 0.5012 [2021-03-26 14:15:25 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 230/1251] eta: 0:08:52 lr: 0.000303 loss: 2.9625 (3.1268) grad_norm: 1.8614 (1.8111) time: 0.5044 [2021-03-26 14:15:30 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 240/1251] eta: 0:08:46 lr: 0.000303 loss: 2.9625 (3.1161) grad_norm: 1.7943 (1.8074) time: 0.5071 [2021-03-26 14:15:36 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 250/1251] eta: 0:08:41 lr: 0.000303 loss: 3.1173 (3.1211) grad_norm: 1.7943 (1.8079) time: 0.5084 [2021-03-26 14:15:41 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 260/1251] eta: 0:08:35 lr: 0.000303 loss: 3.2830 (3.1153) grad_norm: 1.8444 (1.8177) time: 0.5111 [2021-03-26 14:15:46 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 270/1251] eta: 0:08:29 lr: 0.000303 loss: 3.1392 (3.1092) grad_norm: 1.8057 (1.8168) time: 0.5065 [2021-03-26 14:15:51 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 280/1251] eta: 0:08:24 lr: 0.000303 loss: 3.1861 (3.1100) grad_norm: 1.7312 (1.8136) time: 0.5061 [2021-03-26 14:15:56 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 290/1251] eta: 0:08:18 lr: 0.000303 loss: 3.1861 (3.1100) grad_norm: 1.7312 (1.8138) time: 0.5069 [2021-03-26 14:16:01 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 300/1251] eta: 0:08:12 lr: 0.000303 loss: 3.2614 (3.1189) grad_norm: 1.7695 (1.8140) time: 0.5038 [2021-03-26 14:16:06 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 310/1251] eta: 0:08:07 lr: 0.000302 loss: 3.2614 (3.1190) grad_norm: 1.8684 (1.8177) time: 0.5014 [2021-03-26 14:16:11 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 320/1251] eta: 0:08:01 lr: 0.000302 loss: 3.1074 (3.1193) grad_norm: 1.8613 (1.8177) time: 0.4995 [2021-03-26 14:16:16 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 330/1251] eta: 0:07:55 lr: 0.000302 loss: 3.2386 (3.1223) grad_norm: 1.7640 (1.8178) time: 0.5013 [2021-03-26 14:16:21 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 340/1251] eta: 0:07:50 lr: 0.000302 loss: 3.3841 (3.1283) grad_norm: 1.7622 (1.8177) time: 0.5047 [2021-03-26 14:16:26 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 350/1251] eta: 0:07:45 lr: 0.000302 loss: 3.3515 (3.1230) grad_norm: 1.7486 (1.8166) time: 0.5054 [2021-03-26 14:16:31 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 360/1251] eta: 0:07:39 lr: 0.000302 loss: 3.1170 (3.1268) grad_norm: 1.7236 (1.8158) time: 0.5054 [2021-03-26 14:16:36 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 370/1251] eta: 0:07:34 lr: 0.000302 loss: 3.0492 (3.1173) grad_norm: 1.7954 (1.8160) time: 0.5081 [2021-03-26 14:16:41 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 380/1251] eta: 0:07:28 lr: 0.000302 loss: 3.0895 (3.1237) grad_norm: 1.7252 (1.8137) time: 0.5055 [2021-03-26 14:16:46 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 390/1251] eta: 0:07:23 lr: 0.000302 loss: 3.3273 (3.1269) grad_norm: 1.8123 (1.8242) time: 0.5033 [2021-03-26 14:16:51 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 400/1251] eta: 0:07:18 lr: 0.000302 loss: 3.2620 (3.1254) grad_norm: 1.8518 (1.8246) time: 0.5045 [2021-03-26 14:16:56 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 410/1251] eta: 0:07:12 lr: 0.000302 loss: 3.0424 (3.1188) grad_norm: 1.7660 (1.8231) time: 0.5023 [2021-03-26 14:17:01 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 420/1251] eta: 0:07:07 lr: 0.000302 loss: 3.0424 (3.1199) grad_norm: 1.7660 (1.8226) time: 0.5070 [2021-03-26 14:17:06 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 430/1251] eta: 0:07:02 lr: 0.000302 loss: 3.1906 (3.1201) grad_norm: 1.7499 (1.8202) time: 0.5070 [2021-03-26 14:17:12 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 440/1251] eta: 0:06:56 lr: 0.000302 loss: 3.2305 (3.1253) grad_norm: 1.7593 (1.8205) time: 0.5046 [2021-03-26 14:17:17 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 450/1251] eta: 0:06:51 lr: 0.000302 loss: 3.3656 (3.1297) grad_norm: 1.9028 (1.8226) time: 0.5054 [2021-03-26 14:17:22 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 460/1251] eta: 0:06:46 lr: 0.000302 loss: 3.1588 (3.1262) grad_norm: 1.7381 (1.8202) time: 0.5038 [2021-03-26 14:17:27 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 470/1251] eta: 0:06:41 lr: 0.000302 loss: 3.0225 (3.1278) grad_norm: 1.7557 (1.8200) time: 0.5094 [2021-03-26 14:17:32 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 480/1251] eta: 0:06:35 lr: 0.000302 loss: 3.2816 (3.1319) grad_norm: 1.7652 (1.8177) time: 0.5117 [2021-03-26 14:17:37 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 490/1251] eta: 0:06:30 lr: 0.000302 loss: 3.4063 (3.1336) grad_norm: 1.7498 (1.8167) time: 0.5027 [2021-03-26 14:17:42 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 500/1251] eta: 0:06:25 lr: 0.000302 loss: 3.4063 (3.1399) grad_norm: 1.7498 (1.8174) time: 0.5022 [2021-03-26 14:17:47 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 510/1251] eta: 0:06:19 lr: 0.000302 loss: 3.2232 (3.1356) grad_norm: 1.7245 (1.8149) time: 0.5052 [2021-03-26 14:17:52 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 520/1251] eta: 0:06:14 lr: 0.000302 loss: 3.1660 (3.1391) grad_norm: 1.7426 (1.8145) time: 0.5035 [2021-03-26 14:17:57 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 530/1251] eta: 0:06:09 lr: 0.000302 loss: 3.3434 (3.1406) grad_norm: 1.6988 (1.8119) time: 0.5108 [2021-03-26 14:18:02 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 540/1251] eta: 0:06:04 lr: 0.000302 loss: 3.3434 (3.1386) grad_norm: 1.6335 (1.8111) time: 0.5179 [2021-03-26 14:18:08 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 550/1251] eta: 0:05:59 lr: 0.000302 loss: 3.3467 (3.1387) grad_norm: 1.6959 (1.8123) time: 0.5229 [2021-03-26 14:18:13 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 560/1251] eta: 0:05:54 lr: 0.000302 loss: 2.9514 (3.1342) grad_norm: 1.7267 (1.8112) time: 0.5147 [2021-03-26 14:18:18 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 570/1251] eta: 0:05:49 lr: 0.000302 loss: 3.0567 (3.1363) grad_norm: 1.7267 (1.8108) time: 0.5066 [2021-03-26 14:18:23 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 580/1251] eta: 0:05:43 lr: 0.000301 loss: 3.2329 (3.1353) grad_norm: 1.6920 (1.8098) time: 0.5051 [2021-03-26 14:18:28 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 590/1251] eta: 0:05:38 lr: 0.000301 loss: 3.0890 (3.1343) grad_norm: 1.7019 (1.8086) time: 0.5014 [2021-03-26 14:18:33 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 600/1251] eta: 0:05:33 lr: 0.000301 loss: 3.1285 (3.1353) grad_norm: 1.8240 (1.8098) time: 0.5017 [2021-03-26 14:18:38 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 610/1251] eta: 0:05:28 lr: 0.000301 loss: 3.4635 (3.1384) grad_norm: 1.7892 (1.8090) time: 0.5050 [2021-03-26 14:18:43 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 620/1251] eta: 0:05:23 lr: 0.000301 loss: 3.3634 (3.1369) grad_norm: 1.6693 (1.8064) time: 0.5037 [2021-03-26 14:18:48 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 630/1251] eta: 0:05:17 lr: 0.000301 loss: 3.1956 (3.1381) grad_norm: 1.6322 (1.8058) time: 0.5025 [2021-03-26 14:18:53 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 640/1251] eta: 0:05:12 lr: 0.000301 loss: 3.0316 (3.1375) grad_norm: 1.7271 (1.8054) time: 0.5080 [2021-03-26 14:18:58 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 650/1251] eta: 0:05:07 lr: 0.000301 loss: 3.3469 (3.1389) grad_norm: 1.7186 (1.8040) time: 0.5017 [2021-03-26 14:19:03 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 660/1251] eta: 0:05:02 lr: 0.000301 loss: 3.3707 (3.1391) grad_norm: 1.6679 (1.8027) time: 0.4943 [2021-03-26 14:19:08 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 670/1251] eta: 0:04:56 lr: 0.000301 loss: 3.1458 (3.1387) grad_norm: 1.7510 (1.8032) time: 0.4940 [2021-03-26 14:19:13 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 680/1251] eta: 0:04:51 lr: 0.000301 loss: 3.2300 (3.1414) grad_norm: 1.8177 (1.8031) time: 0.4960 [2021-03-26 14:19:18 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 690/1251] eta: 0:04:46 lr: 0.000301 loss: 3.2743 (3.1399) grad_norm: 1.8002 (1.8044) time: 0.5093 [2021-03-26 14:19:23 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 700/1251] eta: 0:04:41 lr: 0.000301 loss: 3.1914 (3.1411) grad_norm: 1.7789 (1.8044) time: 0.5086 [2021-03-26 14:19:28 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 710/1251] eta: 0:04:36 lr: 0.000301 loss: 3.1584 (3.1418) grad_norm: 1.7566 (1.8027) time: 0.5005 [2021-03-26 14:19:33 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 720/1251] eta: 0:04:31 lr: 0.000301 loss: 3.1482 (3.1392) grad_norm: 1.7451 (1.8016) time: 0.5052 [2021-03-26 14:19:38 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 730/1251] eta: 0:04:26 lr: 0.000301 loss: 3.1544 (3.1377) grad_norm: 1.7451 (1.8012) time: 0.5139 [2021-03-26 14:19:44 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 740/1251] eta: 0:04:21 lr: 0.000301 loss: 3.0966 (3.1346) grad_norm: 1.7451 (1.8005) time: 0.5297 [2021-03-26 14:19:49 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 750/1251] eta: 0:04:16 lr: 0.000301 loss: 3.0590 (3.1332) grad_norm: 1.7669 (1.8019) time: 0.5241 [2021-03-26 14:19:54 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 760/1251] eta: 0:04:10 lr: 0.000301 loss: 3.1659 (3.1331) grad_norm: 1.7942 (1.8019) time: 0.5087 [2021-03-26 14:19:59 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 770/1251] eta: 0:04:05 lr: 0.000301 loss: 3.2049 (3.1330) grad_norm: 1.7674 (1.8015) time: 0.5090 [2021-03-26 14:20:04 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 780/1251] eta: 0:04:00 lr: 0.000301 loss: 3.0387 (3.1333) grad_norm: 1.7674 (1.8010) time: 0.5079 [2021-03-26 14:20:09 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 790/1251] eta: 0:03:55 lr: 0.000301 loss: 3.1638 (3.1326) grad_norm: 1.7770 (1.8002) time: 0.5032 [2021-03-26 14:20:14 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 800/1251] eta: 0:03:50 lr: 0.000301 loss: 3.2104 (3.1321) grad_norm: 1.7471 (1.8004) time: 0.5015 [2021-03-26 14:20:19 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 810/1251] eta: 0:03:45 lr: 0.000301 loss: 3.1875 (3.1304) grad_norm: 1.7164 (1.7998) time: 0.5060 [2021-03-26 14:20:24 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 820/1251] eta: 0:03:40 lr: 0.000301 loss: 3.1193 (3.1309) grad_norm: 1.7311 (1.7999) time: 0.5055 [2021-03-26 14:20:29 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 830/1251] eta: 0:03:35 lr: 0.000301 loss: 3.2127 (3.1320) grad_norm: 1.7988 (1.7999) time: 0.5079 [2021-03-26 14:20:34 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 840/1251] eta: 0:03:29 lr: 0.000300 loss: 3.2133 (3.1317) grad_norm: 1.7988 (1.7993) time: 0.5088 [2021-03-26 14:20:39 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 850/1251] eta: 0:03:24 lr: 0.000300 loss: 3.1110 (3.1304) grad_norm: 1.6856 (1.7992) time: 0.5028 [2021-03-26 14:20:44 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 860/1251] eta: 0:03:19 lr: 0.000300 loss: 3.1110 (3.1290) grad_norm: 1.7405 (1.7993) time: 0.5020 [2021-03-26 14:20:49 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 870/1251] eta: 0:03:14 lr: 0.000300 loss: 3.2118 (3.1302) grad_norm: 1.8194 (1.7995) time: 0.4981 [2021-03-26 14:20:55 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 880/1251] eta: 0:03:09 lr: 0.000300 loss: 3.1504 (3.1278) grad_norm: 1.7660 (1.7989) time: 0.5069 [2021-03-26 14:21:00 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 890/1251] eta: 0:03:04 lr: 0.000300 loss: 3.0647 (3.1267) grad_norm: 1.8018 (1.8010) time: 0.5089 [2021-03-26 14:21:05 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 900/1251] eta: 0:02:59 lr: 0.000300 loss: 3.2424 (3.1285) grad_norm: 1.8609 (1.8007) time: 0.4998 [2021-03-26 14:21:10 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 910/1251] eta: 0:02:53 lr: 0.000300 loss: 3.3424 (3.1279) grad_norm: 1.7769 (1.8011) time: 0.5040 [2021-03-26 14:21:15 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 920/1251] eta: 0:02:48 lr: 0.000300 loss: 3.2653 (3.1272) grad_norm: 1.7753 (1.8007) time: 0.5093 [2021-03-26 14:21:20 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 930/1251] eta: 0:02:43 lr: 0.000300 loss: 3.2612 (3.1271) grad_norm: 1.7699 (1.8013) time: 0.5136 [2021-03-26 14:21:25 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 940/1251] eta: 0:02:38 lr: 0.000300 loss: 3.1916 (3.1270) grad_norm: 1.7699 (1.8011) time: 0.5093 [2021-03-26 14:21:30 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 950/1251] eta: 0:02:33 lr: 0.000300 loss: 3.0976 (3.1250) grad_norm: 1.7770 (1.8016) time: 0.5052 [2021-03-26 14:21:35 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 960/1251] eta: 0:02:28 lr: 0.000300 loss: 3.1672 (3.1251) grad_norm: 1.7876 (1.8018) time: 0.5043 [2021-03-26 14:21:40 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 970/1251] eta: 0:02:23 lr: 0.000300 loss: 3.2713 (3.1260) grad_norm: 1.7473 (1.8011) time: 0.5019 [2021-03-26 14:21:45 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 980/1251] eta: 0:02:18 lr: 0.000300 loss: 3.2647 (3.1266) grad_norm: 1.7597 (1.8008) time: 0.5035 [2021-03-26 14:21:50 swin_small_patch4_window7_224] INFO: Epoch: [190] [ 990/1251] eta: 0:02:13 lr: 0.000300 loss: 3.2309 (3.1291) grad_norm: 1.8110 (1.8014) time: 0.5037 [2021-03-26 14:21:55 swin_small_patch4_window7_224] INFO: Epoch: [190] [1000/1251] eta: 0:02:07 lr: 0.000300 loss: 3.2510 (3.1273) grad_norm: 1.7452 (1.8011) time: 0.5046 [2021-03-26 14:22:00 swin_small_patch4_window7_224] INFO: Epoch: [190] [1010/1251] eta: 0:02:02 lr: 0.000300 loss: 3.1551 (3.1265) grad_norm: 1.7056 (1.8008) time: 0.5047 [2021-03-26 14:22:06 swin_small_patch4_window7_224] INFO: Epoch: [190] [1020/1251] eta: 0:01:57 lr: 0.000300 loss: 3.2274 (3.1267) grad_norm: 1.7203 (1.8003) time: 0.5144 [2021-03-26 14:22:11 swin_small_patch4_window7_224] INFO: Epoch: [190] [1030/1251] eta: 0:01:52 lr: 0.000300 loss: 3.1371 (3.1267) grad_norm: 1.7454 (1.8004) time: 0.5146 [2021-03-26 14:22:16 swin_small_patch4_window7_224] INFO: Epoch: [190] [1040/1251] eta: 0:01:47 lr: 0.000300 loss: 3.0837 (3.1259) grad_norm: 1.7454 (1.7999) time: 0.5014 [2021-03-26 14:22:21 swin_small_patch4_window7_224] INFO: Epoch: [190] [1050/1251] eta: 0:01:42 lr: 0.000300 loss: 3.1905 (3.1279) grad_norm: 1.6858 (1.7995) time: 0.5012 [2021-03-26 14:22:26 swin_small_patch4_window7_224] INFO: Epoch: [190] [1060/1251] eta: 0:01:37 lr: 0.000300 loss: 3.5122 (3.1314) grad_norm: 1.7944 (1.8000) time: 0.5034 [2021-03-26 14:22:31 swin_small_patch4_window7_224] INFO: Epoch: [190] [1070/1251] eta: 0:01:32 lr: 0.000300 loss: 3.3979 (3.1326) grad_norm: 1.8009 (1.8004) time: 0.5003 [2021-03-26 14:22:36 swin_small_patch4_window7_224] INFO: Epoch: [190] [1080/1251] eta: 0:01:27 lr: 0.000300 loss: 3.2463 (3.1317) grad_norm: 1.7622 (1.7995) time: 0.5016 [2021-03-26 14:22:41 swin_small_patch4_window7_224] INFO: Epoch: [190] [1090/1251] eta: 0:01:22 lr: 0.000300 loss: 3.1502 (3.1320) grad_norm: 1.7256 (1.8003) time: 0.5069 [2021-03-26 14:22:46 swin_small_patch4_window7_224] INFO: Epoch: [190] [1100/1251] eta: 0:01:16 lr: 0.000300 loss: 3.1661 (3.1329) grad_norm: 1.7543 (1.7996) time: 0.5024 [2021-03-26 14:22:51 swin_small_patch4_window7_224] INFO: Epoch: [190] [1110/1251] eta: 0:01:11 lr: 0.000299 loss: 3.1874 (3.1342) grad_norm: 1.7026 (1.7987) time: 0.4961 [2021-03-26 14:22:56 swin_small_patch4_window7_224] INFO: Epoch: [190] [1120/1251] eta: 0:01:06 lr: 0.000299 loss: 3.1311 (3.1331) grad_norm: 1.7081 (1.7985) time: 0.5007 [2021-03-26 14:23:01 swin_small_patch4_window7_224] INFO: Epoch: [190] [1130/1251] eta: 0:01:01 lr: 0.000299 loss: 2.9573 (3.1314) grad_norm: 1.8494 (nan) time: 0.5015 [2021-03-26 14:23:06 swin_small_patch4_window7_224] INFO: Epoch: [190] [1140/1251] eta: 0:00:56 lr: 0.000299 loss: 2.9936 (3.1318) grad_norm: 1.8385 (nan) time: 0.4997 [2021-03-26 14:23:11 swin_small_patch4_window7_224] INFO: Epoch: [190] [1150/1251] eta: 0:00:51 lr: 0.000299 loss: 2.9989 (3.1316) grad_norm: 1.8387 (nan) time: 0.4982 [2021-03-26 14:23:16 swin_small_patch4_window7_224] INFO: Epoch: [190] [1160/1251] eta: 0:00:46 lr: 0.000299 loss: 3.2443 (3.1332) grad_norm: 1.9014 (nan) time: 0.4974 [2021-03-26 14:23:21 swin_small_patch4_window7_224] INFO: Epoch: [190] [1170/1251] eta: 0:00:41 lr: 0.000299 loss: 3.4208 (3.1340) grad_norm: 1.8426 (nan) time: 0.5033 [2021-03-26 14:23:26 swin_small_patch4_window7_224] INFO: Epoch: [190] [1180/1251] eta: 0:00:36 lr: 0.000299 loss: 3.1504 (3.1330) grad_norm: 1.7346 (nan) time: 0.5066 [2021-03-26 14:23:31 swin_small_patch4_window7_224] INFO: Epoch: [190] [1190/1251] eta: 0:00:31 lr: 0.000299 loss: 3.2258 (3.1345) grad_norm: 1.7544 (nan) time: 0.5023 [2021-03-26 14:23:36 swin_small_patch4_window7_224] INFO: Epoch: [190] [1200/1251] eta: 0:00:25 lr: 0.000299 loss: 3.0596 (3.1302) grad_norm: 1.7586 (nan) time: 0.4963 [2021-03-26 14:23:41 swin_small_patch4_window7_224] INFO: Epoch: [190] [1210/1251] eta: 0:00:20 lr: 0.000299 loss: 2.7159 (3.1277) grad_norm: 1.6980 (nan) time: 0.5001 [2021-03-26 14:23:46 swin_small_patch4_window7_224] INFO: Epoch: [190] [1220/1251] eta: 0:00:15 lr: 0.000299 loss: 3.1773 (3.1294) grad_norm: 1.8328 (nan) time: 0.4995 [2021-03-26 14:23:51 swin_small_patch4_window7_224] INFO: Epoch: [190] [1230/1251] eta: 0:00:10 lr: 0.000299 loss: 3.3597 (3.1295) grad_norm: 1.8821 (nan) time: 0.4976 [2021-03-26 14:23:56 swin_small_patch4_window7_224] INFO: Epoch: [190] [1240/1251] eta: 0:00:05 lr: 0.000299 loss: 3.3356 (3.1311) grad_norm: 1.7650 (nan) time: 0.5027 [2021-03-26 14:24:01 swin_small_patch4_window7_224] INFO: Epoch: [190] [1250/1251] eta: 0:00:00 lr: 0.000299 loss: 3.1319 (3.1296) grad_norm: 1.7127 (nan) time: 0.5009 [2021-03-26 14:24:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:31 loss: 0.7092 (0.7092) acc1: 81.2500 (81.2500) acc5: 98.4375 (98.4375) [2021-03-26 14:24:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:10 loss: 0.9099 (0.9322) acc1: 78.1250 (78.4091) acc5: 93.7500 (94.3182) [2021-03-26 14:24:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8693 (0.8660) acc1: 79.6875 (79.8363) acc5: 93.7500 (94.7917) [2021-03-26 14:24:50 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.8272 (0.8786) acc1: 79.6875 (79.5363) acc5: 95.3125 (94.7077) [2021-03-26 14:24:51 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8552 (0.8683) acc1: 79.6875 (79.7637) acc5: 95.3125 (95.0076) [2021-03-26 14:24:52 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8160 (0.8630) acc1: 79.6875 (79.7760) acc5: 96.8750 (95.2000) [2021-03-26 14:25:03 swin_small_patch4_window7_224] INFO: * Acc@1 80.186 Acc@5 95.264 loss 0.836 [2021-03-26 14:25:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.2% [2021-03-26 14:25:03 swin_small_patch4_window7_224] INFO: Max accuracy: 80.19% [2021-03-26 14:25:07 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 0/1251] eta: 1:27:10 lr: 0.000299 loss: 3.4174 (3.4174) grad_norm: 1.8209 (1.8209) time: 4.1813 [2021-03-26 14:25:12 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 10/1251] eta: 0:17:37 lr: 0.000299 loss: 3.2326 (3.0543) grad_norm: 1.7207 (1.7940) time: 0.8520 [2021-03-26 14:25:17 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 20/1251] eta: 0:14:07 lr: 0.000299 loss: 3.0738 (2.9937) grad_norm: 1.7207 (1.8893) time: 0.5135 [2021-03-26 14:25:22 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 30/1251] eta: 0:12:46 lr: 0.000299 loss: 2.9227 (2.9504) grad_norm: 1.7494 (1.8590) time: 0.5047 [2021-03-26 14:25:27 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 40/1251] eta: 0:12:03 lr: 0.000299 loss: 2.9227 (2.9425) grad_norm: 1.7733 (1.8331) time: 0.5029 [2021-03-26 14:25:32 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 50/1251] eta: 0:11:35 lr: 0.000299 loss: 3.3792 (3.0185) grad_norm: 1.8078 (1.8578) time: 0.5032 [2021-03-26 14:25:37 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 60/1251] eta: 0:11:15 lr: 0.000299 loss: 3.3792 (3.0529) grad_norm: 1.7912 (1.8399) time: 0.5047 [2021-03-26 14:25:42 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 70/1251] eta: 0:11:02 lr: 0.000299 loss: 3.2322 (3.0743) grad_norm: 1.6684 (1.8236) time: 0.5158 [2021-03-26 14:25:48 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 80/1251] eta: 0:10:48 lr: 0.000299 loss: 3.0139 (3.0611) grad_norm: 1.7489 (1.8237) time: 0.5135 [2021-03-26 14:25:53 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 90/1251] eta: 0:10:36 lr: 0.000299 loss: 2.8990 (3.0510) grad_norm: 1.7153 (1.8078) time: 0.5029 [2021-03-26 14:25:58 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 100/1251] eta: 0:10:26 lr: 0.000299 loss: 3.1240 (3.0730) grad_norm: 1.7153 (1.8100) time: 0.5037 [2021-03-26 14:26:03 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 110/1251] eta: 0:10:17 lr: 0.000299 loss: 3.3770 (3.0910) grad_norm: 1.8260 (1.8133) time: 0.5092 [2021-03-26 14:26:08 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 120/1251] eta: 0:10:09 lr: 0.000298 loss: 3.0518 (3.0856) grad_norm: 1.7798 (1.8102) time: 0.5126 [2021-03-26 14:26:13 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 130/1251] eta: 0:10:02 lr: 0.000298 loss: 3.0851 (3.0788) grad_norm: 1.7505 (1.8116) time: 0.5154 [2021-03-26 14:26:18 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 140/1251] eta: 0:09:54 lr: 0.000298 loss: 3.1184 (3.0803) grad_norm: 1.7594 (1.8116) time: 0.5151 [2021-03-26 14:26:23 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 150/1251] eta: 0:09:47 lr: 0.000298 loss: 3.1834 (3.0887) grad_norm: 1.8442 (1.8186) time: 0.5075 [2021-03-26 14:26:28 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 160/1251] eta: 0:09:40 lr: 0.000298 loss: 3.2241 (3.0993) grad_norm: 1.8241 (1.8171) time: 0.5069 [2021-03-26 14:26:33 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 170/1251] eta: 0:09:33 lr: 0.000298 loss: 3.2241 (3.1046) grad_norm: 1.7476 (1.8204) time: 0.5055 [2021-03-26 14:26:38 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 180/1251] eta: 0:09:26 lr: 0.000298 loss: 3.1030 (3.1027) grad_norm: 1.8407 (1.8317) time: 0.5053 [2021-03-26 14:26:43 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 190/1251] eta: 0:09:19 lr: 0.000298 loss: 3.1139 (3.1014) grad_norm: 1.8091 (1.8298) time: 0.5053 [2021-03-26 14:26:49 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 200/1251] eta: 0:09:13 lr: 0.000298 loss: 3.1139 (3.1047) grad_norm: 1.7557 (1.8293) time: 0.5083 [2021-03-26 14:26:54 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 210/1251] eta: 0:09:07 lr: 0.000298 loss: 3.2327 (3.1148) grad_norm: 1.7219 (1.8231) time: 0.5111 [2021-03-26 14:26:59 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 220/1251] eta: 0:09:01 lr: 0.000298 loss: 3.0924 (3.1083) grad_norm: 1.6618 (1.8174) time: 0.5050 [2021-03-26 14:27:04 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 230/1251] eta: 0:08:55 lr: 0.000298 loss: 3.1909 (3.1175) grad_norm: 1.7318 (1.8153) time: 0.5045 [2021-03-26 14:27:09 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 240/1251] eta: 0:08:49 lr: 0.000298 loss: 3.3268 (3.1198) grad_norm: 1.7328 (1.8163) time: 0.5078 [2021-03-26 14:27:14 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 250/1251] eta: 0:08:43 lr: 0.000298 loss: 3.0205 (3.1132) grad_norm: 1.7260 (1.8146) time: 0.5056 [2021-03-26 14:27:19 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 260/1251] eta: 0:08:37 lr: 0.000298 loss: 3.0392 (3.1179) grad_norm: 1.8083 (1.8170) time: 0.5074 [2021-03-26 14:27:24 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 270/1251] eta: 0:08:31 lr: 0.000298 loss: 3.2001 (3.1199) grad_norm: 1.7491 (1.8117) time: 0.5047 [2021-03-26 14:27:29 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 280/1251] eta: 0:08:25 lr: 0.000298 loss: 3.3798 (3.1313) grad_norm: 1.7464 (1.8113) time: 0.5018 [2021-03-26 14:27:34 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 290/1251] eta: 0:08:19 lr: 0.000298 loss: 3.4230 (3.1375) grad_norm: 1.7894 (1.8117) time: 0.5017 [2021-03-26 14:27:39 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 300/1251] eta: 0:08:14 lr: 0.000298 loss: 3.2695 (3.1380) grad_norm: 1.7508 (1.8096) time: 0.5028 [2021-03-26 14:27:44 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 310/1251] eta: 0:08:08 lr: 0.000298 loss: 3.0708 (3.1365) grad_norm: 1.7494 (1.8085) time: 0.5100 [2021-03-26 14:27:49 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 320/1251] eta: 0:08:03 lr: 0.000298 loss: 3.3819 (3.1455) grad_norm: 1.7985 (1.8082) time: 0.5121 [2021-03-26 14:27:54 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 330/1251] eta: 0:07:57 lr: 0.000298 loss: 3.4739 (3.1519) grad_norm: 1.7819 (1.8084) time: 0.5075 [2021-03-26 14:27:59 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 340/1251] eta: 0:07:51 lr: 0.000298 loss: 3.3484 (3.1520) grad_norm: 1.7527 (1.8082) time: 0.5014 [2021-03-26 14:28:04 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 350/1251] eta: 0:07:46 lr: 0.000298 loss: 3.3484 (3.1562) grad_norm: 1.7550 (1.8093) time: 0.5031 [2021-03-26 14:28:09 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 360/1251] eta: 0:07:41 lr: 0.000298 loss: 3.3886 (3.1602) grad_norm: 1.8813 (1.8161) time: 0.5060 [2021-03-26 14:28:14 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 370/1251] eta: 0:07:35 lr: 0.000298 loss: 3.2657 (3.1615) grad_norm: 1.7700 (1.8174) time: 0.5040 [2021-03-26 14:28:19 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 380/1251] eta: 0:07:29 lr: 0.000298 loss: 3.3830 (3.1695) grad_norm: 1.7937 (1.8196) time: 0.5001 [2021-03-26 14:28:24 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 390/1251] eta: 0:07:24 lr: 0.000297 loss: 3.0653 (3.1596) grad_norm: 1.8371 (1.8203) time: 0.4972 [2021-03-26 14:28:29 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 400/1251] eta: 0:07:18 lr: 0.000297 loss: 2.9988 (3.1594) grad_norm: 1.8118 (1.8193) time: 0.4992 [2021-03-26 14:28:34 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 410/1251] eta: 0:07:13 lr: 0.000297 loss: 3.2509 (3.1595) grad_norm: 1.8079 (1.8205) time: 0.5015 [2021-03-26 14:28:40 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 420/1251] eta: 0:07:08 lr: 0.000297 loss: 3.0500 (3.1576) grad_norm: 1.7298 (1.8203) time: 0.5056 [2021-03-26 14:28:45 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 430/1251] eta: 0:07:02 lr: 0.000297 loss: 3.1445 (3.1599) grad_norm: 1.6466 (1.8193) time: 0.5083 [2021-03-26 14:28:50 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 440/1251] eta: 0:06:57 lr: 0.000297 loss: 3.0591 (3.1543) grad_norm: 1.6771 (1.8184) time: 0.5063 [2021-03-26 14:28:55 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 450/1251] eta: 0:06:52 lr: 0.000297 loss: 3.0211 (3.1500) grad_norm: 1.8059 (1.8175) time: 0.5059 [2021-03-26 14:29:00 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 460/1251] eta: 0:06:47 lr: 0.000297 loss: 3.0472 (3.1443) grad_norm: 1.8236 (1.8177) time: 0.5120 [2021-03-26 14:29:05 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 470/1251] eta: 0:06:41 lr: 0.000297 loss: 3.1458 (3.1477) grad_norm: 1.8236 (1.8178) time: 0.5082 [2021-03-26 14:29:10 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 480/1251] eta: 0:06:36 lr: 0.000297 loss: 3.0342 (3.1424) grad_norm: 1.7810 (1.8172) time: 0.4976 [2021-03-26 14:29:15 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 490/1251] eta: 0:06:30 lr: 0.000297 loss: 3.0342 (3.1427) grad_norm: 1.6788 (1.8138) time: 0.4968 [2021-03-26 14:29:20 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 500/1251] eta: 0:06:25 lr: 0.000297 loss: 3.2971 (3.1453) grad_norm: 1.6925 (1.8119) time: 0.4997 [2021-03-26 14:29:25 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 510/1251] eta: 0:06:20 lr: 0.000297 loss: 3.3358 (3.1468) grad_norm: 1.6769 (1.8093) time: 0.5010 [2021-03-26 14:29:30 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 520/1251] eta: 0:06:14 lr: 0.000297 loss: 3.1546 (3.1458) grad_norm: 1.6769 (1.8087) time: 0.4969 [2021-03-26 14:29:35 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 530/1251] eta: 0:06:09 lr: 0.000297 loss: 3.1433 (3.1460) grad_norm: 1.7145 (1.8082) time: 0.4970 [2021-03-26 14:29:40 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 540/1251] eta: 0:06:04 lr: 0.000297 loss: 3.2629 (3.1461) grad_norm: 1.7236 (1.8091) time: 0.5001 [2021-03-26 14:29:45 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 550/1251] eta: 0:05:59 lr: 0.000297 loss: 3.2792 (3.1480) grad_norm: 1.7665 (1.8103) time: 0.5095 [2021-03-26 14:29:50 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 560/1251] eta: 0:05:53 lr: 0.000297 loss: 3.1607 (3.1432) grad_norm: 1.7700 (1.8101) time: 0.5082 [2021-03-26 14:29:55 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 570/1251] eta: 0:05:48 lr: 0.000297 loss: 3.1607 (3.1431) grad_norm: 1.7526 (1.8114) time: 0.4990 [2021-03-26 14:30:00 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 580/1251] eta: 0:05:43 lr: 0.000297 loss: 3.3475 (3.1440) grad_norm: 1.8134 (1.8136) time: 0.5047 [2021-03-26 14:30:05 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 590/1251] eta: 0:05:38 lr: 0.000297 loss: 3.3310 (3.1450) grad_norm: 1.8151 (1.8139) time: 0.5123 [2021-03-26 14:30:10 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 600/1251] eta: 0:05:33 lr: 0.000297 loss: 3.3420 (3.1492) grad_norm: 1.8091 (1.8143) time: 0.5101 [2021-03-26 14:30:15 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 610/1251] eta: 0:05:27 lr: 0.000297 loss: 3.2628 (3.1487) grad_norm: 1.7577 (1.8115) time: 0.5028 [2021-03-26 14:30:20 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 620/1251] eta: 0:05:22 lr: 0.000297 loss: 3.0738 (3.1459) grad_norm: 1.7215 (1.8138) time: 0.5048 [2021-03-26 14:30:25 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 630/1251] eta: 0:05:17 lr: 0.000297 loss: 3.3181 (3.1501) grad_norm: 1.7645 (1.8139) time: 0.5066 [2021-03-26 14:30:30 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 640/1251] eta: 0:05:12 lr: 0.000297 loss: 3.2911 (3.1482) grad_norm: 1.8336 (1.8148) time: 0.5017 [2021-03-26 14:30:36 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 650/1251] eta: 0:05:07 lr: 0.000296 loss: 3.1119 (3.1477) grad_norm: 1.8336 (1.8154) time: 0.5073 [2021-03-26 14:30:41 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 660/1251] eta: 0:05:02 lr: 0.000296 loss: 3.2552 (3.1485) grad_norm: 1.8179 (1.8153) time: 0.5073 [2021-03-26 14:30:46 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 670/1251] eta: 0:04:56 lr: 0.000296 loss: 3.1968 (3.1469) grad_norm: 1.8066 (1.8147) time: 0.5027 [2021-03-26 14:30:51 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 680/1251] eta: 0:04:51 lr: 0.000296 loss: 3.2942 (3.1485) grad_norm: 1.8066 (1.8161) time: 0.5046 [2021-03-26 14:30:56 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 690/1251] eta: 0:04:46 lr: 0.000296 loss: 3.3728 (3.1484) grad_norm: 1.7516 (1.8151) time: 0.5071 [2021-03-26 14:31:01 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 700/1251] eta: 0:04:41 lr: 0.000296 loss: 3.3067 (3.1493) grad_norm: 1.8610 (1.8183) time: 0.5023 [2021-03-26 14:31:06 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 710/1251] eta: 0:04:36 lr: 0.000296 loss: 3.2077 (3.1472) grad_norm: 1.8182 (1.8178) time: 0.5004 [2021-03-26 14:31:11 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 720/1251] eta: 0:04:31 lr: 0.000296 loss: 3.1638 (3.1467) grad_norm: 1.7556 (1.8186) time: 0.5042 [2021-03-26 14:31:16 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 730/1251] eta: 0:04:25 lr: 0.000296 loss: 3.1648 (3.1477) grad_norm: 1.7959 (1.8184) time: 0.5050 [2021-03-26 14:31:21 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 740/1251] eta: 0:04:20 lr: 0.000296 loss: 3.1818 (3.1458) grad_norm: 1.8062 (1.8199) time: 0.5172 [2021-03-26 14:31:26 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 750/1251] eta: 0:04:15 lr: 0.000296 loss: 3.1978 (3.1491) grad_norm: 1.8062 (1.8196) time: 0.5202 [2021-03-26 14:31:31 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 760/1251] eta: 0:04:10 lr: 0.000296 loss: 3.2574 (3.1472) grad_norm: 1.7876 (1.8203) time: 0.5129 [2021-03-26 14:31:36 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 770/1251] eta: 0:04:05 lr: 0.000296 loss: 3.2574 (3.1503) grad_norm: 1.7633 (1.8203) time: 0.5040 [2021-03-26 14:31:41 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 780/1251] eta: 0:04:00 lr: 0.000296 loss: 3.2696 (3.1506) grad_norm: 1.7378 (1.8202) time: 0.5016 [2021-03-26 14:31:47 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 790/1251] eta: 0:03:55 lr: 0.000296 loss: 3.1701 (3.1486) grad_norm: 1.7817 (1.8199) time: 0.5053 [2021-03-26 14:31:51 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 800/1251] eta: 0:03:50 lr: 0.000296 loss: 3.0710 (3.1483) grad_norm: 1.7913 (1.8200) time: 0.4996 [2021-03-26 14:31:57 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 810/1251] eta: 0:03:45 lr: 0.000296 loss: 2.9950 (3.1457) grad_norm: 1.7773 (1.8193) time: 0.5002 [2021-03-26 14:32:02 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 820/1251] eta: 0:03:39 lr: 0.000296 loss: 3.1302 (3.1447) grad_norm: 1.7264 (1.8181) time: 0.5088 [2021-03-26 14:32:07 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 830/1251] eta: 0:03:34 lr: 0.000296 loss: 3.1302 (3.1437) grad_norm: 1.7643 (1.8184) time: 0.5068 [2021-03-26 14:32:12 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 840/1251] eta: 0:03:29 lr: 0.000296 loss: 3.1135 (3.1440) grad_norm: 1.6902 (1.8170) time: 0.5031 [2021-03-26 14:32:17 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 850/1251] eta: 0:03:24 lr: 0.000296 loss: 3.2301 (3.1463) grad_norm: 1.7031 (1.8167) time: 0.5067 [2021-03-26 14:32:22 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 860/1251] eta: 0:03:19 lr: 0.000296 loss: 3.1487 (3.1440) grad_norm: 1.7818 (1.8174) time: 0.5142 [2021-03-26 14:32:27 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 870/1251] eta: 0:03:14 lr: 0.000296 loss: 3.0170 (3.1421) grad_norm: 1.7777 (1.8170) time: 0.5134 [2021-03-26 14:32:32 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 880/1251] eta: 0:03:09 lr: 0.000296 loss: 3.2869 (3.1442) grad_norm: 1.7959 (1.8174) time: 0.5091 [2021-03-26 14:32:37 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 890/1251] eta: 0:03:04 lr: 0.000296 loss: 3.3528 (3.1435) grad_norm: 1.7662 (1.8170) time: 0.5042 [2021-03-26 14:32:42 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 900/1251] eta: 0:02:58 lr: 0.000296 loss: 2.9789 (3.1406) grad_norm: 1.7662 (1.8174) time: 0.4986 [2021-03-26 14:32:47 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 910/1251] eta: 0:02:53 lr: 0.000296 loss: 2.8178 (3.1368) grad_norm: 1.7713 (1.8161) time: 0.5069 [2021-03-26 14:32:52 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 920/1251] eta: 0:02:48 lr: 0.000295 loss: 2.8178 (3.1342) grad_norm: 1.6252 (1.8142) time: 0.5059 [2021-03-26 14:32:57 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 930/1251] eta: 0:02:43 lr: 0.000295 loss: 2.9174 (3.1338) grad_norm: 1.7274 (1.8143) time: 0.5016 [2021-03-26 14:33:02 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 940/1251] eta: 0:02:38 lr: 0.000295 loss: 3.1101 (3.1335) grad_norm: 1.8290 (1.8152) time: 0.5039 [2021-03-26 14:33:08 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 950/1251] eta: 0:02:33 lr: 0.000295 loss: 2.9537 (3.1334) grad_norm: 1.7971 (1.8149) time: 0.5098 [2021-03-26 14:33:13 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 960/1251] eta: 0:02:28 lr: 0.000295 loss: 2.9537 (3.1322) grad_norm: 1.7321 (1.8152) time: 0.5109 [2021-03-26 14:33:18 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 970/1251] eta: 0:02:23 lr: 0.000295 loss: 2.9711 (3.1313) grad_norm: 1.7637 (1.8152) time: 0.5073 [2021-03-26 14:33:23 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 980/1251] eta: 0:02:18 lr: 0.000295 loss: 3.1437 (3.1310) grad_norm: 1.7637 (1.8150) time: 0.5098 [2021-03-26 14:33:28 swin_small_patch4_window7_224] INFO: Epoch: [191] [ 990/1251] eta: 0:02:13 lr: 0.000295 loss: 3.0232 (3.1283) grad_norm: 1.7815 (1.8151) time: 0.5089 [2021-03-26 14:33:33 swin_small_patch4_window7_224] INFO: Epoch: [191] [1000/1251] eta: 0:02:07 lr: 0.000295 loss: 2.9821 (3.1261) grad_norm: 1.8248 (1.8159) time: 0.5065 [2021-03-26 14:33:38 swin_small_patch4_window7_224] INFO: Epoch: [191] [1010/1251] eta: 0:02:02 lr: 0.000295 loss: 3.1555 (3.1279) grad_norm: 1.8248 (1.8158) time: 0.5101 [2021-03-26 14:33:43 swin_small_patch4_window7_224] INFO: Epoch: [191] [1020/1251] eta: 0:01:57 lr: 0.000295 loss: 3.2545 (3.1270) grad_norm: 1.7063 (1.8150) time: 0.5084 [2021-03-26 14:33:48 swin_small_patch4_window7_224] INFO: Epoch: [191] [1030/1251] eta: 0:01:52 lr: 0.000295 loss: 3.1639 (3.1258) grad_norm: 1.7575 (1.8149) time: 0.5021 [2021-03-26 14:33:53 swin_small_patch4_window7_224] INFO: Epoch: [191] [1040/1251] eta: 0:01:47 lr: 0.000295 loss: 3.2620 (3.1272) grad_norm: 1.7639 (1.8145) time: 0.5055 [2021-03-26 14:33:59 swin_small_patch4_window7_224] INFO: Epoch: [191] [1050/1251] eta: 0:01:42 lr: 0.000295 loss: 3.2598 (3.1271) grad_norm: 1.7434 (1.8141) time: 0.5202 [2021-03-26 14:34:04 swin_small_patch4_window7_224] INFO: Epoch: [191] [1060/1251] eta: 0:01:37 lr: 0.000295 loss: 3.2886 (3.1276) grad_norm: 1.7222 (1.8134) time: 0.5162 [2021-03-26 14:34:09 swin_small_patch4_window7_224] INFO: Epoch: [191] [1070/1251] eta: 0:01:32 lr: 0.000295 loss: 3.3083 (3.1270) grad_norm: 1.7222 (1.8146) time: 0.5039 [2021-03-26 14:34:14 swin_small_patch4_window7_224] INFO: Epoch: [191] [1080/1251] eta: 0:01:27 lr: 0.000295 loss: 3.1836 (3.1284) grad_norm: 1.7900 (1.8142) time: 0.5051 [2021-03-26 14:34:19 swin_small_patch4_window7_224] INFO: Epoch: [191] [1090/1251] eta: 0:01:22 lr: 0.000295 loss: 3.2391 (3.1283) grad_norm: 1.7781 (1.8142) time: 0.5007 [2021-03-26 14:34:24 swin_small_patch4_window7_224] INFO: Epoch: [191] [1100/1251] eta: 0:01:16 lr: 0.000295 loss: 3.2391 (3.1288) grad_norm: 1.7781 (1.8145) time: 0.4967 [2021-03-26 14:34:29 swin_small_patch4_window7_224] INFO: Epoch: [191] [1110/1251] eta: 0:01:11 lr: 0.000295 loss: 3.1662 (3.1259) grad_norm: 1.7848 (1.8143) time: 0.5033 [2021-03-26 14:34:34 swin_small_patch4_window7_224] INFO: Epoch: [191] [1120/1251] eta: 0:01:06 lr: 0.000295 loss: 3.1383 (3.1286) grad_norm: 1.8005 (1.8156) time: 0.5093 [2021-03-26 14:34:39 swin_small_patch4_window7_224] INFO: Epoch: [191] [1130/1251] eta: 0:01:01 lr: 0.000295 loss: 3.2298 (3.1287) grad_norm: 1.8277 (1.8152) time: 0.5095 [2021-03-26 14:34:44 swin_small_patch4_window7_224] INFO: Epoch: [191] [1140/1251] eta: 0:00:56 lr: 0.000295 loss: 3.3126 (3.1307) grad_norm: 1.7773 (1.8155) time: 0.5025 [2021-03-26 14:34:49 swin_small_patch4_window7_224] INFO: Epoch: [191] [1150/1251] eta: 0:00:51 lr: 0.000295 loss: 3.2343 (3.1293) grad_norm: 1.6890 (1.8147) time: 0.4951 [2021-03-26 14:34:54 swin_small_patch4_window7_224] INFO: Epoch: [191] [1160/1251] eta: 0:00:46 lr: 0.000295 loss: 3.1413 (3.1295) grad_norm: 1.6890 (1.8142) time: 0.5012 [2021-03-26 14:34:59 swin_small_patch4_window7_224] INFO: Epoch: [191] [1170/1251] eta: 0:00:41 lr: 0.000295 loss: 3.0966 (3.1282) grad_norm: 1.7279 (1.8140) time: 0.5044 [2021-03-26 14:35:04 swin_small_patch4_window7_224] INFO: Epoch: [191] [1180/1251] eta: 0:00:36 lr: 0.000295 loss: 3.2660 (3.1297) grad_norm: 1.7333 (1.8136) time: 0.5027 [2021-03-26 14:35:09 swin_small_patch4_window7_224] INFO: Epoch: [191] [1190/1251] eta: 0:00:31 lr: 0.000294 loss: 3.3034 (3.1290) grad_norm: 1.7333 (1.8138) time: 0.5054 [2021-03-26 14:35:14 swin_small_patch4_window7_224] INFO: Epoch: [191] [1200/1251] eta: 0:00:25 lr: 0.000294 loss: 3.1605 (3.1276) grad_norm: 1.7286 (1.8126) time: 0.5084 [2021-03-26 14:35:19 swin_small_patch4_window7_224] INFO: Epoch: [191] [1210/1251] eta: 0:00:20 lr: 0.000294 loss: 3.1487 (3.1275) grad_norm: 1.7352 (1.8132) time: 0.5098 [2021-03-26 14:35:24 swin_small_patch4_window7_224] INFO: Epoch: [191] [1220/1251] eta: 0:00:15 lr: 0.000294 loss: 3.1487 (3.1269) grad_norm: 1.7772 (1.8127) time: 0.5049 [2021-03-26 14:35:29 swin_small_patch4_window7_224] INFO: Epoch: [191] [1230/1251] eta: 0:00:10 lr: 0.000294 loss: 3.0668 (3.1277) grad_norm: 1.7160 (1.8127) time: 0.4963 [2021-03-26 14:35:34 swin_small_patch4_window7_224] INFO: Epoch: [191] [1240/1251] eta: 0:00:05 lr: 0.000294 loss: 3.2189 (3.1279) grad_norm: 1.7258 (1.8124) time: 0.4984 [2021-03-26 14:35:39 swin_small_patch4_window7_224] INFO: Epoch: [191] [1250/1251] eta: 0:00:00 lr: 0.000294 loss: 3.2528 (3.1291) grad_norm: 1.7476 (1.8126) time: 0.5016 [2021-03-26 14:35:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 0.6729 (0.6729) acc1: 82.8125 (82.8125) acc5: 100.0000 (100.0000) [2021-03-26 14:35:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8145 (0.8407) acc1: 79.6875 (79.5455) acc5: 95.3125 (95.4545) [2021-03-26 14:35:54 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8287 (0.8888) acc1: 78.1250 (78.4226) acc5: 95.3125 (95.0149) [2021-03-26 14:35:56 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8256 (0.8753) acc1: 78.1250 (78.7298) acc5: 95.3125 (95.1109) [2021-03-26 14:35:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7525 (0.8602) acc1: 79.6875 (79.2302) acc5: 95.3125 (95.2744) [2021-03-26 14:35:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8087 (0.8578) acc1: 81.2500 (79.4240) acc5: 93.7500 (95.1360) [2021-03-26 14:36:13 swin_small_patch4_window7_224] INFO: * Acc@1 80.052 Acc@5 95.244 loss 0.842 [2021-03-26 14:36:13 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-26 14:36:13 swin_small_patch4_window7_224] INFO: Max accuracy: 80.19% [2021-03-26 14:36:17 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 0/1251] eta: 1:28:00 lr: 0.000294 loss: 1.9171 (1.9171) grad_norm: 1.7797 (1.7797) time: 4.2209 [2021-03-26 14:36:22 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 10/1251] eta: 0:17:35 lr: 0.000294 loss: 3.2019 (3.0941) grad_norm: 1.7797 (1.7665) time: 0.8508 [2021-03-26 14:36:27 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 20/1251] eta: 0:14:04 lr: 0.000294 loss: 3.3076 (3.2564) grad_norm: 1.7989 (1.8194) time: 0.5097 [2021-03-26 14:36:32 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 30/1251] eta: 0:12:43 lr: 0.000294 loss: 3.3173 (3.2177) grad_norm: 1.8091 (1.8463) time: 0.5018 [2021-03-26 14:36:38 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 40/1251] eta: 0:12:03 lr: 0.000294 loss: 3.0652 (3.1870) grad_norm: 1.7705 (1.8221) time: 0.5049 [2021-03-26 14:36:43 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 50/1251] eta: 0:11:37 lr: 0.000294 loss: 3.0184 (3.1214) grad_norm: 1.7469 (1.8096) time: 0.5110 [2021-03-26 14:36:48 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 60/1251] eta: 0:11:16 lr: 0.000294 loss: 3.2721 (3.1850) grad_norm: 1.7370 (1.7938) time: 0.5063 [2021-03-26 14:36:53 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 70/1251] eta: 0:11:02 lr: 0.000294 loss: 3.3940 (3.1748) grad_norm: 1.7582 (1.7959) time: 0.5108 [2021-03-26 14:36:58 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 80/1251] eta: 0:10:51 lr: 0.000294 loss: 3.1794 (3.1645) grad_norm: 1.7796 (1.8017) time: 0.5225 [2021-03-26 14:37:03 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 90/1251] eta: 0:10:39 lr: 0.000294 loss: 3.2528 (3.1604) grad_norm: 1.7324 (1.7978) time: 0.5153 [2021-03-26 14:37:08 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 100/1251] eta: 0:10:27 lr: 0.000294 loss: 3.3649 (3.1796) grad_norm: 1.8093 (nan) time: 0.4989 [2021-03-26 14:37:13 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 110/1251] eta: 0:10:18 lr: 0.000294 loss: 3.3799 (3.1722) grad_norm: 1.8449 (nan) time: 0.5005 [2021-03-26 14:37:18 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 120/1251] eta: 0:10:09 lr: 0.000294 loss: 2.9043 (3.1505) grad_norm: 1.7979 (nan) time: 0.5055 [2021-03-26 14:37:23 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 130/1251] eta: 0:10:01 lr: 0.000294 loss: 2.9848 (3.1557) grad_norm: 1.7979 (nan) time: 0.5083 [2021-03-26 14:37:28 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 140/1251] eta: 0:09:54 lr: 0.000294 loss: 3.1237 (3.1401) grad_norm: 1.8383 (nan) time: 0.5111 [2021-03-26 14:37:34 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 150/1251] eta: 0:09:46 lr: 0.000294 loss: 3.0596 (3.1266) grad_norm: 1.8503 (nan) time: 0.5059 [2021-03-26 14:37:39 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 160/1251] eta: 0:09:38 lr: 0.000294 loss: 3.2907 (3.1311) grad_norm: 1.8319 (nan) time: 0.5022 [2021-03-26 14:37:44 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 170/1251] eta: 0:09:31 lr: 0.000294 loss: 3.2856 (3.1313) grad_norm: 1.7952 (nan) time: 0.5015 [2021-03-26 14:37:49 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 180/1251] eta: 0:09:24 lr: 0.000294 loss: 3.1850 (3.1311) grad_norm: 1.7568 (nan) time: 0.4999 [2021-03-26 14:37:54 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 190/1251] eta: 0:09:18 lr: 0.000294 loss: 3.1923 (3.1243) grad_norm: 1.6567 (nan) time: 0.5017 [2021-03-26 14:37:59 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 200/1251] eta: 0:09:12 lr: 0.000293 loss: 3.2035 (3.1282) grad_norm: 1.7255 (nan) time: 0.5076 [2021-03-26 14:38:04 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 210/1251] eta: 0:09:05 lr: 0.000293 loss: 3.2035 (3.1238) grad_norm: 1.7970 (nan) time: 0.5032 [2021-03-26 14:38:09 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 220/1251] eta: 0:08:59 lr: 0.000293 loss: 3.1761 (3.1276) grad_norm: 1.7803 (nan) time: 0.4995 [2021-03-26 14:38:14 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 230/1251] eta: 0:08:52 lr: 0.000293 loss: 3.2804 (3.1355) grad_norm: 1.8829 (nan) time: 0.5011 [2021-03-26 14:38:19 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 240/1251] eta: 0:08:47 lr: 0.000293 loss: 3.3361 (3.1321) grad_norm: 1.8541 (nan) time: 0.5066 [2021-03-26 14:38:24 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 250/1251] eta: 0:08:41 lr: 0.000293 loss: 3.2890 (3.1335) grad_norm: 1.7874 (nan) time: 0.5096 [2021-03-26 14:38:29 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 260/1251] eta: 0:08:35 lr: 0.000293 loss: 3.0578 (3.1239) grad_norm: 1.7176 (nan) time: 0.5006 [2021-03-26 14:38:34 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 270/1251] eta: 0:08:29 lr: 0.000293 loss: 3.0031 (3.1191) grad_norm: 1.7896 (nan) time: 0.5039 [2021-03-26 14:38:39 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 280/1251] eta: 0:08:24 lr: 0.000293 loss: 2.9463 (3.1099) grad_norm: 1.7997 (nan) time: 0.5085 [2021-03-26 14:38:44 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 290/1251] eta: 0:08:18 lr: 0.000293 loss: 2.9463 (3.1086) grad_norm: 1.7903 (nan) time: 0.5035 [2021-03-26 14:38:49 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 300/1251] eta: 0:08:12 lr: 0.000293 loss: 3.2007 (3.1082) grad_norm: 1.7903 (nan) time: 0.4983 [2021-03-26 14:38:54 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 310/1251] eta: 0:08:07 lr: 0.000293 loss: 3.0766 (3.1076) grad_norm: 1.7994 (nan) time: 0.5054 [2021-03-26 14:38:59 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 320/1251] eta: 0:08:01 lr: 0.000293 loss: 3.1613 (3.1080) grad_norm: 1.8088 (nan) time: 0.5108 [2021-03-26 14:39:04 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 330/1251] eta: 0:07:56 lr: 0.000293 loss: 3.2860 (3.1129) grad_norm: 1.9006 (nan) time: 0.5029 [2021-03-26 14:39:09 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 340/1251] eta: 0:07:50 lr: 0.000293 loss: 3.3002 (3.1138) grad_norm: 1.8472 (nan) time: 0.5088 [2021-03-26 14:39:14 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 350/1251] eta: 0:07:45 lr: 0.000293 loss: 3.0312 (3.1052) grad_norm: 1.7040 (nan) time: 0.5132 [2021-03-26 14:39:19 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 360/1251] eta: 0:07:39 lr: 0.000293 loss: 3.0004 (3.1078) grad_norm: 1.7508 (nan) time: 0.5049 [2021-03-26 14:39:24 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 370/1251] eta: 0:07:34 lr: 0.000293 loss: 3.3757 (3.1092) grad_norm: 1.8216 (nan) time: 0.5012 [2021-03-26 14:39:30 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 380/1251] eta: 0:07:28 lr: 0.000293 loss: 3.3757 (3.1119) grad_norm: 1.7844 (nan) time: 0.5020 [2021-03-26 14:39:35 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 390/1251] eta: 0:07:23 lr: 0.000293 loss: 3.0906 (3.1118) grad_norm: 1.7764 (nan) time: 0.5011 [2021-03-26 14:39:40 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 400/1251] eta: 0:07:18 lr: 0.000293 loss: 3.2334 (3.1151) grad_norm: 1.7764 (nan) time: 0.5049 [2021-03-26 14:39:45 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 410/1251] eta: 0:07:12 lr: 0.000293 loss: 3.1919 (3.1127) grad_norm: 1.7312 (nan) time: 0.5072 [2021-03-26 14:39:50 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 420/1251] eta: 0:07:07 lr: 0.000293 loss: 3.1919 (3.1160) grad_norm: 1.7083 (nan) time: 0.5047 [2021-03-26 14:39:55 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 430/1251] eta: 0:07:02 lr: 0.000293 loss: 3.3242 (3.1170) grad_norm: 1.7949 (nan) time: 0.5036 [2021-03-26 14:40:00 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 440/1251] eta: 0:06:57 lr: 0.000293 loss: 3.3242 (3.1208) grad_norm: 1.8052 (nan) time: 0.5096 [2021-03-26 14:40:05 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 450/1251] eta: 0:06:51 lr: 0.000293 loss: 2.9629 (3.1124) grad_norm: 1.6956 (nan) time: 0.5096 [2021-03-26 14:40:10 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 460/1251] eta: 0:06:46 lr: 0.000293 loss: 2.8614 (3.1128) grad_norm: 1.6816 (nan) time: 0.4999 [2021-03-26 14:40:15 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 470/1251] eta: 0:06:40 lr: 0.000292 loss: 3.1945 (3.1140) grad_norm: 1.7420 (nan) time: 0.4978 [2021-03-26 14:40:20 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 480/1251] eta: 0:06:35 lr: 0.000292 loss: 3.4336 (3.1178) grad_norm: 1.7411 (nan) time: 0.4990 [2021-03-26 14:40:25 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 490/1251] eta: 0:06:30 lr: 0.000292 loss: 3.2673 (3.1162) grad_norm: 1.7404 (nan) time: 0.4980 [2021-03-26 14:40:30 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 500/1251] eta: 0:06:24 lr: 0.000292 loss: 3.1787 (3.1147) grad_norm: 1.6727 (nan) time: 0.5006 [2021-03-26 14:40:35 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 510/1251] eta: 0:06:19 lr: 0.000292 loss: 3.1611 (3.1107) grad_norm: 1.7156 (nan) time: 0.5035 [2021-03-26 14:40:40 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 520/1251] eta: 0:06:14 lr: 0.000292 loss: 3.1611 (3.1141) grad_norm: 1.9012 (nan) time: 0.5023 [2021-03-26 14:40:45 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 530/1251] eta: 0:06:09 lr: 0.000292 loss: 3.1168 (3.1113) grad_norm: 1.8413 (nan) time: 0.5043 [2021-03-26 14:40:50 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 540/1251] eta: 0:06:04 lr: 0.000292 loss: 3.3013 (3.1166) grad_norm: 1.7512 (nan) time: 0.5120 [2021-03-26 14:40:55 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 550/1251] eta: 0:05:59 lr: 0.000292 loss: 3.1662 (3.1143) grad_norm: 1.7282 (nan) time: 0.5155 [2021-03-26 14:41:00 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 560/1251] eta: 0:05:53 lr: 0.000292 loss: 3.0253 (3.1136) grad_norm: 1.8164 (nan) time: 0.5129 [2021-03-26 14:41:05 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 570/1251] eta: 0:05:48 lr: 0.000292 loss: 3.0420 (3.1131) grad_norm: 1.9259 (nan) time: 0.5063 [2021-03-26 14:41:10 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 580/1251] eta: 0:05:43 lr: 0.000292 loss: 2.7791 (3.1122) grad_norm: 1.8305 (nan) time: 0.5003 [2021-03-26 14:41:16 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 590/1251] eta: 0:05:38 lr: 0.000292 loss: 3.1010 (3.1121) grad_norm: 1.7486 (nan) time: 0.5101 [2021-03-26 14:41:21 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 600/1251] eta: 0:05:33 lr: 0.000292 loss: 3.1509 (3.1145) grad_norm: 1.7558 (nan) time: 0.5160 [2021-03-26 14:41:26 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 610/1251] eta: 0:05:28 lr: 0.000292 loss: 3.1038 (3.1147) grad_norm: 1.7907 (nan) time: 0.5082 [2021-03-26 14:41:31 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 620/1251] eta: 0:05:22 lr: 0.000292 loss: 3.0580 (3.1112) grad_norm: 1.8136 (nan) time: 0.5014 [2021-03-26 14:41:36 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 630/1251] eta: 0:05:17 lr: 0.000292 loss: 2.9902 (3.1123) grad_norm: 1.8256 (nan) time: 0.4948 [2021-03-26 14:41:41 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 640/1251] eta: 0:05:12 lr: 0.000292 loss: 3.3888 (3.1131) grad_norm: 1.7924 (nan) time: 0.5015 [2021-03-26 14:41:46 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 650/1251] eta: 0:05:07 lr: 0.000292 loss: 3.2444 (3.1104) grad_norm: 1.7380 (nan) time: 0.5081 [2021-03-26 14:41:51 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 660/1251] eta: 0:05:01 lr: 0.000292 loss: 3.2011 (3.1123) grad_norm: 1.7232 (nan) time: 0.5021 [2021-03-26 14:41:56 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 670/1251] eta: 0:04:56 lr: 0.000292 loss: 3.2027 (3.1133) grad_norm: 1.6966 (nan) time: 0.5003 [2021-03-26 14:42:01 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 680/1251] eta: 0:04:51 lr: 0.000292 loss: 3.1248 (3.1125) grad_norm: 1.7236 (nan) time: 0.5009 [2021-03-26 14:42:06 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 690/1251] eta: 0:04:46 lr: 0.000292 loss: 3.1022 (3.1114) grad_norm: 1.7719 (nan) time: 0.4979 [2021-03-26 14:42:11 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 700/1251] eta: 0:04:41 lr: 0.000292 loss: 3.0869 (3.1112) grad_norm: 1.7607 (nan) time: 0.4991 [2021-03-26 14:42:16 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 710/1251] eta: 0:04:35 lr: 0.000292 loss: 3.1871 (3.1138) grad_norm: 1.7611 (nan) time: 0.5002 [2021-03-26 14:42:21 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 720/1251] eta: 0:04:30 lr: 0.000292 loss: 3.0944 (3.1117) grad_norm: 1.7677 (nan) time: 0.4973 [2021-03-26 14:42:26 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 730/1251] eta: 0:04:25 lr: 0.000292 loss: 3.0143 (3.1129) grad_norm: 1.6939 (nan) time: 0.5031 [2021-03-26 14:42:31 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 740/1251] eta: 0:04:20 lr: 0.000291 loss: 3.0670 (3.1120) grad_norm: 1.7977 (nan) time: 0.5151 [2021-03-26 14:42:36 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 750/1251] eta: 0:04:15 lr: 0.000291 loss: 3.2487 (3.1129) grad_norm: 1.8173 (nan) time: 0.5245 [2021-03-26 14:42:41 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 760/1251] eta: 0:04:10 lr: 0.000291 loss: 3.2553 (3.1143) grad_norm: 1.8174 (nan) time: 0.5138 [2021-03-26 14:42:47 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 770/1251] eta: 0:04:05 lr: 0.000291 loss: 3.2947 (3.1153) grad_norm: 1.8030 (nan) time: 0.5050 [2021-03-26 14:42:52 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 780/1251] eta: 0:04:00 lr: 0.000291 loss: 3.4948 (3.1176) grad_norm: 1.8030 (nan) time: 0.5090 [2021-03-26 14:42:57 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 790/1251] eta: 0:03:55 lr: 0.000291 loss: 3.3098 (3.1184) grad_norm: 1.8378 (nan) time: 0.5114 [2021-03-26 14:43:02 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 800/1251] eta: 0:03:50 lr: 0.000291 loss: 3.1588 (3.1182) grad_norm: 1.8234 (nan) time: 0.5068 [2021-03-26 14:43:07 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 810/1251] eta: 0:03:44 lr: 0.000291 loss: 3.2190 (3.1204) grad_norm: 1.8234 (nan) time: 0.5063 [2021-03-26 14:43:12 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 820/1251] eta: 0:03:39 lr: 0.000291 loss: 3.2190 (3.1208) grad_norm: 1.8495 (nan) time: 0.5168 [2021-03-26 14:43:17 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 830/1251] eta: 0:03:34 lr: 0.000291 loss: 3.3224 (3.1242) grad_norm: 1.8495 (nan) time: 0.5210 [2021-03-26 14:43:22 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 840/1251] eta: 0:03:29 lr: 0.000291 loss: 3.3841 (3.1278) grad_norm: 1.8152 (nan) time: 0.5122 [2021-03-26 14:43:27 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 850/1251] eta: 0:03:24 lr: 0.000291 loss: 3.4554 (3.1297) grad_norm: 1.7679 (nan) time: 0.5017 [2021-03-26 14:43:32 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 860/1251] eta: 0:03:19 lr: 0.000291 loss: 3.4554 (3.1292) grad_norm: 1.7038 (nan) time: 0.5019 [2021-03-26 14:43:37 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 870/1251] eta: 0:03:14 lr: 0.000291 loss: 3.5034 (3.1317) grad_norm: 1.6341 (nan) time: 0.5022 [2021-03-26 14:43:43 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 880/1251] eta: 0:03:09 lr: 0.000291 loss: 3.2958 (3.1318) grad_norm: 1.6367 (nan) time: 0.5058 [2021-03-26 14:43:48 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 890/1251] eta: 0:03:04 lr: 0.000291 loss: 3.3605 (3.1327) grad_norm: 1.7071 (nan) time: 0.5085 [2021-03-26 14:43:53 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 900/1251] eta: 0:02:58 lr: 0.000291 loss: 3.3901 (3.1344) grad_norm: 1.7454 (nan) time: 0.5058 [2021-03-26 14:43:58 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 910/1251] eta: 0:02:53 lr: 0.000291 loss: 3.3901 (3.1359) grad_norm: 1.7127 (nan) time: 0.5020 [2021-03-26 14:44:03 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 920/1251] eta: 0:02:48 lr: 0.000291 loss: 3.2837 (3.1365) grad_norm: 1.7257 (nan) time: 0.5015 [2021-03-26 14:44:08 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 930/1251] eta: 0:02:43 lr: 0.000291 loss: 3.2837 (3.1384) grad_norm: 1.8258 (nan) time: 0.4978 [2021-03-26 14:44:13 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 940/1251] eta: 0:02:38 lr: 0.000291 loss: 3.2397 (3.1375) grad_norm: 1.8661 (nan) time: 0.5033 [2021-03-26 14:44:18 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 950/1251] eta: 0:02:33 lr: 0.000291 loss: 3.2110 (3.1374) grad_norm: 1.7967 (nan) time: 0.5077 [2021-03-26 14:44:23 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 960/1251] eta: 0:02:28 lr: 0.000291 loss: 3.2084 (3.1355) grad_norm: 1.7474 (nan) time: 0.4989 [2021-03-26 14:44:28 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 970/1251] eta: 0:02:23 lr: 0.000291 loss: 2.9416 (3.1337) grad_norm: 1.7481 (nan) time: 0.4988 [2021-03-26 14:44:33 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 980/1251] eta: 0:02:17 lr: 0.000291 loss: 3.1286 (3.1338) grad_norm: 1.7661 (nan) time: 0.4974 [2021-03-26 14:44:38 swin_small_patch4_window7_224] INFO: Epoch: [192] [ 990/1251] eta: 0:02:12 lr: 0.000291 loss: 3.2805 (3.1324) grad_norm: 1.7397 (nan) time: 0.5056 [2021-03-26 14:44:43 swin_small_patch4_window7_224] INFO: Epoch: [192] [1000/1251] eta: 0:02:07 lr: 0.000290 loss: 3.1131 (3.1316) grad_norm: 1.7397 (nan) time: 0.5123 [2021-03-26 14:44:48 swin_small_patch4_window7_224] INFO: Epoch: [192] [1010/1251] eta: 0:02:02 lr: 0.000290 loss: 3.1918 (3.1325) grad_norm: 1.8284 (nan) time: 0.5075 [2021-03-26 14:44:53 swin_small_patch4_window7_224] INFO: Epoch: [192] [1020/1251] eta: 0:01:57 lr: 0.000290 loss: 3.2496 (3.1325) grad_norm: 1.8284 (nan) time: 0.5072 [2021-03-26 14:44:58 swin_small_patch4_window7_224] INFO: Epoch: [192] [1030/1251] eta: 0:01:52 lr: 0.000290 loss: 3.2124 (3.1330) grad_norm: 1.7611 (nan) time: 0.5061 [2021-03-26 14:45:03 swin_small_patch4_window7_224] INFO: Epoch: [192] [1040/1251] eta: 0:01:47 lr: 0.000290 loss: 3.1731 (3.1347) grad_norm: 1.7373 (nan) time: 0.5068 [2021-03-26 14:45:08 swin_small_patch4_window7_224] INFO: Epoch: [192] [1050/1251] eta: 0:01:42 lr: 0.000290 loss: 3.1908 (3.1336) grad_norm: 1.7578 (nan) time: 0.5140 [2021-03-26 14:45:13 swin_small_patch4_window7_224] INFO: Epoch: [192] [1060/1251] eta: 0:01:37 lr: 0.000290 loss: 2.8224 (3.1291) grad_norm: 1.7404 (nan) time: 0.5100 [2021-03-26 14:45:19 swin_small_patch4_window7_224] INFO: Epoch: [192] [1070/1251] eta: 0:01:32 lr: 0.000290 loss: 3.1042 (3.1312) grad_norm: 1.7912 (nan) time: 0.5075 [2021-03-26 14:45:24 swin_small_patch4_window7_224] INFO: Epoch: [192] [1080/1251] eta: 0:01:27 lr: 0.000290 loss: 3.4089 (3.1302) grad_norm: 1.8128 (nan) time: 0.5101 [2021-03-26 14:45:29 swin_small_patch4_window7_224] INFO: Epoch: [192] [1090/1251] eta: 0:01:21 lr: 0.000290 loss: 3.1693 (3.1303) grad_norm: 1.8536 (nan) time: 0.5043 [2021-03-26 14:45:34 swin_small_patch4_window7_224] INFO: Epoch: [192] [1100/1251] eta: 0:01:16 lr: 0.000290 loss: 3.2136 (3.1306) grad_norm: 1.7829 (nan) time: 0.5043 [2021-03-26 14:45:39 swin_small_patch4_window7_224] INFO: Epoch: [192] [1110/1251] eta: 0:01:11 lr: 0.000290 loss: 3.2553 (3.1325) grad_norm: 1.6604 (nan) time: 0.5036 [2021-03-26 14:45:44 swin_small_patch4_window7_224] INFO: Epoch: [192] [1120/1251] eta: 0:01:06 lr: 0.000290 loss: 3.3102 (3.1327) grad_norm: 1.6589 (nan) time: 0.5017 [2021-03-26 14:45:49 swin_small_patch4_window7_224] INFO: Epoch: [192] [1130/1251] eta: 0:01:01 lr: 0.000290 loss: 2.9545 (3.1316) grad_norm: 1.8174 (nan) time: 0.5030 [2021-03-26 14:45:54 swin_small_patch4_window7_224] INFO: Epoch: [192] [1140/1251] eta: 0:00:56 lr: 0.000290 loss: 3.3426 (3.1342) grad_norm: 1.8271 (nan) time: 0.5048 [2021-03-26 14:45:59 swin_small_patch4_window7_224] INFO: Epoch: [192] [1150/1251] eta: 0:00:51 lr: 0.000290 loss: 3.3156 (3.1337) grad_norm: 1.8414 (nan) time: 0.5077 [2021-03-26 14:46:04 swin_small_patch4_window7_224] INFO: Epoch: [192] [1160/1251] eta: 0:00:46 lr: 0.000290 loss: 3.2844 (3.1350) grad_norm: 1.8014 (nan) time: 0.5089 [2021-03-26 14:46:09 swin_small_patch4_window7_224] INFO: Epoch: [192] [1170/1251] eta: 0:00:41 lr: 0.000290 loss: 3.3115 (3.1355) grad_norm: 1.7012 (nan) time: 0.5029 [2021-03-26 14:46:14 swin_small_patch4_window7_224] INFO: Epoch: [192] [1180/1251] eta: 0:00:36 lr: 0.000290 loss: 3.1740 (3.1361) grad_norm: 1.7745 (nan) time: 0.5079 [2021-03-26 14:46:19 swin_small_patch4_window7_224] INFO: Epoch: [192] [1190/1251] eta: 0:00:31 lr: 0.000290 loss: 3.1981 (3.1356) grad_norm: 1.7654 (nan) time: 0.5140 [2021-03-26 14:46:24 swin_small_patch4_window7_224] INFO: Epoch: [192] [1200/1251] eta: 0:00:25 lr: 0.000290 loss: 3.1395 (3.1345) grad_norm: 1.7233 (nan) time: 0.5052 [2021-03-26 14:46:29 swin_small_patch4_window7_224] INFO: Epoch: [192] [1210/1251] eta: 0:00:20 lr: 0.000290 loss: 3.1767 (3.1354) grad_norm: 1.7754 (nan) time: 0.5016 [2021-03-26 14:46:34 swin_small_patch4_window7_224] INFO: Epoch: [192] [1220/1251] eta: 0:00:15 lr: 0.000290 loss: 3.3934 (3.1370) grad_norm: 1.7703 (nan) time: 0.5009 [2021-03-26 14:46:39 swin_small_patch4_window7_224] INFO: Epoch: [192] [1230/1251] eta: 0:00:10 lr: 0.000290 loss: 3.2826 (3.1367) grad_norm: 1.7689 (nan) time: 0.4971 [2021-03-26 14:46:44 swin_small_patch4_window7_224] INFO: Epoch: [192] [1240/1251] eta: 0:00:05 lr: 0.000290 loss: 3.1421 (3.1368) grad_norm: 1.7531 (nan) time: 0.4979 [2021-03-26 14:46:49 swin_small_patch4_window7_224] INFO: Epoch: [192] [1250/1251] eta: 0:00:00 lr: 0.000290 loss: 3.2307 (3.1366) grad_norm: 1.6890 (nan) time: 0.5087 [2021-03-26 14:47:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:01 loss: 1.0667 (1.0667) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-26 14:47:07 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7918 (0.8271) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.8807) [2021-03-26 14:47:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7918 (0.8495) acc1: 79.6875 (79.0179) acc5: 95.3125 (95.4613) [2021-03-26 14:47:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8082 (0.8335) acc1: 79.6875 (79.2843) acc5: 95.3125 (95.4637) [2021-03-26 14:47:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8174 (0.8458) acc1: 79.6875 (79.1540) acc5: 95.3125 (95.2363) [2021-03-26 14:47:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8238 (0.8333) acc1: 79.6875 (79.6800) acc5: 95.3125 (95.4240) [2021-03-26 14:47:25 swin_small_patch4_window7_224] INFO: * Acc@1 80.326 Acc@5 95.382 loss 0.819 [2021-03-26 14:47:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.3% [2021-03-26 14:47:25 swin_small_patch4_window7_224] INFO: Max accuracy: 80.33% [2021-03-26 14:47:29 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 0/1251] eta: 1:30:09 lr: 0.000290 loss: 3.7424 (3.7424) grad_norm: 1.6486 (1.6486) time: 4.3242 [2021-03-26 14:47:34 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 10/1251] eta: 0:17:55 lr: 0.000290 loss: 3.1218 (3.0656) grad_norm: 1.8055 (1.7971) time: 0.8663 [2021-03-26 14:47:39 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 20/1251] eta: 0:14:10 lr: 0.000289 loss: 3.1218 (3.0599) grad_norm: 1.8358 (1.8422) time: 0.5094 [2021-03-26 14:47:44 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 30/1251] eta: 0:12:50 lr: 0.000289 loss: 3.2521 (3.0648) grad_norm: 1.8358 (1.8329) time: 0.5014 [2021-03-26 14:47:49 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 40/1251] eta: 0:12:06 lr: 0.000289 loss: 3.3901 (3.1381) grad_norm: 1.7994 (1.8351) time: 0.5036 [2021-03-26 14:47:55 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 50/1251] eta: 0:11:37 lr: 0.000289 loss: 3.2287 (3.1281) grad_norm: 1.8155 (1.8298) time: 0.5022 [2021-03-26 14:47:59 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 60/1251] eta: 0:11:15 lr: 0.000289 loss: 3.2257 (3.1493) grad_norm: 1.8155 (1.8282) time: 0.5000 [2021-03-26 14:48:05 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 70/1251] eta: 0:10:58 lr: 0.000289 loss: 2.9116 (3.0949) grad_norm: 1.7161 (1.8149) time: 0.5000 [2021-03-26 14:48:10 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 80/1251] eta: 0:10:45 lr: 0.000289 loss: 2.9116 (3.1188) grad_norm: 1.7161 (1.8136) time: 0.5028 [2021-03-26 14:48:15 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 90/1251] eta: 0:10:35 lr: 0.000289 loss: 3.2826 (3.1174) grad_norm: 1.7680 (1.8129) time: 0.5117 [2021-03-26 14:48:20 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 100/1251] eta: 0:10:25 lr: 0.000289 loss: 2.9744 (3.1040) grad_norm: 1.8200 (1.8184) time: 0.5107 [2021-03-26 14:48:25 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 110/1251] eta: 0:10:16 lr: 0.000289 loss: 3.1412 (3.1152) grad_norm: 1.8200 (1.8174) time: 0.5046 [2021-03-26 14:48:30 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 120/1251] eta: 0:10:08 lr: 0.000289 loss: 3.2827 (3.1209) grad_norm: 1.8032 (1.8132) time: 0.5098 [2021-03-26 14:48:35 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 130/1251] eta: 0:10:00 lr: 0.000289 loss: 3.0376 (3.0929) grad_norm: 1.7574 (1.8114) time: 0.5097 [2021-03-26 14:48:40 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 140/1251] eta: 0:09:52 lr: 0.000289 loss: 3.0376 (3.0980) grad_norm: 1.7644 (1.8153) time: 0.5050 [2021-03-26 14:48:45 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 150/1251] eta: 0:09:45 lr: 0.000289 loss: 3.2955 (3.1177) grad_norm: 1.7576 (1.8126) time: 0.5073 [2021-03-26 14:48:50 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 160/1251] eta: 0:09:38 lr: 0.000289 loss: 3.2715 (3.1123) grad_norm: 1.7494 (1.8107) time: 0.5133 [2021-03-26 14:48:55 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 170/1251] eta: 0:09:32 lr: 0.000289 loss: 3.0356 (3.1125) grad_norm: 1.7529 (1.8169) time: 0.5122 [2021-03-26 14:49:01 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 180/1251] eta: 0:09:25 lr: 0.000289 loss: 3.4459 (3.1284) grad_norm: 1.8008 (1.8182) time: 0.5089 [2021-03-26 14:49:06 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 190/1251] eta: 0:09:19 lr: 0.000289 loss: 3.3058 (3.1259) grad_norm: 1.8268 (1.8201) time: 0.5064 [2021-03-26 14:49:11 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 200/1251] eta: 0:09:12 lr: 0.000289 loss: 3.0718 (3.1136) grad_norm: 1.8159 (1.8250) time: 0.5082 [2021-03-26 14:49:16 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 210/1251] eta: 0:09:06 lr: 0.000289 loss: 3.0114 (3.1122) grad_norm: 1.7111 (1.8191) time: 0.5085 [2021-03-26 14:49:21 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 220/1251] eta: 0:09:00 lr: 0.000289 loss: 3.2603 (3.1124) grad_norm: 1.7067 (1.8176) time: 0.5014 [2021-03-26 14:49:26 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 230/1251] eta: 0:08:54 lr: 0.000289 loss: 3.0820 (3.1087) grad_norm: 1.8156 (1.8206) time: 0.5016 [2021-03-26 14:49:31 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 240/1251] eta: 0:08:48 lr: 0.000289 loss: 3.0719 (3.1090) grad_norm: 1.7774 (1.8167) time: 0.5059 [2021-03-26 14:49:36 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 250/1251] eta: 0:08:42 lr: 0.000289 loss: 3.0719 (3.1020) grad_norm: 1.7476 (1.8170) time: 0.5088 [2021-03-26 14:49:41 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 260/1251] eta: 0:08:36 lr: 0.000289 loss: 3.0610 (3.0963) grad_norm: 1.7623 (1.8177) time: 0.5056 [2021-03-26 14:49:46 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 270/1251] eta: 0:08:30 lr: 0.000289 loss: 3.0660 (3.0947) grad_norm: 1.7698 (1.8161) time: 0.5014 [2021-03-26 14:49:51 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 280/1251] eta: 0:08:25 lr: 0.000289 loss: 3.2671 (3.1010) grad_norm: 1.7840 (1.8327) time: 0.5070 [2021-03-26 14:49:56 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 290/1251] eta: 0:08:19 lr: 0.000288 loss: 3.2905 (3.0971) grad_norm: 1.8350 (1.8325) time: 0.5121 [2021-03-26 14:50:01 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 300/1251] eta: 0:08:13 lr: 0.000288 loss: 3.2288 (3.0959) grad_norm: 1.8385 (1.8347) time: 0.5070 [2021-03-26 14:50:06 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 310/1251] eta: 0:08:08 lr: 0.000288 loss: 3.3375 (3.1006) grad_norm: 1.7616 (1.8302) time: 0.5001 [2021-03-26 14:50:11 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 320/1251] eta: 0:08:02 lr: 0.000288 loss: 2.9004 (3.0888) grad_norm: 1.7171 (1.8301) time: 0.5063 [2021-03-26 14:50:16 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 330/1251] eta: 0:07:56 lr: 0.000288 loss: 2.7973 (3.0893) grad_norm: 1.7494 (1.8302) time: 0.5072 [2021-03-26 14:50:21 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 340/1251] eta: 0:07:51 lr: 0.000288 loss: 3.1689 (3.0859) grad_norm: 1.7642 (1.8315) time: 0.5025 [2021-03-26 14:50:26 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 350/1251] eta: 0:07:45 lr: 0.000288 loss: 2.8851 (3.0809) grad_norm: 1.8260 (1.8363) time: 0.5002 [2021-03-26 14:50:31 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 360/1251] eta: 0:07:40 lr: 0.000288 loss: 2.9548 (3.0835) grad_norm: 1.8281 (1.8369) time: 0.5019 [2021-03-26 14:50:36 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 370/1251] eta: 0:07:34 lr: 0.000288 loss: 3.1948 (3.0802) grad_norm: 1.8613 (1.8365) time: 0.5053 [2021-03-26 14:50:41 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 380/1251] eta: 0:07:29 lr: 0.000288 loss: 3.0808 (3.0821) grad_norm: 1.7359 (1.8332) time: 0.4995 [2021-03-26 14:50:47 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 390/1251] eta: 0:07:23 lr: 0.000288 loss: 3.0783 (3.0783) grad_norm: 1.6975 (1.8308) time: 0.5031 [2021-03-26 14:50:52 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 400/1251] eta: 0:07:18 lr: 0.000288 loss: 3.2413 (3.0838) grad_norm: 1.7293 (1.8284) time: 0.5078 [2021-03-26 14:50:57 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 410/1251] eta: 0:07:13 lr: 0.000288 loss: 3.2413 (3.0843) grad_norm: 1.7319 (1.8267) time: 0.5060 [2021-03-26 14:51:02 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 420/1251] eta: 0:07:07 lr: 0.000288 loss: 3.0293 (3.0860) grad_norm: 1.7619 (1.8256) time: 0.5024 [2021-03-26 14:51:07 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 430/1251] eta: 0:07:02 lr: 0.000288 loss: 3.1690 (3.0827) grad_norm: 1.7962 (1.8258) time: 0.5050 [2021-03-26 14:51:12 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 440/1251] eta: 0:06:57 lr: 0.000288 loss: 3.3055 (3.0858) grad_norm: 1.7633 (1.8247) time: 0.5093 [2021-03-26 14:51:17 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 450/1251] eta: 0:06:51 lr: 0.000288 loss: 3.1622 (3.0832) grad_norm: 1.7616 (1.8232) time: 0.5000 [2021-03-26 14:51:22 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 460/1251] eta: 0:06:46 lr: 0.000288 loss: 3.1015 (3.0843) grad_norm: 1.6994 (1.8206) time: 0.5014 [2021-03-26 14:51:27 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 470/1251] eta: 0:06:41 lr: 0.000288 loss: 3.1037 (3.0836) grad_norm: 1.6917 (1.8175) time: 0.5069 [2021-03-26 14:51:32 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 480/1251] eta: 0:06:35 lr: 0.000288 loss: 2.8679 (3.0778) grad_norm: 1.7467 (1.8184) time: 0.5057 [2021-03-26 14:51:37 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 490/1251] eta: 0:06:30 lr: 0.000288 loss: 2.8061 (3.0749) grad_norm: 1.7966 (1.8229) time: 0.5026 [2021-03-26 14:51:42 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 500/1251] eta: 0:06:25 lr: 0.000288 loss: 3.2507 (3.0799) grad_norm: 1.8430 (1.8242) time: 0.4992 [2021-03-26 14:51:47 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 510/1251] eta: 0:06:20 lr: 0.000288 loss: 3.2435 (3.0786) grad_norm: 1.8695 (1.8274) time: 0.5020 [2021-03-26 14:51:52 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 520/1251] eta: 0:06:14 lr: 0.000288 loss: 3.0994 (3.0776) grad_norm: 1.8443 (1.8264) time: 0.5075 [2021-03-26 14:51:57 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 530/1251] eta: 0:06:09 lr: 0.000288 loss: 3.3245 (3.0838) grad_norm: 1.7184 (1.8238) time: 0.5069 [2021-03-26 14:52:02 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 540/1251] eta: 0:06:04 lr: 0.000288 loss: 3.2857 (3.0850) grad_norm: 1.7184 (1.8241) time: 0.5088 [2021-03-26 14:52:08 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 550/1251] eta: 0:05:59 lr: 0.000288 loss: 3.0394 (3.0830) grad_norm: 1.8252 (1.8238) time: 0.5238 [2021-03-26 14:52:13 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 560/1251] eta: 0:05:54 lr: 0.000287 loss: 3.0076 (3.0832) grad_norm: 1.8119 (1.8319) time: 0.5284 [2021-03-26 14:52:18 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 570/1251] eta: 0:05:49 lr: 0.000287 loss: 3.2711 (3.0856) grad_norm: 1.7541 (1.8319) time: 0.5116 [2021-03-26 14:52:23 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 580/1251] eta: 0:05:44 lr: 0.000287 loss: 3.3748 (3.0868) grad_norm: 1.6893 (1.8306) time: 0.5016 [2021-03-26 14:52:28 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 590/1251] eta: 0:05:38 lr: 0.000287 loss: 3.2178 (3.0874) grad_norm: 1.7436 (1.8312) time: 0.5096 [2021-03-26 14:52:33 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 600/1251] eta: 0:05:33 lr: 0.000287 loss: 3.2178 (3.0906) grad_norm: 1.7460 (1.8318) time: 0.5156 [2021-03-26 14:52:38 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 610/1251] eta: 0:05:28 lr: 0.000287 loss: 3.3701 (3.0952) grad_norm: 1.8457 (1.8328) time: 0.5059 [2021-03-26 14:52:43 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 620/1251] eta: 0:05:23 lr: 0.000287 loss: 3.2032 (3.0926) grad_norm: 1.8696 (1.8337) time: 0.4978 [2021-03-26 14:52:48 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 630/1251] eta: 0:05:18 lr: 0.000287 loss: 2.7950 (3.0906) grad_norm: 1.8630 (1.8345) time: 0.4993 [2021-03-26 14:52:53 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 640/1251] eta: 0:05:12 lr: 0.000287 loss: 2.7950 (3.0882) grad_norm: 1.8770 (1.8366) time: 0.4970 [2021-03-26 14:52:58 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 650/1251] eta: 0:05:07 lr: 0.000287 loss: 3.0225 (3.0877) grad_norm: 1.8597 (1.8354) time: 0.5053 [2021-03-26 14:53:03 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 660/1251] eta: 0:05:02 lr: 0.000287 loss: 3.2596 (3.0905) grad_norm: 1.7414 (1.8349) time: 0.5106 [2021-03-26 14:53:08 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 670/1251] eta: 0:04:57 lr: 0.000287 loss: 3.2905 (3.0940) grad_norm: 1.8019 (1.8342) time: 0.5036 [2021-03-26 14:53:14 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 680/1251] eta: 0:04:52 lr: 0.000287 loss: 3.2183 (3.0935) grad_norm: 1.7997 (1.8328) time: 0.5099 [2021-03-26 14:53:19 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 690/1251] eta: 0:04:47 lr: 0.000287 loss: 3.1761 (3.0922) grad_norm: 1.7755 (1.8319) time: 0.5134 [2021-03-26 14:53:24 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 700/1251] eta: 0:04:41 lr: 0.000287 loss: 3.3537 (3.0971) grad_norm: 1.8632 (1.8331) time: 0.5058 [2021-03-26 14:53:29 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 710/1251] eta: 0:04:36 lr: 0.000287 loss: 3.3295 (3.0973) grad_norm: 1.8822 (1.8331) time: 0.5031 [2021-03-26 14:53:34 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 720/1251] eta: 0:04:31 lr: 0.000287 loss: 3.0482 (3.0939) grad_norm: 1.7322 (1.8310) time: 0.5010 [2021-03-26 14:53:39 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 730/1251] eta: 0:04:26 lr: 0.000287 loss: 2.9487 (3.0937) grad_norm: 1.6918 (1.8292) time: 0.5065 [2021-03-26 14:53:44 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 740/1251] eta: 0:04:21 lr: 0.000287 loss: 3.1978 (3.0968) grad_norm: 1.6949 (1.8276) time: 0.5249 [2021-03-26 14:53:49 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 750/1251] eta: 0:04:16 lr: 0.000287 loss: 3.1839 (3.0964) grad_norm: 1.7411 (1.8268) time: 0.5316 [2021-03-26 14:53:55 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 760/1251] eta: 0:04:11 lr: 0.000287 loss: 3.1297 (3.0971) grad_norm: 1.7822 (1.8270) time: 0.5160 [2021-03-26 14:54:00 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 770/1251] eta: 0:04:06 lr: 0.000287 loss: 3.1297 (3.0968) grad_norm: 1.7784 (1.8266) time: 0.5022 [2021-03-26 14:54:05 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 780/1251] eta: 0:04:00 lr: 0.000287 loss: 3.0543 (3.0996) grad_norm: 1.7362 (1.8256) time: 0.5032 [2021-03-26 14:54:10 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 790/1251] eta: 0:03:55 lr: 0.000287 loss: 3.2005 (3.1018) grad_norm: 1.7446 (1.8257) time: 0.5034 [2021-03-26 14:54:15 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 800/1251] eta: 0:03:50 lr: 0.000287 loss: 3.3029 (3.1006) grad_norm: 1.7647 (1.8245) time: 0.5027 [2021-03-26 14:54:20 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 810/1251] eta: 0:03:45 lr: 0.000287 loss: 3.3234 (3.1022) grad_norm: 1.7647 (1.8241) time: 0.5079 [2021-03-26 14:54:25 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 820/1251] eta: 0:03:40 lr: 0.000287 loss: 3.0997 (3.1002) grad_norm: 1.8215 (1.8256) time: 0.5117 [2021-03-26 14:54:30 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 830/1251] eta: 0:03:35 lr: 0.000286 loss: 3.0432 (3.1007) grad_norm: 1.8426 (1.8263) time: 0.5036 [2021-03-26 14:54:35 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 840/1251] eta: 0:03:30 lr: 0.000286 loss: 3.1919 (3.0988) grad_norm: 1.8389 (1.8259) time: 0.5074 [2021-03-26 14:54:40 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 850/1251] eta: 0:03:25 lr: 0.000286 loss: 3.1919 (3.0997) grad_norm: 1.7984 (1.8260) time: 0.5152 [2021-03-26 14:54:45 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 860/1251] eta: 0:03:19 lr: 0.000286 loss: 3.3392 (3.1012) grad_norm: 1.8163 (1.8267) time: 0.5056 [2021-03-26 14:54:50 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 870/1251] eta: 0:03:14 lr: 0.000286 loss: 3.2066 (3.0985) grad_norm: 1.8163 (1.8278) time: 0.5025 [2021-03-26 14:54:55 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 880/1251] eta: 0:03:09 lr: 0.000286 loss: 2.9296 (3.0972) grad_norm: 1.7812 (1.8282) time: 0.5060 [2021-03-26 14:55:00 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 890/1251] eta: 0:03:04 lr: 0.000286 loss: 3.0691 (3.0957) grad_norm: 1.8296 (1.8294) time: 0.5047 [2021-03-26 14:55:05 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 900/1251] eta: 0:02:59 lr: 0.000286 loss: 3.1435 (3.0961) grad_norm: 1.9074 (1.8299) time: 0.5080 [2021-03-26 14:55:10 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 910/1251] eta: 0:02:54 lr: 0.000286 loss: 3.1435 (3.0963) grad_norm: 1.8425 (1.8293) time: 0.5066 [2021-03-26 14:55:15 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 920/1251] eta: 0:02:49 lr: 0.000286 loss: 3.3390 (3.0956) grad_norm: 1.7353 (1.8292) time: 0.4994 [2021-03-26 14:55:21 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 930/1251] eta: 0:02:44 lr: 0.000286 loss: 3.3297 (3.0957) grad_norm: 1.7852 (1.8298) time: 0.5134 [2021-03-26 14:55:26 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 940/1251] eta: 0:02:38 lr: 0.000286 loss: 3.3035 (3.0964) grad_norm: 1.8117 (1.8309) time: 0.5198 [2021-03-26 14:55:31 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 950/1251] eta: 0:02:33 lr: 0.000286 loss: 3.2502 (3.0976) grad_norm: 1.8275 (1.8338) time: 0.5121 [2021-03-26 14:55:36 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 960/1251] eta: 0:02:28 lr: 0.000286 loss: 3.2502 (3.0991) grad_norm: 1.9067 (1.8351) time: 0.5064 [2021-03-26 14:55:41 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 970/1251] eta: 0:02:23 lr: 0.000286 loss: 3.2610 (3.1012) grad_norm: 1.8908 (1.8367) time: 0.5045 [2021-03-26 14:55:46 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 980/1251] eta: 0:02:18 lr: 0.000286 loss: 3.0832 (3.0977) grad_norm: 1.8865 (1.8374) time: 0.5058 [2021-03-26 14:55:51 swin_small_patch4_window7_224] INFO: Epoch: [193] [ 990/1251] eta: 0:02:13 lr: 0.000286 loss: 3.0832 (3.0976) grad_norm: 1.8027 (1.8365) time: 0.5047 [2021-03-26 14:55:56 swin_small_patch4_window7_224] INFO: Epoch: [193] [1000/1251] eta: 0:02:08 lr: 0.000286 loss: 3.1477 (3.0967) grad_norm: 1.7489 (1.8358) time: 0.5079 [2021-03-26 14:56:01 swin_small_patch4_window7_224] INFO: Epoch: [193] [1010/1251] eta: 0:02:03 lr: 0.000286 loss: 3.1477 (3.0973) grad_norm: 1.7258 (1.8345) time: 0.5052 [2021-03-26 14:56:06 swin_small_patch4_window7_224] INFO: Epoch: [193] [1020/1251] eta: 0:01:57 lr: 0.000286 loss: 3.1742 (3.0973) grad_norm: 1.7258 (1.8340) time: 0.5000 [2021-03-26 14:56:11 swin_small_patch4_window7_224] INFO: Epoch: [193] [1030/1251] eta: 0:01:52 lr: 0.000286 loss: 3.1877 (3.0992) grad_norm: 1.6996 (1.8331) time: 0.4998 [2021-03-26 14:56:16 swin_small_patch4_window7_224] INFO: Epoch: [193] [1040/1251] eta: 0:01:47 lr: 0.000286 loss: 3.1360 (3.0984) grad_norm: 1.6996 (1.8322) time: 0.5033 [2021-03-26 14:56:21 swin_small_patch4_window7_224] INFO: Epoch: [193] [1050/1251] eta: 0:01:42 lr: 0.000286 loss: 3.1242 (3.0989) grad_norm: 1.7960 (1.8324) time: 0.5045 [2021-03-26 14:56:26 swin_small_patch4_window7_224] INFO: Epoch: [193] [1060/1251] eta: 0:01:37 lr: 0.000286 loss: 3.2344 (3.0997) grad_norm: 1.7990 (1.8319) time: 0.5082 [2021-03-26 14:56:32 swin_small_patch4_window7_224] INFO: Epoch: [193] [1070/1251] eta: 0:01:32 lr: 0.000286 loss: 3.2344 (3.1010) grad_norm: 1.7714 (1.8325) time: 0.5088 [2021-03-26 14:56:37 swin_small_patch4_window7_224] INFO: Epoch: [193] [1080/1251] eta: 0:01:27 lr: 0.000286 loss: 2.9398 (3.0977) grad_norm: 1.7515 (1.8318) time: 0.5019 [2021-03-26 14:56:41 swin_small_patch4_window7_224] INFO: Epoch: [193] [1090/1251] eta: 0:01:22 lr: 0.000286 loss: 2.7963 (3.0975) grad_norm: 1.7515 (1.8315) time: 0.4964 [2021-03-26 14:56:46 swin_small_patch4_window7_224] INFO: Epoch: [193] [1100/1251] eta: 0:01:16 lr: 0.000285 loss: 2.7963 (3.0942) grad_norm: 1.8125 (1.8317) time: 0.4951 [2021-03-26 14:56:51 swin_small_patch4_window7_224] INFO: Epoch: [193] [1110/1251] eta: 0:01:11 lr: 0.000285 loss: 3.1310 (3.0957) grad_norm: 1.8055 (1.8320) time: 0.5019 [2021-03-26 14:56:57 swin_small_patch4_window7_224] INFO: Epoch: [193] [1120/1251] eta: 0:01:06 lr: 0.000285 loss: 3.1539 (3.0950) grad_norm: 1.7927 (1.8322) time: 0.5045 [2021-03-26 14:57:02 swin_small_patch4_window7_224] INFO: Epoch: [193] [1130/1251] eta: 0:01:01 lr: 0.000285 loss: 2.9732 (3.0934) grad_norm: 1.7647 (1.8321) time: 0.5123 [2021-03-26 14:57:07 swin_small_patch4_window7_224] INFO: Epoch: [193] [1140/1251] eta: 0:00:56 lr: 0.000285 loss: 3.3125 (3.0954) grad_norm: 1.8088 (1.8328) time: 0.5109 [2021-03-26 14:57:12 swin_small_patch4_window7_224] INFO: Epoch: [193] [1150/1251] eta: 0:00:51 lr: 0.000285 loss: 3.0507 (3.0947) grad_norm: 1.8333 (1.8324) time: 0.5045 [2021-03-26 14:57:17 swin_small_patch4_window7_224] INFO: Epoch: [193] [1160/1251] eta: 0:00:46 lr: 0.000285 loss: 2.8991 (3.0946) grad_norm: 1.8183 (1.8327) time: 0.5052 [2021-03-26 14:57:22 swin_small_patch4_window7_224] INFO: Epoch: [193] [1170/1251] eta: 0:00:41 lr: 0.000285 loss: 2.8991 (3.0926) grad_norm: 1.8952 (1.8352) time: 0.4977 [2021-03-26 14:57:27 swin_small_patch4_window7_224] INFO: Epoch: [193] [1180/1251] eta: 0:00:36 lr: 0.000285 loss: 2.9967 (3.0915) grad_norm: 1.8466 (1.8347) time: 0.4984 [2021-03-26 14:57:32 swin_small_patch4_window7_224] INFO: Epoch: [193] [1190/1251] eta: 0:00:31 lr: 0.000285 loss: 3.1492 (3.0922) grad_norm: 1.7349 (1.8346) time: 0.5049 [2021-03-26 14:57:37 swin_small_patch4_window7_224] INFO: Epoch: [193] [1200/1251] eta: 0:00:25 lr: 0.000285 loss: 2.8645 (3.0877) grad_norm: 1.8486 (1.8347) time: 0.5024 [2021-03-26 14:57:42 swin_small_patch4_window7_224] INFO: Epoch: [193] [1210/1251] eta: 0:00:20 lr: 0.000285 loss: 2.8554 (3.0874) grad_norm: 1.8661 (1.8350) time: 0.5001 [2021-03-26 14:57:47 swin_small_patch4_window7_224] INFO: Epoch: [193] [1220/1251] eta: 0:00:15 lr: 0.000285 loss: 3.3117 (3.0887) grad_norm: 1.8029 (1.8346) time: 0.5046 [2021-03-26 14:57:52 swin_small_patch4_window7_224] INFO: Epoch: [193] [1230/1251] eta: 0:00:10 lr: 0.000285 loss: 3.3255 (3.0901) grad_norm: 1.6857 (1.8338) time: 0.5031 [2021-03-26 14:57:57 swin_small_patch4_window7_224] INFO: Epoch: [193] [1240/1251] eta: 0:00:05 lr: 0.000285 loss: 3.3983 (3.0924) grad_norm: 1.7482 (1.8338) time: 0.5017 [2021-03-26 14:58:02 swin_small_patch4_window7_224] INFO: Epoch: [193] [1250/1251] eta: 0:00:00 lr: 0.000285 loss: 3.3152 (3.0939) grad_norm: 1.7715 (1.8331) time: 0.5020 [2021-03-26 14:58:11 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:37 loss: 0.8305 (0.8305) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-26 14:58:14 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8218 (0.8105) acc1: 81.2500 (79.1193) acc5: 96.8750 (96.0227) [2021-03-26 14:58:16 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8282 (0.8362) acc1: 81.2500 (79.5387) acc5: 95.3125 (95.5357) [2021-03-26 14:58:18 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8555 (0.8457) acc1: 79.6875 (79.1331) acc5: 95.3125 (95.7157) [2021-03-26 14:58:19 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8382 (0.8420) acc1: 79.6875 (79.3826) acc5: 95.3125 (95.5030) [2021-03-26 14:58:21 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8546 (0.8554) acc1: 79.6875 (79.1680) acc5: 95.3125 (95.2960) [2021-03-26 14:58:30 swin_small_patch4_window7_224] INFO: * Acc@1 80.412 Acc@5 95.316 loss 0.832 [2021-03-26 14:58:30 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.4% [2021-03-26 14:58:30 swin_small_patch4_window7_224] INFO: Max accuracy: 80.41% [2021-03-26 14:58:34 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 0/1251] eta: 1:24:13 lr: 0.000285 loss: 2.9584 (2.9584) grad_norm: 1.8167 (1.8167) time: 4.0393 [2021-03-26 14:58:40 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 10/1251] eta: 0:17:38 lr: 0.000285 loss: 3.1228 (3.0312) grad_norm: 1.7173 (1.7414) time: 0.8528 [2021-03-26 14:58:45 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 20/1251] eta: 0:14:17 lr: 0.000285 loss: 3.1828 (3.0263) grad_norm: 1.7842 (1.8101) time: 0.5298 [2021-03-26 14:58:50 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 30/1251] eta: 0:13:01 lr: 0.000285 loss: 3.2053 (3.0365) grad_norm: 1.7842 (1.7913) time: 0.5227 [2021-03-26 14:58:55 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 40/1251] eta: 0:12:13 lr: 0.000285 loss: 3.1946 (3.0988) grad_norm: 1.7089 (1.7871) time: 0.5106 [2021-03-26 14:59:00 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 50/1251] eta: 0:11:44 lr: 0.000285 loss: 3.2647 (3.1259) grad_norm: 1.7542 (1.7827) time: 0.5047 [2021-03-26 14:59:05 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 60/1251] eta: 0:11:23 lr: 0.000285 loss: 3.2535 (3.1046) grad_norm: 1.6963 (1.7788) time: 0.5080 [2021-03-26 14:59:10 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 70/1251] eta: 0:11:04 lr: 0.000285 loss: 3.2535 (3.1144) grad_norm: 1.7518 (1.7773) time: 0.5007 [2021-03-26 14:59:15 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 80/1251] eta: 0:10:49 lr: 0.000285 loss: 3.2304 (3.1182) grad_norm: 1.7707 (1.7750) time: 0.4972 [2021-03-26 14:59:20 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 90/1251] eta: 0:10:37 lr: 0.000285 loss: 3.1756 (3.1138) grad_norm: 1.7551 (1.7677) time: 0.5030 [2021-03-26 14:59:25 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 100/1251] eta: 0:10:26 lr: 0.000285 loss: 3.1892 (3.1142) grad_norm: 1.7039 (1.7656) time: 0.5029 [2021-03-26 14:59:30 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 110/1251] eta: 0:10:17 lr: 0.000284 loss: 3.2274 (3.1194) grad_norm: 1.7271 (1.7654) time: 0.5034 [2021-03-26 14:59:35 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 120/1251] eta: 0:10:08 lr: 0.000284 loss: 3.3284 (3.1275) grad_norm: 1.7279 (1.7699) time: 0.5031 [2021-03-26 14:59:40 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 130/1251] eta: 0:09:59 lr: 0.000284 loss: 2.9556 (3.1051) grad_norm: 1.7289 (1.7682) time: 0.4985 [2021-03-26 14:59:45 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 140/1251] eta: 0:09:51 lr: 0.000284 loss: 2.7890 (3.0874) grad_norm: 1.7880 (1.7760) time: 0.5010 [2021-03-26 14:59:50 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 150/1251] eta: 0:09:43 lr: 0.000284 loss: 3.1562 (3.0925) grad_norm: 1.8015 (1.7779) time: 0.5004 [2021-03-26 14:59:55 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 160/1251] eta: 0:09:36 lr: 0.000284 loss: 3.1801 (3.0875) grad_norm: 1.7114 (1.7748) time: 0.4988 [2021-03-26 15:00:00 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 170/1251] eta: 0:09:28 lr: 0.000284 loss: 3.3258 (3.0931) grad_norm: 1.7175 (1.7751) time: 0.4969 [2021-03-26 15:00:05 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 180/1251] eta: 0:09:22 lr: 0.000284 loss: 3.2933 (3.0960) grad_norm: 1.7088 (1.7694) time: 0.4982 [2021-03-26 15:00:10 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 190/1251] eta: 0:09:16 lr: 0.000284 loss: 3.2735 (3.0922) grad_norm: 1.5976 (1.7656) time: 0.5082 [2021-03-26 15:00:16 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 200/1251] eta: 0:09:10 lr: 0.000284 loss: 2.9666 (3.0779) grad_norm: 1.7082 (1.7684) time: 0.5097 [2021-03-26 15:00:21 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 210/1251] eta: 0:09:03 lr: 0.000284 loss: 2.9666 (3.0756) grad_norm: 1.7118 (1.7687) time: 0.5044 [2021-03-26 15:00:25 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 220/1251] eta: 0:08:57 lr: 0.000284 loss: 3.2611 (3.0753) grad_norm: 1.7122 (1.7686) time: 0.4992 [2021-03-26 15:00:31 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 230/1251] eta: 0:08:51 lr: 0.000284 loss: 3.2410 (3.0797) grad_norm: 1.7168 (1.7678) time: 0.5005 [2021-03-26 15:00:36 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 240/1251] eta: 0:08:45 lr: 0.000284 loss: 3.1365 (3.0759) grad_norm: 1.7302 (1.7655) time: 0.5056 [2021-03-26 15:00:41 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 250/1251] eta: 0:08:40 lr: 0.000284 loss: 3.0491 (3.0726) grad_norm: 1.7880 (1.7710) time: 0.5151 [2021-03-26 15:00:46 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 260/1251] eta: 0:08:34 lr: 0.000284 loss: 3.0632 (3.0699) grad_norm: 1.8687 (1.7745) time: 0.5116 [2021-03-26 15:00:51 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 270/1251] eta: 0:08:28 lr: 0.000284 loss: 3.1061 (3.0692) grad_norm: 1.8337 (1.7810) time: 0.5017 [2021-03-26 15:00:56 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 280/1251] eta: 0:08:23 lr: 0.000284 loss: 3.1877 (3.0768) grad_norm: 1.8598 (1.7920) time: 0.5055 [2021-03-26 15:01:01 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 290/1251] eta: 0:08:17 lr: 0.000284 loss: 3.2612 (3.0801) grad_norm: 1.8263 (1.7933) time: 0.5044 [2021-03-26 15:01:06 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 300/1251] eta: 0:08:11 lr: 0.000284 loss: 3.2475 (3.0864) grad_norm: 1.7340 (1.7899) time: 0.5024 [2021-03-26 15:01:11 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 310/1251] eta: 0:08:06 lr: 0.000284 loss: 3.1532 (3.0857) grad_norm: 1.7340 (1.7944) time: 0.5053 [2021-03-26 15:01:16 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 320/1251] eta: 0:08:00 lr: 0.000284 loss: 3.1532 (3.0878) grad_norm: 1.7662 (1.7963) time: 0.5030 [2021-03-26 15:01:21 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 330/1251] eta: 0:07:55 lr: 0.000284 loss: 3.3944 (3.0940) grad_norm: 1.8358 (1.7991) time: 0.5036 [2021-03-26 15:01:26 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 340/1251] eta: 0:07:49 lr: 0.000284 loss: 3.1577 (3.0948) grad_norm: 1.7709 (1.7986) time: 0.5070 [2021-03-26 15:01:31 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 350/1251] eta: 0:07:44 lr: 0.000284 loss: 3.0320 (3.0934) grad_norm: 1.8414 (inf) time: 0.5007 [2021-03-26 15:01:36 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 360/1251] eta: 0:07:38 lr: 0.000284 loss: 3.0946 (3.0905) grad_norm: 1.8414 (inf) time: 0.5000 [2021-03-26 15:01:41 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 370/1251] eta: 0:07:33 lr: 0.000284 loss: 3.1130 (3.0940) grad_norm: 1.8121 (inf) time: 0.5044 [2021-03-26 15:01:46 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 380/1251] eta: 0:07:27 lr: 0.000283 loss: 3.2116 (3.0928) grad_norm: 1.8326 (inf) time: 0.5022 [2021-03-26 15:01:51 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 390/1251] eta: 0:07:22 lr: 0.000283 loss: 3.1335 (3.0901) grad_norm: 1.8041 (inf) time: 0.4984 [2021-03-26 15:01:56 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 400/1251] eta: 0:07:17 lr: 0.000283 loss: 2.9788 (3.0922) grad_norm: 1.7836 (inf) time: 0.4998 [2021-03-26 15:02:01 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 410/1251] eta: 0:07:11 lr: 0.000283 loss: 3.2716 (3.0907) grad_norm: 1.7646 (inf) time: 0.5004 [2021-03-26 15:02:06 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 420/1251] eta: 0:07:06 lr: 0.000283 loss: 3.2716 (3.0901) grad_norm: 1.8048 (inf) time: 0.5025 [2021-03-26 15:02:11 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 430/1251] eta: 0:07:00 lr: 0.000283 loss: 3.3442 (3.0913) grad_norm: 1.7464 (inf) time: 0.5023 [2021-03-26 15:02:16 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 440/1251] eta: 0:06:55 lr: 0.000283 loss: 3.3672 (3.0954) grad_norm: 1.7181 (inf) time: 0.5071 [2021-03-26 15:02:21 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 450/1251] eta: 0:06:50 lr: 0.000283 loss: 3.4175 (3.1003) grad_norm: 1.6749 (inf) time: 0.5096 [2021-03-26 15:02:27 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 460/1251] eta: 0:06:45 lr: 0.000283 loss: 3.1032 (3.0960) grad_norm: 1.6816 (inf) time: 0.5041 [2021-03-26 15:02:32 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 470/1251] eta: 0:06:40 lr: 0.000283 loss: 2.9012 (3.0901) grad_norm: 1.8251 (inf) time: 0.5081 [2021-03-26 15:02:37 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 480/1251] eta: 0:06:34 lr: 0.000283 loss: 3.1769 (3.0935) grad_norm: 1.8153 (inf) time: 0.5075 [2021-03-26 15:02:42 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 490/1251] eta: 0:06:29 lr: 0.000283 loss: 3.4131 (3.0999) grad_norm: 1.7886 (inf) time: 0.5037 [2021-03-26 15:02:47 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 500/1251] eta: 0:06:24 lr: 0.000283 loss: 3.1842 (3.0914) grad_norm: 1.7506 (inf) time: 0.5030 [2021-03-26 15:02:52 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 510/1251] eta: 0:06:19 lr: 0.000283 loss: 2.8838 (3.0926) grad_norm: 1.6863 (inf) time: 0.5055 [2021-03-26 15:02:57 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 520/1251] eta: 0:06:13 lr: 0.000283 loss: 3.2403 (3.0910) grad_norm: 1.8062 (inf) time: 0.5025 [2021-03-26 15:03:02 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 530/1251] eta: 0:06:08 lr: 0.000283 loss: 3.1709 (3.0922) grad_norm: 1.8732 (inf) time: 0.4987 [2021-03-26 15:03:07 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 540/1251] eta: 0:06:03 lr: 0.000283 loss: 3.3251 (3.0968) grad_norm: 1.7851 (inf) time: 0.4984 [2021-03-26 15:03:12 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 550/1251] eta: 0:05:58 lr: 0.000283 loss: 3.3346 (3.0979) grad_norm: 1.7823 (inf) time: 0.5073 [2021-03-26 15:03:17 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 560/1251] eta: 0:05:53 lr: 0.000283 loss: 3.3432 (3.1035) grad_norm: 1.8504 (inf) time: 0.5080 [2021-03-26 15:03:22 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 570/1251] eta: 0:05:47 lr: 0.000283 loss: 3.3505 (3.1053) grad_norm: 1.8488 (inf) time: 0.5077 [2021-03-26 15:03:27 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 580/1251] eta: 0:05:42 lr: 0.000283 loss: 3.2735 (3.1081) grad_norm: 1.8488 (inf) time: 0.5109 [2021-03-26 15:03:32 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 590/1251] eta: 0:05:37 lr: 0.000283 loss: 3.2313 (3.1104) grad_norm: 1.7884 (inf) time: 0.5028 [2021-03-26 15:03:37 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 600/1251] eta: 0:05:32 lr: 0.000283 loss: 3.1949 (3.1125) grad_norm: 1.7566 (inf) time: 0.5040 [2021-03-26 15:03:42 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 610/1251] eta: 0:05:27 lr: 0.000283 loss: 3.1643 (3.1081) grad_norm: 1.7749 (inf) time: 0.5034 [2021-03-26 15:03:47 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 620/1251] eta: 0:05:22 lr: 0.000283 loss: 2.9808 (3.1083) grad_norm: 1.8361 (inf) time: 0.5002 [2021-03-26 15:03:52 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 630/1251] eta: 0:05:16 lr: 0.000283 loss: 3.1020 (3.1092) grad_norm: 1.8577 (inf) time: 0.5009 [2021-03-26 15:03:57 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 640/1251] eta: 0:05:11 lr: 0.000283 loss: 2.8532 (3.1046) grad_norm: 1.8919 (inf) time: 0.4993 [2021-03-26 15:04:02 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 650/1251] eta: 0:05:06 lr: 0.000282 loss: 3.1391 (3.1102) grad_norm: 1.8569 (inf) time: 0.4980 [2021-03-26 15:04:07 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 660/1251] eta: 0:05:01 lr: 0.000282 loss: 3.3941 (3.1091) grad_norm: 1.7806 (inf) time: 0.5032 [2021-03-26 15:04:12 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 670/1251] eta: 0:04:56 lr: 0.000282 loss: 2.9177 (3.1057) grad_norm: 1.7858 (inf) time: 0.5041 [2021-03-26 15:04:17 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 680/1251] eta: 0:04:50 lr: 0.000282 loss: 2.7248 (3.1018) grad_norm: 1.8296 (inf) time: 0.5011 [2021-03-26 15:04:22 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 690/1251] eta: 0:04:45 lr: 0.000282 loss: 3.0203 (3.1012) grad_norm: 1.8488 (inf) time: 0.5003 [2021-03-26 15:04:27 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 700/1251] eta: 0:04:40 lr: 0.000282 loss: 3.0789 (3.1011) grad_norm: 1.8365 (inf) time: 0.5012 [2021-03-26 15:04:32 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 710/1251] eta: 0:04:35 lr: 0.000282 loss: 3.2678 (3.1030) grad_norm: 1.8365 (inf) time: 0.5027 [2021-03-26 15:04:37 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 720/1251] eta: 0:04:30 lr: 0.000282 loss: 3.1728 (3.1023) grad_norm: 1.8531 (inf) time: 0.5013 [2021-03-26 15:04:43 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 730/1251] eta: 0:04:25 lr: 0.000282 loss: 3.1307 (3.1034) grad_norm: 1.7821 (inf) time: 0.5078 [2021-03-26 15:04:48 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 740/1251] eta: 0:04:20 lr: 0.000282 loss: 3.4201 (3.1082) grad_norm: 1.8309 (inf) time: 0.5174 [2021-03-26 15:04:53 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 750/1251] eta: 0:04:15 lr: 0.000282 loss: 3.4358 (3.1105) grad_norm: 1.7842 (inf) time: 0.5128 [2021-03-26 15:04:58 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 760/1251] eta: 0:04:10 lr: 0.000282 loss: 3.2615 (3.1099) grad_norm: 1.7842 (inf) time: 0.5169 [2021-03-26 15:05:03 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 770/1251] eta: 0:04:05 lr: 0.000282 loss: 3.0299 (3.1072) grad_norm: 1.7967 (inf) time: 0.5197 [2021-03-26 15:05:08 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 780/1251] eta: 0:03:59 lr: 0.000282 loss: 3.2558 (3.1066) grad_norm: 1.8187 (inf) time: 0.5079 [2021-03-26 15:05:13 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 790/1251] eta: 0:03:54 lr: 0.000282 loss: 3.2684 (3.1074) grad_norm: 1.8699 (inf) time: 0.5037 [2021-03-26 15:05:18 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 800/1251] eta: 0:03:49 lr: 0.000282 loss: 3.3632 (3.1082) grad_norm: 1.8984 (inf) time: 0.5039 [2021-03-26 15:05:23 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 810/1251] eta: 0:03:44 lr: 0.000282 loss: 3.3122 (3.1085) grad_norm: 1.8984 (inf) time: 0.5014 [2021-03-26 15:05:28 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 820/1251] eta: 0:03:39 lr: 0.000282 loss: 3.1039 (3.1086) grad_norm: 1.8270 (inf) time: 0.4974 [2021-03-26 15:05:33 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 830/1251] eta: 0:03:34 lr: 0.000282 loss: 2.9240 (3.1049) grad_norm: 1.7774 (inf) time: 0.5034 [2021-03-26 15:05:38 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 840/1251] eta: 0:03:29 lr: 0.000282 loss: 3.0345 (3.1060) grad_norm: 1.8209 (inf) time: 0.5069 [2021-03-26 15:05:44 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 850/1251] eta: 0:03:24 lr: 0.000282 loss: 3.1253 (3.1042) grad_norm: 1.8803 (inf) time: 0.5073 [2021-03-26 15:05:49 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 860/1251] eta: 0:03:18 lr: 0.000282 loss: 3.0093 (3.1023) grad_norm: 1.8332 (inf) time: 0.5069 [2021-03-26 15:05:54 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 870/1251] eta: 0:03:13 lr: 0.000282 loss: 2.8041 (3.0962) grad_norm: 1.8718 (inf) time: 0.5030 [2021-03-26 15:05:59 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 880/1251] eta: 0:03:08 lr: 0.000282 loss: 2.8041 (3.0969) grad_norm: 1.7286 (inf) time: 0.5059 [2021-03-26 15:06:04 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 890/1251] eta: 0:03:03 lr: 0.000282 loss: 3.3036 (3.0940) grad_norm: 1.7102 (inf) time: 0.5075 [2021-03-26 15:06:09 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 900/1251] eta: 0:02:58 lr: 0.000282 loss: 3.3192 (3.0972) grad_norm: 1.7765 (inf) time: 0.5014 [2021-03-26 15:06:14 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 910/1251] eta: 0:02:53 lr: 0.000282 loss: 3.3433 (3.0960) grad_norm: 1.7957 (inf) time: 0.4992 [2021-03-26 15:06:19 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 920/1251] eta: 0:02:48 lr: 0.000281 loss: 3.1272 (3.0974) grad_norm: 1.7616 (inf) time: 0.5071 [2021-03-26 15:06:24 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 930/1251] eta: 0:02:43 lr: 0.000281 loss: 3.3727 (3.1013) grad_norm: 1.7295 (inf) time: 0.5189 [2021-03-26 15:06:29 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 940/1251] eta: 0:02:38 lr: 0.000281 loss: 3.3143 (3.1013) grad_norm: 1.8333 (inf) time: 0.5142 [2021-03-26 15:06:34 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 950/1251] eta: 0:02:33 lr: 0.000281 loss: 3.0989 (3.1009) grad_norm: 1.8333 (inf) time: 0.5032 [2021-03-26 15:06:39 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 960/1251] eta: 0:02:28 lr: 0.000281 loss: 3.1108 (3.1010) grad_norm: 1.7064 (inf) time: 0.5008 [2021-03-26 15:06:44 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 970/1251] eta: 0:02:22 lr: 0.000281 loss: 3.3855 (3.1049) grad_norm: 1.6972 (inf) time: 0.4986 [2021-03-26 15:06:49 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 980/1251] eta: 0:02:17 lr: 0.000281 loss: 3.3852 (3.1063) grad_norm: 1.7503 (inf) time: 0.4964 [2021-03-26 15:06:54 swin_small_patch4_window7_224] INFO: Epoch: [194] [ 990/1251] eta: 0:02:12 lr: 0.000281 loss: 3.2754 (3.1046) grad_norm: 1.7371 (inf) time: 0.5014 [2021-03-26 15:06:59 swin_small_patch4_window7_224] INFO: Epoch: [194] [1000/1251] eta: 0:02:07 lr: 0.000281 loss: 3.0606 (3.1038) grad_norm: 1.7657 (inf) time: 0.5080 [2021-03-26 15:07:04 swin_small_patch4_window7_224] INFO: Epoch: [194] [1010/1251] eta: 0:02:02 lr: 0.000281 loss: 3.2417 (3.1038) grad_norm: 1.7926 (inf) time: 0.5026 [2021-03-26 15:07:09 swin_small_patch4_window7_224] INFO: Epoch: [194] [1020/1251] eta: 0:01:57 lr: 0.000281 loss: 3.1929 (3.1029) grad_norm: 1.7134 (inf) time: 0.5029 [2021-03-26 15:07:14 swin_small_patch4_window7_224] INFO: Epoch: [194] [1030/1251] eta: 0:01:52 lr: 0.000281 loss: 3.1172 (3.1033) grad_norm: 1.7134 (inf) time: 0.5042 [2021-03-26 15:07:19 swin_small_patch4_window7_224] INFO: Epoch: [194] [1040/1251] eta: 0:01:47 lr: 0.000281 loss: 3.1560 (3.1034) grad_norm: 1.8300 (inf) time: 0.5043 [2021-03-26 15:07:25 swin_small_patch4_window7_224] INFO: Epoch: [194] [1050/1251] eta: 0:01:42 lr: 0.000281 loss: 3.1890 (3.1040) grad_norm: 1.7218 (inf) time: 0.5123 [2021-03-26 15:07:30 swin_small_patch4_window7_224] INFO: Epoch: [194] [1060/1251] eta: 0:01:37 lr: 0.000281 loss: 3.2549 (3.1034) grad_norm: 1.7427 (inf) time: 0.5061 [2021-03-26 15:07:35 swin_small_patch4_window7_224] INFO: Epoch: [194] [1070/1251] eta: 0:01:31 lr: 0.000281 loss: 3.3018 (3.1043) grad_norm: 1.8036 (inf) time: 0.5006 [2021-03-26 15:07:40 swin_small_patch4_window7_224] INFO: Epoch: [194] [1080/1251] eta: 0:01:26 lr: 0.000281 loss: 3.0255 (3.1024) grad_norm: 1.7469 (inf) time: 0.5016 [2021-03-26 15:07:45 swin_small_patch4_window7_224] INFO: Epoch: [194] [1090/1251] eta: 0:01:21 lr: 0.000281 loss: 2.7054 (3.0999) grad_norm: 1.8143 (inf) time: 0.5003 [2021-03-26 15:07:50 swin_small_patch4_window7_224] INFO: Epoch: [194] [1100/1251] eta: 0:01:16 lr: 0.000281 loss: 2.7661 (3.0979) grad_norm: 1.8143 (inf) time: 0.5005 [2021-03-26 15:07:55 swin_small_patch4_window7_224] INFO: Epoch: [194] [1110/1251] eta: 0:01:11 lr: 0.000281 loss: 2.9700 (3.0954) grad_norm: 1.7897 (inf) time: 0.4987 [2021-03-26 15:08:00 swin_small_patch4_window7_224] INFO: Epoch: [194] [1120/1251] eta: 0:01:06 lr: 0.000281 loss: 3.1585 (3.0976) grad_norm: 1.8421 (inf) time: 0.4976 [2021-03-26 15:08:05 swin_small_patch4_window7_224] INFO: Epoch: [194] [1130/1251] eta: 0:01:01 lr: 0.000281 loss: 3.3961 (3.0976) grad_norm: 1.9351 (inf) time: 0.4983 [2021-03-26 15:08:10 swin_small_patch4_window7_224] INFO: Epoch: [194] [1140/1251] eta: 0:00:56 lr: 0.000281 loss: 3.2024 (3.0975) grad_norm: 1.9199 (inf) time: 0.5021 [2021-03-26 15:08:15 swin_small_patch4_window7_224] INFO: Epoch: [194] [1150/1251] eta: 0:00:51 lr: 0.000281 loss: 2.9097 (3.0955) grad_norm: 1.8864 (inf) time: 0.5000 [2021-03-26 15:08:20 swin_small_patch4_window7_224] INFO: Epoch: [194] [1160/1251] eta: 0:00:46 lr: 0.000281 loss: 3.1102 (3.0973) grad_norm: 1.8915 (inf) time: 0.5026 [2021-03-26 15:08:25 swin_small_patch4_window7_224] INFO: Epoch: [194] [1170/1251] eta: 0:00:41 lr: 0.000281 loss: 3.1843 (3.0968) grad_norm: 1.8746 (inf) time: 0.5061 [2021-03-26 15:08:30 swin_small_patch4_window7_224] INFO: Epoch: [194] [1180/1251] eta: 0:00:36 lr: 0.000281 loss: 3.1855 (3.0975) grad_norm: 1.8138 (inf) time: 0.4976 [2021-03-26 15:08:35 swin_small_patch4_window7_224] INFO: Epoch: [194] [1190/1251] eta: 0:00:30 lr: 0.000280 loss: 3.1855 (3.0971) grad_norm: 1.7881 (inf) time: 0.5053 [2021-03-26 15:08:40 swin_small_patch4_window7_224] INFO: Epoch: [194] [1200/1251] eta: 0:00:25 lr: 0.000280 loss: 3.0071 (3.0978) grad_norm: 1.7527 (inf) time: 0.5111 [2021-03-26 15:08:45 swin_small_patch4_window7_224] INFO: Epoch: [194] [1210/1251] eta: 0:00:20 lr: 0.000280 loss: 2.8947 (3.0942) grad_norm: 1.7974 (inf) time: 0.5044 [2021-03-26 15:08:50 swin_small_patch4_window7_224] INFO: Epoch: [194] [1220/1251] eta: 0:00:15 lr: 0.000280 loss: 2.7113 (3.0936) grad_norm: 1.8743 (inf) time: 0.4998 [2021-03-26 15:08:55 swin_small_patch4_window7_224] INFO: Epoch: [194] [1230/1251] eta: 0:00:10 lr: 0.000280 loss: 2.8878 (3.0912) grad_norm: 1.8553 (inf) time: 0.5003 [2021-03-26 15:09:00 swin_small_patch4_window7_224] INFO: Epoch: [194] [1240/1251] eta: 0:00:05 lr: 0.000280 loss: 3.0553 (3.0913) grad_norm: 1.8483 (inf) time: 0.5007 [2021-03-26 15:09:05 swin_small_patch4_window7_224] INFO: Epoch: [194] [1250/1251] eta: 0:00:00 lr: 0.000280 loss: 3.2781 (3.0942) grad_norm: 1.8042 (inf) time: 0.4985 [2021-03-26 15:09:12 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 0.7390 (0.7390) acc1: 84.3750 (84.3750) acc5: 98.4375 (98.4375) [2021-03-26 15:09:15 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7390 (0.7972) acc1: 81.2500 (81.1080) acc5: 96.8750 (95.5966) [2021-03-26 15:09:18 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.8317 (0.8388) acc1: 79.6875 (80.1339) acc5: 95.3125 (95.3125) [2021-03-26 15:09:21 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8643 (0.8382) acc1: 79.6875 (80.1411) acc5: 95.3125 (95.5141) [2021-03-26 15:09:22 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8240 (0.8221) acc1: 79.6875 (80.2591) acc5: 95.3125 (95.6555) [2021-03-26 15:09:23 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7968 (0.8191) acc1: 79.6875 (80.3520) acc5: 96.8750 (95.7760) [2021-03-26 15:09:30 swin_small_patch4_window7_224] INFO: * Acc@1 80.398 Acc@5 95.438 loss 0.822 [2021-03-26 15:09:30 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.4% [2021-03-26 15:09:30 swin_small_patch4_window7_224] INFO: Max accuracy: 80.41% [2021-03-26 15:09:35 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 0/1251] eta: 1:31:20 lr: 0.000280 loss: 3.4445 (3.4445) grad_norm: 1.5942 (1.5942) time: 4.3808 [2021-03-26 15:09:40 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 10/1251] eta: 0:17:45 lr: 0.000280 loss: 3.1732 (3.0101) grad_norm: 1.7947 (1.7844) time: 0.8587 [2021-03-26 15:09:45 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 20/1251] eta: 0:14:14 lr: 0.000280 loss: 3.1596 (3.0074) grad_norm: 1.8439 (1.8317) time: 0.5101 [2021-03-26 15:09:50 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 30/1251] eta: 0:12:53 lr: 0.000280 loss: 3.0482 (2.9893) grad_norm: 1.8911 (1.8493) time: 0.5091 [2021-03-26 15:09:55 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 40/1251] eta: 0:12:13 lr: 0.000280 loss: 3.0482 (3.0390) grad_norm: 1.7518 (1.8280) time: 0.5127 [2021-03-26 15:10:00 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 50/1251] eta: 0:11:41 lr: 0.000280 loss: 3.0938 (3.0381) grad_norm: 1.7518 (1.8306) time: 0.5090 [2021-03-26 15:10:05 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 60/1251] eta: 0:11:20 lr: 0.000280 loss: 3.2347 (3.0865) grad_norm: 1.8610 (1.8388) time: 0.4999 [2021-03-26 15:10:10 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 70/1251] eta: 0:11:03 lr: 0.000280 loss: 3.3354 (3.0986) grad_norm: 1.8628 (1.8459) time: 0.5047 [2021-03-26 15:10:15 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 80/1251] eta: 0:10:50 lr: 0.000280 loss: 2.9848 (3.0619) grad_norm: 1.8477 (1.8546) time: 0.5076 [2021-03-26 15:10:20 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 90/1251] eta: 0:10:37 lr: 0.000280 loss: 2.8020 (3.0382) grad_norm: 1.7839 (1.8428) time: 0.5024 [2021-03-26 15:10:25 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 100/1251] eta: 0:10:26 lr: 0.000280 loss: 3.1597 (3.0520) grad_norm: 1.7837 (1.8414) time: 0.4999 [2021-03-26 15:10:30 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 110/1251] eta: 0:10:17 lr: 0.000280 loss: 3.3046 (3.0751) grad_norm: 1.7952 (1.8406) time: 0.5079 [2021-03-26 15:10:35 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 120/1251] eta: 0:10:08 lr: 0.000280 loss: 3.3020 (3.0769) grad_norm: 1.7805 (1.8394) time: 0.5074 [2021-03-26 15:10:41 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 130/1251] eta: 0:10:00 lr: 0.000280 loss: 3.1679 (3.0847) grad_norm: 1.8004 (1.8385) time: 0.5056 [2021-03-26 15:10:46 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 140/1251] eta: 0:09:53 lr: 0.000280 loss: 3.2062 (3.0831) grad_norm: 1.8812 (1.8423) time: 0.5075 [2021-03-26 15:10:51 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 150/1251] eta: 0:09:44 lr: 0.000280 loss: 3.2776 (3.0962) grad_norm: 1.8737 (1.8432) time: 0.4981 [2021-03-26 15:10:56 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 160/1251] eta: 0:09:37 lr: 0.000280 loss: 3.2626 (3.0938) grad_norm: 1.8031 (1.8411) time: 0.4951 [2021-03-26 15:11:01 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 170/1251] eta: 0:09:30 lr: 0.000280 loss: 2.9719 (3.0705) grad_norm: 1.8126 (1.8420) time: 0.4994 [2021-03-26 15:11:06 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 180/1251] eta: 0:09:23 lr: 0.000280 loss: 2.9719 (3.0780) grad_norm: 1.8657 (1.8430) time: 0.5046 [2021-03-26 15:11:11 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 190/1251] eta: 0:09:17 lr: 0.000280 loss: 3.0708 (3.0755) grad_norm: 1.9179 (1.8514) time: 0.5107 [2021-03-26 15:11:16 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 200/1251] eta: 0:09:11 lr: 0.000280 loss: 3.0708 (3.0868) grad_norm: 1.9028 (1.8495) time: 0.5053 [2021-03-26 15:11:21 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 210/1251] eta: 0:09:04 lr: 0.000279 loss: 3.4060 (3.0935) grad_norm: 1.8732 (1.8530) time: 0.5024 [2021-03-26 15:11:26 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 220/1251] eta: 0:08:58 lr: 0.000279 loss: 3.2534 (3.1000) grad_norm: 1.8512 (1.8535) time: 0.5045 [2021-03-26 15:11:31 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 230/1251] eta: 0:08:52 lr: 0.000279 loss: 3.2075 (3.1029) grad_norm: 1.8512 (1.8557) time: 0.5072 [2021-03-26 15:11:36 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 240/1251] eta: 0:08:47 lr: 0.000279 loss: 3.1586 (3.0992) grad_norm: 1.7906 (1.8545) time: 0.5114 [2021-03-26 15:11:41 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 250/1251] eta: 0:08:41 lr: 0.000279 loss: 3.2416 (3.1011) grad_norm: 1.7612 (1.8516) time: 0.5076 [2021-03-26 15:11:46 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 260/1251] eta: 0:08:35 lr: 0.000279 loss: 3.2570 (3.1008) grad_norm: 1.7560 (1.8470) time: 0.5007 [2021-03-26 15:11:51 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 270/1251] eta: 0:08:29 lr: 0.000279 loss: 3.1760 (3.1035) grad_norm: 1.7150 (1.8455) time: 0.4999 [2021-03-26 15:11:56 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 280/1251] eta: 0:08:23 lr: 0.000279 loss: 3.2415 (3.1090) grad_norm: 1.7583 (1.8458) time: 0.5033 [2021-03-26 15:12:01 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 290/1251] eta: 0:08:17 lr: 0.000279 loss: 3.2237 (3.1099) grad_norm: 1.8819 (1.8520) time: 0.5011 [2021-03-26 15:12:06 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 300/1251] eta: 0:08:12 lr: 0.000279 loss: 3.1477 (3.1057) grad_norm: 1.9385 (1.8550) time: 0.5030 [2021-03-26 15:12:11 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 310/1251] eta: 0:08:06 lr: 0.000279 loss: 3.0322 (3.1064) grad_norm: 1.8957 (1.8549) time: 0.5045 [2021-03-26 15:12:16 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 320/1251] eta: 0:08:01 lr: 0.000279 loss: 3.0063 (3.1062) grad_norm: 1.7646 (1.8528) time: 0.5071 [2021-03-26 15:12:21 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 330/1251] eta: 0:07:55 lr: 0.000279 loss: 3.0499 (3.1100) grad_norm: 1.8062 (1.8548) time: 0.5108 [2021-03-26 15:12:26 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 340/1251] eta: 0:07:50 lr: 0.000279 loss: 3.1023 (3.1056) grad_norm: 1.8176 (1.8544) time: 0.5056 [2021-03-26 15:12:31 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 350/1251] eta: 0:07:44 lr: 0.000279 loss: 3.1003 (3.1017) grad_norm: 1.9081 (1.8566) time: 0.5018 [2021-03-26 15:12:37 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 360/1251] eta: 0:07:39 lr: 0.000279 loss: 2.7424 (3.0900) grad_norm: 1.9081 (1.8563) time: 0.5014 [2021-03-26 15:12:42 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 370/1251] eta: 0:07:33 lr: 0.000279 loss: 2.8316 (3.0885) grad_norm: 1.7573 (1.8536) time: 0.5012 [2021-03-26 15:12:47 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 380/1251] eta: 0:07:28 lr: 0.000279 loss: 3.2964 (3.0938) grad_norm: 1.7686 (1.8549) time: 0.5015 [2021-03-26 15:12:52 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 390/1251] eta: 0:07:22 lr: 0.000279 loss: 3.2288 (3.0898) grad_norm: 1.8314 (1.8540) time: 0.5004 [2021-03-26 15:12:57 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 400/1251] eta: 0:07:17 lr: 0.000279 loss: 3.0376 (3.0954) grad_norm: 1.8676 (1.8553) time: 0.5000 [2021-03-26 15:13:02 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 410/1251] eta: 0:07:12 lr: 0.000279 loss: 3.3799 (3.1007) grad_norm: 1.9191 (1.8570) time: 0.5068 [2021-03-26 15:13:07 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 420/1251] eta: 0:07:06 lr: 0.000279 loss: 3.1198 (3.0960) grad_norm: 1.8675 (1.8572) time: 0.5081 [2021-03-26 15:13:12 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 430/1251] eta: 0:07:01 lr: 0.000279 loss: 2.8966 (3.0989) grad_norm: 1.8364 (1.8630) time: 0.5050 [2021-03-26 15:13:17 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 440/1251] eta: 0:06:56 lr: 0.000279 loss: 3.2302 (3.0954) grad_norm: 1.8317 (1.8637) time: 0.5046 [2021-03-26 15:13:22 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 450/1251] eta: 0:06:50 lr: 0.000279 loss: 2.7853 (3.0908) grad_norm: 1.7868 (1.8640) time: 0.5011 [2021-03-26 15:13:27 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 460/1251] eta: 0:06:45 lr: 0.000279 loss: 3.0975 (3.0909) grad_norm: 1.7720 (1.8630) time: 0.4999 [2021-03-26 15:13:32 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 470/1251] eta: 0:06:40 lr: 0.000279 loss: 3.1654 (3.0895) grad_norm: 1.7298 (1.8643) time: 0.4979 [2021-03-26 15:13:37 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 480/1251] eta: 0:06:34 lr: 0.000279 loss: 3.3493 (3.0952) grad_norm: 1.8386 (1.8643) time: 0.4980 [2021-03-26 15:13:42 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 490/1251] eta: 0:06:29 lr: 0.000278 loss: 3.3127 (3.0938) grad_norm: 1.8535 (1.8631) time: 0.5047 [2021-03-26 15:13:47 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 500/1251] eta: 0:06:24 lr: 0.000278 loss: 3.0792 (3.0966) grad_norm: 1.7565 (1.8618) time: 0.5095 [2021-03-26 15:13:52 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 510/1251] eta: 0:06:19 lr: 0.000278 loss: 3.2265 (3.0988) grad_norm: 1.7697 (1.8605) time: 0.5053 [2021-03-26 15:13:57 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 520/1251] eta: 0:06:14 lr: 0.000278 loss: 3.1702 (3.0997) grad_norm: 1.7741 (1.8597) time: 0.5004 [2021-03-26 15:14:02 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 530/1251] eta: 0:06:08 lr: 0.000278 loss: 3.1687 (3.1002) grad_norm: 1.8282 (1.8606) time: 0.5014 [2021-03-26 15:14:07 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 540/1251] eta: 0:06:03 lr: 0.000278 loss: 3.1561 (3.0980) grad_norm: 1.8390 (1.8607) time: 0.5068 [2021-03-26 15:14:12 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 550/1251] eta: 0:05:58 lr: 0.000278 loss: 3.0854 (3.0975) grad_norm: 1.8473 (1.8621) time: 0.5229 [2021-03-26 15:14:17 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 560/1251] eta: 0:05:53 lr: 0.000278 loss: 3.1818 (3.0990) grad_norm: 1.8473 (1.8603) time: 0.5176 [2021-03-26 15:14:23 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 570/1251] eta: 0:05:48 lr: 0.000278 loss: 3.0948 (3.0962) grad_norm: 1.7120 (1.8579) time: 0.5041 [2021-03-26 15:14:28 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 580/1251] eta: 0:05:43 lr: 0.000278 loss: 2.9014 (3.0927) grad_norm: 1.7466 (1.8588) time: 0.5040 [2021-03-26 15:14:33 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 590/1251] eta: 0:05:38 lr: 0.000278 loss: 3.4169 (3.0994) grad_norm: 1.7912 (1.8575) time: 0.5087 [2021-03-26 15:14:38 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 600/1251] eta: 0:05:32 lr: 0.000278 loss: 3.2612 (3.0949) grad_norm: 1.7751 (1.8561) time: 0.5068 [2021-03-26 15:14:43 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 610/1251] eta: 0:05:27 lr: 0.000278 loss: 2.6368 (3.0915) grad_norm: 1.8338 (1.8567) time: 0.5003 [2021-03-26 15:14:48 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 620/1251] eta: 0:05:22 lr: 0.000278 loss: 3.2035 (3.0948) grad_norm: 1.8935 (1.8575) time: 0.5036 [2021-03-26 15:14:53 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 630/1251] eta: 0:05:17 lr: 0.000278 loss: 3.2829 (3.0985) grad_norm: 1.8260 (1.8572) time: 0.5132 [2021-03-26 15:14:58 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 640/1251] eta: 0:05:12 lr: 0.000278 loss: 3.2829 (3.1003) grad_norm: 1.8260 (1.8553) time: 0.5087 [2021-03-26 15:15:03 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 650/1251] eta: 0:05:06 lr: 0.000278 loss: 3.3006 (3.1035) grad_norm: 1.8263 (1.8551) time: 0.4991 [2021-03-26 15:15:08 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 660/1251] eta: 0:05:01 lr: 0.000278 loss: 3.3678 (3.1047) grad_norm: 1.8539 (1.8554) time: 0.5001 [2021-03-26 15:15:13 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 670/1251] eta: 0:04:56 lr: 0.000278 loss: 3.1799 (3.1062) grad_norm: 1.8680 (1.8567) time: 0.4992 [2021-03-26 15:15:18 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 680/1251] eta: 0:04:51 lr: 0.000278 loss: 3.1634 (3.1073) grad_norm: 1.7788 (1.8553) time: 0.5042 [2021-03-26 15:15:23 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 690/1251] eta: 0:04:46 lr: 0.000278 loss: 3.1964 (3.1095) grad_norm: 1.7788 (1.8546) time: 0.5103 [2021-03-26 15:15:28 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 700/1251] eta: 0:04:41 lr: 0.000278 loss: 3.1292 (3.1058) grad_norm: 1.7321 (1.8526) time: 0.5071 [2021-03-26 15:15:33 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 710/1251] eta: 0:04:35 lr: 0.000278 loss: 3.0397 (3.1063) grad_norm: 1.7104 (1.8520) time: 0.4988 [2021-03-26 15:15:38 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 720/1251] eta: 0:04:30 lr: 0.000278 loss: 3.0090 (3.1050) grad_norm: 1.7442 (1.8514) time: 0.4970 [2021-03-26 15:15:43 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 730/1251] eta: 0:04:25 lr: 0.000278 loss: 3.1325 (3.1067) grad_norm: 1.7138 (1.8494) time: 0.5012 [2021-03-26 15:15:49 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 740/1251] eta: 0:04:20 lr: 0.000278 loss: 3.3141 (3.1072) grad_norm: 1.6912 (1.8487) time: 0.5265 [2021-03-26 15:15:54 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 750/1251] eta: 0:04:15 lr: 0.000278 loss: 3.3958 (3.1107) grad_norm: 1.8186 (1.8493) time: 0.5228 [2021-03-26 15:15:59 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 760/1251] eta: 0:04:10 lr: 0.000277 loss: 3.3590 (3.1112) grad_norm: 1.8710 (1.8506) time: 0.5075 [2021-03-26 15:16:04 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 770/1251] eta: 0:04:05 lr: 0.000277 loss: 3.3590 (3.1116) grad_norm: 1.8700 (1.8505) time: 0.5095 [2021-03-26 15:16:09 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 780/1251] eta: 0:04:00 lr: 0.000277 loss: 3.3645 (3.1131) grad_norm: 1.8495 (1.8502) time: 0.5094 [2021-03-26 15:16:14 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 790/1251] eta: 0:03:55 lr: 0.000277 loss: 3.3376 (3.1145) grad_norm: 1.8315 (1.8494) time: 0.5137 [2021-03-26 15:16:19 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 800/1251] eta: 0:03:50 lr: 0.000277 loss: 3.0655 (3.1101) grad_norm: 1.8583 (1.8502) time: 0.5068 [2021-03-26 15:16:24 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 810/1251] eta: 0:03:44 lr: 0.000277 loss: 2.9277 (3.1087) grad_norm: 1.9947 (1.8511) time: 0.5018 [2021-03-26 15:16:29 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 820/1251] eta: 0:03:39 lr: 0.000277 loss: 3.0890 (3.1091) grad_norm: 1.8683 (1.8508) time: 0.5075 [2021-03-26 15:16:34 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 830/1251] eta: 0:03:34 lr: 0.000277 loss: 3.2121 (3.1091) grad_norm: 1.8271 (1.8502) time: 0.5082 [2021-03-26 15:16:39 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 840/1251] eta: 0:03:29 lr: 0.000277 loss: 3.2513 (3.1108) grad_norm: 1.7869 (1.8497) time: 0.5046 [2021-03-26 15:16:44 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 850/1251] eta: 0:03:24 lr: 0.000277 loss: 3.1616 (3.1096) grad_norm: 1.7531 (1.8486) time: 0.5053 [2021-03-26 15:16:49 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 860/1251] eta: 0:03:19 lr: 0.000277 loss: 2.9202 (3.1067) grad_norm: 1.7552 (1.8487) time: 0.4971 [2021-03-26 15:16:54 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 870/1251] eta: 0:03:14 lr: 0.000277 loss: 3.0058 (3.1062) grad_norm: 1.8105 (1.8471) time: 0.4995 [2021-03-26 15:16:59 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 880/1251] eta: 0:03:09 lr: 0.000277 loss: 3.0914 (3.1062) grad_norm: 1.7374 (1.8475) time: 0.5032 [2021-03-26 15:17:04 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 890/1251] eta: 0:03:03 lr: 0.000277 loss: 3.1549 (3.1056) grad_norm: 1.8019 (1.8475) time: 0.5010 [2021-03-26 15:17:10 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 900/1251] eta: 0:02:58 lr: 0.000277 loss: 3.0867 (3.1032) grad_norm: 1.7983 (1.8471) time: 0.5112 [2021-03-26 15:17:15 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 910/1251] eta: 0:02:53 lr: 0.000277 loss: 3.0041 (3.1029) grad_norm: 1.7885 (1.8465) time: 0.5116 [2021-03-26 15:17:20 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 920/1251] eta: 0:02:48 lr: 0.000277 loss: 3.0216 (3.1033) grad_norm: 1.7503 (1.8453) time: 0.5035 [2021-03-26 15:17:25 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 930/1251] eta: 0:02:43 lr: 0.000277 loss: 3.1786 (3.1041) grad_norm: 1.8064 (1.8458) time: 0.5049 [2021-03-26 15:17:30 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 940/1251] eta: 0:02:38 lr: 0.000277 loss: 3.2221 (3.1055) grad_norm: 1.8063 (1.8453) time: 0.5072 [2021-03-26 15:17:35 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 950/1251] eta: 0:02:33 lr: 0.000277 loss: 3.3242 (3.1072) grad_norm: 1.8280 (1.8459) time: 0.5025 [2021-03-26 15:17:40 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 960/1251] eta: 0:02:28 lr: 0.000277 loss: 3.2088 (3.1064) grad_norm: 1.8780 (1.8463) time: 0.5058 [2021-03-26 15:17:45 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 970/1251] eta: 0:02:23 lr: 0.000277 loss: 3.2088 (3.1083) grad_norm: 1.8552 (1.8461) time: 0.5075 [2021-03-26 15:17:50 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 980/1251] eta: 0:02:17 lr: 0.000277 loss: 3.3338 (3.1104) grad_norm: 1.7972 (1.8462) time: 0.5001 [2021-03-26 15:17:55 swin_small_patch4_window7_224] INFO: Epoch: [195] [ 990/1251] eta: 0:02:12 lr: 0.000277 loss: 3.3070 (3.1118) grad_norm: 1.8015 (1.8461) time: 0.5017 [2021-03-26 15:18:00 swin_small_patch4_window7_224] INFO: Epoch: [195] [1000/1251] eta: 0:02:07 lr: 0.000277 loss: 3.1298 (3.1114) grad_norm: 1.8015 (1.8460) time: 0.5054 [2021-03-26 15:18:05 swin_small_patch4_window7_224] INFO: Epoch: [195] [1010/1251] eta: 0:02:02 lr: 0.000277 loss: 3.2297 (3.1142) grad_norm: 1.8318 (1.8467) time: 0.5093 [2021-03-26 15:18:10 swin_small_patch4_window7_224] INFO: Epoch: [195] [1020/1251] eta: 0:01:57 lr: 0.000277 loss: 3.3303 (3.1138) grad_norm: 1.8318 (1.8468) time: 0.5086 [2021-03-26 15:18:15 swin_small_patch4_window7_224] INFO: Epoch: [195] [1030/1251] eta: 0:01:52 lr: 0.000276 loss: 3.1307 (3.1137) grad_norm: 1.7385 (1.8471) time: 0.5080 [2021-03-26 15:18:20 swin_small_patch4_window7_224] INFO: Epoch: [195] [1040/1251] eta: 0:01:47 lr: 0.000276 loss: 3.1498 (3.1143) grad_norm: 1.7308 (1.8462) time: 0.5053 [2021-03-26 15:18:25 swin_small_patch4_window7_224] INFO: Epoch: [195] [1050/1251] eta: 0:01:42 lr: 0.000276 loss: 3.2131 (3.1147) grad_norm: 1.7578 (1.8463) time: 0.5010 [2021-03-26 15:18:31 swin_small_patch4_window7_224] INFO: Epoch: [195] [1060/1251] eta: 0:01:37 lr: 0.000276 loss: 3.1718 (3.1135) grad_norm: 1.8447 (1.8457) time: 0.5063 [2021-03-26 15:18:36 swin_small_patch4_window7_224] INFO: Epoch: [195] [1070/1251] eta: 0:01:32 lr: 0.000276 loss: 3.1718 (3.1143) grad_norm: 1.8122 (1.8459) time: 0.5117 [2021-03-26 15:18:41 swin_small_patch4_window7_224] INFO: Epoch: [195] [1080/1251] eta: 0:01:27 lr: 0.000276 loss: 3.1084 (3.1122) grad_norm: 1.8430 (1.8464) time: 0.5067 [2021-03-26 15:18:46 swin_small_patch4_window7_224] INFO: Epoch: [195] [1090/1251] eta: 0:01:21 lr: 0.000276 loss: 3.0732 (3.1120) grad_norm: 1.9019 (1.8474) time: 0.5021 [2021-03-26 15:18:51 swin_small_patch4_window7_224] INFO: Epoch: [195] [1100/1251] eta: 0:01:16 lr: 0.000276 loss: 3.2204 (3.1120) grad_norm: 1.8920 (1.8481) time: 0.5059 [2021-03-26 15:18:56 swin_small_patch4_window7_224] INFO: Epoch: [195] [1110/1251] eta: 0:01:11 lr: 0.000276 loss: 3.0597 (3.1122) grad_norm: 1.8368 (1.8484) time: 0.5060 [2021-03-26 15:19:01 swin_small_patch4_window7_224] INFO: Epoch: [195] [1120/1251] eta: 0:01:06 lr: 0.000276 loss: 3.0319 (3.1099) grad_norm: 1.9160 (1.8495) time: 0.5016 [2021-03-26 15:19:06 swin_small_patch4_window7_224] INFO: Epoch: [195] [1130/1251] eta: 0:01:01 lr: 0.000276 loss: 2.7022 (3.1079) grad_norm: 1.9051 (1.8499) time: 0.5014 [2021-03-26 15:19:11 swin_small_patch4_window7_224] INFO: Epoch: [195] [1140/1251] eta: 0:00:56 lr: 0.000276 loss: 3.1296 (3.1079) grad_norm: 1.8616 (1.8503) time: 0.5026 [2021-03-26 15:19:16 swin_small_patch4_window7_224] INFO: Epoch: [195] [1150/1251] eta: 0:00:51 lr: 0.000276 loss: 3.3042 (3.1102) grad_norm: 1.8866 (1.8510) time: 0.5058 [2021-03-26 15:19:21 swin_small_patch4_window7_224] INFO: Epoch: [195] [1160/1251] eta: 0:00:46 lr: 0.000276 loss: 3.2430 (3.1092) grad_norm: 1.9624 (1.8530) time: 0.5066 [2021-03-26 15:19:26 swin_small_patch4_window7_224] INFO: Epoch: [195] [1170/1251] eta: 0:00:41 lr: 0.000276 loss: 2.9867 (3.1076) grad_norm: 1.9953 (1.8544) time: 0.5017 [2021-03-26 15:19:31 swin_small_patch4_window7_224] INFO: Epoch: [195] [1180/1251] eta: 0:00:36 lr: 0.000276 loss: 2.9428 (3.1069) grad_norm: 1.9699 (1.8545) time: 0.5029 [2021-03-26 15:19:36 swin_small_patch4_window7_224] INFO: Epoch: [195] [1190/1251] eta: 0:00:31 lr: 0.000276 loss: 3.1223 (3.1081) grad_norm: 1.9034 (1.8554) time: 0.5015 [2021-03-26 15:19:41 swin_small_patch4_window7_224] INFO: Epoch: [195] [1200/1251] eta: 0:00:25 lr: 0.000276 loss: 3.1438 (3.1075) grad_norm: 1.8760 (1.8559) time: 0.4955 [2021-03-26 15:19:46 swin_small_patch4_window7_224] INFO: Epoch: [195] [1210/1251] eta: 0:00:20 lr: 0.000276 loss: 3.1392 (3.1067) grad_norm: 1.8286 (1.8563) time: 0.4962 [2021-03-26 15:19:51 swin_small_patch4_window7_224] INFO: Epoch: [195] [1220/1251] eta: 0:00:15 lr: 0.000276 loss: 3.1922 (3.1074) grad_norm: 1.9169 (1.8573) time: 0.4970 [2021-03-26 15:19:56 swin_small_patch4_window7_224] INFO: Epoch: [195] [1230/1251] eta: 0:00:10 lr: 0.000276 loss: 3.1130 (3.1062) grad_norm: 1.9525 (1.8581) time: 0.4981 [2021-03-26 15:20:01 swin_small_patch4_window7_224] INFO: Epoch: [195] [1240/1251] eta: 0:00:05 lr: 0.000276 loss: 3.1103 (3.1046) grad_norm: 1.8601 (1.8579) time: 0.4978 [2021-03-26 15:20:06 swin_small_patch4_window7_224] INFO: Epoch: [195] [1250/1251] eta: 0:00:00 lr: 0.000276 loss: 3.1532 (3.1049) grad_norm: 1.8848 (1.8585) time: 0.4963 [2021-03-26 15:20:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.7775 (0.7775) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-26 15:20:50 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7631 (0.7823) acc1: 81.2500 (81.8182) acc5: 95.3125 (96.4489) [2021-03-26 15:20:51 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7776 (0.8299) acc1: 81.2500 (80.8780) acc5: 95.3125 (95.9077) [2021-03-26 15:20:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8254 (0.8320) acc1: 79.6875 (80.4940) acc5: 95.3125 (95.8669) [2021-03-26 15:20:53 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8295 (0.8404) acc1: 78.1250 (80.6402) acc5: 95.3125 (95.6174) [2021-03-26 15:20:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8361 (0.8584) acc1: 78.1250 (80.0640) acc5: 95.3125 (95.2320) [2021-03-26 15:21:01 swin_small_patch4_window7_224] INFO: * Acc@1 80.092 Acc@5 95.306 loss 0.837 [2021-03-26 15:21:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.1% [2021-03-26 15:21:01 swin_small_patch4_window7_224] INFO: Max accuracy: 80.41% [2021-03-26 15:21:05 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 0/1251] eta: 1:22:37 lr: 0.000276 loss: 3.3276 (3.3276) grad_norm: 1.9352 (1.9352) time: 3.9626 [2021-03-26 15:21:10 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 10/1251] eta: 0:17:31 lr: 0.000276 loss: 3.1858 (3.1123) grad_norm: 1.8834 (1.9059) time: 0.8470 [2021-03-26 15:21:15 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 20/1251] eta: 0:13:54 lr: 0.000276 loss: 2.9144 (2.9082) grad_norm: 1.8655 (1.8882) time: 0.5137 [2021-03-26 15:21:20 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 30/1251] eta: 0:12:38 lr: 0.000276 loss: 3.0594 (3.0511) grad_norm: 1.8796 (1.9219) time: 0.4968 [2021-03-26 15:21:25 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 40/1251] eta: 0:11:55 lr: 0.000276 loss: 3.3624 (3.0639) grad_norm: 1.8645 (1.8996) time: 0.4995 [2021-03-26 15:21:30 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 50/1251] eta: 0:11:28 lr: 0.000275 loss: 3.1204 (3.0242) grad_norm: 1.8205 (1.8912) time: 0.4998 [2021-03-26 15:21:35 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 60/1251] eta: 0:11:10 lr: 0.000275 loss: 3.0288 (3.0362) grad_norm: 1.8849 (1.9041) time: 0.5057 [2021-03-26 15:21:40 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 70/1251] eta: 0:10:55 lr: 0.000275 loss: 3.1672 (3.0521) grad_norm: 1.9072 (1.9109) time: 0.5070 [2021-03-26 15:21:45 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 80/1251] eta: 0:10:41 lr: 0.000275 loss: 3.2111 (3.0813) grad_norm: 2.0085 (1.9481) time: 0.5026 [2021-03-26 15:21:50 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 90/1251] eta: 0:10:29 lr: 0.000275 loss: 3.1412 (3.0724) grad_norm: 2.0273 (1.9454) time: 0.4993 [2021-03-26 15:21:55 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 100/1251] eta: 0:10:19 lr: 0.000275 loss: 3.0106 (3.0686) grad_norm: 1.8800 (1.9441) time: 0.4982 [2021-03-26 15:22:00 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 110/1251] eta: 0:10:11 lr: 0.000275 loss: 3.2222 (3.0763) grad_norm: 1.9002 (1.9375) time: 0.5034 [2021-03-26 15:22:05 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 120/1251] eta: 0:10:01 lr: 0.000275 loss: 3.2520 (3.0670) grad_norm: 1.8321 (1.9278) time: 0.5015 [2021-03-26 15:22:11 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 130/1251] eta: 0:09:54 lr: 0.000275 loss: 3.2589 (3.0848) grad_norm: 1.7684 (1.9177) time: 0.5039 [2021-03-26 15:22:16 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 140/1251] eta: 0:09:47 lr: 0.000275 loss: 3.1729 (3.0912) grad_norm: 1.7714 (1.9143) time: 0.5077 [2021-03-26 15:22:21 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 150/1251] eta: 0:09:39 lr: 0.000275 loss: 3.1729 (3.1014) grad_norm: 1.9163 (1.9200) time: 0.5008 [2021-03-26 15:22:26 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 160/1251] eta: 0:09:32 lr: 0.000275 loss: 2.9772 (3.0763) grad_norm: 1.8835 (1.9149) time: 0.4976 [2021-03-26 15:22:31 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 170/1251] eta: 0:09:25 lr: 0.000275 loss: 2.8917 (3.0689) grad_norm: 1.8125 (1.9147) time: 0.4963 [2021-03-26 15:22:36 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 180/1251] eta: 0:09:19 lr: 0.000275 loss: 3.1417 (3.0718) grad_norm: 1.8274 (1.9159) time: 0.5073 [2021-03-26 15:22:41 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 190/1251] eta: 0:09:13 lr: 0.000275 loss: 3.2630 (3.0788) grad_norm: 1.8843 (1.9214) time: 0.5095 [2021-03-26 15:22:46 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 200/1251] eta: 0:09:07 lr: 0.000275 loss: 3.2238 (3.0686) grad_norm: 1.8777 (1.9159) time: 0.5026 [2021-03-26 15:22:51 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 210/1251] eta: 0:09:01 lr: 0.000275 loss: 2.7837 (3.0602) grad_norm: 1.7375 (1.9090) time: 0.5005 [2021-03-26 15:22:56 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 220/1251] eta: 0:08:54 lr: 0.000275 loss: 2.9690 (3.0638) grad_norm: 1.7457 (1.9064) time: 0.4975 [2021-03-26 15:23:01 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 230/1251] eta: 0:08:48 lr: 0.000275 loss: 3.0470 (3.0626) grad_norm: 1.8569 (1.9108) time: 0.4983 [2021-03-26 15:23:06 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 240/1251] eta: 0:08:42 lr: 0.000275 loss: 2.9559 (3.0577) grad_norm: 1.8569 (1.9085) time: 0.4996 [2021-03-26 15:23:11 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 250/1251] eta: 0:08:37 lr: 0.000275 loss: 2.9559 (3.0497) grad_norm: 1.8149 (1.9070) time: 0.5038 [2021-03-26 15:23:16 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 260/1251] eta: 0:08:31 lr: 0.000275 loss: 3.0785 (3.0436) grad_norm: 1.9128 (1.9079) time: 0.5062 [2021-03-26 15:23:21 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 270/1251] eta: 0:08:26 lr: 0.000275 loss: 3.0737 (3.0477) grad_norm: 1.9457 (1.9114) time: 0.5098 [2021-03-26 15:23:26 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 280/1251] eta: 0:08:20 lr: 0.000275 loss: 3.3341 (3.0566) grad_norm: 1.8737 (1.9097) time: 0.5109 [2021-03-26 15:23:31 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 290/1251] eta: 0:08:15 lr: 0.000275 loss: 3.0595 (3.0418) grad_norm: 1.8335 (1.9074) time: 0.5025 [2021-03-26 15:23:36 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 300/1251] eta: 0:08:09 lr: 0.000275 loss: 2.8183 (3.0411) grad_norm: 1.7899 (1.9016) time: 0.4974 [2021-03-26 15:23:41 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 310/1251] eta: 0:08:04 lr: 0.000275 loss: 3.2286 (3.0504) grad_norm: 1.8300 (1.9059) time: 0.5070 [2021-03-26 15:23:46 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 320/1251] eta: 0:07:58 lr: 0.000274 loss: 3.2680 (3.0448) grad_norm: 1.7747 (1.9011) time: 0.5084 [2021-03-26 15:23:51 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 330/1251] eta: 0:07:53 lr: 0.000274 loss: 3.0070 (3.0471) grad_norm: 1.7165 (1.8996) time: 0.4967 [2021-03-26 15:23:56 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 340/1251] eta: 0:07:47 lr: 0.000274 loss: 2.9954 (3.0403) grad_norm: 1.7497 (1.8960) time: 0.4945 [2021-03-26 15:24:01 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 350/1251] eta: 0:07:41 lr: 0.000274 loss: 3.1068 (3.0471) grad_norm: 1.7497 (1.8944) time: 0.4957 [2021-03-26 15:24:06 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 360/1251] eta: 0:07:36 lr: 0.000274 loss: 3.2896 (3.0492) grad_norm: 1.8314 (1.8976) time: 0.5000 [2021-03-26 15:24:11 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 370/1251] eta: 0:07:31 lr: 0.000274 loss: 2.9451 (3.0444) grad_norm: 1.8281 (1.8941) time: 0.5040 [2021-03-26 15:24:16 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 380/1251] eta: 0:07:26 lr: 0.000274 loss: 3.1035 (3.0470) grad_norm: 1.7087 (1.8897) time: 0.5059 [2021-03-26 15:24:21 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 390/1251] eta: 0:07:20 lr: 0.000274 loss: 3.1080 (3.0437) grad_norm: 1.7870 (1.8894) time: 0.4999 [2021-03-26 15:24:26 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 400/1251] eta: 0:07:15 lr: 0.000274 loss: 3.1129 (3.0475) grad_norm: 1.8689 (1.8897) time: 0.4987 [2021-03-26 15:24:31 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 410/1251] eta: 0:07:09 lr: 0.000274 loss: 3.1850 (3.0475) grad_norm: 1.8532 (1.8882) time: 0.5043 [2021-03-26 15:24:36 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 420/1251] eta: 0:07:04 lr: 0.000274 loss: 3.1506 (3.0489) grad_norm: 1.8532 (1.8879) time: 0.5080 [2021-03-26 15:24:41 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 430/1251] eta: 0:06:59 lr: 0.000274 loss: 3.1506 (3.0508) grad_norm: 1.8992 (1.8905) time: 0.5072 [2021-03-26 15:24:46 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 440/1251] eta: 0:06:54 lr: 0.000274 loss: 3.2669 (3.0524) grad_norm: 2.0052 (1.8953) time: 0.5035 [2021-03-26 15:24:51 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 450/1251] eta: 0:06:49 lr: 0.000274 loss: 3.2187 (3.0554) grad_norm: 2.0014 (1.8981) time: 0.5060 [2021-03-26 15:24:57 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 460/1251] eta: 0:06:43 lr: 0.000274 loss: 3.2187 (3.0546) grad_norm: 1.9301 (1.8973) time: 0.5054 [2021-03-26 15:25:01 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 470/1251] eta: 0:06:38 lr: 0.000274 loss: 3.3334 (3.0606) grad_norm: 1.7448 (1.8943) time: 0.5010 [2021-03-26 15:25:07 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 480/1251] eta: 0:06:33 lr: 0.000274 loss: 3.1846 (3.0588) grad_norm: 1.7448 (1.8942) time: 0.5012 [2021-03-26 15:25:12 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 490/1251] eta: 0:06:28 lr: 0.000274 loss: 3.1364 (3.0634) grad_norm: 1.8441 (1.8983) time: 0.5050 [2021-03-26 15:25:17 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 500/1251] eta: 0:06:23 lr: 0.000274 loss: 3.3260 (3.0687) grad_norm: 1.9137 (1.8978) time: 0.5066 [2021-03-26 15:25:22 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 510/1251] eta: 0:06:17 lr: 0.000274 loss: 3.3052 (3.0706) grad_norm: 1.8591 (1.8974) time: 0.5042 [2021-03-26 15:25:27 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 520/1251] eta: 0:06:12 lr: 0.000274 loss: 3.3280 (3.0729) grad_norm: 1.8116 (1.8955) time: 0.4987 [2021-03-26 15:25:32 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 530/1251] eta: 0:06:07 lr: 0.000274 loss: 3.3096 (3.0765) grad_norm: 1.7542 (1.8905) time: 0.4944 [2021-03-26 15:25:37 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 540/1251] eta: 0:06:02 lr: 0.000274 loss: 3.3007 (3.0772) grad_norm: 1.7555 (1.8894) time: 0.5015 [2021-03-26 15:25:42 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 550/1251] eta: 0:05:57 lr: 0.000274 loss: 3.2564 (3.0784) grad_norm: 1.7759 (1.8871) time: 0.5233 [2021-03-26 15:25:47 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 560/1251] eta: 0:05:52 lr: 0.000274 loss: 3.0688 (3.0775) grad_norm: 1.7558 (1.8855) time: 0.5204 [2021-03-26 15:25:52 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 570/1251] eta: 0:05:47 lr: 0.000274 loss: 3.2211 (3.0813) grad_norm: 1.7558 (1.8836) time: 0.5049 [2021-03-26 15:25:57 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 580/1251] eta: 0:05:41 lr: 0.000274 loss: 3.0257 (3.0805) grad_norm: 1.8233 (1.8834) time: 0.5063 [2021-03-26 15:26:02 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 590/1251] eta: 0:05:36 lr: 0.000274 loss: 3.1363 (3.0813) grad_norm: 1.8660 (1.8843) time: 0.5063 [2021-03-26 15:26:07 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 600/1251] eta: 0:05:31 lr: 0.000273 loss: 3.3108 (3.0812) grad_norm: 1.8722 (1.8838) time: 0.5012 [2021-03-26 15:26:12 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 610/1251] eta: 0:05:26 lr: 0.000273 loss: 3.2761 (3.0821) grad_norm: 1.8257 (1.8817) time: 0.4977 [2021-03-26 15:26:17 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 620/1251] eta: 0:05:21 lr: 0.000273 loss: 3.2391 (3.0833) grad_norm: 1.7667 (1.8822) time: 0.4975 [2021-03-26 15:26:22 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 630/1251] eta: 0:05:15 lr: 0.000273 loss: 3.0337 (3.0843) grad_norm: 1.8139 (1.8818) time: 0.4976 [2021-03-26 15:26:27 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 640/1251] eta: 0:05:10 lr: 0.000273 loss: 3.1998 (3.0878) grad_norm: 1.8215 (1.8808) time: 0.5025 [2021-03-26 15:26:32 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 650/1251] eta: 0:05:05 lr: 0.000273 loss: 3.2636 (3.0867) grad_norm: 1.8597 (1.8812) time: 0.5057 [2021-03-26 15:26:37 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 660/1251] eta: 0:05:00 lr: 0.000273 loss: 3.3535 (3.0909) grad_norm: 1.8234 (1.8804) time: 0.5014 [2021-03-26 15:26:42 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 670/1251] eta: 0:04:55 lr: 0.000273 loss: 3.3776 (3.0929) grad_norm: 1.8234 (1.8821) time: 0.5051 [2021-03-26 15:26:48 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 680/1251] eta: 0:04:50 lr: 0.000273 loss: 3.2761 (3.0943) grad_norm: 1.9665 (1.8841) time: 0.5136 [2021-03-26 15:26:53 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 690/1251] eta: 0:04:45 lr: 0.000273 loss: 3.1397 (3.0939) grad_norm: 1.9980 (1.8861) time: 0.5140 [2021-03-26 15:26:58 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 700/1251] eta: 0:04:40 lr: 0.000273 loss: 3.2177 (3.0950) grad_norm: 1.9566 (1.8872) time: 0.5027 [2021-03-26 15:27:03 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 710/1251] eta: 0:04:35 lr: 0.000273 loss: 3.1414 (3.0906) grad_norm: 1.9442 (1.8886) time: 0.4961 [2021-03-26 15:27:08 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 720/1251] eta: 0:04:29 lr: 0.000273 loss: 3.1226 (3.0923) grad_norm: 1.9122 (1.8885) time: 0.5007 [2021-03-26 15:27:13 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 730/1251] eta: 0:04:24 lr: 0.000273 loss: 3.1226 (3.0903) grad_norm: 1.8733 (1.8888) time: 0.5088 [2021-03-26 15:27:18 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 740/1251] eta: 0:04:20 lr: 0.000273 loss: 3.0937 (3.0918) grad_norm: 1.9151 (1.8894) time: 0.5276 [2021-03-26 15:27:23 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 750/1251] eta: 0:04:14 lr: 0.000273 loss: 3.1234 (3.0914) grad_norm: 1.8463 (1.8882) time: 0.5209 [2021-03-26 15:27:28 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 760/1251] eta: 0:04:09 lr: 0.000273 loss: 2.9760 (3.0905) grad_norm: 1.8296 (1.8878) time: 0.4978 [2021-03-26 15:27:33 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 770/1251] eta: 0:04:04 lr: 0.000273 loss: 3.2497 (3.0930) grad_norm: 1.7955 (1.8874) time: 0.4983 [2021-03-26 15:27:38 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 780/1251] eta: 0:03:59 lr: 0.000273 loss: 3.1955 (3.0904) grad_norm: 1.7415 (1.8858) time: 0.5055 [2021-03-26 15:27:43 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 790/1251] eta: 0:03:54 lr: 0.000273 loss: 3.1086 (3.0921) grad_norm: 1.7447 (1.8843) time: 0.5013 [2021-03-26 15:27:48 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 800/1251] eta: 0:03:49 lr: 0.000273 loss: 3.1599 (3.0919) grad_norm: 1.8126 (1.8848) time: 0.4991 [2021-03-26 15:27:53 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 810/1251] eta: 0:03:44 lr: 0.000273 loss: 3.1671 (3.0925) grad_norm: 1.8301 (inf) time: 0.5012 [2021-03-26 15:27:58 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 820/1251] eta: 0:03:38 lr: 0.000273 loss: 3.0061 (3.0899) grad_norm: 1.7927 (inf) time: 0.5004 [2021-03-26 15:28:03 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 830/1251] eta: 0:03:33 lr: 0.000273 loss: 2.8882 (3.0885) grad_norm: 1.9213 (inf) time: 0.4990 [2021-03-26 15:28:08 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 840/1251] eta: 0:03:28 lr: 0.000273 loss: 3.0129 (3.0888) grad_norm: 1.9604 (inf) time: 0.5013 [2021-03-26 15:28:13 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 850/1251] eta: 0:03:23 lr: 0.000273 loss: 3.1379 (3.0873) grad_norm: 1.8647 (inf) time: 0.5085 [2021-03-26 15:28:18 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 860/1251] eta: 0:03:18 lr: 0.000273 loss: 2.9443 (3.0860) grad_norm: 1.8761 (inf) time: 0.5048 [2021-03-26 15:28:23 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 870/1251] eta: 0:03:13 lr: 0.000272 loss: 2.9443 (3.0854) grad_norm: 1.8034 (inf) time: 0.5031 [2021-03-26 15:28:29 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 880/1251] eta: 0:03:08 lr: 0.000272 loss: 2.9468 (3.0842) grad_norm: 1.7669 (inf) time: 0.5092 [2021-03-26 15:28:34 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 890/1251] eta: 0:03:03 lr: 0.000272 loss: 3.0565 (3.0833) grad_norm: 1.7532 (inf) time: 0.5084 [2021-03-26 15:28:39 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 900/1251] eta: 0:02:58 lr: 0.000272 loss: 3.2098 (3.0839) grad_norm: 1.7287 (inf) time: 0.5027 [2021-03-26 15:28:44 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 910/1251] eta: 0:02:53 lr: 0.000272 loss: 3.0151 (3.0834) grad_norm: 1.7707 (inf) time: 0.4982 [2021-03-26 15:28:49 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 920/1251] eta: 0:02:47 lr: 0.000272 loss: 3.1394 (3.0863) grad_norm: 1.7740 (inf) time: 0.4934 [2021-03-26 15:28:54 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 930/1251] eta: 0:02:42 lr: 0.000272 loss: 3.1452 (3.0840) grad_norm: 1.8052 (inf) time: 0.4985 [2021-03-26 15:28:58 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 940/1251] eta: 0:02:37 lr: 0.000272 loss: 3.0450 (3.0836) grad_norm: 1.8052 (inf) time: 0.4982 [2021-03-26 15:29:03 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 950/1251] eta: 0:02:32 lr: 0.000272 loss: 3.0354 (3.0817) grad_norm: 1.8368 (inf) time: 0.4947 [2021-03-26 15:29:08 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 960/1251] eta: 0:02:27 lr: 0.000272 loss: 3.2091 (3.0839) grad_norm: 1.9147 (inf) time: 0.4986 [2021-03-26 15:29:14 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 970/1251] eta: 0:02:22 lr: 0.000272 loss: 3.3014 (3.0839) grad_norm: 1.8720 (inf) time: 0.5032 [2021-03-26 15:29:19 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 980/1251] eta: 0:02:17 lr: 0.000272 loss: 3.3014 (3.0841) grad_norm: 1.8533 (inf) time: 0.5023 [2021-03-26 15:29:24 swin_small_patch4_window7_224] INFO: Epoch: [196] [ 990/1251] eta: 0:02:12 lr: 0.000272 loss: 3.3516 (3.0852) grad_norm: 1.8516 (inf) time: 0.5048 [2021-03-26 15:29:29 swin_small_patch4_window7_224] INFO: Epoch: [196] [1000/1251] eta: 0:02:07 lr: 0.000272 loss: 3.3516 (3.0871) grad_norm: 1.8399 (inf) time: 0.5040 [2021-03-26 15:29:34 swin_small_patch4_window7_224] INFO: Epoch: [196] [1010/1251] eta: 0:02:02 lr: 0.000272 loss: 3.0453 (3.0853) grad_norm: 1.8172 (inf) time: 0.5001 [2021-03-26 15:29:39 swin_small_patch4_window7_224] INFO: Epoch: [196] [1020/1251] eta: 0:01:57 lr: 0.000272 loss: 3.0925 (3.0862) grad_norm: 1.8570 (inf) time: 0.5080 [2021-03-26 15:29:44 swin_small_patch4_window7_224] INFO: Epoch: [196] [1030/1251] eta: 0:01:52 lr: 0.000272 loss: 3.2518 (3.0882) grad_norm: 1.8570 (inf) time: 0.5079 [2021-03-26 15:29:49 swin_small_patch4_window7_224] INFO: Epoch: [196] [1040/1251] eta: 0:01:46 lr: 0.000272 loss: 3.1296 (3.0886) grad_norm: 1.8078 (inf) time: 0.5040 [2021-03-26 15:29:54 swin_small_patch4_window7_224] INFO: Epoch: [196] [1050/1251] eta: 0:01:41 lr: 0.000272 loss: 3.1261 (3.0908) grad_norm: 1.8066 (inf) time: 0.5092 [2021-03-26 15:29:59 swin_small_patch4_window7_224] INFO: Epoch: [196] [1060/1251] eta: 0:01:36 lr: 0.000272 loss: 3.2549 (3.0918) grad_norm: 1.8777 (inf) time: 0.5134 [2021-03-26 15:30:04 swin_small_patch4_window7_224] INFO: Epoch: [196] [1070/1251] eta: 0:01:31 lr: 0.000272 loss: 2.9876 (3.0902) grad_norm: 1.8777 (inf) time: 0.5062 [2021-03-26 15:30:09 swin_small_patch4_window7_224] INFO: Epoch: [196] [1080/1251] eta: 0:01:26 lr: 0.000272 loss: 3.1113 (3.0905) grad_norm: 1.7933 (inf) time: 0.4990 [2021-03-26 15:30:14 swin_small_patch4_window7_224] INFO: Epoch: [196] [1090/1251] eta: 0:01:21 lr: 0.000272 loss: 3.1984 (3.0908) grad_norm: 1.8275 (inf) time: 0.4991 [2021-03-26 15:30:19 swin_small_patch4_window7_224] INFO: Epoch: [196] [1100/1251] eta: 0:01:16 lr: 0.000272 loss: 3.2990 (3.0907) grad_norm: 1.8370 (inf) time: 0.5015 [2021-03-26 15:30:24 swin_small_patch4_window7_224] INFO: Epoch: [196] [1110/1251] eta: 0:01:11 lr: 0.000272 loss: 3.2990 (3.0895) grad_norm: 1.9016 (inf) time: 0.4987 [2021-03-26 15:30:29 swin_small_patch4_window7_224] INFO: Epoch: [196] [1120/1251] eta: 0:01:06 lr: 0.000272 loss: 3.4630 (3.0917) grad_norm: 1.9480 (inf) time: 0.4972 [2021-03-26 15:30:34 swin_small_patch4_window7_224] INFO: Epoch: [196] [1130/1251] eta: 0:01:01 lr: 0.000272 loss: 3.2880 (3.0925) grad_norm: 1.8822 (inf) time: 0.4994 [2021-03-26 15:30:39 swin_small_patch4_window7_224] INFO: Epoch: [196] [1140/1251] eta: 0:00:56 lr: 0.000271 loss: 3.2640 (3.0939) grad_norm: 1.8600 (inf) time: 0.5014 [2021-03-26 15:30:44 swin_small_patch4_window7_224] INFO: Epoch: [196] [1150/1251] eta: 0:00:51 lr: 0.000271 loss: 3.2640 (3.0946) grad_norm: 1.8743 (inf) time: 0.4986 [2021-03-26 15:30:49 swin_small_patch4_window7_224] INFO: Epoch: [196] [1160/1251] eta: 0:00:46 lr: 0.000271 loss: 3.2235 (3.0951) grad_norm: 1.8024 (inf) time: 0.4985 [2021-03-26 15:30:54 swin_small_patch4_window7_224] INFO: Epoch: [196] [1170/1251] eta: 0:00:41 lr: 0.000271 loss: 3.2028 (3.0937) grad_norm: 1.7327 (inf) time: 0.5002 [2021-03-26 15:30:59 swin_small_patch4_window7_224] INFO: Epoch: [196] [1180/1251] eta: 0:00:35 lr: 0.000271 loss: 3.0697 (3.0932) grad_norm: 1.7879 (inf) time: 0.4993 [2021-03-26 15:31:04 swin_small_patch4_window7_224] INFO: Epoch: [196] [1190/1251] eta: 0:00:30 lr: 0.000271 loss: 3.1837 (3.0941) grad_norm: 1.8408 (inf) time: 0.4994 [2021-03-26 15:31:09 swin_small_patch4_window7_224] INFO: Epoch: [196] [1200/1251] eta: 0:00:25 lr: 0.000271 loss: 3.3405 (3.0964) grad_norm: 1.8513 (inf) time: 0.5019 [2021-03-26 15:31:14 swin_small_patch4_window7_224] INFO: Epoch: [196] [1210/1251] eta: 0:00:20 lr: 0.000271 loss: 3.2858 (3.0960) grad_norm: 1.7645 (inf) time: 0.5036 [2021-03-26 15:31:19 swin_small_patch4_window7_224] INFO: Epoch: [196] [1220/1251] eta: 0:00:15 lr: 0.000271 loss: 3.0039 (3.0937) grad_norm: 1.7847 (inf) time: 0.5028 [2021-03-26 15:31:24 swin_small_patch4_window7_224] INFO: Epoch: [196] [1230/1251] eta: 0:00:10 lr: 0.000271 loss: 3.0615 (3.0943) grad_norm: 1.8685 (inf) time: 0.5054 [2021-03-26 15:31:29 swin_small_patch4_window7_224] INFO: Epoch: [196] [1240/1251] eta: 0:00:05 lr: 0.000271 loss: 3.2186 (3.0945) grad_norm: 1.8502 (inf) time: 0.5062 [2021-03-26 15:31:34 swin_small_patch4_window7_224] INFO: Epoch: [196] [1250/1251] eta: 0:00:00 lr: 0.000271 loss: 3.1894 (3.0943) grad_norm: 1.8290 (inf) time: 0.5024 [2021-03-26 15:31:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 0.6641 (0.6641) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-26 15:31:46 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8836 (0.8324) acc1: 76.5625 (79.1193) acc5: 95.3125 (95.4545) [2021-03-26 15:31:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8053 (0.8159) acc1: 78.1250 (79.2411) acc5: 95.3125 (95.6845) [2021-03-26 15:31:50 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8388 (0.8416) acc1: 78.1250 (79.0323) acc5: 96.8750 (95.7157) [2021-03-26 15:31:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8347 (0.8315) acc1: 78.1250 (79.4588) acc5: 95.3125 (95.6555) [2021-03-26 15:31:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8347 (0.8487) acc1: 78.1250 (79.2960) acc5: 95.3125 (95.6160) [2021-03-26 15:32:06 swin_small_patch4_window7_224] INFO: * Acc@1 80.528 Acc@5 95.378 loss 0.830 [2021-03-26 15:32:06 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.5% [2021-03-26 15:32:06 swin_small_patch4_window7_224] INFO: Max accuracy: 80.53% [2021-03-26 15:32:10 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 0/1251] eta: 1:28:18 lr: 0.000271 loss: 3.2879 (3.2879) grad_norm: 1.9264 (1.9264) time: 4.2351 [2021-03-26 15:32:15 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 10/1251] eta: 0:17:31 lr: 0.000271 loss: 3.2275 (3.0826) grad_norm: 1.8406 (1.8180) time: 0.8477 [2021-03-26 15:32:20 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 20/1251] eta: 0:14:03 lr: 0.000271 loss: 2.9219 (3.0417) grad_norm: 1.7455 (1.7735) time: 0.5076 [2021-03-26 15:32:25 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 30/1251] eta: 0:12:44 lr: 0.000271 loss: 3.0799 (3.1259) grad_norm: 1.7098 (1.7815) time: 0.5042 [2021-03-26 15:32:31 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 40/1251] eta: 0:12:02 lr: 0.000271 loss: 3.1897 (3.0852) grad_norm: 1.7098 (1.7614) time: 0.5045 [2021-03-26 15:32:36 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 50/1251] eta: 0:11:34 lr: 0.000271 loss: 3.1096 (3.0509) grad_norm: 1.6738 (1.7517) time: 0.5038 [2021-03-26 15:32:41 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 60/1251] eta: 0:11:14 lr: 0.000271 loss: 3.1636 (3.0912) grad_norm: 1.7528 (1.7668) time: 0.5044 [2021-03-26 15:32:46 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 70/1251] eta: 0:11:01 lr: 0.000271 loss: 3.2794 (3.1042) grad_norm: 1.8979 (1.7823) time: 0.5138 [2021-03-26 15:32:51 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 80/1251] eta: 0:10:49 lr: 0.000271 loss: 3.2278 (3.1118) grad_norm: 1.8629 (1.7983) time: 0.5178 [2021-03-26 15:32:56 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 90/1251] eta: 0:10:37 lr: 0.000271 loss: 3.1721 (3.0879) grad_norm: 1.8186 (1.7966) time: 0.5097 [2021-03-26 15:33:01 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 100/1251] eta: 0:10:26 lr: 0.000271 loss: 3.3047 (3.1068) grad_norm: 1.8186 (1.8005) time: 0.5022 [2021-03-26 15:33:06 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 110/1251] eta: 0:10:16 lr: 0.000271 loss: 3.1648 (3.0856) grad_norm: 1.8277 (1.8103) time: 0.5026 [2021-03-26 15:33:11 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 120/1251] eta: 0:10:07 lr: 0.000271 loss: 3.0437 (3.0901) grad_norm: 1.8634 (1.8185) time: 0.5034 [2021-03-26 15:33:16 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 130/1251] eta: 0:09:59 lr: 0.000271 loss: 3.1255 (3.0770) grad_norm: 1.7631 (1.8083) time: 0.5004 [2021-03-26 15:33:21 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 140/1251] eta: 0:09:51 lr: 0.000271 loss: 3.1045 (3.0813) grad_norm: 1.7241 (1.8186) time: 0.5021 [2021-03-26 15:33:26 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 150/1251] eta: 0:09:44 lr: 0.000271 loss: 3.3137 (3.0895) grad_norm: 1.9144 (1.8230) time: 0.5041 [2021-03-26 15:33:31 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 160/1251] eta: 0:09:36 lr: 0.000271 loss: 3.3081 (3.0980) grad_norm: 1.8185 (1.8225) time: 0.5011 [2021-03-26 15:33:36 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 170/1251] eta: 0:09:29 lr: 0.000270 loss: 3.2754 (3.0940) grad_norm: 1.8256 (1.8250) time: 0.5011 [2021-03-26 15:33:41 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 180/1251] eta: 0:09:23 lr: 0.000270 loss: 3.1823 (3.0900) grad_norm: 1.9161 (1.8328) time: 0.5092 [2021-03-26 15:33:46 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 190/1251] eta: 0:09:17 lr: 0.000270 loss: 3.1977 (3.0969) grad_norm: 1.9161 (1.8368) time: 0.5107 [2021-03-26 15:33:52 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 200/1251] eta: 0:09:11 lr: 0.000270 loss: 3.2079 (3.1035) grad_norm: 1.8797 (1.8442) time: 0.5101 [2021-03-26 15:33:56 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 210/1251] eta: 0:09:04 lr: 0.000270 loss: 3.2497 (3.1126) grad_norm: 1.8067 (1.8452) time: 0.5050 [2021-03-26 15:34:02 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 220/1251] eta: 0:08:58 lr: 0.000270 loss: 3.3756 (3.1237) grad_norm: 1.7883 (1.8421) time: 0.4985 [2021-03-26 15:34:07 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 230/1251] eta: 0:08:52 lr: 0.000270 loss: 3.3220 (3.1163) grad_norm: 1.8290 (1.8421) time: 0.5038 [2021-03-26 15:34:12 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 240/1251] eta: 0:08:46 lr: 0.000270 loss: 3.0285 (3.1155) grad_norm: 1.8133 (1.8413) time: 0.5082 [2021-03-26 15:34:17 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 250/1251] eta: 0:08:41 lr: 0.000270 loss: 3.0437 (3.1084) grad_norm: 1.8213 (1.8412) time: 0.5066 [2021-03-26 15:34:22 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 260/1251] eta: 0:08:35 lr: 0.000270 loss: 3.0289 (3.1050) grad_norm: 1.7599 (1.8369) time: 0.5092 [2021-03-26 15:34:27 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 270/1251] eta: 0:08:29 lr: 0.000270 loss: 3.1759 (3.1074) grad_norm: 1.7801 (1.8364) time: 0.5048 [2021-03-26 15:34:32 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 280/1251] eta: 0:08:23 lr: 0.000270 loss: 3.1425 (3.1009) grad_norm: 1.8012 (1.8385) time: 0.4990 [2021-03-26 15:34:37 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 290/1251] eta: 0:08:18 lr: 0.000270 loss: 3.1153 (3.1016) grad_norm: 1.7602 (1.8371) time: 0.5044 [2021-03-26 15:34:42 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 300/1251] eta: 0:08:12 lr: 0.000270 loss: 3.3220 (3.1068) grad_norm: 1.7602 (1.8343) time: 0.5033 [2021-03-26 15:34:47 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 310/1251] eta: 0:08:07 lr: 0.000270 loss: 3.3220 (3.1095) grad_norm: 1.7666 (1.8326) time: 0.5070 [2021-03-26 15:34:52 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 320/1251] eta: 0:08:01 lr: 0.000270 loss: 3.2874 (3.1066) grad_norm: 1.7616 (1.8322) time: 0.5070 [2021-03-26 15:34:57 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 330/1251] eta: 0:07:55 lr: 0.000270 loss: 2.9107 (3.1031) grad_norm: 1.8694 (1.8354) time: 0.4983 [2021-03-26 15:35:02 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 340/1251] eta: 0:07:50 lr: 0.000270 loss: 3.2295 (3.1060) grad_norm: 1.8348 (1.8333) time: 0.4992 [2021-03-26 15:35:07 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 350/1251] eta: 0:07:44 lr: 0.000270 loss: 3.2295 (3.1064) grad_norm: 1.8044 (1.8357) time: 0.5090 [2021-03-26 15:35:12 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 360/1251] eta: 0:07:39 lr: 0.000270 loss: 3.1013 (3.1080) grad_norm: 1.8819 (1.8363) time: 0.5069 [2021-03-26 15:35:17 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 370/1251] eta: 0:07:33 lr: 0.000270 loss: 2.9768 (3.1009) grad_norm: 1.7766 (1.8356) time: 0.5020 [2021-03-26 15:35:22 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 380/1251] eta: 0:07:28 lr: 0.000270 loss: 2.9768 (3.0966) grad_norm: 1.7952 (1.8378) time: 0.5012 [2021-03-26 15:35:27 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 390/1251] eta: 0:07:22 lr: 0.000270 loss: 3.0700 (3.0934) grad_norm: 1.8072 (1.8391) time: 0.4953 [2021-03-26 15:35:32 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 400/1251] eta: 0:07:17 lr: 0.000270 loss: 3.2577 (3.0981) grad_norm: 1.7981 (1.8386) time: 0.4991 [2021-03-26 15:35:37 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 410/1251] eta: 0:07:12 lr: 0.000270 loss: 3.3266 (3.0996) grad_norm: 1.7873 (1.8374) time: 0.5042 [2021-03-26 15:35:42 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 420/1251] eta: 0:07:06 lr: 0.000270 loss: 3.2555 (3.1023) grad_norm: 1.8181 (1.8393) time: 0.5045 [2021-03-26 15:35:47 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 430/1251] eta: 0:07:01 lr: 0.000270 loss: 3.1805 (3.1017) grad_norm: 1.8149 (1.8391) time: 0.5015 [2021-03-26 15:35:52 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 440/1251] eta: 0:06:56 lr: 0.000269 loss: 3.1255 (3.1042) grad_norm: 1.8477 (1.8401) time: 0.5005 [2021-03-26 15:35:57 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 450/1251] eta: 0:06:50 lr: 0.000269 loss: 3.1134 (3.1007) grad_norm: 1.8910 (1.8424) time: 0.5044 [2021-03-26 15:36:02 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 460/1251] eta: 0:06:45 lr: 0.000269 loss: 2.9463 (3.1013) grad_norm: 1.9042 (1.8439) time: 0.5035 [2021-03-26 15:36:08 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 470/1251] eta: 0:06:40 lr: 0.000269 loss: 3.0088 (3.1013) grad_norm: 1.9143 (1.8463) time: 0.5080 [2021-03-26 15:36:13 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 480/1251] eta: 0:06:35 lr: 0.000269 loss: 3.3759 (3.1077) grad_norm: 1.8642 (1.8455) time: 0.5101 [2021-03-26 15:36:18 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 490/1251] eta: 0:06:29 lr: 0.000269 loss: 3.3363 (3.1076) grad_norm: 1.8172 (1.8460) time: 0.5059 [2021-03-26 15:36:23 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 500/1251] eta: 0:06:24 lr: 0.000269 loss: 3.1191 (3.1066) grad_norm: 1.8139 (1.8450) time: 0.5016 [2021-03-26 15:36:28 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 510/1251] eta: 0:06:19 lr: 0.000269 loss: 3.1377 (3.1105) grad_norm: 1.8104 (1.8451) time: 0.4999 [2021-03-26 15:36:33 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 520/1251] eta: 0:06:13 lr: 0.000269 loss: 3.0753 (3.1039) grad_norm: 1.8126 (1.8460) time: 0.4973 [2021-03-26 15:36:38 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 530/1251] eta: 0:06:08 lr: 0.000269 loss: 3.0012 (3.1035) grad_norm: 1.8186 (1.8468) time: 0.4947 [2021-03-26 15:36:42 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 540/1251] eta: 0:06:03 lr: 0.000269 loss: 3.0615 (3.1001) grad_norm: 1.7916 (1.8452) time: 0.4939 [2021-03-26 15:36:48 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 550/1251] eta: 0:05:58 lr: 0.000269 loss: 2.8413 (3.0974) grad_norm: 1.8258 (1.8477) time: 0.5067 [2021-03-26 15:36:53 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 560/1251] eta: 0:05:53 lr: 0.000269 loss: 3.0993 (3.0968) grad_norm: 1.8574 (1.8492) time: 0.5172 [2021-03-26 15:36:58 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 570/1251] eta: 0:05:47 lr: 0.000269 loss: 3.0891 (3.0934) grad_norm: 1.7685 (1.8480) time: 0.5061 [2021-03-26 15:37:03 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 580/1251] eta: 0:05:42 lr: 0.000269 loss: 3.0668 (3.0947) grad_norm: 1.8797 (1.8486) time: 0.4991 [2021-03-26 15:37:08 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 590/1251] eta: 0:05:37 lr: 0.000269 loss: 3.1078 (3.0948) grad_norm: 1.8797 (1.8478) time: 0.4998 [2021-03-26 15:37:13 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 600/1251] eta: 0:05:32 lr: 0.000269 loss: 3.3237 (3.0951) grad_norm: 1.8438 (1.8497) time: 0.5035 [2021-03-26 15:37:18 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 610/1251] eta: 0:05:27 lr: 0.000269 loss: 3.3907 (3.0948) grad_norm: 1.8204 (1.8484) time: 0.5041 [2021-03-26 15:37:23 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 620/1251] eta: 0:05:21 lr: 0.000269 loss: 3.1201 (3.0935) grad_norm: 1.8311 (1.8498) time: 0.5033 [2021-03-26 15:37:28 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 630/1251] eta: 0:05:16 lr: 0.000269 loss: 3.2266 (3.0970) grad_norm: 1.8830 (1.8508) time: 0.4993 [2021-03-26 15:37:33 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 640/1251] eta: 0:05:11 lr: 0.000269 loss: 3.1527 (3.0990) grad_norm: 1.9574 (1.8565) time: 0.5024 [2021-03-26 15:37:38 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 650/1251] eta: 0:05:06 lr: 0.000269 loss: 3.1527 (3.1001) grad_norm: 1.8817 (1.8560) time: 0.5051 [2021-03-26 15:37:43 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 660/1251] eta: 0:05:01 lr: 0.000269 loss: 3.2210 (3.1014) grad_norm: 1.8125 (1.8562) time: 0.5028 [2021-03-26 15:37:48 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 670/1251] eta: 0:04:56 lr: 0.000269 loss: 3.2210 (3.1000) grad_norm: 1.7888 (1.8551) time: 0.5011 [2021-03-26 15:37:53 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 680/1251] eta: 0:04:50 lr: 0.000269 loss: 3.3296 (3.1028) grad_norm: 1.7797 (1.8552) time: 0.4960 [2021-03-26 15:37:58 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 690/1251] eta: 0:04:45 lr: 0.000269 loss: 3.2630 (3.1018) grad_norm: 1.7899 (1.8557) time: 0.4993 [2021-03-26 15:38:03 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 700/1251] eta: 0:04:40 lr: 0.000269 loss: 3.2630 (3.1040) grad_norm: 1.8957 (1.8585) time: 0.5029 [2021-03-26 15:38:08 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 710/1251] eta: 0:04:35 lr: 0.000268 loss: 3.2485 (3.1047) grad_norm: 1.9058 (1.8588) time: 0.5031 [2021-03-26 15:38:13 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 720/1251] eta: 0:04:30 lr: 0.000268 loss: 3.1761 (3.1056) grad_norm: 1.7673 (1.8586) time: 0.5035 [2021-03-26 15:38:18 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 730/1251] eta: 0:04:25 lr: 0.000268 loss: 3.3080 (3.1069) grad_norm: 1.8653 (1.8607) time: 0.5094 [2021-03-26 15:38:24 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 740/1251] eta: 0:04:20 lr: 0.000268 loss: 3.1827 (3.1075) grad_norm: 1.9574 (1.8615) time: 0.5197 [2021-03-26 15:38:29 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 750/1251] eta: 0:04:15 lr: 0.000268 loss: 3.1434 (3.1072) grad_norm: 1.9574 (1.8623) time: 0.5142 [2021-03-26 15:38:34 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 760/1251] eta: 0:04:09 lr: 0.000268 loss: 3.2880 (3.1088) grad_norm: 1.9698 (1.8640) time: 0.5029 [2021-03-26 15:38:39 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 770/1251] eta: 0:04:04 lr: 0.000268 loss: 3.0873 (3.1066) grad_norm: 1.9310 (1.8642) time: 0.5056 [2021-03-26 15:38:44 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 780/1251] eta: 0:03:59 lr: 0.000268 loss: 3.0873 (3.1073) grad_norm: 1.8428 (1.8656) time: 0.5089 [2021-03-26 15:38:49 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 790/1251] eta: 0:03:54 lr: 0.000268 loss: 3.2797 (3.1070) grad_norm: 2.0026 (1.8700) time: 0.5043 [2021-03-26 15:38:54 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 800/1251] eta: 0:03:49 lr: 0.000268 loss: 3.2096 (3.1068) grad_norm: 1.9776 (1.8716) time: 0.5021 [2021-03-26 15:38:59 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 810/1251] eta: 0:03:44 lr: 0.000268 loss: 3.2152 (3.1101) grad_norm: 1.8202 (1.8709) time: 0.5049 [2021-03-26 15:39:04 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 820/1251] eta: 0:03:39 lr: 0.000268 loss: 3.1898 (3.1091) grad_norm: 1.8048 (1.8720) time: 0.5015 [2021-03-26 15:39:09 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 830/1251] eta: 0:03:34 lr: 0.000268 loss: 3.1898 (3.1119) grad_norm: 1.8549 (1.8717) time: 0.5048 [2021-03-26 15:39:14 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 840/1251] eta: 0:03:29 lr: 0.000268 loss: 3.2318 (3.1114) grad_norm: 1.8727 (1.8723) time: 0.5076 [2021-03-26 15:39:19 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 850/1251] eta: 0:03:23 lr: 0.000268 loss: 2.9918 (3.1068) grad_norm: 1.8462 (1.8717) time: 0.4985 [2021-03-26 15:39:24 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 860/1251] eta: 0:03:18 lr: 0.000268 loss: 3.1030 (3.1094) grad_norm: 1.7858 (1.8712) time: 0.5021 [2021-03-26 15:39:29 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 870/1251] eta: 0:03:13 lr: 0.000268 loss: 3.1154 (3.1043) grad_norm: 1.7858 (1.8704) time: 0.5029 [2021-03-26 15:39:34 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 880/1251] eta: 0:03:08 lr: 0.000268 loss: 2.4799 (3.1031) grad_norm: 1.7909 (1.8702) time: 0.4989 [2021-03-26 15:39:39 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 890/1251] eta: 0:03:03 lr: 0.000268 loss: 2.9938 (3.1010) grad_norm: 1.9040 (1.8710) time: 0.5108 [2021-03-26 15:39:44 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 900/1251] eta: 0:02:58 lr: 0.000268 loss: 3.2975 (3.1035) grad_norm: 1.9040 (1.8712) time: 0.5153 [2021-03-26 15:39:49 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 910/1251] eta: 0:02:53 lr: 0.000268 loss: 3.2975 (3.1040) grad_norm: 1.8007 (1.8700) time: 0.5080 [2021-03-26 15:39:54 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 920/1251] eta: 0:02:48 lr: 0.000268 loss: 3.1434 (3.1032) grad_norm: 1.8007 (1.8709) time: 0.5066 [2021-03-26 15:40:00 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 930/1251] eta: 0:02:43 lr: 0.000268 loss: 2.9574 (3.1021) grad_norm: 1.8964 (1.8717) time: 0.5089 [2021-03-26 15:40:05 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 940/1251] eta: 0:02:38 lr: 0.000268 loss: 2.9574 (3.1019) grad_norm: 1.9936 (1.8723) time: 0.5125 [2021-03-26 15:40:10 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 950/1251] eta: 0:02:33 lr: 0.000268 loss: 3.0026 (3.1007) grad_norm: 1.9800 (1.8731) time: 0.5085 [2021-03-26 15:40:15 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 960/1251] eta: 0:02:27 lr: 0.000268 loss: 3.0268 (3.0998) grad_norm: 1.9181 (1.8732) time: 0.5086 [2021-03-26 15:40:20 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 970/1251] eta: 0:02:22 lr: 0.000268 loss: 3.0867 (3.1015) grad_norm: 1.8424 (1.8734) time: 0.5070 [2021-03-26 15:40:25 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 980/1251] eta: 0:02:17 lr: 0.000268 loss: 3.2109 (3.1026) grad_norm: 1.8342 (1.8735) time: 0.4973 [2021-03-26 15:40:30 swin_small_patch4_window7_224] INFO: Epoch: [197] [ 990/1251] eta: 0:02:12 lr: 0.000267 loss: 3.2427 (3.1038) grad_norm: 1.7988 (1.8727) time: 0.4993 [2021-03-26 15:40:35 swin_small_patch4_window7_224] INFO: Epoch: [197] [1000/1251] eta: 0:02:07 lr: 0.000267 loss: 3.3562 (3.1066) grad_norm: 1.7737 (1.8726) time: 0.5099 [2021-03-26 15:40:40 swin_small_patch4_window7_224] INFO: Epoch: [197] [1010/1251] eta: 0:02:02 lr: 0.000267 loss: 3.3562 (3.1065) grad_norm: 1.7754 (1.8740) time: 0.5098 [2021-03-26 15:40:45 swin_small_patch4_window7_224] INFO: Epoch: [197] [1020/1251] eta: 0:01:57 lr: 0.000267 loss: 3.1163 (3.1055) grad_norm: 1.9362 (1.8746) time: 0.4981 [2021-03-26 15:40:50 swin_small_patch4_window7_224] INFO: Epoch: [197] [1030/1251] eta: 0:01:52 lr: 0.000267 loss: 2.9931 (3.1047) grad_norm: 1.8621 (1.8750) time: 0.4939 [2021-03-26 15:40:55 swin_small_patch4_window7_224] INFO: Epoch: [197] [1040/1251] eta: 0:01:47 lr: 0.000267 loss: 3.0046 (3.1031) grad_norm: 1.7843 (1.8741) time: 0.4993 [2021-03-26 15:41:00 swin_small_patch4_window7_224] INFO: Epoch: [197] [1050/1251] eta: 0:01:42 lr: 0.000267 loss: 3.0792 (3.1041) grad_norm: 1.7865 (1.8745) time: 0.5023 [2021-03-26 15:41:05 swin_small_patch4_window7_224] INFO: Epoch: [197] [1060/1251] eta: 0:01:37 lr: 0.000267 loss: 3.1234 (3.1036) grad_norm: 1.7865 (1.8742) time: 0.5058 [2021-03-26 15:41:10 swin_small_patch4_window7_224] INFO: Epoch: [197] [1070/1251] eta: 0:01:31 lr: 0.000267 loss: 3.3324 (3.1045) grad_norm: 1.8550 (1.8743) time: 0.5089 [2021-03-26 15:41:15 swin_small_patch4_window7_224] INFO: Epoch: [197] [1080/1251] eta: 0:01:26 lr: 0.000267 loss: 3.1115 (3.1037) grad_norm: 1.8291 (1.8743) time: 0.5054 [2021-03-26 15:41:20 swin_small_patch4_window7_224] INFO: Epoch: [197] [1090/1251] eta: 0:01:21 lr: 0.000267 loss: 3.0802 (3.1039) grad_norm: 1.7836 (1.8739) time: 0.5028 [2021-03-26 15:41:25 swin_small_patch4_window7_224] INFO: Epoch: [197] [1100/1251] eta: 0:01:16 lr: 0.000267 loss: 3.0544 (3.1033) grad_norm: 1.8331 (1.8734) time: 0.5004 [2021-03-26 15:41:30 swin_small_patch4_window7_224] INFO: Epoch: [197] [1110/1251] eta: 0:01:11 lr: 0.000267 loss: 3.0425 (3.1020) grad_norm: 1.8668 (1.8737) time: 0.5032 [2021-03-26 15:41:35 swin_small_patch4_window7_224] INFO: Epoch: [197] [1120/1251] eta: 0:01:06 lr: 0.000267 loss: 3.1810 (3.1032) grad_norm: 1.9025 (1.8808) time: 0.5036 [2021-03-26 15:41:40 swin_small_patch4_window7_224] INFO: Epoch: [197] [1130/1251] eta: 0:01:01 lr: 0.000267 loss: 3.1501 (3.1029) grad_norm: 1.9427 (1.8814) time: 0.4987 [2021-03-26 15:41:45 swin_small_patch4_window7_224] INFO: Epoch: [197] [1140/1251] eta: 0:00:56 lr: 0.000267 loss: 3.0283 (3.1026) grad_norm: 1.9427 (1.8833) time: 0.5016 [2021-03-26 15:41:50 swin_small_patch4_window7_224] INFO: Epoch: [197] [1150/1251] eta: 0:00:51 lr: 0.000267 loss: 3.0399 (3.1032) grad_norm: 1.9247 (1.8838) time: 0.5036 [2021-03-26 15:41:55 swin_small_patch4_window7_224] INFO: Epoch: [197] [1160/1251] eta: 0:00:46 lr: 0.000267 loss: 3.1822 (3.1031) grad_norm: 1.9082 (1.8842) time: 0.4973 [2021-03-26 15:42:00 swin_small_patch4_window7_224] INFO: Epoch: [197] [1170/1251] eta: 0:00:41 lr: 0.000267 loss: 3.1923 (3.1027) grad_norm: 1.8464 (1.8839) time: 0.4976 [2021-03-26 15:42:05 swin_small_patch4_window7_224] INFO: Epoch: [197] [1180/1251] eta: 0:00:36 lr: 0.000267 loss: 3.1994 (3.1025) grad_norm: 1.8320 (1.8844) time: 0.5012 [2021-03-26 15:42:10 swin_small_patch4_window7_224] INFO: Epoch: [197] [1190/1251] eta: 0:00:30 lr: 0.000267 loss: 3.2513 (3.1048) grad_norm: 1.8606 (1.8848) time: 0.4966 [2021-03-26 15:42:15 swin_small_patch4_window7_224] INFO: Epoch: [197] [1200/1251] eta: 0:00:25 lr: 0.000267 loss: 3.1602 (3.1040) grad_norm: 1.8415 (1.8847) time: 0.4991 [2021-03-26 15:42:20 swin_small_patch4_window7_224] INFO: Epoch: [197] [1210/1251] eta: 0:00:20 lr: 0.000267 loss: 3.0915 (3.1036) grad_norm: 1.8919 (1.8860) time: 0.5072 [2021-03-26 15:42:25 swin_small_patch4_window7_224] INFO: Epoch: [197] [1220/1251] eta: 0:00:15 lr: 0.000267 loss: 3.0225 (3.1038) grad_norm: 1.8559 (1.8853) time: 0.5065 [2021-03-26 15:42:30 swin_small_patch4_window7_224] INFO: Epoch: [197] [1230/1251] eta: 0:00:10 lr: 0.000267 loss: 3.1291 (3.1040) grad_norm: 1.7817 (1.8845) time: 0.5008 [2021-03-26 15:42:35 swin_small_patch4_window7_224] INFO: Epoch: [197] [1240/1251] eta: 0:00:05 lr: 0.000267 loss: 3.1276 (3.1033) grad_norm: 1.9120 (1.8861) time: 0.4989 [2021-03-26 15:42:40 swin_small_patch4_window7_224] INFO: Epoch: [197] [1250/1251] eta: 0:00:00 lr: 0.000267 loss: 3.1079 (3.1036) grad_norm: 1.9467 (1.8873) time: 0.4951 [2021-03-26 15:42:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:17 loss: 1.1396 (1.1396) acc1: 70.3125 (70.3125) acc5: 90.6250 (90.6250) [2021-03-26 15:42:55 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8335 (0.8415) acc1: 81.2500 (79.1193) acc5: 96.8750 (95.8807) [2021-03-26 15:42:57 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8402 (0.8540) acc1: 78.1250 (78.5714) acc5: 96.8750 (95.3869) [2021-03-26 15:42:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8177 (0.8243) acc1: 79.6875 (79.4859) acc5: 95.3125 (95.4637) [2021-03-26 15:43:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8174 (0.8339) acc1: 79.6875 (79.2302) acc5: 95.3125 (95.5793) [2021-03-26 15:43:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8596 (0.8494) acc1: 76.5625 (79.0080) acc5: 95.3125 (95.3920) [2021-03-26 15:43:14 swin_small_patch4_window7_224] INFO: * Acc@1 80.328 Acc@5 95.388 loss 0.828 [2021-03-26 15:43:14 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.3% [2021-03-26 15:43:14 swin_small_patch4_window7_224] INFO: Max accuracy: 80.53% [2021-03-26 15:43:18 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 0/1251] eta: 1:28:03 lr: 0.000267 loss: 3.4337 (3.4337) grad_norm: 1.9011 (1.9011) time: 4.2234 [2021-03-26 15:43:23 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 10/1251] eta: 0:17:37 lr: 0.000266 loss: 3.3278 (3.2884) grad_norm: 1.9169 (2.0161) time: 0.8521 [2021-03-26 15:43:29 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 20/1251] eta: 0:14:07 lr: 0.000266 loss: 3.4384 (3.3852) grad_norm: 1.9725 (2.0768) time: 0.5120 [2021-03-26 15:43:34 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 30/1251] eta: 0:12:46 lr: 0.000266 loss: 3.4540 (3.3489) grad_norm: 1.9380 (2.0170) time: 0.5039 [2021-03-26 15:43:39 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 40/1251] eta: 0:12:09 lr: 0.000266 loss: 3.3130 (3.2850) grad_norm: 1.8905 (2.0157) time: 0.5117 [2021-03-26 15:43:44 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 50/1251] eta: 0:11:39 lr: 0.000266 loss: 3.1778 (3.2187) grad_norm: 1.8544 (2.0047) time: 0.5119 [2021-03-26 15:43:49 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 60/1251] eta: 0:11:18 lr: 0.000266 loss: 3.1391 (3.1818) grad_norm: 1.8507 (1.9804) time: 0.5021 [2021-03-26 15:43:54 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 70/1251] eta: 0:11:05 lr: 0.000266 loss: 3.1391 (3.1515) grad_norm: 1.8874 (2.0103) time: 0.5157 [2021-03-26 15:43:59 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 80/1251] eta: 0:10:50 lr: 0.000266 loss: 3.1802 (3.1528) grad_norm: 1.9442 (1.9986) time: 0.5142 [2021-03-26 15:44:04 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 90/1251] eta: 0:10:37 lr: 0.000266 loss: 3.3753 (3.1570) grad_norm: 1.9347 (1.9865) time: 0.4985 [2021-03-26 15:44:09 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 100/1251] eta: 0:10:26 lr: 0.000266 loss: 3.1000 (3.1420) grad_norm: 1.8187 (1.9729) time: 0.4984 [2021-03-26 15:44:14 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 110/1251] eta: 0:10:17 lr: 0.000266 loss: 3.1000 (3.1502) grad_norm: 1.7445 (1.9493) time: 0.5055 [2021-03-26 15:44:19 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 120/1251] eta: 0:10:09 lr: 0.000266 loss: 3.0959 (3.1286) grad_norm: 1.8463 (1.9523) time: 0.5133 [2021-03-26 15:44:24 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 130/1251] eta: 0:10:01 lr: 0.000266 loss: 3.0663 (3.1339) grad_norm: 1.9261 (1.9522) time: 0.5103 [2021-03-26 15:44:29 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 140/1251] eta: 0:09:53 lr: 0.000266 loss: 3.0663 (3.1218) grad_norm: 1.8609 (1.9452) time: 0.5035 [2021-03-26 15:44:35 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 150/1251] eta: 0:09:46 lr: 0.000266 loss: 3.1440 (3.1268) grad_norm: 1.7630 (1.9331) time: 0.5083 [2021-03-26 15:44:40 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 160/1251] eta: 0:09:39 lr: 0.000266 loss: 3.1440 (3.1178) grad_norm: 1.7888 (1.9304) time: 0.5076 [2021-03-26 15:44:45 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 170/1251] eta: 0:09:32 lr: 0.000266 loss: 3.1759 (3.1180) grad_norm: 1.8528 (1.9267) time: 0.5027 [2021-03-26 15:44:50 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 180/1251] eta: 0:09:25 lr: 0.000266 loss: 3.1793 (3.1026) grad_norm: 1.8756 (1.9240) time: 0.5044 [2021-03-26 15:44:55 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 190/1251] eta: 0:09:19 lr: 0.000266 loss: 3.0208 (3.1008) grad_norm: 1.9124 (1.9221) time: 0.5096 [2021-03-26 15:45:00 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 200/1251] eta: 0:09:12 lr: 0.000266 loss: 3.2076 (3.1117) grad_norm: 1.8721 (1.9305) time: 0.5094 [2021-03-26 15:45:05 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 210/1251] eta: 0:09:06 lr: 0.000266 loss: 3.1780 (3.1097) grad_norm: 1.8721 (1.9252) time: 0.5036 [2021-03-26 15:45:10 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 220/1251] eta: 0:09:00 lr: 0.000266 loss: 3.1766 (3.1059) grad_norm: 1.7166 (1.9174) time: 0.5040 [2021-03-26 15:45:15 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 230/1251] eta: 0:08:54 lr: 0.000266 loss: 3.1766 (3.1025) grad_norm: 1.8606 (1.9271) time: 0.5039 [2021-03-26 15:45:20 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 240/1251] eta: 0:08:48 lr: 0.000266 loss: 3.0301 (3.0989) grad_norm: 1.9573 (1.9262) time: 0.5101 [2021-03-26 15:45:25 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 250/1251] eta: 0:08:42 lr: 0.000266 loss: 3.1357 (3.0990) grad_norm: 1.8501 (1.9241) time: 0.5112 [2021-03-26 15:45:30 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 260/1251] eta: 0:08:36 lr: 0.000266 loss: 3.1922 (3.1041) grad_norm: 1.8461 (1.9244) time: 0.5014 [2021-03-26 15:45:35 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 270/1251] eta: 0:08:31 lr: 0.000266 loss: 3.0806 (3.0992) grad_norm: 1.9347 (1.9251) time: 0.5046 [2021-03-26 15:45:40 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 280/1251] eta: 0:08:24 lr: 0.000266 loss: 3.0806 (3.0929) grad_norm: 1.8756 (1.9230) time: 0.5029 [2021-03-26 15:45:45 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 290/1251] eta: 0:08:19 lr: 0.000265 loss: 3.1608 (3.0930) grad_norm: 1.8457 (1.9201) time: 0.4996 [2021-03-26 15:45:50 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 300/1251] eta: 0:08:13 lr: 0.000265 loss: 3.0268 (3.0842) grad_norm: 1.8771 (1.9208) time: 0.5076 [2021-03-26 15:45:56 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 310/1251] eta: 0:08:08 lr: 0.000265 loss: 3.0260 (3.0817) grad_norm: 1.8789 (1.9194) time: 0.5151 [2021-03-26 15:46:01 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 320/1251] eta: 0:08:03 lr: 0.000265 loss: 3.0260 (3.0764) grad_norm: 1.8967 (1.9198) time: 0.5131 [2021-03-26 15:46:06 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 330/1251] eta: 0:07:57 lr: 0.000265 loss: 3.0666 (3.0758) grad_norm: 1.8558 (1.9173) time: 0.5052 [2021-03-26 15:46:11 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 340/1251] eta: 0:07:52 lr: 0.000265 loss: 3.2888 (3.0772) grad_norm: 1.8343 (1.9168) time: 0.5081 [2021-03-26 15:46:16 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 350/1251] eta: 0:07:46 lr: 0.000265 loss: 3.1117 (3.0738) grad_norm: 1.8692 (1.9174) time: 0.5070 [2021-03-26 15:46:21 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 360/1251] eta: 0:07:41 lr: 0.000265 loss: 3.0128 (3.0684) grad_norm: 1.8616 (1.9132) time: 0.5057 [2021-03-26 15:46:26 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 370/1251] eta: 0:07:35 lr: 0.000265 loss: 3.0783 (3.0732) grad_norm: 1.8409 (1.9130) time: 0.5089 [2021-03-26 15:46:31 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 380/1251] eta: 0:07:30 lr: 0.000265 loss: 3.1674 (3.0749) grad_norm: 1.8409 (1.9123) time: 0.5067 [2021-03-26 15:46:36 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 390/1251] eta: 0:07:24 lr: 0.000265 loss: 3.1877 (3.0811) grad_norm: 1.9180 (1.9156) time: 0.5051 [2021-03-26 15:46:41 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 400/1251] eta: 0:07:19 lr: 0.000265 loss: 3.3159 (3.0900) grad_norm: 1.9567 (1.9171) time: 0.5004 [2021-03-26 15:46:46 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 410/1251] eta: 0:07:13 lr: 0.000265 loss: 3.4431 (3.0958) grad_norm: 1.8974 (1.9186) time: 0.4986 [2021-03-26 15:46:51 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 420/1251] eta: 0:07:08 lr: 0.000265 loss: 3.3003 (3.0965) grad_norm: 1.8943 (1.9161) time: 0.5003 [2021-03-26 15:46:56 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 430/1251] eta: 0:07:02 lr: 0.000265 loss: 3.0243 (3.0931) grad_norm: 1.8353 (1.9137) time: 0.5039 [2021-03-26 15:47:01 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 440/1251] eta: 0:06:57 lr: 0.000265 loss: 2.7528 (3.0847) grad_norm: 1.8397 (1.9130) time: 0.5056 [2021-03-26 15:47:06 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 450/1251] eta: 0:06:52 lr: 0.000265 loss: 2.9454 (3.0835) grad_norm: 1.8706 (1.9133) time: 0.5009 [2021-03-26 15:47:11 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 460/1251] eta: 0:06:46 lr: 0.000265 loss: 2.9650 (3.0801) grad_norm: 1.8488 (1.9122) time: 0.4961 [2021-03-26 15:47:16 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 470/1251] eta: 0:06:41 lr: 0.000265 loss: 3.0530 (3.0833) grad_norm: 1.8316 (1.9121) time: 0.5008 [2021-03-26 15:47:21 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 480/1251] eta: 0:06:36 lr: 0.000265 loss: 3.1139 (3.0799) grad_norm: 1.8377 (1.9112) time: 0.5042 [2021-03-26 15:47:26 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 490/1251] eta: 0:06:30 lr: 0.000265 loss: 3.1101 (3.0750) grad_norm: 1.8236 (1.9096) time: 0.5066 [2021-03-26 15:47:31 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 500/1251] eta: 0:06:25 lr: 0.000265 loss: 3.1750 (3.0770) grad_norm: 1.8236 (1.9087) time: 0.5098 [2021-03-26 15:47:37 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 510/1251] eta: 0:06:20 lr: 0.000265 loss: 3.2703 (3.0822) grad_norm: 1.9003 (1.9110) time: 0.5076 [2021-03-26 15:47:42 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 520/1251] eta: 0:06:15 lr: 0.000265 loss: 3.2567 (3.0831) grad_norm: 2.1240 (1.9174) time: 0.5035 [2021-03-26 15:47:47 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 530/1251] eta: 0:06:09 lr: 0.000265 loss: 3.1783 (3.0863) grad_norm: 1.9251 (1.9184) time: 0.4990 [2021-03-26 15:47:52 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 540/1251] eta: 0:06:04 lr: 0.000265 loss: 3.2313 (3.0885) grad_norm: 1.9248 (1.9200) time: 0.5000 [2021-03-26 15:47:57 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 550/1251] eta: 0:05:59 lr: 0.000265 loss: 3.0846 (3.0855) grad_norm: 1.8875 (1.9187) time: 0.5052 [2021-03-26 15:48:02 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 560/1251] eta: 0:05:54 lr: 0.000265 loss: 2.9488 (3.0853) grad_norm: 1.8036 (1.9172) time: 0.5060 [2021-03-26 15:48:07 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 570/1251] eta: 0:05:48 lr: 0.000264 loss: 3.2441 (3.0853) grad_norm: 1.7969 (1.9159) time: 0.4991 [2021-03-26 15:48:12 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 580/1251] eta: 0:05:43 lr: 0.000264 loss: 3.2014 (3.0860) grad_norm: 1.7267 (1.9135) time: 0.5019 [2021-03-26 15:48:17 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 590/1251] eta: 0:05:38 lr: 0.000264 loss: 3.2303 (3.0906) grad_norm: 1.7282 (1.9121) time: 0.5150 [2021-03-26 15:48:22 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 600/1251] eta: 0:05:33 lr: 0.000264 loss: 3.1766 (3.0894) grad_norm: 1.7757 (1.9107) time: 0.5129 [2021-03-26 15:48:27 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 610/1251] eta: 0:05:28 lr: 0.000264 loss: 2.9355 (3.0863) grad_norm: 1.7784 (1.9095) time: 0.5037 [2021-03-26 15:48:32 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 620/1251] eta: 0:05:22 lr: 0.000264 loss: 3.0439 (3.0865) grad_norm: 1.7753 (1.9075) time: 0.5045 [2021-03-26 15:48:37 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 630/1251] eta: 0:05:17 lr: 0.000264 loss: 3.1201 (3.0825) grad_norm: 1.7768 (1.9088) time: 0.5037 [2021-03-26 15:48:42 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 640/1251] eta: 0:05:12 lr: 0.000264 loss: 3.1201 (3.0833) grad_norm: 1.8157 (1.9081) time: 0.5054 [2021-03-26 15:48:47 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 650/1251] eta: 0:05:07 lr: 0.000264 loss: 3.0891 (3.0821) grad_norm: 1.7812 (1.9094) time: 0.5080 [2021-03-26 15:48:52 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 660/1251] eta: 0:05:02 lr: 0.000264 loss: 3.0814 (3.0822) grad_norm: 1.8329 (1.9090) time: 0.5035 [2021-03-26 15:48:57 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 670/1251] eta: 0:04:57 lr: 0.000264 loss: 3.2395 (3.0846) grad_norm: 1.8586 (1.9095) time: 0.4996 [2021-03-26 15:49:02 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 680/1251] eta: 0:04:51 lr: 0.000264 loss: 3.2109 (3.0847) grad_norm: 1.8586 (1.9094) time: 0.5029 [2021-03-26 15:49:07 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 690/1251] eta: 0:04:46 lr: 0.000264 loss: 3.1942 (3.0839) grad_norm: 1.8620 (1.9092) time: 0.5035 [2021-03-26 15:49:12 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 700/1251] eta: 0:04:41 lr: 0.000264 loss: 3.1942 (3.0836) grad_norm: 1.8620 (1.9074) time: 0.5015 [2021-03-26 15:49:17 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 710/1251] eta: 0:04:36 lr: 0.000264 loss: 3.2113 (3.0873) grad_norm: 1.7186 (1.9062) time: 0.5027 [2021-03-26 15:49:22 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 720/1251] eta: 0:04:31 lr: 0.000264 loss: 3.3810 (3.0889) grad_norm: 1.9037 (1.9071) time: 0.5071 [2021-03-26 15:49:28 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 730/1251] eta: 0:04:26 lr: 0.000264 loss: 3.2664 (3.0894) grad_norm: 1.8679 (1.9068) time: 0.5103 [2021-03-26 15:49:33 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 740/1251] eta: 0:04:20 lr: 0.000264 loss: 3.2597 (3.0905) grad_norm: 1.8393 (1.9074) time: 0.5096 [2021-03-26 15:49:38 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 750/1251] eta: 0:04:15 lr: 0.000264 loss: 2.8625 (3.0846) grad_norm: 1.8970 (1.9078) time: 0.5151 [2021-03-26 15:49:43 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 760/1251] eta: 0:04:10 lr: 0.000264 loss: 2.7204 (3.0818) grad_norm: 1.8406 (1.9061) time: 0.5118 [2021-03-26 15:49:48 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 770/1251] eta: 0:04:05 lr: 0.000264 loss: 2.9585 (3.0815) grad_norm: 1.8057 (1.9061) time: 0.5061 [2021-03-26 15:49:53 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 780/1251] eta: 0:04:00 lr: 0.000264 loss: 3.2142 (3.0816) grad_norm: 1.9411 (1.9082) time: 0.5126 [2021-03-26 15:49:58 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 790/1251] eta: 0:03:55 lr: 0.000264 loss: 3.2142 (3.0814) grad_norm: 1.9208 (1.9079) time: 0.5155 [2021-03-26 15:50:03 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 800/1251] eta: 0:03:50 lr: 0.000264 loss: 3.1193 (3.0816) grad_norm: 1.8791 (1.9087) time: 0.5061 [2021-03-26 15:50:08 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 810/1251] eta: 0:03:45 lr: 0.000264 loss: 3.3453 (3.0846) grad_norm: 1.8791 (1.9089) time: 0.4965 [2021-03-26 15:50:13 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 820/1251] eta: 0:03:40 lr: 0.000264 loss: 3.1846 (3.0840) grad_norm: 1.7901 (1.9080) time: 0.5062 [2021-03-26 15:50:19 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 830/1251] eta: 0:03:34 lr: 0.000264 loss: 3.1094 (3.0842) grad_norm: 1.8039 (1.9083) time: 0.5153 [2021-03-26 15:50:24 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 840/1251] eta: 0:03:29 lr: 0.000263 loss: 3.1182 (3.0822) grad_norm: 1.8039 (1.9074) time: 0.5115 [2021-03-26 15:50:29 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 850/1251] eta: 0:03:24 lr: 0.000263 loss: 3.0666 (3.0822) grad_norm: 1.8095 (1.9078) time: 0.5017 [2021-03-26 15:50:34 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 860/1251] eta: 0:03:19 lr: 0.000263 loss: 3.1657 (3.0824) grad_norm: 1.8243 (1.9067) time: 0.5008 [2021-03-26 15:50:39 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 870/1251] eta: 0:03:14 lr: 0.000263 loss: 3.1719 (3.0817) grad_norm: 1.8473 (1.9069) time: 0.5084 [2021-03-26 15:50:44 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 880/1251] eta: 0:03:09 lr: 0.000263 loss: 3.0413 (3.0810) grad_norm: 1.8833 (1.9067) time: 0.5039 [2021-03-26 15:50:49 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 890/1251] eta: 0:03:04 lr: 0.000263 loss: 3.1047 (3.0805) grad_norm: 1.8522 (1.9068) time: 0.5063 [2021-03-26 15:50:54 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 900/1251] eta: 0:02:59 lr: 0.000263 loss: 2.9733 (3.0785) grad_norm: 1.9437 (1.9080) time: 0.5097 [2021-03-26 15:50:59 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 910/1251] eta: 0:02:53 lr: 0.000263 loss: 2.9222 (3.0791) grad_norm: 1.9006 (1.9069) time: 0.5027 [2021-03-26 15:51:04 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 920/1251] eta: 0:02:48 lr: 0.000263 loss: 3.1337 (3.0795) grad_norm: 1.8213 (1.9064) time: 0.5022 [2021-03-26 15:51:09 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 930/1251] eta: 0:02:43 lr: 0.000263 loss: 3.0857 (3.0803) grad_norm: 1.8289 (1.9056) time: 0.5073 [2021-03-26 15:51:14 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 940/1251] eta: 0:02:38 lr: 0.000263 loss: 3.0959 (3.0794) grad_norm: 1.9025 (1.9062) time: 0.5171 [2021-03-26 15:51:19 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 950/1251] eta: 0:02:33 lr: 0.000263 loss: 3.0070 (3.0785) grad_norm: 1.8929 (1.9059) time: 0.5179 [2021-03-26 15:51:25 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 960/1251] eta: 0:02:28 lr: 0.000263 loss: 3.0570 (3.0784) grad_norm: 1.8288 (1.9047) time: 0.5123 [2021-03-26 15:51:30 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 970/1251] eta: 0:02:23 lr: 0.000263 loss: 3.2321 (3.0790) grad_norm: 1.7997 (1.9059) time: 0.5069 [2021-03-26 15:51:35 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 980/1251] eta: 0:02:18 lr: 0.000263 loss: 3.0847 (3.0778) grad_norm: 1.7997 (1.9052) time: 0.5007 [2021-03-26 15:51:40 swin_small_patch4_window7_224] INFO: Epoch: [198] [ 990/1251] eta: 0:02:13 lr: 0.000263 loss: 3.1319 (3.0774) grad_norm: 1.8783 (1.9060) time: 0.4989 [2021-03-26 15:51:45 swin_small_patch4_window7_224] INFO: Epoch: [198] [1000/1251] eta: 0:02:07 lr: 0.000263 loss: 3.2061 (3.0787) grad_norm: 1.9334 (1.9069) time: 0.5023 [2021-03-26 15:51:50 swin_small_patch4_window7_224] INFO: Epoch: [198] [1010/1251] eta: 0:02:02 lr: 0.000263 loss: 3.4056 (3.0791) grad_norm: 2.0044 (1.9082) time: 0.5079 [2021-03-26 15:51:55 swin_small_patch4_window7_224] INFO: Epoch: [198] [1020/1251] eta: 0:01:57 lr: 0.000263 loss: 3.1650 (3.0766) grad_norm: 2.0044 (1.9091) time: 0.5005 [2021-03-26 15:52:00 swin_small_patch4_window7_224] INFO: Epoch: [198] [1030/1251] eta: 0:01:52 lr: 0.000263 loss: 3.0490 (3.0764) grad_norm: 1.8478 (1.9085) time: 0.4967 [2021-03-26 15:52:05 swin_small_patch4_window7_224] INFO: Epoch: [198] [1040/1251] eta: 0:01:47 lr: 0.000263 loss: 3.0592 (3.0758) grad_norm: 1.8672 (1.9093) time: 0.5058 [2021-03-26 15:52:10 swin_small_patch4_window7_224] INFO: Epoch: [198] [1050/1251] eta: 0:01:42 lr: 0.000263 loss: 3.0592 (3.0745) grad_norm: 1.9167 (1.9089) time: 0.5109 [2021-03-26 15:52:15 swin_small_patch4_window7_224] INFO: Epoch: [198] [1060/1251] eta: 0:01:37 lr: 0.000263 loss: 3.1342 (3.0747) grad_norm: 1.8849 (1.9097) time: 0.5076 [2021-03-26 15:52:20 swin_small_patch4_window7_224] INFO: Epoch: [198] [1070/1251] eta: 0:01:32 lr: 0.000263 loss: 3.1862 (3.0759) grad_norm: 1.8255 (1.9098) time: 0.5030 [2021-03-26 15:52:25 swin_small_patch4_window7_224] INFO: Epoch: [198] [1080/1251] eta: 0:01:27 lr: 0.000263 loss: 3.1862 (3.0776) grad_norm: 1.9088 (1.9099) time: 0.5036 [2021-03-26 15:52:30 swin_small_patch4_window7_224] INFO: Epoch: [198] [1090/1251] eta: 0:01:22 lr: 0.000263 loss: 3.1773 (3.0784) grad_norm: 1.9786 (1.9113) time: 0.5094 [2021-03-26 15:52:35 swin_small_patch4_window7_224] INFO: Epoch: [198] [1100/1251] eta: 0:01:16 lr: 0.000263 loss: 3.1483 (3.0785) grad_norm: 1.8584 (1.9104) time: 0.5059 [2021-03-26 15:52:40 swin_small_patch4_window7_224] INFO: Epoch: [198] [1110/1251] eta: 0:01:11 lr: 0.000263 loss: 3.2705 (3.0804) grad_norm: 1.7804 (1.9102) time: 0.4998 [2021-03-26 15:52:45 swin_small_patch4_window7_224] INFO: Epoch: [198] [1120/1251] eta: 0:01:06 lr: 0.000262 loss: 3.3146 (3.0814) grad_norm: 1.8993 (1.9105) time: 0.5035 [2021-03-26 15:52:50 swin_small_patch4_window7_224] INFO: Epoch: [198] [1130/1251] eta: 0:01:01 lr: 0.000262 loss: 3.2973 (3.0814) grad_norm: 1.9416 (1.9113) time: 0.5071 [2021-03-26 15:52:55 swin_small_patch4_window7_224] INFO: Epoch: [198] [1140/1251] eta: 0:00:56 lr: 0.000262 loss: 3.1357 (3.0814) grad_norm: 1.8891 (1.9105) time: 0.5031 [2021-03-26 15:53:00 swin_small_patch4_window7_224] INFO: Epoch: [198] [1150/1251] eta: 0:00:51 lr: 0.000262 loss: 3.0661 (3.0811) grad_norm: 1.7499 (1.9095) time: 0.4977 [2021-03-26 15:53:05 swin_small_patch4_window7_224] INFO: Epoch: [198] [1160/1251] eta: 0:00:46 lr: 0.000262 loss: 2.8547 (3.0795) grad_norm: 1.8170 (1.9096) time: 0.4969 [2021-03-26 15:53:10 swin_small_patch4_window7_224] INFO: Epoch: [198] [1170/1251] eta: 0:00:41 lr: 0.000262 loss: 3.1665 (3.0817) grad_norm: 1.8282 (1.9096) time: 0.4978 [2021-03-26 15:53:15 swin_small_patch4_window7_224] INFO: Epoch: [198] [1180/1251] eta: 0:00:36 lr: 0.000262 loss: 3.2374 (3.0825) grad_norm: 1.8459 (1.9093) time: 0.5065 [2021-03-26 15:53:20 swin_small_patch4_window7_224] INFO: Epoch: [198] [1190/1251] eta: 0:00:31 lr: 0.000262 loss: 3.2820 (3.0844) grad_norm: 1.8795 (1.9090) time: 0.5090 [2021-03-26 15:53:25 swin_small_patch4_window7_224] INFO: Epoch: [198] [1200/1251] eta: 0:00:25 lr: 0.000262 loss: 3.2820 (3.0852) grad_norm: 1.9203 (1.9092) time: 0.5006 [2021-03-26 15:53:30 swin_small_patch4_window7_224] INFO: Epoch: [198] [1210/1251] eta: 0:00:20 lr: 0.000262 loss: 3.1690 (3.0847) grad_norm: 1.8446 (1.9085) time: 0.4957 [2021-03-26 15:53:35 swin_small_patch4_window7_224] INFO: Epoch: [198] [1220/1251] eta: 0:00:15 lr: 0.000262 loss: 3.1005 (3.0843) grad_norm: 1.8446 (1.9094) time: 0.4958 [2021-03-26 15:53:40 swin_small_patch4_window7_224] INFO: Epoch: [198] [1230/1251] eta: 0:00:10 lr: 0.000262 loss: 3.2419 (3.0861) grad_norm: 1.8662 (1.9090) time: 0.5033 [2021-03-26 15:53:45 swin_small_patch4_window7_224] INFO: Epoch: [198] [1240/1251] eta: 0:00:05 lr: 0.000262 loss: 3.2857 (3.0868) grad_norm: 1.8645 (1.9087) time: 0.5045 [2021-03-26 15:53:50 swin_small_patch4_window7_224] INFO: Epoch: [198] [1250/1251] eta: 0:00:00 lr: 0.000262 loss: 3.0445 (3.0860) grad_norm: 1.8862 (1.9083) time: 0.4929 [2021-03-26 15:54:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 1.0212 (1.0212) acc1: 79.6875 (79.6875) acc5: 90.6250 (90.6250) [2021-03-26 15:54:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7561 (0.7594) acc1: 81.2500 (81.3920) acc5: 96.8750 (96.1648) [2021-03-26 15:54:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7561 (0.8070) acc1: 79.6875 (79.3155) acc5: 96.8750 (95.6101) [2021-03-26 15:54:08 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7949 (0.8113) acc1: 78.1250 (79.6371) acc5: 93.7500 (95.1613) [2021-03-26 15:54:09 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7865 (0.8108) acc1: 79.6875 (79.4588) acc5: 95.3125 (95.2363) [2021-03-26 15:54:10 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7975 (0.8330) acc1: 79.6875 (79.2640) acc5: 95.3125 (95.0720) [2021-03-26 15:54:22 swin_small_patch4_window7_224] INFO: * Acc@1 80.416 Acc@5 95.364 loss 0.819 [2021-03-26 15:54:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.4% [2021-03-26 15:54:22 swin_small_patch4_window7_224] INFO: Max accuracy: 80.53% [2021-03-26 15:54:26 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 0/1251] eta: 1:27:03 lr: 0.000262 loss: 2.2121 (2.2121) grad_norm: 1.9707 (1.9707) time: 4.1752 [2021-03-26 15:54:32 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 10/1251] eta: 0:18:04 lr: 0.000262 loss: 2.9989 (2.9404) grad_norm: 1.8304 (1.8161) time: 0.8739 [2021-03-26 15:54:37 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 20/1251] eta: 0:14:16 lr: 0.000262 loss: 3.2781 (3.0999) grad_norm: 1.8184 (1.8433) time: 0.5222 [2021-03-26 15:54:42 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 30/1251] eta: 0:12:54 lr: 0.000262 loss: 3.2877 (3.0726) grad_norm: 1.8435 (1.8744) time: 0.5027 [2021-03-26 15:54:47 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 40/1251] eta: 0:12:13 lr: 0.000262 loss: 3.1494 (3.0529) grad_norm: 1.8860 (1.8660) time: 0.5109 [2021-03-26 15:54:52 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 50/1251] eta: 0:11:43 lr: 0.000262 loss: 3.2360 (3.0621) grad_norm: 1.8155 (1.8809) time: 0.5095 [2021-03-26 15:54:57 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 60/1251] eta: 0:11:22 lr: 0.000262 loss: 3.2364 (3.0333) grad_norm: 1.8159 (1.8702) time: 0.5048 [2021-03-26 15:55:02 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 70/1251] eta: 0:11:03 lr: 0.000262 loss: 2.9260 (3.0184) grad_norm: 1.7660 (1.8564) time: 0.5024 [2021-03-26 15:55:07 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 80/1251] eta: 0:10:50 lr: 0.000262 loss: 3.1378 (3.0474) grad_norm: 1.7660 (1.8702) time: 0.5034 [2021-03-26 15:55:12 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 90/1251] eta: 0:10:39 lr: 0.000262 loss: 3.2052 (3.0591) grad_norm: 1.8188 (1.8727) time: 0.5096 [2021-03-26 15:55:17 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 100/1251] eta: 0:10:28 lr: 0.000262 loss: 3.0099 (3.0481) grad_norm: 1.8404 (1.8848) time: 0.5058 [2021-03-26 15:55:22 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 110/1251] eta: 0:10:19 lr: 0.000262 loss: 3.0099 (3.0541) grad_norm: 1.9075 (1.8933) time: 0.5100 [2021-03-26 15:55:27 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 120/1251] eta: 0:10:11 lr: 0.000262 loss: 3.2973 (3.0826) grad_norm: 1.8843 (1.8936) time: 0.5163 [2021-03-26 15:55:32 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 130/1251] eta: 0:10:03 lr: 0.000262 loss: 3.2973 (3.0850) grad_norm: 1.8843 (1.9025) time: 0.5098 [2021-03-26 15:55:38 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 140/1251] eta: 0:09:55 lr: 0.000261 loss: 3.2444 (3.0947) grad_norm: 1.9836 (1.9062) time: 0.5081 [2021-03-26 15:55:43 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 150/1251] eta: 0:09:48 lr: 0.000261 loss: 3.0631 (3.0827) grad_norm: 1.9041 (1.9088) time: 0.5125 [2021-03-26 15:55:48 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 160/1251] eta: 0:09:40 lr: 0.000261 loss: 2.9592 (3.0757) grad_norm: 1.8861 (1.9091) time: 0.5058 [2021-03-26 15:55:53 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 170/1251] eta: 0:09:33 lr: 0.000261 loss: 3.1183 (3.0747) grad_norm: 1.8585 (1.9151) time: 0.4988 [2021-03-26 15:55:58 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 180/1251] eta: 0:09:26 lr: 0.000261 loss: 3.1779 (3.0761) grad_norm: 1.8242 (1.9161) time: 0.5034 [2021-03-26 15:56:03 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 190/1251] eta: 0:09:19 lr: 0.000261 loss: 3.1940 (3.0746) grad_norm: 1.8961 (1.9429) time: 0.5034 [2021-03-26 15:56:08 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 200/1251] eta: 0:09:13 lr: 0.000261 loss: 3.0738 (3.0630) grad_norm: 2.0253 (1.9448) time: 0.5065 [2021-03-26 15:56:13 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 210/1251] eta: 0:09:07 lr: 0.000261 loss: 3.0514 (3.0662) grad_norm: 1.8699 (1.9389) time: 0.5072 [2021-03-26 15:56:18 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 220/1251] eta: 0:09:00 lr: 0.000261 loss: 3.0569 (3.0680) grad_norm: 1.8376 (1.9401) time: 0.4994 [2021-03-26 15:56:23 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 230/1251] eta: 0:08:54 lr: 0.000261 loss: 3.2696 (3.0739) grad_norm: 1.8403 (1.9395) time: 0.5005 [2021-03-26 15:56:28 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 240/1251] eta: 0:08:48 lr: 0.000261 loss: 3.2696 (3.0773) grad_norm: 1.8459 (1.9379) time: 0.5038 [2021-03-26 15:56:33 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 250/1251] eta: 0:08:42 lr: 0.000261 loss: 3.1352 (3.0737) grad_norm: 1.8898 (1.9389) time: 0.5083 [2021-03-26 15:56:38 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 260/1251] eta: 0:08:36 lr: 0.000261 loss: 3.1335 (3.0788) grad_norm: 1.9056 (1.9376) time: 0.5088 [2021-03-26 15:56:43 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 270/1251] eta: 0:08:31 lr: 0.000261 loss: 3.1371 (3.0810) grad_norm: 1.8834 (1.9361) time: 0.5036 [2021-03-26 15:56:48 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 280/1251] eta: 0:08:25 lr: 0.000261 loss: 3.2056 (3.0755) grad_norm: 1.8185 (1.9345) time: 0.5026 [2021-03-26 15:56:53 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 290/1251] eta: 0:08:19 lr: 0.000261 loss: 3.2478 (3.0796) grad_norm: 1.8772 (1.9367) time: 0.5008 [2021-03-26 15:56:58 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 300/1251] eta: 0:08:13 lr: 0.000261 loss: 3.0125 (3.0733) grad_norm: 1.9124 (1.9381) time: 0.5064 [2021-03-26 15:57:03 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 310/1251] eta: 0:08:08 lr: 0.000261 loss: 2.7404 (3.0638) grad_norm: 1.9418 (1.9395) time: 0.5069 [2021-03-26 15:57:08 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 320/1251] eta: 0:08:02 lr: 0.000261 loss: 3.1207 (3.0688) grad_norm: 1.8809 (1.9381) time: 0.5000 [2021-03-26 15:57:13 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 330/1251] eta: 0:07:56 lr: 0.000261 loss: 3.2679 (3.0705) grad_norm: 1.8135 (1.9331) time: 0.5003 [2021-03-26 15:57:18 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 340/1251] eta: 0:07:51 lr: 0.000261 loss: 3.1170 (3.0691) grad_norm: 1.8135 (1.9341) time: 0.5062 [2021-03-26 15:57:24 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 350/1251] eta: 0:07:45 lr: 0.000261 loss: 3.0950 (3.0668) grad_norm: 1.8928 (1.9364) time: 0.5067 [2021-03-26 15:57:29 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 360/1251] eta: 0:07:40 lr: 0.000261 loss: 3.1402 (3.0709) grad_norm: 1.9407 (1.9381) time: 0.5024 [2021-03-26 15:57:34 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 370/1251] eta: 0:07:34 lr: 0.000261 loss: 3.1646 (3.0732) grad_norm: 1.8872 (1.9373) time: 0.5001 [2021-03-26 15:57:38 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 380/1251] eta: 0:07:29 lr: 0.000261 loss: 3.0968 (3.0698) grad_norm: 1.8390 (1.9345) time: 0.4968 [2021-03-26 15:57:44 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 390/1251] eta: 0:07:23 lr: 0.000261 loss: 3.1088 (3.0682) grad_norm: 1.8739 (1.9341) time: 0.5024 [2021-03-26 15:57:49 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 400/1251] eta: 0:07:18 lr: 0.000261 loss: 3.1533 (3.0698) grad_norm: 1.9268 (1.9347) time: 0.5009 [2021-03-26 15:57:54 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 410/1251] eta: 0:07:12 lr: 0.000261 loss: 3.0975 (3.0688) grad_norm: 1.8999 (1.9335) time: 0.4993 [2021-03-26 15:57:59 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 420/1251] eta: 0:07:07 lr: 0.000260 loss: 3.2430 (3.0703) grad_norm: 1.9430 (1.9365) time: 0.5025 [2021-03-26 15:58:04 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 430/1251] eta: 0:07:02 lr: 0.000260 loss: 3.2977 (3.0716) grad_norm: 2.0084 (1.9405) time: 0.5039 [2021-03-26 15:58:09 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 440/1251] eta: 0:06:56 lr: 0.000260 loss: 3.2455 (3.0761) grad_norm: 1.9108 (1.9399) time: 0.5089 [2021-03-26 15:58:14 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 450/1251] eta: 0:06:51 lr: 0.000260 loss: 3.2382 (3.0791) grad_norm: 1.8460 (1.9522) time: 0.5141 [2021-03-26 15:58:19 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 460/1251] eta: 0:06:46 lr: 0.000260 loss: 3.1653 (3.0821) grad_norm: 1.8957 (1.9531) time: 0.5139 [2021-03-26 15:58:24 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 470/1251] eta: 0:06:41 lr: 0.000260 loss: 3.0492 (3.0757) grad_norm: 1.9190 (1.9559) time: 0.5096 [2021-03-26 15:58:29 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 480/1251] eta: 0:06:36 lr: 0.000260 loss: 2.7780 (3.0714) grad_norm: 1.8643 (1.9543) time: 0.5068 [2021-03-26 15:58:34 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 490/1251] eta: 0:06:30 lr: 0.000260 loss: 3.0673 (3.0713) grad_norm: 1.7333 (1.9529) time: 0.5031 [2021-03-26 15:58:39 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 500/1251] eta: 0:06:25 lr: 0.000260 loss: 2.9214 (3.0650) grad_norm: 1.7307 (1.9487) time: 0.5043 [2021-03-26 15:58:44 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 510/1251] eta: 0:06:20 lr: 0.000260 loss: 3.0883 (3.0652) grad_norm: 1.7485 (1.9453) time: 0.5071 [2021-03-26 15:58:49 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 520/1251] eta: 0:06:15 lr: 0.000260 loss: 3.3480 (3.0680) grad_norm: 1.8181 (1.9442) time: 0.5070 [2021-03-26 15:58:54 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 530/1251] eta: 0:06:09 lr: 0.000260 loss: 2.9742 (3.0613) grad_norm: 1.8262 (1.9436) time: 0.5065 [2021-03-26 15:58:59 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 540/1251] eta: 0:06:04 lr: 0.000260 loss: 2.9693 (3.0629) grad_norm: 1.8262 (1.9430) time: 0.5041 [2021-03-26 15:59:05 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 550/1251] eta: 0:05:59 lr: 0.000260 loss: 3.1572 (3.0608) grad_norm: 1.8327 (1.9419) time: 0.5119 [2021-03-26 15:59:10 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 560/1251] eta: 0:05:54 lr: 0.000260 loss: 3.1287 (3.0618) grad_norm: 1.8197 (1.9402) time: 0.5149 [2021-03-26 15:59:15 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 570/1251] eta: 0:05:49 lr: 0.000260 loss: 3.1317 (3.0624) grad_norm: 1.8106 (1.9394) time: 0.5050 [2021-03-26 15:59:20 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 580/1251] eta: 0:05:43 lr: 0.000260 loss: 3.2443 (3.0637) grad_norm: 1.7844 (1.9408) time: 0.4985 [2021-03-26 15:59:25 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 590/1251] eta: 0:05:38 lr: 0.000260 loss: 3.1372 (3.0618) grad_norm: 1.9001 (1.9404) time: 0.4988 [2021-03-26 15:59:30 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 600/1251] eta: 0:05:33 lr: 0.000260 loss: 3.1317 (3.0625) grad_norm: 1.9370 (1.9411) time: 0.5052 [2021-03-26 15:59:35 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 610/1251] eta: 0:05:28 lr: 0.000260 loss: 2.9716 (3.0593) grad_norm: 1.9015 (1.9405) time: 0.5063 [2021-03-26 15:59:40 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 620/1251] eta: 0:05:23 lr: 0.000260 loss: 3.1583 (3.0641) grad_norm: 1.8892 (1.9401) time: 0.5071 [2021-03-26 15:59:45 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 630/1251] eta: 0:05:17 lr: 0.000260 loss: 3.1515 (3.0598) grad_norm: 1.8772 (1.9398) time: 0.5049 [2021-03-26 15:59:50 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 640/1251] eta: 0:05:12 lr: 0.000260 loss: 3.1363 (3.0603) grad_norm: 1.8052 (1.9382) time: 0.5028 [2021-03-26 15:59:55 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 650/1251] eta: 0:05:07 lr: 0.000260 loss: 3.2043 (3.0615) grad_norm: 1.8027 (1.9375) time: 0.5046 [2021-03-26 16:00:00 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 660/1251] eta: 0:05:02 lr: 0.000260 loss: 3.2043 (3.0642) grad_norm: 1.8392 (1.9367) time: 0.5050 [2021-03-26 16:00:05 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 670/1251] eta: 0:04:57 lr: 0.000260 loss: 3.1319 (3.0635) grad_norm: 1.8759 (1.9382) time: 0.5047 [2021-03-26 16:00:10 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 680/1251] eta: 0:04:52 lr: 0.000260 loss: 3.1149 (3.0640) grad_norm: 1.8945 (1.9380) time: 0.5094 [2021-03-26 16:00:15 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 690/1251] eta: 0:04:46 lr: 0.000260 loss: 3.1149 (3.0653) grad_norm: 1.9864 (1.9384) time: 0.5095 [2021-03-26 16:00:20 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 700/1251] eta: 0:04:41 lr: 0.000259 loss: 3.2190 (3.0644) grad_norm: 1.8948 (1.9368) time: 0.5044 [2021-03-26 16:00:25 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 710/1251] eta: 0:04:36 lr: 0.000259 loss: 3.1967 (3.0649) grad_norm: 1.8601 (1.9363) time: 0.5019 [2021-03-26 16:00:30 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 720/1251] eta: 0:04:31 lr: 0.000259 loss: 3.2416 (3.0669) grad_norm: 1.9474 (1.9368) time: 0.5006 [2021-03-26 16:00:36 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 730/1251] eta: 0:04:26 lr: 0.000259 loss: 3.3154 (3.0668) grad_norm: 1.8869 (1.9359) time: 0.5095 [2021-03-26 16:00:41 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 740/1251] eta: 0:04:21 lr: 0.000259 loss: 3.2874 (3.0693) grad_norm: 1.7433 (1.9329) time: 0.5123 [2021-03-26 16:00:46 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 750/1251] eta: 0:04:16 lr: 0.000259 loss: 3.2823 (3.0717) grad_norm: 1.7433 (1.9318) time: 0.5176 [2021-03-26 16:00:51 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 760/1251] eta: 0:04:10 lr: 0.000259 loss: 3.3709 (3.0749) grad_norm: 1.8916 (1.9330) time: 0.5143 [2021-03-26 16:00:56 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 770/1251] eta: 0:04:05 lr: 0.000259 loss: 3.0850 (3.0716) grad_norm: 1.8892 (1.9320) time: 0.5040 [2021-03-26 16:01:01 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 780/1251] eta: 0:04:00 lr: 0.000259 loss: 2.7700 (3.0702) grad_norm: 1.8589 (1.9316) time: 0.5062 [2021-03-26 16:01:06 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 790/1251] eta: 0:03:55 lr: 0.000259 loss: 3.1175 (3.0691) grad_norm: 1.8554 (1.9300) time: 0.5064 [2021-03-26 16:01:11 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 800/1251] eta: 0:03:50 lr: 0.000259 loss: 3.0059 (3.0676) grad_norm: 1.7431 (1.9274) time: 0.5051 [2021-03-26 16:01:16 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 810/1251] eta: 0:03:45 lr: 0.000259 loss: 3.0630 (3.0696) grad_norm: 1.7312 (1.9270) time: 0.5046 [2021-03-26 16:01:21 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 820/1251] eta: 0:03:40 lr: 0.000259 loss: 3.1520 (3.0703) grad_norm: 1.8182 (1.9257) time: 0.5019 [2021-03-26 16:01:26 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 830/1251] eta: 0:03:34 lr: 0.000259 loss: 3.2448 (3.0710) grad_norm: 1.8675 (1.9254) time: 0.5048 [2021-03-26 16:01:31 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 840/1251] eta: 0:03:29 lr: 0.000259 loss: 3.2448 (3.0728) grad_norm: 1.8896 (1.9252) time: 0.5026 [2021-03-26 16:01:36 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 850/1251] eta: 0:03:24 lr: 0.000259 loss: 3.2729 (3.0745) grad_norm: 1.8368 (1.9244) time: 0.5035 [2021-03-26 16:01:42 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 860/1251] eta: 0:03:19 lr: 0.000259 loss: 3.2045 (3.0753) grad_norm: 1.8098 (1.9239) time: 0.5115 [2021-03-26 16:01:47 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 870/1251] eta: 0:03:14 lr: 0.000259 loss: 3.2169 (3.0774) grad_norm: 1.8067 (1.9239) time: 0.5084 [2021-03-26 16:01:52 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 880/1251] eta: 0:03:09 lr: 0.000259 loss: 3.3086 (3.0783) grad_norm: 1.8305 (1.9233) time: 0.5114 [2021-03-26 16:01:57 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 890/1251] eta: 0:03:04 lr: 0.000259 loss: 3.1970 (3.0773) grad_norm: 1.8015 (1.9211) time: 0.5156 [2021-03-26 16:02:02 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 900/1251] eta: 0:02:59 lr: 0.000259 loss: 3.1826 (3.0785) grad_norm: 1.8077 (1.9215) time: 0.5084 [2021-03-26 16:02:07 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 910/1251] eta: 0:02:54 lr: 0.000259 loss: 3.2242 (3.0788) grad_norm: 1.8592 (1.9204) time: 0.5018 [2021-03-26 16:02:12 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 920/1251] eta: 0:02:48 lr: 0.000259 loss: 3.1768 (3.0789) grad_norm: 1.7731 (1.9188) time: 0.5096 [2021-03-26 16:02:17 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 930/1251] eta: 0:02:43 lr: 0.000259 loss: 2.9398 (3.0771) grad_norm: 1.7805 (1.9172) time: 0.5042 [2021-03-26 16:02:22 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 940/1251] eta: 0:02:38 lr: 0.000259 loss: 3.1515 (3.0790) grad_norm: 1.8123 (1.9174) time: 0.4943 [2021-03-26 16:02:27 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 950/1251] eta: 0:02:33 lr: 0.000259 loss: 3.4483 (3.0823) grad_norm: 1.9095 (1.9179) time: 0.5031 [2021-03-26 16:02:32 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 960/1251] eta: 0:02:28 lr: 0.000259 loss: 3.3163 (3.0827) grad_norm: 1.9255 (1.9185) time: 0.5088 [2021-03-26 16:02:37 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 970/1251] eta: 0:02:23 lr: 0.000259 loss: 3.3051 (3.0834) grad_norm: 1.9141 (1.9177) time: 0.5070 [2021-03-26 16:02:42 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 980/1251] eta: 0:02:18 lr: 0.000258 loss: 3.2078 (3.0813) grad_norm: 1.8300 (1.9163) time: 0.5071 [2021-03-26 16:02:47 swin_small_patch4_window7_224] INFO: Epoch: [199] [ 990/1251] eta: 0:02:13 lr: 0.000258 loss: 2.9572 (3.0809) grad_norm: 1.8644 (1.9169) time: 0.5069 [2021-03-26 16:02:52 swin_small_patch4_window7_224] INFO: Epoch: [199] [1000/1251] eta: 0:02:07 lr: 0.000258 loss: 3.0626 (3.0798) grad_norm: 1.8778 (1.9165) time: 0.5038 [2021-03-26 16:02:57 swin_small_patch4_window7_224] INFO: Epoch: [199] [1010/1251] eta: 0:02:02 lr: 0.000258 loss: 3.0626 (3.0774) grad_norm: 1.8703 (1.9164) time: 0.5001 [2021-03-26 16:03:03 swin_small_patch4_window7_224] INFO: Epoch: [199] [1020/1251] eta: 0:01:57 lr: 0.000258 loss: 2.9260 (3.0770) grad_norm: 1.9618 (1.9173) time: 0.5032 [2021-03-26 16:03:08 swin_small_patch4_window7_224] INFO: Epoch: [199] [1030/1251] eta: 0:01:52 lr: 0.000258 loss: 2.9260 (3.0761) grad_norm: 1.9141 (1.9164) time: 0.5081 [2021-03-26 16:03:13 swin_small_patch4_window7_224] INFO: Epoch: [199] [1040/1251] eta: 0:01:47 lr: 0.000258 loss: 3.0021 (3.0749) grad_norm: 1.8301 (1.9173) time: 0.5059 [2021-03-26 16:03:18 swin_small_patch4_window7_224] INFO: Epoch: [199] [1050/1251] eta: 0:01:42 lr: 0.000258 loss: 3.1318 (3.0750) grad_norm: 1.9354 (1.9178) time: 0.5010 [2021-03-26 16:03:23 swin_small_patch4_window7_224] INFO: Epoch: [199] [1060/1251] eta: 0:01:37 lr: 0.000258 loss: 3.1318 (3.0741) grad_norm: 1.9365 (1.9188) time: 0.5013 [2021-03-26 16:03:28 swin_small_patch4_window7_224] INFO: Epoch: [199] [1070/1251] eta: 0:01:32 lr: 0.000258 loss: 2.8732 (3.0730) grad_norm: 1.9212 (1.9183) time: 0.5045 [2021-03-26 16:03:33 swin_small_patch4_window7_224] INFO: Epoch: [199] [1080/1251] eta: 0:01:27 lr: 0.000258 loss: 2.9593 (3.0733) grad_norm: 1.8689 (1.9181) time: 0.5044 [2021-03-26 16:03:38 swin_small_patch4_window7_224] INFO: Epoch: [199] [1090/1251] eta: 0:01:21 lr: 0.000258 loss: 3.1072 (3.0741) grad_norm: 1.9380 (1.9182) time: 0.5030 [2021-03-26 16:03:43 swin_small_patch4_window7_224] INFO: Epoch: [199] [1100/1251] eta: 0:01:16 lr: 0.000258 loss: 2.8316 (3.0717) grad_norm: 1.9428 (1.9192) time: 0.5005 [2021-03-26 16:03:48 swin_small_patch4_window7_224] INFO: Epoch: [199] [1110/1251] eta: 0:01:11 lr: 0.000258 loss: 2.7818 (3.0700) grad_norm: 1.8677 (1.9183) time: 0.5006 [2021-03-26 16:03:53 swin_small_patch4_window7_224] INFO: Epoch: [199] [1120/1251] eta: 0:01:06 lr: 0.000258 loss: 2.7611 (3.0683) grad_norm: 1.8336 (1.9180) time: 0.5006 [2021-03-26 16:03:58 swin_small_patch4_window7_224] INFO: Epoch: [199] [1130/1251] eta: 0:01:01 lr: 0.000258 loss: 2.9398 (3.0683) grad_norm: 1.8960 (1.9194) time: 0.4989 [2021-03-26 16:04:03 swin_small_patch4_window7_224] INFO: Epoch: [199] [1140/1251] eta: 0:00:56 lr: 0.000258 loss: 3.0119 (3.0665) grad_norm: 1.9167 (1.9193) time: 0.5023 [2021-03-26 16:04:08 swin_small_patch4_window7_224] INFO: Epoch: [199] [1150/1251] eta: 0:00:51 lr: 0.000258 loss: 2.5892 (3.0642) grad_norm: 1.8601 (1.9190) time: 0.5047 [2021-03-26 16:04:13 swin_small_patch4_window7_224] INFO: Epoch: [199] [1160/1251] eta: 0:00:46 lr: 0.000258 loss: 3.0202 (3.0635) grad_norm: 1.8305 (1.9185) time: 0.5020 [2021-03-26 16:04:18 swin_small_patch4_window7_224] INFO: Epoch: [199] [1170/1251] eta: 0:00:41 lr: 0.000258 loss: 3.0729 (3.0633) grad_norm: 1.9041 (1.9186) time: 0.5018 [2021-03-26 16:04:23 swin_small_patch4_window7_224] INFO: Epoch: [199] [1180/1251] eta: 0:00:36 lr: 0.000258 loss: 3.1737 (3.0641) grad_norm: 1.9663 (1.9192) time: 0.5039 [2021-03-26 16:04:28 swin_small_patch4_window7_224] INFO: Epoch: [199] [1190/1251] eta: 0:00:31 lr: 0.000258 loss: 3.2068 (3.0622) grad_norm: 1.8779 (1.9185) time: 0.5085 [2021-03-26 16:04:33 swin_small_patch4_window7_224] INFO: Epoch: [199] [1200/1251] eta: 0:00:25 lr: 0.000258 loss: 3.2199 (3.0634) grad_norm: 1.8779 (1.9189) time: 0.5033 [2021-03-26 16:04:38 swin_small_patch4_window7_224] INFO: Epoch: [199] [1210/1251] eta: 0:00:20 lr: 0.000258 loss: 3.3595 (3.0651) grad_norm: 1.8722 (1.9180) time: 0.4977 [2021-03-26 16:04:43 swin_small_patch4_window7_224] INFO: Epoch: [199] [1220/1251] eta: 0:00:15 lr: 0.000258 loss: 3.2634 (3.0657) grad_norm: 1.9027 (1.9193) time: 0.5051 [2021-03-26 16:04:48 swin_small_patch4_window7_224] INFO: Epoch: [199] [1230/1251] eta: 0:00:10 lr: 0.000258 loss: 3.1613 (3.0649) grad_norm: 1.9974 (1.9199) time: 0.5019 [2021-03-26 16:04:53 swin_small_patch4_window7_224] INFO: Epoch: [199] [1240/1251] eta: 0:00:05 lr: 0.000258 loss: 3.0979 (3.0658) grad_norm: 1.9974 (1.9209) time: 0.4956 [2021-03-26 16:04:58 swin_small_patch4_window7_224] INFO: Epoch: [199] [1250/1251] eta: 0:00:00 lr: 0.000258 loss: 3.0648 (3.0652) grad_norm: 1.8481 (1.9203) time: 0.5007 [2021-03-26 16:05:06 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:16 loss: 1.0296 (1.0296) acc1: 70.3125 (70.3125) acc5: 93.7500 (93.7500) [2021-03-26 16:05:08 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8648 (0.8503) acc1: 81.2500 (79.9716) acc5: 93.7500 (94.7443) [2021-03-26 16:05:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8280 (0.8522) acc1: 79.6875 (79.5387) acc5: 95.3125 (95.1637) [2021-03-26 16:05:14 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8627 (0.8544) acc1: 76.5625 (78.9315) acc5: 95.3125 (95.3125) [2021-03-26 16:05:15 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8451 (0.8617) acc1: 76.5625 (78.6966) acc5: 95.3125 (95.3125) [2021-03-26 16:05:16 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7999 (0.8434) acc1: 79.6875 (79.2960) acc5: 95.3125 (95.4240) [2021-03-26 16:05:25 swin_small_patch4_window7_224] INFO: * Acc@1 80.450 Acc@5 95.396 loss 0.817 [2021-03-26 16:05:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.5% [2021-03-26 16:05:25 swin_small_patch4_window7_224] INFO: Max accuracy: 80.53% [2021-03-26 16:05:28 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 0/1251] eta: 1:22:01 lr: 0.000258 loss: 2.9360 (2.9360) grad_norm: 1.6929 (1.6929) time: 3.9343 [2021-03-26 16:05:34 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 10/1251] eta: 0:17:44 lr: 0.000257 loss: 2.9360 (2.9342) grad_norm: 1.8629 (2.0478) time: 0.8579 [2021-03-26 16:05:39 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 20/1251] eta: 0:14:17 lr: 0.000257 loss: 3.0049 (2.9771) grad_norm: 1.9381 (2.0718) time: 0.5349 [2021-03-26 16:05:44 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 30/1251] eta: 0:12:58 lr: 0.000257 loss: 3.1349 (3.0281) grad_norm: 1.9248 (1.9983) time: 0.5162 [2021-03-26 16:05:49 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 40/1251] eta: 0:12:12 lr: 0.000257 loss: 3.2063 (3.0748) grad_norm: 1.8293 (1.9857) time: 0.5080 [2021-03-26 16:05:54 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 50/1251] eta: 0:11:41 lr: 0.000257 loss: 3.2293 (3.0665) grad_norm: 1.8827 (1.9708) time: 0.5019 [2021-03-26 16:05:59 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 60/1251] eta: 0:11:21 lr: 0.000257 loss: 3.2725 (3.0753) grad_norm: 1.8827 (1.9599) time: 0.5045 [2021-03-26 16:06:05 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 70/1251] eta: 0:11:05 lr: 0.000257 loss: 3.1616 (3.0717) grad_norm: 1.8648 (1.9625) time: 0.5111 [2021-03-26 16:06:10 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 80/1251] eta: 0:10:50 lr: 0.000257 loss: 3.1224 (3.0803) grad_norm: 1.9104 (1.9520) time: 0.5066 [2021-03-26 16:06:15 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 90/1251] eta: 0:10:39 lr: 0.000257 loss: 3.0022 (3.0565) grad_norm: 1.8469 (1.9414) time: 0.5064 [2021-03-26 16:06:20 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 100/1251] eta: 0:10:29 lr: 0.000257 loss: 3.0023 (3.0589) grad_norm: 1.8296 (1.9547) time: 0.5108 [2021-03-26 16:06:25 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 110/1251] eta: 0:10:21 lr: 0.000257 loss: 3.0098 (3.0412) grad_norm: 1.8294 (1.9562) time: 0.5146 [2021-03-26 16:06:30 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 120/1251] eta: 0:10:13 lr: 0.000257 loss: 2.9328 (3.0202) grad_norm: 1.8018 (1.9450) time: 0.5180 [2021-03-26 16:06:35 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 130/1251] eta: 0:10:04 lr: 0.000257 loss: 2.8601 (3.0244) grad_norm: 1.8441 (inf) time: 0.5110 [2021-03-26 16:06:40 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 140/1251] eta: 0:09:57 lr: 0.000257 loss: 3.0785 (3.0393) grad_norm: 1.9288 (inf) time: 0.5147 [2021-03-26 16:06:46 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 150/1251] eta: 0:09:50 lr: 0.000257 loss: 3.0733 (3.0342) grad_norm: 1.8949 (inf) time: 0.5163 [2021-03-26 16:06:51 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 160/1251] eta: 0:09:42 lr: 0.000257 loss: 3.0303 (3.0295) grad_norm: 1.8799 (inf) time: 0.5024 [2021-03-26 16:06:56 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 170/1251] eta: 0:09:35 lr: 0.000257 loss: 3.1575 (3.0423) grad_norm: 2.0174 (inf) time: 0.5003 [2021-03-26 16:07:01 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 180/1251] eta: 0:09:28 lr: 0.000257 loss: 3.2489 (3.0444) grad_norm: 2.0119 (inf) time: 0.5092 [2021-03-26 16:07:06 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 190/1251] eta: 0:09:22 lr: 0.000257 loss: 3.2889 (3.0546) grad_norm: 1.9225 (inf) time: 0.5109 [2021-03-26 16:07:11 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 200/1251] eta: 0:09:15 lr: 0.000257 loss: 3.1731 (3.0503) grad_norm: 1.8769 (inf) time: 0.5094 [2021-03-26 16:07:16 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 210/1251] eta: 0:09:09 lr: 0.000257 loss: 3.0715 (3.0514) grad_norm: 1.8769 (inf) time: 0.5046 [2021-03-26 16:07:21 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 220/1251] eta: 0:09:03 lr: 0.000257 loss: 3.1347 (3.0564) grad_norm: 1.8777 (inf) time: 0.5079 [2021-03-26 16:07:26 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 230/1251] eta: 0:08:57 lr: 0.000257 loss: 3.1274 (3.0517) grad_norm: 1.8777 (inf) time: 0.5137 [2021-03-26 16:07:31 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 240/1251] eta: 0:08:50 lr: 0.000257 loss: 2.9705 (3.0401) grad_norm: 1.8995 (inf) time: 0.5034 [2021-03-26 16:07:36 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 250/1251] eta: 0:08:44 lr: 0.000257 loss: 2.9622 (3.0398) grad_norm: 1.9399 (inf) time: 0.5008 [2021-03-26 16:07:41 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 260/1251] eta: 0:08:39 lr: 0.000257 loss: 3.1230 (3.0404) grad_norm: 1.9713 (inf) time: 0.5095 [2021-03-26 16:07:46 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 270/1251] eta: 0:08:33 lr: 0.000257 loss: 3.1477 (3.0410) grad_norm: 1.8758 (inf) time: 0.5104 [2021-03-26 16:07:51 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 280/1251] eta: 0:08:27 lr: 0.000256 loss: 3.1057 (3.0408) grad_norm: 1.8283 (inf) time: 0.5073 [2021-03-26 16:07:57 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 290/1251] eta: 0:08:21 lr: 0.000256 loss: 3.1381 (3.0459) grad_norm: 1.8283 (inf) time: 0.5058 [2021-03-26 16:08:02 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 300/1251] eta: 0:08:16 lr: 0.000256 loss: 3.2428 (3.0535) grad_norm: 1.8225 (inf) time: 0.5112 [2021-03-26 16:08:07 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 310/1251] eta: 0:08:10 lr: 0.000256 loss: 3.1632 (3.0556) grad_norm: 1.8969 (inf) time: 0.5119 [2021-03-26 16:08:12 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 320/1251] eta: 0:08:05 lr: 0.000256 loss: 2.9721 (3.0482) grad_norm: 1.9182 (inf) time: 0.5116 [2021-03-26 16:08:17 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 330/1251] eta: 0:07:59 lr: 0.000256 loss: 2.4853 (3.0439) grad_norm: 1.8224 (inf) time: 0.5115 [2021-03-26 16:08:22 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 340/1251] eta: 0:07:54 lr: 0.000256 loss: 3.0371 (3.0451) grad_norm: 1.8665 (inf) time: 0.5096 [2021-03-26 16:08:27 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 350/1251] eta: 0:07:48 lr: 0.000256 loss: 3.0089 (3.0434) grad_norm: 1.9805 (inf) time: 0.5094 [2021-03-26 16:08:32 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 360/1251] eta: 0:07:42 lr: 0.000256 loss: 3.0089 (3.0394) grad_norm: 1.8734 (inf) time: 0.5012 [2021-03-26 16:08:37 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 370/1251] eta: 0:07:37 lr: 0.000256 loss: 3.2141 (3.0468) grad_norm: 1.7822 (inf) time: 0.4985 [2021-03-26 16:08:42 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 380/1251] eta: 0:07:31 lr: 0.000256 loss: 3.2514 (3.0508) grad_norm: 1.7622 (inf) time: 0.4990 [2021-03-26 16:08:47 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 390/1251] eta: 0:07:25 lr: 0.000256 loss: 3.0737 (3.0472) grad_norm: 1.8400 (inf) time: 0.4996 [2021-03-26 16:08:52 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 400/1251] eta: 0:07:20 lr: 0.000256 loss: 3.0737 (3.0518) grad_norm: 1.8775 (inf) time: 0.5007 [2021-03-26 16:08:57 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 410/1251] eta: 0:07:15 lr: 0.000256 loss: 3.2679 (3.0557) grad_norm: 1.8274 (inf) time: 0.5038 [2021-03-26 16:09:02 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 420/1251] eta: 0:07:09 lr: 0.000256 loss: 3.0678 (3.0498) grad_norm: 1.8325 (inf) time: 0.5098 [2021-03-26 16:09:07 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 430/1251] eta: 0:07:04 lr: 0.000256 loss: 3.1141 (3.0562) grad_norm: 1.8931 (inf) time: 0.5064 [2021-03-26 16:09:12 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 440/1251] eta: 0:06:58 lr: 0.000256 loss: 3.1039 (3.0532) grad_norm: 1.9091 (inf) time: 0.5012 [2021-03-26 16:09:17 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 450/1251] eta: 0:06:53 lr: 0.000256 loss: 2.9588 (3.0559) grad_norm: 1.8751 (inf) time: 0.5009 [2021-03-26 16:09:22 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 460/1251] eta: 0:06:48 lr: 0.000256 loss: 3.0716 (3.0585) grad_norm: 1.8895 (inf) time: 0.5053 [2021-03-26 16:09:28 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 470/1251] eta: 0:06:42 lr: 0.000256 loss: 2.9289 (3.0519) grad_norm: 1.8471 (inf) time: 0.5087 [2021-03-26 16:09:33 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 480/1251] eta: 0:06:37 lr: 0.000256 loss: 3.0541 (3.0556) grad_norm: 1.8599 (inf) time: 0.5030 [2021-03-26 16:09:38 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 490/1251] eta: 0:06:32 lr: 0.000256 loss: 3.1822 (3.0537) grad_norm: 1.8599 (inf) time: 0.5046 [2021-03-26 16:09:43 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 500/1251] eta: 0:06:26 lr: 0.000256 loss: 2.7572 (3.0512) grad_norm: 1.8128 (inf) time: 0.5090 [2021-03-26 16:09:48 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 510/1251] eta: 0:06:21 lr: 0.000256 loss: 2.6718 (3.0471) grad_norm: 1.9023 (inf) time: 0.5013 [2021-03-26 16:09:53 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 520/1251] eta: 0:06:16 lr: 0.000256 loss: 2.8636 (3.0427) grad_norm: 1.9285 (inf) time: 0.5021 [2021-03-26 16:09:58 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 530/1251] eta: 0:06:10 lr: 0.000256 loss: 3.1192 (3.0468) grad_norm: 1.9951 (inf) time: 0.5034 [2021-03-26 16:10:03 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 540/1251] eta: 0:06:05 lr: 0.000256 loss: 3.2125 (3.0501) grad_norm: 1.8583 (inf) time: 0.5007 [2021-03-26 16:10:08 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 550/1251] eta: 0:06:00 lr: 0.000256 loss: 3.1047 (3.0501) grad_norm: 1.8583 (inf) time: 0.5170 [2021-03-26 16:10:13 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 560/1251] eta: 0:05:55 lr: 0.000255 loss: 3.1047 (3.0507) grad_norm: 1.9160 (inf) time: 0.5168 [2021-03-26 16:10:18 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 570/1251] eta: 0:05:50 lr: 0.000255 loss: 3.1067 (3.0508) grad_norm: 1.8736 (inf) time: 0.5028 [2021-03-26 16:10:23 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 580/1251] eta: 0:05:44 lr: 0.000255 loss: 3.2370 (3.0535) grad_norm: 1.8987 (inf) time: 0.5076 [2021-03-26 16:10:28 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 590/1251] eta: 0:05:39 lr: 0.000255 loss: 3.1044 (3.0503) grad_norm: 1.8792 (inf) time: 0.5064 [2021-03-26 16:10:33 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 600/1251] eta: 0:05:34 lr: 0.000255 loss: 3.0663 (3.0531) grad_norm: 1.8724 (inf) time: 0.4967 [2021-03-26 16:10:38 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 610/1251] eta: 0:05:29 lr: 0.000255 loss: 3.0832 (3.0522) grad_norm: 1.8201 (inf) time: 0.5014 [2021-03-26 16:10:43 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 620/1251] eta: 0:05:23 lr: 0.000255 loss: 3.1503 (3.0563) grad_norm: 1.7818 (inf) time: 0.5072 [2021-03-26 16:10:48 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 630/1251] eta: 0:05:18 lr: 0.000255 loss: 3.2635 (3.0557) grad_norm: 1.7818 (inf) time: 0.5086 [2021-03-26 16:10:54 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 640/1251] eta: 0:05:13 lr: 0.000255 loss: 3.1783 (3.0566) grad_norm: 1.8142 (inf) time: 0.5075 [2021-03-26 16:10:59 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 650/1251] eta: 0:05:08 lr: 0.000255 loss: 3.1783 (3.0542) grad_norm: 1.9788 (inf) time: 0.5044 [2021-03-26 16:11:04 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 660/1251] eta: 0:05:03 lr: 0.000255 loss: 3.2294 (3.0543) grad_norm: 2.0125 (inf) time: 0.5023 [2021-03-26 16:11:09 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 670/1251] eta: 0:04:57 lr: 0.000255 loss: 3.2491 (3.0572) grad_norm: 1.8488 (inf) time: 0.5066 [2021-03-26 16:11:14 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 680/1251] eta: 0:04:52 lr: 0.000255 loss: 3.3247 (3.0598) grad_norm: 1.8819 (inf) time: 0.5155 [2021-03-26 16:11:19 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 690/1251] eta: 0:04:47 lr: 0.000255 loss: 3.2634 (3.0622) grad_norm: 1.9040 (inf) time: 0.5149 [2021-03-26 16:11:24 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 700/1251] eta: 0:04:42 lr: 0.000255 loss: 3.2372 (3.0631) grad_norm: 1.9042 (inf) time: 0.5095 [2021-03-26 16:11:29 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 710/1251] eta: 0:04:37 lr: 0.000255 loss: 3.2115 (3.0617) grad_norm: 1.9042 (inf) time: 0.5031 [2021-03-26 16:11:34 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 720/1251] eta: 0:04:32 lr: 0.000255 loss: 2.8757 (3.0598) grad_norm: 1.8779 (inf) time: 0.4985 [2021-03-26 16:11:39 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 730/1251] eta: 0:04:26 lr: 0.000255 loss: 3.1103 (3.0619) grad_norm: 1.8892 (inf) time: 0.5034 [2021-03-26 16:11:44 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 740/1251] eta: 0:04:21 lr: 0.000255 loss: 3.2054 (3.0644) grad_norm: 1.9656 (inf) time: 0.5203 [2021-03-26 16:11:49 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 750/1251] eta: 0:04:16 lr: 0.000255 loss: 3.2207 (3.0680) grad_norm: 2.0011 (inf) time: 0.5164 [2021-03-26 16:11:55 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 760/1251] eta: 0:04:11 lr: 0.000255 loss: 3.2792 (3.0708) grad_norm: 1.8726 (inf) time: 0.5062 [2021-03-26 16:12:00 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 770/1251] eta: 0:04:06 lr: 0.000255 loss: 3.1416 (3.0684) grad_norm: 1.8596 (inf) time: 0.5168 [2021-03-26 16:12:05 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 780/1251] eta: 0:04:01 lr: 0.000255 loss: 3.0178 (3.0663) grad_norm: 1.7947 (inf) time: 0.5174 [2021-03-26 16:12:10 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 790/1251] eta: 0:03:56 lr: 0.000255 loss: 3.1428 (3.0686) grad_norm: 1.8807 (inf) time: 0.5061 [2021-03-26 16:12:15 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 800/1251] eta: 0:03:51 lr: 0.000255 loss: 3.1951 (3.0685) grad_norm: 1.8971 (inf) time: 0.5079 [2021-03-26 16:12:20 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 810/1251] eta: 0:03:45 lr: 0.000255 loss: 3.2385 (3.0720) grad_norm: 1.8763 (inf) time: 0.5120 [2021-03-26 16:12:25 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 820/1251] eta: 0:03:40 lr: 0.000255 loss: 3.1660 (3.0697) grad_norm: 1.9546 (inf) time: 0.5047 [2021-03-26 16:12:30 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 830/1251] eta: 0:03:35 lr: 0.000255 loss: 3.1342 (3.0722) grad_norm: 1.9675 (inf) time: 0.5084 [2021-03-26 16:12:35 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 840/1251] eta: 0:03:30 lr: 0.000254 loss: 3.3745 (3.0744) grad_norm: 1.8394 (inf) time: 0.5093 [2021-03-26 16:12:40 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 850/1251] eta: 0:03:25 lr: 0.000254 loss: 3.1372 (3.0722) grad_norm: 1.8864 (inf) time: 0.5067 [2021-03-26 16:12:46 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 860/1251] eta: 0:03:20 lr: 0.000254 loss: 2.8766 (3.0714) grad_norm: 1.9255 (inf) time: 0.5111 [2021-03-26 16:12:51 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 870/1251] eta: 0:03:15 lr: 0.000254 loss: 3.0169 (3.0723) grad_norm: 1.9255 (inf) time: 0.5113 [2021-03-26 16:12:56 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 880/1251] eta: 0:03:09 lr: 0.000254 loss: 3.0169 (3.0702) grad_norm: 1.8443 (inf) time: 0.5124 [2021-03-26 16:13:01 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 890/1251] eta: 0:03:04 lr: 0.000254 loss: 2.9937 (3.0700) grad_norm: 1.8651 (inf) time: 0.5103 [2021-03-26 16:13:06 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 900/1251] eta: 0:02:59 lr: 0.000254 loss: 3.0142 (3.0699) grad_norm: 1.9074 (inf) time: 0.5098 [2021-03-26 16:13:11 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 910/1251] eta: 0:02:54 lr: 0.000254 loss: 3.1469 (3.0718) grad_norm: 1.8291 (inf) time: 0.5059 [2021-03-26 16:13:16 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 920/1251] eta: 0:02:49 lr: 0.000254 loss: 3.1469 (3.0696) grad_norm: 1.8469 (inf) time: 0.5065 [2021-03-26 16:13:21 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 930/1251] eta: 0:02:44 lr: 0.000254 loss: 3.1707 (3.0706) grad_norm: 1.8944 (inf) time: 0.5092 [2021-03-26 16:13:26 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 940/1251] eta: 0:02:39 lr: 0.000254 loss: 3.2302 (3.0729) grad_norm: 1.9144 (inf) time: 0.5044 [2021-03-26 16:13:31 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 950/1251] eta: 0:02:34 lr: 0.000254 loss: 3.0989 (3.0709) grad_norm: 1.9144 (inf) time: 0.5048 [2021-03-26 16:13:37 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 960/1251] eta: 0:02:28 lr: 0.000254 loss: 2.8887 (3.0709) grad_norm: 1.9336 (inf) time: 0.5158 [2021-03-26 16:13:42 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 970/1251] eta: 0:02:23 lr: 0.000254 loss: 3.2712 (3.0709) grad_norm: 1.9951 (inf) time: 0.5157 [2021-03-26 16:13:47 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 980/1251] eta: 0:02:18 lr: 0.000254 loss: 3.2590 (3.0733) grad_norm: 1.9583 (inf) time: 0.5066 [2021-03-26 16:13:52 swin_small_patch4_window7_224] INFO: Epoch: [200] [ 990/1251] eta: 0:02:13 lr: 0.000254 loss: 3.2590 (3.0732) grad_norm: 1.9450 (inf) time: 0.5037 [2021-03-26 16:13:57 swin_small_patch4_window7_224] INFO: Epoch: [200] [1000/1251] eta: 0:02:08 lr: 0.000254 loss: 3.0523 (3.0719) grad_norm: 1.9961 (inf) time: 0.5100 [2021-03-26 16:14:02 swin_small_patch4_window7_224] INFO: Epoch: [200] [1010/1251] eta: 0:02:03 lr: 0.000254 loss: 3.0562 (3.0729) grad_norm: 1.9174 (inf) time: 0.5158 [2021-03-26 16:14:07 swin_small_patch4_window7_224] INFO: Epoch: [200] [1020/1251] eta: 0:01:58 lr: 0.000254 loss: 3.2970 (3.0728) grad_norm: 1.7640 (inf) time: 0.5075 [2021-03-26 16:14:12 swin_small_patch4_window7_224] INFO: Epoch: [200] [1030/1251] eta: 0:01:53 lr: 0.000254 loss: 3.1929 (3.0731) grad_norm: 1.8762 (inf) time: 0.5032 [2021-03-26 16:14:17 swin_small_patch4_window7_224] INFO: Epoch: [200] [1040/1251] eta: 0:01:47 lr: 0.000254 loss: 3.1572 (3.0731) grad_norm: 1.9016 (inf) time: 0.5024 [2021-03-26 16:14:22 swin_small_patch4_window7_224] INFO: Epoch: [200] [1050/1251] eta: 0:01:42 lr: 0.000254 loss: 3.1572 (3.0724) grad_norm: 1.9710 (inf) time: 0.5102 [2021-03-26 16:14:27 swin_small_patch4_window7_224] INFO: Epoch: [200] [1060/1251] eta: 0:01:37 lr: 0.000254 loss: 2.9803 (3.0693) grad_norm: 1.9602 (inf) time: 0.5082 [2021-03-26 16:14:32 swin_small_patch4_window7_224] INFO: Epoch: [200] [1070/1251] eta: 0:01:32 lr: 0.000254 loss: 3.0552 (3.0710) grad_norm: 1.9117 (inf) time: 0.4972 [2021-03-26 16:14:37 swin_small_patch4_window7_224] INFO: Epoch: [200] [1080/1251] eta: 0:01:27 lr: 0.000254 loss: 3.2972 (3.0728) grad_norm: 2.0187 (inf) time: 0.4950 [2021-03-26 16:14:42 swin_small_patch4_window7_224] INFO: Epoch: [200] [1090/1251] eta: 0:01:22 lr: 0.000254 loss: 3.2972 (3.0735) grad_norm: 1.8898 (inf) time: 0.4988 [2021-03-26 16:14:47 swin_small_patch4_window7_224] INFO: Epoch: [200] [1100/1251] eta: 0:01:17 lr: 0.000254 loss: 3.1832 (3.0724) grad_norm: 1.9398 (inf) time: 0.5075 [2021-03-26 16:14:52 swin_small_patch4_window7_224] INFO: Epoch: [200] [1110/1251] eta: 0:01:12 lr: 0.000254 loss: 3.3473 (3.0751) grad_norm: 1.9946 (inf) time: 0.5115 [2021-03-26 16:14:58 swin_small_patch4_window7_224] INFO: Epoch: [200] [1120/1251] eta: 0:01:06 lr: 0.000253 loss: 3.5427 (3.0778) grad_norm: 1.9882 (inf) time: 0.5071 [2021-03-26 16:15:02 swin_small_patch4_window7_224] INFO: Epoch: [200] [1130/1251] eta: 0:01:01 lr: 0.000253 loss: 3.3501 (3.0769) grad_norm: 1.9867 (inf) time: 0.4985 [2021-03-26 16:15:07 swin_small_patch4_window7_224] INFO: Epoch: [200] [1140/1251] eta: 0:00:56 lr: 0.000253 loss: 3.1339 (3.0774) grad_norm: 1.9041 (inf) time: 0.4958 [2021-03-26 16:15:13 swin_small_patch4_window7_224] INFO: Epoch: [200] [1150/1251] eta: 0:00:51 lr: 0.000253 loss: 3.0771 (3.0755) grad_norm: 1.9014 (inf) time: 0.5035 [2021-03-26 16:15:18 swin_small_patch4_window7_224] INFO: Epoch: [200] [1160/1251] eta: 0:00:46 lr: 0.000253 loss: 3.0633 (3.0769) grad_norm: 1.9474 (inf) time: 0.5036 [2021-03-26 16:15:23 swin_small_patch4_window7_224] INFO: Epoch: [200] [1170/1251] eta: 0:00:41 lr: 0.000253 loss: 3.2734 (3.0778) grad_norm: 1.9375 (inf) time: 0.5031 [2021-03-26 16:15:28 swin_small_patch4_window7_224] INFO: Epoch: [200] [1180/1251] eta: 0:00:36 lr: 0.000253 loss: 3.2177 (3.0780) grad_norm: 1.9203 (inf) time: 0.5042 [2021-03-26 16:15:33 swin_small_patch4_window7_224] INFO: Epoch: [200] [1190/1251] eta: 0:00:31 lr: 0.000253 loss: 3.1483 (3.0790) grad_norm: 1.8879 (inf) time: 0.5038 [2021-03-26 16:15:38 swin_small_patch4_window7_224] INFO: Epoch: [200] [1200/1251] eta: 0:00:26 lr: 0.000253 loss: 3.1317 (3.0785) grad_norm: 1.8540 (inf) time: 0.5074 [2021-03-26 16:15:43 swin_small_patch4_window7_224] INFO: Epoch: [200] [1210/1251] eta: 0:00:20 lr: 0.000253 loss: 3.1317 (3.0796) grad_norm: 1.9150 (inf) time: 0.5130 [2021-03-26 16:15:48 swin_small_patch4_window7_224] INFO: Epoch: [200] [1220/1251] eta: 0:00:15 lr: 0.000253 loss: 3.1656 (3.0802) grad_norm: 1.9230 (inf) time: 0.5081 [2021-03-26 16:15:53 swin_small_patch4_window7_224] INFO: Epoch: [200] [1230/1251] eta: 0:00:10 lr: 0.000253 loss: 3.1519 (3.0805) grad_norm: 1.9335 (inf) time: 0.4991 [2021-03-26 16:15:58 swin_small_patch4_window7_224] INFO: Epoch: [200] [1240/1251] eta: 0:00:05 lr: 0.000253 loss: 3.0861 (3.0797) grad_norm: 1.8934 (inf) time: 0.5051 [2021-03-26 16:16:03 swin_small_patch4_window7_224] INFO: Epoch: [200] [1250/1251] eta: 0:00:00 lr: 0.000253 loss: 3.2255 (3.0829) grad_norm: 1.9608 (inf) time: 0.5023 [2021-03-26 16:16:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.9801 (0.9801) acc1: 78.1250 (78.1250) acc5: 90.6250 (90.6250) [2021-03-26 16:16:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7867 (0.7829) acc1: 79.6875 (81.8182) acc5: 95.3125 (95.0284) [2021-03-26 16:16:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7972 (0.8304) acc1: 79.6875 (80.8036) acc5: 95.3125 (94.8661) [2021-03-26 16:16:56 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8189 (0.8169) acc1: 79.6875 (80.7460) acc5: 95.3125 (95.2117) [2021-03-26 16:16:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8189 (0.8228) acc1: 78.1250 (80.1448) acc5: 95.3125 (95.3125) [2021-03-26 16:16:58 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8139 (0.8202) acc1: 79.6875 (80.1600) acc5: 95.3125 (95.3280) [2021-03-26 16:17:08 swin_small_patch4_window7_224] INFO: * Acc@1 80.478 Acc@5 95.514 loss 0.810 [2021-03-26 16:17:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.5% [2021-03-26 16:17:08 swin_small_patch4_window7_224] INFO: Max accuracy: 80.53% [2021-03-26 16:17:12 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 0/1251] eta: 1:26:09 lr: 0.000253 loss: 2.5366 (2.5366) grad_norm: 1.7885 (1.7885) time: 4.1323 [2021-03-26 16:17:17 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 10/1251] eta: 0:17:51 lr: 0.000253 loss: 3.1461 (3.0717) grad_norm: 1.8791 (2.0237) time: 0.8637 [2021-03-26 16:17:22 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 20/1251] eta: 0:14:12 lr: 0.000253 loss: 3.1989 (3.1599) grad_norm: 1.9267 (2.0112) time: 0.5208 [2021-03-26 16:17:27 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 30/1251] eta: 0:12:47 lr: 0.000253 loss: 3.1989 (3.1369) grad_norm: 1.9166 (1.9690) time: 0.4991 [2021-03-26 16:17:32 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 40/1251] eta: 0:12:02 lr: 0.000253 loss: 3.0107 (3.0856) grad_norm: 1.8744 (1.9493) time: 0.4963 [2021-03-26 16:17:37 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 50/1251] eta: 0:11:36 lr: 0.000253 loss: 3.0107 (3.0535) grad_norm: 1.8523 (1.9308) time: 0.5051 [2021-03-26 16:17:42 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 60/1251] eta: 0:11:17 lr: 0.000253 loss: 3.1761 (3.0665) grad_norm: 1.8523 (1.9381) time: 0.5114 [2021-03-26 16:17:47 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 70/1251] eta: 0:11:01 lr: 0.000253 loss: 3.1309 (3.0679) grad_norm: 1.9147 (1.9558) time: 0.5091 [2021-03-26 16:17:53 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 80/1251] eta: 0:10:49 lr: 0.000253 loss: 3.1309 (3.0712) grad_norm: 1.9484 (1.9606) time: 0.5121 [2021-03-26 16:17:58 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 90/1251] eta: 0:10:37 lr: 0.000253 loss: 2.7123 (3.0469) grad_norm: 1.9240 (1.9724) time: 0.5096 [2021-03-26 16:18:03 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 100/1251] eta: 0:10:27 lr: 0.000253 loss: 3.1113 (3.0702) grad_norm: 1.9228 (1.9678) time: 0.5038 [2021-03-26 16:18:08 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 110/1251] eta: 0:10:18 lr: 0.000253 loss: 3.2492 (3.0896) grad_norm: 1.9112 (1.9625) time: 0.5110 [2021-03-26 16:18:13 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 120/1251] eta: 0:10:10 lr: 0.000253 loss: 3.2492 (3.0945) grad_norm: 1.9300 (1.9562) time: 0.5147 [2021-03-26 16:18:18 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 130/1251] eta: 0:10:02 lr: 0.000253 loss: 3.1381 (3.0979) grad_norm: 1.8994 (1.9530) time: 0.5124 [2021-03-26 16:18:23 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 140/1251] eta: 0:09:55 lr: 0.000253 loss: 3.2748 (3.1102) grad_norm: 1.9075 (1.9641) time: 0.5143 [2021-03-26 16:18:28 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 150/1251] eta: 0:09:47 lr: 0.000252 loss: 3.3143 (3.1278) grad_norm: 1.9722 (1.9659) time: 0.5088 [2021-03-26 16:18:33 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 160/1251] eta: 0:09:39 lr: 0.000252 loss: 3.3851 (3.1485) grad_norm: 1.8965 (1.9753) time: 0.4995 [2021-03-26 16:18:38 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 170/1251] eta: 0:09:33 lr: 0.000252 loss: 3.2253 (3.1467) grad_norm: 1.9029 (1.9748) time: 0.5023 [2021-03-26 16:18:43 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 180/1251] eta: 0:09:26 lr: 0.000252 loss: 3.0760 (3.1461) grad_norm: 1.8663 (1.9671) time: 0.5062 [2021-03-26 16:18:48 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 190/1251] eta: 0:09:19 lr: 0.000252 loss: 3.1085 (3.1444) grad_norm: 1.8314 (1.9665) time: 0.5042 [2021-03-26 16:18:53 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 200/1251] eta: 0:09:12 lr: 0.000252 loss: 3.3207 (3.1439) grad_norm: 1.8766 (1.9723) time: 0.5020 [2021-03-26 16:18:58 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 210/1251] eta: 0:09:06 lr: 0.000252 loss: 3.3962 (3.1494) grad_norm: 2.0498 (1.9723) time: 0.5034 [2021-03-26 16:19:03 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 220/1251] eta: 0:09:00 lr: 0.000252 loss: 3.2953 (3.1472) grad_norm: 1.9459 (1.9737) time: 0.5045 [2021-03-26 16:19:08 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 230/1251] eta: 0:08:54 lr: 0.000252 loss: 3.1591 (3.1502) grad_norm: 1.9366 (1.9715) time: 0.5055 [2021-03-26 16:19:13 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 240/1251] eta: 0:08:48 lr: 0.000252 loss: 3.1070 (3.1423) grad_norm: 1.9069 (1.9718) time: 0.5011 [2021-03-26 16:19:19 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 250/1251] eta: 0:08:42 lr: 0.000252 loss: 3.0405 (3.1396) grad_norm: 1.9447 (1.9709) time: 0.5023 [2021-03-26 16:19:24 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 260/1251] eta: 0:08:36 lr: 0.000252 loss: 2.8745 (3.1149) grad_norm: 1.8789 (1.9662) time: 0.5051 [2021-03-26 16:19:29 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 270/1251] eta: 0:08:30 lr: 0.000252 loss: 2.9018 (3.1149) grad_norm: 1.8447 (1.9635) time: 0.5007 [2021-03-26 16:19:33 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 280/1251] eta: 0:08:24 lr: 0.000252 loss: 3.1068 (3.1105) grad_norm: 1.9331 (1.9643) time: 0.4968 [2021-03-26 16:19:38 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 290/1251] eta: 0:08:18 lr: 0.000252 loss: 2.8255 (3.1000) grad_norm: 1.9427 (1.9635) time: 0.4960 [2021-03-26 16:19:44 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 300/1251] eta: 0:08:13 lr: 0.000252 loss: 3.1376 (3.1025) grad_norm: 1.9311 (1.9630) time: 0.5073 [2021-03-26 16:19:49 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 310/1251] eta: 0:08:07 lr: 0.000252 loss: 3.2944 (3.1045) grad_norm: 1.9331 (1.9645) time: 0.5113 [2021-03-26 16:19:54 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 320/1251] eta: 0:08:01 lr: 0.000252 loss: 3.0801 (3.0983) grad_norm: 1.9546 (1.9682) time: 0.5014 [2021-03-26 16:19:59 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 330/1251] eta: 0:07:55 lr: 0.000252 loss: 3.2735 (3.1027) grad_norm: 1.9568 (1.9682) time: 0.4953 [2021-03-26 16:20:04 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 340/1251] eta: 0:07:50 lr: 0.000252 loss: 3.2855 (3.1029) grad_norm: 2.0016 (1.9723) time: 0.4995 [2021-03-26 16:20:09 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 350/1251] eta: 0:07:44 lr: 0.000252 loss: 3.2373 (3.0996) grad_norm: 1.9629 (1.9713) time: 0.4988 [2021-03-26 16:20:14 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 360/1251] eta: 0:07:39 lr: 0.000252 loss: 3.1798 (3.1027) grad_norm: 1.9629 (1.9731) time: 0.4995 [2021-03-26 16:20:19 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 370/1251] eta: 0:07:33 lr: 0.000252 loss: 3.1613 (3.1025) grad_norm: 1.9397 (1.9710) time: 0.5089 [2021-03-26 16:20:24 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 380/1251] eta: 0:07:28 lr: 0.000252 loss: 3.2052 (3.1018) grad_norm: 1.9397 (1.9720) time: 0.5054 [2021-03-26 16:20:29 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 390/1251] eta: 0:07:23 lr: 0.000252 loss: 2.9724 (3.0950) grad_norm: 2.0026 (1.9719) time: 0.5016 [2021-03-26 16:20:34 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 400/1251] eta: 0:07:17 lr: 0.000252 loss: 2.9724 (3.0972) grad_norm: 1.9864 (1.9752) time: 0.5074 [2021-03-26 16:20:39 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 410/1251] eta: 0:07:12 lr: 0.000252 loss: 3.1805 (3.0977) grad_norm: 2.0325 (1.9742) time: 0.5108 [2021-03-26 16:20:44 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 420/1251] eta: 0:07:07 lr: 0.000252 loss: 3.2693 (3.1007) grad_norm: 1.9138 (1.9753) time: 0.5067 [2021-03-26 16:20:49 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 430/1251] eta: 0:07:01 lr: 0.000251 loss: 3.4444 (3.1053) grad_norm: 1.9405 (1.9751) time: 0.5038 [2021-03-26 16:20:54 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 440/1251] eta: 0:06:56 lr: 0.000251 loss: 3.2964 (3.1068) grad_norm: 1.8972 (1.9732) time: 0.5023 [2021-03-26 16:20:59 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 450/1251] eta: 0:06:51 lr: 0.000251 loss: 3.2653 (3.1094) grad_norm: 1.8000 (1.9699) time: 0.5009 [2021-03-26 16:21:04 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 460/1251] eta: 0:06:45 lr: 0.000251 loss: 3.2136 (3.1086) grad_norm: 1.8607 (1.9682) time: 0.5014 [2021-03-26 16:21:09 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 470/1251] eta: 0:06:40 lr: 0.000251 loss: 3.2136 (3.1106) grad_norm: 1.8988 (1.9676) time: 0.4991 [2021-03-26 16:21:14 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 480/1251] eta: 0:06:35 lr: 0.000251 loss: 3.2514 (3.1091) grad_norm: 1.8726 (1.9672) time: 0.5012 [2021-03-26 16:21:19 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 490/1251] eta: 0:06:30 lr: 0.000251 loss: 3.2802 (3.1122) grad_norm: 1.8862 (1.9661) time: 0.5076 [2021-03-26 16:21:24 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 500/1251] eta: 0:06:24 lr: 0.000251 loss: 3.2116 (3.1111) grad_norm: 1.8993 (1.9645) time: 0.5089 [2021-03-26 16:21:29 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 510/1251] eta: 0:06:19 lr: 0.000251 loss: 3.1386 (3.1102) grad_norm: 1.9207 (1.9659) time: 0.5012 [2021-03-26 16:21:34 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 520/1251] eta: 0:06:14 lr: 0.000251 loss: 3.0382 (3.1088) grad_norm: 2.0006 (1.9661) time: 0.4997 [2021-03-26 16:21:39 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 530/1251] eta: 0:06:08 lr: 0.000251 loss: 3.0268 (3.1093) grad_norm: 1.8639 (1.9647) time: 0.5013 [2021-03-26 16:21:44 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 540/1251] eta: 0:06:03 lr: 0.000251 loss: 3.0833 (3.1074) grad_norm: 1.8706 (1.9650) time: 0.5064 [2021-03-26 16:21:50 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 550/1251] eta: 0:05:58 lr: 0.000251 loss: 2.9956 (3.1078) grad_norm: 1.9302 (1.9641) time: 0.5214 [2021-03-26 16:21:55 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 560/1251] eta: 0:05:53 lr: 0.000251 loss: 3.3416 (3.1081) grad_norm: 1.9034 (1.9636) time: 0.5230 [2021-03-26 16:22:00 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 570/1251] eta: 0:05:48 lr: 0.000251 loss: 3.2353 (3.1080) grad_norm: 1.8175 (1.9614) time: 0.5156 [2021-03-26 16:22:05 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 580/1251] eta: 0:05:43 lr: 0.000251 loss: 2.7908 (3.1023) grad_norm: 1.8147 (1.9597) time: 0.5061 [2021-03-26 16:22:10 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 590/1251] eta: 0:05:38 lr: 0.000251 loss: 2.7046 (3.0989) grad_norm: 1.9018 (1.9589) time: 0.4993 [2021-03-26 16:22:15 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 600/1251] eta: 0:05:32 lr: 0.000251 loss: 3.0325 (3.1019) grad_norm: 1.9119 (1.9595) time: 0.4988 [2021-03-26 16:22:20 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 610/1251] eta: 0:05:27 lr: 0.000251 loss: 3.2969 (3.1053) grad_norm: 1.8974 (1.9586) time: 0.5038 [2021-03-26 16:22:25 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 620/1251] eta: 0:05:22 lr: 0.000251 loss: 3.0963 (3.1011) grad_norm: 1.8030 (1.9571) time: 0.5105 [2021-03-26 16:22:30 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 630/1251] eta: 0:05:17 lr: 0.000251 loss: 2.8636 (3.0993) grad_norm: 1.8605 (1.9564) time: 0.5117 [2021-03-26 16:22:36 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 640/1251] eta: 0:05:12 lr: 0.000251 loss: 2.9162 (3.0968) grad_norm: 1.8908 (1.9556) time: 0.5166 [2021-03-26 16:22:41 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 650/1251] eta: 0:05:07 lr: 0.000251 loss: 2.9942 (3.0970) grad_norm: 1.9054 (1.9570) time: 0.5123 [2021-03-26 16:22:46 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 660/1251] eta: 0:05:02 lr: 0.000251 loss: 3.2723 (3.1006) grad_norm: 1.9183 (1.9565) time: 0.5042 [2021-03-26 16:22:51 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 670/1251] eta: 0:04:57 lr: 0.000251 loss: 3.0944 (3.0978) grad_norm: 1.8981 (1.9567) time: 0.5038 [2021-03-26 16:22:56 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 680/1251] eta: 0:04:51 lr: 0.000251 loss: 3.0944 (3.1004) grad_norm: 1.8481 (1.9559) time: 0.5080 [2021-03-26 16:23:01 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 690/1251] eta: 0:04:46 lr: 0.000251 loss: 3.1525 (3.0948) grad_norm: 1.9037 (1.9560) time: 0.5115 [2021-03-26 16:23:06 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 700/1251] eta: 0:04:41 lr: 0.000251 loss: 2.9292 (3.0940) grad_norm: 1.9403 (1.9592) time: 0.5079 [2021-03-26 16:23:11 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 710/1251] eta: 0:04:36 lr: 0.000250 loss: 3.2775 (3.0970) grad_norm: 1.9279 (1.9592) time: 0.5070 [2021-03-26 16:23:16 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 720/1251] eta: 0:04:31 lr: 0.000250 loss: 3.3621 (3.0952) grad_norm: 1.9279 (1.9598) time: 0.5117 [2021-03-26 16:23:21 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 730/1251] eta: 0:04:26 lr: 0.000250 loss: 3.0636 (3.0938) grad_norm: 1.8651 (1.9573) time: 0.5086 [2021-03-26 16:23:27 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 740/1251] eta: 0:04:21 lr: 0.000250 loss: 3.0172 (3.0906) grad_norm: 1.8318 (1.9564) time: 0.5183 [2021-03-26 16:23:32 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 750/1251] eta: 0:04:16 lr: 0.000250 loss: 3.2099 (3.0938) grad_norm: 1.8654 (1.9556) time: 0.5262 [2021-03-26 16:23:37 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 760/1251] eta: 0:04:11 lr: 0.000250 loss: 3.3786 (3.0966) grad_norm: 1.8908 (1.9551) time: 0.5124 [2021-03-26 16:23:42 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 770/1251] eta: 0:04:05 lr: 0.000250 loss: 3.3314 (3.0989) grad_norm: 1.8474 (1.9536) time: 0.5016 [2021-03-26 16:23:47 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 780/1251] eta: 0:04:00 lr: 0.000250 loss: 3.1655 (3.0998) grad_norm: 1.8030 (1.9527) time: 0.5042 [2021-03-26 16:23:52 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 790/1251] eta: 0:03:55 lr: 0.000250 loss: 3.0815 (3.0995) grad_norm: 1.9085 (1.9539) time: 0.5109 [2021-03-26 16:23:57 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 800/1251] eta: 0:03:50 lr: 0.000250 loss: 3.2269 (3.0999) grad_norm: 1.9256 (1.9535) time: 0.5102 [2021-03-26 16:24:02 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 810/1251] eta: 0:03:45 lr: 0.000250 loss: 3.1119 (3.0979) grad_norm: 1.9082 (1.9539) time: 0.5085 [2021-03-26 16:24:07 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 820/1251] eta: 0:03:40 lr: 0.000250 loss: 3.0434 (3.0962) grad_norm: 1.9082 (1.9543) time: 0.5080 [2021-03-26 16:24:12 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 830/1251] eta: 0:03:35 lr: 0.000250 loss: 3.1307 (3.0969) grad_norm: 1.8771 (1.9537) time: 0.5115 [2021-03-26 16:24:18 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 840/1251] eta: 0:03:30 lr: 0.000250 loss: 3.2859 (3.0979) grad_norm: 1.8974 (1.9554) time: 0.5121 [2021-03-26 16:24:23 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 850/1251] eta: 0:03:24 lr: 0.000250 loss: 3.1147 (3.0985) grad_norm: 1.9234 (1.9550) time: 0.5135 [2021-03-26 16:24:28 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 860/1251] eta: 0:03:19 lr: 0.000250 loss: 3.4119 (3.1022) grad_norm: 1.9529 (1.9563) time: 0.5147 [2021-03-26 16:24:33 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 870/1251] eta: 0:03:14 lr: 0.000250 loss: 3.4565 (3.1039) grad_norm: 2.0101 (1.9562) time: 0.5101 [2021-03-26 16:24:38 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 880/1251] eta: 0:03:09 lr: 0.000250 loss: 3.0066 (3.1003) grad_norm: 1.8797 (1.9555) time: 0.5057 [2021-03-26 16:24:43 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 890/1251] eta: 0:03:04 lr: 0.000250 loss: 3.0481 (3.1030) grad_norm: 1.8797 (1.9551) time: 0.5065 [2021-03-26 16:24:48 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 900/1251] eta: 0:02:59 lr: 0.000250 loss: 3.1039 (3.1021) grad_norm: 1.8513 (1.9542) time: 0.5037 [2021-03-26 16:24:53 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 910/1251] eta: 0:02:54 lr: 0.000250 loss: 3.1039 (3.1017) grad_norm: 1.8473 (1.9535) time: 0.5006 [2021-03-26 16:24:58 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 920/1251] eta: 0:02:49 lr: 0.000250 loss: 3.2389 (3.1023) grad_norm: 1.8473 (1.9529) time: 0.5051 [2021-03-26 16:25:03 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 930/1251] eta: 0:02:43 lr: 0.000250 loss: 3.2436 (3.1040) grad_norm: 1.7856 (1.9509) time: 0.5061 [2021-03-26 16:25:08 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 940/1251] eta: 0:02:38 lr: 0.000250 loss: 3.2813 (3.1050) grad_norm: 1.7474 (1.9487) time: 0.5066 [2021-03-26 16:25:13 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 950/1251] eta: 0:02:33 lr: 0.000250 loss: 3.2259 (3.1064) grad_norm: 1.7339 (1.9472) time: 0.5052 [2021-03-26 16:25:18 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 960/1251] eta: 0:02:28 lr: 0.000250 loss: 3.0880 (3.1049) grad_norm: 1.8025 (1.9465) time: 0.5039 [2021-03-26 16:25:23 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 970/1251] eta: 0:02:23 lr: 0.000250 loss: 3.0373 (3.1031) grad_norm: 1.8071 (1.9457) time: 0.5084 [2021-03-26 16:25:29 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 980/1251] eta: 0:02:18 lr: 0.000250 loss: 3.2007 (3.1042) grad_norm: 1.8867 (1.9452) time: 0.5139 [2021-03-26 16:25:34 swin_small_patch4_window7_224] INFO: Epoch: [201] [ 990/1251] eta: 0:02:13 lr: 0.000250 loss: 3.1847 (3.1038) grad_norm: 1.9131 (1.9449) time: 0.5163 [2021-03-26 16:25:39 swin_small_patch4_window7_224] INFO: Epoch: [201] [1000/1251] eta: 0:02:08 lr: 0.000249 loss: 2.9540 (3.1023) grad_norm: 1.8739 (1.9445) time: 0.5110 [2021-03-26 16:25:44 swin_small_patch4_window7_224] INFO: Epoch: [201] [1010/1251] eta: 0:02:03 lr: 0.000249 loss: 3.0358 (3.1008) grad_norm: 1.7997 (1.9437) time: 0.5026 [2021-03-26 16:25:49 swin_small_patch4_window7_224] INFO: Epoch: [201] [1020/1251] eta: 0:01:57 lr: 0.000249 loss: 3.2145 (3.0993) grad_norm: 1.9052 (1.9446) time: 0.4989 [2021-03-26 16:25:54 swin_small_patch4_window7_224] INFO: Epoch: [201] [1030/1251] eta: 0:01:52 lr: 0.000249 loss: 3.0511 (3.0981) grad_norm: 1.9428 (1.9443) time: 0.5033 [2021-03-26 16:25:59 swin_small_patch4_window7_224] INFO: Epoch: [201] [1040/1251] eta: 0:01:47 lr: 0.000249 loss: 3.1249 (3.0983) grad_norm: 1.8257 (1.9429) time: 0.5050 [2021-03-26 16:26:04 swin_small_patch4_window7_224] INFO: Epoch: [201] [1050/1251] eta: 0:01:42 lr: 0.000249 loss: 3.1249 (3.0970) grad_norm: 1.7825 (1.9424) time: 0.5114 [2021-03-26 16:26:09 swin_small_patch4_window7_224] INFO: Epoch: [201] [1060/1251] eta: 0:01:37 lr: 0.000249 loss: 2.9972 (3.0954) grad_norm: 1.8632 (1.9420) time: 0.5116 [2021-03-26 16:26:14 swin_small_patch4_window7_224] INFO: Epoch: [201] [1070/1251] eta: 0:01:32 lr: 0.000249 loss: 3.3310 (3.0982) grad_norm: 1.8814 (1.9412) time: 0.5033 [2021-03-26 16:26:19 swin_small_patch4_window7_224] INFO: Epoch: [201] [1080/1251] eta: 0:01:27 lr: 0.000249 loss: 3.3090 (3.0980) grad_norm: 1.8565 (1.9408) time: 0.5039 [2021-03-26 16:26:24 swin_small_patch4_window7_224] INFO: Epoch: [201] [1090/1251] eta: 0:01:22 lr: 0.000249 loss: 2.9666 (3.0955) grad_norm: 1.8333 (1.9402) time: 0.5056 [2021-03-26 16:26:29 swin_small_patch4_window7_224] INFO: Epoch: [201] [1100/1251] eta: 0:01:17 lr: 0.000249 loss: 2.9666 (3.0953) grad_norm: 1.8333 (1.9393) time: 0.5027 [2021-03-26 16:26:34 swin_small_patch4_window7_224] INFO: Epoch: [201] [1110/1251] eta: 0:01:11 lr: 0.000249 loss: 3.1248 (3.0943) grad_norm: 1.8604 (1.9387) time: 0.5026 [2021-03-26 16:26:39 swin_small_patch4_window7_224] INFO: Epoch: [201] [1120/1251] eta: 0:01:06 lr: 0.000249 loss: 3.0561 (3.0926) grad_norm: 1.8861 (1.9394) time: 0.5026 [2021-03-26 16:26:44 swin_small_patch4_window7_224] INFO: Epoch: [201] [1130/1251] eta: 0:01:01 lr: 0.000249 loss: 3.0561 (3.0928) grad_norm: 1.8898 (1.9393) time: 0.5004 [2021-03-26 16:26:49 swin_small_patch4_window7_224] INFO: Epoch: [201] [1140/1251] eta: 0:00:56 lr: 0.000249 loss: 3.2575 (3.0949) grad_norm: 1.8649 (1.9400) time: 0.5003 [2021-03-26 16:26:54 swin_small_patch4_window7_224] INFO: Epoch: [201] [1150/1251] eta: 0:00:51 lr: 0.000249 loss: 3.2568 (3.0938) grad_norm: 1.9707 (1.9402) time: 0.4985 [2021-03-26 16:26:59 swin_small_patch4_window7_224] INFO: Epoch: [201] [1160/1251] eta: 0:00:46 lr: 0.000249 loss: 3.1060 (3.0917) grad_norm: 1.8786 (1.9393) time: 0.5017 [2021-03-26 16:27:04 swin_small_patch4_window7_224] INFO: Epoch: [201] [1170/1251] eta: 0:00:41 lr: 0.000249 loss: 3.1145 (3.0927) grad_norm: 1.8799 (1.9391) time: 0.5022 [2021-03-26 16:27:09 swin_small_patch4_window7_224] INFO: Epoch: [201] [1180/1251] eta: 0:00:36 lr: 0.000249 loss: 3.2255 (3.0930) grad_norm: 1.9032 (1.9389) time: 0.4988 [2021-03-26 16:27:14 swin_small_patch4_window7_224] INFO: Epoch: [201] [1190/1251] eta: 0:00:31 lr: 0.000249 loss: 3.0896 (3.0913) grad_norm: 1.8601 (1.9377) time: 0.5003 [2021-03-26 16:27:19 swin_small_patch4_window7_224] INFO: Epoch: [201] [1200/1251] eta: 0:00:25 lr: 0.000249 loss: 3.0285 (3.0925) grad_norm: 1.8531 (1.9370) time: 0.5023 [2021-03-26 16:27:25 swin_small_patch4_window7_224] INFO: Epoch: [201] [1210/1251] eta: 0:00:20 lr: 0.000249 loss: 3.4265 (3.0931) grad_norm: 1.8306 (1.9369) time: 0.5028 [2021-03-26 16:27:30 swin_small_patch4_window7_224] INFO: Epoch: [201] [1220/1251] eta: 0:00:15 lr: 0.000249 loss: 3.0872 (3.0923) grad_norm: 1.8187 (1.9370) time: 0.5067 [2021-03-26 16:27:35 swin_small_patch4_window7_224] INFO: Epoch: [201] [1230/1251] eta: 0:00:10 lr: 0.000249 loss: 3.0646 (3.0912) grad_norm: 1.8187 (1.9380) time: 0.5063 [2021-03-26 16:27:40 swin_small_patch4_window7_224] INFO: Epoch: [201] [1240/1251] eta: 0:00:05 lr: 0.000249 loss: 3.2188 (3.0916) grad_norm: 1.9654 (1.9390) time: 0.4997 [2021-03-26 16:27:45 swin_small_patch4_window7_224] INFO: Epoch: [201] [1250/1251] eta: 0:00:00 lr: 0.000249 loss: 3.1816 (3.0923) grad_norm: 1.9886 (1.9399) time: 0.5023 [2021-03-26 16:27:59 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:06 loss: 0.7329 (0.7329) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-26 16:28:01 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7952 (0.8182) acc1: 81.2500 (79.2614) acc5: 95.3125 (95.8807) [2021-03-26 16:28:03 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8614 (0.8526) acc1: 78.1250 (78.9435) acc5: 95.3125 (95.0149) [2021-03-26 16:28:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.8358 (0.8471) acc1: 79.6875 (79.2843) acc5: 95.3125 (95.0605) [2021-03-26 16:28:07 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8018 (0.8258) acc1: 79.6875 (79.8780) acc5: 95.3125 (95.1982) [2021-03-26 16:28:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8305 (0.8187) acc1: 79.6875 (79.8080) acc5: 95.3125 (95.3600) [2021-03-26 16:28:23 swin_small_patch4_window7_224] INFO: * Acc@1 80.422 Acc@5 95.528 loss 0.817 [2021-03-26 16:28:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.4% [2021-03-26 16:28:23 swin_small_patch4_window7_224] INFO: Max accuracy: 80.53% [2021-03-26 16:28:27 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 0/1251] eta: 1:29:03 lr: 0.000249 loss: 3.3470 (3.3470) grad_norm: 1.7604 (1.7604) time: 4.2716 [2021-03-26 16:28:33 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 10/1251] eta: 0:17:46 lr: 0.000249 loss: 3.0716 (2.8606) grad_norm: 1.8389 (1.8696) time: 0.8597 [2021-03-26 16:28:38 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 20/1251] eta: 0:14:15 lr: 0.000249 loss: 3.0716 (2.9882) grad_norm: 1.8882 (1.9016) time: 0.5159 [2021-03-26 16:28:43 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 30/1251] eta: 0:12:50 lr: 0.000248 loss: 3.2605 (3.0494) grad_norm: 1.9576 (1.9655) time: 0.5051 [2021-03-26 16:28:48 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 40/1251] eta: 0:12:05 lr: 0.000248 loss: 3.1464 (3.0593) grad_norm: 1.9462 (1.9867) time: 0.4981 [2021-03-26 16:28:53 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 50/1251] eta: 0:11:35 lr: 0.000248 loss: 3.2195 (3.0849) grad_norm: 1.8876 (1.9631) time: 0.4998 [2021-03-26 16:28:58 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 60/1251] eta: 0:11:14 lr: 0.000248 loss: 3.3331 (3.1204) grad_norm: 1.8242 (1.9523) time: 0.5009 [2021-03-26 16:29:03 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 70/1251] eta: 0:10:59 lr: 0.000248 loss: 3.3779 (3.1428) grad_norm: 1.8529 (1.9491) time: 0.5048 [2021-03-26 16:29:08 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 80/1251] eta: 0:10:48 lr: 0.000248 loss: 3.3068 (3.1646) grad_norm: 1.9087 (1.9641) time: 0.5153 [2021-03-26 16:29:13 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 90/1251] eta: 0:10:39 lr: 0.000248 loss: 3.2928 (3.1648) grad_norm: 1.9142 (1.9499) time: 0.5235 [2021-03-26 16:29:18 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 100/1251] eta: 0:10:28 lr: 0.000248 loss: 3.2467 (3.1685) grad_norm: 1.8116 (1.9408) time: 0.5133 [2021-03-26 16:29:23 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 110/1251] eta: 0:10:18 lr: 0.000248 loss: 3.0791 (3.1560) grad_norm: 1.8507 (1.9392) time: 0.5028 [2021-03-26 16:29:28 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 120/1251] eta: 0:10:09 lr: 0.000248 loss: 3.0289 (3.1441) grad_norm: 1.8507 (1.9387) time: 0.5012 [2021-03-26 16:29:33 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 130/1251] eta: 0:10:00 lr: 0.000248 loss: 3.1863 (3.1339) grad_norm: 1.8850 (1.9395) time: 0.5007 [2021-03-26 16:29:38 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 140/1251] eta: 0:09:53 lr: 0.000248 loss: 3.0078 (3.1122) grad_norm: 1.8816 (1.9324) time: 0.5078 [2021-03-26 16:29:43 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 150/1251] eta: 0:09:45 lr: 0.000248 loss: 2.7086 (3.0920) grad_norm: 1.8816 (1.9434) time: 0.5023 [2021-03-26 16:29:48 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 160/1251] eta: 0:09:37 lr: 0.000248 loss: 3.0004 (3.0958) grad_norm: 2.0883 (1.9513) time: 0.4963 [2021-03-26 16:29:53 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 170/1251] eta: 0:09:30 lr: 0.000248 loss: 2.9496 (3.0859) grad_norm: 1.9605 (1.9554) time: 0.5018 [2021-03-26 16:29:59 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 180/1251] eta: 0:09:25 lr: 0.000248 loss: 3.1485 (3.0933) grad_norm: 1.9289 (1.9521) time: 0.5165 [2021-03-26 16:30:04 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 190/1251] eta: 0:09:19 lr: 0.000248 loss: 3.3042 (3.1015) grad_norm: 1.8432 (1.9445) time: 0.5216 [2021-03-26 16:30:09 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 200/1251] eta: 0:09:13 lr: 0.000248 loss: 3.1045 (3.0926) grad_norm: 1.8049 (1.9389) time: 0.5155 [2021-03-26 16:30:14 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 210/1251] eta: 0:09:07 lr: 0.000248 loss: 3.1045 (3.0922) grad_norm: 1.8858 (1.9428) time: 0.5119 [2021-03-26 16:30:19 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 220/1251] eta: 0:09:00 lr: 0.000248 loss: 3.0975 (3.0812) grad_norm: 1.9651 (1.9443) time: 0.5018 [2021-03-26 16:30:24 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 230/1251] eta: 0:08:54 lr: 0.000248 loss: 2.9826 (3.0732) grad_norm: 2.0637 (1.9524) time: 0.5049 [2021-03-26 16:30:29 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 240/1251] eta: 0:08:48 lr: 0.000248 loss: 3.0685 (3.0815) grad_norm: 2.0637 (1.9568) time: 0.5056 [2021-03-26 16:30:34 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 250/1251] eta: 0:08:43 lr: 0.000248 loss: 3.2235 (3.0802) grad_norm: 1.9303 (1.9537) time: 0.5076 [2021-03-26 16:30:39 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 260/1251] eta: 0:08:37 lr: 0.000248 loss: 3.2820 (3.0830) grad_norm: 1.8908 (1.9517) time: 0.5081 [2021-03-26 16:30:44 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 270/1251] eta: 0:08:31 lr: 0.000248 loss: 3.2688 (3.0781) grad_norm: 1.9206 (1.9531) time: 0.5041 [2021-03-26 16:30:49 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 280/1251] eta: 0:08:25 lr: 0.000248 loss: 3.0877 (3.0738) grad_norm: 1.9333 (1.9523) time: 0.5034 [2021-03-26 16:30:54 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 290/1251] eta: 0:08:19 lr: 0.000248 loss: 3.0468 (3.0766) grad_norm: 1.9757 (1.9580) time: 0.5032 [2021-03-26 16:30:59 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 300/1251] eta: 0:08:13 lr: 0.000248 loss: 3.0468 (3.0759) grad_norm: 2.0194 (1.9602) time: 0.5038 [2021-03-26 16:31:05 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 310/1251] eta: 0:08:08 lr: 0.000247 loss: 2.8839 (3.0712) grad_norm: 1.9541 (1.9613) time: 0.5032 [2021-03-26 16:31:10 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 320/1251] eta: 0:08:02 lr: 0.000247 loss: 2.9714 (3.0717) grad_norm: 1.9812 (1.9642) time: 0.5017 [2021-03-26 16:31:15 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 330/1251] eta: 0:07:57 lr: 0.000247 loss: 3.0425 (3.0706) grad_norm: 1.9055 (1.9632) time: 0.5035 [2021-03-26 16:31:20 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 340/1251] eta: 0:07:51 lr: 0.000247 loss: 2.9574 (3.0654) grad_norm: 1.7821 (1.9603) time: 0.5101 [2021-03-26 16:31:25 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 350/1251] eta: 0:07:46 lr: 0.000247 loss: 2.9229 (3.0591) grad_norm: 1.8365 (1.9594) time: 0.5082 [2021-03-26 16:31:30 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 360/1251] eta: 0:07:40 lr: 0.000247 loss: 3.1035 (3.0590) grad_norm: 1.8428 (1.9583) time: 0.5033 [2021-03-26 16:31:35 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 370/1251] eta: 0:07:35 lr: 0.000247 loss: 3.1322 (3.0576) grad_norm: 2.0755 (1.9648) time: 0.5078 [2021-03-26 16:31:40 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 380/1251] eta: 0:07:29 lr: 0.000247 loss: 3.0142 (3.0561) grad_norm: 2.0817 (1.9638) time: 0.5078 [2021-03-26 16:31:45 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 390/1251] eta: 0:07:24 lr: 0.000247 loss: 3.0142 (3.0522) grad_norm: 1.8483 (1.9610) time: 0.5005 [2021-03-26 16:31:50 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 400/1251] eta: 0:07:18 lr: 0.000247 loss: 3.1373 (3.0560) grad_norm: 1.8412 (1.9592) time: 0.5010 [2021-03-26 16:31:55 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 410/1251] eta: 0:07:13 lr: 0.000247 loss: 3.1483 (3.0575) grad_norm: 1.8412 (1.9580) time: 0.5008 [2021-03-26 16:32:00 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 420/1251] eta: 0:07:07 lr: 0.000247 loss: 3.1483 (3.0624) grad_norm: 1.8934 (1.9559) time: 0.4978 [2021-03-26 16:32:05 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 430/1251] eta: 0:07:02 lr: 0.000247 loss: 3.2558 (3.0656) grad_norm: 1.8434 (1.9551) time: 0.4993 [2021-03-26 16:32:10 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 440/1251] eta: 0:06:57 lr: 0.000247 loss: 3.1685 (3.0659) grad_norm: 1.8420 (1.9548) time: 0.5005 [2021-03-26 16:32:15 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 450/1251] eta: 0:06:51 lr: 0.000247 loss: 3.1740 (3.0683) grad_norm: 1.9505 (1.9538) time: 0.4970 [2021-03-26 16:32:20 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 460/1251] eta: 0:06:46 lr: 0.000247 loss: 3.1983 (3.0669) grad_norm: 1.9366 (1.9542) time: 0.5015 [2021-03-26 16:32:25 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 470/1251] eta: 0:06:41 lr: 0.000247 loss: 3.0700 (3.0676) grad_norm: 1.9370 (1.9554) time: 0.5076 [2021-03-26 16:32:30 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 480/1251] eta: 0:06:35 lr: 0.000247 loss: 3.1541 (3.0700) grad_norm: 2.0127 (1.9554) time: 0.5036 [2021-03-26 16:32:35 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 490/1251] eta: 0:06:30 lr: 0.000247 loss: 3.3402 (3.0722) grad_norm: 1.9775 (1.9544) time: 0.4994 [2021-03-26 16:32:40 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 500/1251] eta: 0:06:25 lr: 0.000247 loss: 3.1468 (3.0732) grad_norm: 1.8577 (1.9524) time: 0.4993 [2021-03-26 16:32:45 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 510/1251] eta: 0:06:19 lr: 0.000247 loss: 3.2715 (3.0756) grad_norm: 1.9147 (1.9530) time: 0.5026 [2021-03-26 16:32:50 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 520/1251] eta: 0:06:14 lr: 0.000247 loss: 3.1908 (3.0739) grad_norm: 1.9233 (1.9514) time: 0.5078 [2021-03-26 16:32:55 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 530/1251] eta: 0:06:09 lr: 0.000247 loss: 3.0073 (3.0709) grad_norm: 1.9080 (1.9525) time: 0.5061 [2021-03-26 16:33:00 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 540/1251] eta: 0:06:04 lr: 0.000247 loss: 3.0182 (3.0716) grad_norm: 1.9127 (1.9570) time: 0.5020 [2021-03-26 16:33:06 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 550/1251] eta: 0:05:59 lr: 0.000247 loss: 3.1190 (3.0748) grad_norm: 1.9675 (1.9584) time: 0.5198 [2021-03-26 16:33:11 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 560/1251] eta: 0:05:54 lr: 0.000247 loss: 3.1663 (3.0728) grad_norm: 1.9726 (1.9585) time: 0.5235 [2021-03-26 16:33:16 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 570/1251] eta: 0:05:48 lr: 0.000247 loss: 3.0722 (3.0750) grad_norm: 1.9276 (1.9583) time: 0.5056 [2021-03-26 16:33:21 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 580/1251] eta: 0:05:43 lr: 0.000247 loss: 3.2226 (3.0770) grad_norm: 1.8541 (1.9582) time: 0.5054 [2021-03-26 16:33:26 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 590/1251] eta: 0:05:38 lr: 0.000246 loss: 3.2437 (3.0796) grad_norm: 1.8555 (1.9574) time: 0.5075 [2021-03-26 16:33:31 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 600/1251] eta: 0:05:33 lr: 0.000246 loss: 3.2437 (3.0813) grad_norm: 1.8555 (1.9560) time: 0.5079 [2021-03-26 16:33:36 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 610/1251] eta: 0:05:28 lr: 0.000246 loss: 3.1729 (3.0835) grad_norm: 1.8835 (1.9556) time: 0.5069 [2021-03-26 16:33:41 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 620/1251] eta: 0:05:22 lr: 0.000246 loss: 3.2351 (3.0862) grad_norm: 1.8835 (1.9550) time: 0.5032 [2021-03-26 16:33:46 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 630/1251] eta: 0:05:17 lr: 0.000246 loss: 3.1821 (3.0828) grad_norm: 1.9142 (1.9545) time: 0.5075 [2021-03-26 16:33:51 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 640/1251] eta: 0:05:12 lr: 0.000246 loss: 3.0702 (3.0850) grad_norm: 1.9490 (1.9553) time: 0.5104 [2021-03-26 16:33:56 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 650/1251] eta: 0:05:07 lr: 0.000246 loss: 3.0567 (3.0787) grad_norm: 1.9601 (1.9553) time: 0.5057 [2021-03-26 16:34:01 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 660/1251] eta: 0:05:02 lr: 0.000246 loss: 2.6482 (3.0764) grad_norm: 1.8476 (1.9569) time: 0.5056 [2021-03-26 16:34:06 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 670/1251] eta: 0:04:57 lr: 0.000246 loss: 3.1317 (3.0783) grad_norm: 1.8476 (1.9570) time: 0.5026 [2021-03-26 16:34:11 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 680/1251] eta: 0:04:51 lr: 0.000246 loss: 3.1317 (3.0763) grad_norm: 1.9738 (1.9589) time: 0.4970 [2021-03-26 16:34:16 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 690/1251] eta: 0:04:46 lr: 0.000246 loss: 3.1904 (3.0778) grad_norm: 1.9302 (1.9593) time: 0.4963 [2021-03-26 16:34:21 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 700/1251] eta: 0:04:41 lr: 0.000246 loss: 3.1466 (3.0768) grad_norm: 1.9493 (1.9605) time: 0.4999 [2021-03-26 16:34:26 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 710/1251] eta: 0:04:36 lr: 0.000246 loss: 2.8009 (3.0732) grad_norm: 1.9493 (1.9605) time: 0.5044 [2021-03-26 16:34:31 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 720/1251] eta: 0:04:31 lr: 0.000246 loss: 2.8166 (3.0703) grad_norm: 1.9265 (1.9603) time: 0.5036 [2021-03-26 16:34:37 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 730/1251] eta: 0:04:26 lr: 0.000246 loss: 3.1781 (3.0702) grad_norm: 1.9563 (1.9600) time: 0.5115 [2021-03-26 16:34:42 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 740/1251] eta: 0:04:21 lr: 0.000246 loss: 3.0449 (3.0681) grad_norm: 1.9563 (1.9603) time: 0.5315 [2021-03-26 16:34:47 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 750/1251] eta: 0:04:16 lr: 0.000246 loss: 3.2442 (3.0720) grad_norm: 1.8992 (1.9589) time: 0.5189 [2021-03-26 16:34:52 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 760/1251] eta: 0:04:11 lr: 0.000246 loss: 3.2716 (3.0715) grad_norm: 1.8680 (1.9594) time: 0.5123 [2021-03-26 16:34:57 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 770/1251] eta: 0:04:05 lr: 0.000246 loss: 2.8938 (3.0681) grad_norm: 1.8056 (1.9574) time: 0.5135 [2021-03-26 16:35:02 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 780/1251] eta: 0:04:00 lr: 0.000246 loss: 2.9106 (3.0682) grad_norm: 1.8104 (1.9562) time: 0.4988 [2021-03-26 16:35:07 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 790/1251] eta: 0:03:55 lr: 0.000246 loss: 3.1540 (3.0678) grad_norm: 1.9168 (1.9580) time: 0.4966 [2021-03-26 16:35:12 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 800/1251] eta: 0:03:50 lr: 0.000246 loss: 3.1778 (3.0691) grad_norm: 1.9897 (1.9602) time: 0.4988 [2021-03-26 16:35:17 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 810/1251] eta: 0:03:45 lr: 0.000246 loss: 3.2811 (3.0704) grad_norm: 1.9173 (1.9602) time: 0.5064 [2021-03-26 16:35:22 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 820/1251] eta: 0:03:40 lr: 0.000246 loss: 3.4016 (3.0716) grad_norm: 1.9454 (1.9608) time: 0.5087 [2021-03-26 16:35:28 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 830/1251] eta: 0:03:35 lr: 0.000246 loss: 3.1746 (3.0703) grad_norm: 2.0076 (1.9620) time: 0.5167 [2021-03-26 16:35:33 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 840/1251] eta: 0:03:29 lr: 0.000246 loss: 2.9819 (3.0695) grad_norm: 1.9852 (1.9626) time: 0.5128 [2021-03-26 16:35:38 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 850/1251] eta: 0:03:24 lr: 0.000246 loss: 2.9819 (3.0686) grad_norm: 1.9143 (1.9631) time: 0.5041 [2021-03-26 16:35:43 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 860/1251] eta: 0:03:19 lr: 0.000246 loss: 3.1429 (3.0668) grad_norm: 1.8773 (1.9622) time: 0.5063 [2021-03-26 16:35:48 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 870/1251] eta: 0:03:14 lr: 0.000245 loss: 2.9681 (3.0652) grad_norm: 1.9355 (1.9631) time: 0.5040 [2021-03-26 16:35:53 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 880/1251] eta: 0:03:09 lr: 0.000245 loss: 2.8652 (3.0639) grad_norm: 2.0077 (1.9641) time: 0.5074 [2021-03-26 16:35:58 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 890/1251] eta: 0:03:04 lr: 0.000245 loss: 3.0032 (3.0632) grad_norm: 1.9825 (1.9642) time: 0.5069 [2021-03-26 16:36:03 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 900/1251] eta: 0:02:59 lr: 0.000245 loss: 3.1138 (3.0635) grad_norm: 1.8915 (1.9645) time: 0.5027 [2021-03-26 16:36:08 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 910/1251] eta: 0:02:53 lr: 0.000245 loss: 3.0284 (3.0620) grad_norm: 1.9718 (1.9658) time: 0.5038 [2021-03-26 16:36:13 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 920/1251] eta: 0:02:48 lr: 0.000245 loss: 3.1368 (3.0619) grad_norm: 1.9894 (1.9660) time: 0.5062 [2021-03-26 16:36:18 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 930/1251] eta: 0:02:43 lr: 0.000245 loss: 3.1368 (3.0594) grad_norm: 1.9107 (1.9658) time: 0.5123 [2021-03-26 16:36:23 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 940/1251] eta: 0:02:38 lr: 0.000245 loss: 2.9924 (3.0598) grad_norm: 1.8145 (1.9644) time: 0.5093 [2021-03-26 16:36:29 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 950/1251] eta: 0:02:33 lr: 0.000245 loss: 3.1727 (3.0604) grad_norm: 1.8118 (1.9636) time: 0.5144 [2021-03-26 16:36:34 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 960/1251] eta: 0:02:28 lr: 0.000245 loss: 3.1727 (3.0611) grad_norm: 1.9759 (1.9646) time: 0.5183 [2021-03-26 16:36:39 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 970/1251] eta: 0:02:23 lr: 0.000245 loss: 3.1304 (3.0614) grad_norm: 2.0478 (1.9669) time: 0.5071 [2021-03-26 16:36:44 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 980/1251] eta: 0:02:18 lr: 0.000245 loss: 3.1939 (3.0619) grad_norm: 2.0070 (1.9666) time: 0.5073 [2021-03-26 16:36:49 swin_small_patch4_window7_224] INFO: Epoch: [202] [ 990/1251] eta: 0:02:13 lr: 0.000245 loss: 3.1021 (3.0617) grad_norm: 1.8847 (1.9662) time: 0.5114 [2021-03-26 16:36:54 swin_small_patch4_window7_224] INFO: Epoch: [202] [1000/1251] eta: 0:02:08 lr: 0.000245 loss: 3.0567 (3.0600) grad_norm: 1.8583 (1.9658) time: 0.5057 [2021-03-26 16:36:59 swin_small_patch4_window7_224] INFO: Epoch: [202] [1010/1251] eta: 0:02:02 lr: 0.000245 loss: 3.3479 (3.0621) grad_norm: 1.9176 (1.9657) time: 0.5054 [2021-03-26 16:37:04 swin_small_patch4_window7_224] INFO: Epoch: [202] [1020/1251] eta: 0:01:57 lr: 0.000245 loss: 3.1822 (3.0601) grad_norm: 1.8906 (1.9660) time: 0.5077 [2021-03-26 16:37:09 swin_small_patch4_window7_224] INFO: Epoch: [202] [1030/1251] eta: 0:01:52 lr: 0.000245 loss: 3.2162 (3.0617) grad_norm: 1.8616 (1.9655) time: 0.5019 [2021-03-26 16:37:14 swin_small_patch4_window7_224] INFO: Epoch: [202] [1040/1251] eta: 0:01:47 lr: 0.000245 loss: 3.1932 (3.0585) grad_norm: 1.8271 (1.9652) time: 0.5009 [2021-03-26 16:37:19 swin_small_patch4_window7_224] INFO: Epoch: [202] [1050/1251] eta: 0:01:42 lr: 0.000245 loss: 3.1932 (3.0598) grad_norm: 1.9736 (1.9667) time: 0.5046 [2021-03-26 16:37:24 swin_small_patch4_window7_224] INFO: Epoch: [202] [1060/1251] eta: 0:01:37 lr: 0.000245 loss: 3.2868 (3.0610) grad_norm: 2.0070 (1.9668) time: 0.5027 [2021-03-26 16:37:29 swin_small_patch4_window7_224] INFO: Epoch: [202] [1070/1251] eta: 0:01:32 lr: 0.000245 loss: 3.1389 (3.0615) grad_norm: 2.0070 (1.9686) time: 0.4993 [2021-03-26 16:37:34 swin_small_patch4_window7_224] INFO: Epoch: [202] [1080/1251] eta: 0:01:27 lr: 0.000245 loss: 3.1389 (3.0627) grad_norm: 2.0175 (1.9695) time: 0.4995 [2021-03-26 16:37:39 swin_small_patch4_window7_224] INFO: Epoch: [202] [1090/1251] eta: 0:01:22 lr: 0.000245 loss: 3.2813 (3.0642) grad_norm: 1.9595 (1.9695) time: 0.5045 [2021-03-26 16:37:44 swin_small_patch4_window7_224] INFO: Epoch: [202] [1100/1251] eta: 0:01:16 lr: 0.000245 loss: 3.2174 (3.0638) grad_norm: 1.9999 (1.9708) time: 0.5083 [2021-03-26 16:37:50 swin_small_patch4_window7_224] INFO: Epoch: [202] [1110/1251] eta: 0:01:11 lr: 0.000245 loss: 2.7810 (3.0623) grad_norm: 2.0509 (1.9712) time: 0.5096 [2021-03-26 16:37:55 swin_small_patch4_window7_224] INFO: Epoch: [202] [1120/1251] eta: 0:01:06 lr: 0.000245 loss: 2.8745 (3.0621) grad_norm: 1.8760 (1.9709) time: 0.5133 [2021-03-26 16:38:00 swin_small_patch4_window7_224] INFO: Epoch: [202] [1130/1251] eta: 0:01:01 lr: 0.000245 loss: 3.1340 (3.0634) grad_norm: 1.8359 (1.9706) time: 0.5054 [2021-03-26 16:38:05 swin_small_patch4_window7_224] INFO: Epoch: [202] [1140/1251] eta: 0:00:56 lr: 0.000245 loss: 3.0260 (3.0631) grad_norm: 1.9005 (1.9707) time: 0.5048 [2021-03-26 16:38:10 swin_small_patch4_window7_224] INFO: Epoch: [202] [1150/1251] eta: 0:00:51 lr: 0.000245 loss: 3.0699 (3.0647) grad_norm: 1.9604 (1.9708) time: 0.5059 [2021-03-26 16:38:15 swin_small_patch4_window7_224] INFO: Epoch: [202] [1160/1251] eta: 0:00:46 lr: 0.000244 loss: 3.3007 (3.0660) grad_norm: 2.0195 (1.9717) time: 0.5021 [2021-03-26 16:38:20 swin_small_patch4_window7_224] INFO: Epoch: [202] [1170/1251] eta: 0:00:41 lr: 0.000244 loss: 3.3231 (3.0674) grad_norm: 2.0503 (1.9723) time: 0.5019 [2021-03-26 16:38:25 swin_small_patch4_window7_224] INFO: Epoch: [202] [1180/1251] eta: 0:00:36 lr: 0.000244 loss: 3.2408 (3.0689) grad_norm: 1.9671 (1.9722) time: 0.4993 [2021-03-26 16:38:30 swin_small_patch4_window7_224] INFO: Epoch: [202] [1190/1251] eta: 0:00:31 lr: 0.000244 loss: 3.2315 (3.0674) grad_norm: 1.9256 (1.9718) time: 0.4983 [2021-03-26 16:38:35 swin_small_patch4_window7_224] INFO: Epoch: [202] [1200/1251] eta: 0:00:25 lr: 0.000244 loss: 3.1193 (3.0672) grad_norm: 1.9209 (1.9714) time: 0.4982 [2021-03-26 16:38:40 swin_small_patch4_window7_224] INFO: Epoch: [202] [1210/1251] eta: 0:00:20 lr: 0.000244 loss: 3.0886 (3.0672) grad_norm: 1.9259 (1.9722) time: 0.5003 [2021-03-26 16:38:45 swin_small_patch4_window7_224] INFO: Epoch: [202] [1220/1251] eta: 0:00:15 lr: 0.000244 loss: 3.1671 (3.0679) grad_norm: 1.9259 (1.9715) time: 0.5034 [2021-03-26 16:38:50 swin_small_patch4_window7_224] INFO: Epoch: [202] [1230/1251] eta: 0:00:10 lr: 0.000244 loss: 3.2413 (3.0703) grad_norm: 1.9049 (1.9715) time: 0.5052 [2021-03-26 16:38:55 swin_small_patch4_window7_224] INFO: Epoch: [202] [1240/1251] eta: 0:00:05 lr: 0.000244 loss: 3.2413 (3.0687) grad_norm: 1.9632 (1.9709) time: 0.5057 [2021-03-26 16:39:00 swin_small_patch4_window7_224] INFO: Epoch: [202] [1250/1251] eta: 0:00:00 lr: 0.000244 loss: 2.9721 (3.0672) grad_norm: 1.9678 (1.9716) time: 0.5030 [2021-03-26 16:39:10 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:29 loss: 0.7877 (0.7877) acc1: 78.1250 (78.1250) acc5: 98.4375 (98.4375) [2021-03-26 16:39:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8084 (0.8470) acc1: 81.2500 (78.9773) acc5: 95.3125 (95.7386) [2021-03-26 16:39:14 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8084 (0.8541) acc1: 79.6875 (79.4643) acc5: 95.3125 (95.8333) [2021-03-26 16:39:16 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7707 (0.8237) acc1: 79.6875 (80.2923) acc5: 95.3125 (95.9173) [2021-03-26 16:39:18 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7509 (0.8083) acc1: 82.8125 (80.9451) acc5: 96.8750 (95.9223) [2021-03-26 16:39:19 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7560 (0.8277) acc1: 81.2500 (80.5120) acc5: 95.3125 (95.5840) [2021-03-26 16:39:29 swin_small_patch4_window7_224] INFO: * Acc@1 80.626 Acc@5 95.572 loss 0.816 [2021-03-26 16:39:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.6% [2021-03-26 16:39:29 swin_small_patch4_window7_224] INFO: Max accuracy: 80.63% [2021-03-26 16:39:33 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 0/1251] eta: 1:32:26 lr: 0.000244 loss: 2.6234 (2.6234) grad_norm: 2.2228 (2.2228) time: 4.4336 [2021-03-26 16:39:38 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 10/1251] eta: 0:18:09 lr: 0.000244 loss: 3.1769 (3.1107) grad_norm: 1.9071 (2.0636) time: 0.8780 [2021-03-26 16:39:43 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 20/1251] eta: 0:14:23 lr: 0.000244 loss: 3.2695 (3.1322) grad_norm: 1.9460 (2.0718) time: 0.5149 [2021-03-26 16:39:48 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 30/1251] eta: 0:12:58 lr: 0.000244 loss: 3.2695 (3.1585) grad_norm: 1.9590 (2.0229) time: 0.5050 [2021-03-26 16:39:54 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 40/1251] eta: 0:12:17 lr: 0.000244 loss: 3.2959 (3.1513) grad_norm: 1.8891 (2.0058) time: 0.5111 [2021-03-26 16:39:59 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 50/1251] eta: 0:11:48 lr: 0.000244 loss: 3.2753 (3.1345) grad_norm: 1.8377 (1.9698) time: 0.5172 [2021-03-26 16:40:04 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 60/1251] eta: 0:11:24 lr: 0.000244 loss: 3.2145 (3.1344) grad_norm: 1.8114 (1.9716) time: 0.5062 [2021-03-26 16:40:09 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 70/1251] eta: 0:11:06 lr: 0.000244 loss: 3.1215 (3.1140) grad_norm: 1.8114 (1.9498) time: 0.4979 [2021-03-26 16:40:14 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 80/1251] eta: 0:10:54 lr: 0.000244 loss: 3.1478 (3.1217) grad_norm: 1.7999 (1.9387) time: 0.5102 [2021-03-26 16:40:19 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 90/1251] eta: 0:10:42 lr: 0.000244 loss: 3.0817 (3.0987) grad_norm: 1.8879 (1.9456) time: 0.5134 [2021-03-26 16:40:24 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 100/1251] eta: 0:10:30 lr: 0.000244 loss: 3.1209 (3.1006) grad_norm: 1.9037 (1.9427) time: 0.5013 [2021-03-26 16:40:29 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 110/1251] eta: 0:10:21 lr: 0.000244 loss: 3.2174 (3.1102) grad_norm: 1.9037 (1.9414) time: 0.5078 [2021-03-26 16:40:34 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 120/1251] eta: 0:10:12 lr: 0.000244 loss: 2.9891 (3.0962) grad_norm: 1.9258 (1.9338) time: 0.5086 [2021-03-26 16:40:39 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 130/1251] eta: 0:10:02 lr: 0.000244 loss: 2.9348 (3.0936) grad_norm: 1.9258 (1.9386) time: 0.4986 [2021-03-26 16:40:44 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 140/1251] eta: 0:09:56 lr: 0.000244 loss: 3.0409 (3.0933) grad_norm: 1.9743 (1.9412) time: 0.5119 [2021-03-26 16:40:49 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 150/1251] eta: 0:09:49 lr: 0.000244 loss: 3.1059 (3.0968) grad_norm: 1.9104 (1.9387) time: 0.5172 [2021-03-26 16:40:54 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 160/1251] eta: 0:09:41 lr: 0.000244 loss: 3.1725 (3.0959) grad_norm: 1.8582 (1.9400) time: 0.5056 [2021-03-26 16:41:00 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 170/1251] eta: 0:09:34 lr: 0.000244 loss: 3.1910 (3.1067) grad_norm: 1.8282 (1.9318) time: 0.5036 [2021-03-26 16:41:05 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 180/1251] eta: 0:09:27 lr: 0.000244 loss: 3.1212 (3.1016) grad_norm: 1.7995 (1.9281) time: 0.5046 [2021-03-26 16:41:10 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 190/1251] eta: 0:09:21 lr: 0.000243 loss: 3.2736 (3.1194) grad_norm: 1.8390 (1.9289) time: 0.5083 [2021-03-26 16:41:15 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 200/1251] eta: 0:09:15 lr: 0.000243 loss: 3.4962 (3.1223) grad_norm: 1.9091 (1.9313) time: 0.5158 [2021-03-26 16:41:20 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 210/1251] eta: 0:09:08 lr: 0.000243 loss: 3.2396 (3.1271) grad_norm: 2.0054 (1.9363) time: 0.5104 [2021-03-26 16:41:25 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 220/1251] eta: 0:09:02 lr: 0.000243 loss: 3.2565 (3.1318) grad_norm: 2.0054 (1.9394) time: 0.4992 [2021-03-26 16:41:30 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 230/1251] eta: 0:08:55 lr: 0.000243 loss: 3.1028 (3.1221) grad_norm: 1.9620 (1.9381) time: 0.4979 [2021-03-26 16:41:35 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 240/1251] eta: 0:08:49 lr: 0.000243 loss: 3.0444 (3.1259) grad_norm: 1.9750 (1.9467) time: 0.5008 [2021-03-26 16:41:40 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 250/1251] eta: 0:08:43 lr: 0.000243 loss: 3.0444 (3.1122) grad_norm: 2.0194 (1.9509) time: 0.5031 [2021-03-26 16:41:45 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 260/1251] eta: 0:08:37 lr: 0.000243 loss: 3.0004 (3.1100) grad_norm: 1.9980 (1.9531) time: 0.5051 [2021-03-26 16:41:50 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 270/1251] eta: 0:08:31 lr: 0.000243 loss: 2.9790 (3.1013) grad_norm: 1.9544 (1.9538) time: 0.5028 [2021-03-26 16:41:55 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 280/1251] eta: 0:08:25 lr: 0.000243 loss: 2.9510 (3.0950) grad_norm: 1.8513 (1.9642) time: 0.5004 [2021-03-26 16:42:00 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 290/1251] eta: 0:08:19 lr: 0.000243 loss: 3.0413 (3.0979) grad_norm: 1.9370 (1.9675) time: 0.5015 [2021-03-26 16:42:05 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 300/1251] eta: 0:08:14 lr: 0.000243 loss: 2.9374 (3.0840) grad_norm: 2.0506 (1.9734) time: 0.5043 [2021-03-26 16:42:10 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 310/1251] eta: 0:08:08 lr: 0.000243 loss: 2.7721 (3.0751) grad_norm: 1.9062 (1.9725) time: 0.5043 [2021-03-26 16:42:15 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 320/1251] eta: 0:08:02 lr: 0.000243 loss: 3.0156 (3.0787) grad_norm: 1.9612 (1.9738) time: 0.5040 [2021-03-26 16:42:20 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 330/1251] eta: 0:07:57 lr: 0.000243 loss: 3.1983 (3.0804) grad_norm: 2.0187 (1.9746) time: 0.5082 [2021-03-26 16:42:25 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 340/1251] eta: 0:07:52 lr: 0.000243 loss: 3.2125 (3.0783) grad_norm: 1.9089 (1.9708) time: 0.5122 [2021-03-26 16:42:30 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 350/1251] eta: 0:07:46 lr: 0.000243 loss: 3.0330 (3.0751) grad_norm: 1.7958 (1.9677) time: 0.5060 [2021-03-26 16:42:36 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 360/1251] eta: 0:07:41 lr: 0.000243 loss: 3.0101 (3.0719) grad_norm: 1.8505 (1.9680) time: 0.5039 [2021-03-26 16:42:41 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 370/1251] eta: 0:07:35 lr: 0.000243 loss: 3.2448 (3.0739) grad_norm: 1.9029 (1.9673) time: 0.5094 [2021-03-26 16:42:46 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 380/1251] eta: 0:07:30 lr: 0.000243 loss: 3.3097 (3.0720) grad_norm: 1.8739 (1.9654) time: 0.5063 [2021-03-26 16:42:51 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 390/1251] eta: 0:07:24 lr: 0.000243 loss: 3.2794 (3.0732) grad_norm: 1.8739 (1.9660) time: 0.5063 [2021-03-26 16:42:56 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 400/1251] eta: 0:07:19 lr: 0.000243 loss: 3.0958 (3.0701) grad_norm: 1.9099 (1.9647) time: 0.5048 [2021-03-26 16:43:01 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 410/1251] eta: 0:07:13 lr: 0.000243 loss: 3.0463 (3.0673) grad_norm: 1.7984 (1.9605) time: 0.4999 [2021-03-26 16:43:06 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 420/1251] eta: 0:07:08 lr: 0.000243 loss: 3.3284 (3.0757) grad_norm: 1.8401 (1.9602) time: 0.4990 [2021-03-26 16:43:11 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 430/1251] eta: 0:07:03 lr: 0.000243 loss: 3.2074 (3.0736) grad_norm: 1.8475 (1.9581) time: 0.5032 [2021-03-26 16:43:16 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 440/1251] eta: 0:06:57 lr: 0.000243 loss: 3.0822 (3.0733) grad_norm: 1.8684 (1.9571) time: 0.5060 [2021-03-26 16:43:21 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 450/1251] eta: 0:06:52 lr: 0.000243 loss: 3.0955 (3.0745) grad_norm: 1.8684 (1.9539) time: 0.4987 [2021-03-26 16:43:26 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 460/1251] eta: 0:06:46 lr: 0.000243 loss: 3.2593 (3.0744) grad_norm: 1.8573 (1.9535) time: 0.4979 [2021-03-26 16:43:31 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 470/1251] eta: 0:06:41 lr: 0.000243 loss: 3.1952 (3.0771) grad_norm: 1.9109 (1.9544) time: 0.5049 [2021-03-26 16:43:36 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 480/1251] eta: 0:06:36 lr: 0.000242 loss: 3.1127 (3.0783) grad_norm: 1.8942 (1.9528) time: 0.5037 [2021-03-26 16:43:41 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 490/1251] eta: 0:06:30 lr: 0.000242 loss: 2.9362 (3.0706) grad_norm: 1.9071 (1.9537) time: 0.5039 [2021-03-26 16:43:46 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 500/1251] eta: 0:06:25 lr: 0.000242 loss: 2.4847 (3.0640) grad_norm: 1.9938 (1.9559) time: 0.5064 [2021-03-26 16:43:51 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 510/1251] eta: 0:06:20 lr: 0.000242 loss: 2.9385 (3.0639) grad_norm: 1.9938 (1.9567) time: 0.5028 [2021-03-26 16:43:56 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 520/1251] eta: 0:06:15 lr: 0.000242 loss: 3.0802 (3.0631) grad_norm: 1.9196 (1.9556) time: 0.5037 [2021-03-26 16:44:01 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 530/1251] eta: 0:06:09 lr: 0.000242 loss: 3.1253 (3.0663) grad_norm: 1.9066 (1.9568) time: 0.5032 [2021-03-26 16:44:06 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 540/1251] eta: 0:06:04 lr: 0.000242 loss: 3.2125 (3.0654) grad_norm: 1.9501 (1.9577) time: 0.4972 [2021-03-26 16:44:11 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 550/1251] eta: 0:05:59 lr: 0.000242 loss: 3.1721 (3.0669) grad_norm: 1.9501 (1.9568) time: 0.5143 [2021-03-26 16:44:16 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 560/1251] eta: 0:05:54 lr: 0.000242 loss: 3.1406 (3.0662) grad_norm: 1.9234 (1.9562) time: 0.5183 [2021-03-26 16:44:21 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 570/1251] eta: 0:05:49 lr: 0.000242 loss: 3.2557 (3.0709) grad_norm: 1.8436 (1.9540) time: 0.5048 [2021-03-26 16:44:27 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 580/1251] eta: 0:05:43 lr: 0.000242 loss: 3.3821 (3.0727) grad_norm: 1.9192 (1.9549) time: 0.5063 [2021-03-26 16:44:32 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 590/1251] eta: 0:05:38 lr: 0.000242 loss: 3.2376 (3.0749) grad_norm: 1.9849 (1.9557) time: 0.5098 [2021-03-26 16:44:37 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 600/1251] eta: 0:05:33 lr: 0.000242 loss: 3.2770 (3.0773) grad_norm: 1.9916 (1.9560) time: 0.5063 [2021-03-26 16:44:42 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 610/1251] eta: 0:05:28 lr: 0.000242 loss: 3.2663 (3.0785) grad_norm: 1.8985 (1.9573) time: 0.5050 [2021-03-26 16:44:47 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 620/1251] eta: 0:05:23 lr: 0.000242 loss: 2.9273 (3.0740) grad_norm: 1.9022 (1.9591) time: 0.5111 [2021-03-26 16:44:52 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 630/1251] eta: 0:05:18 lr: 0.000242 loss: 2.8631 (3.0750) grad_norm: 1.9022 (1.9590) time: 0.5142 [2021-03-26 16:44:57 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 640/1251] eta: 0:05:13 lr: 0.000242 loss: 3.2075 (3.0761) grad_norm: 1.9226 (1.9587) time: 0.5102 [2021-03-26 16:45:02 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 650/1251] eta: 0:05:07 lr: 0.000242 loss: 3.2801 (3.0788) grad_norm: 1.9314 (1.9588) time: 0.5039 [2021-03-26 16:45:07 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 660/1251] eta: 0:05:02 lr: 0.000242 loss: 3.1924 (3.0776) grad_norm: 1.9602 (1.9591) time: 0.5060 [2021-03-26 16:45:12 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 670/1251] eta: 0:04:57 lr: 0.000242 loss: 3.1316 (3.0786) grad_norm: 1.9764 (1.9593) time: 0.5048 [2021-03-26 16:45:17 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 680/1251] eta: 0:04:52 lr: 0.000242 loss: 3.2690 (3.0796) grad_norm: 1.9616 (1.9588) time: 0.5085 [2021-03-26 16:45:22 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 690/1251] eta: 0:04:47 lr: 0.000242 loss: 3.2805 (3.0800) grad_norm: 1.9616 (1.9602) time: 0.5106 [2021-03-26 16:45:28 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 700/1251] eta: 0:04:41 lr: 0.000242 loss: 3.2805 (3.0803) grad_norm: 1.9917 (1.9611) time: 0.5047 [2021-03-26 16:45:33 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 710/1251] eta: 0:04:36 lr: 0.000242 loss: 3.1106 (3.0805) grad_norm: 1.9917 (1.9611) time: 0.5073 [2021-03-26 16:45:38 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 720/1251] eta: 0:04:31 lr: 0.000242 loss: 3.1255 (3.0811) grad_norm: 1.9401 (1.9596) time: 0.5030 [2021-03-26 16:45:43 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 730/1251] eta: 0:04:26 lr: 0.000242 loss: 3.2430 (3.0824) grad_norm: 1.8773 (1.9596) time: 0.5032 [2021-03-26 16:45:48 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 740/1251] eta: 0:04:21 lr: 0.000242 loss: 3.2613 (3.0839) grad_norm: 1.9236 (1.9617) time: 0.5197 [2021-03-26 16:45:53 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 750/1251] eta: 0:04:16 lr: 0.000242 loss: 3.2287 (3.0833) grad_norm: 1.9378 (1.9622) time: 0.5251 [2021-03-26 16:45:58 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 760/1251] eta: 0:04:11 lr: 0.000241 loss: 3.1191 (3.0838) grad_norm: 1.9698 (1.9638) time: 0.5206 [2021-03-26 16:46:03 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 770/1251] eta: 0:04:06 lr: 0.000241 loss: 3.1240 (3.0855) grad_norm: 1.9932 (1.9646) time: 0.5134 [2021-03-26 16:46:08 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 780/1251] eta: 0:04:01 lr: 0.000241 loss: 3.1918 (3.0866) grad_norm: 1.9655 (1.9656) time: 0.5037 [2021-03-26 16:46:14 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 790/1251] eta: 0:03:55 lr: 0.000241 loss: 3.2532 (3.0877) grad_norm: 2.1124 (1.9684) time: 0.5095 [2021-03-26 16:46:19 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 800/1251] eta: 0:03:50 lr: 0.000241 loss: 3.2945 (3.0899) grad_norm: 1.9291 (1.9672) time: 0.5109 [2021-03-26 16:46:24 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 810/1251] eta: 0:03:45 lr: 0.000241 loss: 3.0963 (3.0891) grad_norm: 1.8515 (1.9655) time: 0.5062 [2021-03-26 16:46:29 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 820/1251] eta: 0:03:40 lr: 0.000241 loss: 2.9370 (3.0850) grad_norm: 1.8735 (1.9651) time: 0.5087 [2021-03-26 16:46:34 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 830/1251] eta: 0:03:35 lr: 0.000241 loss: 2.9854 (3.0831) grad_norm: 1.8751 (1.9646) time: 0.5083 [2021-03-26 16:46:39 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 840/1251] eta: 0:03:30 lr: 0.000241 loss: 3.0706 (3.0829) grad_norm: 1.9732 (1.9658) time: 0.5037 [2021-03-26 16:46:44 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 850/1251] eta: 0:03:25 lr: 0.000241 loss: 3.0706 (3.0795) grad_norm: 1.9825 (1.9664) time: 0.5061 [2021-03-26 16:46:49 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 860/1251] eta: 0:03:20 lr: 0.000241 loss: 3.0549 (3.0811) grad_norm: 1.8925 (1.9656) time: 0.5147 [2021-03-26 16:46:54 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 870/1251] eta: 0:03:14 lr: 0.000241 loss: 3.1853 (3.0819) grad_norm: 1.8987 (1.9660) time: 0.5095 [2021-03-26 16:46:59 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 880/1251] eta: 0:03:09 lr: 0.000241 loss: 3.2306 (3.0834) grad_norm: 2.0925 (1.9670) time: 0.5068 [2021-03-26 16:47:04 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 890/1251] eta: 0:03:04 lr: 0.000241 loss: 3.2964 (3.0854) grad_norm: 2.1233 (1.9684) time: 0.5090 [2021-03-26 16:47:09 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 900/1251] eta: 0:02:59 lr: 0.000241 loss: 3.2108 (3.0855) grad_norm: 1.9656 (1.9676) time: 0.5007 [2021-03-26 16:47:14 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 910/1251] eta: 0:02:54 lr: 0.000241 loss: 3.1832 (3.0858) grad_norm: 1.9140 (1.9682) time: 0.5003 [2021-03-26 16:47:20 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 920/1251] eta: 0:02:49 lr: 0.000241 loss: 3.2760 (3.0875) grad_norm: 2.0651 (1.9701) time: 0.5131 [2021-03-26 16:47:25 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 930/1251] eta: 0:02:44 lr: 0.000241 loss: 3.2760 (3.0874) grad_norm: 2.0728 (1.9704) time: 0.5174 [2021-03-26 16:47:30 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 940/1251] eta: 0:02:38 lr: 0.000241 loss: 3.3497 (3.0905) grad_norm: 1.8980 (1.9712) time: 0.5096 [2021-03-26 16:47:35 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 950/1251] eta: 0:02:33 lr: 0.000241 loss: 3.3364 (3.0891) grad_norm: 1.8980 (1.9709) time: 0.5051 [2021-03-26 16:47:40 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 960/1251] eta: 0:02:28 lr: 0.000241 loss: 3.0363 (3.0902) grad_norm: 1.8643 (1.9702) time: 0.5059 [2021-03-26 16:47:45 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 970/1251] eta: 0:02:23 lr: 0.000241 loss: 3.1095 (3.0910) grad_norm: 1.8826 (1.9701) time: 0.5011 [2021-03-26 16:47:50 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 980/1251] eta: 0:02:18 lr: 0.000241 loss: 3.0131 (3.0892) grad_norm: 1.9078 (1.9698) time: 0.4997 [2021-03-26 16:47:55 swin_small_patch4_window7_224] INFO: Epoch: [203] [ 990/1251] eta: 0:02:13 lr: 0.000241 loss: 3.0427 (3.0905) grad_norm: 1.9034 (1.9700) time: 0.5006 [2021-03-26 16:48:00 swin_small_patch4_window7_224] INFO: Epoch: [203] [1000/1251] eta: 0:02:08 lr: 0.000241 loss: 3.0875 (3.0893) grad_norm: 2.0327 (1.9709) time: 0.4981 [2021-03-26 16:48:05 swin_small_patch4_window7_224] INFO: Epoch: [203] [1010/1251] eta: 0:02:03 lr: 0.000241 loss: 3.0644 (3.0898) grad_norm: 1.9991 (1.9701) time: 0.4978 [2021-03-26 16:48:10 swin_small_patch4_window7_224] INFO: Epoch: [203] [1020/1251] eta: 0:01:57 lr: 0.000241 loss: 3.2434 (3.0900) grad_norm: 1.9155 (1.9705) time: 0.4983 [2021-03-26 16:48:15 swin_small_patch4_window7_224] INFO: Epoch: [203] [1030/1251] eta: 0:01:52 lr: 0.000241 loss: 3.2015 (3.0884) grad_norm: 2.0591 (1.9726) time: 0.5006 [2021-03-26 16:48:20 swin_small_patch4_window7_224] INFO: Epoch: [203] [1040/1251] eta: 0:01:47 lr: 0.000241 loss: 2.8565 (3.0862) grad_norm: 2.1490 (1.9763) time: 0.5024 [2021-03-26 16:48:25 swin_small_patch4_window7_224] INFO: Epoch: [203] [1050/1251] eta: 0:01:42 lr: 0.000240 loss: 2.7735 (3.0855) grad_norm: 2.1060 (1.9767) time: 0.5024 [2021-03-26 16:48:30 swin_small_patch4_window7_224] INFO: Epoch: [203] [1060/1251] eta: 0:01:37 lr: 0.000240 loss: 3.1519 (3.0877) grad_norm: 1.9797 (1.9770) time: 0.5001 [2021-03-26 16:48:35 swin_small_patch4_window7_224] INFO: Epoch: [203] [1070/1251] eta: 0:01:32 lr: 0.000240 loss: 3.3611 (3.0881) grad_norm: 1.9244 (1.9767) time: 0.5072 [2021-03-26 16:48:40 swin_small_patch4_window7_224] INFO: Epoch: [203] [1080/1251] eta: 0:01:27 lr: 0.000240 loss: 3.2410 (3.0856) grad_norm: 1.9271 (1.9787) time: 0.5166 [2021-03-26 16:48:45 swin_small_patch4_window7_224] INFO: Epoch: [203] [1090/1251] eta: 0:01:22 lr: 0.000240 loss: 3.1634 (3.0866) grad_norm: 2.0072 (1.9794) time: 0.5124 [2021-03-26 16:48:50 swin_small_patch4_window7_224] INFO: Epoch: [203] [1100/1251] eta: 0:01:17 lr: 0.000240 loss: 3.2627 (3.0878) grad_norm: 2.0092 (1.9793) time: 0.5038 [2021-03-26 16:48:56 swin_small_patch4_window7_224] INFO: Epoch: [203] [1110/1251] eta: 0:01:11 lr: 0.000240 loss: 3.2140 (3.0858) grad_norm: 1.9572 (1.9789) time: 0.5064 [2021-03-26 16:49:01 swin_small_patch4_window7_224] INFO: Epoch: [203] [1120/1251] eta: 0:01:06 lr: 0.000240 loss: 2.9912 (3.0858) grad_norm: 1.9092 (1.9782) time: 0.5075 [2021-03-26 16:49:06 swin_small_patch4_window7_224] INFO: Epoch: [203] [1130/1251] eta: 0:01:01 lr: 0.000240 loss: 3.1994 (3.0871) grad_norm: 1.9092 (1.9785) time: 0.5019 [2021-03-26 16:49:11 swin_small_patch4_window7_224] INFO: Epoch: [203] [1140/1251] eta: 0:00:56 lr: 0.000240 loss: 3.1172 (3.0874) grad_norm: 1.9188 (1.9783) time: 0.5035 [2021-03-26 16:49:16 swin_small_patch4_window7_224] INFO: Epoch: [203] [1150/1251] eta: 0:00:51 lr: 0.000240 loss: 2.9712 (3.0858) grad_norm: 1.9495 (1.9781) time: 0.5042 [2021-03-26 16:49:21 swin_small_patch4_window7_224] INFO: Epoch: [203] [1160/1251] eta: 0:00:46 lr: 0.000240 loss: 2.9422 (3.0858) grad_norm: 1.9437 (1.9783) time: 0.5005 [2021-03-26 16:49:26 swin_small_patch4_window7_224] INFO: Epoch: [203] [1170/1251] eta: 0:00:41 lr: 0.000240 loss: 3.1557 (3.0868) grad_norm: 1.9792 (1.9785) time: 0.4991 [2021-03-26 16:49:31 swin_small_patch4_window7_224] INFO: Epoch: [203] [1180/1251] eta: 0:00:36 lr: 0.000240 loss: 3.4353 (3.0884) grad_norm: 1.9562 (1.9774) time: 0.5041 [2021-03-26 16:49:36 swin_small_patch4_window7_224] INFO: Epoch: [203] [1190/1251] eta: 0:00:31 lr: 0.000240 loss: 3.4206 (3.0891) grad_norm: 1.8472 (1.9765) time: 0.5046 [2021-03-26 16:49:41 swin_small_patch4_window7_224] INFO: Epoch: [203] [1200/1251] eta: 0:00:25 lr: 0.000240 loss: 3.2332 (3.0908) grad_norm: 1.9102 (1.9772) time: 0.5021 [2021-03-26 16:49:46 swin_small_patch4_window7_224] INFO: Epoch: [203] [1210/1251] eta: 0:00:20 lr: 0.000240 loss: 3.3245 (3.0911) grad_norm: 1.9429 (1.9771) time: 0.5045 [2021-03-26 16:49:51 swin_small_patch4_window7_224] INFO: Epoch: [203] [1220/1251] eta: 0:00:15 lr: 0.000240 loss: 3.3245 (3.0920) grad_norm: 1.9443 (1.9773) time: 0.5029 [2021-03-26 16:49:56 swin_small_patch4_window7_224] INFO: Epoch: [203] [1230/1251] eta: 0:00:10 lr: 0.000240 loss: 3.2708 (3.0916) grad_norm: 1.9970 (1.9820) time: 0.5063 [2021-03-26 16:50:01 swin_small_patch4_window7_224] INFO: Epoch: [203] [1240/1251] eta: 0:00:05 lr: 0.000240 loss: 3.1845 (3.0916) grad_norm: 1.9980 (1.9826) time: 0.5010 [2021-03-26 16:50:06 swin_small_patch4_window7_224] INFO: Epoch: [203] [1250/1251] eta: 0:00:00 lr: 0.000240 loss: 3.0961 (3.0906) grad_norm: 1.9841 (1.9824) time: 0.4885 [2021-03-26 16:50:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:36 loss: 0.6569 (0.6569) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-26 16:50:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8820 (0.8273) acc1: 79.6875 (78.9773) acc5: 95.3125 (95.4545) [2021-03-26 16:50:21 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8179 (0.8054) acc1: 79.6875 (80.1339) acc5: 95.3125 (95.9821) [2021-03-26 16:50:23 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7865 (0.8139) acc1: 78.1250 (79.7379) acc5: 95.3125 (95.7661) [2021-03-26 16:50:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8152 (0.8211) acc1: 78.1250 (79.9924) acc5: 95.3125 (95.6936) [2021-03-26 16:50:26 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8131 (0.8219) acc1: 79.6875 (79.8720) acc5: 95.3125 (95.7440) [2021-03-26 16:50:33 swin_small_patch4_window7_224] INFO: * Acc@1 80.616 Acc@5 95.490 loss 0.823 [2021-03-26 16:50:33 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.6% [2021-03-26 16:50:33 swin_small_patch4_window7_224] INFO: Max accuracy: 80.63% [2021-03-26 16:50:37 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 0/1251] eta: 1:29:32 lr: 0.000240 loss: 2.1517 (2.1517) grad_norm: 2.2357 (2.2357) time: 4.2944 [2021-03-26 16:50:43 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 10/1251] eta: 0:17:48 lr: 0.000240 loss: 3.4562 (3.1980) grad_norm: 2.0287 (2.0244) time: 0.8608 [2021-03-26 16:50:48 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 20/1251] eta: 0:14:11 lr: 0.000240 loss: 3.1900 (3.0536) grad_norm: 1.9020 (2.0063) time: 0.5114 [2021-03-26 16:50:53 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 30/1251] eta: 0:12:50 lr: 0.000240 loss: 3.0109 (3.0536) grad_norm: 1.8829 (1.9917) time: 0.5045 [2021-03-26 16:50:58 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 40/1251] eta: 0:12:09 lr: 0.000240 loss: 3.0109 (3.0348) grad_norm: 1.8765 (1.9795) time: 0.5088 [2021-03-26 16:51:03 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 50/1251] eta: 0:11:44 lr: 0.000240 loss: 3.1170 (3.0691) grad_norm: 1.9213 (1.9883) time: 0.5175 [2021-03-26 16:51:08 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 60/1251] eta: 0:11:22 lr: 0.000240 loss: 3.1812 (3.0454) grad_norm: 1.9213 (1.9898) time: 0.5116 [2021-03-26 16:51:13 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 70/1251] eta: 0:11:05 lr: 0.000240 loss: 3.2285 (3.0689) grad_norm: 1.9319 (1.9803) time: 0.5055 [2021-03-26 16:51:18 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 80/1251] eta: 0:10:52 lr: 0.000239 loss: 3.2285 (3.0657) grad_norm: 1.9400 (1.9969) time: 0.5096 [2021-03-26 16:51:23 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 90/1251] eta: 0:10:39 lr: 0.000239 loss: 3.1597 (3.0739) grad_norm: 1.9864 (1.9897) time: 0.5063 [2021-03-26 16:51:28 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 100/1251] eta: 0:10:27 lr: 0.000239 loss: 3.2953 (3.0941) grad_norm: 1.9534 (1.9877) time: 0.4975 [2021-03-26 16:51:33 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 110/1251] eta: 0:10:19 lr: 0.000239 loss: 3.3384 (3.0990) grad_norm: 1.9527 (1.9967) time: 0.5064 [2021-03-26 16:51:38 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 120/1251] eta: 0:10:10 lr: 0.000239 loss: 3.0742 (3.0743) grad_norm: 1.9232 (1.9881) time: 0.5145 [2021-03-26 16:51:43 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 130/1251] eta: 0:10:02 lr: 0.000239 loss: 2.8889 (3.0553) grad_norm: 1.9232 (1.9859) time: 0.5046 [2021-03-26 16:51:49 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 140/1251] eta: 0:09:54 lr: 0.000239 loss: 2.9244 (3.0587) grad_norm: 2.0579 (1.9949) time: 0.5055 [2021-03-26 16:51:54 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 150/1251] eta: 0:09:46 lr: 0.000239 loss: 3.2920 (3.0723) grad_norm: 2.0104 (1.9963) time: 0.5051 [2021-03-26 16:51:59 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 160/1251] eta: 0:09:39 lr: 0.000239 loss: 3.2475 (3.0666) grad_norm: 1.9639 (1.9951) time: 0.4986 [2021-03-26 16:52:04 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 170/1251] eta: 0:09:32 lr: 0.000239 loss: 3.1150 (3.0714) grad_norm: 1.9460 (2.0017) time: 0.5060 [2021-03-26 16:52:09 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 180/1251] eta: 0:09:26 lr: 0.000239 loss: 3.0851 (3.0586) grad_norm: 2.0922 (2.0086) time: 0.5137 [2021-03-26 16:52:14 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 190/1251] eta: 0:09:19 lr: 0.000239 loss: 2.9734 (3.0559) grad_norm: 1.9658 (2.0065) time: 0.5083 [2021-03-26 16:52:19 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 200/1251] eta: 0:09:13 lr: 0.000239 loss: 3.3192 (3.0733) grad_norm: 1.9446 (2.0071) time: 0.5087 [2021-03-26 16:52:24 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 210/1251] eta: 0:09:06 lr: 0.000239 loss: 3.3478 (3.0788) grad_norm: 1.9341 (2.0006) time: 0.5047 [2021-03-26 16:52:29 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 220/1251] eta: 0:09:00 lr: 0.000239 loss: 3.2823 (3.0809) grad_norm: 1.9667 (2.0161) time: 0.4978 [2021-03-26 16:52:34 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 230/1251] eta: 0:08:54 lr: 0.000239 loss: 3.2491 (3.0774) grad_norm: 1.9815 (2.0126) time: 0.4991 [2021-03-26 16:52:39 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 240/1251] eta: 0:08:48 lr: 0.000239 loss: 3.1047 (3.0762) grad_norm: 1.9483 (2.0132) time: 0.5094 [2021-03-26 16:52:44 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 250/1251] eta: 0:08:42 lr: 0.000239 loss: 3.2041 (3.0824) grad_norm: 1.9673 (2.0139) time: 0.5113 [2021-03-26 16:52:49 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 260/1251] eta: 0:08:36 lr: 0.000239 loss: 3.2035 (3.0862) grad_norm: 2.0108 (nan) time: 0.5040 [2021-03-26 16:52:54 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 270/1251] eta: 0:08:30 lr: 0.000239 loss: 3.3205 (3.0981) grad_norm: 2.1195 (nan) time: 0.5004 [2021-03-26 16:52:59 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 280/1251] eta: 0:08:24 lr: 0.000239 loss: 3.4122 (3.0903) grad_norm: 2.0087 (nan) time: 0.4984 [2021-03-26 16:53:04 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 290/1251] eta: 0:08:18 lr: 0.000239 loss: 2.8537 (3.0819) grad_norm: 1.9259 (nan) time: 0.4995 [2021-03-26 16:53:09 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 300/1251] eta: 0:08:13 lr: 0.000239 loss: 3.0112 (3.0777) grad_norm: 1.9259 (nan) time: 0.5028 [2021-03-26 16:53:14 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 310/1251] eta: 0:08:07 lr: 0.000239 loss: 3.1340 (3.0783) grad_norm: 2.0097 (nan) time: 0.5106 [2021-03-26 16:53:19 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 320/1251] eta: 0:08:02 lr: 0.000239 loss: 3.1684 (3.0824) grad_norm: 2.0552 (nan) time: 0.5089 [2021-03-26 16:53:24 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 330/1251] eta: 0:07:56 lr: 0.000239 loss: 2.9961 (3.0781) grad_norm: 1.9691 (nan) time: 0.5029 [2021-03-26 16:53:30 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 340/1251] eta: 0:07:51 lr: 0.000239 loss: 3.2090 (3.0841) grad_norm: 1.8892 (nan) time: 0.5017 [2021-03-26 16:53:35 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 350/1251] eta: 0:07:45 lr: 0.000239 loss: 3.2434 (3.0837) grad_norm: 1.8757 (nan) time: 0.5007 [2021-03-26 16:53:40 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 360/1251] eta: 0:07:40 lr: 0.000239 loss: 3.3039 (3.0868) grad_norm: 1.8810 (nan) time: 0.5015 [2021-03-26 16:53:45 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 370/1251] eta: 0:07:34 lr: 0.000238 loss: 3.3251 (3.0913) grad_norm: 1.8761 (nan) time: 0.5079 [2021-03-26 16:53:50 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 380/1251] eta: 0:07:29 lr: 0.000238 loss: 3.2129 (3.0930) grad_norm: 1.9122 (nan) time: 0.5053 [2021-03-26 16:53:55 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 390/1251] eta: 0:07:23 lr: 0.000238 loss: 3.1749 (3.0925) grad_norm: 2.0670 (nan) time: 0.5029 [2021-03-26 16:54:00 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 400/1251] eta: 0:07:18 lr: 0.000238 loss: 3.1749 (3.0908) grad_norm: 1.8956 (nan) time: 0.5068 [2021-03-26 16:54:05 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 410/1251] eta: 0:07:13 lr: 0.000238 loss: 2.9623 (3.0835) grad_norm: 1.8908 (nan) time: 0.5044 [2021-03-26 16:54:10 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 420/1251] eta: 0:07:07 lr: 0.000238 loss: 2.9623 (3.0824) grad_norm: 1.9137 (nan) time: 0.5026 [2021-03-26 16:54:15 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 430/1251] eta: 0:07:02 lr: 0.000238 loss: 3.0496 (3.0823) grad_norm: 1.9118 (nan) time: 0.5038 [2021-03-26 16:54:20 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 440/1251] eta: 0:06:57 lr: 0.000238 loss: 3.2957 (3.0831) grad_norm: 1.9285 (nan) time: 0.5041 [2021-03-26 16:54:25 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 450/1251] eta: 0:06:52 lr: 0.000238 loss: 3.1491 (3.0798) grad_norm: 2.0296 (nan) time: 0.5131 [2021-03-26 16:54:30 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 460/1251] eta: 0:06:46 lr: 0.000238 loss: 3.1751 (3.0798) grad_norm: 2.0133 (nan) time: 0.5191 [2021-03-26 16:54:35 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 470/1251] eta: 0:06:41 lr: 0.000238 loss: 3.1775 (3.0805) grad_norm: 2.0393 (nan) time: 0.5137 [2021-03-26 16:54:41 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 480/1251] eta: 0:06:36 lr: 0.000238 loss: 3.3493 (3.0866) grad_norm: 2.0118 (nan) time: 0.5097 [2021-03-26 16:54:46 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 490/1251] eta: 0:06:31 lr: 0.000238 loss: 3.3554 (3.0842) grad_norm: 1.9164 (nan) time: 0.5065 [2021-03-26 16:54:51 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 500/1251] eta: 0:06:25 lr: 0.000238 loss: 2.9600 (3.0840) grad_norm: 1.9164 (nan) time: 0.5027 [2021-03-26 16:54:56 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 510/1251] eta: 0:06:20 lr: 0.000238 loss: 2.9600 (3.0823) grad_norm: 1.9695 (nan) time: 0.5026 [2021-03-26 16:55:01 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 520/1251] eta: 0:06:15 lr: 0.000238 loss: 3.1643 (3.0825) grad_norm: 2.0658 (nan) time: 0.5059 [2021-03-26 16:55:06 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 530/1251] eta: 0:06:10 lr: 0.000238 loss: 3.2030 (3.0830) grad_norm: 2.1263 (nan) time: 0.5085 [2021-03-26 16:55:11 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 540/1251] eta: 0:06:04 lr: 0.000238 loss: 3.2032 (3.0831) grad_norm: 2.1286 (nan) time: 0.5050 [2021-03-26 16:55:16 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 550/1251] eta: 0:05:59 lr: 0.000238 loss: 3.2252 (3.0873) grad_norm: 1.9704 (nan) time: 0.5143 [2021-03-26 16:55:21 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 560/1251] eta: 0:05:54 lr: 0.000238 loss: 3.2765 (3.0920) grad_norm: 1.8660 (nan) time: 0.5161 [2021-03-26 16:55:26 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 570/1251] eta: 0:05:49 lr: 0.000238 loss: 3.2639 (3.0941) grad_norm: 1.9289 (nan) time: 0.5019 [2021-03-26 16:55:31 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 580/1251] eta: 0:05:44 lr: 0.000238 loss: 3.0688 (3.0915) grad_norm: 1.9783 (nan) time: 0.5051 [2021-03-26 16:55:36 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 590/1251] eta: 0:05:38 lr: 0.000238 loss: 2.8857 (3.0892) grad_norm: 1.9783 (nan) time: 0.5078 [2021-03-26 16:55:41 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 600/1251] eta: 0:05:33 lr: 0.000238 loss: 3.2014 (3.0919) grad_norm: 1.9563 (nan) time: 0.5089 [2021-03-26 16:55:46 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 610/1251] eta: 0:05:28 lr: 0.000238 loss: 3.2014 (3.0893) grad_norm: 1.9578 (nan) time: 0.5064 [2021-03-26 16:55:51 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 620/1251] eta: 0:05:23 lr: 0.000238 loss: 3.0152 (3.0887) grad_norm: 1.9598 (nan) time: 0.5022 [2021-03-26 16:55:57 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 630/1251] eta: 0:05:18 lr: 0.000238 loss: 3.0152 (3.0864) grad_norm: 1.9598 (nan) time: 0.5057 [2021-03-26 16:56:02 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 640/1251] eta: 0:05:12 lr: 0.000238 loss: 3.1030 (3.0868) grad_norm: 2.0904 (nan) time: 0.5052 [2021-03-26 16:56:07 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 650/1251] eta: 0:05:07 lr: 0.000237 loss: 2.9569 (3.0812) grad_norm: 2.0562 (nan) time: 0.5027 [2021-03-26 16:56:12 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 660/1251] eta: 0:05:02 lr: 0.000237 loss: 3.0431 (3.0830) grad_norm: 1.9593 (nan) time: 0.5036 [2021-03-26 16:56:17 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 670/1251] eta: 0:04:57 lr: 0.000237 loss: 3.1216 (3.0824) grad_norm: 1.9350 (nan) time: 0.5037 [2021-03-26 16:56:22 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 680/1251] eta: 0:04:52 lr: 0.000237 loss: 3.0906 (3.0847) grad_norm: 1.9350 (nan) time: 0.5024 [2021-03-26 16:56:27 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 690/1251] eta: 0:04:46 lr: 0.000237 loss: 3.1741 (3.0860) grad_norm: 1.9911 (nan) time: 0.5025 [2021-03-26 16:56:32 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 700/1251] eta: 0:04:41 lr: 0.000237 loss: 3.3485 (3.0889) grad_norm: 1.9183 (nan) time: 0.5015 [2021-03-26 16:56:37 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 710/1251] eta: 0:04:36 lr: 0.000237 loss: 3.2899 (3.0919) grad_norm: 1.9121 (nan) time: 0.5017 [2021-03-26 16:56:42 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 720/1251] eta: 0:04:31 lr: 0.000237 loss: 3.2328 (3.0893) grad_norm: 1.9181 (nan) time: 0.5088 [2021-03-26 16:56:47 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 730/1251] eta: 0:04:26 lr: 0.000237 loss: 2.9865 (3.0869) grad_norm: 1.8929 (nan) time: 0.5177 [2021-03-26 16:56:53 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 740/1251] eta: 0:04:21 lr: 0.000237 loss: 3.0651 (3.0883) grad_norm: 1.9298 (nan) time: 0.5312 [2021-03-26 16:56:58 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 750/1251] eta: 0:04:16 lr: 0.000237 loss: 3.2189 (3.0909) grad_norm: 1.9298 (nan) time: 0.5228 [2021-03-26 16:57:03 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 760/1251] eta: 0:04:11 lr: 0.000237 loss: 3.2875 (3.0912) grad_norm: 1.8823 (nan) time: 0.5096 [2021-03-26 16:57:08 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 770/1251] eta: 0:04:06 lr: 0.000237 loss: 3.1068 (3.0894) grad_norm: 1.9316 (nan) time: 0.5063 [2021-03-26 16:57:13 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 780/1251] eta: 0:04:00 lr: 0.000237 loss: 3.0900 (3.0894) grad_norm: 1.9810 (nan) time: 0.5007 [2021-03-26 16:57:18 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 790/1251] eta: 0:03:55 lr: 0.000237 loss: 3.1028 (3.0893) grad_norm: 2.0790 (nan) time: 0.5114 [2021-03-26 16:57:23 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 800/1251] eta: 0:03:50 lr: 0.000237 loss: 3.0919 (3.0867) grad_norm: 1.9265 (nan) time: 0.5120 [2021-03-26 16:57:28 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 810/1251] eta: 0:03:45 lr: 0.000237 loss: 3.0454 (3.0860) grad_norm: 1.9367 (nan) time: 0.5009 [2021-03-26 16:57:33 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 820/1251] eta: 0:03:40 lr: 0.000237 loss: 3.2026 (3.0862) grad_norm: 2.0366 (nan) time: 0.5001 [2021-03-26 16:57:38 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 830/1251] eta: 0:03:35 lr: 0.000237 loss: 3.3517 (3.0894) grad_norm: 1.9149 (nan) time: 0.5059 [2021-03-26 16:57:43 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 840/1251] eta: 0:03:30 lr: 0.000237 loss: 3.2963 (3.0892) grad_norm: 1.9228 (nan) time: 0.5090 [2021-03-26 16:57:48 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 850/1251] eta: 0:03:24 lr: 0.000237 loss: 3.1836 (3.0875) grad_norm: 1.9910 (nan) time: 0.5098 [2021-03-26 16:57:53 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 860/1251] eta: 0:03:19 lr: 0.000237 loss: 3.0153 (3.0867) grad_norm: 1.9723 (nan) time: 0.5093 [2021-03-26 16:57:58 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 870/1251] eta: 0:03:14 lr: 0.000237 loss: 2.9639 (3.0841) grad_norm: 1.9403 (nan) time: 0.5029 [2021-03-26 16:58:03 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 880/1251] eta: 0:03:09 lr: 0.000237 loss: 2.9145 (3.0818) grad_norm: 2.0188 (nan) time: 0.5015 [2021-03-26 16:58:08 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 890/1251] eta: 0:03:04 lr: 0.000237 loss: 2.9145 (3.0816) grad_norm: 2.0151 (nan) time: 0.5046 [2021-03-26 16:58:14 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 900/1251] eta: 0:02:59 lr: 0.000237 loss: 2.8652 (3.0779) grad_norm: 1.9989 (nan) time: 0.5070 [2021-03-26 16:58:19 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 910/1251] eta: 0:02:54 lr: 0.000237 loss: 2.9211 (3.0762) grad_norm: 1.9580 (nan) time: 0.5129 [2021-03-26 16:58:24 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 920/1251] eta: 0:02:49 lr: 0.000237 loss: 3.1071 (3.0766) grad_norm: 1.8783 (nan) time: 0.5138 [2021-03-26 16:58:29 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 930/1251] eta: 0:02:44 lr: 0.000237 loss: 3.2327 (3.0774) grad_norm: 1.9525 (nan) time: 0.5137 [2021-03-26 16:58:34 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 940/1251] eta: 0:02:38 lr: 0.000236 loss: 3.3154 (3.0792) grad_norm: 1.9316 (nan) time: 0.5091 [2021-03-26 16:58:39 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 950/1251] eta: 0:02:33 lr: 0.000236 loss: 3.2190 (3.0785) grad_norm: 1.8162 (nan) time: 0.5083 [2021-03-26 16:58:44 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 960/1251] eta: 0:02:28 lr: 0.000236 loss: 3.0713 (3.0771) grad_norm: 1.8580 (nan) time: 0.5098 [2021-03-26 16:58:49 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 970/1251] eta: 0:02:23 lr: 0.000236 loss: 3.0713 (3.0755) grad_norm: 1.9508 (nan) time: 0.5070 [2021-03-26 16:58:54 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 980/1251] eta: 0:02:18 lr: 0.000236 loss: 3.2017 (3.0762) grad_norm: 2.0054 (nan) time: 0.5071 [2021-03-26 16:58:59 swin_small_patch4_window7_224] INFO: Epoch: [204] [ 990/1251] eta: 0:02:13 lr: 0.000236 loss: 3.1492 (3.0744) grad_norm: 2.0328 (nan) time: 0.5047 [2021-03-26 16:59:04 swin_small_patch4_window7_224] INFO: Epoch: [204] [1000/1251] eta: 0:02:08 lr: 0.000236 loss: 3.0970 (3.0753) grad_norm: 1.9328 (nan) time: 0.5010 [2021-03-26 16:59:10 swin_small_patch4_window7_224] INFO: Epoch: [204] [1010/1251] eta: 0:02:03 lr: 0.000236 loss: 3.2860 (3.0769) grad_norm: 1.8972 (nan) time: 0.5118 [2021-03-26 16:59:15 swin_small_patch4_window7_224] INFO: Epoch: [204] [1020/1251] eta: 0:01:57 lr: 0.000236 loss: 3.2949 (3.0778) grad_norm: 1.9840 (nan) time: 0.5123 [2021-03-26 16:59:20 swin_small_patch4_window7_224] INFO: Epoch: [204] [1030/1251] eta: 0:01:52 lr: 0.000236 loss: 3.2691 (3.0788) grad_norm: 1.9966 (nan) time: 0.5040 [2021-03-26 16:59:25 swin_small_patch4_window7_224] INFO: Epoch: [204] [1040/1251] eta: 0:01:47 lr: 0.000236 loss: 3.2428 (3.0801) grad_norm: 2.0051 (nan) time: 0.5102 [2021-03-26 16:59:30 swin_small_patch4_window7_224] INFO: Epoch: [204] [1050/1251] eta: 0:01:42 lr: 0.000236 loss: 3.1524 (3.0796) grad_norm: 1.9434 (nan) time: 0.5104 [2021-03-26 16:59:35 swin_small_patch4_window7_224] INFO: Epoch: [204] [1060/1251] eta: 0:01:37 lr: 0.000236 loss: 3.1224 (3.0794) grad_norm: 1.8968 (nan) time: 0.5027 [2021-03-26 16:59:40 swin_small_patch4_window7_224] INFO: Epoch: [204] [1070/1251] eta: 0:01:32 lr: 0.000236 loss: 3.2821 (3.0807) grad_norm: 1.9929 (nan) time: 0.5029 [2021-03-26 16:59:45 swin_small_patch4_window7_224] INFO: Epoch: [204] [1080/1251] eta: 0:01:27 lr: 0.000236 loss: 3.3101 (3.0827) grad_norm: 1.9929 (nan) time: 0.5091 [2021-03-26 16:59:50 swin_small_patch4_window7_224] INFO: Epoch: [204] [1090/1251] eta: 0:01:22 lr: 0.000236 loss: 3.1755 (3.0824) grad_norm: 1.9558 (nan) time: 0.5070 [2021-03-26 16:59:55 swin_small_patch4_window7_224] INFO: Epoch: [204] [1100/1251] eta: 0:01:17 lr: 0.000236 loss: 3.1486 (3.0815) grad_norm: 2.0846 (nan) time: 0.5032 [2021-03-26 17:00:00 swin_small_patch4_window7_224] INFO: Epoch: [204] [1110/1251] eta: 0:01:11 lr: 0.000236 loss: 3.0941 (3.0816) grad_norm: 2.1451 (nan) time: 0.4992 [2021-03-26 17:00:05 swin_small_patch4_window7_224] INFO: Epoch: [204] [1120/1251] eta: 0:01:06 lr: 0.000236 loss: 3.0888 (3.0800) grad_norm: 2.0231 (nan) time: 0.4997 [2021-03-26 17:00:10 swin_small_patch4_window7_224] INFO: Epoch: [204] [1130/1251] eta: 0:01:01 lr: 0.000236 loss: 2.8667 (3.0790) grad_norm: 1.9727 (nan) time: 0.5026 [2021-03-26 17:00:15 swin_small_patch4_window7_224] INFO: Epoch: [204] [1140/1251] eta: 0:00:56 lr: 0.000236 loss: 3.0800 (3.0786) grad_norm: 2.0472 (nan) time: 0.5011 [2021-03-26 17:00:20 swin_small_patch4_window7_224] INFO: Epoch: [204] [1150/1251] eta: 0:00:51 lr: 0.000236 loss: 3.3281 (3.0797) grad_norm: 2.0199 (nan) time: 0.5043 [2021-03-26 17:00:25 swin_small_patch4_window7_224] INFO: Epoch: [204] [1160/1251] eta: 0:00:46 lr: 0.000236 loss: 3.2886 (3.0793) grad_norm: 2.0124 (nan) time: 0.5058 [2021-03-26 17:00:30 swin_small_patch4_window7_224] INFO: Epoch: [204] [1170/1251] eta: 0:00:41 lr: 0.000236 loss: 3.1930 (3.0793) grad_norm: 1.9797 (nan) time: 0.4975 [2021-03-26 17:00:35 swin_small_patch4_window7_224] INFO: Epoch: [204] [1180/1251] eta: 0:00:36 lr: 0.000236 loss: 3.2556 (3.0808) grad_norm: 1.9379 (nan) time: 0.4984 [2021-03-26 17:00:40 swin_small_patch4_window7_224] INFO: Epoch: [204] [1190/1251] eta: 0:00:31 lr: 0.000236 loss: 3.2536 (3.0796) grad_norm: 1.9266 (nan) time: 0.5034 [2021-03-26 17:00:45 swin_small_patch4_window7_224] INFO: Epoch: [204] [1200/1251] eta: 0:00:25 lr: 0.000236 loss: 3.2000 (3.0810) grad_norm: 1.8642 (nan) time: 0.5094 [2021-03-26 17:00:50 swin_small_patch4_window7_224] INFO: Epoch: [204] [1210/1251] eta: 0:00:20 lr: 0.000236 loss: 3.3433 (3.0816) grad_norm: 1.9313 (nan) time: 0.5071 [2021-03-26 17:00:55 swin_small_patch4_window7_224] INFO: Epoch: [204] [1220/1251] eta: 0:00:15 lr: 0.000236 loss: 3.3449 (3.0834) grad_norm: 1.9808 (nan) time: 0.4993 [2021-03-26 17:01:00 swin_small_patch4_window7_224] INFO: Epoch: [204] [1230/1251] eta: 0:00:10 lr: 0.000235 loss: 3.2741 (3.0833) grad_norm: 1.9213 (nan) time: 0.5008 [2021-03-26 17:01:06 swin_small_patch4_window7_224] INFO: Epoch: [204] [1240/1251] eta: 0:00:05 lr: 0.000235 loss: 2.9043 (3.0820) grad_norm: 1.9111 (nan) time: 0.5049 [2021-03-26 17:01:10 swin_small_patch4_window7_224] INFO: Epoch: [204] [1250/1251] eta: 0:00:00 lr: 0.000235 loss: 3.0474 (3.0828) grad_norm: 1.9183 (nan) time: 0.5004 [2021-03-26 17:01:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:50 loss: 1.0863 (1.0863) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-26 17:01:21 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7086 (0.8169) acc1: 79.6875 (79.5455) acc5: 95.3125 (95.4545) [2021-03-26 17:01:24 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7818 (0.8495) acc1: 79.6875 (79.7619) acc5: 95.3125 (95.3869) [2021-03-26 17:01:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7939 (0.8337) acc1: 79.6875 (79.7379) acc5: 95.3125 (95.4133) [2021-03-26 17:01:28 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8002 (0.8371) acc1: 79.6875 (79.7637) acc5: 96.8750 (95.5030) [2021-03-26 17:01:29 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8047 (0.8428) acc1: 76.5625 (79.4880) acc5: 95.3125 (95.4560) [2021-03-26 17:01:41 swin_small_patch4_window7_224] INFO: * Acc@1 80.504 Acc@5 95.470 loss 0.830 [2021-03-26 17:01:41 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.5% [2021-03-26 17:01:41 swin_small_patch4_window7_224] INFO: Max accuracy: 80.63% [2021-03-26 17:01:45 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 0/1251] eta: 1:26:57 lr: 0.000235 loss: 3.3189 (3.3189) grad_norm: 1.7244 (1.7244) time: 4.1709 [2021-03-26 17:01:50 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 10/1251] eta: 0:17:28 lr: 0.000235 loss: 3.2764 (3.2511) grad_norm: 1.8946 (1.9131) time: 0.8448 [2021-03-26 17:01:55 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 20/1251] eta: 0:14:00 lr: 0.000235 loss: 3.1670 (3.1544) grad_norm: 2.0200 (1.9942) time: 0.5087 [2021-03-26 17:02:00 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 30/1251] eta: 0:12:41 lr: 0.000235 loss: 3.2443 (3.1701) grad_norm: 2.1032 (2.0649) time: 0.5018 [2021-03-26 17:02:05 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 40/1251] eta: 0:12:04 lr: 0.000235 loss: 3.2624 (3.1493) grad_norm: 2.0140 (2.0440) time: 0.5084 [2021-03-26 17:02:10 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 50/1251] eta: 0:11:39 lr: 0.000235 loss: 3.1664 (3.0975) grad_norm: 1.9757 (2.0646) time: 0.5192 [2021-03-26 17:02:15 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 60/1251] eta: 0:11:18 lr: 0.000235 loss: 3.1446 (3.0835) grad_norm: 2.0122 (2.0537) time: 0.5124 [2021-03-26 17:02:20 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 70/1251] eta: 0:11:00 lr: 0.000235 loss: 3.3127 (3.1173) grad_norm: 1.9764 (2.0518) time: 0.4986 [2021-03-26 17:02:25 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 80/1251] eta: 0:10:46 lr: 0.000235 loss: 3.4480 (3.1573) grad_norm: 2.0080 (2.0599) time: 0.4989 [2021-03-26 17:02:30 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 90/1251] eta: 0:10:34 lr: 0.000235 loss: 3.4300 (3.1708) grad_norm: 2.0080 (2.0719) time: 0.5026 [2021-03-26 17:02:35 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 100/1251] eta: 0:10:25 lr: 0.000235 loss: 3.2252 (3.1701) grad_norm: 1.9486 (2.0684) time: 0.5057 [2021-03-26 17:02:41 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 110/1251] eta: 0:10:15 lr: 0.000235 loss: 3.0624 (3.1467) grad_norm: 2.0277 (2.0729) time: 0.5085 [2021-03-26 17:02:46 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 120/1251] eta: 0:10:08 lr: 0.000235 loss: 3.1510 (3.1480) grad_norm: 2.0865 (2.0947) time: 0.5099 [2021-03-26 17:02:51 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 130/1251] eta: 0:09:59 lr: 0.000235 loss: 3.1510 (3.1295) grad_norm: 2.0872 (2.0936) time: 0.5075 [2021-03-26 17:02:56 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 140/1251] eta: 0:09:53 lr: 0.000235 loss: 3.0615 (3.1174) grad_norm: 1.9519 (2.0891) time: 0.5147 [2021-03-26 17:03:01 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 150/1251] eta: 0:09:46 lr: 0.000235 loss: 3.0845 (3.0989) grad_norm: 2.0705 (2.0991) time: 0.5183 [2021-03-26 17:03:06 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 160/1251] eta: 0:09:38 lr: 0.000235 loss: 3.1352 (3.0995) grad_norm: 2.1015 (2.1000) time: 0.5029 [2021-03-26 17:03:11 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 170/1251] eta: 0:09:31 lr: 0.000235 loss: 3.1352 (3.0993) grad_norm: 1.9872 (2.0931) time: 0.5005 [2021-03-26 17:03:16 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 180/1251] eta: 0:09:25 lr: 0.000235 loss: 3.2244 (3.0967) grad_norm: 1.9151 (2.0805) time: 0.5086 [2021-03-26 17:03:21 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 190/1251] eta: 0:09:18 lr: 0.000235 loss: 3.2126 (3.0932) grad_norm: 1.9480 (2.0785) time: 0.5083 [2021-03-26 17:03:26 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 200/1251] eta: 0:09:13 lr: 0.000235 loss: 3.0619 (3.0932) grad_norm: 1.9728 (2.0734) time: 0.5119 [2021-03-26 17:03:32 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 210/1251] eta: 0:09:06 lr: 0.000235 loss: 3.0619 (3.0898) grad_norm: 2.0098 (2.0739) time: 0.5137 [2021-03-26 17:03:36 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 220/1251] eta: 0:09:00 lr: 0.000235 loss: 3.0979 (3.0838) grad_norm: 2.0146 (2.0701) time: 0.5006 [2021-03-26 17:03:42 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 230/1251] eta: 0:08:54 lr: 0.000235 loss: 3.0979 (3.0721) grad_norm: 1.9439 (2.0677) time: 0.5013 [2021-03-26 17:03:47 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 240/1251] eta: 0:08:48 lr: 0.000235 loss: 3.1209 (3.0688) grad_norm: 1.8907 (2.0630) time: 0.5124 [2021-03-26 17:03:52 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 250/1251] eta: 0:08:42 lr: 0.000235 loss: 3.0240 (3.0567) grad_norm: 1.9571 (2.0652) time: 0.5085 [2021-03-26 17:03:57 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 260/1251] eta: 0:08:37 lr: 0.000235 loss: 2.9166 (3.0538) grad_norm: 2.0254 (2.0657) time: 0.5048 [2021-03-26 17:04:02 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 270/1251] eta: 0:08:31 lr: 0.000234 loss: 3.1922 (3.0570) grad_norm: 1.9879 (2.0644) time: 0.5061 [2021-03-26 17:04:07 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 280/1251] eta: 0:08:25 lr: 0.000234 loss: 3.1582 (3.0546) grad_norm: 2.0395 (2.0634) time: 0.4997 [2021-03-26 17:04:12 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 290/1251] eta: 0:08:19 lr: 0.000234 loss: 3.1882 (3.0606) grad_norm: 1.9488 (2.0609) time: 0.5094 [2021-03-26 17:04:17 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 300/1251] eta: 0:08:14 lr: 0.000234 loss: 3.1696 (3.0594) grad_norm: 1.9143 (2.0553) time: 0.5150 [2021-03-26 17:04:22 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 310/1251] eta: 0:08:08 lr: 0.000234 loss: 3.0976 (3.0645) grad_norm: 1.8765 (2.0532) time: 0.5043 [2021-03-26 17:04:27 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 320/1251] eta: 0:08:02 lr: 0.000234 loss: 3.0976 (3.0678) grad_norm: 2.0076 (2.0528) time: 0.5015 [2021-03-26 17:04:32 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 330/1251] eta: 0:07:57 lr: 0.000234 loss: 3.0089 (3.0641) grad_norm: 1.9304 (2.0518) time: 0.5020 [2021-03-26 17:04:37 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 340/1251] eta: 0:07:51 lr: 0.000234 loss: 2.7488 (3.0566) grad_norm: 1.9225 (2.0500) time: 0.4994 [2021-03-26 17:04:42 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 350/1251] eta: 0:07:46 lr: 0.000234 loss: 2.6971 (3.0534) grad_norm: 1.9439 (2.0498) time: 0.5019 [2021-03-26 17:04:47 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 360/1251] eta: 0:07:40 lr: 0.000234 loss: 2.9392 (3.0536) grad_norm: 2.0506 (2.0547) time: 0.5074 [2021-03-26 17:04:52 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 370/1251] eta: 0:07:35 lr: 0.000234 loss: 3.0961 (3.0531) grad_norm: 2.0506 (2.0569) time: 0.5076 [2021-03-26 17:04:57 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 380/1251] eta: 0:07:29 lr: 0.000234 loss: 3.0223 (3.0458) grad_norm: 2.0103 (2.0705) time: 0.5045 [2021-03-26 17:05:02 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 390/1251] eta: 0:07:24 lr: 0.000234 loss: 2.9735 (3.0462) grad_norm: 2.0137 (2.0689) time: 0.5052 [2021-03-26 17:05:08 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 400/1251] eta: 0:07:18 lr: 0.000234 loss: 3.1865 (3.0455) grad_norm: 1.9759 (2.0671) time: 0.5066 [2021-03-26 17:05:13 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 410/1251] eta: 0:07:13 lr: 0.000234 loss: 3.1985 (3.0502) grad_norm: 1.8854 (2.0652) time: 0.5029 [2021-03-26 17:05:18 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 420/1251] eta: 0:07:08 lr: 0.000234 loss: 3.2006 (3.0539) grad_norm: 1.9144 (2.0633) time: 0.5082 [2021-03-26 17:05:23 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 430/1251] eta: 0:07:02 lr: 0.000234 loss: 3.3687 (3.0627) grad_norm: 1.9144 (2.0605) time: 0.5102 [2021-03-26 17:05:28 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 440/1251] eta: 0:06:57 lr: 0.000234 loss: 3.0966 (3.0554) grad_norm: 1.8701 (2.0579) time: 0.5052 [2021-03-26 17:05:33 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 450/1251] eta: 0:06:52 lr: 0.000234 loss: 3.0966 (3.0577) grad_norm: 2.0067 (2.0596) time: 0.5029 [2021-03-26 17:05:38 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 460/1251] eta: 0:06:46 lr: 0.000234 loss: 3.1403 (3.0561) grad_norm: 1.9730 (2.0573) time: 0.5004 [2021-03-26 17:05:43 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 470/1251] eta: 0:06:41 lr: 0.000234 loss: 3.1770 (3.0543) grad_norm: 1.9356 (2.0564) time: 0.4994 [2021-03-26 17:05:48 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 480/1251] eta: 0:06:36 lr: 0.000234 loss: 3.1933 (3.0578) grad_norm: 1.9641 (2.0556) time: 0.5009 [2021-03-26 17:05:53 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 490/1251] eta: 0:06:30 lr: 0.000234 loss: 3.1554 (3.0579) grad_norm: 1.9819 (2.0559) time: 0.5000 [2021-03-26 17:05:58 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 500/1251] eta: 0:06:25 lr: 0.000234 loss: 2.9962 (3.0573) grad_norm: 1.9533 (2.0538) time: 0.4983 [2021-03-26 17:06:03 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 510/1251] eta: 0:06:20 lr: 0.000234 loss: 3.2340 (3.0621) grad_norm: 1.8859 (2.0517) time: 0.5036 [2021-03-26 17:06:08 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 520/1251] eta: 0:06:14 lr: 0.000234 loss: 3.0760 (3.0610) grad_norm: 1.8821 (2.0480) time: 0.5012 [2021-03-26 17:06:13 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 530/1251] eta: 0:06:09 lr: 0.000234 loss: 3.0057 (3.0588) grad_norm: 1.9168 (2.0465) time: 0.4994 [2021-03-26 17:06:18 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 540/1251] eta: 0:06:04 lr: 0.000234 loss: 2.9001 (3.0566) grad_norm: 1.9395 (2.0505) time: 0.5089 [2021-03-26 17:06:23 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 550/1251] eta: 0:05:59 lr: 0.000233 loss: 3.2149 (3.0577) grad_norm: 1.9780 (2.0525) time: 0.5120 [2021-03-26 17:06:28 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 560/1251] eta: 0:05:54 lr: 0.000233 loss: 3.1431 (3.0594) grad_norm: 1.9788 (2.0518) time: 0.5091 [2021-03-26 17:06:33 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 570/1251] eta: 0:05:49 lr: 0.000233 loss: 2.9415 (3.0571) grad_norm: 1.8864 (2.0492) time: 0.5118 [2021-03-26 17:06:38 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 580/1251] eta: 0:05:43 lr: 0.000233 loss: 2.9362 (3.0565) grad_norm: 1.8461 (2.0463) time: 0.5090 [2021-03-26 17:06:43 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 590/1251] eta: 0:05:38 lr: 0.000233 loss: 2.9551 (3.0529) grad_norm: 1.8134 (2.0441) time: 0.5065 [2021-03-26 17:06:49 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 600/1251] eta: 0:05:33 lr: 0.000233 loss: 2.9909 (3.0539) grad_norm: 1.8740 (2.0425) time: 0.5078 [2021-03-26 17:06:54 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 610/1251] eta: 0:05:28 lr: 0.000233 loss: 2.9909 (3.0531) grad_norm: 1.9323 (2.0418) time: 0.5026 [2021-03-26 17:06:58 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 620/1251] eta: 0:05:22 lr: 0.000233 loss: 3.2722 (3.0565) grad_norm: 1.9325 (nan) time: 0.4960 [2021-03-26 17:07:04 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 630/1251] eta: 0:05:17 lr: 0.000233 loss: 3.0556 (3.0539) grad_norm: 1.9693 (nan) time: 0.5006 [2021-03-26 17:07:09 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 640/1251] eta: 0:05:12 lr: 0.000233 loss: 3.0349 (3.0550) grad_norm: 2.0239 (nan) time: 0.5076 [2021-03-26 17:07:14 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 650/1251] eta: 0:05:07 lr: 0.000233 loss: 2.9463 (3.0483) grad_norm: 1.9686 (nan) time: 0.5049 [2021-03-26 17:07:19 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 660/1251] eta: 0:05:02 lr: 0.000233 loss: 2.8893 (3.0470) grad_norm: 2.0261 (nan) time: 0.5033 [2021-03-26 17:07:24 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 670/1251] eta: 0:04:56 lr: 0.000233 loss: 2.9755 (3.0463) grad_norm: 2.0365 (nan) time: 0.5024 [2021-03-26 17:07:29 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 680/1251] eta: 0:04:51 lr: 0.000233 loss: 3.2634 (3.0483) grad_norm: 1.9127 (nan) time: 0.5034 [2021-03-26 17:07:34 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 690/1251] eta: 0:04:46 lr: 0.000233 loss: 3.1475 (3.0451) grad_norm: 1.9103 (nan) time: 0.5090 [2021-03-26 17:07:39 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 700/1251] eta: 0:04:41 lr: 0.000233 loss: 2.8949 (3.0456) grad_norm: 2.1393 (nan) time: 0.5061 [2021-03-26 17:07:44 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 710/1251] eta: 0:04:36 lr: 0.000233 loss: 3.1368 (3.0432) grad_norm: 2.0512 (nan) time: 0.5005 [2021-03-26 17:07:49 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 720/1251] eta: 0:04:31 lr: 0.000233 loss: 3.0271 (3.0427) grad_norm: 1.9415 (nan) time: 0.5023 [2021-03-26 17:07:54 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 730/1251] eta: 0:04:26 lr: 0.000233 loss: 3.1537 (3.0456) grad_norm: 1.9055 (nan) time: 0.5097 [2021-03-26 17:07:59 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 740/1251] eta: 0:04:21 lr: 0.000233 loss: 3.2665 (3.0475) grad_norm: 1.9094 (nan) time: 0.5157 [2021-03-26 17:08:04 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 750/1251] eta: 0:04:16 lr: 0.000233 loss: 3.1997 (3.0460) grad_norm: 1.9182 (nan) time: 0.5190 [2021-03-26 17:08:10 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 760/1251] eta: 0:04:10 lr: 0.000233 loss: 3.0639 (3.0468) grad_norm: 1.9395 (nan) time: 0.5209 [2021-03-26 17:08:15 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 770/1251] eta: 0:04:05 lr: 0.000233 loss: 3.0639 (3.0459) grad_norm: 2.0404 (nan) time: 0.5106 [2021-03-26 17:08:20 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 780/1251] eta: 0:04:00 lr: 0.000233 loss: 3.0408 (3.0460) grad_norm: 2.0404 (nan) time: 0.5041 [2021-03-26 17:08:25 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 790/1251] eta: 0:03:55 lr: 0.000233 loss: 3.1145 (3.0478) grad_norm: 1.9664 (nan) time: 0.5049 [2021-03-26 17:08:30 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 800/1251] eta: 0:03:50 lr: 0.000233 loss: 3.1031 (3.0461) grad_norm: 1.9664 (nan) time: 0.5103 [2021-03-26 17:08:35 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 810/1251] eta: 0:03:45 lr: 0.000233 loss: 3.0991 (3.0471) grad_norm: 2.0456 (nan) time: 0.5142 [2021-03-26 17:08:40 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 820/1251] eta: 0:03:40 lr: 0.000233 loss: 3.3032 (3.0485) grad_norm: 2.0174 (nan) time: 0.5068 [2021-03-26 17:08:45 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 830/1251] eta: 0:03:34 lr: 0.000233 loss: 3.2689 (3.0485) grad_norm: 1.9719 (nan) time: 0.5015 [2021-03-26 17:08:50 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 840/1251] eta: 0:03:29 lr: 0.000232 loss: 3.1737 (3.0491) grad_norm: 1.9719 (nan) time: 0.5039 [2021-03-26 17:08:55 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 850/1251] eta: 0:03:24 lr: 0.000232 loss: 3.2621 (3.0503) grad_norm: 2.0004 (nan) time: 0.5076 [2021-03-26 17:09:00 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 860/1251] eta: 0:03:19 lr: 0.000232 loss: 3.2402 (3.0513) grad_norm: 1.9646 (nan) time: 0.5053 [2021-03-26 17:09:05 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 870/1251] eta: 0:03:14 lr: 0.000232 loss: 3.1383 (3.0513) grad_norm: 2.0198 (nan) time: 0.5082 [2021-03-26 17:09:11 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 880/1251] eta: 0:03:09 lr: 0.000232 loss: 3.0767 (3.0490) grad_norm: 1.9935 (nan) time: 0.5168 [2021-03-26 17:09:16 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 890/1251] eta: 0:03:04 lr: 0.000232 loss: 2.9060 (3.0481) grad_norm: 1.9126 (nan) time: 0.5166 [2021-03-26 17:09:21 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 900/1251] eta: 0:02:59 lr: 0.000232 loss: 2.9060 (3.0468) grad_norm: 1.8594 (nan) time: 0.5038 [2021-03-26 17:09:26 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 910/1251] eta: 0:02:54 lr: 0.000232 loss: 2.9777 (3.0467) grad_norm: 1.8764 (nan) time: 0.5022 [2021-03-26 17:09:31 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 920/1251] eta: 0:02:48 lr: 0.000232 loss: 3.1053 (3.0476) grad_norm: 1.9753 (nan) time: 0.5031 [2021-03-26 17:09:36 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 930/1251] eta: 0:02:43 lr: 0.000232 loss: 3.1844 (3.0470) grad_norm: 1.9093 (nan) time: 0.4998 [2021-03-26 17:09:41 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 940/1251] eta: 0:02:38 lr: 0.000232 loss: 3.1809 (3.0474) grad_norm: 1.8751 (nan) time: 0.5085 [2021-03-26 17:09:46 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 950/1251] eta: 0:02:33 lr: 0.000232 loss: 3.0808 (3.0468) grad_norm: 1.8762 (nan) time: 0.5076 [2021-03-26 17:09:51 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 960/1251] eta: 0:02:28 lr: 0.000232 loss: 3.0808 (3.0474) grad_norm: 1.8784 (nan) time: 0.5012 [2021-03-26 17:09:56 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 970/1251] eta: 0:02:23 lr: 0.000232 loss: 3.1968 (3.0488) grad_norm: 2.0192 (nan) time: 0.5035 [2021-03-26 17:10:01 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 980/1251] eta: 0:02:18 lr: 0.000232 loss: 3.1413 (3.0489) grad_norm: 2.0066 (nan) time: 0.5067 [2021-03-26 17:10:06 swin_small_patch4_window7_224] INFO: Epoch: [205] [ 990/1251] eta: 0:02:13 lr: 0.000232 loss: 3.1308 (3.0466) grad_norm: 1.9643 (nan) time: 0.5060 [2021-03-26 17:10:11 swin_small_patch4_window7_224] INFO: Epoch: [205] [1000/1251] eta: 0:02:07 lr: 0.000232 loss: 2.9926 (3.0462) grad_norm: 1.8929 (nan) time: 0.5046 [2021-03-26 17:10:16 swin_small_patch4_window7_224] INFO: Epoch: [205] [1010/1251] eta: 0:02:02 lr: 0.000232 loss: 2.9926 (3.0455) grad_norm: 1.9046 (nan) time: 0.5064 [2021-03-26 17:10:21 swin_small_patch4_window7_224] INFO: Epoch: [205] [1020/1251] eta: 0:01:57 lr: 0.000232 loss: 2.9783 (3.0465) grad_norm: 2.0953 (nan) time: 0.5016 [2021-03-26 17:10:26 swin_small_patch4_window7_224] INFO: Epoch: [205] [1030/1251] eta: 0:01:52 lr: 0.000232 loss: 2.9783 (3.0455) grad_norm: 2.1359 (nan) time: 0.4947 [2021-03-26 17:10:31 swin_small_patch4_window7_224] INFO: Epoch: [205] [1040/1251] eta: 0:01:47 lr: 0.000232 loss: 2.9331 (3.0452) grad_norm: 2.1656 (nan) time: 0.5064 [2021-03-26 17:10:36 swin_small_patch4_window7_224] INFO: Epoch: [205] [1050/1251] eta: 0:01:42 lr: 0.000232 loss: 3.0378 (3.0449) grad_norm: 2.0103 (nan) time: 0.5103 [2021-03-26 17:10:41 swin_small_patch4_window7_224] INFO: Epoch: [205] [1060/1251] eta: 0:01:37 lr: 0.000232 loss: 3.2125 (3.0472) grad_norm: 1.9593 (nan) time: 0.4991 [2021-03-26 17:10:46 swin_small_patch4_window7_224] INFO: Epoch: [205] [1070/1251] eta: 0:01:32 lr: 0.000232 loss: 3.2125 (3.0491) grad_norm: 1.9609 (nan) time: 0.4984 [2021-03-26 17:10:51 swin_small_patch4_window7_224] INFO: Epoch: [205] [1080/1251] eta: 0:01:27 lr: 0.000232 loss: 3.1556 (3.0472) grad_norm: 1.9296 (nan) time: 0.5023 [2021-03-26 17:10:56 swin_small_patch4_window7_224] INFO: Epoch: [205] [1090/1251] eta: 0:01:21 lr: 0.000232 loss: 3.0491 (3.0483) grad_norm: 1.8733 (nan) time: 0.5020 [2021-03-26 17:11:02 swin_small_patch4_window7_224] INFO: Epoch: [205] [1100/1251] eta: 0:01:16 lr: 0.000232 loss: 2.9509 (3.0452) grad_norm: 1.9041 (nan) time: 0.5037 [2021-03-26 17:11:07 swin_small_patch4_window7_224] INFO: Epoch: [205] [1110/1251] eta: 0:01:11 lr: 0.000232 loss: 2.7510 (3.0446) grad_norm: 1.9157 (nan) time: 0.5111 [2021-03-26 17:11:12 swin_small_patch4_window7_224] INFO: Epoch: [205] [1120/1251] eta: 0:01:06 lr: 0.000232 loss: 3.1813 (3.0456) grad_norm: 1.8497 (nan) time: 0.5069 [2021-03-26 17:11:17 swin_small_patch4_window7_224] INFO: Epoch: [205] [1130/1251] eta: 0:01:01 lr: 0.000231 loss: 3.1813 (3.0448) grad_norm: 1.8748 (nan) time: 0.5020 [2021-03-26 17:11:22 swin_small_patch4_window7_224] INFO: Epoch: [205] [1140/1251] eta: 0:00:56 lr: 0.000231 loss: 3.1026 (3.0437) grad_norm: 1.9086 (nan) time: 0.5053 [2021-03-26 17:11:27 swin_small_patch4_window7_224] INFO: Epoch: [205] [1150/1251] eta: 0:00:51 lr: 0.000231 loss: 3.1026 (3.0427) grad_norm: 1.9646 (nan) time: 0.5040 [2021-03-26 17:11:32 swin_small_patch4_window7_224] INFO: Epoch: [205] [1160/1251] eta: 0:00:46 lr: 0.000231 loss: 3.2716 (3.0436) grad_norm: 2.0012 (nan) time: 0.5082 [2021-03-26 17:11:37 swin_small_patch4_window7_224] INFO: Epoch: [205] [1170/1251] eta: 0:00:41 lr: 0.000231 loss: 3.2168 (3.0435) grad_norm: 1.9613 (nan) time: 0.5126 [2021-03-26 17:11:42 swin_small_patch4_window7_224] INFO: Epoch: [205] [1180/1251] eta: 0:00:36 lr: 0.000231 loss: 3.1984 (3.0439) grad_norm: 2.0560 (nan) time: 0.5112 [2021-03-26 17:11:47 swin_small_patch4_window7_224] INFO: Epoch: [205] [1190/1251] eta: 0:00:31 lr: 0.000231 loss: 3.1708 (3.0434) grad_norm: 2.1176 (nan) time: 0.5044 [2021-03-26 17:11:52 swin_small_patch4_window7_224] INFO: Epoch: [205] [1200/1251] eta: 0:00:25 lr: 0.000231 loss: 3.0417 (3.0434) grad_norm: 1.9600 (nan) time: 0.4992 [2021-03-26 17:11:57 swin_small_patch4_window7_224] INFO: Epoch: [205] [1210/1251] eta: 0:00:20 lr: 0.000231 loss: 3.2536 (3.0447) grad_norm: 2.0416 (nan) time: 0.5008 [2021-03-26 17:12:02 swin_small_patch4_window7_224] INFO: Epoch: [205] [1220/1251] eta: 0:00:15 lr: 0.000231 loss: 3.3631 (3.0470) grad_norm: 2.1568 (nan) time: 0.5035 [2021-03-26 17:12:07 swin_small_patch4_window7_224] INFO: Epoch: [205] [1230/1251] eta: 0:00:10 lr: 0.000231 loss: 3.3154 (3.0479) grad_norm: 2.0834 (nan) time: 0.5035 [2021-03-26 17:12:12 swin_small_patch4_window7_224] INFO: Epoch: [205] [1240/1251] eta: 0:00:05 lr: 0.000231 loss: 3.0513 (3.0490) grad_norm: 2.0917 (nan) time: 0.4982 [2021-03-26 17:12:17 swin_small_patch4_window7_224] INFO: Epoch: [205] [1250/1251] eta: 0:00:00 lr: 0.000231 loss: 2.8373 (3.0462) grad_norm: 1.9952 (nan) time: 0.4927 [2021-03-26 17:13:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.5858 (0.5858) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-26 17:13:10 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.8082 (0.8129) acc1: 79.6875 (78.9773) acc5: 95.3125 (95.4545) [2021-03-26 17:13:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.8265 (0.8407) acc1: 79.6875 (79.3899) acc5: 95.3125 (95.2381) [2021-03-26 17:13:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8265 (0.8382) acc1: 79.6875 (79.3851) acc5: 95.3125 (95.3125) [2021-03-26 17:13:13 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8165 (0.8326) acc1: 79.6875 (79.4970) acc5: 95.3125 (95.3887) [2021-03-26 17:13:14 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8165 (0.8240) acc1: 81.2500 (80.0000) acc5: 96.8750 (95.4880) [2021-03-26 17:13:25 swin_small_patch4_window7_224] INFO: * Acc@1 80.648 Acc@5 95.616 loss 0.808 [2021-03-26 17:13:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.6% [2021-03-26 17:13:25 swin_small_patch4_window7_224] INFO: Max accuracy: 80.65% [2021-03-26 17:13:29 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 0/1251] eta: 1:26:42 lr: 0.000231 loss: 3.2546 (3.2546) grad_norm: 1.8821 (1.8821) time: 4.1588 [2021-03-26 17:13:34 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 10/1251] eta: 0:17:28 lr: 0.000231 loss: 3.0879 (3.0592) grad_norm: 1.9295 (2.1063) time: 0.8453 [2021-03-26 17:13:39 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 20/1251] eta: 0:13:54 lr: 0.000231 loss: 2.9764 (2.9588) grad_norm: 2.0251 (2.1420) time: 0.5042 [2021-03-26 17:13:44 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 30/1251] eta: 0:12:44 lr: 0.000231 loss: 3.0011 (2.9924) grad_norm: 2.0398 (2.1315) time: 0.5058 [2021-03-26 17:13:50 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 40/1251] eta: 0:12:07 lr: 0.000231 loss: 3.0683 (3.0068) grad_norm: 2.0405 (2.1124) time: 0.5196 [2021-03-26 17:13:55 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 50/1251] eta: 0:11:38 lr: 0.000231 loss: 3.1352 (2.9885) grad_norm: 2.0405 (2.0968) time: 0.5121 [2021-03-26 17:14:00 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 60/1251] eta: 0:11:17 lr: 0.000231 loss: 3.1692 (3.0078) grad_norm: 1.9739 (2.0688) time: 0.5032 [2021-03-26 17:14:05 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 70/1251] eta: 0:11:00 lr: 0.000231 loss: 3.0452 (2.9910) grad_norm: 1.9190 (2.0603) time: 0.5028 [2021-03-26 17:14:10 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 80/1251] eta: 0:10:46 lr: 0.000231 loss: 3.1527 (3.0195) grad_norm: 1.8474 (2.0338) time: 0.5000 [2021-03-26 17:14:15 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 90/1251] eta: 0:10:34 lr: 0.000231 loss: 3.1710 (3.0101) grad_norm: 1.8877 (2.0363) time: 0.4995 [2021-03-26 17:14:20 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 100/1251] eta: 0:10:24 lr: 0.000231 loss: 3.1481 (3.0282) grad_norm: 1.9767 (2.0310) time: 0.5061 [2021-03-26 17:14:25 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 110/1251] eta: 0:10:14 lr: 0.000231 loss: 3.1534 (3.0134) grad_norm: 1.9681 (2.0252) time: 0.5060 [2021-03-26 17:14:30 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 120/1251] eta: 0:10:07 lr: 0.000231 loss: 3.1534 (3.0155) grad_norm: 1.9622 (2.0198) time: 0.5062 [2021-03-26 17:14:35 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 130/1251] eta: 0:09:58 lr: 0.000231 loss: 2.9155 (2.9978) grad_norm: 1.9307 (2.0174) time: 0.5040 [2021-03-26 17:14:40 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 140/1251] eta: 0:09:50 lr: 0.000231 loss: 3.0669 (3.0092) grad_norm: 1.9401 (2.0129) time: 0.4979 [2021-03-26 17:14:45 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 150/1251] eta: 0:09:42 lr: 0.000231 loss: 3.2618 (3.0270) grad_norm: 1.9866 (2.0248) time: 0.4992 [2021-03-26 17:14:50 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 160/1251] eta: 0:09:35 lr: 0.000231 loss: 3.2887 (3.0445) grad_norm: 2.0460 (2.0234) time: 0.5030 [2021-03-26 17:14:55 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 170/1251] eta: 0:09:28 lr: 0.000230 loss: 3.2647 (3.0393) grad_norm: 2.0518 (2.0305) time: 0.5032 [2021-03-26 17:15:00 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 180/1251] eta: 0:09:22 lr: 0.000230 loss: 3.0668 (3.0435) grad_norm: 1.8890 (2.0202) time: 0.5033 [2021-03-26 17:15:05 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 190/1251] eta: 0:09:15 lr: 0.000230 loss: 3.0360 (3.0444) grad_norm: 1.8595 (2.0148) time: 0.5065 [2021-03-26 17:15:10 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 200/1251] eta: 0:09:09 lr: 0.000230 loss: 3.1300 (3.0508) grad_norm: 1.9684 (2.0153) time: 0.5028 [2021-03-26 17:15:15 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 210/1251] eta: 0:09:03 lr: 0.000230 loss: 3.2759 (3.0648) grad_norm: 2.0006 (2.0109) time: 0.5015 [2021-03-26 17:15:20 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 220/1251] eta: 0:08:57 lr: 0.000230 loss: 3.2720 (3.0664) grad_norm: 1.9803 (2.0093) time: 0.5033 [2021-03-26 17:15:25 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 230/1251] eta: 0:08:51 lr: 0.000230 loss: 3.2599 (3.0730) grad_norm: 1.9803 (2.0084) time: 0.5078 [2021-03-26 17:15:30 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 240/1251] eta: 0:08:45 lr: 0.000230 loss: 3.2599 (3.0672) grad_norm: 1.9395 (2.0056) time: 0.5042 [2021-03-26 17:15:35 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 250/1251] eta: 0:08:39 lr: 0.000230 loss: 2.8451 (3.0638) grad_norm: 1.9395 (2.0037) time: 0.5015 [2021-03-26 17:15:40 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 260/1251] eta: 0:08:33 lr: 0.000230 loss: 3.1614 (3.0632) grad_norm: 2.0453 (2.0139) time: 0.5029 [2021-03-26 17:15:45 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 270/1251] eta: 0:08:27 lr: 0.000230 loss: 3.1973 (3.0714) grad_norm: 2.0930 (2.0155) time: 0.4996 [2021-03-26 17:15:50 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 280/1251] eta: 0:08:22 lr: 0.000230 loss: 3.1743 (3.0709) grad_norm: 1.9850 (2.0137) time: 0.5065 [2021-03-26 17:15:55 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 290/1251] eta: 0:08:16 lr: 0.000230 loss: 3.0597 (3.0612) grad_norm: 1.9821 (2.0157) time: 0.5091 [2021-03-26 17:16:00 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 300/1251] eta: 0:08:11 lr: 0.000230 loss: 3.0597 (3.0573) grad_norm: 1.9778 (2.0138) time: 0.5041 [2021-03-26 17:16:05 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 310/1251] eta: 0:08:05 lr: 0.000230 loss: 3.1325 (3.0596) grad_norm: 2.0094 (2.0158) time: 0.5011 [2021-03-26 17:16:11 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 320/1251] eta: 0:08:00 lr: 0.000230 loss: 3.0861 (3.0572) grad_norm: 1.9502 (2.0117) time: 0.5078 [2021-03-26 17:16:16 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 330/1251] eta: 0:07:55 lr: 0.000230 loss: 2.9495 (3.0545) grad_norm: 1.9298 (2.0112) time: 0.5164 [2021-03-26 17:16:21 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 340/1251] eta: 0:07:49 lr: 0.000230 loss: 3.0691 (3.0554) grad_norm: 1.8855 (2.0076) time: 0.5092 [2021-03-26 17:16:26 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 350/1251] eta: 0:07:44 lr: 0.000230 loss: 2.9745 (3.0448) grad_norm: 1.9695 (2.0105) time: 0.5083 [2021-03-26 17:16:31 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 360/1251] eta: 0:07:39 lr: 0.000230 loss: 2.9763 (3.0466) grad_norm: 2.0251 (2.0111) time: 0.5127 [2021-03-26 17:16:36 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 370/1251] eta: 0:07:33 lr: 0.000230 loss: 3.2696 (3.0496) grad_norm: 1.9496 (2.0089) time: 0.5080 [2021-03-26 17:16:41 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 380/1251] eta: 0:07:28 lr: 0.000230 loss: 2.9813 (3.0402) grad_norm: 1.9884 (2.0107) time: 0.5057 [2021-03-26 17:16:46 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 390/1251] eta: 0:07:23 lr: 0.000230 loss: 3.0207 (3.0465) grad_norm: 2.0583 (2.0107) time: 0.5054 [2021-03-26 17:16:51 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 400/1251] eta: 0:07:17 lr: 0.000230 loss: 3.3368 (3.0492) grad_norm: 1.9978 (2.0140) time: 0.5040 [2021-03-26 17:16:56 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 410/1251] eta: 0:07:12 lr: 0.000230 loss: 3.1419 (3.0457) grad_norm: 2.0402 (2.0164) time: 0.5042 [2021-03-26 17:17:01 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 420/1251] eta: 0:07:07 lr: 0.000230 loss: 3.0058 (3.0424) grad_norm: 2.0663 (2.0201) time: 0.5071 [2021-03-26 17:17:06 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 430/1251] eta: 0:07:01 lr: 0.000230 loss: 2.7167 (3.0337) grad_norm: 2.0101 (2.0261) time: 0.5035 [2021-03-26 17:17:11 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 440/1251] eta: 0:06:56 lr: 0.000230 loss: 2.6248 (3.0308) grad_norm: 2.0025 (2.0256) time: 0.5029 [2021-03-26 17:17:17 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 450/1251] eta: 0:06:51 lr: 0.000230 loss: 2.9820 (3.0330) grad_norm: 1.9841 (2.0261) time: 0.5070 [2021-03-26 17:17:22 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 460/1251] eta: 0:06:45 lr: 0.000229 loss: 3.1476 (3.0380) grad_norm: 1.9337 (2.0251) time: 0.5023 [2021-03-26 17:17:27 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 470/1251] eta: 0:06:40 lr: 0.000229 loss: 3.0985 (3.0357) grad_norm: 1.9850 (2.0251) time: 0.5003 [2021-03-26 17:17:32 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 480/1251] eta: 0:06:35 lr: 0.000229 loss: 2.8599 (3.0334) grad_norm: 2.0593 (2.0349) time: 0.5078 [2021-03-26 17:17:37 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 490/1251] eta: 0:06:30 lr: 0.000229 loss: 3.1503 (3.0311) grad_norm: 2.2520 (2.0385) time: 0.5166 [2021-03-26 17:17:42 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 500/1251] eta: 0:06:25 lr: 0.000229 loss: 2.8985 (3.0269) grad_norm: 2.0953 (2.0370) time: 0.5153 [2021-03-26 17:17:47 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 510/1251] eta: 0:06:19 lr: 0.000229 loss: 2.8985 (3.0254) grad_norm: 2.0017 (2.0368) time: 0.5047 [2021-03-26 17:17:52 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 520/1251] eta: 0:06:14 lr: 0.000229 loss: 3.0681 (3.0284) grad_norm: 2.0816 (2.0430) time: 0.4991 [2021-03-26 17:17:57 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 530/1251] eta: 0:06:09 lr: 0.000229 loss: 3.0681 (3.0277) grad_norm: 2.0658 (2.0427) time: 0.5029 [2021-03-26 17:18:02 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 540/1251] eta: 0:06:04 lr: 0.000229 loss: 2.8865 (3.0257) grad_norm: 1.7903 (2.0377) time: 0.5255 [2021-03-26 17:18:08 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 550/1251] eta: 0:05:59 lr: 0.000229 loss: 3.0779 (3.0297) grad_norm: 1.7919 (2.0366) time: 0.5337 [2021-03-26 17:18:13 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 560/1251] eta: 0:05:54 lr: 0.000229 loss: 3.4204 (3.0313) grad_norm: 2.0429 (2.0396) time: 0.5115 [2021-03-26 17:18:18 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 570/1251] eta: 0:05:49 lr: 0.000229 loss: 3.1187 (3.0297) grad_norm: 2.1485 (2.0415) time: 0.5036 [2021-03-26 17:18:23 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 580/1251] eta: 0:05:44 lr: 0.000229 loss: 2.8900 (3.0274) grad_norm: 2.1143 (2.0406) time: 0.5067 [2021-03-26 17:18:28 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 590/1251] eta: 0:05:38 lr: 0.000229 loss: 3.1535 (3.0290) grad_norm: 1.9547 (2.0393) time: 0.5097 [2021-03-26 17:18:33 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 600/1251] eta: 0:05:33 lr: 0.000229 loss: 3.1919 (3.0311) grad_norm: 1.9631 (2.0412) time: 0.5137 [2021-03-26 17:18:38 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 610/1251] eta: 0:05:28 lr: 0.000229 loss: 3.1543 (3.0310) grad_norm: 1.9631 (nan) time: 0.5029 [2021-03-26 17:18:43 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 620/1251] eta: 0:05:23 lr: 0.000229 loss: 3.1806 (3.0354) grad_norm: 1.8912 (nan) time: 0.4978 [2021-03-26 17:18:48 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 630/1251] eta: 0:05:18 lr: 0.000229 loss: 3.0791 (3.0290) grad_norm: 1.8694 (nan) time: 0.5054 [2021-03-26 17:18:53 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 640/1251] eta: 0:05:12 lr: 0.000229 loss: 2.9356 (3.0294) grad_norm: 1.9151 (nan) time: 0.5026 [2021-03-26 17:18:58 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 650/1251] eta: 0:05:07 lr: 0.000229 loss: 3.1615 (3.0307) grad_norm: 1.9872 (nan) time: 0.5040 [2021-03-26 17:19:03 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 660/1251] eta: 0:05:02 lr: 0.000229 loss: 3.2155 (3.0277) grad_norm: 1.9529 (nan) time: 0.5087 [2021-03-26 17:19:08 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 670/1251] eta: 0:04:57 lr: 0.000229 loss: 3.2159 (3.0320) grad_norm: 1.9199 (nan) time: 0.5063 [2021-03-26 17:19:13 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 680/1251] eta: 0:04:52 lr: 0.000229 loss: 3.2957 (3.0336) grad_norm: 2.0142 (nan) time: 0.4980 [2021-03-26 17:19:18 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 690/1251] eta: 0:04:46 lr: 0.000229 loss: 3.1849 (3.0354) grad_norm: 2.0142 (nan) time: 0.4937 [2021-03-26 17:19:23 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 700/1251] eta: 0:04:41 lr: 0.000229 loss: 3.1601 (3.0376) grad_norm: 2.0121 (nan) time: 0.4967 [2021-03-26 17:19:28 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 710/1251] eta: 0:04:36 lr: 0.000229 loss: 3.1036 (3.0384) grad_norm: 2.0760 (nan) time: 0.5021 [2021-03-26 17:19:33 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 720/1251] eta: 0:04:31 lr: 0.000229 loss: 3.0600 (3.0343) grad_norm: 2.0240 (nan) time: 0.4997 [2021-03-26 17:19:38 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 730/1251] eta: 0:04:26 lr: 0.000229 loss: 2.8942 (3.0339) grad_norm: 1.8582 (nan) time: 0.5081 [2021-03-26 17:19:44 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 740/1251] eta: 0:04:21 lr: 0.000229 loss: 2.7618 (3.0316) grad_norm: 1.9933 (nan) time: 0.5296 [2021-03-26 17:19:49 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 750/1251] eta: 0:04:16 lr: 0.000228 loss: 2.6946 (3.0280) grad_norm: 2.0234 (nan) time: 0.5203 [2021-03-26 17:19:54 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 760/1251] eta: 0:04:10 lr: 0.000228 loss: 2.9496 (3.0299) grad_norm: 2.0234 (nan) time: 0.5065 [2021-03-26 17:19:59 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 770/1251] eta: 0:04:05 lr: 0.000228 loss: 3.0902 (3.0290) grad_norm: 2.0418 (nan) time: 0.5152 [2021-03-26 17:20:04 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 780/1251] eta: 0:04:00 lr: 0.000228 loss: 3.0456 (3.0314) grad_norm: 1.9928 (nan) time: 0.5100 [2021-03-26 17:20:09 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 790/1251] eta: 0:03:55 lr: 0.000228 loss: 3.2399 (3.0311) grad_norm: 1.9632 (nan) time: 0.5097 [2021-03-26 17:20:14 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 800/1251] eta: 0:03:50 lr: 0.000228 loss: 3.2249 (3.0324) grad_norm: 1.9390 (nan) time: 0.5084 [2021-03-26 17:20:19 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 810/1251] eta: 0:03:45 lr: 0.000228 loss: 3.0317 (3.0292) grad_norm: 1.9580 (nan) time: 0.5023 [2021-03-26 17:20:24 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 820/1251] eta: 0:03:40 lr: 0.000228 loss: 3.1170 (3.0330) grad_norm: 1.9855 (nan) time: 0.5074 [2021-03-26 17:20:30 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 830/1251] eta: 0:03:35 lr: 0.000228 loss: 3.3071 (3.0353) grad_norm: 1.9832 (nan) time: 0.5068 [2021-03-26 17:20:35 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 840/1251] eta: 0:03:29 lr: 0.000228 loss: 3.3527 (3.0383) grad_norm: 1.9338 (nan) time: 0.5090 [2021-03-26 17:20:40 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 850/1251] eta: 0:03:24 lr: 0.000228 loss: 3.2803 (3.0395) grad_norm: 1.9330 (nan) time: 0.5040 [2021-03-26 17:20:45 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 860/1251] eta: 0:03:19 lr: 0.000228 loss: 3.1934 (3.0412) grad_norm: 2.0045 (nan) time: 0.5004 [2021-03-26 17:20:50 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 870/1251] eta: 0:03:14 lr: 0.000228 loss: 3.2279 (3.0416) grad_norm: 2.0263 (nan) time: 0.5070 [2021-03-26 17:20:55 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 880/1251] eta: 0:03:09 lr: 0.000228 loss: 3.1049 (3.0425) grad_norm: 1.9774 (nan) time: 0.5087 [2021-03-26 17:21:00 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 890/1251] eta: 0:03:04 lr: 0.000228 loss: 2.9778 (3.0433) grad_norm: 1.9661 (nan) time: 0.5066 [2021-03-26 17:21:05 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 900/1251] eta: 0:02:59 lr: 0.000228 loss: 3.0999 (3.0442) grad_norm: 1.8765 (nan) time: 0.5031 [2021-03-26 17:21:10 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 910/1251] eta: 0:02:53 lr: 0.000228 loss: 3.1885 (3.0447) grad_norm: 1.9401 (nan) time: 0.4963 [2021-03-26 17:21:15 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 920/1251] eta: 0:02:48 lr: 0.000228 loss: 3.1690 (3.0448) grad_norm: 1.9712 (nan) time: 0.4995 [2021-03-26 17:21:20 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 930/1251] eta: 0:02:43 lr: 0.000228 loss: 3.1132 (3.0450) grad_norm: 1.9458 (nan) time: 0.5075 [2021-03-26 17:21:25 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 940/1251] eta: 0:02:38 lr: 0.000228 loss: 3.1397 (3.0449) grad_norm: 1.9834 (nan) time: 0.5068 [2021-03-26 17:21:30 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 950/1251] eta: 0:02:33 lr: 0.000228 loss: 3.1733 (3.0446) grad_norm: 2.0088 (nan) time: 0.5057 [2021-03-26 17:21:35 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 960/1251] eta: 0:02:28 lr: 0.000228 loss: 3.1195 (3.0451) grad_norm: 1.8994 (nan) time: 0.5063 [2021-03-26 17:21:40 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 970/1251] eta: 0:02:23 lr: 0.000228 loss: 3.1195 (3.0441) grad_norm: 1.9607 (nan) time: 0.5103 [2021-03-26 17:21:45 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 980/1251] eta: 0:02:18 lr: 0.000228 loss: 3.1113 (3.0425) grad_norm: 1.9708 (nan) time: 0.5064 [2021-03-26 17:21:50 swin_small_patch4_window7_224] INFO: Epoch: [206] [ 990/1251] eta: 0:02:13 lr: 0.000228 loss: 3.0123 (3.0408) grad_norm: 1.9808 (nan) time: 0.5008 [2021-03-26 17:21:55 swin_small_patch4_window7_224] INFO: Epoch: [206] [1000/1251] eta: 0:02:07 lr: 0.000228 loss: 3.0813 (3.0415) grad_norm: 1.9656 (nan) time: 0.5055 [2021-03-26 17:22:00 swin_small_patch4_window7_224] INFO: Epoch: [206] [1010/1251] eta: 0:02:02 lr: 0.000228 loss: 3.2081 (3.0435) grad_norm: 1.9062 (nan) time: 0.5057 [2021-03-26 17:22:06 swin_small_patch4_window7_224] INFO: Epoch: [206] [1020/1251] eta: 0:01:57 lr: 0.000228 loss: 3.1184 (3.0431) grad_norm: 1.9263 (nan) time: 0.5042 [2021-03-26 17:22:11 swin_small_patch4_window7_224] INFO: Epoch: [206] [1030/1251] eta: 0:01:52 lr: 0.000228 loss: 3.0117 (3.0447) grad_norm: 1.9967 (nan) time: 0.5085 [2021-03-26 17:22:16 swin_small_patch4_window7_224] INFO: Epoch: [206] [1040/1251] eta: 0:01:47 lr: 0.000227 loss: 3.1036 (3.0448) grad_norm: 2.0381 (nan) time: 0.5103 [2021-03-26 17:22:21 swin_small_patch4_window7_224] INFO: Epoch: [206] [1050/1251] eta: 0:01:42 lr: 0.000227 loss: 3.1906 (3.0451) grad_norm: 1.9423 (nan) time: 0.5080 [2021-03-26 17:22:26 swin_small_patch4_window7_224] INFO: Epoch: [206] [1060/1251] eta: 0:01:37 lr: 0.000227 loss: 3.2285 (3.0467) grad_norm: 1.9401 (nan) time: 0.5135 [2021-03-26 17:22:31 swin_small_patch4_window7_224] INFO: Epoch: [206] [1070/1251] eta: 0:01:32 lr: 0.000227 loss: 3.1632 (3.0463) grad_norm: 1.9215 (nan) time: 0.5146 [2021-03-26 17:22:36 swin_small_patch4_window7_224] INFO: Epoch: [206] [1080/1251] eta: 0:01:27 lr: 0.000227 loss: 3.1077 (3.0458) grad_norm: 1.8869 (nan) time: 0.5031 [2021-03-26 17:22:41 swin_small_patch4_window7_224] INFO: Epoch: [206] [1090/1251] eta: 0:01:22 lr: 0.000227 loss: 3.2898 (3.0488) grad_norm: 1.9103 (nan) time: 0.5092 [2021-03-26 17:22:46 swin_small_patch4_window7_224] INFO: Epoch: [206] [1100/1251] eta: 0:01:16 lr: 0.000227 loss: 3.3199 (3.0497) grad_norm: 1.9545 (nan) time: 0.5170 [2021-03-26 17:22:51 swin_small_patch4_window7_224] INFO: Epoch: [206] [1110/1251] eta: 0:01:11 lr: 0.000227 loss: 3.1994 (3.0482) grad_norm: 2.0348 (nan) time: 0.5070 [2021-03-26 17:22:56 swin_small_patch4_window7_224] INFO: Epoch: [206] [1120/1251] eta: 0:01:06 lr: 0.000227 loss: 3.1661 (3.0479) grad_norm: 2.0309 (nan) time: 0.5013 [2021-03-26 17:23:01 swin_small_patch4_window7_224] INFO: Epoch: [206] [1130/1251] eta: 0:01:01 lr: 0.000227 loss: 3.2738 (3.0475) grad_norm: 1.9799 (nan) time: 0.5020 [2021-03-26 17:23:06 swin_small_patch4_window7_224] INFO: Epoch: [206] [1140/1251] eta: 0:00:56 lr: 0.000227 loss: 2.6993 (3.0449) grad_norm: 2.0097 (nan) time: 0.5008 [2021-03-26 17:23:11 swin_small_patch4_window7_224] INFO: Epoch: [206] [1150/1251] eta: 0:00:51 lr: 0.000227 loss: 3.0466 (3.0461) grad_norm: 2.0089 (nan) time: 0.4969 [2021-03-26 17:23:17 swin_small_patch4_window7_224] INFO: Epoch: [206] [1160/1251] eta: 0:00:46 lr: 0.000227 loss: 3.2871 (3.0474) grad_norm: 1.9549 (nan) time: 0.5042 [2021-03-26 17:23:22 swin_small_patch4_window7_224] INFO: Epoch: [206] [1170/1251] eta: 0:00:41 lr: 0.000227 loss: 3.2833 (3.0492) grad_norm: 2.0450 (nan) time: 0.5061 [2021-03-26 17:23:27 swin_small_patch4_window7_224] INFO: Epoch: [206] [1180/1251] eta: 0:00:36 lr: 0.000227 loss: 3.2706 (3.0495) grad_norm: 1.9793 (nan) time: 0.4994 [2021-03-26 17:23:32 swin_small_patch4_window7_224] INFO: Epoch: [206] [1190/1251] eta: 0:00:31 lr: 0.000227 loss: 3.1638 (3.0496) grad_norm: 1.9257 (nan) time: 0.5012 [2021-03-26 17:23:37 swin_small_patch4_window7_224] INFO: Epoch: [206] [1200/1251] eta: 0:00:25 lr: 0.000227 loss: 3.1783 (3.0510) grad_norm: 2.0199 (nan) time: 0.5060 [2021-03-26 17:23:42 swin_small_patch4_window7_224] INFO: Epoch: [206] [1210/1251] eta: 0:00:20 lr: 0.000227 loss: 3.1858 (3.0525) grad_norm: 1.9787 (nan) time: 0.5031 [2021-03-26 17:23:47 swin_small_patch4_window7_224] INFO: Epoch: [206] [1220/1251] eta: 0:00:15 lr: 0.000227 loss: 3.0379 (3.0506) grad_norm: 1.9787 (nan) time: 0.4992 [2021-03-26 17:23:52 swin_small_patch4_window7_224] INFO: Epoch: [206] [1230/1251] eta: 0:00:10 lr: 0.000227 loss: 3.1736 (3.0523) grad_norm: 2.0716 (nan) time: 0.5088 [2021-03-26 17:23:57 swin_small_patch4_window7_224] INFO: Epoch: [206] [1240/1251] eta: 0:00:05 lr: 0.000227 loss: 3.1100 (3.0517) grad_norm: 2.0067 (nan) time: 0.5142 [2021-03-26 17:24:02 swin_small_patch4_window7_224] INFO: Epoch: [206] [1250/1251] eta: 0:00:00 lr: 0.000227 loss: 2.9789 (3.0516) grad_norm: 1.9120 (nan) time: 0.5049 [2021-03-26 17:24:11 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:11 loss: 0.6529 (0.6529) acc1: 82.8125 (82.8125) acc5: 98.4375 (98.4375) [2021-03-26 17:24:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.8344 (0.8042) acc1: 82.8125 (81.8182) acc5: 95.3125 (95.3125) [2021-03-26 17:24:15 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8344 (0.7986) acc1: 81.2500 (81.1756) acc5: 95.3125 (95.5357) [2021-03-26 17:24:18 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.8210 (0.8078) acc1: 81.2500 (80.7964) acc5: 95.3125 (95.5141) [2021-03-26 17:24:20 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8604 (0.8246) acc1: 79.6875 (80.4878) acc5: 95.3125 (95.4649) [2021-03-26 17:24:21 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8604 (0.8253) acc1: 81.2500 (80.7360) acc5: 95.3125 (95.4880) [2021-03-26 17:24:31 swin_small_patch4_window7_224] INFO: * Acc@1 80.848 Acc@5 95.620 loss 0.813 [2021-03-26 17:24:31 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.8% [2021-03-26 17:24:31 swin_small_patch4_window7_224] INFO: Max accuracy: 80.85% [2021-03-26 17:24:35 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 0/1251] eta: 1:31:21 lr: 0.000227 loss: 3.0141 (3.0141) grad_norm: 2.4155 (2.4155) time: 4.3820 [2021-03-26 17:24:40 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 10/1251] eta: 0:17:50 lr: 0.000227 loss: 3.2403 (3.1731) grad_norm: 2.1212 (2.1387) time: 0.8623 [2021-03-26 17:24:45 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 20/1251] eta: 0:14:07 lr: 0.000227 loss: 3.2122 (3.1131) grad_norm: 2.0280 (2.0657) time: 0.5036 [2021-03-26 17:24:50 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 30/1251] eta: 0:12:45 lr: 0.000227 loss: 3.0909 (3.0358) grad_norm: 1.9464 (2.0454) time: 0.4979 [2021-03-26 17:24:55 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 40/1251] eta: 0:12:05 lr: 0.000227 loss: 3.0118 (3.0626) grad_norm: 1.9464 (2.0240) time: 0.5053 [2021-03-26 17:25:00 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 50/1251] eta: 0:11:36 lr: 0.000227 loss: 2.9457 (3.0032) grad_norm: 1.9617 (2.0073) time: 0.5070 [2021-03-26 17:25:05 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 60/1251] eta: 0:11:15 lr: 0.000227 loss: 2.9317 (3.0196) grad_norm: 1.9617 (2.0012) time: 0.5015 [2021-03-26 17:25:10 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 70/1251] eta: 0:10:58 lr: 0.000227 loss: 3.0729 (2.9960) grad_norm: 1.9930 (1.9989) time: 0.5015 [2021-03-26 17:25:15 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 80/1251] eta: 0:10:46 lr: 0.000226 loss: 2.8609 (2.9742) grad_norm: 1.9930 (2.0000) time: 0.5053 [2021-03-26 17:25:20 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 90/1251] eta: 0:10:34 lr: 0.000226 loss: 3.0321 (2.9957) grad_norm: 2.0396 (2.0119) time: 0.5067 [2021-03-26 17:25:25 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 100/1251] eta: 0:10:24 lr: 0.000226 loss: 3.0321 (2.9549) grad_norm: 1.9580 (2.0184) time: 0.5041 [2021-03-26 17:25:31 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 110/1251] eta: 0:10:16 lr: 0.000226 loss: 3.0571 (2.9689) grad_norm: 1.8778 (2.0173) time: 0.5097 [2021-03-26 17:25:36 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 120/1251] eta: 0:10:07 lr: 0.000226 loss: 3.2501 (2.9749) grad_norm: 1.8861 (2.0095) time: 0.5100 [2021-03-26 17:25:41 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 130/1251] eta: 0:09:59 lr: 0.000226 loss: 3.1026 (2.9817) grad_norm: 1.9159 (2.0075) time: 0.5067 [2021-03-26 17:25:46 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 140/1251] eta: 0:09:52 lr: 0.000226 loss: 3.0246 (2.9710) grad_norm: 1.9260 (1.9992) time: 0.5114 [2021-03-26 17:25:51 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 150/1251] eta: 0:09:45 lr: 0.000226 loss: 2.8310 (2.9673) grad_norm: 1.8641 (1.9963) time: 0.5126 [2021-03-26 17:25:56 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 160/1251] eta: 0:09:38 lr: 0.000226 loss: 3.1507 (2.9784) grad_norm: 1.8898 (1.9925) time: 0.5086 [2021-03-26 17:26:01 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 170/1251] eta: 0:09:31 lr: 0.000226 loss: 3.2608 (2.9911) grad_norm: 1.8750 (1.9904) time: 0.5031 [2021-03-26 17:26:06 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 180/1251] eta: 0:09:25 lr: 0.000226 loss: 3.2291 (2.9923) grad_norm: 1.9560 (1.9878) time: 0.5078 [2021-03-26 17:26:11 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 190/1251] eta: 0:09:19 lr: 0.000226 loss: 3.2016 (2.9985) grad_norm: 1.9664 (1.9891) time: 0.5172 [2021-03-26 17:26:16 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 200/1251] eta: 0:09:13 lr: 0.000226 loss: 3.2727 (3.0165) grad_norm: 2.0267 (2.0037) time: 0.5114 [2021-03-26 17:26:21 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 210/1251] eta: 0:09:06 lr: 0.000226 loss: 3.1678 (3.0181) grad_norm: 2.0659 (2.0115) time: 0.5027 [2021-03-26 17:26:27 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 220/1251] eta: 0:09:00 lr: 0.000226 loss: 3.1612 (3.0212) grad_norm: 2.0343 (2.0192) time: 0.5036 [2021-03-26 17:26:31 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 230/1251] eta: 0:08:53 lr: 0.000226 loss: 3.1287 (3.0217) grad_norm: 2.1151 (2.0407) time: 0.5008 [2021-03-26 17:26:37 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 240/1251] eta: 0:08:48 lr: 0.000226 loss: 3.2929 (3.0292) grad_norm: 2.0628 (2.0435) time: 0.5051 [2021-03-26 17:26:42 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 250/1251] eta: 0:08:41 lr: 0.000226 loss: 3.1446 (3.0259) grad_norm: 2.0217 (2.0440) time: 0.5040 [2021-03-26 17:26:47 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 260/1251] eta: 0:08:35 lr: 0.000226 loss: 2.9177 (3.0197) grad_norm: 2.0684 (2.0534) time: 0.4951 [2021-03-26 17:26:52 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 270/1251] eta: 0:08:29 lr: 0.000226 loss: 3.1269 (3.0240) grad_norm: 2.0744 (2.0535) time: 0.4993 [2021-03-26 17:26:56 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 280/1251] eta: 0:08:23 lr: 0.000226 loss: 3.0895 (3.0228) grad_norm: 2.0744 (2.0605) time: 0.4977 [2021-03-26 17:27:02 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 290/1251] eta: 0:08:18 lr: 0.000226 loss: 3.1181 (3.0250) grad_norm: 2.1407 (2.0672) time: 0.4985 [2021-03-26 17:27:06 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 300/1251] eta: 0:08:12 lr: 0.000226 loss: 3.2671 (3.0371) grad_norm: 2.1407 (2.0666) time: 0.5001 [2021-03-26 17:27:12 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 310/1251] eta: 0:08:06 lr: 0.000226 loss: 3.2532 (3.0384) grad_norm: 1.9906 (2.0634) time: 0.5021 [2021-03-26 17:27:17 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 320/1251] eta: 0:08:01 lr: 0.000226 loss: 3.2049 (3.0410) grad_norm: 2.0165 (2.0644) time: 0.5061 [2021-03-26 17:27:22 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 330/1251] eta: 0:07:55 lr: 0.000226 loss: 2.9733 (3.0358) grad_norm: 2.1341 (2.0673) time: 0.5042 [2021-03-26 17:27:27 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 340/1251] eta: 0:07:50 lr: 0.000226 loss: 2.9398 (3.0314) grad_norm: 2.1013 (2.0681) time: 0.5063 [2021-03-26 17:27:32 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 350/1251] eta: 0:07:44 lr: 0.000226 loss: 2.8376 (3.0293) grad_norm: 2.1281 (2.0704) time: 0.5064 [2021-03-26 17:27:37 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 360/1251] eta: 0:07:39 lr: 0.000226 loss: 2.8376 (3.0266) grad_norm: 2.1867 (2.0752) time: 0.5030 [2021-03-26 17:27:42 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 370/1251] eta: 0:07:33 lr: 0.000226 loss: 3.1978 (3.0321) grad_norm: 2.0813 (2.0771) time: 0.5021 [2021-03-26 17:27:47 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 380/1251] eta: 0:07:28 lr: 0.000225 loss: 3.2674 (3.0344) grad_norm: 1.9882 (2.0725) time: 0.5038 [2021-03-26 17:27:52 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 390/1251] eta: 0:07:23 lr: 0.000225 loss: 3.1143 (3.0390) grad_norm: 1.9722 (2.0712) time: 0.5047 [2021-03-26 17:27:57 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 400/1251] eta: 0:07:17 lr: 0.000225 loss: 3.2132 (3.0402) grad_norm: 2.0851 (2.0722) time: 0.5048 [2021-03-26 17:28:02 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 410/1251] eta: 0:07:12 lr: 0.000225 loss: 3.2265 (3.0390) grad_norm: 2.0856 (2.0728) time: 0.5046 [2021-03-26 17:28:07 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 420/1251] eta: 0:07:06 lr: 0.000225 loss: 3.2054 (3.0448) grad_norm: 1.9993 (2.0715) time: 0.4993 [2021-03-26 17:28:12 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 430/1251] eta: 0:07:01 lr: 0.000225 loss: 3.3045 (3.0496) grad_norm: 1.9124 (2.0680) time: 0.5001 [2021-03-26 17:28:17 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 440/1251] eta: 0:06:56 lr: 0.000225 loss: 3.1985 (3.0483) grad_norm: 1.9124 (2.0668) time: 0.5160 [2021-03-26 17:28:22 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 450/1251] eta: 0:06:51 lr: 0.000225 loss: 3.0285 (3.0453) grad_norm: 1.9513 (2.0651) time: 0.5173 [2021-03-26 17:28:28 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 460/1251] eta: 0:06:46 lr: 0.000225 loss: 3.0285 (3.0473) grad_norm: 1.9596 (2.0610) time: 0.5106 [2021-03-26 17:28:33 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 470/1251] eta: 0:06:41 lr: 0.000225 loss: 3.0356 (3.0456) grad_norm: 1.8721 (2.0584) time: 0.5091 [2021-03-26 17:28:38 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 480/1251] eta: 0:06:35 lr: 0.000225 loss: 3.0356 (3.0468) grad_norm: 1.9207 (2.0563) time: 0.5028 [2021-03-26 17:28:43 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 490/1251] eta: 0:06:30 lr: 0.000225 loss: 3.0149 (3.0457) grad_norm: 1.9844 (2.0578) time: 0.5012 [2021-03-26 17:28:48 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 500/1251] eta: 0:06:25 lr: 0.000225 loss: 3.0369 (3.0471) grad_norm: 1.9858 (2.0559) time: 0.5020 [2021-03-26 17:28:53 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 510/1251] eta: 0:06:19 lr: 0.000225 loss: 3.0369 (3.0489) grad_norm: 1.9858 (2.0553) time: 0.4996 [2021-03-26 17:28:58 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 520/1251] eta: 0:06:14 lr: 0.000225 loss: 2.9762 (3.0479) grad_norm: 2.0239 (2.0555) time: 0.4984 [2021-03-26 17:29:03 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 530/1251] eta: 0:06:09 lr: 0.000225 loss: 3.0819 (3.0459) grad_norm: 2.0629 (2.0562) time: 0.4991 [2021-03-26 17:29:08 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 540/1251] eta: 0:06:03 lr: 0.000225 loss: 3.0457 (3.0453) grad_norm: 1.9866 (2.0546) time: 0.5040 [2021-03-26 17:29:13 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 550/1251] eta: 0:05:59 lr: 0.000225 loss: 2.9318 (3.0437) grad_norm: 1.9001 (2.0522) time: 0.5170 [2021-03-26 17:29:18 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 560/1251] eta: 0:05:53 lr: 0.000225 loss: 2.9257 (3.0436) grad_norm: 1.8757 (2.0490) time: 0.5184 [2021-03-26 17:29:23 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 570/1251] eta: 0:05:48 lr: 0.000225 loss: 2.8371 (3.0399) grad_norm: 1.9399 (2.0470) time: 0.5035 [2021-03-26 17:29:28 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 580/1251] eta: 0:05:43 lr: 0.000225 loss: 3.0760 (3.0404) grad_norm: 1.9411 (2.0455) time: 0.4984 [2021-03-26 17:29:33 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 590/1251] eta: 0:05:38 lr: 0.000225 loss: 3.0679 (3.0388) grad_norm: 1.9188 (2.0444) time: 0.5027 [2021-03-26 17:29:38 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 600/1251] eta: 0:05:32 lr: 0.000225 loss: 3.0417 (3.0367) grad_norm: 1.8901 (2.0427) time: 0.4994 [2021-03-26 17:29:43 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 610/1251] eta: 0:05:27 lr: 0.000225 loss: 3.2096 (3.0412) grad_norm: 1.8901 (2.0411) time: 0.4983 [2021-03-26 17:29:48 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 620/1251] eta: 0:05:22 lr: 0.000225 loss: 3.1789 (3.0400) grad_norm: 1.9761 (2.0431) time: 0.5016 [2021-03-26 17:29:53 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 630/1251] eta: 0:05:17 lr: 0.000225 loss: 2.9788 (3.0400) grad_norm: 1.9893 (2.0428) time: 0.5026 [2021-03-26 17:29:58 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 640/1251] eta: 0:05:12 lr: 0.000225 loss: 3.0118 (3.0391) grad_norm: 2.0232 (2.0433) time: 0.5035 [2021-03-26 17:30:03 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 650/1251] eta: 0:05:06 lr: 0.000225 loss: 3.0496 (3.0375) grad_norm: 2.0049 (2.0476) time: 0.5081 [2021-03-26 17:30:08 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 660/1251] eta: 0:05:01 lr: 0.000225 loss: 2.7426 (3.0331) grad_norm: 1.9456 (2.0475) time: 0.5105 [2021-03-26 17:30:13 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 670/1251] eta: 0:04:56 lr: 0.000224 loss: 2.9180 (3.0326) grad_norm: 1.9328 (2.0458) time: 0.4993 [2021-03-26 17:30:18 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 680/1251] eta: 0:04:51 lr: 0.000224 loss: 2.9435 (3.0308) grad_norm: 1.9824 (2.0483) time: 0.4977 [2021-03-26 17:30:23 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 690/1251] eta: 0:04:46 lr: 0.000224 loss: 3.1180 (3.0291) grad_norm: 2.0212 (2.0517) time: 0.5061 [2021-03-26 17:30:28 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 700/1251] eta: 0:04:41 lr: 0.000224 loss: 3.1438 (3.0319) grad_norm: 2.0950 (2.0520) time: 0.5048 [2021-03-26 17:30:33 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 710/1251] eta: 0:04:35 lr: 0.000224 loss: 3.2957 (3.0329) grad_norm: 1.9643 (2.0512) time: 0.5054 [2021-03-26 17:30:39 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 720/1251] eta: 0:04:30 lr: 0.000224 loss: 3.1612 (3.0326) grad_norm: 1.9643 (2.0506) time: 0.5086 [2021-03-26 17:30:44 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 730/1251] eta: 0:04:25 lr: 0.000224 loss: 3.0804 (3.0307) grad_norm: 2.0074 (2.0507) time: 0.5204 [2021-03-26 17:30:49 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 740/1251] eta: 0:04:20 lr: 0.000224 loss: 3.0794 (3.0315) grad_norm: 1.9428 (2.0492) time: 0.5296 [2021-03-26 17:30:54 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 750/1251] eta: 0:04:15 lr: 0.000224 loss: 2.9530 (3.0271) grad_norm: 1.9735 (2.0549) time: 0.5202 [2021-03-26 17:30:59 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 760/1251] eta: 0:04:10 lr: 0.000224 loss: 3.0239 (3.0286) grad_norm: 1.9873 (2.0544) time: 0.5116 [2021-03-26 17:31:04 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 770/1251] eta: 0:04:05 lr: 0.000224 loss: 3.1030 (3.0306) grad_norm: 1.9209 (2.0535) time: 0.5045 [2021-03-26 17:31:09 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 780/1251] eta: 0:04:00 lr: 0.000224 loss: 3.2263 (3.0326) grad_norm: 1.9663 (2.0529) time: 0.5012 [2021-03-26 17:31:14 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 790/1251] eta: 0:03:55 lr: 0.000224 loss: 3.1156 (3.0323) grad_norm: 1.9663 (2.0514) time: 0.5019 [2021-03-26 17:31:19 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 800/1251] eta: 0:03:50 lr: 0.000224 loss: 2.9413 (3.0316) grad_norm: 1.9332 (2.0508) time: 0.5004 [2021-03-26 17:31:24 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 810/1251] eta: 0:03:44 lr: 0.000224 loss: 3.2724 (3.0344) grad_norm: 2.0541 (2.0538) time: 0.5000 [2021-03-26 17:31:29 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 820/1251] eta: 0:03:39 lr: 0.000224 loss: 3.2724 (3.0370) grad_norm: 2.1089 (2.0541) time: 0.5011 [2021-03-26 17:31:35 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 830/1251] eta: 0:03:34 lr: 0.000224 loss: 3.0833 (3.0352) grad_norm: 2.0542 (2.0550) time: 0.5033 [2021-03-26 17:31:40 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 840/1251] eta: 0:03:29 lr: 0.000224 loss: 2.9588 (3.0329) grad_norm: 2.0181 (2.0538) time: 0.5064 [2021-03-26 17:31:45 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 850/1251] eta: 0:03:24 lr: 0.000224 loss: 3.0135 (3.0327) grad_norm: 2.0181 (2.0537) time: 0.5032 [2021-03-26 17:31:50 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 860/1251] eta: 0:03:19 lr: 0.000224 loss: 3.1185 (3.0333) grad_norm: 1.8980 (2.0536) time: 0.5036 [2021-03-26 17:31:55 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 870/1251] eta: 0:03:14 lr: 0.000224 loss: 3.0226 (3.0300) grad_norm: 2.0014 (2.0558) time: 0.5057 [2021-03-26 17:32:00 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 880/1251] eta: 0:03:09 lr: 0.000224 loss: 3.0597 (3.0316) grad_norm: 2.0830 (2.0553) time: 0.5072 [2021-03-26 17:32:05 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 890/1251] eta: 0:03:03 lr: 0.000224 loss: 3.1060 (3.0303) grad_norm: 1.9594 (2.0551) time: 0.5069 [2021-03-26 17:32:10 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 900/1251] eta: 0:02:58 lr: 0.000224 loss: 3.1043 (3.0294) grad_norm: 1.9494 (2.0548) time: 0.5066 [2021-03-26 17:32:15 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 910/1251] eta: 0:02:53 lr: 0.000224 loss: 3.1640 (3.0309) grad_norm: 1.9233 (2.0535) time: 0.5053 [2021-03-26 17:32:20 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 920/1251] eta: 0:02:48 lr: 0.000224 loss: 3.3139 (3.0338) grad_norm: 1.9159 (2.0526) time: 0.5059 [2021-03-26 17:32:25 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 930/1251] eta: 0:02:43 lr: 0.000224 loss: 3.3033 (3.0352) grad_norm: 2.0080 (2.0533) time: 0.5155 [2021-03-26 17:32:30 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 940/1251] eta: 0:02:38 lr: 0.000224 loss: 3.1034 (3.0351) grad_norm: 2.0010 (2.0530) time: 0.5129 [2021-03-26 17:32:35 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 950/1251] eta: 0:02:33 lr: 0.000224 loss: 2.9154 (3.0345) grad_norm: 2.0793 (2.0551) time: 0.5070 [2021-03-26 17:32:40 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 960/1251] eta: 0:02:28 lr: 0.000223 loss: 3.1541 (3.0368) grad_norm: 2.1861 (2.0559) time: 0.5036 [2021-03-26 17:32:45 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 970/1251] eta: 0:02:23 lr: 0.000223 loss: 3.1765 (3.0360) grad_norm: 2.1509 (2.0568) time: 0.5010 [2021-03-26 17:32:50 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 980/1251] eta: 0:02:18 lr: 0.000223 loss: 3.0053 (3.0353) grad_norm: 2.0933 (2.0664) time: 0.5033 [2021-03-26 17:32:56 swin_small_patch4_window7_224] INFO: Epoch: [207] [ 990/1251] eta: 0:02:12 lr: 0.000223 loss: 3.1847 (3.0380) grad_norm: 2.0970 (2.0669) time: 0.5101 [2021-03-26 17:33:01 swin_small_patch4_window7_224] INFO: Epoch: [207] [1000/1251] eta: 0:02:07 lr: 0.000223 loss: 3.1847 (3.0377) grad_norm: 1.9569 (2.0657) time: 0.5106 [2021-03-26 17:33:06 swin_small_patch4_window7_224] INFO: Epoch: [207] [1010/1251] eta: 0:02:02 lr: 0.000223 loss: 3.0773 (3.0386) grad_norm: 2.0500 (2.0672) time: 0.5054 [2021-03-26 17:33:11 swin_small_patch4_window7_224] INFO: Epoch: [207] [1020/1251] eta: 0:01:57 lr: 0.000223 loss: 3.1647 (3.0386) grad_norm: 2.0985 (2.0665) time: 0.5055 [2021-03-26 17:33:16 swin_small_patch4_window7_224] INFO: Epoch: [207] [1030/1251] eta: 0:01:52 lr: 0.000223 loss: 3.1320 (3.0386) grad_norm: 1.9046 (2.0659) time: 0.5028 [2021-03-26 17:33:21 swin_small_patch4_window7_224] INFO: Epoch: [207] [1040/1251] eta: 0:01:47 lr: 0.000223 loss: 3.1320 (3.0379) grad_norm: 1.9920 (2.0667) time: 0.5024 [2021-03-26 17:33:26 swin_small_patch4_window7_224] INFO: Epoch: [207] [1050/1251] eta: 0:01:42 lr: 0.000223 loss: 3.1734 (3.0378) grad_norm: 2.0918 (2.0674) time: 0.5105 [2021-03-26 17:33:31 swin_small_patch4_window7_224] INFO: Epoch: [207] [1060/1251] eta: 0:01:37 lr: 0.000223 loss: 3.0155 (3.0380) grad_norm: 2.0874 (2.0671) time: 0.5040 [2021-03-26 17:33:36 swin_small_patch4_window7_224] INFO: Epoch: [207] [1070/1251] eta: 0:01:32 lr: 0.000223 loss: 3.2997 (3.0415) grad_norm: 2.0711 (2.0677) time: 0.5055 [2021-03-26 17:33:41 swin_small_patch4_window7_224] INFO: Epoch: [207] [1080/1251] eta: 0:01:27 lr: 0.000223 loss: 3.3823 (3.0445) grad_norm: 1.8751 (2.0663) time: 0.5050 [2021-03-26 17:33:46 swin_small_patch4_window7_224] INFO: Epoch: [207] [1090/1251] eta: 0:01:21 lr: 0.000223 loss: 3.3064 (3.0445) grad_norm: 1.9256 (2.0659) time: 0.5014 [2021-03-26 17:33:51 swin_small_patch4_window7_224] INFO: Epoch: [207] [1100/1251] eta: 0:01:16 lr: 0.000223 loss: 3.2683 (3.0460) grad_norm: 2.0483 (2.0679) time: 0.5059 [2021-03-26 17:33:56 swin_small_patch4_window7_224] INFO: Epoch: [207] [1110/1251] eta: 0:01:11 lr: 0.000223 loss: 3.1911 (3.0469) grad_norm: 2.0663 (2.0679) time: 0.5008 [2021-03-26 17:34:01 swin_small_patch4_window7_224] INFO: Epoch: [207] [1120/1251] eta: 0:01:06 lr: 0.000223 loss: 3.0047 (3.0458) grad_norm: 1.9957 (2.0669) time: 0.5031 [2021-03-26 17:34:06 swin_small_patch4_window7_224] INFO: Epoch: [207] [1130/1251] eta: 0:01:01 lr: 0.000223 loss: 2.8811 (3.0448) grad_norm: 1.9463 (2.0661) time: 0.5007 [2021-03-26 17:34:11 swin_small_patch4_window7_224] INFO: Epoch: [207] [1140/1251] eta: 0:00:56 lr: 0.000223 loss: 2.7785 (3.0425) grad_norm: 1.9479 (2.0660) time: 0.4987 [2021-03-26 17:34:16 swin_small_patch4_window7_224] INFO: Epoch: [207] [1150/1251] eta: 0:00:51 lr: 0.000223 loss: 2.8270 (3.0413) grad_norm: 1.9700 (2.0651) time: 0.5031 [2021-03-26 17:34:21 swin_small_patch4_window7_224] INFO: Epoch: [207] [1160/1251] eta: 0:00:46 lr: 0.000223 loss: 2.9453 (3.0414) grad_norm: 1.9403 (2.0641) time: 0.5023 [2021-03-26 17:34:26 swin_small_patch4_window7_224] INFO: Epoch: [207] [1170/1251] eta: 0:00:41 lr: 0.000223 loss: 3.1579 (3.0422) grad_norm: 1.8792 (2.0633) time: 0.5008 [2021-03-26 17:34:31 swin_small_patch4_window7_224] INFO: Epoch: [207] [1180/1251] eta: 0:00:36 lr: 0.000223 loss: 3.1579 (3.0424) grad_norm: 1.9784 (2.0636) time: 0.5068 [2021-03-26 17:34:36 swin_small_patch4_window7_224] INFO: Epoch: [207] [1190/1251] eta: 0:00:31 lr: 0.000223 loss: 3.1883 (3.0438) grad_norm: 2.0252 (2.0630) time: 0.5056 [2021-03-26 17:34:41 swin_small_patch4_window7_224] INFO: Epoch: [207] [1200/1251] eta: 0:00:25 lr: 0.000223 loss: 3.1617 (3.0430) grad_norm: 2.0272 (2.0633) time: 0.5044 [2021-03-26 17:34:47 swin_small_patch4_window7_224] INFO: Epoch: [207] [1210/1251] eta: 0:00:20 lr: 0.000223 loss: 3.1539 (3.0435) grad_norm: 2.0447 (2.0634) time: 0.5083 [2021-03-26 17:34:52 swin_small_patch4_window7_224] INFO: Epoch: [207] [1220/1251] eta: 0:00:15 lr: 0.000223 loss: 3.1539 (3.0426) grad_norm: 1.9523 (2.0628) time: 0.5051 [2021-03-26 17:34:57 swin_small_patch4_window7_224] INFO: Epoch: [207] [1230/1251] eta: 0:00:10 lr: 0.000223 loss: 2.9449 (3.0416) grad_norm: 1.9523 (2.0629) time: 0.5055 [2021-03-26 17:35:02 swin_small_patch4_window7_224] INFO: Epoch: [207] [1240/1251] eta: 0:00:05 lr: 0.000223 loss: 2.9369 (3.0406) grad_norm: 1.9488 (2.0624) time: 0.5032 [2021-03-26 17:35:07 swin_small_patch4_window7_224] INFO: Epoch: [207] [1250/1251] eta: 0:00:00 lr: 0.000223 loss: 2.9644 (3.0416) grad_norm: 2.0036 (2.0625) time: 0.5009 [2021-03-26 17:35:15 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:37 loss: 0.5984 (0.5984) acc1: 81.2500 (81.2500) acc5: 100.0000 (100.0000) [2021-03-26 17:35:17 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.8191 (0.7756) acc1: 81.2500 (79.6875) acc5: 96.8750 (96.8750) [2021-03-26 17:35:19 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7407 (0.7461) acc1: 81.2500 (80.8780) acc5: 96.8750 (96.8750) [2021-03-26 17:35:21 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.7435 (0.7909) acc1: 79.6875 (80.2923) acc5: 95.3125 (96.2198) [2021-03-26 17:35:23 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8683 (0.8163) acc1: 76.5625 (79.8018) acc5: 95.3125 (96.0747) [2021-03-26 17:35:24 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8351 (0.8144) acc1: 79.6875 (80.2880) acc5: 95.3125 (95.8720) [2021-03-26 17:35:38 swin_small_patch4_window7_224] INFO: * Acc@1 80.788 Acc@5 95.590 loss 0.810 [2021-03-26 17:35:38 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.8% [2021-03-26 17:35:38 swin_small_patch4_window7_224] INFO: Max accuracy: 80.85% [2021-03-26 17:35:42 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 0/1251] eta: 1:25:11 lr: 0.000222 loss: 3.6064 (3.6064) grad_norm: 1.8044 (1.8044) time: 4.0859 [2021-03-26 17:35:47 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 10/1251] eta: 0:17:37 lr: 0.000222 loss: 3.2065 (3.2121) grad_norm: 1.9817 (1.9384) time: 0.8522 [2021-03-26 17:35:52 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 20/1251] eta: 0:14:04 lr: 0.000222 loss: 2.9250 (3.0287) grad_norm: 1.9610 (1.9400) time: 0.5157 [2021-03-26 17:35:57 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 30/1251] eta: 0:12:53 lr: 0.000222 loss: 2.7612 (2.9838) grad_norm: 1.9143 (1.9507) time: 0.5127 [2021-03-26 17:36:02 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 40/1251] eta: 0:12:08 lr: 0.000222 loss: 3.1547 (2.9790) grad_norm: 2.0246 (1.9502) time: 0.5136 [2021-03-26 17:36:08 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 50/1251] eta: 0:11:41 lr: 0.000222 loss: 3.1311 (2.9948) grad_norm: 1.8759 (1.9451) time: 0.5086 [2021-03-26 17:36:13 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 60/1251] eta: 0:11:19 lr: 0.000222 loss: 3.1311 (3.0136) grad_norm: 1.8759 (1.9529) time: 0.5073 [2021-03-26 17:36:18 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 70/1251] eta: 0:11:04 lr: 0.000222 loss: 3.2191 (3.0463) grad_norm: 1.9825 (1.9758) time: 0.5060 [2021-03-26 17:36:23 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 80/1251] eta: 0:10:49 lr: 0.000222 loss: 3.2575 (3.0666) grad_norm: 2.0943 (1.9939) time: 0.5037 [2021-03-26 17:36:28 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 90/1251] eta: 0:10:36 lr: 0.000222 loss: 3.1815 (3.0251) grad_norm: 2.0525 (2.0076) time: 0.4974 [2021-03-26 17:36:33 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 100/1251] eta: 0:10:26 lr: 0.000222 loss: 3.0902 (3.0364) grad_norm: 2.0882 (2.0287) time: 0.5056 [2021-03-26 17:36:38 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 110/1251] eta: 0:10:18 lr: 0.000222 loss: 3.2341 (3.0301) grad_norm: 2.1558 (2.0333) time: 0.5139 [2021-03-26 17:36:43 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 120/1251] eta: 0:10:09 lr: 0.000222 loss: 3.1076 (3.0283) grad_norm: 2.0336 (2.0323) time: 0.5099 [2021-03-26 17:36:48 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 130/1251] eta: 0:10:01 lr: 0.000222 loss: 3.0052 (3.0220) grad_norm: 2.0336 (2.0361) time: 0.5089 [2021-03-26 17:36:53 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 140/1251] eta: 0:09:53 lr: 0.000222 loss: 3.1024 (3.0349) grad_norm: 2.0198 (2.0324) time: 0.5091 [2021-03-26 17:36:58 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 150/1251] eta: 0:09:46 lr: 0.000222 loss: 3.0871 (3.0247) grad_norm: 1.9719 (2.0278) time: 0.5051 [2021-03-26 17:37:03 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 160/1251] eta: 0:09:39 lr: 0.000222 loss: 3.0871 (3.0354) grad_norm: 1.9960 (2.0317) time: 0.5042 [2021-03-26 17:37:08 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 170/1251] eta: 0:09:32 lr: 0.000222 loss: 3.2402 (3.0385) grad_norm: 2.0254 (2.0287) time: 0.5052 [2021-03-26 17:37:13 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 180/1251] eta: 0:09:25 lr: 0.000222 loss: 3.0572 (3.0397) grad_norm: 2.0100 (2.0307) time: 0.5073 [2021-03-26 17:37:18 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 190/1251] eta: 0:09:19 lr: 0.000222 loss: 3.0874 (3.0341) grad_norm: 2.1123 (2.0402) time: 0.5068 [2021-03-26 17:37:24 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 200/1251] eta: 0:09:13 lr: 0.000222 loss: 3.2126 (3.0316) grad_norm: 2.0616 (2.0378) time: 0.5120 [2021-03-26 17:37:29 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 210/1251] eta: 0:09:06 lr: 0.000222 loss: 3.1696 (3.0256) grad_norm: 1.9164 (2.0406) time: 0.5069 [2021-03-26 17:37:34 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 220/1251] eta: 0:09:00 lr: 0.000222 loss: 3.0941 (3.0262) grad_norm: 1.9767 (2.0357) time: 0.4978 [2021-03-26 17:37:39 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 230/1251] eta: 0:08:54 lr: 0.000222 loss: 3.0911 (3.0224) grad_norm: 1.8220 (2.0295) time: 0.5027 [2021-03-26 17:37:44 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 240/1251] eta: 0:08:48 lr: 0.000222 loss: 3.2181 (3.0241) grad_norm: 1.8450 (2.0265) time: 0.5074 [2021-03-26 17:37:49 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 250/1251] eta: 0:08:42 lr: 0.000222 loss: 2.9113 (3.0080) grad_norm: 1.8797 (2.0252) time: 0.5043 [2021-03-26 17:37:54 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 260/1251] eta: 0:08:36 lr: 0.000222 loss: 2.8692 (3.0072) grad_norm: 1.9862 (2.0331) time: 0.5065 [2021-03-26 17:37:59 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 270/1251] eta: 0:08:30 lr: 0.000222 loss: 3.0522 (3.0111) grad_norm: 2.0393 (2.0356) time: 0.5055 [2021-03-26 17:38:04 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 280/1251] eta: 0:08:24 lr: 0.000222 loss: 3.1376 (3.0099) grad_norm: 2.0792 (2.0386) time: 0.5026 [2021-03-26 17:38:09 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 290/1251] eta: 0:08:19 lr: 0.000222 loss: 3.1672 (3.0122) grad_norm: 2.0820 (2.0625) time: 0.5085 [2021-03-26 17:38:14 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 300/1251] eta: 0:08:13 lr: 0.000221 loss: 3.3116 (3.0164) grad_norm: 2.0121 (2.0669) time: 0.5095 [2021-03-26 17:38:19 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 310/1251] eta: 0:08:08 lr: 0.000221 loss: 3.2344 (3.0188) grad_norm: 1.9443 (2.0676) time: 0.5124 [2021-03-26 17:38:24 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 320/1251] eta: 0:08:03 lr: 0.000221 loss: 3.1807 (3.0235) grad_norm: 1.9527 (2.0652) time: 0.5112 [2021-03-26 17:38:29 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 330/1251] eta: 0:07:57 lr: 0.000221 loss: 3.1642 (3.0270) grad_norm: 1.9725 (2.0651) time: 0.5050 [2021-03-26 17:38:34 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 340/1251] eta: 0:07:51 lr: 0.000221 loss: 3.0687 (3.0262) grad_norm: 2.0373 (2.0704) time: 0.5009 [2021-03-26 17:38:39 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 350/1251] eta: 0:07:45 lr: 0.000221 loss: 3.2573 (3.0340) grad_norm: 2.0437 (2.0698) time: 0.4979 [2021-03-26 17:38:44 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 360/1251] eta: 0:07:40 lr: 0.000221 loss: 3.1887 (3.0276) grad_norm: 1.9110 (2.0660) time: 0.5049 [2021-03-26 17:38:50 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 370/1251] eta: 0:07:35 lr: 0.000221 loss: 2.8063 (3.0206) grad_norm: 1.9883 (2.0698) time: 0.5124 [2021-03-26 17:38:55 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 380/1251] eta: 0:07:29 lr: 0.000221 loss: 3.1188 (3.0291) grad_norm: 2.1203 (2.0709) time: 0.5049 [2021-03-26 17:39:00 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 390/1251] eta: 0:07:24 lr: 0.000221 loss: 3.2374 (3.0268) grad_norm: 2.0384 (2.0675) time: 0.5009 [2021-03-26 17:39:05 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 400/1251] eta: 0:07:18 lr: 0.000221 loss: 3.1192 (3.0245) grad_norm: 1.9508 (2.0675) time: 0.5013 [2021-03-26 17:39:10 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 410/1251] eta: 0:07:13 lr: 0.000221 loss: 3.1117 (3.0242) grad_norm: 1.9419 (2.0655) time: 0.5008 [2021-03-26 17:39:15 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 420/1251] eta: 0:07:08 lr: 0.000221 loss: 3.1117 (3.0257) grad_norm: 1.9419 (2.0637) time: 0.5020 [2021-03-26 17:39:20 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 430/1251] eta: 0:07:02 lr: 0.000221 loss: 3.2150 (3.0270) grad_norm: 1.9243 (2.0623) time: 0.5075 [2021-03-26 17:39:25 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 440/1251] eta: 0:06:57 lr: 0.000221 loss: 3.1688 (3.0269) grad_norm: 1.9909 (2.0616) time: 0.5106 [2021-03-26 17:39:30 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 450/1251] eta: 0:06:52 lr: 0.000221 loss: 3.0850 (3.0279) grad_norm: 1.9939 (2.0617) time: 0.5085 [2021-03-26 17:39:35 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 460/1251] eta: 0:06:46 lr: 0.000221 loss: 3.1882 (3.0292) grad_norm: 1.9562 (2.0580) time: 0.5076 [2021-03-26 17:39:40 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 470/1251] eta: 0:06:41 lr: 0.000221 loss: 3.2137 (3.0300) grad_norm: 1.8993 (2.0575) time: 0.5023 [2021-03-26 17:39:45 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 480/1251] eta: 0:06:36 lr: 0.000221 loss: 3.1000 (3.0297) grad_norm: 1.9797 (2.0557) time: 0.5011 [2021-03-26 17:39:50 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 490/1251] eta: 0:06:31 lr: 0.000221 loss: 3.1000 (3.0304) grad_norm: 1.9864 (2.0560) time: 0.5054 [2021-03-26 17:39:55 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 500/1251] eta: 0:06:25 lr: 0.000221 loss: 3.0789 (3.0312) grad_norm: 1.9927 (2.0562) time: 0.5031 [2021-03-26 17:40:00 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 510/1251] eta: 0:06:20 lr: 0.000221 loss: 3.0789 (3.0334) grad_norm: 1.9805 (2.0534) time: 0.5035 [2021-03-26 17:40:05 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 520/1251] eta: 0:06:15 lr: 0.000221 loss: 3.2590 (3.0345) grad_norm: 1.9381 (2.0527) time: 0.5049 [2021-03-26 17:40:10 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 530/1251] eta: 0:06:09 lr: 0.000221 loss: 2.9965 (3.0303) grad_norm: 1.9730 (2.0511) time: 0.5039 [2021-03-26 17:40:15 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 540/1251] eta: 0:06:04 lr: 0.000221 loss: 3.1719 (3.0335) grad_norm: 1.9958 (2.0525) time: 0.5094 [2021-03-26 17:40:21 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 550/1251] eta: 0:05:59 lr: 0.000221 loss: 3.1410 (3.0285) grad_norm: 2.1048 (2.0529) time: 0.5165 [2021-03-26 17:40:26 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 560/1251] eta: 0:05:54 lr: 0.000221 loss: 3.1410 (3.0329) grad_norm: 2.0600 (2.0546) time: 0.5172 [2021-03-26 17:40:31 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 570/1251] eta: 0:05:49 lr: 0.000221 loss: 3.0951 (3.0302) grad_norm: 1.9853 (2.0533) time: 0.5121 [2021-03-26 17:40:36 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 580/1251] eta: 0:05:44 lr: 0.000221 loss: 3.0569 (3.0302) grad_norm: 1.9820 (2.0521) time: 0.5098 [2021-03-26 17:40:41 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 590/1251] eta: 0:05:39 lr: 0.000220 loss: 3.0956 (3.0303) grad_norm: 2.1189 (2.0543) time: 0.5119 [2021-03-26 17:40:46 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 600/1251] eta: 0:05:34 lr: 0.000220 loss: 3.1492 (3.0325) grad_norm: 2.1197 (2.0540) time: 0.5136 [2021-03-26 17:40:51 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 610/1251] eta: 0:05:28 lr: 0.000220 loss: 2.9709 (3.0300) grad_norm: 1.9860 (2.0534) time: 0.5088 [2021-03-26 17:40:56 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 620/1251] eta: 0:05:23 lr: 0.000220 loss: 2.9709 (3.0309) grad_norm: 1.9555 (2.0517) time: 0.5058 [2021-03-26 17:41:01 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 630/1251] eta: 0:05:18 lr: 0.000220 loss: 3.0966 (3.0285) grad_norm: 1.9828 (2.0537) time: 0.5064 [2021-03-26 17:41:06 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 640/1251] eta: 0:05:13 lr: 0.000220 loss: 2.9203 (3.0312) grad_norm: 1.9725 (2.0525) time: 0.5024 [2021-03-26 17:41:11 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 650/1251] eta: 0:05:07 lr: 0.000220 loss: 3.1887 (3.0297) grad_norm: 1.9725 (2.0533) time: 0.4989 [2021-03-26 17:41:16 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 660/1251] eta: 0:05:02 lr: 0.000220 loss: 2.9149 (3.0262) grad_norm: 1.9672 (2.0525) time: 0.4966 [2021-03-26 17:41:21 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 670/1251] eta: 0:04:57 lr: 0.000220 loss: 2.9547 (3.0309) grad_norm: 1.9436 (2.0519) time: 0.5010 [2021-03-26 17:41:26 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 680/1251] eta: 0:04:52 lr: 0.000220 loss: 3.0716 (3.0295) grad_norm: 2.0089 (2.0503) time: 0.5048 [2021-03-26 17:41:32 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 690/1251] eta: 0:04:47 lr: 0.000220 loss: 2.9530 (3.0291) grad_norm: 1.9419 (2.0488) time: 0.5047 [2021-03-26 17:41:36 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 700/1251] eta: 0:04:41 lr: 0.000220 loss: 3.0662 (3.0314) grad_norm: 1.9100 (2.0470) time: 0.5010 [2021-03-26 17:41:42 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 710/1251] eta: 0:04:36 lr: 0.000220 loss: 3.1020 (3.0305) grad_norm: 1.8786 (2.0454) time: 0.5011 [2021-03-26 17:41:47 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 720/1251] eta: 0:04:31 lr: 0.000220 loss: 2.9905 (3.0287) grad_norm: 1.9828 (2.0460) time: 0.5074 [2021-03-26 17:41:52 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 730/1251] eta: 0:04:26 lr: 0.000220 loss: 2.7141 (3.0232) grad_norm: 1.8708 (2.0451) time: 0.5186 [2021-03-26 17:41:57 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 740/1251] eta: 0:04:21 lr: 0.000220 loss: 2.7141 (3.0210) grad_norm: 1.8634 (2.0439) time: 0.5278 [2021-03-26 17:42:02 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 750/1251] eta: 0:04:16 lr: 0.000220 loss: 2.9414 (3.0207) grad_norm: 1.8969 (2.0436) time: 0.5148 [2021-03-26 17:42:07 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 760/1251] eta: 0:04:11 lr: 0.000220 loss: 3.0856 (3.0241) grad_norm: 1.9813 (2.0451) time: 0.5055 [2021-03-26 17:42:12 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 770/1251] eta: 0:04:06 lr: 0.000220 loss: 3.1845 (3.0233) grad_norm: 1.9364 (2.0434) time: 0.5053 [2021-03-26 17:42:17 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 780/1251] eta: 0:04:00 lr: 0.000220 loss: 3.0707 (3.0226) grad_norm: 1.8848 (2.0419) time: 0.5049 [2021-03-26 17:42:22 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 790/1251] eta: 0:03:55 lr: 0.000220 loss: 2.9610 (3.0205) grad_norm: 1.8985 (2.0416) time: 0.5085 [2021-03-26 17:42:28 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 800/1251] eta: 0:03:50 lr: 0.000220 loss: 2.9619 (3.0206) grad_norm: 2.0320 (2.0424) time: 0.5051 [2021-03-26 17:42:32 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 810/1251] eta: 0:03:45 lr: 0.000220 loss: 3.0817 (3.0197) grad_norm: 2.0238 (2.0421) time: 0.4983 [2021-03-26 17:42:37 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 820/1251] eta: 0:03:40 lr: 0.000220 loss: 3.1034 (3.0191) grad_norm: 2.0209 (2.0421) time: 0.4979 [2021-03-26 17:42:42 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 830/1251] eta: 0:03:35 lr: 0.000220 loss: 3.1205 (3.0173) grad_norm: 2.0069 (2.0461) time: 0.4988 [2021-03-26 17:42:47 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 840/1251] eta: 0:03:29 lr: 0.000220 loss: 2.9561 (3.0156) grad_norm: 1.9734 (2.0462) time: 0.4984 [2021-03-26 17:42:53 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 850/1251] eta: 0:03:24 lr: 0.000220 loss: 3.0289 (3.0181) grad_norm: 1.9134 (2.0445) time: 0.5088 [2021-03-26 17:42:58 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 860/1251] eta: 0:03:19 lr: 0.000220 loss: 3.2094 (3.0166) grad_norm: 1.9134 (2.0432) time: 0.5157 [2021-03-26 17:43:03 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 870/1251] eta: 0:03:14 lr: 0.000220 loss: 2.7073 (3.0119) grad_norm: 1.9688 (2.0441) time: 0.5102 [2021-03-26 17:43:08 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 880/1251] eta: 0:03:09 lr: 0.000220 loss: 2.9583 (3.0133) grad_norm: 2.0052 (2.0457) time: 0.5061 [2021-03-26 17:43:13 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 890/1251] eta: 0:03:04 lr: 0.000219 loss: 3.1357 (3.0134) grad_norm: 2.0052 (2.0454) time: 0.5005 [2021-03-26 17:43:18 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 900/1251] eta: 0:02:59 lr: 0.000219 loss: 3.1357 (3.0152) grad_norm: 1.9502 (2.0448) time: 0.4998 [2021-03-26 17:43:23 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 910/1251] eta: 0:02:54 lr: 0.000219 loss: 2.9949 (3.0152) grad_norm: 1.9535 (2.0441) time: 0.5012 [2021-03-26 17:43:28 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 920/1251] eta: 0:02:48 lr: 0.000219 loss: 3.1985 (3.0172) grad_norm: 1.9535 (2.0432) time: 0.5062 [2021-03-26 17:43:33 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 930/1251] eta: 0:02:43 lr: 0.000219 loss: 3.2248 (3.0175) grad_norm: 1.9609 (2.0425) time: 0.5138 [2021-03-26 17:43:38 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 940/1251] eta: 0:02:38 lr: 0.000219 loss: 3.1115 (3.0166) grad_norm: 1.9642 (2.0429) time: 0.5078 [2021-03-26 17:43:43 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 950/1251] eta: 0:02:33 lr: 0.000219 loss: 3.0597 (3.0168) grad_norm: 2.0742 (2.0442) time: 0.5082 [2021-03-26 17:43:48 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 960/1251] eta: 0:02:28 lr: 0.000219 loss: 3.0106 (3.0159) grad_norm: 1.9528 (2.0436) time: 0.5090 [2021-03-26 17:43:53 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 970/1251] eta: 0:02:23 lr: 0.000219 loss: 3.1433 (3.0183) grad_norm: 1.9718 (2.0442) time: 0.5042 [2021-03-26 17:43:58 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 980/1251] eta: 0:02:18 lr: 0.000219 loss: 3.1030 (3.0154) grad_norm: 2.0407 (2.0446) time: 0.5022 [2021-03-26 17:44:03 swin_small_patch4_window7_224] INFO: Epoch: [208] [ 990/1251] eta: 0:02:13 lr: 0.000219 loss: 3.0635 (3.0161) grad_norm: 2.0334 (2.0476) time: 0.5012 [2021-03-26 17:44:08 swin_small_patch4_window7_224] INFO: Epoch: [208] [1000/1251] eta: 0:02:08 lr: 0.000219 loss: 3.2313 (3.0168) grad_norm: 2.0334 (2.0479) time: 0.5025 [2021-03-26 17:44:14 swin_small_patch4_window7_224] INFO: Epoch: [208] [1010/1251] eta: 0:02:02 lr: 0.000219 loss: 3.1861 (3.0176) grad_norm: 1.9947 (2.0479) time: 0.5071 [2021-03-26 17:44:19 swin_small_patch4_window7_224] INFO: Epoch: [208] [1020/1251] eta: 0:01:57 lr: 0.000219 loss: 3.0100 (3.0170) grad_norm: 2.0244 (2.0537) time: 0.5119 [2021-03-26 17:44:24 swin_small_patch4_window7_224] INFO: Epoch: [208] [1030/1251] eta: 0:01:52 lr: 0.000219 loss: 3.0079 (3.0178) grad_norm: 2.0446 (2.0531) time: 0.5122 [2021-03-26 17:44:29 swin_small_patch4_window7_224] INFO: Epoch: [208] [1040/1251] eta: 0:01:47 lr: 0.000219 loss: 3.1402 (3.0189) grad_norm: 1.9360 (2.0518) time: 0.5101 [2021-03-26 17:44:34 swin_small_patch4_window7_224] INFO: Epoch: [208] [1050/1251] eta: 0:01:42 lr: 0.000219 loss: 3.1915 (3.0187) grad_norm: 1.9235 (2.0504) time: 0.5160 [2021-03-26 17:44:39 swin_small_patch4_window7_224] INFO: Epoch: [208] [1060/1251] eta: 0:01:37 lr: 0.000219 loss: 3.3105 (3.0192) grad_norm: 1.9434 (2.0503) time: 0.5136 [2021-03-26 17:44:44 swin_small_patch4_window7_224] INFO: Epoch: [208] [1070/1251] eta: 0:01:32 lr: 0.000219 loss: 3.1123 (3.0185) grad_norm: 1.9543 (2.0493) time: 0.5019 [2021-03-26 17:44:49 swin_small_patch4_window7_224] INFO: Epoch: [208] [1080/1251] eta: 0:01:27 lr: 0.000219 loss: 3.0112 (3.0178) grad_norm: 1.9543 (2.0488) time: 0.5025 [2021-03-26 17:44:54 swin_small_patch4_window7_224] INFO: Epoch: [208] [1090/1251] eta: 0:01:22 lr: 0.000219 loss: 2.9294 (3.0176) grad_norm: 1.9410 (2.0485) time: 0.5037 [2021-03-26 17:44:59 swin_small_patch4_window7_224] INFO: Epoch: [208] [1100/1251] eta: 0:01:16 lr: 0.000219 loss: 3.0958 (3.0170) grad_norm: 2.0825 (2.0505) time: 0.5035 [2021-03-26 17:45:04 swin_small_patch4_window7_224] INFO: Epoch: [208] [1110/1251] eta: 0:01:11 lr: 0.000219 loss: 2.9532 (3.0159) grad_norm: 2.0464 (2.0500) time: 0.5108 [2021-03-26 17:45:09 swin_small_patch4_window7_224] INFO: Epoch: [208] [1120/1251] eta: 0:01:06 lr: 0.000219 loss: 3.0255 (3.0176) grad_norm: 1.9824 (2.0501) time: 0.5081 [2021-03-26 17:45:15 swin_small_patch4_window7_224] INFO: Epoch: [208] [1130/1251] eta: 0:01:01 lr: 0.000219 loss: 3.3888 (3.0199) grad_norm: 1.9824 (2.0499) time: 0.5047 [2021-03-26 17:45:20 swin_small_patch4_window7_224] INFO: Epoch: [208] [1140/1251] eta: 0:00:56 lr: 0.000219 loss: 3.1958 (3.0196) grad_norm: 1.9636 (2.0494) time: 0.5089 [2021-03-26 17:45:25 swin_small_patch4_window7_224] INFO: Epoch: [208] [1150/1251] eta: 0:00:51 lr: 0.000219 loss: 3.0691 (3.0172) grad_norm: 2.0095 (2.0499) time: 0.5073 [2021-03-26 17:45:30 swin_small_patch4_window7_224] INFO: Epoch: [208] [1160/1251] eta: 0:00:46 lr: 0.000219 loss: 3.0691 (3.0181) grad_norm: 2.0345 (2.0494) time: 0.5064 [2021-03-26 17:45:35 swin_small_patch4_window7_224] INFO: Epoch: [208] [1170/1251] eta: 0:00:41 lr: 0.000219 loss: 2.9893 (3.0166) grad_norm: 2.0017 (2.0499) time: 0.4993 [2021-03-26 17:45:40 swin_small_patch4_window7_224] INFO: Epoch: [208] [1180/1251] eta: 0:00:36 lr: 0.000218 loss: 2.9340 (3.0165) grad_norm: 1.9442 (2.0503) time: 0.5052 [2021-03-26 17:45:45 swin_small_patch4_window7_224] INFO: Epoch: [208] [1190/1251] eta: 0:00:31 lr: 0.000218 loss: 3.0779 (3.0180) grad_norm: 2.0849 (2.0507) time: 0.5083 [2021-03-26 17:45:50 swin_small_patch4_window7_224] INFO: Epoch: [208] [1200/1251] eta: 0:00:25 lr: 0.000218 loss: 3.1216 (3.0185) grad_norm: 2.0798 (2.0499) time: 0.5034 [2021-03-26 17:45:55 swin_small_patch4_window7_224] INFO: Epoch: [208] [1210/1251] eta: 0:00:20 lr: 0.000218 loss: 3.2517 (3.0212) grad_norm: 2.0268 (2.0512) time: 0.5012 [2021-03-26 17:46:00 swin_small_patch4_window7_224] INFO: Epoch: [208] [1220/1251] eta: 0:00:15 lr: 0.000218 loss: 3.2850 (3.0220) grad_norm: 2.1070 (2.0519) time: 0.4991 [2021-03-26 17:46:05 swin_small_patch4_window7_224] INFO: Epoch: [208] [1230/1251] eta: 0:00:10 lr: 0.000218 loss: 3.0915 (3.0232) grad_norm: 2.1284 (2.0539) time: 0.5053 [2021-03-26 17:46:10 swin_small_patch4_window7_224] INFO: Epoch: [208] [1240/1251] eta: 0:00:05 lr: 0.000218 loss: 3.1084 (3.0222) grad_norm: 2.1577 (2.0537) time: 0.5038 [2021-03-26 17:46:15 swin_small_patch4_window7_224] INFO: Epoch: [208] [1250/1251] eta: 0:00:00 lr: 0.000218 loss: 3.0227 (3.0217) grad_norm: 1.9112 (2.0528) time: 0.5000 [2021-03-26 17:46:23 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 0.7330 (0.7330) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-26 17:46:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:22 loss: 0.7794 (0.7911) acc1: 79.6875 (79.8295) acc5: 96.8750 (96.1648) [2021-03-26 17:46:29 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7794 (0.8100) acc1: 79.6875 (79.5387) acc5: 95.3125 (95.9821) [2021-03-26 17:46:30 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7521 (0.8042) acc1: 79.6875 (80.1915) acc5: 95.3125 (95.8165) [2021-03-26 17:46:32 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7401 (0.8039) acc1: 82.8125 (80.5640) acc5: 96.8750 (96.0366) [2021-03-26 17:46:33 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8043 (0.8103) acc1: 81.2500 (80.4800) acc5: 95.3125 (95.7760) [2021-03-26 17:46:39 swin_small_patch4_window7_224] INFO: * Acc@1 80.868 Acc@5 95.574 loss 0.809 [2021-03-26 17:46:39 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-26 17:46:39 swin_small_patch4_window7_224] INFO: Max accuracy: 80.87% [2021-03-26 17:46:43 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 0/1251] eta: 1:20:16 lr: 0.000218 loss: 2.6421 (2.6421) grad_norm: 1.9614 (1.9614) time: 3.8501 [2021-03-26 17:46:48 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 10/1251] eta: 0:17:30 lr: 0.000218 loss: 3.2797 (3.0723) grad_norm: 1.9614 (1.9683) time: 0.8462 [2021-03-26 17:46:53 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 20/1251] eta: 0:14:00 lr: 0.000218 loss: 3.2797 (3.0736) grad_norm: 1.9267 (2.0303) time: 0.5245 [2021-03-26 17:46:59 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 30/1251] eta: 0:12:45 lr: 0.000218 loss: 3.0159 (3.0489) grad_norm: 1.9191 (2.0451) time: 0.5063 [2021-03-26 17:47:04 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 40/1251] eta: 0:12:07 lr: 0.000218 loss: 2.9309 (3.0126) grad_norm: 1.8958 (2.0280) time: 0.5150 [2021-03-26 17:47:09 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 50/1251] eta: 0:11:39 lr: 0.000218 loss: 2.9976 (3.0335) grad_norm: 1.9909 (2.0294) time: 0.5142 [2021-03-26 17:47:14 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 60/1251] eta: 0:11:18 lr: 0.000218 loss: 3.1203 (3.0546) grad_norm: 1.9940 (2.0245) time: 0.5053 [2021-03-26 17:47:19 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 70/1251] eta: 0:11:01 lr: 0.000218 loss: 3.1070 (3.0407) grad_norm: 1.9508 (2.0400) time: 0.5022 [2021-03-26 17:47:24 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 80/1251] eta: 0:10:46 lr: 0.000218 loss: 3.1650 (3.0586) grad_norm: 2.0403 (2.0450) time: 0.4993 [2021-03-26 17:47:29 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 90/1251] eta: 0:10:37 lr: 0.000218 loss: 3.0861 (3.0403) grad_norm: 1.9727 (2.0300) time: 0.5085 [2021-03-26 17:47:34 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 100/1251] eta: 0:10:26 lr: 0.000218 loss: 3.1301 (3.0653) grad_norm: 1.9254 (2.0268) time: 0.5106 [2021-03-26 17:47:39 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 110/1251] eta: 0:10:18 lr: 0.000218 loss: 3.1028 (3.0558) grad_norm: 1.9729 (2.0286) time: 0.5131 [2021-03-26 17:47:44 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 120/1251] eta: 0:10:10 lr: 0.000218 loss: 2.9722 (3.0419) grad_norm: 1.9214 (2.0186) time: 0.5201 [2021-03-26 17:47:49 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 130/1251] eta: 0:10:02 lr: 0.000218 loss: 3.0624 (3.0487) grad_norm: 1.9128 (2.0211) time: 0.5086 [2021-03-26 17:47:54 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 140/1251] eta: 0:09:53 lr: 0.000218 loss: 3.3437 (3.0734) grad_norm: 1.9222 (2.0177) time: 0.5014 [2021-03-26 17:48:00 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 150/1251] eta: 0:09:47 lr: 0.000218 loss: 3.3279 (3.0701) grad_norm: 1.9619 (2.0243) time: 0.5071 [2021-03-26 17:48:05 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 160/1251] eta: 0:09:39 lr: 0.000218 loss: 2.9711 (3.0603) grad_norm: 2.0131 (2.0281) time: 0.5052 [2021-03-26 17:48:10 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 170/1251] eta: 0:09:31 lr: 0.000218 loss: 3.0113 (3.0665) grad_norm: 1.9854 (2.0265) time: 0.4974 [2021-03-26 17:48:15 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 180/1251] eta: 0:09:25 lr: 0.000218 loss: 3.0669 (3.0628) grad_norm: 1.9554 (2.0221) time: 0.5080 [2021-03-26 17:48:20 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 190/1251] eta: 0:09:19 lr: 0.000218 loss: 2.9847 (3.0557) grad_norm: 1.9296 (2.0155) time: 0.5139 [2021-03-26 17:48:25 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 200/1251] eta: 0:09:13 lr: 0.000218 loss: 3.0817 (3.0496) grad_norm: 1.9396 (2.0175) time: 0.5105 [2021-03-26 17:48:30 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 210/1251] eta: 0:09:06 lr: 0.000218 loss: 3.0042 (3.0455) grad_norm: 2.0055 (2.0208) time: 0.5037 [2021-03-26 17:48:35 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 220/1251] eta: 0:09:00 lr: 0.000218 loss: 2.9865 (3.0356) grad_norm: 2.0140 (2.0228) time: 0.5006 [2021-03-26 17:48:40 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 230/1251] eta: 0:08:54 lr: 0.000217 loss: 3.0575 (3.0362) grad_norm: 2.0122 (2.0203) time: 0.5063 [2021-03-26 17:48:45 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 240/1251] eta: 0:08:48 lr: 0.000217 loss: 3.0835 (3.0315) grad_norm: 1.8539 (2.0165) time: 0.5118 [2021-03-26 17:48:50 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 250/1251] eta: 0:08:43 lr: 0.000217 loss: 3.0775 (3.0339) grad_norm: 1.8584 (2.0111) time: 0.5125 [2021-03-26 17:48:55 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 260/1251] eta: 0:08:37 lr: 0.000217 loss: 3.1742 (3.0387) grad_norm: 1.9093 (2.0107) time: 0.5069 [2021-03-26 17:49:00 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 270/1251] eta: 0:08:31 lr: 0.000217 loss: 3.1742 (3.0368) grad_norm: 1.9093 (2.0119) time: 0.5059 [2021-03-26 17:49:05 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 280/1251] eta: 0:08:25 lr: 0.000217 loss: 3.1482 (3.0355) grad_norm: 1.9966 (2.0240) time: 0.5057 [2021-03-26 17:49:10 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 290/1251] eta: 0:08:19 lr: 0.000217 loss: 3.0415 (3.0289) grad_norm: 2.0360 (2.0233) time: 0.5008 [2021-03-26 17:49:16 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 300/1251] eta: 0:08:14 lr: 0.000217 loss: 2.7766 (3.0240) grad_norm: 1.9763 (2.0220) time: 0.5046 [2021-03-26 17:49:21 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 310/1251] eta: 0:08:08 lr: 0.000217 loss: 3.0585 (3.0310) grad_norm: 2.0263 (2.0232) time: 0.5112 [2021-03-26 17:49:26 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 320/1251] eta: 0:08:03 lr: 0.000217 loss: 3.1420 (3.0298) grad_norm: 2.0326 (2.0221) time: 0.5094 [2021-03-26 17:49:31 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 330/1251] eta: 0:07:57 lr: 0.000217 loss: 2.9781 (3.0262) grad_norm: 1.9451 (2.0240) time: 0.5077 [2021-03-26 17:49:36 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 340/1251] eta: 0:07:52 lr: 0.000217 loss: 2.8642 (3.0229) grad_norm: 1.9640 (2.0271) time: 0.5067 [2021-03-26 17:49:41 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 350/1251] eta: 0:07:46 lr: 0.000217 loss: 2.9402 (3.0278) grad_norm: 1.9640 (2.0278) time: 0.5086 [2021-03-26 17:49:46 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 360/1251] eta: 0:07:41 lr: 0.000217 loss: 3.1726 (3.0279) grad_norm: 2.0486 (2.0312) time: 0.5106 [2021-03-26 17:49:51 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 370/1251] eta: 0:07:36 lr: 0.000217 loss: 2.9511 (3.0227) grad_norm: 1.9920 (2.0292) time: 0.5106 [2021-03-26 17:49:56 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 380/1251] eta: 0:07:30 lr: 0.000217 loss: 2.9045 (3.0232) grad_norm: 1.9619 (2.0264) time: 0.5072 [2021-03-26 17:50:01 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 390/1251] eta: 0:07:25 lr: 0.000217 loss: 3.0086 (3.0203) grad_norm: 1.8747 (2.0238) time: 0.5054 [2021-03-26 17:50:06 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 400/1251] eta: 0:07:19 lr: 0.000217 loss: 2.9107 (3.0185) grad_norm: 1.9065 (2.0236) time: 0.5107 [2021-03-26 17:50:12 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 410/1251] eta: 0:07:14 lr: 0.000217 loss: 3.1003 (3.0256) grad_norm: 1.9114 (2.0206) time: 0.5080 [2021-03-26 17:50:16 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 420/1251] eta: 0:07:08 lr: 0.000217 loss: 3.2487 (3.0211) grad_norm: 1.9595 (2.0206) time: 0.5003 [2021-03-26 17:50:22 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 430/1251] eta: 0:07:03 lr: 0.000217 loss: 2.9382 (3.0201) grad_norm: 2.0108 (2.0254) time: 0.5040 [2021-03-26 17:50:27 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 440/1251] eta: 0:06:58 lr: 0.000217 loss: 2.9880 (3.0193) grad_norm: 1.8959 (2.0230) time: 0.5046 [2021-03-26 17:50:32 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 450/1251] eta: 0:06:52 lr: 0.000217 loss: 3.1731 (3.0206) grad_norm: 1.8821 (2.0210) time: 0.5026 [2021-03-26 17:50:37 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 460/1251] eta: 0:06:47 lr: 0.000217 loss: 3.1667 (3.0202) grad_norm: 1.9343 (2.0179) time: 0.5008 [2021-03-26 17:50:42 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 470/1251] eta: 0:06:42 lr: 0.000217 loss: 2.8817 (3.0158) grad_norm: 1.9032 (2.0166) time: 0.4999 [2021-03-26 17:50:47 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 480/1251] eta: 0:06:36 lr: 0.000217 loss: 2.7879 (3.0112) grad_norm: 1.9121 (2.0155) time: 0.5016 [2021-03-26 17:50:52 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 490/1251] eta: 0:06:31 lr: 0.000217 loss: 3.0160 (3.0128) grad_norm: 1.8626 (2.0125) time: 0.5015 [2021-03-26 17:50:57 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 500/1251] eta: 0:06:26 lr: 0.000217 loss: 3.0624 (3.0165) grad_norm: 1.9823 (2.0141) time: 0.5056 [2021-03-26 17:51:02 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 510/1251] eta: 0:06:20 lr: 0.000217 loss: 3.1663 (3.0210) grad_norm: 1.9862 (2.0149) time: 0.5067 [2021-03-26 17:51:07 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 520/1251] eta: 0:06:15 lr: 0.000217 loss: 3.0508 (3.0147) grad_norm: 2.0680 (2.0160) time: 0.5051 [2021-03-26 17:51:12 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 530/1251] eta: 0:06:10 lr: 0.000216 loss: 2.8952 (3.0158) grad_norm: 2.0794 (2.0168) time: 0.5067 [2021-03-26 17:51:17 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 540/1251] eta: 0:06:05 lr: 0.000216 loss: 3.2576 (3.0171) grad_norm: 2.1095 (2.0199) time: 0.5053 [2021-03-26 17:51:22 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 550/1251] eta: 0:06:00 lr: 0.000216 loss: 3.1782 (3.0130) grad_norm: 2.1095 (2.0213) time: 0.5128 [2021-03-26 17:51:27 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 560/1251] eta: 0:05:55 lr: 0.000216 loss: 2.6208 (3.0067) grad_norm: 1.9905 (2.0210) time: 0.5234 [2021-03-26 17:51:33 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 570/1251] eta: 0:05:49 lr: 0.000216 loss: 2.9722 (3.0087) grad_norm: 1.9516 (2.0216) time: 0.5156 [2021-03-26 17:51:38 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 580/1251] eta: 0:05:44 lr: 0.000216 loss: 3.0472 (3.0096) grad_norm: 2.0107 (2.0222) time: 0.5064 [2021-03-26 17:51:43 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 590/1251] eta: 0:05:39 lr: 0.000216 loss: 3.1092 (3.0100) grad_norm: 1.9966 (2.0221) time: 0.5117 [2021-03-26 17:51:48 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 600/1251] eta: 0:05:34 lr: 0.000216 loss: 2.5955 (3.0028) grad_norm: 1.9542 (2.0215) time: 0.5116 [2021-03-26 17:51:53 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 610/1251] eta: 0:05:29 lr: 0.000216 loss: 3.0440 (3.0055) grad_norm: 1.9268 (2.0213) time: 0.5058 [2021-03-26 17:51:58 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 620/1251] eta: 0:05:23 lr: 0.000216 loss: 3.2083 (3.0060) grad_norm: 1.9417 (2.0201) time: 0.5037 [2021-03-26 17:52:03 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 630/1251] eta: 0:05:18 lr: 0.000216 loss: 3.2083 (3.0049) grad_norm: 1.9984 (2.0205) time: 0.5029 [2021-03-26 17:52:08 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 640/1251] eta: 0:05:13 lr: 0.000216 loss: 3.2179 (3.0108) grad_norm: 1.9984 (2.0203) time: 0.5088 [2021-03-26 17:52:13 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 650/1251] eta: 0:05:08 lr: 0.000216 loss: 3.2461 (3.0124) grad_norm: 1.8850 (2.0186) time: 0.5070 [2021-03-26 17:52:18 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 660/1251] eta: 0:05:03 lr: 0.000216 loss: 3.1928 (3.0135) grad_norm: 2.0163 (2.0202) time: 0.5024 [2021-03-26 17:52:23 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 670/1251] eta: 0:04:57 lr: 0.000216 loss: 2.9422 (3.0127) grad_norm: 2.0163 (2.0187) time: 0.5035 [2021-03-26 17:52:28 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 680/1251] eta: 0:04:52 lr: 0.000216 loss: 2.6111 (3.0069) grad_norm: 1.9220 (2.0199) time: 0.5013 [2021-03-26 17:52:33 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 690/1251] eta: 0:04:47 lr: 0.000216 loss: 2.7654 (3.0074) grad_norm: 1.9854 (2.0241) time: 0.5022 [2021-03-26 17:52:38 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 700/1251] eta: 0:04:42 lr: 0.000216 loss: 3.1751 (3.0115) grad_norm: 1.9708 (2.0238) time: 0.5077 [2021-03-26 17:52:43 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 710/1251] eta: 0:04:37 lr: 0.000216 loss: 3.2322 (3.0122) grad_norm: 2.0503 (2.0257) time: 0.5068 [2021-03-26 17:52:48 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 720/1251] eta: 0:04:31 lr: 0.000216 loss: 3.2322 (3.0136) grad_norm: 2.0538 (2.0280) time: 0.5066 [2021-03-26 17:52:54 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 730/1251] eta: 0:04:26 lr: 0.000216 loss: 3.1651 (3.0129) grad_norm: 2.0789 (2.0305) time: 0.5131 [2021-03-26 17:52:59 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 740/1251] eta: 0:04:21 lr: 0.000216 loss: 3.1502 (3.0134) grad_norm: 2.1246 (2.0347) time: 0.5165 [2021-03-26 17:53:04 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 750/1251] eta: 0:04:16 lr: 0.000216 loss: 3.1947 (3.0170) grad_norm: 2.1774 (2.0377) time: 0.5144 [2021-03-26 17:53:09 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 760/1251] eta: 0:04:11 lr: 0.000216 loss: 3.2155 (3.0178) grad_norm: 1.9200 (2.0353) time: 0.5034 [2021-03-26 17:53:14 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 770/1251] eta: 0:04:06 lr: 0.000216 loss: 3.0431 (3.0166) grad_norm: 1.8591 (2.0344) time: 0.4988 [2021-03-26 17:53:19 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 780/1251] eta: 0:04:01 lr: 0.000216 loss: 3.0010 (3.0171) grad_norm: 1.8851 (2.0332) time: 0.5086 [2021-03-26 17:53:24 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 790/1251] eta: 0:03:55 lr: 0.000216 loss: 3.0367 (3.0167) grad_norm: 2.0463 (2.0349) time: 0.5134 [2021-03-26 17:53:29 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 800/1251] eta: 0:03:50 lr: 0.000216 loss: 3.1545 (3.0201) grad_norm: 2.0527 (2.0340) time: 0.5130 [2021-03-26 17:53:34 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 810/1251] eta: 0:03:45 lr: 0.000216 loss: 3.1545 (3.0208) grad_norm: 1.9710 (2.0339) time: 0.5095 [2021-03-26 17:53:39 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 820/1251] eta: 0:03:40 lr: 0.000215 loss: 3.1191 (3.0226) grad_norm: 2.0374 (2.0337) time: 0.5050 [2021-03-26 17:53:45 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 830/1251] eta: 0:03:35 lr: 0.000215 loss: 3.3228 (3.0243) grad_norm: 2.0626 (2.0377) time: 0.5099 [2021-03-26 17:53:50 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 840/1251] eta: 0:03:30 lr: 0.000215 loss: 2.9048 (3.0208) grad_norm: 1.9750 (2.0364) time: 0.5103 [2021-03-26 17:53:55 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 850/1251] eta: 0:03:25 lr: 0.000215 loss: 3.0605 (3.0232) grad_norm: 1.9886 (2.0361) time: 0.5117 [2021-03-26 17:54:00 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 860/1251] eta: 0:03:20 lr: 0.000215 loss: 3.2138 (3.0229) grad_norm: 1.9459 (2.0343) time: 0.5162 [2021-03-26 17:54:05 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 870/1251] eta: 0:03:14 lr: 0.000215 loss: 3.1592 (3.0240) grad_norm: 1.8855 (2.0331) time: 0.5097 [2021-03-26 17:54:10 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 880/1251] eta: 0:03:09 lr: 0.000215 loss: 2.9809 (3.0219) grad_norm: 1.9537 (2.0330) time: 0.5017 [2021-03-26 17:54:15 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 890/1251] eta: 0:03:04 lr: 0.000215 loss: 2.8794 (3.0195) grad_norm: 1.9458 (2.0320) time: 0.4958 [2021-03-26 17:54:20 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 900/1251] eta: 0:02:59 lr: 0.000215 loss: 2.9449 (3.0202) grad_norm: 2.0041 (2.0343) time: 0.4970 [2021-03-26 17:54:25 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 910/1251] eta: 0:02:54 lr: 0.000215 loss: 3.3008 (3.0234) grad_norm: 2.1944 (2.0358) time: 0.5035 [2021-03-26 17:54:30 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 920/1251] eta: 0:02:49 lr: 0.000215 loss: 3.1735 (3.0229) grad_norm: 2.0819 (2.0365) time: 0.5073 [2021-03-26 17:54:35 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 930/1251] eta: 0:02:44 lr: 0.000215 loss: 3.1432 (3.0255) grad_norm: 2.0623 (2.0363) time: 0.5153 [2021-03-26 17:54:40 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 940/1251] eta: 0:02:38 lr: 0.000215 loss: 3.2004 (3.0266) grad_norm: 1.9488 (2.0358) time: 0.5129 [2021-03-26 17:54:45 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 950/1251] eta: 0:02:33 lr: 0.000215 loss: 3.0750 (3.0261) grad_norm: 1.9388 (2.0350) time: 0.5005 [2021-03-26 17:54:50 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 960/1251] eta: 0:02:28 lr: 0.000215 loss: 3.2143 (3.0284) grad_norm: 2.0393 (2.0355) time: 0.4967 [2021-03-26 17:54:55 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 970/1251] eta: 0:02:23 lr: 0.000215 loss: 3.2543 (3.0302) grad_norm: 2.0299 (2.0348) time: 0.5002 [2021-03-26 17:55:00 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 980/1251] eta: 0:02:18 lr: 0.000215 loss: 3.2262 (3.0317) grad_norm: 2.0299 (2.0351) time: 0.5044 [2021-03-26 17:55:05 swin_small_patch4_window7_224] INFO: Epoch: [209] [ 990/1251] eta: 0:02:13 lr: 0.000215 loss: 3.0311 (3.0314) grad_norm: 2.0310 (2.0345) time: 0.5019 [2021-03-26 17:55:10 swin_small_patch4_window7_224] INFO: Epoch: [209] [1000/1251] eta: 0:02:08 lr: 0.000215 loss: 3.1939 (3.0346) grad_norm: 1.9848 (2.0351) time: 0.5031 [2021-03-26 17:55:15 swin_small_patch4_window7_224] INFO: Epoch: [209] [1010/1251] eta: 0:02:03 lr: 0.000215 loss: 3.2727 (3.0361) grad_norm: 2.0793 (2.0379) time: 0.5033 [2021-03-26 17:55:20 swin_small_patch4_window7_224] INFO: Epoch: [209] [1020/1251] eta: 0:01:57 lr: 0.000215 loss: 3.0756 (3.0365) grad_norm: 2.0868 (2.0394) time: 0.5000 [2021-03-26 17:55:25 swin_small_patch4_window7_224] INFO: Epoch: [209] [1030/1251] eta: 0:01:52 lr: 0.000215 loss: 3.0756 (3.0368) grad_norm: 2.1021 (2.0419) time: 0.5028 [2021-03-26 17:55:31 swin_small_patch4_window7_224] INFO: Epoch: [209] [1040/1251] eta: 0:01:47 lr: 0.000215 loss: 3.0585 (3.0370) grad_norm: 1.9504 (2.0405) time: 0.5086 [2021-03-26 17:55:36 swin_small_patch4_window7_224] INFO: Epoch: [209] [1050/1251] eta: 0:01:42 lr: 0.000215 loss: 2.9825 (3.0362) grad_norm: 1.9504 (2.0401) time: 0.5123 [2021-03-26 17:55:41 swin_small_patch4_window7_224] INFO: Epoch: [209] [1060/1251] eta: 0:01:37 lr: 0.000215 loss: 3.1609 (3.0377) grad_norm: 2.0313 (2.0400) time: 0.5131 [2021-03-26 17:55:46 swin_small_patch4_window7_224] INFO: Epoch: [209] [1070/1251] eta: 0:01:32 lr: 0.000215 loss: 3.2102 (3.0378) grad_norm: 2.0157 (2.0401) time: 0.5053 [2021-03-26 17:55:51 swin_small_patch4_window7_224] INFO: Epoch: [209] [1080/1251] eta: 0:01:27 lr: 0.000215 loss: 3.1574 (3.0374) grad_norm: 1.9230 (2.0399) time: 0.5024 [2021-03-26 17:55:56 swin_small_patch4_window7_224] INFO: Epoch: [209] [1090/1251] eta: 0:01:22 lr: 0.000215 loss: 3.0616 (3.0374) grad_norm: 2.0099 (2.0411) time: 0.5059 [2021-03-26 17:56:01 swin_small_patch4_window7_224] INFO: Epoch: [209] [1100/1251] eta: 0:01:17 lr: 0.000215 loss: 2.9679 (3.0376) grad_norm: 2.0107 (2.0404) time: 0.5055 [2021-03-26 17:56:06 swin_small_patch4_window7_224] INFO: Epoch: [209] [1110/1251] eta: 0:01:11 lr: 0.000215 loss: 3.1507 (3.0374) grad_norm: 2.0400 (2.0412) time: 0.5116 [2021-03-26 17:56:11 swin_small_patch4_window7_224] INFO: Epoch: [209] [1120/1251] eta: 0:01:06 lr: 0.000214 loss: 3.2667 (3.0387) grad_norm: 2.1011 (2.0421) time: 0.5072 [2021-03-26 17:56:16 swin_small_patch4_window7_224] INFO: Epoch: [209] [1130/1251] eta: 0:01:01 lr: 0.000214 loss: 3.2623 (3.0400) grad_norm: 2.0148 (2.0412) time: 0.5000 [2021-03-26 17:56:21 swin_small_patch4_window7_224] INFO: Epoch: [209] [1140/1251] eta: 0:00:56 lr: 0.000214 loss: 3.1863 (3.0393) grad_norm: 2.0098 (2.0428) time: 0.5072 [2021-03-26 17:56:26 swin_small_patch4_window7_224] INFO: Epoch: [209] [1150/1251] eta: 0:00:51 lr: 0.000214 loss: 2.7986 (3.0370) grad_norm: 2.1967 (2.0433) time: 0.5090 [2021-03-26 17:56:31 swin_small_patch4_window7_224] INFO: Epoch: [209] [1160/1251] eta: 0:00:46 lr: 0.000214 loss: 2.9903 (3.0371) grad_norm: 2.0839 (2.0440) time: 0.5043 [2021-03-26 17:56:36 swin_small_patch4_window7_224] INFO: Epoch: [209] [1170/1251] eta: 0:00:41 lr: 0.000214 loss: 2.9903 (3.0367) grad_norm: 2.0337 (2.0441) time: 0.5062 [2021-03-26 17:56:41 swin_small_patch4_window7_224] INFO: Epoch: [209] [1180/1251] eta: 0:00:36 lr: 0.000214 loss: 2.9785 (3.0370) grad_norm: 2.0341 (2.0447) time: 0.5024 [2021-03-26 17:56:46 swin_small_patch4_window7_224] INFO: Epoch: [209] [1190/1251] eta: 0:00:31 lr: 0.000214 loss: 3.1480 (3.0373) grad_norm: 2.0709 (2.0451) time: 0.4998 [2021-03-26 17:56:52 swin_small_patch4_window7_224] INFO: Epoch: [209] [1200/1251] eta: 0:00:25 lr: 0.000214 loss: 3.1480 (3.0377) grad_norm: 2.0174 (2.0443) time: 0.5043 [2021-03-26 17:56:57 swin_small_patch4_window7_224] INFO: Epoch: [209] [1210/1251] eta: 0:00:20 lr: 0.000214 loss: 2.9415 (3.0352) grad_norm: 1.9804 (2.0441) time: 0.5022 [2021-03-26 17:57:02 swin_small_patch4_window7_224] INFO: Epoch: [209] [1220/1251] eta: 0:00:15 lr: 0.000214 loss: 2.9264 (3.0353) grad_norm: 2.0742 (2.0461) time: 0.5034 [2021-03-26 17:57:07 swin_small_patch4_window7_224] INFO: Epoch: [209] [1230/1251] eta: 0:00:10 lr: 0.000214 loss: 3.1727 (3.0349) grad_norm: 2.1012 (2.0461) time: 0.5016 [2021-03-26 17:57:12 swin_small_patch4_window7_224] INFO: Epoch: [209] [1240/1251] eta: 0:00:05 lr: 0.000214 loss: 3.0639 (3.0349) grad_norm: 2.0508 (2.0464) time: 0.4988 [2021-03-26 17:57:16 swin_small_patch4_window7_224] INFO: Epoch: [209] [1250/1251] eta: 0:00:00 lr: 0.000214 loss: 3.1376 (3.0345) grad_norm: 2.0508 (2.0472) time: 0.4958 [2021-03-26 17:57:26 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:57 loss: 0.8256 (0.8256) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-26 17:57:28 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.9611 (0.9081) acc1: 78.1250 (77.9830) acc5: 95.3125 (94.6023) [2021-03-26 17:57:30 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7433 (0.8230) acc1: 81.2500 (79.9851) acc5: 95.3125 (95.4613) [2021-03-26 17:57:33 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7041 (0.7973) acc1: 81.2500 (80.4435) acc5: 96.8750 (96.1190) [2021-03-26 17:57:35 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7428 (0.8016) acc1: 79.6875 (80.4878) acc5: 95.3125 (95.6936) [2021-03-26 17:57:36 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8238 (0.8247) acc1: 79.6875 (80.0960) acc5: 93.7500 (95.4560) [2021-03-26 17:57:46 swin_small_patch4_window7_224] INFO: * Acc@1 80.894 Acc@5 95.562 loss 0.809 [2021-03-26 17:57:46 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.9% [2021-03-26 17:57:46 swin_small_patch4_window7_224] INFO: Max accuracy: 80.89% [2021-03-26 17:57:50 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 0/1251] eta: 1:31:14 lr: 0.000214 loss: 3.5088 (3.5088) grad_norm: 2.0713 (2.0713) time: 4.3763 [2021-03-26 17:57:55 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 10/1251] eta: 0:17:55 lr: 0.000214 loss: 2.9740 (2.8740) grad_norm: 2.0039 (2.2069) time: 0.8665 [2021-03-26 17:58:00 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 20/1251] eta: 0:14:18 lr: 0.000214 loss: 2.9851 (2.9993) grad_norm: 1.9299 (2.0651) time: 0.5135 [2021-03-26 17:58:05 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 30/1251] eta: 0:12:53 lr: 0.000214 loss: 3.2014 (3.0575) grad_norm: 1.8659 (2.0435) time: 0.5048 [2021-03-26 17:58:10 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 40/1251] eta: 0:12:10 lr: 0.000214 loss: 3.1697 (3.0256) grad_norm: 1.8659 (2.0282) time: 0.5037 [2021-03-26 17:58:15 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 50/1251] eta: 0:11:38 lr: 0.000214 loss: 2.8878 (3.0040) grad_norm: 2.0506 (2.0569) time: 0.5026 [2021-03-26 17:58:20 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 60/1251] eta: 0:11:15 lr: 0.000214 loss: 3.0131 (2.9877) grad_norm: 2.0246 (2.0700) time: 0.4941 [2021-03-26 17:58:25 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 70/1251] eta: 0:10:59 lr: 0.000214 loss: 3.1652 (3.0010) grad_norm: 2.0107 (2.0673) time: 0.4987 [2021-03-26 17:58:30 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 80/1251] eta: 0:10:47 lr: 0.000214 loss: 3.1652 (2.9865) grad_norm: 1.9705 (2.0556) time: 0.5088 [2021-03-26 17:58:35 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 90/1251] eta: 0:10:35 lr: 0.000214 loss: 2.7129 (2.9418) grad_norm: 2.0060 (2.0581) time: 0.5076 [2021-03-26 17:58:40 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 100/1251] eta: 0:10:24 lr: 0.000214 loss: 2.9366 (2.9417) grad_norm: 2.0372 (2.0630) time: 0.5006 [2021-03-26 17:58:46 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 110/1251] eta: 0:10:16 lr: 0.000214 loss: 3.0330 (2.9496) grad_norm: 2.1625 (2.0921) time: 0.5074 [2021-03-26 17:58:51 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 120/1251] eta: 0:10:08 lr: 0.000214 loss: 2.9303 (2.9456) grad_norm: 2.1625 (2.0974) time: 0.5130 [2021-03-26 17:58:56 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 130/1251] eta: 0:10:00 lr: 0.000214 loss: 2.8247 (2.9460) grad_norm: 1.9764 (2.0874) time: 0.5093 [2021-03-26 17:59:01 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 140/1251] eta: 0:09:51 lr: 0.000214 loss: 3.1031 (2.9557) grad_norm: 1.9477 (2.0849) time: 0.5017 [2021-03-26 17:59:06 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 150/1251] eta: 0:09:43 lr: 0.000214 loss: 3.1040 (2.9563) grad_norm: 1.9983 (2.0829) time: 0.4961 [2021-03-26 17:59:11 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 160/1251] eta: 0:09:36 lr: 0.000214 loss: 3.0614 (2.9646) grad_norm: 1.9983 (2.0891) time: 0.4990 [2021-03-26 17:59:16 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 170/1251] eta: 0:09:29 lr: 0.000213 loss: 3.0036 (2.9637) grad_norm: 2.0353 (2.0948) time: 0.5020 [2021-03-26 17:59:21 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 180/1251] eta: 0:09:22 lr: 0.000213 loss: 3.1283 (2.9828) grad_norm: 2.0603 (2.0937) time: 0.4983 [2021-03-26 17:59:26 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 190/1251] eta: 0:09:15 lr: 0.000213 loss: 3.2932 (2.9978) grad_norm: 1.9742 (2.0893) time: 0.4970 [2021-03-26 17:59:31 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 200/1251] eta: 0:09:10 lr: 0.000213 loss: 3.1202 (2.9983) grad_norm: 1.9112 (2.0875) time: 0.5078 [2021-03-26 17:59:36 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 210/1251] eta: 0:09:04 lr: 0.000213 loss: 3.2745 (3.0197) grad_norm: 1.9567 (2.0830) time: 0.5135 [2021-03-26 17:59:41 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 220/1251] eta: 0:08:58 lr: 0.000213 loss: 3.2786 (3.0162) grad_norm: 1.9490 (2.0854) time: 0.5122 [2021-03-26 17:59:46 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 230/1251] eta: 0:08:52 lr: 0.000213 loss: 3.2652 (3.0314) grad_norm: 1.9580 (2.0877) time: 0.5087 [2021-03-26 17:59:51 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 240/1251] eta: 0:08:46 lr: 0.000213 loss: 3.3161 (3.0327) grad_norm: 2.0627 (2.0944) time: 0.5068 [2021-03-26 17:59:56 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 250/1251] eta: 0:08:41 lr: 0.000213 loss: 3.2352 (3.0334) grad_norm: 2.0981 (2.0962) time: 0.5086 [2021-03-26 18:00:01 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 260/1251] eta: 0:08:35 lr: 0.000213 loss: 3.1323 (3.0263) grad_norm: 2.0917 (2.0932) time: 0.5062 [2021-03-26 18:00:06 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 270/1251] eta: 0:08:29 lr: 0.000213 loss: 2.8084 (3.0194) grad_norm: 2.0784 (2.0926) time: 0.5017 [2021-03-26 18:00:11 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 280/1251] eta: 0:08:23 lr: 0.000213 loss: 2.8647 (3.0177) grad_norm: 1.9720 (2.0866) time: 0.4986 [2021-03-26 18:00:16 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 290/1251] eta: 0:08:17 lr: 0.000213 loss: 3.2244 (3.0263) grad_norm: 1.9720 (2.0866) time: 0.5022 [2021-03-26 18:00:22 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 300/1251] eta: 0:08:12 lr: 0.000213 loss: 3.2248 (3.0297) grad_norm: 2.0496 (2.0863) time: 0.5103 [2021-03-26 18:00:27 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 310/1251] eta: 0:08:07 lr: 0.000213 loss: 3.1991 (3.0366) grad_norm: 2.0394 (2.0951) time: 0.5185 [2021-03-26 18:00:32 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 320/1251] eta: 0:08:01 lr: 0.000213 loss: 3.0736 (3.0330) grad_norm: 1.9821 (2.0924) time: 0.5132 [2021-03-26 18:00:37 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 330/1251] eta: 0:07:56 lr: 0.000213 loss: 3.2200 (3.0440) grad_norm: 2.0142 (2.0929) time: 0.5049 [2021-03-26 18:00:42 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 340/1251] eta: 0:07:50 lr: 0.000213 loss: 3.2200 (3.0454) grad_norm: 2.0142 (2.0895) time: 0.5007 [2021-03-26 18:00:47 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 350/1251] eta: 0:07:44 lr: 0.000213 loss: 2.9997 (3.0454) grad_norm: 2.0107 (2.0905) time: 0.4945 [2021-03-26 18:00:52 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 360/1251] eta: 0:07:39 lr: 0.000213 loss: 3.1951 (3.0492) grad_norm: 2.0829 (2.0960) time: 0.4955 [2021-03-26 18:00:57 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 370/1251] eta: 0:07:33 lr: 0.000213 loss: 3.2059 (3.0498) grad_norm: 2.0796 (2.0939) time: 0.4943 [2021-03-26 18:01:02 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 380/1251] eta: 0:07:28 lr: 0.000213 loss: 3.1691 (3.0474) grad_norm: 2.0146 (2.0946) time: 0.4977 [2021-03-26 18:01:07 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 390/1251] eta: 0:07:22 lr: 0.000213 loss: 3.1059 (3.0485) grad_norm: 2.0007 (2.0938) time: 0.5041 [2021-03-26 18:01:12 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 400/1251] eta: 0:07:17 lr: 0.000213 loss: 3.1747 (3.0517) grad_norm: 2.0007 (2.0930) time: 0.5039 [2021-03-26 18:01:17 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 410/1251] eta: 0:07:11 lr: 0.000213 loss: 3.2791 (3.0529) grad_norm: 2.0077 (2.0908) time: 0.5024 [2021-03-26 18:01:22 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 420/1251] eta: 0:07:06 lr: 0.000213 loss: 3.0555 (3.0507) grad_norm: 1.9488 (2.0895) time: 0.5040 [2021-03-26 18:01:27 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 430/1251] eta: 0:07:01 lr: 0.000213 loss: 3.0555 (3.0532) grad_norm: 1.9010 (2.0863) time: 0.5069 [2021-03-26 18:01:32 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 440/1251] eta: 0:06:56 lr: 0.000213 loss: 3.0231 (3.0471) grad_norm: 1.9427 (2.0864) time: 0.5035 [2021-03-26 18:01:37 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 450/1251] eta: 0:06:50 lr: 0.000213 loss: 2.6984 (3.0364) grad_norm: 1.9444 (2.0827) time: 0.4979 [2021-03-26 18:01:42 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 460/1251] eta: 0:06:45 lr: 0.000213 loss: 2.8594 (3.0361) grad_norm: 1.8825 (2.0822) time: 0.4983 [2021-03-26 18:01:47 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 470/1251] eta: 0:06:39 lr: 0.000212 loss: 2.9289 (3.0319) grad_norm: 1.9277 (2.0824) time: 0.5002 [2021-03-26 18:01:52 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 480/1251] eta: 0:06:34 lr: 0.000212 loss: 2.8419 (3.0274) grad_norm: 1.9881 (2.0813) time: 0.4987 [2021-03-26 18:01:57 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 490/1251] eta: 0:06:29 lr: 0.000212 loss: 2.9954 (3.0265) grad_norm: 2.0365 (2.0820) time: 0.4967 [2021-03-26 18:02:02 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 500/1251] eta: 0:06:24 lr: 0.000212 loss: 3.0669 (3.0259) grad_norm: 2.1202 (2.0855) time: 0.5014 [2021-03-26 18:02:07 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 510/1251] eta: 0:06:18 lr: 0.000212 loss: 2.9597 (3.0241) grad_norm: 2.0698 (2.0848) time: 0.5062 [2021-03-26 18:02:12 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 520/1251] eta: 0:06:13 lr: 0.000212 loss: 2.9597 (3.0260) grad_norm: 2.0698 (2.0851) time: 0.4998 [2021-03-26 18:02:17 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 530/1251] eta: 0:06:08 lr: 0.000212 loss: 3.0917 (3.0230) grad_norm: 2.0254 (2.0834) time: 0.4967 [2021-03-26 18:02:22 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 540/1251] eta: 0:06:03 lr: 0.000212 loss: 3.1311 (3.0258) grad_norm: 2.1121 (2.0846) time: 0.5051 [2021-03-26 18:02:27 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 550/1251] eta: 0:05:58 lr: 0.000212 loss: 3.1595 (3.0272) grad_norm: 2.1932 (2.0924) time: 0.5148 [2021-03-26 18:02:32 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 560/1251] eta: 0:05:52 lr: 0.000212 loss: 3.1538 (3.0295) grad_norm: 2.0980 (2.0913) time: 0.5126 [2021-03-26 18:02:37 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 570/1251] eta: 0:05:47 lr: 0.000212 loss: 3.1538 (3.0319) grad_norm: 2.1124 (2.0942) time: 0.5045 [2021-03-26 18:02:42 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 580/1251] eta: 0:05:42 lr: 0.000212 loss: 3.2172 (3.0327) grad_norm: 2.1279 (2.0976) time: 0.5023 [2021-03-26 18:02:47 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 590/1251] eta: 0:05:37 lr: 0.000212 loss: 3.2155 (3.0360) grad_norm: 2.0388 (2.0983) time: 0.5075 [2021-03-26 18:02:53 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 600/1251] eta: 0:05:32 lr: 0.000212 loss: 3.1060 (3.0295) grad_norm: 2.0472 (2.0985) time: 0.5093 [2021-03-26 18:02:57 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 610/1251] eta: 0:05:27 lr: 0.000212 loss: 3.0281 (3.0285) grad_norm: 2.1211 (2.0993) time: 0.4999 [2021-03-26 18:03:03 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 620/1251] eta: 0:05:21 lr: 0.000212 loss: 3.1504 (3.0315) grad_norm: 1.9997 (2.0972) time: 0.5001 [2021-03-26 18:03:08 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 630/1251] eta: 0:05:16 lr: 0.000212 loss: 3.1834 (3.0305) grad_norm: 1.9611 (2.0952) time: 0.5130 [2021-03-26 18:03:13 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 640/1251] eta: 0:05:11 lr: 0.000212 loss: 3.1280 (3.0324) grad_norm: 1.9611 (2.0937) time: 0.5160 [2021-03-26 18:03:18 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 650/1251] eta: 0:05:06 lr: 0.000212 loss: 3.2972 (3.0361) grad_norm: 2.0731 (2.0958) time: 0.5058 [2021-03-26 18:03:23 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 660/1251] eta: 0:05:01 lr: 0.000212 loss: 3.2737 (3.0368) grad_norm: 2.0784 (2.0955) time: 0.5020 [2021-03-26 18:03:28 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 670/1251] eta: 0:04:56 lr: 0.000212 loss: 3.1775 (3.0361) grad_norm: 2.0006 (2.0935) time: 0.5043 [2021-03-26 18:03:33 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 680/1251] eta: 0:04:51 lr: 0.000212 loss: 3.0931 (3.0361) grad_norm: 2.0006 (2.0933) time: 0.5058 [2021-03-26 18:03:38 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 690/1251] eta: 0:04:46 lr: 0.000212 loss: 3.2533 (3.0401) grad_norm: 2.0331 (2.0944) time: 0.5046 [2021-03-26 18:03:43 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 700/1251] eta: 0:04:40 lr: 0.000212 loss: 3.2473 (3.0391) grad_norm: 2.2739 (2.0966) time: 0.5002 [2021-03-26 18:03:48 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 710/1251] eta: 0:04:35 lr: 0.000212 loss: 2.9444 (3.0383) grad_norm: 1.9954 (2.0952) time: 0.4985 [2021-03-26 18:03:53 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 720/1251] eta: 0:04:30 lr: 0.000212 loss: 2.9444 (3.0381) grad_norm: 1.8897 (2.0923) time: 0.5009 [2021-03-26 18:03:58 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 730/1251] eta: 0:04:25 lr: 0.000212 loss: 3.2077 (3.0413) grad_norm: 1.9094 (2.0924) time: 0.5048 [2021-03-26 18:04:03 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 740/1251] eta: 0:04:20 lr: 0.000212 loss: 3.2077 (3.0396) grad_norm: 1.9129 (2.0901) time: 0.5128 [2021-03-26 18:04:08 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 750/1251] eta: 0:04:15 lr: 0.000212 loss: 2.8177 (3.0383) grad_norm: 1.9968 (2.0896) time: 0.5176 [2021-03-26 18:04:14 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 760/1251] eta: 0:04:10 lr: 0.000212 loss: 2.8177 (3.0356) grad_norm: 2.0442 (2.0899) time: 0.5116 [2021-03-26 18:04:19 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 770/1251] eta: 0:04:05 lr: 0.000211 loss: 2.9939 (3.0348) grad_norm: 1.9684 (2.0880) time: 0.5085 [2021-03-26 18:04:24 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 780/1251] eta: 0:03:59 lr: 0.000211 loss: 2.9469 (3.0350) grad_norm: 1.9996 (2.0873) time: 0.5064 [2021-03-26 18:04:29 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 790/1251] eta: 0:03:54 lr: 0.000211 loss: 2.9469 (3.0319) grad_norm: 1.9469 (2.0849) time: 0.5089 [2021-03-26 18:04:34 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 800/1251] eta: 0:03:49 lr: 0.000211 loss: 3.0430 (3.0337) grad_norm: 1.9469 (2.0854) time: 0.5051 [2021-03-26 18:04:39 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 810/1251] eta: 0:03:44 lr: 0.000211 loss: 3.2022 (3.0336) grad_norm: 2.1647 (2.0860) time: 0.5000 [2021-03-26 18:04:44 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 820/1251] eta: 0:03:39 lr: 0.000211 loss: 2.9269 (3.0321) grad_norm: 2.1080 (2.0853) time: 0.5000 [2021-03-26 18:04:49 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 830/1251] eta: 0:03:34 lr: 0.000211 loss: 2.9486 (3.0334) grad_norm: 2.1080 (2.0866) time: 0.5001 [2021-03-26 18:04:54 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 840/1251] eta: 0:03:29 lr: 0.000211 loss: 3.2154 (3.0352) grad_norm: 2.1786 (2.0878) time: 0.5008 [2021-03-26 18:04:59 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 850/1251] eta: 0:03:24 lr: 0.000211 loss: 3.2685 (3.0383) grad_norm: 2.0911 (2.0876) time: 0.5015 [2021-03-26 18:05:04 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 860/1251] eta: 0:03:19 lr: 0.000211 loss: 3.2442 (3.0380) grad_norm: 2.1324 (2.0894) time: 0.5141 [2021-03-26 18:05:09 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 870/1251] eta: 0:03:13 lr: 0.000211 loss: 3.1072 (3.0391) grad_norm: 2.1324 (2.0900) time: 0.5150 [2021-03-26 18:05:14 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 880/1251] eta: 0:03:08 lr: 0.000211 loss: 3.2128 (3.0407) grad_norm: 2.0830 (2.0904) time: 0.5048 [2021-03-26 18:05:19 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 890/1251] eta: 0:03:03 lr: 0.000211 loss: 3.2128 (3.0420) grad_norm: 1.9906 (2.0889) time: 0.5016 [2021-03-26 18:05:24 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 900/1251] eta: 0:02:58 lr: 0.000211 loss: 3.1885 (3.0424) grad_norm: 1.9508 (2.0886) time: 0.5013 [2021-03-26 18:05:29 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 910/1251] eta: 0:02:53 lr: 0.000211 loss: 3.1238 (3.0407) grad_norm: 1.9408 (2.0879) time: 0.5013 [2021-03-26 18:05:34 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 920/1251] eta: 0:02:48 lr: 0.000211 loss: 3.1095 (3.0416) grad_norm: 1.9262 (2.0865) time: 0.5007 [2021-03-26 18:05:39 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 930/1251] eta: 0:02:43 lr: 0.000211 loss: 2.9757 (3.0388) grad_norm: 2.0083 (2.0872) time: 0.4981 [2021-03-26 18:05:44 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 940/1251] eta: 0:02:38 lr: 0.000211 loss: 2.7626 (3.0361) grad_norm: 2.0232 (2.0867) time: 0.5005 [2021-03-26 18:05:49 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 950/1251] eta: 0:02:33 lr: 0.000211 loss: 3.1269 (3.0379) grad_norm: 1.9980 (2.0869) time: 0.5105 [2021-03-26 18:05:55 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 960/1251] eta: 0:02:28 lr: 0.000211 loss: 3.1896 (3.0386) grad_norm: 1.9189 (2.0861) time: 0.5199 [2021-03-26 18:06:00 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 970/1251] eta: 0:02:22 lr: 0.000211 loss: 3.1440 (3.0374) grad_norm: 1.9059 (2.0845) time: 0.5088 [2021-03-26 18:06:05 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 980/1251] eta: 0:02:17 lr: 0.000211 loss: 3.0546 (3.0367) grad_norm: 1.9973 (2.0843) time: 0.5005 [2021-03-26 18:06:10 swin_small_patch4_window7_224] INFO: Epoch: [210] [ 990/1251] eta: 0:02:12 lr: 0.000211 loss: 3.0546 (3.0360) grad_norm: 1.9250 (2.0821) time: 0.5034 [2021-03-26 18:06:15 swin_small_patch4_window7_224] INFO: Epoch: [210] [1000/1251] eta: 0:02:07 lr: 0.000211 loss: 3.2750 (3.0382) grad_norm: 1.9250 (2.0813) time: 0.5023 [2021-03-26 18:06:20 swin_small_patch4_window7_224] INFO: Epoch: [210] [1010/1251] eta: 0:02:02 lr: 0.000211 loss: 3.2172 (3.0376) grad_norm: 2.0347 (2.0817) time: 0.5034 [2021-03-26 18:06:25 swin_small_patch4_window7_224] INFO: Epoch: [210] [1020/1251] eta: 0:01:57 lr: 0.000211 loss: 3.2133 (3.0401) grad_norm: 2.1304 (2.0824) time: 0.5022 [2021-03-26 18:06:30 swin_small_patch4_window7_224] INFO: Epoch: [210] [1030/1251] eta: 0:01:52 lr: 0.000211 loss: 3.1108 (3.0391) grad_norm: 1.9808 (2.0811) time: 0.4985 [2021-03-26 18:06:35 swin_small_patch4_window7_224] INFO: Epoch: [210] [1040/1251] eta: 0:01:47 lr: 0.000211 loss: 3.1212 (3.0398) grad_norm: 1.9899 (2.0813) time: 0.4982 [2021-03-26 18:06:40 swin_small_patch4_window7_224] INFO: Epoch: [210] [1050/1251] eta: 0:01:42 lr: 0.000211 loss: 3.1819 (3.0409) grad_norm: 2.0276 (2.0809) time: 0.5158 [2021-03-26 18:06:45 swin_small_patch4_window7_224] INFO: Epoch: [210] [1060/1251] eta: 0:01:37 lr: 0.000211 loss: 3.2711 (3.0417) grad_norm: 1.9587 (2.0799) time: 0.5137 [2021-03-26 18:06:50 swin_small_patch4_window7_224] INFO: Epoch: [210] [1070/1251] eta: 0:01:31 lr: 0.000210 loss: 3.1743 (3.0408) grad_norm: 1.9632 (2.0794) time: 0.5028 [2021-03-26 18:06:55 swin_small_patch4_window7_224] INFO: Epoch: [210] [1080/1251] eta: 0:01:26 lr: 0.000210 loss: 3.1737 (3.0387) grad_norm: 2.0380 (2.0795) time: 0.5070 [2021-03-26 18:07:00 swin_small_patch4_window7_224] INFO: Epoch: [210] [1090/1251] eta: 0:01:21 lr: 0.000210 loss: 2.8156 (3.0375) grad_norm: 2.0415 (2.0798) time: 0.5020 [2021-03-26 18:07:05 swin_small_patch4_window7_224] INFO: Epoch: [210] [1100/1251] eta: 0:01:16 lr: 0.000210 loss: 2.8156 (3.0370) grad_norm: 2.0104 (2.0793) time: 0.4999 [2021-03-26 18:07:10 swin_small_patch4_window7_224] INFO: Epoch: [210] [1110/1251] eta: 0:01:11 lr: 0.000210 loss: 3.0183 (3.0387) grad_norm: 1.9667 (2.0792) time: 0.4995 [2021-03-26 18:07:15 swin_small_patch4_window7_224] INFO: Epoch: [210] [1120/1251] eta: 0:01:06 lr: 0.000210 loss: 3.3447 (3.0405) grad_norm: 1.9520 (2.0783) time: 0.4956 [2021-03-26 18:07:20 swin_small_patch4_window7_224] INFO: Epoch: [210] [1130/1251] eta: 0:01:01 lr: 0.000210 loss: 3.2244 (3.0406) grad_norm: 1.9066 (2.0780) time: 0.4974 [2021-03-26 18:07:25 swin_small_patch4_window7_224] INFO: Epoch: [210] [1140/1251] eta: 0:00:56 lr: 0.000210 loss: 3.1981 (3.0405) grad_norm: 1.9276 (2.0770) time: 0.5024 [2021-03-26 18:07:30 swin_small_patch4_window7_224] INFO: Epoch: [210] [1150/1251] eta: 0:00:51 lr: 0.000210 loss: 3.1726 (3.0411) grad_norm: 1.9669 (2.0768) time: 0.5028 [2021-03-26 18:07:35 swin_small_patch4_window7_224] INFO: Epoch: [210] [1160/1251] eta: 0:00:46 lr: 0.000210 loss: 3.0830 (3.0408) grad_norm: 2.0099 (2.0759) time: 0.4996 [2021-03-26 18:07:40 swin_small_patch4_window7_224] INFO: Epoch: [210] [1170/1251] eta: 0:00:41 lr: 0.000210 loss: 2.9247 (3.0390) grad_norm: 2.0338 (2.0767) time: 0.5035 [2021-03-26 18:07:45 swin_small_patch4_window7_224] INFO: Epoch: [210] [1180/1251] eta: 0:00:36 lr: 0.000210 loss: 2.9247 (3.0385) grad_norm: 1.9287 (2.0749) time: 0.5028 [2021-03-26 18:07:50 swin_small_patch4_window7_224] INFO: Epoch: [210] [1190/1251] eta: 0:00:30 lr: 0.000210 loss: 3.1495 (3.0383) grad_norm: 1.8392 (2.0734) time: 0.5022 [2021-03-26 18:07:55 swin_small_patch4_window7_224] INFO: Epoch: [210] [1200/1251] eta: 0:00:25 lr: 0.000210 loss: 3.0371 (3.0374) grad_norm: 1.9334 (2.0735) time: 0.5041 [2021-03-26 18:08:00 swin_small_patch4_window7_224] INFO: Epoch: [210] [1210/1251] eta: 0:00:20 lr: 0.000210 loss: 2.8285 (3.0354) grad_norm: 2.0322 (2.0733) time: 0.5051 [2021-03-26 18:08:05 swin_small_patch4_window7_224] INFO: Epoch: [210] [1220/1251] eta: 0:00:15 lr: 0.000210 loss: 2.7961 (3.0331) grad_norm: 2.0030 (2.0736) time: 0.5089 [2021-03-26 18:08:10 swin_small_patch4_window7_224] INFO: Epoch: [210] [1230/1251] eta: 0:00:10 lr: 0.000210 loss: 2.9064 (3.0330) grad_norm: 1.9443 (2.0745) time: 0.5046 [2021-03-26 18:08:16 swin_small_patch4_window7_224] INFO: Epoch: [210] [1240/1251] eta: 0:00:05 lr: 0.000210 loss: 2.9830 (3.0313) grad_norm: 2.0971 (2.0745) time: 0.5066 [2021-03-26 18:08:21 swin_small_patch4_window7_224] INFO: Epoch: [210] [1250/1251] eta: 0:00:00 lr: 0.000210 loss: 3.1559 (3.0325) grad_norm: 2.0215 (2.0741) time: 0.5070 [2021-03-26 18:09:06 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 0.7596 (0.7596) acc1: 78.1250 (78.1250) acc5: 93.7500 (93.7500) [2021-03-26 18:09:07 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.8089 (0.8393) acc1: 78.1250 (77.9830) acc5: 95.3125 (94.7443) [2021-03-26 18:09:09 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.8089 (0.8267) acc1: 78.1250 (79.0179) acc5: 95.3125 (95.2381) [2021-03-26 18:09:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7696 (0.7870) acc1: 79.6875 (79.6371) acc5: 96.8750 (95.8669) [2021-03-26 18:09:11 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7155 (0.8067) acc1: 79.6875 (79.1921) acc5: 96.8750 (95.6936) [2021-03-26 18:09:12 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7193 (0.7999) acc1: 81.2500 (79.5520) acc5: 94.3396 (95.5840) [2021-03-26 18:09:22 swin_small_patch4_window7_224] INFO: * Acc@1 81.060 Acc@5 95.670 loss 0.787 [2021-03-26 18:09:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.1% [2021-03-26 18:09:22 swin_small_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-26 18:09:26 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 0/1251] eta: 1:27:08 lr: 0.000210 loss: 2.8322 (2.8322) grad_norm: 2.3449 (2.3449) time: 4.1796 [2021-03-26 18:09:31 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 10/1251] eta: 0:17:43 lr: 0.000210 loss: 2.9966 (2.8937) grad_norm: 2.0399 (2.1097) time: 0.8566 [2021-03-26 18:09:36 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 20/1251] eta: 0:14:08 lr: 0.000210 loss: 2.9966 (2.8532) grad_norm: 1.9756 (2.0219) time: 0.5151 [2021-03-26 18:09:41 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 30/1251] eta: 0:12:47 lr: 0.000210 loss: 3.0012 (2.9351) grad_norm: 1.9727 (2.0345) time: 0.5032 [2021-03-26 18:09:46 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 40/1251] eta: 0:12:03 lr: 0.000210 loss: 3.0012 (2.9332) grad_norm: 2.0946 (2.0295) time: 0.5008 [2021-03-26 18:09:52 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 50/1251] eta: 0:11:37 lr: 0.000210 loss: 3.1328 (2.9904) grad_norm: 1.9542 (2.0250) time: 0.5071 [2021-03-26 18:09:57 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 60/1251] eta: 0:11:18 lr: 0.000210 loss: 3.2230 (3.0047) grad_norm: 1.9280 (2.0341) time: 0.5130 [2021-03-26 18:10:02 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 70/1251] eta: 0:11:01 lr: 0.000210 loss: 3.0690 (2.9796) grad_norm: 1.8747 (2.0170) time: 0.5056 [2021-03-26 18:10:07 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 80/1251] eta: 0:10:49 lr: 0.000210 loss: 2.9898 (2.9873) grad_norm: 1.8971 (2.0097) time: 0.5086 [2021-03-26 18:10:12 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 90/1251] eta: 0:10:37 lr: 0.000210 loss: 2.9856 (2.9834) grad_norm: 2.0056 (2.0179) time: 0.5133 [2021-03-26 18:10:17 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 100/1251] eta: 0:10:27 lr: 0.000210 loss: 2.9856 (2.9899) grad_norm: 2.1182 (2.0307) time: 0.5061 [2021-03-26 18:10:22 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 110/1251] eta: 0:10:17 lr: 0.000210 loss: 3.0658 (2.9978) grad_norm: 2.0246 (2.0238) time: 0.5037 [2021-03-26 18:10:27 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 120/1251] eta: 0:10:09 lr: 0.000209 loss: 2.9771 (2.9975) grad_norm: 2.0124 (2.0316) time: 0.5060 [2021-03-26 18:10:32 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 130/1251] eta: 0:10:02 lr: 0.000209 loss: 2.9527 (3.0041) grad_norm: 2.0794 (2.0364) time: 0.5162 [2021-03-26 18:10:38 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 140/1251] eta: 0:09:55 lr: 0.000209 loss: 3.0790 (3.0006) grad_norm: 2.0321 (2.0327) time: 0.5217 [2021-03-26 18:10:43 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 150/1251] eta: 0:09:48 lr: 0.000209 loss: 3.0608 (2.9939) grad_norm: 1.9680 (2.0320) time: 0.5132 [2021-03-26 18:10:48 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 160/1251] eta: 0:09:41 lr: 0.000209 loss: 3.0277 (2.9860) grad_norm: 1.9680 (2.0295) time: 0.5081 [2021-03-26 18:10:53 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 170/1251] eta: 0:09:33 lr: 0.000209 loss: 2.8616 (2.9715) grad_norm: 1.9809 (2.0288) time: 0.5057 [2021-03-26 18:10:58 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 180/1251] eta: 0:09:26 lr: 0.000209 loss: 2.8666 (2.9703) grad_norm: 2.0287 (2.0324) time: 0.5004 [2021-03-26 18:11:03 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 190/1251] eta: 0:09:19 lr: 0.000209 loss: 3.0301 (2.9713) grad_norm: 2.0614 (2.0366) time: 0.5012 [2021-03-26 18:11:08 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 200/1251] eta: 0:09:13 lr: 0.000209 loss: 2.7396 (2.9625) grad_norm: 2.0513 (2.0367) time: 0.5060 [2021-03-26 18:11:13 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 210/1251] eta: 0:09:06 lr: 0.000209 loss: 3.2273 (2.9740) grad_norm: 1.9296 (2.0335) time: 0.5021 [2021-03-26 18:11:18 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 220/1251] eta: 0:09:00 lr: 0.000209 loss: 3.2273 (2.9787) grad_norm: 1.9849 (2.0346) time: 0.4994 [2021-03-26 18:11:23 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 230/1251] eta: 0:08:53 lr: 0.000209 loss: 3.2471 (2.9886) grad_norm: 2.1525 (2.0429) time: 0.4970 [2021-03-26 18:11:28 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 240/1251] eta: 0:08:48 lr: 0.000209 loss: 3.3795 (2.9965) grad_norm: 2.1501 (2.0475) time: 0.5019 [2021-03-26 18:11:33 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 250/1251] eta: 0:08:42 lr: 0.000209 loss: 2.9122 (2.9865) grad_norm: 1.9150 (2.0430) time: 0.5097 [2021-03-26 18:11:38 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 260/1251] eta: 0:08:36 lr: 0.000209 loss: 2.5835 (2.9779) grad_norm: 1.9044 (2.0408) time: 0.5038 [2021-03-26 18:11:43 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 270/1251] eta: 0:08:30 lr: 0.000209 loss: 2.8000 (2.9719) grad_norm: 1.9217 (2.0423) time: 0.5002 [2021-03-26 18:11:48 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 280/1251] eta: 0:08:24 lr: 0.000209 loss: 3.1881 (2.9855) grad_norm: 2.0484 (2.0423) time: 0.4994 [2021-03-26 18:11:53 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 290/1251] eta: 0:08:18 lr: 0.000209 loss: 3.2377 (2.9845) grad_norm: 1.9627 (2.0386) time: 0.5002 [2021-03-26 18:11:58 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 300/1251] eta: 0:08:12 lr: 0.000209 loss: 3.1741 (2.9891) grad_norm: 1.9355 (2.0384) time: 0.5025 [2021-03-26 18:12:03 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 310/1251] eta: 0:08:07 lr: 0.000209 loss: 3.1320 (2.9904) grad_norm: 1.9843 (2.0420) time: 0.5006 [2021-03-26 18:12:08 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 320/1251] eta: 0:08:01 lr: 0.000209 loss: 3.2175 (2.9969) grad_norm: 2.0945 (2.0437) time: 0.5045 [2021-03-26 18:12:13 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 330/1251] eta: 0:07:56 lr: 0.000209 loss: 3.2175 (2.9969) grad_norm: 2.0982 (2.0466) time: 0.5084 [2021-03-26 18:12:18 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 340/1251] eta: 0:07:51 lr: 0.000209 loss: 3.1108 (2.9998) grad_norm: 2.0506 (2.0461) time: 0.5142 [2021-03-26 18:12:23 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 350/1251] eta: 0:07:45 lr: 0.000209 loss: 3.0760 (2.9976) grad_norm: 1.9959 (2.0439) time: 0.5105 [2021-03-26 18:12:28 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 360/1251] eta: 0:07:40 lr: 0.000209 loss: 2.8213 (2.9935) grad_norm: 1.9852 (2.0436) time: 0.4988 [2021-03-26 18:12:33 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 370/1251] eta: 0:07:34 lr: 0.000209 loss: 2.7950 (2.9911) grad_norm: 2.0569 (2.0433) time: 0.5012 [2021-03-26 18:12:38 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 380/1251] eta: 0:07:29 lr: 0.000209 loss: 2.9969 (2.9933) grad_norm: 2.0185 (2.0409) time: 0.5028 [2021-03-26 18:12:44 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 390/1251] eta: 0:07:23 lr: 0.000209 loss: 2.9969 (2.9852) grad_norm: 1.9815 (2.0408) time: 0.5044 [2021-03-26 18:12:48 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 400/1251] eta: 0:07:18 lr: 0.000209 loss: 3.1335 (2.9938) grad_norm: 2.0036 (2.0411) time: 0.4992 [2021-03-26 18:12:54 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 410/1251] eta: 0:07:12 lr: 0.000209 loss: 3.1751 (2.9926) grad_norm: 2.0294 (2.0395) time: 0.4989 [2021-03-26 18:12:59 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 420/1251] eta: 0:07:07 lr: 0.000208 loss: 3.2046 (2.9987) grad_norm: 1.9656 (2.0416) time: 0.5081 [2021-03-26 18:13:04 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 430/1251] eta: 0:07:02 lr: 0.000208 loss: 3.2046 (2.9971) grad_norm: 1.9656 (2.0472) time: 0.5107 [2021-03-26 18:13:09 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 440/1251] eta: 0:06:56 lr: 0.000208 loss: 3.1231 (3.0044) grad_norm: 2.1662 (2.0493) time: 0.5060 [2021-03-26 18:13:14 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 450/1251] eta: 0:06:51 lr: 0.000208 loss: 3.2577 (3.0094) grad_norm: 2.1451 (2.0517) time: 0.5033 [2021-03-26 18:13:19 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 460/1251] eta: 0:06:46 lr: 0.000208 loss: 3.2332 (3.0124) grad_norm: 1.9912 (2.0497) time: 0.5022 [2021-03-26 18:13:24 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 470/1251] eta: 0:06:40 lr: 0.000208 loss: 3.1389 (3.0145) grad_norm: 2.0211 (2.0537) time: 0.4996 [2021-03-26 18:13:29 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 480/1251] eta: 0:06:35 lr: 0.000208 loss: 3.0462 (3.0107) grad_norm: 2.0549 (2.0529) time: 0.4996 [2021-03-26 18:13:34 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 490/1251] eta: 0:06:30 lr: 0.000208 loss: 2.7436 (3.0034) grad_norm: 2.0313 (2.0549) time: 0.5020 [2021-03-26 18:13:39 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 500/1251] eta: 0:06:24 lr: 0.000208 loss: 2.8532 (2.9974) grad_norm: 2.0466 (2.0544) time: 0.4996 [2021-03-26 18:13:44 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 510/1251] eta: 0:06:19 lr: 0.000208 loss: 3.0807 (2.9998) grad_norm: 2.0206 (2.0536) time: 0.4972 [2021-03-26 18:13:49 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 520/1251] eta: 0:06:14 lr: 0.000208 loss: 3.1767 (3.0014) grad_norm: 2.0917 (2.0614) time: 0.5038 [2021-03-26 18:13:54 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 530/1251] eta: 0:06:08 lr: 0.000208 loss: 3.2447 (3.0030) grad_norm: 2.1054 (2.0605) time: 0.4996 [2021-03-26 18:13:59 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 540/1251] eta: 0:06:03 lr: 0.000208 loss: 3.1905 (3.0060) grad_norm: 1.9918 (2.0599) time: 0.4951 [2021-03-26 18:14:04 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 550/1251] eta: 0:05:58 lr: 0.000208 loss: 3.0815 (3.0033) grad_norm: 1.9402 (2.0577) time: 0.5085 [2021-03-26 18:14:09 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 560/1251] eta: 0:05:53 lr: 0.000208 loss: 3.0328 (3.0054) grad_norm: 1.9074 (2.0563) time: 0.5164 [2021-03-26 18:14:14 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 570/1251] eta: 0:05:48 lr: 0.000208 loss: 2.9288 (3.0014) grad_norm: 1.9829 (2.0557) time: 0.5064 [2021-03-26 18:14:19 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 580/1251] eta: 0:05:42 lr: 0.000208 loss: 2.5905 (2.9963) grad_norm: 2.0027 (2.0548) time: 0.4976 [2021-03-26 18:14:24 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 590/1251] eta: 0:05:37 lr: 0.000208 loss: 3.2055 (3.0021) grad_norm: 2.0110 (2.0539) time: 0.5008 [2021-03-26 18:14:29 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 600/1251] eta: 0:05:32 lr: 0.000208 loss: 3.2055 (3.0027) grad_norm: 1.9987 (2.0547) time: 0.5066 [2021-03-26 18:14:34 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 610/1251] eta: 0:05:27 lr: 0.000208 loss: 3.2122 (3.0064) grad_norm: 1.9946 (2.0541) time: 0.5074 [2021-03-26 18:14:39 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 620/1251] eta: 0:05:22 lr: 0.000208 loss: 3.3751 (3.0102) grad_norm: 1.9614 (2.0538) time: 0.5020 [2021-03-26 18:14:44 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 630/1251] eta: 0:05:17 lr: 0.000208 loss: 3.2831 (3.0127) grad_norm: 1.9588 (2.0547) time: 0.5005 [2021-03-26 18:14:49 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 640/1251] eta: 0:05:12 lr: 0.000208 loss: 2.9765 (3.0094) grad_norm: 1.9701 (2.0540) time: 0.5131 [2021-03-26 18:14:54 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 650/1251] eta: 0:05:06 lr: 0.000208 loss: 3.0377 (3.0094) grad_norm: 1.9987 (nan) time: 0.5051 [2021-03-26 18:14:59 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 660/1251] eta: 0:05:01 lr: 0.000208 loss: 3.0614 (3.0057) grad_norm: 2.0071 (nan) time: 0.4939 [2021-03-26 18:15:04 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 670/1251] eta: 0:04:56 lr: 0.000208 loss: 2.9617 (3.0071) grad_norm: 2.0071 (nan) time: 0.5028 [2021-03-26 18:15:10 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 680/1251] eta: 0:04:51 lr: 0.000208 loss: 3.1841 (3.0072) grad_norm: 2.1313 (nan) time: 0.5099 [2021-03-26 18:15:15 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 690/1251] eta: 0:04:46 lr: 0.000208 loss: 3.0702 (3.0052) grad_norm: 2.1072 (nan) time: 0.5116 [2021-03-26 18:15:20 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 700/1251] eta: 0:04:41 lr: 0.000208 loss: 3.0088 (3.0067) grad_norm: 2.0806 (nan) time: 0.5089 [2021-03-26 18:15:25 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 710/1251] eta: 0:04:36 lr: 0.000208 loss: 3.1962 (3.0089) grad_norm: 2.0629 (nan) time: 0.5108 [2021-03-26 18:15:30 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 720/1251] eta: 0:04:30 lr: 0.000207 loss: 3.1415 (3.0108) grad_norm: 2.0380 (nan) time: 0.5108 [2021-03-26 18:15:35 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 730/1251] eta: 0:04:25 lr: 0.000207 loss: 3.1415 (3.0139) grad_norm: 1.9649 (nan) time: 0.5086 [2021-03-26 18:15:40 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 740/1251] eta: 0:04:20 lr: 0.000207 loss: 3.1461 (3.0143) grad_norm: 1.9649 (nan) time: 0.5181 [2021-03-26 18:15:45 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 750/1251] eta: 0:04:15 lr: 0.000207 loss: 2.9891 (3.0157) grad_norm: 2.0385 (nan) time: 0.5112 [2021-03-26 18:15:50 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 760/1251] eta: 0:04:10 lr: 0.000207 loss: 3.2270 (3.0177) grad_norm: 2.0385 (nan) time: 0.4994 [2021-03-26 18:15:55 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 770/1251] eta: 0:04:05 lr: 0.000207 loss: 3.2371 (3.0179) grad_norm: 1.9942 (nan) time: 0.5047 [2021-03-26 18:16:00 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 780/1251] eta: 0:04:00 lr: 0.000207 loss: 3.0344 (3.0154) grad_norm: 1.9942 (nan) time: 0.5036 [2021-03-26 18:16:06 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 790/1251] eta: 0:03:55 lr: 0.000207 loss: 2.8647 (3.0136) grad_norm: 2.0008 (nan) time: 0.5087 [2021-03-26 18:16:11 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 800/1251] eta: 0:03:50 lr: 0.000207 loss: 2.8647 (3.0122) grad_norm: 2.0062 (nan) time: 0.5113 [2021-03-26 18:16:16 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 810/1251] eta: 0:03:44 lr: 0.000207 loss: 3.1664 (3.0174) grad_norm: 2.0354 (nan) time: 0.5065 [2021-03-26 18:16:21 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 820/1251] eta: 0:03:39 lr: 0.000207 loss: 3.2384 (3.0166) grad_norm: 2.0624 (nan) time: 0.5033 [2021-03-26 18:16:26 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 830/1251] eta: 0:03:34 lr: 0.000207 loss: 3.0563 (3.0172) grad_norm: 2.0097 (nan) time: 0.5107 [2021-03-26 18:16:31 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 840/1251] eta: 0:03:29 lr: 0.000207 loss: 3.0563 (3.0175) grad_norm: 1.9537 (nan) time: 0.5099 [2021-03-26 18:16:36 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 850/1251] eta: 0:03:24 lr: 0.000207 loss: 3.1901 (3.0186) grad_norm: 1.9483 (nan) time: 0.5039 [2021-03-26 18:16:41 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 860/1251] eta: 0:03:19 lr: 0.000207 loss: 3.0693 (3.0182) grad_norm: 1.9483 (nan) time: 0.5058 [2021-03-26 18:16:46 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 870/1251] eta: 0:03:14 lr: 0.000207 loss: 3.1025 (3.0189) grad_norm: 1.9700 (nan) time: 0.5114 [2021-03-26 18:16:51 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 880/1251] eta: 0:03:09 lr: 0.000207 loss: 3.1025 (3.0175) grad_norm: 1.9700 (nan) time: 0.5176 [2021-03-26 18:16:57 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 890/1251] eta: 0:03:04 lr: 0.000207 loss: 3.0440 (3.0171) grad_norm: 2.0590 (nan) time: 0.5149 [2021-03-26 18:17:02 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 900/1251] eta: 0:02:58 lr: 0.000207 loss: 3.1170 (3.0168) grad_norm: 2.0953 (nan) time: 0.5069 [2021-03-26 18:17:07 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 910/1251] eta: 0:02:53 lr: 0.000207 loss: 2.8652 (3.0135) grad_norm: 2.2156 (nan) time: 0.4993 [2021-03-26 18:17:12 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 920/1251] eta: 0:02:48 lr: 0.000207 loss: 3.0684 (3.0153) grad_norm: 2.2136 (nan) time: 0.5017 [2021-03-26 18:17:17 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 930/1251] eta: 0:02:43 lr: 0.000207 loss: 3.2070 (3.0153) grad_norm: 2.0794 (nan) time: 0.5026 [2021-03-26 18:17:22 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 940/1251] eta: 0:02:38 lr: 0.000207 loss: 3.1363 (3.0146) grad_norm: 2.0682 (nan) time: 0.5059 [2021-03-26 18:17:27 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 950/1251] eta: 0:02:33 lr: 0.000207 loss: 3.0108 (3.0145) grad_norm: 2.0682 (nan) time: 0.5122 [2021-03-26 18:17:32 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 960/1251] eta: 0:02:28 lr: 0.000207 loss: 3.0520 (3.0158) grad_norm: 2.1247 (nan) time: 0.5052 [2021-03-26 18:17:37 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 970/1251] eta: 0:02:23 lr: 0.000207 loss: 3.1092 (3.0147) grad_norm: 2.1252 (nan) time: 0.5011 [2021-03-26 18:17:42 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 980/1251] eta: 0:02:18 lr: 0.000207 loss: 3.1655 (3.0167) grad_norm: 2.0307 (nan) time: 0.5086 [2021-03-26 18:17:47 swin_small_patch4_window7_224] INFO: Epoch: [211] [ 990/1251] eta: 0:02:12 lr: 0.000207 loss: 3.0213 (3.0162) grad_norm: 1.9992 (nan) time: 0.5049 [2021-03-26 18:17:52 swin_small_patch4_window7_224] INFO: Epoch: [211] [1000/1251] eta: 0:02:07 lr: 0.000207 loss: 3.0213 (3.0175) grad_norm: 1.9887 (nan) time: 0.5014 [2021-03-26 18:17:57 swin_small_patch4_window7_224] INFO: Epoch: [211] [1010/1251] eta: 0:02:02 lr: 0.000207 loss: 3.1331 (3.0182) grad_norm: 2.1571 (nan) time: 0.5037 [2021-03-26 18:18:02 swin_small_patch4_window7_224] INFO: Epoch: [211] [1020/1251] eta: 0:01:57 lr: 0.000206 loss: 3.1331 (3.0189) grad_norm: 2.1430 (nan) time: 0.5002 [2021-03-26 18:18:07 swin_small_patch4_window7_224] INFO: Epoch: [211] [1030/1251] eta: 0:01:52 lr: 0.000206 loss: 2.9725 (3.0191) grad_norm: 1.9976 (nan) time: 0.5016 [2021-03-26 18:18:12 swin_small_patch4_window7_224] INFO: Epoch: [211] [1040/1251] eta: 0:01:47 lr: 0.000206 loss: 2.9211 (3.0171) grad_norm: 2.0691 (nan) time: 0.5046 [2021-03-26 18:18:17 swin_small_patch4_window7_224] INFO: Epoch: [211] [1050/1251] eta: 0:01:42 lr: 0.000206 loss: 3.1037 (3.0187) grad_norm: 2.0730 (nan) time: 0.5046 [2021-03-26 18:18:22 swin_small_patch4_window7_224] INFO: Epoch: [211] [1060/1251] eta: 0:01:37 lr: 0.000206 loss: 3.3446 (3.0210) grad_norm: 1.9335 (nan) time: 0.5085 [2021-03-26 18:18:27 swin_small_patch4_window7_224] INFO: Epoch: [211] [1070/1251] eta: 0:01:32 lr: 0.000206 loss: 3.1055 (3.0217) grad_norm: 1.9108 (nan) time: 0.5073 [2021-03-26 18:18:32 swin_small_patch4_window7_224] INFO: Epoch: [211] [1080/1251] eta: 0:01:27 lr: 0.000206 loss: 3.0222 (3.0194) grad_norm: 1.9920 (nan) time: 0.5016 [2021-03-26 18:18:37 swin_small_patch4_window7_224] INFO: Epoch: [211] [1090/1251] eta: 0:01:21 lr: 0.000206 loss: 2.8666 (3.0180) grad_norm: 2.0515 (nan) time: 0.5051 [2021-03-26 18:18:42 swin_small_patch4_window7_224] INFO: Epoch: [211] [1100/1251] eta: 0:01:16 lr: 0.000206 loss: 2.8478 (3.0152) grad_norm: 2.1047 (nan) time: 0.5031 [2021-03-26 18:18:47 swin_small_patch4_window7_224] INFO: Epoch: [211] [1110/1251] eta: 0:01:11 lr: 0.000206 loss: 2.8999 (3.0145) grad_norm: 2.0454 (nan) time: 0.4967 [2021-03-26 18:18:52 swin_small_patch4_window7_224] INFO: Epoch: [211] [1120/1251] eta: 0:01:06 lr: 0.000206 loss: 2.9594 (3.0133) grad_norm: 1.9464 (nan) time: 0.4979 [2021-03-26 18:18:57 swin_small_patch4_window7_224] INFO: Epoch: [211] [1130/1251] eta: 0:01:01 lr: 0.000206 loss: 3.0882 (3.0144) grad_norm: 2.0052 (nan) time: 0.4982 [2021-03-26 18:19:02 swin_small_patch4_window7_224] INFO: Epoch: [211] [1140/1251] eta: 0:00:56 lr: 0.000206 loss: 3.2478 (3.0148) grad_norm: 2.0871 (nan) time: 0.5012 [2021-03-26 18:19:07 swin_small_patch4_window7_224] INFO: Epoch: [211] [1150/1251] eta: 0:00:51 lr: 0.000206 loss: 3.0804 (3.0131) grad_norm: 2.0189 (nan) time: 0.5055 [2021-03-26 18:19:12 swin_small_patch4_window7_224] INFO: Epoch: [211] [1160/1251] eta: 0:00:46 lr: 0.000206 loss: 3.0109 (3.0134) grad_norm: 1.9811 (nan) time: 0.5052 [2021-03-26 18:19:18 swin_small_patch4_window7_224] INFO: Epoch: [211] [1170/1251] eta: 0:00:41 lr: 0.000206 loss: 3.2547 (3.0146) grad_norm: 2.0349 (nan) time: 0.5043 [2021-03-26 18:19:23 swin_small_patch4_window7_224] INFO: Epoch: [211] [1180/1251] eta: 0:00:36 lr: 0.000206 loss: 3.2381 (3.0141) grad_norm: 2.0736 (nan) time: 0.5059 [2021-03-26 18:19:28 swin_small_patch4_window7_224] INFO: Epoch: [211] [1190/1251] eta: 0:00:31 lr: 0.000206 loss: 3.0326 (3.0137) grad_norm: 2.0895 (nan) time: 0.5039 [2021-03-26 18:19:33 swin_small_patch4_window7_224] INFO: Epoch: [211] [1200/1251] eta: 0:00:25 lr: 0.000206 loss: 3.1331 (3.0117) grad_norm: 2.0895 (nan) time: 0.5009 [2021-03-26 18:19:38 swin_small_patch4_window7_224] INFO: Epoch: [211] [1210/1251] eta: 0:00:20 lr: 0.000206 loss: 2.8732 (3.0111) grad_norm: 2.1004 (nan) time: 0.5009 [2021-03-26 18:19:43 swin_small_patch4_window7_224] INFO: Epoch: [211] [1220/1251] eta: 0:00:15 lr: 0.000206 loss: 2.8732 (3.0107) grad_norm: 1.9929 (nan) time: 0.4990 [2021-03-26 18:19:48 swin_small_patch4_window7_224] INFO: Epoch: [211] [1230/1251] eta: 0:00:10 lr: 0.000206 loss: 2.9489 (3.0124) grad_norm: 2.0315 (nan) time: 0.4987 [2021-03-26 18:19:53 swin_small_patch4_window7_224] INFO: Epoch: [211] [1240/1251] eta: 0:00:05 lr: 0.000206 loss: 3.1358 (3.0130) grad_norm: 2.0557 (nan) time: 0.5017 [2021-03-26 18:19:58 swin_small_patch4_window7_224] INFO: Epoch: [211] [1250/1251] eta: 0:00:00 lr: 0.000206 loss: 3.0888 (3.0136) grad_norm: 1.9987 (nan) time: 0.5026 [2021-03-26 18:20:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:17 loss: 0.9612 (0.9612) acc1: 76.5625 (76.5625) acc5: 92.1875 (92.1875) [2021-03-26 18:20:10 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.9321 (0.8606) acc1: 79.6875 (78.6932) acc5: 95.3125 (95.3125) [2021-03-26 18:20:12 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7577 (0.8312) acc1: 81.2500 (79.9107) acc5: 95.3125 (95.6845) [2021-03-26 18:20:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7936 (0.8390) acc1: 81.2500 (80.2419) acc5: 95.3125 (95.4133) [2021-03-26 18:20:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8089 (0.8270) acc1: 81.2500 (80.1448) acc5: 95.3125 (95.5793) [2021-03-26 18:20:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8075 (0.8331) acc1: 79.6875 (80.0960) acc5: 95.3125 (95.5840) [2021-03-26 18:20:28 swin_small_patch4_window7_224] INFO: * Acc@1 80.844 Acc@5 95.548 loss 0.816 [2021-03-26 18:20:28 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 80.8% [2021-03-26 18:20:28 swin_small_patch4_window7_224] INFO: Max accuracy: 81.06% [2021-03-26 18:20:33 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 0/1251] eta: 1:48:16 lr: 0.000206 loss: 2.3046 (2.3046) grad_norm: 2.2881 (2.2881) time: 5.1931 [2021-03-26 18:20:38 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 10/1251] eta: 0:19:05 lr: 0.000206 loss: 2.9282 (2.8817) grad_norm: 2.0579 (2.0806) time: 0.9232 [2021-03-26 18:20:43 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 20/1251] eta: 0:14:57 lr: 0.000206 loss: 2.9950 (2.9342) grad_norm: 2.0545 (2.1046) time: 0.5059 [2021-03-26 18:20:48 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 30/1251] eta: 0:13:22 lr: 0.000206 loss: 2.9950 (2.8993) grad_norm: 2.0545 (2.0884) time: 0.5114 [2021-03-26 18:20:53 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 40/1251] eta: 0:12:29 lr: 0.000206 loss: 2.7865 (2.8916) grad_norm: 2.0043 (2.0720) time: 0.5038 [2021-03-26 18:20:58 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 50/1251] eta: 0:11:57 lr: 0.000206 loss: 2.9345 (2.9117) grad_norm: 2.0719 (2.0892) time: 0.5051 [2021-03-26 18:21:03 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 60/1251] eta: 0:11:32 lr: 0.000206 loss: 3.0018 (2.9084) grad_norm: 2.0377 (2.0805) time: 0.5031 [2021-03-26 18:21:09 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 70/1251] eta: 0:11:16 lr: 0.000205 loss: 3.0994 (2.9300) grad_norm: 2.0377 (2.0919) time: 0.5093 [2021-03-26 18:21:14 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 80/1251] eta: 0:11:01 lr: 0.000205 loss: 3.1004 (2.9366) grad_norm: 2.0275 (2.0813) time: 0.5137 [2021-03-26 18:21:19 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 90/1251] eta: 0:10:47 lr: 0.000205 loss: 3.0611 (2.9275) grad_norm: 2.0429 (2.0893) time: 0.5053 [2021-03-26 18:21:24 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 100/1251] eta: 0:10:35 lr: 0.000205 loss: 3.0611 (2.9415) grad_norm: 2.0928 (2.0842) time: 0.5030 [2021-03-26 18:21:29 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 110/1251] eta: 0:10:24 lr: 0.000205 loss: 3.0593 (2.9393) grad_norm: 2.0813 (2.0866) time: 0.4980 [2021-03-26 18:21:34 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 120/1251] eta: 0:10:13 lr: 0.000205 loss: 3.0593 (2.9487) grad_norm: 2.1435 (2.0936) time: 0.4952 [2021-03-26 18:21:39 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 130/1251] eta: 0:10:06 lr: 0.000205 loss: 3.2578 (2.9780) grad_norm: 2.1231 (2.0928) time: 0.5049 [2021-03-26 18:21:44 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 140/1251] eta: 0:09:57 lr: 0.000205 loss: 3.2578 (2.9833) grad_norm: 2.0353 (2.0900) time: 0.5047 [2021-03-26 18:21:49 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 150/1251] eta: 0:09:49 lr: 0.000205 loss: 3.2536 (2.9952) grad_norm: 2.0141 (2.0821) time: 0.4975 [2021-03-26 18:21:54 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 160/1251] eta: 0:09:41 lr: 0.000205 loss: 3.1388 (2.9956) grad_norm: 1.9919 (2.0819) time: 0.5000 [2021-03-26 18:21:59 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 170/1251] eta: 0:09:35 lr: 0.000205 loss: 3.1388 (3.0023) grad_norm: 1.9835 (2.0711) time: 0.5107 [2021-03-26 18:22:04 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 180/1251] eta: 0:09:27 lr: 0.000205 loss: 3.0291 (2.9935) grad_norm: 1.9087 (2.0702) time: 0.5101 [2021-03-26 18:22:09 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 190/1251] eta: 0:09:21 lr: 0.000205 loss: 3.0860 (3.0038) grad_norm: 1.9552 (2.0656) time: 0.5014 [2021-03-26 18:22:14 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 200/1251] eta: 0:09:14 lr: 0.000205 loss: 3.2558 (3.0127) grad_norm: 1.9319 (2.0604) time: 0.5008 [2021-03-26 18:22:19 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 210/1251] eta: 0:09:08 lr: 0.000205 loss: 3.1307 (3.0134) grad_norm: 1.9900 (2.0596) time: 0.5050 [2021-03-26 18:22:24 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 220/1251] eta: 0:09:02 lr: 0.000205 loss: 3.0047 (3.0114) grad_norm: 2.0572 (2.0657) time: 0.5122 [2021-03-26 18:22:29 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 230/1251] eta: 0:08:56 lr: 0.000205 loss: 3.0193 (3.0156) grad_norm: 2.1279 (2.0707) time: 0.5113 [2021-03-26 18:22:34 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 240/1251] eta: 0:08:50 lr: 0.000205 loss: 3.0193 (3.0046) grad_norm: 2.0160 (2.0690) time: 0.5049 [2021-03-26 18:22:39 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 250/1251] eta: 0:08:43 lr: 0.000205 loss: 3.0275 (3.0036) grad_norm: 1.9974 (2.0674) time: 0.4977 [2021-03-26 18:22:44 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 260/1251] eta: 0:08:38 lr: 0.000205 loss: 2.9470 (2.9942) grad_norm: 2.0200 (2.0676) time: 0.5095 [2021-03-26 18:22:49 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 270/1251] eta: 0:08:32 lr: 0.000205 loss: 2.7096 (2.9910) grad_norm: 2.0394 (2.0701) time: 0.5107 [2021-03-26 18:22:54 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 280/1251] eta: 0:08:26 lr: 0.000205 loss: 2.8129 (2.9887) grad_norm: 2.0573 (2.0708) time: 0.4976 [2021-03-26 18:22:59 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 290/1251] eta: 0:08:20 lr: 0.000205 loss: 3.1339 (2.9901) grad_norm: 2.0573 (2.0700) time: 0.4952 [2021-03-26 18:23:04 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 300/1251] eta: 0:08:14 lr: 0.000205 loss: 3.1339 (2.9867) grad_norm: 1.9107 (2.0643) time: 0.4984 [2021-03-26 18:23:09 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 310/1251] eta: 0:08:08 lr: 0.000205 loss: 2.9180 (2.9840) grad_norm: 1.9017 (2.0700) time: 0.5030 [2021-03-26 18:23:14 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 320/1251] eta: 0:08:02 lr: 0.000205 loss: 2.8953 (2.9767) grad_norm: 2.0191 (2.0730) time: 0.5032 [2021-03-26 18:23:20 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 330/1251] eta: 0:07:57 lr: 0.000205 loss: 2.8223 (2.9731) grad_norm: 2.0188 (2.0798) time: 0.5082 [2021-03-26 18:23:25 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 340/1251] eta: 0:07:52 lr: 0.000205 loss: 2.9729 (2.9709) grad_norm: 2.0121 (2.0789) time: 0.5112 [2021-03-26 18:23:30 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 350/1251] eta: 0:07:46 lr: 0.000205 loss: 3.0461 (2.9763) grad_norm: 1.9638 (2.0759) time: 0.5036 [2021-03-26 18:23:35 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 360/1251] eta: 0:07:41 lr: 0.000205 loss: 3.0545 (2.9793) grad_norm: 2.0015 (2.0759) time: 0.5028 [2021-03-26 18:23:40 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 370/1251] eta: 0:07:35 lr: 0.000205 loss: 2.9841 (2.9773) grad_norm: 2.0804 (2.0796) time: 0.5056 [2021-03-26 18:23:45 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 380/1251] eta: 0:07:29 lr: 0.000204 loss: 2.8942 (2.9710) grad_norm: 2.0047 (2.0762) time: 0.5008 [2021-03-26 18:23:50 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 390/1251] eta: 0:07:24 lr: 0.000204 loss: 2.8498 (2.9675) grad_norm: 1.9558 (2.0745) time: 0.5059 [2021-03-26 18:23:55 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 400/1251] eta: 0:07:19 lr: 0.000204 loss: 2.8375 (2.9694) grad_norm: 1.9699 (2.0727) time: 0.5085 [2021-03-26 18:24:00 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 410/1251] eta: 0:07:13 lr: 0.000204 loss: 2.9170 (2.9711) grad_norm: 1.9610 (2.0720) time: 0.5048 [2021-03-26 18:24:05 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 420/1251] eta: 0:07:08 lr: 0.000204 loss: 2.9170 (2.9681) grad_norm: 1.9565 (2.0690) time: 0.5025 [2021-03-26 18:24:10 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 430/1251] eta: 0:07:02 lr: 0.000204 loss: 2.7794 (2.9655) grad_norm: 1.9333 (2.0663) time: 0.4968 [2021-03-26 18:24:15 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 440/1251] eta: 0:06:57 lr: 0.000204 loss: 2.9432 (2.9662) grad_norm: 1.9470 (2.0632) time: 0.5002 [2021-03-26 18:24:20 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 450/1251] eta: 0:06:52 lr: 0.000204 loss: 3.2192 (2.9731) grad_norm: 1.9554 (2.0618) time: 0.5047 [2021-03-26 18:24:25 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 460/1251] eta: 0:06:46 lr: 0.000204 loss: 3.1404 (2.9693) grad_norm: 1.9564 (2.0596) time: 0.5077 [2021-03-26 18:24:30 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 470/1251] eta: 0:06:41 lr: 0.000204 loss: 2.7828 (2.9686) grad_norm: 1.9337 (2.0569) time: 0.5047 [2021-03-26 18:24:35 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 480/1251] eta: 0:06:36 lr: 0.000204 loss: 2.8957 (2.9709) grad_norm: 1.9603 (2.0564) time: 0.5036 [2021-03-26 18:24:40 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 490/1251] eta: 0:06:31 lr: 0.000204 loss: 3.0578 (2.9708) grad_norm: 2.0546 (2.0570) time: 0.5072 [2021-03-26 18:24:45 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 500/1251] eta: 0:06:25 lr: 0.000204 loss: 3.0110 (2.9692) grad_norm: 2.0348 (2.0565) time: 0.5035 [2021-03-26 18:24:50 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 510/1251] eta: 0:06:20 lr: 0.000204 loss: 3.0542 (2.9681) grad_norm: 1.9322 (2.0549) time: 0.5043 [2021-03-26 18:24:55 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 520/1251] eta: 0:06:15 lr: 0.000204 loss: 3.1398 (2.9713) grad_norm: 1.9721 (2.0543) time: 0.5032 [2021-03-26 18:25:00 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 530/1251] eta: 0:06:09 lr: 0.000204 loss: 3.2857 (2.9736) grad_norm: 2.0166 (2.0547) time: 0.5009 [2021-03-26 18:25:05 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 540/1251] eta: 0:06:04 lr: 0.000204 loss: 2.9939 (2.9731) grad_norm: 1.9812 (2.0542) time: 0.4992 [2021-03-26 18:25:11 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 550/1251] eta: 0:05:59 lr: 0.000204 loss: 3.0639 (2.9766) grad_norm: 1.9812 (2.0545) time: 0.5096 [2021-03-26 18:25:16 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 560/1251] eta: 0:05:54 lr: 0.000204 loss: 3.2426 (2.9783) grad_norm: 2.0437 (2.0579) time: 0.5175 [2021-03-26 18:25:21 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 570/1251] eta: 0:05:49 lr: 0.000204 loss: 3.1840 (2.9807) grad_norm: 1.9988 (2.0553) time: 0.5112 [2021-03-26 18:25:26 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 580/1251] eta: 0:05:44 lr: 0.000204 loss: 3.1378 (2.9810) grad_norm: 1.9483 (2.0552) time: 0.5091 [2021-03-26 18:25:31 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 590/1251] eta: 0:05:38 lr: 0.000204 loss: 3.1378 (2.9820) grad_norm: 1.9979 (2.0564) time: 0.5012 [2021-03-26 18:25:36 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 600/1251] eta: 0:05:33 lr: 0.000204 loss: 3.1023 (2.9837) grad_norm: 1.9959 (2.0572) time: 0.5042 [2021-03-26 18:25:41 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 610/1251] eta: 0:05:28 lr: 0.000204 loss: 3.0361 (2.9860) grad_norm: 1.9380 (2.0562) time: 0.5051 [2021-03-26 18:25:46 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 620/1251] eta: 0:05:23 lr: 0.000204 loss: 3.1761 (2.9877) grad_norm: 2.0274 (2.0561) time: 0.5003 [2021-03-26 18:25:51 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 630/1251] eta: 0:05:18 lr: 0.000204 loss: 3.1669 (2.9869) grad_norm: 2.0100 (2.0561) time: 0.5098 [2021-03-26 18:25:56 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 640/1251] eta: 0:05:12 lr: 0.000204 loss: 2.9863 (2.9852) grad_norm: 2.0632 (2.0591) time: 0.5091 [2021-03-26 18:26:01 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 650/1251] eta: 0:05:07 lr: 0.000204 loss: 3.0669 (2.9893) grad_norm: 2.0632 (2.0585) time: 0.5080 [2021-03-26 18:26:06 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 660/1251] eta: 0:05:02 lr: 0.000204 loss: 3.3600 (2.9911) grad_norm: 2.0283 (2.0686) time: 0.5108 [2021-03-26 18:26:11 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 670/1251] eta: 0:04:57 lr: 0.000204 loss: 3.2396 (2.9937) grad_norm: 2.1276 (2.0697) time: 0.5071 [2021-03-26 18:26:16 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 680/1251] eta: 0:04:52 lr: 0.000203 loss: 3.1023 (2.9929) grad_norm: 2.1142 (2.0693) time: 0.5062 [2021-03-26 18:26:21 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 690/1251] eta: 0:04:46 lr: 0.000203 loss: 3.0477 (2.9909) grad_norm: 1.9865 (2.0681) time: 0.5020 [2021-03-26 18:26:27 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 700/1251] eta: 0:04:41 lr: 0.000203 loss: 2.8721 (2.9904) grad_norm: 2.0131 (2.0705) time: 0.5024 [2021-03-26 18:26:32 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 710/1251] eta: 0:04:36 lr: 0.000203 loss: 3.0972 (2.9924) grad_norm: 2.0295 (2.0693) time: 0.5107 [2021-03-26 18:26:37 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 720/1251] eta: 0:04:31 lr: 0.000203 loss: 3.1447 (2.9933) grad_norm: 2.0465 (2.0691) time: 0.5164 [2021-03-26 18:26:42 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 730/1251] eta: 0:04:26 lr: 0.000203 loss: 3.1434 (2.9928) grad_norm: 2.0569 (2.0688) time: 0.5078 [2021-03-26 18:26:47 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 740/1251] eta: 0:04:21 lr: 0.000203 loss: 2.9940 (2.9895) grad_norm: 2.1043 (2.0716) time: 0.5130 [2021-03-26 18:26:52 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 750/1251] eta: 0:04:16 lr: 0.000203 loss: 2.9727 (2.9898) grad_norm: 2.1098 (2.0723) time: 0.5134 [2021-03-26 18:26:57 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 760/1251] eta: 0:04:11 lr: 0.000203 loss: 2.8832 (2.9881) grad_norm: 1.9504 (2.0726) time: 0.5044 [2021-03-26 18:27:02 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 770/1251] eta: 0:04:06 lr: 0.000203 loss: 2.8294 (2.9871) grad_norm: 1.9975 (2.0722) time: 0.5094 [2021-03-26 18:27:07 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 780/1251] eta: 0:04:00 lr: 0.000203 loss: 2.8814 (2.9879) grad_norm: 1.9975 (2.0728) time: 0.5034 [2021-03-26 18:27:12 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 790/1251] eta: 0:03:55 lr: 0.000203 loss: 3.1091 (2.9913) grad_norm: 1.9903 (2.0723) time: 0.5030 [2021-03-26 18:27:17 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 800/1251] eta: 0:03:50 lr: 0.000203 loss: 3.1385 (2.9934) grad_norm: 1.9903 (2.0713) time: 0.5042 [2021-03-26 18:27:23 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 810/1251] eta: 0:03:45 lr: 0.000203 loss: 3.0214 (2.9925) grad_norm: 2.0350 (2.0717) time: 0.5099 [2021-03-26 18:27:28 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 820/1251] eta: 0:03:40 lr: 0.000203 loss: 2.8790 (2.9892) grad_norm: 2.0350 (2.0711) time: 0.5123 [2021-03-26 18:27:33 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 830/1251] eta: 0:03:35 lr: 0.000203 loss: 2.9993 (2.9889) grad_norm: 2.0199 (2.0708) time: 0.5108 [2021-03-26 18:27:38 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 840/1251] eta: 0:03:30 lr: 0.000203 loss: 3.0402 (2.9879) grad_norm: 2.0285 (2.0712) time: 0.5116 [2021-03-26 18:27:43 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 850/1251] eta: 0:03:24 lr: 0.000203 loss: 3.1050 (2.9888) grad_norm: 2.1956 (2.0722) time: 0.5010 [2021-03-26 18:27:48 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 860/1251] eta: 0:03:19 lr: 0.000203 loss: 3.0773 (2.9881) grad_norm: 2.1002 (2.0728) time: 0.4937 [2021-03-26 18:27:53 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 870/1251] eta: 0:03:14 lr: 0.000203 loss: 2.9349 (2.9868) grad_norm: 2.0009 (2.0721) time: 0.5005 [2021-03-26 18:27:58 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 880/1251] eta: 0:03:09 lr: 0.000203 loss: 3.1857 (2.9908) grad_norm: 1.9914 (2.0718) time: 0.5094 [2021-03-26 18:28:03 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 890/1251] eta: 0:03:04 lr: 0.000203 loss: 3.1437 (2.9893) grad_norm: 1.9586 (2.0709) time: 0.5087 [2021-03-26 18:28:08 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 900/1251] eta: 0:02:59 lr: 0.000203 loss: 2.9957 (2.9903) grad_norm: 1.9399 (2.0700) time: 0.5055 [2021-03-26 18:28:13 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 910/1251] eta: 0:02:54 lr: 0.000203 loss: 3.0879 (2.9906) grad_norm: 2.0854 (2.0731) time: 0.5097 [2021-03-26 18:28:18 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 920/1251] eta: 0:02:48 lr: 0.000203 loss: 3.0423 (2.9906) grad_norm: 2.0854 (2.0724) time: 0.5052 [2021-03-26 18:28:23 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 930/1251] eta: 0:02:43 lr: 0.000203 loss: 3.1145 (2.9922) grad_norm: 1.9399 (2.0709) time: 0.5051 [2021-03-26 18:28:28 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 940/1251] eta: 0:02:38 lr: 0.000203 loss: 2.9206 (2.9908) grad_norm: 1.9399 (2.0702) time: 0.5032 [2021-03-26 18:28:33 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 950/1251] eta: 0:02:33 lr: 0.000203 loss: 2.9001 (2.9893) grad_norm: 2.0501 (2.0697) time: 0.5092 [2021-03-26 18:28:39 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 960/1251] eta: 0:02:28 lr: 0.000203 loss: 2.9868 (2.9883) grad_norm: 2.0209 (2.0689) time: 0.5203 [2021-03-26 18:28:44 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 970/1251] eta: 0:02:23 lr: 0.000203 loss: 3.1009 (2.9885) grad_norm: 1.9991 (2.0685) time: 0.5096 [2021-03-26 18:28:49 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 980/1251] eta: 0:02:18 lr: 0.000202 loss: 2.9851 (2.9883) grad_norm: 2.0589 (2.0695) time: 0.5004 [2021-03-26 18:28:54 swin_small_patch4_window7_224] INFO: Epoch: [212] [ 990/1251] eta: 0:02:13 lr: 0.000202 loss: 2.9851 (2.9891) grad_norm: 2.0965 (2.0701) time: 0.4968 [2021-03-26 18:28:59 swin_small_patch4_window7_224] INFO: Epoch: [212] [1000/1251] eta: 0:02:08 lr: 0.000202 loss: 3.1060 (2.9899) grad_norm: 1.9858 (2.0694) time: 0.4960 [2021-03-26 18:29:04 swin_small_patch4_window7_224] INFO: Epoch: [212] [1010/1251] eta: 0:02:02 lr: 0.000202 loss: 3.0942 (2.9908) grad_norm: 1.9858 (2.0699) time: 0.5097 [2021-03-26 18:29:09 swin_small_patch4_window7_224] INFO: Epoch: [212] [1020/1251] eta: 0:01:57 lr: 0.000202 loss: 3.0513 (2.9892) grad_norm: 2.0942 (2.0708) time: 0.5107 [2021-03-26 18:29:14 swin_small_patch4_window7_224] INFO: Epoch: [212] [1030/1251] eta: 0:01:52 lr: 0.000202 loss: 2.8484 (2.9889) grad_norm: 2.1556 (2.0720) time: 0.5011 [2021-03-26 18:29:19 swin_small_patch4_window7_224] INFO: Epoch: [212] [1040/1251] eta: 0:01:47 lr: 0.000202 loss: 3.0044 (2.9895) grad_norm: 2.1362 (2.0746) time: 0.4984 [2021-03-26 18:29:24 swin_small_patch4_window7_224] INFO: Epoch: [212] [1050/1251] eta: 0:01:42 lr: 0.000202 loss: 3.0044 (2.9874) grad_norm: 2.0971 (2.0753) time: 0.4946 [2021-03-26 18:29:29 swin_small_patch4_window7_224] INFO: Epoch: [212] [1060/1251] eta: 0:01:37 lr: 0.000202 loss: 3.0854 (2.9886) grad_norm: 2.0503 (2.0756) time: 0.5002 [2021-03-26 18:29:34 swin_small_patch4_window7_224] INFO: Epoch: [212] [1070/1251] eta: 0:01:32 lr: 0.000202 loss: 3.0989 (2.9882) grad_norm: 2.0242 (2.0742) time: 0.5086 [2021-03-26 18:29:39 swin_small_patch4_window7_224] INFO: Epoch: [212] [1080/1251] eta: 0:01:27 lr: 0.000202 loss: 3.0289 (2.9883) grad_norm: 2.0012 (2.0736) time: 0.5111 [2021-03-26 18:29:44 swin_small_patch4_window7_224] INFO: Epoch: [212] [1090/1251] eta: 0:01:22 lr: 0.000202 loss: 3.0512 (2.9888) grad_norm: 2.0820 (2.0754) time: 0.5024 [2021-03-26 18:29:49 swin_small_patch4_window7_224] INFO: Epoch: [212] [1100/1251] eta: 0:01:16 lr: 0.000202 loss: 2.9218 (2.9879) grad_norm: 2.1256 (2.0764) time: 0.4984 [2021-03-26 18:29:54 swin_small_patch4_window7_224] INFO: Epoch: [212] [1110/1251] eta: 0:01:11 lr: 0.000202 loss: 3.0661 (2.9890) grad_norm: 2.0297 (2.0761) time: 0.5016 [2021-03-26 18:29:59 swin_small_patch4_window7_224] INFO: Epoch: [212] [1120/1251] eta: 0:01:06 lr: 0.000202 loss: 3.1649 (2.9893) grad_norm: 1.9937 (2.0754) time: 0.5027 [2021-03-26 18:30:04 swin_small_patch4_window7_224] INFO: Epoch: [212] [1130/1251] eta: 0:01:01 lr: 0.000202 loss: 2.8050 (2.9870) grad_norm: 1.9688 (2.0742) time: 0.5009 [2021-03-26 18:30:09 swin_small_patch4_window7_224] INFO: Epoch: [212] [1140/1251] eta: 0:00:56 lr: 0.000202 loss: 3.0870 (2.9891) grad_norm: 1.9688 (2.0763) time: 0.4974 [2021-03-26 18:30:14 swin_small_patch4_window7_224] INFO: Epoch: [212] [1150/1251] eta: 0:00:51 lr: 0.000202 loss: 3.0870 (2.9897) grad_norm: 2.0654 (2.0761) time: 0.4992 [2021-03-26 18:30:19 swin_small_patch4_window7_224] INFO: Epoch: [212] [1160/1251] eta: 0:00:46 lr: 0.000202 loss: 3.2289 (2.9917) grad_norm: 2.0436 (2.0789) time: 0.5020 [2021-03-26 18:30:24 swin_small_patch4_window7_224] INFO: Epoch: [212] [1170/1251] eta: 0:00:41 lr: 0.000202 loss: 3.1552 (2.9907) grad_norm: 2.0349 (2.0784) time: 0.5015 [2021-03-26 18:30:29 swin_small_patch4_window7_224] INFO: Epoch: [212] [1180/1251] eta: 0:00:36 lr: 0.000202 loss: 3.0734 (2.9912) grad_norm: 2.0436 (2.0783) time: 0.5058 [2021-03-26 18:30:34 swin_small_patch4_window7_224] INFO: Epoch: [212] [1190/1251] eta: 0:00:31 lr: 0.000202 loss: 3.2644 (2.9929) grad_norm: 1.9646 (2.0769) time: 0.5029 [2021-03-26 18:30:39 swin_small_patch4_window7_224] INFO: Epoch: [212] [1200/1251] eta: 0:00:25 lr: 0.000202 loss: 3.1257 (2.9925) grad_norm: 2.0102 (2.0769) time: 0.5051 [2021-03-26 18:30:44 swin_small_patch4_window7_224] INFO: Epoch: [212] [1210/1251] eta: 0:00:20 lr: 0.000202 loss: 3.1024 (2.9935) grad_norm: 2.0822 (2.0780) time: 0.5085 [2021-03-26 18:30:49 swin_small_patch4_window7_224] INFO: Epoch: [212] [1220/1251] eta: 0:00:15 lr: 0.000202 loss: 3.2093 (2.9949) grad_norm: 2.0357 (2.0780) time: 0.5024 [2021-03-26 18:30:54 swin_small_patch4_window7_224] INFO: Epoch: [212] [1230/1251] eta: 0:00:10 lr: 0.000202 loss: 3.1964 (2.9943) grad_norm: 2.0625 (2.0821) time: 0.5033 [2021-03-26 18:30:59 swin_small_patch4_window7_224] INFO: Epoch: [212] [1240/1251] eta: 0:00:05 lr: 0.000202 loss: 2.9757 (2.9938) grad_norm: 2.2054 (2.0846) time: 0.4996 [2021-03-26 18:31:04 swin_small_patch4_window7_224] INFO: Epoch: [212] [1250/1251] eta: 0:00:00 lr: 0.000202 loss: 3.0085 (2.9934) grad_norm: 2.1104 (2.0843) time: 0.4987 [2021-03-26 18:31:13 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:28 loss: 0.9135 (0.9135) acc1: 75.0000 (75.0000) acc5: 96.8750 (96.8750) [2021-03-26 18:31:15 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8702 (0.8786) acc1: 79.6875 (78.9773) acc5: 95.3125 (94.6023) [2021-03-26 18:31:18 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.8373 (0.8675) acc1: 79.6875 (79.5387) acc5: 95.3125 (94.8661) [2021-03-26 18:31:20 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7325 (0.8329) acc1: 79.6875 (80.0907) acc5: 95.3125 (95.3125) [2021-03-26 18:31:21 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8211 (0.8316) acc1: 79.6875 (80.0686) acc5: 95.3125 (95.5030) [2021-03-26 18:31:22 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8411 (0.8243) acc1: 78.1250 (79.9360) acc5: 96.2264 (95.5840) [2021-03-26 18:31:32 swin_small_patch4_window7_224] INFO: * Acc@1 81.132 Acc@5 95.680 loss 0.806 [2021-03-26 18:31:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.1% [2021-03-26 18:31:32 swin_small_patch4_window7_224] INFO: Max accuracy: 81.13% [2021-03-26 18:31:36 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 0/1251] eta: 1:26:03 lr: 0.000202 loss: 3.7391 (3.7391) grad_norm: 1.7219 (1.7219) time: 4.1272 [2021-03-26 18:31:41 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 10/1251] eta: 0:17:30 lr: 0.000202 loss: 3.3266 (3.3332) grad_norm: 1.9640 (1.9812) time: 0.8461 [2021-03-26 18:31:46 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 20/1251] eta: 0:14:01 lr: 0.000202 loss: 3.1919 (3.1361) grad_norm: 2.0796 (2.0878) time: 0.5118 [2021-03-26 18:31:51 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 30/1251] eta: 0:12:50 lr: 0.000202 loss: 2.9324 (3.0168) grad_norm: 2.0872 (2.0808) time: 0.5125 [2021-03-26 18:31:57 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 40/1251] eta: 0:12:09 lr: 0.000201 loss: 2.8046 (2.9957) grad_norm: 1.9298 (2.0319) time: 0.5165 [2021-03-26 18:32:02 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 50/1251] eta: 0:11:39 lr: 0.000201 loss: 2.8405 (2.9931) grad_norm: 1.9298 (2.0503) time: 0.5071 [2021-03-26 18:32:06 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 60/1251] eta: 0:11:15 lr: 0.000201 loss: 2.8405 (2.9623) grad_norm: 1.9890 (2.0407) time: 0.4954 [2021-03-26 18:32:12 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 70/1251] eta: 0:10:59 lr: 0.000201 loss: 3.0327 (2.9711) grad_norm: 2.0230 (2.0544) time: 0.4980 [2021-03-26 18:32:17 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 80/1251] eta: 0:10:46 lr: 0.000201 loss: 3.0350 (2.9562) grad_norm: 2.0824 (2.0499) time: 0.5057 [2021-03-26 18:32:22 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 90/1251] eta: 0:10:35 lr: 0.000201 loss: 2.9000 (2.9485) grad_norm: 2.0491 (2.0380) time: 0.5093 [2021-03-26 18:32:27 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 100/1251] eta: 0:10:25 lr: 0.000201 loss: 2.9838 (2.9479) grad_norm: 1.9583 (2.0341) time: 0.5085 [2021-03-26 18:32:32 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 110/1251] eta: 0:10:16 lr: 0.000201 loss: 2.9838 (2.9465) grad_norm: 1.9918 (2.0382) time: 0.5046 [2021-03-26 18:32:37 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 120/1251] eta: 0:10:06 lr: 0.000201 loss: 3.3076 (2.9803) grad_norm: 2.0393 (2.0426) time: 0.5017 [2021-03-26 18:32:42 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 130/1251] eta: 0:09:59 lr: 0.000201 loss: 3.3143 (2.9942) grad_norm: 2.1527 (2.0565) time: 0.5073 [2021-03-26 18:32:47 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 140/1251] eta: 0:09:52 lr: 0.000201 loss: 2.9883 (2.9931) grad_norm: 2.1551 (2.0631) time: 0.5162 [2021-03-26 18:32:52 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 150/1251] eta: 0:09:44 lr: 0.000201 loss: 3.0491 (2.9921) grad_norm: 2.1116 (2.0620) time: 0.5062 [2021-03-26 18:32:57 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 160/1251] eta: 0:09:37 lr: 0.000201 loss: 3.0396 (2.9892) grad_norm: 2.0307 (2.0627) time: 0.4999 [2021-03-26 18:33:02 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 170/1251] eta: 0:09:30 lr: 0.000201 loss: 2.8572 (2.9787) grad_norm: 2.0274 (2.0611) time: 0.5022 [2021-03-26 18:33:07 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 180/1251] eta: 0:09:23 lr: 0.000201 loss: 3.0493 (2.9839) grad_norm: 1.9988 (2.0599) time: 0.4995 [2021-03-26 18:33:12 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 190/1251] eta: 0:09:17 lr: 0.000201 loss: 3.2053 (2.9916) grad_norm: 2.0695 (2.0665) time: 0.5085 [2021-03-26 18:33:18 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 200/1251] eta: 0:09:12 lr: 0.000201 loss: 3.2415 (2.9999) grad_norm: 2.1348 (2.0720) time: 0.5203 [2021-03-26 18:33:23 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 210/1251] eta: 0:09:06 lr: 0.000201 loss: 2.9516 (2.9884) grad_norm: 2.0878 (2.0742) time: 0.5170 [2021-03-26 18:33:28 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 220/1251] eta: 0:08:59 lr: 0.000201 loss: 2.6913 (2.9834) grad_norm: 2.0727 (2.0723) time: 0.5049 [2021-03-26 18:33:33 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 230/1251] eta: 0:08:53 lr: 0.000201 loss: 3.0296 (2.9847) grad_norm: 1.9527 (2.0675) time: 0.5017 [2021-03-26 18:33:38 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 240/1251] eta: 0:08:47 lr: 0.000201 loss: 3.1984 (2.9949) grad_norm: 1.9417 (2.0670) time: 0.4998 [2021-03-26 18:33:43 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 250/1251] eta: 0:08:41 lr: 0.000201 loss: 3.1567 (2.9919) grad_norm: 2.1370 (2.0725) time: 0.4988 [2021-03-26 18:33:48 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 260/1251] eta: 0:08:35 lr: 0.000201 loss: 3.2599 (3.0069) grad_norm: 2.1376 (2.0735) time: 0.5054 [2021-03-26 18:33:53 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 270/1251] eta: 0:08:30 lr: 0.000201 loss: 3.2771 (3.0042) grad_norm: 2.0714 (2.0746) time: 0.5074 [2021-03-26 18:33:58 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 280/1251] eta: 0:08:24 lr: 0.000201 loss: 3.0476 (3.0016) grad_norm: 2.0309 (2.0726) time: 0.5022 [2021-03-26 18:34:03 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 290/1251] eta: 0:08:18 lr: 0.000201 loss: 3.0784 (3.0095) grad_norm: 1.9846 (2.0703) time: 0.5019 [2021-03-26 18:34:08 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 300/1251] eta: 0:08:12 lr: 0.000201 loss: 3.2059 (3.0079) grad_norm: 2.0384 (2.0727) time: 0.5051 [2021-03-26 18:34:13 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 310/1251] eta: 0:08:07 lr: 0.000201 loss: 3.0531 (3.0116) grad_norm: 2.0294 (2.0718) time: 0.5012 [2021-03-26 18:34:18 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 320/1251] eta: 0:08:01 lr: 0.000201 loss: 3.0512 (3.0106) grad_norm: 1.9989 (2.0689) time: 0.5042 [2021-03-26 18:34:23 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 330/1251] eta: 0:07:56 lr: 0.000201 loss: 2.9058 (3.0100) grad_norm: 1.9965 (2.0688) time: 0.5045 [2021-03-26 18:34:28 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 340/1251] eta: 0:07:50 lr: 0.000200 loss: 2.7413 (3.0016) grad_norm: 2.0288 (2.0693) time: 0.5068 [2021-03-26 18:34:33 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 350/1251] eta: 0:07:45 lr: 0.000200 loss: 2.8281 (3.0006) grad_norm: 2.1402 (2.0761) time: 0.5083 [2021-03-26 18:34:38 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 360/1251] eta: 0:07:39 lr: 0.000200 loss: 2.9807 (3.0013) grad_norm: 2.2039 (inf) time: 0.5007 [2021-03-26 18:34:43 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 370/1251] eta: 0:07:34 lr: 0.000200 loss: 3.0919 (3.0034) grad_norm: 2.2030 (inf) time: 0.5002 [2021-03-26 18:34:48 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 380/1251] eta: 0:07:28 lr: 0.000200 loss: 3.0919 (3.0042) grad_norm: 2.1163 (inf) time: 0.5069 [2021-03-26 18:34:53 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 390/1251] eta: 0:07:23 lr: 0.000200 loss: 3.0997 (3.0041) grad_norm: 2.0506 (inf) time: 0.5112 [2021-03-26 18:34:58 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 400/1251] eta: 0:07:18 lr: 0.000200 loss: 3.1309 (3.0051) grad_norm: 1.9845 (inf) time: 0.5090 [2021-03-26 18:35:04 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 410/1251] eta: 0:07:13 lr: 0.000200 loss: 3.2818 (3.0082) grad_norm: 1.9884 (inf) time: 0.5078 [2021-03-26 18:35:09 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 420/1251] eta: 0:07:07 lr: 0.000200 loss: 3.0791 (3.0082) grad_norm: 1.9570 (inf) time: 0.5098 [2021-03-26 18:35:14 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 430/1251] eta: 0:07:02 lr: 0.000200 loss: 2.9508 (3.0103) grad_norm: 2.0537 (inf) time: 0.5080 [2021-03-26 18:35:19 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 440/1251] eta: 0:06:57 lr: 0.000200 loss: 3.2776 (3.0107) grad_norm: 2.0685 (inf) time: 0.5041 [2021-03-26 18:35:24 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 450/1251] eta: 0:06:51 lr: 0.000200 loss: 3.1835 (3.0036) grad_norm: 1.9447 (inf) time: 0.5034 [2021-03-26 18:35:29 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 460/1251] eta: 0:06:46 lr: 0.000200 loss: 2.8744 (3.0031) grad_norm: 1.8759 (inf) time: 0.5076 [2021-03-26 18:35:34 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 470/1251] eta: 0:06:41 lr: 0.000200 loss: 2.8744 (2.9979) grad_norm: 1.9938 (inf) time: 0.5072 [2021-03-26 18:35:39 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 480/1251] eta: 0:06:35 lr: 0.000200 loss: 3.0570 (2.9942) grad_norm: 2.0239 (inf) time: 0.5021 [2021-03-26 18:35:44 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 490/1251] eta: 0:06:30 lr: 0.000200 loss: 2.8945 (2.9910) grad_norm: 2.0416 (inf) time: 0.5009 [2021-03-26 18:35:49 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 500/1251] eta: 0:06:25 lr: 0.000200 loss: 2.8635 (2.9863) grad_norm: 2.0754 (inf) time: 0.5019 [2021-03-26 18:35:54 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 510/1251] eta: 0:06:20 lr: 0.000200 loss: 2.8635 (2.9872) grad_norm: 2.0462 (inf) time: 0.5032 [2021-03-26 18:35:59 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 520/1251] eta: 0:06:14 lr: 0.000200 loss: 3.0660 (2.9864) grad_norm: 2.0113 (inf) time: 0.5034 [2021-03-26 18:36:04 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 530/1251] eta: 0:06:09 lr: 0.000200 loss: 3.0660 (2.9880) grad_norm: 1.9805 (inf) time: 0.5054 [2021-03-26 18:36:09 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 540/1251] eta: 0:06:04 lr: 0.000200 loss: 3.1008 (2.9889) grad_norm: 1.9927 (inf) time: 0.5098 [2021-03-26 18:36:15 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 550/1251] eta: 0:05:59 lr: 0.000200 loss: 3.1008 (2.9884) grad_norm: 2.0051 (inf) time: 0.5194 [2021-03-26 18:36:20 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 560/1251] eta: 0:05:54 lr: 0.000200 loss: 2.9840 (2.9869) grad_norm: 2.0507 (inf) time: 0.5127 [2021-03-26 18:36:25 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 570/1251] eta: 0:05:49 lr: 0.000200 loss: 3.0163 (2.9886) grad_norm: 2.0313 (inf) time: 0.5049 [2021-03-26 18:36:30 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 580/1251] eta: 0:05:43 lr: 0.000200 loss: 3.1677 (2.9907) grad_norm: 1.8926 (inf) time: 0.5124 [2021-03-26 18:36:35 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 590/1251] eta: 0:05:38 lr: 0.000200 loss: 3.1276 (2.9918) grad_norm: 1.8771 (inf) time: 0.5085 [2021-03-26 18:36:40 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 600/1251] eta: 0:05:33 lr: 0.000200 loss: 3.1752 (2.9929) grad_norm: 1.8781 (inf) time: 0.5034 [2021-03-26 18:36:45 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 610/1251] eta: 0:05:28 lr: 0.000200 loss: 3.2754 (2.9972) grad_norm: 1.9792 (inf) time: 0.5030 [2021-03-26 18:36:50 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 620/1251] eta: 0:05:23 lr: 0.000200 loss: 3.2683 (2.9966) grad_norm: 1.9224 (inf) time: 0.5031 [2021-03-26 18:36:55 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 630/1251] eta: 0:05:17 lr: 0.000200 loss: 3.0584 (2.9972) grad_norm: 1.9344 (inf) time: 0.5024 [2021-03-26 18:37:00 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 640/1251] eta: 0:05:12 lr: 0.000200 loss: 3.0760 (2.9986) grad_norm: 1.9913 (inf) time: 0.5075 [2021-03-26 18:37:05 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 650/1251] eta: 0:05:07 lr: 0.000199 loss: 3.1110 (2.9980) grad_norm: 1.9499 (inf) time: 0.5048 [2021-03-26 18:37:10 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 660/1251] eta: 0:05:02 lr: 0.000199 loss: 3.1110 (2.9978) grad_norm: 1.9064 (inf) time: 0.4988 [2021-03-26 18:37:15 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 670/1251] eta: 0:04:57 lr: 0.000199 loss: 3.2110 (3.0010) grad_norm: 1.9085 (inf) time: 0.5005 [2021-03-26 18:37:20 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 680/1251] eta: 0:04:51 lr: 0.000199 loss: 3.0353 (2.9994) grad_norm: 1.9422 (inf) time: 0.4965 [2021-03-26 18:37:25 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 690/1251] eta: 0:04:46 lr: 0.000199 loss: 3.0277 (2.9996) grad_norm: 2.0070 (inf) time: 0.5030 [2021-03-26 18:37:30 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 700/1251] eta: 0:04:41 lr: 0.000199 loss: 2.9365 (2.9971) grad_norm: 1.9999 (inf) time: 0.5042 [2021-03-26 18:37:35 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 710/1251] eta: 0:04:36 lr: 0.000199 loss: 2.9764 (2.9982) grad_norm: 1.9999 (inf) time: 0.4964 [2021-03-26 18:37:40 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 720/1251] eta: 0:04:31 lr: 0.000199 loss: 3.0002 (2.9942) grad_norm: 1.9736 (inf) time: 0.5007 [2021-03-26 18:37:45 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 730/1251] eta: 0:04:25 lr: 0.000199 loss: 2.7708 (2.9913) grad_norm: 1.8619 (inf) time: 0.5045 [2021-03-26 18:37:50 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 740/1251] eta: 0:04:20 lr: 0.000199 loss: 2.8841 (2.9912) grad_norm: 1.9853 (inf) time: 0.5175 [2021-03-26 18:37:56 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 750/1251] eta: 0:04:15 lr: 0.000199 loss: 3.0997 (2.9932) grad_norm: 1.9856 (inf) time: 0.5251 [2021-03-26 18:38:01 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 760/1251] eta: 0:04:10 lr: 0.000199 loss: 3.1072 (2.9939) grad_norm: 1.9994 (inf) time: 0.5187 [2021-03-26 18:38:06 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 770/1251] eta: 0:04:05 lr: 0.000199 loss: 3.0525 (2.9935) grad_norm: 2.0355 (inf) time: 0.5155 [2021-03-26 18:38:11 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 780/1251] eta: 0:04:00 lr: 0.000199 loss: 2.7875 (2.9887) grad_norm: 1.9739 (inf) time: 0.5117 [2021-03-26 18:38:16 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 790/1251] eta: 0:03:55 lr: 0.000199 loss: 2.9567 (2.9903) grad_norm: 1.9724 (inf) time: 0.5031 [2021-03-26 18:38:21 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 800/1251] eta: 0:03:50 lr: 0.000199 loss: 3.1892 (2.9926) grad_norm: 1.9826 (inf) time: 0.5003 [2021-03-26 18:38:26 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 810/1251] eta: 0:03:45 lr: 0.000199 loss: 3.1743 (2.9925) grad_norm: 1.9371 (inf) time: 0.5000 [2021-03-26 18:38:31 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 820/1251] eta: 0:03:39 lr: 0.000199 loss: 3.2300 (2.9967) grad_norm: 1.9700 (inf) time: 0.4968 [2021-03-26 18:38:36 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 830/1251] eta: 0:03:34 lr: 0.000199 loss: 3.2300 (2.9982) grad_norm: 2.0450 (inf) time: 0.5066 [2021-03-26 18:38:41 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 840/1251] eta: 0:03:29 lr: 0.000199 loss: 3.1921 (2.9990) grad_norm: 2.0063 (inf) time: 0.5067 [2021-03-26 18:38:46 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 850/1251] eta: 0:03:24 lr: 0.000199 loss: 3.0281 (2.9989) grad_norm: 2.0534 (inf) time: 0.5090 [2021-03-26 18:38:51 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 860/1251] eta: 0:03:19 lr: 0.000199 loss: 3.0474 (2.9995) grad_norm: 2.1197 (inf) time: 0.5115 [2021-03-26 18:38:56 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 870/1251] eta: 0:03:14 lr: 0.000199 loss: 2.8652 (2.9975) grad_norm: 2.0675 (inf) time: 0.5044 [2021-03-26 18:39:02 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 880/1251] eta: 0:03:09 lr: 0.000199 loss: 2.9610 (2.9996) grad_norm: 2.0675 (inf) time: 0.5073 [2021-03-26 18:39:07 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 890/1251] eta: 0:03:04 lr: 0.000199 loss: 3.0654 (2.9989) grad_norm: 1.9972 (inf) time: 0.5067 [2021-03-26 18:39:12 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 900/1251] eta: 0:02:59 lr: 0.000199 loss: 3.0464 (2.9982) grad_norm: 1.9972 (inf) time: 0.5010 [2021-03-26 18:39:16 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 910/1251] eta: 0:02:53 lr: 0.000199 loss: 3.0799 (2.9981) grad_norm: 2.0270 (inf) time: 0.4966 [2021-03-26 18:39:21 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 920/1251] eta: 0:02:48 lr: 0.000199 loss: 3.1288 (2.9986) grad_norm: 1.9623 (inf) time: 0.4960 [2021-03-26 18:39:27 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 930/1251] eta: 0:02:43 lr: 0.000199 loss: 3.2985 (3.0011) grad_norm: 1.9530 (inf) time: 0.5054 [2021-03-26 18:39:32 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 940/1251] eta: 0:02:38 lr: 0.000199 loss: 3.2273 (3.0017) grad_norm: 2.0023 (inf) time: 0.5109 [2021-03-26 18:39:37 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 950/1251] eta: 0:02:33 lr: 0.000199 loss: 3.1141 (3.0030) grad_norm: 2.0106 (inf) time: 0.5153 [2021-03-26 18:39:42 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 960/1251] eta: 0:02:28 lr: 0.000198 loss: 3.1426 (3.0032) grad_norm: 2.0096 (inf) time: 0.5119 [2021-03-26 18:39:47 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 970/1251] eta: 0:02:23 lr: 0.000198 loss: 3.1749 (3.0032) grad_norm: 2.0135 (inf) time: 0.5057 [2021-03-26 18:39:52 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 980/1251] eta: 0:02:18 lr: 0.000198 loss: 3.0833 (3.0017) grad_norm: 2.0135 (inf) time: 0.5040 [2021-03-26 18:39:57 swin_small_patch4_window7_224] INFO: Epoch: [213] [ 990/1251] eta: 0:02:13 lr: 0.000198 loss: 3.0413 (3.0040) grad_norm: 2.0101 (inf) time: 0.5018 [2021-03-26 18:40:02 swin_small_patch4_window7_224] INFO: Epoch: [213] [1000/1251] eta: 0:02:07 lr: 0.000198 loss: 3.0808 (3.0032) grad_norm: 1.9242 (inf) time: 0.5024 [2021-03-26 18:40:07 swin_small_patch4_window7_224] INFO: Epoch: [213] [1010/1251] eta: 0:02:02 lr: 0.000198 loss: 3.1102 (3.0040) grad_norm: 1.9275 (inf) time: 0.4978 [2021-03-26 18:40:12 swin_small_patch4_window7_224] INFO: Epoch: [213] [1020/1251] eta: 0:01:57 lr: 0.000198 loss: 3.1123 (3.0043) grad_norm: 1.9492 (inf) time: 0.4952 [2021-03-26 18:40:17 swin_small_patch4_window7_224] INFO: Epoch: [213] [1030/1251] eta: 0:01:52 lr: 0.000198 loss: 2.9183 (3.0032) grad_norm: 1.9977 (inf) time: 0.4972 [2021-03-26 18:40:22 swin_small_patch4_window7_224] INFO: Epoch: [213] [1040/1251] eta: 0:01:47 lr: 0.000198 loss: 3.0517 (3.0047) grad_norm: 2.0618 (inf) time: 0.5107 [2021-03-26 18:40:27 swin_small_patch4_window7_224] INFO: Epoch: [213] [1050/1251] eta: 0:01:42 lr: 0.000198 loss: 3.1141 (3.0049) grad_norm: 2.0070 (inf) time: 0.5144 [2021-03-26 18:40:32 swin_small_patch4_window7_224] INFO: Epoch: [213] [1060/1251] eta: 0:01:37 lr: 0.000198 loss: 3.1415 (3.0045) grad_norm: 1.9892 (inf) time: 0.5060 [2021-03-26 18:40:37 swin_small_patch4_window7_224] INFO: Epoch: [213] [1070/1251] eta: 0:01:32 lr: 0.000198 loss: 3.1422 (3.0069) grad_norm: 1.8563 (inf) time: 0.5057 [2021-03-26 18:40:42 swin_small_patch4_window7_224] INFO: Epoch: [213] [1080/1251] eta: 0:01:27 lr: 0.000198 loss: 3.3095 (3.0087) grad_norm: 2.0389 (inf) time: 0.5075 [2021-03-26 18:40:47 swin_small_patch4_window7_224] INFO: Epoch: [213] [1090/1251] eta: 0:01:21 lr: 0.000198 loss: 3.2489 (3.0094) grad_norm: 2.1083 (inf) time: 0.5000 [2021-03-26 18:40:52 swin_small_patch4_window7_224] INFO: Epoch: [213] [1100/1251] eta: 0:01:16 lr: 0.000198 loss: 3.0684 (3.0099) grad_norm: 2.1083 (inf) time: 0.4974 [2021-03-26 18:40:57 swin_small_patch4_window7_224] INFO: Epoch: [213] [1110/1251] eta: 0:01:11 lr: 0.000198 loss: 3.1645 (3.0100) grad_norm: 2.0731 (inf) time: 0.5003 [2021-03-26 18:41:02 swin_small_patch4_window7_224] INFO: Epoch: [213] [1120/1251] eta: 0:01:06 lr: 0.000198 loss: 2.9757 (3.0079) grad_norm: 1.9855 (inf) time: 0.4978 [2021-03-26 18:41:07 swin_small_patch4_window7_224] INFO: Epoch: [213] [1130/1251] eta: 0:01:01 lr: 0.000198 loss: 2.9112 (3.0078) grad_norm: 1.9966 (inf) time: 0.5043 [2021-03-26 18:41:13 swin_small_patch4_window7_224] INFO: Epoch: [213] [1140/1251] eta: 0:00:56 lr: 0.000198 loss: 2.9649 (3.0077) grad_norm: 1.9966 (inf) time: 0.5079 [2021-03-26 18:41:18 swin_small_patch4_window7_224] INFO: Epoch: [213] [1150/1251] eta: 0:00:51 lr: 0.000198 loss: 2.9968 (3.0080) grad_norm: 2.0324 (inf) time: 0.5032 [2021-03-26 18:41:23 swin_small_patch4_window7_224] INFO: Epoch: [213] [1160/1251] eta: 0:00:46 lr: 0.000198 loss: 3.0002 (3.0084) grad_norm: 1.9365 (inf) time: 0.5001 [2021-03-26 18:41:28 swin_small_patch4_window7_224] INFO: Epoch: [213] [1170/1251] eta: 0:00:41 lr: 0.000198 loss: 2.9765 (3.0064) grad_norm: 1.9580 (inf) time: 0.5061 [2021-03-26 18:41:33 swin_small_patch4_window7_224] INFO: Epoch: [213] [1180/1251] eta: 0:00:36 lr: 0.000198 loss: 3.1490 (3.0083) grad_norm: 2.1169 (inf) time: 0.5058 [2021-03-26 18:41:38 swin_small_patch4_window7_224] INFO: Epoch: [213] [1190/1251] eta: 0:00:31 lr: 0.000198 loss: 3.1490 (3.0072) grad_norm: 2.0118 (inf) time: 0.4965 [2021-03-26 18:41:43 swin_small_patch4_window7_224] INFO: Epoch: [213] [1200/1251] eta: 0:00:25 lr: 0.000198 loss: 3.1387 (3.0069) grad_norm: 2.0502 (inf) time: 0.4975 [2021-03-26 18:41:48 swin_small_patch4_window7_224] INFO: Epoch: [213] [1210/1251] eta: 0:00:20 lr: 0.000198 loss: 3.2195 (3.0083) grad_norm: 2.0843 (inf) time: 0.5036 [2021-03-26 18:41:53 swin_small_patch4_window7_224] INFO: Epoch: [213] [1220/1251] eta: 0:00:15 lr: 0.000198 loss: 3.2682 (3.0090) grad_norm: 1.9788 (inf) time: 0.5047 [2021-03-26 18:41:58 swin_small_patch4_window7_224] INFO: Epoch: [213] [1230/1251] eta: 0:00:10 lr: 0.000198 loss: 3.1674 (3.0104) grad_norm: 2.0078 (inf) time: 0.5020 [2021-03-26 18:42:03 swin_small_patch4_window7_224] INFO: Epoch: [213] [1240/1251] eta: 0:00:05 lr: 0.000198 loss: 3.2180 (3.0125) grad_norm: 2.0386 (inf) time: 0.5053 [2021-03-26 18:42:08 swin_small_patch4_window7_224] INFO: Epoch: [213] [1250/1251] eta: 0:00:00 lr: 0.000198 loss: 3.1442 (3.0120) grad_norm: 2.1078 (inf) time: 0.4956 [2021-03-26 18:42:17 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 0.5694 (0.5694) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-26 18:42:19 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8213 (0.8393) acc1: 81.2500 (80.6818) acc5: 95.3125 (94.6023) [2021-03-26 18:42:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8213 (0.8194) acc1: 81.2500 (80.9524) acc5: 95.3125 (95.2381) [2021-03-26 18:42:22 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7749 (0.8064) acc1: 81.2500 (81.4516) acc5: 96.8750 (95.5645) [2021-03-26 18:42:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7721 (0.7977) acc1: 81.2500 (80.9832) acc5: 96.8750 (95.9604) [2021-03-26 18:42:26 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8064 (0.8221) acc1: 78.1250 (80.3520) acc5: 96.2264 (95.6800) [2021-03-26 18:42:35 swin_small_patch4_window7_224] INFO: * Acc@1 81.122 Acc@5 95.708 loss 0.798 [2021-03-26 18:42:35 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.1% [2021-03-26 18:42:35 swin_small_patch4_window7_224] INFO: Max accuracy: 81.13% [2021-03-26 18:42:39 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 0/1251] eta: 1:28:10 lr: 0.000198 loss: 3.3610 (3.3610) grad_norm: 2.0895 (2.0895) time: 4.2289 [2021-03-26 18:42:44 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 10/1251] eta: 0:17:37 lr: 0.000197 loss: 3.1087 (3.1214) grad_norm: 2.1108 (2.1338) time: 0.8520 [2021-03-26 18:42:49 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 20/1251] eta: 0:14:08 lr: 0.000197 loss: 3.1140 (3.1083) grad_norm: 1.9833 (2.0820) time: 0.5122 [2021-03-26 18:42:55 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 30/1251] eta: 0:12:52 lr: 0.000197 loss: 3.2438 (3.1003) grad_norm: 1.9964 (2.1220) time: 0.5118 [2021-03-26 18:43:00 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 40/1251] eta: 0:12:10 lr: 0.000197 loss: 3.1559 (3.0532) grad_norm: 1.9964 (2.0740) time: 0.5126 [2021-03-26 18:43:05 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 50/1251] eta: 0:11:39 lr: 0.000197 loss: 3.0462 (3.0573) grad_norm: 1.9181 (2.0546) time: 0.5051 [2021-03-26 18:43:10 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 60/1251] eta: 0:11:16 lr: 0.000197 loss: 3.0582 (3.0435) grad_norm: 1.8935 (2.0326) time: 0.4954 [2021-03-26 18:43:15 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 70/1251] eta: 0:10:58 lr: 0.000197 loss: 2.7609 (3.0222) grad_norm: 2.0407 (2.0449) time: 0.4953 [2021-03-26 18:43:20 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 80/1251] eta: 0:10:46 lr: 0.000197 loss: 2.7944 (3.0081) grad_norm: 2.0491 (2.0421) time: 0.5038 [2021-03-26 18:43:25 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 90/1251] eta: 0:10:35 lr: 0.000197 loss: 3.1312 (3.0143) grad_norm: 2.0041 (2.0462) time: 0.5094 [2021-03-26 18:43:30 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 100/1251] eta: 0:10:24 lr: 0.000197 loss: 3.0838 (3.0137) grad_norm: 2.0754 (2.0548) time: 0.5051 [2021-03-26 18:43:35 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 110/1251] eta: 0:10:14 lr: 0.000197 loss: 3.0210 (3.0170) grad_norm: 2.0286 (2.0591) time: 0.5009 [2021-03-26 18:43:40 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 120/1251] eta: 0:10:05 lr: 0.000197 loss: 3.0775 (3.0275) grad_norm: 2.0155 (2.0579) time: 0.4988 [2021-03-26 18:43:45 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 130/1251] eta: 0:09:58 lr: 0.000197 loss: 3.0775 (3.0150) grad_norm: 2.0065 (2.0565) time: 0.5049 [2021-03-26 18:43:50 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 140/1251] eta: 0:09:51 lr: 0.000197 loss: 3.0026 (3.0188) grad_norm: 2.0191 (2.0660) time: 0.5128 [2021-03-26 18:43:55 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 150/1251] eta: 0:09:43 lr: 0.000197 loss: 3.0026 (3.0072) grad_norm: 2.1569 (2.0671) time: 0.5064 [2021-03-26 18:44:00 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 160/1251] eta: 0:09:36 lr: 0.000197 loss: 3.0385 (3.0097) grad_norm: 2.0773 (2.0674) time: 0.5002 [2021-03-26 18:44:05 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 170/1251] eta: 0:09:29 lr: 0.000197 loss: 3.1951 (3.0148) grad_norm: 2.0264 (2.0742) time: 0.4991 [2021-03-26 18:44:10 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 180/1251] eta: 0:09:22 lr: 0.000197 loss: 3.0203 (3.0079) grad_norm: 2.1134 (2.0806) time: 0.5013 [2021-03-26 18:44:15 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 190/1251] eta: 0:09:16 lr: 0.000197 loss: 2.8972 (3.0035) grad_norm: 2.0622 (2.0769) time: 0.5035 [2021-03-26 18:44:20 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 200/1251] eta: 0:09:10 lr: 0.000197 loss: 3.0264 (3.0057) grad_norm: 2.0873 (2.0796) time: 0.5065 [2021-03-26 18:44:25 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 210/1251] eta: 0:09:04 lr: 0.000197 loss: 3.2068 (3.0175) grad_norm: 2.1323 (2.0883) time: 0.5144 [2021-03-26 18:44:30 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 220/1251] eta: 0:08:58 lr: 0.000197 loss: 3.2758 (3.0238) grad_norm: 2.2232 (2.0914) time: 0.5120 [2021-03-26 18:44:36 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 230/1251] eta: 0:08:52 lr: 0.000197 loss: 3.0740 (3.0235) grad_norm: 2.0971 (2.0952) time: 0.5061 [2021-03-26 18:44:41 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 240/1251] eta: 0:08:46 lr: 0.000197 loss: 3.0166 (3.0250) grad_norm: 2.0284 (2.0923) time: 0.5038 [2021-03-26 18:44:46 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 250/1251] eta: 0:08:40 lr: 0.000197 loss: 3.1609 (3.0279) grad_norm: 1.9701 (2.0914) time: 0.5059 [2021-03-26 18:44:51 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 260/1251] eta: 0:08:34 lr: 0.000197 loss: 3.1787 (3.0322) grad_norm: 2.0312 (2.0902) time: 0.5048 [2021-03-26 18:44:56 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 270/1251] eta: 0:08:29 lr: 0.000197 loss: 3.1787 (3.0359) grad_norm: 2.0587 (2.0911) time: 0.5021 [2021-03-26 18:45:01 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 280/1251] eta: 0:08:23 lr: 0.000197 loss: 3.0412 (3.0316) grad_norm: 2.0562 (2.1099) time: 0.5024 [2021-03-26 18:45:06 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 290/1251] eta: 0:08:17 lr: 0.000197 loss: 3.0882 (3.0410) grad_norm: 2.0116 (2.1068) time: 0.5004 [2021-03-26 18:45:11 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 300/1251] eta: 0:08:11 lr: 0.000197 loss: 3.2386 (3.0369) grad_norm: 1.9756 (2.1024) time: 0.5011 [2021-03-26 18:45:16 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 310/1251] eta: 0:08:06 lr: 0.000197 loss: 3.0883 (3.0304) grad_norm: 1.9945 (2.1024) time: 0.5019 [2021-03-26 18:45:21 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 320/1251] eta: 0:08:00 lr: 0.000196 loss: 3.2112 (3.0310) grad_norm: 2.0765 (2.1014) time: 0.5016 [2021-03-26 18:45:26 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 330/1251] eta: 0:07:55 lr: 0.000196 loss: 3.2188 (3.0370) grad_norm: 2.1138 (2.1063) time: 0.5111 [2021-03-26 18:45:31 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 340/1251] eta: 0:07:50 lr: 0.000196 loss: 2.9568 (3.0240) grad_norm: 2.1138 (2.1064) time: 0.5170 [2021-03-26 18:45:36 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 350/1251] eta: 0:07:44 lr: 0.000196 loss: 2.7350 (3.0128) grad_norm: 2.0534 (2.1042) time: 0.5101 [2021-03-26 18:45:41 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 360/1251] eta: 0:07:39 lr: 0.000196 loss: 2.9127 (3.0187) grad_norm: 2.0830 (2.1032) time: 0.5093 [2021-03-26 18:45:46 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 370/1251] eta: 0:07:34 lr: 0.000196 loss: 3.1001 (3.0126) grad_norm: 2.0996 (2.1030) time: 0.5076 [2021-03-26 18:45:51 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 380/1251] eta: 0:07:28 lr: 0.000196 loss: 2.8058 (3.0033) grad_norm: 2.1043 (2.1032) time: 0.4994 [2021-03-26 18:45:56 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 390/1251] eta: 0:07:23 lr: 0.000196 loss: 3.0875 (3.0134) grad_norm: 2.0962 (2.1020) time: 0.4943 [2021-03-26 18:46:01 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 400/1251] eta: 0:07:17 lr: 0.000196 loss: 3.2314 (3.0144) grad_norm: 2.0013 (2.0996) time: 0.4932 [2021-03-26 18:46:06 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 410/1251] eta: 0:07:11 lr: 0.000196 loss: 3.0992 (3.0156) grad_norm: 2.0325 (2.0992) time: 0.4941 [2021-03-26 18:46:11 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 420/1251] eta: 0:07:06 lr: 0.000196 loss: 3.2507 (3.0213) grad_norm: 2.1036 (2.0990) time: 0.4943 [2021-03-26 18:46:16 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 430/1251] eta: 0:07:01 lr: 0.000196 loss: 3.2686 (3.0208) grad_norm: 2.0583 (2.0964) time: 0.4978 [2021-03-26 18:46:21 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 440/1251] eta: 0:06:55 lr: 0.000196 loss: 3.0483 (3.0185) grad_norm: 2.0503 (2.0982) time: 0.5027 [2021-03-26 18:46:26 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 450/1251] eta: 0:06:50 lr: 0.000196 loss: 2.9526 (3.0172) grad_norm: 2.1479 (2.1045) time: 0.5008 [2021-03-26 18:46:31 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 460/1251] eta: 0:06:45 lr: 0.000196 loss: 3.0442 (3.0177) grad_norm: 2.1436 (2.1049) time: 0.5022 [2021-03-26 18:46:36 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 470/1251] eta: 0:06:39 lr: 0.000196 loss: 3.1652 (3.0176) grad_norm: 2.0275 (2.1031) time: 0.5037 [2021-03-26 18:46:41 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 480/1251] eta: 0:06:34 lr: 0.000196 loss: 3.0879 (3.0155) grad_norm: 1.9638 (2.1025) time: 0.5028 [2021-03-26 18:46:46 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 490/1251] eta: 0:06:29 lr: 0.000196 loss: 3.1072 (3.0171) grad_norm: 1.9667 (2.0999) time: 0.5048 [2021-03-26 18:46:51 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 500/1251] eta: 0:06:23 lr: 0.000196 loss: 3.0353 (3.0157) grad_norm: 1.9454 (2.0975) time: 0.5005 [2021-03-26 18:46:56 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 510/1251] eta: 0:06:18 lr: 0.000196 loss: 3.0699 (3.0170) grad_norm: 1.9840 (2.0966) time: 0.4940 [2021-03-26 18:47:01 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 520/1251] eta: 0:06:13 lr: 0.000196 loss: 3.2556 (3.0215) grad_norm: 2.0440 (2.0971) time: 0.4973 [2021-03-26 18:47:06 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 530/1251] eta: 0:06:08 lr: 0.000196 loss: 3.0774 (3.0170) grad_norm: 1.9675 (2.0956) time: 0.5023 [2021-03-26 18:47:11 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 540/1251] eta: 0:06:03 lr: 0.000196 loss: 2.9648 (3.0178) grad_norm: 1.9657 (2.0953) time: 0.5090 [2021-03-26 18:47:17 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 550/1251] eta: 0:05:58 lr: 0.000196 loss: 3.2281 (3.0207) grad_norm: 2.0469 (2.0975) time: 0.5203 [2021-03-26 18:47:22 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 560/1251] eta: 0:05:52 lr: 0.000196 loss: 3.3399 (3.0260) grad_norm: 2.1308 (2.0992) time: 0.5129 [2021-03-26 18:47:27 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 570/1251] eta: 0:05:47 lr: 0.000196 loss: 3.1469 (3.0271) grad_norm: 2.0857 (2.1008) time: 0.4985 [2021-03-26 18:47:32 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 580/1251] eta: 0:05:42 lr: 0.000196 loss: 3.3005 (3.0273) grad_norm: 2.0659 (2.1015) time: 0.4978 [2021-03-26 18:47:37 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 590/1251] eta: 0:05:37 lr: 0.000196 loss: 3.2985 (3.0299) grad_norm: 2.0122 (2.1006) time: 0.5032 [2021-03-26 18:47:42 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 600/1251] eta: 0:05:32 lr: 0.000196 loss: 3.1890 (3.0327) grad_norm: 2.0127 (2.1019) time: 0.5080 [2021-03-26 18:47:47 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 610/1251] eta: 0:05:26 lr: 0.000196 loss: 3.2010 (3.0349) grad_norm: 2.0810 (2.1018) time: 0.5018 [2021-03-26 18:47:52 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 620/1251] eta: 0:05:21 lr: 0.000196 loss: 3.2897 (3.0331) grad_norm: 2.0197 (2.1009) time: 0.5022 [2021-03-26 18:47:57 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 630/1251] eta: 0:05:16 lr: 0.000195 loss: 2.7381 (3.0275) grad_norm: 2.0263 (2.1012) time: 0.5064 [2021-03-26 18:48:02 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 640/1251] eta: 0:05:11 lr: 0.000195 loss: 2.9144 (3.0282) grad_norm: 2.2052 (2.1049) time: 0.5012 [2021-03-26 18:48:07 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 650/1251] eta: 0:05:06 lr: 0.000195 loss: 3.0281 (3.0271) grad_norm: 2.2308 (2.1103) time: 0.5031 [2021-03-26 18:48:12 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 660/1251] eta: 0:05:01 lr: 0.000195 loss: 2.8128 (3.0224) grad_norm: 2.0907 (2.1102) time: 0.5061 [2021-03-26 18:48:17 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 670/1251] eta: 0:04:56 lr: 0.000195 loss: 2.9556 (3.0235) grad_norm: 2.0421 (2.1089) time: 0.5052 [2021-03-26 18:48:22 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 680/1251] eta: 0:04:50 lr: 0.000195 loss: 3.0583 (3.0211) grad_norm: 2.0605 (2.1082) time: 0.5069 [2021-03-26 18:48:27 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 690/1251] eta: 0:04:45 lr: 0.000195 loss: 2.7783 (3.0172) grad_norm: 2.0508 (2.1085) time: 0.5054 [2021-03-26 18:48:32 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 700/1251] eta: 0:04:40 lr: 0.000195 loss: 2.8637 (3.0169) grad_norm: 2.0658 (2.1093) time: 0.5032 [2021-03-26 18:48:37 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 710/1251] eta: 0:04:35 lr: 0.000195 loss: 2.9698 (3.0179) grad_norm: 2.0842 (2.1091) time: 0.5020 [2021-03-26 18:48:42 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 720/1251] eta: 0:04:30 lr: 0.000195 loss: 3.2240 (3.0219) grad_norm: 1.9948 (2.1082) time: 0.5016 [2021-03-26 18:48:47 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 730/1251] eta: 0:04:25 lr: 0.000195 loss: 3.1762 (3.0194) grad_norm: 2.0077 (2.1085) time: 0.5110 [2021-03-26 18:48:53 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 740/1251] eta: 0:04:20 lr: 0.000195 loss: 3.1179 (3.0206) grad_norm: 2.0571 (2.1085) time: 0.5273 [2021-03-26 18:48:58 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 750/1251] eta: 0:04:15 lr: 0.000195 loss: 3.1338 (3.0192) grad_norm: 2.0725 (2.1081) time: 0.5224 [2021-03-26 18:49:03 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 760/1251] eta: 0:04:10 lr: 0.000195 loss: 2.9901 (3.0165) grad_norm: 2.0041 (2.1076) time: 0.5113 [2021-03-26 18:49:08 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 770/1251] eta: 0:04:05 lr: 0.000195 loss: 2.9901 (3.0156) grad_norm: 2.0407 (2.1063) time: 0.5093 [2021-03-26 18:49:13 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 780/1251] eta: 0:04:00 lr: 0.000195 loss: 3.2830 (3.0208) grad_norm: 2.0707 (2.1070) time: 0.5097 [2021-03-26 18:49:18 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 790/1251] eta: 0:03:54 lr: 0.000195 loss: 3.2582 (3.0193) grad_norm: 2.1697 (2.1086) time: 0.5079 [2021-03-26 18:49:23 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 800/1251] eta: 0:03:49 lr: 0.000195 loss: 3.0060 (3.0204) grad_norm: 2.1334 (2.1089) time: 0.5018 [2021-03-26 18:49:28 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 810/1251] eta: 0:03:44 lr: 0.000195 loss: 3.0060 (3.0200) grad_norm: 2.0527 (2.1079) time: 0.5003 [2021-03-26 18:49:33 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 820/1251] eta: 0:03:39 lr: 0.000195 loss: 3.0532 (3.0226) grad_norm: 1.9934 (2.1070) time: 0.5035 [2021-03-26 18:49:38 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 830/1251] eta: 0:03:34 lr: 0.000195 loss: 3.3300 (3.0245) grad_norm: 2.0294 (2.1059) time: 0.5058 [2021-03-26 18:49:43 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 840/1251] eta: 0:03:29 lr: 0.000195 loss: 3.1217 (3.0249) grad_norm: 2.0890 (2.1059) time: 0.5081 [2021-03-26 18:49:49 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 850/1251] eta: 0:03:24 lr: 0.000195 loss: 2.9942 (3.0244) grad_norm: 2.1337 (2.1081) time: 0.5106 [2021-03-26 18:49:53 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 860/1251] eta: 0:03:19 lr: 0.000195 loss: 3.1538 (3.0265) grad_norm: 2.1281 (2.1079) time: 0.5031 [2021-03-26 18:49:59 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 870/1251] eta: 0:03:13 lr: 0.000195 loss: 3.1882 (3.0255) grad_norm: 2.0393 (2.1092) time: 0.5011 [2021-03-26 18:50:04 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 880/1251] eta: 0:03:08 lr: 0.000195 loss: 3.0411 (3.0264) grad_norm: 2.0134 (2.1078) time: 0.5080 [2021-03-26 18:50:09 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 890/1251] eta: 0:03:03 lr: 0.000195 loss: 3.2018 (3.0284) grad_norm: 1.9657 (2.1068) time: 0.5079 [2021-03-26 18:50:14 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 900/1251] eta: 0:02:58 lr: 0.000195 loss: 3.2047 (3.0300) grad_norm: 1.9219 (2.1052) time: 0.5001 [2021-03-26 18:50:19 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 910/1251] eta: 0:02:53 lr: 0.000195 loss: 3.1624 (3.0298) grad_norm: 1.9592 (2.1063) time: 0.4968 [2021-03-26 18:50:24 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 920/1251] eta: 0:02:48 lr: 0.000195 loss: 3.1266 (3.0317) grad_norm: 2.0352 (2.1055) time: 0.4951 [2021-03-26 18:50:29 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 930/1251] eta: 0:02:43 lr: 0.000195 loss: 3.0673 (3.0298) grad_norm: 2.0206 (2.1053) time: 0.5039 [2021-03-26 18:50:34 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 940/1251] eta: 0:02:38 lr: 0.000194 loss: 2.9892 (3.0288) grad_norm: 2.0653 (2.1064) time: 0.5144 [2021-03-26 18:50:39 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 950/1251] eta: 0:02:33 lr: 0.000194 loss: 3.0409 (3.0291) grad_norm: 2.0639 (2.1063) time: 0.5123 [2021-03-26 18:50:44 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 960/1251] eta: 0:02:28 lr: 0.000194 loss: 3.0818 (3.0309) grad_norm: 1.9926 (2.1055) time: 0.5066 [2021-03-26 18:50:49 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 970/1251] eta: 0:02:22 lr: 0.000194 loss: 2.9053 (3.0283) grad_norm: 2.0326 (2.1066) time: 0.4993 [2021-03-26 18:50:54 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 980/1251] eta: 0:02:17 lr: 0.000194 loss: 3.0469 (3.0296) grad_norm: 1.9435 (2.1060) time: 0.4962 [2021-03-26 18:50:59 swin_small_patch4_window7_224] INFO: Epoch: [214] [ 990/1251] eta: 0:02:12 lr: 0.000194 loss: 3.0659 (3.0299) grad_norm: 1.9636 (2.1058) time: 0.5003 [2021-03-26 18:51:04 swin_small_patch4_window7_224] INFO: Epoch: [214] [1000/1251] eta: 0:02:07 lr: 0.000194 loss: 3.0659 (3.0308) grad_norm: 2.0463 (2.1044) time: 0.5005 [2021-03-26 18:51:09 swin_small_patch4_window7_224] INFO: Epoch: [214] [1010/1251] eta: 0:02:02 lr: 0.000194 loss: 3.1182 (3.0309) grad_norm: 2.0982 (2.1054) time: 0.5049 [2021-03-26 18:51:14 swin_small_patch4_window7_224] INFO: Epoch: [214] [1020/1251] eta: 0:01:57 lr: 0.000194 loss: 3.1159 (3.0310) grad_norm: 2.1979 (2.1052) time: 0.5034 [2021-03-26 18:51:19 swin_small_patch4_window7_224] INFO: Epoch: [214] [1030/1251] eta: 0:01:52 lr: 0.000194 loss: 2.9277 (3.0299) grad_norm: 2.1286 (2.1093) time: 0.4975 [2021-03-26 18:51:24 swin_small_patch4_window7_224] INFO: Epoch: [214] [1040/1251] eta: 0:01:47 lr: 0.000194 loss: 3.1542 (3.0316) grad_norm: 2.1828 (2.1098) time: 0.5021 [2021-03-26 18:51:29 swin_small_patch4_window7_224] INFO: Epoch: [214] [1050/1251] eta: 0:01:42 lr: 0.000194 loss: 3.1367 (3.0324) grad_norm: 2.1988 (2.1108) time: 0.5022 [2021-03-26 18:51:34 swin_small_patch4_window7_224] INFO: Epoch: [214] [1060/1251] eta: 0:01:37 lr: 0.000194 loss: 3.0002 (3.0302) grad_norm: 2.1130 (2.1114) time: 0.5061 [2021-03-26 18:51:39 swin_small_patch4_window7_224] INFO: Epoch: [214] [1070/1251] eta: 0:01:31 lr: 0.000194 loss: 2.9967 (3.0301) grad_norm: 2.0848 (2.1113) time: 0.5187 [2021-03-26 18:51:44 swin_small_patch4_window7_224] INFO: Epoch: [214] [1080/1251] eta: 0:01:26 lr: 0.000194 loss: 2.9527 (3.0296) grad_norm: 2.1270 (2.1117) time: 0.5103 [2021-03-26 18:51:49 swin_small_patch4_window7_224] INFO: Epoch: [214] [1090/1251] eta: 0:01:21 lr: 0.000194 loss: 2.9890 (3.0289) grad_norm: 2.0735 (2.1104) time: 0.4933 [2021-03-26 18:51:54 swin_small_patch4_window7_224] INFO: Epoch: [214] [1100/1251] eta: 0:01:16 lr: 0.000194 loss: 2.9601 (3.0278) grad_norm: 1.9090 (2.1104) time: 0.4947 [2021-03-26 18:51:59 swin_small_patch4_window7_224] INFO: Epoch: [214] [1110/1251] eta: 0:01:11 lr: 0.000194 loss: 3.0822 (3.0282) grad_norm: 2.0599 (2.1101) time: 0.4986 [2021-03-26 18:52:04 swin_small_patch4_window7_224] INFO: Epoch: [214] [1120/1251] eta: 0:01:06 lr: 0.000194 loss: 3.1212 (3.0289) grad_norm: 2.0636 (2.1105) time: 0.4976 [2021-03-26 18:52:09 swin_small_patch4_window7_224] INFO: Epoch: [214] [1130/1251] eta: 0:01:01 lr: 0.000194 loss: 3.1796 (3.0302) grad_norm: 2.1422 (2.1114) time: 0.4972 [2021-03-26 18:52:14 swin_small_patch4_window7_224] INFO: Epoch: [214] [1140/1251] eta: 0:00:56 lr: 0.000194 loss: 3.0648 (3.0291) grad_norm: 2.1422 (2.1122) time: 0.5022 [2021-03-26 18:52:19 swin_small_patch4_window7_224] INFO: Epoch: [214] [1150/1251] eta: 0:00:51 lr: 0.000194 loss: 2.9543 (3.0298) grad_norm: 2.0575 (2.1126) time: 0.5002 [2021-03-26 18:52:24 swin_small_patch4_window7_224] INFO: Epoch: [214] [1160/1251] eta: 0:00:46 lr: 0.000194 loss: 2.9543 (3.0283) grad_norm: 2.0291 (2.1127) time: 0.5008 [2021-03-26 18:52:29 swin_small_patch4_window7_224] INFO: Epoch: [214] [1170/1251] eta: 0:00:41 lr: 0.000194 loss: 3.0872 (3.0284) grad_norm: 2.0679 (2.1129) time: 0.5021 [2021-03-26 18:52:34 swin_small_patch4_window7_224] INFO: Epoch: [214] [1180/1251] eta: 0:00:36 lr: 0.000194 loss: 3.0360 (3.0280) grad_norm: 2.0994 (2.1140) time: 0.5051 [2021-03-26 18:52:39 swin_small_patch4_window7_224] INFO: Epoch: [214] [1190/1251] eta: 0:00:30 lr: 0.000194 loss: 2.9214 (3.0267) grad_norm: 2.1594 (2.1151) time: 0.5063 [2021-03-26 18:52:44 swin_small_patch4_window7_224] INFO: Epoch: [214] [1200/1251] eta: 0:00:25 lr: 0.000194 loss: 3.0277 (3.0278) grad_norm: 2.1036 (2.1149) time: 0.5039 [2021-03-26 18:52:50 swin_small_patch4_window7_224] INFO: Epoch: [214] [1210/1251] eta: 0:00:20 lr: 0.000194 loss: 3.0785 (3.0282) grad_norm: 2.0818 (2.1144) time: 0.5114 [2021-03-26 18:52:55 swin_small_patch4_window7_224] INFO: Epoch: [214] [1220/1251] eta: 0:00:15 lr: 0.000194 loss: 2.9367 (3.0269) grad_norm: 2.0085 (2.1137) time: 0.5117 [2021-03-26 18:53:00 swin_small_patch4_window7_224] INFO: Epoch: [214] [1230/1251] eta: 0:00:10 lr: 0.000194 loss: 3.0323 (3.0278) grad_norm: 2.0788 (2.1146) time: 0.5062 [2021-03-26 18:53:05 swin_small_patch4_window7_224] INFO: Epoch: [214] [1240/1251] eta: 0:00:05 lr: 0.000194 loss: 3.3326 (3.0292) grad_norm: 2.0917 (2.1144) time: 0.5060 [2021-03-26 18:53:10 swin_small_patch4_window7_224] INFO: Epoch: [214] [1250/1251] eta: 0:00:00 lr: 0.000193 loss: 3.1324 (3.0269) grad_norm: 2.0641 (2.1139) time: 0.5038 [2021-03-26 18:53:22 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:20 loss: 0.9071 (0.9071) acc1: 70.3125 (70.3125) acc5: 95.3125 (95.3125) [2021-03-26 18:53:25 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8313 (0.8279) acc1: 76.5625 (78.1250) acc5: 96.8750 (96.0227) [2021-03-26 18:53:27 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7928 (0.8343) acc1: 79.6875 (79.3899) acc5: 96.8750 (95.9821) [2021-03-26 18:53:28 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7928 (0.8406) acc1: 79.6875 (79.5867) acc5: 95.3125 (95.6653) [2021-03-26 18:53:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7820 (0.8388) acc1: 78.1250 (79.5732) acc5: 95.3125 (95.5793) [2021-03-26 18:53:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7820 (0.8239) acc1: 79.6875 (79.6800) acc5: 95.3125 (95.7120) [2021-03-26 18:53:42 swin_small_patch4_window7_224] INFO: * Acc@1 81.106 Acc@5 95.750 loss 0.794 [2021-03-26 18:53:42 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.1% [2021-03-26 18:53:42 swin_small_patch4_window7_224] INFO: Max accuracy: 81.13% [2021-03-26 18:53:46 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 0/1251] eta: 1:24:03 lr: 0.000193 loss: 2.1584 (2.1584) grad_norm: 1.9839 (1.9839) time: 4.0317 [2021-03-26 18:53:52 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 10/1251] eta: 0:17:52 lr: 0.000193 loss: 3.3173 (3.1742) grad_norm: 2.0698 (2.0998) time: 0.8639 [2021-03-26 18:53:57 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 20/1251] eta: 0:14:15 lr: 0.000193 loss: 3.2862 (3.1499) grad_norm: 2.0863 (2.1345) time: 0.5285 [2021-03-26 18:54:02 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 30/1251] eta: 0:12:52 lr: 0.000193 loss: 3.2862 (3.1730) grad_norm: 1.9828 (2.0885) time: 0.5059 [2021-03-26 18:54:07 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 40/1251] eta: 0:12:16 lr: 0.000193 loss: 3.1887 (3.1657) grad_norm: 1.9375 (2.1044) time: 0.5163 [2021-03-26 18:54:12 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 50/1251] eta: 0:11:46 lr: 0.000193 loss: 3.1887 (3.1833) grad_norm: 2.1049 (2.1399) time: 0.5188 [2021-03-26 18:54:17 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 60/1251] eta: 0:11:24 lr: 0.000193 loss: 3.0787 (3.1063) grad_norm: 2.0392 (2.1262) time: 0.5074 [2021-03-26 18:54:22 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 70/1251] eta: 0:11:05 lr: 0.000193 loss: 3.1599 (3.1321) grad_norm: 2.1108 (2.1415) time: 0.5017 [2021-03-26 18:54:27 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 80/1251] eta: 0:10:51 lr: 0.000193 loss: 3.2503 (3.1028) grad_norm: 2.1717 (2.1419) time: 0.4989 [2021-03-26 18:54:32 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 90/1251] eta: 0:10:38 lr: 0.000193 loss: 2.9236 (3.0844) grad_norm: 2.0874 (2.1458) time: 0.5011 [2021-03-26 18:54:37 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 100/1251] eta: 0:10:27 lr: 0.000193 loss: 2.9929 (3.0557) grad_norm: 2.1570 (2.1397) time: 0.5018 [2021-03-26 18:54:42 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 110/1251] eta: 0:10:16 lr: 0.000193 loss: 3.0669 (3.0550) grad_norm: 2.1570 (2.1573) time: 0.4985 [2021-03-26 18:54:47 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 120/1251] eta: 0:10:07 lr: 0.000193 loss: 3.1324 (3.0539) grad_norm: 2.1623 (2.1845) time: 0.4953 [2021-03-26 18:54:52 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 130/1251] eta: 0:10:00 lr: 0.000193 loss: 2.9567 (3.0473) grad_norm: 2.1623 (2.1826) time: 0.5053 [2021-03-26 18:54:57 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 140/1251] eta: 0:09:52 lr: 0.000193 loss: 2.9502 (3.0468) grad_norm: 2.1361 (2.1854) time: 0.5110 [2021-03-26 18:55:02 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 150/1251] eta: 0:09:45 lr: 0.000193 loss: 3.2315 (3.0487) grad_norm: 2.1361 (2.1832) time: 0.5098 [2021-03-26 18:55:07 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 160/1251] eta: 0:09:38 lr: 0.000193 loss: 2.9430 (3.0331) grad_norm: 2.0548 (2.1804) time: 0.5078 [2021-03-26 18:55:13 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 170/1251] eta: 0:09:31 lr: 0.000193 loss: 2.9430 (3.0230) grad_norm: 2.0567 (2.1803) time: 0.5068 [2021-03-26 18:55:18 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 180/1251] eta: 0:09:25 lr: 0.000193 loss: 3.0850 (3.0292) grad_norm: 2.0673 (2.1732) time: 0.5058 [2021-03-26 18:55:23 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 190/1251] eta: 0:09:18 lr: 0.000193 loss: 3.1455 (3.0308) grad_norm: 2.0673 (2.1762) time: 0.5000 [2021-03-26 18:55:28 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 200/1251] eta: 0:09:12 lr: 0.000193 loss: 3.1722 (3.0375) grad_norm: 2.1831 (2.1803) time: 0.5054 [2021-03-26 18:55:33 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 210/1251] eta: 0:09:05 lr: 0.000193 loss: 3.1786 (3.0437) grad_norm: 2.1310 (2.1801) time: 0.5081 [2021-03-26 18:55:38 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 220/1251] eta: 0:08:59 lr: 0.000193 loss: 3.0511 (3.0344) grad_norm: 2.0772 (2.1742) time: 0.5031 [2021-03-26 18:55:43 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 230/1251] eta: 0:08:53 lr: 0.000193 loss: 2.8403 (3.0275) grad_norm: 2.0772 (2.1779) time: 0.5041 [2021-03-26 18:55:48 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 240/1251] eta: 0:08:47 lr: 0.000193 loss: 2.8403 (3.0206) grad_norm: 2.1471 (2.1734) time: 0.4993 [2021-03-26 18:55:53 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 250/1251] eta: 0:08:41 lr: 0.000193 loss: 2.9857 (3.0257) grad_norm: 2.0365 (2.1724) time: 0.4995 [2021-03-26 18:55:58 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 260/1251] eta: 0:08:35 lr: 0.000193 loss: 3.1512 (3.0284) grad_norm: 2.0365 (2.1716) time: 0.5114 [2021-03-26 18:56:03 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 270/1251] eta: 0:08:29 lr: 0.000193 loss: 3.0732 (3.0255) grad_norm: 2.1584 (2.1751) time: 0.5059 [2021-03-26 18:56:08 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 280/1251] eta: 0:08:23 lr: 0.000193 loss: 3.0938 (3.0273) grad_norm: 2.1919 (2.1798) time: 0.4983 [2021-03-26 18:56:13 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 290/1251] eta: 0:08:18 lr: 0.000193 loss: 3.1359 (3.0301) grad_norm: 2.1137 (2.1796) time: 0.5021 [2021-03-26 18:56:18 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 300/1251] eta: 0:08:12 lr: 0.000193 loss: 3.2132 (3.0357) grad_norm: 2.0932 (2.1759) time: 0.4983 [2021-03-26 18:56:23 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 310/1251] eta: 0:08:06 lr: 0.000192 loss: 3.0830 (3.0343) grad_norm: 2.0932 (2.1764) time: 0.4969 [2021-03-26 18:56:28 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 320/1251] eta: 0:08:01 lr: 0.000192 loss: 3.0029 (3.0367) grad_norm: 2.0833 (2.1755) time: 0.5040 [2021-03-26 18:56:33 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 330/1251] eta: 0:07:55 lr: 0.000192 loss: 2.8832 (3.0286) grad_norm: 2.0149 (2.1696) time: 0.5081 [2021-03-26 18:56:38 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 340/1251] eta: 0:07:50 lr: 0.000192 loss: 2.8832 (3.0299) grad_norm: 2.0538 (2.1686) time: 0.5057 [2021-03-26 18:56:43 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 350/1251] eta: 0:07:44 lr: 0.000192 loss: 3.0052 (3.0267) grad_norm: 2.0304 (2.1656) time: 0.5028 [2021-03-26 18:56:48 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 360/1251] eta: 0:07:39 lr: 0.000192 loss: 3.0052 (3.0279) grad_norm: 2.0304 (2.1635) time: 0.4988 [2021-03-26 18:56:53 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 370/1251] eta: 0:07:33 lr: 0.000192 loss: 3.1776 (3.0290) grad_norm: 2.1037 (2.1616) time: 0.5000 [2021-03-26 18:56:58 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 380/1251] eta: 0:07:27 lr: 0.000192 loss: 3.1797 (3.0324) grad_norm: 2.0573 (2.1600) time: 0.4993 [2021-03-26 18:57:03 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 390/1251] eta: 0:07:22 lr: 0.000192 loss: 3.1722 (3.0333) grad_norm: 2.0685 (2.1591) time: 0.4939 [2021-03-26 18:57:08 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 400/1251] eta: 0:07:16 lr: 0.000192 loss: 3.0280 (3.0334) grad_norm: 2.1352 (2.1581) time: 0.4953 [2021-03-26 18:57:13 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 410/1251] eta: 0:07:11 lr: 0.000192 loss: 2.9054 (3.0290) grad_norm: 2.1406 (2.1581) time: 0.4987 [2021-03-26 18:57:18 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 420/1251] eta: 0:07:06 lr: 0.000192 loss: 3.1139 (3.0331) grad_norm: 2.1017 (2.1559) time: 0.4986 [2021-03-26 18:57:23 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 430/1251] eta: 0:07:00 lr: 0.000192 loss: 3.3681 (3.0414) grad_norm: 2.1017 (2.1559) time: 0.5000 [2021-03-26 18:57:28 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 440/1251] eta: 0:06:55 lr: 0.000192 loss: 3.2636 (3.0371) grad_norm: 2.1296 (2.1567) time: 0.5016 [2021-03-26 18:57:33 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 450/1251] eta: 0:06:50 lr: 0.000192 loss: 3.0566 (3.0415) grad_norm: 2.0041 (2.1534) time: 0.5100 [2021-03-26 18:57:38 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 460/1251] eta: 0:06:45 lr: 0.000192 loss: 2.9925 (3.0362) grad_norm: 1.9864 (2.1566) time: 0.5096 [2021-03-26 18:57:43 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 470/1251] eta: 0:06:39 lr: 0.000192 loss: 2.9925 (3.0362) grad_norm: 2.0074 (2.1561) time: 0.5001 [2021-03-26 18:57:48 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 480/1251] eta: 0:06:34 lr: 0.000192 loss: 3.1943 (3.0390) grad_norm: 2.0809 (2.1580) time: 0.4989 [2021-03-26 18:57:53 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 490/1251] eta: 0:06:29 lr: 0.000192 loss: 3.1819 (3.0380) grad_norm: 2.1314 (2.1614) time: 0.4998 [2021-03-26 18:57:58 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 500/1251] eta: 0:06:23 lr: 0.000192 loss: 2.9848 (3.0354) grad_norm: 1.9633 (2.1577) time: 0.5002 [2021-03-26 18:58:03 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 510/1251] eta: 0:06:18 lr: 0.000192 loss: 3.0617 (3.0336) grad_norm: 2.0323 (2.1564) time: 0.4980 [2021-03-26 18:58:08 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 520/1251] eta: 0:06:13 lr: 0.000192 loss: 3.0861 (3.0338) grad_norm: 2.0784 (2.1545) time: 0.5003 [2021-03-26 18:58:13 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 530/1251] eta: 0:06:08 lr: 0.000192 loss: 3.0788 (3.0294) grad_norm: 2.0267 (2.1568) time: 0.5023 [2021-03-26 18:58:18 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 540/1251] eta: 0:06:02 lr: 0.000192 loss: 3.0969 (3.0295) grad_norm: 2.0267 (2.1569) time: 0.5033 [2021-03-26 18:58:24 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 550/1251] eta: 0:05:58 lr: 0.000192 loss: 3.0969 (3.0295) grad_norm: 2.0432 (2.1562) time: 0.5199 [2021-03-26 18:58:29 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 560/1251] eta: 0:05:52 lr: 0.000192 loss: 3.2179 (3.0320) grad_norm: 2.2433 (2.1603) time: 0.5206 [2021-03-26 18:58:34 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 570/1251] eta: 0:05:47 lr: 0.000192 loss: 3.2179 (3.0308) grad_norm: 2.3031 (2.1607) time: 0.5064 [2021-03-26 18:58:39 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 580/1251] eta: 0:05:42 lr: 0.000192 loss: 3.0855 (3.0285) grad_norm: 2.1914 (2.1608) time: 0.5068 [2021-03-26 18:58:44 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 590/1251] eta: 0:05:37 lr: 0.000192 loss: 3.1155 (3.0313) grad_norm: 2.0933 (2.1602) time: 0.5101 [2021-03-26 18:58:49 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 600/1251] eta: 0:05:32 lr: 0.000192 loss: 3.0824 (3.0268) grad_norm: 2.0380 (2.1578) time: 0.5058 [2021-03-26 18:58:54 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 610/1251] eta: 0:05:27 lr: 0.000192 loss: 2.6649 (3.0222) grad_norm: 2.0190 (2.1580) time: 0.4992 [2021-03-26 18:58:59 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 620/1251] eta: 0:05:21 lr: 0.000191 loss: 3.1237 (3.0256) grad_norm: 2.1116 (2.1576) time: 0.4961 [2021-03-26 18:59:04 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 630/1251] eta: 0:05:16 lr: 0.000191 loss: 3.2606 (3.0270) grad_norm: 2.1084 (2.1570) time: 0.4980 [2021-03-26 18:59:09 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 640/1251] eta: 0:05:11 lr: 0.000191 loss: 3.1042 (3.0269) grad_norm: 2.1251 (2.1592) time: 0.5019 [2021-03-26 18:59:14 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 650/1251] eta: 0:05:06 lr: 0.000191 loss: 2.9193 (3.0256) grad_norm: 2.0748 (2.1571) time: 0.5036 [2021-03-26 18:59:19 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 660/1251] eta: 0:05:01 lr: 0.000191 loss: 2.9952 (3.0242) grad_norm: 2.0040 (2.1556) time: 0.5022 [2021-03-26 18:59:24 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 670/1251] eta: 0:04:55 lr: 0.000191 loss: 2.9952 (3.0241) grad_norm: 2.0307 (2.1565) time: 0.4949 [2021-03-26 18:59:29 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 680/1251] eta: 0:04:50 lr: 0.000191 loss: 3.1159 (3.0242) grad_norm: 2.0673 (2.1560) time: 0.4947 [2021-03-26 18:59:34 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 690/1251] eta: 0:04:45 lr: 0.000191 loss: 3.1159 (3.0260) grad_norm: 2.0673 (2.1573) time: 0.5035 [2021-03-26 18:59:39 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 700/1251] eta: 0:04:40 lr: 0.000191 loss: 3.0027 (3.0224) grad_norm: 2.1656 (2.1605) time: 0.5079 [2021-03-26 18:59:44 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 710/1251] eta: 0:04:35 lr: 0.000191 loss: 2.9272 (3.0216) grad_norm: 2.2050 (2.1610) time: 0.5074 [2021-03-26 18:59:49 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 720/1251] eta: 0:04:30 lr: 0.000191 loss: 3.0933 (3.0212) grad_norm: 2.1077 (2.1594) time: 0.5041 [2021-03-26 18:59:54 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 730/1251] eta: 0:04:25 lr: 0.000191 loss: 3.1707 (3.0213) grad_norm: 2.0525 (2.1576) time: 0.5075 [2021-03-26 19:00:00 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 740/1251] eta: 0:04:20 lr: 0.000191 loss: 3.1782 (3.0226) grad_norm: 2.0684 (2.1572) time: 0.5273 [2021-03-26 19:00:05 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 750/1251] eta: 0:04:15 lr: 0.000191 loss: 3.2910 (3.0251) grad_norm: 2.0691 (2.1553) time: 0.5232 [2021-03-26 19:00:10 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 760/1251] eta: 0:04:10 lr: 0.000191 loss: 3.1824 (3.0221) grad_norm: 1.9990 (2.1534) time: 0.5072 [2021-03-26 19:00:15 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 770/1251] eta: 0:04:04 lr: 0.000191 loss: 3.0162 (3.0225) grad_norm: 2.0220 (2.1523) time: 0.5016 [2021-03-26 19:00:20 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 780/1251] eta: 0:03:59 lr: 0.000191 loss: 3.0361 (3.0226) grad_norm: 2.0520 (2.1531) time: 0.5027 [2021-03-26 19:00:25 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 790/1251] eta: 0:03:54 lr: 0.000191 loss: 3.0935 (3.0202) grad_norm: 2.2483 (2.1546) time: 0.5136 [2021-03-26 19:00:30 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 800/1251] eta: 0:03:49 lr: 0.000191 loss: 3.0935 (3.0194) grad_norm: 2.1086 (2.1551) time: 0.5078 [2021-03-26 19:00:35 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 810/1251] eta: 0:03:44 lr: 0.000191 loss: 3.0976 (3.0183) grad_norm: 2.2103 (2.1565) time: 0.4950 [2021-03-26 19:00:40 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 820/1251] eta: 0:03:39 lr: 0.000191 loss: 3.0192 (3.0179) grad_norm: 2.1882 (2.1580) time: 0.4955 [2021-03-26 19:00:45 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 830/1251] eta: 0:03:34 lr: 0.000191 loss: 2.8884 (3.0164) grad_norm: 2.1083 (2.1572) time: 0.4953 [2021-03-26 19:00:50 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 840/1251] eta: 0:03:28 lr: 0.000191 loss: 3.1375 (3.0183) grad_norm: 2.0916 (2.1568) time: 0.4943 [2021-03-26 19:00:55 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 850/1251] eta: 0:03:23 lr: 0.000191 loss: 3.1111 (3.0169) grad_norm: 2.1862 (2.1582) time: 0.4983 [2021-03-26 19:01:00 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 860/1251] eta: 0:03:18 lr: 0.000191 loss: 2.9062 (3.0155) grad_norm: 2.1741 (2.1573) time: 0.5040 [2021-03-26 19:01:05 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 870/1251] eta: 0:03:13 lr: 0.000191 loss: 3.0803 (3.0151) grad_norm: 2.1078 (2.1577) time: 0.5055 [2021-03-26 19:01:10 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 880/1251] eta: 0:03:08 lr: 0.000191 loss: 3.1674 (3.0166) grad_norm: 2.0493 (2.1562) time: 0.4996 [2021-03-26 19:01:15 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 890/1251] eta: 0:03:03 lr: 0.000191 loss: 3.1047 (3.0162) grad_norm: 2.0585 (2.1561) time: 0.4998 [2021-03-26 19:01:20 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 900/1251] eta: 0:02:58 lr: 0.000191 loss: 3.1674 (3.0180) grad_norm: 2.1206 (2.1574) time: 0.4980 [2021-03-26 19:01:25 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 910/1251] eta: 0:02:53 lr: 0.000191 loss: 3.1546 (3.0181) grad_norm: 2.0553 (2.1548) time: 0.4961 [2021-03-26 19:01:30 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 920/1251] eta: 0:02:48 lr: 0.000191 loss: 3.0621 (3.0176) grad_norm: 1.8783 (2.1524) time: 0.4992 [2021-03-26 19:01:35 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 930/1251] eta: 0:02:42 lr: 0.000191 loss: 2.9989 (3.0158) grad_norm: 1.9752 (2.1526) time: 0.5000 [2021-03-26 19:01:40 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 940/1251] eta: 0:02:37 lr: 0.000190 loss: 3.0240 (3.0171) grad_norm: 2.0481 (2.1515) time: 0.5023 [2021-03-26 19:01:45 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 950/1251] eta: 0:02:32 lr: 0.000190 loss: 3.0611 (3.0144) grad_norm: 2.0470 (2.1501) time: 0.5057 [2021-03-26 19:01:50 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 960/1251] eta: 0:02:27 lr: 0.000190 loss: 3.0900 (3.0149) grad_norm: 1.9647 (2.1489) time: 0.5050 [2021-03-26 19:01:55 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 970/1251] eta: 0:02:22 lr: 0.000190 loss: 3.0634 (3.0124) grad_norm: 2.0003 (2.1486) time: 0.4997 [2021-03-26 19:02:00 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 980/1251] eta: 0:02:17 lr: 0.000190 loss: 2.9959 (3.0124) grad_norm: 2.0668 (2.1483) time: 0.4994 [2021-03-26 19:02:05 swin_small_patch4_window7_224] INFO: Epoch: [215] [ 990/1251] eta: 0:02:12 lr: 0.000190 loss: 3.0170 (3.0118) grad_norm: 2.0391 (2.1480) time: 0.4993 [2021-03-26 19:02:10 swin_small_patch4_window7_224] INFO: Epoch: [215] [1000/1251] eta: 0:02:07 lr: 0.000190 loss: 3.0565 (3.0127) grad_norm: 2.1172 (2.1484) time: 0.5040 [2021-03-26 19:02:15 swin_small_patch4_window7_224] INFO: Epoch: [215] [1010/1251] eta: 0:02:02 lr: 0.000190 loss: 3.0452 (3.0116) grad_norm: 2.0776 (2.1470) time: 0.5047 [2021-03-26 19:02:20 swin_small_patch4_window7_224] INFO: Epoch: [215] [1020/1251] eta: 0:01:57 lr: 0.000190 loss: 3.0453 (3.0117) grad_norm: 2.0488 (2.1461) time: 0.5012 [2021-03-26 19:02:25 swin_small_patch4_window7_224] INFO: Epoch: [215] [1030/1251] eta: 0:01:52 lr: 0.000190 loss: 3.1431 (3.0122) grad_norm: 2.0665 (2.1458) time: 0.5050 [2021-03-26 19:02:30 swin_small_patch4_window7_224] INFO: Epoch: [215] [1040/1251] eta: 0:01:46 lr: 0.000190 loss: 3.1469 (3.0145) grad_norm: 2.0663 (2.1451) time: 0.5013 [2021-03-26 19:02:35 swin_small_patch4_window7_224] INFO: Epoch: [215] [1050/1251] eta: 0:01:41 lr: 0.000190 loss: 3.1762 (3.0157) grad_norm: 2.0406 (2.1449) time: 0.4951 [2021-03-26 19:02:40 swin_small_patch4_window7_224] INFO: Epoch: [215] [1060/1251] eta: 0:01:36 lr: 0.000190 loss: 3.0110 (3.0148) grad_norm: 2.0406 (2.1438) time: 0.4967 [2021-03-26 19:02:45 swin_small_patch4_window7_224] INFO: Epoch: [215] [1070/1251] eta: 0:01:31 lr: 0.000190 loss: 3.0110 (3.0149) grad_norm: 2.0573 (2.1447) time: 0.5031 [2021-03-26 19:02:50 swin_small_patch4_window7_224] INFO: Epoch: [215] [1080/1251] eta: 0:01:26 lr: 0.000190 loss: 3.1311 (3.0145) grad_norm: 2.0877 (2.1444) time: 0.5088 [2021-03-26 19:02:55 swin_small_patch4_window7_224] INFO: Epoch: [215] [1090/1251] eta: 0:01:21 lr: 0.000190 loss: 3.0954 (3.0125) grad_norm: 2.0489 (2.1437) time: 0.5050 [2021-03-26 19:03:00 swin_small_patch4_window7_224] INFO: Epoch: [215] [1100/1251] eta: 0:01:16 lr: 0.000190 loss: 3.1655 (3.0135) grad_norm: 2.0852 (2.1441) time: 0.5040 [2021-03-26 19:03:05 swin_small_patch4_window7_224] INFO: Epoch: [215] [1110/1251] eta: 0:01:11 lr: 0.000190 loss: 3.2261 (3.0147) grad_norm: 2.1340 (2.1443) time: 0.5088 [2021-03-26 19:03:11 swin_small_patch4_window7_224] INFO: Epoch: [215] [1120/1251] eta: 0:01:06 lr: 0.000190 loss: 3.2341 (3.0139) grad_norm: 2.2208 (2.1453) time: 0.5105 [2021-03-26 19:03:16 swin_small_patch4_window7_224] INFO: Epoch: [215] [1130/1251] eta: 0:01:01 lr: 0.000190 loss: 3.1586 (3.0143) grad_norm: 2.2221 (2.1482) time: 0.5083 [2021-03-26 19:03:21 swin_small_patch4_window7_224] INFO: Epoch: [215] [1140/1251] eta: 0:00:56 lr: 0.000190 loss: 3.1586 (3.0128) grad_norm: 2.1447 (2.1479) time: 0.5014 [2021-03-26 19:03:26 swin_small_patch4_window7_224] INFO: Epoch: [215] [1150/1251] eta: 0:00:51 lr: 0.000190 loss: 3.1514 (3.0133) grad_norm: 2.1284 (2.1486) time: 0.4991 [2021-03-26 19:03:31 swin_small_patch4_window7_224] INFO: Epoch: [215] [1160/1251] eta: 0:00:46 lr: 0.000190 loss: 3.1514 (3.0138) grad_norm: 2.0478 (2.1476) time: 0.4985 [2021-03-26 19:03:36 swin_small_patch4_window7_224] INFO: Epoch: [215] [1170/1251] eta: 0:00:41 lr: 0.000190 loss: 2.7575 (3.0093) grad_norm: 2.0191 (2.1465) time: 0.4999 [2021-03-26 19:03:41 swin_small_patch4_window7_224] INFO: Epoch: [215] [1180/1251] eta: 0:00:35 lr: 0.000190 loss: 3.0798 (3.0114) grad_norm: 2.1147 (2.1475) time: 0.5089 [2021-03-26 19:03:46 swin_small_patch4_window7_224] INFO: Epoch: [215] [1190/1251] eta: 0:00:30 lr: 0.000190 loss: 3.2014 (3.0096) grad_norm: 2.0993 (2.1463) time: 0.5119 [2021-03-26 19:03:51 swin_small_patch4_window7_224] INFO: Epoch: [215] [1200/1251] eta: 0:00:25 lr: 0.000190 loss: 2.9523 (3.0089) grad_norm: 2.0420 (2.1468) time: 0.5046 [2021-03-26 19:03:56 swin_small_patch4_window7_224] INFO: Epoch: [215] [1210/1251] eta: 0:00:20 lr: 0.000190 loss: 3.0529 (3.0094) grad_norm: 2.2160 (2.1468) time: 0.4967 [2021-03-26 19:04:01 swin_small_patch4_window7_224] INFO: Epoch: [215] [1220/1251] eta: 0:00:15 lr: 0.000190 loss: 3.1557 (3.0115) grad_norm: 2.0521 (2.1457) time: 0.4959 [2021-03-26 19:04:06 swin_small_patch4_window7_224] INFO: Epoch: [215] [1230/1251] eta: 0:00:10 lr: 0.000190 loss: 3.0932 (3.0113) grad_norm: 2.0481 (2.1455) time: 0.4985 [2021-03-26 19:04:11 swin_small_patch4_window7_224] INFO: Epoch: [215] [1240/1251] eta: 0:00:05 lr: 0.000190 loss: 2.9804 (3.0109) grad_norm: 2.0481 (2.1454) time: 0.4958 [2021-03-26 19:04:16 swin_small_patch4_window7_224] INFO: Epoch: [215] [1250/1251] eta: 0:00:00 lr: 0.000189 loss: 2.9036 (3.0103) grad_norm: 2.1537 (2.1466) time: 0.4958 [2021-03-26 19:04:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 0.7660 (0.7660) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-26 19:04:58 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7110 (0.7989) acc1: 81.2500 (80.6818) acc5: 95.3125 (95.1705) [2021-03-26 19:04:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7143 (0.8085) acc1: 81.2500 (80.3571) acc5: 96.8750 (95.4613) [2021-03-26 19:05:00 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7459 (0.7917) acc1: 79.6875 (80.4940) acc5: 96.8750 (95.5645) [2021-03-26 19:05:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7644 (0.8119) acc1: 79.6875 (79.9162) acc5: 95.3125 (95.5793) [2021-03-26 19:05:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7820 (0.8081) acc1: 79.6875 (80.1600) acc5: 95.3125 (95.5520) [2021-03-26 19:05:09 swin_small_patch4_window7_224] INFO: * Acc@1 81.330 Acc@5 95.762 loss 0.784 [2021-03-26 19:05:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.3% [2021-03-26 19:05:09 swin_small_patch4_window7_224] INFO: Max accuracy: 81.33% [2021-03-26 19:05:13 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 0/1251] eta: 1:21:58 lr: 0.000189 loss: 3.0783 (3.0783) grad_norm: 1.9806 (1.9806) time: 3.9315 [2021-03-26 19:05:18 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 10/1251] eta: 0:17:29 lr: 0.000189 loss: 3.0783 (2.9914) grad_norm: 1.9806 (2.0438) time: 0.8455 [2021-03-26 19:05:23 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 20/1251] eta: 0:14:02 lr: 0.000189 loss: 3.1249 (3.1134) grad_norm: 1.9701 (2.0610) time: 0.5224 [2021-03-26 19:05:28 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 30/1251] eta: 0:12:43 lr: 0.000189 loss: 3.1249 (3.0845) grad_norm: 2.0821 (2.0783) time: 0.5043 [2021-03-26 19:05:33 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 40/1251] eta: 0:12:01 lr: 0.000189 loss: 3.1225 (3.0397) grad_norm: 2.0725 (2.0796) time: 0.5017 [2021-03-26 19:05:38 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 50/1251] eta: 0:11:34 lr: 0.000189 loss: 3.1618 (3.0150) grad_norm: 2.2638 (2.1730) time: 0.5053 [2021-03-26 19:05:43 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 60/1251] eta: 0:11:13 lr: 0.000189 loss: 3.1662 (3.0039) grad_norm: 2.1539 (2.1701) time: 0.5040 [2021-03-26 19:05:48 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 70/1251] eta: 0:10:58 lr: 0.000189 loss: 3.0550 (3.0056) grad_norm: 2.1539 (2.1719) time: 0.5032 [2021-03-26 19:05:53 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 80/1251] eta: 0:10:44 lr: 0.000189 loss: 3.0462 (2.9812) grad_norm: 2.2077 (2.1659) time: 0.5037 [2021-03-26 19:05:58 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 90/1251] eta: 0:10:31 lr: 0.000189 loss: 3.0462 (2.9859) grad_norm: 2.2077 (2.1744) time: 0.4969 [2021-03-26 19:06:03 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 100/1251] eta: 0:10:20 lr: 0.000189 loss: 3.1625 (3.0073) grad_norm: 2.2337 (inf) time: 0.4927 [2021-03-26 19:06:08 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 110/1251] eta: 0:10:11 lr: 0.000189 loss: 3.1587 (3.0077) grad_norm: 2.2058 (inf) time: 0.4979 [2021-03-26 19:06:13 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 120/1251] eta: 0:10:03 lr: 0.000189 loss: 2.9466 (2.9896) grad_norm: 2.1073 (inf) time: 0.5074 [2021-03-26 19:06:19 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 130/1251] eta: 0:09:57 lr: 0.000189 loss: 2.9850 (3.0019) grad_norm: 2.1539 (inf) time: 0.5158 [2021-03-26 19:06:24 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 140/1251] eta: 0:09:50 lr: 0.000189 loss: 2.8165 (2.9661) grad_norm: 2.1420 (inf) time: 0.5175 [2021-03-26 19:06:29 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 150/1251] eta: 0:09:42 lr: 0.000189 loss: 2.7550 (2.9610) grad_norm: 2.0464 (inf) time: 0.5042 [2021-03-26 19:06:34 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 160/1251] eta: 0:09:35 lr: 0.000189 loss: 3.1369 (2.9768) grad_norm: 2.0705 (inf) time: 0.5011 [2021-03-26 19:06:39 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 170/1251] eta: 0:09:29 lr: 0.000189 loss: 3.2434 (2.9767) grad_norm: 2.0705 (inf) time: 0.5112 [2021-03-26 19:06:44 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 180/1251] eta: 0:09:23 lr: 0.000189 loss: 3.0242 (2.9743) grad_norm: 2.0617 (inf) time: 0.5147 [2021-03-26 19:06:49 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 190/1251] eta: 0:09:17 lr: 0.000189 loss: 3.1565 (2.9813) grad_norm: 2.0197 (inf) time: 0.5160 [2021-03-26 19:06:54 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 200/1251] eta: 0:09:11 lr: 0.000189 loss: 3.1813 (2.9819) grad_norm: 2.1507 (inf) time: 0.5117 [2021-03-26 19:06:59 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 210/1251] eta: 0:09:04 lr: 0.000189 loss: 2.8648 (2.9734) grad_norm: 2.1024 (inf) time: 0.5002 [2021-03-26 19:07:04 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 220/1251] eta: 0:08:58 lr: 0.000189 loss: 2.8352 (2.9685) grad_norm: 1.9790 (inf) time: 0.4947 [2021-03-26 19:07:09 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 230/1251] eta: 0:08:51 lr: 0.000189 loss: 2.8715 (2.9652) grad_norm: 2.0244 (inf) time: 0.4964 [2021-03-26 19:07:14 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 240/1251] eta: 0:08:45 lr: 0.000189 loss: 2.9743 (2.9619) grad_norm: 2.0375 (inf) time: 0.5011 [2021-03-26 19:07:19 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 250/1251] eta: 0:08:40 lr: 0.000189 loss: 3.0590 (2.9593) grad_norm: 2.0057 (inf) time: 0.5085 [2021-03-26 19:07:24 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 260/1251] eta: 0:08:34 lr: 0.000189 loss: 2.8667 (2.9524) grad_norm: 2.0253 (inf) time: 0.5082 [2021-03-26 19:07:30 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 270/1251] eta: 0:08:29 lr: 0.000189 loss: 3.0153 (2.9560) grad_norm: 2.1178 (inf) time: 0.5073 [2021-03-26 19:07:35 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 280/1251] eta: 0:08:23 lr: 0.000189 loss: 3.1810 (2.9651) grad_norm: 2.1788 (inf) time: 0.5076 [2021-03-26 19:07:40 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 290/1251] eta: 0:08:17 lr: 0.000189 loss: 3.3172 (2.9695) grad_norm: 2.1793 (inf) time: 0.5021 [2021-03-26 19:07:45 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 300/1251] eta: 0:08:11 lr: 0.000189 loss: 3.1920 (2.9729) grad_norm: 2.1531 (inf) time: 0.5005 [2021-03-26 19:07:50 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 310/1251] eta: 0:08:06 lr: 0.000188 loss: 2.8681 (2.9657) grad_norm: 2.0382 (inf) time: 0.5030 [2021-03-26 19:07:55 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 320/1251] eta: 0:08:00 lr: 0.000188 loss: 2.8408 (2.9578) grad_norm: 2.0539 (inf) time: 0.5023 [2021-03-26 19:08:00 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 330/1251] eta: 0:07:55 lr: 0.000188 loss: 3.0631 (2.9629) grad_norm: 2.1341 (inf) time: 0.4982 [2021-03-26 19:08:05 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 340/1251] eta: 0:07:49 lr: 0.000188 loss: 3.0727 (2.9664) grad_norm: 2.1790 (inf) time: 0.4994 [2021-03-26 19:08:10 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 350/1251] eta: 0:07:43 lr: 0.000188 loss: 3.1573 (2.9686) grad_norm: 2.1635 (inf) time: 0.5009 [2021-03-26 19:08:15 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 360/1251] eta: 0:07:38 lr: 0.000188 loss: 3.0966 (2.9693) grad_norm: 2.1013 (inf) time: 0.5053 [2021-03-26 19:08:20 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 370/1251] eta: 0:07:33 lr: 0.000188 loss: 2.9782 (2.9670) grad_norm: 2.1013 (inf) time: 0.5035 [2021-03-26 19:08:25 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 380/1251] eta: 0:07:27 lr: 0.000188 loss: 3.0556 (2.9720) grad_norm: 2.0925 (inf) time: 0.5000 [2021-03-26 19:08:30 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 390/1251] eta: 0:07:22 lr: 0.000188 loss: 3.0732 (2.9734) grad_norm: 2.0106 (inf) time: 0.5073 [2021-03-26 19:08:35 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 400/1251] eta: 0:07:17 lr: 0.000188 loss: 3.0732 (2.9751) grad_norm: 2.0192 (inf) time: 0.5067 [2021-03-26 19:08:40 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 410/1251] eta: 0:07:11 lr: 0.000188 loss: 2.8730 (2.9712) grad_norm: 2.0367 (inf) time: 0.5031 [2021-03-26 19:08:45 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 420/1251] eta: 0:07:06 lr: 0.000188 loss: 2.7567 (2.9701) grad_norm: 2.0367 (inf) time: 0.5067 [2021-03-26 19:08:50 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 430/1251] eta: 0:07:01 lr: 0.000188 loss: 2.8601 (2.9676) grad_norm: 2.1690 (inf) time: 0.5059 [2021-03-26 19:08:55 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 440/1251] eta: 0:06:55 lr: 0.000188 loss: 3.0259 (2.9693) grad_norm: 2.2167 (inf) time: 0.5044 [2021-03-26 19:09:00 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 450/1251] eta: 0:06:50 lr: 0.000188 loss: 3.2195 (2.9724) grad_norm: 2.1588 (inf) time: 0.5116 [2021-03-26 19:09:05 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 460/1251] eta: 0:06:45 lr: 0.000188 loss: 3.0680 (2.9755) grad_norm: 2.0793 (inf) time: 0.5136 [2021-03-26 19:09:10 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 470/1251] eta: 0:06:40 lr: 0.000188 loss: 3.0153 (2.9773) grad_norm: 2.0889 (inf) time: 0.5052 [2021-03-26 19:09:15 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 480/1251] eta: 0:06:35 lr: 0.000188 loss: 3.1337 (2.9794) grad_norm: 2.1706 (inf) time: 0.5032 [2021-03-26 19:09:20 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 490/1251] eta: 0:06:29 lr: 0.000188 loss: 3.0938 (2.9834) grad_norm: 2.0877 (inf) time: 0.5020 [2021-03-26 19:09:26 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 500/1251] eta: 0:06:24 lr: 0.000188 loss: 3.1226 (2.9887) grad_norm: 1.9605 (inf) time: 0.5029 [2021-03-26 19:09:31 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 510/1251] eta: 0:06:19 lr: 0.000188 loss: 3.3630 (2.9916) grad_norm: 1.9620 (inf) time: 0.5070 [2021-03-26 19:09:36 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 520/1251] eta: 0:06:14 lr: 0.000188 loss: 3.1406 (2.9895) grad_norm: 2.0255 (inf) time: 0.5024 [2021-03-26 19:09:41 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 530/1251] eta: 0:06:08 lr: 0.000188 loss: 2.9536 (2.9851) grad_norm: 2.2834 (inf) time: 0.5019 [2021-03-26 19:09:46 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 540/1251] eta: 0:06:03 lr: 0.000188 loss: 2.4883 (2.9780) grad_norm: 2.2834 (inf) time: 0.5101 [2021-03-26 19:09:51 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 550/1251] eta: 0:05:59 lr: 0.000188 loss: 2.9853 (2.9804) grad_norm: 2.1097 (inf) time: 0.5268 [2021-03-26 19:09:56 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 560/1251] eta: 0:05:53 lr: 0.000188 loss: 3.1437 (2.9831) grad_norm: 1.9976 (inf) time: 0.5192 [2021-03-26 19:10:01 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 570/1251] eta: 0:05:48 lr: 0.000188 loss: 3.1151 (2.9803) grad_norm: 2.0453 (inf) time: 0.5013 [2021-03-26 19:10:06 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 580/1251] eta: 0:05:43 lr: 0.000188 loss: 2.7298 (2.9726) grad_norm: 2.0993 (inf) time: 0.5006 [2021-03-26 19:10:11 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 590/1251] eta: 0:05:38 lr: 0.000188 loss: 2.6150 (2.9684) grad_norm: 2.0691 (inf) time: 0.5012 [2021-03-26 19:10:16 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 600/1251] eta: 0:05:32 lr: 0.000188 loss: 2.9783 (2.9650) grad_norm: 1.9759 (inf) time: 0.5010 [2021-03-26 19:10:21 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 610/1251] eta: 0:05:27 lr: 0.000188 loss: 2.8207 (2.9626) grad_norm: 1.9867 (inf) time: 0.4985 [2021-03-26 19:10:26 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 620/1251] eta: 0:05:22 lr: 0.000187 loss: 2.9147 (2.9617) grad_norm: 2.0811 (inf) time: 0.4976 [2021-03-26 19:10:31 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 630/1251] eta: 0:05:17 lr: 0.000187 loss: 2.9471 (2.9611) grad_norm: 2.1044 (inf) time: 0.5008 [2021-03-26 19:10:36 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 640/1251] eta: 0:05:11 lr: 0.000187 loss: 3.0291 (2.9639) grad_norm: 2.1633 (inf) time: 0.5023 [2021-03-26 19:10:41 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 650/1251] eta: 0:05:06 lr: 0.000187 loss: 3.0522 (2.9637) grad_norm: 2.1633 (inf) time: 0.5018 [2021-03-26 19:10:46 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 660/1251] eta: 0:05:01 lr: 0.000187 loss: 3.0383 (2.9646) grad_norm: 2.1016 (inf) time: 0.5011 [2021-03-26 19:10:51 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 670/1251] eta: 0:04:56 lr: 0.000187 loss: 3.1786 (2.9638) grad_norm: 2.0561 (inf) time: 0.4993 [2021-03-26 19:10:56 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 680/1251] eta: 0:04:51 lr: 0.000187 loss: 2.8370 (2.9592) grad_norm: 2.0170 (inf) time: 0.5029 [2021-03-26 19:11:01 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 690/1251] eta: 0:04:46 lr: 0.000187 loss: 3.1186 (2.9635) grad_norm: 2.0170 (inf) time: 0.5099 [2021-03-26 19:11:06 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 700/1251] eta: 0:04:41 lr: 0.000187 loss: 3.1605 (2.9633) grad_norm: 1.9985 (inf) time: 0.5100 [2021-03-26 19:11:12 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 710/1251] eta: 0:04:35 lr: 0.000187 loss: 3.0842 (2.9626) grad_norm: 2.0039 (inf) time: 0.5041 [2021-03-26 19:11:17 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 720/1251] eta: 0:04:30 lr: 0.000187 loss: 3.0491 (2.9624) grad_norm: 2.0889 (inf) time: 0.5080 [2021-03-26 19:11:22 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 730/1251] eta: 0:04:25 lr: 0.000187 loss: 3.0491 (2.9613) grad_norm: 2.0644 (inf) time: 0.5133 [2021-03-26 19:11:27 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 740/1251] eta: 0:04:20 lr: 0.000187 loss: 3.0025 (2.9600) grad_norm: 2.0853 (inf) time: 0.5308 [2021-03-26 19:11:32 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 750/1251] eta: 0:04:15 lr: 0.000187 loss: 3.0494 (2.9618) grad_norm: 2.1135 (inf) time: 0.5271 [2021-03-26 19:11:37 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 760/1251] eta: 0:04:10 lr: 0.000187 loss: 3.0730 (2.9613) grad_norm: 2.1474 (inf) time: 0.5037 [2021-03-26 19:11:42 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 770/1251] eta: 0:04:05 lr: 0.000187 loss: 2.9914 (2.9636) grad_norm: 2.1565 (inf) time: 0.5005 [2021-03-26 19:11:47 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 780/1251] eta: 0:04:00 lr: 0.000187 loss: 3.0606 (2.9644) grad_norm: 2.1565 (inf) time: 0.4983 [2021-03-26 19:11:52 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 790/1251] eta: 0:03:55 lr: 0.000187 loss: 2.8018 (2.9620) grad_norm: 2.0827 (inf) time: 0.4990 [2021-03-26 19:11:57 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 800/1251] eta: 0:03:49 lr: 0.000187 loss: 2.8323 (2.9617) grad_norm: 2.0330 (inf) time: 0.5011 [2021-03-26 19:12:02 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 810/1251] eta: 0:03:44 lr: 0.000187 loss: 2.9826 (2.9626) grad_norm: 2.0032 (inf) time: 0.5018 [2021-03-26 19:12:07 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 820/1251] eta: 0:03:39 lr: 0.000187 loss: 2.9756 (2.9611) grad_norm: 2.1751 (inf) time: 0.5051 [2021-03-26 19:12:13 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 830/1251] eta: 0:03:34 lr: 0.000187 loss: 2.9756 (2.9620) grad_norm: 2.1799 (inf) time: 0.5072 [2021-03-26 19:12:18 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 840/1251] eta: 0:03:29 lr: 0.000187 loss: 2.9992 (2.9616) grad_norm: 2.2000 (inf) time: 0.5042 [2021-03-26 19:12:23 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 850/1251] eta: 0:03:24 lr: 0.000187 loss: 2.7775 (2.9595) grad_norm: 2.3009 (inf) time: 0.5038 [2021-03-26 19:12:28 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 860/1251] eta: 0:03:19 lr: 0.000187 loss: 2.9986 (2.9601) grad_norm: 2.1911 (inf) time: 0.5038 [2021-03-26 19:12:33 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 870/1251] eta: 0:03:14 lr: 0.000187 loss: 3.0936 (2.9607) grad_norm: 2.1330 (inf) time: 0.4999 [2021-03-26 19:12:38 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 880/1251] eta: 0:03:09 lr: 0.000187 loss: 3.2691 (2.9651) grad_norm: 2.1259 (inf) time: 0.5124 [2021-03-26 19:12:43 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 890/1251] eta: 0:03:03 lr: 0.000187 loss: 3.3410 (2.9665) grad_norm: 2.1259 (inf) time: 0.5138 [2021-03-26 19:12:48 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 900/1251] eta: 0:02:58 lr: 0.000187 loss: 3.0159 (2.9650) grad_norm: 2.0818 (inf) time: 0.5023 [2021-03-26 19:12:53 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 910/1251] eta: 0:02:53 lr: 0.000187 loss: 2.9852 (2.9661) grad_norm: 2.0423 (inf) time: 0.5092 [2021-03-26 19:12:58 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 920/1251] eta: 0:02:48 lr: 0.000187 loss: 2.9852 (2.9654) grad_norm: 2.1017 (inf) time: 0.5061 [2021-03-26 19:13:03 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 930/1251] eta: 0:02:43 lr: 0.000187 loss: 3.0704 (2.9653) grad_norm: 1.9797 (inf) time: 0.5026 [2021-03-26 19:13:08 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 940/1251] eta: 0:02:38 lr: 0.000186 loss: 3.2004 (2.9683) grad_norm: 2.0208 (inf) time: 0.5086 [2021-03-26 19:13:13 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 950/1251] eta: 0:02:33 lr: 0.000186 loss: 3.2396 (2.9702) grad_norm: 2.0636 (inf) time: 0.5059 [2021-03-26 19:13:18 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 960/1251] eta: 0:02:28 lr: 0.000186 loss: 3.1578 (2.9705) grad_norm: 2.0994 (inf) time: 0.4994 [2021-03-26 19:13:23 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 970/1251] eta: 0:02:23 lr: 0.000186 loss: 3.1186 (2.9716) grad_norm: 2.0994 (inf) time: 0.5040 [2021-03-26 19:13:28 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 980/1251] eta: 0:02:17 lr: 0.000186 loss: 3.0633 (2.9697) grad_norm: 2.0327 (inf) time: 0.5055 [2021-03-26 19:13:33 swin_small_patch4_window7_224] INFO: Epoch: [216] [ 990/1251] eta: 0:02:12 lr: 0.000186 loss: 2.9266 (2.9701) grad_norm: 2.0949 (inf) time: 0.5003 [2021-03-26 19:13:38 swin_small_patch4_window7_224] INFO: Epoch: [216] [1000/1251] eta: 0:02:07 lr: 0.000186 loss: 2.9266 (2.9689) grad_norm: 2.1853 (inf) time: 0.5056 [2021-03-26 19:13:43 swin_small_patch4_window7_224] INFO: Epoch: [216] [1010/1251] eta: 0:02:02 lr: 0.000186 loss: 3.0411 (2.9706) grad_norm: 2.0899 (inf) time: 0.5072 [2021-03-26 19:13:48 swin_small_patch4_window7_224] INFO: Epoch: [216] [1020/1251] eta: 0:01:57 lr: 0.000186 loss: 3.0477 (2.9711) grad_norm: 2.0841 (inf) time: 0.4999 [2021-03-26 19:13:53 swin_small_patch4_window7_224] INFO: Epoch: [216] [1030/1251] eta: 0:01:52 lr: 0.000186 loss: 3.0982 (2.9729) grad_norm: 2.0959 (inf) time: 0.4996 [2021-03-26 19:13:58 swin_small_patch4_window7_224] INFO: Epoch: [216] [1040/1251] eta: 0:01:47 lr: 0.000186 loss: 3.2105 (2.9740) grad_norm: 2.0625 (inf) time: 0.5010 [2021-03-26 19:14:04 swin_small_patch4_window7_224] INFO: Epoch: [216] [1050/1251] eta: 0:01:42 lr: 0.000186 loss: 2.9761 (2.9738) grad_norm: 2.0590 (inf) time: 0.5035 [2021-03-26 19:14:09 swin_small_patch4_window7_224] INFO: Epoch: [216] [1060/1251] eta: 0:01:37 lr: 0.000186 loss: 3.1240 (2.9760) grad_norm: 2.0532 (inf) time: 0.5062 [2021-03-26 19:14:14 swin_small_patch4_window7_224] INFO: Epoch: [216] [1070/1251] eta: 0:01:32 lr: 0.000186 loss: 3.1861 (2.9774) grad_norm: 2.0955 (inf) time: 0.5046 [2021-03-26 19:14:19 swin_small_patch4_window7_224] INFO: Epoch: [216] [1080/1251] eta: 0:01:26 lr: 0.000186 loss: 3.1090 (2.9783) grad_norm: 2.1714 (inf) time: 0.5067 [2021-03-26 19:14:24 swin_small_patch4_window7_224] INFO: Epoch: [216] [1090/1251] eta: 0:01:21 lr: 0.000186 loss: 3.2459 (2.9807) grad_norm: 2.1714 (inf) time: 0.5056 [2021-03-26 19:14:29 swin_small_patch4_window7_224] INFO: Epoch: [216] [1100/1251] eta: 0:01:16 lr: 0.000186 loss: 3.2811 (2.9836) grad_norm: 2.1448 (inf) time: 0.5099 [2021-03-26 19:14:34 swin_small_patch4_window7_224] INFO: Epoch: [216] [1110/1251] eta: 0:01:11 lr: 0.000186 loss: 3.2797 (2.9836) grad_norm: 2.1050 (inf) time: 0.5117 [2021-03-26 19:14:39 swin_small_patch4_window7_224] INFO: Epoch: [216] [1120/1251] eta: 0:01:06 lr: 0.000186 loss: 3.2023 (2.9841) grad_norm: 2.0879 (inf) time: 0.5066 [2021-03-26 19:14:44 swin_small_patch4_window7_224] INFO: Epoch: [216] [1130/1251] eta: 0:01:01 lr: 0.000186 loss: 3.1729 (2.9846) grad_norm: 2.0869 (inf) time: 0.5055 [2021-03-26 19:14:49 swin_small_patch4_window7_224] INFO: Epoch: [216] [1140/1251] eta: 0:00:56 lr: 0.000186 loss: 3.0416 (2.9847) grad_norm: 2.0767 (inf) time: 0.5032 [2021-03-26 19:14:54 swin_small_patch4_window7_224] INFO: Epoch: [216] [1150/1251] eta: 0:00:51 lr: 0.000186 loss: 3.0329 (2.9835) grad_norm: 2.1135 (inf) time: 0.5050 [2021-03-26 19:14:59 swin_small_patch4_window7_224] INFO: Epoch: [216] [1160/1251] eta: 0:00:46 lr: 0.000186 loss: 2.8492 (2.9822) grad_norm: 2.2935 (inf) time: 0.5104 [2021-03-26 19:15:04 swin_small_patch4_window7_224] INFO: Epoch: [216] [1170/1251] eta: 0:00:41 lr: 0.000186 loss: 2.7445 (2.9803) grad_norm: 2.1607 (inf) time: 0.5075 [2021-03-26 19:15:09 swin_small_patch4_window7_224] INFO: Epoch: [216] [1180/1251] eta: 0:00:36 lr: 0.000186 loss: 3.2304 (2.9829) grad_norm: 2.1080 (inf) time: 0.4995 [2021-03-26 19:15:14 swin_small_patch4_window7_224] INFO: Epoch: [216] [1190/1251] eta: 0:00:31 lr: 0.000186 loss: 3.2149 (2.9827) grad_norm: 2.1429 (inf) time: 0.5017 [2021-03-26 19:15:19 swin_small_patch4_window7_224] INFO: Epoch: [216] [1200/1251] eta: 0:00:25 lr: 0.000186 loss: 3.1111 (2.9835) grad_norm: 2.1429 (inf) time: 0.5043 [2021-03-26 19:15:25 swin_small_patch4_window7_224] INFO: Epoch: [216] [1210/1251] eta: 0:00:20 lr: 0.000186 loss: 3.0900 (2.9848) grad_norm: 2.0549 (inf) time: 0.5061 [2021-03-26 19:15:30 swin_small_patch4_window7_224] INFO: Epoch: [216] [1220/1251] eta: 0:00:15 lr: 0.000186 loss: 3.0570 (2.9857) grad_norm: 2.0401 (inf) time: 0.5055 [2021-03-26 19:15:35 swin_small_patch4_window7_224] INFO: Epoch: [216] [1230/1251] eta: 0:00:10 lr: 0.000186 loss: 3.0245 (2.9850) grad_norm: 2.0401 (inf) time: 0.5034 [2021-03-26 19:15:40 swin_small_patch4_window7_224] INFO: Epoch: [216] [1240/1251] eta: 0:00:05 lr: 0.000186 loss: 3.1545 (2.9862) grad_norm: 2.1632 (inf) time: 0.5076 [2021-03-26 19:15:45 swin_small_patch4_window7_224] INFO: Epoch: [216] [1250/1251] eta: 0:00:00 lr: 0.000186 loss: 3.1545 (2.9864) grad_norm: 2.1974 (inf) time: 0.5062 [2021-03-26 19:15:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 1.0279 (1.0279) acc1: 78.1250 (78.1250) acc5: 92.1875 (92.1875) [2021-03-26 19:15:56 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8625 (0.8399) acc1: 79.6875 (80.8239) acc5: 95.3125 (95.4545) [2021-03-26 19:15:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7899 (0.8263) acc1: 79.6875 (80.3571) acc5: 95.3125 (95.9077) [2021-03-26 19:16:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7977 (0.8160) acc1: 81.2500 (80.9476) acc5: 95.3125 (95.7661) [2021-03-26 19:16:02 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8001 (0.8151) acc1: 81.2500 (80.7165) acc5: 95.3125 (95.7698) [2021-03-26 19:16:03 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7601 (0.8151) acc1: 81.2500 (80.5440) acc5: 95.3125 (95.8080) [2021-03-26 19:16:15 swin_small_patch4_window7_224] INFO: * Acc@1 81.254 Acc@5 95.716 loss 0.796 [2021-03-26 19:16:15 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.3% [2021-03-26 19:16:15 swin_small_patch4_window7_224] INFO: Max accuracy: 81.33% [2021-03-26 19:16:19 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 0/1251] eta: 1:27:23 lr: 0.000185 loss: 2.8572 (2.8572) grad_norm: 2.2490 (2.2490) time: 4.1918 [2021-03-26 19:16:24 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 10/1251] eta: 0:17:35 lr: 0.000185 loss: 2.8406 (2.8506) grad_norm: 2.1588 (2.1849) time: 0.8507 [2021-03-26 19:16:29 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 20/1251] eta: 0:14:03 lr: 0.000185 loss: 3.2034 (3.1081) grad_norm: 2.0815 (2.1583) time: 0.5095 [2021-03-26 19:16:34 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 30/1251] eta: 0:12:45 lr: 0.000185 loss: 3.0629 (2.9951) grad_norm: 2.1424 (2.1551) time: 0.5033 [2021-03-26 19:16:39 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 40/1251] eta: 0:12:05 lr: 0.000185 loss: 2.9818 (2.9718) grad_norm: 2.1424 (2.1530) time: 0.5095 [2021-03-26 19:16:44 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 50/1251] eta: 0:11:37 lr: 0.000185 loss: 2.7513 (2.9092) grad_norm: 2.1107 (2.1772) time: 0.5088 [2021-03-26 19:16:49 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 60/1251] eta: 0:11:14 lr: 0.000185 loss: 2.8529 (2.9056) grad_norm: 2.1614 (2.1919) time: 0.4986 [2021-03-26 19:16:55 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 70/1251] eta: 0:10:59 lr: 0.000185 loss: 3.0636 (2.9379) grad_norm: 2.1122 (2.1722) time: 0.5034 [2021-03-26 19:17:00 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 80/1251] eta: 0:10:45 lr: 0.000185 loss: 3.1850 (2.9596) grad_norm: 2.1168 (2.1792) time: 0.5055 [2021-03-26 19:17:05 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 90/1251] eta: 0:10:33 lr: 0.000185 loss: 2.9497 (2.9331) grad_norm: 2.1682 (2.2002) time: 0.4986 [2021-03-26 19:17:10 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 100/1251] eta: 0:10:23 lr: 0.000185 loss: 3.1087 (2.9582) grad_norm: 2.0338 (2.1831) time: 0.5017 [2021-03-26 19:17:15 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 110/1251] eta: 0:10:15 lr: 0.000185 loss: 3.1912 (2.9647) grad_norm: 1.9949 (2.1654) time: 0.5114 [2021-03-26 19:17:20 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 120/1251] eta: 0:10:06 lr: 0.000185 loss: 2.8761 (2.9396) grad_norm: 2.0212 (2.1601) time: 0.5110 [2021-03-26 19:17:25 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 130/1251] eta: 0:09:58 lr: 0.000185 loss: 2.9760 (2.9596) grad_norm: 2.0705 (2.1614) time: 0.5052 [2021-03-26 19:17:30 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 140/1251] eta: 0:09:51 lr: 0.000185 loss: 3.1663 (2.9556) grad_norm: 2.0705 (2.1615) time: 0.5094 [2021-03-26 19:17:35 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 150/1251] eta: 0:09:43 lr: 0.000185 loss: 3.0521 (2.9474) grad_norm: 2.2353 (2.1733) time: 0.5054 [2021-03-26 19:17:40 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 160/1251] eta: 0:09:36 lr: 0.000185 loss: 2.9182 (2.9532) grad_norm: 2.1627 (2.1702) time: 0.5005 [2021-03-26 19:17:45 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 170/1251] eta: 0:09:30 lr: 0.000185 loss: 2.9915 (2.9646) grad_norm: 2.1262 (2.1697) time: 0.5057 [2021-03-26 19:17:50 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 180/1251] eta: 0:09:23 lr: 0.000185 loss: 3.0832 (2.9608) grad_norm: 2.0703 (2.1651) time: 0.5073 [2021-03-26 19:17:55 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 190/1251] eta: 0:09:17 lr: 0.000185 loss: 3.1333 (2.9663) grad_norm: 2.1223 (2.1655) time: 0.5072 [2021-03-26 19:18:00 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 200/1251] eta: 0:09:10 lr: 0.000185 loss: 3.1331 (2.9632) grad_norm: 2.1223 (2.1645) time: 0.5025 [2021-03-26 19:18:05 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 210/1251] eta: 0:09:04 lr: 0.000185 loss: 3.1331 (2.9781) grad_norm: 2.1036 (2.1626) time: 0.4970 [2021-03-26 19:18:10 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 220/1251] eta: 0:08:57 lr: 0.000185 loss: 3.1038 (2.9768) grad_norm: 2.0611 (2.1591) time: 0.4989 [2021-03-26 19:18:15 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 230/1251] eta: 0:08:51 lr: 0.000185 loss: 2.8907 (2.9636) grad_norm: 2.1138 (2.1626) time: 0.4990 [2021-03-26 19:18:20 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 240/1251] eta: 0:08:45 lr: 0.000185 loss: 2.9694 (2.9729) grad_norm: 2.1223 (2.1654) time: 0.4993 [2021-03-26 19:18:25 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 250/1251] eta: 0:08:39 lr: 0.000185 loss: 2.9739 (2.9648) grad_norm: 2.1503 (2.1721) time: 0.5006 [2021-03-26 19:18:30 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 260/1251] eta: 0:08:33 lr: 0.000185 loss: 2.7174 (2.9553) grad_norm: 2.1503 (2.1707) time: 0.5024 [2021-03-26 19:18:35 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 270/1251] eta: 0:08:27 lr: 0.000185 loss: 2.8515 (2.9564) grad_norm: 2.0025 (2.1669) time: 0.4998 [2021-03-26 19:18:40 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 280/1251] eta: 0:08:22 lr: 0.000185 loss: 3.1237 (2.9621) grad_norm: 2.0993 (2.1674) time: 0.5012 [2021-03-26 19:18:45 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 290/1251] eta: 0:08:16 lr: 0.000185 loss: 3.0444 (2.9575) grad_norm: 2.0845 (2.1632) time: 0.5028 [2021-03-26 19:18:50 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 300/1251] eta: 0:08:10 lr: 0.000185 loss: 2.8243 (2.9565) grad_norm: 2.0484 (2.1611) time: 0.4982 [2021-03-26 19:18:55 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 310/1251] eta: 0:08:05 lr: 0.000185 loss: 2.9920 (2.9613) grad_norm: 2.0975 (2.1575) time: 0.5074 [2021-03-26 19:19:00 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 320/1251] eta: 0:08:00 lr: 0.000184 loss: 3.1215 (2.9618) grad_norm: 2.0146 (2.1532) time: 0.5099 [2021-03-26 19:19:05 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 330/1251] eta: 0:07:54 lr: 0.000184 loss: 3.1215 (2.9673) grad_norm: 2.0146 (2.1513) time: 0.5047 [2021-03-26 19:19:10 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 340/1251] eta: 0:07:48 lr: 0.000184 loss: 3.0035 (2.9643) grad_norm: 1.9853 (2.1466) time: 0.5025 [2021-03-26 19:19:16 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 350/1251] eta: 0:07:43 lr: 0.000184 loss: 3.0406 (2.9750) grad_norm: 1.9931 (2.1457) time: 0.5009 [2021-03-26 19:19:20 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 360/1251] eta: 0:07:37 lr: 0.000184 loss: 3.0934 (2.9750) grad_norm: 2.0170 (2.1440) time: 0.4977 [2021-03-26 19:19:25 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 370/1251] eta: 0:07:32 lr: 0.000184 loss: 2.9320 (2.9733) grad_norm: 1.9870 (2.1429) time: 0.4940 [2021-03-26 19:19:30 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 380/1251] eta: 0:07:26 lr: 0.000184 loss: 3.0372 (2.9771) grad_norm: 2.0612 (2.1428) time: 0.4956 [2021-03-26 19:19:35 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 390/1251] eta: 0:07:21 lr: 0.000184 loss: 3.0372 (2.9753) grad_norm: 2.1375 (2.1430) time: 0.4966 [2021-03-26 19:19:40 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 400/1251] eta: 0:07:15 lr: 0.000184 loss: 3.1030 (2.9772) grad_norm: 2.0995 (2.1408) time: 0.4981 [2021-03-26 19:19:45 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 410/1251] eta: 0:07:10 lr: 0.000184 loss: 3.1175 (2.9737) grad_norm: 2.0567 (2.1387) time: 0.5017 [2021-03-26 19:19:50 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 420/1251] eta: 0:07:05 lr: 0.000184 loss: 3.0737 (2.9725) grad_norm: 1.9934 (2.1355) time: 0.5008 [2021-03-26 19:19:55 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 430/1251] eta: 0:06:59 lr: 0.000184 loss: 3.0737 (2.9741) grad_norm: 2.0276 (2.1345) time: 0.4994 [2021-03-26 19:20:00 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 440/1251] eta: 0:06:54 lr: 0.000184 loss: 3.0250 (2.9723) grad_norm: 2.0060 (2.1319) time: 0.4967 [2021-03-26 19:20:05 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 450/1251] eta: 0:06:49 lr: 0.000184 loss: 3.0030 (2.9712) grad_norm: 2.0451 (2.1325) time: 0.4961 [2021-03-26 19:20:10 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 460/1251] eta: 0:06:43 lr: 0.000184 loss: 3.0104 (2.9733) grad_norm: 2.1588 (2.1339) time: 0.4986 [2021-03-26 19:20:15 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 470/1251] eta: 0:06:38 lr: 0.000184 loss: 3.0610 (2.9754) grad_norm: 2.1536 (2.1357) time: 0.4998 [2021-03-26 19:20:20 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 480/1251] eta: 0:06:33 lr: 0.000184 loss: 3.0610 (2.9751) grad_norm: 2.1174 (2.1346) time: 0.5029 [2021-03-26 19:20:25 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 490/1251] eta: 0:06:28 lr: 0.000184 loss: 2.9453 (2.9752) grad_norm: 2.1173 (2.1340) time: 0.5042 [2021-03-26 19:20:30 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 500/1251] eta: 0:06:22 lr: 0.000184 loss: 3.0275 (2.9791) grad_norm: 2.0554 (2.1333) time: 0.5049 [2021-03-26 19:20:35 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 510/1251] eta: 0:06:17 lr: 0.000184 loss: 3.0487 (2.9787) grad_norm: 2.0202 (2.1340) time: 0.5037 [2021-03-26 19:20:40 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 520/1251] eta: 0:06:12 lr: 0.000184 loss: 2.9947 (2.9779) grad_norm: 2.0309 (2.1334) time: 0.4997 [2021-03-26 19:20:45 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 530/1251] eta: 0:06:07 lr: 0.000184 loss: 2.9947 (2.9800) grad_norm: 2.1048 (2.1346) time: 0.4957 [2021-03-26 19:20:50 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 540/1251] eta: 0:06:02 lr: 0.000184 loss: 2.9861 (2.9791) grad_norm: 2.1048 (2.1343) time: 0.5021 [2021-03-26 19:20:56 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 550/1251] eta: 0:05:57 lr: 0.000184 loss: 3.0893 (2.9832) grad_norm: 2.0704 (2.1395) time: 0.5188 [2021-03-26 19:21:01 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 560/1251] eta: 0:05:52 lr: 0.000184 loss: 3.1643 (2.9851) grad_norm: 2.1393 (2.1392) time: 0.5183 [2021-03-26 19:21:06 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 570/1251] eta: 0:05:46 lr: 0.000184 loss: 3.1767 (2.9843) grad_norm: 2.0802 (2.1376) time: 0.5036 [2021-03-26 19:21:11 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 580/1251] eta: 0:05:41 lr: 0.000184 loss: 3.2217 (2.9872) grad_norm: 2.0802 (2.1383) time: 0.5029 [2021-03-26 19:21:16 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 590/1251] eta: 0:05:36 lr: 0.000184 loss: 3.2492 (2.9901) grad_norm: 2.1393 (2.1379) time: 0.5073 [2021-03-26 19:21:21 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 600/1251] eta: 0:05:31 lr: 0.000184 loss: 3.0823 (2.9897) grad_norm: 2.0655 (2.1378) time: 0.5072 [2021-03-26 19:21:26 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 610/1251] eta: 0:05:26 lr: 0.000184 loss: 2.9548 (2.9898) grad_norm: 2.1317 (2.1387) time: 0.5059 [2021-03-26 19:21:31 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 620/1251] eta: 0:05:21 lr: 0.000184 loss: 2.9548 (2.9889) grad_norm: 2.1576 (2.1407) time: 0.5070 [2021-03-26 19:21:36 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 630/1251] eta: 0:05:16 lr: 0.000184 loss: 2.9104 (2.9877) grad_norm: 2.0263 (2.1402) time: 0.5077 [2021-03-26 19:21:41 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 640/1251] eta: 0:05:11 lr: 0.000183 loss: 2.9249 (2.9879) grad_norm: 2.0332 (2.1399) time: 0.5090 [2021-03-26 19:21:46 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 650/1251] eta: 0:05:05 lr: 0.000183 loss: 3.2283 (2.9919) grad_norm: 2.0920 (2.1427) time: 0.5052 [2021-03-26 19:21:51 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 660/1251] eta: 0:05:00 lr: 0.000183 loss: 3.2283 (2.9917) grad_norm: 2.0920 (2.1421) time: 0.5047 [2021-03-26 19:21:57 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 670/1251] eta: 0:04:55 lr: 0.000183 loss: 2.9955 (2.9923) grad_norm: 2.0131 (2.1394) time: 0.5092 [2021-03-26 19:22:02 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 680/1251] eta: 0:04:50 lr: 0.000183 loss: 2.9382 (2.9936) grad_norm: 1.9667 (2.1383) time: 0.5067 [2021-03-26 19:22:07 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 690/1251] eta: 0:04:45 lr: 0.000183 loss: 2.9332 (2.9893) grad_norm: 1.9820 (2.1366) time: 0.5125 [2021-03-26 19:22:12 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 700/1251] eta: 0:04:40 lr: 0.000183 loss: 3.0244 (2.9900) grad_norm: 2.0246 (2.1356) time: 0.5143 [2021-03-26 19:22:17 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 710/1251] eta: 0:04:35 lr: 0.000183 loss: 3.0481 (2.9897) grad_norm: 2.1459 (2.1376) time: 0.5051 [2021-03-26 19:22:22 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 720/1251] eta: 0:04:30 lr: 0.000183 loss: 3.0168 (2.9891) grad_norm: 2.1459 (2.1368) time: 0.5010 [2021-03-26 19:22:27 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 730/1251] eta: 0:04:25 lr: 0.000183 loss: 3.0372 (2.9882) grad_norm: 2.1448 (2.1390) time: 0.5093 [2021-03-26 19:22:32 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 740/1251] eta: 0:04:20 lr: 0.000183 loss: 2.7877 (2.9852) grad_norm: 2.1448 (2.1392) time: 0.5169 [2021-03-26 19:22:37 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 750/1251] eta: 0:04:15 lr: 0.000183 loss: 2.8854 (2.9835) grad_norm: 2.0720 (2.1396) time: 0.5097 [2021-03-26 19:22:42 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 760/1251] eta: 0:04:09 lr: 0.000183 loss: 3.0140 (2.9869) grad_norm: 2.0720 (2.1384) time: 0.5056 [2021-03-26 19:22:47 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 770/1251] eta: 0:04:04 lr: 0.000183 loss: 3.2958 (2.9904) grad_norm: 2.0593 (2.1371) time: 0.5068 [2021-03-26 19:22:52 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 780/1251] eta: 0:03:59 lr: 0.000183 loss: 3.2795 (2.9893) grad_norm: 2.0365 (2.1348) time: 0.5019 [2021-03-26 19:22:58 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 790/1251] eta: 0:03:54 lr: 0.000183 loss: 2.8940 (2.9879) grad_norm: 1.9898 (2.1340) time: 0.5090 [2021-03-26 19:23:03 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 800/1251] eta: 0:03:49 lr: 0.000183 loss: 3.1099 (2.9898) grad_norm: 2.0939 (2.1355) time: 0.5050 [2021-03-26 19:23:08 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 810/1251] eta: 0:03:44 lr: 0.000183 loss: 3.1099 (2.9917) grad_norm: 2.1212 (2.1350) time: 0.4983 [2021-03-26 19:23:13 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 820/1251] eta: 0:03:39 lr: 0.000183 loss: 2.9620 (2.9881) grad_norm: 2.1338 (2.1364) time: 0.4998 [2021-03-26 19:23:17 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 830/1251] eta: 0:03:34 lr: 0.000183 loss: 2.7840 (2.9874) grad_norm: 2.1170 (2.1362) time: 0.4952 [2021-03-26 19:23:23 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 840/1251] eta: 0:03:28 lr: 0.000183 loss: 2.7840 (2.9846) grad_norm: 2.0798 (2.1359) time: 0.5042 [2021-03-26 19:23:28 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 850/1251] eta: 0:03:23 lr: 0.000183 loss: 2.9712 (2.9848) grad_norm: 2.1041 (2.1363) time: 0.5029 [2021-03-26 19:23:33 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 860/1251] eta: 0:03:18 lr: 0.000183 loss: 3.0347 (2.9849) grad_norm: 2.1901 (2.1378) time: 0.5066 [2021-03-26 19:23:38 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 870/1251] eta: 0:03:13 lr: 0.000183 loss: 3.0672 (2.9851) grad_norm: 2.1675 (2.1420) time: 0.5123 [2021-03-26 19:23:43 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 880/1251] eta: 0:03:08 lr: 0.000183 loss: 3.0810 (2.9840) grad_norm: 2.1508 (2.1421) time: 0.5097 [2021-03-26 19:23:48 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 890/1251] eta: 0:03:03 lr: 0.000183 loss: 2.9750 (2.9852) grad_norm: 2.1020 (2.1417) time: 0.5109 [2021-03-26 19:23:53 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 900/1251] eta: 0:02:58 lr: 0.000183 loss: 2.9750 (2.9841) grad_norm: 2.1182 (2.1410) time: 0.5041 [2021-03-26 19:23:58 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 910/1251] eta: 0:02:53 lr: 0.000183 loss: 3.0157 (2.9829) grad_norm: 2.1182 (2.1412) time: 0.5031 [2021-03-26 19:24:03 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 920/1251] eta: 0:02:48 lr: 0.000183 loss: 2.9099 (2.9810) grad_norm: 2.1522 (2.1441) time: 0.5088 [2021-03-26 19:24:08 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 930/1251] eta: 0:02:43 lr: 0.000183 loss: 2.8962 (2.9803) grad_norm: 2.1197 (2.1451) time: 0.5029 [2021-03-26 19:24:13 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 940/1251] eta: 0:02:37 lr: 0.000183 loss: 2.9755 (2.9810) grad_norm: 2.1317 (2.1457) time: 0.4946 [2021-03-26 19:24:18 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 950/1251] eta: 0:02:32 lr: 0.000183 loss: 3.1471 (2.9827) grad_norm: 2.1317 (2.1449) time: 0.4998 [2021-03-26 19:24:23 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 960/1251] eta: 0:02:27 lr: 0.000182 loss: 3.1471 (2.9830) grad_norm: 2.0881 (2.1449) time: 0.5030 [2021-03-26 19:24:28 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 970/1251] eta: 0:02:22 lr: 0.000182 loss: 3.1312 (2.9841) grad_norm: 2.0664 (2.1440) time: 0.4984 [2021-03-26 19:24:33 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 980/1251] eta: 0:02:17 lr: 0.000182 loss: 2.8368 (2.9822) grad_norm: 2.0289 (2.1435) time: 0.4982 [2021-03-26 19:24:38 swin_small_patch4_window7_224] INFO: Epoch: [217] [ 990/1251] eta: 0:02:12 lr: 0.000182 loss: 2.7790 (2.9797) grad_norm: 2.2097 (2.1447) time: 0.5011 [2021-03-26 19:24:43 swin_small_patch4_window7_224] INFO: Epoch: [217] [1000/1251] eta: 0:02:07 lr: 0.000182 loss: 3.0144 (2.9808) grad_norm: 2.2136 (2.1455) time: 0.5062 [2021-03-26 19:24:48 swin_small_patch4_window7_224] INFO: Epoch: [217] [1010/1251] eta: 0:02:02 lr: 0.000182 loss: 3.0424 (2.9814) grad_norm: 2.0812 (2.1458) time: 0.5056 [2021-03-26 19:24:53 swin_small_patch4_window7_224] INFO: Epoch: [217] [1020/1251] eta: 0:01:57 lr: 0.000182 loss: 2.9181 (2.9809) grad_norm: 2.1381 (2.1461) time: 0.5039 [2021-03-26 19:24:58 swin_small_patch4_window7_224] INFO: Epoch: [217] [1030/1251] eta: 0:01:52 lr: 0.000182 loss: 2.8675 (2.9797) grad_norm: 2.1233 (2.1463) time: 0.5005 [2021-03-26 19:25:03 swin_small_patch4_window7_224] INFO: Epoch: [217] [1040/1251] eta: 0:01:47 lr: 0.000182 loss: 2.8078 (2.9768) grad_norm: 2.0847 (2.1460) time: 0.4952 [2021-03-26 19:25:08 swin_small_patch4_window7_224] INFO: Epoch: [217] [1050/1251] eta: 0:01:42 lr: 0.000182 loss: 2.7725 (2.9748) grad_norm: 2.0155 (2.1453) time: 0.5072 [2021-03-26 19:25:13 swin_small_patch4_window7_224] INFO: Epoch: [217] [1060/1251] eta: 0:01:36 lr: 0.000182 loss: 2.8165 (2.9725) grad_norm: 2.0743 (2.1466) time: 0.5085 [2021-03-26 19:25:18 swin_small_patch4_window7_224] INFO: Epoch: [217] [1070/1251] eta: 0:01:31 lr: 0.000182 loss: 2.6077 (2.9684) grad_norm: 2.1784 (2.1475) time: 0.5015 [2021-03-26 19:25:23 swin_small_patch4_window7_224] INFO: Epoch: [217] [1080/1251] eta: 0:01:26 lr: 0.000182 loss: 2.6077 (2.9670) grad_norm: 2.1138 (2.1463) time: 0.5019 [2021-03-26 19:25:28 swin_small_patch4_window7_224] INFO: Epoch: [217] [1090/1251] eta: 0:01:21 lr: 0.000182 loss: 2.9007 (2.9649) grad_norm: 2.0860 (2.1468) time: 0.4997 [2021-03-26 19:25:33 swin_small_patch4_window7_224] INFO: Epoch: [217] [1100/1251] eta: 0:01:16 lr: 0.000182 loss: 2.8991 (2.9644) grad_norm: 2.1387 (2.1469) time: 0.5026 [2021-03-26 19:25:39 swin_small_patch4_window7_224] INFO: Epoch: [217] [1110/1251] eta: 0:01:11 lr: 0.000182 loss: 2.8435 (2.9617) grad_norm: 2.1250 (2.1464) time: 0.5078 [2021-03-26 19:25:44 swin_small_patch4_window7_224] INFO: Epoch: [217] [1120/1251] eta: 0:01:06 lr: 0.000182 loss: 2.8365 (2.9607) grad_norm: 2.0651 (2.1465) time: 0.5050 [2021-03-26 19:25:49 swin_small_patch4_window7_224] INFO: Epoch: [217] [1130/1251] eta: 0:01:01 lr: 0.000182 loss: 2.9732 (2.9612) grad_norm: 2.2332 (2.1478) time: 0.5040 [2021-03-26 19:25:54 swin_small_patch4_window7_224] INFO: Epoch: [217] [1140/1251] eta: 0:00:56 lr: 0.000182 loss: 3.1669 (2.9612) grad_norm: 2.1895 (2.1472) time: 0.5039 [2021-03-26 19:25:59 swin_small_patch4_window7_224] INFO: Epoch: [217] [1150/1251] eta: 0:00:51 lr: 0.000182 loss: 3.1462 (2.9634) grad_norm: 2.1410 (2.1472) time: 0.5057 [2021-03-26 19:26:04 swin_small_patch4_window7_224] INFO: Epoch: [217] [1160/1251] eta: 0:00:46 lr: 0.000182 loss: 3.1222 (2.9634) grad_norm: 2.0682 (2.1472) time: 0.5075 [2021-03-26 19:26:09 swin_small_patch4_window7_224] INFO: Epoch: [217] [1170/1251] eta: 0:00:41 lr: 0.000182 loss: 2.8767 (2.9639) grad_norm: 2.1298 (2.1513) time: 0.5007 [2021-03-26 19:26:14 swin_small_patch4_window7_224] INFO: Epoch: [217] [1180/1251] eta: 0:00:35 lr: 0.000182 loss: 2.9099 (2.9638) grad_norm: 2.2230 (2.1529) time: 0.4968 [2021-03-26 19:26:19 swin_small_patch4_window7_224] INFO: Epoch: [217] [1190/1251] eta: 0:00:30 lr: 0.000182 loss: 3.0917 (2.9640) grad_norm: 2.2439 (2.1536) time: 0.5054 [2021-03-26 19:26:24 swin_small_patch4_window7_224] INFO: Epoch: [217] [1200/1251] eta: 0:00:25 lr: 0.000182 loss: 2.9652 (2.9637) grad_norm: 2.1290 (nan) time: 0.5033 [2021-03-26 19:26:29 swin_small_patch4_window7_224] INFO: Epoch: [217] [1210/1251] eta: 0:00:20 lr: 0.000182 loss: 2.9271 (2.9635) grad_norm: 2.1586 (nan) time: 0.4981 [2021-03-26 19:26:34 swin_small_patch4_window7_224] INFO: Epoch: [217] [1220/1251] eta: 0:00:15 lr: 0.000182 loss: 2.7386 (2.9632) grad_norm: 2.1586 (nan) time: 0.5023 [2021-03-26 19:26:39 swin_small_patch4_window7_224] INFO: Epoch: [217] [1230/1251] eta: 0:00:10 lr: 0.000182 loss: 3.0850 (2.9648) grad_norm: 2.0934 (nan) time: 0.4987 [2021-03-26 19:26:44 swin_small_patch4_window7_224] INFO: Epoch: [217] [1240/1251] eta: 0:00:05 lr: 0.000182 loss: 3.2013 (2.9646) grad_norm: 2.1345 (nan) time: 0.4946 [2021-03-26 19:26:49 swin_small_patch4_window7_224] INFO: Epoch: [217] [1250/1251] eta: 0:00:00 lr: 0.000182 loss: 3.1426 (2.9653) grad_norm: 2.1078 (nan) time: 0.4947 [2021-03-26 19:27:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 0.8372 (0.8372) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-26 19:27:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7161 (0.7588) acc1: 84.3750 (82.6705) acc5: 96.8750 (96.0227) [2021-03-26 19:27:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7191 (0.7709) acc1: 82.8125 (80.9524) acc5: 96.8750 (96.4286) [2021-03-26 19:27:07 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7502 (0.8003) acc1: 78.1250 (80.2419) acc5: 96.8750 (95.7157) [2021-03-26 19:27:09 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.9320 (0.8131) acc1: 78.1250 (79.7256) acc5: 93.7500 (95.6936) [2021-03-26 19:27:09 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7463 (0.8080) acc1: 79.2453 (79.9680) acc5: 95.3125 (95.7760) [2021-03-26 19:27:20 swin_small_patch4_window7_224] INFO: * Acc@1 81.274 Acc@5 95.720 loss 0.795 [2021-03-26 19:27:20 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.3% [2021-03-26 19:27:20 swin_small_patch4_window7_224] INFO: Max accuracy: 81.33% [2021-03-26 19:27:24 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 0/1251] eta: 1:23:38 lr: 0.000182 loss: 3.0186 (3.0186) grad_norm: 1.8607 (1.8607) time: 4.0115 [2021-03-26 19:27:29 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 10/1251] eta: 0:17:21 lr: 0.000182 loss: 3.1961 (3.1111) grad_norm: 2.1315 (2.1278) time: 0.8392 [2021-03-26 19:27:34 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 20/1251] eta: 0:13:56 lr: 0.000181 loss: 3.2413 (3.1727) grad_norm: 2.1424 (2.1322) time: 0.5133 [2021-03-26 19:27:39 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 30/1251] eta: 0:12:36 lr: 0.000181 loss: 3.1434 (3.0547) grad_norm: 2.1107 (2.1761) time: 0.4994 [2021-03-26 19:27:44 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 40/1251] eta: 0:12:00 lr: 0.000181 loss: 3.1291 (3.0938) grad_norm: 2.1296 (2.2063) time: 0.5056 [2021-03-26 19:27:49 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 50/1251] eta: 0:11:32 lr: 0.000181 loss: 3.1291 (3.0426) grad_norm: 2.1433 (2.1779) time: 0.5093 [2021-03-26 19:27:54 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 60/1251] eta: 0:11:12 lr: 0.000181 loss: 2.7058 (2.9988) grad_norm: 2.0882 (2.1749) time: 0.5033 [2021-03-26 19:28:00 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 70/1251] eta: 0:10:57 lr: 0.000181 loss: 3.0262 (3.0086) grad_norm: 2.1333 (2.2029) time: 0.5070 [2021-03-26 19:28:05 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 80/1251] eta: 0:10:44 lr: 0.000181 loss: 3.0648 (3.0160) grad_norm: 2.1365 (2.2295) time: 0.5073 [2021-03-26 19:28:10 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 90/1251] eta: 0:10:32 lr: 0.000181 loss: 3.0439 (3.0234) grad_norm: 2.0208 (2.2112) time: 0.5023 [2021-03-26 19:28:15 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 100/1251] eta: 0:10:22 lr: 0.000181 loss: 3.0439 (3.0046) grad_norm: 2.0014 (2.2074) time: 0.4999 [2021-03-26 19:28:20 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 110/1251] eta: 0:10:15 lr: 0.000181 loss: 3.1394 (3.0065) grad_norm: 2.0631 (2.2043) time: 0.5122 [2021-03-26 19:28:25 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 120/1251] eta: 0:10:06 lr: 0.000181 loss: 3.1394 (3.0006) grad_norm: 2.1528 (2.2103) time: 0.5169 [2021-03-26 19:28:30 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 130/1251] eta: 0:09:58 lr: 0.000181 loss: 3.0812 (3.0083) grad_norm: 2.1391 (2.2026) time: 0.5062 [2021-03-26 19:28:35 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 140/1251] eta: 0:09:51 lr: 0.000181 loss: 3.1653 (3.0132) grad_norm: 2.0355 (2.1988) time: 0.5049 [2021-03-26 19:28:40 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 150/1251] eta: 0:09:43 lr: 0.000181 loss: 3.0021 (3.0035) grad_norm: 2.0717 (2.1948) time: 0.5051 [2021-03-26 19:28:45 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 160/1251] eta: 0:09:36 lr: 0.000181 loss: 3.0021 (3.0115) grad_norm: 2.0195 (2.1835) time: 0.5055 [2021-03-26 19:28:50 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 170/1251] eta: 0:09:29 lr: 0.000181 loss: 3.0517 (3.0055) grad_norm: 2.0195 (2.1763) time: 0.5012 [2021-03-26 19:28:55 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 180/1251] eta: 0:09:23 lr: 0.000181 loss: 2.9626 (3.0070) grad_norm: 2.0808 (2.1710) time: 0.5049 [2021-03-26 19:29:00 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 190/1251] eta: 0:09:18 lr: 0.000181 loss: 3.0833 (3.0100) grad_norm: 2.2004 (2.1777) time: 0.5185 [2021-03-26 19:29:05 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 200/1251] eta: 0:09:11 lr: 0.000181 loss: 3.2955 (3.0246) grad_norm: 2.2746 (2.1822) time: 0.5074 [2021-03-26 19:29:10 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 210/1251] eta: 0:09:04 lr: 0.000181 loss: 3.3687 (3.0362) grad_norm: 2.2627 (2.1837) time: 0.4973 [2021-03-26 19:29:15 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 220/1251] eta: 0:08:58 lr: 0.000181 loss: 3.2883 (3.0373) grad_norm: 2.2280 (2.1838) time: 0.5010 [2021-03-26 19:29:20 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 230/1251] eta: 0:08:52 lr: 0.000181 loss: 3.0359 (3.0273) grad_norm: 2.1376 (2.1843) time: 0.5023 [2021-03-26 19:29:26 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 240/1251] eta: 0:08:46 lr: 0.000181 loss: 3.0359 (3.0266) grad_norm: 2.1853 (2.1885) time: 0.5083 [2021-03-26 19:29:31 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 250/1251] eta: 0:08:41 lr: 0.000181 loss: 3.1053 (3.0318) grad_norm: 2.1329 (2.1955) time: 0.5109 [2021-03-26 19:29:36 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 260/1251] eta: 0:08:35 lr: 0.000181 loss: 3.1151 (3.0297) grad_norm: 2.0318 (2.1956) time: 0.5118 [2021-03-26 19:29:41 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 270/1251] eta: 0:08:29 lr: 0.000181 loss: 2.8702 (3.0207) grad_norm: 2.2064 (2.1972) time: 0.5091 [2021-03-26 19:29:46 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 280/1251] eta: 0:08:24 lr: 0.000181 loss: 2.8575 (3.0151) grad_norm: 2.2188 (2.1975) time: 0.5042 [2021-03-26 19:29:51 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 290/1251] eta: 0:08:18 lr: 0.000181 loss: 2.7096 (3.0008) grad_norm: 2.0981 (2.1927) time: 0.4992 [2021-03-26 19:29:56 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 300/1251] eta: 0:08:12 lr: 0.000181 loss: 2.9645 (3.0056) grad_norm: 2.0981 (2.1930) time: 0.4997 [2021-03-26 19:30:01 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 310/1251] eta: 0:08:06 lr: 0.000181 loss: 3.1555 (3.0019) grad_norm: 2.1141 (2.1903) time: 0.5048 [2021-03-26 19:30:06 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 320/1251] eta: 0:08:01 lr: 0.000181 loss: 2.9811 (2.9981) grad_norm: 2.1086 (2.1963) time: 0.5002 [2021-03-26 19:30:11 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 330/1251] eta: 0:07:55 lr: 0.000181 loss: 3.0713 (3.0019) grad_norm: 2.2117 (2.1972) time: 0.4957 [2021-03-26 19:30:16 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 340/1251] eta: 0:07:49 lr: 0.000180 loss: 3.2457 (3.0040) grad_norm: 2.1563 (2.1953) time: 0.4986 [2021-03-26 19:30:21 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 350/1251] eta: 0:07:44 lr: 0.000180 loss: 3.1076 (3.0052) grad_norm: 2.1180 (2.1947) time: 0.5014 [2021-03-26 19:30:26 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 360/1251] eta: 0:07:38 lr: 0.000180 loss: 3.0859 (3.0054) grad_norm: 2.0704 (2.1900) time: 0.5016 [2021-03-26 19:30:31 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 370/1251] eta: 0:07:33 lr: 0.000180 loss: 2.9836 (3.0047) grad_norm: 2.0170 (2.1883) time: 0.4996 [2021-03-26 19:30:36 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 380/1251] eta: 0:07:27 lr: 0.000180 loss: 2.9262 (2.9984) grad_norm: 2.0505 (2.1850) time: 0.4934 [2021-03-26 19:30:41 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 390/1251] eta: 0:07:22 lr: 0.000180 loss: 2.9047 (2.9965) grad_norm: 2.0577 (2.1829) time: 0.4980 [2021-03-26 19:30:46 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 400/1251] eta: 0:07:16 lr: 0.000180 loss: 2.9073 (2.9961) grad_norm: 2.0780 (2.1806) time: 0.4986 [2021-03-26 19:30:51 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 410/1251] eta: 0:07:11 lr: 0.000180 loss: 2.9732 (2.9934) grad_norm: 2.0652 (2.1786) time: 0.4941 [2021-03-26 19:30:56 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 420/1251] eta: 0:07:05 lr: 0.000180 loss: 3.2286 (2.9961) grad_norm: 2.0637 (2.1774) time: 0.4965 [2021-03-26 19:31:01 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 430/1251] eta: 0:07:00 lr: 0.000180 loss: 3.2405 (2.9977) grad_norm: 2.0788 (2.1742) time: 0.5059 [2021-03-26 19:31:06 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 440/1251] eta: 0:06:55 lr: 0.000180 loss: 2.8835 (2.9963) grad_norm: 2.0964 (2.1738) time: 0.5062 [2021-03-26 19:31:11 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 450/1251] eta: 0:06:49 lr: 0.000180 loss: 3.0169 (2.9973) grad_norm: 2.1348 (2.1740) time: 0.4985 [2021-03-26 19:31:16 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 460/1251] eta: 0:06:44 lr: 0.000180 loss: 3.1499 (3.0021) grad_norm: 2.1064 (2.1743) time: 0.5058 [2021-03-26 19:31:21 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 470/1251] eta: 0:06:39 lr: 0.000180 loss: 3.1095 (3.0010) grad_norm: 2.1057 (2.1744) time: 0.5072 [2021-03-26 19:31:26 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 480/1251] eta: 0:06:34 lr: 0.000180 loss: 3.0366 (3.0020) grad_norm: 2.0765 (2.1722) time: 0.5017 [2021-03-26 19:31:31 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 490/1251] eta: 0:06:28 lr: 0.000180 loss: 2.9692 (2.9987) grad_norm: 2.0605 (2.1726) time: 0.5011 [2021-03-26 19:31:36 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 500/1251] eta: 0:06:23 lr: 0.000180 loss: 2.9692 (2.9990) grad_norm: 2.1080 (2.1740) time: 0.5014 [2021-03-26 19:31:41 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 510/1251] eta: 0:06:18 lr: 0.000180 loss: 2.9859 (2.9970) grad_norm: 2.1769 (2.1755) time: 0.4999 [2021-03-26 19:31:46 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 520/1251] eta: 0:06:13 lr: 0.000180 loss: 2.9723 (2.9944) grad_norm: 2.1784 (2.1790) time: 0.4955 [2021-03-26 19:31:51 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 530/1251] eta: 0:06:07 lr: 0.000180 loss: 2.9180 (2.9951) grad_norm: 2.2374 (2.1809) time: 0.4937 [2021-03-26 19:31:56 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 540/1251] eta: 0:06:02 lr: 0.000180 loss: 3.0199 (2.9991) grad_norm: 2.1208 (2.1795) time: 0.5020 [2021-03-26 19:32:01 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 550/1251] eta: 0:05:57 lr: 0.000180 loss: 3.0498 (2.9983) grad_norm: 2.0952 (2.1791) time: 0.5157 [2021-03-26 19:32:06 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 560/1251] eta: 0:05:52 lr: 0.000180 loss: 3.0326 (2.9992) grad_norm: 2.1364 (2.1805) time: 0.5103 [2021-03-26 19:32:11 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 570/1251] eta: 0:05:47 lr: 0.000180 loss: 2.9937 (2.9917) grad_norm: 2.0581 (2.1800) time: 0.4986 [2021-03-26 19:32:16 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 580/1251] eta: 0:05:41 lr: 0.000180 loss: 3.0898 (2.9956) grad_norm: 2.0963 (2.1805) time: 0.4977 [2021-03-26 19:32:21 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 590/1251] eta: 0:05:36 lr: 0.000180 loss: 3.2412 (2.9992) grad_norm: 2.1652 (2.1789) time: 0.5002 [2021-03-26 19:32:26 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 600/1251] eta: 0:05:31 lr: 0.000180 loss: 3.2412 (3.0015) grad_norm: 2.0610 (2.1770) time: 0.5032 [2021-03-26 19:32:31 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 610/1251] eta: 0:05:26 lr: 0.000180 loss: 3.1331 (3.0004) grad_norm: 2.0490 (2.1750) time: 0.5031 [2021-03-26 19:32:36 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 620/1251] eta: 0:05:21 lr: 0.000180 loss: 2.9615 (2.9979) grad_norm: 2.0967 (2.1764) time: 0.5022 [2021-03-26 19:32:41 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 630/1251] eta: 0:05:16 lr: 0.000180 loss: 2.9615 (2.9997) grad_norm: 2.1904 (2.1786) time: 0.4992 [2021-03-26 19:32:46 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 640/1251] eta: 0:05:10 lr: 0.000180 loss: 2.8742 (2.9955) grad_norm: 2.1113 (2.1785) time: 0.5026 [2021-03-26 19:32:51 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 650/1251] eta: 0:05:05 lr: 0.000180 loss: 2.9456 (2.9983) grad_norm: 2.0762 (2.1785) time: 0.5042 [2021-03-26 19:32:56 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 660/1251] eta: 0:05:00 lr: 0.000179 loss: 3.1380 (2.9991) grad_norm: 2.1081 (2.1784) time: 0.4966 [2021-03-26 19:33:01 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 670/1251] eta: 0:04:55 lr: 0.000179 loss: 3.0490 (2.9974) grad_norm: 2.1385 (2.1788) time: 0.4979 [2021-03-26 19:33:06 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 680/1251] eta: 0:04:50 lr: 0.000179 loss: 2.9497 (2.9982) grad_norm: 2.1752 (2.1791) time: 0.5055 [2021-03-26 19:33:11 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 690/1251] eta: 0:04:45 lr: 0.000179 loss: 2.9791 (2.9960) grad_norm: 2.1754 (2.1797) time: 0.5047 [2021-03-26 19:33:16 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 700/1251] eta: 0:04:40 lr: 0.000179 loss: 3.1030 (2.9984) grad_norm: 2.0280 (2.1770) time: 0.5063 [2021-03-26 19:33:22 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 710/1251] eta: 0:04:35 lr: 0.000179 loss: 3.0749 (2.9966) grad_norm: 2.0922 (2.1764) time: 0.5074 [2021-03-26 19:33:27 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 720/1251] eta: 0:04:29 lr: 0.000179 loss: 2.8428 (2.9942) grad_norm: 2.1050 (2.1750) time: 0.5065 [2021-03-26 19:33:32 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 730/1251] eta: 0:04:24 lr: 0.000179 loss: 3.0000 (2.9944) grad_norm: 2.1063 (2.1756) time: 0.5106 [2021-03-26 19:33:37 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 740/1251] eta: 0:04:20 lr: 0.000179 loss: 3.1509 (2.9972) grad_norm: 2.1646 (2.1754) time: 0.5267 [2021-03-26 19:33:42 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 750/1251] eta: 0:04:14 lr: 0.000179 loss: 3.1979 (2.9973) grad_norm: 2.1646 (2.1775) time: 0.5244 [2021-03-26 19:33:47 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 760/1251] eta: 0:04:09 lr: 0.000179 loss: 3.1019 (2.9995) grad_norm: 2.1665 (2.1778) time: 0.5096 [2021-03-26 19:33:52 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 770/1251] eta: 0:04:04 lr: 0.000179 loss: 2.9985 (2.9981) grad_norm: 2.1709 (2.1805) time: 0.5042 [2021-03-26 19:33:57 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 780/1251] eta: 0:03:59 lr: 0.000179 loss: 2.9622 (2.9981) grad_norm: 2.2834 (2.1816) time: 0.4990 [2021-03-26 19:34:02 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 790/1251] eta: 0:03:54 lr: 0.000179 loss: 3.0505 (2.9973) grad_norm: 2.2154 (2.1837) time: 0.5017 [2021-03-26 19:34:07 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 800/1251] eta: 0:03:49 lr: 0.000179 loss: 3.0907 (2.9993) grad_norm: 2.1072 (2.1826) time: 0.5018 [2021-03-26 19:34:12 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 810/1251] eta: 0:03:44 lr: 0.000179 loss: 3.1431 (3.0008) grad_norm: 2.0016 (2.1810) time: 0.5055 [2021-03-26 19:34:18 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 820/1251] eta: 0:03:39 lr: 0.000179 loss: 3.1431 (2.9997) grad_norm: 1.9851 (2.1800) time: 0.5118 [2021-03-26 19:34:23 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 830/1251] eta: 0:03:34 lr: 0.000179 loss: 2.8631 (2.9993) grad_norm: 2.0802 (2.1795) time: 0.5112 [2021-03-26 19:34:28 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 840/1251] eta: 0:03:29 lr: 0.000179 loss: 3.2192 (3.0030) grad_norm: 2.0802 (2.1805) time: 0.5085 [2021-03-26 19:34:33 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 850/1251] eta: 0:03:23 lr: 0.000179 loss: 3.2818 (3.0050) grad_norm: 2.1370 (2.1822) time: 0.5098 [2021-03-26 19:34:38 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 860/1251] eta: 0:03:18 lr: 0.000179 loss: 3.0627 (3.0026) grad_norm: 2.1471 (2.1822) time: 0.5106 [2021-03-26 19:34:43 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 870/1251] eta: 0:03:13 lr: 0.000179 loss: 2.8453 (3.0011) grad_norm: 2.1471 (2.1827) time: 0.5085 [2021-03-26 19:34:48 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 880/1251] eta: 0:03:08 lr: 0.000179 loss: 2.8061 (2.9998) grad_norm: 2.2234 (2.1844) time: 0.5066 [2021-03-26 19:34:53 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 890/1251] eta: 0:03:03 lr: 0.000179 loss: 2.8061 (3.0004) grad_norm: 2.2234 (2.1852) time: 0.5055 [2021-03-26 19:34:58 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 900/1251] eta: 0:02:58 lr: 0.000179 loss: 3.0474 (3.0001) grad_norm: 2.0867 (2.1866) time: 0.5049 [2021-03-26 19:35:03 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 910/1251] eta: 0:02:53 lr: 0.000179 loss: 3.0474 (3.0012) grad_norm: 2.2352 (2.1881) time: 0.4978 [2021-03-26 19:35:08 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 920/1251] eta: 0:02:48 lr: 0.000179 loss: 3.2455 (3.0025) grad_norm: 2.1342 (2.1871) time: 0.5015 [2021-03-26 19:35:13 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 930/1251] eta: 0:02:43 lr: 0.000179 loss: 3.1538 (3.0033) grad_norm: 2.0445 (2.1930) time: 0.5167 [2021-03-26 19:35:19 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 940/1251] eta: 0:02:38 lr: 0.000179 loss: 3.0512 (3.0029) grad_norm: 2.1290 (2.1948) time: 0.5171 [2021-03-26 19:35:24 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 950/1251] eta: 0:02:33 lr: 0.000179 loss: 2.8757 (3.0017) grad_norm: 2.1290 (2.1945) time: 0.5055 [2021-03-26 19:35:29 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 960/1251] eta: 0:02:27 lr: 0.000179 loss: 2.9017 (3.0008) grad_norm: 2.1012 (2.1947) time: 0.4996 [2021-03-26 19:35:34 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 970/1251] eta: 0:02:22 lr: 0.000179 loss: 2.9017 (2.9999) grad_norm: 2.2064 (2.1974) time: 0.4970 [2021-03-26 19:35:39 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 980/1251] eta: 0:02:17 lr: 0.000178 loss: 3.0272 (3.0015) grad_norm: 2.4060 (2.2003) time: 0.4962 [2021-03-26 19:35:44 swin_small_patch4_window7_224] INFO: Epoch: [218] [ 990/1251] eta: 0:02:12 lr: 0.000178 loss: 3.2179 (3.0015) grad_norm: 2.3125 (2.2002) time: 0.5073 [2021-03-26 19:35:49 swin_small_patch4_window7_224] INFO: Epoch: [218] [1000/1251] eta: 0:02:07 lr: 0.000178 loss: 2.8341 (3.0002) grad_norm: 2.2571 (2.2015) time: 0.5155 [2021-03-26 19:35:54 swin_small_patch4_window7_224] INFO: Epoch: [218] [1010/1251] eta: 0:02:02 lr: 0.000178 loss: 2.8341 (2.9992) grad_norm: 2.2932 (2.2033) time: 0.5157 [2021-03-26 19:35:59 swin_small_patch4_window7_224] INFO: Epoch: [218] [1020/1251] eta: 0:01:57 lr: 0.000178 loss: 2.9184 (2.9985) grad_norm: 2.2932 (2.2063) time: 0.5060 [2021-03-26 19:36:04 swin_small_patch4_window7_224] INFO: Epoch: [218] [1030/1251] eta: 0:01:52 lr: 0.000178 loss: 2.9493 (2.9995) grad_norm: 2.3050 (2.2113) time: 0.4995 [2021-03-26 19:36:09 swin_small_patch4_window7_224] INFO: Epoch: [218] [1040/1251] eta: 0:01:47 lr: 0.000178 loss: 2.9078 (2.9952) grad_norm: 2.1988 (2.2107) time: 0.5037 [2021-03-26 19:36:14 swin_small_patch4_window7_224] INFO: Epoch: [218] [1050/1251] eta: 0:01:42 lr: 0.000178 loss: 2.8142 (2.9945) grad_norm: 2.1377 (2.2110) time: 0.5020 [2021-03-26 19:36:19 swin_small_patch4_window7_224] INFO: Epoch: [218] [1060/1251] eta: 0:01:37 lr: 0.000178 loss: 3.0364 (2.9957) grad_norm: 2.2091 (2.2112) time: 0.5001 [2021-03-26 19:36:24 swin_small_patch4_window7_224] INFO: Epoch: [218] [1070/1251] eta: 0:01:31 lr: 0.000178 loss: 3.0511 (2.9963) grad_norm: 2.1489 (2.2105) time: 0.5004 [2021-03-26 19:36:29 swin_small_patch4_window7_224] INFO: Epoch: [218] [1080/1251] eta: 0:01:26 lr: 0.000178 loss: 3.0533 (2.9983) grad_norm: 2.1307 (2.2109) time: 0.4980 [2021-03-26 19:36:34 swin_small_patch4_window7_224] INFO: Epoch: [218] [1090/1251] eta: 0:01:21 lr: 0.000178 loss: 3.1810 (2.9994) grad_norm: 2.1304 (2.2107) time: 0.4968 [2021-03-26 19:36:39 swin_small_patch4_window7_224] INFO: Epoch: [218] [1100/1251] eta: 0:01:16 lr: 0.000178 loss: 3.1133 (2.9989) grad_norm: 2.2623 (2.2135) time: 0.5029 [2021-03-26 19:36:44 swin_small_patch4_window7_224] INFO: Epoch: [218] [1110/1251] eta: 0:01:11 lr: 0.000178 loss: 3.1088 (3.0001) grad_norm: 2.2778 (2.2135) time: 0.5090 [2021-03-26 19:36:49 swin_small_patch4_window7_224] INFO: Epoch: [218] [1120/1251] eta: 0:01:06 lr: 0.000178 loss: 3.0527 (2.9984) grad_norm: 2.1781 (2.2148) time: 0.5051 [2021-03-26 19:36:54 swin_small_patch4_window7_224] INFO: Epoch: [218] [1130/1251] eta: 0:01:01 lr: 0.000178 loss: 3.0702 (2.9992) grad_norm: 2.1202 (2.2148) time: 0.5026 [2021-03-26 19:36:59 swin_small_patch4_window7_224] INFO: Epoch: [218] [1140/1251] eta: 0:00:56 lr: 0.000178 loss: 3.1596 (3.0000) grad_norm: 2.1706 (2.2180) time: 0.5016 [2021-03-26 19:37:04 swin_small_patch4_window7_224] INFO: Epoch: [218] [1150/1251] eta: 0:00:51 lr: 0.000178 loss: 3.0064 (2.9997) grad_norm: 2.1295 (2.2172) time: 0.4987 [2021-03-26 19:37:09 swin_small_patch4_window7_224] INFO: Epoch: [218] [1160/1251] eta: 0:00:46 lr: 0.000178 loss: 2.9488 (2.9983) grad_norm: 2.0915 (2.2166) time: 0.5001 [2021-03-26 19:37:14 swin_small_patch4_window7_224] INFO: Epoch: [218] [1170/1251] eta: 0:00:41 lr: 0.000178 loss: 3.1435 (3.0006) grad_norm: 2.1211 (2.2164) time: 0.4968 [2021-03-26 19:37:19 swin_small_patch4_window7_224] INFO: Epoch: [218] [1180/1251] eta: 0:00:36 lr: 0.000178 loss: 3.1608 (2.9998) grad_norm: 2.1974 (2.2163) time: 0.5016 [2021-03-26 19:37:24 swin_small_patch4_window7_224] INFO: Epoch: [218] [1190/1251] eta: 0:00:30 lr: 0.000178 loss: 3.1608 (2.9995) grad_norm: 2.2616 (2.2168) time: 0.5058 [2021-03-26 19:37:29 swin_small_patch4_window7_224] INFO: Epoch: [218] [1200/1251] eta: 0:00:25 lr: 0.000178 loss: 3.2063 (3.0011) grad_norm: 2.2484 (2.2173) time: 0.5000 [2021-03-26 19:37:34 swin_small_patch4_window7_224] INFO: Epoch: [218] [1210/1251] eta: 0:00:20 lr: 0.000178 loss: 3.0675 (3.0009) grad_norm: 2.2691 (2.2184) time: 0.4988 [2021-03-26 19:37:39 swin_small_patch4_window7_224] INFO: Epoch: [218] [1220/1251] eta: 0:00:15 lr: 0.000178 loss: 2.6615 (2.9973) grad_norm: 2.2691 (2.2183) time: 0.4959 [2021-03-26 19:37:44 swin_small_patch4_window7_224] INFO: Epoch: [218] [1230/1251] eta: 0:00:10 lr: 0.000178 loss: 2.8356 (2.9973) grad_norm: 2.1706 (2.2187) time: 0.4962 [2021-03-26 19:37:49 swin_small_patch4_window7_224] INFO: Epoch: [218] [1240/1251] eta: 0:00:05 lr: 0.000178 loss: 3.0198 (2.9989) grad_norm: 2.1771 (2.2191) time: 0.4944 [2021-03-26 19:37:54 swin_small_patch4_window7_224] INFO: Epoch: [218] [1250/1251] eta: 0:00:00 lr: 0.000178 loss: 3.1258 (3.0004) grad_norm: 2.1614 (2.2181) time: 0.4887 [2021-03-26 19:38:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:03 loss: 1.0267 (1.0267) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.7500) [2021-03-26 19:38:06 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8597 (0.8524) acc1: 78.1250 (78.9773) acc5: 93.7500 (94.7443) [2021-03-26 19:38:08 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7648 (0.8073) acc1: 81.2500 (80.5804) acc5: 96.8750 (95.6101) [2021-03-26 19:38:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7297 (0.7978) acc1: 79.6875 (80.0403) acc5: 96.8750 (96.1190) [2021-03-26 19:38:12 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7511 (0.8043) acc1: 79.6875 (80.2210) acc5: 95.3125 (95.7698) [2021-03-26 19:38:13 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8559 (0.8202) acc1: 79.6875 (80.0960) acc5: 95.3125 (95.4880) [2021-03-26 19:38:24 swin_small_patch4_window7_224] INFO: * Acc@1 81.216 Acc@5 95.678 loss 0.795 [2021-03-26 19:38:24 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.2% [2021-03-26 19:38:24 swin_small_patch4_window7_224] INFO: Max accuracy: 81.33% [2021-03-26 19:38:29 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 0/1251] eta: 1:51:42 lr: 0.000178 loss: 2.9589 (2.9589) grad_norm: 2.0904 (2.0904) time: 5.3575 [2021-03-26 19:38:34 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 10/1251] eta: 0:19:36 lr: 0.000178 loss: 3.1018 (3.0859) grad_norm: 2.1673 (2.1856) time: 0.9478 [2021-03-26 19:38:39 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 20/1251] eta: 0:15:05 lr: 0.000178 loss: 2.9934 (2.9334) grad_norm: 2.1673 (2.1757) time: 0.5043 [2021-03-26 19:38:44 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 30/1251] eta: 0:13:26 lr: 0.000178 loss: 3.0146 (2.9818) grad_norm: 2.1143 (2.1742) time: 0.5024 [2021-03-26 19:38:50 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 40/1251] eta: 0:12:36 lr: 0.000178 loss: 3.0890 (2.9880) grad_norm: 2.1824 (2.2151) time: 0.5092 [2021-03-26 19:38:55 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 50/1251] eta: 0:12:01 lr: 0.000177 loss: 3.0733 (2.9973) grad_norm: 2.2805 (2.2200) time: 0.5089 [2021-03-26 19:39:00 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 60/1251] eta: 0:11:37 lr: 0.000177 loss: 3.0123 (2.9765) grad_norm: 2.0730 (2.1944) time: 0.5038 [2021-03-26 19:39:05 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 70/1251] eta: 0:11:19 lr: 0.000177 loss: 2.9690 (2.9757) grad_norm: 2.1239 (2.2103) time: 0.5112 [2021-03-26 19:39:10 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 80/1251] eta: 0:11:03 lr: 0.000177 loss: 3.0529 (2.9725) grad_norm: 2.1266 (2.2092) time: 0.5081 [2021-03-26 19:39:15 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 90/1251] eta: 0:10:49 lr: 0.000177 loss: 3.0854 (2.9773) grad_norm: 2.1400 (2.2189) time: 0.5017 [2021-03-26 19:39:20 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 100/1251] eta: 0:10:37 lr: 0.000177 loss: 3.0531 (2.9572) grad_norm: 2.2320 (2.2108) time: 0.5027 [2021-03-26 19:39:25 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 110/1251] eta: 0:10:26 lr: 0.000177 loss: 3.1551 (2.9830) grad_norm: 2.2320 (2.2261) time: 0.5017 [2021-03-26 19:39:30 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 120/1251] eta: 0:10:17 lr: 0.000177 loss: 3.2357 (2.9912) grad_norm: 2.2251 (2.2232) time: 0.5054 [2021-03-26 19:39:35 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 130/1251] eta: 0:10:08 lr: 0.000177 loss: 3.0727 (2.9867) grad_norm: 2.1803 (2.2394) time: 0.5088 [2021-03-26 19:39:40 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 140/1251] eta: 0:10:00 lr: 0.000177 loss: 2.9449 (2.9736) grad_norm: 2.1870 (2.2303) time: 0.5076 [2021-03-26 19:39:45 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 150/1251] eta: 0:09:52 lr: 0.000177 loss: 3.0150 (2.9812) grad_norm: 2.0977 (2.2286) time: 0.5036 [2021-03-26 19:39:50 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 160/1251] eta: 0:09:44 lr: 0.000177 loss: 3.1676 (2.9936) grad_norm: 2.2945 (2.2441) time: 0.5029 [2021-03-26 19:39:55 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 170/1251] eta: 0:09:36 lr: 0.000177 loss: 3.0807 (2.9935) grad_norm: 2.2421 (2.2396) time: 0.5013 [2021-03-26 19:40:00 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 180/1251] eta: 0:09:29 lr: 0.000177 loss: 3.0252 (2.9997) grad_norm: 2.0978 (2.2373) time: 0.5038 [2021-03-26 19:40:06 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 190/1251] eta: 0:09:23 lr: 0.000177 loss: 3.0179 (2.9913) grad_norm: 2.1560 (2.2555) time: 0.5142 [2021-03-26 19:40:11 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 200/1251] eta: 0:09:17 lr: 0.000177 loss: 2.9535 (2.9825) grad_norm: 2.1706 (2.2570) time: 0.5129 [2021-03-26 19:40:16 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 210/1251] eta: 0:09:10 lr: 0.000177 loss: 3.1151 (2.9884) grad_norm: 2.2366 (2.2620) time: 0.5047 [2021-03-26 19:40:21 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 220/1251] eta: 0:09:03 lr: 0.000177 loss: 3.1838 (2.9920) grad_norm: 2.1656 (2.2549) time: 0.4996 [2021-03-26 19:40:26 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 230/1251] eta: 0:08:57 lr: 0.000177 loss: 3.1463 (2.9892) grad_norm: 2.1085 (2.2537) time: 0.5042 [2021-03-26 19:40:31 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 240/1251] eta: 0:08:51 lr: 0.000177 loss: 3.0599 (2.9929) grad_norm: 2.2128 (2.2540) time: 0.5030 [2021-03-26 19:40:36 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 250/1251] eta: 0:08:45 lr: 0.000177 loss: 3.0640 (2.9983) grad_norm: 2.1342 (2.2488) time: 0.5003 [2021-03-26 19:40:41 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 260/1251] eta: 0:08:38 lr: 0.000177 loss: 3.0536 (2.9976) grad_norm: 2.1010 (2.2457) time: 0.5013 [2021-03-26 19:40:46 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 270/1251] eta: 0:08:33 lr: 0.000177 loss: 2.9983 (2.9985) grad_norm: 2.1350 (2.2427) time: 0.5046 [2021-03-26 19:40:51 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 280/1251] eta: 0:08:27 lr: 0.000177 loss: 3.0964 (3.0005) grad_norm: 2.1072 (2.2369) time: 0.5076 [2021-03-26 19:40:56 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 290/1251] eta: 0:08:21 lr: 0.000177 loss: 2.9949 (2.9963) grad_norm: 2.0779 (2.2338) time: 0.4989 [2021-03-26 19:41:01 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 300/1251] eta: 0:08:15 lr: 0.000177 loss: 2.9678 (2.9945) grad_norm: 2.0867 (2.2306) time: 0.4981 [2021-03-26 19:41:06 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 310/1251] eta: 0:08:09 lr: 0.000177 loss: 3.0973 (2.9920) grad_norm: 2.1272 (2.2312) time: 0.5008 [2021-03-26 19:41:11 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 320/1251] eta: 0:08:04 lr: 0.000177 loss: 3.0199 (2.9931) grad_norm: 2.1879 (2.2330) time: 0.5076 [2021-03-26 19:41:16 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 330/1251] eta: 0:07:58 lr: 0.000177 loss: 2.9680 (2.9888) grad_norm: 2.2489 (2.2323) time: 0.5114 [2021-03-26 19:41:21 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 340/1251] eta: 0:07:52 lr: 0.000177 loss: 2.9680 (2.9822) grad_norm: 2.2326 (2.2362) time: 0.5039 [2021-03-26 19:41:26 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 350/1251] eta: 0:07:47 lr: 0.000177 loss: 3.0964 (2.9884) grad_norm: 2.1753 (2.2331) time: 0.5071 [2021-03-26 19:41:31 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 360/1251] eta: 0:07:41 lr: 0.000177 loss: 3.2178 (2.9894) grad_norm: 2.1850 (2.2345) time: 0.5094 [2021-03-26 19:41:36 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 370/1251] eta: 0:07:36 lr: 0.000177 loss: 3.1477 (2.9906) grad_norm: 2.1358 (2.2355) time: 0.5035 [2021-03-26 19:41:41 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 380/1251] eta: 0:07:30 lr: 0.000176 loss: 3.0479 (2.9927) grad_norm: 2.0902 (2.2346) time: 0.5015 [2021-03-26 19:41:46 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 390/1251] eta: 0:07:25 lr: 0.000176 loss: 3.1032 (2.9925) grad_norm: 2.1652 (2.2358) time: 0.5036 [2021-03-26 19:41:51 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 400/1251] eta: 0:07:19 lr: 0.000176 loss: 3.1441 (2.9912) grad_norm: 2.2436 (2.2414) time: 0.5042 [2021-03-26 19:41:56 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 410/1251] eta: 0:07:14 lr: 0.000176 loss: 3.0548 (2.9929) grad_norm: 2.3331 (2.2463) time: 0.5007 [2021-03-26 19:42:01 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 420/1251] eta: 0:07:09 lr: 0.000176 loss: 3.0985 (2.9946) grad_norm: 2.2905 (2.2457) time: 0.5047 [2021-03-26 19:42:07 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 430/1251] eta: 0:07:03 lr: 0.000176 loss: 3.0313 (2.9876) grad_norm: 2.1673 (2.2441) time: 0.5077 [2021-03-26 19:42:12 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 440/1251] eta: 0:06:58 lr: 0.000176 loss: 2.9930 (2.9871) grad_norm: 2.0910 (2.2403) time: 0.5049 [2021-03-26 19:42:17 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 450/1251] eta: 0:06:52 lr: 0.000176 loss: 2.9675 (2.9801) grad_norm: 2.1210 (2.2429) time: 0.5005 [2021-03-26 19:42:22 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 460/1251] eta: 0:06:47 lr: 0.000176 loss: 2.8400 (2.9770) grad_norm: 2.1863 (2.2461) time: 0.4984 [2021-03-26 19:42:27 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 470/1251] eta: 0:06:42 lr: 0.000176 loss: 2.9598 (2.9770) grad_norm: 2.2506 (2.2472) time: 0.5020 [2021-03-26 19:42:32 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 480/1251] eta: 0:06:36 lr: 0.000176 loss: 2.8013 (2.9661) grad_norm: 2.2095 (2.2464) time: 0.5054 [2021-03-26 19:42:37 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 490/1251] eta: 0:06:31 lr: 0.000176 loss: 2.7968 (2.9687) grad_norm: 2.2089 (2.2488) time: 0.5009 [2021-03-26 19:42:42 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 500/1251] eta: 0:06:26 lr: 0.000176 loss: 3.1765 (2.9694) grad_norm: 2.2272 (2.2494) time: 0.5005 [2021-03-26 19:42:47 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 510/1251] eta: 0:06:21 lr: 0.000176 loss: 3.1164 (2.9682) grad_norm: 2.2272 (2.2580) time: 0.5123 [2021-03-26 19:42:52 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 520/1251] eta: 0:06:15 lr: 0.000176 loss: 2.9803 (2.9670) grad_norm: 2.1584 (2.2567) time: 0.5134 [2021-03-26 19:42:57 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 530/1251] eta: 0:06:10 lr: 0.000176 loss: 3.0286 (2.9636) grad_norm: 2.1272 (2.2546) time: 0.5051 [2021-03-26 19:43:02 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 540/1251] eta: 0:06:05 lr: 0.000176 loss: 2.9456 (2.9607) grad_norm: 2.1272 (2.2553) time: 0.5059 [2021-03-26 19:43:07 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 550/1251] eta: 0:06:00 lr: 0.000176 loss: 2.9772 (2.9659) grad_norm: 2.1830 (2.2546) time: 0.5230 [2021-03-26 19:43:12 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 560/1251] eta: 0:05:55 lr: 0.000176 loss: 3.2681 (2.9712) grad_norm: 2.1134 (2.2514) time: 0.5166 [2021-03-26 19:43:17 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 570/1251] eta: 0:05:49 lr: 0.000176 loss: 3.2811 (2.9757) grad_norm: 2.1936 (2.2536) time: 0.4948 [2021-03-26 19:43:22 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 580/1251] eta: 0:05:44 lr: 0.000176 loss: 3.2114 (2.9762) grad_norm: 2.2618 (2.2535) time: 0.4953 [2021-03-26 19:43:27 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 590/1251] eta: 0:05:39 lr: 0.000176 loss: 2.9891 (2.9722) grad_norm: 2.1425 (2.2523) time: 0.5060 [2021-03-26 19:43:32 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 600/1251] eta: 0:05:34 lr: 0.000176 loss: 2.9330 (2.9712) grad_norm: 2.2455 (2.2537) time: 0.5077 [2021-03-26 19:43:37 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 610/1251] eta: 0:05:28 lr: 0.000176 loss: 2.8215 (2.9679) grad_norm: 2.2455 (2.2568) time: 0.5013 [2021-03-26 19:43:42 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 620/1251] eta: 0:05:23 lr: 0.000176 loss: 2.8217 (2.9669) grad_norm: 2.2685 (nan) time: 0.5020 [2021-03-26 19:43:47 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 630/1251] eta: 0:05:18 lr: 0.000176 loss: 3.0735 (2.9706) grad_norm: 2.1838 (nan) time: 0.4987 [2021-03-26 19:43:52 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 640/1251] eta: 0:05:12 lr: 0.000176 loss: 3.1871 (2.9665) grad_norm: 2.0463 (nan) time: 0.4972 [2021-03-26 19:43:57 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 650/1251] eta: 0:05:07 lr: 0.000176 loss: 2.9682 (2.9638) grad_norm: 2.1457 (nan) time: 0.5011 [2021-03-26 19:44:02 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 660/1251] eta: 0:05:02 lr: 0.000176 loss: 3.0483 (2.9653) grad_norm: 2.2466 (nan) time: 0.5025 [2021-03-26 19:44:08 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 670/1251] eta: 0:04:57 lr: 0.000176 loss: 3.1883 (2.9675) grad_norm: 2.2215 (nan) time: 0.5075 [2021-03-26 19:44:13 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 680/1251] eta: 0:04:52 lr: 0.000176 loss: 3.1070 (2.9691) grad_norm: 2.2215 (nan) time: 0.5128 [2021-03-26 19:44:18 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 690/1251] eta: 0:04:47 lr: 0.000176 loss: 3.0489 (2.9695) grad_norm: 2.1111 (nan) time: 0.5069 [2021-03-26 19:44:23 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 700/1251] eta: 0:04:41 lr: 0.000175 loss: 3.0537 (2.9699) grad_norm: 2.1918 (nan) time: 0.5003 [2021-03-26 19:44:28 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 710/1251] eta: 0:04:36 lr: 0.000175 loss: 3.0537 (2.9687) grad_norm: 2.2949 (nan) time: 0.5022 [2021-03-26 19:44:33 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 720/1251] eta: 0:04:31 lr: 0.000175 loss: 3.0026 (2.9681) grad_norm: 2.3020 (nan) time: 0.5042 [2021-03-26 19:44:38 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 730/1251] eta: 0:04:26 lr: 0.000175 loss: 3.0635 (2.9670) grad_norm: 2.1713 (nan) time: 0.5113 [2021-03-26 19:44:43 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 740/1251] eta: 0:04:21 lr: 0.000175 loss: 3.0853 (2.9694) grad_norm: 2.1276 (nan) time: 0.5275 [2021-03-26 19:44:48 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 750/1251] eta: 0:04:16 lr: 0.000175 loss: 3.0737 (2.9675) grad_norm: 2.1985 (nan) time: 0.5193 [2021-03-26 19:44:53 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 760/1251] eta: 0:04:11 lr: 0.000175 loss: 3.0250 (2.9688) grad_norm: 2.1460 (nan) time: 0.5035 [2021-03-26 19:44:58 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 770/1251] eta: 0:04:06 lr: 0.000175 loss: 3.1116 (2.9683) grad_norm: 2.1449 (nan) time: 0.5030 [2021-03-26 19:45:04 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 780/1251] eta: 0:04:00 lr: 0.000175 loss: 3.2971 (2.9700) grad_norm: 2.3094 (nan) time: 0.5122 [2021-03-26 19:45:09 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 790/1251] eta: 0:03:55 lr: 0.000175 loss: 3.1111 (2.9700) grad_norm: 2.3542 (nan) time: 0.5193 [2021-03-26 19:45:14 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 800/1251] eta: 0:03:50 lr: 0.000175 loss: 2.9855 (2.9696) grad_norm: 2.2616 (nan) time: 0.5070 [2021-03-26 19:45:19 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 810/1251] eta: 0:03:45 lr: 0.000175 loss: 2.9855 (2.9703) grad_norm: 2.2175 (nan) time: 0.5042 [2021-03-26 19:45:24 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 820/1251] eta: 0:03:40 lr: 0.000175 loss: 2.9882 (2.9705) grad_norm: 2.1892 (nan) time: 0.5110 [2021-03-26 19:45:29 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 830/1251] eta: 0:03:35 lr: 0.000175 loss: 3.1326 (2.9726) grad_norm: 2.1512 (nan) time: 0.5061 [2021-03-26 19:45:34 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 840/1251] eta: 0:03:30 lr: 0.000175 loss: 3.1634 (2.9735) grad_norm: 2.2423 (nan) time: 0.5027 [2021-03-26 19:45:39 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 850/1251] eta: 0:03:24 lr: 0.000175 loss: 3.0994 (2.9730) grad_norm: 2.3503 (nan) time: 0.5024 [2021-03-26 19:45:44 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 860/1251] eta: 0:03:19 lr: 0.000175 loss: 3.1284 (2.9752) grad_norm: 2.2562 (nan) time: 0.5025 [2021-03-26 19:45:49 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 870/1251] eta: 0:03:14 lr: 0.000175 loss: 3.1353 (2.9743) grad_norm: 2.1517 (nan) time: 0.5026 [2021-03-26 19:45:54 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 880/1251] eta: 0:03:09 lr: 0.000175 loss: 3.1021 (2.9770) grad_norm: 2.1146 (nan) time: 0.5035 [2021-03-26 19:45:59 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 890/1251] eta: 0:03:04 lr: 0.000175 loss: 3.3240 (2.9788) grad_norm: 2.1929 (nan) time: 0.5040 [2021-03-26 19:46:04 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 900/1251] eta: 0:02:59 lr: 0.000175 loss: 3.0123 (2.9771) grad_norm: 2.1929 (nan) time: 0.4998 [2021-03-26 19:46:09 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 910/1251] eta: 0:02:54 lr: 0.000175 loss: 2.9618 (2.9771) grad_norm: 2.1333 (nan) time: 0.5032 [2021-03-26 19:46:14 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 920/1251] eta: 0:02:48 lr: 0.000175 loss: 3.1936 (2.9787) grad_norm: 2.1326 (nan) time: 0.5010 [2021-03-26 19:46:19 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 930/1251] eta: 0:02:43 lr: 0.000175 loss: 3.1936 (2.9790) grad_norm: 2.1434 (nan) time: 0.5021 [2021-03-26 19:46:25 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 940/1251] eta: 0:02:38 lr: 0.000175 loss: 3.0572 (2.9787) grad_norm: 2.0854 (nan) time: 0.5110 [2021-03-26 19:46:30 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 950/1251] eta: 0:02:33 lr: 0.000175 loss: 3.0057 (2.9798) grad_norm: 2.1596 (nan) time: 0.5061 [2021-03-26 19:46:34 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 960/1251] eta: 0:02:28 lr: 0.000175 loss: 2.8000 (2.9751) grad_norm: 2.1596 (nan) time: 0.4987 [2021-03-26 19:46:39 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 970/1251] eta: 0:02:23 lr: 0.000175 loss: 2.8145 (2.9757) grad_norm: 2.1320 (nan) time: 0.4974 [2021-03-26 19:46:44 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 980/1251] eta: 0:02:18 lr: 0.000175 loss: 3.0536 (2.9763) grad_norm: 2.0272 (nan) time: 0.5005 [2021-03-26 19:46:50 swin_small_patch4_window7_224] INFO: Epoch: [219] [ 990/1251] eta: 0:02:13 lr: 0.000175 loss: 3.0141 (2.9764) grad_norm: 2.0101 (nan) time: 0.5023 [2021-03-26 19:46:55 swin_small_patch4_window7_224] INFO: Epoch: [219] [1000/1251] eta: 0:02:07 lr: 0.000175 loss: 3.0027 (2.9765) grad_norm: 2.1656 (nan) time: 0.5019 [2021-03-26 19:47:00 swin_small_patch4_window7_224] INFO: Epoch: [219] [1010/1251] eta: 0:02:02 lr: 0.000175 loss: 3.0447 (2.9744) grad_norm: 2.1513 (nan) time: 0.5027 [2021-03-26 19:47:05 swin_small_patch4_window7_224] INFO: Epoch: [219] [1020/1251] eta: 0:01:57 lr: 0.000174 loss: 2.5510 (2.9727) grad_norm: 2.1081 (nan) time: 0.5049 [2021-03-26 19:47:10 swin_small_patch4_window7_224] INFO: Epoch: [219] [1030/1251] eta: 0:01:52 lr: 0.000174 loss: 3.1194 (2.9746) grad_norm: 2.1398 (nan) time: 0.5033 [2021-03-26 19:47:15 swin_small_patch4_window7_224] INFO: Epoch: [219] [1040/1251] eta: 0:01:47 lr: 0.000174 loss: 3.0997 (2.9739) grad_norm: 2.0754 (nan) time: 0.4986 [2021-03-26 19:47:20 swin_small_patch4_window7_224] INFO: Epoch: [219] [1050/1251] eta: 0:01:42 lr: 0.000174 loss: 2.7760 (2.9726) grad_norm: 2.1678 (nan) time: 0.4973 [2021-03-26 19:47:25 swin_small_patch4_window7_224] INFO: Epoch: [219] [1060/1251] eta: 0:01:37 lr: 0.000174 loss: 3.0767 (2.9737) grad_norm: 2.1794 (nan) time: 0.5058 [2021-03-26 19:47:30 swin_small_patch4_window7_224] INFO: Epoch: [219] [1070/1251] eta: 0:01:32 lr: 0.000174 loss: 3.0847 (2.9736) grad_norm: 2.0775 (nan) time: 0.5084 [2021-03-26 19:47:35 swin_small_patch4_window7_224] INFO: Epoch: [219] [1080/1251] eta: 0:01:27 lr: 0.000174 loss: 2.8826 (2.9716) grad_norm: 2.1452 (nan) time: 0.5003 [2021-03-26 19:47:40 swin_small_patch4_window7_224] INFO: Epoch: [219] [1090/1251] eta: 0:01:21 lr: 0.000174 loss: 2.9589 (2.9731) grad_norm: 2.1452 (nan) time: 0.4999 [2021-03-26 19:47:45 swin_small_patch4_window7_224] INFO: Epoch: [219] [1100/1251] eta: 0:01:16 lr: 0.000174 loss: 3.1139 (2.9744) grad_norm: 2.1499 (nan) time: 0.4996 [2021-03-26 19:47:50 swin_small_patch4_window7_224] INFO: Epoch: [219] [1110/1251] eta: 0:01:11 lr: 0.000174 loss: 3.1139 (2.9756) grad_norm: 2.2753 (nan) time: 0.4980 [2021-03-26 19:47:55 swin_small_patch4_window7_224] INFO: Epoch: [219] [1120/1251] eta: 0:01:06 lr: 0.000174 loss: 3.0139 (2.9756) grad_norm: 2.1981 (nan) time: 0.4978 [2021-03-26 19:48:00 swin_small_patch4_window7_224] INFO: Epoch: [219] [1130/1251] eta: 0:01:01 lr: 0.000174 loss: 2.8721 (2.9747) grad_norm: 2.1675 (nan) time: 0.5008 [2021-03-26 19:48:05 swin_small_patch4_window7_224] INFO: Epoch: [219] [1140/1251] eta: 0:00:56 lr: 0.000174 loss: 2.9279 (2.9743) grad_norm: 2.2448 (nan) time: 0.5019 [2021-03-26 19:48:10 swin_small_patch4_window7_224] INFO: Epoch: [219] [1150/1251] eta: 0:00:51 lr: 0.000174 loss: 2.9280 (2.9742) grad_norm: 2.1951 (nan) time: 0.5016 [2021-03-26 19:48:15 swin_small_patch4_window7_224] INFO: Epoch: [219] [1160/1251] eta: 0:00:46 lr: 0.000174 loss: 3.0147 (2.9743) grad_norm: 2.1574 (nan) time: 0.5038 [2021-03-26 19:48:20 swin_small_patch4_window7_224] INFO: Epoch: [219] [1170/1251] eta: 0:00:41 lr: 0.000174 loss: 2.9404 (2.9721) grad_norm: 2.2417 (nan) time: 0.5065 [2021-03-26 19:48:25 swin_small_patch4_window7_224] INFO: Epoch: [219] [1180/1251] eta: 0:00:36 lr: 0.000174 loss: 2.9727 (2.9721) grad_norm: 2.2748 (nan) time: 0.5101 [2021-03-26 19:48:30 swin_small_patch4_window7_224] INFO: Epoch: [219] [1190/1251] eta: 0:00:31 lr: 0.000174 loss: 2.9914 (2.9710) grad_norm: 2.3399 (nan) time: 0.5082 [2021-03-26 19:48:35 swin_small_patch4_window7_224] INFO: Epoch: [219] [1200/1251] eta: 0:00:25 lr: 0.000174 loss: 2.6967 (2.9678) grad_norm: 2.3332 (nan) time: 0.5044 [2021-03-26 19:48:40 swin_small_patch4_window7_224] INFO: Epoch: [219] [1210/1251] eta: 0:00:20 lr: 0.000174 loss: 2.7357 (2.9668) grad_norm: 2.3236 (nan) time: 0.5018 [2021-03-26 19:48:45 swin_small_patch4_window7_224] INFO: Epoch: [219] [1220/1251] eta: 0:00:15 lr: 0.000174 loss: 2.8547 (2.9672) grad_norm: 2.2971 (nan) time: 0.5038 [2021-03-26 19:48:50 swin_small_patch4_window7_224] INFO: Epoch: [219] [1230/1251] eta: 0:00:10 lr: 0.000174 loss: 2.8981 (2.9671) grad_norm: 2.2113 (nan) time: 0.5065 [2021-03-26 19:48:55 swin_small_patch4_window7_224] INFO: Epoch: [219] [1240/1251] eta: 0:00:05 lr: 0.000174 loss: 3.0209 (2.9672) grad_norm: 2.2358 (nan) time: 0.4982 [2021-03-26 19:49:00 swin_small_patch4_window7_224] INFO: Epoch: [219] [1250/1251] eta: 0:00:00 lr: 0.000174 loss: 3.0490 (2.9683) grad_norm: 2.1918 (nan) time: 0.4942 [2021-03-26 19:49:11 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:04 loss: 0.8730 (0.8730) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-26 19:49:14 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8348 (0.8059) acc1: 81.2500 (79.9716) acc5: 96.8750 (96.3068) [2021-03-26 19:49:16 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7412 (0.8135) acc1: 79.6875 (79.9107) acc5: 95.3125 (95.6845) [2021-03-26 19:49:18 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7874 (0.8254) acc1: 79.6875 (80.1915) acc5: 95.3125 (95.8165) [2021-03-26 19:49:20 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7920 (0.8155) acc1: 81.2500 (79.9924) acc5: 96.8750 (95.9604) [2021-03-26 19:49:20 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8365 (0.8228) acc1: 78.1250 (79.8400) acc5: 95.3125 (95.7760) [2021-03-26 19:49:30 swin_small_patch4_window7_224] INFO: * Acc@1 81.182 Acc@5 95.692 loss 0.805 [2021-03-26 19:49:30 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.2% [2021-03-26 19:49:30 swin_small_patch4_window7_224] INFO: Max accuracy: 81.33% [2021-03-26 19:49:34 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 0/1251] eta: 1:37:26 lr: 0.000174 loss: 2.9689 (2.9689) grad_norm: 2.1151 (2.1151) time: 4.6735 [2021-03-26 19:49:39 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 10/1251] eta: 0:18:20 lr: 0.000174 loss: 2.9689 (2.8183) grad_norm: 2.2451 (2.2784) time: 0.8871 [2021-03-26 19:49:45 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 20/1251] eta: 0:14:27 lr: 0.000174 loss: 3.0804 (2.8739) grad_norm: 2.2451 (2.2596) time: 0.5061 [2021-03-26 19:49:50 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 30/1251] eta: 0:13:04 lr: 0.000174 loss: 3.0592 (2.9004) grad_norm: 2.1595 (2.2364) time: 0.5074 [2021-03-26 19:49:55 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 40/1251] eta: 0:12:15 lr: 0.000174 loss: 3.0369 (2.9257) grad_norm: 2.0821 (2.2350) time: 0.5061 [2021-03-26 19:50:00 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 50/1251] eta: 0:11:44 lr: 0.000174 loss: 3.1623 (2.9782) grad_norm: 2.2180 (2.2320) time: 0.4997 [2021-03-26 19:50:05 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 60/1251] eta: 0:11:22 lr: 0.000174 loss: 3.1623 (2.9914) grad_norm: 2.2219 (2.2345) time: 0.5022 [2021-03-26 19:50:10 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 70/1251] eta: 0:11:08 lr: 0.000174 loss: 2.8974 (2.9742) grad_norm: 2.1730 (2.2352) time: 0.5147 [2021-03-26 19:50:15 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 80/1251] eta: 0:10:52 lr: 0.000174 loss: 2.9217 (2.9947) grad_norm: 2.0941 (2.2076) time: 0.5085 [2021-03-26 19:50:20 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 90/1251] eta: 0:10:39 lr: 0.000174 loss: 2.9703 (2.9949) grad_norm: 1.9823 (2.1895) time: 0.4955 [2021-03-26 19:50:25 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 100/1251] eta: 0:10:27 lr: 0.000173 loss: 2.9703 (2.9971) grad_norm: 2.0844 (2.1865) time: 0.4967 [2021-03-26 19:50:30 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 110/1251] eta: 0:10:18 lr: 0.000173 loss: 2.9952 (2.9812) grad_norm: 2.2046 (2.2411) time: 0.5057 [2021-03-26 19:50:35 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 120/1251] eta: 0:10:08 lr: 0.000173 loss: 3.2065 (3.0003) grad_norm: 2.3789 (2.2714) time: 0.5041 [2021-03-26 19:50:40 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 130/1251] eta: 0:10:01 lr: 0.000173 loss: 3.2413 (2.9976) grad_norm: 2.3789 (2.2792) time: 0.5024 [2021-03-26 19:50:45 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 140/1251] eta: 0:09:52 lr: 0.000173 loss: 3.1148 (3.0010) grad_norm: 2.3119 (2.2791) time: 0.5030 [2021-03-26 19:50:50 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 150/1251] eta: 0:09:46 lr: 0.000173 loss: 3.1832 (3.0194) grad_norm: 2.1668 (2.2810) time: 0.5071 [2021-03-26 19:50:55 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 160/1251] eta: 0:09:38 lr: 0.000173 loss: 3.1832 (3.0289) grad_norm: 2.1636 (2.2773) time: 0.5090 [2021-03-26 19:51:00 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 170/1251] eta: 0:09:31 lr: 0.000173 loss: 3.1086 (3.0252) grad_norm: 2.2029 (2.2767) time: 0.4984 [2021-03-26 19:51:05 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 180/1251] eta: 0:09:24 lr: 0.000173 loss: 2.7346 (3.0000) grad_norm: 2.1867 (2.2830) time: 0.5034 [2021-03-26 19:51:10 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 190/1251] eta: 0:09:17 lr: 0.000173 loss: 2.8342 (3.0041) grad_norm: 2.3982 (2.3017) time: 0.5037 [2021-03-26 19:51:15 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 200/1251] eta: 0:09:11 lr: 0.000173 loss: 3.1046 (3.0099) grad_norm: 2.2700 (2.2934) time: 0.4968 [2021-03-26 19:51:20 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 210/1251] eta: 0:09:04 lr: 0.000173 loss: 3.1046 (3.0047) grad_norm: 2.1823 (2.2941) time: 0.4944 [2021-03-26 19:51:25 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 220/1251] eta: 0:08:58 lr: 0.000173 loss: 3.0459 (3.0023) grad_norm: 2.3717 (2.2986) time: 0.4965 [2021-03-26 19:51:30 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 230/1251] eta: 0:08:51 lr: 0.000173 loss: 3.0005 (2.9976) grad_norm: 2.3456 (2.2998) time: 0.5013 [2021-03-26 19:51:35 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 240/1251] eta: 0:08:46 lr: 0.000173 loss: 3.0118 (3.0057) grad_norm: 2.1296 (2.3035) time: 0.5048 [2021-03-26 19:51:40 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 250/1251] eta: 0:08:40 lr: 0.000173 loss: 3.2158 (3.0068) grad_norm: 2.3386 (2.3035) time: 0.5082 [2021-03-26 19:51:45 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 260/1251] eta: 0:08:35 lr: 0.000173 loss: 2.9898 (3.0057) grad_norm: 2.2988 (2.2998) time: 0.5132 [2021-03-26 19:51:50 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 270/1251] eta: 0:08:29 lr: 0.000173 loss: 2.9898 (3.0029) grad_norm: 2.1835 (2.2952) time: 0.5067 [2021-03-26 19:51:55 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 280/1251] eta: 0:08:23 lr: 0.000173 loss: 3.1703 (3.0077) grad_norm: 2.1130 (2.2896) time: 0.4948 [2021-03-26 19:52:00 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 290/1251] eta: 0:08:17 lr: 0.000173 loss: 3.0521 (2.9998) grad_norm: 2.0793 (2.2842) time: 0.5014 [2021-03-26 19:52:05 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 300/1251] eta: 0:08:11 lr: 0.000173 loss: 2.9159 (2.9965) grad_norm: 2.0793 (2.2812) time: 0.5044 [2021-03-26 19:52:10 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 310/1251] eta: 0:08:06 lr: 0.000173 loss: 2.9355 (2.9880) grad_norm: 2.0376 (2.2750) time: 0.5019 [2021-03-26 19:52:16 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 320/1251] eta: 0:08:00 lr: 0.000173 loss: 3.0076 (2.9883) grad_norm: 2.0238 (2.2682) time: 0.5073 [2021-03-26 19:52:21 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 330/1251] eta: 0:07:55 lr: 0.000173 loss: 3.2242 (2.9962) grad_norm: 2.0502 (2.2694) time: 0.5058 [2021-03-26 19:52:26 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 340/1251] eta: 0:07:49 lr: 0.000173 loss: 2.9995 (2.9856) grad_norm: 2.1517 (2.2697) time: 0.4996 [2021-03-26 19:52:31 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 350/1251] eta: 0:07:44 lr: 0.000173 loss: 2.7942 (2.9862) grad_norm: 2.1618 (2.2653) time: 0.4983 [2021-03-26 19:52:36 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 360/1251] eta: 0:07:38 lr: 0.000173 loss: 3.1137 (2.9940) grad_norm: 2.1177 (2.2610) time: 0.5035 [2021-03-26 19:52:41 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 370/1251] eta: 0:07:33 lr: 0.000173 loss: 3.2254 (2.9936) grad_norm: 2.1437 (2.2604) time: 0.5034 [2021-03-26 19:52:46 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 380/1251] eta: 0:07:27 lr: 0.000173 loss: 3.1629 (2.9930) grad_norm: 2.2262 (2.2671) time: 0.4981 [2021-03-26 19:52:51 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 390/1251] eta: 0:07:22 lr: 0.000173 loss: 3.1208 (2.9913) grad_norm: 2.1803 (2.2628) time: 0.4995 [2021-03-26 19:52:56 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 400/1251] eta: 0:07:16 lr: 0.000173 loss: 3.0952 (2.9917) grad_norm: 2.0406 (2.2590) time: 0.5013 [2021-03-26 19:53:01 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 410/1251] eta: 0:07:11 lr: 0.000173 loss: 3.0297 (2.9896) grad_norm: 2.0998 (2.2595) time: 0.5032 [2021-03-26 19:53:06 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 420/1251] eta: 0:07:06 lr: 0.000172 loss: 2.9557 (2.9937) grad_norm: 2.1645 (2.2566) time: 0.5026 [2021-03-26 19:53:11 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 430/1251] eta: 0:07:00 lr: 0.000172 loss: 2.9632 (2.9907) grad_norm: 2.1645 (2.2575) time: 0.4974 [2021-03-26 19:53:16 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 440/1251] eta: 0:06:55 lr: 0.000172 loss: 2.5737 (2.9846) grad_norm: 2.2482 (2.2595) time: 0.5067 [2021-03-26 19:53:21 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 450/1251] eta: 0:06:50 lr: 0.000172 loss: 2.5676 (2.9778) grad_norm: 2.1919 (2.2594) time: 0.5073 [2021-03-26 19:53:26 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 460/1251] eta: 0:06:45 lr: 0.000172 loss: 2.8393 (2.9776) grad_norm: 2.1147 (2.2582) time: 0.5005 [2021-03-26 19:53:31 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 470/1251] eta: 0:06:39 lr: 0.000172 loss: 2.8771 (2.9758) grad_norm: 2.2358 (2.2662) time: 0.4995 [2021-03-26 19:53:36 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 480/1251] eta: 0:06:34 lr: 0.000172 loss: 3.0621 (2.9809) grad_norm: 2.2472 (2.2677) time: 0.4998 [2021-03-26 19:53:41 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 490/1251] eta: 0:06:29 lr: 0.000172 loss: 3.0707 (2.9831) grad_norm: 2.2472 (2.2658) time: 0.5044 [2021-03-26 19:53:46 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 500/1251] eta: 0:06:24 lr: 0.000172 loss: 2.9264 (2.9796) grad_norm: 2.1773 (2.2643) time: 0.5060 [2021-03-26 19:53:51 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 510/1251] eta: 0:06:18 lr: 0.000172 loss: 3.0131 (2.9790) grad_norm: 2.1773 (2.2650) time: 0.5084 [2021-03-26 19:53:56 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 520/1251] eta: 0:06:13 lr: 0.000172 loss: 3.0354 (2.9756) grad_norm: 2.1730 (2.2633) time: 0.5028 [2021-03-26 19:54:01 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 530/1251] eta: 0:06:08 lr: 0.000172 loss: 3.1008 (2.9748) grad_norm: 2.2025 (2.2647) time: 0.4999 [2021-03-26 19:54:06 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 540/1251] eta: 0:06:03 lr: 0.000172 loss: 2.8792 (2.9742) grad_norm: 2.1887 (2.2643) time: 0.5080 [2021-03-26 19:54:11 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 550/1251] eta: 0:05:58 lr: 0.000172 loss: 2.8792 (2.9764) grad_norm: 2.1887 (2.2715) time: 0.5188 [2021-03-26 19:54:16 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 560/1251] eta: 0:05:53 lr: 0.000172 loss: 3.0922 (2.9767) grad_norm: 2.3460 (2.2759) time: 0.5152 [2021-03-26 19:54:21 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 570/1251] eta: 0:05:47 lr: 0.000172 loss: 2.9299 (2.9754) grad_norm: 2.3537 (2.2761) time: 0.5016 [2021-03-26 19:54:26 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 580/1251] eta: 0:05:42 lr: 0.000172 loss: 3.0175 (2.9776) grad_norm: 2.1837 (2.2754) time: 0.4994 [2021-03-26 19:54:31 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 590/1251] eta: 0:05:37 lr: 0.000172 loss: 3.0175 (2.9768) grad_norm: 2.1837 (2.2789) time: 0.5003 [2021-03-26 19:54:36 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 600/1251] eta: 0:05:32 lr: 0.000172 loss: 2.8649 (2.9722) grad_norm: 2.2333 (2.2778) time: 0.5001 [2021-03-26 19:54:41 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 610/1251] eta: 0:05:26 lr: 0.000172 loss: 3.0340 (2.9752) grad_norm: 2.1589 (2.2763) time: 0.5001 [2021-03-26 19:54:47 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 620/1251] eta: 0:05:21 lr: 0.000172 loss: 3.2720 (2.9777) grad_norm: 2.1589 (2.2767) time: 0.5013 [2021-03-26 19:54:52 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 630/1251] eta: 0:05:16 lr: 0.000172 loss: 3.0868 (2.9774) grad_norm: 2.1828 (2.2760) time: 0.5034 [2021-03-26 19:54:57 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 640/1251] eta: 0:05:11 lr: 0.000172 loss: 3.0590 (2.9778) grad_norm: 2.0867 (2.2724) time: 0.5014 [2021-03-26 19:55:02 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 650/1251] eta: 0:05:06 lr: 0.000172 loss: 3.0701 (2.9772) grad_norm: 2.0415 (2.2694) time: 0.5040 [2021-03-26 19:55:07 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 660/1251] eta: 0:05:01 lr: 0.000172 loss: 3.0156 (2.9766) grad_norm: 2.0726 (2.2678) time: 0.5095 [2021-03-26 19:55:12 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 670/1251] eta: 0:04:56 lr: 0.000172 loss: 3.1869 (2.9796) grad_norm: 2.1167 (2.2693) time: 0.5042 [2021-03-26 19:55:17 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 680/1251] eta: 0:04:50 lr: 0.000172 loss: 3.1079 (2.9787) grad_norm: 2.1701 (2.2749) time: 0.5061 [2021-03-26 19:55:22 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 690/1251] eta: 0:04:45 lr: 0.000172 loss: 3.0320 (2.9786) grad_norm: 2.1701 (2.2724) time: 0.5132 [2021-03-26 19:55:27 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 700/1251] eta: 0:04:40 lr: 0.000172 loss: 3.1737 (2.9804) grad_norm: 2.1377 (2.2712) time: 0.5098 [2021-03-26 19:55:32 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 710/1251] eta: 0:04:35 lr: 0.000172 loss: 3.0450 (2.9801) grad_norm: 2.0821 (2.2700) time: 0.5053 [2021-03-26 19:55:37 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 720/1251] eta: 0:04:30 lr: 0.000172 loss: 3.0936 (2.9826) grad_norm: 2.1721 (2.2691) time: 0.5035 [2021-03-26 19:55:42 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 730/1251] eta: 0:04:25 lr: 0.000172 loss: 3.1388 (2.9828) grad_norm: 2.1816 (2.2712) time: 0.5138 [2021-03-26 19:55:48 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 740/1251] eta: 0:04:20 lr: 0.000172 loss: 2.9878 (2.9795) grad_norm: 2.1130 (2.2685) time: 0.5242 [2021-03-26 19:55:53 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 750/1251] eta: 0:04:15 lr: 0.000171 loss: 2.9593 (2.9813) grad_norm: 2.1003 (2.2680) time: 0.5224 [2021-03-26 19:55:58 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 760/1251] eta: 0:04:10 lr: 0.000171 loss: 3.2266 (2.9798) grad_norm: 2.2758 (2.2707) time: 0.5138 [2021-03-26 19:56:03 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 770/1251] eta: 0:04:05 lr: 0.000171 loss: 3.1665 (2.9811) grad_norm: 2.2464 (2.2697) time: 0.5052 [2021-03-26 19:56:08 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 780/1251] eta: 0:04:00 lr: 0.000171 loss: 3.1424 (2.9832) grad_norm: 2.1376 (2.2691) time: 0.5074 [2021-03-26 19:56:13 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 790/1251] eta: 0:03:55 lr: 0.000171 loss: 3.0205 (2.9817) grad_norm: 2.2334 (2.2700) time: 0.5071 [2021-03-26 19:56:18 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 800/1251] eta: 0:03:49 lr: 0.000171 loss: 3.1296 (2.9822) grad_norm: 2.2711 (2.2701) time: 0.5042 [2021-03-26 19:56:23 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 810/1251] eta: 0:03:44 lr: 0.000171 loss: 3.2546 (2.9848) grad_norm: 2.2695 (2.2703) time: 0.5104 [2021-03-26 19:56:28 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 820/1251] eta: 0:03:39 lr: 0.000171 loss: 3.1089 (2.9823) grad_norm: 2.2168 (2.2695) time: 0.5071 [2021-03-26 19:56:33 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 830/1251] eta: 0:03:34 lr: 0.000171 loss: 2.8377 (2.9829) grad_norm: 2.1568 (2.2687) time: 0.5019 [2021-03-26 19:56:38 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 840/1251] eta: 0:03:29 lr: 0.000171 loss: 3.0295 (2.9845) grad_norm: 2.1458 (2.2674) time: 0.5005 [2021-03-26 19:56:43 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 850/1251] eta: 0:03:24 lr: 0.000171 loss: 3.0170 (2.9834) grad_norm: 2.1951 (2.2661) time: 0.4980 [2021-03-26 19:56:48 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 860/1251] eta: 0:03:19 lr: 0.000171 loss: 2.9342 (2.9839) grad_norm: 2.1621 (2.2648) time: 0.5012 [2021-03-26 19:56:53 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 870/1251] eta: 0:03:14 lr: 0.000171 loss: 3.1296 (2.9849) grad_norm: 2.1292 (2.2655) time: 0.5064 [2021-03-26 19:56:59 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 880/1251] eta: 0:03:08 lr: 0.000171 loss: 3.1417 (2.9851) grad_norm: 2.2227 (2.2655) time: 0.5099 [2021-03-26 19:57:04 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 890/1251] eta: 0:03:03 lr: 0.000171 loss: 3.0286 (2.9841) grad_norm: 2.1824 (2.2663) time: 0.5059 [2021-03-26 19:57:09 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 900/1251] eta: 0:02:58 lr: 0.000171 loss: 3.0236 (2.9837) grad_norm: 2.1824 (2.2665) time: 0.5057 [2021-03-26 19:57:14 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 910/1251] eta: 0:02:53 lr: 0.000171 loss: 2.7684 (2.9811) grad_norm: 2.2092 (2.2671) time: 0.5124 [2021-03-26 19:57:19 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 920/1251] eta: 0:02:48 lr: 0.000171 loss: 2.7430 (2.9809) grad_norm: 2.1679 (2.2660) time: 0.5119 [2021-03-26 19:57:24 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 930/1251] eta: 0:02:43 lr: 0.000171 loss: 3.2265 (2.9825) grad_norm: 2.2018 (2.2687) time: 0.5129 [2021-03-26 19:57:29 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 940/1251] eta: 0:02:38 lr: 0.000171 loss: 3.2839 (2.9851) grad_norm: 2.2996 (2.2700) time: 0.5102 [2021-03-26 19:57:34 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 950/1251] eta: 0:02:33 lr: 0.000171 loss: 3.2034 (2.9843) grad_norm: 2.1736 (2.2695) time: 0.4999 [2021-03-26 19:57:39 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 960/1251] eta: 0:02:28 lr: 0.000171 loss: 3.2034 (2.9860) grad_norm: 2.2038 (2.2694) time: 0.4981 [2021-03-26 19:57:44 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 970/1251] eta: 0:02:23 lr: 0.000171 loss: 3.2546 (2.9872) grad_norm: 2.2170 (2.2694) time: 0.5020 [2021-03-26 19:57:49 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 980/1251] eta: 0:02:17 lr: 0.000171 loss: 3.2383 (2.9889) grad_norm: 2.1871 (2.2686) time: 0.5038 [2021-03-26 19:57:54 swin_small_patch4_window7_224] INFO: Epoch: [220] [ 990/1251] eta: 0:02:12 lr: 0.000171 loss: 3.1556 (2.9906) grad_norm: 2.2072 (2.2697) time: 0.4997 [2021-03-26 19:57:59 swin_small_patch4_window7_224] INFO: Epoch: [220] [1000/1251] eta: 0:02:07 lr: 0.000171 loss: 3.1157 (2.9893) grad_norm: 2.3634 (2.2709) time: 0.5065 [2021-03-26 19:58:04 swin_small_patch4_window7_224] INFO: Epoch: [220] [1010/1251] eta: 0:02:02 lr: 0.000171 loss: 2.9113 (2.9895) grad_norm: 2.2486 (2.2699) time: 0.5069 [2021-03-26 19:58:09 swin_small_patch4_window7_224] INFO: Epoch: [220] [1020/1251] eta: 0:01:57 lr: 0.000171 loss: 3.0949 (2.9881) grad_norm: 2.2008 (2.2705) time: 0.5013 [2021-03-26 19:58:14 swin_small_patch4_window7_224] INFO: Epoch: [220] [1030/1251] eta: 0:01:52 lr: 0.000171 loss: 3.1424 (2.9888) grad_norm: 2.1733 (2.2782) time: 0.5077 [2021-03-26 19:58:19 swin_small_patch4_window7_224] INFO: Epoch: [220] [1040/1251] eta: 0:01:47 lr: 0.000171 loss: 3.0728 (2.9877) grad_norm: 2.2249 (2.2785) time: 0.5034 [2021-03-26 19:58:24 swin_small_patch4_window7_224] INFO: Epoch: [220] [1050/1251] eta: 0:01:42 lr: 0.000171 loss: 3.0430 (2.9868) grad_norm: 2.2443 (2.2789) time: 0.5025 [2021-03-26 19:58:30 swin_small_patch4_window7_224] INFO: Epoch: [220] [1060/1251] eta: 0:01:37 lr: 0.000171 loss: 2.8198 (2.9851) grad_norm: 2.2555 (2.2792) time: 0.5117 [2021-03-26 19:58:35 swin_small_patch4_window7_224] INFO: Epoch: [220] [1070/1251] eta: 0:01:32 lr: 0.000170 loss: 2.8078 (2.9833) grad_norm: 2.2936 (2.2797) time: 0.5057 [2021-03-26 19:58:40 swin_small_patch4_window7_224] INFO: Epoch: [220] [1080/1251] eta: 0:01:26 lr: 0.000170 loss: 3.0166 (2.9852) grad_norm: 2.2691 (2.2797) time: 0.4990 [2021-03-26 19:58:45 swin_small_patch4_window7_224] INFO: Epoch: [220] [1090/1251] eta: 0:01:21 lr: 0.000170 loss: 3.1539 (2.9843) grad_norm: 2.1871 (2.2781) time: 0.4992 [2021-03-26 19:58:50 swin_small_patch4_window7_224] INFO: Epoch: [220] [1100/1251] eta: 0:01:16 lr: 0.000170 loss: 2.2876 (2.9785) grad_norm: 2.0521 (2.2768) time: 0.5002 [2021-03-26 19:58:55 swin_small_patch4_window7_224] INFO: Epoch: [220] [1110/1251] eta: 0:01:11 lr: 0.000170 loss: 2.6723 (2.9795) grad_norm: 2.1986 (2.2771) time: 0.5045 [2021-03-26 19:59:00 swin_small_patch4_window7_224] INFO: Epoch: [220] [1120/1251] eta: 0:01:06 lr: 0.000170 loss: 3.0707 (2.9784) grad_norm: 2.1989 (2.2767) time: 0.5026 [2021-03-26 19:59:05 swin_small_patch4_window7_224] INFO: Epoch: [220] [1130/1251] eta: 0:01:01 lr: 0.000170 loss: 3.0290 (2.9790) grad_norm: 2.1743 (2.2773) time: 0.5000 [2021-03-26 19:59:10 swin_small_patch4_window7_224] INFO: Epoch: [220] [1140/1251] eta: 0:00:56 lr: 0.000170 loss: 3.0290 (2.9798) grad_norm: 2.1587 (2.2772) time: 0.4987 [2021-03-26 19:59:15 swin_small_patch4_window7_224] INFO: Epoch: [220] [1150/1251] eta: 0:00:51 lr: 0.000170 loss: 2.9719 (2.9792) grad_norm: 2.1587 (2.2763) time: 0.5024 [2021-03-26 19:59:20 swin_small_patch4_window7_224] INFO: Epoch: [220] [1160/1251] eta: 0:00:46 lr: 0.000170 loss: 3.0633 (2.9800) grad_norm: 2.1850 (2.2766) time: 0.5028 [2021-03-26 19:59:25 swin_small_patch4_window7_224] INFO: Epoch: [220] [1170/1251] eta: 0:00:41 lr: 0.000170 loss: 3.0604 (2.9793) grad_norm: 2.1155 (2.2755) time: 0.5043 [2021-03-26 19:59:30 swin_small_patch4_window7_224] INFO: Epoch: [220] [1180/1251] eta: 0:00:36 lr: 0.000170 loss: 3.0185 (2.9803) grad_norm: 2.1814 (2.2765) time: 0.5073 [2021-03-26 19:59:35 swin_small_patch4_window7_224] INFO: Epoch: [220] [1190/1251] eta: 0:00:30 lr: 0.000170 loss: 3.0458 (2.9792) grad_norm: 2.2128 (2.2775) time: 0.5037 [2021-03-26 19:59:40 swin_small_patch4_window7_224] INFO: Epoch: [220] [1200/1251] eta: 0:00:25 lr: 0.000170 loss: 3.1980 (2.9808) grad_norm: 2.2128 (2.2780) time: 0.5059 [2021-03-26 19:59:45 swin_small_patch4_window7_224] INFO: Epoch: [220] [1210/1251] eta: 0:00:20 lr: 0.000170 loss: 3.1980 (2.9806) grad_norm: 2.1675 (2.2775) time: 0.5011 [2021-03-26 19:59:50 swin_small_patch4_window7_224] INFO: Epoch: [220] [1220/1251] eta: 0:00:15 lr: 0.000170 loss: 2.9428 (2.9806) grad_norm: 2.2241 (2.2789) time: 0.4998 [2021-03-26 19:59:55 swin_small_patch4_window7_224] INFO: Epoch: [220] [1230/1251] eta: 0:00:10 lr: 0.000170 loss: 3.0143 (2.9805) grad_norm: 2.1617 (2.2779) time: 0.5079 [2021-03-26 20:00:00 swin_small_patch4_window7_224] INFO: Epoch: [220] [1240/1251] eta: 0:00:05 lr: 0.000170 loss: 3.0952 (2.9820) grad_norm: 2.2254 (2.2808) time: 0.5134 [2021-03-26 20:00:05 swin_small_patch4_window7_224] INFO: Epoch: [220] [1250/1251] eta: 0:00:00 lr: 0.000170 loss: 3.1692 (2.9829) grad_norm: 2.2733 (2.2811) time: 0.5155 [2021-03-26 20:00:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.4919 (0.4919) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-26 20:00:51 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7823 (0.7466) acc1: 82.8125 (83.3807) acc5: 95.3125 (95.8807) [2021-03-26 20:00:52 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7665 (0.7560) acc1: 81.2500 (81.9940) acc5: 95.3125 (96.2798) [2021-03-26 20:00:53 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7665 (0.7796) acc1: 79.6875 (81.6028) acc5: 95.3125 (95.8165) [2021-03-26 20:00:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8165 (0.7854) acc1: 81.2500 (81.3643) acc5: 95.3125 (95.9985) [2021-03-26 20:00:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8201 (0.7956) acc1: 81.2500 (81.0560) acc5: 95.3125 (95.9680) [2021-03-26 20:01:08 swin_small_patch4_window7_224] INFO: * Acc@1 81.426 Acc@5 95.748 loss 0.792 [2021-03-26 20:01:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.4% [2021-03-26 20:01:08 swin_small_patch4_window7_224] INFO: Max accuracy: 81.43% [2021-03-26 20:01:12 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 0/1251] eta: 1:23:56 lr: 0.000170 loss: 2.8969 (2.8969) grad_norm: 2.1129 (2.1129) time: 4.0263 [2021-03-26 20:01:17 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 10/1251] eta: 0:17:43 lr: 0.000170 loss: 3.1415 (3.0671) grad_norm: 2.1802 (2.1809) time: 0.8572 [2021-03-26 20:01:22 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 20/1251] eta: 0:14:06 lr: 0.000170 loss: 2.9547 (3.0038) grad_norm: 2.1512 (2.1679) time: 0.5210 [2021-03-26 20:01:27 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 30/1251] eta: 0:12:46 lr: 0.000170 loss: 2.9225 (2.9809) grad_norm: 2.1148 (2.1743) time: 0.5019 [2021-03-26 20:01:32 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 40/1251] eta: 0:12:07 lr: 0.000170 loss: 3.0303 (3.0138) grad_norm: 2.2049 (2.1829) time: 0.5089 [2021-03-26 20:01:38 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 50/1251] eta: 0:11:40 lr: 0.000170 loss: 3.1961 (3.0534) grad_norm: 2.2049 (2.2159) time: 0.5145 [2021-03-26 20:01:43 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 60/1251] eta: 0:11:19 lr: 0.000170 loss: 3.1527 (3.0318) grad_norm: 2.2236 (2.2021) time: 0.5086 [2021-03-26 20:01:48 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 70/1251] eta: 0:11:01 lr: 0.000170 loss: 2.9903 (3.0105) grad_norm: 2.2236 (2.2371) time: 0.5008 [2021-03-26 20:01:53 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 80/1251] eta: 0:10:50 lr: 0.000170 loss: 2.8384 (3.0176) grad_norm: 2.1989 (2.2324) time: 0.5106 [2021-03-26 20:01:58 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 90/1251] eta: 0:10:38 lr: 0.000170 loss: 3.0389 (2.9981) grad_norm: 2.1989 (2.2283) time: 0.5140 [2021-03-26 20:02:03 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 100/1251] eta: 0:10:27 lr: 0.000170 loss: 2.7784 (2.9593) grad_norm: 2.2207 (2.2277) time: 0.5036 [2021-03-26 20:02:08 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 110/1251] eta: 0:10:19 lr: 0.000170 loss: 2.8331 (2.9632) grad_norm: 2.1433 (2.2228) time: 0.5128 [2021-03-26 20:02:13 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 120/1251] eta: 0:10:10 lr: 0.000170 loss: 3.0560 (2.9667) grad_norm: 2.2151 (2.2301) time: 0.5141 [2021-03-26 20:02:18 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 130/1251] eta: 0:10:01 lr: 0.000170 loss: 2.9629 (2.9573) grad_norm: 2.2007 (2.2251) time: 0.5004 [2021-03-26 20:02:23 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 140/1251] eta: 0:09:53 lr: 0.000170 loss: 3.0177 (2.9570) grad_norm: 2.1583 (2.2257) time: 0.4957 [2021-03-26 20:02:28 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 150/1251] eta: 0:09:45 lr: 0.000169 loss: 3.0177 (2.9509) grad_norm: 2.1940 (2.2228) time: 0.4974 [2021-03-26 20:02:33 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 160/1251] eta: 0:09:38 lr: 0.000169 loss: 3.1529 (2.9694) grad_norm: 2.2759 (2.2266) time: 0.5036 [2021-03-26 20:02:38 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 170/1251] eta: 0:09:31 lr: 0.000169 loss: 3.1781 (2.9627) grad_norm: 2.3133 (2.2269) time: 0.5105 [2021-03-26 20:02:44 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 180/1251] eta: 0:09:26 lr: 0.000169 loss: 2.9323 (2.9603) grad_norm: 2.1486 (2.2295) time: 0.5164 [2021-03-26 20:02:49 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 190/1251] eta: 0:09:19 lr: 0.000169 loss: 2.9712 (2.9625) grad_norm: 2.3257 (2.2397) time: 0.5115 [2021-03-26 20:02:54 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 200/1251] eta: 0:09:12 lr: 0.000169 loss: 3.0673 (2.9702) grad_norm: 2.3998 (2.2447) time: 0.5040 [2021-03-26 20:02:59 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 210/1251] eta: 0:09:07 lr: 0.000169 loss: 3.1307 (2.9725) grad_norm: 2.2829 (2.2408) time: 0.5082 [2021-03-26 20:03:04 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 220/1251] eta: 0:09:00 lr: 0.000169 loss: 3.0361 (2.9647) grad_norm: 2.2228 (2.2423) time: 0.5052 [2021-03-26 20:03:09 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 230/1251] eta: 0:08:54 lr: 0.000169 loss: 3.0682 (2.9706) grad_norm: 2.2414 (2.2407) time: 0.4980 [2021-03-26 20:03:14 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 240/1251] eta: 0:08:48 lr: 0.000169 loss: 3.1293 (2.9794) grad_norm: 2.2477 (2.2962) time: 0.5028 [2021-03-26 20:03:19 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 250/1251] eta: 0:08:42 lr: 0.000169 loss: 3.1190 (2.9800) grad_norm: 2.2606 (2.2949) time: 0.5103 [2021-03-26 20:03:24 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 260/1251] eta: 0:08:36 lr: 0.000169 loss: 3.1378 (2.9869) grad_norm: 2.0987 (2.2874) time: 0.5071 [2021-03-26 20:03:29 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 270/1251] eta: 0:08:30 lr: 0.000169 loss: 3.2081 (2.9955) grad_norm: 2.0657 (2.2817) time: 0.5059 [2021-03-26 20:03:34 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 280/1251] eta: 0:08:25 lr: 0.000169 loss: 3.1553 (2.9939) grad_norm: 2.1256 (2.2845) time: 0.5168 [2021-03-26 20:03:39 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 290/1251] eta: 0:08:20 lr: 0.000169 loss: 2.9605 (2.9858) grad_norm: 2.1256 (2.2810) time: 0.5132 [2021-03-26 20:03:44 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 300/1251] eta: 0:08:14 lr: 0.000169 loss: 2.9641 (2.9843) grad_norm: 2.2573 (2.3271) time: 0.5066 [2021-03-26 20:03:49 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 310/1251] eta: 0:08:08 lr: 0.000169 loss: 2.7282 (2.9733) grad_norm: 2.2697 (2.3334) time: 0.5073 [2021-03-26 20:03:55 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 320/1251] eta: 0:08:03 lr: 0.000169 loss: 2.8095 (2.9719) grad_norm: 2.2697 (2.3352) time: 0.5062 [2021-03-26 20:04:00 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 330/1251] eta: 0:07:57 lr: 0.000169 loss: 3.0296 (2.9682) grad_norm: 2.2599 (2.3321) time: 0.5048 [2021-03-26 20:04:05 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 340/1251] eta: 0:07:52 lr: 0.000169 loss: 3.1589 (2.9719) grad_norm: 2.1731 (2.3292) time: 0.5032 [2021-03-26 20:04:10 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 350/1251] eta: 0:07:46 lr: 0.000169 loss: 3.0183 (2.9708) grad_norm: 2.2618 (2.3303) time: 0.5074 [2021-03-26 20:04:15 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 360/1251] eta: 0:07:41 lr: 0.000169 loss: 2.8150 (2.9659) grad_norm: 2.1636 (2.3266) time: 0.5072 [2021-03-26 20:04:20 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 370/1251] eta: 0:07:35 lr: 0.000169 loss: 2.8150 (2.9623) grad_norm: 2.1231 (2.3252) time: 0.5019 [2021-03-26 20:04:25 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 380/1251] eta: 0:07:30 lr: 0.000169 loss: 3.1232 (2.9627) grad_norm: 2.2540 (2.3265) time: 0.5049 [2021-03-26 20:04:30 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 390/1251] eta: 0:07:24 lr: 0.000169 loss: 3.0365 (2.9577) grad_norm: 2.2331 (2.3272) time: 0.5056 [2021-03-26 20:04:35 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 400/1251] eta: 0:07:19 lr: 0.000169 loss: 3.1328 (2.9628) grad_norm: 2.2331 (2.3258) time: 0.4982 [2021-03-26 20:04:40 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 410/1251] eta: 0:07:13 lr: 0.000169 loss: 3.1270 (2.9573) grad_norm: 2.2365 (2.3223) time: 0.5005 [2021-03-26 20:04:45 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 420/1251] eta: 0:07:08 lr: 0.000169 loss: 2.7117 (2.9553) grad_norm: 2.1796 (2.3192) time: 0.5041 [2021-03-26 20:04:50 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 430/1251] eta: 0:07:02 lr: 0.000169 loss: 2.7591 (2.9498) grad_norm: 2.1812 (2.3176) time: 0.5039 [2021-03-26 20:04:55 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 440/1251] eta: 0:06:57 lr: 0.000169 loss: 2.7251 (2.9440) grad_norm: 2.1412 (2.3138) time: 0.5008 [2021-03-26 20:05:00 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 450/1251] eta: 0:06:52 lr: 0.000169 loss: 2.9672 (2.9448) grad_norm: 2.1904 (2.3161) time: 0.4989 [2021-03-26 20:05:05 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 460/1251] eta: 0:06:46 lr: 0.000169 loss: 3.1798 (2.9513) grad_norm: 2.1691 (2.3118) time: 0.5013 [2021-03-26 20:05:10 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 470/1251] eta: 0:06:41 lr: 0.000169 loss: 3.0512 (2.9497) grad_norm: 2.1307 (2.3105) time: 0.5015 [2021-03-26 20:05:15 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 480/1251] eta: 0:06:36 lr: 0.000168 loss: 3.0036 (2.9474) grad_norm: 2.2040 (2.3086) time: 0.5007 [2021-03-26 20:05:20 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 490/1251] eta: 0:06:30 lr: 0.000168 loss: 3.0353 (2.9513) grad_norm: 2.2383 (2.3104) time: 0.5017 [2021-03-26 20:05:25 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 500/1251] eta: 0:06:25 lr: 0.000168 loss: 3.0353 (2.9494) grad_norm: 2.2580 (2.3094) time: 0.5050 [2021-03-26 20:05:30 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 510/1251] eta: 0:06:20 lr: 0.000168 loss: 2.9714 (2.9491) grad_norm: 2.2201 (2.3084) time: 0.5063 [2021-03-26 20:05:35 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 520/1251] eta: 0:06:15 lr: 0.000168 loss: 3.0001 (2.9496) grad_norm: 2.1992 (2.3057) time: 0.5079 [2021-03-26 20:05:40 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 530/1251] eta: 0:06:09 lr: 0.000168 loss: 3.2008 (2.9545) grad_norm: 2.1363 (2.3032) time: 0.5025 [2021-03-26 20:05:45 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 540/1251] eta: 0:06:04 lr: 0.000168 loss: 3.1729 (2.9549) grad_norm: 2.2666 (2.3049) time: 0.5001 [2021-03-26 20:05:50 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 550/1251] eta: 0:05:59 lr: 0.000168 loss: 3.0523 (2.9574) grad_norm: 2.2354 (2.3020) time: 0.5148 [2021-03-26 20:05:56 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 560/1251] eta: 0:05:54 lr: 0.000168 loss: 3.1317 (2.9597) grad_norm: 2.0727 (2.2987) time: 0.5163 [2021-03-26 20:06:01 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 570/1251] eta: 0:05:49 lr: 0.000168 loss: 3.2198 (2.9648) grad_norm: 2.1594 (2.2978) time: 0.5074 [2021-03-26 20:06:06 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 580/1251] eta: 0:05:43 lr: 0.000168 loss: 3.1706 (2.9621) grad_norm: 2.1774 (2.2961) time: 0.5046 [2021-03-26 20:06:11 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 590/1251] eta: 0:05:38 lr: 0.000168 loss: 2.8015 (2.9624) grad_norm: 2.1947 (2.2994) time: 0.5044 [2021-03-26 20:06:16 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 600/1251] eta: 0:05:33 lr: 0.000168 loss: 2.9898 (2.9611) grad_norm: 2.2510 (2.2985) time: 0.4999 [2021-03-26 20:06:21 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 610/1251] eta: 0:05:28 lr: 0.000168 loss: 3.0041 (2.9640) grad_norm: 2.2510 (2.3006) time: 0.4968 [2021-03-26 20:06:26 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 620/1251] eta: 0:05:22 lr: 0.000168 loss: 3.0989 (2.9647) grad_norm: 2.1939 (2.3015) time: 0.4973 [2021-03-26 20:06:31 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 630/1251] eta: 0:05:17 lr: 0.000168 loss: 3.0963 (2.9647) grad_norm: 2.2403 (2.3015) time: 0.5034 [2021-03-26 20:06:36 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 640/1251] eta: 0:05:12 lr: 0.000168 loss: 3.2253 (2.9693) grad_norm: 2.2033 (2.3029) time: 0.5115 [2021-03-26 20:06:41 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 650/1251] eta: 0:05:07 lr: 0.000168 loss: 3.2237 (2.9697) grad_norm: 2.1328 (2.3025) time: 0.5089 [2021-03-26 20:06:46 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 660/1251] eta: 0:05:02 lr: 0.000168 loss: 3.2207 (2.9741) grad_norm: 2.2745 (2.3018) time: 0.5039 [2021-03-26 20:06:51 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 670/1251] eta: 0:04:57 lr: 0.000168 loss: 3.0324 (2.9717) grad_norm: 2.2785 (2.3027) time: 0.5052 [2021-03-26 20:06:56 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 680/1251] eta: 0:04:51 lr: 0.000168 loss: 2.8804 (2.9699) grad_norm: 2.3050 (2.3054) time: 0.5040 [2021-03-26 20:07:01 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 690/1251] eta: 0:04:46 lr: 0.000168 loss: 3.0837 (2.9724) grad_norm: 2.2207 (2.3043) time: 0.4992 [2021-03-26 20:07:06 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 700/1251] eta: 0:04:41 lr: 0.000168 loss: 3.0837 (2.9734) grad_norm: 2.1125 (2.3054) time: 0.5010 [2021-03-26 20:07:11 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 710/1251] eta: 0:04:36 lr: 0.000168 loss: 3.0703 (2.9715) grad_norm: 2.1990 (2.3059) time: 0.5049 [2021-03-26 20:07:16 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 720/1251] eta: 0:04:31 lr: 0.000168 loss: 2.8823 (2.9703) grad_norm: 2.1990 (2.3091) time: 0.5046 [2021-03-26 20:07:21 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 730/1251] eta: 0:04:26 lr: 0.000168 loss: 3.0974 (2.9726) grad_norm: 2.1471 (2.3081) time: 0.5067 [2021-03-26 20:07:27 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 740/1251] eta: 0:04:21 lr: 0.000168 loss: 3.1117 (2.9725) grad_norm: 2.1450 (2.3094) time: 0.5231 [2021-03-26 20:07:32 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 750/1251] eta: 0:04:15 lr: 0.000168 loss: 2.8491 (2.9688) grad_norm: 2.1954 (2.3113) time: 0.5183 [2021-03-26 20:07:37 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 760/1251] eta: 0:04:10 lr: 0.000168 loss: 2.7379 (2.9682) grad_norm: 2.2830 (2.3106) time: 0.5047 [2021-03-26 20:07:42 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 770/1251] eta: 0:04:05 lr: 0.000168 loss: 2.9387 (2.9662) grad_norm: 2.2830 (2.3106) time: 0.5091 [2021-03-26 20:07:47 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 780/1251] eta: 0:04:00 lr: 0.000168 loss: 2.9463 (2.9665) grad_norm: 2.2890 (2.3108) time: 0.5062 [2021-03-26 20:07:52 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 790/1251] eta: 0:03:55 lr: 0.000168 loss: 3.2256 (2.9681) grad_norm: 2.2783 (2.3110) time: 0.5075 [2021-03-26 20:07:57 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 800/1251] eta: 0:03:50 lr: 0.000168 loss: 3.0643 (2.9683) grad_norm: 2.2653 (2.3109) time: 0.5085 [2021-03-26 20:08:02 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 810/1251] eta: 0:03:45 lr: 0.000167 loss: 2.8603 (2.9660) grad_norm: 2.2409 (2.3083) time: 0.5063 [2021-03-26 20:08:07 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 820/1251] eta: 0:03:40 lr: 0.000167 loss: 2.8369 (2.9650) grad_norm: 2.0684 (2.3063) time: 0.5098 [2021-03-26 20:08:12 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 830/1251] eta: 0:03:34 lr: 0.000167 loss: 2.8777 (2.9621) grad_norm: 2.2264 (2.3061) time: 0.5089 [2021-03-26 20:08:17 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 840/1251] eta: 0:03:29 lr: 0.000167 loss: 2.7279 (2.9612) grad_norm: 2.2293 (2.3059) time: 0.5033 [2021-03-26 20:08:22 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 850/1251] eta: 0:03:24 lr: 0.000167 loss: 2.7279 (2.9603) grad_norm: 2.2687 (2.3063) time: 0.5058 [2021-03-26 20:08:27 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 860/1251] eta: 0:03:19 lr: 0.000167 loss: 2.9110 (2.9612) grad_norm: 2.2544 (2.3059) time: 0.5073 [2021-03-26 20:08:33 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 870/1251] eta: 0:03:14 lr: 0.000167 loss: 3.0598 (2.9603) grad_norm: 2.1989 (2.3059) time: 0.5071 [2021-03-26 20:08:38 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 880/1251] eta: 0:03:09 lr: 0.000167 loss: 3.1158 (2.9627) grad_norm: 2.2562 (2.3077) time: 0.5099 [2021-03-26 20:08:43 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 890/1251] eta: 0:03:04 lr: 0.000167 loss: 3.1732 (2.9617) grad_norm: 2.4249 (2.3081) time: 0.5074 [2021-03-26 20:08:48 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 900/1251] eta: 0:02:59 lr: 0.000167 loss: 2.9383 (2.9603) grad_norm: 2.2381 (2.3066) time: 0.5047 [2021-03-26 20:08:53 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 910/1251] eta: 0:02:53 lr: 0.000167 loss: 2.9617 (2.9599) grad_norm: 2.2248 (2.3075) time: 0.5054 [2021-03-26 20:08:58 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 920/1251] eta: 0:02:48 lr: 0.000167 loss: 2.9514 (2.9596) grad_norm: 2.2683 (2.3066) time: 0.5054 [2021-03-26 20:09:03 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 930/1251] eta: 0:02:43 lr: 0.000167 loss: 3.0488 (2.9597) grad_norm: 2.2100 (2.3077) time: 0.4985 [2021-03-26 20:09:08 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 940/1251] eta: 0:02:38 lr: 0.000167 loss: 3.0270 (2.9593) grad_norm: 2.2755 (2.3089) time: 0.5024 [2021-03-26 20:09:13 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 950/1251] eta: 0:02:33 lr: 0.000167 loss: 3.0270 (2.9600) grad_norm: 2.1521 (2.3071) time: 0.5090 [2021-03-26 20:09:18 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 960/1251] eta: 0:02:28 lr: 0.000167 loss: 3.0609 (2.9602) grad_norm: 2.1283 (2.3060) time: 0.5053 [2021-03-26 20:09:23 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 970/1251] eta: 0:02:23 lr: 0.000167 loss: 3.1765 (2.9628) grad_norm: 2.1689 (2.3045) time: 0.5017 [2021-03-26 20:09:28 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 980/1251] eta: 0:02:18 lr: 0.000167 loss: 3.2094 (2.9618) grad_norm: 2.1689 (2.3033) time: 0.5032 [2021-03-26 20:09:33 swin_small_patch4_window7_224] INFO: Epoch: [221] [ 990/1251] eta: 0:02:12 lr: 0.000167 loss: 3.1428 (2.9624) grad_norm: 2.1643 (2.3019) time: 0.4991 [2021-03-26 20:09:38 swin_small_patch4_window7_224] INFO: Epoch: [221] [1000/1251] eta: 0:02:07 lr: 0.000167 loss: 3.2308 (2.9657) grad_norm: 2.1643 (2.3011) time: 0.4981 [2021-03-26 20:09:43 swin_small_patch4_window7_224] INFO: Epoch: [221] [1010/1251] eta: 0:02:02 lr: 0.000167 loss: 3.1875 (2.9663) grad_norm: 2.0695 (2.2986) time: 0.5043 [2021-03-26 20:09:48 swin_small_patch4_window7_224] INFO: Epoch: [221] [1020/1251] eta: 0:01:57 lr: 0.000167 loss: 3.1009 (2.9646) grad_norm: 2.0912 (2.2992) time: 0.5091 [2021-03-26 20:09:53 swin_small_patch4_window7_224] INFO: Epoch: [221] [1030/1251] eta: 0:01:52 lr: 0.000167 loss: 3.0241 (2.9641) grad_norm: 2.3258 (2.2992) time: 0.5136 [2021-03-26 20:09:58 swin_small_patch4_window7_224] INFO: Epoch: [221] [1040/1251] eta: 0:01:47 lr: 0.000167 loss: 2.9194 (2.9609) grad_norm: 2.3056 (2.2988) time: 0.5105 [2021-03-26 20:10:04 swin_small_patch4_window7_224] INFO: Epoch: [221] [1050/1251] eta: 0:01:42 lr: 0.000167 loss: 2.9327 (2.9623) grad_norm: 2.2336 (2.2987) time: 0.5126 [2021-03-26 20:10:09 swin_small_patch4_window7_224] INFO: Epoch: [221] [1060/1251] eta: 0:01:37 lr: 0.000167 loss: 2.9646 (2.9613) grad_norm: 2.2351 (2.2999) time: 0.5068 [2021-03-26 20:10:14 swin_small_patch4_window7_224] INFO: Epoch: [221] [1070/1251] eta: 0:01:32 lr: 0.000167 loss: 3.0083 (2.9626) grad_norm: 2.1953 (2.2996) time: 0.5031 [2021-03-26 20:10:19 swin_small_patch4_window7_224] INFO: Epoch: [221] [1080/1251] eta: 0:01:27 lr: 0.000167 loss: 3.1688 (2.9629) grad_norm: 2.1880 (2.2982) time: 0.5068 [2021-03-26 20:10:24 swin_small_patch4_window7_224] INFO: Epoch: [221] [1090/1251] eta: 0:01:21 lr: 0.000167 loss: 2.8245 (2.9596) grad_norm: 2.0691 (2.2972) time: 0.4997 [2021-03-26 20:10:29 swin_small_patch4_window7_224] INFO: Epoch: [221] [1100/1251] eta: 0:01:16 lr: 0.000167 loss: 2.8221 (2.9592) grad_norm: 2.1449 (2.2975) time: 0.4957 [2021-03-26 20:10:34 swin_small_patch4_window7_224] INFO: Epoch: [221] [1110/1251] eta: 0:01:11 lr: 0.000167 loss: 3.0572 (2.9597) grad_norm: 2.2985 (2.2983) time: 0.4969 [2021-03-26 20:10:39 swin_small_patch4_window7_224] INFO: Epoch: [221] [1120/1251] eta: 0:01:06 lr: 0.000167 loss: 3.0572 (2.9603) grad_norm: 2.1998 (2.2977) time: 0.5048 [2021-03-26 20:10:44 swin_small_patch4_window7_224] INFO: Epoch: [221] [1130/1251] eta: 0:01:01 lr: 0.000167 loss: 3.0214 (2.9610) grad_norm: 2.1622 (2.2973) time: 0.5126 [2021-03-26 20:10:49 swin_small_patch4_window7_224] INFO: Epoch: [221] [1140/1251] eta: 0:00:56 lr: 0.000166 loss: 2.9510 (2.9601) grad_norm: 2.1622 (2.2989) time: 0.5083 [2021-03-26 20:10:54 swin_small_patch4_window7_224] INFO: Epoch: [221] [1150/1251] eta: 0:00:51 lr: 0.000166 loss: 2.8596 (2.9591) grad_norm: 2.1898 (2.2985) time: 0.5029 [2021-03-26 20:10:59 swin_small_patch4_window7_224] INFO: Epoch: [221] [1160/1251] eta: 0:00:46 lr: 0.000166 loss: 2.8714 (2.9588) grad_norm: 2.2194 (2.2980) time: 0.4996 [2021-03-26 20:11:04 swin_small_patch4_window7_224] INFO: Epoch: [221] [1170/1251] eta: 0:00:41 lr: 0.000166 loss: 2.9207 (2.9580) grad_norm: 2.1822 (2.2968) time: 0.4957 [2021-03-26 20:11:09 swin_small_patch4_window7_224] INFO: Epoch: [221] [1180/1251] eta: 0:00:36 lr: 0.000166 loss: 2.7658 (2.9560) grad_norm: 2.1198 (2.2955) time: 0.5004 [2021-03-26 20:11:14 swin_small_patch4_window7_224] INFO: Epoch: [221] [1190/1251] eta: 0:00:31 lr: 0.000166 loss: 2.8841 (2.9554) grad_norm: 2.0809 (2.2941) time: 0.5054 [2021-03-26 20:11:19 swin_small_patch4_window7_224] INFO: Epoch: [221] [1200/1251] eta: 0:00:25 lr: 0.000166 loss: 3.1567 (2.9577) grad_norm: 2.1273 (2.2929) time: 0.5044 [2021-03-26 20:11:24 swin_small_patch4_window7_224] INFO: Epoch: [221] [1210/1251] eta: 0:00:20 lr: 0.000166 loss: 3.1041 (2.9573) grad_norm: 2.1897 (2.2923) time: 0.5035 [2021-03-26 20:11:29 swin_small_patch4_window7_224] INFO: Epoch: [221] [1220/1251] eta: 0:00:15 lr: 0.000166 loss: 2.9692 (2.9580) grad_norm: 2.1808 (2.2925) time: 0.5027 [2021-03-26 20:11:34 swin_small_patch4_window7_224] INFO: Epoch: [221] [1230/1251] eta: 0:00:10 lr: 0.000166 loss: 3.0065 (2.9587) grad_norm: 2.2233 (2.2922) time: 0.5033 [2021-03-26 20:11:39 swin_small_patch4_window7_224] INFO: Epoch: [221] [1240/1251] eta: 0:00:05 lr: 0.000166 loss: 3.1375 (2.9595) grad_norm: 2.3199 (2.2973) time: 0.5104 [2021-03-26 20:11:44 swin_small_patch4_window7_224] INFO: Epoch: [221] [1250/1251] eta: 0:00:00 lr: 0.000166 loss: 3.1088 (2.9589) grad_norm: 2.2587 (2.2962) time: 0.5089 [2021-03-26 20:11:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 0.5712 (0.5712) acc1: 87.5000 (87.5000) acc5: 96.8750 (96.8750) [2021-03-26 20:11:54 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.6865 (0.7177) acc1: 82.8125 (82.9545) acc5: 96.8750 (96.3068) [2021-03-26 20:11:56 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7320 (0.7437) acc1: 81.2500 (81.9940) acc5: 96.8750 (96.2798) [2021-03-26 20:11:58 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8122 (0.7587) acc1: 81.2500 (81.4012) acc5: 96.8750 (96.2702) [2021-03-26 20:11:59 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7441 (0.7749) acc1: 81.2500 (81.2119) acc5: 96.8750 (96.0747) [2021-03-26 20:12:00 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7881 (0.8009) acc1: 79.6875 (80.5120) acc5: 95.3125 (95.7760) [2021-03-26 20:12:10 swin_small_patch4_window7_224] INFO: * Acc@1 81.494 Acc@5 95.818 loss 0.785 [2021-03-26 20:12:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-26 20:12:10 swin_small_patch4_window7_224] INFO: Max accuracy: 81.49% [2021-03-26 20:12:15 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 0/1251] eta: 1:38:07 lr: 0.000166 loss: 3.4820 (3.4820) grad_norm: 2.1355 (2.1355) time: 4.7063 [2021-03-26 20:12:20 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 10/1251] eta: 0:18:27 lr: 0.000166 loss: 3.1199 (3.0518) grad_norm: 2.1989 (2.2791) time: 0.8928 [2021-03-26 20:12:25 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 20/1251] eta: 0:14:31 lr: 0.000166 loss: 2.9925 (2.9640) grad_norm: 2.1871 (2.3069) time: 0.5080 [2021-03-26 20:12:30 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 30/1251] eta: 0:13:01 lr: 0.000166 loss: 2.9744 (2.9787) grad_norm: 2.1128 (2.3025) time: 0.5013 [2021-03-26 20:12:35 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 40/1251] eta: 0:12:14 lr: 0.000166 loss: 3.1061 (3.0005) grad_norm: 2.0268 (2.2271) time: 0.4999 [2021-03-26 20:12:40 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 50/1251] eta: 0:11:41 lr: 0.000166 loss: 3.0536 (2.9782) grad_norm: 2.1716 (2.2603) time: 0.4967 [2021-03-26 20:12:45 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 60/1251] eta: 0:11:18 lr: 0.000166 loss: 2.7896 (2.9396) grad_norm: 2.3551 (2.2736) time: 0.4953 [2021-03-26 20:12:50 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 70/1251] eta: 0:11:02 lr: 0.000166 loss: 2.9336 (2.9257) grad_norm: 2.2305 (2.2662) time: 0.5026 [2021-03-26 20:12:55 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 80/1251] eta: 0:10:50 lr: 0.000166 loss: 3.1112 (2.9515) grad_norm: 2.2253 (2.2715) time: 0.5117 [2021-03-26 20:13:00 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 90/1251] eta: 0:10:38 lr: 0.000166 loss: 3.0501 (2.8926) grad_norm: 2.2583 (2.2736) time: 0.5102 [2021-03-26 20:13:05 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 100/1251] eta: 0:10:27 lr: 0.000166 loss: 2.4305 (2.8742) grad_norm: 2.3087 (2.3194) time: 0.5017 [2021-03-26 20:13:10 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 110/1251] eta: 0:10:19 lr: 0.000166 loss: 2.7472 (2.8728) grad_norm: 2.2416 (2.3057) time: 0.5109 [2021-03-26 20:13:15 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 120/1251] eta: 0:10:10 lr: 0.000166 loss: 2.8222 (2.8761) grad_norm: 2.1890 (2.3073) time: 0.5146 [2021-03-26 20:13:20 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 130/1251] eta: 0:10:02 lr: 0.000166 loss: 3.0433 (2.8832) grad_norm: 2.3345 (2.3110) time: 0.5051 [2021-03-26 20:13:26 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 140/1251] eta: 0:09:54 lr: 0.000166 loss: 2.9960 (2.8827) grad_norm: 2.3189 (2.3106) time: 0.5039 [2021-03-26 20:13:31 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 150/1251] eta: 0:09:46 lr: 0.000166 loss: 2.9227 (2.8815) grad_norm: 2.1045 (2.2993) time: 0.5062 [2021-03-26 20:13:36 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 160/1251] eta: 0:09:39 lr: 0.000166 loss: 2.9802 (2.8919) grad_norm: 2.1045 (2.2964) time: 0.5053 [2021-03-26 20:13:41 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 170/1251] eta: 0:09:32 lr: 0.000166 loss: 3.1147 (2.8951) grad_norm: 2.1853 (2.2924) time: 0.5016 [2021-03-26 20:13:46 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 180/1251] eta: 0:09:25 lr: 0.000166 loss: 2.9013 (2.8917) grad_norm: 2.1321 (2.2828) time: 0.5012 [2021-03-26 20:13:51 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 190/1251] eta: 0:09:18 lr: 0.000166 loss: 2.8869 (2.8854) grad_norm: 2.2001 (2.2798) time: 0.5054 [2021-03-26 20:13:56 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 200/1251] eta: 0:09:12 lr: 0.000166 loss: 2.9964 (2.8864) grad_norm: 2.1580 (2.2896) time: 0.5036 [2021-03-26 20:14:01 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 210/1251] eta: 0:09:06 lr: 0.000166 loss: 3.0494 (2.8977) grad_norm: 2.1508 (2.2876) time: 0.5049 [2021-03-26 20:14:06 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 220/1251] eta: 0:09:00 lr: 0.000165 loss: 3.0343 (2.8983) grad_norm: 2.2359 (2.2913) time: 0.5110 [2021-03-26 20:14:11 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 230/1251] eta: 0:08:54 lr: 0.000165 loss: 2.9104 (2.8952) grad_norm: 2.3129 (2.2966) time: 0.5084 [2021-03-26 20:14:16 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 240/1251] eta: 0:08:47 lr: 0.000165 loss: 2.9017 (2.8988) grad_norm: 2.2754 (2.2995) time: 0.4989 [2021-03-26 20:14:21 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 250/1251] eta: 0:08:41 lr: 0.000165 loss: 3.1974 (2.9079) grad_norm: 2.3159 (2.3040) time: 0.4983 [2021-03-26 20:14:26 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 260/1251] eta: 0:08:35 lr: 0.000165 loss: 3.0002 (2.9048) grad_norm: 2.2807 (2.3012) time: 0.5035 [2021-03-26 20:14:31 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 270/1251] eta: 0:08:30 lr: 0.000165 loss: 3.0002 (2.9131) grad_norm: 2.1939 (2.2934) time: 0.5031 [2021-03-26 20:14:36 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 280/1251] eta: 0:08:24 lr: 0.000165 loss: 3.2515 (2.9200) grad_norm: 2.1700 (2.3210) time: 0.5066 [2021-03-26 20:14:41 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 290/1251] eta: 0:08:18 lr: 0.000165 loss: 3.2515 (2.9259) grad_norm: 2.2639 (2.3234) time: 0.5029 [2021-03-26 20:14:46 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 300/1251] eta: 0:08:13 lr: 0.000165 loss: 2.9454 (2.9190) grad_norm: 2.1077 (2.3134) time: 0.5065 [2021-03-26 20:14:51 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 310/1251] eta: 0:08:07 lr: 0.000165 loss: 2.9072 (2.9189) grad_norm: 2.0752 (2.3073) time: 0.5100 [2021-03-26 20:14:56 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 320/1251] eta: 0:08:01 lr: 0.000165 loss: 2.8236 (2.9112) grad_norm: 2.1021 (2.3059) time: 0.4990 [2021-03-26 20:15:01 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 330/1251] eta: 0:07:56 lr: 0.000165 loss: 2.9387 (2.9172) grad_norm: 2.2496 (2.3064) time: 0.4996 [2021-03-26 20:15:06 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 340/1251] eta: 0:07:50 lr: 0.000165 loss: 3.0368 (2.9179) grad_norm: 2.2013 (2.3068) time: 0.5046 [2021-03-26 20:15:11 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 350/1251] eta: 0:07:45 lr: 0.000165 loss: 3.0307 (2.9139) grad_norm: 2.1867 (2.3061) time: 0.5028 [2021-03-26 20:15:16 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 360/1251] eta: 0:07:39 lr: 0.000165 loss: 3.0307 (2.9147) grad_norm: 2.1867 (2.3069) time: 0.5005 [2021-03-26 20:15:21 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 370/1251] eta: 0:07:34 lr: 0.000165 loss: 3.1195 (2.9189) grad_norm: 2.1945 (2.3071) time: 0.5025 [2021-03-26 20:15:26 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 380/1251] eta: 0:07:28 lr: 0.000165 loss: 2.9566 (2.9123) grad_norm: 2.1711 (2.3042) time: 0.5035 [2021-03-26 20:15:31 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 390/1251] eta: 0:07:23 lr: 0.000165 loss: 2.7162 (2.9121) grad_norm: 2.1235 (2.3011) time: 0.4977 [2021-03-26 20:15:37 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 400/1251] eta: 0:07:18 lr: 0.000165 loss: 3.0586 (2.9159) grad_norm: 2.1235 (2.2976) time: 0.5066 [2021-03-26 20:15:41 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 410/1251] eta: 0:07:12 lr: 0.000165 loss: 2.9560 (2.9126) grad_norm: 2.1686 (2.3008) time: 0.5052 [2021-03-26 20:15:47 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 420/1251] eta: 0:07:07 lr: 0.000165 loss: 3.0361 (2.9173) grad_norm: 2.1990 (2.2986) time: 0.4998 [2021-03-26 20:15:52 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 430/1251] eta: 0:07:01 lr: 0.000165 loss: 3.1868 (2.9248) grad_norm: 2.1643 (2.3057) time: 0.5080 [2021-03-26 20:15:57 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 440/1251] eta: 0:06:56 lr: 0.000165 loss: 3.0892 (2.9218) grad_norm: 2.1242 (2.3027) time: 0.5022 [2021-03-26 20:16:02 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 450/1251] eta: 0:06:51 lr: 0.000165 loss: 2.8158 (2.9198) grad_norm: 2.1216 (2.3008) time: 0.4992 [2021-03-26 20:16:07 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 460/1251] eta: 0:06:45 lr: 0.000165 loss: 3.0278 (2.9212) grad_norm: 2.2862 (2.3100) time: 0.5034 [2021-03-26 20:16:12 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 470/1251] eta: 0:06:40 lr: 0.000165 loss: 2.8915 (2.9152) grad_norm: 2.3091 (2.3080) time: 0.5069 [2021-03-26 20:16:17 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 480/1251] eta: 0:06:35 lr: 0.000165 loss: 3.0967 (2.9191) grad_norm: 2.2302 (2.3116) time: 0.5048 [2021-03-26 20:16:22 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 490/1251] eta: 0:06:30 lr: 0.000165 loss: 3.0967 (2.9177) grad_norm: 2.1552 (2.3142) time: 0.5057 [2021-03-26 20:16:27 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 500/1251] eta: 0:06:24 lr: 0.000165 loss: 2.5483 (2.9125) grad_norm: 2.1694 (2.3140) time: 0.5084 [2021-03-26 20:16:32 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 510/1251] eta: 0:06:19 lr: 0.000165 loss: 2.8087 (2.9152) grad_norm: 2.1694 (2.3138) time: 0.5032 [2021-03-26 20:16:37 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 520/1251] eta: 0:06:14 lr: 0.000165 loss: 3.0076 (2.9133) grad_norm: 2.2359 (2.3181) time: 0.5005 [2021-03-26 20:16:42 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 530/1251] eta: 0:06:09 lr: 0.000165 loss: 2.9296 (2.9135) grad_norm: 2.1785 (2.3146) time: 0.5058 [2021-03-26 20:16:47 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 540/1251] eta: 0:06:04 lr: 0.000165 loss: 2.8739 (2.9119) grad_norm: 2.0899 (2.3121) time: 0.5154 [2021-03-26 20:16:52 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 550/1251] eta: 0:05:59 lr: 0.000164 loss: 2.6283 (2.9089) grad_norm: 2.1682 (2.3124) time: 0.5173 [2021-03-26 20:16:58 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 560/1251] eta: 0:05:54 lr: 0.000164 loss: 3.0233 (2.9137) grad_norm: 2.1827 (2.3110) time: 0.5152 [2021-03-26 20:17:03 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 570/1251] eta: 0:05:48 lr: 0.000164 loss: 3.1020 (2.9144) grad_norm: 2.3588 (2.3125) time: 0.5063 [2021-03-26 20:17:08 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 580/1251] eta: 0:05:43 lr: 0.000164 loss: 3.0381 (2.9142) grad_norm: 2.3211 (2.3104) time: 0.4983 [2021-03-26 20:17:13 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 590/1251] eta: 0:05:38 lr: 0.000164 loss: 2.9437 (2.9140) grad_norm: 2.1429 (2.3087) time: 0.5009 [2021-03-26 20:17:18 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 600/1251] eta: 0:05:33 lr: 0.000164 loss: 2.9437 (2.9161) grad_norm: 2.1662 (2.3068) time: 0.5062 [2021-03-26 20:17:23 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 610/1251] eta: 0:05:27 lr: 0.000164 loss: 2.9833 (2.9180) grad_norm: 2.1417 (2.3039) time: 0.5091 [2021-03-26 20:17:28 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 620/1251] eta: 0:05:22 lr: 0.000164 loss: 2.9833 (2.9166) grad_norm: 2.0619 (2.3003) time: 0.5043 [2021-03-26 20:17:33 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 630/1251] eta: 0:05:17 lr: 0.000164 loss: 3.0478 (2.9185) grad_norm: 2.1412 (2.3005) time: 0.4991 [2021-03-26 20:17:38 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 640/1251] eta: 0:05:12 lr: 0.000164 loss: 2.9673 (2.9166) grad_norm: 2.2047 (2.2995) time: 0.5015 [2021-03-26 20:17:43 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 650/1251] eta: 0:05:07 lr: 0.000164 loss: 2.8940 (2.9172) grad_norm: 2.2004 (2.3128) time: 0.5068 [2021-03-26 20:17:48 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 660/1251] eta: 0:05:02 lr: 0.000164 loss: 2.8859 (2.9171) grad_norm: 2.2929 (2.3137) time: 0.5076 [2021-03-26 20:17:53 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 670/1251] eta: 0:04:57 lr: 0.000164 loss: 2.8823 (2.9180) grad_norm: 2.2929 (2.3127) time: 0.5203 [2021-03-26 20:17:58 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 680/1251] eta: 0:04:51 lr: 0.000164 loss: 2.8929 (2.9167) grad_norm: 2.1381 (2.3097) time: 0.5197 [2021-03-26 20:18:03 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 690/1251] eta: 0:04:46 lr: 0.000164 loss: 2.7396 (2.9152) grad_norm: 2.1162 (2.3081) time: 0.5031 [2021-03-26 20:18:08 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 700/1251] eta: 0:04:41 lr: 0.000164 loss: 2.7396 (2.9155) grad_norm: 2.1402 (2.3080) time: 0.4996 [2021-03-26 20:18:13 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 710/1251] eta: 0:04:36 lr: 0.000164 loss: 2.7462 (2.9107) grad_norm: 2.2753 (2.3071) time: 0.4983 [2021-03-26 20:18:18 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 720/1251] eta: 0:04:31 lr: 0.000164 loss: 2.7745 (2.9104) grad_norm: 2.2445 (2.3086) time: 0.5040 [2021-03-26 20:18:24 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 730/1251] eta: 0:04:26 lr: 0.000164 loss: 2.9589 (2.9103) grad_norm: 2.2309 (2.3079) time: 0.5102 [2021-03-26 20:18:29 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 740/1251] eta: 0:04:21 lr: 0.000164 loss: 2.9411 (2.9098) grad_norm: 2.2521 (2.3079) time: 0.5170 [2021-03-26 20:18:34 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 750/1251] eta: 0:04:15 lr: 0.000164 loss: 3.0207 (2.9108) grad_norm: 2.2015 (2.3072) time: 0.5114 [2021-03-26 20:18:39 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 760/1251] eta: 0:04:10 lr: 0.000164 loss: 3.0399 (2.9134) grad_norm: 2.2197 (2.3081) time: 0.5056 [2021-03-26 20:18:44 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 770/1251] eta: 0:04:05 lr: 0.000164 loss: 3.1051 (2.9134) grad_norm: 2.2385 (2.3072) time: 0.5061 [2021-03-26 20:18:49 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 780/1251] eta: 0:04:00 lr: 0.000164 loss: 3.0630 (2.9164) grad_norm: 2.1828 (2.3062) time: 0.4961 [2021-03-26 20:18:54 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 790/1251] eta: 0:03:55 lr: 0.000164 loss: 2.9345 (2.9131) grad_norm: 2.1828 (2.3057) time: 0.5034 [2021-03-26 20:18:59 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 800/1251] eta: 0:03:50 lr: 0.000164 loss: 2.8516 (2.9135) grad_norm: 2.1663 (2.3042) time: 0.5030 [2021-03-26 20:19:04 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 810/1251] eta: 0:03:44 lr: 0.000164 loss: 3.0660 (2.9144) grad_norm: 2.1832 (2.3038) time: 0.4948 [2021-03-26 20:19:09 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 820/1251] eta: 0:03:39 lr: 0.000164 loss: 3.2244 (2.9162) grad_norm: 2.1832 (2.3059) time: 0.5038 [2021-03-26 20:19:14 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 830/1251] eta: 0:03:34 lr: 0.000164 loss: 3.0585 (2.9164) grad_norm: 2.2766 (2.3085) time: 0.5123 [2021-03-26 20:19:19 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 840/1251] eta: 0:03:29 lr: 0.000164 loss: 3.0319 (2.9159) grad_norm: 2.3464 (2.3107) time: 0.5087 [2021-03-26 20:19:24 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 850/1251] eta: 0:03:24 lr: 0.000164 loss: 3.0381 (2.9180) grad_norm: 2.2611 (2.3097) time: 0.5075 [2021-03-26 20:19:29 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 860/1251] eta: 0:03:19 lr: 0.000164 loss: 3.1037 (2.9196) grad_norm: 2.1726 (2.3081) time: 0.5110 [2021-03-26 20:19:34 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 870/1251] eta: 0:03:14 lr: 0.000164 loss: 3.0655 (2.9193) grad_norm: 2.1269 (2.3066) time: 0.5090 [2021-03-26 20:19:39 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 880/1251] eta: 0:03:09 lr: 0.000164 loss: 2.9803 (2.9178) grad_norm: 2.1476 (2.3061) time: 0.5023 [2021-03-26 20:19:44 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 890/1251] eta: 0:03:04 lr: 0.000163 loss: 2.9696 (2.9195) grad_norm: 2.0863 (2.3051) time: 0.5021 [2021-03-26 20:19:49 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 900/1251] eta: 0:02:58 lr: 0.000163 loss: 2.9615 (2.9186) grad_norm: 2.2525 (2.3074) time: 0.5023 [2021-03-26 20:19:54 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 910/1251] eta: 0:02:53 lr: 0.000163 loss: 2.9124 (2.9179) grad_norm: 2.3063 (2.3062) time: 0.4990 [2021-03-26 20:20:00 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 920/1251] eta: 0:02:48 lr: 0.000163 loss: 3.0552 (2.9200) grad_norm: 2.1305 (2.3047) time: 0.5072 [2021-03-26 20:20:05 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 930/1251] eta: 0:02:43 lr: 0.000163 loss: 3.0952 (2.9191) grad_norm: 2.1305 (2.3040) time: 0.5180 [2021-03-26 20:20:10 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 940/1251] eta: 0:02:38 lr: 0.000163 loss: 2.9334 (2.9173) grad_norm: 2.0655 (2.3021) time: 0.5108 [2021-03-26 20:20:15 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 950/1251] eta: 0:02:33 lr: 0.000163 loss: 2.9694 (2.9199) grad_norm: 2.2363 (2.3040) time: 0.4991 [2021-03-26 20:20:20 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 960/1251] eta: 0:02:28 lr: 0.000163 loss: 3.1368 (2.9227) grad_norm: 2.2483 (2.3033) time: 0.5078 [2021-03-26 20:20:25 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 970/1251] eta: 0:02:23 lr: 0.000163 loss: 3.2153 (2.9255) grad_norm: 2.1276 (2.3025) time: 0.5107 [2021-03-26 20:20:30 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 980/1251] eta: 0:02:18 lr: 0.000163 loss: 3.2715 (2.9279) grad_norm: 2.2567 (2.3021) time: 0.5007 [2021-03-26 20:20:35 swin_small_patch4_window7_224] INFO: Epoch: [222] [ 990/1251] eta: 0:02:12 lr: 0.000163 loss: 3.0869 (2.9257) grad_norm: 2.2567 (2.3036) time: 0.5000 [2021-03-26 20:20:40 swin_small_patch4_window7_224] INFO: Epoch: [222] [1000/1251] eta: 0:02:07 lr: 0.000163 loss: 2.9179 (2.9260) grad_norm: 2.1573 (2.3022) time: 0.4994 [2021-03-26 20:20:45 swin_small_patch4_window7_224] INFO: Epoch: [222] [1010/1251] eta: 0:02:02 lr: 0.000163 loss: 2.7851 (2.9245) grad_norm: 2.2157 (2.3018) time: 0.4963 [2021-03-26 20:20:50 swin_small_patch4_window7_224] INFO: Epoch: [222] [1020/1251] eta: 0:01:57 lr: 0.000163 loss: 2.9006 (2.9247) grad_norm: 2.2863 (2.3011) time: 0.4964 [2021-03-26 20:20:55 swin_small_patch4_window7_224] INFO: Epoch: [222] [1030/1251] eta: 0:01:52 lr: 0.000163 loss: 3.1218 (2.9241) grad_norm: 2.1774 (2.3002) time: 0.4973 [2021-03-26 20:21:00 swin_small_patch4_window7_224] INFO: Epoch: [222] [1040/1251] eta: 0:01:47 lr: 0.000163 loss: 2.9249 (2.9229) grad_norm: 2.1738 (2.2989) time: 0.5016 [2021-03-26 20:21:05 swin_small_patch4_window7_224] INFO: Epoch: [222] [1050/1251] eta: 0:01:42 lr: 0.000163 loss: 2.9249 (2.9239) grad_norm: 2.0307 (2.2963) time: 0.5059 [2021-03-26 20:21:10 swin_small_patch4_window7_224] INFO: Epoch: [222] [1060/1251] eta: 0:01:37 lr: 0.000163 loss: 2.9201 (2.9213) grad_norm: 2.1168 (2.2957) time: 0.5066 [2021-03-26 20:21:15 swin_small_patch4_window7_224] INFO: Epoch: [222] [1070/1251] eta: 0:01:32 lr: 0.000163 loss: 2.9042 (2.9214) grad_norm: 2.1643 (2.2948) time: 0.5046 [2021-03-26 20:21:20 swin_small_patch4_window7_224] INFO: Epoch: [222] [1080/1251] eta: 0:01:26 lr: 0.000163 loss: 2.9539 (2.9215) grad_norm: 2.1128 (2.2934) time: 0.5021 [2021-03-26 20:21:25 swin_small_patch4_window7_224] INFO: Epoch: [222] [1090/1251] eta: 0:01:21 lr: 0.000163 loss: 3.0113 (2.9220) grad_norm: 2.2322 (2.2958) time: 0.5028 [2021-03-26 20:21:30 swin_small_patch4_window7_224] INFO: Epoch: [222] [1100/1251] eta: 0:01:16 lr: 0.000163 loss: 3.1669 (2.9237) grad_norm: 2.2908 (2.2953) time: 0.5017 [2021-03-26 20:21:35 swin_small_patch4_window7_224] INFO: Epoch: [222] [1110/1251] eta: 0:01:11 lr: 0.000163 loss: 3.1712 (2.9246) grad_norm: 2.3302 (2.2961) time: 0.5033 [2021-03-26 20:21:40 swin_small_patch4_window7_224] INFO: Epoch: [222] [1120/1251] eta: 0:01:06 lr: 0.000163 loss: 3.0567 (2.9245) grad_norm: 2.3442 (2.2971) time: 0.5056 [2021-03-26 20:21:45 swin_small_patch4_window7_224] INFO: Epoch: [222] [1130/1251] eta: 0:01:01 lr: 0.000163 loss: 3.1635 (2.9280) grad_norm: 2.1921 (2.2969) time: 0.5019 [2021-03-26 20:21:50 swin_small_patch4_window7_224] INFO: Epoch: [222] [1140/1251] eta: 0:00:56 lr: 0.000163 loss: 3.2248 (2.9289) grad_norm: 2.1983 (2.2970) time: 0.5000 [2021-03-26 20:21:55 swin_small_patch4_window7_224] INFO: Epoch: [222] [1150/1251] eta: 0:00:51 lr: 0.000163 loss: 3.2265 (2.9307) grad_norm: 2.2627 (2.2971) time: 0.5067 [2021-03-26 20:22:00 swin_small_patch4_window7_224] INFO: Epoch: [222] [1160/1251] eta: 0:00:46 lr: 0.000163 loss: 3.0712 (2.9298) grad_norm: 2.1910 (2.2963) time: 0.5081 [2021-03-26 20:22:06 swin_small_patch4_window7_224] INFO: Epoch: [222] [1170/1251] eta: 0:00:41 lr: 0.000163 loss: 2.8342 (2.9284) grad_norm: 2.2227 (2.2961) time: 0.5046 [2021-03-26 20:22:11 swin_small_patch4_window7_224] INFO: Epoch: [222] [1180/1251] eta: 0:00:36 lr: 0.000163 loss: 2.8572 (2.9282) grad_norm: 2.2227 (2.2965) time: 0.5041 [2021-03-26 20:22:16 swin_small_patch4_window7_224] INFO: Epoch: [222] [1190/1251] eta: 0:00:31 lr: 0.000163 loss: 2.9331 (2.9291) grad_norm: 2.2401 (2.2961) time: 0.5020 [2021-03-26 20:22:21 swin_small_patch4_window7_224] INFO: Epoch: [222] [1200/1251] eta: 0:00:25 lr: 0.000163 loss: 3.0793 (2.9293) grad_norm: 2.2087 (2.2957) time: 0.5035 [2021-03-26 20:22:26 swin_small_patch4_window7_224] INFO: Epoch: [222] [1210/1251] eta: 0:00:20 lr: 0.000163 loss: 2.9518 (2.9290) grad_norm: 2.2143 (2.2951) time: 0.5062 [2021-03-26 20:22:31 swin_small_patch4_window7_224] INFO: Epoch: [222] [1220/1251] eta: 0:00:15 lr: 0.000162 loss: 3.0047 (2.9308) grad_norm: 2.2143 (2.2959) time: 0.5059 [2021-03-26 20:22:36 swin_small_patch4_window7_224] INFO: Epoch: [222] [1230/1251] eta: 0:00:10 lr: 0.000162 loss: 3.0184 (2.9305) grad_norm: 2.2121 (2.2960) time: 0.5044 [2021-03-26 20:22:41 swin_small_patch4_window7_224] INFO: Epoch: [222] [1240/1251] eta: 0:00:05 lr: 0.000162 loss: 2.9642 (2.9305) grad_norm: 2.2653 (2.2966) time: 0.4999 [2021-03-26 20:22:46 swin_small_patch4_window7_224] INFO: Epoch: [222] [1250/1251] eta: 0:00:00 lr: 0.000162 loss: 2.9643 (2.9301) grad_norm: 2.3202 (2.2979) time: 0.4921 [2021-03-26 20:22:55 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:18 loss: 0.5951 (0.5951) acc1: 87.5000 (87.5000) acc5: 96.8750 (96.8750) [2021-03-26 20:22:58 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8925 (0.8282) acc1: 78.1250 (80.9659) acc5: 95.3125 (95.4545) [2021-03-26 20:23:00 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8925 (0.8477) acc1: 78.1250 (80.0595) acc5: 93.7500 (94.7173) [2021-03-26 20:23:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7784 (0.8076) acc1: 79.6875 (80.5444) acc5: 95.3125 (95.5141) [2021-03-26 20:23:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7949 (0.8104) acc1: 79.6875 (80.1067) acc5: 96.8750 (95.6174) [2021-03-26 20:23:04 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7949 (0.7959) acc1: 79.6875 (80.3520) acc5: 96.8750 (95.8400) [2021-03-26 20:23:14 swin_small_patch4_window7_224] INFO: * Acc@1 81.316 Acc@5 95.696 loss 0.789 [2021-03-26 20:23:14 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.3% [2021-03-26 20:23:14 swin_small_patch4_window7_224] INFO: Max accuracy: 81.49% [2021-03-26 20:23:18 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 0/1251] eta: 1:24:00 lr: 0.000162 loss: 3.3846 (3.3846) grad_norm: 1.9296 (1.9296) time: 4.0295 [2021-03-26 20:23:24 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 10/1251] eta: 0:18:07 lr: 0.000162 loss: 2.8236 (2.7288) grad_norm: 2.3158 (2.3719) time: 0.8766 [2021-03-26 20:23:29 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 20/1251] eta: 0:14:22 lr: 0.000162 loss: 2.8236 (2.8131) grad_norm: 2.3158 (2.3866) time: 0.5345 [2021-03-26 20:23:34 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 30/1251] eta: 0:12:59 lr: 0.000162 loss: 3.1110 (2.8853) grad_norm: 2.1940 (2.3383) time: 0.5071 [2021-03-26 20:23:39 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 40/1251] eta: 0:12:12 lr: 0.000162 loss: 3.1513 (2.9355) grad_norm: 2.1810 (2.3412) time: 0.5048 [2021-03-26 20:23:44 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 50/1251] eta: 0:11:44 lr: 0.000162 loss: 3.1954 (2.9260) grad_norm: 2.1984 (2.3235) time: 0.5056 [2021-03-26 20:23:49 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 60/1251] eta: 0:11:19 lr: 0.000162 loss: 3.0859 (2.9383) grad_norm: 2.0817 (2.2850) time: 0.5003 [2021-03-26 20:23:54 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 70/1251] eta: 0:11:02 lr: 0.000162 loss: 3.0591 (2.9531) grad_norm: 2.0817 (2.2856) time: 0.4976 [2021-03-26 20:23:59 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 80/1251] eta: 0:10:49 lr: 0.000162 loss: 3.0754 (2.9731) grad_norm: 2.1963 (2.2811) time: 0.5042 [2021-03-26 20:24:04 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 90/1251] eta: 0:10:36 lr: 0.000162 loss: 3.0771 (2.9731) grad_norm: 2.2174 (2.2688) time: 0.5038 [2021-03-26 20:24:09 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 100/1251] eta: 0:10:25 lr: 0.000162 loss: 3.0771 (2.9673) grad_norm: 2.2093 (2.2641) time: 0.4975 [2021-03-26 20:24:14 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 110/1251] eta: 0:10:16 lr: 0.000162 loss: 3.1637 (2.9670) grad_norm: 2.1838 (2.2577) time: 0.5033 [2021-03-26 20:24:20 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 120/1251] eta: 0:10:09 lr: 0.000162 loss: 3.0220 (2.9493) grad_norm: 2.1306 (2.2619) time: 0.5151 [2021-03-26 20:24:25 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 130/1251] eta: 0:10:00 lr: 0.000162 loss: 3.0343 (2.9573) grad_norm: 2.1306 (2.2555) time: 0.5080 [2021-03-26 20:24:30 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 140/1251] eta: 0:09:52 lr: 0.000162 loss: 3.0958 (2.9581) grad_norm: 2.1192 (2.2467) time: 0.5005 [2021-03-26 20:24:35 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 150/1251] eta: 0:09:45 lr: 0.000162 loss: 3.0176 (2.9514) grad_norm: 2.1246 (2.2461) time: 0.5052 [2021-03-26 20:24:40 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 160/1251] eta: 0:09:37 lr: 0.000162 loss: 3.0587 (2.9521) grad_norm: 2.1855 (2.2420) time: 0.5055 [2021-03-26 20:24:45 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 170/1251] eta: 0:09:30 lr: 0.000162 loss: 2.8694 (2.9366) grad_norm: 2.2275 (2.2434) time: 0.5000 [2021-03-26 20:24:50 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 180/1251] eta: 0:09:24 lr: 0.000162 loss: 3.0756 (2.9499) grad_norm: 2.2720 (2.2499) time: 0.5045 [2021-03-26 20:24:55 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 190/1251] eta: 0:09:17 lr: 0.000162 loss: 3.1091 (2.9514) grad_norm: 2.2741 (2.2521) time: 0.5065 [2021-03-26 20:25:00 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 200/1251] eta: 0:09:11 lr: 0.000162 loss: 2.9772 (2.9528) grad_norm: 2.3301 (2.2634) time: 0.5049 [2021-03-26 20:25:05 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 210/1251] eta: 0:09:05 lr: 0.000162 loss: 2.9152 (2.9509) grad_norm: 2.4801 (2.2654) time: 0.5127 [2021-03-26 20:25:10 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 220/1251] eta: 0:08:59 lr: 0.000162 loss: 2.8331 (2.9445) grad_norm: 2.1988 (2.2632) time: 0.5072 [2021-03-26 20:25:15 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 230/1251] eta: 0:08:53 lr: 0.000162 loss: 3.2149 (2.9600) grad_norm: 2.1789 (2.2580) time: 0.5044 [2021-03-26 20:25:20 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 240/1251] eta: 0:08:47 lr: 0.000162 loss: 3.2605 (2.9588) grad_norm: 2.1928 (2.2572) time: 0.5085 [2021-03-26 20:25:25 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 250/1251] eta: 0:08:41 lr: 0.000162 loss: 2.8694 (2.9505) grad_norm: 2.2498 (2.2657) time: 0.5017 [2021-03-26 20:25:30 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 260/1251] eta: 0:08:35 lr: 0.000162 loss: 2.9097 (2.9573) grad_norm: 2.2498 (2.2661) time: 0.4980 [2021-03-26 20:25:35 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 270/1251] eta: 0:08:29 lr: 0.000162 loss: 3.1131 (2.9604) grad_norm: 2.1481 (2.2643) time: 0.4968 [2021-03-26 20:25:40 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 280/1251] eta: 0:08:23 lr: 0.000162 loss: 2.9367 (2.9486) grad_norm: 2.1255 (2.2652) time: 0.5007 [2021-03-26 20:25:45 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 290/1251] eta: 0:08:17 lr: 0.000162 loss: 2.6122 (2.9357) grad_norm: 2.2136 (2.2642) time: 0.5041 [2021-03-26 20:25:50 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 300/1251] eta: 0:08:12 lr: 0.000161 loss: 2.7730 (2.9303) grad_norm: 2.2428 (2.2672) time: 0.5058 [2021-03-26 20:25:55 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 310/1251] eta: 0:08:07 lr: 0.000161 loss: 3.0568 (2.9343) grad_norm: 2.1813 (2.2662) time: 0.5099 [2021-03-26 20:26:01 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 320/1251] eta: 0:08:01 lr: 0.000161 loss: 3.0993 (2.9349) grad_norm: 2.1197 (2.2607) time: 0.5138 [2021-03-26 20:26:06 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 330/1251] eta: 0:07:56 lr: 0.000161 loss: 2.9233 (2.9371) grad_norm: 2.1233 (2.2581) time: 0.5106 [2021-03-26 20:26:11 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 340/1251] eta: 0:07:50 lr: 0.000161 loss: 2.9803 (2.9389) grad_norm: 2.1437 (2.2578) time: 0.5006 [2021-03-26 20:26:16 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 350/1251] eta: 0:07:45 lr: 0.000161 loss: 3.1487 (2.9467) grad_norm: 2.1610 (2.2588) time: 0.4979 [2021-03-26 20:26:21 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 360/1251] eta: 0:07:39 lr: 0.000161 loss: 3.1687 (2.9514) grad_norm: 2.1267 (2.2552) time: 0.4993 [2021-03-26 20:26:26 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 370/1251] eta: 0:07:33 lr: 0.000161 loss: 3.1336 (2.9524) grad_norm: 2.1504 (2.2547) time: 0.5011 [2021-03-26 20:26:31 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 380/1251] eta: 0:07:28 lr: 0.000161 loss: 3.1336 (2.9537) grad_norm: 2.2335 (2.2591) time: 0.5005 [2021-03-26 20:26:36 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 390/1251] eta: 0:07:22 lr: 0.000161 loss: 3.0372 (2.9545) grad_norm: 2.1228 (2.2560) time: 0.4994 [2021-03-26 20:26:41 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 400/1251] eta: 0:07:17 lr: 0.000161 loss: 2.9954 (2.9573) grad_norm: 2.1341 (2.2569) time: 0.5060 [2021-03-26 20:26:46 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 410/1251] eta: 0:07:12 lr: 0.000161 loss: 3.2241 (2.9645) grad_norm: 2.2201 (2.2551) time: 0.5043 [2021-03-26 20:26:51 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 420/1251] eta: 0:07:06 lr: 0.000161 loss: 3.2512 (2.9728) grad_norm: 2.2201 (2.2552) time: 0.4979 [2021-03-26 20:26:56 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 430/1251] eta: 0:07:01 lr: 0.000161 loss: 3.0504 (2.9670) grad_norm: 2.2591 (2.2671) time: 0.5032 [2021-03-26 20:27:01 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 440/1251] eta: 0:06:56 lr: 0.000161 loss: 2.8901 (2.9686) grad_norm: 2.2393 (2.2675) time: 0.5049 [2021-03-26 20:27:06 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 450/1251] eta: 0:06:50 lr: 0.000161 loss: 3.0686 (2.9682) grad_norm: 2.2490 (2.2702) time: 0.4965 [2021-03-26 20:27:11 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 460/1251] eta: 0:06:45 lr: 0.000161 loss: 3.0541 (2.9704) grad_norm: 2.1966 (2.2684) time: 0.4955 [2021-03-26 20:27:16 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 470/1251] eta: 0:06:39 lr: 0.000161 loss: 3.0541 (2.9685) grad_norm: 2.1349 (2.2647) time: 0.4955 [2021-03-26 20:27:21 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 480/1251] eta: 0:06:34 lr: 0.000161 loss: 3.1631 (2.9736) grad_norm: 2.1194 (2.2628) time: 0.4942 [2021-03-26 20:27:26 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 490/1251] eta: 0:06:29 lr: 0.000161 loss: 2.9466 (2.9652) grad_norm: 2.0924 (2.2605) time: 0.5004 [2021-03-26 20:27:31 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 500/1251] eta: 0:06:24 lr: 0.000161 loss: 2.8327 (2.9633) grad_norm: 2.0899 (2.2651) time: 0.5025 [2021-03-26 20:27:36 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 510/1251] eta: 0:06:18 lr: 0.000161 loss: 3.0713 (2.9651) grad_norm: 2.2447 (2.2646) time: 0.5033 [2021-03-26 20:27:41 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 520/1251] eta: 0:06:13 lr: 0.000161 loss: 3.0799 (2.9630) grad_norm: 2.1932 (2.2651) time: 0.5031 [2021-03-26 20:27:46 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 530/1251] eta: 0:06:08 lr: 0.000161 loss: 2.8384 (2.9622) grad_norm: 2.1281 (2.2639) time: 0.4998 [2021-03-26 20:27:51 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 540/1251] eta: 0:06:03 lr: 0.000161 loss: 3.0328 (2.9597) grad_norm: 2.1231 (2.2622) time: 0.5022 [2021-03-26 20:27:56 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 550/1251] eta: 0:05:58 lr: 0.000161 loss: 2.8569 (2.9573) grad_norm: 2.1548 (2.2610) time: 0.5129 [2021-03-26 20:28:01 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 560/1251] eta: 0:05:52 lr: 0.000161 loss: 3.0239 (2.9627) grad_norm: 2.2309 (2.2682) time: 0.5143 [2021-03-26 20:28:06 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 570/1251] eta: 0:05:47 lr: 0.000161 loss: 3.3032 (2.9666) grad_norm: 2.4144 (2.2713) time: 0.5049 [2021-03-26 20:28:11 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 580/1251] eta: 0:05:42 lr: 0.000161 loss: 3.2032 (2.9657) grad_norm: 2.3785 (2.2780) time: 0.5016 [2021-03-26 20:28:16 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 590/1251] eta: 0:05:37 lr: 0.000161 loss: 3.0994 (2.9640) grad_norm: 2.3559 (2.2802) time: 0.5027 [2021-03-26 20:28:21 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 600/1251] eta: 0:05:32 lr: 0.000161 loss: 3.1254 (2.9656) grad_norm: 2.2606 (2.2779) time: 0.4995 [2021-03-26 20:28:26 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 610/1251] eta: 0:05:26 lr: 0.000161 loss: 3.1989 (2.9681) grad_norm: 2.2000 (2.2770) time: 0.4971 [2021-03-26 20:28:31 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 620/1251] eta: 0:05:21 lr: 0.000161 loss: 3.1581 (2.9697) grad_norm: 2.2472 (2.2768) time: 0.4957 [2021-03-26 20:28:36 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 630/1251] eta: 0:05:16 lr: 0.000161 loss: 3.0379 (2.9717) grad_norm: 2.2244 (2.2774) time: 0.4993 [2021-03-26 20:28:41 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 640/1251] eta: 0:05:11 lr: 0.000160 loss: 3.0379 (2.9718) grad_norm: 2.1302 (2.2748) time: 0.5026 [2021-03-26 20:28:46 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 650/1251] eta: 0:05:06 lr: 0.000160 loss: 2.9954 (2.9707) grad_norm: 2.0683 (2.2712) time: 0.5015 [2021-03-26 20:28:51 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 660/1251] eta: 0:05:00 lr: 0.000160 loss: 3.1229 (2.9712) grad_norm: 2.0299 (2.2685) time: 0.5036 [2021-03-26 20:28:56 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 670/1251] eta: 0:04:55 lr: 0.000160 loss: 3.1229 (2.9701) grad_norm: 2.0363 (2.2665) time: 0.5023 [2021-03-26 20:29:01 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 680/1251] eta: 0:04:50 lr: 0.000160 loss: 3.0257 (2.9704) grad_norm: 2.1137 (2.2646) time: 0.4976 [2021-03-26 20:29:06 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 690/1251] eta: 0:04:45 lr: 0.000160 loss: 3.0003 (2.9702) grad_norm: 2.2310 (2.2653) time: 0.4969 [2021-03-26 20:29:11 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 700/1251] eta: 0:04:40 lr: 0.000160 loss: 3.1123 (2.9743) grad_norm: 2.2738 (2.2656) time: 0.5030 [2021-03-26 20:29:16 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 710/1251] eta: 0:04:35 lr: 0.000160 loss: 3.2707 (2.9756) grad_norm: 2.1335 (2.2658) time: 0.5007 [2021-03-26 20:29:21 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 720/1251] eta: 0:04:29 lr: 0.000160 loss: 3.2388 (2.9748) grad_norm: 2.2393 (2.2685) time: 0.4980 [2021-03-26 20:29:26 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 730/1251] eta: 0:04:24 lr: 0.000160 loss: 3.1605 (2.9771) grad_norm: 2.2438 (2.2696) time: 0.5051 [2021-03-26 20:29:32 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 740/1251] eta: 0:04:19 lr: 0.000160 loss: 2.9617 (2.9725) grad_norm: 2.2438 (2.2724) time: 0.5187 [2021-03-26 20:29:36 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 750/1251] eta: 0:04:14 lr: 0.000160 loss: 2.8630 (2.9725) grad_norm: 2.2360 (2.2730) time: 0.5098 [2021-03-26 20:29:42 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 760/1251] eta: 0:04:09 lr: 0.000160 loss: 3.1521 (2.9741) grad_norm: 2.3353 (2.2752) time: 0.5095 [2021-03-26 20:29:47 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 770/1251] eta: 0:04:04 lr: 0.000160 loss: 2.9262 (2.9728) grad_norm: 2.1842 (2.2752) time: 0.5107 [2021-03-26 20:29:52 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 780/1251] eta: 0:03:59 lr: 0.000160 loss: 2.8800 (2.9718) grad_norm: 2.1308 (2.2736) time: 0.4979 [2021-03-26 20:29:57 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 790/1251] eta: 0:03:54 lr: 0.000160 loss: 2.8001 (2.9671) grad_norm: 2.1850 (2.2738) time: 0.5033 [2021-03-26 20:30:02 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 800/1251] eta: 0:03:49 lr: 0.000160 loss: 2.7912 (2.9661) grad_norm: 2.0685 (2.2737) time: 0.5033 [2021-03-26 20:30:07 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 810/1251] eta: 0:03:44 lr: 0.000160 loss: 2.8430 (2.9650) grad_norm: 2.0384 (2.2715) time: 0.4985 [2021-03-26 20:30:12 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 820/1251] eta: 0:03:39 lr: 0.000160 loss: 2.8186 (2.9629) grad_norm: 2.1822 (2.2716) time: 0.5006 [2021-03-26 20:30:17 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 830/1251] eta: 0:03:33 lr: 0.000160 loss: 2.8186 (2.9624) grad_norm: 2.2707 (2.2718) time: 0.5022 [2021-03-26 20:30:22 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 840/1251] eta: 0:03:28 lr: 0.000160 loss: 2.9093 (2.9624) grad_norm: 2.3036 (2.2719) time: 0.4958 [2021-03-26 20:30:27 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 850/1251] eta: 0:03:23 lr: 0.000160 loss: 2.9093 (2.9629) grad_norm: 2.1748 (2.2717) time: 0.5001 [2021-03-26 20:30:32 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 860/1251] eta: 0:03:18 lr: 0.000160 loss: 2.9754 (2.9628) grad_norm: 2.1558 (2.2699) time: 0.5180 [2021-03-26 20:30:37 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 870/1251] eta: 0:03:13 lr: 0.000160 loss: 3.0619 (2.9635) grad_norm: 2.0949 (2.2679) time: 0.5147 [2021-03-26 20:30:42 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 880/1251] eta: 0:03:08 lr: 0.000160 loss: 3.0297 (2.9621) grad_norm: 2.1206 (2.2687) time: 0.5016 [2021-03-26 20:30:47 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 890/1251] eta: 0:03:03 lr: 0.000160 loss: 2.8779 (2.9619) grad_norm: 2.2844 (2.2697) time: 0.5011 [2021-03-26 20:30:52 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 900/1251] eta: 0:02:58 lr: 0.000160 loss: 2.9331 (2.9614) grad_norm: 2.2739 (2.2693) time: 0.4990 [2021-03-26 20:30:57 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 910/1251] eta: 0:02:53 lr: 0.000160 loss: 3.1294 (2.9635) grad_norm: 2.1456 (2.2690) time: 0.4952 [2021-03-26 20:31:02 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 920/1251] eta: 0:02:47 lr: 0.000160 loss: 3.1292 (2.9615) grad_norm: 2.1505 (2.2680) time: 0.4980 [2021-03-26 20:31:07 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 930/1251] eta: 0:02:42 lr: 0.000160 loss: 2.9902 (2.9627) grad_norm: 2.2478 (2.2695) time: 0.5017 [2021-03-26 20:31:12 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 940/1251] eta: 0:02:37 lr: 0.000160 loss: 3.0150 (2.9617) grad_norm: 2.2064 (2.2684) time: 0.4963 [2021-03-26 20:31:17 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 950/1251] eta: 0:02:32 lr: 0.000160 loss: 3.0150 (2.9607) grad_norm: 2.1290 (2.2687) time: 0.5047 [2021-03-26 20:31:22 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 960/1251] eta: 0:02:27 lr: 0.000160 loss: 3.0339 (2.9618) grad_norm: 2.2076 (2.2681) time: 0.5041 [2021-03-26 20:31:27 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 970/1251] eta: 0:02:22 lr: 0.000159 loss: 3.2219 (2.9641) grad_norm: 2.1850 (2.2683) time: 0.4962 [2021-03-26 20:31:32 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 980/1251] eta: 0:02:17 lr: 0.000159 loss: 3.1125 (2.9623) grad_norm: 2.1283 (2.2676) time: 0.5082 [2021-03-26 20:31:37 swin_small_patch4_window7_224] INFO: Epoch: [223] [ 990/1251] eta: 0:02:12 lr: 0.000159 loss: 3.1083 (2.9648) grad_norm: 2.2305 (2.2673) time: 0.5075 [2021-03-26 20:31:42 swin_small_patch4_window7_224] INFO: Epoch: [223] [1000/1251] eta: 0:02:07 lr: 0.000159 loss: 3.1692 (2.9664) grad_norm: 2.2420 (2.2665) time: 0.4997 [2021-03-26 20:31:47 swin_small_patch4_window7_224] INFO: Epoch: [223] [1010/1251] eta: 0:02:02 lr: 0.000159 loss: 3.1692 (2.9685) grad_norm: 2.1203 (2.2656) time: 0.4998 [2021-03-26 20:31:52 swin_small_patch4_window7_224] INFO: Epoch: [223] [1020/1251] eta: 0:01:57 lr: 0.000159 loss: 3.1632 (2.9698) grad_norm: 2.1200 (2.2702) time: 0.4993 [2021-03-26 20:31:57 swin_small_patch4_window7_224] INFO: Epoch: [223] [1030/1251] eta: 0:01:52 lr: 0.000159 loss: 3.0744 (2.9703) grad_norm: 2.1163 (2.2686) time: 0.4959 [2021-03-26 20:32:02 swin_small_patch4_window7_224] INFO: Epoch: [223] [1040/1251] eta: 0:01:46 lr: 0.000159 loss: 2.9717 (2.9693) grad_norm: 2.0853 (2.2669) time: 0.4955 [2021-03-26 20:32:07 swin_small_patch4_window7_224] INFO: Epoch: [223] [1050/1251] eta: 0:01:41 lr: 0.000159 loss: 2.8052 (2.9665) grad_norm: 2.1133 (2.2656) time: 0.5037 [2021-03-26 20:32:12 swin_small_patch4_window7_224] INFO: Epoch: [223] [1060/1251] eta: 0:01:36 lr: 0.000159 loss: 2.8052 (2.9660) grad_norm: 2.1723 (2.2649) time: 0.5099 [2021-03-26 20:32:17 swin_small_patch4_window7_224] INFO: Epoch: [223] [1070/1251] eta: 0:01:31 lr: 0.000159 loss: 3.0234 (2.9674) grad_norm: 2.1062 (2.2630) time: 0.5036 [2021-03-26 20:32:22 swin_small_patch4_window7_224] INFO: Epoch: [223] [1080/1251] eta: 0:01:26 lr: 0.000159 loss: 3.0442 (2.9684) grad_norm: 2.0789 (2.2620) time: 0.4923 [2021-03-26 20:32:27 swin_small_patch4_window7_224] INFO: Epoch: [223] [1090/1251] eta: 0:01:21 lr: 0.000159 loss: 2.9345 (2.9677) grad_norm: 2.1589 (2.2614) time: 0.4917 [2021-03-26 20:32:32 swin_small_patch4_window7_224] INFO: Epoch: [223] [1100/1251] eta: 0:01:16 lr: 0.000159 loss: 2.9345 (2.9670) grad_norm: 2.1589 (2.2609) time: 0.4972 [2021-03-26 20:32:37 swin_small_patch4_window7_224] INFO: Epoch: [223] [1110/1251] eta: 0:01:11 lr: 0.000159 loss: 2.8861 (2.9640) grad_norm: 2.1827 (2.2610) time: 0.4985 [2021-03-26 20:32:42 swin_small_patch4_window7_224] INFO: Epoch: [223] [1120/1251] eta: 0:01:06 lr: 0.000159 loss: 2.8870 (2.9638) grad_norm: 2.1827 (2.2607) time: 0.4970 [2021-03-26 20:32:47 swin_small_patch4_window7_224] INFO: Epoch: [223] [1130/1251] eta: 0:01:01 lr: 0.000159 loss: 2.9550 (2.9648) grad_norm: 2.1823 (2.2605) time: 0.4983 [2021-03-26 20:32:52 swin_small_patch4_window7_224] INFO: Epoch: [223] [1140/1251] eta: 0:00:56 lr: 0.000159 loss: 3.0281 (2.9646) grad_norm: 2.1823 (2.2601) time: 0.4997 [2021-03-26 20:32:57 swin_small_patch4_window7_224] INFO: Epoch: [223] [1150/1251] eta: 0:00:51 lr: 0.000159 loss: 3.0281 (2.9650) grad_norm: 2.1864 (2.2597) time: 0.4981 [2021-03-26 20:33:02 swin_small_patch4_window7_224] INFO: Epoch: [223] [1160/1251] eta: 0:00:46 lr: 0.000159 loss: 2.8119 (2.9624) grad_norm: 2.2349 (2.2601) time: 0.5007 [2021-03-26 20:33:07 swin_small_patch4_window7_224] INFO: Epoch: [223] [1170/1251] eta: 0:00:40 lr: 0.000159 loss: 2.8119 (2.9609) grad_norm: 2.1781 (2.2601) time: 0.5043 [2021-03-26 20:33:12 swin_small_patch4_window7_224] INFO: Epoch: [223] [1180/1251] eta: 0:00:35 lr: 0.000159 loss: 3.1481 (2.9628) grad_norm: 2.2747 (2.2623) time: 0.5032 [2021-03-26 20:33:17 swin_small_patch4_window7_224] INFO: Epoch: [223] [1190/1251] eta: 0:00:30 lr: 0.000159 loss: 3.1600 (2.9624) grad_norm: 2.4144 (2.2631) time: 0.5002 [2021-03-26 20:33:22 swin_small_patch4_window7_224] INFO: Epoch: [223] [1200/1251] eta: 0:00:25 lr: 0.000159 loss: 2.9239 (2.9615) grad_norm: 2.2819 (2.2636) time: 0.5046 [2021-03-26 20:33:27 swin_small_patch4_window7_224] INFO: Epoch: [223] [1210/1251] eta: 0:00:20 lr: 0.000159 loss: 2.9486 (2.9630) grad_norm: 2.2819 (2.2639) time: 0.5116 [2021-03-26 20:33:32 swin_small_patch4_window7_224] INFO: Epoch: [223] [1220/1251] eta: 0:00:15 lr: 0.000159 loss: 3.1480 (2.9642) grad_norm: 2.3536 (2.2648) time: 0.5057 [2021-03-26 20:33:37 swin_small_patch4_window7_224] INFO: Epoch: [223] [1230/1251] eta: 0:00:10 lr: 0.000159 loss: 3.1079 (2.9635) grad_norm: 2.3154 (2.2651) time: 0.5032 [2021-03-26 20:33:42 swin_small_patch4_window7_224] INFO: Epoch: [223] [1240/1251] eta: 0:00:05 lr: 0.000159 loss: 2.8973 (2.9624) grad_norm: 2.1262 (2.2647) time: 0.4997 [2021-03-26 20:33:47 swin_small_patch4_window7_224] INFO: Epoch: [223] [1250/1251] eta: 0:00:00 lr: 0.000159 loss: 3.0256 (2.9636) grad_norm: 2.0895 (2.2634) time: 0.5006 [2021-03-26 20:33:59 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 1.0109 (1.0109) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-26 20:34:01 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8037 (0.7685) acc1: 81.2500 (81.6761) acc5: 95.3125 (95.5966) [2021-03-26 20:34:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7922 (0.7935) acc1: 81.2500 (80.9524) acc5: 95.3125 (95.6101) [2021-03-26 20:34:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7225 (0.7554) acc1: 82.8125 (81.6028) acc5: 96.8750 (96.1190) [2021-03-26 20:34:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6848 (0.7645) acc1: 81.2500 (81.4024) acc5: 96.8750 (96.0366) [2021-03-26 20:34:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8040 (0.7934) acc1: 79.6875 (80.8000) acc5: 95.3125 (95.7120) [2021-03-26 20:34:17 swin_small_patch4_window7_224] INFO: * Acc@1 81.572 Acc@5 95.766 loss 0.780 [2021-03-26 20:34:17 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.6% [2021-03-26 20:34:17 swin_small_patch4_window7_224] INFO: Max accuracy: 81.57% [2021-03-26 20:34:21 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 0/1251] eta: 1:28:46 lr: 0.000159 loss: 2.8863 (2.8863) grad_norm: 1.8518 (1.8518) time: 4.2575 [2021-03-26 20:34:26 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 10/1251] eta: 0:17:43 lr: 0.000159 loss: 3.0863 (2.9964) grad_norm: 2.1009 (2.1543) time: 0.8572 [2021-03-26 20:34:31 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 20/1251] eta: 0:14:04 lr: 0.000159 loss: 3.0885 (3.0137) grad_norm: 2.2058 (2.2096) time: 0.5077 [2021-03-26 20:34:36 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 30/1251] eta: 0:12:45 lr: 0.000159 loss: 3.2016 (2.9836) grad_norm: 2.2058 (2.2305) time: 0.4997 [2021-03-26 20:34:41 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 40/1251] eta: 0:11:59 lr: 0.000159 loss: 3.0803 (2.9759) grad_norm: 2.2926 (2.2523) time: 0.4982 [2021-03-26 20:34:46 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 50/1251] eta: 0:11:34 lr: 0.000159 loss: 3.0803 (2.9940) grad_norm: 2.3804 (2.2757) time: 0.5028 [2021-03-26 20:34:51 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 60/1251] eta: 0:11:15 lr: 0.000158 loss: 3.1177 (3.0148) grad_norm: 2.3036 (2.2720) time: 0.5102 [2021-03-26 20:34:56 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 70/1251] eta: 0:10:58 lr: 0.000158 loss: 3.0049 (2.9844) grad_norm: 2.2793 (2.3138) time: 0.5040 [2021-03-26 20:35:01 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 80/1251] eta: 0:10:43 lr: 0.000158 loss: 2.9309 (3.0085) grad_norm: 2.1992 (2.2936) time: 0.4958 [2021-03-26 20:35:06 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 90/1251] eta: 0:10:30 lr: 0.000158 loss: 3.0029 (2.9898) grad_norm: 2.1677 (2.3112) time: 0.4944 [2021-03-26 20:35:11 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 100/1251] eta: 0:10:20 lr: 0.000158 loss: 3.0088 (2.9995) grad_norm: 2.2257 (2.3043) time: 0.4981 [2021-03-26 20:35:16 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 110/1251] eta: 0:10:12 lr: 0.000158 loss: 3.1382 (2.9998) grad_norm: 2.1666 (2.2989) time: 0.5045 [2021-03-26 20:35:21 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 120/1251] eta: 0:10:03 lr: 0.000158 loss: 3.1382 (3.0019) grad_norm: 2.2584 (2.2997) time: 0.5055 [2021-03-26 20:35:26 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 130/1251] eta: 0:09:56 lr: 0.000158 loss: 3.0628 (2.9858) grad_norm: 2.2611 (2.2946) time: 0.5094 [2021-03-26 20:35:31 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 140/1251] eta: 0:09:49 lr: 0.000158 loss: 2.8291 (2.9629) grad_norm: 2.2116 (2.2932) time: 0.5101 [2021-03-26 20:35:36 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 150/1251] eta: 0:09:42 lr: 0.000158 loss: 2.8452 (2.9563) grad_norm: 2.2647 (2.3054) time: 0.5061 [2021-03-26 20:35:41 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 160/1251] eta: 0:09:35 lr: 0.000158 loss: 2.5067 (2.9289) grad_norm: 2.3729 (2.3137) time: 0.5052 [2021-03-26 20:35:46 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 170/1251] eta: 0:09:28 lr: 0.000158 loss: 2.4999 (2.9212) grad_norm: 2.1474 (2.3091) time: 0.5008 [2021-03-26 20:35:52 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 180/1251] eta: 0:09:22 lr: 0.000158 loss: 2.4999 (2.8932) grad_norm: 2.2529 (2.3076) time: 0.5054 [2021-03-26 20:35:57 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 190/1251] eta: 0:09:15 lr: 0.000158 loss: 2.7357 (2.8957) grad_norm: 2.2602 (2.3207) time: 0.5087 [2021-03-26 20:36:02 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 200/1251] eta: 0:09:08 lr: 0.000158 loss: 3.0275 (2.8982) grad_norm: 2.1042 (2.3096) time: 0.5002 [2021-03-26 20:36:07 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 210/1251] eta: 0:09:02 lr: 0.000158 loss: 3.0888 (2.9062) grad_norm: 2.1510 (2.3043) time: 0.4975 [2021-03-26 20:36:12 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 220/1251] eta: 0:08:56 lr: 0.000158 loss: 3.0382 (2.8968) grad_norm: 2.2829 (2.3316) time: 0.5059 [2021-03-26 20:36:17 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 230/1251] eta: 0:08:51 lr: 0.000158 loss: 2.7880 (2.8967) grad_norm: 2.3558 (2.3323) time: 0.5090 [2021-03-26 20:36:22 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 240/1251] eta: 0:08:45 lr: 0.000158 loss: 2.9659 (2.9048) grad_norm: 2.2291 (2.3308) time: 0.5128 [2021-03-26 20:36:27 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 250/1251] eta: 0:08:40 lr: 0.000158 loss: 3.2225 (2.9078) grad_norm: 2.2279 (2.3260) time: 0.5156 [2021-03-26 20:36:32 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 260/1251] eta: 0:08:34 lr: 0.000158 loss: 2.9049 (2.9068) grad_norm: 2.1146 (2.3214) time: 0.5101 [2021-03-26 20:36:37 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 270/1251] eta: 0:08:28 lr: 0.000158 loss: 3.1161 (2.9201) grad_norm: 2.1163 (2.3222) time: 0.5042 [2021-03-26 20:36:42 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 280/1251] eta: 0:08:22 lr: 0.000158 loss: 3.1161 (2.9235) grad_norm: 2.1716 (2.3187) time: 0.4999 [2021-03-26 20:36:47 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 290/1251] eta: 0:08:17 lr: 0.000158 loss: 3.1133 (2.9299) grad_norm: 2.1716 (2.3244) time: 0.4989 [2021-03-26 20:36:52 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 300/1251] eta: 0:08:11 lr: 0.000158 loss: 3.1054 (2.9309) grad_norm: 2.3161 (2.3238) time: 0.5026 [2021-03-26 20:36:57 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 310/1251] eta: 0:08:06 lr: 0.000158 loss: 3.1054 (2.9358) grad_norm: 2.1866 (2.3206) time: 0.5047 [2021-03-26 20:37:02 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 320/1251] eta: 0:08:00 lr: 0.000158 loss: 3.3776 (2.9495) grad_norm: 2.1866 (2.3177) time: 0.5004 [2021-03-26 20:37:07 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 330/1251] eta: 0:07:54 lr: 0.000158 loss: 3.2652 (2.9491) grad_norm: 2.1577 (2.3136) time: 0.4981 [2021-03-26 20:37:12 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 340/1251] eta: 0:07:48 lr: 0.000158 loss: 3.0952 (2.9461) grad_norm: 2.0885 (2.3069) time: 0.4953 [2021-03-26 20:37:17 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 350/1251] eta: 0:07:43 lr: 0.000158 loss: 2.8252 (2.9393) grad_norm: 2.0768 (2.3030) time: 0.4995 [2021-03-26 20:37:22 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 360/1251] eta: 0:07:37 lr: 0.000158 loss: 2.8491 (2.9380) grad_norm: 2.0766 (2.2973) time: 0.5013 [2021-03-26 20:37:27 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 370/1251] eta: 0:07:32 lr: 0.000158 loss: 2.8724 (2.9431) grad_norm: 2.1040 (2.2951) time: 0.4963 [2021-03-26 20:37:32 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 380/1251] eta: 0:07:26 lr: 0.000158 loss: 3.0218 (2.9409) grad_norm: 2.1757 (2.2987) time: 0.4978 [2021-03-26 20:37:37 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 390/1251] eta: 0:07:21 lr: 0.000158 loss: 3.0079 (2.9425) grad_norm: 2.1538 (2.2932) time: 0.4972 [2021-03-26 20:37:42 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 400/1251] eta: 0:07:16 lr: 0.000157 loss: 2.9845 (2.9430) grad_norm: 2.1570 (2.2960) time: 0.4969 [2021-03-26 20:37:47 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 410/1251] eta: 0:07:10 lr: 0.000157 loss: 2.9100 (2.9425) grad_norm: 2.3608 (2.2983) time: 0.4999 [2021-03-26 20:37:52 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 420/1251] eta: 0:07:05 lr: 0.000157 loss: 3.0555 (2.9456) grad_norm: 2.2062 (2.2956) time: 0.5021 [2021-03-26 20:37:57 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 430/1251] eta: 0:07:00 lr: 0.000157 loss: 2.8167 (2.9394) grad_norm: 2.1050 (2.2936) time: 0.5072 [2021-03-26 20:38:02 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 440/1251] eta: 0:06:54 lr: 0.000157 loss: 2.6674 (2.9407) grad_norm: 2.1179 (2.2904) time: 0.5071 [2021-03-26 20:38:07 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 450/1251] eta: 0:06:49 lr: 0.000157 loss: 3.1558 (2.9470) grad_norm: 2.2266 (2.2967) time: 0.5002 [2021-03-26 20:38:12 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 460/1251] eta: 0:06:44 lr: 0.000157 loss: 3.1657 (2.9505) grad_norm: 2.3282 (2.2978) time: 0.4969 [2021-03-26 20:38:17 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 470/1251] eta: 0:06:38 lr: 0.000157 loss: 3.3171 (2.9573) grad_norm: 2.3503 (2.2979) time: 0.4970 [2021-03-26 20:38:22 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 480/1251] eta: 0:06:33 lr: 0.000157 loss: 3.0780 (2.9540) grad_norm: 2.3318 (2.3008) time: 0.4990 [2021-03-26 20:38:27 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 490/1251] eta: 0:06:28 lr: 0.000157 loss: 2.7804 (2.9543) grad_norm: 2.3243 (2.3003) time: 0.5031 [2021-03-26 20:38:32 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 500/1251] eta: 0:06:23 lr: 0.000157 loss: 3.1295 (2.9561) grad_norm: 2.2146 (2.2988) time: 0.5007 [2021-03-26 20:38:37 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 510/1251] eta: 0:06:17 lr: 0.000157 loss: 2.9916 (2.9571) grad_norm: 2.2146 (2.2976) time: 0.4977 [2021-03-26 20:38:42 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 520/1251] eta: 0:06:12 lr: 0.000157 loss: 2.8423 (2.9579) grad_norm: 2.2766 (2.2979) time: 0.4973 [2021-03-26 20:38:47 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 530/1251] eta: 0:06:07 lr: 0.000157 loss: 2.9649 (2.9576) grad_norm: 2.2738 (2.2954) time: 0.4979 [2021-03-26 20:38:52 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 540/1251] eta: 0:06:02 lr: 0.000157 loss: 3.0622 (2.9620) grad_norm: 2.2091 (2.2961) time: 0.5019 [2021-03-26 20:38:57 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 550/1251] eta: 0:05:57 lr: 0.000157 loss: 3.0935 (2.9636) grad_norm: 2.1383 (2.2932) time: 0.5112 [2021-03-26 20:39:02 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 560/1251] eta: 0:05:51 lr: 0.000157 loss: 2.7554 (2.9588) grad_norm: 2.1517 (2.2921) time: 0.5094 [2021-03-26 20:39:07 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 570/1251] eta: 0:05:46 lr: 0.000157 loss: 2.9149 (2.9631) grad_norm: 2.2070 (2.2909) time: 0.4973 [2021-03-26 20:39:12 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 580/1251] eta: 0:05:41 lr: 0.000157 loss: 3.1495 (2.9624) grad_norm: 2.3246 (2.2948) time: 0.5008 [2021-03-26 20:39:17 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 590/1251] eta: 0:05:36 lr: 0.000157 loss: 2.8960 (2.9628) grad_norm: 2.4017 (2.2949) time: 0.5045 [2021-03-26 20:39:22 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 600/1251] eta: 0:05:31 lr: 0.000157 loss: 2.9762 (2.9635) grad_norm: 2.3226 (2.2951) time: 0.4996 [2021-03-26 20:39:27 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 610/1251] eta: 0:05:26 lr: 0.000157 loss: 2.8766 (2.9630) grad_norm: 2.2829 (2.2968) time: 0.5037 [2021-03-26 20:39:33 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 620/1251] eta: 0:05:20 lr: 0.000157 loss: 2.7323 (2.9568) grad_norm: 2.2829 (2.2983) time: 0.5062 [2021-03-26 20:39:37 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 630/1251] eta: 0:05:15 lr: 0.000157 loss: 2.9605 (2.9585) grad_norm: 2.1814 (2.2971) time: 0.4980 [2021-03-26 20:39:42 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 640/1251] eta: 0:05:10 lr: 0.000157 loss: 2.9879 (2.9575) grad_norm: 2.2768 (2.2986) time: 0.4975 [2021-03-26 20:39:47 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 650/1251] eta: 0:05:05 lr: 0.000157 loss: 2.9140 (2.9577) grad_norm: 2.2674 (2.2967) time: 0.4988 [2021-03-26 20:39:52 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 660/1251] eta: 0:05:00 lr: 0.000157 loss: 3.2204 (2.9589) grad_norm: 2.2674 (2.2979) time: 0.4969 [2021-03-26 20:39:57 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 670/1251] eta: 0:04:55 lr: 0.000157 loss: 3.2642 (2.9641) grad_norm: 2.2570 (2.2970) time: 0.5007 [2021-03-26 20:40:03 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 680/1251] eta: 0:04:50 lr: 0.000157 loss: 3.3314 (2.9665) grad_norm: 2.1802 (2.2962) time: 0.5065 [2021-03-26 20:40:08 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 690/1251] eta: 0:04:44 lr: 0.000157 loss: 3.3471 (2.9689) grad_norm: 2.2903 (2.2989) time: 0.5035 [2021-03-26 20:40:13 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 700/1251] eta: 0:04:39 lr: 0.000157 loss: 3.0475 (2.9674) grad_norm: 2.4857 (2.3012) time: 0.5043 [2021-03-26 20:40:18 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 710/1251] eta: 0:04:34 lr: 0.000157 loss: 2.9723 (2.9672) grad_norm: 2.4754 (2.3027) time: 0.5018 [2021-03-26 20:40:23 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 720/1251] eta: 0:04:29 lr: 0.000157 loss: 2.9723 (2.9677) grad_norm: 2.2249 (2.3055) time: 0.4949 [2021-03-26 20:40:28 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 730/1251] eta: 0:04:24 lr: 0.000157 loss: 2.9415 (2.9654) grad_norm: 2.1969 (2.3059) time: 0.5036 [2021-03-26 20:40:33 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 740/1251] eta: 0:04:19 lr: 0.000156 loss: 2.9371 (2.9651) grad_norm: 2.1969 (2.3053) time: 0.5172 [2021-03-26 20:40:38 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 750/1251] eta: 0:04:14 lr: 0.000156 loss: 2.8362 (2.9621) grad_norm: 2.3006 (2.3049) time: 0.5104 [2021-03-26 20:40:43 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 760/1251] eta: 0:04:09 lr: 0.000156 loss: 2.5869 (2.9593) grad_norm: 2.3209 (2.3064) time: 0.5031 [2021-03-26 20:40:48 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 770/1251] eta: 0:04:04 lr: 0.000156 loss: 2.5869 (2.9581) grad_norm: 2.2393 (2.3056) time: 0.5090 [2021-03-26 20:40:53 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 780/1251] eta: 0:03:59 lr: 0.000156 loss: 2.8778 (2.9571) grad_norm: 2.2207 (2.3047) time: 0.5078 [2021-03-26 20:40:58 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 790/1251] eta: 0:03:53 lr: 0.000156 loss: 2.7479 (2.9550) grad_norm: 2.2639 (2.3054) time: 0.5021 [2021-03-26 20:41:03 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 800/1251] eta: 0:03:48 lr: 0.000156 loss: 2.7880 (2.9527) grad_norm: 2.2729 (2.3054) time: 0.5037 [2021-03-26 20:41:08 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 810/1251] eta: 0:03:43 lr: 0.000156 loss: 3.0336 (2.9529) grad_norm: 2.2270 (2.3040) time: 0.5060 [2021-03-26 20:41:13 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 820/1251] eta: 0:03:38 lr: 0.000156 loss: 3.0336 (2.9522) grad_norm: 2.2270 (2.3040) time: 0.4977 [2021-03-26 20:41:18 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 830/1251] eta: 0:03:33 lr: 0.000156 loss: 3.0090 (2.9548) grad_norm: 2.2563 (2.3031) time: 0.4952 [2021-03-26 20:41:23 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 840/1251] eta: 0:03:28 lr: 0.000156 loss: 3.1077 (2.9552) grad_norm: 2.2563 (2.3035) time: 0.4998 [2021-03-26 20:41:28 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 850/1251] eta: 0:03:23 lr: 0.000156 loss: 3.0487 (2.9556) grad_norm: 2.3074 (2.3037) time: 0.5053 [2021-03-26 20:41:33 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 860/1251] eta: 0:03:18 lr: 0.000156 loss: 3.0487 (2.9561) grad_norm: 2.1917 (2.3038) time: 0.5037 [2021-03-26 20:41:38 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 870/1251] eta: 0:03:13 lr: 0.000156 loss: 3.1195 (2.9574) grad_norm: 2.3213 (2.3041) time: 0.5025 [2021-03-26 20:41:43 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 880/1251] eta: 0:03:08 lr: 0.000156 loss: 3.1645 (2.9590) grad_norm: 2.2152 (2.3031) time: 0.5030 [2021-03-26 20:41:48 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 890/1251] eta: 0:03:03 lr: 0.000156 loss: 2.9045 (2.9582) grad_norm: 2.2181 (2.3038) time: 0.5103 [2021-03-26 20:41:54 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 900/1251] eta: 0:02:57 lr: 0.000156 loss: 3.0520 (2.9604) grad_norm: 2.2842 (2.3053) time: 0.5118 [2021-03-26 20:41:58 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 910/1251] eta: 0:02:52 lr: 0.000156 loss: 3.0247 (2.9578) grad_norm: 2.2189 (2.3040) time: 0.5004 [2021-03-26 20:42:04 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 920/1251] eta: 0:02:47 lr: 0.000156 loss: 3.0006 (2.9590) grad_norm: 2.0755 (2.3013) time: 0.5004 [2021-03-26 20:42:09 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 930/1251] eta: 0:02:42 lr: 0.000156 loss: 3.0191 (2.9567) grad_norm: 2.0983 (2.3033) time: 0.5081 [2021-03-26 20:42:14 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 940/1251] eta: 0:02:37 lr: 0.000156 loss: 2.8936 (2.9560) grad_norm: 2.1611 (2.3018) time: 0.5083 [2021-03-26 20:42:19 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 950/1251] eta: 0:02:32 lr: 0.000156 loss: 3.1404 (2.9577) grad_norm: 2.2395 (2.3010) time: 0.5028 [2021-03-26 20:42:24 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 960/1251] eta: 0:02:27 lr: 0.000156 loss: 3.1980 (2.9594) grad_norm: 2.2298 (2.3004) time: 0.5041 [2021-03-26 20:42:29 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 970/1251] eta: 0:02:22 lr: 0.000156 loss: 3.1411 (2.9585) grad_norm: 2.1538 (2.2993) time: 0.5034 [2021-03-26 20:42:34 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 980/1251] eta: 0:02:17 lr: 0.000156 loss: 2.9699 (2.9574) grad_norm: 2.1765 (2.2983) time: 0.5107 [2021-03-26 20:42:39 swin_small_patch4_window7_224] INFO: Epoch: [224] [ 990/1251] eta: 0:02:12 lr: 0.000156 loss: 3.0719 (2.9596) grad_norm: 2.1380 (2.2964) time: 0.5144 [2021-03-26 20:42:44 swin_small_patch4_window7_224] INFO: Epoch: [224] [1000/1251] eta: 0:02:07 lr: 0.000156 loss: 2.9973 (2.9580) grad_norm: 2.0265 (2.2943) time: 0.5049 [2021-03-26 20:42:49 swin_small_patch4_window7_224] INFO: Epoch: [224] [1010/1251] eta: 0:02:02 lr: 0.000156 loss: 2.7187 (2.9570) grad_norm: 2.0296 (2.2938) time: 0.5010 [2021-03-26 20:42:54 swin_small_patch4_window7_224] INFO: Epoch: [224] [1020/1251] eta: 0:01:57 lr: 0.000156 loss: 2.9555 (2.9567) grad_norm: 2.1982 (2.2932) time: 0.5001 [2021-03-26 20:42:59 swin_small_patch4_window7_224] INFO: Epoch: [224] [1030/1251] eta: 0:01:51 lr: 0.000156 loss: 3.1096 (2.9567) grad_norm: 2.1258 (2.2934) time: 0.4975 [2021-03-26 20:43:04 swin_small_patch4_window7_224] INFO: Epoch: [224] [1040/1251] eta: 0:01:46 lr: 0.000156 loss: 2.9631 (2.9566) grad_norm: 2.1598 (nan) time: 0.5012 [2021-03-26 20:43:09 swin_small_patch4_window7_224] INFO: Epoch: [224] [1050/1251] eta: 0:01:41 lr: 0.000156 loss: 2.9631 (2.9574) grad_norm: 2.1764 (nan) time: 0.5044 [2021-03-26 20:43:14 swin_small_patch4_window7_224] INFO: Epoch: [224] [1060/1251] eta: 0:01:36 lr: 0.000156 loss: 3.0881 (2.9590) grad_norm: 2.1654 (nan) time: 0.4996 [2021-03-26 20:43:19 swin_small_patch4_window7_224] INFO: Epoch: [224] [1070/1251] eta: 0:01:31 lr: 0.000156 loss: 2.7815 (2.9556) grad_norm: 2.3016 (nan) time: 0.5000 [2021-03-26 20:43:24 swin_small_patch4_window7_224] INFO: Epoch: [224] [1080/1251] eta: 0:01:26 lr: 0.000155 loss: 2.7815 (2.9566) grad_norm: 2.2983 (nan) time: 0.5018 [2021-03-26 20:43:29 swin_small_patch4_window7_224] INFO: Epoch: [224] [1090/1251] eta: 0:01:21 lr: 0.000155 loss: 2.9837 (2.9542) grad_norm: 2.1447 (nan) time: 0.4984 [2021-03-26 20:43:34 swin_small_patch4_window7_224] INFO: Epoch: [224] [1100/1251] eta: 0:01:16 lr: 0.000155 loss: 2.8287 (2.9551) grad_norm: 2.2424 (nan) time: 0.4971 [2021-03-26 20:43:39 swin_small_patch4_window7_224] INFO: Epoch: [224] [1110/1251] eta: 0:01:11 lr: 0.000155 loss: 3.0806 (2.9544) grad_norm: 2.2737 (nan) time: 0.4981 [2021-03-26 20:43:44 swin_small_patch4_window7_224] INFO: Epoch: [224] [1120/1251] eta: 0:01:06 lr: 0.000155 loss: 2.6714 (2.9520) grad_norm: 2.1782 (nan) time: 0.4990 [2021-03-26 20:43:49 swin_small_patch4_window7_224] INFO: Epoch: [224] [1130/1251] eta: 0:01:01 lr: 0.000155 loss: 2.7201 (2.9517) grad_norm: 2.1151 (nan) time: 0.5056 [2021-03-26 20:43:54 swin_small_patch4_window7_224] INFO: Epoch: [224] [1140/1251] eta: 0:00:56 lr: 0.000155 loss: 2.9814 (2.9524) grad_norm: 2.2137 (nan) time: 0.5052 [2021-03-26 20:43:59 swin_small_patch4_window7_224] INFO: Epoch: [224] [1150/1251] eta: 0:00:51 lr: 0.000155 loss: 3.0036 (2.9534) grad_norm: 2.2809 (nan) time: 0.4976 [2021-03-26 20:44:04 swin_small_patch4_window7_224] INFO: Epoch: [224] [1160/1251] eta: 0:00:46 lr: 0.000155 loss: 3.0036 (2.9530) grad_norm: 2.2380 (nan) time: 0.4987 [2021-03-26 20:44:09 swin_small_patch4_window7_224] INFO: Epoch: [224] [1170/1251] eta: 0:00:40 lr: 0.000155 loss: 3.0997 (2.9533) grad_norm: 2.1908 (nan) time: 0.5086 [2021-03-26 20:44:14 swin_small_patch4_window7_224] INFO: Epoch: [224] [1180/1251] eta: 0:00:35 lr: 0.000155 loss: 3.0316 (2.9535) grad_norm: 2.1191 (nan) time: 0.5079 [2021-03-26 20:44:19 swin_small_patch4_window7_224] INFO: Epoch: [224] [1190/1251] eta: 0:00:30 lr: 0.000155 loss: 2.8459 (2.9517) grad_norm: 2.1174 (nan) time: 0.4989 [2021-03-26 20:44:24 swin_small_patch4_window7_224] INFO: Epoch: [224] [1200/1251] eta: 0:00:25 lr: 0.000155 loss: 2.8409 (2.9517) grad_norm: 2.1613 (nan) time: 0.4961 [2021-03-26 20:44:29 swin_small_patch4_window7_224] INFO: Epoch: [224] [1210/1251] eta: 0:00:20 lr: 0.000155 loss: 2.9533 (2.9523) grad_norm: 2.1006 (nan) time: 0.4958 [2021-03-26 20:44:34 swin_small_patch4_window7_224] INFO: Epoch: [224] [1220/1251] eta: 0:00:15 lr: 0.000155 loss: 2.9506 (2.9514) grad_norm: 2.1860 (nan) time: 0.4995 [2021-03-26 20:44:39 swin_small_patch4_window7_224] INFO: Epoch: [224] [1230/1251] eta: 0:00:10 lr: 0.000155 loss: 2.9506 (2.9514) grad_norm: 2.2100 (nan) time: 0.5031 [2021-03-26 20:44:44 swin_small_patch4_window7_224] INFO: Epoch: [224] [1240/1251] eta: 0:00:05 lr: 0.000155 loss: 3.0222 (2.9516) grad_norm: 2.2723 (nan) time: 0.5069 [2021-03-26 20:44:50 swin_small_patch4_window7_224] INFO: Epoch: [224] [1250/1251] eta: 0:00:00 lr: 0.000155 loss: 3.0061 (2.9495) grad_norm: 2.2189 (nan) time: 0.5114 [2021-03-26 20:45:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 0.6750 (0.6750) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-26 20:45:08 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7243 (0.7648) acc1: 81.2500 (79.8295) acc5: 96.8750 (97.1591) [2021-03-26 20:45:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7243 (0.7771) acc1: 81.2500 (80.2083) acc5: 96.8750 (96.7262) [2021-03-26 20:45:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7082 (0.7877) acc1: 81.2500 (80.8972) acc5: 95.3125 (96.2702) [2021-03-26 20:45:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7169 (0.7832) acc1: 81.2500 (81.1738) acc5: 95.3125 (95.9985) [2021-03-26 20:45:15 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7818 (0.7838) acc1: 81.2500 (80.9280) acc5: 95.3125 (95.9680) [2021-03-26 20:45:25 swin_small_patch4_window7_224] INFO: * Acc@1 81.588 Acc@5 95.796 loss 0.775 [2021-03-26 20:45:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.6% [2021-03-26 20:45:25 swin_small_patch4_window7_224] INFO: Max accuracy: 81.59% [2021-03-26 20:45:29 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 0/1251] eta: 1:21:35 lr: 0.000155 loss: 2.2418 (2.2418) grad_norm: 2.1359 (2.1359) time: 3.9131 [2021-03-26 20:45:34 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 10/1251] eta: 0:17:29 lr: 0.000155 loss: 3.0801 (2.8718) grad_norm: 2.2399 (2.3130) time: 0.8454 [2021-03-26 20:45:39 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 20/1251] eta: 0:13:58 lr: 0.000155 loss: 3.0607 (2.7779) grad_norm: 2.3212 (2.3135) time: 0.5194 [2021-03-26 20:45:44 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 30/1251] eta: 0:12:42 lr: 0.000155 loss: 2.5223 (2.7499) grad_norm: 2.3167 (2.3873) time: 0.5034 [2021-03-26 20:45:49 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 40/1251] eta: 0:12:00 lr: 0.000155 loss: 2.7292 (2.7249) grad_norm: 2.1426 (2.3520) time: 0.5048 [2021-03-26 20:45:54 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 50/1251] eta: 0:11:30 lr: 0.000155 loss: 2.7652 (2.7654) grad_norm: 2.1426 (2.3894) time: 0.4980 [2021-03-26 20:45:59 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 60/1251] eta: 0:11:12 lr: 0.000155 loss: 3.0415 (2.8303) grad_norm: 2.1826 (2.3582) time: 0.5024 [2021-03-26 20:46:04 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 70/1251] eta: 0:10:55 lr: 0.000155 loss: 2.9392 (2.8038) grad_norm: 2.2637 (2.3517) time: 0.5034 [2021-03-26 20:46:09 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 80/1251] eta: 0:10:42 lr: 0.000155 loss: 2.7077 (2.8083) grad_norm: 2.2309 (2.3414) time: 0.5012 [2021-03-26 20:46:14 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 90/1251] eta: 0:10:30 lr: 0.000155 loss: 3.0345 (2.8211) grad_norm: 2.1888 (2.3236) time: 0.5019 [2021-03-26 20:46:19 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 100/1251] eta: 0:10:20 lr: 0.000155 loss: 3.0345 (2.8409) grad_norm: 2.2035 (2.3141) time: 0.4995 [2021-03-26 20:46:25 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 110/1251] eta: 0:10:12 lr: 0.000155 loss: 3.0053 (2.8457) grad_norm: 2.1684 (2.3051) time: 0.5078 [2021-03-26 20:46:30 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 120/1251] eta: 0:10:04 lr: 0.000155 loss: 2.8368 (2.8547) grad_norm: 2.2188 (2.3022) time: 0.5097 [2021-03-26 20:46:35 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 130/1251] eta: 0:09:56 lr: 0.000155 loss: 2.8700 (2.8510) grad_norm: 2.2255 (2.2933) time: 0.5086 [2021-03-26 20:46:40 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 140/1251] eta: 0:09:48 lr: 0.000155 loss: 2.8913 (2.8545) grad_norm: 2.2028 (2.2916) time: 0.5035 [2021-03-26 20:46:45 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 150/1251] eta: 0:09:41 lr: 0.000155 loss: 2.9534 (2.8596) grad_norm: 2.1055 (2.2860) time: 0.4980 [2021-03-26 20:46:50 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 160/1251] eta: 0:09:34 lr: 0.000155 loss: 2.9534 (2.8528) grad_norm: 2.1276 (2.2863) time: 0.5015 [2021-03-26 20:46:55 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 170/1251] eta: 0:09:27 lr: 0.000154 loss: 2.9581 (2.8601) grad_norm: 2.2209 (2.2920) time: 0.5039 [2021-03-26 20:47:00 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 180/1251] eta: 0:09:21 lr: 0.000154 loss: 2.8166 (2.8510) grad_norm: 2.2600 (2.2876) time: 0.5035 [2021-03-26 20:47:05 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 190/1251] eta: 0:09:14 lr: 0.000154 loss: 2.9213 (2.8541) grad_norm: 2.2520 (2.2900) time: 0.4978 [2021-03-26 20:47:10 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 200/1251] eta: 0:09:08 lr: 0.000154 loss: 3.0232 (2.8638) grad_norm: 2.2511 (2.2956) time: 0.5057 [2021-03-26 20:47:15 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 210/1251] eta: 0:09:02 lr: 0.000154 loss: 3.0537 (2.8695) grad_norm: 2.2511 (2.2958) time: 0.5141 [2021-03-26 20:47:20 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 220/1251] eta: 0:08:57 lr: 0.000154 loss: 2.9843 (2.8681) grad_norm: 2.2041 (2.2902) time: 0.5106 [2021-03-26 20:47:25 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 230/1251] eta: 0:08:51 lr: 0.000154 loss: 2.9719 (2.8733) grad_norm: 2.2634 (2.2936) time: 0.5079 [2021-03-26 20:47:30 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 240/1251] eta: 0:08:45 lr: 0.000154 loss: 2.9972 (2.8798) grad_norm: 2.2584 (2.2923) time: 0.5020 [2021-03-26 20:47:35 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 250/1251] eta: 0:08:39 lr: 0.000154 loss: 2.9515 (2.8848) grad_norm: 2.1708 (2.2867) time: 0.5033 [2021-03-26 20:47:40 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 260/1251] eta: 0:08:34 lr: 0.000154 loss: 2.9215 (2.8897) grad_norm: 2.1996 (2.2865) time: 0.5097 [2021-03-26 20:47:45 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 270/1251] eta: 0:08:28 lr: 0.000154 loss: 3.0208 (2.8882) grad_norm: 2.2690 (2.2907) time: 0.5076 [2021-03-26 20:47:50 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 280/1251] eta: 0:08:22 lr: 0.000154 loss: 2.8581 (2.8825) grad_norm: 2.2468 (2.2872) time: 0.4977 [2021-03-26 20:47:55 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 290/1251] eta: 0:08:16 lr: 0.000154 loss: 2.7360 (2.8770) grad_norm: 2.1592 (2.2857) time: 0.4947 [2021-03-26 20:48:00 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 300/1251] eta: 0:08:10 lr: 0.000154 loss: 2.7360 (2.8738) grad_norm: 2.2458 (2.2839) time: 0.4984 [2021-03-26 20:48:05 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 310/1251] eta: 0:08:05 lr: 0.000154 loss: 2.7722 (2.8650) grad_norm: 2.3133 (2.2851) time: 0.5024 [2021-03-26 20:48:10 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 320/1251] eta: 0:07:59 lr: 0.000154 loss: 2.7392 (2.8630) grad_norm: 2.3767 (2.2870) time: 0.5067 [2021-03-26 20:48:15 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 330/1251] eta: 0:07:54 lr: 0.000154 loss: 2.6856 (2.8570) grad_norm: 2.2303 (2.2866) time: 0.5000 [2021-03-26 20:48:20 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 340/1251] eta: 0:07:48 lr: 0.000154 loss: 2.6825 (2.8521) grad_norm: 2.1433 (2.2853) time: 0.4940 [2021-03-26 20:48:25 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 350/1251] eta: 0:07:43 lr: 0.000154 loss: 2.8549 (2.8535) grad_norm: 2.1781 (2.2834) time: 0.5015 [2021-03-26 20:48:30 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 360/1251] eta: 0:07:37 lr: 0.000154 loss: 2.8886 (2.8532) grad_norm: 2.1781 (2.2824) time: 0.5072 [2021-03-26 20:48:36 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 370/1251] eta: 0:07:32 lr: 0.000154 loss: 2.6647 (2.8494) grad_norm: 2.2852 (2.2851) time: 0.5098 [2021-03-26 20:48:41 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 380/1251] eta: 0:07:27 lr: 0.000154 loss: 2.9947 (2.8523) grad_norm: 2.3008 (2.2868) time: 0.5053 [2021-03-26 20:48:46 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 390/1251] eta: 0:07:21 lr: 0.000154 loss: 3.0621 (2.8585) grad_norm: 2.2562 (2.2871) time: 0.5014 [2021-03-26 20:48:51 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 400/1251] eta: 0:07:16 lr: 0.000154 loss: 3.0621 (2.8577) grad_norm: 2.1338 (2.2832) time: 0.5028 [2021-03-26 20:48:56 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 410/1251] eta: 0:07:10 lr: 0.000154 loss: 3.0151 (2.8619) grad_norm: 2.2271 (2.2948) time: 0.4961 [2021-03-26 20:49:01 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 420/1251] eta: 0:07:05 lr: 0.000154 loss: 3.0460 (2.8670) grad_norm: 2.5433 (2.3061) time: 0.4983 [2021-03-26 20:49:06 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 430/1251] eta: 0:07:00 lr: 0.000154 loss: 3.0838 (2.8728) grad_norm: 2.4702 (2.3168) time: 0.5039 [2021-03-26 20:49:11 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 440/1251] eta: 0:06:54 lr: 0.000154 loss: 3.1353 (2.8764) grad_norm: 2.2072 (2.3132) time: 0.5023 [2021-03-26 20:49:16 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 450/1251] eta: 0:06:49 lr: 0.000154 loss: 3.0195 (2.8773) grad_norm: 2.1620 (2.3116) time: 0.5061 [2021-03-26 20:49:21 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 460/1251] eta: 0:06:44 lr: 0.000154 loss: 2.9351 (2.8802) grad_norm: 2.1459 (2.3088) time: 0.5042 [2021-03-26 20:49:26 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 470/1251] eta: 0:06:39 lr: 0.000154 loss: 2.9218 (2.8786) grad_norm: 2.0550 (2.3071) time: 0.4994 [2021-03-26 20:49:31 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 480/1251] eta: 0:06:33 lr: 0.000154 loss: 2.8861 (2.8813) grad_norm: 2.1979 (2.3081) time: 0.4996 [2021-03-26 20:49:36 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 490/1251] eta: 0:06:28 lr: 0.000154 loss: 2.8861 (2.8796) grad_norm: 2.1985 (2.3060) time: 0.5010 [2021-03-26 20:49:41 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 500/1251] eta: 0:06:23 lr: 0.000154 loss: 2.9910 (2.8786) grad_norm: 2.0980 (2.3029) time: 0.4999 [2021-03-26 20:49:46 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 510/1251] eta: 0:06:18 lr: 0.000153 loss: 3.0401 (2.8767) grad_norm: 2.1508 (2.3011) time: 0.4980 [2021-03-26 20:49:51 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 520/1251] eta: 0:06:12 lr: 0.000153 loss: 2.9987 (2.8811) grad_norm: 2.2396 (2.3037) time: 0.4983 [2021-03-26 20:49:56 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 530/1251] eta: 0:06:07 lr: 0.000153 loss: 2.9987 (2.8804) grad_norm: 2.1585 (2.3012) time: 0.5022 [2021-03-26 20:50:01 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 540/1251] eta: 0:06:02 lr: 0.000153 loss: 2.8956 (2.8793) grad_norm: 2.0960 (2.3007) time: 0.5068 [2021-03-26 20:50:06 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 550/1251] eta: 0:05:57 lr: 0.000153 loss: 3.0995 (2.8842) grad_norm: 2.2044 (2.3016) time: 0.5214 [2021-03-26 20:50:11 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 560/1251] eta: 0:05:52 lr: 0.000153 loss: 3.0325 (2.8827) grad_norm: 2.3096 (2.3017) time: 0.5165 [2021-03-26 20:50:16 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 570/1251] eta: 0:05:47 lr: 0.000153 loss: 3.0343 (2.8861) grad_norm: 2.2934 (2.3014) time: 0.4965 [2021-03-26 20:50:21 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 580/1251] eta: 0:05:41 lr: 0.000153 loss: 3.0450 (2.8843) grad_norm: 2.2140 (2.3013) time: 0.4970 [2021-03-26 20:50:26 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 590/1251] eta: 0:05:36 lr: 0.000153 loss: 2.9339 (2.8850) grad_norm: 2.2779 (2.3021) time: 0.5031 [2021-03-26 20:50:31 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 600/1251] eta: 0:05:31 lr: 0.000153 loss: 2.9465 (2.8857) grad_norm: 2.2661 (2.3001) time: 0.5072 [2021-03-26 20:50:36 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 610/1251] eta: 0:05:26 lr: 0.000153 loss: 3.0684 (2.8881) grad_norm: 2.1363 (2.2973) time: 0.5060 [2021-03-26 20:50:41 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 620/1251] eta: 0:05:21 lr: 0.000153 loss: 3.0515 (2.8900) grad_norm: 2.2278 (2.2982) time: 0.5056 [2021-03-26 20:50:46 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 630/1251] eta: 0:05:16 lr: 0.000153 loss: 3.0087 (2.8904) grad_norm: 2.2428 (2.2965) time: 0.5068 [2021-03-26 20:50:51 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 640/1251] eta: 0:05:11 lr: 0.000153 loss: 3.0498 (2.8915) grad_norm: 2.1793 (2.2957) time: 0.5000 [2021-03-26 20:50:56 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 650/1251] eta: 0:05:05 lr: 0.000153 loss: 3.0743 (2.8916) grad_norm: 2.2154 (2.2981) time: 0.5000 [2021-03-26 20:51:01 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 660/1251] eta: 0:05:00 lr: 0.000153 loss: 2.8928 (2.8926) grad_norm: 2.2154 (2.2969) time: 0.5064 [2021-03-26 20:51:06 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 670/1251] eta: 0:04:55 lr: 0.000153 loss: 2.9579 (2.8957) grad_norm: 2.2011 (2.2969) time: 0.5021 [2021-03-26 20:51:12 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 680/1251] eta: 0:04:50 lr: 0.000153 loss: 3.1194 (2.8963) grad_norm: 2.3014 (2.2986) time: 0.5022 [2021-03-26 20:51:17 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 690/1251] eta: 0:04:45 lr: 0.000153 loss: 3.2064 (2.9002) grad_norm: 2.2894 (2.2999) time: 0.5048 [2021-03-26 20:51:22 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 700/1251] eta: 0:04:40 lr: 0.000153 loss: 3.2232 (2.8976) grad_norm: 2.2708 (2.2999) time: 0.5013 [2021-03-26 20:51:26 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 710/1251] eta: 0:04:35 lr: 0.000153 loss: 3.1162 (2.9013) grad_norm: 2.2310 (2.2993) time: 0.4953 [2021-03-26 20:51:31 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 720/1251] eta: 0:04:29 lr: 0.000153 loss: 3.2346 (2.9044) grad_norm: 2.2409 (2.2985) time: 0.4957 [2021-03-26 20:51:37 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 730/1251] eta: 0:04:24 lr: 0.000153 loss: 3.0433 (2.9028) grad_norm: 2.2025 (2.2962) time: 0.5015 [2021-03-26 20:51:42 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 740/1251] eta: 0:04:19 lr: 0.000153 loss: 3.0433 (2.9047) grad_norm: 2.1088 (2.2942) time: 0.5122 [2021-03-26 20:51:47 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 750/1251] eta: 0:04:14 lr: 0.000153 loss: 3.1204 (2.9064) grad_norm: 2.1447 (2.2936) time: 0.5191 [2021-03-26 20:51:52 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 760/1251] eta: 0:04:09 lr: 0.000153 loss: 3.0550 (2.9046) grad_norm: 2.1141 (2.2913) time: 0.5065 [2021-03-26 20:51:57 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 770/1251] eta: 0:04:04 lr: 0.000153 loss: 2.8392 (2.9018) grad_norm: 2.1392 (2.2899) time: 0.4975 [2021-03-26 20:52:02 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 780/1251] eta: 0:03:59 lr: 0.000153 loss: 2.8392 (2.9007) grad_norm: 2.1655 (2.2886) time: 0.5002 [2021-03-26 20:52:07 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 790/1251] eta: 0:03:54 lr: 0.000153 loss: 2.9636 (2.9012) grad_norm: 2.1655 (2.2898) time: 0.5084 [2021-03-26 20:52:12 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 800/1251] eta: 0:03:49 lr: 0.000153 loss: 3.1310 (2.9040) grad_norm: 2.1612 (2.2890) time: 0.5079 [2021-03-26 20:52:17 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 810/1251] eta: 0:03:44 lr: 0.000153 loss: 3.1359 (2.9076) grad_norm: 2.1335 (2.2882) time: 0.4996 [2021-03-26 20:52:22 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 820/1251] eta: 0:03:38 lr: 0.000153 loss: 3.0228 (2.9060) grad_norm: 2.1281 (2.2863) time: 0.5038 [2021-03-26 20:52:27 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 830/1251] eta: 0:03:33 lr: 0.000153 loss: 3.0123 (2.9070) grad_norm: 2.0134 (2.2840) time: 0.5044 [2021-03-26 20:52:32 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 840/1251] eta: 0:03:28 lr: 0.000153 loss: 3.0967 (2.9092) grad_norm: 2.1351 (2.2835) time: 0.4974 [2021-03-26 20:52:37 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 850/1251] eta: 0:03:23 lr: 0.000153 loss: 3.0967 (2.9109) grad_norm: 2.1038 (2.2825) time: 0.4967 [2021-03-26 20:52:42 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 860/1251] eta: 0:03:18 lr: 0.000152 loss: 3.0132 (2.9092) grad_norm: 2.1029 (2.2830) time: 0.5038 [2021-03-26 20:52:47 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 870/1251] eta: 0:03:13 lr: 0.000152 loss: 2.7527 (2.9090) grad_norm: 2.1197 (2.2814) time: 0.5072 [2021-03-26 20:52:52 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 880/1251] eta: 0:03:08 lr: 0.000152 loss: 3.0437 (2.9107) grad_norm: 2.0496 (2.2856) time: 0.5014 [2021-03-26 20:52:57 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 890/1251] eta: 0:03:03 lr: 0.000152 loss: 2.9142 (2.9089) grad_norm: 2.0701 (2.2844) time: 0.4974 [2021-03-26 20:53:02 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 900/1251] eta: 0:02:58 lr: 0.000152 loss: 2.8304 (2.9086) grad_norm: 2.1052 (2.2833) time: 0.4987 [2021-03-26 20:53:07 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 910/1251] eta: 0:02:52 lr: 0.000152 loss: 3.1110 (2.9123) grad_norm: 2.1245 (2.2826) time: 0.4998 [2021-03-26 20:53:12 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 920/1251] eta: 0:02:47 lr: 0.000152 loss: 3.1071 (2.9133) grad_norm: 2.1584 (2.2813) time: 0.5112 [2021-03-26 20:53:17 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 930/1251] eta: 0:02:42 lr: 0.000152 loss: 3.0706 (2.9153) grad_norm: 2.2395 (2.2826) time: 0.5137 [2021-03-26 20:53:23 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 940/1251] eta: 0:02:37 lr: 0.000152 loss: 3.0673 (2.9160) grad_norm: 2.3088 (2.2833) time: 0.5078 [2021-03-26 20:53:28 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 950/1251] eta: 0:02:32 lr: 0.000152 loss: 2.9845 (2.9175) grad_norm: 2.2878 (2.2840) time: 0.5091 [2021-03-26 20:53:33 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 960/1251] eta: 0:02:27 lr: 0.000152 loss: 2.7833 (2.9143) grad_norm: 2.3051 (2.2850) time: 0.5004 [2021-03-26 20:53:38 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 970/1251] eta: 0:02:22 lr: 0.000152 loss: 2.6652 (2.9153) grad_norm: 2.2429 (2.2850) time: 0.4994 [2021-03-26 20:53:43 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 980/1251] eta: 0:02:17 lr: 0.000152 loss: 3.2931 (2.9169) grad_norm: 2.2301 (2.2859) time: 0.5043 [2021-03-26 20:53:48 swin_small_patch4_window7_224] INFO: Epoch: [225] [ 990/1251] eta: 0:02:12 lr: 0.000152 loss: 2.9752 (2.9158) grad_norm: 2.3224 (2.2865) time: 0.5035 [2021-03-26 20:53:53 swin_small_patch4_window7_224] INFO: Epoch: [225] [1000/1251] eta: 0:02:07 lr: 0.000152 loss: 2.9272 (2.9171) grad_norm: 2.2509 (2.2865) time: 0.5038 [2021-03-26 20:53:58 swin_small_patch4_window7_224] INFO: Epoch: [225] [1010/1251] eta: 0:02:02 lr: 0.000152 loss: 2.9528 (2.9181) grad_norm: 2.1421 (2.2861) time: 0.5045 [2021-03-26 20:54:03 swin_small_patch4_window7_224] INFO: Epoch: [225] [1020/1251] eta: 0:01:57 lr: 0.000152 loss: 3.0965 (2.9197) grad_norm: 2.2016 (2.2854) time: 0.4987 [2021-03-26 20:54:08 swin_small_patch4_window7_224] INFO: Epoch: [225] [1030/1251] eta: 0:01:52 lr: 0.000152 loss: 3.0849 (2.9197) grad_norm: 2.1841 (2.2844) time: 0.5037 [2021-03-26 20:54:13 swin_small_patch4_window7_224] INFO: Epoch: [225] [1040/1251] eta: 0:01:46 lr: 0.000152 loss: 3.0372 (2.9205) grad_norm: 2.0991 (2.2841) time: 0.5024 [2021-03-26 20:54:18 swin_small_patch4_window7_224] INFO: Epoch: [225] [1050/1251] eta: 0:01:41 lr: 0.000152 loss: 3.0697 (2.9210) grad_norm: 2.2472 (2.2841) time: 0.5018 [2021-03-26 20:54:23 swin_small_patch4_window7_224] INFO: Epoch: [225] [1060/1251] eta: 0:01:36 lr: 0.000152 loss: 2.9700 (2.9201) grad_norm: 2.2706 (2.2845) time: 0.5126 [2021-03-26 20:54:28 swin_small_patch4_window7_224] INFO: Epoch: [225] [1070/1251] eta: 0:01:31 lr: 0.000152 loss: 2.9597 (2.9206) grad_norm: 2.3086 (2.2864) time: 0.5047 [2021-03-26 20:54:33 swin_small_patch4_window7_224] INFO: Epoch: [225] [1080/1251] eta: 0:01:26 lr: 0.000152 loss: 3.1572 (2.9236) grad_norm: 2.3030 (2.2862) time: 0.4982 [2021-03-26 20:54:38 swin_small_patch4_window7_224] INFO: Epoch: [225] [1090/1251] eta: 0:01:21 lr: 0.000152 loss: 3.1735 (2.9241) grad_norm: 2.1399 (2.2859) time: 0.4989 [2021-03-26 20:54:43 swin_small_patch4_window7_224] INFO: Epoch: [225] [1100/1251] eta: 0:01:16 lr: 0.000152 loss: 2.9995 (2.9256) grad_norm: 2.2633 (2.2858) time: 0.5079 [2021-03-26 20:54:48 swin_small_patch4_window7_224] INFO: Epoch: [225] [1110/1251] eta: 0:01:11 lr: 0.000152 loss: 2.9275 (2.9248) grad_norm: 2.2739 (2.2857) time: 0.5113 [2021-03-26 20:54:53 swin_small_patch4_window7_224] INFO: Epoch: [225] [1120/1251] eta: 0:01:06 lr: 0.000152 loss: 2.8562 (2.9231) grad_norm: 2.1204 (2.2847) time: 0.5018 [2021-03-26 20:54:58 swin_small_patch4_window7_224] INFO: Epoch: [225] [1130/1251] eta: 0:01:01 lr: 0.000152 loss: 2.9636 (2.9230) grad_norm: 2.1816 (2.2849) time: 0.4937 [2021-03-26 20:55:03 swin_small_patch4_window7_224] INFO: Epoch: [225] [1140/1251] eta: 0:00:56 lr: 0.000152 loss: 2.8569 (2.9213) grad_norm: 2.1567 (2.2844) time: 0.4925 [2021-03-26 20:55:08 swin_small_patch4_window7_224] INFO: Epoch: [225] [1150/1251] eta: 0:00:51 lr: 0.000152 loss: 3.0937 (2.9234) grad_norm: 2.1550 (2.2842) time: 0.5008 [2021-03-26 20:55:13 swin_small_patch4_window7_224] INFO: Epoch: [225] [1160/1251] eta: 0:00:46 lr: 0.000152 loss: 3.1708 (2.9250) grad_norm: 2.1835 (2.2834) time: 0.5073 [2021-03-26 20:55:18 swin_small_patch4_window7_224] INFO: Epoch: [225] [1170/1251] eta: 0:00:41 lr: 0.000152 loss: 3.0551 (2.9242) grad_norm: 2.1835 (2.2825) time: 0.5008 [2021-03-26 20:55:23 swin_small_patch4_window7_224] INFO: Epoch: [225] [1180/1251] eta: 0:00:35 lr: 0.000152 loss: 3.0551 (2.9263) grad_norm: 2.2610 (2.2853) time: 0.4962 [2021-03-26 20:55:28 swin_small_patch4_window7_224] INFO: Epoch: [225] [1190/1251] eta: 0:00:30 lr: 0.000152 loss: 3.0913 (2.9262) grad_norm: 2.3323 (2.2846) time: 0.4938 [2021-03-26 20:55:33 swin_small_patch4_window7_224] INFO: Epoch: [225] [1200/1251] eta: 0:00:25 lr: 0.000151 loss: 2.8488 (2.9253) grad_norm: 2.1464 (2.2844) time: 0.5031 [2021-03-26 20:55:38 swin_small_patch4_window7_224] INFO: Epoch: [225] [1210/1251] eta: 0:00:20 lr: 0.000151 loss: 2.8521 (2.9242) grad_norm: 2.1718 (2.2837) time: 0.5113 [2021-03-26 20:55:43 swin_small_patch4_window7_224] INFO: Epoch: [225] [1220/1251] eta: 0:00:15 lr: 0.000151 loss: 3.0084 (2.9257) grad_norm: 2.1718 (2.2836) time: 0.5005 [2021-03-26 20:55:48 swin_small_patch4_window7_224] INFO: Epoch: [225] [1230/1251] eta: 0:00:10 lr: 0.000151 loss: 2.8850 (2.9250) grad_norm: 2.2025 (2.2830) time: 0.4982 [2021-03-26 20:55:53 swin_small_patch4_window7_224] INFO: Epoch: [225] [1240/1251] eta: 0:00:05 lr: 0.000151 loss: 3.0606 (2.9272) grad_norm: 2.1738 (2.2823) time: 0.5002 [2021-03-26 20:55:58 swin_small_patch4_window7_224] INFO: Epoch: [225] [1250/1251] eta: 0:00:00 lr: 0.000151 loss: 3.2209 (2.9279) grad_norm: 2.2010 (2.2830) time: 0.5060 [2021-03-26 20:56:44 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 0.8738 (0.8738) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-26 20:56:45 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.8239 (0.8031) acc1: 81.2500 (80.6818) acc5: 95.3125 (95.8807) [2021-03-26 20:56:46 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7702 (0.7726) acc1: 81.2500 (81.5476) acc5: 96.8750 (96.5030) [2021-03-26 20:56:47 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7568 (0.7642) acc1: 82.8125 (81.8548) acc5: 96.8750 (96.4718) [2021-03-26 20:56:48 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7642 (0.7976) acc1: 81.2500 (81.0595) acc5: 95.3125 (95.9223) [2021-03-26 20:56:49 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8188 (0.7964) acc1: 81.1321 (81.1200) acc5: 95.3125 (95.7760) [2021-03-26 20:56:58 swin_small_patch4_window7_224] INFO: * Acc@1 81.532 Acc@5 95.808 loss 0.787 [2021-03-26 20:56:58 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.5% [2021-03-26 20:56:58 swin_small_patch4_window7_224] INFO: Max accuracy: 81.59% [2021-03-26 20:57:03 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 0/1251] eta: 1:41:37 lr: 0.000151 loss: 3.1073 (3.1073) grad_norm: 2.2045 (2.2045) time: 4.8745 [2021-03-26 20:57:08 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 10/1251] eta: 0:18:43 lr: 0.000151 loss: 3.0915 (2.8820) grad_norm: 2.2122 (2.2611) time: 0.9054 [2021-03-26 20:57:13 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 20/1251] eta: 0:14:42 lr: 0.000151 loss: 2.7444 (2.7620) grad_norm: 2.2207 (2.2940) time: 0.5089 [2021-03-26 20:57:18 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 30/1251] eta: 0:13:08 lr: 0.000151 loss: 2.8896 (2.8333) grad_norm: 2.2207 (2.2812) time: 0.5034 [2021-03-26 20:57:23 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 40/1251] eta: 0:12:17 lr: 0.000151 loss: 2.9780 (2.8531) grad_norm: 2.2330 (2.3890) time: 0.4955 [2021-03-26 20:57:28 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 50/1251] eta: 0:11:48 lr: 0.000151 loss: 3.1044 (2.8941) grad_norm: 2.2775 (2.3813) time: 0.5028 [2021-03-26 20:57:33 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 60/1251] eta: 0:11:23 lr: 0.000151 loss: 2.9709 (2.8487) grad_norm: 2.2645 (2.3718) time: 0.5033 [2021-03-26 20:57:38 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 70/1251] eta: 0:11:06 lr: 0.000151 loss: 2.9508 (2.8764) grad_norm: 2.3229 (2.3619) time: 0.4996 [2021-03-26 20:57:43 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 80/1251] eta: 0:10:52 lr: 0.000151 loss: 2.9798 (2.8724) grad_norm: 2.2784 (2.3518) time: 0.5048 [2021-03-26 20:57:48 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 90/1251] eta: 0:10:42 lr: 0.000151 loss: 2.9798 (2.8963) grad_norm: 2.2030 (2.3615) time: 0.5130 [2021-03-26 20:57:53 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 100/1251] eta: 0:10:31 lr: 0.000151 loss: 3.0679 (2.8879) grad_norm: 2.2791 (2.3781) time: 0.5126 [2021-03-26 20:57:58 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 110/1251] eta: 0:10:20 lr: 0.000151 loss: 3.1324 (2.8978) grad_norm: 2.3752 (2.3803) time: 0.5015 [2021-03-26 20:58:03 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 120/1251] eta: 0:10:11 lr: 0.000151 loss: 3.2120 (2.9162) grad_norm: 2.3416 (2.3761) time: 0.5018 [2021-03-26 20:58:08 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 130/1251] eta: 0:10:02 lr: 0.000151 loss: 3.1921 (2.9118) grad_norm: 2.2223 (2.3746) time: 0.5033 [2021-03-26 20:58:13 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 140/1251] eta: 0:09:54 lr: 0.000151 loss: 3.1672 (2.9209) grad_norm: 2.3750 (2.3790) time: 0.5017 [2021-03-26 20:58:18 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 150/1251] eta: 0:09:46 lr: 0.000151 loss: 3.1672 (2.9144) grad_norm: 2.2963 (2.3678) time: 0.5021 [2021-03-26 20:58:23 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 160/1251] eta: 0:09:38 lr: 0.000151 loss: 2.9469 (2.9136) grad_norm: 2.2061 (2.3600) time: 0.4993 [2021-03-26 20:58:28 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 170/1251] eta: 0:09:31 lr: 0.000151 loss: 3.0462 (2.9294) grad_norm: 2.1901 (2.3502) time: 0.4953 [2021-03-26 20:58:33 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 180/1251] eta: 0:09:25 lr: 0.000151 loss: 3.1113 (2.9344) grad_norm: 2.1266 (2.3397) time: 0.5031 [2021-03-26 20:58:38 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 190/1251] eta: 0:09:18 lr: 0.000151 loss: 3.0047 (2.9318) grad_norm: 2.1507 (2.3299) time: 0.5054 [2021-03-26 20:58:43 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 200/1251] eta: 0:09:12 lr: 0.000151 loss: 2.9704 (2.9325) grad_norm: 2.1396 (2.3226) time: 0.5082 [2021-03-26 20:58:48 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 210/1251] eta: 0:09:05 lr: 0.000151 loss: 2.6727 (2.9178) grad_norm: 2.0978 (2.3101) time: 0.5054 [2021-03-26 20:58:53 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 220/1251] eta: 0:08:59 lr: 0.000151 loss: 2.6105 (2.9063) grad_norm: 2.1688 (2.3080) time: 0.4953 [2021-03-26 20:58:58 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 230/1251] eta: 0:08:52 lr: 0.000151 loss: 2.8223 (2.9066) grad_norm: 2.2121 (2.3072) time: 0.4952 [2021-03-26 20:59:03 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 240/1251] eta: 0:08:46 lr: 0.000151 loss: 3.0564 (2.9053) grad_norm: 2.2121 (2.3044) time: 0.4963 [2021-03-26 20:59:08 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 250/1251] eta: 0:08:40 lr: 0.000151 loss: 3.0602 (2.9073) grad_norm: 2.2272 (2.3021) time: 0.5020 [2021-03-26 20:59:13 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 260/1251] eta: 0:08:34 lr: 0.000151 loss: 2.9233 (2.9068) grad_norm: 2.2103 (2.2972) time: 0.4995 [2021-03-26 20:59:18 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 270/1251] eta: 0:08:28 lr: 0.000151 loss: 3.0039 (2.9129) grad_norm: 2.1798 (2.2999) time: 0.4952 [2021-03-26 20:59:23 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 280/1251] eta: 0:08:22 lr: 0.000151 loss: 3.2129 (2.9226) grad_norm: 2.1789 (2.2988) time: 0.4978 [2021-03-26 20:59:28 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 290/1251] eta: 0:08:16 lr: 0.000150 loss: 3.0347 (2.9158) grad_norm: 2.1789 (2.2984) time: 0.5022 [2021-03-26 20:59:33 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 300/1251] eta: 0:08:11 lr: 0.000150 loss: 2.9052 (2.9198) grad_norm: 2.1532 (2.3078) time: 0.5026 [2021-03-26 20:59:38 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 310/1251] eta: 0:08:05 lr: 0.000150 loss: 3.1033 (2.9275) grad_norm: 2.1052 (2.3047) time: 0.5008 [2021-03-26 20:59:43 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 320/1251] eta: 0:08:00 lr: 0.000150 loss: 3.1065 (2.9313) grad_norm: 2.1624 (2.3012) time: 0.5025 [2021-03-26 20:59:48 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 330/1251] eta: 0:07:54 lr: 0.000150 loss: 3.0203 (2.9292) grad_norm: 2.2028 (2.2996) time: 0.5049 [2021-03-26 20:59:53 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 340/1251] eta: 0:07:49 lr: 0.000150 loss: 2.6174 (2.9223) grad_norm: 2.2481 (2.3030) time: 0.5041 [2021-03-26 20:59:58 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 350/1251] eta: 0:07:43 lr: 0.000150 loss: 3.1151 (2.9305) grad_norm: 2.2761 (2.3049) time: 0.5060 [2021-03-26 21:00:03 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 360/1251] eta: 0:07:38 lr: 0.000150 loss: 3.0903 (2.9285) grad_norm: 2.2619 (2.3041) time: 0.5015 [2021-03-26 21:00:08 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 370/1251] eta: 0:07:32 lr: 0.000150 loss: 2.9372 (2.9265) grad_norm: 2.2619 (2.3037) time: 0.4953 [2021-03-26 21:00:14 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 380/1251] eta: 0:07:27 lr: 0.000150 loss: 2.7870 (2.9206) grad_norm: 2.2691 (2.3027) time: 0.5043 [2021-03-26 21:00:19 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 390/1251] eta: 0:07:22 lr: 0.000150 loss: 2.8122 (2.9206) grad_norm: 2.1342 (2.2984) time: 0.5131 [2021-03-26 21:00:24 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 400/1251] eta: 0:07:17 lr: 0.000150 loss: 3.0502 (2.9236) grad_norm: 2.2141 (2.2975) time: 0.5133 [2021-03-26 21:00:29 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 410/1251] eta: 0:07:11 lr: 0.000150 loss: 2.8932 (2.9237) grad_norm: 2.2737 (2.2980) time: 0.5088 [2021-03-26 21:00:34 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 420/1251] eta: 0:07:06 lr: 0.000150 loss: 2.9408 (2.9259) grad_norm: 2.1776 (2.2976) time: 0.5065 [2021-03-26 21:00:39 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 430/1251] eta: 0:07:01 lr: 0.000150 loss: 2.9620 (2.9255) grad_norm: 2.4071 (2.3050) time: 0.5008 [2021-03-26 21:00:44 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 440/1251] eta: 0:06:55 lr: 0.000150 loss: 2.9105 (2.9264) grad_norm: 2.4071 (2.3055) time: 0.4929 [2021-03-26 21:00:49 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 450/1251] eta: 0:06:50 lr: 0.000150 loss: 3.0868 (2.9281) grad_norm: 2.3119 (2.3099) time: 0.4959 [2021-03-26 21:00:54 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 460/1251] eta: 0:06:44 lr: 0.000150 loss: 3.0954 (2.9251) grad_norm: 2.3526 (2.3106) time: 0.4993 [2021-03-26 21:00:59 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 470/1251] eta: 0:06:39 lr: 0.000150 loss: 3.0577 (2.9304) grad_norm: 2.2992 (2.3100) time: 0.4946 [2021-03-26 21:01:04 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 480/1251] eta: 0:06:34 lr: 0.000150 loss: 3.0419 (2.9278) grad_norm: 2.2409 (2.3106) time: 0.4960 [2021-03-26 21:01:09 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 490/1251] eta: 0:06:29 lr: 0.000150 loss: 2.5518 (2.9210) grad_norm: 2.2937 (2.3101) time: 0.5085 [2021-03-26 21:01:14 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 500/1251] eta: 0:06:23 lr: 0.000150 loss: 3.0301 (2.9249) grad_norm: 2.2441 (2.3068) time: 0.5113 [2021-03-26 21:01:19 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 510/1251] eta: 0:06:18 lr: 0.000150 loss: 2.8458 (2.9174) grad_norm: 2.2081 (2.3051) time: 0.5049 [2021-03-26 21:01:24 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 520/1251] eta: 0:06:13 lr: 0.000150 loss: 2.7386 (2.9176) grad_norm: 2.2081 (2.3030) time: 0.5073 [2021-03-26 21:01:29 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 530/1251] eta: 0:06:08 lr: 0.000150 loss: 2.9623 (2.9177) grad_norm: 2.2370 (2.3086) time: 0.5023 [2021-03-26 21:01:34 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 540/1251] eta: 0:06:03 lr: 0.000150 loss: 2.8619 (2.9158) grad_norm: 2.2299 (2.3054) time: 0.5010 [2021-03-26 21:01:39 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 550/1251] eta: 0:05:58 lr: 0.000150 loss: 2.9976 (2.9150) grad_norm: 2.1689 (2.3056) time: 0.5111 [2021-03-26 21:01:44 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 560/1251] eta: 0:05:52 lr: 0.000150 loss: 3.0977 (2.9162) grad_norm: 2.2708 (2.3062) time: 0.5070 [2021-03-26 21:01:49 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 570/1251] eta: 0:05:47 lr: 0.000150 loss: 3.1904 (2.9196) grad_norm: 2.3173 (2.3111) time: 0.5005 [2021-03-26 21:01:54 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 580/1251] eta: 0:05:42 lr: 0.000150 loss: 3.1045 (2.9207) grad_norm: 2.2150 (2.3094) time: 0.5068 [2021-03-26 21:01:59 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 590/1251] eta: 0:05:37 lr: 0.000150 loss: 2.9908 (2.9237) grad_norm: 2.1301 (2.3066) time: 0.5076 [2021-03-26 21:02:04 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 600/1251] eta: 0:05:32 lr: 0.000150 loss: 3.0266 (2.9235) grad_norm: 2.1653 (2.3055) time: 0.5011 [2021-03-26 21:02:09 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 610/1251] eta: 0:05:26 lr: 0.000150 loss: 3.0266 (2.9256) grad_norm: 2.2128 (2.3057) time: 0.5028 [2021-03-26 21:02:15 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 620/1251] eta: 0:05:21 lr: 0.000150 loss: 2.9479 (2.9246) grad_norm: 2.2128 (2.3046) time: 0.5054 [2021-03-26 21:02:20 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 630/1251] eta: 0:05:16 lr: 0.000150 loss: 3.0110 (2.9263) grad_norm: 2.1514 (2.3042) time: 0.5032 [2021-03-26 21:02:25 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 640/1251] eta: 0:05:11 lr: 0.000149 loss: 3.1154 (2.9271) grad_norm: 2.2753 (2.3061) time: 0.5058 [2021-03-26 21:02:30 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 650/1251] eta: 0:05:06 lr: 0.000149 loss: 3.1727 (2.9284) grad_norm: 2.3282 (2.3057) time: 0.5037 [2021-03-26 21:02:35 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 660/1251] eta: 0:05:01 lr: 0.000149 loss: 3.1046 (2.9286) grad_norm: 2.2341 (2.3053) time: 0.5016 [2021-03-26 21:02:40 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 670/1251] eta: 0:04:56 lr: 0.000149 loss: 2.9958 (2.9279) grad_norm: 2.1389 (2.3029) time: 0.5070 [2021-03-26 21:02:45 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 680/1251] eta: 0:04:50 lr: 0.000149 loss: 2.9376 (2.9284) grad_norm: 2.1389 (2.3035) time: 0.5014 [2021-03-26 21:02:50 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 690/1251] eta: 0:04:45 lr: 0.000149 loss: 2.8466 (2.9273) grad_norm: 2.3940 (2.3048) time: 0.4949 [2021-03-26 21:02:55 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 700/1251] eta: 0:04:40 lr: 0.000149 loss: 3.0231 (2.9292) grad_norm: 2.3157 (2.3033) time: 0.4956 [2021-03-26 21:03:00 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 710/1251] eta: 0:04:35 lr: 0.000149 loss: 2.9104 (2.9277) grad_norm: 2.1421 (2.3010) time: 0.5088 [2021-03-26 21:03:05 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 720/1251] eta: 0:04:30 lr: 0.000149 loss: 2.9104 (2.9274) grad_norm: 2.2033 (2.2997) time: 0.5113 [2021-03-26 21:03:10 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 730/1251] eta: 0:04:25 lr: 0.000149 loss: 2.9947 (2.9282) grad_norm: 2.2207 (2.2992) time: 0.5066 [2021-03-26 21:03:15 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 740/1251] eta: 0:04:20 lr: 0.000149 loss: 2.7984 (2.9256) grad_norm: 2.1915 (2.2979) time: 0.5123 [2021-03-26 21:03:20 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 750/1251] eta: 0:04:15 lr: 0.000149 loss: 3.0560 (2.9291) grad_norm: 2.1859 (2.2986) time: 0.5142 [2021-03-26 21:03:25 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 760/1251] eta: 0:04:09 lr: 0.000149 loss: 3.2311 (2.9340) grad_norm: 2.2315 (2.2985) time: 0.5092 [2021-03-26 21:03:30 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 770/1251] eta: 0:04:04 lr: 0.000149 loss: 3.2893 (2.9374) grad_norm: 2.2964 (2.2992) time: 0.5082 [2021-03-26 21:03:36 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 780/1251] eta: 0:03:59 lr: 0.000149 loss: 3.2921 (2.9405) grad_norm: 2.2113 (2.2967) time: 0.5117 [2021-03-26 21:03:41 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 790/1251] eta: 0:03:54 lr: 0.000149 loss: 3.1809 (2.9399) grad_norm: 2.1508 (2.2957) time: 0.5072 [2021-03-26 21:03:46 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 800/1251] eta: 0:03:49 lr: 0.000149 loss: 2.9016 (2.9385) grad_norm: 2.2173 (2.2958) time: 0.5056 [2021-03-26 21:03:51 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 810/1251] eta: 0:03:44 lr: 0.000149 loss: 3.0441 (2.9388) grad_norm: 2.2670 (inf) time: 0.4993 [2021-03-26 21:03:56 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 820/1251] eta: 0:03:39 lr: 0.000149 loss: 2.9945 (2.9382) grad_norm: 2.2305 (inf) time: 0.4946 [2021-03-26 21:04:01 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 830/1251] eta: 0:03:34 lr: 0.000149 loss: 2.9945 (2.9403) grad_norm: 2.1474 (inf) time: 0.5105 [2021-03-26 21:04:06 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 840/1251] eta: 0:03:29 lr: 0.000149 loss: 3.1462 (2.9430) grad_norm: 2.2320 (inf) time: 0.5132 [2021-03-26 21:04:11 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 850/1251] eta: 0:03:24 lr: 0.000149 loss: 3.2874 (2.9445) grad_norm: 2.2441 (inf) time: 0.5006 [2021-03-26 21:04:16 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 860/1251] eta: 0:03:18 lr: 0.000149 loss: 3.1359 (2.9453) grad_norm: 2.2099 (inf) time: 0.4964 [2021-03-26 21:04:21 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 870/1251] eta: 0:03:13 lr: 0.000149 loss: 3.1633 (2.9484) grad_norm: 2.1854 (inf) time: 0.4975 [2021-03-26 21:04:26 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 880/1251] eta: 0:03:08 lr: 0.000149 loss: 3.2324 (2.9481) grad_norm: 2.1986 (inf) time: 0.5046 [2021-03-26 21:04:31 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 890/1251] eta: 0:03:03 lr: 0.000149 loss: 3.1995 (2.9489) grad_norm: 2.1884 (inf) time: 0.5002 [2021-03-26 21:04:36 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 900/1251] eta: 0:02:58 lr: 0.000149 loss: 3.1995 (2.9509) grad_norm: 2.2121 (inf) time: 0.4932 [2021-03-26 21:04:41 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 910/1251] eta: 0:02:53 lr: 0.000149 loss: 3.1492 (2.9521) grad_norm: 2.2376 (inf) time: 0.4948 [2021-03-26 21:04:46 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 920/1251] eta: 0:02:48 lr: 0.000149 loss: 3.0656 (2.9512) grad_norm: 2.3809 (inf) time: 0.4945 [2021-03-26 21:04:51 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 930/1251] eta: 0:02:43 lr: 0.000149 loss: 2.9217 (2.9511) grad_norm: 2.3653 (inf) time: 0.5106 [2021-03-26 21:04:56 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 940/1251] eta: 0:02:38 lr: 0.000149 loss: 3.0800 (2.9522) grad_norm: 2.1781 (inf) time: 0.5209 [2021-03-26 21:05:01 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 950/1251] eta: 0:02:32 lr: 0.000149 loss: 2.9692 (2.9504) grad_norm: 2.3897 (inf) time: 0.5073 [2021-03-26 21:05:06 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 960/1251] eta: 0:02:27 lr: 0.000149 loss: 2.9111 (2.9497) grad_norm: 2.2569 (inf) time: 0.4998 [2021-03-26 21:05:11 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 970/1251] eta: 0:02:22 lr: 0.000149 loss: 3.0084 (2.9496) grad_norm: 2.2569 (inf) time: 0.4990 [2021-03-26 21:05:16 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 980/1251] eta: 0:02:17 lr: 0.000149 loss: 3.1068 (2.9505) grad_norm: 2.3050 (inf) time: 0.5012 [2021-03-26 21:05:21 swin_small_patch4_window7_224] INFO: Epoch: [226] [ 990/1251] eta: 0:02:12 lr: 0.000148 loss: 2.9855 (2.9500) grad_norm: 2.3142 (inf) time: 0.5028 [2021-03-26 21:05:26 swin_small_patch4_window7_224] INFO: Epoch: [226] [1000/1251] eta: 0:02:07 lr: 0.000148 loss: 2.8114 (2.9488) grad_norm: 2.2782 (inf) time: 0.5026 [2021-03-26 21:05:31 swin_small_patch4_window7_224] INFO: Epoch: [226] [1010/1251] eta: 0:02:02 lr: 0.000148 loss: 2.8729 (2.9482) grad_norm: 2.2021 (inf) time: 0.5031 [2021-03-26 21:05:36 swin_small_patch4_window7_224] INFO: Epoch: [226] [1020/1251] eta: 0:01:57 lr: 0.000148 loss: 3.0479 (2.9484) grad_norm: 2.1346 (inf) time: 0.5021 [2021-03-26 21:05:41 swin_small_patch4_window7_224] INFO: Epoch: [226] [1030/1251] eta: 0:01:52 lr: 0.000148 loss: 2.9884 (2.9485) grad_norm: 2.1063 (inf) time: 0.4964 [2021-03-26 21:05:46 swin_small_patch4_window7_224] INFO: Epoch: [226] [1040/1251] eta: 0:01:47 lr: 0.000148 loss: 2.9884 (2.9495) grad_norm: 2.2155 (inf) time: 0.4987 [2021-03-26 21:05:51 swin_small_patch4_window7_224] INFO: Epoch: [226] [1050/1251] eta: 0:01:41 lr: 0.000148 loss: 2.9414 (2.9485) grad_norm: 2.3824 (inf) time: 0.5034 [2021-03-26 21:05:56 swin_small_patch4_window7_224] INFO: Epoch: [226] [1060/1251] eta: 0:01:36 lr: 0.000148 loss: 2.9414 (2.9487) grad_norm: 2.3201 (inf) time: 0.5014 [2021-03-26 21:06:01 swin_small_patch4_window7_224] INFO: Epoch: [226] [1070/1251] eta: 0:01:31 lr: 0.000148 loss: 2.9566 (2.9477) grad_norm: 2.3948 (inf) time: 0.5047 [2021-03-26 21:06:06 swin_small_patch4_window7_224] INFO: Epoch: [226] [1080/1251] eta: 0:01:26 lr: 0.000148 loss: 2.9566 (2.9475) grad_norm: 2.2777 (inf) time: 0.5045 [2021-03-26 21:06:11 swin_small_patch4_window7_224] INFO: Epoch: [226] [1090/1251] eta: 0:01:21 lr: 0.000148 loss: 2.9937 (2.9481) grad_norm: 2.2506 (inf) time: 0.5012 [2021-03-26 21:06:16 swin_small_patch4_window7_224] INFO: Epoch: [226] [1100/1251] eta: 0:01:16 lr: 0.000148 loss: 2.9954 (2.9482) grad_norm: 2.2919 (inf) time: 0.4990 [2021-03-26 21:06:21 swin_small_patch4_window7_224] INFO: Epoch: [226] [1110/1251] eta: 0:01:11 lr: 0.000148 loss: 2.9954 (2.9488) grad_norm: 2.3058 (inf) time: 0.4993 [2021-03-26 21:06:26 swin_small_patch4_window7_224] INFO: Epoch: [226] [1120/1251] eta: 0:01:06 lr: 0.000148 loss: 3.0255 (2.9484) grad_norm: 2.2383 (inf) time: 0.5073 [2021-03-26 21:06:31 swin_small_patch4_window7_224] INFO: Epoch: [226] [1130/1251] eta: 0:01:01 lr: 0.000148 loss: 3.0255 (2.9482) grad_norm: 2.2638 (inf) time: 0.5063 [2021-03-26 21:06:36 swin_small_patch4_window7_224] INFO: Epoch: [226] [1140/1251] eta: 0:00:56 lr: 0.000148 loss: 3.0213 (2.9487) grad_norm: 2.2230 (inf) time: 0.5023 [2021-03-26 21:06:42 swin_small_patch4_window7_224] INFO: Epoch: [226] [1150/1251] eta: 0:00:51 lr: 0.000148 loss: 3.0335 (2.9494) grad_norm: 2.1637 (inf) time: 0.5077 [2021-03-26 21:06:47 swin_small_patch4_window7_224] INFO: Epoch: [226] [1160/1251] eta: 0:00:46 lr: 0.000148 loss: 3.0335 (2.9488) grad_norm: 2.2485 (inf) time: 0.5043 [2021-03-26 21:06:52 swin_small_patch4_window7_224] INFO: Epoch: [226] [1170/1251] eta: 0:00:41 lr: 0.000148 loss: 2.9372 (2.9485) grad_norm: 2.2229 (inf) time: 0.5031 [2021-03-26 21:06:57 swin_small_patch4_window7_224] INFO: Epoch: [226] [1180/1251] eta: 0:00:35 lr: 0.000148 loss: 3.1536 (2.9497) grad_norm: 2.1769 (inf) time: 0.5012 [2021-03-26 21:07:02 swin_small_patch4_window7_224] INFO: Epoch: [226] [1190/1251] eta: 0:00:30 lr: 0.000148 loss: 3.0815 (2.9489) grad_norm: 2.2433 (inf) time: 0.4964 [2021-03-26 21:07:07 swin_small_patch4_window7_224] INFO: Epoch: [226] [1200/1251] eta: 0:00:25 lr: 0.000148 loss: 3.0528 (2.9492) grad_norm: 2.2824 (inf) time: 0.5000 [2021-03-26 21:07:12 swin_small_patch4_window7_224] INFO: Epoch: [226] [1210/1251] eta: 0:00:20 lr: 0.000148 loss: 3.0528 (2.9488) grad_norm: 2.2650 (inf) time: 0.5016 [2021-03-26 21:07:17 swin_small_patch4_window7_224] INFO: Epoch: [226] [1220/1251] eta: 0:00:15 lr: 0.000148 loss: 3.0376 (2.9499) grad_norm: 2.2650 (inf) time: 0.5012 [2021-03-26 21:07:22 swin_small_patch4_window7_224] INFO: Epoch: [226] [1230/1251] eta: 0:00:10 lr: 0.000148 loss: 3.0489 (2.9493) grad_norm: 2.2890 (inf) time: 0.5017 [2021-03-26 21:07:27 swin_small_patch4_window7_224] INFO: Epoch: [226] [1240/1251] eta: 0:00:05 lr: 0.000148 loss: 3.0867 (2.9504) grad_norm: 2.2757 (inf) time: 0.4990 [2021-03-26 21:07:32 swin_small_patch4_window7_224] INFO: Epoch: [226] [1250/1251] eta: 0:00:00 lr: 0.000148 loss: 3.0867 (2.9514) grad_norm: 2.1811 (inf) time: 0.4962 [2021-03-26 21:07:41 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:28 loss: 1.0593 (1.0593) acc1: 79.6875 (79.6875) acc5: 90.6250 (90.6250) [2021-03-26 21:07:45 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:22 loss: 0.7842 (0.7882) acc1: 82.8125 (81.9602) acc5: 96.8750 (96.3068) [2021-03-26 21:07:47 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:12 loss: 0.7651 (0.7992) acc1: 81.2500 (81.3244) acc5: 96.8750 (96.2798) [2021-03-26 21:07:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7628 (0.7624) acc1: 81.2500 (81.8044) acc5: 96.8750 (96.2702) [2021-03-26 21:07:50 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7628 (0.7721) acc1: 81.2500 (81.7073) acc5: 95.3125 (96.1890) [2021-03-26 21:07:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8447 (0.7898) acc1: 79.6875 (80.9920) acc5: 95.3125 (96.0960) [2021-03-26 21:08:01 swin_small_patch4_window7_224] INFO: * Acc@1 81.704 Acc@5 95.824 loss 0.781 [2021-03-26 21:08:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.7% [2021-03-26 21:08:01 swin_small_patch4_window7_224] INFO: Max accuracy: 81.70% [2021-03-26 21:08:07 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 0/1251] eta: 1:55:03 lr: 0.000148 loss: 2.3046 (2.3046) grad_norm: 2.4520 (2.4520) time: 5.5186 [2021-03-26 21:08:12 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 10/1251] eta: 0:19:57 lr: 0.000148 loss: 2.7071 (2.7613) grad_norm: 2.0973 (2.1837) time: 0.9650 [2021-03-26 21:08:17 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 20/1251] eta: 0:15:25 lr: 0.000148 loss: 2.9040 (2.9091) grad_norm: 2.2244 (2.2530) time: 0.5137 [2021-03-26 21:08:22 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 30/1251] eta: 0:13:37 lr: 0.000148 loss: 2.9357 (2.8961) grad_norm: 2.2526 (2.2590) time: 0.5067 [2021-03-26 21:08:27 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 40/1251] eta: 0:12:42 lr: 0.000148 loss: 2.9505 (2.8998) grad_norm: 2.2645 (2.3113) time: 0.5019 [2021-03-26 21:08:32 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 50/1251] eta: 0:12:06 lr: 0.000148 loss: 3.0070 (2.8950) grad_norm: 2.1957 (2.2765) time: 0.5042 [2021-03-26 21:08:37 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 60/1251] eta: 0:11:41 lr: 0.000148 loss: 3.0166 (2.9224) grad_norm: 2.1701 (2.2783) time: 0.5044 [2021-03-26 21:08:42 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 70/1251] eta: 0:11:20 lr: 0.000148 loss: 3.3594 (2.9650) grad_norm: 2.1701 (2.2711) time: 0.5037 [2021-03-26 21:08:47 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 80/1251] eta: 0:11:02 lr: 0.000147 loss: 3.2091 (2.9787) grad_norm: 2.1904 (2.2833) time: 0.4970 [2021-03-26 21:08:52 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 90/1251] eta: 0:10:50 lr: 0.000147 loss: 3.0751 (2.9683) grad_norm: 2.2855 (2.2830) time: 0.5025 [2021-03-26 21:08:57 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 100/1251] eta: 0:10:37 lr: 0.000147 loss: 2.9079 (2.9397) grad_norm: 2.2499 (2.2797) time: 0.5039 [2021-03-26 21:09:02 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 110/1251] eta: 0:10:28 lr: 0.000147 loss: 3.0591 (2.9589) grad_norm: 2.2807 (2.2963) time: 0.5093 [2021-03-26 21:09:07 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 120/1251] eta: 0:10:18 lr: 0.000147 loss: 3.1730 (2.9771) grad_norm: 2.2753 (2.2961) time: 0.5102 [2021-03-26 21:09:12 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 130/1251] eta: 0:10:09 lr: 0.000147 loss: 3.1730 (2.9669) grad_norm: 2.2030 (2.2957) time: 0.5040 [2021-03-26 21:09:17 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 140/1251] eta: 0:10:00 lr: 0.000147 loss: 2.9394 (2.9616) grad_norm: 2.2081 (2.2872) time: 0.5020 [2021-03-26 21:09:22 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 150/1251] eta: 0:09:52 lr: 0.000147 loss: 3.1702 (2.9795) grad_norm: 2.2537 (2.2980) time: 0.5049 [2021-03-26 21:09:27 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 160/1251] eta: 0:09:45 lr: 0.000147 loss: 2.9728 (2.9739) grad_norm: 2.2522 (2.2895) time: 0.5077 [2021-03-26 21:09:33 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 170/1251] eta: 0:09:38 lr: 0.000147 loss: 2.9720 (2.9704) grad_norm: 2.1271 (2.2838) time: 0.5111 [2021-03-26 21:09:38 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 180/1251] eta: 0:09:31 lr: 0.000147 loss: 3.0514 (2.9823) grad_norm: 2.1789 (2.2847) time: 0.5101 [2021-03-26 21:09:43 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 190/1251] eta: 0:09:24 lr: 0.000147 loss: 3.1947 (2.9885) grad_norm: 2.1789 (2.2789) time: 0.5066 [2021-03-26 21:09:48 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 200/1251] eta: 0:09:17 lr: 0.000147 loss: 3.1131 (2.9848) grad_norm: 2.0943 (2.2706) time: 0.5086 [2021-03-26 21:09:53 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 210/1251] eta: 0:09:11 lr: 0.000147 loss: 2.9497 (2.9734) grad_norm: 2.1976 (2.2730) time: 0.5060 [2021-03-26 21:09:58 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 220/1251] eta: 0:09:05 lr: 0.000147 loss: 2.9369 (2.9766) grad_norm: 2.2852 (2.2787) time: 0.5109 [2021-03-26 21:10:03 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 230/1251] eta: 0:08:59 lr: 0.000147 loss: 2.9338 (2.9654) grad_norm: 2.3625 (2.2823) time: 0.5093 [2021-03-26 21:10:08 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 240/1251] eta: 0:08:52 lr: 0.000147 loss: 2.9338 (2.9642) grad_norm: 2.2199 (2.2838) time: 0.5011 [2021-03-26 21:10:13 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 250/1251] eta: 0:08:46 lr: 0.000147 loss: 2.9738 (2.9635) grad_norm: 2.2590 (2.2855) time: 0.5024 [2021-03-26 21:10:18 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 260/1251] eta: 0:08:40 lr: 0.000147 loss: 2.9738 (2.9622) grad_norm: 2.3262 (2.2910) time: 0.5084 [2021-03-26 21:10:23 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 270/1251] eta: 0:08:34 lr: 0.000147 loss: 3.0369 (2.9622) grad_norm: 2.2837 (2.2893) time: 0.5041 [2021-03-26 21:10:28 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 280/1251] eta: 0:08:28 lr: 0.000147 loss: 2.7240 (2.9556) grad_norm: 2.2793 (2.2947) time: 0.4963 [2021-03-26 21:10:33 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 290/1251] eta: 0:08:22 lr: 0.000147 loss: 2.7240 (2.9501) grad_norm: 2.3354 (2.2993) time: 0.5040 [2021-03-26 21:10:38 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 300/1251] eta: 0:08:16 lr: 0.000147 loss: 3.0029 (2.9562) grad_norm: 2.3190 (2.3002) time: 0.5049 [2021-03-26 21:10:43 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 310/1251] eta: 0:08:10 lr: 0.000147 loss: 3.0990 (2.9573) grad_norm: 2.3060 (2.3011) time: 0.4990 [2021-03-26 21:10:48 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 320/1251] eta: 0:08:04 lr: 0.000147 loss: 2.8741 (2.9504) grad_norm: 2.3127 (2.3035) time: 0.5012 [2021-03-26 21:10:53 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 330/1251] eta: 0:07:59 lr: 0.000147 loss: 2.8741 (2.9517) grad_norm: 2.3099 (2.3033) time: 0.5061 [2021-03-26 21:10:58 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 340/1251] eta: 0:07:53 lr: 0.000147 loss: 3.0942 (2.9550) grad_norm: 2.2174 (2.3000) time: 0.5040 [2021-03-26 21:11:03 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 350/1251] eta: 0:07:47 lr: 0.000147 loss: 3.0887 (2.9564) grad_norm: 2.1505 (2.2958) time: 0.4931 [2021-03-26 21:11:08 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 360/1251] eta: 0:07:41 lr: 0.000147 loss: 3.0571 (2.9564) grad_norm: 2.1505 (2.3069) time: 0.4918 [2021-03-26 21:11:13 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 370/1251] eta: 0:07:36 lr: 0.000147 loss: 2.8733 (2.9512) grad_norm: 2.2579 (2.3101) time: 0.4975 [2021-03-26 21:11:18 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 380/1251] eta: 0:07:30 lr: 0.000147 loss: 2.7966 (2.9450) grad_norm: 2.2767 (2.3101) time: 0.5037 [2021-03-26 21:11:23 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 390/1251] eta: 0:07:25 lr: 0.000147 loss: 2.8213 (2.9460) grad_norm: 2.1461 (2.3068) time: 0.5055 [2021-03-26 21:11:28 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 400/1251] eta: 0:07:19 lr: 0.000147 loss: 2.7986 (2.9363) grad_norm: 2.1336 (2.3034) time: 0.5050 [2021-03-26 21:11:33 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 410/1251] eta: 0:07:14 lr: 0.000147 loss: 2.7216 (2.9313) grad_norm: 2.1982 (2.3046) time: 0.5049 [2021-03-26 21:11:38 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 420/1251] eta: 0:07:08 lr: 0.000147 loss: 2.9057 (2.9352) grad_norm: 2.2057 (2.3050) time: 0.5026 [2021-03-26 21:11:43 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 430/1251] eta: 0:07:03 lr: 0.000146 loss: 3.2023 (2.9410) grad_norm: 2.2057 (2.3059) time: 0.5005 [2021-03-26 21:11:49 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 440/1251] eta: 0:06:58 lr: 0.000146 loss: 3.1346 (2.9417) grad_norm: 2.2431 (2.3062) time: 0.5051 [2021-03-26 21:11:54 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 450/1251] eta: 0:06:52 lr: 0.000146 loss: 2.9095 (2.9415) grad_norm: 2.3383 (2.3120) time: 0.5072 [2021-03-26 21:11:59 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 460/1251] eta: 0:06:47 lr: 0.000146 loss: 2.9858 (2.9464) grad_norm: 2.3809 (2.3156) time: 0.5027 [2021-03-26 21:12:04 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 470/1251] eta: 0:06:42 lr: 0.000146 loss: 3.1062 (2.9431) grad_norm: 2.2891 (2.3154) time: 0.4993 [2021-03-26 21:12:09 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 480/1251] eta: 0:06:36 lr: 0.000146 loss: 3.0403 (2.9456) grad_norm: 2.2203 (2.3134) time: 0.5034 [2021-03-26 21:12:14 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 490/1251] eta: 0:06:31 lr: 0.000146 loss: 2.8391 (2.9419) grad_norm: 2.1973 (2.3177) time: 0.5034 [2021-03-26 21:12:19 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 500/1251] eta: 0:06:26 lr: 0.000146 loss: 2.8299 (2.9393) grad_norm: 2.2405 (2.3172) time: 0.5001 [2021-03-26 21:12:24 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 510/1251] eta: 0:06:20 lr: 0.000146 loss: 2.8861 (2.9388) grad_norm: 2.2405 (2.3176) time: 0.4982 [2021-03-26 21:12:29 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 520/1251] eta: 0:06:15 lr: 0.000146 loss: 3.0299 (2.9395) grad_norm: 2.2042 (2.3167) time: 0.4996 [2021-03-26 21:12:34 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 530/1251] eta: 0:06:10 lr: 0.000146 loss: 3.0299 (2.9413) grad_norm: 2.2072 (2.3278) time: 0.5008 [2021-03-26 21:12:39 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 540/1251] eta: 0:06:04 lr: 0.000146 loss: 3.0584 (2.9414) grad_norm: 2.2072 (2.3289) time: 0.4982 [2021-03-26 21:12:44 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 550/1251] eta: 0:05:59 lr: 0.000146 loss: 2.9997 (2.9390) grad_norm: 2.2759 (2.3289) time: 0.5127 [2021-03-26 21:12:49 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 560/1251] eta: 0:05:54 lr: 0.000146 loss: 3.0988 (2.9393) grad_norm: 2.3232 (2.3305) time: 0.5129 [2021-03-26 21:12:54 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 570/1251] eta: 0:05:49 lr: 0.000146 loss: 3.0988 (2.9417) grad_norm: 2.3959 (2.3343) time: 0.4979 [2021-03-26 21:12:59 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 580/1251] eta: 0:05:43 lr: 0.000146 loss: 2.9958 (2.9414) grad_norm: 2.3429 (2.3341) time: 0.4966 [2021-03-26 21:13:04 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 590/1251] eta: 0:05:38 lr: 0.000146 loss: 2.7803 (2.9370) grad_norm: 2.1781 (2.3328) time: 0.5045 [2021-03-26 21:13:09 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 600/1251] eta: 0:05:33 lr: 0.000146 loss: 2.8232 (2.9372) grad_norm: 2.2377 (2.3319) time: 0.5051 [2021-03-26 21:13:14 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 610/1251] eta: 0:05:28 lr: 0.000146 loss: 2.9726 (2.9375) grad_norm: 2.3009 (2.3337) time: 0.5002 [2021-03-26 21:13:19 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 620/1251] eta: 0:05:22 lr: 0.000146 loss: 2.8664 (2.9360) grad_norm: 2.2787 (2.3351) time: 0.5023 [2021-03-26 21:13:24 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 630/1251] eta: 0:05:17 lr: 0.000146 loss: 3.1234 (2.9379) grad_norm: 2.2787 (2.3348) time: 0.4985 [2021-03-26 21:13:29 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 640/1251] eta: 0:05:12 lr: 0.000146 loss: 3.1599 (2.9394) grad_norm: 2.3059 (2.3366) time: 0.4936 [2021-03-26 21:13:34 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 650/1251] eta: 0:05:07 lr: 0.000146 loss: 3.0957 (2.9411) grad_norm: 2.3059 (2.3394) time: 0.4922 [2021-03-26 21:13:39 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 660/1251] eta: 0:05:01 lr: 0.000146 loss: 2.9856 (2.9403) grad_norm: 2.2855 (2.3394) time: 0.4930 [2021-03-26 21:13:44 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 670/1251] eta: 0:04:56 lr: 0.000146 loss: 2.9645 (2.9391) grad_norm: 2.2796 (2.3376) time: 0.5023 [2021-03-26 21:13:49 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 680/1251] eta: 0:04:51 lr: 0.000146 loss: 3.1240 (2.9402) grad_norm: 2.2631 (2.3394) time: 0.5053 [2021-03-26 21:13:54 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 690/1251] eta: 0:04:46 lr: 0.000146 loss: 3.1429 (2.9407) grad_norm: 2.2631 (2.3387) time: 0.4989 [2021-03-26 21:13:59 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 700/1251] eta: 0:04:41 lr: 0.000146 loss: 3.1124 (2.9422) grad_norm: 2.1690 (2.3362) time: 0.5010 [2021-03-26 21:14:04 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 710/1251] eta: 0:04:35 lr: 0.000146 loss: 3.0670 (2.9420) grad_norm: 2.2195 (2.3380) time: 0.5009 [2021-03-26 21:14:09 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 720/1251] eta: 0:04:30 lr: 0.000146 loss: 2.8992 (2.9389) grad_norm: 2.2544 (2.3406) time: 0.5048 [2021-03-26 21:14:14 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 730/1251] eta: 0:04:25 lr: 0.000146 loss: 2.9055 (2.9398) grad_norm: 2.1955 (2.3420) time: 0.5071 [2021-03-26 21:14:19 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 740/1251] eta: 0:04:20 lr: 0.000146 loss: 3.0523 (2.9405) grad_norm: 2.4091 (2.3433) time: 0.5213 [2021-03-26 21:14:24 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 750/1251] eta: 0:04:15 lr: 0.000146 loss: 3.0523 (2.9412) grad_norm: 2.3610 (2.3432) time: 0.5190 [2021-03-26 21:14:30 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 760/1251] eta: 0:04:10 lr: 0.000146 loss: 3.0030 (2.9413) grad_norm: 2.2956 (2.3418) time: 0.5043 [2021-03-26 21:14:35 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 770/1251] eta: 0:04:05 lr: 0.000146 loss: 3.0470 (2.9434) grad_norm: 2.2029 (2.3410) time: 0.5108 [2021-03-26 21:14:40 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 780/1251] eta: 0:04:00 lr: 0.000145 loss: 3.0677 (2.9459) grad_norm: 2.2675 (2.3409) time: 0.5098 [2021-03-26 21:14:45 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 790/1251] eta: 0:03:55 lr: 0.000145 loss: 2.9505 (2.9455) grad_norm: 2.3691 (2.3426) time: 0.5049 [2021-03-26 21:14:50 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 800/1251] eta: 0:03:49 lr: 0.000145 loss: 2.8371 (2.9455) grad_norm: 2.4005 (2.3443) time: 0.4967 [2021-03-26 21:14:55 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 810/1251] eta: 0:03:44 lr: 0.000145 loss: 2.9519 (2.9471) grad_norm: 2.3262 (2.3433) time: 0.4977 [2021-03-26 21:15:00 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 820/1251] eta: 0:03:39 lr: 0.000145 loss: 3.2625 (2.9474) grad_norm: 2.2066 (2.3417) time: 0.5011 [2021-03-26 21:15:05 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 830/1251] eta: 0:03:34 lr: 0.000145 loss: 3.1487 (2.9497) grad_norm: 2.2503 (2.3412) time: 0.5017 [2021-03-26 21:15:10 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 840/1251] eta: 0:03:29 lr: 0.000145 loss: 3.0000 (2.9488) grad_norm: 2.2812 (2.3420) time: 0.5006 [2021-03-26 21:15:15 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 850/1251] eta: 0:03:24 lr: 0.000145 loss: 2.6710 (2.9460) grad_norm: 2.2761 (2.3397) time: 0.4953 [2021-03-26 21:15:20 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 860/1251] eta: 0:03:19 lr: 0.000145 loss: 2.9466 (2.9472) grad_norm: 2.3316 (2.3424) time: 0.5027 [2021-03-26 21:15:25 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 870/1251] eta: 0:03:14 lr: 0.000145 loss: 2.9466 (2.9431) grad_norm: 2.4688 (2.3452) time: 0.5072 [2021-03-26 21:15:30 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 880/1251] eta: 0:03:08 lr: 0.000145 loss: 2.5293 (2.9427) grad_norm: 2.2549 (2.3435) time: 0.5031 [2021-03-26 21:15:35 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 890/1251] eta: 0:03:03 lr: 0.000145 loss: 3.0128 (2.9437) grad_norm: 2.2805 (2.3440) time: 0.5013 [2021-03-26 21:15:40 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 900/1251] eta: 0:02:58 lr: 0.000145 loss: 3.1248 (2.9453) grad_norm: 2.3213 (2.3443) time: 0.4983 [2021-03-26 21:15:45 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 910/1251] eta: 0:02:53 lr: 0.000145 loss: 3.0721 (2.9448) grad_norm: 2.3212 (2.3443) time: 0.5048 [2021-03-26 21:15:50 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 920/1251] eta: 0:02:48 lr: 0.000145 loss: 2.8291 (2.9420) grad_norm: 2.2507 (2.3429) time: 0.5075 [2021-03-26 21:15:55 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 930/1251] eta: 0:02:43 lr: 0.000145 loss: 2.9618 (2.9448) grad_norm: 2.2064 (2.3421) time: 0.4975 [2021-03-26 21:16:00 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 940/1251] eta: 0:02:38 lr: 0.000145 loss: 2.9284 (2.9420) grad_norm: 2.2148 (2.3405) time: 0.5002 [2021-03-26 21:16:05 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 950/1251] eta: 0:02:33 lr: 0.000145 loss: 2.5703 (2.9386) grad_norm: 2.1852 (2.3395) time: 0.5103 [2021-03-26 21:16:10 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 960/1251] eta: 0:02:28 lr: 0.000145 loss: 2.5703 (2.9365) grad_norm: 2.2197 (2.3386) time: 0.5066 [2021-03-26 21:16:15 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 970/1251] eta: 0:02:22 lr: 0.000145 loss: 2.8712 (2.9370) grad_norm: 2.2753 (2.3377) time: 0.5028 [2021-03-26 21:16:20 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 980/1251] eta: 0:02:17 lr: 0.000145 loss: 3.0028 (2.9351) grad_norm: 2.2746 (2.3375) time: 0.5024 [2021-03-26 21:16:25 swin_small_patch4_window7_224] INFO: Epoch: [227] [ 990/1251] eta: 0:02:12 lr: 0.000145 loss: 2.9789 (2.9334) grad_norm: 2.2105 (2.3387) time: 0.5026 [2021-03-26 21:16:30 swin_small_patch4_window7_224] INFO: Epoch: [227] [1000/1251] eta: 0:02:07 lr: 0.000145 loss: 3.0583 (2.9353) grad_norm: 2.3095 (2.3396) time: 0.5024 [2021-03-26 21:16:35 swin_small_patch4_window7_224] INFO: Epoch: [227] [1010/1251] eta: 0:02:02 lr: 0.000145 loss: 3.1409 (2.9354) grad_norm: 2.3186 (2.3411) time: 0.5052 [2021-03-26 21:16:40 swin_small_patch4_window7_224] INFO: Epoch: [227] [1020/1251] eta: 0:01:57 lr: 0.000145 loss: 2.9446 (2.9357) grad_norm: 2.2733 (2.3426) time: 0.5043 [2021-03-26 21:16:45 swin_small_patch4_window7_224] INFO: Epoch: [227] [1030/1251] eta: 0:01:52 lr: 0.000145 loss: 2.9446 (2.9369) grad_norm: 2.4366 (2.3436) time: 0.5010 [2021-03-26 21:16:50 swin_small_patch4_window7_224] INFO: Epoch: [227] [1040/1251] eta: 0:01:47 lr: 0.000145 loss: 3.1495 (2.9390) grad_norm: 2.2558 (2.3432) time: 0.5015 [2021-03-26 21:16:55 swin_small_patch4_window7_224] INFO: Epoch: [227] [1050/1251] eta: 0:01:42 lr: 0.000145 loss: 3.1782 (2.9416) grad_norm: 2.2495 (2.3439) time: 0.5025 [2021-03-26 21:17:00 swin_small_patch4_window7_224] INFO: Epoch: [227] [1060/1251] eta: 0:01:37 lr: 0.000145 loss: 2.9949 (2.9399) grad_norm: 2.2950 (2.3436) time: 0.5002 [2021-03-26 21:17:06 swin_small_patch4_window7_224] INFO: Epoch: [227] [1070/1251] eta: 0:01:31 lr: 0.000145 loss: 2.8226 (2.9411) grad_norm: 2.2912 (2.3439) time: 0.5065 [2021-03-26 21:17:10 swin_small_patch4_window7_224] INFO: Epoch: [227] [1080/1251] eta: 0:01:26 lr: 0.000145 loss: 3.0432 (2.9404) grad_norm: 2.2953 (2.3438) time: 0.5058 [2021-03-26 21:17:15 swin_small_patch4_window7_224] INFO: Epoch: [227] [1090/1251] eta: 0:01:21 lr: 0.000145 loss: 2.9624 (2.9406) grad_norm: 2.2923 (2.3443) time: 0.4991 [2021-03-26 21:17:21 swin_small_patch4_window7_224] INFO: Epoch: [227] [1100/1251] eta: 0:01:16 lr: 0.000145 loss: 2.9499 (2.9395) grad_norm: 2.2709 (2.3445) time: 0.5069 [2021-03-26 21:17:26 swin_small_patch4_window7_224] INFO: Epoch: [227] [1110/1251] eta: 0:01:11 lr: 0.000145 loss: 2.8189 (2.9370) grad_norm: 2.2793 (2.3440) time: 0.5011 [2021-03-26 21:17:30 swin_small_patch4_window7_224] INFO: Epoch: [227] [1120/1251] eta: 0:01:06 lr: 0.000145 loss: 2.7903 (2.9352) grad_norm: 2.2929 (2.3445) time: 0.4957 [2021-03-26 21:17:35 swin_small_patch4_window7_224] INFO: Epoch: [227] [1130/1251] eta: 0:01:01 lr: 0.000145 loss: 2.9682 (2.9352) grad_norm: 2.2897 (2.3448) time: 0.4965 [2021-03-26 21:17:41 swin_small_patch4_window7_224] INFO: Epoch: [227] [1140/1251] eta: 0:00:56 lr: 0.000144 loss: 2.9749 (2.9364) grad_norm: 2.3294 (2.3474) time: 0.5011 [2021-03-26 21:17:46 swin_small_patch4_window7_224] INFO: Epoch: [227] [1150/1251] eta: 0:00:51 lr: 0.000144 loss: 3.0106 (2.9356) grad_norm: 2.2509 (2.3474) time: 0.5038 [2021-03-26 21:17:51 swin_small_patch4_window7_224] INFO: Epoch: [227] [1160/1251] eta: 0:00:46 lr: 0.000144 loss: 3.1299 (2.9358) grad_norm: 2.2207 (2.3474) time: 0.5050 [2021-03-26 21:17:56 swin_small_patch4_window7_224] INFO: Epoch: [227] [1170/1251] eta: 0:00:41 lr: 0.000144 loss: 2.9658 (2.9355) grad_norm: 2.2520 (2.3469) time: 0.5043 [2021-03-26 21:18:01 swin_small_patch4_window7_224] INFO: Epoch: [227] [1180/1251] eta: 0:00:36 lr: 0.000144 loss: 2.9567 (2.9356) grad_norm: 2.2499 (2.3468) time: 0.4979 [2021-03-26 21:18:06 swin_small_patch4_window7_224] INFO: Epoch: [227] [1190/1251] eta: 0:00:30 lr: 0.000144 loss: 3.1081 (2.9368) grad_norm: 2.2669 (2.3481) time: 0.4956 [2021-03-26 21:18:11 swin_small_patch4_window7_224] INFO: Epoch: [227] [1200/1251] eta: 0:00:25 lr: 0.000144 loss: 3.1081 (2.9368) grad_norm: 2.4405 (2.3488) time: 0.5037 [2021-03-26 21:18:16 swin_small_patch4_window7_224] INFO: Epoch: [227] [1210/1251] eta: 0:00:20 lr: 0.000144 loss: 3.1551 (2.9366) grad_norm: 2.3070 (2.3506) time: 0.5058 [2021-03-26 21:18:21 swin_small_patch4_window7_224] INFO: Epoch: [227] [1220/1251] eta: 0:00:15 lr: 0.000144 loss: 3.0742 (2.9366) grad_norm: 2.2895 (2.3497) time: 0.5032 [2021-03-26 21:18:26 swin_small_patch4_window7_224] INFO: Epoch: [227] [1230/1251] eta: 0:00:10 lr: 0.000144 loss: 2.8607 (2.9349) grad_norm: 2.1654 (2.3501) time: 0.5079 [2021-03-26 21:18:31 swin_small_patch4_window7_224] INFO: Epoch: [227] [1240/1251] eta: 0:00:05 lr: 0.000144 loss: 2.5959 (2.9323) grad_norm: 2.1769 (2.3490) time: 0.5038 [2021-03-26 21:18:36 swin_small_patch4_window7_224] INFO: Epoch: [227] [1250/1251] eta: 0:00:00 lr: 0.000144 loss: 2.6569 (2.9312) grad_norm: 2.1613 (2.3480) time: 0.4935 [2021-03-26 21:18:43 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:10 loss: 1.0839 (1.0839) acc1: 73.4375 (73.4375) acc5: 93.7500 (93.7500) [2021-03-26 21:18:45 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7870 (0.8171) acc1: 81.2500 (80.8239) acc5: 95.3125 (95.4545) [2021-03-26 21:18:47 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7597 (0.8046) acc1: 81.2500 (80.7292) acc5: 96.8750 (96.0565) [2021-03-26 21:18:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7542 (0.8004) acc1: 81.2500 (80.9476) acc5: 95.3125 (95.7157) [2021-03-26 21:18:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7995 (0.8087) acc1: 81.2500 (81.0213) acc5: 95.3125 (95.4649) [2021-03-26 21:18:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7995 (0.7978) acc1: 81.2500 (81.2800) acc5: 95.3125 (95.6160) [2021-03-26 21:19:04 swin_small_patch4_window7_224] INFO: * Acc@1 81.586 Acc@5 95.760 loss 0.788 [2021-03-26 21:19:04 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.6% [2021-03-26 21:19:04 swin_small_patch4_window7_224] INFO: Max accuracy: 81.70% [2021-03-26 21:19:08 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 0/1251] eta: 1:27:16 lr: 0.000144 loss: 3.6689 (3.6689) grad_norm: 2.2616 (2.2616) time: 4.1856 [2021-03-26 21:19:14 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 10/1251] eta: 0:17:59 lr: 0.000144 loss: 2.9494 (2.9242) grad_norm: 2.4481 (2.3964) time: 0.8697 [2021-03-26 21:19:19 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 20/1251] eta: 0:14:19 lr: 0.000144 loss: 2.9350 (2.9659) grad_norm: 2.3198 (2.3365) time: 0.5239 [2021-03-26 21:19:24 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 30/1251] eta: 0:12:57 lr: 0.000144 loss: 2.9350 (2.9797) grad_norm: 2.1606 (2.2902) time: 0.5090 [2021-03-26 21:19:29 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 40/1251] eta: 0:12:11 lr: 0.000144 loss: 2.9560 (2.9548) grad_norm: 2.2235 (2.2887) time: 0.5052 [2021-03-26 21:19:34 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 50/1251] eta: 0:11:41 lr: 0.000144 loss: 3.0611 (2.9551) grad_norm: 2.2086 (2.2862) time: 0.5022 [2021-03-26 21:19:39 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 60/1251] eta: 0:11:19 lr: 0.000144 loss: 3.0611 (2.9705) grad_norm: 2.1974 (2.2768) time: 0.5017 [2021-03-26 21:19:44 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 70/1251] eta: 0:11:02 lr: 0.000144 loss: 2.9652 (2.9416) grad_norm: 2.2762 (2.2806) time: 0.5023 [2021-03-26 21:19:49 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 80/1251] eta: 0:10:48 lr: 0.000144 loss: 3.0347 (2.9467) grad_norm: 2.3614 (2.2944) time: 0.5016 [2021-03-26 21:19:54 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 90/1251] eta: 0:10:37 lr: 0.000144 loss: 2.9972 (2.9310) grad_norm: 2.3886 (2.3107) time: 0.5048 [2021-03-26 21:19:59 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 100/1251] eta: 0:10:27 lr: 0.000144 loss: 2.9972 (2.9564) grad_norm: 2.3377 (2.3335) time: 0.5132 [2021-03-26 21:20:04 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 110/1251] eta: 0:10:17 lr: 0.000144 loss: 2.9737 (2.9356) grad_norm: 2.2510 (2.3277) time: 0.5090 [2021-03-26 21:20:09 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 120/1251] eta: 0:10:09 lr: 0.000144 loss: 2.9211 (2.9393) grad_norm: 2.2278 (2.3205) time: 0.5037 [2021-03-26 21:20:14 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 130/1251] eta: 0:10:01 lr: 0.000144 loss: 3.0140 (2.9464) grad_norm: 2.1591 (2.3311) time: 0.5089 [2021-03-26 21:20:20 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 140/1251] eta: 0:09:54 lr: 0.000144 loss: 2.9032 (2.9300) grad_norm: 2.2517 (2.3380) time: 0.5132 [2021-03-26 21:20:25 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 150/1251] eta: 0:09:47 lr: 0.000144 loss: 2.7081 (2.9119) grad_norm: 2.3203 (2.3359) time: 0.5112 [2021-03-26 21:20:30 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 160/1251] eta: 0:09:39 lr: 0.000144 loss: 2.9034 (2.9137) grad_norm: 2.3060 (2.3354) time: 0.5015 [2021-03-26 21:20:34 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 170/1251] eta: 0:09:31 lr: 0.000144 loss: 2.9470 (2.9218) grad_norm: 2.2877 (2.3392) time: 0.4922 [2021-03-26 21:20:40 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 180/1251] eta: 0:09:25 lr: 0.000144 loss: 2.9106 (2.9123) grad_norm: 2.2861 (2.3425) time: 0.5017 [2021-03-26 21:20:45 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 190/1251] eta: 0:09:18 lr: 0.000144 loss: 2.7819 (2.9029) grad_norm: 2.2864 (2.3427) time: 0.5104 [2021-03-26 21:20:50 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 200/1251] eta: 0:09:12 lr: 0.000144 loss: 2.7958 (2.9105) grad_norm: 2.2864 (2.3373) time: 0.5056 [2021-03-26 21:20:55 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 210/1251] eta: 0:09:06 lr: 0.000144 loss: 2.9363 (2.9086) grad_norm: 2.2469 (2.3335) time: 0.5065 [2021-03-26 21:21:00 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 220/1251] eta: 0:08:59 lr: 0.000144 loss: 2.9586 (2.9141) grad_norm: 2.3150 (2.3450) time: 0.5027 [2021-03-26 21:21:05 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 230/1251] eta: 0:08:53 lr: 0.000144 loss: 2.9806 (2.9164) grad_norm: 2.3670 (2.3541) time: 0.5020 [2021-03-26 21:21:10 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 240/1251] eta: 0:08:47 lr: 0.000143 loss: 3.1032 (2.9309) grad_norm: 2.3977 (2.3572) time: 0.5083 [2021-03-26 21:21:15 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 250/1251] eta: 0:08:41 lr: 0.000143 loss: 3.1365 (2.9245) grad_norm: 2.2626 (2.3549) time: 0.5058 [2021-03-26 21:21:20 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 260/1251] eta: 0:08:36 lr: 0.000143 loss: 2.8396 (2.9216) grad_norm: 2.2626 (2.3546) time: 0.5050 [2021-03-26 21:21:25 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 270/1251] eta: 0:08:30 lr: 0.000143 loss: 2.9405 (2.9248) grad_norm: 2.2250 (2.3485) time: 0.5086 [2021-03-26 21:21:30 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 280/1251] eta: 0:08:24 lr: 0.000143 loss: 3.1331 (2.9321) grad_norm: 2.1816 (2.3459) time: 0.5076 [2021-03-26 21:21:35 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 290/1251] eta: 0:08:18 lr: 0.000143 loss: 3.0305 (2.9320) grad_norm: 2.2633 (2.3499) time: 0.5019 [2021-03-26 21:21:40 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 300/1251] eta: 0:08:13 lr: 0.000143 loss: 2.9680 (2.9352) grad_norm: 2.2302 (2.3448) time: 0.4987 [2021-03-26 21:21:45 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 310/1251] eta: 0:08:07 lr: 0.000143 loss: 3.0115 (2.9392) grad_norm: 2.1895 (2.3449) time: 0.5006 [2021-03-26 21:21:50 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 320/1251] eta: 0:08:01 lr: 0.000143 loss: 2.9708 (2.9356) grad_norm: 2.2613 (2.3486) time: 0.5062 [2021-03-26 21:21:55 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 330/1251] eta: 0:07:56 lr: 0.000143 loss: 2.9494 (2.9344) grad_norm: 2.2923 (2.3551) time: 0.5076 [2021-03-26 21:22:01 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 340/1251] eta: 0:07:51 lr: 0.000143 loss: 2.8168 (2.9292) grad_norm: 2.3901 (2.3575) time: 0.5089 [2021-03-26 21:22:06 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 350/1251] eta: 0:07:45 lr: 0.000143 loss: 2.9398 (2.9352) grad_norm: 2.3901 (2.3601) time: 0.5056 [2021-03-26 21:22:10 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 360/1251] eta: 0:07:39 lr: 0.000143 loss: 3.1737 (2.9379) grad_norm: 2.2430 (2.3575) time: 0.4954 [2021-03-26 21:22:16 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 370/1251] eta: 0:07:34 lr: 0.000143 loss: 3.0616 (2.9372) grad_norm: 2.2224 (2.3560) time: 0.5006 [2021-03-26 21:22:20 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 380/1251] eta: 0:07:28 lr: 0.000143 loss: 3.1452 (2.9419) grad_norm: 2.3277 (2.3624) time: 0.5033 [2021-03-26 21:22:26 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 390/1251] eta: 0:07:23 lr: 0.000143 loss: 3.1244 (2.9393) grad_norm: 2.2800 (2.3608) time: 0.5015 [2021-03-26 21:22:31 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 400/1251] eta: 0:07:17 lr: 0.000143 loss: 2.8918 (2.9364) grad_norm: 2.2643 (2.3587) time: 0.5006 [2021-03-26 21:22:35 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 410/1251] eta: 0:07:12 lr: 0.000143 loss: 2.9412 (2.9327) grad_norm: 2.2215 (2.3556) time: 0.4960 [2021-03-26 21:22:41 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 420/1251] eta: 0:07:07 lr: 0.000143 loss: 3.0373 (2.9328) grad_norm: 2.1287 (2.3495) time: 0.5004 [2021-03-26 21:22:46 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 430/1251] eta: 0:07:01 lr: 0.000143 loss: 3.0701 (2.9323) grad_norm: 2.1040 (2.3460) time: 0.5073 [2021-03-26 21:22:51 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 440/1251] eta: 0:06:56 lr: 0.000143 loss: 3.1227 (2.9378) grad_norm: 2.2909 (2.3465) time: 0.5057 [2021-03-26 21:22:56 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 450/1251] eta: 0:06:51 lr: 0.000143 loss: 2.9454 (2.9336) grad_norm: 2.2955 (2.3522) time: 0.5062 [2021-03-26 21:23:01 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 460/1251] eta: 0:06:45 lr: 0.000143 loss: 3.0010 (2.9346) grad_norm: 2.2985 (2.3518) time: 0.5026 [2021-03-26 21:23:06 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 470/1251] eta: 0:06:40 lr: 0.000143 loss: 3.0578 (2.9354) grad_norm: 2.3296 (2.3521) time: 0.5004 [2021-03-26 21:23:11 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 480/1251] eta: 0:06:35 lr: 0.000143 loss: 2.9612 (2.9360) grad_norm: 2.2421 (2.3487) time: 0.5035 [2021-03-26 21:23:16 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 490/1251] eta: 0:06:29 lr: 0.000143 loss: 2.7897 (2.9330) grad_norm: 2.2449 (2.3479) time: 0.5017 [2021-03-26 21:23:21 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 500/1251] eta: 0:06:24 lr: 0.000143 loss: 3.0817 (2.9359) grad_norm: 2.2814 (2.3498) time: 0.5037 [2021-03-26 21:23:26 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 510/1251] eta: 0:06:19 lr: 0.000143 loss: 3.1602 (2.9380) grad_norm: 2.3962 (2.3537) time: 0.5048 [2021-03-26 21:23:31 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 520/1251] eta: 0:06:14 lr: 0.000143 loss: 3.0688 (2.9337) grad_norm: 2.3221 (2.3521) time: 0.5015 [2021-03-26 21:23:36 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 530/1251] eta: 0:06:08 lr: 0.000143 loss: 2.9185 (2.9333) grad_norm: 2.2288 (2.3500) time: 0.5017 [2021-03-26 21:23:41 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 540/1251] eta: 0:06:03 lr: 0.000143 loss: 2.9493 (2.9330) grad_norm: 2.2206 (2.3481) time: 0.5053 [2021-03-26 21:23:46 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 550/1251] eta: 0:05:58 lr: 0.000143 loss: 2.9474 (2.9329) grad_norm: 2.1679 (2.3446) time: 0.5119 [2021-03-26 21:23:51 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 560/1251] eta: 0:05:53 lr: 0.000143 loss: 2.9165 (2.9293) grad_norm: 2.2528 (2.3504) time: 0.5139 [2021-03-26 21:23:56 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 570/1251] eta: 0:05:48 lr: 0.000143 loss: 2.6859 (2.9292) grad_norm: 2.3644 (2.3483) time: 0.5111 [2021-03-26 21:24:01 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 580/1251] eta: 0:05:43 lr: 0.000143 loss: 2.8895 (2.9296) grad_norm: 2.2093 (2.3458) time: 0.5080 [2021-03-26 21:24:07 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 590/1251] eta: 0:05:38 lr: 0.000142 loss: 3.1401 (2.9332) grad_norm: 2.1591 (2.3436) time: 0.5081 [2021-03-26 21:24:11 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 600/1251] eta: 0:05:32 lr: 0.000142 loss: 3.1620 (2.9364) grad_norm: 2.2239 (inf) time: 0.5017 [2021-03-26 21:24:17 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 610/1251] eta: 0:05:27 lr: 0.000142 loss: 3.1622 (2.9371) grad_norm: 2.3861 (inf) time: 0.4990 [2021-03-26 21:24:22 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 620/1251] eta: 0:05:22 lr: 0.000142 loss: 3.0850 (2.9383) grad_norm: 2.3347 (inf) time: 0.5026 [2021-03-26 21:24:27 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 630/1251] eta: 0:05:17 lr: 0.000142 loss: 2.9617 (2.9365) grad_norm: 2.2271 (inf) time: 0.4980 [2021-03-26 21:24:32 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 640/1251] eta: 0:05:12 lr: 0.000142 loss: 2.9378 (2.9387) grad_norm: 2.2749 (inf) time: 0.5053 [2021-03-26 21:24:37 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 650/1251] eta: 0:05:06 lr: 0.000142 loss: 3.0470 (2.9396) grad_norm: 2.2389 (inf) time: 0.5042 [2021-03-26 21:24:42 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 660/1251] eta: 0:05:01 lr: 0.000142 loss: 3.0470 (2.9391) grad_norm: 2.1725 (inf) time: 0.5047 [2021-03-26 21:24:47 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 670/1251] eta: 0:04:56 lr: 0.000142 loss: 3.0095 (2.9371) grad_norm: 2.2447 (inf) time: 0.5106 [2021-03-26 21:24:52 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 680/1251] eta: 0:04:51 lr: 0.000142 loss: 3.0095 (2.9369) grad_norm: 2.2306 (inf) time: 0.5102 [2021-03-26 21:24:57 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 690/1251] eta: 0:04:46 lr: 0.000142 loss: 3.1495 (2.9391) grad_norm: 2.2680 (inf) time: 0.5041 [2021-03-26 21:25:02 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 700/1251] eta: 0:04:41 lr: 0.000142 loss: 3.0538 (2.9400) grad_norm: 2.2382 (inf) time: 0.4995 [2021-03-26 21:25:07 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 710/1251] eta: 0:04:35 lr: 0.000142 loss: 3.0351 (2.9390) grad_norm: 2.2368 (inf) time: 0.4985 [2021-03-26 21:25:12 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 720/1251] eta: 0:04:30 lr: 0.000142 loss: 3.0529 (2.9409) grad_norm: 2.2459 (inf) time: 0.4938 [2021-03-26 21:25:17 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 730/1251] eta: 0:04:25 lr: 0.000142 loss: 3.0957 (2.9421) grad_norm: 2.2459 (inf) time: 0.4972 [2021-03-26 21:25:22 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 740/1251] eta: 0:04:20 lr: 0.000142 loss: 3.0957 (2.9423) grad_norm: 2.2924 (inf) time: 0.5264 [2021-03-26 21:25:28 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 750/1251] eta: 0:04:15 lr: 0.000142 loss: 2.9946 (2.9404) grad_norm: 2.2106 (inf) time: 0.5369 [2021-03-26 21:25:33 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 760/1251] eta: 0:04:10 lr: 0.000142 loss: 2.8485 (2.9370) grad_norm: 2.1872 (inf) time: 0.5126 [2021-03-26 21:25:38 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 770/1251] eta: 0:04:05 lr: 0.000142 loss: 2.9239 (2.9364) grad_norm: 2.2285 (inf) time: 0.5084 [2021-03-26 21:25:43 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 780/1251] eta: 0:04:00 lr: 0.000142 loss: 2.8588 (2.9330) grad_norm: 2.2396 (inf) time: 0.5093 [2021-03-26 21:25:48 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 790/1251] eta: 0:03:55 lr: 0.000142 loss: 2.6587 (2.9298) grad_norm: 2.2938 (inf) time: 0.5072 [2021-03-26 21:25:53 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 800/1251] eta: 0:03:50 lr: 0.000142 loss: 2.7640 (2.9294) grad_norm: 2.3363 (inf) time: 0.5074 [2021-03-26 21:25:58 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 810/1251] eta: 0:03:44 lr: 0.000142 loss: 3.1044 (2.9313) grad_norm: 2.3363 (inf) time: 0.5029 [2021-03-26 21:26:03 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 820/1251] eta: 0:03:39 lr: 0.000142 loss: 2.9919 (2.9315) grad_norm: 2.3074 (inf) time: 0.4973 [2021-03-26 21:26:08 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 830/1251] eta: 0:03:34 lr: 0.000142 loss: 2.9723 (2.9310) grad_norm: 2.2535 (inf) time: 0.4988 [2021-03-26 21:26:13 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 840/1251] eta: 0:03:29 lr: 0.000142 loss: 2.9969 (2.9330) grad_norm: 2.2585 (inf) time: 0.5043 [2021-03-26 21:26:18 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 850/1251] eta: 0:03:24 lr: 0.000142 loss: 3.1060 (2.9349) grad_norm: 2.2585 (inf) time: 0.5046 [2021-03-26 21:26:23 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 860/1251] eta: 0:03:19 lr: 0.000142 loss: 3.0490 (2.9358) grad_norm: 2.3096 (inf) time: 0.5117 [2021-03-26 21:26:28 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 870/1251] eta: 0:03:14 lr: 0.000142 loss: 3.1282 (2.9384) grad_norm: 2.3598 (inf) time: 0.5168 [2021-03-26 21:26:33 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 880/1251] eta: 0:03:09 lr: 0.000142 loss: 3.0219 (2.9372) grad_norm: 2.2513 (inf) time: 0.5048 [2021-03-26 21:26:38 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 890/1251] eta: 0:03:04 lr: 0.000142 loss: 2.5338 (2.9339) grad_norm: 2.2154 (inf) time: 0.5042 [2021-03-26 21:26:44 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 900/1251] eta: 0:02:58 lr: 0.000142 loss: 2.5619 (2.9326) grad_norm: 2.3843 (inf) time: 0.5100 [2021-03-26 21:26:49 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 910/1251] eta: 0:02:53 lr: 0.000142 loss: 3.0389 (2.9345) grad_norm: 2.1710 (inf) time: 0.5042 [2021-03-26 21:26:54 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 920/1251] eta: 0:02:48 lr: 0.000142 loss: 3.1151 (2.9359) grad_norm: 2.1710 (inf) time: 0.5013 [2021-03-26 21:26:59 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 930/1251] eta: 0:02:43 lr: 0.000142 loss: 3.0429 (2.9364) grad_norm: 2.3551 (inf) time: 0.5123 [2021-03-26 21:27:04 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 940/1251] eta: 0:02:38 lr: 0.000142 loss: 3.0301 (2.9363) grad_norm: 2.3570 (inf) time: 0.5111 [2021-03-26 21:27:09 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 950/1251] eta: 0:02:33 lr: 0.000141 loss: 2.7485 (2.9327) grad_norm: 2.1654 (inf) time: 0.5005 [2021-03-26 21:27:14 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 960/1251] eta: 0:02:28 lr: 0.000141 loss: 2.9757 (2.9356) grad_norm: 2.2326 (inf) time: 0.5012 [2021-03-26 21:27:19 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 970/1251] eta: 0:02:23 lr: 0.000141 loss: 3.1494 (2.9371) grad_norm: 2.2329 (inf) time: 0.5058 [2021-03-26 21:27:24 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 980/1251] eta: 0:02:18 lr: 0.000141 loss: 3.1658 (2.9394) grad_norm: 2.1766 (inf) time: 0.5098 [2021-03-26 21:27:29 swin_small_patch4_window7_224] INFO: Epoch: [228] [ 990/1251] eta: 0:02:12 lr: 0.000141 loss: 3.1658 (2.9397) grad_norm: 2.2241 (inf) time: 0.5035 [2021-03-26 21:27:34 swin_small_patch4_window7_224] INFO: Epoch: [228] [1000/1251] eta: 0:02:07 lr: 0.000141 loss: 3.0388 (2.9390) grad_norm: 2.1928 (inf) time: 0.5039 [2021-03-26 21:27:39 swin_small_patch4_window7_224] INFO: Epoch: [228] [1010/1251] eta: 0:02:02 lr: 0.000141 loss: 3.1395 (2.9416) grad_norm: 2.2598 (inf) time: 0.5030 [2021-03-26 21:27:44 swin_small_patch4_window7_224] INFO: Epoch: [228] [1020/1251] eta: 0:01:57 lr: 0.000141 loss: 3.1806 (2.9419) grad_norm: 2.3999 (inf) time: 0.5032 [2021-03-26 21:27:49 swin_small_patch4_window7_224] INFO: Epoch: [228] [1030/1251] eta: 0:01:52 lr: 0.000141 loss: 3.0710 (2.9435) grad_norm: 2.2631 (inf) time: 0.5123 [2021-03-26 21:27:54 swin_small_patch4_window7_224] INFO: Epoch: [228] [1040/1251] eta: 0:01:47 lr: 0.000141 loss: 3.0829 (2.9443) grad_norm: 2.2757 (inf) time: 0.5138 [2021-03-26 21:27:59 swin_small_patch4_window7_224] INFO: Epoch: [228] [1050/1251] eta: 0:01:42 lr: 0.000141 loss: 3.0253 (2.9432) grad_norm: 2.3337 (inf) time: 0.5075 [2021-03-26 21:28:05 swin_small_patch4_window7_224] INFO: Epoch: [228] [1060/1251] eta: 0:01:37 lr: 0.000141 loss: 2.9111 (2.9425) grad_norm: 2.2911 (inf) time: 0.5057 [2021-03-26 21:28:10 swin_small_patch4_window7_224] INFO: Epoch: [228] [1070/1251] eta: 0:01:32 lr: 0.000141 loss: 3.0689 (2.9447) grad_norm: 2.2881 (inf) time: 0.5054 [2021-03-26 21:28:15 swin_small_patch4_window7_224] INFO: Epoch: [228] [1080/1251] eta: 0:01:27 lr: 0.000141 loss: 3.0924 (2.9443) grad_norm: 2.2261 (inf) time: 0.5060 [2021-03-26 21:28:20 swin_small_patch4_window7_224] INFO: Epoch: [228] [1090/1251] eta: 0:01:21 lr: 0.000141 loss: 3.0660 (2.9447) grad_norm: 2.1945 (inf) time: 0.5109 [2021-03-26 21:28:25 swin_small_patch4_window7_224] INFO: Epoch: [228] [1100/1251] eta: 0:01:16 lr: 0.000141 loss: 3.1357 (2.9471) grad_norm: 2.1369 (inf) time: 0.5077 [2021-03-26 21:28:30 swin_small_patch4_window7_224] INFO: Epoch: [228] [1110/1251] eta: 0:01:11 lr: 0.000141 loss: 3.1471 (2.9470) grad_norm: 2.2327 (inf) time: 0.4980 [2021-03-26 21:28:35 swin_small_patch4_window7_224] INFO: Epoch: [228] [1120/1251] eta: 0:01:06 lr: 0.000141 loss: 3.1471 (2.9490) grad_norm: 2.4023 (inf) time: 0.4980 [2021-03-26 21:28:40 swin_small_patch4_window7_224] INFO: Epoch: [228] [1130/1251] eta: 0:01:01 lr: 0.000141 loss: 3.1495 (2.9481) grad_norm: 2.2538 (inf) time: 0.5005 [2021-03-26 21:28:45 swin_small_patch4_window7_224] INFO: Epoch: [228] [1140/1251] eta: 0:00:56 lr: 0.000141 loss: 2.5566 (2.9471) grad_norm: 2.2361 (inf) time: 0.5068 [2021-03-26 21:28:50 swin_small_patch4_window7_224] INFO: Epoch: [228] [1150/1251] eta: 0:00:51 lr: 0.000141 loss: 3.0292 (2.9464) grad_norm: 2.3211 (inf) time: 0.5101 [2021-03-26 21:28:55 swin_small_patch4_window7_224] INFO: Epoch: [228] [1160/1251] eta: 0:00:46 lr: 0.000141 loss: 3.0817 (2.9472) grad_norm: 2.4024 (inf) time: 0.5062 [2021-03-26 21:29:00 swin_small_patch4_window7_224] INFO: Epoch: [228] [1170/1251] eta: 0:00:41 lr: 0.000141 loss: 3.1057 (2.9487) grad_norm: 2.4579 (inf) time: 0.5150 [2021-03-26 21:29:05 swin_small_patch4_window7_224] INFO: Epoch: [228] [1180/1251] eta: 0:00:36 lr: 0.000141 loss: 3.0687 (2.9486) grad_norm: 2.3454 (inf) time: 0.5139 [2021-03-26 21:29:10 swin_small_patch4_window7_224] INFO: Epoch: [228] [1190/1251] eta: 0:00:31 lr: 0.000141 loss: 2.9175 (2.9482) grad_norm: 2.3158 (inf) time: 0.5014 [2021-03-26 21:29:15 swin_small_patch4_window7_224] INFO: Epoch: [228] [1200/1251] eta: 0:00:25 lr: 0.000141 loss: 2.9175 (2.9488) grad_norm: 2.3387 (inf) time: 0.5030 [2021-03-26 21:29:20 swin_small_patch4_window7_224] INFO: Epoch: [228] [1210/1251] eta: 0:00:20 lr: 0.000141 loss: 3.0096 (2.9493) grad_norm: 2.3965 (inf) time: 0.5063 [2021-03-26 21:29:25 swin_small_patch4_window7_224] INFO: Epoch: [228] [1220/1251] eta: 0:00:15 lr: 0.000141 loss: 2.8467 (2.9469) grad_norm: 2.3206 (inf) time: 0.5035 [2021-03-26 21:29:30 swin_small_patch4_window7_224] INFO: Epoch: [228] [1230/1251] eta: 0:00:10 lr: 0.000141 loss: 2.6888 (2.9449) grad_norm: 2.2696 (inf) time: 0.5019 [2021-03-26 21:29:36 swin_small_patch4_window7_224] INFO: Epoch: [228] [1240/1251] eta: 0:00:05 lr: 0.000141 loss: 2.9583 (2.9449) grad_norm: 2.2623 (inf) time: 0.5042 [2021-03-26 21:29:41 swin_small_patch4_window7_224] INFO: Epoch: [228] [1250/1251] eta: 0:00:00 lr: 0.000141 loss: 2.9583 (2.9423) grad_norm: 2.3032 (inf) time: 0.5045 [2021-03-26 21:29:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 0.7131 (0.7131) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-26 21:29:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7195 (0.7853) acc1: 81.2500 (80.2557) acc5: 96.8750 (95.7386) [2021-03-26 21:29:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7546 (0.7487) acc1: 81.2500 (81.6964) acc5: 96.8750 (96.2054) [2021-03-26 21:29:57 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7546 (0.7413) acc1: 82.8125 (82.2077) acc5: 96.8750 (96.3710) [2021-03-26 21:29:59 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8099 (0.7696) acc1: 81.2500 (81.4024) acc5: 95.3125 (95.9604) [2021-03-26 21:30:00 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8960 (0.7905) acc1: 79.6875 (81.2160) acc5: 95.3125 (95.9040) [2021-03-26 21:30:13 swin_small_patch4_window7_224] INFO: * Acc@1 81.684 Acc@5 95.790 loss 0.779 [2021-03-26 21:30:13 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.7% [2021-03-26 21:30:13 swin_small_patch4_window7_224] INFO: Max accuracy: 81.70% [2021-03-26 21:30:17 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 0/1251] eta: 1:27:25 lr: 0.000141 loss: 2.0529 (2.0529) grad_norm: 2.1297 (2.1297) time: 4.1932 [2021-03-26 21:30:22 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 10/1251] eta: 0:17:58 lr: 0.000141 loss: 2.8121 (2.7505) grad_norm: 2.1986 (2.2343) time: 0.8692 [2021-03-26 21:30:27 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 20/1251] eta: 0:14:17 lr: 0.000141 loss: 2.8889 (2.8092) grad_norm: 2.2416 (2.2752) time: 0.5219 [2021-03-26 21:30:32 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 30/1251] eta: 0:12:55 lr: 0.000141 loss: 2.8889 (2.8034) grad_norm: 2.2416 (2.2775) time: 0.5069 [2021-03-26 21:30:37 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 40/1251] eta: 0:12:09 lr: 0.000141 loss: 2.9486 (2.8316) grad_norm: 2.2060 (2.2648) time: 0.5040 [2021-03-26 21:30:42 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 50/1251] eta: 0:11:39 lr: 0.000140 loss: 2.8918 (2.8311) grad_norm: 2.2278 (2.2675) time: 0.5003 [2021-03-26 21:30:47 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 60/1251] eta: 0:11:19 lr: 0.000140 loss: 2.8159 (2.8268) grad_norm: 2.2278 (2.2610) time: 0.5054 [2021-03-26 21:30:52 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 70/1251] eta: 0:11:01 lr: 0.000140 loss: 2.7633 (2.8122) grad_norm: 2.2606 (2.2761) time: 0.5035 [2021-03-26 21:30:57 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 80/1251] eta: 0:10:47 lr: 0.000140 loss: 2.8208 (2.8506) grad_norm: 2.3785 (2.2891) time: 0.4991 [2021-03-26 21:31:02 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 90/1251] eta: 0:10:36 lr: 0.000140 loss: 3.0675 (2.8648) grad_norm: 2.2908 (2.2930) time: 0.5043 [2021-03-26 21:31:07 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 100/1251] eta: 0:10:25 lr: 0.000140 loss: 3.0675 (2.8876) grad_norm: 2.2908 (2.2964) time: 0.5061 [2021-03-26 21:31:13 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 110/1251] eta: 0:10:16 lr: 0.000140 loss: 3.0249 (2.8938) grad_norm: 2.1936 (2.2869) time: 0.5053 [2021-03-26 21:31:18 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 120/1251] eta: 0:10:09 lr: 0.000140 loss: 2.8062 (2.8798) grad_norm: 2.2412 (2.2904) time: 0.5121 [2021-03-26 21:31:23 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 130/1251] eta: 0:10:01 lr: 0.000140 loss: 2.8062 (2.8846) grad_norm: 2.2707 (2.2880) time: 0.5183 [2021-03-26 21:31:28 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 140/1251] eta: 0:09:53 lr: 0.000140 loss: 3.1285 (2.8812) grad_norm: 2.2707 (2.2906) time: 0.5087 [2021-03-26 21:31:33 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 150/1251] eta: 0:09:46 lr: 0.000140 loss: 3.0499 (2.8773) grad_norm: 2.1563 (2.2792) time: 0.5019 [2021-03-26 21:31:38 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 160/1251] eta: 0:09:37 lr: 0.000140 loss: 3.1180 (2.9045) grad_norm: 2.2333 (2.2911) time: 0.4974 [2021-03-26 21:31:43 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 170/1251] eta: 0:09:31 lr: 0.000140 loss: 3.1180 (2.9114) grad_norm: 2.3331 (2.2928) time: 0.4996 [2021-03-26 21:31:48 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 180/1251] eta: 0:09:24 lr: 0.000140 loss: 3.1187 (2.9211) grad_norm: 2.3214 (2.3053) time: 0.5071 [2021-03-26 21:31:53 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 190/1251] eta: 0:09:19 lr: 0.000140 loss: 3.0598 (2.9085) grad_norm: 2.3492 (2.3064) time: 0.5134 [2021-03-26 21:31:58 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 200/1251] eta: 0:09:12 lr: 0.000140 loss: 2.8299 (2.9134) grad_norm: 2.3109 (2.3072) time: 0.5108 [2021-03-26 21:32:03 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 210/1251] eta: 0:09:06 lr: 0.000140 loss: 3.0952 (2.9095) grad_norm: 2.3311 (2.3157) time: 0.5033 [2021-03-26 21:32:08 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 220/1251] eta: 0:08:59 lr: 0.000140 loss: 3.0477 (2.9172) grad_norm: 2.3509 (2.3265) time: 0.5042 [2021-03-26 21:32:13 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 230/1251] eta: 0:08:53 lr: 0.000140 loss: 3.0318 (2.9141) grad_norm: 2.3509 (2.3290) time: 0.5033 [2021-03-26 21:32:18 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 240/1251] eta: 0:08:48 lr: 0.000140 loss: 2.9721 (2.9174) grad_norm: 2.2838 (2.3272) time: 0.5074 [2021-03-26 21:32:24 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 250/1251] eta: 0:08:42 lr: 0.000140 loss: 2.9400 (2.9132) grad_norm: 2.2818 (2.3300) time: 0.5133 [2021-03-26 21:32:29 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 260/1251] eta: 0:08:36 lr: 0.000140 loss: 2.8524 (2.9139) grad_norm: 2.3990 (2.3317) time: 0.5092 [2021-03-26 21:32:34 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 270/1251] eta: 0:08:30 lr: 0.000140 loss: 2.8775 (2.9154) grad_norm: 2.2951 (2.3280) time: 0.5033 [2021-03-26 21:32:39 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 280/1251] eta: 0:08:25 lr: 0.000140 loss: 2.8141 (2.9137) grad_norm: 2.2156 (2.3256) time: 0.5083 [2021-03-26 21:32:44 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 290/1251] eta: 0:08:19 lr: 0.000140 loss: 3.1022 (2.9229) grad_norm: 2.2489 (2.3324) time: 0.5102 [2021-03-26 21:32:49 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 300/1251] eta: 0:08:13 lr: 0.000140 loss: 3.0556 (2.9228) grad_norm: 2.3816 (2.3345) time: 0.5037 [2021-03-26 21:32:54 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 310/1251] eta: 0:08:08 lr: 0.000140 loss: 2.9862 (2.9204) grad_norm: 2.3315 (2.3345) time: 0.5054 [2021-03-26 21:32:59 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 320/1251] eta: 0:08:03 lr: 0.000140 loss: 2.8685 (2.9140) grad_norm: 2.2390 (2.3311) time: 0.5166 [2021-03-26 21:33:04 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 330/1251] eta: 0:07:57 lr: 0.000140 loss: 2.7874 (2.9128) grad_norm: 2.1807 (2.3331) time: 0.5120 [2021-03-26 21:33:09 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 340/1251] eta: 0:07:51 lr: 0.000140 loss: 3.0121 (2.9188) grad_norm: 2.3802 (2.3395) time: 0.5022 [2021-03-26 21:33:14 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 350/1251] eta: 0:07:46 lr: 0.000140 loss: 3.0121 (2.9167) grad_norm: 2.3685 (2.3400) time: 0.5066 [2021-03-26 21:33:19 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 360/1251] eta: 0:07:40 lr: 0.000140 loss: 2.9071 (2.9192) grad_norm: 2.3094 (2.3419) time: 0.5041 [2021-03-26 21:33:24 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 370/1251] eta: 0:07:35 lr: 0.000140 loss: 3.0904 (2.9232) grad_norm: 2.3486 (2.3426) time: 0.4970 [2021-03-26 21:33:29 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 380/1251] eta: 0:07:29 lr: 0.000140 loss: 3.0587 (2.9168) grad_norm: 2.3835 (2.3413) time: 0.4999 [2021-03-26 21:33:34 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 390/1251] eta: 0:07:24 lr: 0.000140 loss: 2.6053 (2.9110) grad_norm: 2.2666 (2.3426) time: 0.5041 [2021-03-26 21:33:39 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 400/1251] eta: 0:07:18 lr: 0.000140 loss: 2.6199 (2.9060) grad_norm: 2.3132 (2.3495) time: 0.5024 [2021-03-26 21:33:44 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 410/1251] eta: 0:07:13 lr: 0.000139 loss: 2.8144 (2.9051) grad_norm: 2.3655 (2.3505) time: 0.5040 [2021-03-26 21:33:50 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 420/1251] eta: 0:07:08 lr: 0.000139 loss: 2.8653 (2.8993) grad_norm: 2.1288 (2.3440) time: 0.5046 [2021-03-26 21:33:55 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 430/1251] eta: 0:07:03 lr: 0.000139 loss: 2.6405 (2.8915) grad_norm: 2.1686 (2.3446) time: 0.5097 [2021-03-26 21:34:00 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 440/1251] eta: 0:06:57 lr: 0.000139 loss: 2.7617 (2.8889) grad_norm: 2.2772 (2.3456) time: 0.5100 [2021-03-26 21:34:05 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 450/1251] eta: 0:06:52 lr: 0.000139 loss: 2.8960 (2.8857) grad_norm: 2.3616 (2.3478) time: 0.5046 [2021-03-26 21:34:10 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 460/1251] eta: 0:06:47 lr: 0.000139 loss: 2.9341 (2.8874) grad_norm: 2.3616 (2.3474) time: 0.5083 [2021-03-26 21:34:15 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 470/1251] eta: 0:06:42 lr: 0.000139 loss: 2.9523 (2.8898) grad_norm: 2.4159 (2.3493) time: 0.5153 [2021-03-26 21:34:20 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 480/1251] eta: 0:06:36 lr: 0.000139 loss: 3.0750 (2.8938) grad_norm: 2.2598 (2.3458) time: 0.5119 [2021-03-26 21:34:25 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 490/1251] eta: 0:06:31 lr: 0.000139 loss: 3.0570 (2.8969) grad_norm: 2.1517 (2.3425) time: 0.5021 [2021-03-26 21:34:30 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 500/1251] eta: 0:06:26 lr: 0.000139 loss: 2.8286 (2.8929) grad_norm: 2.1517 (2.3416) time: 0.5012 [2021-03-26 21:34:35 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 510/1251] eta: 0:06:20 lr: 0.000139 loss: 2.8202 (2.8959) grad_norm: 2.1778 (2.3397) time: 0.5018 [2021-03-26 21:34:40 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 520/1251] eta: 0:06:15 lr: 0.000139 loss: 3.0039 (2.8982) grad_norm: 2.2743 (2.3402) time: 0.5051 [2021-03-26 21:34:45 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 530/1251] eta: 0:06:10 lr: 0.000139 loss: 3.0801 (2.8976) grad_norm: 2.3171 (2.3519) time: 0.5066 [2021-03-26 21:34:50 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 540/1251] eta: 0:06:04 lr: 0.000139 loss: 2.9781 (2.9006) grad_norm: 2.3171 (2.3522) time: 0.5044 [2021-03-26 21:34:56 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 550/1251] eta: 0:05:59 lr: 0.000139 loss: 2.8879 (2.9025) grad_norm: 2.2404 (2.3510) time: 0.5124 [2021-03-26 21:35:01 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 560/1251] eta: 0:05:54 lr: 0.000139 loss: 3.0525 (2.9050) grad_norm: 2.1598 (2.3502) time: 0.5104 [2021-03-26 21:35:06 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 570/1251] eta: 0:05:49 lr: 0.000139 loss: 3.0816 (2.9078) grad_norm: 2.2715 (2.3555) time: 0.5024 [2021-03-26 21:35:11 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 580/1251] eta: 0:05:44 lr: 0.000139 loss: 3.1027 (2.9069) grad_norm: 2.2610 (2.3546) time: 0.5024 [2021-03-26 21:35:16 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 590/1251] eta: 0:05:38 lr: 0.000139 loss: 2.8470 (2.9050) grad_norm: 2.2062 (2.3525) time: 0.5024 [2021-03-26 21:35:21 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 600/1251] eta: 0:05:33 lr: 0.000139 loss: 2.7935 (2.9006) grad_norm: 2.3109 (2.3534) time: 0.5034 [2021-03-26 21:35:26 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 610/1251] eta: 0:05:28 lr: 0.000139 loss: 2.9176 (2.9032) grad_norm: 2.3683 (2.3589) time: 0.4988 [2021-03-26 21:35:31 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 620/1251] eta: 0:05:23 lr: 0.000139 loss: 3.0799 (2.9050) grad_norm: 2.3781 (2.3585) time: 0.5017 [2021-03-26 21:35:36 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 630/1251] eta: 0:05:17 lr: 0.000139 loss: 3.1329 (2.9077) grad_norm: 2.3155 (2.3590) time: 0.5045 [2021-03-26 21:35:41 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 640/1251] eta: 0:05:12 lr: 0.000139 loss: 3.0762 (2.9092) grad_norm: 2.2710 (2.3689) time: 0.5083 [2021-03-26 21:35:46 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 650/1251] eta: 0:05:07 lr: 0.000139 loss: 3.0684 (2.9095) grad_norm: 2.2705 (2.3702) time: 0.5052 [2021-03-26 21:35:51 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 660/1251] eta: 0:05:02 lr: 0.000139 loss: 3.0290 (2.9104) grad_norm: 2.3812 (2.3760) time: 0.5029 [2021-03-26 21:35:56 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 670/1251] eta: 0:04:57 lr: 0.000139 loss: 3.0132 (2.9095) grad_norm: 2.4574 (2.3784) time: 0.5073 [2021-03-26 21:36:01 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 680/1251] eta: 0:04:52 lr: 0.000139 loss: 2.9714 (2.9087) grad_norm: 2.3619 (2.3815) time: 0.5088 [2021-03-26 21:36:06 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 690/1251] eta: 0:04:46 lr: 0.000139 loss: 2.9714 (2.9105) grad_norm: 2.3778 (2.3829) time: 0.5060 [2021-03-26 21:36:11 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 700/1251] eta: 0:04:41 lr: 0.000139 loss: 2.9637 (2.9088) grad_norm: 2.3272 (2.3817) time: 0.4954 [2021-03-26 21:36:16 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 710/1251] eta: 0:04:36 lr: 0.000139 loss: 2.9198 (2.9062) grad_norm: 2.2286 (2.3788) time: 0.4986 [2021-03-26 21:36:21 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 720/1251] eta: 0:04:31 lr: 0.000139 loss: 3.0304 (2.9087) grad_norm: 2.1897 (2.3773) time: 0.5094 [2021-03-26 21:36:26 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 730/1251] eta: 0:04:26 lr: 0.000139 loss: 2.8580 (2.9066) grad_norm: 2.1436 (2.3740) time: 0.5138 [2021-03-26 21:36:32 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 740/1251] eta: 0:04:21 lr: 0.000139 loss: 2.7453 (2.9053) grad_norm: 2.1421 (2.3719) time: 0.5160 [2021-03-26 21:36:37 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 750/1251] eta: 0:04:16 lr: 0.000139 loss: 2.8631 (2.9033) grad_norm: 2.2722 (2.3721) time: 0.5121 [2021-03-26 21:36:42 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 760/1251] eta: 0:04:10 lr: 0.000139 loss: 2.7044 (2.9013) grad_norm: 2.2722 (2.3703) time: 0.5052 [2021-03-26 21:36:47 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 770/1251] eta: 0:04:05 lr: 0.000138 loss: 2.7845 (2.9003) grad_norm: 2.1334 (2.3704) time: 0.5026 [2021-03-26 21:36:52 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 780/1251] eta: 0:04:00 lr: 0.000138 loss: 2.7845 (2.8986) grad_norm: 2.2336 (2.3695) time: 0.5019 [2021-03-26 21:36:57 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 790/1251] eta: 0:03:55 lr: 0.000138 loss: 2.5338 (2.8928) grad_norm: 2.3751 (2.3702) time: 0.5039 [2021-03-26 21:37:02 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 800/1251] eta: 0:03:50 lr: 0.000138 loss: 2.5742 (2.8920) grad_norm: 2.3656 (2.3698) time: 0.5036 [2021-03-26 21:37:07 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 810/1251] eta: 0:03:45 lr: 0.000138 loss: 2.9285 (2.8921) grad_norm: 2.3519 (2.3699) time: 0.5030 [2021-03-26 21:37:12 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 820/1251] eta: 0:03:40 lr: 0.000138 loss: 2.9886 (2.8920) grad_norm: 2.2429 (2.3695) time: 0.5040 [2021-03-26 21:37:17 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 830/1251] eta: 0:03:34 lr: 0.000138 loss: 3.0254 (2.8938) grad_norm: 2.1966 (2.3690) time: 0.5082 [2021-03-26 21:37:22 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 840/1251] eta: 0:03:29 lr: 0.000138 loss: 3.1158 (2.8960) grad_norm: 2.3215 (2.3691) time: 0.5086 [2021-03-26 21:37:27 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 850/1251] eta: 0:03:24 lr: 0.000138 loss: 3.0948 (2.8952) grad_norm: 2.3196 (2.3688) time: 0.5044 [2021-03-26 21:37:32 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 860/1251] eta: 0:03:19 lr: 0.000138 loss: 2.9612 (2.8958) grad_norm: 2.3141 (2.3686) time: 0.5091 [2021-03-26 21:37:37 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 870/1251] eta: 0:03:14 lr: 0.000138 loss: 2.9612 (2.8957) grad_norm: 2.3009 (2.3685) time: 0.5133 [2021-03-26 21:37:42 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 880/1251] eta: 0:03:09 lr: 0.000138 loss: 2.7834 (2.8931) grad_norm: 2.2401 (2.3695) time: 0.5032 [2021-03-26 21:37:47 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 890/1251] eta: 0:03:04 lr: 0.000138 loss: 2.8299 (2.8933) grad_norm: 2.0833 (2.3698) time: 0.4997 [2021-03-26 21:37:52 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 900/1251] eta: 0:02:59 lr: 0.000138 loss: 2.9957 (2.8947) grad_norm: 2.1996 (2.3699) time: 0.5011 [2021-03-26 21:37:57 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 910/1251] eta: 0:02:53 lr: 0.000138 loss: 3.0137 (2.8947) grad_norm: 2.4151 (2.3698) time: 0.4997 [2021-03-26 21:38:02 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 920/1251] eta: 0:02:48 lr: 0.000138 loss: 2.8858 (2.8939) grad_norm: 2.3181 (2.3689) time: 0.5027 [2021-03-26 21:38:07 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 930/1251] eta: 0:02:43 lr: 0.000138 loss: 2.8616 (2.8935) grad_norm: 2.2300 (2.3683) time: 0.4986 [2021-03-26 21:38:12 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 940/1251] eta: 0:02:38 lr: 0.000138 loss: 2.8497 (2.8920) grad_norm: 2.2764 (2.3678) time: 0.5017 [2021-03-26 21:38:17 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 950/1251] eta: 0:02:33 lr: 0.000138 loss: 2.8810 (2.8922) grad_norm: 2.2764 (2.3679) time: 0.5044 [2021-03-26 21:38:22 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 960/1251] eta: 0:02:28 lr: 0.000138 loss: 2.9530 (2.8927) grad_norm: 2.2529 (2.3671) time: 0.4987 [2021-03-26 21:38:27 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 970/1251] eta: 0:02:23 lr: 0.000138 loss: 3.0630 (2.8926) grad_norm: 2.3019 (2.3669) time: 0.4969 [2021-03-26 21:38:32 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 980/1251] eta: 0:02:18 lr: 0.000138 loss: 2.9896 (2.8920) grad_norm: 2.4972 (2.3707) time: 0.5054 [2021-03-26 21:38:37 swin_small_patch4_window7_224] INFO: Epoch: [229] [ 990/1251] eta: 0:02:12 lr: 0.000138 loss: 2.8431 (2.8902) grad_norm: 2.4239 (2.3709) time: 0.5035 [2021-03-26 21:38:43 swin_small_patch4_window7_224] INFO: Epoch: [229] [1000/1251] eta: 0:02:07 lr: 0.000138 loss: 2.9530 (2.8918) grad_norm: 2.3523 (2.3706) time: 0.5024 [2021-03-26 21:38:48 swin_small_patch4_window7_224] INFO: Epoch: [229] [1010/1251] eta: 0:02:02 lr: 0.000138 loss: 2.9530 (2.8917) grad_norm: 2.3251 (2.3698) time: 0.5072 [2021-03-26 21:38:53 swin_small_patch4_window7_224] INFO: Epoch: [229] [1020/1251] eta: 0:01:57 lr: 0.000138 loss: 2.9883 (2.8937) grad_norm: 2.3229 (2.3694) time: 0.5065 [2021-03-26 21:38:58 swin_small_patch4_window7_224] INFO: Epoch: [229] [1030/1251] eta: 0:01:52 lr: 0.000138 loss: 2.9624 (2.8940) grad_norm: 2.3023 (2.3687) time: 0.5036 [2021-03-26 21:39:03 swin_small_patch4_window7_224] INFO: Epoch: [229] [1040/1251] eta: 0:01:47 lr: 0.000138 loss: 2.8394 (2.8926) grad_norm: 2.2733 (2.3678) time: 0.4993 [2021-03-26 21:39:08 swin_small_patch4_window7_224] INFO: Epoch: [229] [1050/1251] eta: 0:01:42 lr: 0.000138 loss: 2.9418 (2.8941) grad_norm: 2.2914 (2.3682) time: 0.5027 [2021-03-26 21:39:13 swin_small_patch4_window7_224] INFO: Epoch: [229] [1060/1251] eta: 0:01:37 lr: 0.000138 loss: 3.0481 (2.8951) grad_norm: 2.3914 (2.3700) time: 0.5042 [2021-03-26 21:39:18 swin_small_patch4_window7_224] INFO: Epoch: [229] [1070/1251] eta: 0:01:32 lr: 0.000138 loss: 2.9715 (2.8950) grad_norm: 2.4786 (2.3708) time: 0.5031 [2021-03-26 21:39:23 swin_small_patch4_window7_224] INFO: Epoch: [229] [1080/1251] eta: 0:01:27 lr: 0.000138 loss: 3.0145 (2.8968) grad_norm: 2.3822 (2.3728) time: 0.5032 [2021-03-26 21:39:28 swin_small_patch4_window7_224] INFO: Epoch: [229] [1090/1251] eta: 0:01:21 lr: 0.000138 loss: 3.0413 (2.8977) grad_norm: 2.4027 (2.3752) time: 0.5066 [2021-03-26 21:39:33 swin_small_patch4_window7_224] INFO: Epoch: [229] [1100/1251] eta: 0:01:16 lr: 0.000138 loss: 3.1005 (2.8992) grad_norm: 2.4639 (2.3768) time: 0.5033 [2021-03-26 21:39:38 swin_small_patch4_window7_224] INFO: Epoch: [229] [1110/1251] eta: 0:01:11 lr: 0.000138 loss: 3.0766 (2.8988) grad_norm: 2.2874 (2.3759) time: 0.4977 [2021-03-26 21:39:43 swin_small_patch4_window7_224] INFO: Epoch: [229] [1120/1251] eta: 0:01:06 lr: 0.000138 loss: 2.9562 (2.8994) grad_norm: 2.2715 (2.3751) time: 0.4967 [2021-03-26 21:39:48 swin_small_patch4_window7_224] INFO: Epoch: [229] [1130/1251] eta: 0:01:01 lr: 0.000137 loss: 2.9947 (2.9005) grad_norm: 2.1708 (2.3732) time: 0.4960 [2021-03-26 21:39:53 swin_small_patch4_window7_224] INFO: Epoch: [229] [1140/1251] eta: 0:00:56 lr: 0.000137 loss: 2.9947 (2.8998) grad_norm: 2.1708 (2.3803) time: 0.5012 [2021-03-26 21:39:58 swin_small_patch4_window7_224] INFO: Epoch: [229] [1150/1251] eta: 0:00:51 lr: 0.000137 loss: 3.0672 (2.9006) grad_norm: 2.5827 (2.3817) time: 0.5062 [2021-03-26 21:40:03 swin_small_patch4_window7_224] INFO: Epoch: [229] [1160/1251] eta: 0:00:46 lr: 0.000137 loss: 3.2146 (2.9036) grad_norm: 2.5827 (2.3836) time: 0.5001 [2021-03-26 21:40:08 swin_small_patch4_window7_224] INFO: Epoch: [229] [1170/1251] eta: 0:00:41 lr: 0.000137 loss: 3.1569 (2.9050) grad_norm: 2.3884 (2.3831) time: 0.4939 [2021-03-26 21:40:13 swin_small_patch4_window7_224] INFO: Epoch: [229] [1180/1251] eta: 0:00:36 lr: 0.000137 loss: 3.0304 (2.9050) grad_norm: 2.3269 (2.3828) time: 0.5001 [2021-03-26 21:40:18 swin_small_patch4_window7_224] INFO: Epoch: [229] [1190/1251] eta: 0:00:30 lr: 0.000137 loss: 3.1440 (2.9057) grad_norm: 2.3997 (2.3836) time: 0.5042 [2021-03-26 21:40:23 swin_small_patch4_window7_224] INFO: Epoch: [229] [1200/1251] eta: 0:00:25 lr: 0.000137 loss: 3.2169 (2.9076) grad_norm: 2.3997 (2.3843) time: 0.5031 [2021-03-26 21:40:28 swin_small_patch4_window7_224] INFO: Epoch: [229] [1210/1251] eta: 0:00:20 lr: 0.000137 loss: 3.0399 (2.9076) grad_norm: 2.4022 (2.3857) time: 0.5075 [2021-03-26 21:40:33 swin_small_patch4_window7_224] INFO: Epoch: [229] [1220/1251] eta: 0:00:15 lr: 0.000137 loss: 2.7362 (2.9053) grad_norm: 2.3330 (2.3850) time: 0.5067 [2021-03-26 21:40:38 swin_small_patch4_window7_224] INFO: Epoch: [229] [1230/1251] eta: 0:00:10 lr: 0.000137 loss: 2.9604 (2.9063) grad_norm: 2.2372 (2.3849) time: 0.5026 [2021-03-26 21:40:43 swin_small_patch4_window7_224] INFO: Epoch: [229] [1240/1251] eta: 0:00:05 lr: 0.000137 loss: 2.9856 (2.9070) grad_norm: 2.2176 (2.3838) time: 0.4972 [2021-03-26 21:40:48 swin_small_patch4_window7_224] INFO: Epoch: [229] [1250/1251] eta: 0:00:00 lr: 0.000137 loss: 2.8348 (2.9057) grad_norm: 2.2176 (2.3840) time: 0.4908 [2021-03-26 21:40:59 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:00 loss: 0.5561 (0.5561) acc1: 90.6250 (90.6250) acc5: 96.8750 (96.8750) [2021-03-26 21:41:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:14 loss: 0.7335 (0.7167) acc1: 84.3750 (84.5170) acc5: 95.3125 (95.5966) [2021-03-26 21:41:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7690 (0.7902) acc1: 81.2500 (82.3661) acc5: 95.3125 (95.5357) [2021-03-26 21:41:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.7878 (0.7907) acc1: 78.1250 (81.9556) acc5: 95.3125 (95.7157) [2021-03-26 21:41:05 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7720 (0.8001) acc1: 79.6875 (81.5168) acc5: 95.3125 (95.6174) [2021-03-26 21:41:06 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7620 (0.7952) acc1: 78.1250 (81.2160) acc5: 95.3125 (95.7440) [2021-03-26 21:41:21 swin_small_patch4_window7_224] INFO: * Acc@1 81.752 Acc@5 95.844 loss 0.778 [2021-03-26 21:41:21 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-26 21:41:21 swin_small_patch4_window7_224] INFO: Max accuracy: 81.75% [2021-03-26 21:41:25 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 0/1251] eta: 1:28:35 lr: 0.000137 loss: 3.3477 (3.3477) grad_norm: 2.2516 (2.2516) time: 4.2490 [2021-03-26 21:41:30 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 10/1251] eta: 0:17:57 lr: 0.000137 loss: 3.2888 (3.0879) grad_norm: 2.3927 (2.4047) time: 0.8684 [2021-03-26 21:41:35 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 20/1251] eta: 0:14:21 lr: 0.000137 loss: 2.9596 (2.8839) grad_norm: 2.2905 (2.4378) time: 0.5222 [2021-03-26 21:41:40 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 30/1251] eta: 0:12:57 lr: 0.000137 loss: 2.8219 (2.8859) grad_norm: 2.2321 (2.5519) time: 0.5099 [2021-03-26 21:41:46 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 40/1251] eta: 0:12:14 lr: 0.000137 loss: 3.0341 (2.8875) grad_norm: 2.3788 (2.5006) time: 0.5085 [2021-03-26 21:41:51 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 50/1251] eta: 0:11:48 lr: 0.000137 loss: 2.8841 (2.8856) grad_norm: 2.3512 (2.4759) time: 0.5164 [2021-03-26 21:41:56 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 60/1251] eta: 0:11:26 lr: 0.000137 loss: 2.8841 (2.8752) grad_norm: 2.1673 (2.4360) time: 0.5149 [2021-03-26 21:42:01 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 70/1251] eta: 0:11:08 lr: 0.000137 loss: 2.6124 (2.8525) grad_norm: 2.1673 (2.4275) time: 0.5048 [2021-03-26 21:42:06 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 80/1251] eta: 0:10:54 lr: 0.000137 loss: 2.8573 (2.8495) grad_norm: 2.3820 (2.5125) time: 0.5049 [2021-03-26 21:42:11 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 90/1251] eta: 0:10:43 lr: 0.000137 loss: 2.9367 (2.8593) grad_norm: 2.3022 (2.4927) time: 0.5132 [2021-03-26 21:42:16 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 100/1251] eta: 0:10:31 lr: 0.000137 loss: 2.9482 (2.8680) grad_norm: 2.2072 (2.4629) time: 0.5063 [2021-03-26 21:42:21 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 110/1251] eta: 0:10:20 lr: 0.000137 loss: 2.9324 (2.8688) grad_norm: 2.2409 (2.4849) time: 0.4941 [2021-03-26 21:42:26 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 120/1251] eta: 0:10:11 lr: 0.000137 loss: 2.8620 (2.8656) grad_norm: 2.4813 (2.4901) time: 0.5000 [2021-03-26 21:42:31 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 130/1251] eta: 0:10:03 lr: 0.000137 loss: 2.8620 (2.8651) grad_norm: 2.4782 (2.4910) time: 0.5093 [2021-03-26 21:42:36 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 140/1251] eta: 0:09:55 lr: 0.000137 loss: 3.0545 (2.8728) grad_norm: 2.4062 (2.4938) time: 0.5113 [2021-03-26 21:42:41 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 150/1251] eta: 0:09:48 lr: 0.000137 loss: 3.0572 (2.8780) grad_norm: 2.3288 (2.4862) time: 0.5092 [2021-03-26 21:42:46 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 160/1251] eta: 0:09:40 lr: 0.000137 loss: 2.9811 (2.8814) grad_norm: 2.3288 (2.4777) time: 0.5027 [2021-03-26 21:42:51 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 170/1251] eta: 0:09:33 lr: 0.000137 loss: 2.9731 (2.8831) grad_norm: 2.2539 (2.4710) time: 0.5037 [2021-03-26 21:42:57 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 180/1251] eta: 0:09:27 lr: 0.000137 loss: 2.9363 (2.8713) grad_norm: 2.2879 (2.4648) time: 0.5124 [2021-03-26 21:43:02 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 190/1251] eta: 0:09:20 lr: 0.000137 loss: 2.9363 (2.8658) grad_norm: 2.2879 (2.4557) time: 0.5083 [2021-03-26 21:43:07 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 200/1251] eta: 0:09:14 lr: 0.000137 loss: 2.9828 (2.8721) grad_norm: 2.3750 (2.4702) time: 0.5055 [2021-03-26 21:43:12 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 210/1251] eta: 0:09:08 lr: 0.000137 loss: 2.9774 (2.8769) grad_norm: 2.4595 (2.4717) time: 0.5088 [2021-03-26 21:43:17 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 220/1251] eta: 0:09:01 lr: 0.000137 loss: 2.9774 (2.8781) grad_norm: 2.3575 (2.4601) time: 0.5053 [2021-03-26 21:43:22 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 230/1251] eta: 0:08:55 lr: 0.000137 loss: 2.8444 (2.8674) grad_norm: 2.2419 (2.4644) time: 0.5015 [2021-03-26 21:43:27 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 240/1251] eta: 0:08:49 lr: 0.000136 loss: 2.6522 (2.8605) grad_norm: 2.3550 (2.4598) time: 0.5026 [2021-03-26 21:43:32 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 250/1251] eta: 0:08:43 lr: 0.000136 loss: 2.6666 (2.8563) grad_norm: 2.3744 (2.4622) time: 0.5068 [2021-03-26 21:43:37 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 260/1251] eta: 0:08:37 lr: 0.000136 loss: 2.8700 (2.8518) grad_norm: 2.3816 (2.4624) time: 0.5051 [2021-03-26 21:43:42 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 270/1251] eta: 0:08:31 lr: 0.000136 loss: 2.8705 (2.8524) grad_norm: 2.2086 (2.4574) time: 0.5011 [2021-03-26 21:43:47 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 280/1251] eta: 0:08:25 lr: 0.000136 loss: 3.0167 (2.8575) grad_norm: 2.2011 (2.4547) time: 0.4986 [2021-03-26 21:43:52 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 290/1251] eta: 0:08:19 lr: 0.000136 loss: 3.0167 (2.8564) grad_norm: 2.2561 (2.4497) time: 0.4975 [2021-03-26 21:43:57 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 300/1251] eta: 0:08:13 lr: 0.000136 loss: 2.7841 (2.8519) grad_norm: 2.2887 (inf) time: 0.4949 [2021-03-26 21:44:02 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 310/1251] eta: 0:08:07 lr: 0.000136 loss: 2.8871 (2.8554) grad_norm: 2.3435 (inf) time: 0.4950 [2021-03-26 21:44:07 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 320/1251] eta: 0:08:01 lr: 0.000136 loss: 2.9862 (2.8575) grad_norm: 2.5096 (inf) time: 0.4991 [2021-03-26 21:44:12 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 330/1251] eta: 0:07:56 lr: 0.000136 loss: 2.7345 (2.8508) grad_norm: 2.5096 (inf) time: 0.5010 [2021-03-26 21:44:17 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 340/1251] eta: 0:07:50 lr: 0.000136 loss: 2.7771 (2.8574) grad_norm: 2.3793 (inf) time: 0.5021 [2021-03-26 21:44:22 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 350/1251] eta: 0:07:44 lr: 0.000136 loss: 3.0039 (2.8575) grad_norm: 2.2129 (inf) time: 0.4980 [2021-03-26 21:44:27 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 360/1251] eta: 0:07:39 lr: 0.000136 loss: 2.7589 (2.8540) grad_norm: 2.1418 (inf) time: 0.5015 [2021-03-26 21:44:32 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 370/1251] eta: 0:07:34 lr: 0.000136 loss: 2.7571 (2.8546) grad_norm: 2.2388 (inf) time: 0.5047 [2021-03-26 21:44:37 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 380/1251] eta: 0:07:28 lr: 0.000136 loss: 2.9008 (2.8554) grad_norm: 2.3472 (inf) time: 0.5001 [2021-03-26 21:44:42 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 390/1251] eta: 0:07:22 lr: 0.000136 loss: 2.7956 (2.8548) grad_norm: 2.3953 (inf) time: 0.4970 [2021-03-26 21:44:47 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 400/1251] eta: 0:07:17 lr: 0.000136 loss: 2.9801 (2.8579) grad_norm: 2.3188 (inf) time: 0.4981 [2021-03-26 21:44:52 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 410/1251] eta: 0:07:12 lr: 0.000136 loss: 2.9963 (2.8573) grad_norm: 2.3458 (inf) time: 0.5005 [2021-03-26 21:44:57 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 420/1251] eta: 0:07:06 lr: 0.000136 loss: 2.9702 (2.8594) grad_norm: 2.2286 (inf) time: 0.4983 [2021-03-26 21:45:02 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 430/1251] eta: 0:07:01 lr: 0.000136 loss: 2.9624 (2.8582) grad_norm: 2.1980 (inf) time: 0.4992 [2021-03-26 21:45:07 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 440/1251] eta: 0:06:55 lr: 0.000136 loss: 2.9257 (2.8566) grad_norm: 2.2902 (inf) time: 0.4994 [2021-03-26 21:45:12 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 450/1251] eta: 0:06:50 lr: 0.000136 loss: 2.9257 (2.8573) grad_norm: 2.3375 (inf) time: 0.4989 [2021-03-26 21:45:17 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 460/1251] eta: 0:06:45 lr: 0.000136 loss: 3.1167 (2.8584) grad_norm: 2.3375 (inf) time: 0.5000 [2021-03-26 21:45:22 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 470/1251] eta: 0:06:39 lr: 0.000136 loss: 3.2018 (2.8620) grad_norm: 2.4163 (inf) time: 0.5004 [2021-03-26 21:45:27 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 480/1251] eta: 0:06:34 lr: 0.000136 loss: 3.0366 (2.8636) grad_norm: 2.2910 (inf) time: 0.5007 [2021-03-26 21:45:32 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 490/1251] eta: 0:06:29 lr: 0.000136 loss: 2.9678 (2.8648) grad_norm: 2.2466 (inf) time: 0.5046 [2021-03-26 21:45:37 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 500/1251] eta: 0:06:24 lr: 0.000136 loss: 3.1043 (2.8717) grad_norm: 2.3946 (inf) time: 0.5063 [2021-03-26 21:45:42 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 510/1251] eta: 0:06:18 lr: 0.000136 loss: 3.0623 (2.8740) grad_norm: 2.3821 (inf) time: 0.5019 [2021-03-26 21:45:47 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 520/1251] eta: 0:06:13 lr: 0.000136 loss: 3.0614 (2.8749) grad_norm: 2.4625 (inf) time: 0.5108 [2021-03-26 21:45:52 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 530/1251] eta: 0:06:08 lr: 0.000136 loss: 2.9667 (2.8765) grad_norm: 2.3392 (inf) time: 0.5128 [2021-03-26 21:45:57 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 540/1251] eta: 0:06:03 lr: 0.000136 loss: 2.9893 (2.8765) grad_norm: 2.4174 (inf) time: 0.5045 [2021-03-26 21:46:02 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 550/1251] eta: 0:05:58 lr: 0.000136 loss: 3.0884 (2.8803) grad_norm: 2.3259 (inf) time: 0.5078 [2021-03-26 21:46:07 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 560/1251] eta: 0:05:53 lr: 0.000136 loss: 3.1384 (2.8855) grad_norm: 2.3295 (inf) time: 0.5090 [2021-03-26 21:46:12 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 570/1251] eta: 0:05:47 lr: 0.000136 loss: 3.1293 (2.8884) grad_norm: 2.3649 (inf) time: 0.5009 [2021-03-26 21:46:17 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 580/1251] eta: 0:05:42 lr: 0.000136 loss: 3.0527 (2.8907) grad_norm: 2.2451 (inf) time: 0.4990 [2021-03-26 21:46:22 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 590/1251] eta: 0:05:37 lr: 0.000136 loss: 2.9832 (2.8892) grad_norm: 2.3344 (inf) time: 0.5005 [2021-03-26 21:46:28 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 600/1251] eta: 0:05:32 lr: 0.000135 loss: 2.9832 (2.8893) grad_norm: 2.3949 (inf) time: 0.5077 [2021-03-26 21:46:33 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 610/1251] eta: 0:05:27 lr: 0.000135 loss: 3.0821 (2.8915) grad_norm: 2.3339 (inf) time: 0.5131 [2021-03-26 21:46:38 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 620/1251] eta: 0:05:22 lr: 0.000135 loss: 2.7810 (2.8886) grad_norm: 2.4056 (inf) time: 0.5093 [2021-03-26 21:46:43 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 630/1251] eta: 0:05:16 lr: 0.000135 loss: 2.7040 (2.8896) grad_norm: 2.4256 (inf) time: 0.5058 [2021-03-26 21:46:48 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 640/1251] eta: 0:05:11 lr: 0.000135 loss: 3.0041 (2.8898) grad_norm: 2.5042 (inf) time: 0.5094 [2021-03-26 21:46:53 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 650/1251] eta: 0:05:06 lr: 0.000135 loss: 3.1420 (2.8910) grad_norm: 2.3933 (inf) time: 0.5053 [2021-03-26 21:46:58 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 660/1251] eta: 0:05:01 lr: 0.000135 loss: 2.9420 (2.8880) grad_norm: 2.3933 (inf) time: 0.4980 [2021-03-26 21:47:03 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 670/1251] eta: 0:04:56 lr: 0.000135 loss: 2.9531 (2.8896) grad_norm: 2.3705 (inf) time: 0.5018 [2021-03-26 21:47:08 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 680/1251] eta: 0:04:51 lr: 0.000135 loss: 2.9531 (2.8884) grad_norm: 2.4940 (inf) time: 0.5044 [2021-03-26 21:47:13 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 690/1251] eta: 0:04:46 lr: 0.000135 loss: 2.6486 (2.8847) grad_norm: 2.4677 (inf) time: 0.5038 [2021-03-26 21:47:18 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 700/1251] eta: 0:04:40 lr: 0.000135 loss: 2.8268 (2.8845) grad_norm: 2.4045 (inf) time: 0.5031 [2021-03-26 21:47:23 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 710/1251] eta: 0:04:35 lr: 0.000135 loss: 3.1613 (2.8891) grad_norm: 2.3910 (inf) time: 0.5057 [2021-03-26 21:47:28 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 720/1251] eta: 0:04:30 lr: 0.000135 loss: 3.2140 (2.8924) grad_norm: 2.3477 (inf) time: 0.5034 [2021-03-26 21:47:33 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 730/1251] eta: 0:04:25 lr: 0.000135 loss: 2.9893 (2.8912) grad_norm: 2.2519 (inf) time: 0.5010 [2021-03-26 21:47:38 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 740/1251] eta: 0:04:20 lr: 0.000135 loss: 2.9521 (2.8915) grad_norm: 2.3087 (inf) time: 0.5082 [2021-03-26 21:47:43 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 750/1251] eta: 0:04:15 lr: 0.000135 loss: 3.1237 (2.8945) grad_norm: 2.4966 (inf) time: 0.5115 [2021-03-26 21:47:48 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 760/1251] eta: 0:04:10 lr: 0.000135 loss: 3.0375 (2.8910) grad_norm: 2.4719 (inf) time: 0.5053 [2021-03-26 21:47:54 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 770/1251] eta: 0:04:05 lr: 0.000135 loss: 2.8199 (2.8931) grad_norm: 2.2671 (inf) time: 0.5049 [2021-03-26 21:47:59 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 780/1251] eta: 0:03:59 lr: 0.000135 loss: 2.9249 (2.8904) grad_norm: 2.4678 (inf) time: 0.5038 [2021-03-26 21:48:04 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 790/1251] eta: 0:03:54 lr: 0.000135 loss: 2.9179 (2.8895) grad_norm: 2.2431 (inf) time: 0.5081 [2021-03-26 21:48:09 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 800/1251] eta: 0:03:49 lr: 0.000135 loss: 2.7823 (2.8892) grad_norm: 2.2697 (inf) time: 0.5124 [2021-03-26 21:48:14 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 810/1251] eta: 0:03:44 lr: 0.000135 loss: 2.7338 (2.8863) grad_norm: 2.3587 (inf) time: 0.5098 [2021-03-26 21:48:19 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 820/1251] eta: 0:03:39 lr: 0.000135 loss: 2.9163 (2.8868) grad_norm: 2.3587 (inf) time: 0.5064 [2021-03-26 21:48:24 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 830/1251] eta: 0:03:34 lr: 0.000135 loss: 2.8674 (2.8844) grad_norm: 2.3517 (inf) time: 0.5066 [2021-03-26 21:48:29 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 840/1251] eta: 0:03:29 lr: 0.000135 loss: 3.0283 (2.8849) grad_norm: 2.3447 (inf) time: 0.5070 [2021-03-26 21:48:34 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 850/1251] eta: 0:03:24 lr: 0.000135 loss: 3.2816 (2.8891) grad_norm: 2.3637 (inf) time: 0.5025 [2021-03-26 21:48:39 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 860/1251] eta: 0:03:19 lr: 0.000135 loss: 3.1560 (2.8893) grad_norm: 2.3744 (inf) time: 0.5086 [2021-03-26 21:48:44 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 870/1251] eta: 0:03:14 lr: 0.000135 loss: 2.8756 (2.8869) grad_norm: 2.3744 (inf) time: 0.5135 [2021-03-26 21:48:49 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 880/1251] eta: 0:03:08 lr: 0.000135 loss: 2.7650 (2.8875) grad_norm: 2.3569 (inf) time: 0.5113 [2021-03-26 21:48:55 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 890/1251] eta: 0:03:03 lr: 0.000135 loss: 3.0420 (2.8902) grad_norm: 2.3344 (inf) time: 0.5105 [2021-03-26 21:49:00 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 900/1251] eta: 0:02:58 lr: 0.000135 loss: 3.0420 (2.8870) grad_norm: 2.2469 (inf) time: 0.5052 [2021-03-26 21:49:05 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 910/1251] eta: 0:02:53 lr: 0.000135 loss: 2.7143 (2.8862) grad_norm: 2.3132 (inf) time: 0.5017 [2021-03-26 21:49:10 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 920/1251] eta: 0:02:48 lr: 0.000135 loss: 3.0581 (2.8872) grad_norm: 2.2705 (inf) time: 0.5039 [2021-03-26 21:49:15 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 930/1251] eta: 0:02:43 lr: 0.000135 loss: 2.9214 (2.8857) grad_norm: 2.2705 (inf) time: 0.5062 [2021-03-26 21:49:20 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 940/1251] eta: 0:02:38 lr: 0.000135 loss: 2.9751 (2.8894) grad_norm: 2.3196 (inf) time: 0.5007 [2021-03-26 21:49:25 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 950/1251] eta: 0:02:33 lr: 0.000135 loss: 3.0280 (2.8892) grad_norm: 2.2871 (inf) time: 0.5049 [2021-03-26 21:49:30 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 960/1251] eta: 0:02:28 lr: 0.000134 loss: 2.9014 (2.8890) grad_norm: 2.3036 (inf) time: 0.5055 [2021-03-26 21:49:35 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 970/1251] eta: 0:02:22 lr: 0.000134 loss: 2.9085 (2.8882) grad_norm: 2.3588 (inf) time: 0.4958 [2021-03-26 21:49:40 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 980/1251] eta: 0:02:17 lr: 0.000134 loss: 2.9036 (2.8883) grad_norm: 2.3295 (inf) time: 0.4977 [2021-03-26 21:49:45 swin_small_patch4_window7_224] INFO: Epoch: [230] [ 990/1251] eta: 0:02:12 lr: 0.000134 loss: 3.0898 (2.8900) grad_norm: 2.3751 (inf) time: 0.5021 [2021-03-26 21:49:50 swin_small_patch4_window7_224] INFO: Epoch: [230] [1000/1251] eta: 0:02:07 lr: 0.000134 loss: 3.1229 (2.8916) grad_norm: 2.4600 (inf) time: 0.5031 [2021-03-26 21:49:55 swin_small_patch4_window7_224] INFO: Epoch: [230] [1010/1251] eta: 0:02:02 lr: 0.000134 loss: 2.9696 (2.8908) grad_norm: 2.4604 (inf) time: 0.4999 [2021-03-26 21:50:00 swin_small_patch4_window7_224] INFO: Epoch: [230] [1020/1251] eta: 0:01:57 lr: 0.000134 loss: 2.9156 (2.8926) grad_norm: 2.3635 (inf) time: 0.4964 [2021-03-26 21:50:05 swin_small_patch4_window7_224] INFO: Epoch: [230] [1030/1251] eta: 0:01:52 lr: 0.000134 loss: 3.0261 (2.8938) grad_norm: 2.3387 (inf) time: 0.4993 [2021-03-26 21:50:10 swin_small_patch4_window7_224] INFO: Epoch: [230] [1040/1251] eta: 0:01:47 lr: 0.000134 loss: 2.8726 (2.8902) grad_norm: 2.3713 (inf) time: 0.5037 [2021-03-26 21:50:15 swin_small_patch4_window7_224] INFO: Epoch: [230] [1050/1251] eta: 0:01:42 lr: 0.000134 loss: 2.8137 (2.8902) grad_norm: 2.2992 (inf) time: 0.5029 [2021-03-26 21:50:20 swin_small_patch4_window7_224] INFO: Epoch: [230] [1060/1251] eta: 0:01:37 lr: 0.000134 loss: 3.0552 (2.8921) grad_norm: 2.3009 (inf) time: 0.5071 [2021-03-26 21:50:25 swin_small_patch4_window7_224] INFO: Epoch: [230] [1070/1251] eta: 0:01:31 lr: 0.000134 loss: 3.0427 (2.8913) grad_norm: 2.3009 (inf) time: 0.5045 [2021-03-26 21:50:30 swin_small_patch4_window7_224] INFO: Epoch: [230] [1080/1251] eta: 0:01:26 lr: 0.000134 loss: 2.9239 (2.8901) grad_norm: 2.4405 (inf) time: 0.4994 [2021-03-26 21:50:35 swin_small_patch4_window7_224] INFO: Epoch: [230] [1090/1251] eta: 0:01:21 lr: 0.000134 loss: 2.7849 (2.8891) grad_norm: 2.5652 (inf) time: 0.4995 [2021-03-26 21:50:40 swin_small_patch4_window7_224] INFO: Epoch: [230] [1100/1251] eta: 0:01:16 lr: 0.000134 loss: 3.0559 (2.8911) grad_norm: 2.4089 (inf) time: 0.5015 [2021-03-26 21:50:45 swin_small_patch4_window7_224] INFO: Epoch: [230] [1110/1251] eta: 0:01:11 lr: 0.000134 loss: 2.9410 (2.8900) grad_norm: 2.4089 (inf) time: 0.5050 [2021-03-26 21:50:50 swin_small_patch4_window7_224] INFO: Epoch: [230] [1120/1251] eta: 0:01:06 lr: 0.000134 loss: 2.7479 (2.8885) grad_norm: 2.4038 (inf) time: 0.5038 [2021-03-26 21:50:55 swin_small_patch4_window7_224] INFO: Epoch: [230] [1130/1251] eta: 0:01:01 lr: 0.000134 loss: 2.6006 (2.8868) grad_norm: 2.4786 (inf) time: 0.5034 [2021-03-26 21:51:00 swin_small_patch4_window7_224] INFO: Epoch: [230] [1140/1251] eta: 0:00:56 lr: 0.000134 loss: 2.8767 (2.8884) grad_norm: 2.4163 (inf) time: 0.4969 [2021-03-26 21:51:05 swin_small_patch4_window7_224] INFO: Epoch: [230] [1150/1251] eta: 0:00:51 lr: 0.000134 loss: 3.1345 (2.8903) grad_norm: 2.1826 (inf) time: 0.4918 [2021-03-26 21:51:10 swin_small_patch4_window7_224] INFO: Epoch: [230] [1160/1251] eta: 0:00:46 lr: 0.000134 loss: 3.0478 (2.8903) grad_norm: 2.1826 (inf) time: 0.4956 [2021-03-26 21:51:15 swin_small_patch4_window7_224] INFO: Epoch: [230] [1170/1251] eta: 0:00:41 lr: 0.000134 loss: 3.0119 (2.8912) grad_norm: 2.1732 (inf) time: 0.5026 [2021-03-26 21:51:20 swin_small_patch4_window7_224] INFO: Epoch: [230] [1180/1251] eta: 0:00:36 lr: 0.000134 loss: 3.0753 (2.8914) grad_norm: 2.2019 (inf) time: 0.5028 [2021-03-26 21:51:25 swin_small_patch4_window7_224] INFO: Epoch: [230] [1190/1251] eta: 0:00:30 lr: 0.000134 loss: 3.0127 (2.8927) grad_norm: 2.3067 (inf) time: 0.5024 [2021-03-26 21:51:30 swin_small_patch4_window7_224] INFO: Epoch: [230] [1200/1251] eta: 0:00:25 lr: 0.000134 loss: 3.0070 (2.8920) grad_norm: 2.3205 (inf) time: 0.5014 [2021-03-26 21:51:35 swin_small_patch4_window7_224] INFO: Epoch: [230] [1210/1251] eta: 0:00:20 lr: 0.000134 loss: 2.8988 (2.8923) grad_norm: 2.1533 (inf) time: 0.4950 [2021-03-26 21:51:40 swin_small_patch4_window7_224] INFO: Epoch: [230] [1220/1251] eta: 0:00:15 lr: 0.000134 loss: 3.0282 (2.8935) grad_norm: 2.3148 (inf) time: 0.4955 [2021-03-26 21:51:45 swin_small_patch4_window7_224] INFO: Epoch: [230] [1230/1251] eta: 0:00:10 lr: 0.000134 loss: 3.1189 (2.8947) grad_norm: 2.3148 (inf) time: 0.5049 [2021-03-26 21:51:50 swin_small_patch4_window7_224] INFO: Epoch: [230] [1240/1251] eta: 0:00:05 lr: 0.000134 loss: 2.9335 (2.8940) grad_norm: 2.2887 (inf) time: 0.5063 [2021-03-26 21:51:55 swin_small_patch4_window7_224] INFO: Epoch: [230] [1250/1251] eta: 0:00:00 lr: 0.000134 loss: 2.9869 (2.8961) grad_norm: 2.2945 (inf) time: 0.4986 [2021-03-26 21:52:46 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.4619 (0.4619) acc1: 90.6250 (90.6250) acc5: 100.0000 (100.0000) [2021-03-26 21:52:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7417 (0.7140) acc1: 82.8125 (83.9489) acc5: 96.8750 (96.3068) [2021-03-26 21:52:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7793 (0.7676) acc1: 79.6875 (81.6964) acc5: 96.8750 (96.2054) [2021-03-26 21:52:49 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.8392 (0.7822) acc1: 78.1250 (81.2500) acc5: 95.3125 (95.8165) [2021-03-26 21:52:50 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7804 (0.7858) acc1: 79.6875 (81.2881) acc5: 95.3125 (95.8460) [2021-03-26 21:52:51 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7804 (0.7971) acc1: 78.1250 (80.8000) acc5: 95.3125 (95.6480) [2021-03-26 21:53:07 swin_small_patch4_window7_224] INFO: * Acc@1 81.624 Acc@5 95.776 loss 0.782 [2021-03-26 21:53:07 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.6% [2021-03-26 21:53:07 swin_small_patch4_window7_224] INFO: Max accuracy: 81.75% [2021-03-26 21:53:11 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 0/1251] eta: 1:23:13 lr: 0.000134 loss: 2.7238 (2.7238) grad_norm: 2.3924 (2.3924) time: 3.9913 [2021-03-26 21:53:16 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 10/1251] eta: 0:17:56 lr: 0.000134 loss: 3.3054 (3.0829) grad_norm: 2.2941 (2.3316) time: 0.8675 [2021-03-26 21:53:21 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 20/1251] eta: 0:14:10 lr: 0.000134 loss: 3.0255 (3.0222) grad_norm: 2.4474 (2.4656) time: 0.5261 [2021-03-26 21:53:26 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 30/1251] eta: 0:12:47 lr: 0.000134 loss: 2.9917 (2.9877) grad_norm: 2.4243 (2.4590) time: 0.4977 [2021-03-26 21:53:31 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 40/1251] eta: 0:12:05 lr: 0.000134 loss: 3.0355 (2.9780) grad_norm: 2.2646 (2.4006) time: 0.5022 [2021-03-26 21:53:36 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 50/1251] eta: 0:11:37 lr: 0.000134 loss: 2.9347 (2.9659) grad_norm: 2.2402 (2.4093) time: 0.5062 [2021-03-26 21:53:41 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 60/1251] eta: 0:11:18 lr: 0.000134 loss: 3.1472 (3.0174) grad_norm: 2.2376 (2.3858) time: 0.5103 [2021-03-26 21:53:46 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 70/1251] eta: 0:11:01 lr: 0.000134 loss: 3.1472 (3.0087) grad_norm: 2.2446 (2.3966) time: 0.5060 [2021-03-26 21:53:52 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 80/1251] eta: 0:10:48 lr: 0.000133 loss: 3.2087 (3.0210) grad_norm: 2.2446 (2.3767) time: 0.5062 [2021-03-26 21:53:57 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 90/1251] eta: 0:10:39 lr: 0.000133 loss: 2.9206 (3.0006) grad_norm: 2.1751 (2.3651) time: 0.5182 [2021-03-26 21:54:02 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 100/1251] eta: 0:10:28 lr: 0.000133 loss: 2.8678 (3.0095) grad_norm: 2.2641 (2.3692) time: 0.5136 [2021-03-26 21:54:07 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 110/1251] eta: 0:10:19 lr: 0.000133 loss: 2.9385 (2.9861) grad_norm: 2.3576 (2.3626) time: 0.5061 [2021-03-26 21:54:12 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 120/1251] eta: 0:10:09 lr: 0.000133 loss: 2.7014 (2.9613) grad_norm: 2.2417 (2.3593) time: 0.5027 [2021-03-26 21:54:17 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 130/1251] eta: 0:10:00 lr: 0.000133 loss: 2.9591 (2.9630) grad_norm: 2.4489 (2.3870) time: 0.4963 [2021-03-26 21:54:22 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 140/1251] eta: 0:09:51 lr: 0.000133 loss: 3.1407 (2.9766) grad_norm: 2.4179 (2.3808) time: 0.4928 [2021-03-26 21:54:27 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 150/1251] eta: 0:09:44 lr: 0.000133 loss: 3.1407 (2.9784) grad_norm: 2.1656 (2.3716) time: 0.4976 [2021-03-26 21:54:32 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 160/1251] eta: 0:09:36 lr: 0.000133 loss: 3.1045 (2.9819) grad_norm: 2.3524 (2.3766) time: 0.5007 [2021-03-26 21:54:37 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 170/1251] eta: 0:09:31 lr: 0.000133 loss: 3.1385 (2.9842) grad_norm: 2.4472 (2.3887) time: 0.5144 [2021-03-26 21:54:42 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 180/1251] eta: 0:09:24 lr: 0.000133 loss: 3.1455 (2.9785) grad_norm: 2.3912 (2.4068) time: 0.5179 [2021-03-26 21:54:47 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 190/1251] eta: 0:09:18 lr: 0.000133 loss: 3.1455 (2.9829) grad_norm: 2.3362 (2.4067) time: 0.5063 [2021-03-26 21:54:52 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 200/1251] eta: 0:09:11 lr: 0.000133 loss: 3.0603 (2.9873) grad_norm: 2.3362 (2.4160) time: 0.5005 [2021-03-26 21:54:57 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 210/1251] eta: 0:09:04 lr: 0.000133 loss: 3.0407 (2.9792) grad_norm: 2.2844 (2.4158) time: 0.4968 [2021-03-26 21:55:02 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 220/1251] eta: 0:08:58 lr: 0.000133 loss: 3.0692 (2.9829) grad_norm: 2.2906 (2.4126) time: 0.5007 [2021-03-26 21:55:07 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 230/1251] eta: 0:08:52 lr: 0.000133 loss: 3.0744 (2.9850) grad_norm: 2.2891 (2.4080) time: 0.4983 [2021-03-26 21:55:12 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 240/1251] eta: 0:08:46 lr: 0.000133 loss: 3.0343 (2.9750) grad_norm: 2.2319 (2.3997) time: 0.4991 [2021-03-26 21:55:17 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 250/1251] eta: 0:08:40 lr: 0.000133 loss: 2.7532 (2.9660) grad_norm: 2.2412 (2.3995) time: 0.5053 [2021-03-26 21:55:22 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 260/1251] eta: 0:08:34 lr: 0.000133 loss: 2.9594 (2.9658) grad_norm: 2.2836 (2.4038) time: 0.5075 [2021-03-26 21:55:27 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 270/1251] eta: 0:08:29 lr: 0.000133 loss: 3.0125 (2.9613) grad_norm: 2.3413 (2.4031) time: 0.5054 [2021-03-26 21:55:32 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 280/1251] eta: 0:08:23 lr: 0.000133 loss: 3.0125 (2.9629) grad_norm: 2.3101 (2.3991) time: 0.5041 [2021-03-26 21:55:37 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 290/1251] eta: 0:08:17 lr: 0.000133 loss: 2.8445 (2.9495) grad_norm: 2.3101 (2.4000) time: 0.5033 [2021-03-26 21:55:42 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 300/1251] eta: 0:08:11 lr: 0.000133 loss: 2.7445 (2.9512) grad_norm: 2.3465 (2.3964) time: 0.5004 [2021-03-26 21:55:47 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 310/1251] eta: 0:08:06 lr: 0.000133 loss: 2.9857 (2.9512) grad_norm: 2.3465 (2.3926) time: 0.5025 [2021-03-26 21:55:52 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 320/1251] eta: 0:08:00 lr: 0.000133 loss: 2.9857 (2.9512) grad_norm: 2.3305 (2.3901) time: 0.5017 [2021-03-26 21:55:57 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 330/1251] eta: 0:07:54 lr: 0.000133 loss: 2.8803 (2.9457) grad_norm: 2.2548 (2.3855) time: 0.4971 [2021-03-26 21:56:02 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 340/1251] eta: 0:07:49 lr: 0.000133 loss: 2.8803 (2.9412) grad_norm: 2.1980 (2.3829) time: 0.5004 [2021-03-26 21:56:08 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 350/1251] eta: 0:07:44 lr: 0.000133 loss: 2.8050 (2.9337) grad_norm: 2.2509 (2.3862) time: 0.5057 [2021-03-26 21:56:13 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 360/1251] eta: 0:07:38 lr: 0.000133 loss: 2.9097 (2.9277) grad_norm: 2.3086 (2.3890) time: 0.5061 [2021-03-26 21:56:18 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 370/1251] eta: 0:07:33 lr: 0.000133 loss: 2.9097 (2.9276) grad_norm: 2.2407 (2.3825) time: 0.5043 [2021-03-26 21:56:23 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 380/1251] eta: 0:07:27 lr: 0.000133 loss: 2.9855 (2.9264) grad_norm: 2.1563 (2.3794) time: 0.5010 [2021-03-26 21:56:28 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 390/1251] eta: 0:07:22 lr: 0.000133 loss: 3.1339 (2.9329) grad_norm: 2.2964 (2.3848) time: 0.4983 [2021-03-26 21:56:33 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 400/1251] eta: 0:07:16 lr: 0.000133 loss: 3.1748 (2.9348) grad_norm: 2.3832 (2.3912) time: 0.5023 [2021-03-26 21:56:38 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 410/1251] eta: 0:07:11 lr: 0.000133 loss: 2.9975 (2.9345) grad_norm: 2.3239 (2.3907) time: 0.5047 [2021-03-26 21:56:43 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 420/1251] eta: 0:07:06 lr: 0.000133 loss: 2.9557 (2.9347) grad_norm: 2.3642 (2.3939) time: 0.5006 [2021-03-26 21:56:48 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 430/1251] eta: 0:07:00 lr: 0.000133 loss: 2.8119 (2.9265) grad_norm: 2.3125 (2.3914) time: 0.4999 [2021-03-26 21:56:53 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 440/1251] eta: 0:06:55 lr: 0.000132 loss: 2.9173 (2.9302) grad_norm: 2.4515 (2.3959) time: 0.5042 [2021-03-26 21:56:58 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 450/1251] eta: 0:06:50 lr: 0.000132 loss: 3.0954 (2.9335) grad_norm: 2.5565 (2.3965) time: 0.5043 [2021-03-26 21:57:03 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 460/1251] eta: 0:06:44 lr: 0.000132 loss: 3.0954 (2.9367) grad_norm: 2.2846 (2.3973) time: 0.5004 [2021-03-26 21:57:08 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 470/1251] eta: 0:06:39 lr: 0.000132 loss: 3.1003 (2.9358) grad_norm: 2.2409 (2.3958) time: 0.4978 [2021-03-26 21:57:13 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 480/1251] eta: 0:06:34 lr: 0.000132 loss: 3.0480 (2.9322) grad_norm: 2.2409 (2.3935) time: 0.5037 [2021-03-26 21:57:18 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 490/1251] eta: 0:06:29 lr: 0.000132 loss: 2.9123 (2.9329) grad_norm: 2.2495 (2.3910) time: 0.5045 [2021-03-26 21:57:23 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 500/1251] eta: 0:06:23 lr: 0.000132 loss: 2.9385 (2.9325) grad_norm: 2.2495 (2.3896) time: 0.4951 [2021-03-26 21:57:28 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 510/1251] eta: 0:06:18 lr: 0.000132 loss: 2.9567 (2.9336) grad_norm: 2.1513 (2.3871) time: 0.4993 [2021-03-26 21:57:33 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 520/1251] eta: 0:06:13 lr: 0.000132 loss: 2.9413 (2.9336) grad_norm: 2.2528 (2.3871) time: 0.4999 [2021-03-26 21:57:38 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 530/1251] eta: 0:06:07 lr: 0.000132 loss: 3.0604 (2.9378) grad_norm: 2.3594 (2.3860) time: 0.4936 [2021-03-26 21:57:43 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 540/1251] eta: 0:06:02 lr: 0.000132 loss: 3.0721 (2.9403) grad_norm: 2.2956 (2.3856) time: 0.5010 [2021-03-26 21:57:48 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 550/1251] eta: 0:05:57 lr: 0.000132 loss: 3.0519 (2.9383) grad_norm: 2.3260 (2.3876) time: 0.5157 [2021-03-26 21:57:53 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 560/1251] eta: 0:05:52 lr: 0.000132 loss: 2.6905 (2.9338) grad_norm: 2.4496 (2.3883) time: 0.5253 [2021-03-26 21:57:58 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 570/1251] eta: 0:05:47 lr: 0.000132 loss: 2.6758 (2.9291) grad_norm: 2.3820 (2.3857) time: 0.5120 [2021-03-26 21:58:03 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 580/1251] eta: 0:05:42 lr: 0.000132 loss: 2.8760 (2.9294) grad_norm: 2.1502 (2.3813) time: 0.5024 [2021-03-26 21:58:08 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 590/1251] eta: 0:05:37 lr: 0.000132 loss: 2.8760 (2.9288) grad_norm: 2.2448 (2.3831) time: 0.5083 [2021-03-26 21:58:14 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 600/1251] eta: 0:05:32 lr: 0.000132 loss: 3.0606 (2.9312) grad_norm: 2.4141 (2.3848) time: 0.5089 [2021-03-26 21:58:19 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 610/1251] eta: 0:05:27 lr: 0.000132 loss: 3.1549 (2.9347) grad_norm: 2.3866 (2.3855) time: 0.5064 [2021-03-26 21:58:24 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 620/1251] eta: 0:05:21 lr: 0.000132 loss: 3.2487 (2.9379) grad_norm: 2.2938 (2.3866) time: 0.5039 [2021-03-26 21:58:29 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 630/1251] eta: 0:05:16 lr: 0.000132 loss: 3.1227 (2.9340) grad_norm: 2.2503 (2.3860) time: 0.5041 [2021-03-26 21:58:34 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 640/1251] eta: 0:05:11 lr: 0.000132 loss: 3.0417 (2.9337) grad_norm: 2.2103 (2.3844) time: 0.5058 [2021-03-26 21:58:39 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 650/1251] eta: 0:05:06 lr: 0.000132 loss: 3.0417 (2.9363) grad_norm: 2.2536 (2.3840) time: 0.5037 [2021-03-26 21:58:44 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 660/1251] eta: 0:05:01 lr: 0.000132 loss: 3.0868 (2.9391) grad_norm: 2.2697 (2.3897) time: 0.5026 [2021-03-26 21:58:49 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 670/1251] eta: 0:04:56 lr: 0.000132 loss: 3.0719 (2.9365) grad_norm: 2.1965 (2.3894) time: 0.5001 [2021-03-26 21:58:54 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 680/1251] eta: 0:04:50 lr: 0.000132 loss: 2.8478 (2.9335) grad_norm: 2.1965 (2.3878) time: 0.4985 [2021-03-26 21:58:59 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 690/1251] eta: 0:04:45 lr: 0.000132 loss: 2.9022 (2.9327) grad_norm: 2.3732 (2.3888) time: 0.5005 [2021-03-26 21:59:04 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 700/1251] eta: 0:04:40 lr: 0.000132 loss: 2.9537 (2.9297) grad_norm: 2.4265 (2.3883) time: 0.5028 [2021-03-26 21:59:09 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 710/1251] eta: 0:04:35 lr: 0.000132 loss: 3.0216 (2.9320) grad_norm: 2.3280 (2.3877) time: 0.5072 [2021-03-26 21:59:14 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 720/1251] eta: 0:04:30 lr: 0.000132 loss: 3.1069 (2.9336) grad_norm: 2.2976 (2.3863) time: 0.5113 [2021-03-26 21:59:19 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 730/1251] eta: 0:04:25 lr: 0.000132 loss: 3.0939 (2.9363) grad_norm: 2.3329 (2.3872) time: 0.5196 [2021-03-26 21:59:25 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 740/1251] eta: 0:04:20 lr: 0.000132 loss: 3.0559 (2.9339) grad_norm: 2.3730 (2.3870) time: 0.5250 [2021-03-26 21:59:30 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 750/1251] eta: 0:04:15 lr: 0.000132 loss: 2.9238 (2.9326) grad_norm: 2.2831 (2.3867) time: 0.5285 [2021-03-26 21:59:35 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 760/1251] eta: 0:04:10 lr: 0.000132 loss: 2.9738 (2.9320) grad_norm: 2.3340 (2.3890) time: 0.5131 [2021-03-26 21:59:40 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 770/1251] eta: 0:04:05 lr: 0.000132 loss: 3.0007 (2.9329) grad_norm: 2.3850 (2.3904) time: 0.4972 [2021-03-26 21:59:45 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 780/1251] eta: 0:04:00 lr: 0.000132 loss: 2.9528 (2.9327) grad_norm: 2.3820 (2.3919) time: 0.4998 [2021-03-26 21:59:50 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 790/1251] eta: 0:03:54 lr: 0.000132 loss: 3.0909 (2.9341) grad_norm: 2.3820 (2.3923) time: 0.5010 [2021-03-26 21:59:55 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 800/1251] eta: 0:03:49 lr: 0.000132 loss: 3.0334 (2.9350) grad_norm: 2.3589 (2.3928) time: 0.5100 [2021-03-26 22:00:00 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 810/1251] eta: 0:03:44 lr: 0.000131 loss: 3.0334 (2.9365) grad_norm: 2.2685 (2.3921) time: 0.5108 [2021-03-26 22:00:05 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 820/1251] eta: 0:03:39 lr: 0.000131 loss: 2.9619 (2.9330) grad_norm: 2.2685 (2.3915) time: 0.5071 [2021-03-26 22:00:10 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 830/1251] eta: 0:03:34 lr: 0.000131 loss: 2.7368 (2.9321) grad_norm: 2.3178 (2.3914) time: 0.5143 [2021-03-26 22:00:15 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 840/1251] eta: 0:03:29 lr: 0.000131 loss: 2.9836 (2.9323) grad_norm: 2.3925 (2.3927) time: 0.5041 [2021-03-26 22:00:20 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 850/1251] eta: 0:03:24 lr: 0.000131 loss: 3.0020 (2.9325) grad_norm: 2.3572 (2.3943) time: 0.4976 [2021-03-26 22:00:25 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 860/1251] eta: 0:03:19 lr: 0.000131 loss: 3.0020 (2.9309) grad_norm: 2.3274 (2.3946) time: 0.5064 [2021-03-26 22:00:30 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 870/1251] eta: 0:03:14 lr: 0.000131 loss: 2.8846 (2.9290) grad_norm: 2.2799 (2.3940) time: 0.5046 [2021-03-26 22:00:36 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 880/1251] eta: 0:03:08 lr: 0.000131 loss: 2.9012 (2.9290) grad_norm: 2.2685 (2.3924) time: 0.5086 [2021-03-26 22:00:41 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 890/1251] eta: 0:03:03 lr: 0.000131 loss: 2.8619 (2.9251) grad_norm: 2.2981 (2.3921) time: 0.5076 [2021-03-26 22:00:46 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 900/1251] eta: 0:02:58 lr: 0.000131 loss: 2.8619 (2.9265) grad_norm: 2.3256 (2.3916) time: 0.4985 [2021-03-26 22:00:51 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 910/1251] eta: 0:02:53 lr: 0.000131 loss: 2.9867 (2.9260) grad_norm: 2.3236 (2.3913) time: 0.5038 [2021-03-26 22:00:56 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 920/1251] eta: 0:02:48 lr: 0.000131 loss: 2.9670 (2.9242) grad_norm: 2.4698 (2.3924) time: 0.5139 [2021-03-26 22:01:01 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 930/1251] eta: 0:02:43 lr: 0.000131 loss: 2.8549 (2.9219) grad_norm: 2.3962 (2.3911) time: 0.5068 [2021-03-26 22:01:06 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 940/1251] eta: 0:02:38 lr: 0.000131 loss: 3.0685 (2.9233) grad_norm: 2.2661 (2.3909) time: 0.4989 [2021-03-26 22:01:11 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 950/1251] eta: 0:02:33 lr: 0.000131 loss: 3.0888 (2.9253) grad_norm: 2.2864 (2.3908) time: 0.4995 [2021-03-26 22:01:16 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 960/1251] eta: 0:02:28 lr: 0.000131 loss: 2.9236 (2.9235) grad_norm: 2.3640 (2.3910) time: 0.5018 [2021-03-26 22:01:21 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 970/1251] eta: 0:02:22 lr: 0.000131 loss: 2.7115 (2.9211) grad_norm: 2.3098 (2.3897) time: 0.5014 [2021-03-26 22:01:26 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 980/1251] eta: 0:02:17 lr: 0.000131 loss: 2.9188 (2.9219) grad_norm: 2.2218 (2.3889) time: 0.4972 [2021-03-26 22:01:31 swin_small_patch4_window7_224] INFO: Epoch: [231] [ 990/1251] eta: 0:02:12 lr: 0.000131 loss: 2.9828 (2.9227) grad_norm: 2.2732 (2.3879) time: 0.4966 [2021-03-26 22:01:36 swin_small_patch4_window7_224] INFO: Epoch: [231] [1000/1251] eta: 0:02:07 lr: 0.000131 loss: 3.1210 (2.9235) grad_norm: 2.3614 (2.3884) time: 0.5035 [2021-03-26 22:01:41 swin_small_patch4_window7_224] INFO: Epoch: [231] [1010/1251] eta: 0:02:02 lr: 0.000131 loss: 2.9339 (2.9220) grad_norm: 2.2946 (2.3883) time: 0.5067 [2021-03-26 22:01:46 swin_small_patch4_window7_224] INFO: Epoch: [231] [1020/1251] eta: 0:01:57 lr: 0.000131 loss: 2.6956 (2.9197) grad_norm: 2.3588 (2.3894) time: 0.5018 [2021-03-26 22:01:51 swin_small_patch4_window7_224] INFO: Epoch: [231] [1030/1251] eta: 0:01:52 lr: 0.000131 loss: 2.8904 (2.9207) grad_norm: 2.4588 (2.3909) time: 0.5056 [2021-03-26 22:01:56 swin_small_patch4_window7_224] INFO: Epoch: [231] [1040/1251] eta: 0:01:47 lr: 0.000131 loss: 2.8904 (2.9196) grad_norm: 2.4493 (2.3919) time: 0.5035 [2021-03-26 22:02:01 swin_small_patch4_window7_224] INFO: Epoch: [231] [1050/1251] eta: 0:01:42 lr: 0.000131 loss: 2.8442 (2.9176) grad_norm: 2.4382 (2.3931) time: 0.5002 [2021-03-26 22:02:06 swin_small_patch4_window7_224] INFO: Epoch: [231] [1060/1251] eta: 0:01:37 lr: 0.000131 loss: 2.8650 (2.9189) grad_norm: 2.3805 (2.3926) time: 0.5024 [2021-03-26 22:02:11 swin_small_patch4_window7_224] INFO: Epoch: [231] [1070/1251] eta: 0:01:31 lr: 0.000131 loss: 3.1256 (2.9215) grad_norm: 2.2527 (2.3927) time: 0.5010 [2021-03-26 22:02:16 swin_small_patch4_window7_224] INFO: Epoch: [231] [1080/1251] eta: 0:01:26 lr: 0.000131 loss: 3.1354 (2.9200) grad_norm: 2.2460 (2.3911) time: 0.5025 [2021-03-26 22:02:21 swin_small_patch4_window7_224] INFO: Epoch: [231] [1090/1251] eta: 0:01:21 lr: 0.000131 loss: 2.9985 (2.9206) grad_norm: 2.2086 (2.3898) time: 0.5034 [2021-03-26 22:02:26 swin_small_patch4_window7_224] INFO: Epoch: [231] [1100/1251] eta: 0:01:16 lr: 0.000131 loss: 2.8521 (2.9198) grad_norm: 2.2490 (2.3890) time: 0.5017 [2021-03-26 22:02:31 swin_small_patch4_window7_224] INFO: Epoch: [231] [1110/1251] eta: 0:01:11 lr: 0.000131 loss: 2.8521 (2.9190) grad_norm: 2.3139 (2.3889) time: 0.5036 [2021-03-26 22:02:36 swin_small_patch4_window7_224] INFO: Epoch: [231] [1120/1251] eta: 0:01:06 lr: 0.000131 loss: 3.1365 (2.9209) grad_norm: 2.3093 (2.3877) time: 0.5029 [2021-03-26 22:02:41 swin_small_patch4_window7_224] INFO: Epoch: [231] [1130/1251] eta: 0:01:01 lr: 0.000131 loss: 3.1549 (2.9214) grad_norm: 2.1552 (2.3865) time: 0.4969 [2021-03-26 22:02:46 swin_small_patch4_window7_224] INFO: Epoch: [231] [1140/1251] eta: 0:00:56 lr: 0.000131 loss: 3.0755 (2.9214) grad_norm: 2.1988 (2.3863) time: 0.4978 [2021-03-26 22:02:51 swin_small_patch4_window7_224] INFO: Epoch: [231] [1150/1251] eta: 0:00:51 lr: 0.000131 loss: 2.9430 (2.9205) grad_norm: 2.3391 (2.3882) time: 0.4976 [2021-03-26 22:02:56 swin_small_patch4_window7_224] INFO: Epoch: [231] [1160/1251] eta: 0:00:46 lr: 0.000131 loss: 2.8511 (2.9206) grad_norm: 2.5305 (2.3889) time: 0.4968 [2021-03-26 22:03:01 swin_small_patch4_window7_224] INFO: Epoch: [231] [1170/1251] eta: 0:00:41 lr: 0.000131 loss: 2.8764 (2.9199) grad_norm: 2.3482 (2.3887) time: 0.5003 [2021-03-26 22:03:06 swin_small_patch4_window7_224] INFO: Epoch: [231] [1180/1251] eta: 0:00:36 lr: 0.000130 loss: 2.9711 (2.9200) grad_norm: 2.2768 (2.3878) time: 0.5018 [2021-03-26 22:03:11 swin_small_patch4_window7_224] INFO: Epoch: [231] [1190/1251] eta: 0:00:30 lr: 0.000130 loss: 3.0286 (2.9201) grad_norm: 2.2800 (2.3871) time: 0.4974 [2021-03-26 22:03:16 swin_small_patch4_window7_224] INFO: Epoch: [231] [1200/1251] eta: 0:00:25 lr: 0.000130 loss: 3.0688 (2.9220) grad_norm: 2.3136 (2.3866) time: 0.4961 [2021-03-26 22:03:21 swin_small_patch4_window7_224] INFO: Epoch: [231] [1210/1251] eta: 0:00:20 lr: 0.000130 loss: 2.9719 (2.9210) grad_norm: 2.2807 (2.3862) time: 0.5002 [2021-03-26 22:03:26 swin_small_patch4_window7_224] INFO: Epoch: [231] [1220/1251] eta: 0:00:15 lr: 0.000130 loss: 2.9078 (2.9198) grad_norm: 2.2953 (2.3852) time: 0.4985 [2021-03-26 22:03:31 swin_small_patch4_window7_224] INFO: Epoch: [231] [1230/1251] eta: 0:00:10 lr: 0.000130 loss: 2.9837 (2.9211) grad_norm: 2.2963 (2.3863) time: 0.4988 [2021-03-26 22:03:36 swin_small_patch4_window7_224] INFO: Epoch: [231] [1240/1251] eta: 0:00:05 lr: 0.000130 loss: 3.0559 (2.9219) grad_norm: 2.2755 (2.3854) time: 0.4964 [2021-03-26 22:03:41 swin_small_patch4_window7_224] INFO: Epoch: [231] [1250/1251] eta: 0:00:00 lr: 0.000130 loss: 3.1411 (2.9242) grad_norm: 2.3083 (2.3861) time: 0.4926 [2021-03-26 22:03:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 0.5647 (0.5647) acc1: 89.0625 (89.0625) acc5: 96.8750 (96.8750) [2021-03-26 22:03:56 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7450 (0.7268) acc1: 82.8125 (83.5227) acc5: 96.8750 (96.7330) [2021-03-26 22:03:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7652 (0.7675) acc1: 81.2500 (81.7708) acc5: 95.3125 (96.2798) [2021-03-26 22:03:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7652 (0.7560) acc1: 79.6875 (81.6028) acc5: 95.3125 (96.4214) [2021-03-26 22:04:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7238 (0.7734) acc1: 78.1250 (80.9451) acc5: 96.8750 (96.3034) [2021-03-26 22:04:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7238 (0.7836) acc1: 79.6875 (81.0240) acc5: 95.3125 (96.1280) [2021-03-26 22:04:17 swin_small_patch4_window7_224] INFO: * Acc@1 81.766 Acc@5 95.876 loss 0.769 [2021-03-26 22:04:17 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-26 22:04:17 swin_small_patch4_window7_224] INFO: Max accuracy: 81.77% [2021-03-26 22:04:21 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 0/1251] eta: 1:26:48 lr: 0.000130 loss: 3.1897 (3.1897) grad_norm: 2.5001 (2.5001) time: 4.1632 [2021-03-26 22:04:26 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 10/1251] eta: 0:17:32 lr: 0.000130 loss: 3.1913 (3.1096) grad_norm: 2.4289 (2.3623) time: 0.8479 [2021-03-26 22:04:31 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 20/1251] eta: 0:13:56 lr: 0.000130 loss: 3.1064 (3.0226) grad_norm: 2.3791 (2.3587) time: 0.5052 [2021-03-26 22:04:36 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 30/1251] eta: 0:12:42 lr: 0.000130 loss: 3.0865 (3.0780) grad_norm: 2.3932 (2.3876) time: 0.5018 [2021-03-26 22:04:41 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 40/1251] eta: 0:12:01 lr: 0.000130 loss: 3.0971 (3.0678) grad_norm: 2.3904 (2.3746) time: 0.5085 [2021-03-26 22:04:47 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 50/1251] eta: 0:11:33 lr: 0.000130 loss: 2.9773 (3.0325) grad_norm: 2.2519 (2.3591) time: 0.5052 [2021-03-26 22:04:52 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 60/1251] eta: 0:11:13 lr: 0.000130 loss: 2.9773 (3.0252) grad_norm: 2.3308 (2.3618) time: 0.5016 [2021-03-26 22:04:57 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 70/1251] eta: 0:10:57 lr: 0.000130 loss: 2.8893 (2.9926) grad_norm: 2.2979 (2.3488) time: 0.5039 [2021-03-26 22:05:02 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 80/1251] eta: 0:10:44 lr: 0.000130 loss: 2.8893 (2.9838) grad_norm: 2.2400 (2.3635) time: 0.5067 [2021-03-26 22:05:07 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 90/1251] eta: 0:10:33 lr: 0.000130 loss: 3.1104 (2.9869) grad_norm: 2.3306 (2.3925) time: 0.5070 [2021-03-26 22:05:12 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 100/1251] eta: 0:10:22 lr: 0.000130 loss: 3.0102 (2.9760) grad_norm: 2.3797 (2.4036) time: 0.5012 [2021-03-26 22:05:17 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 110/1251] eta: 0:10:15 lr: 0.000130 loss: 3.1264 (2.9871) grad_norm: 2.3918 (2.4142) time: 0.5079 [2021-03-26 22:05:22 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 120/1251] eta: 0:10:06 lr: 0.000130 loss: 3.1962 (2.9850) grad_norm: 2.4597 (2.4164) time: 0.5120 [2021-03-26 22:05:27 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 130/1251] eta: 0:09:57 lr: 0.000130 loss: 2.8212 (2.9784) grad_norm: 2.3764 (2.4104) time: 0.4986 [2021-03-26 22:05:32 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 140/1251] eta: 0:09:49 lr: 0.000130 loss: 2.9557 (2.9721) grad_norm: 2.3274 (2.4014) time: 0.4989 [2021-03-26 22:05:37 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 150/1251] eta: 0:09:42 lr: 0.000130 loss: 3.0932 (2.9631) grad_norm: 2.3401 (2.4103) time: 0.5013 [2021-03-26 22:05:42 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 160/1251] eta: 0:09:34 lr: 0.000130 loss: 2.7378 (2.9543) grad_norm: 2.4083 (2.4137) time: 0.4997 [2021-03-26 22:05:47 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 170/1251] eta: 0:09:27 lr: 0.000130 loss: 2.7378 (2.9491) grad_norm: 2.3416 (2.4180) time: 0.4982 [2021-03-26 22:05:52 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 180/1251] eta: 0:09:21 lr: 0.000130 loss: 2.6921 (2.9355) grad_norm: 2.2680 (2.4075) time: 0.5035 [2021-03-26 22:05:57 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 190/1251] eta: 0:09:15 lr: 0.000130 loss: 2.9828 (2.9409) grad_norm: 2.2444 (2.4038) time: 0.5099 [2021-03-26 22:06:02 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 200/1251] eta: 0:09:10 lr: 0.000130 loss: 3.1345 (2.9467) grad_norm: 2.2834 (2.4008) time: 0.5182 [2021-03-26 22:06:07 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 210/1251] eta: 0:09:04 lr: 0.000130 loss: 3.0674 (2.9380) grad_norm: 2.2654 (2.3958) time: 0.5159 [2021-03-26 22:06:12 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 220/1251] eta: 0:08:57 lr: 0.000130 loss: 3.0330 (2.9385) grad_norm: 2.1459 (2.3921) time: 0.5005 [2021-03-26 22:06:17 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 230/1251] eta: 0:08:51 lr: 0.000130 loss: 3.0087 (2.9329) grad_norm: 2.3753 (2.3963) time: 0.4978 [2021-03-26 22:06:22 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 240/1251] eta: 0:08:45 lr: 0.000130 loss: 2.9489 (2.9348) grad_norm: 2.3870 (2.3975) time: 0.4993 [2021-03-26 22:06:27 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 250/1251] eta: 0:08:39 lr: 0.000130 loss: 3.1240 (2.9409) grad_norm: 2.2295 (2.3902) time: 0.4987 [2021-03-26 22:06:32 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 260/1251] eta: 0:08:33 lr: 0.000130 loss: 3.0479 (2.9406) grad_norm: 2.2020 (2.3876) time: 0.5010 [2021-03-26 22:06:37 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 270/1251] eta: 0:08:27 lr: 0.000130 loss: 3.0151 (2.9413) grad_norm: 2.2663 (2.3905) time: 0.5024 [2021-03-26 22:06:42 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 280/1251] eta: 0:08:22 lr: 0.000130 loss: 3.0448 (2.9429) grad_norm: 2.3352 (2.4009) time: 0.5026 [2021-03-26 22:06:47 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 290/1251] eta: 0:08:16 lr: 0.000130 loss: 2.9993 (2.9332) grad_norm: 2.3148 (2.4038) time: 0.5014 [2021-03-26 22:06:53 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 300/1251] eta: 0:08:11 lr: 0.000129 loss: 2.9480 (2.9312) grad_norm: 2.3148 (2.4007) time: 0.5038 [2021-03-26 22:06:57 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 310/1251] eta: 0:08:05 lr: 0.000129 loss: 2.9179 (2.9169) grad_norm: 2.3127 (2.4049) time: 0.5039 [2021-03-26 22:07:03 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 320/1251] eta: 0:08:00 lr: 0.000129 loss: 2.8337 (2.9129) grad_norm: 2.3290 (2.4016) time: 0.5048 [2021-03-26 22:07:08 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 330/1251] eta: 0:07:54 lr: 0.000129 loss: 2.8982 (2.9156) grad_norm: 2.3396 (2.3989) time: 0.5076 [2021-03-26 22:07:13 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 340/1251] eta: 0:07:49 lr: 0.000129 loss: 3.0372 (2.9195) grad_norm: 2.3184 (2.3957) time: 0.5068 [2021-03-26 22:07:18 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 350/1251] eta: 0:07:43 lr: 0.000129 loss: 2.8707 (2.9147) grad_norm: 2.2840 (2.4019) time: 0.5085 [2021-03-26 22:07:23 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 360/1251] eta: 0:07:38 lr: 0.000129 loss: 2.9441 (2.9188) grad_norm: 2.2997 (2.4000) time: 0.5048 [2021-03-26 22:07:28 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 370/1251] eta: 0:07:33 lr: 0.000129 loss: 3.1391 (2.9223) grad_norm: 2.3514 (2.4102) time: 0.5020 [2021-03-26 22:07:33 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 380/1251] eta: 0:07:27 lr: 0.000129 loss: 3.1347 (2.9235) grad_norm: 2.3203 (2.4100) time: 0.4988 [2021-03-26 22:07:38 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 390/1251] eta: 0:07:22 lr: 0.000129 loss: 2.8401 (2.9168) grad_norm: 2.3203 (2.4102) time: 0.5058 [2021-03-26 22:07:43 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 400/1251] eta: 0:07:16 lr: 0.000129 loss: 2.8401 (2.9191) grad_norm: 2.3035 (2.4083) time: 0.5079 [2021-03-26 22:07:48 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 410/1251] eta: 0:07:11 lr: 0.000129 loss: 2.8901 (2.9164) grad_norm: 2.2597 (2.4065) time: 0.5018 [2021-03-26 22:07:53 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 420/1251] eta: 0:07:06 lr: 0.000129 loss: 3.0547 (2.9243) grad_norm: 2.3023 (2.4079) time: 0.5052 [2021-03-26 22:07:58 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 430/1251] eta: 0:07:01 lr: 0.000129 loss: 3.2679 (2.9243) grad_norm: 2.3753 (2.4084) time: 0.5078 [2021-03-26 22:08:03 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 440/1251] eta: 0:06:55 lr: 0.000129 loss: 2.8769 (2.9173) grad_norm: 2.3681 (2.4065) time: 0.5066 [2021-03-26 22:08:08 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 450/1251] eta: 0:06:50 lr: 0.000129 loss: 2.7750 (2.9179) grad_norm: 2.3493 (2.4059) time: 0.4996 [2021-03-26 22:08:13 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 460/1251] eta: 0:06:45 lr: 0.000129 loss: 3.0345 (2.9202) grad_norm: 2.3493 (2.4088) time: 0.5001 [2021-03-26 22:08:18 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 470/1251] eta: 0:06:39 lr: 0.000129 loss: 2.9837 (2.9178) grad_norm: 2.3176 (2.4055) time: 0.5040 [2021-03-26 22:08:23 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 480/1251] eta: 0:06:34 lr: 0.000129 loss: 2.7592 (2.9108) grad_norm: 2.2672 (2.4039) time: 0.5028 [2021-03-26 22:08:28 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 490/1251] eta: 0:06:29 lr: 0.000129 loss: 2.7592 (2.9107) grad_norm: 2.2672 (2.4009) time: 0.5007 [2021-03-26 22:08:33 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 500/1251] eta: 0:06:23 lr: 0.000129 loss: 3.0301 (2.9128) grad_norm: 2.2569 (2.4016) time: 0.4947 [2021-03-26 22:08:38 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 510/1251] eta: 0:06:18 lr: 0.000129 loss: 3.0525 (2.9125) grad_norm: 2.4852 (inf) time: 0.4940 [2021-03-26 22:08:43 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 520/1251] eta: 0:06:13 lr: 0.000129 loss: 3.0454 (2.9160) grad_norm: 2.4289 (inf) time: 0.4983 [2021-03-26 22:08:48 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 530/1251] eta: 0:06:07 lr: 0.000129 loss: 3.1218 (2.9170) grad_norm: 2.3217 (inf) time: 0.4990 [2021-03-26 22:08:53 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 540/1251] eta: 0:06:02 lr: 0.000129 loss: 3.0211 (2.9169) grad_norm: 2.3604 (inf) time: 0.4993 [2021-03-26 22:08:58 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 550/1251] eta: 0:05:57 lr: 0.000129 loss: 3.0111 (2.9165) grad_norm: 2.4603 (inf) time: 0.5123 [2021-03-26 22:09:03 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 560/1251] eta: 0:05:52 lr: 0.000129 loss: 3.0356 (2.9136) grad_norm: 2.3546 (inf) time: 0.5099 [2021-03-26 22:09:08 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 570/1251] eta: 0:05:47 lr: 0.000129 loss: 2.6985 (2.9088) grad_norm: 2.3770 (inf) time: 0.4976 [2021-03-26 22:09:13 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 580/1251] eta: 0:05:42 lr: 0.000129 loss: 2.8906 (2.9131) grad_norm: 2.3741 (inf) time: 0.5020 [2021-03-26 22:09:18 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 590/1251] eta: 0:05:36 lr: 0.000129 loss: 3.1317 (2.9111) grad_norm: 2.3594 (inf) time: 0.5035 [2021-03-26 22:09:24 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 600/1251] eta: 0:05:31 lr: 0.000129 loss: 2.9097 (2.9117) grad_norm: 2.3479 (inf) time: 0.5055 [2021-03-26 22:09:28 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 610/1251] eta: 0:05:26 lr: 0.000129 loss: 2.9840 (2.9121) grad_norm: 2.4916 (inf) time: 0.5038 [2021-03-26 22:09:34 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 620/1251] eta: 0:05:21 lr: 0.000129 loss: 2.9840 (2.9114) grad_norm: 2.4313 (inf) time: 0.5002 [2021-03-26 22:09:39 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 630/1251] eta: 0:05:16 lr: 0.000129 loss: 2.9601 (2.9100) grad_norm: 2.3303 (inf) time: 0.5044 [2021-03-26 22:09:44 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 640/1251] eta: 0:05:11 lr: 0.000129 loss: 3.0104 (2.9121) grad_norm: 2.3515 (inf) time: 0.5093 [2021-03-26 22:09:49 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 650/1251] eta: 0:05:06 lr: 0.000129 loss: 3.1431 (2.9154) grad_norm: 2.3505 (inf) time: 0.5094 [2021-03-26 22:09:54 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 660/1251] eta: 0:05:01 lr: 0.000129 loss: 3.0693 (2.9157) grad_norm: 2.2940 (inf) time: 0.5080 [2021-03-26 22:09:59 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 670/1251] eta: 0:04:55 lr: 0.000128 loss: 2.9604 (2.9193) grad_norm: 2.3048 (inf) time: 0.5040 [2021-03-26 22:10:04 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 680/1251] eta: 0:04:50 lr: 0.000128 loss: 3.0038 (2.9181) grad_norm: 2.4965 (inf) time: 0.4971 [2021-03-26 22:10:09 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 690/1251] eta: 0:04:45 lr: 0.000128 loss: 3.0038 (2.9203) grad_norm: 2.4965 (inf) time: 0.4969 [2021-03-26 22:10:14 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 700/1251] eta: 0:04:40 lr: 0.000128 loss: 3.1481 (2.9228) grad_norm: 2.3657 (inf) time: 0.4976 [2021-03-26 22:10:19 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 710/1251] eta: 0:04:35 lr: 0.000128 loss: 2.8923 (2.9177) grad_norm: 2.3731 (inf) time: 0.4996 [2021-03-26 22:10:24 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 720/1251] eta: 0:04:30 lr: 0.000128 loss: 2.8314 (2.9186) grad_norm: 2.4579 (inf) time: 0.5010 [2021-03-26 22:10:29 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 730/1251] eta: 0:04:25 lr: 0.000128 loss: 3.0160 (2.9187) grad_norm: 2.4337 (inf) time: 0.5086 [2021-03-26 22:10:34 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 740/1251] eta: 0:04:20 lr: 0.000128 loss: 2.7886 (2.9165) grad_norm: 2.3987 (inf) time: 0.5288 [2021-03-26 22:10:40 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 750/1251] eta: 0:04:15 lr: 0.000128 loss: 3.0608 (2.9183) grad_norm: 2.2194 (inf) time: 0.5304 [2021-03-26 22:10:45 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 760/1251] eta: 0:04:09 lr: 0.000128 loss: 3.0848 (2.9189) grad_norm: 2.2194 (inf) time: 0.5110 [2021-03-26 22:10:50 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 770/1251] eta: 0:04:04 lr: 0.000128 loss: 2.9429 (2.9171) grad_norm: 2.3205 (inf) time: 0.5004 [2021-03-26 22:10:55 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 780/1251] eta: 0:03:59 lr: 0.000128 loss: 2.7175 (2.9147) grad_norm: 2.4506 (inf) time: 0.4991 [2021-03-26 22:11:00 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 790/1251] eta: 0:03:54 lr: 0.000128 loss: 2.7389 (2.9154) grad_norm: 2.4402 (inf) time: 0.4999 [2021-03-26 22:11:05 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 800/1251] eta: 0:03:49 lr: 0.000128 loss: 2.9861 (2.9151) grad_norm: 2.3471 (inf) time: 0.5008 [2021-03-26 22:11:10 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 810/1251] eta: 0:03:44 lr: 0.000128 loss: 2.8746 (2.9134) grad_norm: 2.4028 (inf) time: 0.5047 [2021-03-26 22:11:15 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 820/1251] eta: 0:03:39 lr: 0.000128 loss: 2.8642 (2.9128) grad_norm: 2.3762 (inf) time: 0.5071 [2021-03-26 22:11:20 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 830/1251] eta: 0:03:34 lr: 0.000128 loss: 3.0476 (2.9147) grad_norm: 2.4896 (inf) time: 0.5093 [2021-03-26 22:11:25 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 840/1251] eta: 0:03:29 lr: 0.000128 loss: 2.8156 (2.9101) grad_norm: 2.3775 (inf) time: 0.5064 [2021-03-26 22:11:30 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 850/1251] eta: 0:03:24 lr: 0.000128 loss: 2.6833 (2.9101) grad_norm: 2.3142 (inf) time: 0.5122 [2021-03-26 22:11:35 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 860/1251] eta: 0:03:18 lr: 0.000128 loss: 2.9694 (2.9106) grad_norm: 2.2415 (inf) time: 0.5137 [2021-03-26 22:11:40 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 870/1251] eta: 0:03:13 lr: 0.000128 loss: 3.0554 (2.9082) grad_norm: 2.2354 (inf) time: 0.5033 [2021-03-26 22:11:45 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 880/1251] eta: 0:03:08 lr: 0.000128 loss: 2.9481 (2.9062) grad_norm: 2.2329 (inf) time: 0.4996 [2021-03-26 22:11:50 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 890/1251] eta: 0:03:03 lr: 0.000128 loss: 2.7733 (2.9037) grad_norm: 2.2225 (inf) time: 0.5002 [2021-03-26 22:11:55 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 900/1251] eta: 0:02:58 lr: 0.000128 loss: 2.8107 (2.9023) grad_norm: 2.2531 (inf) time: 0.5085 [2021-03-26 22:12:00 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 910/1251] eta: 0:02:53 lr: 0.000128 loss: 2.8493 (2.9011) grad_norm: 2.3611 (inf) time: 0.5121 [2021-03-26 22:12:06 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 920/1251] eta: 0:02:48 lr: 0.000128 loss: 2.8088 (2.9009) grad_norm: 2.4002 (inf) time: 0.5127 [2021-03-26 22:12:10 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 930/1251] eta: 0:02:43 lr: 0.000128 loss: 2.8646 (2.9019) grad_norm: 2.3294 (inf) time: 0.5019 [2021-03-26 22:12:16 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 940/1251] eta: 0:02:38 lr: 0.000128 loss: 2.9512 (2.9040) grad_norm: 2.2682 (inf) time: 0.5000 [2021-03-26 22:12:21 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 950/1251] eta: 0:02:33 lr: 0.000128 loss: 3.1715 (2.9068) grad_norm: 2.2634 (inf) time: 0.5117 [2021-03-26 22:12:26 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 960/1251] eta: 0:02:27 lr: 0.000128 loss: 3.1046 (2.9064) grad_norm: 2.2492 (inf) time: 0.5079 [2021-03-26 22:12:31 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 970/1251] eta: 0:02:22 lr: 0.000128 loss: 2.8804 (2.9054) grad_norm: 2.2334 (inf) time: 0.5007 [2021-03-26 22:12:36 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 980/1251] eta: 0:02:17 lr: 0.000128 loss: 2.9550 (2.9074) grad_norm: 2.2623 (inf) time: 0.4995 [2021-03-26 22:12:41 swin_small_patch4_window7_224] INFO: Epoch: [232] [ 990/1251] eta: 0:02:12 lr: 0.000128 loss: 3.0298 (2.9082) grad_norm: 2.3270 (inf) time: 0.5026 [2021-03-26 22:12:46 swin_small_patch4_window7_224] INFO: Epoch: [232] [1000/1251] eta: 0:02:07 lr: 0.000128 loss: 2.9883 (2.9069) grad_norm: 2.4141 (inf) time: 0.5016 [2021-03-26 22:12:51 swin_small_patch4_window7_224] INFO: Epoch: [232] [1010/1251] eta: 0:02:02 lr: 0.000128 loss: 3.0286 (2.9077) grad_norm: 2.4195 (inf) time: 0.4963 [2021-03-26 22:12:56 swin_small_patch4_window7_224] INFO: Epoch: [232] [1020/1251] eta: 0:01:57 lr: 0.000128 loss: 3.0967 (2.9082) grad_norm: 2.3580 (inf) time: 0.4961 [2021-03-26 22:13:01 swin_small_patch4_window7_224] INFO: Epoch: [232] [1030/1251] eta: 0:01:52 lr: 0.000128 loss: 3.0886 (2.9082) grad_norm: 2.5103 (inf) time: 0.4999 [2021-03-26 22:13:06 swin_small_patch4_window7_224] INFO: Epoch: [232] [1040/1251] eta: 0:01:47 lr: 0.000127 loss: 3.0658 (2.9093) grad_norm: 2.4412 (inf) time: 0.5061 [2021-03-26 22:13:11 swin_small_patch4_window7_224] INFO: Epoch: [232] [1050/1251] eta: 0:01:42 lr: 0.000127 loss: 2.9845 (2.9075) grad_norm: 2.2859 (inf) time: 0.5090 [2021-03-26 22:13:16 swin_small_patch4_window7_224] INFO: Epoch: [232] [1060/1251] eta: 0:01:36 lr: 0.000127 loss: 2.9355 (2.9078) grad_norm: 2.2859 (inf) time: 0.5074 [2021-03-26 22:13:21 swin_small_patch4_window7_224] INFO: Epoch: [232] [1070/1251] eta: 0:01:31 lr: 0.000127 loss: 3.0027 (2.9078) grad_norm: 2.2575 (inf) time: 0.5026 [2021-03-26 22:13:26 swin_small_patch4_window7_224] INFO: Epoch: [232] [1080/1251] eta: 0:01:26 lr: 0.000127 loss: 3.0027 (2.9078) grad_norm: 2.4283 (inf) time: 0.5029 [2021-03-26 22:13:31 swin_small_patch4_window7_224] INFO: Epoch: [232] [1090/1251] eta: 0:01:21 lr: 0.000127 loss: 2.7940 (2.9063) grad_norm: 2.4589 (inf) time: 0.5014 [2021-03-26 22:13:36 swin_small_patch4_window7_224] INFO: Epoch: [232] [1100/1251] eta: 0:01:16 lr: 0.000127 loss: 2.7747 (2.9034) grad_norm: 2.3395 (inf) time: 0.4949 [2021-03-26 22:13:41 swin_small_patch4_window7_224] INFO: Epoch: [232] [1110/1251] eta: 0:01:11 lr: 0.000127 loss: 2.7136 (2.9041) grad_norm: 2.3794 (inf) time: 0.4985 [2021-03-26 22:13:46 swin_small_patch4_window7_224] INFO: Epoch: [232] [1120/1251] eta: 0:01:06 lr: 0.000127 loss: 3.1208 (2.9066) grad_norm: 2.2958 (inf) time: 0.5015 [2021-03-26 22:13:51 swin_small_patch4_window7_224] INFO: Epoch: [232] [1130/1251] eta: 0:01:01 lr: 0.000127 loss: 3.1138 (2.9053) grad_norm: 2.2355 (inf) time: 0.4979 [2021-03-26 22:13:56 swin_small_patch4_window7_224] INFO: Epoch: [232] [1140/1251] eta: 0:00:56 lr: 0.000127 loss: 2.8186 (2.9054) grad_norm: 2.2507 (inf) time: 0.5049 [2021-03-26 22:14:01 swin_small_patch4_window7_224] INFO: Epoch: [232] [1150/1251] eta: 0:00:51 lr: 0.000127 loss: 2.9351 (2.9044) grad_norm: 2.2528 (inf) time: 0.5067 [2021-03-26 22:14:06 swin_small_patch4_window7_224] INFO: Epoch: [232] [1160/1251] eta: 0:00:46 lr: 0.000127 loss: 2.9351 (2.9035) grad_norm: 2.3678 (inf) time: 0.5025 [2021-03-26 22:14:11 swin_small_patch4_window7_224] INFO: Epoch: [232] [1170/1251] eta: 0:00:41 lr: 0.000127 loss: 2.8626 (2.9020) grad_norm: 2.3679 (inf) time: 0.5029 [2021-03-26 22:14:16 swin_small_patch4_window7_224] INFO: Epoch: [232] [1180/1251] eta: 0:00:36 lr: 0.000127 loss: 2.7603 (2.8998) grad_norm: 2.2698 (inf) time: 0.5034 [2021-03-26 22:14:21 swin_small_patch4_window7_224] INFO: Epoch: [232] [1190/1251] eta: 0:00:30 lr: 0.000127 loss: 2.7603 (2.8988) grad_norm: 2.3402 (inf) time: 0.5015 [2021-03-26 22:14:26 swin_small_patch4_window7_224] INFO: Epoch: [232] [1200/1251] eta: 0:00:25 lr: 0.000127 loss: 3.0074 (2.8981) grad_norm: 2.4381 (inf) time: 0.5017 [2021-03-26 22:14:31 swin_small_patch4_window7_224] INFO: Epoch: [232] [1210/1251] eta: 0:00:20 lr: 0.000127 loss: 3.1119 (2.8997) grad_norm: 2.3377 (inf) time: 0.5008 [2021-03-26 22:14:36 swin_small_patch4_window7_224] INFO: Epoch: [232] [1220/1251] eta: 0:00:15 lr: 0.000127 loss: 3.0804 (2.9000) grad_norm: 2.2899 (inf) time: 0.4960 [2021-03-26 22:14:41 swin_small_patch4_window7_224] INFO: Epoch: [232] [1230/1251] eta: 0:00:10 lr: 0.000127 loss: 2.9230 (2.8990) grad_norm: 2.4558 (inf) time: 0.4976 [2021-03-26 22:14:46 swin_small_patch4_window7_224] INFO: Epoch: [232] [1240/1251] eta: 0:00:05 lr: 0.000127 loss: 3.0299 (2.8995) grad_norm: 2.4648 (inf) time: 0.4989 [2021-03-26 22:14:51 swin_small_patch4_window7_224] INFO: Epoch: [232] [1250/1251] eta: 0:00:00 lr: 0.000127 loss: 3.0836 (2.9014) grad_norm: 2.4648 (inf) time: 0.4974 [2021-03-26 22:15:01 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 0.6901 (0.6901) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-26 22:15:03 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8139 (0.8041) acc1: 81.2500 (81.1080) acc5: 96.8750 (95.7386) [2021-03-26 22:15:06 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7959 (0.7893) acc1: 81.2500 (81.7708) acc5: 96.8750 (95.8333) [2021-03-26 22:15:08 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7217 (0.7617) acc1: 82.8125 (82.1069) acc5: 96.8750 (96.2198) [2021-03-26 22:15:10 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7529 (0.7693) acc1: 81.2500 (81.4787) acc5: 96.8750 (95.9985) [2021-03-26 22:15:11 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7540 (0.7727) acc1: 79.6875 (81.4080) acc5: 96.8750 (96.1280) [2021-03-26 22:15:23 swin_small_patch4_window7_224] INFO: * Acc@1 81.764 Acc@5 95.890 loss 0.768 [2021-03-26 22:15:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-26 22:15:23 swin_small_patch4_window7_224] INFO: Max accuracy: 81.77% [2021-03-26 22:15:27 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 0/1251] eta: 1:33:16 lr: 0.000127 loss: 2.7998 (2.7998) grad_norm: 2.8558 (2.8558) time: 4.4734 [2021-03-26 22:15:32 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 10/1251] eta: 0:18:10 lr: 0.000127 loss: 3.0077 (3.0500) grad_norm: 2.5968 (2.5038) time: 0.8788 [2021-03-26 22:15:37 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 20/1251] eta: 0:14:29 lr: 0.000127 loss: 3.1797 (3.0610) grad_norm: 2.3524 (2.4591) time: 0.5177 [2021-03-26 22:15:42 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 30/1251] eta: 0:13:01 lr: 0.000127 loss: 3.1797 (3.0234) grad_norm: 2.3887 (2.4328) time: 0.5081 [2021-03-26 22:15:48 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 40/1251] eta: 0:12:15 lr: 0.000127 loss: 2.8873 (2.9933) grad_norm: 2.4014 (2.4135) time: 0.5043 [2021-03-26 22:15:53 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 50/1251] eta: 0:11:46 lr: 0.000127 loss: 3.0264 (3.0061) grad_norm: 2.3469 (2.4106) time: 0.5089 [2021-03-26 22:15:58 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 60/1251] eta: 0:11:22 lr: 0.000127 loss: 3.1513 (3.0032) grad_norm: 2.3469 (2.4001) time: 0.5029 [2021-03-26 22:16:03 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 70/1251] eta: 0:11:04 lr: 0.000127 loss: 3.1217 (3.0319) grad_norm: 2.4007 (2.4104) time: 0.4970 [2021-03-26 22:16:08 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 80/1251] eta: 0:10:49 lr: 0.000127 loss: 3.1217 (3.0234) grad_norm: 2.4008 (2.4016) time: 0.4972 [2021-03-26 22:16:13 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 90/1251] eta: 0:10:37 lr: 0.000127 loss: 3.0992 (3.0225) grad_norm: 2.2347 (2.3895) time: 0.4998 [2021-03-26 22:16:18 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 100/1251] eta: 0:10:26 lr: 0.000127 loss: 2.8630 (2.9731) grad_norm: 2.1558 (2.3706) time: 0.5024 [2021-03-26 22:16:23 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 110/1251] eta: 0:10:17 lr: 0.000127 loss: 2.9207 (2.9855) grad_norm: 2.3047 (2.3819) time: 0.5062 [2021-03-26 22:16:28 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 120/1251] eta: 0:10:09 lr: 0.000127 loss: 2.9463 (2.9691) grad_norm: 2.4115 (2.4013) time: 0.5119 [2021-03-26 22:16:33 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 130/1251] eta: 0:10:01 lr: 0.000127 loss: 2.8493 (2.9706) grad_norm: 2.3659 (2.4056) time: 0.5098 [2021-03-26 22:16:38 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 140/1251] eta: 0:09:53 lr: 0.000127 loss: 3.1234 (2.9822) grad_norm: 2.3187 (2.4233) time: 0.5068 [2021-03-26 22:16:43 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 150/1251] eta: 0:09:46 lr: 0.000127 loss: 3.1234 (2.9885) grad_norm: 2.3584 (2.4162) time: 0.5057 [2021-03-26 22:16:48 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 160/1251] eta: 0:09:38 lr: 0.000126 loss: 3.0863 (2.9884) grad_norm: 2.2491 (2.4113) time: 0.5045 [2021-03-26 22:16:53 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 170/1251] eta: 0:09:32 lr: 0.000126 loss: 3.0738 (2.9883) grad_norm: 2.2535 (2.4036) time: 0.5080 [2021-03-26 22:16:58 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 180/1251] eta: 0:09:25 lr: 0.000126 loss: 2.9464 (2.9803) grad_norm: 2.3272 (2.4021) time: 0.5099 [2021-03-26 22:17:03 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 190/1251] eta: 0:09:19 lr: 0.000126 loss: 2.9205 (2.9714) grad_norm: 2.4023 (2.4078) time: 0.5051 [2021-03-26 22:17:09 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 200/1251] eta: 0:09:13 lr: 0.000126 loss: 2.9699 (2.9730) grad_norm: 2.4555 (2.4136) time: 0.5152 [2021-03-26 22:17:14 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 210/1251] eta: 0:09:07 lr: 0.000126 loss: 3.0984 (2.9755) grad_norm: 2.5176 (2.4209) time: 0.5199 [2021-03-26 22:17:19 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 220/1251] eta: 0:09:01 lr: 0.000126 loss: 2.9620 (2.9748) grad_norm: 2.5176 (2.4204) time: 0.5093 [2021-03-26 22:17:24 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 230/1251] eta: 0:08:55 lr: 0.000126 loss: 3.1032 (2.9842) grad_norm: 2.5481 (2.4308) time: 0.5075 [2021-03-26 22:17:29 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 240/1251] eta: 0:08:49 lr: 0.000126 loss: 3.0357 (2.9696) grad_norm: 2.4775 (2.4257) time: 0.5018 [2021-03-26 22:17:34 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 250/1251] eta: 0:08:43 lr: 0.000126 loss: 2.8201 (2.9620) grad_norm: 2.3995 (2.4329) time: 0.5019 [2021-03-26 22:17:39 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 260/1251] eta: 0:08:37 lr: 0.000126 loss: 2.8906 (2.9639) grad_norm: 2.3995 (2.4296) time: 0.5025 [2021-03-26 22:17:44 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 270/1251] eta: 0:08:30 lr: 0.000126 loss: 3.0088 (2.9596) grad_norm: 2.3609 (2.4273) time: 0.4947 [2021-03-26 22:17:49 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 280/1251] eta: 0:08:25 lr: 0.000126 loss: 2.9083 (2.9560) grad_norm: 2.3644 (2.4249) time: 0.5000 [2021-03-26 22:17:54 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 290/1251] eta: 0:08:19 lr: 0.000126 loss: 2.6955 (2.9445) grad_norm: 2.2874 (2.4202) time: 0.5045 [2021-03-26 22:17:59 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 300/1251] eta: 0:08:13 lr: 0.000126 loss: 2.9757 (2.9452) grad_norm: 2.3272 (2.4184) time: 0.5041 [2021-03-26 22:18:04 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 310/1251] eta: 0:08:07 lr: 0.000126 loss: 3.0728 (2.9461) grad_norm: 2.3680 (2.4218) time: 0.5032 [2021-03-26 22:18:09 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 320/1251] eta: 0:08:02 lr: 0.000126 loss: 2.8079 (2.9412) grad_norm: 2.3969 (2.4252) time: 0.5026 [2021-03-26 22:18:14 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 330/1251] eta: 0:07:56 lr: 0.000126 loss: 2.8763 (2.9432) grad_norm: 2.2495 (2.4223) time: 0.5054 [2021-03-26 22:18:19 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 340/1251] eta: 0:07:51 lr: 0.000126 loss: 3.1813 (2.9456) grad_norm: 2.2360 (2.4175) time: 0.5067 [2021-03-26 22:18:24 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 350/1251] eta: 0:07:45 lr: 0.000126 loss: 3.0415 (2.9477) grad_norm: 2.2604 (2.4161) time: 0.5058 [2021-03-26 22:18:29 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 360/1251] eta: 0:07:40 lr: 0.000126 loss: 3.1067 (2.9534) grad_norm: 2.4108 (2.4178) time: 0.5003 [2021-03-26 22:18:34 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 370/1251] eta: 0:07:34 lr: 0.000126 loss: 3.1067 (2.9496) grad_norm: 2.4161 (2.4187) time: 0.4980 [2021-03-26 22:18:39 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 380/1251] eta: 0:07:29 lr: 0.000126 loss: 3.1403 (2.9518) grad_norm: 2.3984 (2.4228) time: 0.5003 [2021-03-26 22:18:44 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 390/1251] eta: 0:07:23 lr: 0.000126 loss: 3.1403 (2.9485) grad_norm: 2.3488 (2.4215) time: 0.5024 [2021-03-26 22:18:49 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 400/1251] eta: 0:07:18 lr: 0.000126 loss: 3.1480 (2.9551) grad_norm: 2.3258 (2.4206) time: 0.5004 [2021-03-26 22:18:54 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 410/1251] eta: 0:07:12 lr: 0.000126 loss: 3.1480 (2.9590) grad_norm: 2.3234 (2.4183) time: 0.4977 [2021-03-26 22:18:59 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 420/1251] eta: 0:07:07 lr: 0.000126 loss: 3.1208 (2.9601) grad_norm: 2.3895 (2.4299) time: 0.5093 [2021-03-26 22:19:04 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 430/1251] eta: 0:07:02 lr: 0.000126 loss: 3.0911 (2.9625) grad_norm: 2.4748 (2.4329) time: 0.5108 [2021-03-26 22:19:09 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 440/1251] eta: 0:06:56 lr: 0.000126 loss: 2.7736 (2.9542) grad_norm: 2.4279 (2.4361) time: 0.4969 [2021-03-26 22:19:14 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 450/1251] eta: 0:06:51 lr: 0.000126 loss: 2.7633 (2.9519) grad_norm: 2.4125 (2.4342) time: 0.4982 [2021-03-26 22:19:19 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 460/1251] eta: 0:06:46 lr: 0.000126 loss: 3.0211 (2.9523) grad_norm: 2.3296 (2.4372) time: 0.5031 [2021-03-26 22:19:24 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 470/1251] eta: 0:06:40 lr: 0.000126 loss: 3.1111 (2.9536) grad_norm: 2.3405 (2.4361) time: 0.5016 [2021-03-26 22:19:29 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 480/1251] eta: 0:06:35 lr: 0.000126 loss: 3.1549 (2.9554) grad_norm: 2.3405 (2.4336) time: 0.4978 [2021-03-26 22:19:34 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 490/1251] eta: 0:06:30 lr: 0.000126 loss: 3.0579 (2.9542) grad_norm: 2.2941 (2.4344) time: 0.5036 [2021-03-26 22:19:39 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 500/1251] eta: 0:06:24 lr: 0.000126 loss: 2.9373 (2.9533) grad_norm: 2.2659 (2.4336) time: 0.5099 [2021-03-26 22:19:44 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 510/1251] eta: 0:06:19 lr: 0.000126 loss: 2.9109 (2.9527) grad_norm: 2.2659 (2.4322) time: 0.5025 [2021-03-26 22:19:49 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 520/1251] eta: 0:06:14 lr: 0.000126 loss: 2.9820 (2.9536) grad_norm: 2.3091 (2.4310) time: 0.4944 [2021-03-26 22:19:54 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 530/1251] eta: 0:06:08 lr: 0.000126 loss: 3.1180 (2.9559) grad_norm: 2.3157 (2.4291) time: 0.4946 [2021-03-26 22:19:59 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 540/1251] eta: 0:06:03 lr: 0.000125 loss: 3.0774 (2.9568) grad_norm: 2.3133 (2.4307) time: 0.5045 [2021-03-26 22:20:05 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 550/1251] eta: 0:05:58 lr: 0.000125 loss: 3.0950 (2.9582) grad_norm: 2.3133 (2.4292) time: 0.5218 [2021-03-26 22:20:10 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 560/1251] eta: 0:05:53 lr: 0.000125 loss: 3.0372 (2.9560) grad_norm: 2.3168 (2.4293) time: 0.5129 [2021-03-26 22:20:15 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 570/1251] eta: 0:05:48 lr: 0.000125 loss: 2.9732 (2.9594) grad_norm: 2.3746 (2.4283) time: 0.4985 [2021-03-26 22:20:20 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 580/1251] eta: 0:05:43 lr: 0.000125 loss: 2.9118 (2.9556) grad_norm: 2.3746 (2.4274) time: 0.5019 [2021-03-26 22:20:25 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 590/1251] eta: 0:05:37 lr: 0.000125 loss: 2.6043 (2.9523) grad_norm: 2.3825 (2.4280) time: 0.5030 [2021-03-26 22:20:30 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 600/1251] eta: 0:05:32 lr: 0.000125 loss: 2.8600 (2.9503) grad_norm: 2.3825 (2.4272) time: 0.5069 [2021-03-26 22:20:35 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 610/1251] eta: 0:05:27 lr: 0.000125 loss: 2.9464 (2.9461) grad_norm: 2.3574 (2.4278) time: 0.5025 [2021-03-26 22:20:40 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 620/1251] eta: 0:05:22 lr: 0.000125 loss: 2.9129 (2.9454) grad_norm: 2.3574 (2.4274) time: 0.4965 [2021-03-26 22:20:45 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 630/1251] eta: 0:05:17 lr: 0.000125 loss: 3.1136 (2.9495) grad_norm: 2.4873 (2.4385) time: 0.4968 [2021-03-26 22:20:50 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 640/1251] eta: 0:05:11 lr: 0.000125 loss: 3.1136 (2.9481) grad_norm: 2.3481 (2.4380) time: 0.4998 [2021-03-26 22:20:55 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 650/1251] eta: 0:05:06 lr: 0.000125 loss: 2.7462 (2.9441) grad_norm: 2.3481 (2.4387) time: 0.5041 [2021-03-26 22:21:00 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 660/1251] eta: 0:05:01 lr: 0.000125 loss: 2.8033 (2.9442) grad_norm: 2.3772 (2.4386) time: 0.5024 [2021-03-26 22:21:05 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 670/1251] eta: 0:04:56 lr: 0.000125 loss: 2.8749 (2.9418) grad_norm: 2.2855 (2.4374) time: 0.5058 [2021-03-26 22:21:10 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 680/1251] eta: 0:04:51 lr: 0.000125 loss: 2.9905 (2.9423) grad_norm: 2.2952 (2.4369) time: 0.5094 [2021-03-26 22:21:15 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 690/1251] eta: 0:04:46 lr: 0.000125 loss: 3.0426 (2.9419) grad_norm: 2.4110 (2.4369) time: 0.5050 [2021-03-26 22:21:20 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 700/1251] eta: 0:04:41 lr: 0.000125 loss: 2.9018 (2.9413) grad_norm: 2.4110 (2.4356) time: 0.5066 [2021-03-26 22:21:25 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 710/1251] eta: 0:04:35 lr: 0.000125 loss: 2.9090 (2.9408) grad_norm: 2.3483 (2.4346) time: 0.5053 [2021-03-26 22:21:30 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 720/1251] eta: 0:04:30 lr: 0.000125 loss: 2.6587 (2.9358) grad_norm: 2.4444 (2.4387) time: 0.5027 [2021-03-26 22:21:35 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 730/1251] eta: 0:04:25 lr: 0.000125 loss: 2.8406 (2.9385) grad_norm: 2.4153 (2.4401) time: 0.4992 [2021-03-26 22:21:41 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 740/1251] eta: 0:04:20 lr: 0.000125 loss: 3.1286 (2.9414) grad_norm: 2.3525 (2.4409) time: 0.5269 [2021-03-26 22:21:46 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 750/1251] eta: 0:04:15 lr: 0.000125 loss: 3.0333 (2.9405) grad_norm: 2.3804 (2.4425) time: 0.5390 [2021-03-26 22:21:51 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 760/1251] eta: 0:04:10 lr: 0.000125 loss: 2.8373 (2.9391) grad_norm: 2.3655 (2.4434) time: 0.5188 [2021-03-26 22:21:56 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 770/1251] eta: 0:04:05 lr: 0.000125 loss: 2.9230 (2.9366) grad_norm: 2.3123 (2.4427) time: 0.5124 [2021-03-26 22:22:01 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 780/1251] eta: 0:04:00 lr: 0.000125 loss: 2.8631 (2.9339) grad_norm: 2.3921 (2.4426) time: 0.4987 [2021-03-26 22:22:06 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 790/1251] eta: 0:03:55 lr: 0.000125 loss: 2.8378 (2.9346) grad_norm: 2.4160 (2.4432) time: 0.5011 [2021-03-26 22:22:11 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 800/1251] eta: 0:03:50 lr: 0.000125 loss: 2.9742 (2.9333) grad_norm: 2.4460 (2.4447) time: 0.5043 [2021-03-26 22:22:16 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 810/1251] eta: 0:03:44 lr: 0.000125 loss: 3.0707 (2.9355) grad_norm: 2.3618 (2.4435) time: 0.5015 [2021-03-26 22:22:21 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 820/1251] eta: 0:03:39 lr: 0.000125 loss: 3.1796 (2.9364) grad_norm: 2.4837 (2.4453) time: 0.5016 [2021-03-26 22:22:26 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 830/1251] eta: 0:03:34 lr: 0.000125 loss: 3.0260 (2.9356) grad_norm: 2.5928 (2.4456) time: 0.4969 [2021-03-26 22:22:31 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 840/1251] eta: 0:03:29 lr: 0.000125 loss: 3.0260 (2.9366) grad_norm: 2.6074 (2.4492) time: 0.4978 [2021-03-26 22:22:36 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 850/1251] eta: 0:03:24 lr: 0.000125 loss: 3.0393 (2.9366) grad_norm: 2.5947 (2.4493) time: 0.5093 [2021-03-26 22:22:42 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 860/1251] eta: 0:03:19 lr: 0.000125 loss: 2.9335 (2.9369) grad_norm: 2.3812 (2.4478) time: 0.5116 [2021-03-26 22:22:46 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 870/1251] eta: 0:03:14 lr: 0.000125 loss: 2.7557 (2.9325) grad_norm: 2.2782 (2.4473) time: 0.5021 [2021-03-26 22:22:51 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 880/1251] eta: 0:03:08 lr: 0.000125 loss: 2.8080 (2.9325) grad_norm: 2.5346 (2.4479) time: 0.4969 [2021-03-26 22:22:56 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 890/1251] eta: 0:03:03 lr: 0.000125 loss: 2.9269 (2.9305) grad_norm: 2.5071 (2.4480) time: 0.4937 [2021-03-26 22:23:01 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 900/1251] eta: 0:02:58 lr: 0.000125 loss: 2.8938 (2.9309) grad_norm: 2.3329 (2.4498) time: 0.4936 [2021-03-26 22:23:06 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 910/1251] eta: 0:02:53 lr: 0.000124 loss: 2.9235 (2.9321) grad_norm: 2.5441 (2.4500) time: 0.4996 [2021-03-26 22:23:11 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 920/1251] eta: 0:02:48 lr: 0.000124 loss: 3.0917 (2.9321) grad_norm: 2.3869 (2.4486) time: 0.5005 [2021-03-26 22:23:16 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 930/1251] eta: 0:02:43 lr: 0.000124 loss: 3.1086 (2.9333) grad_norm: 2.3245 (2.4480) time: 0.5056 [2021-03-26 22:23:22 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 940/1251] eta: 0:02:38 lr: 0.000124 loss: 3.1342 (2.9327) grad_norm: 2.3669 (2.4492) time: 0.5127 [2021-03-26 22:23:27 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 950/1251] eta: 0:02:33 lr: 0.000124 loss: 3.0782 (2.9308) grad_norm: 2.5190 (2.4500) time: 0.5118 [2021-03-26 22:23:32 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 960/1251] eta: 0:02:28 lr: 0.000124 loss: 2.9602 (2.9303) grad_norm: 2.4879 (2.4498) time: 0.5100 [2021-03-26 22:23:37 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 970/1251] eta: 0:02:23 lr: 0.000124 loss: 3.0106 (2.9319) grad_norm: 2.4060 (2.4511) time: 0.5081 [2021-03-26 22:23:42 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 980/1251] eta: 0:02:17 lr: 0.000124 loss: 3.2725 (2.9334) grad_norm: 2.3618 (2.4502) time: 0.5035 [2021-03-26 22:23:47 swin_small_patch4_window7_224] INFO: Epoch: [233] [ 990/1251] eta: 0:02:12 lr: 0.000124 loss: 3.1708 (2.9355) grad_norm: 2.4130 (2.4502) time: 0.5015 [2021-03-26 22:23:52 swin_small_patch4_window7_224] INFO: Epoch: [233] [1000/1251] eta: 0:02:07 lr: 0.000124 loss: 3.0023 (2.9351) grad_norm: 2.4912 (2.4505) time: 0.5030 [2021-03-26 22:23:57 swin_small_patch4_window7_224] INFO: Epoch: [233] [1010/1251] eta: 0:02:02 lr: 0.000124 loss: 2.8833 (2.9351) grad_norm: 2.5249 (2.4518) time: 0.5003 [2021-03-26 22:24:02 swin_small_patch4_window7_224] INFO: Epoch: [233] [1020/1251] eta: 0:01:57 lr: 0.000124 loss: 3.0140 (2.9354) grad_norm: 2.4496 (2.4518) time: 0.5024 [2021-03-26 22:24:07 swin_small_patch4_window7_224] INFO: Epoch: [233] [1030/1251] eta: 0:01:52 lr: 0.000124 loss: 3.0140 (2.9356) grad_norm: 2.3496 (2.4509) time: 0.5030 [2021-03-26 22:24:12 swin_small_patch4_window7_224] INFO: Epoch: [233] [1040/1251] eta: 0:01:47 lr: 0.000124 loss: 3.1351 (2.9376) grad_norm: 2.3496 (2.4505) time: 0.5010 [2021-03-26 22:24:17 swin_small_patch4_window7_224] INFO: Epoch: [233] [1050/1251] eta: 0:01:42 lr: 0.000124 loss: 3.1351 (2.9390) grad_norm: 2.3557 (2.4498) time: 0.5010 [2021-03-26 22:24:22 swin_small_patch4_window7_224] INFO: Epoch: [233] [1060/1251] eta: 0:01:37 lr: 0.000124 loss: 3.0609 (2.9399) grad_norm: 2.4124 (2.4516) time: 0.4993 [2021-03-26 22:24:27 swin_small_patch4_window7_224] INFO: Epoch: [233] [1070/1251] eta: 0:01:31 lr: 0.000124 loss: 3.0609 (2.9406) grad_norm: 2.3544 (2.4501) time: 0.4980 [2021-03-26 22:24:32 swin_small_patch4_window7_224] INFO: Epoch: [233] [1080/1251] eta: 0:01:26 lr: 0.000124 loss: 2.8811 (2.9383) grad_norm: 2.3628 (2.4496) time: 0.5013 [2021-03-26 22:24:37 swin_small_patch4_window7_224] INFO: Epoch: [233] [1090/1251] eta: 0:01:21 lr: 0.000124 loss: 2.8811 (2.9378) grad_norm: 2.4186 (2.4486) time: 0.5047 [2021-03-26 22:24:42 swin_small_patch4_window7_224] INFO: Epoch: [233] [1100/1251] eta: 0:01:16 lr: 0.000124 loss: 3.0555 (2.9389) grad_norm: 2.4050 (2.4483) time: 0.4990 [2021-03-26 22:24:47 swin_small_patch4_window7_224] INFO: Epoch: [233] [1110/1251] eta: 0:01:11 lr: 0.000124 loss: 3.0555 (2.9392) grad_norm: 2.3154 (2.4467) time: 0.4955 [2021-03-26 22:24:52 swin_small_patch4_window7_224] INFO: Epoch: [233] [1120/1251] eta: 0:01:06 lr: 0.000124 loss: 3.0827 (2.9391) grad_norm: 2.3300 (2.4478) time: 0.5031 [2021-03-26 22:24:57 swin_small_patch4_window7_224] INFO: Epoch: [233] [1130/1251] eta: 0:01:01 lr: 0.000124 loss: 3.0025 (2.9388) grad_norm: 2.4742 (2.4480) time: 0.5027 [2021-03-26 22:25:02 swin_small_patch4_window7_224] INFO: Epoch: [233] [1140/1251] eta: 0:00:56 lr: 0.000124 loss: 2.8797 (2.9369) grad_norm: 2.2923 (2.4465) time: 0.4999 [2021-03-26 22:25:07 swin_small_patch4_window7_224] INFO: Epoch: [233] [1150/1251] eta: 0:00:51 lr: 0.000124 loss: 3.0563 (2.9381) grad_norm: 2.2574 (2.4452) time: 0.4991 [2021-03-26 22:25:12 swin_small_patch4_window7_224] INFO: Epoch: [233] [1160/1251] eta: 0:00:46 lr: 0.000124 loss: 3.0651 (2.9378) grad_norm: 2.3829 (2.4459) time: 0.5063 [2021-03-26 22:25:17 swin_small_patch4_window7_224] INFO: Epoch: [233] [1170/1251] eta: 0:00:41 lr: 0.000124 loss: 3.1050 (2.9386) grad_norm: 2.4240 (2.4467) time: 0.5075 [2021-03-26 22:25:22 swin_small_patch4_window7_224] INFO: Epoch: [233] [1180/1251] eta: 0:00:36 lr: 0.000124 loss: 3.1689 (2.9404) grad_norm: 2.3476 (2.4464) time: 0.4988 [2021-03-26 22:25:27 swin_small_patch4_window7_224] INFO: Epoch: [233] [1190/1251] eta: 0:00:30 lr: 0.000124 loss: 3.0899 (2.9403) grad_norm: 2.4428 (2.4475) time: 0.4989 [2021-03-26 22:25:32 swin_small_patch4_window7_224] INFO: Epoch: [233] [1200/1251] eta: 0:00:25 lr: 0.000124 loss: 3.0029 (2.9401) grad_norm: 2.5730 (2.4494) time: 0.4992 [2021-03-26 22:25:37 swin_small_patch4_window7_224] INFO: Epoch: [233] [1210/1251] eta: 0:00:20 lr: 0.000124 loss: 3.0058 (2.9404) grad_norm: 2.3796 (2.4491) time: 0.4990 [2021-03-26 22:25:42 swin_small_patch4_window7_224] INFO: Epoch: [233] [1220/1251] eta: 0:00:15 lr: 0.000124 loss: 2.9593 (2.9406) grad_norm: 2.3065 (2.4492) time: 0.5002 [2021-03-26 22:25:47 swin_small_patch4_window7_224] INFO: Epoch: [233] [1230/1251] eta: 0:00:10 lr: 0.000124 loss: 2.9098 (2.9391) grad_norm: 2.2813 (2.4491) time: 0.5028 [2021-03-26 22:25:52 swin_small_patch4_window7_224] INFO: Epoch: [233] [1240/1251] eta: 0:00:05 lr: 0.000124 loss: 3.0196 (2.9415) grad_norm: 2.3992 (2.4493) time: 0.5026 [2021-03-26 22:25:57 swin_small_patch4_window7_224] INFO: Epoch: [233] [1250/1251] eta: 0:00:00 lr: 0.000124 loss: 3.2670 (2.9436) grad_norm: 2.4377 (2.4498) time: 0.5012 [2021-03-26 22:26:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:05 loss: 0.7346 (0.7346) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-26 22:26:08 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7363 (0.8177) acc1: 79.6875 (79.1193) acc5: 96.8750 (95.7386) [2021-03-26 22:26:10 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7237 (0.7649) acc1: 81.2500 (81.4732) acc5: 96.8750 (96.5774) [2021-03-26 22:26:11 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7237 (0.7809) acc1: 81.2500 (81.0988) acc5: 96.8750 (96.3710) [2021-03-26 22:26:14 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8609 (0.7854) acc1: 78.1250 (80.7927) acc5: 96.8750 (96.2652) [2021-03-26 22:26:14 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8297 (0.7925) acc1: 79.6875 (80.5440) acc5: 96.8750 (96.2240) [2021-03-26 22:26:24 swin_small_patch4_window7_224] INFO: * Acc@1 81.830 Acc@5 95.864 loss 0.776 [2021-03-26 22:26:24 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-26 22:26:24 swin_small_patch4_window7_224] INFO: Max accuracy: 81.83% [2021-03-26 22:26:28 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 0/1251] eta: 1:25:55 lr: 0.000124 loss: 3.0185 (3.0185) grad_norm: 2.4934 (2.4934) time: 4.1212 [2021-03-26 22:26:34 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 10/1251] eta: 0:17:29 lr: 0.000124 loss: 3.2917 (3.1337) grad_norm: 2.3818 (2.3032) time: 0.8455 [2021-03-26 22:26:39 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 20/1251] eta: 0:14:01 lr: 0.000124 loss: 3.1474 (3.1518) grad_norm: 2.3818 (2.4424) time: 0.5119 [2021-03-26 22:26:44 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 30/1251] eta: 0:12:45 lr: 0.000124 loss: 3.0545 (3.0319) grad_norm: 2.4233 (2.5219) time: 0.5062 [2021-03-26 22:26:49 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 40/1251] eta: 0:12:06 lr: 0.000123 loss: 3.0247 (3.0343) grad_norm: 2.4233 (2.5070) time: 0.5127 [2021-03-26 22:26:54 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 50/1251] eta: 0:11:41 lr: 0.000123 loss: 3.1225 (3.0780) grad_norm: 2.4127 (2.4803) time: 0.5176 [2021-03-26 22:26:59 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 60/1251] eta: 0:11:20 lr: 0.000123 loss: 3.0436 (3.0112) grad_norm: 2.3968 (2.4804) time: 0.5120 [2021-03-26 22:27:04 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 70/1251] eta: 0:11:02 lr: 0.000123 loss: 2.8529 (3.0161) grad_norm: 2.5000 (inf) time: 0.5014 [2021-03-26 22:27:09 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 80/1251] eta: 0:10:49 lr: 0.000123 loss: 2.9815 (3.0277) grad_norm: 2.4161 (inf) time: 0.5023 [2021-03-26 22:27:14 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 90/1251] eta: 0:10:37 lr: 0.000123 loss: 3.1360 (3.0132) grad_norm: 2.3390 (inf) time: 0.5095 [2021-03-26 22:27:19 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 100/1251] eta: 0:10:26 lr: 0.000123 loss: 3.1069 (3.0079) grad_norm: 2.4555 (inf) time: 0.5026 [2021-03-26 22:27:24 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 110/1251] eta: 0:10:15 lr: 0.000123 loss: 3.0567 (2.9844) grad_norm: 2.4555 (inf) time: 0.4963 [2021-03-26 22:27:29 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 120/1251] eta: 0:10:06 lr: 0.000123 loss: 2.9542 (2.9783) grad_norm: 2.4493 (inf) time: 0.4971 [2021-03-26 22:27:34 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 130/1251] eta: 0:09:57 lr: 0.000123 loss: 2.9542 (2.9650) grad_norm: 2.4217 (inf) time: 0.4968 [2021-03-26 22:27:39 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 140/1251] eta: 0:09:51 lr: 0.000123 loss: 2.7796 (2.9601) grad_norm: 2.3420 (inf) time: 0.5058 [2021-03-26 22:27:44 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 150/1251] eta: 0:09:43 lr: 0.000123 loss: 2.6200 (2.9479) grad_norm: 2.3851 (inf) time: 0.5096 [2021-03-26 22:27:49 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 160/1251] eta: 0:09:36 lr: 0.000123 loss: 2.6483 (2.9376) grad_norm: 2.4826 (inf) time: 0.5005 [2021-03-26 22:27:54 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 170/1251] eta: 0:09:28 lr: 0.000123 loss: 2.7908 (2.9242) grad_norm: 2.5303 (inf) time: 0.4966 [2021-03-26 22:27:59 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 180/1251] eta: 0:09:22 lr: 0.000123 loss: 3.0683 (2.9348) grad_norm: 2.4191 (inf) time: 0.5017 [2021-03-26 22:28:04 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 190/1251] eta: 0:09:16 lr: 0.000123 loss: 2.9980 (2.9336) grad_norm: 2.3423 (inf) time: 0.5064 [2021-03-26 22:28:10 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 200/1251] eta: 0:09:10 lr: 0.000123 loss: 2.8234 (2.9212) grad_norm: 2.5485 (inf) time: 0.5114 [2021-03-26 22:28:15 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 210/1251] eta: 0:09:04 lr: 0.000123 loss: 2.5651 (2.9068) grad_norm: 2.5126 (inf) time: 0.5078 [2021-03-26 22:28:20 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 220/1251] eta: 0:08:58 lr: 0.000123 loss: 2.9749 (2.9066) grad_norm: 2.4681 (inf) time: 0.5027 [2021-03-26 22:28:25 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 230/1251] eta: 0:08:52 lr: 0.000123 loss: 3.0855 (2.9109) grad_norm: 2.4718 (inf) time: 0.5053 [2021-03-26 22:28:30 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 240/1251] eta: 0:08:46 lr: 0.000123 loss: 3.0855 (2.9119) grad_norm: 2.4614 (inf) time: 0.5081 [2021-03-26 22:28:35 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 250/1251] eta: 0:08:40 lr: 0.000123 loss: 3.1288 (2.9193) grad_norm: 2.4326 (inf) time: 0.5052 [2021-03-26 22:28:40 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 260/1251] eta: 0:08:34 lr: 0.000123 loss: 3.0297 (2.9147) grad_norm: 2.4114 (inf) time: 0.5010 [2021-03-26 22:28:45 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 270/1251] eta: 0:08:28 lr: 0.000123 loss: 2.8677 (2.9167) grad_norm: 2.4684 (inf) time: 0.4995 [2021-03-26 22:28:50 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 280/1251] eta: 0:08:22 lr: 0.000123 loss: 2.8868 (2.9131) grad_norm: 2.4961 (inf) time: 0.4989 [2021-03-26 22:28:55 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 290/1251] eta: 0:08:16 lr: 0.000123 loss: 2.8632 (2.9070) grad_norm: 2.5421 (inf) time: 0.5004 [2021-03-26 22:29:00 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 300/1251] eta: 0:08:11 lr: 0.000123 loss: 3.0008 (2.9098) grad_norm: 2.4131 (inf) time: 0.4974 [2021-03-26 22:29:05 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 310/1251] eta: 0:08:05 lr: 0.000123 loss: 3.1200 (2.9156) grad_norm: 2.4590 (inf) time: 0.4987 [2021-03-26 22:29:10 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 320/1251] eta: 0:07:59 lr: 0.000123 loss: 3.0947 (2.9149) grad_norm: 2.3764 (inf) time: 0.4960 [2021-03-26 22:29:15 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 330/1251] eta: 0:07:54 lr: 0.000123 loss: 3.1377 (2.9218) grad_norm: 2.3317 (inf) time: 0.4991 [2021-03-26 22:29:20 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 340/1251] eta: 0:07:48 lr: 0.000123 loss: 3.2117 (2.9246) grad_norm: 2.4424 (inf) time: 0.5063 [2021-03-26 22:29:25 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 350/1251] eta: 0:07:43 lr: 0.000123 loss: 2.7676 (2.9164) grad_norm: 2.4752 (inf) time: 0.5089 [2021-03-26 22:29:30 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 360/1251] eta: 0:07:38 lr: 0.000123 loss: 2.7390 (2.9102) grad_norm: 2.5746 (inf) time: 0.5076 [2021-03-26 22:29:35 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 370/1251] eta: 0:07:32 lr: 0.000123 loss: 3.0123 (2.9136) grad_norm: 2.5502 (inf) time: 0.4993 [2021-03-26 22:29:40 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 380/1251] eta: 0:07:27 lr: 0.000123 loss: 3.2296 (2.9144) grad_norm: 2.4809 (inf) time: 0.5004 [2021-03-26 22:29:45 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 390/1251] eta: 0:07:21 lr: 0.000123 loss: 3.0541 (2.9162) grad_norm: 2.4767 (inf) time: 0.5015 [2021-03-26 22:29:50 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 400/1251] eta: 0:07:16 lr: 0.000123 loss: 2.9285 (2.9160) grad_norm: 2.5910 (inf) time: 0.4962 [2021-03-26 22:29:55 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 410/1251] eta: 0:07:10 lr: 0.000123 loss: 2.8190 (2.9154) grad_norm: 2.7222 (inf) time: 0.4964 [2021-03-26 22:30:00 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 420/1251] eta: 0:07:05 lr: 0.000122 loss: 2.8272 (2.9133) grad_norm: 2.3867 (inf) time: 0.5026 [2021-03-26 22:30:05 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 430/1251] eta: 0:07:00 lr: 0.000122 loss: 2.8624 (2.9101) grad_norm: 2.4461 (inf) time: 0.5030 [2021-03-26 22:30:10 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 440/1251] eta: 0:06:54 lr: 0.000122 loss: 2.5251 (2.9059) grad_norm: 2.4598 (inf) time: 0.4971 [2021-03-26 22:30:15 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 450/1251] eta: 0:06:49 lr: 0.000122 loss: 2.9966 (2.9050) grad_norm: 2.4784 (inf) time: 0.4986 [2021-03-26 22:30:20 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 460/1251] eta: 0:06:44 lr: 0.000122 loss: 2.9966 (2.9023) grad_norm: 2.4683 (inf) time: 0.4998 [2021-03-26 22:30:25 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 470/1251] eta: 0:06:38 lr: 0.000122 loss: 2.8640 (2.9011) grad_norm: 2.4280 (inf) time: 0.4971 [2021-03-26 22:30:30 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 480/1251] eta: 0:06:33 lr: 0.000122 loss: 2.9072 (2.9022) grad_norm: 2.4593 (inf) time: 0.4950 [2021-03-26 22:30:35 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 490/1251] eta: 0:06:28 lr: 0.000122 loss: 2.9072 (2.8999) grad_norm: 2.4879 (inf) time: 0.4970 [2021-03-26 22:30:40 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 500/1251] eta: 0:06:22 lr: 0.000122 loss: 2.9710 (2.9046) grad_norm: 2.4333 (inf) time: 0.4982 [2021-03-26 22:30:45 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 510/1251] eta: 0:06:17 lr: 0.000122 loss: 3.0567 (2.9070) grad_norm: 2.3459 (inf) time: 0.4998 [2021-03-26 22:30:50 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 520/1251] eta: 0:06:12 lr: 0.000122 loss: 2.8770 (2.9063) grad_norm: 2.4579 (inf) time: 0.5082 [2021-03-26 22:30:55 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 530/1251] eta: 0:06:07 lr: 0.000122 loss: 2.8770 (2.9059) grad_norm: 2.6397 (inf) time: 0.5074 [2021-03-26 22:31:00 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 540/1251] eta: 0:06:02 lr: 0.000122 loss: 3.0612 (2.9096) grad_norm: 2.6397 (inf) time: 0.5093 [2021-03-26 22:31:05 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 550/1251] eta: 0:05:57 lr: 0.000122 loss: 3.1129 (2.9103) grad_norm: 2.4628 (inf) time: 0.5174 [2021-03-26 22:31:10 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 560/1251] eta: 0:05:52 lr: 0.000122 loss: 2.9110 (2.9102) grad_norm: 2.3989 (inf) time: 0.5112 [2021-03-26 22:31:15 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 570/1251] eta: 0:05:47 lr: 0.000122 loss: 2.9453 (2.9135) grad_norm: 2.3989 (inf) time: 0.5049 [2021-03-26 22:31:20 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 580/1251] eta: 0:05:41 lr: 0.000122 loss: 3.0656 (2.9112) grad_norm: 2.3487 (inf) time: 0.4988 [2021-03-26 22:31:25 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 590/1251] eta: 0:05:36 lr: 0.000122 loss: 2.9651 (2.9092) grad_norm: 2.2984 (inf) time: 0.4967 [2021-03-26 22:31:31 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 600/1251] eta: 0:05:31 lr: 0.000122 loss: 2.9651 (2.9115) grad_norm: 2.4413 (inf) time: 0.5102 [2021-03-26 22:31:36 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 610/1251] eta: 0:05:26 lr: 0.000122 loss: 3.0804 (2.9114) grad_norm: 2.4413 (inf) time: 0.5087 [2021-03-26 22:31:41 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 620/1251] eta: 0:05:21 lr: 0.000122 loss: 3.0452 (2.9111) grad_norm: 2.4472 (inf) time: 0.5007 [2021-03-26 22:31:46 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 630/1251] eta: 0:05:16 lr: 0.000122 loss: 2.9554 (2.9109) grad_norm: 2.4472 (inf) time: 0.4992 [2021-03-26 22:31:51 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 640/1251] eta: 0:05:10 lr: 0.000122 loss: 2.8368 (2.9093) grad_norm: 2.3767 (inf) time: 0.4976 [2021-03-26 22:31:56 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 650/1251] eta: 0:05:05 lr: 0.000122 loss: 2.8276 (2.9090) grad_norm: 2.3780 (inf) time: 0.5009 [2021-03-26 22:32:01 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 660/1251] eta: 0:05:00 lr: 0.000122 loss: 2.8276 (2.9097) grad_norm: 2.4709 (inf) time: 0.4991 [2021-03-26 22:32:05 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 670/1251] eta: 0:04:55 lr: 0.000122 loss: 2.8260 (2.9089) grad_norm: 2.4075 (inf) time: 0.4945 [2021-03-26 22:32:10 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 680/1251] eta: 0:04:50 lr: 0.000122 loss: 2.9636 (2.9086) grad_norm: 2.4724 (inf) time: 0.4941 [2021-03-26 22:32:15 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 690/1251] eta: 0:04:44 lr: 0.000122 loss: 2.9716 (2.9086) grad_norm: 2.4284 (inf) time: 0.4980 [2021-03-26 22:32:20 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 700/1251] eta: 0:04:39 lr: 0.000122 loss: 2.9057 (2.9065) grad_norm: 2.3835 (inf) time: 0.4999 [2021-03-26 22:32:25 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 710/1251] eta: 0:04:34 lr: 0.000122 loss: 2.9837 (2.9083) grad_norm: 2.4435 (inf) time: 0.5029 [2021-03-26 22:32:30 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 720/1251] eta: 0:04:29 lr: 0.000122 loss: 3.1527 (2.9084) grad_norm: 2.3606 (inf) time: 0.5014 [2021-03-26 22:32:36 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 730/1251] eta: 0:04:24 lr: 0.000122 loss: 3.0399 (2.9086) grad_norm: 2.1854 (inf) time: 0.5046 [2021-03-26 22:32:41 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 740/1251] eta: 0:04:19 lr: 0.000122 loss: 3.0171 (2.9073) grad_norm: 2.2938 (inf) time: 0.5202 [2021-03-26 22:32:46 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 750/1251] eta: 0:04:14 lr: 0.000122 loss: 2.9233 (2.9062) grad_norm: 2.3839 (inf) time: 0.5227 [2021-03-26 22:32:51 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 760/1251] eta: 0:04:09 lr: 0.000122 loss: 3.0373 (2.9091) grad_norm: 2.3839 (inf) time: 0.5088 [2021-03-26 22:32:56 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 770/1251] eta: 0:04:04 lr: 0.000122 loss: 3.0626 (2.9107) grad_norm: 2.3477 (inf) time: 0.4974 [2021-03-26 22:33:01 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 780/1251] eta: 0:03:59 lr: 0.000122 loss: 3.0575 (2.9129) grad_norm: 2.3047 (inf) time: 0.4961 [2021-03-26 22:33:06 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 790/1251] eta: 0:03:54 lr: 0.000122 loss: 3.1843 (2.9153) grad_norm: 2.4585 (inf) time: 0.5010 [2021-03-26 22:33:11 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 800/1251] eta: 0:03:48 lr: 0.000121 loss: 3.0180 (2.9137) grad_norm: 2.4615 (inf) time: 0.5062 [2021-03-26 22:33:16 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 810/1251] eta: 0:03:43 lr: 0.000121 loss: 3.0641 (2.9154) grad_norm: 2.4615 (inf) time: 0.5034 [2021-03-26 22:33:21 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 820/1251] eta: 0:03:38 lr: 0.000121 loss: 3.0641 (2.9138) grad_norm: 2.5473 (inf) time: 0.5001 [2021-03-26 22:33:26 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 830/1251] eta: 0:03:33 lr: 0.000121 loss: 2.9102 (2.9148) grad_norm: 2.4244 (inf) time: 0.5047 [2021-03-26 22:33:31 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 840/1251] eta: 0:03:28 lr: 0.000121 loss: 2.8096 (2.9133) grad_norm: 2.3267 (inf) time: 0.5072 [2021-03-26 22:33:36 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 850/1251] eta: 0:03:23 lr: 0.000121 loss: 2.7950 (2.9121) grad_norm: 2.4736 (inf) time: 0.5049 [2021-03-26 22:33:41 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 860/1251] eta: 0:03:18 lr: 0.000121 loss: 2.8971 (2.9123) grad_norm: 2.4736 (inf) time: 0.5043 [2021-03-26 22:33:46 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 870/1251] eta: 0:03:13 lr: 0.000121 loss: 2.8971 (2.9118) grad_norm: 2.4310 (inf) time: 0.5043 [2021-03-26 22:33:51 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 880/1251] eta: 0:03:08 lr: 0.000121 loss: 2.8767 (2.9109) grad_norm: 2.4267 (inf) time: 0.5022 [2021-03-26 22:33:56 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 890/1251] eta: 0:03:03 lr: 0.000121 loss: 2.9075 (2.9116) grad_norm: 2.2183 (inf) time: 0.5002 [2021-03-26 22:34:01 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 900/1251] eta: 0:02:58 lr: 0.000121 loss: 3.0291 (2.9131) grad_norm: 2.2916 (inf) time: 0.5042 [2021-03-26 22:34:06 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 910/1251] eta: 0:02:52 lr: 0.000121 loss: 3.0725 (2.9132) grad_norm: 2.3964 (inf) time: 0.5062 [2021-03-26 22:34:11 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 920/1251] eta: 0:02:47 lr: 0.000121 loss: 2.9613 (2.9132) grad_norm: 2.4340 (inf) time: 0.5019 [2021-03-26 22:34:16 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 930/1251] eta: 0:02:42 lr: 0.000121 loss: 2.9521 (2.9129) grad_norm: 2.4782 (inf) time: 0.5010 [2021-03-26 22:34:22 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 940/1251] eta: 0:02:37 lr: 0.000121 loss: 3.0288 (2.9132) grad_norm: 2.4862 (inf) time: 0.5086 [2021-03-26 22:34:27 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 950/1251] eta: 0:02:32 lr: 0.000121 loss: 2.8207 (2.9113) grad_norm: 2.3393 (inf) time: 0.5083 [2021-03-26 22:34:32 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 960/1251] eta: 0:02:27 lr: 0.000121 loss: 2.7944 (2.9090) grad_norm: 2.3874 (inf) time: 0.4977 [2021-03-26 22:34:37 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 970/1251] eta: 0:02:22 lr: 0.000121 loss: 2.9744 (2.9106) grad_norm: 2.4871 (inf) time: 0.4955 [2021-03-26 22:34:42 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 980/1251] eta: 0:02:17 lr: 0.000121 loss: 3.0072 (2.9117) grad_norm: 2.5155 (inf) time: 0.4987 [2021-03-26 22:34:47 swin_small_patch4_window7_224] INFO: Epoch: [234] [ 990/1251] eta: 0:02:12 lr: 0.000121 loss: 2.9907 (2.9114) grad_norm: 2.3959 (inf) time: 0.5012 [2021-03-26 22:34:52 swin_small_patch4_window7_224] INFO: Epoch: [234] [1000/1251] eta: 0:02:07 lr: 0.000121 loss: 3.0165 (2.9116) grad_norm: 2.3101 (inf) time: 0.5010 [2021-03-26 22:34:57 swin_small_patch4_window7_224] INFO: Epoch: [234] [1010/1251] eta: 0:02:02 lr: 0.000121 loss: 3.1680 (2.9118) grad_norm: 2.3855 (inf) time: 0.5005 [2021-03-26 22:35:02 swin_small_patch4_window7_224] INFO: Epoch: [234] [1020/1251] eta: 0:01:57 lr: 0.000121 loss: 2.9764 (2.9110) grad_norm: 2.3832 (inf) time: 0.5006 [2021-03-26 22:35:07 swin_small_patch4_window7_224] INFO: Epoch: [234] [1030/1251] eta: 0:01:51 lr: 0.000121 loss: 3.0863 (2.9125) grad_norm: 2.3333 (inf) time: 0.5002 [2021-03-26 22:35:12 swin_small_patch4_window7_224] INFO: Epoch: [234] [1040/1251] eta: 0:01:46 lr: 0.000121 loss: 3.0863 (2.9112) grad_norm: 2.3561 (inf) time: 0.5007 [2021-03-26 22:35:17 swin_small_patch4_window7_224] INFO: Epoch: [234] [1050/1251] eta: 0:01:41 lr: 0.000121 loss: 3.0612 (2.9131) grad_norm: 2.5520 (inf) time: 0.5005 [2021-03-26 22:35:22 swin_small_patch4_window7_224] INFO: Epoch: [234] [1060/1251] eta: 0:01:36 lr: 0.000121 loss: 3.0422 (2.9133) grad_norm: 2.4698 (inf) time: 0.4976 [2021-03-26 22:35:27 swin_small_patch4_window7_224] INFO: Epoch: [234] [1070/1251] eta: 0:01:31 lr: 0.000121 loss: 3.0351 (2.9142) grad_norm: 2.4286 (inf) time: 0.5005 [2021-03-26 22:35:32 swin_small_patch4_window7_224] INFO: Epoch: [234] [1080/1251] eta: 0:01:26 lr: 0.000121 loss: 2.9586 (2.9124) grad_norm: 2.5247 (inf) time: 0.5035 [2021-03-26 22:35:37 swin_small_patch4_window7_224] INFO: Epoch: [234] [1090/1251] eta: 0:01:21 lr: 0.000121 loss: 2.9304 (2.9117) grad_norm: 2.5108 (inf) time: 0.5012 [2021-03-26 22:35:42 swin_small_patch4_window7_224] INFO: Epoch: [234] [1100/1251] eta: 0:01:16 lr: 0.000121 loss: 2.9149 (2.9115) grad_norm: 2.4210 (inf) time: 0.4987 [2021-03-26 22:35:47 swin_small_patch4_window7_224] INFO: Epoch: [234] [1110/1251] eta: 0:01:11 lr: 0.000121 loss: 2.9334 (2.9121) grad_norm: 2.4210 (inf) time: 0.4993 [2021-03-26 22:35:52 swin_small_patch4_window7_224] INFO: Epoch: [234] [1120/1251] eta: 0:01:06 lr: 0.000121 loss: 3.0681 (2.9122) grad_norm: 2.4034 (inf) time: 0.5012 [2021-03-26 22:35:57 swin_small_patch4_window7_224] INFO: Epoch: [234] [1130/1251] eta: 0:01:01 lr: 0.000121 loss: 2.6861 (2.9090) grad_norm: 2.4117 (inf) time: 0.5022 [2021-03-26 22:36:02 swin_small_patch4_window7_224] INFO: Epoch: [234] [1140/1251] eta: 0:00:56 lr: 0.000121 loss: 2.6956 (2.9089) grad_norm: 2.4489 (inf) time: 0.5007 [2021-03-26 22:36:07 swin_small_patch4_window7_224] INFO: Epoch: [234] [1150/1251] eta: 0:00:51 lr: 0.000121 loss: 2.9855 (2.9074) grad_norm: 2.4477 (inf) time: 0.4950 [2021-03-26 22:36:12 swin_small_patch4_window7_224] INFO: Epoch: [234] [1160/1251] eta: 0:00:46 lr: 0.000121 loss: 2.9855 (2.9069) grad_norm: 2.2682 (inf) time: 0.4969 [2021-03-26 22:36:17 swin_small_patch4_window7_224] INFO: Epoch: [234] [1170/1251] eta: 0:00:40 lr: 0.000121 loss: 3.0194 (2.9062) grad_norm: 2.4129 (inf) time: 0.4986 [2021-03-26 22:36:22 swin_small_patch4_window7_224] INFO: Epoch: [234] [1180/1251] eta: 0:00:35 lr: 0.000120 loss: 2.7579 (2.9047) grad_norm: 2.3003 (inf) time: 0.4965 [2021-03-26 22:36:27 swin_small_patch4_window7_224] INFO: Epoch: [234] [1190/1251] eta: 0:00:30 lr: 0.000120 loss: 2.7579 (2.9044) grad_norm: 2.3003 (inf) time: 0.4972 [2021-03-26 22:36:32 swin_small_patch4_window7_224] INFO: Epoch: [234] [1200/1251] eta: 0:00:25 lr: 0.000120 loss: 2.9886 (2.9057) grad_norm: 2.4157 (inf) time: 0.4986 [2021-03-26 22:36:37 swin_small_patch4_window7_224] INFO: Epoch: [234] [1210/1251] eta: 0:00:20 lr: 0.000120 loss: 2.9886 (2.9051) grad_norm: 2.3600 (inf) time: 0.5035 [2021-03-26 22:36:42 swin_small_patch4_window7_224] INFO: Epoch: [234] [1220/1251] eta: 0:00:15 lr: 0.000120 loss: 2.7877 (2.9033) grad_norm: 2.2877 (inf) time: 0.5042 [2021-03-26 22:36:47 swin_small_patch4_window7_224] INFO: Epoch: [234] [1230/1251] eta: 0:00:10 lr: 0.000120 loss: 2.7102 (2.9024) grad_norm: 2.4587 (inf) time: 0.5045 [2021-03-26 22:36:52 swin_small_patch4_window7_224] INFO: Epoch: [234] [1240/1251] eta: 0:00:05 lr: 0.000120 loss: 2.9528 (2.9023) grad_norm: 2.4310 (inf) time: 0.5082 [2021-03-26 22:36:57 swin_small_patch4_window7_224] INFO: Epoch: [234] [1250/1251] eta: 0:00:00 lr: 0.000120 loss: 3.0475 (2.9033) grad_norm: 2.3927 (inf) time: 0.4973 [2021-03-26 22:37:08 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:12 loss: 0.5096 (0.5096) acc1: 92.1875 (92.1875) acc5: 98.4375 (98.4375) [2021-03-26 22:37:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7099 (0.7089) acc1: 82.8125 (84.0909) acc5: 98.4375 (96.8750) [2021-03-26 22:37:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7652 (0.7651) acc1: 79.6875 (81.8452) acc5: 95.3125 (96.0565) [2021-03-26 22:37:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8783 (0.8058) acc1: 79.6875 (80.6452) acc5: 95.3125 (95.9173) [2021-03-26 22:37:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8056 (0.7965) acc1: 79.6875 (80.9832) acc5: 96.8750 (95.9985) [2021-03-26 22:37:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7933 (0.7892) acc1: 81.2500 (81.0240) acc5: 96.8750 (96.1600) [2021-03-26 22:37:30 swin_small_patch4_window7_224] INFO: * Acc@1 81.830 Acc@5 95.884 loss 0.776 [2021-03-26 22:37:30 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.8% [2021-03-26 22:37:30 swin_small_patch4_window7_224] INFO: Max accuracy: 81.83% [2021-03-26 22:37:35 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 0/1251] eta: 1:28:23 lr: 0.000120 loss: 3.2154 (3.2154) grad_norm: 2.4548 (2.4548) time: 4.2394 [2021-03-26 22:37:40 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 10/1251] eta: 0:17:32 lr: 0.000120 loss: 3.0300 (2.9708) grad_norm: 2.3825 (2.4147) time: 0.8481 [2021-03-26 22:37:45 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 20/1251] eta: 0:14:01 lr: 0.000120 loss: 3.0300 (2.9495) grad_norm: 2.3825 (2.4419) time: 0.5056 [2021-03-26 22:37:50 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 30/1251] eta: 0:12:41 lr: 0.000120 loss: 2.9722 (2.9479) grad_norm: 2.4837 (2.4779) time: 0.4999 [2021-03-26 22:37:55 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 40/1251] eta: 0:11:57 lr: 0.000120 loss: 2.9036 (2.9678) grad_norm: 2.6034 (2.5085) time: 0.4965 [2021-03-26 22:38:00 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 50/1251] eta: 0:11:30 lr: 0.000120 loss: 3.0389 (2.9716) grad_norm: 2.5953 (2.5335) time: 0.4989 [2021-03-26 22:38:05 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 60/1251] eta: 0:11:08 lr: 0.000120 loss: 2.9179 (2.9295) grad_norm: 2.5115 (2.5728) time: 0.4971 [2021-03-26 22:38:10 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 70/1251] eta: 0:10:50 lr: 0.000120 loss: 2.9179 (2.9373) grad_norm: 2.5115 (2.5826) time: 0.4911 [2021-03-26 22:38:15 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 80/1251] eta: 0:10:37 lr: 0.000120 loss: 2.9461 (2.8995) grad_norm: 2.3803 (2.5567) time: 0.4948 [2021-03-26 22:38:20 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 90/1251] eta: 0:10:26 lr: 0.000120 loss: 2.8865 (2.9048) grad_norm: 2.3113 (2.5368) time: 0.4997 [2021-03-26 22:38:25 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 100/1251] eta: 0:10:17 lr: 0.000120 loss: 2.8865 (2.8862) grad_norm: 2.3609 (2.5164) time: 0.5014 [2021-03-26 22:38:30 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 110/1251] eta: 0:10:08 lr: 0.000120 loss: 2.4818 (2.8786) grad_norm: 2.3415 (2.5064) time: 0.5049 [2021-03-26 22:38:35 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 120/1251] eta: 0:10:00 lr: 0.000120 loss: 3.0399 (2.8885) grad_norm: 2.3288 (2.5080) time: 0.5064 [2021-03-26 22:38:40 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 130/1251] eta: 0:09:52 lr: 0.000120 loss: 3.0368 (2.8869) grad_norm: 2.4149 (2.5072) time: 0.5029 [2021-03-26 22:38:45 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 140/1251] eta: 0:09:44 lr: 0.000120 loss: 2.9553 (2.8912) grad_norm: 2.3954 (2.4931) time: 0.4979 [2021-03-26 22:38:50 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 150/1251] eta: 0:09:37 lr: 0.000120 loss: 2.8367 (2.8868) grad_norm: 2.2665 (2.4829) time: 0.4983 [2021-03-26 22:38:55 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 160/1251] eta: 0:09:31 lr: 0.000120 loss: 2.8367 (2.8819) grad_norm: 2.2666 (2.4726) time: 0.5028 [2021-03-26 22:39:00 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 170/1251] eta: 0:09:24 lr: 0.000120 loss: 3.0494 (2.8934) grad_norm: 2.2766 (2.4714) time: 0.5028 [2021-03-26 22:39:05 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 180/1251] eta: 0:09:18 lr: 0.000120 loss: 3.0494 (2.8966) grad_norm: 2.3157 (2.4697) time: 0.5056 [2021-03-26 22:39:10 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 190/1251] eta: 0:09:13 lr: 0.000120 loss: 3.1488 (2.9022) grad_norm: 2.4294 (2.4752) time: 0.5148 [2021-03-26 22:39:15 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 200/1251] eta: 0:09:07 lr: 0.000120 loss: 3.1267 (2.9101) grad_norm: 2.4462 (2.4753) time: 0.5152 [2021-03-26 22:39:20 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 210/1251] eta: 0:09:01 lr: 0.000120 loss: 3.0178 (2.9108) grad_norm: 2.4419 (2.4789) time: 0.5036 [2021-03-26 22:39:25 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 220/1251] eta: 0:08:54 lr: 0.000120 loss: 3.0029 (2.9087) grad_norm: 2.3943 (2.4739) time: 0.4982 [2021-03-26 22:39:30 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 230/1251] eta: 0:08:48 lr: 0.000120 loss: 2.8022 (2.8958) grad_norm: 2.1938 (2.4615) time: 0.4962 [2021-03-26 22:39:35 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 240/1251] eta: 0:08:42 lr: 0.000120 loss: 2.8022 (2.8986) grad_norm: 2.1763 (2.4522) time: 0.4975 [2021-03-26 22:39:40 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 250/1251] eta: 0:08:37 lr: 0.000120 loss: 3.0533 (2.8948) grad_norm: 2.2542 (2.4568) time: 0.5026 [2021-03-26 22:39:45 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 260/1251] eta: 0:08:31 lr: 0.000120 loss: 3.0773 (2.9047) grad_norm: 2.3959 (2.4602) time: 0.5050 [2021-03-26 22:39:50 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 270/1251] eta: 0:08:26 lr: 0.000120 loss: 3.2705 (2.9129) grad_norm: 2.4727 (2.4690) time: 0.5080 [2021-03-26 22:39:55 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 280/1251] eta: 0:08:20 lr: 0.000120 loss: 3.0531 (2.9138) grad_norm: 2.5188 (2.4784) time: 0.5038 [2021-03-26 22:40:00 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 290/1251] eta: 0:08:14 lr: 0.000120 loss: 3.0577 (2.9133) grad_norm: 2.4348 (2.4750) time: 0.4983 [2021-03-26 22:40:05 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 300/1251] eta: 0:08:08 lr: 0.000120 loss: 3.0977 (2.9181) grad_norm: 2.4939 (2.4852) time: 0.4961 [2021-03-26 22:40:10 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 310/1251] eta: 0:08:03 lr: 0.000120 loss: 3.0849 (2.9162) grad_norm: 2.4939 (2.4814) time: 0.4968 [2021-03-26 22:40:15 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 320/1251] eta: 0:07:58 lr: 0.000119 loss: 3.0574 (2.9166) grad_norm: 2.3641 (2.4854) time: 0.5122 [2021-03-26 22:40:20 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 330/1251] eta: 0:07:53 lr: 0.000119 loss: 2.9967 (2.9160) grad_norm: 2.5503 (2.4925) time: 0.5154 [2021-03-26 22:40:25 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 340/1251] eta: 0:07:47 lr: 0.000119 loss: 2.9498 (2.9144) grad_norm: 2.4616 (2.4902) time: 0.5005 [2021-03-26 22:40:30 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 350/1251] eta: 0:07:41 lr: 0.000119 loss: 2.8315 (2.9041) grad_norm: 2.4616 (2.4923) time: 0.4977 [2021-03-26 22:40:35 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 360/1251] eta: 0:07:36 lr: 0.000119 loss: 2.7898 (2.9075) grad_norm: 2.4579 (2.4937) time: 0.4984 [2021-03-26 22:40:40 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 370/1251] eta: 0:07:31 lr: 0.000119 loss: 3.0765 (2.9088) grad_norm: 2.4137 (2.4904) time: 0.5002 [2021-03-26 22:40:46 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 380/1251] eta: 0:07:25 lr: 0.000119 loss: 3.0746 (2.9064) grad_norm: 2.3475 (2.4909) time: 0.5049 [2021-03-26 22:40:51 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 390/1251] eta: 0:07:20 lr: 0.000119 loss: 2.8137 (2.9049) grad_norm: 2.3813 (2.4881) time: 0.5037 [2021-03-26 22:40:55 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 400/1251] eta: 0:07:14 lr: 0.000119 loss: 2.8133 (2.9020) grad_norm: 2.3926 (2.4842) time: 0.4958 [2021-03-26 22:41:00 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 410/1251] eta: 0:07:09 lr: 0.000119 loss: 2.6824 (2.8978) grad_norm: 2.3035 (2.4802) time: 0.4936 [2021-03-26 22:41:05 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 420/1251] eta: 0:07:04 lr: 0.000119 loss: 2.7727 (2.8973) grad_norm: 2.2864 (2.4749) time: 0.4981 [2021-03-26 22:41:10 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 430/1251] eta: 0:06:58 lr: 0.000119 loss: 2.9790 (2.8971) grad_norm: 2.2680 (2.4721) time: 0.4993 [2021-03-26 22:41:15 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 440/1251] eta: 0:06:53 lr: 0.000119 loss: 3.1041 (2.8983) grad_norm: 2.3899 (2.4750) time: 0.5027 [2021-03-26 22:41:21 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 450/1251] eta: 0:06:48 lr: 0.000119 loss: 3.0475 (2.8966) grad_norm: 2.4705 (2.4754) time: 0.5058 [2021-03-26 22:41:26 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 460/1251] eta: 0:06:43 lr: 0.000119 loss: 2.9060 (2.8944) grad_norm: 2.3117 (2.4784) time: 0.5066 [2021-03-26 22:41:31 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 470/1251] eta: 0:06:38 lr: 0.000119 loss: 2.9549 (2.8945) grad_norm: 2.3829 (2.4888) time: 0.5074 [2021-03-26 22:41:36 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 480/1251] eta: 0:06:32 lr: 0.000119 loss: 2.9372 (2.8900) grad_norm: 2.4753 (2.4892) time: 0.5011 [2021-03-26 22:41:41 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 490/1251] eta: 0:06:27 lr: 0.000119 loss: 2.7615 (2.8891) grad_norm: 2.3994 (2.4890) time: 0.4981 [2021-03-26 22:41:46 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 500/1251] eta: 0:06:22 lr: 0.000119 loss: 2.9422 (2.8877) grad_norm: 2.4013 (2.4887) time: 0.4976 [2021-03-26 22:41:51 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 510/1251] eta: 0:06:17 lr: 0.000119 loss: 2.9137 (2.8856) grad_norm: 2.4532 (2.4959) time: 0.4975 [2021-03-26 22:41:56 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 520/1251] eta: 0:06:11 lr: 0.000119 loss: 2.9137 (2.8842) grad_norm: 2.4924 (2.4960) time: 0.5000 [2021-03-26 22:42:01 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 530/1251] eta: 0:06:06 lr: 0.000119 loss: 3.1337 (2.8893) grad_norm: 2.5105 (2.4972) time: 0.5007 [2021-03-26 22:42:06 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 540/1251] eta: 0:06:01 lr: 0.000119 loss: 3.1564 (2.8914) grad_norm: 2.3593 (2.4943) time: 0.5120 [2021-03-26 22:42:11 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 550/1251] eta: 0:05:56 lr: 0.000119 loss: 3.0881 (2.8957) grad_norm: 2.3293 (2.4928) time: 0.5159 [2021-03-26 22:42:16 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 560/1251] eta: 0:05:51 lr: 0.000119 loss: 3.0161 (2.8927) grad_norm: 2.3473 (2.4923) time: 0.5075 [2021-03-26 22:42:21 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 570/1251] eta: 0:05:46 lr: 0.000119 loss: 3.0405 (2.8937) grad_norm: 2.3981 (2.4982) time: 0.5054 [2021-03-26 22:42:26 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 580/1251] eta: 0:05:41 lr: 0.000119 loss: 2.9877 (2.8925) grad_norm: 2.5575 (2.4991) time: 0.5016 [2021-03-26 22:42:31 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 590/1251] eta: 0:05:36 lr: 0.000119 loss: 2.9877 (2.8936) grad_norm: 2.4344 (2.4989) time: 0.4990 [2021-03-26 22:42:36 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 600/1251] eta: 0:05:30 lr: 0.000119 loss: 3.2589 (2.9012) grad_norm: 2.4432 (2.4965) time: 0.5022 [2021-03-26 22:42:41 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 610/1251] eta: 0:05:25 lr: 0.000119 loss: 3.1816 (2.8993) grad_norm: 2.4432 (2.4952) time: 0.5081 [2021-03-26 22:42:46 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 620/1251] eta: 0:05:20 lr: 0.000119 loss: 3.0175 (2.9011) grad_norm: 2.2496 (2.4948) time: 0.5021 [2021-03-26 22:42:51 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 630/1251] eta: 0:05:15 lr: 0.000119 loss: 3.0175 (2.9013) grad_norm: 2.2035 (2.4923) time: 0.4979 [2021-03-26 22:42:56 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 640/1251] eta: 0:05:10 lr: 0.000119 loss: 3.0844 (2.9028) grad_norm: 2.2448 (2.4889) time: 0.4999 [2021-03-26 22:43:01 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 650/1251] eta: 0:05:05 lr: 0.000119 loss: 3.0159 (2.9014) grad_norm: 2.3089 (2.4899) time: 0.4934 [2021-03-26 22:43:06 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 660/1251] eta: 0:04:59 lr: 0.000119 loss: 2.8191 (2.9024) grad_norm: 2.4314 (2.5021) time: 0.4960 [2021-03-26 22:43:11 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 670/1251] eta: 0:04:54 lr: 0.000119 loss: 2.8186 (2.8996) grad_norm: 2.4655 (2.5025) time: 0.5038 [2021-03-26 22:43:16 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 680/1251] eta: 0:04:49 lr: 0.000119 loss: 2.7557 (2.8980) grad_norm: 2.5045 (2.5035) time: 0.5051 [2021-03-26 22:43:21 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 690/1251] eta: 0:04:44 lr: 0.000119 loss: 2.7557 (2.8961) grad_norm: 2.4632 (2.5017) time: 0.5042 [2021-03-26 22:43:26 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 700/1251] eta: 0:04:39 lr: 0.000118 loss: 3.0236 (2.8980) grad_norm: 2.2904 (2.5007) time: 0.5051 [2021-03-26 22:43:31 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 710/1251] eta: 0:04:34 lr: 0.000118 loss: 3.0373 (2.8977) grad_norm: 2.3687 (2.4987) time: 0.5021 [2021-03-26 22:43:36 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 720/1251] eta: 0:04:29 lr: 0.000118 loss: 2.8549 (2.8970) grad_norm: 2.3676 (2.4971) time: 0.4998 [2021-03-26 22:43:41 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 730/1251] eta: 0:04:24 lr: 0.000118 loss: 2.8549 (2.8931) grad_norm: 2.3654 (2.4953) time: 0.5073 [2021-03-26 22:43:47 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 740/1251] eta: 0:04:19 lr: 0.000118 loss: 2.7187 (2.8926) grad_norm: 2.3654 (2.4939) time: 0.5179 [2021-03-26 22:43:52 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 750/1251] eta: 0:04:14 lr: 0.000118 loss: 2.9243 (2.8913) grad_norm: 2.4037 (2.4943) time: 0.5232 [2021-03-26 22:43:57 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 760/1251] eta: 0:04:09 lr: 0.000118 loss: 2.9730 (2.8916) grad_norm: 2.3813 (2.4933) time: 0.5144 [2021-03-26 22:44:02 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 770/1251] eta: 0:04:04 lr: 0.000118 loss: 3.1287 (2.8929) grad_norm: 2.3871 (2.4930) time: 0.5019 [2021-03-26 22:44:07 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 780/1251] eta: 0:03:59 lr: 0.000118 loss: 3.0157 (2.8924) grad_norm: 2.4716 (2.4979) time: 0.4977 [2021-03-26 22:44:12 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 790/1251] eta: 0:03:53 lr: 0.000118 loss: 3.0157 (2.8938) grad_norm: 2.4353 (2.4964) time: 0.4965 [2021-03-26 22:44:17 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 800/1251] eta: 0:03:48 lr: 0.000118 loss: 3.0352 (2.8942) grad_norm: 2.4219 (2.4974) time: 0.4954 [2021-03-26 22:44:22 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 810/1251] eta: 0:03:43 lr: 0.000118 loss: 3.0319 (2.8938) grad_norm: 2.4174 (2.4963) time: 0.4980 [2021-03-26 22:44:27 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 820/1251] eta: 0:03:38 lr: 0.000118 loss: 3.0995 (2.8946) grad_norm: 2.4840 (2.4996) time: 0.4968 [2021-03-26 22:44:32 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 830/1251] eta: 0:03:33 lr: 0.000118 loss: 3.1484 (2.8944) grad_norm: 2.5995 (2.5001) time: 0.4965 [2021-03-26 22:44:37 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 840/1251] eta: 0:03:28 lr: 0.000118 loss: 3.0028 (2.8951) grad_norm: 2.4959 (2.5025) time: 0.5020 [2021-03-26 22:44:42 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 850/1251] eta: 0:03:23 lr: 0.000118 loss: 3.0963 (2.8978) grad_norm: 2.4872 (2.5017) time: 0.5022 [2021-03-26 22:44:47 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 860/1251] eta: 0:03:18 lr: 0.000118 loss: 3.0963 (2.8991) grad_norm: 2.4240 (2.5009) time: 0.5033 [2021-03-26 22:44:52 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 870/1251] eta: 0:03:13 lr: 0.000118 loss: 3.0308 (2.8997) grad_norm: 2.4300 (2.5011) time: 0.5070 [2021-03-26 22:44:57 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 880/1251] eta: 0:03:07 lr: 0.000118 loss: 2.9700 (2.8979) grad_norm: 2.4158 (2.5008) time: 0.5046 [2021-03-26 22:45:02 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 890/1251] eta: 0:03:02 lr: 0.000118 loss: 2.8539 (2.8962) grad_norm: 2.4074 (2.5005) time: 0.5042 [2021-03-26 22:45:07 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 900/1251] eta: 0:02:57 lr: 0.000118 loss: 3.0875 (2.8981) grad_norm: 2.4567 (2.4992) time: 0.5024 [2021-03-26 22:45:12 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 910/1251] eta: 0:02:52 lr: 0.000118 loss: 2.9513 (2.8956) grad_norm: 2.2912 (2.4970) time: 0.4995 [2021-03-26 22:45:17 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 920/1251] eta: 0:02:47 lr: 0.000118 loss: 2.8542 (2.8953) grad_norm: 2.3466 (2.5056) time: 0.5109 [2021-03-26 22:45:22 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 930/1251] eta: 0:02:42 lr: 0.000118 loss: 2.8542 (2.8939) grad_norm: 2.4914 (2.5054) time: 0.5094 [2021-03-26 22:45:27 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 940/1251] eta: 0:02:37 lr: 0.000118 loss: 2.7981 (2.8945) grad_norm: 2.5255 (2.5056) time: 0.5117 [2021-03-26 22:45:32 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 950/1251] eta: 0:02:32 lr: 0.000118 loss: 2.9390 (2.8935) grad_norm: 2.3631 (2.5040) time: 0.5142 [2021-03-26 22:45:37 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 960/1251] eta: 0:02:27 lr: 0.000118 loss: 2.9001 (2.8929) grad_norm: 2.3968 (2.5047) time: 0.4996 [2021-03-26 22:45:42 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 970/1251] eta: 0:02:22 lr: 0.000118 loss: 3.0544 (2.8954) grad_norm: 2.5775 (2.5057) time: 0.4969 [2021-03-26 22:45:47 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 980/1251] eta: 0:02:17 lr: 0.000118 loss: 3.1370 (2.8971) grad_norm: 2.4148 (2.5034) time: 0.4986 [2021-03-26 22:45:52 swin_small_patch4_window7_224] INFO: Epoch: [235] [ 990/1251] eta: 0:02:12 lr: 0.000118 loss: 3.0931 (2.8993) grad_norm: 2.3602 (2.5027) time: 0.5012 [2021-03-26 22:45:57 swin_small_patch4_window7_224] INFO: Epoch: [235] [1000/1251] eta: 0:02:07 lr: 0.000118 loss: 2.8882 (2.8992) grad_norm: 2.4890 (2.5052) time: 0.5001 [2021-03-26 22:46:02 swin_small_patch4_window7_224] INFO: Epoch: [235] [1010/1251] eta: 0:02:01 lr: 0.000118 loss: 2.9578 (2.9000) grad_norm: 2.5645 (2.5063) time: 0.4969 [2021-03-26 22:46:07 swin_small_patch4_window7_224] INFO: Epoch: [235] [1020/1251] eta: 0:01:56 lr: 0.000118 loss: 3.0133 (2.8994) grad_norm: 2.3742 (2.5036) time: 0.5023 [2021-03-26 22:46:12 swin_small_patch4_window7_224] INFO: Epoch: [235] [1030/1251] eta: 0:01:51 lr: 0.000118 loss: 2.8910 (2.9011) grad_norm: 2.2965 (2.5024) time: 0.5013 [2021-03-26 22:46:17 swin_small_patch4_window7_224] INFO: Epoch: [235] [1040/1251] eta: 0:01:46 lr: 0.000118 loss: 3.0293 (2.9028) grad_norm: 2.4192 (2.5023) time: 0.4940 [2021-03-26 22:46:22 swin_small_patch4_window7_224] INFO: Epoch: [235] [1050/1251] eta: 0:01:41 lr: 0.000118 loss: 3.0754 (2.9041) grad_norm: 2.4754 (2.5048) time: 0.4958 [2021-03-26 22:46:27 swin_small_patch4_window7_224] INFO: Epoch: [235] [1060/1251] eta: 0:01:36 lr: 0.000118 loss: 3.0613 (2.9046) grad_norm: 2.2646 (2.5028) time: 0.5071 [2021-03-26 22:46:32 swin_small_patch4_window7_224] INFO: Epoch: [235] [1070/1251] eta: 0:01:31 lr: 0.000118 loss: 2.8599 (2.9035) grad_norm: 2.3414 (2.5045) time: 0.5084 [2021-03-26 22:46:37 swin_small_patch4_window7_224] INFO: Epoch: [235] [1080/1251] eta: 0:01:26 lr: 0.000118 loss: 2.9139 (2.9041) grad_norm: 2.5628 (2.5048) time: 0.4992 [2021-03-26 22:46:42 swin_small_patch4_window7_224] INFO: Epoch: [235] [1090/1251] eta: 0:01:21 lr: 0.000117 loss: 2.9401 (2.9027) grad_norm: 2.5379 (2.5044) time: 0.4985 [2021-03-26 22:46:47 swin_small_patch4_window7_224] INFO: Epoch: [235] [1100/1251] eta: 0:01:16 lr: 0.000117 loss: 2.8289 (2.9024) grad_norm: 2.4033 (2.5034) time: 0.4961 [2021-03-26 22:46:52 swin_small_patch4_window7_224] INFO: Epoch: [235] [1110/1251] eta: 0:01:11 lr: 0.000117 loss: 2.9331 (2.9027) grad_norm: 2.3907 (2.5034) time: 0.4980 [2021-03-26 22:46:57 swin_small_patch4_window7_224] INFO: Epoch: [235] [1120/1251] eta: 0:01:06 lr: 0.000117 loss: 2.9516 (2.9031) grad_norm: 2.3456 (2.5024) time: 0.5004 [2021-03-26 22:47:02 swin_small_patch4_window7_224] INFO: Epoch: [235] [1130/1251] eta: 0:01:01 lr: 0.000117 loss: 3.0360 (2.9027) grad_norm: 2.3428 (2.5009) time: 0.5017 [2021-03-26 22:47:08 swin_small_patch4_window7_224] INFO: Epoch: [235] [1140/1251] eta: 0:00:56 lr: 0.000117 loss: 3.0360 (2.9028) grad_norm: 2.4013 (2.5010) time: 0.5071 [2021-03-26 22:47:13 swin_small_patch4_window7_224] INFO: Epoch: [235] [1150/1251] eta: 0:00:51 lr: 0.000117 loss: 2.9325 (2.9010) grad_norm: 2.2931 (2.4986) time: 0.5043 [2021-03-26 22:47:18 swin_small_patch4_window7_224] INFO: Epoch: [235] [1160/1251] eta: 0:00:46 lr: 0.000117 loss: 2.9892 (2.9007) grad_norm: 2.2303 (2.4966) time: 0.5032 [2021-03-26 22:47:23 swin_small_patch4_window7_224] INFO: Epoch: [235] [1170/1251] eta: 0:00:40 lr: 0.000117 loss: 2.9921 (2.9014) grad_norm: 2.3048 (2.4964) time: 0.4998 [2021-03-26 22:47:28 swin_small_patch4_window7_224] INFO: Epoch: [235] [1180/1251] eta: 0:00:35 lr: 0.000117 loss: 2.9760 (2.9011) grad_norm: 2.4964 (2.4975) time: 0.4978 [2021-03-26 22:47:33 swin_small_patch4_window7_224] INFO: Epoch: [235] [1190/1251] eta: 0:00:30 lr: 0.000117 loss: 2.9708 (2.9014) grad_norm: 2.5963 (2.5045) time: 0.5006 [2021-03-26 22:47:38 swin_small_patch4_window7_224] INFO: Epoch: [235] [1200/1251] eta: 0:00:25 lr: 0.000117 loss: 2.8520 (2.9003) grad_norm: 2.5633 (2.5040) time: 0.4994 [2021-03-26 22:47:43 swin_small_patch4_window7_224] INFO: Epoch: [235] [1210/1251] eta: 0:00:20 lr: 0.000117 loss: 2.4914 (2.8964) grad_norm: 2.3442 (2.5029) time: 0.5099 [2021-03-26 22:47:48 swin_small_patch4_window7_224] INFO: Epoch: [235] [1220/1251] eta: 0:00:15 lr: 0.000117 loss: 2.6027 (2.8955) grad_norm: 2.3442 (2.5032) time: 0.5154 [2021-03-26 22:47:53 swin_small_patch4_window7_224] INFO: Epoch: [235] [1230/1251] eta: 0:00:10 lr: 0.000117 loss: 2.8249 (2.8934) grad_norm: 2.4214 (2.5031) time: 0.5071 [2021-03-26 22:47:58 swin_small_patch4_window7_224] INFO: Epoch: [235] [1240/1251] eta: 0:00:05 lr: 0.000117 loss: 2.8617 (2.8925) grad_norm: 2.4159 (2.5026) time: 0.5003 [2021-03-26 22:48:03 swin_small_patch4_window7_224] INFO: Epoch: [235] [1250/1251] eta: 0:00:00 lr: 0.000117 loss: 2.8745 (2.8929) grad_norm: 2.3525 (2.5051) time: 0.4974 [2021-03-26 22:48:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.6658 (0.6658) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-26 22:48:49 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7581 (0.7409) acc1: 81.2500 (81.9602) acc5: 95.3125 (96.3068) [2021-03-26 22:48:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7360 (0.7218) acc1: 81.2500 (82.1429) acc5: 95.3125 (96.5030) [2021-03-26 22:48:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7860 (0.7653) acc1: 81.2500 (81.2500) acc5: 95.3125 (96.1694) [2021-03-26 22:48:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.8401 (0.7838) acc1: 79.6875 (80.9832) acc5: 95.3125 (95.9604) [2021-03-26 22:48:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8232 (0.7764) acc1: 79.6875 (81.1520) acc5: 96.8750 (96.1280) [2021-03-26 22:49:03 swin_small_patch4_window7_224] INFO: * Acc@1 81.938 Acc@5 95.874 loss 0.763 [2021-03-26 22:49:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-26 22:49:03 swin_small_patch4_window7_224] INFO: Max accuracy: 81.94% [2021-03-26 22:49:07 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 0/1251] eta: 1:20:32 lr: 0.000117 loss: 3.7248 (3.7248) grad_norm: 2.2895 (2.2895) time: 3.8632 [2021-03-26 22:49:13 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 10/1251] eta: 0:17:28 lr: 0.000117 loss: 3.1472 (3.1338) grad_norm: 2.2887 (2.3231) time: 0.8447 [2021-03-26 22:49:18 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 20/1251] eta: 0:14:02 lr: 0.000117 loss: 2.9417 (2.9601) grad_norm: 2.2887 (2.3348) time: 0.5256 [2021-03-26 22:49:23 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 30/1251] eta: 0:12:46 lr: 0.000117 loss: 2.9092 (2.9589) grad_norm: 2.3110 (2.3708) time: 0.5083 [2021-03-26 22:49:28 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 40/1251] eta: 0:12:02 lr: 0.000117 loss: 2.9150 (2.9654) grad_norm: 2.3105 (2.3924) time: 0.5049 [2021-03-26 22:49:33 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 50/1251] eta: 0:11:33 lr: 0.000117 loss: 2.9167 (2.9453) grad_norm: 2.4474 (2.4127) time: 0.5005 [2021-03-26 22:49:38 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 60/1251] eta: 0:11:12 lr: 0.000117 loss: 2.9279 (2.9540) grad_norm: 2.4573 (2.4261) time: 0.4985 [2021-03-26 22:49:43 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 70/1251] eta: 0:10:56 lr: 0.000117 loss: 2.9881 (2.9365) grad_norm: 2.4722 (2.4340) time: 0.4999 [2021-03-26 22:49:48 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 80/1251] eta: 0:10:42 lr: 0.000117 loss: 2.9881 (2.9430) grad_norm: 2.4931 (2.4375) time: 0.4994 [2021-03-26 22:49:53 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 90/1251] eta: 0:10:31 lr: 0.000117 loss: 2.8779 (2.9350) grad_norm: 2.4989 (2.4612) time: 0.5006 [2021-03-26 22:49:58 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 100/1251] eta: 0:10:21 lr: 0.000117 loss: 2.9356 (2.9252) grad_norm: 2.4967 (2.4652) time: 0.5063 [2021-03-26 22:50:03 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 110/1251] eta: 0:10:12 lr: 0.000117 loss: 2.6782 (2.9055) grad_norm: 2.4967 (2.4808) time: 0.5058 [2021-03-26 22:50:08 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 120/1251] eta: 0:10:04 lr: 0.000117 loss: 2.8977 (2.9127) grad_norm: 2.3760 (2.4695) time: 0.5078 [2021-03-26 22:50:13 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 130/1251] eta: 0:09:56 lr: 0.000117 loss: 2.9583 (2.9073) grad_norm: 2.4325 (2.4824) time: 0.5078 [2021-03-26 22:50:18 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 140/1251] eta: 0:09:49 lr: 0.000117 loss: 2.9320 (2.9082) grad_norm: 2.4862 (2.4839) time: 0.5030 [2021-03-26 22:50:23 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 150/1251] eta: 0:09:41 lr: 0.000117 loss: 2.7762 (2.9046) grad_norm: 2.3401 (2.4773) time: 0.4987 [2021-03-26 22:50:28 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 160/1251] eta: 0:09:34 lr: 0.000117 loss: 2.7683 (2.8931) grad_norm: 2.3076 (2.4697) time: 0.5012 [2021-03-26 22:50:33 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 170/1251] eta: 0:09:27 lr: 0.000117 loss: 2.8715 (2.8910) grad_norm: 2.4763 (2.4741) time: 0.5058 [2021-03-26 22:50:38 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 180/1251] eta: 0:09:22 lr: 0.000117 loss: 3.0306 (2.8889) grad_norm: 2.5548 (2.4742) time: 0.5097 [2021-03-26 22:50:43 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 190/1251] eta: 0:09:15 lr: 0.000117 loss: 2.9443 (2.8902) grad_norm: 2.5899 (2.4869) time: 0.5081 [2021-03-26 22:50:48 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 200/1251] eta: 0:09:08 lr: 0.000117 loss: 2.9542 (2.8955) grad_norm: 2.5470 (2.4889) time: 0.4993 [2021-03-26 22:50:54 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 210/1251] eta: 0:09:02 lr: 0.000117 loss: 3.1304 (2.9066) grad_norm: 2.4003 (2.4821) time: 0.5012 [2021-03-26 22:50:58 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 220/1251] eta: 0:08:56 lr: 0.000117 loss: 3.0975 (2.8966) grad_norm: 2.4003 (2.4979) time: 0.5004 [2021-03-26 22:51:03 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 230/1251] eta: 0:08:50 lr: 0.000116 loss: 2.8944 (2.8980) grad_norm: 2.4727 (2.5016) time: 0.4998 [2021-03-26 22:51:09 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 240/1251] eta: 0:08:44 lr: 0.000116 loss: 2.8471 (2.8908) grad_norm: 2.4708 (2.5075) time: 0.5031 [2021-03-26 22:51:14 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 250/1251] eta: 0:08:38 lr: 0.000116 loss: 2.6930 (2.8738) grad_norm: 2.4708 (2.5034) time: 0.5024 [2021-03-26 22:51:19 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 260/1251] eta: 0:08:32 lr: 0.000116 loss: 2.5747 (2.8647) grad_norm: 2.3439 (2.4993) time: 0.5008 [2021-03-26 22:51:24 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 270/1251] eta: 0:08:27 lr: 0.000116 loss: 2.7575 (2.8672) grad_norm: 2.3627 (2.4975) time: 0.4997 [2021-03-26 22:51:29 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 280/1251] eta: 0:08:21 lr: 0.000116 loss: 2.9817 (2.8633) grad_norm: 2.3627 (2.4925) time: 0.4999 [2021-03-26 22:51:34 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 290/1251] eta: 0:08:15 lr: 0.000116 loss: 3.0453 (2.8730) grad_norm: 2.3434 (2.4912) time: 0.5016 [2021-03-26 22:51:39 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 300/1251] eta: 0:08:10 lr: 0.000116 loss: 3.1083 (2.8819) grad_norm: 2.5110 (2.4932) time: 0.5028 [2021-03-26 22:51:44 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 310/1251] eta: 0:08:04 lr: 0.000116 loss: 3.0487 (2.8856) grad_norm: 2.5260 (2.4960) time: 0.5067 [2021-03-26 22:51:49 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 320/1251] eta: 0:07:59 lr: 0.000116 loss: 2.9597 (2.8895) grad_norm: 2.3521 (2.4892) time: 0.5136 [2021-03-26 22:51:54 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 330/1251] eta: 0:07:54 lr: 0.000116 loss: 2.9916 (2.8894) grad_norm: 2.3322 (2.4887) time: 0.5093 [2021-03-26 22:51:59 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 340/1251] eta: 0:07:48 lr: 0.000116 loss: 2.9550 (2.8871) grad_norm: 2.3322 (2.4879) time: 0.5070 [2021-03-26 22:52:04 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 350/1251] eta: 0:07:43 lr: 0.000116 loss: 2.9469 (2.8877) grad_norm: 2.2267 (2.4811) time: 0.5077 [2021-03-26 22:52:09 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 360/1251] eta: 0:07:38 lr: 0.000116 loss: 3.0016 (2.8865) grad_norm: 2.2191 (2.4753) time: 0.5023 [2021-03-26 22:52:14 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 370/1251] eta: 0:07:32 lr: 0.000116 loss: 3.0140 (2.8898) grad_norm: 2.3593 (2.4766) time: 0.4999 [2021-03-26 22:52:19 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 380/1251] eta: 0:07:27 lr: 0.000116 loss: 2.7093 (2.8848) grad_norm: 2.6387 (2.4840) time: 0.5029 [2021-03-26 22:52:24 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 390/1251] eta: 0:07:21 lr: 0.000116 loss: 2.9008 (2.8883) grad_norm: 2.6429 (2.4853) time: 0.5018 [2021-03-26 22:52:29 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 400/1251] eta: 0:07:16 lr: 0.000116 loss: 2.8570 (2.8842) grad_norm: 2.4287 (2.4852) time: 0.4951 [2021-03-26 22:52:34 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 410/1251] eta: 0:07:10 lr: 0.000116 loss: 2.8202 (2.8845) grad_norm: 2.4287 (2.4856) time: 0.4961 [2021-03-26 22:52:39 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 420/1251] eta: 0:07:05 lr: 0.000116 loss: 2.9888 (2.8880) grad_norm: 2.4596 (2.4847) time: 0.5023 [2021-03-26 22:52:44 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 430/1251] eta: 0:07:00 lr: 0.000116 loss: 2.9251 (2.8841) grad_norm: 2.4280 (2.4870) time: 0.5051 [2021-03-26 22:52:49 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 440/1251] eta: 0:06:54 lr: 0.000116 loss: 2.9718 (2.8870) grad_norm: 2.3991 (2.4921) time: 0.5031 [2021-03-26 22:52:54 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 450/1251] eta: 0:06:49 lr: 0.000116 loss: 3.0046 (2.8901) grad_norm: 2.3651 (2.4918) time: 0.4990 [2021-03-26 22:52:59 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 460/1251] eta: 0:06:44 lr: 0.000116 loss: 2.8131 (2.8886) grad_norm: 2.3950 (2.4894) time: 0.4946 [2021-03-26 22:53:04 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 470/1251] eta: 0:06:38 lr: 0.000116 loss: 2.8095 (2.8873) grad_norm: 2.3837 (2.4873) time: 0.4925 [2021-03-26 22:53:09 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 480/1251] eta: 0:06:33 lr: 0.000116 loss: 2.9204 (2.8880) grad_norm: 2.3454 (2.4858) time: 0.4926 [2021-03-26 22:53:14 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 490/1251] eta: 0:06:28 lr: 0.000116 loss: 3.0340 (2.8883) grad_norm: 2.3303 (2.4842) time: 0.4990 [2021-03-26 22:53:19 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 500/1251] eta: 0:06:22 lr: 0.000116 loss: 2.9438 (2.8853) grad_norm: 2.3407 (2.4819) time: 0.5043 [2021-03-26 22:53:24 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 510/1251] eta: 0:06:17 lr: 0.000116 loss: 2.7825 (2.8823) grad_norm: 2.4085 (2.4827) time: 0.5044 [2021-03-26 22:53:29 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 520/1251] eta: 0:06:12 lr: 0.000116 loss: 2.9071 (2.8824) grad_norm: 2.5162 (2.4846) time: 0.5129 [2021-03-26 22:53:34 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 530/1251] eta: 0:06:07 lr: 0.000116 loss: 3.0483 (2.8847) grad_norm: 2.4571 (2.4830) time: 0.5143 [2021-03-26 22:53:39 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 540/1251] eta: 0:06:02 lr: 0.000116 loss: 3.1724 (2.8877) grad_norm: 2.5096 (2.4908) time: 0.5065 [2021-03-26 22:53:45 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 550/1251] eta: 0:05:57 lr: 0.000116 loss: 2.9818 (2.8873) grad_norm: 2.3208 (2.4870) time: 0.5173 [2021-03-26 22:53:50 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 560/1251] eta: 0:05:52 lr: 0.000116 loss: 2.7456 (2.8822) grad_norm: 2.2995 (2.4906) time: 0.5145 [2021-03-26 22:53:55 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 570/1251] eta: 0:05:47 lr: 0.000116 loss: 2.8401 (2.8813) grad_norm: 2.3922 (2.4886) time: 0.4967 [2021-03-26 22:54:00 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 580/1251] eta: 0:05:41 lr: 0.000116 loss: 2.9298 (2.8802) grad_norm: 2.3194 (2.4908) time: 0.4975 [2021-03-26 22:54:05 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 590/1251] eta: 0:05:36 lr: 0.000116 loss: 3.0261 (2.8829) grad_norm: 2.4140 (2.4900) time: 0.5024 [2021-03-26 22:54:10 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 600/1251] eta: 0:05:31 lr: 0.000116 loss: 3.0694 (2.8824) grad_norm: 2.5042 (2.4910) time: 0.5035 [2021-03-26 22:54:15 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 610/1251] eta: 0:05:26 lr: 0.000116 loss: 2.9675 (2.8827) grad_norm: 2.5111 (2.4895) time: 0.5017 [2021-03-26 22:54:20 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 620/1251] eta: 0:05:21 lr: 0.000115 loss: 2.9675 (2.8839) grad_norm: 2.4210 (2.4926) time: 0.5019 [2021-03-26 22:54:25 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 630/1251] eta: 0:05:16 lr: 0.000115 loss: 2.9889 (2.8833) grad_norm: 2.3784 (2.4894) time: 0.5060 [2021-03-26 22:54:30 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 640/1251] eta: 0:05:11 lr: 0.000115 loss: 2.7576 (2.8801) grad_norm: 2.2315 (2.4862) time: 0.5079 [2021-03-26 22:54:35 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 650/1251] eta: 0:05:05 lr: 0.000115 loss: 2.8228 (2.8795) grad_norm: 2.2252 (2.4831) time: 0.5063 [2021-03-26 22:54:40 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 660/1251] eta: 0:05:00 lr: 0.000115 loss: 3.0279 (2.8819) grad_norm: 2.3396 (2.4849) time: 0.5092 [2021-03-26 22:54:45 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 670/1251] eta: 0:04:55 lr: 0.000115 loss: 2.7620 (2.8787) grad_norm: 2.4002 (2.4834) time: 0.5060 [2021-03-26 22:54:50 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 680/1251] eta: 0:04:50 lr: 0.000115 loss: 2.4764 (2.8740) grad_norm: 2.3248 (2.4824) time: 0.5027 [2021-03-26 22:54:55 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 690/1251] eta: 0:04:45 lr: 0.000115 loss: 2.8585 (2.8759) grad_norm: 2.2932 (2.4799) time: 0.5025 [2021-03-26 22:55:00 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 700/1251] eta: 0:04:40 lr: 0.000115 loss: 3.0117 (2.8745) grad_norm: 2.2553 (2.4790) time: 0.5015 [2021-03-26 22:55:05 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 710/1251] eta: 0:04:35 lr: 0.000115 loss: 2.9582 (2.8765) grad_norm: 2.4451 (2.4784) time: 0.5072 [2021-03-26 22:55:10 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 720/1251] eta: 0:04:30 lr: 0.000115 loss: 3.0684 (2.8761) grad_norm: 2.3985 (2.4766) time: 0.5044 [2021-03-26 22:55:15 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 730/1251] eta: 0:04:25 lr: 0.000115 loss: 3.1227 (2.8803) grad_norm: 2.3857 (2.4766) time: 0.5047 [2021-03-26 22:55:21 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 740/1251] eta: 0:04:20 lr: 0.000115 loss: 3.0596 (2.8791) grad_norm: 2.2899 (2.4784) time: 0.5178 [2021-03-26 22:55:26 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 750/1251] eta: 0:04:14 lr: 0.000115 loss: 2.9755 (2.8813) grad_norm: 2.2288 (2.4758) time: 0.5168 [2021-03-26 22:55:31 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 760/1251] eta: 0:04:09 lr: 0.000115 loss: 2.9407 (2.8801) grad_norm: 2.3247 (2.4753) time: 0.5016 [2021-03-26 22:55:36 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 770/1251] eta: 0:04:04 lr: 0.000115 loss: 2.9217 (2.8804) grad_norm: 2.3978 (2.4748) time: 0.4976 [2021-03-26 22:55:41 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 780/1251] eta: 0:03:59 lr: 0.000115 loss: 2.7897 (2.8799) grad_norm: 2.3978 (2.4747) time: 0.5001 [2021-03-26 22:55:46 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 790/1251] eta: 0:03:54 lr: 0.000115 loss: 2.9089 (2.8808) grad_norm: 2.4193 (2.4745) time: 0.5064 [2021-03-26 22:55:51 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 800/1251] eta: 0:03:49 lr: 0.000115 loss: 2.9411 (2.8805) grad_norm: 2.3860 (2.4741) time: 0.5064 [2021-03-26 22:55:56 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 810/1251] eta: 0:03:44 lr: 0.000115 loss: 2.8386 (2.8795) grad_norm: 2.3103 (2.4723) time: 0.5010 [2021-03-26 22:56:01 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 820/1251] eta: 0:03:39 lr: 0.000115 loss: 2.7948 (2.8790) grad_norm: 2.3198 (2.4720) time: 0.4980 [2021-03-26 22:56:06 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 830/1251] eta: 0:03:33 lr: 0.000115 loss: 2.7730 (2.8782) grad_norm: 2.4043 (nan) time: 0.4959 [2021-03-26 22:56:11 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 840/1251] eta: 0:03:28 lr: 0.000115 loss: 2.8129 (2.8773) grad_norm: 2.4632 (nan) time: 0.4986 [2021-03-26 22:56:16 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 850/1251] eta: 0:03:23 lr: 0.000115 loss: 2.8776 (2.8783) grad_norm: 2.4847 (nan) time: 0.5056 [2021-03-26 22:56:21 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 860/1251] eta: 0:03:18 lr: 0.000115 loss: 2.9620 (2.8761) grad_norm: 2.4657 (nan) time: 0.5080 [2021-03-26 22:56:26 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 870/1251] eta: 0:03:13 lr: 0.000115 loss: 2.9543 (2.8765) grad_norm: 2.4165 (nan) time: 0.5102 [2021-03-26 22:56:31 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 880/1251] eta: 0:03:08 lr: 0.000115 loss: 2.9288 (2.8766) grad_norm: 2.4097 (nan) time: 0.5122 [2021-03-26 22:56:36 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 890/1251] eta: 0:03:03 lr: 0.000115 loss: 2.9552 (2.8761) grad_norm: 2.4621 (nan) time: 0.5078 [2021-03-26 22:56:41 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 900/1251] eta: 0:02:58 lr: 0.000115 loss: 2.9238 (2.8759) grad_norm: 2.4540 (nan) time: 0.5046 [2021-03-26 22:56:46 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 910/1251] eta: 0:02:53 lr: 0.000115 loss: 2.8375 (2.8760) grad_norm: 2.4695 (nan) time: 0.4988 [2021-03-26 22:56:51 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 920/1251] eta: 0:02:48 lr: 0.000115 loss: 2.9442 (2.8776) grad_norm: 2.5276 (nan) time: 0.5032 [2021-03-26 22:56:56 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 930/1251] eta: 0:02:43 lr: 0.000115 loss: 2.9951 (2.8772) grad_norm: 2.5683 (nan) time: 0.5080 [2021-03-26 22:57:01 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 940/1251] eta: 0:02:37 lr: 0.000115 loss: 3.0083 (2.8782) grad_norm: 2.5529 (nan) time: 0.5038 [2021-03-26 22:57:06 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 950/1251] eta: 0:02:32 lr: 0.000115 loss: 3.0474 (2.8798) grad_norm: 2.4772 (nan) time: 0.5038 [2021-03-26 22:57:12 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 960/1251] eta: 0:02:27 lr: 0.000115 loss: 3.0782 (2.8802) grad_norm: 2.4772 (nan) time: 0.5059 [2021-03-26 22:57:17 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 970/1251] eta: 0:02:22 lr: 0.000115 loss: 3.0234 (2.8797) grad_norm: 2.4447 (nan) time: 0.5051 [2021-03-26 22:57:22 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 980/1251] eta: 0:02:17 lr: 0.000115 loss: 3.0022 (2.8783) grad_norm: 2.4252 (nan) time: 0.4993 [2021-03-26 22:57:27 swin_small_patch4_window7_224] INFO: Epoch: [236] [ 990/1251] eta: 0:02:12 lr: 0.000115 loss: 2.9402 (2.8782) grad_norm: 2.5744 (nan) time: 0.4970 [2021-03-26 22:57:32 swin_small_patch4_window7_224] INFO: Epoch: [236] [1000/1251] eta: 0:02:07 lr: 0.000115 loss: 2.8815 (2.8779) grad_norm: 2.5506 (nan) time: 0.5004 [2021-03-26 22:57:37 swin_small_patch4_window7_224] INFO: Epoch: [236] [1010/1251] eta: 0:02:02 lr: 0.000114 loss: 2.8815 (2.8792) grad_norm: 2.4000 (nan) time: 0.5009 [2021-03-26 22:57:42 swin_small_patch4_window7_224] INFO: Epoch: [236] [1020/1251] eta: 0:01:57 lr: 0.000114 loss: 3.0727 (2.8805) grad_norm: 2.3814 (nan) time: 0.4994 [2021-03-26 22:57:47 swin_small_patch4_window7_224] INFO: Epoch: [236] [1030/1251] eta: 0:01:52 lr: 0.000114 loss: 2.9351 (2.8792) grad_norm: 2.3776 (nan) time: 0.5014 [2021-03-26 22:57:52 swin_small_patch4_window7_224] INFO: Epoch: [236] [1040/1251] eta: 0:01:47 lr: 0.000114 loss: 2.7736 (2.8794) grad_norm: 2.3263 (nan) time: 0.5011 [2021-03-26 22:57:57 swin_small_patch4_window7_224] INFO: Epoch: [236] [1050/1251] eta: 0:01:41 lr: 0.000114 loss: 2.9899 (2.8794) grad_norm: 2.3873 (nan) time: 0.5022 [2021-03-26 22:58:02 swin_small_patch4_window7_224] INFO: Epoch: [236] [1060/1251] eta: 0:01:36 lr: 0.000114 loss: 2.7929 (2.8770) grad_norm: 2.4170 (nan) time: 0.5131 [2021-03-26 22:58:07 swin_small_patch4_window7_224] INFO: Epoch: [236] [1070/1251] eta: 0:01:31 lr: 0.000114 loss: 2.6359 (2.8762) grad_norm: 2.3579 (nan) time: 0.5165 [2021-03-26 22:58:12 swin_small_patch4_window7_224] INFO: Epoch: [236] [1080/1251] eta: 0:01:26 lr: 0.000114 loss: 3.0005 (2.8770) grad_norm: 2.4085 (nan) time: 0.5055 [2021-03-26 22:58:17 swin_small_patch4_window7_224] INFO: Epoch: [236] [1090/1251] eta: 0:01:21 lr: 0.000114 loss: 3.0880 (2.8785) grad_norm: 2.4085 (nan) time: 0.5029 [2021-03-26 22:58:22 swin_small_patch4_window7_224] INFO: Epoch: [236] [1100/1251] eta: 0:01:16 lr: 0.000114 loss: 3.0726 (2.8790) grad_norm: 2.3812 (nan) time: 0.5083 [2021-03-26 22:58:27 swin_small_patch4_window7_224] INFO: Epoch: [236] [1110/1251] eta: 0:01:11 lr: 0.000114 loss: 2.9403 (2.8785) grad_norm: 2.3547 (nan) time: 0.5051 [2021-03-26 22:58:32 swin_small_patch4_window7_224] INFO: Epoch: [236] [1120/1251] eta: 0:01:06 lr: 0.000114 loss: 3.0507 (2.8793) grad_norm: 2.4388 (nan) time: 0.5006 [2021-03-26 22:58:37 swin_small_patch4_window7_224] INFO: Epoch: [236] [1130/1251] eta: 0:01:01 lr: 0.000114 loss: 3.0212 (2.8782) grad_norm: 2.3795 (nan) time: 0.5029 [2021-03-26 22:58:42 swin_small_patch4_window7_224] INFO: Epoch: [236] [1140/1251] eta: 0:00:56 lr: 0.000114 loss: 2.8812 (2.8791) grad_norm: 2.3548 (nan) time: 0.5063 [2021-03-26 22:58:47 swin_small_patch4_window7_224] INFO: Epoch: [236] [1150/1251] eta: 0:00:51 lr: 0.000114 loss: 3.0862 (2.8804) grad_norm: 2.6297 (nan) time: 0.5053 [2021-03-26 22:58:52 swin_small_patch4_window7_224] INFO: Epoch: [236] [1160/1251] eta: 0:00:46 lr: 0.000114 loss: 3.0743 (2.8804) grad_norm: 2.4856 (nan) time: 0.5069 [2021-03-26 22:58:57 swin_small_patch4_window7_224] INFO: Epoch: [236] [1170/1251] eta: 0:00:41 lr: 0.000114 loss: 2.9439 (2.8801) grad_norm: 2.3076 (nan) time: 0.5077 [2021-03-26 22:59:02 swin_small_patch4_window7_224] INFO: Epoch: [236] [1180/1251] eta: 0:00:35 lr: 0.000114 loss: 2.8940 (2.8793) grad_norm: 2.3881 (nan) time: 0.5007 [2021-03-26 22:59:07 swin_small_patch4_window7_224] INFO: Epoch: [236] [1190/1251] eta: 0:00:30 lr: 0.000114 loss: 2.8940 (2.8794) grad_norm: 2.3911 (nan) time: 0.4955 [2021-03-26 22:59:12 swin_small_patch4_window7_224] INFO: Epoch: [236] [1200/1251] eta: 0:00:25 lr: 0.000114 loss: 2.8393 (2.8790) grad_norm: 2.3589 (nan) time: 0.4977 [2021-03-26 22:59:17 swin_small_patch4_window7_224] INFO: Epoch: [236] [1210/1251] eta: 0:00:20 lr: 0.000114 loss: 2.8807 (2.8807) grad_norm: 2.4134 (nan) time: 0.5004 [2021-03-26 22:59:22 swin_small_patch4_window7_224] INFO: Epoch: [236] [1220/1251] eta: 0:00:15 lr: 0.000114 loss: 2.8807 (2.8795) grad_norm: 2.4220 (nan) time: 0.5049 [2021-03-26 22:59:27 swin_small_patch4_window7_224] INFO: Epoch: [236] [1230/1251] eta: 0:00:10 lr: 0.000114 loss: 3.0323 (2.8820) grad_norm: 2.4761 (nan) time: 0.5019 [2021-03-26 22:59:32 swin_small_patch4_window7_224] INFO: Epoch: [236] [1240/1251] eta: 0:00:05 lr: 0.000114 loss: 3.1192 (2.8827) grad_norm: 2.4995 (nan) time: 0.4974 [2021-03-26 22:59:37 swin_small_patch4_window7_224] INFO: Epoch: [236] [1250/1251] eta: 0:00:00 lr: 0.000114 loss: 2.9655 (2.8821) grad_norm: 2.4025 (nan) time: 0.4979 [2021-03-26 22:59:49 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:26 loss: 1.0745 (1.0745) acc1: 76.5625 (76.5625) acc5: 93.7500 (93.7500) [2021-03-26 22:59:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7583 (0.7711) acc1: 79.6875 (80.9659) acc5: 96.8750 (96.7330) [2021-03-26 22:59:54 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7505 (0.7619) acc1: 79.6875 (80.6548) acc5: 96.8750 (96.4286) [2021-03-26 22:59:57 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7052 (0.7507) acc1: 81.2500 (80.9476) acc5: 95.3125 (96.3710) [2021-03-26 22:59:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7792 (0.7831) acc1: 81.2500 (80.5640) acc5: 95.3125 (96.1128) [2021-03-26 22:59:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8344 (0.7833) acc1: 79.6875 (80.9280) acc5: 95.3125 (96.0960) [2021-03-26 23:00:12 swin_small_patch4_window7_224] INFO: * Acc@1 81.920 Acc@5 95.906 loss 0.773 [2021-03-26 23:00:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-26 23:00:12 swin_small_patch4_window7_224] INFO: Max accuracy: 81.94% [2021-03-26 23:00:16 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 0/1251] eta: 1:33:07 lr: 0.000114 loss: 2.7843 (2.7843) grad_norm: 2.9113 (2.9113) time: 4.4665 [2021-03-26 23:00:21 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 10/1251] eta: 0:18:04 lr: 0.000114 loss: 3.1853 (2.9979) grad_norm: 2.4419 (2.6196) time: 0.8743 [2021-03-26 23:00:26 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 20/1251] eta: 0:14:19 lr: 0.000114 loss: 2.9661 (2.8408) grad_norm: 2.3958 (2.4602) time: 0.5100 [2021-03-26 23:00:31 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 30/1251] eta: 0:12:55 lr: 0.000114 loss: 3.0243 (2.8141) grad_norm: 2.3716 (2.4769) time: 0.5036 [2021-03-26 23:00:36 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 40/1251] eta: 0:12:10 lr: 0.000114 loss: 3.0260 (2.8307) grad_norm: 2.4352 (2.4758) time: 0.5030 [2021-03-26 23:00:41 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 50/1251] eta: 0:11:39 lr: 0.000114 loss: 2.9557 (2.8433) grad_norm: 2.4851 (2.4712) time: 0.5017 [2021-03-26 23:00:46 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 60/1251] eta: 0:11:18 lr: 0.000114 loss: 2.6922 (2.8154) grad_norm: 2.3909 (2.4558) time: 0.5001 [2021-03-26 23:00:51 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 70/1251] eta: 0:11:00 lr: 0.000114 loss: 2.7416 (2.8102) grad_norm: 2.3624 (2.4505) time: 0.5005 [2021-03-26 23:00:56 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 80/1251] eta: 0:10:46 lr: 0.000114 loss: 2.7762 (2.7837) grad_norm: 2.4569 (2.5249) time: 0.5006 [2021-03-26 23:01:02 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 90/1251] eta: 0:10:37 lr: 0.000114 loss: 3.0117 (2.8037) grad_norm: 2.4534 (2.5218) time: 0.5122 [2021-03-26 23:01:07 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 100/1251] eta: 0:10:26 lr: 0.000114 loss: 2.9152 (2.8042) grad_norm: 2.4331 (2.5191) time: 0.5127 [2021-03-26 23:01:12 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 110/1251] eta: 0:10:17 lr: 0.000114 loss: 2.7825 (2.7959) grad_norm: 2.4666 (2.5297) time: 0.5032 [2021-03-26 23:01:17 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 120/1251] eta: 0:10:07 lr: 0.000114 loss: 2.8531 (2.8104) grad_norm: 2.4666 (2.5304) time: 0.5025 [2021-03-26 23:01:22 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 130/1251] eta: 0:09:59 lr: 0.000114 loss: 2.7670 (2.7742) grad_norm: 2.5402 (2.5271) time: 0.5008 [2021-03-26 23:01:27 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 140/1251] eta: 0:09:51 lr: 0.000114 loss: 2.4211 (2.7589) grad_norm: 2.5020 (2.5253) time: 0.4988 [2021-03-26 23:01:32 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 150/1251] eta: 0:09:43 lr: 0.000113 loss: 2.8477 (2.7744) grad_norm: 2.5020 (2.5376) time: 0.4985 [2021-03-26 23:01:37 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 160/1251] eta: 0:09:35 lr: 0.000113 loss: 2.9825 (2.7798) grad_norm: 2.4324 (2.5311) time: 0.4964 [2021-03-26 23:01:42 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 170/1251] eta: 0:09:28 lr: 0.000113 loss: 2.9825 (2.7887) grad_norm: 2.2752 (2.5169) time: 0.4989 [2021-03-26 23:01:47 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 180/1251] eta: 0:09:22 lr: 0.000113 loss: 2.9699 (2.7994) grad_norm: 2.3837 (2.5183) time: 0.5098 [2021-03-26 23:01:52 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 190/1251] eta: 0:09:16 lr: 0.000113 loss: 3.0593 (2.8114) grad_norm: 2.5985 (2.5227) time: 0.5083 [2021-03-26 23:01:57 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 200/1251] eta: 0:09:10 lr: 0.000113 loss: 2.9410 (2.8102) grad_norm: 2.4885 (2.5153) time: 0.5021 [2021-03-26 23:02:02 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 210/1251] eta: 0:09:03 lr: 0.000113 loss: 2.7288 (2.8039) grad_norm: 2.3172 (2.5189) time: 0.4989 [2021-03-26 23:02:07 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 220/1251] eta: 0:08:57 lr: 0.000113 loss: 2.7123 (2.7986) grad_norm: 2.3706 (2.5381) time: 0.4985 [2021-03-26 23:02:12 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 230/1251] eta: 0:08:50 lr: 0.000113 loss: 2.8676 (2.8086) grad_norm: 2.5030 (2.5382) time: 0.4979 [2021-03-26 23:02:17 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 240/1251] eta: 0:08:45 lr: 0.000113 loss: 3.0993 (2.8198) grad_norm: 2.5276 (2.5361) time: 0.5040 [2021-03-26 23:02:22 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 250/1251] eta: 0:08:40 lr: 0.000113 loss: 3.0250 (2.8221) grad_norm: 2.5033 (2.5363) time: 0.5210 [2021-03-26 23:02:27 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 260/1251] eta: 0:08:34 lr: 0.000113 loss: 2.9727 (2.8278) grad_norm: 2.6187 (2.5485) time: 0.5115 [2021-03-26 23:02:32 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 270/1251] eta: 0:08:28 lr: 0.000113 loss: 2.9443 (2.8251) grad_norm: 2.5338 (2.5447) time: 0.4972 [2021-03-26 23:02:37 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 280/1251] eta: 0:08:22 lr: 0.000113 loss: 2.8511 (2.8306) grad_norm: 2.4126 (2.5435) time: 0.5020 [2021-03-26 23:02:42 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 290/1251] eta: 0:08:17 lr: 0.000113 loss: 2.9208 (2.8273) grad_norm: 2.4126 (2.5432) time: 0.5012 [2021-03-26 23:02:47 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 300/1251] eta: 0:08:11 lr: 0.000113 loss: 2.8457 (2.8312) grad_norm: 2.3741 (2.5372) time: 0.5027 [2021-03-26 23:02:52 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 310/1251] eta: 0:08:05 lr: 0.000113 loss: 3.0962 (2.8359) grad_norm: 2.3741 (2.5329) time: 0.5028 [2021-03-26 23:02:57 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 320/1251] eta: 0:08:00 lr: 0.000113 loss: 3.0962 (2.8420) grad_norm: 2.3772 (2.5291) time: 0.4988 [2021-03-26 23:03:02 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 330/1251] eta: 0:07:54 lr: 0.000113 loss: 3.0561 (2.8415) grad_norm: 2.4488 (2.5307) time: 0.5004 [2021-03-26 23:03:07 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 340/1251] eta: 0:07:49 lr: 0.000113 loss: 2.8213 (2.8401) grad_norm: 2.5805 (2.5360) time: 0.5062 [2021-03-26 23:03:12 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 350/1251] eta: 0:07:43 lr: 0.000113 loss: 2.7754 (2.8402) grad_norm: 2.4533 (2.5328) time: 0.5087 [2021-03-26 23:03:17 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 360/1251] eta: 0:07:38 lr: 0.000113 loss: 3.0891 (2.8477) grad_norm: 2.3873 (2.5299) time: 0.5016 [2021-03-26 23:03:22 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 370/1251] eta: 0:07:32 lr: 0.000113 loss: 3.0891 (2.8504) grad_norm: 2.4987 (2.5343) time: 0.4952 [2021-03-26 23:03:27 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 380/1251] eta: 0:07:27 lr: 0.000113 loss: 2.9558 (2.8513) grad_norm: 2.5144 (2.5330) time: 0.4998 [2021-03-26 23:03:33 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 390/1251] eta: 0:07:22 lr: 0.000113 loss: 3.0545 (2.8499) grad_norm: 2.3900 (2.5299) time: 0.5084 [2021-03-26 23:03:38 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 400/1251] eta: 0:07:16 lr: 0.000113 loss: 3.0545 (2.8537) grad_norm: 2.4827 (2.5315) time: 0.5088 [2021-03-26 23:03:43 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 410/1251] eta: 0:07:11 lr: 0.000113 loss: 3.0201 (2.8534) grad_norm: 2.4827 (2.5313) time: 0.5045 [2021-03-26 23:03:48 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 420/1251] eta: 0:07:06 lr: 0.000113 loss: 3.1576 (2.8603) grad_norm: 2.4337 (2.5314) time: 0.5036 [2021-03-26 23:03:53 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 430/1251] eta: 0:07:01 lr: 0.000113 loss: 3.0695 (2.8592) grad_norm: 2.3780 (2.5330) time: 0.5073 [2021-03-26 23:03:58 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 440/1251] eta: 0:06:55 lr: 0.000113 loss: 2.7097 (2.8586) grad_norm: 2.4054 (2.5310) time: 0.5119 [2021-03-26 23:04:03 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 450/1251] eta: 0:06:50 lr: 0.000113 loss: 3.0643 (2.8620) grad_norm: 2.4321 (2.5315) time: 0.5096 [2021-03-26 23:04:08 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 460/1251] eta: 0:06:45 lr: 0.000113 loss: 3.0821 (2.8638) grad_norm: 2.4655 (2.5311) time: 0.4984 [2021-03-26 23:04:13 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 470/1251] eta: 0:06:39 lr: 0.000113 loss: 2.9603 (2.8624) grad_norm: 2.4904 (2.5360) time: 0.4951 [2021-03-26 23:04:18 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 480/1251] eta: 0:06:34 lr: 0.000113 loss: 3.0089 (2.8652) grad_norm: 2.5023 (2.5351) time: 0.5047 [2021-03-26 23:04:23 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 490/1251] eta: 0:06:29 lr: 0.000113 loss: 3.0507 (2.8655) grad_norm: 2.3572 (2.5315) time: 0.5015 [2021-03-26 23:04:28 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 500/1251] eta: 0:06:23 lr: 0.000113 loss: 2.8533 (2.8656) grad_norm: 2.3636 (2.5319) time: 0.4925 [2021-03-26 23:04:33 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 510/1251] eta: 0:06:18 lr: 0.000113 loss: 2.8533 (2.8662) grad_norm: 2.3811 (2.5309) time: 0.4945 [2021-03-26 23:04:38 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 520/1251] eta: 0:06:13 lr: 0.000113 loss: 2.9432 (2.8684) grad_norm: 2.3740 (2.5271) time: 0.4959 [2021-03-26 23:04:43 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 530/1251] eta: 0:06:08 lr: 0.000113 loss: 3.0219 (2.8691) grad_norm: 2.3679 (2.5254) time: 0.4997 [2021-03-26 23:04:48 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 540/1251] eta: 0:06:02 lr: 0.000113 loss: 3.0212 (2.8709) grad_norm: 2.3499 (2.5230) time: 0.5062 [2021-03-26 23:04:53 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 550/1251] eta: 0:05:57 lr: 0.000112 loss: 2.9194 (2.8682) grad_norm: 2.3485 (2.5203) time: 0.5135 [2021-03-26 23:04:58 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 560/1251] eta: 0:05:52 lr: 0.000112 loss: 2.8652 (2.8675) grad_norm: 2.4131 (2.5191) time: 0.5074 [2021-03-26 23:05:03 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 570/1251] eta: 0:05:47 lr: 0.000112 loss: 2.8652 (2.8682) grad_norm: 2.4315 (2.5216) time: 0.5024 [2021-03-26 23:05:08 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 580/1251] eta: 0:05:42 lr: 0.000112 loss: 3.0057 (2.8728) grad_norm: 2.4404 (2.5252) time: 0.5081 [2021-03-26 23:05:13 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 590/1251] eta: 0:05:37 lr: 0.000112 loss: 3.1358 (2.8765) grad_norm: 2.4404 (2.5253) time: 0.5099 [2021-03-26 23:05:18 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 600/1251] eta: 0:05:32 lr: 0.000112 loss: 3.1722 (2.8778) grad_norm: 2.4290 (2.5244) time: 0.5058 [2021-03-26 23:05:23 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 610/1251] eta: 0:05:26 lr: 0.000112 loss: 3.0954 (2.8773) grad_norm: 2.4606 (2.5233) time: 0.5034 [2021-03-26 23:05:28 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 620/1251] eta: 0:05:21 lr: 0.000112 loss: 3.1758 (2.8833) grad_norm: 2.4001 (2.5206) time: 0.5021 [2021-03-26 23:05:33 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 630/1251] eta: 0:05:16 lr: 0.000112 loss: 3.1790 (2.8826) grad_norm: 2.3903 (2.5195) time: 0.4928 [2021-03-26 23:05:38 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 640/1251] eta: 0:05:11 lr: 0.000112 loss: 3.0047 (2.8822) grad_norm: 2.3556 (2.5191) time: 0.5046 [2021-03-26 23:05:43 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 650/1251] eta: 0:05:06 lr: 0.000112 loss: 2.9674 (2.8809) grad_norm: 2.3924 (2.5176) time: 0.5071 [2021-03-26 23:05:48 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 660/1251] eta: 0:05:00 lr: 0.000112 loss: 2.9712 (2.8808) grad_norm: 2.3966 (2.5166) time: 0.4956 [2021-03-26 23:05:53 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 670/1251] eta: 0:04:55 lr: 0.000112 loss: 2.9318 (2.8812) grad_norm: 2.3587 (2.5144) time: 0.4980 [2021-03-26 23:05:58 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 680/1251] eta: 0:04:50 lr: 0.000112 loss: 2.8869 (2.8795) grad_norm: 2.3149 (2.5146) time: 0.4932 [2021-03-26 23:06:03 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 690/1251] eta: 0:04:45 lr: 0.000112 loss: 2.8748 (2.8786) grad_norm: 2.5175 (2.5144) time: 0.4934 [2021-03-26 23:06:08 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 700/1251] eta: 0:04:40 lr: 0.000112 loss: 2.8752 (2.8794) grad_norm: 2.5254 (2.5146) time: 0.4979 [2021-03-26 23:06:13 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 710/1251] eta: 0:04:35 lr: 0.000112 loss: 2.9440 (2.8780) grad_norm: 2.5254 (2.5158) time: 0.4983 [2021-03-26 23:06:18 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 720/1251] eta: 0:04:29 lr: 0.000112 loss: 2.8898 (2.8767) grad_norm: 2.4338 (2.5152) time: 0.5058 [2021-03-26 23:06:23 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 730/1251] eta: 0:04:24 lr: 0.000112 loss: 2.9202 (2.8757) grad_norm: 2.4364 (2.5150) time: 0.5047 [2021-03-26 23:06:29 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 740/1251] eta: 0:04:19 lr: 0.000112 loss: 2.9605 (2.8750) grad_norm: 2.4631 (2.5133) time: 0.5146 [2021-03-26 23:06:34 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 750/1251] eta: 0:04:14 lr: 0.000112 loss: 2.9776 (2.8746) grad_norm: 2.4078 (2.5114) time: 0.5165 [2021-03-26 23:06:39 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 760/1251] eta: 0:04:09 lr: 0.000112 loss: 2.8878 (2.8735) grad_norm: 2.3989 (2.5113) time: 0.5066 [2021-03-26 23:06:44 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 770/1251] eta: 0:04:04 lr: 0.000112 loss: 2.8878 (2.8751) grad_norm: 2.4578 (2.5128) time: 0.5115 [2021-03-26 23:06:49 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 780/1251] eta: 0:03:59 lr: 0.000112 loss: 2.9594 (2.8734) grad_norm: 2.6237 (2.5132) time: 0.5119 [2021-03-26 23:06:54 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 790/1251] eta: 0:03:54 lr: 0.000112 loss: 2.8484 (2.8737) grad_norm: 2.3535 (2.5111) time: 0.5074 [2021-03-26 23:06:59 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 800/1251] eta: 0:03:49 lr: 0.000112 loss: 2.9977 (2.8751) grad_norm: 2.3492 (2.5130) time: 0.5017 [2021-03-26 23:07:04 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 810/1251] eta: 0:03:44 lr: 0.000112 loss: 3.1138 (2.8775) grad_norm: 2.5656 (2.5161) time: 0.4991 [2021-03-26 23:07:09 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 820/1251] eta: 0:03:39 lr: 0.000112 loss: 2.8794 (2.8751) grad_norm: 2.6059 (2.5183) time: 0.5014 [2021-03-26 23:07:14 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 830/1251] eta: 0:03:33 lr: 0.000112 loss: 2.8039 (2.8760) grad_norm: 2.3593 (2.5162) time: 0.5062 [2021-03-26 23:07:19 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 840/1251] eta: 0:03:28 lr: 0.000112 loss: 2.6942 (2.8733) grad_norm: 2.2978 (2.5151) time: 0.5041 [2021-03-26 23:07:24 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 850/1251] eta: 0:03:23 lr: 0.000112 loss: 2.7551 (2.8731) grad_norm: 2.4760 (2.5159) time: 0.5035 [2021-03-26 23:07:29 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 860/1251] eta: 0:03:18 lr: 0.000112 loss: 2.9805 (2.8747) grad_norm: 2.4980 (2.5168) time: 0.5006 [2021-03-26 23:07:34 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 870/1251] eta: 0:03:13 lr: 0.000112 loss: 3.0046 (2.8759) grad_norm: 2.6126 (2.5178) time: 0.4944 [2021-03-26 23:07:39 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 880/1251] eta: 0:03:08 lr: 0.000112 loss: 2.9498 (2.8744) grad_norm: 2.6309 (2.5201) time: 0.4998 [2021-03-26 23:07:44 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 890/1251] eta: 0:03:03 lr: 0.000112 loss: 2.9498 (2.8738) grad_norm: 2.5237 (2.5199) time: 0.5032 [2021-03-26 23:07:49 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 900/1251] eta: 0:02:58 lr: 0.000112 loss: 3.0195 (2.8749) grad_norm: 2.3580 (2.5198) time: 0.4961 [2021-03-26 23:07:54 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 910/1251] eta: 0:02:53 lr: 0.000112 loss: 2.9115 (2.8750) grad_norm: 2.4297 (2.5228) time: 0.5039 [2021-03-26 23:07:59 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 920/1251] eta: 0:02:48 lr: 0.000112 loss: 2.9984 (2.8751) grad_norm: 2.5613 (2.5250) time: 0.5096 [2021-03-26 23:08:04 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 930/1251] eta: 0:02:42 lr: 0.000112 loss: 3.0073 (2.8760) grad_norm: 2.5402 (2.5241) time: 0.4985 [2021-03-26 23:08:09 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 940/1251] eta: 0:02:37 lr: 0.000111 loss: 2.7777 (2.8734) grad_norm: 2.5402 (2.5281) time: 0.5012 [2021-03-26 23:08:14 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 950/1251] eta: 0:02:32 lr: 0.000111 loss: 2.8770 (2.8759) grad_norm: 2.6329 (2.5288) time: 0.5136 [2021-03-26 23:08:19 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 960/1251] eta: 0:02:27 lr: 0.000111 loss: 3.2035 (2.8771) grad_norm: 2.4964 (2.5277) time: 0.5098 [2021-03-26 23:08:24 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 970/1251] eta: 0:02:22 lr: 0.000111 loss: 2.9045 (2.8754) grad_norm: 2.3282 (2.5264) time: 0.5002 [2021-03-26 23:08:30 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 980/1251] eta: 0:02:17 lr: 0.000111 loss: 2.9045 (2.8762) grad_norm: 2.3440 (2.5248) time: 0.5009 [2021-03-26 23:08:35 swin_small_patch4_window7_224] INFO: Epoch: [237] [ 990/1251] eta: 0:02:12 lr: 0.000111 loss: 3.0062 (2.8768) grad_norm: 2.3519 (2.5234) time: 0.5029 [2021-03-26 23:08:40 swin_small_patch4_window7_224] INFO: Epoch: [237] [1000/1251] eta: 0:02:07 lr: 0.000111 loss: 2.9293 (2.8773) grad_norm: 2.3968 (2.5229) time: 0.5045 [2021-03-26 23:08:45 swin_small_patch4_window7_224] INFO: Epoch: [237] [1010/1251] eta: 0:02:02 lr: 0.000111 loss: 2.9120 (2.8765) grad_norm: 2.4265 (2.5222) time: 0.5076 [2021-03-26 23:08:50 swin_small_patch4_window7_224] INFO: Epoch: [237] [1020/1251] eta: 0:01:57 lr: 0.000111 loss: 2.9405 (2.8773) grad_norm: 2.3731 (2.5211) time: 0.5074 [2021-03-26 23:08:55 swin_small_patch4_window7_224] INFO: Epoch: [237] [1030/1251] eta: 0:01:52 lr: 0.000111 loss: 2.8023 (2.8743) grad_norm: 2.3731 (2.5198) time: 0.5047 [2021-03-26 23:09:00 swin_small_patch4_window7_224] INFO: Epoch: [237] [1040/1251] eta: 0:01:47 lr: 0.000111 loss: 2.7824 (2.8759) grad_norm: 2.3639 (2.5186) time: 0.5086 [2021-03-26 23:09:05 swin_small_patch4_window7_224] INFO: Epoch: [237] [1050/1251] eta: 0:01:41 lr: 0.000111 loss: 3.0194 (2.8773) grad_norm: 2.3701 (2.5180) time: 0.5079 [2021-03-26 23:09:10 swin_small_patch4_window7_224] INFO: Epoch: [237] [1060/1251] eta: 0:01:36 lr: 0.000111 loss: 2.9115 (2.8758) grad_norm: 2.4749 (2.5162) time: 0.4971 [2021-03-26 23:09:15 swin_small_patch4_window7_224] INFO: Epoch: [237] [1070/1251] eta: 0:01:31 lr: 0.000111 loss: 2.9862 (2.8770) grad_norm: 2.4499 (2.5186) time: 0.4954 [2021-03-26 23:09:20 swin_small_patch4_window7_224] INFO: Epoch: [237] [1080/1251] eta: 0:01:26 lr: 0.000111 loss: 2.9680 (2.8747) grad_norm: 2.4499 (2.5204) time: 0.5000 [2021-03-26 23:09:25 swin_small_patch4_window7_224] INFO: Epoch: [237] [1090/1251] eta: 0:01:21 lr: 0.000111 loss: 2.9597 (2.8762) grad_norm: 2.3712 (2.5194) time: 0.4963 [2021-03-26 23:09:30 swin_small_patch4_window7_224] INFO: Epoch: [237] [1100/1251] eta: 0:01:16 lr: 0.000111 loss: 3.0026 (2.8773) grad_norm: 2.3729 (2.5185) time: 0.4972 [2021-03-26 23:09:35 swin_small_patch4_window7_224] INFO: Epoch: [237] [1110/1251] eta: 0:01:11 lr: 0.000111 loss: 3.0132 (2.8779) grad_norm: 2.3664 (2.5181) time: 0.4970 [2021-03-26 23:09:40 swin_small_patch4_window7_224] INFO: Epoch: [237] [1120/1251] eta: 0:01:06 lr: 0.000111 loss: 3.0467 (2.8786) grad_norm: 2.3064 (2.5168) time: 0.4930 [2021-03-26 23:09:45 swin_small_patch4_window7_224] INFO: Epoch: [237] [1130/1251] eta: 0:01:01 lr: 0.000111 loss: 2.9499 (2.8778) grad_norm: 2.3064 (2.5159) time: 0.4965 [2021-03-26 23:09:50 swin_small_patch4_window7_224] INFO: Epoch: [237] [1140/1251] eta: 0:00:56 lr: 0.000111 loss: 2.8872 (2.8771) grad_norm: 2.3717 (2.5157) time: 0.4998 [2021-03-26 23:09:55 swin_small_patch4_window7_224] INFO: Epoch: [237] [1150/1251] eta: 0:00:51 lr: 0.000111 loss: 2.8700 (2.8755) grad_norm: 2.4373 (2.5154) time: 0.4978 [2021-03-26 23:10:00 swin_small_patch4_window7_224] INFO: Epoch: [237] [1160/1251] eta: 0:00:46 lr: 0.000111 loss: 2.7480 (2.8749) grad_norm: 2.4788 (2.5158) time: 0.4959 [2021-03-26 23:10:05 swin_small_patch4_window7_224] INFO: Epoch: [237] [1170/1251] eta: 0:00:41 lr: 0.000111 loss: 2.9317 (2.8757) grad_norm: 2.3321 (2.5141) time: 0.4982 [2021-03-26 23:10:10 swin_small_patch4_window7_224] INFO: Epoch: [237] [1180/1251] eta: 0:00:35 lr: 0.000111 loss: 3.0929 (2.8754) grad_norm: 2.5326 (2.5149) time: 0.4952 [2021-03-26 23:10:15 swin_small_patch4_window7_224] INFO: Epoch: [237] [1190/1251] eta: 0:00:30 lr: 0.000111 loss: 3.1507 (2.8757) grad_norm: 2.6471 (2.5157) time: 0.5007 [2021-03-26 23:10:20 swin_small_patch4_window7_224] INFO: Epoch: [237] [1200/1251] eta: 0:00:25 lr: 0.000111 loss: 3.0788 (2.8756) grad_norm: 2.5190 (2.5157) time: 0.5074 [2021-03-26 23:10:25 swin_small_patch4_window7_224] INFO: Epoch: [237] [1210/1251] eta: 0:00:20 lr: 0.000111 loss: 3.0841 (2.8779) grad_norm: 2.4358 (2.5178) time: 0.5067 [2021-03-26 23:10:30 swin_small_patch4_window7_224] INFO: Epoch: [237] [1220/1251] eta: 0:00:15 lr: 0.000111 loss: 3.0840 (2.8771) grad_norm: 2.5136 (2.5195) time: 0.5039 [2021-03-26 23:10:35 swin_small_patch4_window7_224] INFO: Epoch: [237] [1230/1251] eta: 0:00:10 lr: 0.000111 loss: 2.8072 (2.8773) grad_norm: 2.5511 (2.5195) time: 0.4979 [2021-03-26 23:10:40 swin_small_patch4_window7_224] INFO: Epoch: [237] [1240/1251] eta: 0:00:05 lr: 0.000111 loss: 3.0928 (2.8793) grad_norm: 2.5277 (2.5190) time: 0.4999 [2021-03-26 23:10:45 swin_small_patch4_window7_224] INFO: Epoch: [237] [1250/1251] eta: 0:00:00 lr: 0.000111 loss: 2.9812 (2.8790) grad_norm: 2.4094 (2.5200) time: 0.4967 [2021-03-26 23:10:53 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:53 loss: 0.7098 (0.7098) acc1: 76.5625 (76.5625) acc5: 98.4375 (98.4375) [2021-03-26 23:10:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:21 loss: 0.6899 (0.7391) acc1: 81.2500 (80.5398) acc5: 98.4375 (97.7273) [2021-03-26 23:10:59 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7107 (0.7565) acc1: 82.8125 (80.8780) acc5: 96.8750 (97.1726) [2021-03-26 23:11:01 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7719 (0.7968) acc1: 78.1250 (80.1411) acc5: 96.8750 (96.6734) [2021-03-26 23:11:03 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7531 (0.7802) acc1: 82.8125 (80.9832) acc5: 95.3125 (96.2652) [2021-03-26 23:11:03 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7497 (0.7764) acc1: 82.8125 (80.9600) acc5: 95.3125 (96.2880) [2021-03-26 23:11:15 swin_small_patch4_window7_224] INFO: * Acc@1 81.950 Acc@5 95.982 loss 0.764 [2021-03-26 23:11:15 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.0% [2021-03-26 23:11:15 swin_small_patch4_window7_224] INFO: Max accuracy: 81.95% [2021-03-26 23:11:19 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 0/1251] eta: 1:26:01 lr: 0.000111 loss: 3.1941 (3.1941) grad_norm: 2.4866 (2.4866) time: 4.1260 [2021-03-26 23:11:24 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 10/1251] eta: 0:17:19 lr: 0.000111 loss: 2.9898 (2.8443) grad_norm: 2.5766 (2.5592) time: 0.8373 [2021-03-26 23:11:29 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 20/1251] eta: 0:13:59 lr: 0.000111 loss: 2.9898 (2.9343) grad_norm: 2.6242 (3.1203) time: 0.5096 [2021-03-26 23:11:34 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 30/1251] eta: 0:12:39 lr: 0.000111 loss: 3.0198 (2.9622) grad_norm: 2.5257 (2.9880) time: 0.5038 [2021-03-26 23:11:39 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 40/1251] eta: 0:12:01 lr: 0.000111 loss: 3.0963 (2.9926) grad_norm: 2.4909 (2.9006) time: 0.5060 [2021-03-26 23:11:44 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 50/1251] eta: 0:11:31 lr: 0.000111 loss: 3.0963 (2.9900) grad_norm: 2.4909 (2.8854) time: 0.5039 [2021-03-26 23:11:49 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 60/1251] eta: 0:11:10 lr: 0.000111 loss: 3.0285 (2.9845) grad_norm: 2.4628 (2.8124) time: 0.4963 [2021-03-26 23:11:54 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 70/1251] eta: 0:10:56 lr: 0.000111 loss: 2.9642 (2.9892) grad_norm: 2.4147 (2.7802) time: 0.5041 [2021-03-26 23:11:59 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 80/1251] eta: 0:10:43 lr: 0.000111 loss: 2.9845 (2.9861) grad_norm: 2.5398 (2.7476) time: 0.5076 [2021-03-26 23:12:04 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 90/1251] eta: 0:10:30 lr: 0.000110 loss: 2.9845 (2.9704) grad_norm: 2.3865 (2.7120) time: 0.5005 [2021-03-26 23:12:09 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 100/1251] eta: 0:10:21 lr: 0.000110 loss: 2.8604 (2.9657) grad_norm: 2.3331 (2.6701) time: 0.5013 [2021-03-26 23:12:14 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 110/1251] eta: 0:10:12 lr: 0.000110 loss: 2.8256 (2.9410) grad_norm: 2.3157 (2.6498) time: 0.5048 [2021-03-26 23:12:19 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 120/1251] eta: 0:10:02 lr: 0.000110 loss: 2.8726 (2.9373) grad_norm: 2.4037 (2.6319) time: 0.4982 [2021-03-26 23:12:24 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 130/1251] eta: 0:09:57 lr: 0.000110 loss: 2.9794 (2.9382) grad_norm: 2.4898 (2.6248) time: 0.5123 [2021-03-26 23:12:29 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 140/1251] eta: 0:09:49 lr: 0.000110 loss: 3.1280 (2.9381) grad_norm: 2.4797 (2.6215) time: 0.5138 [2021-03-26 23:12:34 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 150/1251] eta: 0:09:41 lr: 0.000110 loss: 3.0792 (2.9381) grad_norm: 2.3980 (2.6040) time: 0.5001 [2021-03-26 23:12:39 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 160/1251] eta: 0:09:34 lr: 0.000110 loss: 3.0870 (2.9497) grad_norm: 2.3854 (2.6011) time: 0.4979 [2021-03-26 23:12:44 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 170/1251] eta: 0:09:27 lr: 0.000110 loss: 3.1539 (2.9437) grad_norm: 2.3531 (2.5893) time: 0.4998 [2021-03-26 23:12:49 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 180/1251] eta: 0:09:21 lr: 0.000110 loss: 3.1563 (2.9509) grad_norm: 2.3531 (2.5880) time: 0.5064 [2021-03-26 23:12:55 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 190/1251] eta: 0:09:15 lr: 0.000110 loss: 3.1713 (2.9566) grad_norm: 2.3352 (2.5762) time: 0.5059 [2021-03-26 23:13:00 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 200/1251] eta: 0:09:08 lr: 0.000110 loss: 3.1397 (2.9561) grad_norm: 2.2674 (2.5632) time: 0.5031 [2021-03-26 23:13:05 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 210/1251] eta: 0:09:02 lr: 0.000110 loss: 3.1397 (2.9559) grad_norm: 2.3547 (2.5600) time: 0.5046 [2021-03-26 23:13:10 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 220/1251] eta: 0:08:56 lr: 0.000110 loss: 3.0145 (2.9604) grad_norm: 2.4334 (2.5531) time: 0.5054 [2021-03-26 23:13:15 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 230/1251] eta: 0:08:50 lr: 0.000110 loss: 2.9707 (2.9507) grad_norm: 2.4145 (2.5460) time: 0.5063 [2021-03-26 23:13:20 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 240/1251] eta: 0:08:45 lr: 0.000110 loss: 2.9318 (2.9533) grad_norm: 2.3582 (2.5411) time: 0.5064 [2021-03-26 23:13:25 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 250/1251] eta: 0:08:39 lr: 0.000110 loss: 2.9456 (2.9490) grad_norm: 2.3582 (2.5361) time: 0.5010 [2021-03-26 23:13:30 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 260/1251] eta: 0:08:33 lr: 0.000110 loss: 2.9253 (2.9480) grad_norm: 2.3173 (2.5329) time: 0.5037 [2021-03-26 23:13:35 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 270/1251] eta: 0:08:27 lr: 0.000110 loss: 2.7317 (2.9359) grad_norm: 2.4102 (2.5287) time: 0.5052 [2021-03-26 23:13:40 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 280/1251] eta: 0:08:21 lr: 0.000110 loss: 2.8286 (2.9376) grad_norm: 2.4430 (2.5269) time: 0.5015 [2021-03-26 23:13:45 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 290/1251] eta: 0:08:16 lr: 0.000110 loss: 2.9939 (2.9372) grad_norm: 2.5504 (2.5302) time: 0.5054 [2021-03-26 23:13:50 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 300/1251] eta: 0:08:10 lr: 0.000110 loss: 2.9990 (2.9364) grad_norm: 2.5504 (2.5272) time: 0.5025 [2021-03-26 23:13:55 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 310/1251] eta: 0:08:05 lr: 0.000110 loss: 2.9615 (2.9362) grad_norm: 2.5019 (2.5272) time: 0.4998 [2021-03-26 23:14:00 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 320/1251] eta: 0:07:59 lr: 0.000110 loss: 2.8893 (2.9348) grad_norm: 2.4872 (2.5302) time: 0.5047 [2021-03-26 23:14:05 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 330/1251] eta: 0:07:54 lr: 0.000110 loss: 2.9993 (2.9356) grad_norm: 2.3744 (2.5246) time: 0.5080 [2021-03-26 23:14:10 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 340/1251] eta: 0:07:48 lr: 0.000110 loss: 2.9319 (2.9270) grad_norm: 2.4529 (2.5318) time: 0.5062 [2021-03-26 23:14:15 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 350/1251] eta: 0:07:43 lr: 0.000110 loss: 2.9504 (2.9315) grad_norm: 2.4627 (2.5308) time: 0.4980 [2021-03-26 23:14:20 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 360/1251] eta: 0:07:37 lr: 0.000110 loss: 3.1063 (2.9313) grad_norm: 2.4544 (2.5301) time: 0.4938 [2021-03-26 23:14:25 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 370/1251] eta: 0:07:32 lr: 0.000110 loss: 2.8761 (2.9303) grad_norm: 2.3674 (2.5262) time: 0.4971 [2021-03-26 23:14:30 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 380/1251] eta: 0:07:26 lr: 0.000110 loss: 3.1011 (2.9342) grad_norm: 2.4464 (2.5284) time: 0.5023 [2021-03-26 23:14:35 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 390/1251] eta: 0:07:21 lr: 0.000110 loss: 3.1011 (2.9325) grad_norm: 2.4855 (2.5258) time: 0.4980 [2021-03-26 23:14:40 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 400/1251] eta: 0:07:15 lr: 0.000110 loss: 3.0304 (2.9353) grad_norm: 2.2732 (2.5243) time: 0.4934 [2021-03-26 23:14:45 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 410/1251] eta: 0:07:10 lr: 0.000110 loss: 2.9190 (2.9263) grad_norm: 2.4079 (2.5332) time: 0.4961 [2021-03-26 23:14:50 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 420/1251] eta: 0:07:05 lr: 0.000110 loss: 2.7966 (2.9229) grad_norm: 2.4895 (2.5345) time: 0.5063 [2021-03-26 23:14:55 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 430/1251] eta: 0:07:00 lr: 0.000110 loss: 2.9791 (2.9227) grad_norm: 2.3793 (2.5302) time: 0.5115 [2021-03-26 23:15:00 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 440/1251] eta: 0:06:54 lr: 0.000110 loss: 2.8427 (2.9161) grad_norm: 2.3086 (2.5293) time: 0.4993 [2021-03-26 23:15:05 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 450/1251] eta: 0:06:49 lr: 0.000110 loss: 2.9443 (2.9201) grad_norm: 2.3086 (2.5256) time: 0.4956 [2021-03-26 23:15:10 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 460/1251] eta: 0:06:44 lr: 0.000110 loss: 3.0392 (2.9166) grad_norm: 2.4631 (2.5275) time: 0.5042 [2021-03-26 23:15:15 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 470/1251] eta: 0:06:38 lr: 0.000110 loss: 3.0198 (2.9179) grad_norm: 2.4631 (2.5249) time: 0.5014 [2021-03-26 23:15:20 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 480/1251] eta: 0:06:33 lr: 0.000110 loss: 3.0474 (2.9177) grad_norm: 2.5134 (2.5285) time: 0.5002 [2021-03-26 23:15:25 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 490/1251] eta: 0:06:28 lr: 0.000109 loss: 2.5965 (2.9083) grad_norm: 2.4991 (2.5319) time: 0.5028 [2021-03-26 23:15:30 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 500/1251] eta: 0:06:22 lr: 0.000109 loss: 2.5965 (2.9069) grad_norm: 2.3475 (2.5286) time: 0.4978 [2021-03-26 23:15:35 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 510/1251] eta: 0:06:17 lr: 0.000109 loss: 2.9049 (2.9067) grad_norm: 2.3592 (2.5293) time: 0.4961 [2021-03-26 23:15:40 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 520/1251] eta: 0:06:12 lr: 0.000109 loss: 2.9935 (2.9103) grad_norm: 2.4152 (2.5280) time: 0.4966 [2021-03-26 23:15:45 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 530/1251] eta: 0:06:07 lr: 0.000109 loss: 2.9935 (2.9092) grad_norm: 2.3889 (2.5261) time: 0.4979 [2021-03-26 23:15:50 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 540/1251] eta: 0:06:02 lr: 0.000109 loss: 2.9113 (2.9083) grad_norm: 2.3905 (2.5249) time: 0.5019 [2021-03-26 23:15:55 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 550/1251] eta: 0:05:57 lr: 0.000109 loss: 2.7152 (2.9062) grad_norm: 2.5269 (2.5281) time: 0.5182 [2021-03-26 23:16:00 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 560/1251] eta: 0:05:52 lr: 0.000109 loss: 2.7015 (2.9044) grad_norm: 2.5745 (2.5305) time: 0.5192 [2021-03-26 23:16:06 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 570/1251] eta: 0:05:46 lr: 0.000109 loss: 3.0068 (2.9044) grad_norm: 2.4988 (2.5299) time: 0.5067 [2021-03-26 23:16:10 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 580/1251] eta: 0:05:41 lr: 0.000109 loss: 2.8036 (2.9034) grad_norm: 2.5434 (2.5325) time: 0.4994 [2021-03-26 23:16:16 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 590/1251] eta: 0:05:36 lr: 0.000109 loss: 3.0125 (2.9059) grad_norm: 2.5077 (2.5312) time: 0.5036 [2021-03-26 23:16:21 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 600/1251] eta: 0:05:31 lr: 0.000109 loss: 3.0582 (2.9049) grad_norm: 2.4619 (2.5296) time: 0.5067 [2021-03-26 23:16:26 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 610/1251] eta: 0:05:26 lr: 0.000109 loss: 3.0582 (2.9045) grad_norm: 2.3554 (2.5274) time: 0.5009 [2021-03-26 23:16:31 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 620/1251] eta: 0:05:21 lr: 0.000109 loss: 3.0949 (2.9071) grad_norm: 2.3554 (2.5263) time: 0.5068 [2021-03-26 23:16:36 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 630/1251] eta: 0:05:16 lr: 0.000109 loss: 3.0555 (2.9092) grad_norm: 2.3916 (2.5242) time: 0.5055 [2021-03-26 23:16:41 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 640/1251] eta: 0:05:10 lr: 0.000109 loss: 2.9536 (2.9077) grad_norm: 2.3933 (2.5243) time: 0.5015 [2021-03-26 23:16:46 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 650/1251] eta: 0:05:05 lr: 0.000109 loss: 2.9536 (2.9108) grad_norm: 2.4472 (2.5266) time: 0.5029 [2021-03-26 23:16:51 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 660/1251] eta: 0:05:00 lr: 0.000109 loss: 2.8833 (2.9065) grad_norm: 2.4472 (2.5243) time: 0.5014 [2021-03-26 23:16:56 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 670/1251] eta: 0:04:55 lr: 0.000109 loss: 2.8789 (2.9063) grad_norm: 2.3317 (2.5217) time: 0.5002 [2021-03-26 23:17:01 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 680/1251] eta: 0:04:50 lr: 0.000109 loss: 2.8789 (2.9023) grad_norm: 2.2737 (2.5182) time: 0.5016 [2021-03-26 23:17:06 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 690/1251] eta: 0:04:45 lr: 0.000109 loss: 2.7847 (2.9005) grad_norm: 2.3025 (2.5186) time: 0.5031 [2021-03-26 23:17:11 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 700/1251] eta: 0:04:39 lr: 0.000109 loss: 3.1317 (2.9019) grad_norm: 2.5001 (2.5195) time: 0.4999 [2021-03-26 23:17:16 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 710/1251] eta: 0:04:34 lr: 0.000109 loss: 3.1283 (2.9046) grad_norm: 2.5049 (2.5301) time: 0.4990 [2021-03-26 23:17:21 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 720/1251] eta: 0:04:29 lr: 0.000109 loss: 2.9693 (2.9042) grad_norm: 2.5049 (2.5296) time: 0.5002 [2021-03-26 23:17:26 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 730/1251] eta: 0:04:24 lr: 0.000109 loss: 3.0125 (2.9059) grad_norm: 2.4297 (2.5308) time: 0.5062 [2021-03-26 23:17:31 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 740/1251] eta: 0:04:19 lr: 0.000109 loss: 2.8566 (2.9007) grad_norm: 2.4665 (2.5325) time: 0.5270 [2021-03-26 23:17:36 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 750/1251] eta: 0:04:14 lr: 0.000109 loss: 2.7172 (2.9011) grad_norm: 2.4665 (2.5316) time: 0.5182 [2021-03-26 23:17:41 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 760/1251] eta: 0:04:09 lr: 0.000109 loss: 2.9643 (2.9002) grad_norm: 2.4233 (2.5321) time: 0.5027 [2021-03-26 23:17:46 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 770/1251] eta: 0:04:04 lr: 0.000109 loss: 2.8326 (2.9007) grad_norm: 2.4280 (2.5311) time: 0.5025 [2021-03-26 23:17:51 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 780/1251] eta: 0:03:59 lr: 0.000109 loss: 3.1278 (2.9039) grad_norm: 2.3906 (2.5290) time: 0.5001 [2021-03-26 23:17:56 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 790/1251] eta: 0:03:54 lr: 0.000109 loss: 3.2005 (2.9066) grad_norm: 2.3906 (2.5321) time: 0.4979 [2021-03-26 23:18:01 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 800/1251] eta: 0:03:48 lr: 0.000109 loss: 3.0331 (2.9053) grad_norm: 2.3885 (2.5304) time: 0.4938 [2021-03-26 23:18:07 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 810/1251] eta: 0:03:43 lr: 0.000109 loss: 2.6838 (2.9039) grad_norm: 2.4003 (2.5292) time: 0.5076 [2021-03-26 23:18:12 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 820/1251] eta: 0:03:38 lr: 0.000109 loss: 2.6345 (2.9027) grad_norm: 2.5088 (2.5294) time: 0.5086 [2021-03-26 23:18:17 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 830/1251] eta: 0:03:33 lr: 0.000109 loss: 2.7540 (2.9011) grad_norm: 2.4302 (2.5282) time: 0.5009 [2021-03-26 23:18:22 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 840/1251] eta: 0:03:28 lr: 0.000109 loss: 2.9336 (2.9021) grad_norm: 2.3980 (2.5262) time: 0.5020 [2021-03-26 23:18:27 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 850/1251] eta: 0:03:23 lr: 0.000109 loss: 2.9850 (2.9026) grad_norm: 2.4378 (2.5316) time: 0.5036 [2021-03-26 23:18:32 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 860/1251] eta: 0:03:18 lr: 0.000109 loss: 2.9492 (2.9020) grad_norm: 2.5111 (2.5305) time: 0.5053 [2021-03-26 23:18:37 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 870/1251] eta: 0:03:13 lr: 0.000109 loss: 2.9172 (2.9009) grad_norm: 2.3306 (2.5287) time: 0.5100 [2021-03-26 23:18:42 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 880/1251] eta: 0:03:08 lr: 0.000109 loss: 2.6253 (2.8978) grad_norm: 2.3306 (2.5271) time: 0.5104 [2021-03-26 23:18:47 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 890/1251] eta: 0:03:03 lr: 0.000108 loss: 2.6916 (2.8967) grad_norm: 2.3237 (2.5260) time: 0.5060 [2021-03-26 23:18:52 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 900/1251] eta: 0:02:58 lr: 0.000108 loss: 3.0190 (2.8995) grad_norm: 2.3702 (2.5259) time: 0.5020 [2021-03-26 23:18:57 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 910/1251] eta: 0:02:53 lr: 0.000108 loss: 3.0728 (2.9000) grad_norm: 2.4507 (2.5262) time: 0.4968 [2021-03-26 23:19:02 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 920/1251] eta: 0:02:47 lr: 0.000108 loss: 3.0675 (2.9012) grad_norm: 2.4440 (2.5262) time: 0.5065 [2021-03-26 23:19:07 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 930/1251] eta: 0:02:42 lr: 0.000108 loss: 2.9447 (2.9007) grad_norm: 2.4105 (2.5263) time: 0.5095 [2021-03-26 23:19:12 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 940/1251] eta: 0:02:37 lr: 0.000108 loss: 3.0321 (2.9013) grad_norm: 2.4105 (2.5268) time: 0.5019 [2021-03-26 23:19:17 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 950/1251] eta: 0:02:32 lr: 0.000108 loss: 3.1371 (2.9019) grad_norm: 2.5461 (2.5281) time: 0.5029 [2021-03-26 23:19:22 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 960/1251] eta: 0:02:27 lr: 0.000108 loss: 3.1231 (2.9032) grad_norm: 2.5168 (2.5273) time: 0.5044 [2021-03-26 23:19:27 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 970/1251] eta: 0:02:22 lr: 0.000108 loss: 3.0204 (2.9011) grad_norm: 2.4289 (2.5261) time: 0.5112 [2021-03-26 23:19:32 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 980/1251] eta: 0:02:17 lr: 0.000108 loss: 3.0204 (2.9021) grad_norm: 2.3755 (2.5244) time: 0.5090 [2021-03-26 23:19:37 swin_small_patch4_window7_224] INFO: Epoch: [238] [ 990/1251] eta: 0:02:12 lr: 0.000108 loss: 3.0631 (2.9025) grad_norm: 2.3074 (2.5218) time: 0.5012 [2021-03-26 23:19:42 swin_small_patch4_window7_224] INFO: Epoch: [238] [1000/1251] eta: 0:02:07 lr: 0.000108 loss: 3.0074 (2.9012) grad_norm: 2.2368 (2.5202) time: 0.5044 [2021-03-26 23:19:47 swin_small_patch4_window7_224] INFO: Epoch: [238] [1010/1251] eta: 0:02:02 lr: 0.000108 loss: 3.0758 (2.9023) grad_norm: 2.3799 (2.5222) time: 0.5019 [2021-03-26 23:19:53 swin_small_patch4_window7_224] INFO: Epoch: [238] [1020/1251] eta: 0:01:57 lr: 0.000108 loss: 3.0994 (2.9041) grad_norm: 2.3799 (2.5213) time: 0.5022 [2021-03-26 23:19:58 swin_small_patch4_window7_224] INFO: Epoch: [238] [1030/1251] eta: 0:01:52 lr: 0.000108 loss: 3.0994 (2.9051) grad_norm: 2.3073 (2.5194) time: 0.5045 [2021-03-26 23:20:03 swin_small_patch4_window7_224] INFO: Epoch: [238] [1040/1251] eta: 0:01:46 lr: 0.000108 loss: 3.0058 (2.9043) grad_norm: 2.3932 (2.5209) time: 0.5039 [2021-03-26 23:20:08 swin_small_patch4_window7_224] INFO: Epoch: [238] [1050/1251] eta: 0:01:41 lr: 0.000108 loss: 2.9713 (2.9048) grad_norm: 2.5880 (2.5211) time: 0.5031 [2021-03-26 23:20:13 swin_small_patch4_window7_224] INFO: Epoch: [238] [1060/1251] eta: 0:01:36 lr: 0.000108 loss: 2.9205 (2.9030) grad_norm: 2.4448 (2.5212) time: 0.5053 [2021-03-26 23:20:18 swin_small_patch4_window7_224] INFO: Epoch: [238] [1070/1251] eta: 0:01:31 lr: 0.000108 loss: 2.9205 (2.9028) grad_norm: 2.3928 (2.5199) time: 0.5090 [2021-03-26 23:20:23 swin_small_patch4_window7_224] INFO: Epoch: [238] [1080/1251] eta: 0:01:26 lr: 0.000108 loss: 3.1213 (2.9054) grad_norm: 2.4258 (2.5201) time: 0.5037 [2021-03-26 23:20:28 swin_small_patch4_window7_224] INFO: Epoch: [238] [1090/1251] eta: 0:01:21 lr: 0.000108 loss: 2.8916 (2.9021) grad_norm: 2.4856 (2.5199) time: 0.4968 [2021-03-26 23:20:33 swin_small_patch4_window7_224] INFO: Epoch: [238] [1100/1251] eta: 0:01:16 lr: 0.000108 loss: 2.6960 (2.9027) grad_norm: 2.4797 (2.5209) time: 0.5026 [2021-03-26 23:20:38 swin_small_patch4_window7_224] INFO: Epoch: [238] [1110/1251] eta: 0:01:11 lr: 0.000108 loss: 2.8725 (2.9010) grad_norm: 2.5065 (2.5213) time: 0.5076 [2021-03-26 23:20:43 swin_small_patch4_window7_224] INFO: Epoch: [238] [1120/1251] eta: 0:01:06 lr: 0.000108 loss: 2.7547 (2.9011) grad_norm: 2.4800 (2.5203) time: 0.4990 [2021-03-26 23:20:48 swin_small_patch4_window7_224] INFO: Epoch: [238] [1130/1251] eta: 0:01:01 lr: 0.000108 loss: 2.8721 (2.9007) grad_norm: 2.4450 (2.5202) time: 0.4983 [2021-03-26 23:20:53 swin_small_patch4_window7_224] INFO: Epoch: [238] [1140/1251] eta: 0:00:56 lr: 0.000108 loss: 2.8706 (2.8994) grad_norm: 2.4594 (2.5204) time: 0.5037 [2021-03-26 23:20:58 swin_small_patch4_window7_224] INFO: Epoch: [238] [1150/1251] eta: 0:00:51 lr: 0.000108 loss: 2.9640 (2.9003) grad_norm: 2.3600 (2.5190) time: 0.5015 [2021-03-26 23:21:03 swin_small_patch4_window7_224] INFO: Epoch: [238] [1160/1251] eta: 0:00:46 lr: 0.000108 loss: 3.0843 (2.9022) grad_norm: 2.3284 (2.5180) time: 0.5014 [2021-03-26 23:21:08 swin_small_patch4_window7_224] INFO: Epoch: [238] [1170/1251] eta: 0:00:41 lr: 0.000108 loss: 2.9852 (2.9005) grad_norm: 2.4514 (2.5183) time: 0.5058 [2021-03-26 23:21:13 swin_small_patch4_window7_224] INFO: Epoch: [238] [1180/1251] eta: 0:00:35 lr: 0.000108 loss: 2.8072 (2.8989) grad_norm: 2.5300 (2.5190) time: 0.5036 [2021-03-26 23:21:18 swin_small_patch4_window7_224] INFO: Epoch: [238] [1190/1251] eta: 0:00:30 lr: 0.000108 loss: 2.8729 (2.8997) grad_norm: 2.5300 (2.5210) time: 0.5011 [2021-03-26 23:21:23 swin_small_patch4_window7_224] INFO: Epoch: [238] [1200/1251] eta: 0:00:25 lr: 0.000108 loss: 3.0202 (2.9000) grad_norm: 2.4482 (2.5212) time: 0.5043 [2021-03-26 23:21:28 swin_small_patch4_window7_224] INFO: Epoch: [238] [1210/1251] eta: 0:00:20 lr: 0.000108 loss: 2.8645 (2.8992) grad_norm: 2.4482 (2.5239) time: 0.5039 [2021-03-26 23:21:33 swin_small_patch4_window7_224] INFO: Epoch: [238] [1220/1251] eta: 0:00:15 lr: 0.000108 loss: 2.6876 (2.8973) grad_norm: 2.4556 (2.5234) time: 0.5048 [2021-03-26 23:21:38 swin_small_patch4_window7_224] INFO: Epoch: [238] [1230/1251] eta: 0:00:10 lr: 0.000108 loss: 2.7813 (2.8960) grad_norm: 2.4934 (2.5247) time: 0.5083 [2021-03-26 23:21:43 swin_small_patch4_window7_224] INFO: Epoch: [238] [1240/1251] eta: 0:00:05 lr: 0.000108 loss: 2.9521 (2.8962) grad_norm: 2.4993 (2.5244) time: 0.5047 [2021-03-26 23:21:48 swin_small_patch4_window7_224] INFO: Epoch: [238] [1250/1251] eta: 0:00:00 lr: 0.000108 loss: 3.0726 (2.8971) grad_norm: 2.4653 (2.5250) time: 0.4943 [2021-03-26 23:22:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 0.6533 (0.6533) acc1: 87.5000 (87.5000) acc5: 95.3125 (95.3125) [2021-03-26 23:22:03 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7179 (0.7892) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.1648) [2021-03-26 23:22:05 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7826 (0.7898) acc1: 81.2500 (82.3661) acc5: 96.8750 (96.2054) [2021-03-26 23:22:08 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7559 (0.7787) acc1: 81.2500 (81.9052) acc5: 96.8750 (96.2198) [2021-03-26 23:22:09 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7687 (0.7875) acc1: 81.2500 (81.5549) acc5: 95.3125 (96.0366) [2021-03-26 23:22:10 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7564 (0.7736) acc1: 81.2500 (81.8880) acc5: 95.3125 (96.0320) [2021-03-26 23:22:24 swin_small_patch4_window7_224] INFO: * Acc@1 82.048 Acc@5 95.946 loss 0.770 [2021-03-26 23:22:24 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.0% [2021-03-26 23:22:24 swin_small_patch4_window7_224] INFO: Max accuracy: 82.05% [2021-03-26 23:22:28 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 0/1251] eta: 1:23:48 lr: 0.000108 loss: 3.0635 (3.0635) grad_norm: 2.6343 (2.6343) time: 4.0195 [2021-03-26 23:22:34 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 10/1251] eta: 0:17:33 lr: 0.000108 loss: 2.8558 (2.8459) grad_norm: 2.5302 (2.4873) time: 0.8491 [2021-03-26 23:22:39 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 20/1251] eta: 0:14:07 lr: 0.000108 loss: 2.8558 (2.7774) grad_norm: 2.3869 (2.5695) time: 0.5215 [2021-03-26 23:22:44 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 30/1251] eta: 0:12:49 lr: 0.000108 loss: 2.7927 (2.6927) grad_norm: 2.3690 (2.5180) time: 0.5094 [2021-03-26 23:22:49 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 40/1251] eta: 0:12:03 lr: 0.000108 loss: 2.8276 (2.7407) grad_norm: 2.3797 (2.4827) time: 0.5021 [2021-03-26 23:22:54 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 50/1251] eta: 0:11:37 lr: 0.000107 loss: 3.1474 (2.8181) grad_norm: 2.3669 (2.4687) time: 0.5036 [2021-03-26 23:22:59 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 60/1251] eta: 0:11:17 lr: 0.000107 loss: 3.1817 (2.8219) grad_norm: 2.3958 (2.4680) time: 0.5100 [2021-03-26 23:23:04 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 70/1251] eta: 0:11:00 lr: 0.000107 loss: 2.7853 (2.8155) grad_norm: 2.3891 (2.4602) time: 0.5062 [2021-03-26 23:23:09 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 80/1251] eta: 0:10:46 lr: 0.000107 loss: 2.6829 (2.8038) grad_norm: 2.4843 (2.4702) time: 0.5005 [2021-03-26 23:23:14 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 90/1251] eta: 0:10:37 lr: 0.000107 loss: 2.9344 (2.8054) grad_norm: 2.5198 (2.4731) time: 0.5111 [2021-03-26 23:23:19 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 100/1251] eta: 0:10:26 lr: 0.000107 loss: 2.8200 (2.8082) grad_norm: 2.3885 (2.4606) time: 0.5153 [2021-03-26 23:23:24 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 110/1251] eta: 0:10:17 lr: 0.000107 loss: 2.8200 (2.8068) grad_norm: 2.3487 (2.4664) time: 0.5072 [2021-03-26 23:23:29 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 120/1251] eta: 0:10:07 lr: 0.000107 loss: 2.9354 (2.8108) grad_norm: 2.4934 (2.4800) time: 0.5005 [2021-03-26 23:23:34 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 130/1251] eta: 0:09:59 lr: 0.000107 loss: 3.0040 (2.8334) grad_norm: 2.4926 (2.4867) time: 0.4979 [2021-03-26 23:23:39 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 140/1251] eta: 0:09:51 lr: 0.000107 loss: 3.0366 (2.8355) grad_norm: 2.4542 (2.4791) time: 0.5014 [2021-03-26 23:23:44 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 150/1251] eta: 0:09:43 lr: 0.000107 loss: 2.9726 (2.8530) grad_norm: 2.4651 (2.4785) time: 0.5003 [2021-03-26 23:23:49 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 160/1251] eta: 0:09:36 lr: 0.000107 loss: 2.9450 (2.8522) grad_norm: 2.4010 (2.4803) time: 0.5040 [2021-03-26 23:23:54 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 170/1251] eta: 0:09:29 lr: 0.000107 loss: 3.0015 (2.8627) grad_norm: 2.3359 (2.4767) time: 0.5048 [2021-03-26 23:24:00 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 180/1251] eta: 0:09:23 lr: 0.000107 loss: 3.1125 (2.8642) grad_norm: 2.3337 (2.4736) time: 0.5096 [2021-03-26 23:24:05 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 190/1251] eta: 0:09:17 lr: 0.000107 loss: 3.1016 (2.8717) grad_norm: 2.4242 (2.4748) time: 0.5096 [2021-03-26 23:24:10 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 200/1251] eta: 0:09:12 lr: 0.000107 loss: 3.1702 (2.8826) grad_norm: 2.5612 (2.4824) time: 0.5159 [2021-03-26 23:24:15 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 210/1251] eta: 0:09:05 lr: 0.000107 loss: 3.1560 (2.8833) grad_norm: 2.6496 (2.4888) time: 0.5145 [2021-03-26 23:24:20 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 220/1251] eta: 0:08:59 lr: 0.000107 loss: 3.0158 (2.8885) grad_norm: 2.6444 (2.4995) time: 0.4993 [2021-03-26 23:24:25 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 230/1251] eta: 0:08:53 lr: 0.000107 loss: 2.9917 (2.8879) grad_norm: 2.4232 (2.4997) time: 0.5059 [2021-03-26 23:24:30 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 240/1251] eta: 0:08:47 lr: 0.000107 loss: 2.9237 (2.8915) grad_norm: 2.4231 (2.5024) time: 0.5110 [2021-03-26 23:24:35 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 250/1251] eta: 0:08:41 lr: 0.000107 loss: 2.9234 (2.8890) grad_norm: 2.3510 (2.4964) time: 0.5070 [2021-03-26 23:24:40 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 260/1251] eta: 0:08:35 lr: 0.000107 loss: 2.8212 (2.8819) grad_norm: 2.3510 (2.4931) time: 0.5010 [2021-03-26 23:24:45 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 270/1251] eta: 0:08:29 lr: 0.000107 loss: 2.7632 (2.8744) grad_norm: 2.4665 (2.4968) time: 0.4966 [2021-03-26 23:24:50 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 280/1251] eta: 0:08:23 lr: 0.000107 loss: 2.8469 (2.8828) grad_norm: 2.5073 (2.5060) time: 0.4984 [2021-03-26 23:24:55 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 290/1251] eta: 0:08:18 lr: 0.000107 loss: 3.0720 (2.8848) grad_norm: 2.5692 (2.5103) time: 0.5035 [2021-03-26 23:25:00 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 300/1251] eta: 0:08:12 lr: 0.000107 loss: 2.9304 (2.8811) grad_norm: 2.4090 (2.5081) time: 0.5045 [2021-03-26 23:25:05 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 310/1251] eta: 0:08:06 lr: 0.000107 loss: 2.9476 (2.8831) grad_norm: 2.3567 (2.5081) time: 0.5018 [2021-03-26 23:25:10 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 320/1251] eta: 0:08:00 lr: 0.000107 loss: 2.9873 (2.8843) grad_norm: 2.3807 (2.5032) time: 0.4948 [2021-03-26 23:25:15 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 330/1251] eta: 0:07:55 lr: 0.000107 loss: 2.9477 (2.8886) grad_norm: 2.3807 (2.5025) time: 0.4974 [2021-03-26 23:25:20 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 340/1251] eta: 0:07:49 lr: 0.000107 loss: 3.0205 (2.8890) grad_norm: 2.4375 (2.5009) time: 0.5027 [2021-03-26 23:25:25 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 350/1251] eta: 0:07:44 lr: 0.000107 loss: 3.0197 (2.8900) grad_norm: 2.4199 (2.5052) time: 0.5042 [2021-03-26 23:25:30 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 360/1251] eta: 0:07:38 lr: 0.000107 loss: 3.0197 (2.8927) grad_norm: 2.6761 (2.5129) time: 0.5044 [2021-03-26 23:25:35 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 370/1251] eta: 0:07:33 lr: 0.000107 loss: 2.9868 (2.8889) grad_norm: 2.4773 (2.5111) time: 0.4984 [2021-03-26 23:25:40 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 380/1251] eta: 0:07:27 lr: 0.000107 loss: 2.8805 (2.8896) grad_norm: 2.4230 (2.5198) time: 0.4968 [2021-03-26 23:25:45 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 390/1251] eta: 0:07:22 lr: 0.000107 loss: 2.8953 (2.8901) grad_norm: 2.5288 (2.5221) time: 0.4942 [2021-03-26 23:25:50 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 400/1251] eta: 0:07:16 lr: 0.000107 loss: 3.0300 (2.8972) grad_norm: 2.5876 (2.5248) time: 0.4927 [2021-03-26 23:25:55 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 410/1251] eta: 0:07:11 lr: 0.000107 loss: 3.0300 (2.8980) grad_norm: 2.5112 (2.5255) time: 0.4967 [2021-03-26 23:26:00 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 420/1251] eta: 0:07:06 lr: 0.000107 loss: 2.8925 (2.8917) grad_norm: 2.2940 (2.5218) time: 0.5053 [2021-03-26 23:26:05 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 430/1251] eta: 0:07:00 lr: 0.000107 loss: 2.8925 (2.8915) grad_norm: 2.3364 (2.5213) time: 0.5035 [2021-03-26 23:26:10 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 440/1251] eta: 0:06:55 lr: 0.000107 loss: 2.9710 (2.8906) grad_norm: 2.4426 (2.5214) time: 0.4969 [2021-03-26 23:26:15 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 450/1251] eta: 0:06:50 lr: 0.000106 loss: 2.9710 (2.8904) grad_norm: 2.4605 (2.5217) time: 0.5049 [2021-03-26 23:26:20 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 460/1251] eta: 0:06:44 lr: 0.000106 loss: 3.1690 (2.8973) grad_norm: 2.4605 (2.5230) time: 0.5074 [2021-03-26 23:26:25 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 470/1251] eta: 0:06:39 lr: 0.000106 loss: 3.1109 (2.8997) grad_norm: 2.4974 (2.5222) time: 0.5043 [2021-03-26 23:26:30 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 480/1251] eta: 0:06:34 lr: 0.000106 loss: 2.8090 (2.8904) grad_norm: 2.5725 (2.5249) time: 0.4984 [2021-03-26 23:26:35 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 490/1251] eta: 0:06:28 lr: 0.000106 loss: 2.7668 (2.8894) grad_norm: 2.5919 (2.5278) time: 0.4946 [2021-03-26 23:26:40 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 500/1251] eta: 0:06:23 lr: 0.000106 loss: 3.0165 (2.8911) grad_norm: 2.5354 (2.5274) time: 0.4984 [2021-03-26 23:26:45 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 510/1251] eta: 0:06:18 lr: 0.000106 loss: 2.8770 (2.8916) grad_norm: 2.4520 (2.5251) time: 0.5007 [2021-03-26 23:26:50 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 520/1251] eta: 0:06:13 lr: 0.000106 loss: 2.9727 (2.8917) grad_norm: 2.4618 (2.5281) time: 0.5008 [2021-03-26 23:26:55 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 530/1251] eta: 0:06:07 lr: 0.000106 loss: 2.9577 (2.8909) grad_norm: 2.5494 (nan) time: 0.4944 [2021-03-26 23:27:00 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 540/1251] eta: 0:06:02 lr: 0.000106 loss: 2.7688 (2.8862) grad_norm: 2.4695 (nan) time: 0.4986 [2021-03-26 23:27:05 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 550/1251] eta: 0:05:57 lr: 0.000106 loss: 2.7866 (2.8867) grad_norm: 2.4913 (nan) time: 0.5159 [2021-03-26 23:27:10 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 560/1251] eta: 0:05:52 lr: 0.000106 loss: 3.1278 (2.8908) grad_norm: 2.4796 (nan) time: 0.5091 [2021-03-26 23:27:15 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 570/1251] eta: 0:05:47 lr: 0.000106 loss: 3.1340 (2.8912) grad_norm: 2.4796 (nan) time: 0.5035 [2021-03-26 23:27:20 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 580/1251] eta: 0:05:42 lr: 0.000106 loss: 2.9387 (2.8881) grad_norm: 2.4139 (nan) time: 0.5068 [2021-03-26 23:27:25 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 590/1251] eta: 0:05:36 lr: 0.000106 loss: 2.9387 (2.8879) grad_norm: 2.4344 (nan) time: 0.4967 [2021-03-26 23:27:31 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 600/1251] eta: 0:05:31 lr: 0.000106 loss: 3.0657 (2.8946) grad_norm: 2.5078 (nan) time: 0.5047 [2021-03-26 23:27:35 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 610/1251] eta: 0:05:26 lr: 0.000106 loss: 3.0858 (2.8969) grad_norm: 2.4342 (nan) time: 0.5036 [2021-03-26 23:27:41 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 620/1251] eta: 0:05:21 lr: 0.000106 loss: 3.0300 (2.8984) grad_norm: 2.3677 (nan) time: 0.4989 [2021-03-26 23:27:46 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 630/1251] eta: 0:05:16 lr: 0.000106 loss: 2.8074 (2.8925) grad_norm: 2.4321 (nan) time: 0.5031 [2021-03-26 23:27:51 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 640/1251] eta: 0:05:11 lr: 0.000106 loss: 2.6301 (2.8914) grad_norm: 2.4447 (nan) time: 0.5059 [2021-03-26 23:27:56 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 650/1251] eta: 0:05:05 lr: 0.000106 loss: 3.0113 (2.8942) grad_norm: 2.4634 (nan) time: 0.5048 [2021-03-26 23:28:01 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 660/1251] eta: 0:05:00 lr: 0.000106 loss: 3.1338 (2.8960) grad_norm: 2.3493 (nan) time: 0.4955 [2021-03-26 23:28:06 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 670/1251] eta: 0:04:55 lr: 0.000106 loss: 2.8573 (2.8922) grad_norm: 2.2656 (nan) time: 0.4945 [2021-03-26 23:28:11 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 680/1251] eta: 0:04:50 lr: 0.000106 loss: 2.7690 (2.8906) grad_norm: 2.5099 (nan) time: 0.4979 [2021-03-26 23:28:15 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 690/1251] eta: 0:04:45 lr: 0.000106 loss: 2.8730 (2.8909) grad_norm: 2.5045 (nan) time: 0.4970 [2021-03-26 23:28:20 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 700/1251] eta: 0:04:39 lr: 0.000106 loss: 3.0263 (2.8930) grad_norm: 2.4102 (nan) time: 0.4942 [2021-03-26 23:28:25 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 710/1251] eta: 0:04:34 lr: 0.000106 loss: 2.9763 (2.8916) grad_norm: 2.3687 (nan) time: 0.5012 [2021-03-26 23:28:30 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 720/1251] eta: 0:04:29 lr: 0.000106 loss: 2.9380 (2.8921) grad_norm: 2.3773 (nan) time: 0.5026 [2021-03-26 23:28:35 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 730/1251] eta: 0:04:24 lr: 0.000106 loss: 2.9380 (2.8917) grad_norm: 2.4248 (nan) time: 0.5005 [2021-03-26 23:28:41 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 740/1251] eta: 0:04:19 lr: 0.000106 loss: 2.7570 (2.8910) grad_norm: 2.4251 (nan) time: 0.5145 [2021-03-26 23:28:46 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 750/1251] eta: 0:04:14 lr: 0.000106 loss: 2.9638 (2.8922) grad_norm: 2.3942 (nan) time: 0.5223 [2021-03-26 23:28:51 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 760/1251] eta: 0:04:09 lr: 0.000106 loss: 3.2431 (2.8951) grad_norm: 2.4384 (nan) time: 0.5161 [2021-03-26 23:28:56 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 770/1251] eta: 0:04:04 lr: 0.000106 loss: 3.1250 (2.8973) grad_norm: 2.5654 (nan) time: 0.5105 [2021-03-26 23:29:01 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 780/1251] eta: 0:03:59 lr: 0.000106 loss: 3.0655 (2.8970) grad_norm: 2.5548 (nan) time: 0.5034 [2021-03-26 23:29:06 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 790/1251] eta: 0:03:54 lr: 0.000106 loss: 2.9055 (2.8977) grad_norm: 2.5165 (nan) time: 0.5014 [2021-03-26 23:29:11 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 800/1251] eta: 0:03:49 lr: 0.000106 loss: 2.7722 (2.8934) grad_norm: 2.5165 (nan) time: 0.5076 [2021-03-26 23:29:16 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 810/1251] eta: 0:03:44 lr: 0.000106 loss: 2.7910 (2.8924) grad_norm: 2.4972 (nan) time: 0.5067 [2021-03-26 23:29:21 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 820/1251] eta: 0:03:39 lr: 0.000106 loss: 2.8560 (2.8895) grad_norm: 2.4849 (nan) time: 0.5082 [2021-03-26 23:29:27 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 830/1251] eta: 0:03:33 lr: 0.000106 loss: 2.9707 (2.8914) grad_norm: 2.3747 (nan) time: 0.5185 [2021-03-26 23:29:32 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 840/1251] eta: 0:03:28 lr: 0.000106 loss: 3.0167 (2.8918) grad_norm: 2.3766 (nan) time: 0.5211 [2021-03-26 23:29:37 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 850/1251] eta: 0:03:23 lr: 0.000106 loss: 2.9998 (2.8921) grad_norm: 2.4685 (nan) time: 0.5126 [2021-03-26 23:29:42 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 860/1251] eta: 0:03:18 lr: 0.000105 loss: 2.8513 (2.8891) grad_norm: 2.3991 (nan) time: 0.5047 [2021-03-26 23:29:47 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 870/1251] eta: 0:03:13 lr: 0.000105 loss: 2.8468 (2.8884) grad_norm: 2.3659 (nan) time: 0.5019 [2021-03-26 23:29:52 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 880/1251] eta: 0:03:08 lr: 0.000105 loss: 2.9448 (2.8889) grad_norm: 2.3911 (nan) time: 0.5026 [2021-03-26 23:29:57 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 890/1251] eta: 0:03:03 lr: 0.000105 loss: 3.0493 (2.8901) grad_norm: 2.3229 (nan) time: 0.5062 [2021-03-26 23:30:02 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 900/1251] eta: 0:02:58 lr: 0.000105 loss: 2.9185 (2.8875) grad_norm: 2.4126 (nan) time: 0.5092 [2021-03-26 23:30:07 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 910/1251] eta: 0:02:53 lr: 0.000105 loss: 2.8389 (2.8870) grad_norm: 2.4001 (nan) time: 0.5071 [2021-03-26 23:30:12 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 920/1251] eta: 0:02:48 lr: 0.000105 loss: 2.9126 (2.8864) grad_norm: 2.4105 (nan) time: 0.5021 [2021-03-26 23:30:17 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 930/1251] eta: 0:02:43 lr: 0.000105 loss: 2.7743 (2.8842) grad_norm: 2.5733 (nan) time: 0.5007 [2021-03-26 23:30:22 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 940/1251] eta: 0:02:37 lr: 0.000105 loss: 2.8597 (2.8846) grad_norm: 2.4578 (nan) time: 0.5021 [2021-03-26 23:30:27 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 950/1251] eta: 0:02:32 lr: 0.000105 loss: 2.8083 (2.8826) grad_norm: 2.3596 (nan) time: 0.5067 [2021-03-26 23:30:32 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 960/1251] eta: 0:02:27 lr: 0.000105 loss: 2.7457 (2.8822) grad_norm: 2.4238 (nan) time: 0.5081 [2021-03-26 23:30:38 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 970/1251] eta: 0:02:22 lr: 0.000105 loss: 2.8185 (2.8809) grad_norm: 2.4600 (nan) time: 0.5078 [2021-03-26 23:30:43 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 980/1251] eta: 0:02:17 lr: 0.000105 loss: 2.6052 (2.8775) grad_norm: 2.4797 (nan) time: 0.5031 [2021-03-26 23:30:48 swin_small_patch4_window7_224] INFO: Epoch: [239] [ 990/1251] eta: 0:02:12 lr: 0.000105 loss: 2.3917 (2.8740) grad_norm: 2.4511 (nan) time: 0.4963 [2021-03-26 23:30:53 swin_small_patch4_window7_224] INFO: Epoch: [239] [1000/1251] eta: 0:02:07 lr: 0.000105 loss: 2.7304 (2.8751) grad_norm: 2.4271 (nan) time: 0.4993 [2021-03-26 23:30:58 swin_small_patch4_window7_224] INFO: Epoch: [239] [1010/1251] eta: 0:02:02 lr: 0.000105 loss: 2.9512 (2.8763) grad_norm: 2.3641 (nan) time: 0.5045 [2021-03-26 23:31:03 swin_small_patch4_window7_224] INFO: Epoch: [239] [1020/1251] eta: 0:01:57 lr: 0.000105 loss: 3.0217 (2.8752) grad_norm: 2.3413 (nan) time: 0.5009 [2021-03-26 23:31:08 swin_small_patch4_window7_224] INFO: Epoch: [239] [1030/1251] eta: 0:01:52 lr: 0.000105 loss: 2.9493 (2.8740) grad_norm: 2.3588 (nan) time: 0.4957 [2021-03-26 23:31:13 swin_small_patch4_window7_224] INFO: Epoch: [239] [1040/1251] eta: 0:01:47 lr: 0.000105 loss: 3.0138 (2.8760) grad_norm: 2.4284 (nan) time: 0.4988 [2021-03-26 23:31:18 swin_small_patch4_window7_224] INFO: Epoch: [239] [1050/1251] eta: 0:01:41 lr: 0.000105 loss: 2.9821 (2.8747) grad_norm: 2.3888 (nan) time: 0.5037 [2021-03-26 23:31:23 swin_small_patch4_window7_224] INFO: Epoch: [239] [1060/1251] eta: 0:01:36 lr: 0.000105 loss: 2.9821 (2.8761) grad_norm: 2.3888 (nan) time: 0.4991 [2021-03-26 23:31:28 swin_small_patch4_window7_224] INFO: Epoch: [239] [1070/1251] eta: 0:01:31 lr: 0.000105 loss: 3.1844 (2.8764) grad_norm: 2.3308 (nan) time: 0.4993 [2021-03-26 23:31:33 swin_small_patch4_window7_224] INFO: Epoch: [239] [1080/1251] eta: 0:01:26 lr: 0.000105 loss: 3.0970 (2.8759) grad_norm: 2.4233 (nan) time: 0.5038 [2021-03-26 23:31:38 swin_small_patch4_window7_224] INFO: Epoch: [239] [1090/1251] eta: 0:01:21 lr: 0.000105 loss: 2.9265 (2.8745) grad_norm: 2.4233 (nan) time: 0.5005 [2021-03-26 23:31:43 swin_small_patch4_window7_224] INFO: Epoch: [239] [1100/1251] eta: 0:01:16 lr: 0.000105 loss: 2.9265 (2.8755) grad_norm: 2.5563 (nan) time: 0.5058 [2021-03-26 23:31:48 swin_small_patch4_window7_224] INFO: Epoch: [239] [1110/1251] eta: 0:01:11 lr: 0.000105 loss: 3.0652 (2.8763) grad_norm: 2.5581 (nan) time: 0.5066 [2021-03-26 23:31:53 swin_small_patch4_window7_224] INFO: Epoch: [239] [1120/1251] eta: 0:01:06 lr: 0.000105 loss: 3.1165 (2.8791) grad_norm: 2.2814 (nan) time: 0.4993 [2021-03-26 23:31:58 swin_small_patch4_window7_224] INFO: Epoch: [239] [1130/1251] eta: 0:01:01 lr: 0.000105 loss: 3.0793 (2.8798) grad_norm: 2.4023 (nan) time: 0.4991 [2021-03-26 23:32:03 swin_small_patch4_window7_224] INFO: Epoch: [239] [1140/1251] eta: 0:00:56 lr: 0.000105 loss: 3.0793 (2.8816) grad_norm: 2.4617 (nan) time: 0.5009 [2021-03-26 23:32:08 swin_small_patch4_window7_224] INFO: Epoch: [239] [1150/1251] eta: 0:00:51 lr: 0.000105 loss: 3.1605 (2.8822) grad_norm: 2.4869 (nan) time: 0.5041 [2021-03-26 23:32:13 swin_small_patch4_window7_224] INFO: Epoch: [239] [1160/1251] eta: 0:00:46 lr: 0.000105 loss: 3.0653 (2.8829) grad_norm: 2.4415 (nan) time: 0.5056 [2021-03-26 23:32:18 swin_small_patch4_window7_224] INFO: Epoch: [239] [1170/1251] eta: 0:00:41 lr: 0.000105 loss: 2.9141 (2.8810) grad_norm: 2.3348 (nan) time: 0.5050 [2021-03-26 23:32:23 swin_small_patch4_window7_224] INFO: Epoch: [239] [1180/1251] eta: 0:00:35 lr: 0.000105 loss: 2.8480 (2.8815) grad_norm: 2.3277 (nan) time: 0.4997 [2021-03-26 23:32:28 swin_small_patch4_window7_224] INFO: Epoch: [239] [1190/1251] eta: 0:00:30 lr: 0.000105 loss: 3.0373 (2.8816) grad_norm: 2.4102 (nan) time: 0.4966 [2021-03-26 23:32:33 swin_small_patch4_window7_224] INFO: Epoch: [239] [1200/1251] eta: 0:00:25 lr: 0.000105 loss: 2.9719 (2.8819) grad_norm: 2.4826 (nan) time: 0.4982 [2021-03-26 23:32:38 swin_small_patch4_window7_224] INFO: Epoch: [239] [1210/1251] eta: 0:00:20 lr: 0.000105 loss: 2.8876 (2.8817) grad_norm: 2.3879 (nan) time: 0.4975 [2021-03-26 23:32:43 swin_small_patch4_window7_224] INFO: Epoch: [239] [1220/1251] eta: 0:00:15 lr: 0.000105 loss: 2.9980 (2.8816) grad_norm: 2.3207 (nan) time: 0.4984 [2021-03-26 23:32:48 swin_small_patch4_window7_224] INFO: Epoch: [239] [1230/1251] eta: 0:00:10 lr: 0.000105 loss: 2.9941 (2.8814) grad_norm: 2.3534 (nan) time: 0.5047 [2021-03-26 23:32:53 swin_small_patch4_window7_224] INFO: Epoch: [239] [1240/1251] eta: 0:00:05 lr: 0.000105 loss: 3.0054 (2.8825) grad_norm: 2.4929 (nan) time: 0.5080 [2021-03-26 23:32:58 swin_small_patch4_window7_224] INFO: Epoch: [239] [1250/1251] eta: 0:00:00 lr: 0.000105 loss: 3.0054 (2.8821) grad_norm: 2.6079 (nan) time: 0.5083 [2021-03-26 23:33:05 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 0.6244 (0.6244) acc1: 85.9375 (85.9375) acc5: 95.3125 (95.3125) [2021-03-26 23:33:09 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9000 (0.8750) acc1: 78.1250 (79.1193) acc5: 95.3125 (95.0284) [2021-03-26 23:33:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8364 (0.8340) acc1: 79.6875 (80.2827) acc5: 95.3125 (95.2381) [2021-03-26 23:33:14 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7105 (0.8038) acc1: 82.8125 (81.3004) acc5: 95.3125 (95.5141) [2021-03-26 23:33:16 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7105 (0.7890) acc1: 81.2500 (81.0213) acc5: 95.3125 (95.5793) [2021-03-26 23:33:16 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6950 (0.7863) acc1: 81.2500 (81.0240) acc5: 96.8750 (95.8400) [2021-03-26 23:33:27 swin_small_patch4_window7_224] INFO: * Acc@1 81.908 Acc@5 95.924 loss 0.770 [2021-03-26 23:33:27 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 81.9% [2021-03-26 23:33:27 swin_small_patch4_window7_224] INFO: Max accuracy: 82.05% [2021-03-26 23:33:31 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 0/1251] eta: 1:25:11 lr: 0.000105 loss: 2.2004 (2.2004) grad_norm: 2.6477 (2.6477) time: 4.0858 [2021-03-26 23:33:36 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 10/1251] eta: 0:17:22 lr: 0.000105 loss: 2.5718 (2.6549) grad_norm: 2.5208 (2.5750) time: 0.8397 [2021-03-26 23:33:41 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 20/1251] eta: 0:13:58 lr: 0.000104 loss: 2.9656 (2.8367) grad_norm: 2.5001 (2.5205) time: 0.5110 [2021-03-26 23:33:47 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 30/1251] eta: 0:12:45 lr: 0.000104 loss: 2.9997 (2.8386) grad_norm: 2.5038 (2.5437) time: 0.5102 [2021-03-26 23:33:52 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 40/1251] eta: 0:12:04 lr: 0.000104 loss: 2.9560 (2.8333) grad_norm: 2.4627 (2.5313) time: 0.5108 [2021-03-26 23:33:57 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 50/1251] eta: 0:11:37 lr: 0.000104 loss: 2.9560 (2.8180) grad_norm: 2.4305 (2.5402) time: 0.5094 [2021-03-26 23:34:02 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 60/1251] eta: 0:11:15 lr: 0.000104 loss: 2.9369 (2.8354) grad_norm: 2.4120 (2.5366) time: 0.5044 [2021-03-26 23:34:07 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 70/1251] eta: 0:10:59 lr: 0.000104 loss: 2.9742 (2.8588) grad_norm: 2.4427 (2.7391) time: 0.5009 [2021-03-26 23:34:12 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 80/1251] eta: 0:10:47 lr: 0.000104 loss: 3.0102 (2.8624) grad_norm: 2.4854 (2.7263) time: 0.5101 [2021-03-26 23:34:17 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 90/1251] eta: 0:10:35 lr: 0.000104 loss: 2.8955 (2.8607) grad_norm: 2.4680 (2.7038) time: 0.5064 [2021-03-26 23:34:22 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 100/1251] eta: 0:10:25 lr: 0.000104 loss: 2.7782 (2.8632) grad_norm: 2.4993 (2.7047) time: 0.5024 [2021-03-26 23:34:27 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 110/1251] eta: 0:10:14 lr: 0.000104 loss: 2.8734 (2.8642) grad_norm: 2.8005 (2.7202) time: 0.5005 [2021-03-26 23:34:32 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 120/1251] eta: 0:10:06 lr: 0.000104 loss: 2.8734 (2.8723) grad_norm: 2.7264 (2.7437) time: 0.4989 [2021-03-26 23:34:37 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 130/1251] eta: 0:09:58 lr: 0.000104 loss: 2.8545 (2.8704) grad_norm: 2.5506 (2.7616) time: 0.5105 [2021-03-26 23:34:42 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 140/1251] eta: 0:09:52 lr: 0.000104 loss: 2.9527 (2.8752) grad_norm: 2.3785 (2.7494) time: 0.5158 [2021-03-26 23:34:47 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 150/1251] eta: 0:09:44 lr: 0.000104 loss: 3.0495 (2.8713) grad_norm: 2.4653 (2.7395) time: 0.5095 [2021-03-26 23:34:52 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 160/1251] eta: 0:09:37 lr: 0.000104 loss: 2.8698 (2.8678) grad_norm: 2.4806 (2.7280) time: 0.5014 [2021-03-26 23:34:57 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 170/1251] eta: 0:09:29 lr: 0.000104 loss: 2.6733 (2.8622) grad_norm: 2.6329 (2.7367) time: 0.4981 [2021-03-26 23:35:02 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 180/1251] eta: 0:09:22 lr: 0.000104 loss: 2.6334 (2.8523) grad_norm: 2.5646 (2.7220) time: 0.4975 [2021-03-26 23:35:07 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 190/1251] eta: 0:09:16 lr: 0.000104 loss: 2.4680 (2.8370) grad_norm: 2.4756 (2.7172) time: 0.5061 [2021-03-26 23:35:12 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 200/1251] eta: 0:09:10 lr: 0.000104 loss: 2.9248 (2.8456) grad_norm: 2.4859 (2.7137) time: 0.5085 [2021-03-26 23:35:18 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 210/1251] eta: 0:09:04 lr: 0.000104 loss: 3.0601 (2.8400) grad_norm: 2.4023 (2.7044) time: 0.5056 [2021-03-26 23:35:23 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 220/1251] eta: 0:08:58 lr: 0.000104 loss: 2.9581 (2.8483) grad_norm: 2.3924 (2.6929) time: 0.5080 [2021-03-26 23:35:28 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 230/1251] eta: 0:08:52 lr: 0.000104 loss: 2.9651 (2.8580) grad_norm: 2.4850 (2.6818) time: 0.5033 [2021-03-26 23:35:33 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 240/1251] eta: 0:08:45 lr: 0.000104 loss: 2.9885 (2.8615) grad_norm: 2.5144 (2.6764) time: 0.4958 [2021-03-26 23:35:37 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 250/1251] eta: 0:08:39 lr: 0.000104 loss: 2.9885 (2.8607) grad_norm: 2.4534 (2.6665) time: 0.4937 [2021-03-26 23:35:42 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 260/1251] eta: 0:08:33 lr: 0.000104 loss: 2.9701 (2.8606) grad_norm: 2.4153 (2.6640) time: 0.4981 [2021-03-26 23:35:47 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 270/1251] eta: 0:08:27 lr: 0.000104 loss: 2.9702 (2.8645) grad_norm: 2.3603 (2.6546) time: 0.4954 [2021-03-26 23:35:52 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 280/1251] eta: 0:08:22 lr: 0.000104 loss: 2.7774 (2.8618) grad_norm: 2.3411 (2.6464) time: 0.4971 [2021-03-26 23:35:57 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 290/1251] eta: 0:08:16 lr: 0.000104 loss: 2.8525 (2.8665) grad_norm: 2.3883 (2.6431) time: 0.4993 [2021-03-26 23:36:02 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 300/1251] eta: 0:08:10 lr: 0.000104 loss: 3.0518 (2.8724) grad_norm: 2.5322 (2.6421) time: 0.4945 [2021-03-26 23:36:07 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 310/1251] eta: 0:08:04 lr: 0.000104 loss: 3.0731 (2.8739) grad_norm: 2.4991 (2.6351) time: 0.4975 [2021-03-26 23:36:12 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 320/1251] eta: 0:07:59 lr: 0.000104 loss: 3.0398 (2.8722) grad_norm: 2.4458 (2.6345) time: 0.5031 [2021-03-26 23:36:17 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 330/1251] eta: 0:07:53 lr: 0.000104 loss: 2.8105 (2.8707) grad_norm: 2.4639 (2.6305) time: 0.5058 [2021-03-26 23:36:22 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 340/1251] eta: 0:07:48 lr: 0.000104 loss: 2.8278 (2.8659) grad_norm: 2.4515 (2.6316) time: 0.5022 [2021-03-26 23:36:28 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 350/1251] eta: 0:07:42 lr: 0.000104 loss: 2.8028 (2.8622) grad_norm: 2.4339 (2.6254) time: 0.5037 [2021-03-26 23:36:32 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 360/1251] eta: 0:07:37 lr: 0.000104 loss: 2.8028 (2.8620) grad_norm: 2.3148 (2.6187) time: 0.5032 [2021-03-26 23:36:37 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 370/1251] eta: 0:07:31 lr: 0.000104 loss: 2.9839 (2.8658) grad_norm: 2.4511 (2.6210) time: 0.4980 [2021-03-26 23:36:42 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 380/1251] eta: 0:07:26 lr: 0.000104 loss: 2.8793 (2.8632) grad_norm: 2.7164 (2.6219) time: 0.4968 [2021-03-26 23:36:48 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 390/1251] eta: 0:07:21 lr: 0.000104 loss: 2.7712 (2.8649) grad_norm: 2.6599 (2.6231) time: 0.5037 [2021-03-26 23:36:53 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 400/1251] eta: 0:07:16 lr: 0.000104 loss: 2.9016 (2.8646) grad_norm: 2.5175 (2.6206) time: 0.5120 [2021-03-26 23:36:58 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 410/1251] eta: 0:07:10 lr: 0.000104 loss: 2.9820 (2.8663) grad_norm: 2.4583 (2.6224) time: 0.5058 [2021-03-26 23:37:03 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 420/1251] eta: 0:07:05 lr: 0.000104 loss: 2.9766 (2.8644) grad_norm: 2.4232 (2.6178) time: 0.4956 [2021-03-26 23:37:08 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 430/1251] eta: 0:06:59 lr: 0.000103 loss: 2.9063 (2.8663) grad_norm: 2.3705 (2.6127) time: 0.4969 [2021-03-26 23:37:13 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 440/1251] eta: 0:06:54 lr: 0.000103 loss: 2.9787 (2.8618) grad_norm: 2.3387 (2.6083) time: 0.5034 [2021-03-26 23:37:18 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 450/1251] eta: 0:06:49 lr: 0.000103 loss: 2.9826 (2.8633) grad_norm: 2.5756 (2.6109) time: 0.5064 [2021-03-26 23:37:23 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 460/1251] eta: 0:06:44 lr: 0.000103 loss: 2.7865 (2.8579) grad_norm: 2.6601 (2.6118) time: 0.5014 [2021-03-26 23:37:28 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 470/1251] eta: 0:06:38 lr: 0.000103 loss: 2.7583 (2.8574) grad_norm: 2.4535 (2.6111) time: 0.4966 [2021-03-26 23:37:33 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 480/1251] eta: 0:06:33 lr: 0.000103 loss: 2.9091 (2.8597) grad_norm: 2.5210 (2.6108) time: 0.4997 [2021-03-26 23:37:38 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 490/1251] eta: 0:06:28 lr: 0.000103 loss: 3.1062 (2.8651) grad_norm: 2.5210 (2.6088) time: 0.5009 [2021-03-26 23:37:43 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 500/1251] eta: 0:06:23 lr: 0.000103 loss: 3.1286 (2.8705) grad_norm: 2.5318 (2.6096) time: 0.5052 [2021-03-26 23:37:48 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 510/1251] eta: 0:06:17 lr: 0.000103 loss: 3.0511 (2.8669) grad_norm: 2.6148 (2.6097) time: 0.5057 [2021-03-26 23:37:53 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 520/1251] eta: 0:06:12 lr: 0.000103 loss: 2.9161 (2.8643) grad_norm: 2.5645 (2.6111) time: 0.5021 [2021-03-26 23:37:58 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 530/1251] eta: 0:06:07 lr: 0.000103 loss: 2.9161 (2.8626) grad_norm: 2.4946 (2.6082) time: 0.5017 [2021-03-26 23:38:03 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 540/1251] eta: 0:06:02 lr: 0.000103 loss: 2.8575 (2.8636) grad_norm: 2.5557 (2.6091) time: 0.5033 [2021-03-26 23:38:08 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 550/1251] eta: 0:05:57 lr: 0.000103 loss: 2.9004 (2.8638) grad_norm: 2.5528 (2.6080) time: 0.5198 [2021-03-26 23:38:13 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 560/1251] eta: 0:05:52 lr: 0.000103 loss: 2.9242 (2.8654) grad_norm: 2.5454 (2.6087) time: 0.5201 [2021-03-26 23:38:18 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 570/1251] eta: 0:05:47 lr: 0.000103 loss: 2.9267 (2.8666) grad_norm: 2.4739 (2.6065) time: 0.5107 [2021-03-26 23:38:24 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 580/1251] eta: 0:05:42 lr: 0.000103 loss: 2.8753 (2.8660) grad_norm: 2.3701 (2.6048) time: 0.5105 [2021-03-26 23:38:29 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 590/1251] eta: 0:05:37 lr: 0.000103 loss: 2.9694 (2.8654) grad_norm: 2.5037 (2.6074) time: 0.5057 [2021-03-26 23:38:34 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 600/1251] eta: 0:05:31 lr: 0.000103 loss: 2.6657 (2.8602) grad_norm: 2.6609 (2.6080) time: 0.5025 [2021-03-26 23:38:39 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 610/1251] eta: 0:05:26 lr: 0.000103 loss: 2.6657 (2.8605) grad_norm: 2.5395 (2.6065) time: 0.4964 [2021-03-26 23:38:44 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 620/1251] eta: 0:05:21 lr: 0.000103 loss: 3.0029 (2.8624) grad_norm: 2.5309 (2.6058) time: 0.4963 [2021-03-26 23:38:49 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 630/1251] eta: 0:05:16 lr: 0.000103 loss: 3.0479 (2.8656) grad_norm: 2.5226 (2.6062) time: 0.4992 [2021-03-26 23:38:54 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 640/1251] eta: 0:05:11 lr: 0.000103 loss: 3.2131 (2.8714) grad_norm: 2.5778 (2.6080) time: 0.5049 [2021-03-26 23:38:59 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 650/1251] eta: 0:05:05 lr: 0.000103 loss: 3.0427 (2.8691) grad_norm: 2.5524 (2.6081) time: 0.5066 [2021-03-26 23:39:04 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 660/1251] eta: 0:05:00 lr: 0.000103 loss: 2.8598 (2.8687) grad_norm: 2.4690 (2.6063) time: 0.4993 [2021-03-26 23:39:09 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 670/1251] eta: 0:04:55 lr: 0.000103 loss: 3.0700 (2.8707) grad_norm: 2.5006 (2.6033) time: 0.4976 [2021-03-26 23:39:14 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 680/1251] eta: 0:04:50 lr: 0.000103 loss: 3.1537 (2.8729) grad_norm: 2.4643 (2.6019) time: 0.4994 [2021-03-26 23:39:19 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 690/1251] eta: 0:04:45 lr: 0.000103 loss: 2.8736 (2.8705) grad_norm: 2.5553 (2.6088) time: 0.4983 [2021-03-26 23:39:24 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 700/1251] eta: 0:04:40 lr: 0.000103 loss: 2.8022 (2.8713) grad_norm: 2.7641 (2.6094) time: 0.4974 [2021-03-26 23:39:29 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 710/1251] eta: 0:04:34 lr: 0.000103 loss: 2.7954 (2.8673) grad_norm: 2.5676 (2.6101) time: 0.4968 [2021-03-26 23:39:34 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 720/1251] eta: 0:04:29 lr: 0.000103 loss: 2.7253 (2.8683) grad_norm: 2.5253 (2.6094) time: 0.4979 [2021-03-26 23:39:39 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 730/1251] eta: 0:04:24 lr: 0.000103 loss: 2.9619 (2.8682) grad_norm: 2.6490 (2.6107) time: 0.5023 [2021-03-26 23:39:44 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 740/1251] eta: 0:04:19 lr: 0.000103 loss: 2.9619 (2.8681) grad_norm: 2.6135 (2.6142) time: 0.5219 [2021-03-26 23:39:49 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 750/1251] eta: 0:04:14 lr: 0.000103 loss: 2.9322 (2.8687) grad_norm: 2.5935 (2.6138) time: 0.5187 [2021-03-26 23:39:54 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 760/1251] eta: 0:04:09 lr: 0.000103 loss: 2.9159 (2.8680) grad_norm: 2.5840 (2.6145) time: 0.5008 [2021-03-26 23:39:59 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 770/1251] eta: 0:04:04 lr: 0.000103 loss: 2.8936 (2.8679) grad_norm: 2.4495 (2.6123) time: 0.5072 [2021-03-26 23:40:04 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 780/1251] eta: 0:03:59 lr: 0.000103 loss: 3.0394 (2.8696) grad_norm: 2.4567 (2.6127) time: 0.5080 [2021-03-26 23:40:09 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 790/1251] eta: 0:03:54 lr: 0.000103 loss: 3.0069 (2.8702) grad_norm: 2.5011 (2.6108) time: 0.5041 [2021-03-26 23:40:14 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 800/1251] eta: 0:03:49 lr: 0.000103 loss: 2.8704 (2.8678) grad_norm: 2.4051 (2.6101) time: 0.5038 [2021-03-26 23:40:19 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 810/1251] eta: 0:03:44 lr: 0.000103 loss: 2.9570 (2.8662) grad_norm: 2.4958 (2.6086) time: 0.5020 [2021-03-26 23:40:24 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 820/1251] eta: 0:03:38 lr: 0.000103 loss: 2.9570 (2.8664) grad_norm: 2.5141 (2.6098) time: 0.5022 [2021-03-26 23:40:29 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 830/1251] eta: 0:03:33 lr: 0.000103 loss: 3.0022 (2.8675) grad_norm: 2.7688 (2.6126) time: 0.5050 [2021-03-26 23:40:34 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 840/1251] eta: 0:03:28 lr: 0.000103 loss: 3.0022 (2.8692) grad_norm: 2.8099 (2.6138) time: 0.5015 [2021-03-26 23:40:39 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 850/1251] eta: 0:03:23 lr: 0.000102 loss: 3.0121 (2.8704) grad_norm: 2.5159 (2.6132) time: 0.4973 [2021-03-26 23:40:44 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 860/1251] eta: 0:03:18 lr: 0.000102 loss: 2.9795 (2.8703) grad_norm: 2.6496 (2.6156) time: 0.4968 [2021-03-26 23:40:49 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 870/1251] eta: 0:03:13 lr: 0.000102 loss: 3.0044 (2.8715) grad_norm: 2.6546 (2.6159) time: 0.5035 [2021-03-26 23:40:54 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 880/1251] eta: 0:03:08 lr: 0.000102 loss: 3.1114 (2.8726) grad_norm: 2.5869 (2.6157) time: 0.5113 [2021-03-26 23:40:59 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 890/1251] eta: 0:03:03 lr: 0.000102 loss: 3.0627 (2.8732) grad_norm: 2.6083 (2.6158) time: 0.5035 [2021-03-26 23:41:04 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 900/1251] eta: 0:02:58 lr: 0.000102 loss: 2.9615 (2.8736) grad_norm: 2.4379 (2.6191) time: 0.4992 [2021-03-26 23:41:09 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 910/1251] eta: 0:02:52 lr: 0.000102 loss: 2.9532 (2.8735) grad_norm: 2.4271 (2.6201) time: 0.4977 [2021-03-26 23:41:14 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 920/1251] eta: 0:02:47 lr: 0.000102 loss: 2.7172 (2.8721) grad_norm: 2.4502 (2.6220) time: 0.4961 [2021-03-26 23:41:19 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 930/1251] eta: 0:02:42 lr: 0.000102 loss: 2.6574 (2.8703) grad_norm: 2.4434 (2.6199) time: 0.4993 [2021-03-26 23:41:24 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 940/1251] eta: 0:02:37 lr: 0.000102 loss: 2.8606 (2.8712) grad_norm: 2.5311 (2.6215) time: 0.5026 [2021-03-26 23:41:29 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 950/1251] eta: 0:02:32 lr: 0.000102 loss: 2.9232 (2.8706) grad_norm: 2.6931 (2.6213) time: 0.5018 [2021-03-26 23:41:35 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 960/1251] eta: 0:02:27 lr: 0.000102 loss: 2.8552 (2.8689) grad_norm: 2.6009 (2.6281) time: 0.5045 [2021-03-26 23:41:40 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 970/1251] eta: 0:02:22 lr: 0.000102 loss: 2.8997 (2.8700) grad_norm: 2.5790 (2.6275) time: 0.5085 [2021-03-26 23:41:45 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 980/1251] eta: 0:02:17 lr: 0.000102 loss: 2.9069 (2.8695) grad_norm: 2.4992 (2.6261) time: 0.5038 [2021-03-26 23:41:50 swin_small_patch4_window7_224] INFO: Epoch: [240] [ 990/1251] eta: 0:02:12 lr: 0.000102 loss: 3.0484 (2.8721) grad_norm: 2.4444 (2.6278) time: 0.5066 [2021-03-26 23:41:55 swin_small_patch4_window7_224] INFO: Epoch: [240] [1000/1251] eta: 0:02:07 lr: 0.000102 loss: 3.0908 (2.8740) grad_norm: 2.4444 (2.6269) time: 0.5086 [2021-03-26 23:42:00 swin_small_patch4_window7_224] INFO: Epoch: [240] [1010/1251] eta: 0:02:02 lr: 0.000102 loss: 3.0908 (2.8742) grad_norm: 2.5300 (2.6288) time: 0.5012 [2021-03-26 23:42:05 swin_small_patch4_window7_224] INFO: Epoch: [240] [1020/1251] eta: 0:01:57 lr: 0.000102 loss: 3.0769 (2.8737) grad_norm: 2.5300 (2.6285) time: 0.4977 [2021-03-26 23:42:10 swin_small_patch4_window7_224] INFO: Epoch: [240] [1030/1251] eta: 0:01:51 lr: 0.000102 loss: 2.8874 (2.8721) grad_norm: 2.4899 (2.6278) time: 0.4986 [2021-03-26 23:42:15 swin_small_patch4_window7_224] INFO: Epoch: [240] [1040/1251] eta: 0:01:46 lr: 0.000102 loss: 2.9636 (2.8726) grad_norm: 2.4935 (2.6274) time: 0.4982 [2021-03-26 23:42:20 swin_small_patch4_window7_224] INFO: Epoch: [240] [1050/1251] eta: 0:01:41 lr: 0.000102 loss: 2.9636 (2.8735) grad_norm: 2.5123 (2.6275) time: 0.5000 [2021-03-26 23:42:25 swin_small_patch4_window7_224] INFO: Epoch: [240] [1060/1251] eta: 0:01:36 lr: 0.000102 loss: 2.8468 (2.8730) grad_norm: 2.4403 (2.6265) time: 0.4954 [2021-03-26 23:42:30 swin_small_patch4_window7_224] INFO: Epoch: [240] [1070/1251] eta: 0:01:31 lr: 0.000102 loss: 2.8344 (2.8721) grad_norm: 2.3278 (2.6261) time: 0.5028 [2021-03-26 23:42:35 swin_small_patch4_window7_224] INFO: Epoch: [240] [1080/1251] eta: 0:01:26 lr: 0.000102 loss: 2.7380 (2.8686) grad_norm: 2.4244 (2.6262) time: 0.5036 [2021-03-26 23:42:40 swin_small_patch4_window7_224] INFO: Epoch: [240] [1090/1251] eta: 0:01:21 lr: 0.000102 loss: 2.7380 (2.8685) grad_norm: 2.5027 (2.6257) time: 0.4956 [2021-03-26 23:42:45 swin_small_patch4_window7_224] INFO: Epoch: [240] [1100/1251] eta: 0:01:16 lr: 0.000102 loss: 3.0113 (2.8687) grad_norm: 2.4806 (2.6239) time: 0.5058 [2021-03-26 23:42:50 swin_small_patch4_window7_224] INFO: Epoch: [240] [1110/1251] eta: 0:01:11 lr: 0.000102 loss: 2.9194 (2.8680) grad_norm: 2.4516 (2.6232) time: 0.5086 [2021-03-26 23:42:55 swin_small_patch4_window7_224] INFO: Epoch: [240] [1120/1251] eta: 0:01:06 lr: 0.000102 loss: 2.6955 (2.8675) grad_norm: 2.6214 (2.6240) time: 0.4986 [2021-03-26 23:43:00 swin_small_patch4_window7_224] INFO: Epoch: [240] [1130/1251] eta: 0:01:01 lr: 0.000102 loss: 2.7444 (2.8673) grad_norm: 2.6481 (2.6246) time: 0.4918 [2021-03-26 23:43:05 swin_small_patch4_window7_224] INFO: Epoch: [240] [1140/1251] eta: 0:00:56 lr: 0.000102 loss: 2.8595 (2.8671) grad_norm: 2.5026 (2.6241) time: 0.4995 [2021-03-26 23:43:10 swin_small_patch4_window7_224] INFO: Epoch: [240] [1150/1251] eta: 0:00:51 lr: 0.000102 loss: 2.8891 (2.8679) grad_norm: 2.5026 (2.6235) time: 0.5060 [2021-03-26 23:43:15 swin_small_patch4_window7_224] INFO: Epoch: [240] [1160/1251] eta: 0:00:46 lr: 0.000102 loss: 2.9823 (2.8681) grad_norm: 2.4984 (2.6230) time: 0.5011 [2021-03-26 23:43:20 swin_small_patch4_window7_224] INFO: Epoch: [240] [1170/1251] eta: 0:00:40 lr: 0.000102 loss: 2.9569 (2.8681) grad_norm: 2.5129 (2.6236) time: 0.5025 [2021-03-26 23:43:25 swin_small_patch4_window7_224] INFO: Epoch: [240] [1180/1251] eta: 0:00:35 lr: 0.000102 loss: 2.9759 (2.8683) grad_norm: 2.6809 (2.6247) time: 0.5074 [2021-03-26 23:43:30 swin_small_patch4_window7_224] INFO: Epoch: [240] [1190/1251] eta: 0:00:30 lr: 0.000102 loss: 2.9883 (2.8684) grad_norm: 2.5458 (2.6234) time: 0.5017 [2021-03-26 23:43:35 swin_small_patch4_window7_224] INFO: Epoch: [240] [1200/1251] eta: 0:00:25 lr: 0.000102 loss: 2.9746 (2.8682) grad_norm: 2.4088 (2.6241) time: 0.4994 [2021-03-26 23:43:40 swin_small_patch4_window7_224] INFO: Epoch: [240] [1210/1251] eta: 0:00:20 lr: 0.000102 loss: 2.8356 (2.8684) grad_norm: 2.4954 (2.6244) time: 0.5049 [2021-03-26 23:43:45 swin_small_patch4_window7_224] INFO: Epoch: [240] [1220/1251] eta: 0:00:15 lr: 0.000102 loss: 2.7983 (2.8670) grad_norm: 2.4954 (2.6248) time: 0.5070 [2021-03-26 23:43:50 swin_small_patch4_window7_224] INFO: Epoch: [240] [1230/1251] eta: 0:00:10 lr: 0.000102 loss: 2.9713 (2.8682) grad_norm: 2.4204 (2.6241) time: 0.5023 [2021-03-26 23:43:55 swin_small_patch4_window7_224] INFO: Epoch: [240] [1240/1251] eta: 0:00:05 lr: 0.000102 loss: 3.0455 (2.8690) grad_norm: 2.4164 (2.6229) time: 0.4992 [2021-03-26 23:44:00 swin_small_patch4_window7_224] INFO: Epoch: [240] [1250/1251] eta: 0:00:00 lr: 0.000102 loss: 2.9708 (2.8680) grad_norm: 2.3502 (2.6204) time: 0.4976 [2021-03-26 23:44:49 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:07 loss: 1.0315 (1.0315) acc1: 75.0000 (75.0000) acc5: 92.1875 (92.1875) [2021-03-26 23:44:50 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7166 (0.7383) acc1: 81.2500 (80.8239) acc5: 95.3125 (95.8807) [2021-03-26 23:44:52 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7166 (0.7721) acc1: 81.2500 (80.3571) acc5: 96.8750 (96.1310) [2021-03-26 23:44:53 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7788 (0.7753) acc1: 81.2500 (80.6956) acc5: 96.8750 (95.9677) [2021-03-26 23:44:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7502 (0.7739) acc1: 81.2500 (81.0595) acc5: 96.8750 (95.9604) [2021-03-26 23:44:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7502 (0.7750) acc1: 79.6875 (80.8960) acc5: 96.8750 (95.9040) [2021-03-26 23:45:05 swin_small_patch4_window7_224] INFO: * Acc@1 82.106 Acc@5 95.998 loss 0.758 [2021-03-26 23:45:05 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-26 23:45:05 swin_small_patch4_window7_224] INFO: Max accuracy: 82.11% [2021-03-26 23:45:09 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 0/1251] eta: 1:25:40 lr: 0.000102 loss: 2.8193 (2.8193) grad_norm: 2.4420 (2.4420) time: 4.1089 [2021-03-26 23:45:14 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 10/1251] eta: 0:17:38 lr: 0.000101 loss: 2.6190 (2.5981) grad_norm: 2.5901 (2.7427) time: 0.8531 [2021-03-26 23:45:19 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 20/1251] eta: 0:14:02 lr: 0.000101 loss: 2.7277 (2.7584) grad_norm: 2.5935 (2.7486) time: 0.5132 [2021-03-26 23:45:24 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 30/1251] eta: 0:12:41 lr: 0.000101 loss: 3.1050 (2.8427) grad_norm: 2.5935 (2.7750) time: 0.4972 [2021-03-26 23:45:29 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 40/1251] eta: 0:11:57 lr: 0.000101 loss: 2.9614 (2.8522) grad_norm: 2.5800 (2.7226) time: 0.4962 [2021-03-26 23:45:35 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 50/1251] eta: 0:11:32 lr: 0.000101 loss: 2.7753 (2.8489) grad_norm: 2.5512 (2.7065) time: 0.5048 [2021-03-26 23:45:40 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 60/1251] eta: 0:11:13 lr: 0.000101 loss: 3.0024 (2.8652) grad_norm: 2.5659 (2.7011) time: 0.5097 [2021-03-26 23:45:45 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 70/1251] eta: 0:10:57 lr: 0.000101 loss: 3.0024 (2.8457) grad_norm: 2.5659 (2.6792) time: 0.5062 [2021-03-26 23:45:50 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 80/1251] eta: 0:10:43 lr: 0.000101 loss: 2.7042 (2.8315) grad_norm: 2.4420 (2.6706) time: 0.5027 [2021-03-26 23:45:55 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 90/1251] eta: 0:10:34 lr: 0.000101 loss: 2.9816 (2.8502) grad_norm: 2.4492 (2.6443) time: 0.5097 [2021-03-26 23:46:00 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 100/1251] eta: 0:10:24 lr: 0.000101 loss: 3.0631 (2.8693) grad_norm: 2.4492 (2.6346) time: 0.5150 [2021-03-26 23:46:05 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 110/1251] eta: 0:10:15 lr: 0.000101 loss: 3.0914 (2.8843) grad_norm: 2.5710 (2.6774) time: 0.5058 [2021-03-26 23:46:10 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 120/1251] eta: 0:10:07 lr: 0.000101 loss: 2.9362 (2.8757) grad_norm: 2.6031 (2.6669) time: 0.5072 [2021-03-26 23:46:15 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 130/1251] eta: 0:09:59 lr: 0.000101 loss: 3.0002 (2.8850) grad_norm: 2.5679 (2.6657) time: 0.5091 [2021-03-26 23:46:20 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 140/1251] eta: 0:09:51 lr: 0.000101 loss: 3.0075 (2.8813) grad_norm: 2.5387 (2.6559) time: 0.5015 [2021-03-26 23:46:25 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 150/1251] eta: 0:09:43 lr: 0.000101 loss: 3.0075 (2.8903) grad_norm: 2.5317 (2.6530) time: 0.5004 [2021-03-26 23:46:30 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 160/1251] eta: 0:09:36 lr: 0.000101 loss: 3.0865 (2.8964) grad_norm: 2.5369 (2.6519) time: 0.5005 [2021-03-26 23:46:35 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 170/1251] eta: 0:09:29 lr: 0.000101 loss: 3.0014 (2.8911) grad_norm: 2.4354 (2.6394) time: 0.4993 [2021-03-26 23:46:40 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 180/1251] eta: 0:09:22 lr: 0.000101 loss: 2.9776 (2.8926) grad_norm: 2.5044 (2.6408) time: 0.4982 [2021-03-26 23:46:45 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 190/1251] eta: 0:09:15 lr: 0.000101 loss: 2.9776 (2.8829) grad_norm: 2.5656 (2.6411) time: 0.4963 [2021-03-26 23:46:50 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 200/1251] eta: 0:09:09 lr: 0.000101 loss: 2.8340 (2.8772) grad_norm: 2.4728 (2.6358) time: 0.5016 [2021-03-26 23:46:55 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 210/1251] eta: 0:09:02 lr: 0.000101 loss: 2.9199 (2.8858) grad_norm: 2.5068 (2.6313) time: 0.5002 [2021-03-26 23:47:00 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 220/1251] eta: 0:08:56 lr: 0.000101 loss: 2.9506 (2.8898) grad_norm: 2.5327 (2.6375) time: 0.5014 [2021-03-26 23:47:05 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 230/1251] eta: 0:08:50 lr: 0.000101 loss: 2.9008 (2.8896) grad_norm: 2.4882 (2.6364) time: 0.5025 [2021-03-26 23:47:10 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 240/1251] eta: 0:08:44 lr: 0.000101 loss: 2.9231 (2.8947) grad_norm: 2.4344 (2.6276) time: 0.4980 [2021-03-26 23:47:15 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 250/1251] eta: 0:08:38 lr: 0.000101 loss: 2.9672 (2.8926) grad_norm: 2.4574 (2.6355) time: 0.5000 [2021-03-26 23:47:20 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 260/1251] eta: 0:08:33 lr: 0.000101 loss: 2.9063 (2.8945) grad_norm: 2.5136 (2.6273) time: 0.5060 [2021-03-26 23:47:25 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 270/1251] eta: 0:08:27 lr: 0.000101 loss: 2.9063 (2.8928) grad_norm: 2.4530 (2.6285) time: 0.5091 [2021-03-26 23:47:30 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 280/1251] eta: 0:08:21 lr: 0.000101 loss: 2.7745 (2.8813) grad_norm: 2.6429 (2.6274) time: 0.5049 [2021-03-26 23:47:35 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 290/1251] eta: 0:08:16 lr: 0.000101 loss: 2.7745 (2.8821) grad_norm: 2.6959 (2.6396) time: 0.5021 [2021-03-26 23:47:40 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 300/1251] eta: 0:08:10 lr: 0.000101 loss: 2.8853 (2.8792) grad_norm: 2.5132 (2.6354) time: 0.5019 [2021-03-26 23:47:46 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 310/1251] eta: 0:08:05 lr: 0.000101 loss: 2.8178 (2.8739) grad_norm: 2.5132 (2.6339) time: 0.5077 [2021-03-26 23:47:51 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 320/1251] eta: 0:07:59 lr: 0.000101 loss: 2.6682 (2.8693) grad_norm: 2.5943 (2.6353) time: 0.5056 [2021-03-26 23:47:55 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 330/1251] eta: 0:07:54 lr: 0.000101 loss: 2.9592 (2.8683) grad_norm: 2.5521 (2.6305) time: 0.4990 [2021-03-26 23:48:00 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 340/1251] eta: 0:07:48 lr: 0.000101 loss: 2.9592 (2.8669) grad_norm: 2.5521 (nan) time: 0.4960 [2021-03-26 23:48:05 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 350/1251] eta: 0:07:42 lr: 0.000101 loss: 3.0349 (2.8689) grad_norm: 2.6812 (nan) time: 0.4965 [2021-03-26 23:48:10 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 360/1251] eta: 0:07:37 lr: 0.000101 loss: 3.0407 (2.8689) grad_norm: 2.5630 (nan) time: 0.4994 [2021-03-26 23:48:15 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 370/1251] eta: 0:07:31 lr: 0.000101 loss: 3.0685 (2.8681) grad_norm: 2.5288 (nan) time: 0.4981 [2021-03-26 23:48:20 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 380/1251] eta: 0:07:26 lr: 0.000101 loss: 3.1557 (2.8700) grad_norm: 2.6179 (nan) time: 0.5005 [2021-03-26 23:48:25 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 390/1251] eta: 0:07:21 lr: 0.000101 loss: 3.0153 (2.8726) grad_norm: 2.5515 (nan) time: 0.5043 [2021-03-26 23:48:30 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 400/1251] eta: 0:07:15 lr: 0.000101 loss: 3.0109 (2.8737) grad_norm: 2.5229 (nan) time: 0.4992 [2021-03-26 23:48:35 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 410/1251] eta: 0:07:10 lr: 0.000101 loss: 3.0109 (2.8762) grad_norm: 2.5042 (nan) time: 0.4937 [2021-03-26 23:48:40 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 420/1251] eta: 0:07:04 lr: 0.000101 loss: 2.9481 (2.8780) grad_norm: 2.5042 (nan) time: 0.4970 [2021-03-26 23:48:45 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 430/1251] eta: 0:06:59 lr: 0.000100 loss: 2.9768 (2.8809) grad_norm: 2.4062 (nan) time: 0.4995 [2021-03-26 23:48:50 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 440/1251] eta: 0:06:54 lr: 0.000100 loss: 3.1394 (2.8882) grad_norm: 2.4765 (nan) time: 0.4976 [2021-03-26 23:48:55 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 450/1251] eta: 0:06:48 lr: 0.000100 loss: 3.0999 (2.8891) grad_norm: 2.5480 (nan) time: 0.5035 [2021-03-26 23:49:00 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 460/1251] eta: 0:06:43 lr: 0.000100 loss: 2.8786 (2.8901) grad_norm: 2.5228 (nan) time: 0.5061 [2021-03-26 23:49:05 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 470/1251] eta: 0:06:38 lr: 0.000100 loss: 2.9643 (2.8911) grad_norm: 2.4248 (nan) time: 0.5012 [2021-03-26 23:49:11 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 480/1251] eta: 0:06:33 lr: 0.000100 loss: 2.9336 (2.8906) grad_norm: 2.5394 (nan) time: 0.5036 [2021-03-26 23:49:16 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 490/1251] eta: 0:06:28 lr: 0.000100 loss: 3.0075 (2.8949) grad_norm: 2.5635 (nan) time: 0.5049 [2021-03-26 23:49:21 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 500/1251] eta: 0:06:22 lr: 0.000100 loss: 2.9604 (2.8908) grad_norm: 2.5621 (nan) time: 0.4997 [2021-03-26 23:49:26 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 510/1251] eta: 0:06:17 lr: 0.000100 loss: 2.9019 (2.8901) grad_norm: 2.5255 (nan) time: 0.4972 [2021-03-26 23:49:31 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 520/1251] eta: 0:06:12 lr: 0.000100 loss: 2.9337 (2.8896) grad_norm: 2.4994 (nan) time: 0.5038 [2021-03-26 23:49:36 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 530/1251] eta: 0:06:07 lr: 0.000100 loss: 2.9734 (2.8889) grad_norm: 2.4994 (nan) time: 0.5030 [2021-03-26 23:49:41 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 540/1251] eta: 0:06:01 lr: 0.000100 loss: 2.9056 (2.8854) grad_norm: 2.4491 (nan) time: 0.4972 [2021-03-26 23:49:46 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 550/1251] eta: 0:05:56 lr: 0.000100 loss: 2.8098 (2.8848) grad_norm: 2.5686 (nan) time: 0.5081 [2021-03-26 23:49:51 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 560/1251] eta: 0:05:51 lr: 0.000100 loss: 2.9907 (2.8906) grad_norm: 2.4786 (nan) time: 0.5134 [2021-03-26 23:49:56 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 570/1251] eta: 0:05:46 lr: 0.000100 loss: 3.0356 (2.8920) grad_norm: 2.4022 (nan) time: 0.5061 [2021-03-26 23:50:01 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 580/1251] eta: 0:05:41 lr: 0.000100 loss: 2.9011 (2.8896) grad_norm: 2.5676 (nan) time: 0.5027 [2021-03-26 23:50:06 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 590/1251] eta: 0:05:36 lr: 0.000100 loss: 2.9011 (2.8910) grad_norm: 2.6526 (nan) time: 0.5003 [2021-03-26 23:50:11 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 600/1251] eta: 0:05:31 lr: 0.000100 loss: 3.0599 (2.8939) grad_norm: 2.5972 (nan) time: 0.4991 [2021-03-26 23:50:16 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 610/1251] eta: 0:05:26 lr: 0.000100 loss: 3.0234 (2.8945) grad_norm: 2.4695 (nan) time: 0.5082 [2021-03-26 23:50:21 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 620/1251] eta: 0:05:20 lr: 0.000100 loss: 2.9653 (2.8938) grad_norm: 2.4616 (nan) time: 0.5071 [2021-03-26 23:50:26 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 630/1251] eta: 0:05:15 lr: 0.000100 loss: 2.9639 (2.8930) grad_norm: 2.5906 (nan) time: 0.4974 [2021-03-26 23:50:31 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 640/1251] eta: 0:05:10 lr: 0.000100 loss: 2.9230 (2.8913) grad_norm: 2.5917 (nan) time: 0.5044 [2021-03-26 23:50:36 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 650/1251] eta: 0:05:05 lr: 0.000100 loss: 2.8218 (2.8877) grad_norm: 2.5528 (nan) time: 0.5074 [2021-03-26 23:50:41 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 660/1251] eta: 0:05:00 lr: 0.000100 loss: 2.8831 (2.8899) grad_norm: 2.5528 (nan) time: 0.5067 [2021-03-26 23:50:46 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 670/1251] eta: 0:04:55 lr: 0.000100 loss: 3.0658 (2.8921) grad_norm: 2.5097 (nan) time: 0.5015 [2021-03-26 23:50:51 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 680/1251] eta: 0:04:50 lr: 0.000100 loss: 2.8478 (2.8896) grad_norm: 2.4339 (nan) time: 0.4961 [2021-03-26 23:50:56 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 690/1251] eta: 0:04:45 lr: 0.000100 loss: 2.6517 (2.8852) grad_norm: 2.4436 (nan) time: 0.5045 [2021-03-26 23:51:01 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 700/1251] eta: 0:04:39 lr: 0.000100 loss: 2.3292 (2.8823) grad_norm: 2.5263 (nan) time: 0.5052 [2021-03-26 23:51:06 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 710/1251] eta: 0:04:34 lr: 0.000100 loss: 2.9619 (2.8845) grad_norm: 2.5306 (nan) time: 0.5012 [2021-03-26 23:51:11 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 720/1251] eta: 0:04:29 lr: 0.000100 loss: 3.0958 (2.8846) grad_norm: 2.6345 (nan) time: 0.4981 [2021-03-26 23:51:16 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 730/1251] eta: 0:04:24 lr: 0.000100 loss: 2.9144 (2.8835) grad_norm: 2.5457 (nan) time: 0.4951 [2021-03-26 23:51:21 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 740/1251] eta: 0:04:19 lr: 0.000100 loss: 2.9004 (2.8846) grad_norm: 2.5288 (nan) time: 0.5117 [2021-03-26 23:51:27 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 750/1251] eta: 0:04:14 lr: 0.000100 loss: 3.1109 (2.8867) grad_norm: 2.5931 (nan) time: 0.5218 [2021-03-26 23:51:32 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 760/1251] eta: 0:04:09 lr: 0.000100 loss: 3.0294 (2.8866) grad_norm: 2.4744 (nan) time: 0.5061 [2021-03-26 23:51:37 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 770/1251] eta: 0:04:04 lr: 0.000100 loss: 3.0212 (2.8882) grad_norm: 2.3519 (nan) time: 0.5006 [2021-03-26 23:51:42 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 780/1251] eta: 0:03:59 lr: 0.000100 loss: 3.0212 (2.8867) grad_norm: 2.4164 (nan) time: 0.5030 [2021-03-26 23:51:47 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 790/1251] eta: 0:03:54 lr: 0.000100 loss: 2.8722 (2.8854) grad_norm: 2.4180 (nan) time: 0.5043 [2021-03-26 23:51:52 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 800/1251] eta: 0:03:49 lr: 0.000100 loss: 2.8722 (2.8873) grad_norm: 2.4829 (nan) time: 0.5178 [2021-03-26 23:51:57 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 810/1251] eta: 0:03:43 lr: 0.000100 loss: 2.9098 (2.8851) grad_norm: 2.5905 (nan) time: 0.5154 [2021-03-26 23:52:02 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 820/1251] eta: 0:03:38 lr: 0.000100 loss: 2.8631 (2.8841) grad_norm: 2.5661 (nan) time: 0.5077 [2021-03-26 23:52:07 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 830/1251] eta: 0:03:33 lr: 0.000100 loss: 2.8859 (2.8844) grad_norm: 2.5948 (nan) time: 0.5117 [2021-03-26 23:52:12 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 840/1251] eta: 0:03:28 lr: 0.000100 loss: 2.8427 (2.8799) grad_norm: 2.5186 (nan) time: 0.5103 [2021-03-26 23:52:17 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 850/1251] eta: 0:03:23 lr: 0.000099 loss: 2.8727 (2.8811) grad_norm: 2.4503 (nan) time: 0.5066 [2021-03-26 23:52:23 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 860/1251] eta: 0:03:18 lr: 0.000099 loss: 3.1022 (2.8840) grad_norm: 2.4782 (nan) time: 0.5075 [2021-03-26 23:52:28 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 870/1251] eta: 0:03:13 lr: 0.000099 loss: 3.0749 (2.8856) grad_norm: 2.7615 (nan) time: 0.5070 [2021-03-26 23:52:33 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 880/1251] eta: 0:03:08 lr: 0.000099 loss: 3.1268 (2.8883) grad_norm: 2.5084 (nan) time: 0.5009 [2021-03-26 23:52:38 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 890/1251] eta: 0:03:03 lr: 0.000099 loss: 2.9602 (2.8863) grad_norm: 2.4556 (nan) time: 0.4972 [2021-03-26 23:52:43 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 900/1251] eta: 0:02:58 lr: 0.000099 loss: 2.9568 (2.8880) grad_norm: 2.4556 (nan) time: 0.5017 [2021-03-26 23:52:48 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 910/1251] eta: 0:02:53 lr: 0.000099 loss: 3.0910 (2.8881) grad_norm: 2.4783 (nan) time: 0.5037 [2021-03-26 23:52:53 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 920/1251] eta: 0:02:47 lr: 0.000099 loss: 3.0997 (2.8891) grad_norm: 2.6331 (nan) time: 0.5020 [2021-03-26 23:52:58 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 930/1251] eta: 0:02:42 lr: 0.000099 loss: 3.0690 (2.8906) grad_norm: 2.6134 (nan) time: 0.5037 [2021-03-26 23:53:03 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 940/1251] eta: 0:02:37 lr: 0.000099 loss: 3.0690 (2.8916) grad_norm: 2.5787 (nan) time: 0.5079 [2021-03-26 23:53:08 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 950/1251] eta: 0:02:32 lr: 0.000099 loss: 3.0414 (2.8907) grad_norm: 2.8473 (nan) time: 0.5081 [2021-03-26 23:53:13 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 960/1251] eta: 0:02:27 lr: 0.000099 loss: 2.8202 (2.8899) grad_norm: 2.8473 (nan) time: 0.4999 [2021-03-26 23:53:18 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 970/1251] eta: 0:02:22 lr: 0.000099 loss: 2.8466 (2.8881) grad_norm: 2.6392 (nan) time: 0.4997 [2021-03-26 23:53:23 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 980/1251] eta: 0:02:17 lr: 0.000099 loss: 3.0348 (2.8891) grad_norm: 2.5928 (nan) time: 0.5027 [2021-03-26 23:53:28 swin_small_patch4_window7_224] INFO: Epoch: [241] [ 990/1251] eta: 0:02:12 lr: 0.000099 loss: 2.9809 (2.8876) grad_norm: 2.7507 (nan) time: 0.4975 [2021-03-26 23:53:33 swin_small_patch4_window7_224] INFO: Epoch: [241] [1000/1251] eta: 0:02:07 lr: 0.000099 loss: 2.9212 (2.8870) grad_norm: 2.6821 (nan) time: 0.4972 [2021-03-26 23:53:38 swin_small_patch4_window7_224] INFO: Epoch: [241] [1010/1251] eta: 0:02:02 lr: 0.000099 loss: 2.9686 (2.8858) grad_norm: 2.5384 (nan) time: 0.5043 [2021-03-26 23:53:43 swin_small_patch4_window7_224] INFO: Epoch: [241] [1020/1251] eta: 0:01:57 lr: 0.000099 loss: 2.9686 (2.8866) grad_norm: 2.5585 (nan) time: 0.5025 [2021-03-26 23:53:48 swin_small_patch4_window7_224] INFO: Epoch: [241] [1030/1251] eta: 0:01:52 lr: 0.000099 loss: 3.0060 (2.8875) grad_norm: 2.6696 (nan) time: 0.4979 [2021-03-26 23:53:53 swin_small_patch4_window7_224] INFO: Epoch: [241] [1040/1251] eta: 0:01:46 lr: 0.000099 loss: 3.1277 (2.8883) grad_norm: 2.6351 (nan) time: 0.4996 [2021-03-26 23:53:58 swin_small_patch4_window7_224] INFO: Epoch: [241] [1050/1251] eta: 0:01:41 lr: 0.000099 loss: 3.1621 (2.8902) grad_norm: 2.4351 (nan) time: 0.5025 [2021-03-26 23:54:03 swin_small_patch4_window7_224] INFO: Epoch: [241] [1060/1251] eta: 0:01:36 lr: 0.000099 loss: 3.1383 (2.8893) grad_norm: 2.4351 (nan) time: 0.5074 [2021-03-26 23:54:08 swin_small_patch4_window7_224] INFO: Epoch: [241] [1070/1251] eta: 0:01:31 lr: 0.000099 loss: 2.7266 (2.8886) grad_norm: 2.4951 (nan) time: 0.5067 [2021-03-26 23:54:13 swin_small_patch4_window7_224] INFO: Epoch: [241] [1080/1251] eta: 0:01:26 lr: 0.000099 loss: 2.8308 (2.8885) grad_norm: 2.5102 (nan) time: 0.5024 [2021-03-26 23:54:18 swin_small_patch4_window7_224] INFO: Epoch: [241] [1090/1251] eta: 0:01:21 lr: 0.000099 loss: 2.8308 (2.8875) grad_norm: 2.5396 (nan) time: 0.5001 [2021-03-26 23:54:23 swin_small_patch4_window7_224] INFO: Epoch: [241] [1100/1251] eta: 0:01:16 lr: 0.000099 loss: 2.7352 (2.8856) grad_norm: 2.5526 (nan) time: 0.4964 [2021-03-26 23:54:28 swin_small_patch4_window7_224] INFO: Epoch: [241] [1110/1251] eta: 0:01:11 lr: 0.000099 loss: 2.7302 (2.8850) grad_norm: 2.6140 (nan) time: 0.4938 [2021-03-26 23:54:33 swin_small_patch4_window7_224] INFO: Epoch: [241] [1120/1251] eta: 0:01:06 lr: 0.000099 loss: 2.8589 (2.8852) grad_norm: 2.6545 (nan) time: 0.5021 [2021-03-26 23:54:38 swin_small_patch4_window7_224] INFO: Epoch: [241] [1130/1251] eta: 0:01:01 lr: 0.000099 loss: 2.7781 (2.8838) grad_norm: 2.4897 (nan) time: 0.5056 [2021-03-26 23:54:43 swin_small_patch4_window7_224] INFO: Epoch: [241] [1140/1251] eta: 0:00:56 lr: 0.000099 loss: 2.7600 (2.8827) grad_norm: 2.3034 (nan) time: 0.4976 [2021-03-26 23:54:48 swin_small_patch4_window7_224] INFO: Epoch: [241] [1150/1251] eta: 0:00:51 lr: 0.000099 loss: 2.8859 (2.8821) grad_norm: 2.5070 (nan) time: 0.4972 [2021-03-26 23:54:53 swin_small_patch4_window7_224] INFO: Epoch: [241] [1160/1251] eta: 0:00:46 lr: 0.000099 loss: 2.9390 (2.8826) grad_norm: 2.5090 (nan) time: 0.4992 [2021-03-26 23:54:58 swin_small_patch4_window7_224] INFO: Epoch: [241] [1170/1251] eta: 0:00:41 lr: 0.000099 loss: 2.9919 (2.8835) grad_norm: 2.5515 (nan) time: 0.5021 [2021-03-26 23:55:03 swin_small_patch4_window7_224] INFO: Epoch: [241] [1180/1251] eta: 0:00:35 lr: 0.000099 loss: 2.9919 (2.8835) grad_norm: 2.5008 (nan) time: 0.5038 [2021-03-26 23:55:08 swin_small_patch4_window7_224] INFO: Epoch: [241] [1190/1251] eta: 0:00:30 lr: 0.000099 loss: 2.9810 (2.8849) grad_norm: 2.4846 (nan) time: 0.5050 [2021-03-26 23:55:13 swin_small_patch4_window7_224] INFO: Epoch: [241] [1200/1251] eta: 0:00:25 lr: 0.000099 loss: 2.9300 (2.8832) grad_norm: 2.5978 (nan) time: 0.5048 [2021-03-26 23:55:18 swin_small_patch4_window7_224] INFO: Epoch: [241] [1210/1251] eta: 0:00:20 lr: 0.000099 loss: 3.0788 (2.8840) grad_norm: 2.5469 (nan) time: 0.4991 [2021-03-26 23:55:23 swin_small_patch4_window7_224] INFO: Epoch: [241] [1220/1251] eta: 0:00:15 lr: 0.000099 loss: 3.0970 (2.8849) grad_norm: 2.5558 (nan) time: 0.4955 [2021-03-26 23:55:28 swin_small_patch4_window7_224] INFO: Epoch: [241] [1230/1251] eta: 0:00:10 lr: 0.000099 loss: 2.8058 (2.8837) grad_norm: 2.5223 (nan) time: 0.4987 [2021-03-26 23:55:33 swin_small_patch4_window7_224] INFO: Epoch: [241] [1240/1251] eta: 0:00:05 lr: 0.000099 loss: 2.9036 (2.8845) grad_norm: 2.5244 (nan) time: 0.5007 [2021-03-26 23:55:38 swin_small_patch4_window7_224] INFO: Epoch: [241] [1250/1251] eta: 0:00:00 lr: 0.000099 loss: 2.9991 (2.8864) grad_norm: 2.7367 (nan) time: 0.4990 [2021-03-26 23:55:46 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:15 loss: 0.7624 (0.7624) acc1: 82.8125 (82.8125) acc5: 100.0000 (100.0000) [2021-03-26 23:55:49 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.6927 (0.7146) acc1: 82.8125 (82.1023) acc5: 98.4375 (97.5852) [2021-03-26 23:55:51 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7648 (0.7580) acc1: 81.2500 (81.7708) acc5: 96.8750 (96.8006) [2021-03-26 23:55:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7648 (0.7523) acc1: 81.2500 (82.4597) acc5: 95.3125 (96.5222) [2021-03-26 23:55:56 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7329 (0.7814) acc1: 82.8125 (81.5549) acc5: 95.3125 (96.3796) [2021-03-26 23:55:57 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6914 (0.7760) acc1: 81.2500 (81.5680) acc5: 95.3125 (96.3840) [2021-03-26 23:56:06 swin_small_patch4_window7_224] INFO: * Acc@1 82.106 Acc@5 96.082 loss 0.768 [2021-03-26 23:56:06 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-26 23:56:06 swin_small_patch4_window7_224] INFO: Max accuracy: 82.11% [2021-03-26 23:56:11 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 0/1251] eta: 1:42:02 lr: 0.000099 loss: 3.5047 (3.5047) grad_norm: 2.7020 (2.7020) time: 4.8944 [2021-03-26 23:56:16 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 10/1251] eta: 0:18:59 lr: 0.000099 loss: 2.9538 (2.7671) grad_norm: 2.6773 (2.5841) time: 0.9180 [2021-03-26 23:56:21 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 20/1251] eta: 0:14:49 lr: 0.000098 loss: 2.8664 (2.8280) grad_norm: 2.6773 (2.7320) time: 0.5140 [2021-03-26 23:56:26 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 30/1251] eta: 0:13:23 lr: 0.000098 loss: 2.8974 (2.8803) grad_norm: 2.6214 (2.6491) time: 0.5146 [2021-03-26 23:56:31 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 40/1251] eta: 0:12:28 lr: 0.000098 loss: 2.9099 (2.8603) grad_norm: 2.3597 (2.6431) time: 0.5080 [2021-03-26 23:56:36 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 50/1251] eta: 0:11:57 lr: 0.000098 loss: 2.8849 (2.8288) grad_norm: 2.5449 (2.6215) time: 0.5050 [2021-03-26 23:56:41 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 60/1251] eta: 0:11:32 lr: 0.000098 loss: 2.5539 (2.7980) grad_norm: 2.5943 (2.7090) time: 0.5069 [2021-03-26 23:56:46 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 70/1251] eta: 0:11:13 lr: 0.000098 loss: 2.7871 (2.8115) grad_norm: 2.5127 (2.6852) time: 0.4998 [2021-03-26 23:56:51 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 80/1251] eta: 0:10:58 lr: 0.000098 loss: 2.9984 (2.8265) grad_norm: 2.4509 (2.6842) time: 0.5036 [2021-03-26 23:56:56 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 90/1251] eta: 0:10:45 lr: 0.000098 loss: 3.0968 (2.8468) grad_norm: 2.4831 (2.6781) time: 0.5072 [2021-03-26 23:57:02 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 100/1251] eta: 0:10:34 lr: 0.000098 loss: 3.0578 (2.8484) grad_norm: 2.5188 (2.6649) time: 0.5066 [2021-03-26 23:57:07 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 110/1251] eta: 0:10:23 lr: 0.000098 loss: 3.0479 (2.8541) grad_norm: 2.5268 (2.6569) time: 0.5020 [2021-03-26 23:57:11 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 120/1251] eta: 0:10:13 lr: 0.000098 loss: 2.9786 (2.8496) grad_norm: 2.5944 (2.6579) time: 0.4974 [2021-03-26 23:57:17 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 130/1251] eta: 0:10:05 lr: 0.000098 loss: 3.0032 (2.8506) grad_norm: 2.5547 (2.6594) time: 0.5017 [2021-03-26 23:57:22 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 140/1251] eta: 0:09:56 lr: 0.000098 loss: 2.7250 (2.8334) grad_norm: 2.5908 (2.6655) time: 0.5037 [2021-03-26 23:57:27 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 150/1251] eta: 0:09:48 lr: 0.000098 loss: 2.7250 (2.8326) grad_norm: 2.6116 (2.6615) time: 0.4999 [2021-03-26 23:57:32 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 160/1251] eta: 0:09:40 lr: 0.000098 loss: 2.9731 (2.8375) grad_norm: 2.5130 (2.6532) time: 0.4989 [2021-03-26 23:57:37 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 170/1251] eta: 0:09:33 lr: 0.000098 loss: 3.0429 (2.8430) grad_norm: 2.4570 (2.6521) time: 0.5045 [2021-03-26 23:57:42 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 180/1251] eta: 0:09:27 lr: 0.000098 loss: 2.9050 (2.8397) grad_norm: 2.5187 (2.6532) time: 0.5110 [2021-03-26 23:57:47 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 190/1251] eta: 0:09:20 lr: 0.000098 loss: 2.7804 (2.8297) grad_norm: 2.5187 (2.6489) time: 0.5028 [2021-03-26 23:57:52 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 200/1251] eta: 0:09:14 lr: 0.000098 loss: 2.7804 (2.8279) grad_norm: 2.6272 (2.6660) time: 0.5116 [2021-03-26 23:57:57 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 210/1251] eta: 0:09:08 lr: 0.000098 loss: 2.8415 (2.8300) grad_norm: 2.8820 (2.6950) time: 0.5179 [2021-03-26 23:58:02 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 220/1251] eta: 0:09:02 lr: 0.000098 loss: 3.0500 (2.8455) grad_norm: 2.8820 (2.7094) time: 0.5056 [2021-03-26 23:58:07 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 230/1251] eta: 0:08:56 lr: 0.000098 loss: 3.0500 (2.8475) grad_norm: 2.5688 (2.7015) time: 0.5052 [2021-03-26 23:58:12 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 240/1251] eta: 0:08:49 lr: 0.000098 loss: 2.5290 (2.8310) grad_norm: 2.5561 (2.6973) time: 0.4996 [2021-03-26 23:58:17 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 250/1251] eta: 0:08:43 lr: 0.000098 loss: 2.7719 (2.8342) grad_norm: 2.6119 (2.7010) time: 0.4979 [2021-03-26 23:58:22 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 260/1251] eta: 0:08:37 lr: 0.000098 loss: 2.9332 (2.8355) grad_norm: 2.6119 (2.7055) time: 0.5018 [2021-03-26 23:58:27 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 270/1251] eta: 0:08:31 lr: 0.000098 loss: 2.8257 (2.8318) grad_norm: 2.7032 (2.7227) time: 0.4984 [2021-03-26 23:58:32 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 280/1251] eta: 0:08:25 lr: 0.000098 loss: 2.8257 (2.8375) grad_norm: 2.9138 (2.7397) time: 0.4983 [2021-03-26 23:58:37 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 290/1251] eta: 0:08:19 lr: 0.000098 loss: 2.8349 (2.8361) grad_norm: 2.5829 (2.7336) time: 0.5014 [2021-03-26 23:58:42 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 300/1251] eta: 0:08:13 lr: 0.000098 loss: 2.9797 (2.8383) grad_norm: 2.5467 (2.7290) time: 0.5044 [2021-03-26 23:58:47 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 310/1251] eta: 0:08:08 lr: 0.000098 loss: 2.8234 (2.8306) grad_norm: 2.5648 (2.7232) time: 0.5027 [2021-03-26 23:58:52 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 320/1251] eta: 0:08:02 lr: 0.000098 loss: 2.7733 (2.8344) grad_norm: 2.5255 (2.7185) time: 0.5040 [2021-03-26 23:58:57 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 330/1251] eta: 0:07:57 lr: 0.000098 loss: 2.9765 (2.8359) grad_norm: 2.5249 (2.7345) time: 0.5062 [2021-03-26 23:59:02 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 340/1251] eta: 0:07:51 lr: 0.000098 loss: 3.0835 (2.8420) grad_norm: 2.6680 (2.7353) time: 0.5040 [2021-03-26 23:59:07 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 350/1251] eta: 0:07:45 lr: 0.000098 loss: 3.0140 (2.8398) grad_norm: 2.6269 (2.7297) time: 0.5006 [2021-03-26 23:59:12 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 360/1251] eta: 0:07:40 lr: 0.000098 loss: 2.8912 (2.8388) grad_norm: 2.5794 (2.7319) time: 0.4992 [2021-03-26 23:59:17 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 370/1251] eta: 0:07:34 lr: 0.000098 loss: 2.9130 (2.8378) grad_norm: 2.6826 (2.7352) time: 0.4970 [2021-03-26 23:59:22 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 380/1251] eta: 0:07:28 lr: 0.000098 loss: 2.8925 (2.8385) grad_norm: 2.6659 (2.7341) time: 0.4955 [2021-03-26 23:59:27 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 390/1251] eta: 0:07:23 lr: 0.000098 loss: 2.6894 (2.8390) grad_norm: 2.5502 (2.7282) time: 0.4994 [2021-03-26 23:59:32 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 400/1251] eta: 0:07:17 lr: 0.000098 loss: 3.0917 (2.8389) grad_norm: 2.5732 (2.7272) time: 0.4999 [2021-03-26 23:59:37 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 410/1251] eta: 0:07:12 lr: 0.000098 loss: 3.0917 (2.8415) grad_norm: 2.5368 (2.7217) time: 0.4966 [2021-03-26 23:59:42 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 420/1251] eta: 0:07:06 lr: 0.000098 loss: 3.1542 (2.8473) grad_norm: 2.5060 (2.7189) time: 0.4951 [2021-03-26 23:59:47 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 430/1251] eta: 0:07:01 lr: 0.000098 loss: 2.9350 (2.8476) grad_norm: 2.5072 (2.7163) time: 0.4995 [2021-03-26 23:59:52 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 440/1251] eta: 0:06:56 lr: 0.000097 loss: 2.9047 (2.8505) grad_norm: 2.5524 (2.7135) time: 0.5012 [2021-03-26 23:59:57 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 450/1251] eta: 0:06:50 lr: 0.000097 loss: 3.0111 (2.8572) grad_norm: 2.5987 (2.7125) time: 0.4953 [2021-03-27 00:00:02 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 460/1251] eta: 0:06:45 lr: 0.000097 loss: 3.1197 (2.8564) grad_norm: 2.5521 (2.7097) time: 0.4959 [2021-03-27 00:00:07 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 470/1251] eta: 0:06:40 lr: 0.000097 loss: 2.9594 (2.8589) grad_norm: 2.6547 (2.7113) time: 0.5023 [2021-03-27 00:00:12 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 480/1251] eta: 0:06:34 lr: 0.000097 loss: 2.9739 (2.8608) grad_norm: 2.7117 (2.7195) time: 0.5039 [2021-03-27 00:00:17 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 490/1251] eta: 0:06:29 lr: 0.000097 loss: 2.9995 (2.8613) grad_norm: 2.5822 (2.7138) time: 0.4998 [2021-03-27 00:00:22 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 500/1251] eta: 0:06:24 lr: 0.000097 loss: 2.9467 (2.8580) grad_norm: 2.4959 (2.7116) time: 0.4969 [2021-03-27 00:00:27 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 510/1251] eta: 0:06:18 lr: 0.000097 loss: 3.0523 (2.8638) grad_norm: 2.6413 (2.7177) time: 0.5014 [2021-03-27 00:00:32 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 520/1251] eta: 0:06:13 lr: 0.000097 loss: 3.1256 (2.8665) grad_norm: 2.5457 (2.7163) time: 0.5001 [2021-03-27 00:00:37 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 530/1251] eta: 0:06:08 lr: 0.000097 loss: 3.1149 (2.8710) grad_norm: 2.5319 (2.7159) time: 0.4943 [2021-03-27 00:00:42 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 540/1251] eta: 0:06:02 lr: 0.000097 loss: 3.0441 (2.8689) grad_norm: 2.5319 (2.7130) time: 0.4967 [2021-03-27 00:00:47 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 550/1251] eta: 0:05:57 lr: 0.000097 loss: 2.7165 (2.8662) grad_norm: 2.5554 (2.7144) time: 0.5091 [2021-03-27 00:00:52 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 560/1251] eta: 0:05:52 lr: 0.000097 loss: 2.8698 (2.8660) grad_norm: 2.8000 (2.7184) time: 0.5164 [2021-03-27 00:00:58 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 570/1251] eta: 0:05:47 lr: 0.000097 loss: 2.8698 (2.8675) grad_norm: 2.5526 (2.7178) time: 0.5111 [2021-03-27 00:01:03 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 580/1251] eta: 0:05:42 lr: 0.000097 loss: 2.9862 (2.8682) grad_norm: 2.5498 (2.7212) time: 0.5071 [2021-03-27 00:01:08 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 590/1251] eta: 0:05:37 lr: 0.000097 loss: 3.0802 (2.8708) grad_norm: 2.4850 (2.7159) time: 0.5071 [2021-03-27 00:01:13 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 600/1251] eta: 0:05:32 lr: 0.000097 loss: 2.8932 (2.8672) grad_norm: 2.4193 (2.7129) time: 0.5089 [2021-03-27 00:01:18 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 610/1251] eta: 0:05:27 lr: 0.000097 loss: 2.6267 (2.8678) grad_norm: 2.4391 (2.7095) time: 0.5056 [2021-03-27 00:01:23 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 620/1251] eta: 0:05:21 lr: 0.000097 loss: 2.7565 (2.8686) grad_norm: 2.5262 (2.7074) time: 0.4981 [2021-03-27 00:01:28 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 630/1251] eta: 0:05:16 lr: 0.000097 loss: 2.9652 (2.8694) grad_norm: 2.5841 (2.7054) time: 0.4952 [2021-03-27 00:01:33 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 640/1251] eta: 0:05:11 lr: 0.000097 loss: 2.9358 (2.8663) grad_norm: 2.4828 (2.7014) time: 0.5023 [2021-03-27 00:01:38 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 650/1251] eta: 0:05:06 lr: 0.000097 loss: 2.8424 (2.8679) grad_norm: 2.4802 (2.6984) time: 0.5067 [2021-03-27 00:01:43 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 660/1251] eta: 0:05:01 lr: 0.000097 loss: 2.9165 (2.8673) grad_norm: 2.4826 (2.6976) time: 0.5054 [2021-03-27 00:01:48 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 670/1251] eta: 0:04:56 lr: 0.000097 loss: 3.0592 (2.8708) grad_norm: 2.5207 (2.6954) time: 0.5022 [2021-03-27 00:01:53 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 680/1251] eta: 0:04:50 lr: 0.000097 loss: 3.1389 (2.8705) grad_norm: 2.5310 (2.6953) time: 0.5033 [2021-03-27 00:01:58 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 690/1251] eta: 0:04:45 lr: 0.000097 loss: 2.7957 (2.8684) grad_norm: 2.5310 (2.6941) time: 0.5013 [2021-03-27 00:02:03 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 700/1251] eta: 0:04:40 lr: 0.000097 loss: 2.6119 (2.8670) grad_norm: 2.5186 (2.6914) time: 0.4977 [2021-03-27 00:02:08 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 710/1251] eta: 0:04:35 lr: 0.000097 loss: 2.5733 (2.8616) grad_norm: 2.5186 (2.6933) time: 0.5010 [2021-03-27 00:02:13 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 720/1251] eta: 0:04:30 lr: 0.000097 loss: 2.4320 (2.8597) grad_norm: 2.5653 (2.6957) time: 0.5072 [2021-03-27 00:02:18 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 730/1251] eta: 0:04:25 lr: 0.000097 loss: 2.8967 (2.8616) grad_norm: 2.6903 (2.7005) time: 0.5122 [2021-03-27 00:02:23 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 740/1251] eta: 0:04:20 lr: 0.000097 loss: 2.9261 (2.8610) grad_norm: 2.5721 (2.6994) time: 0.5194 [2021-03-27 00:02:29 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 750/1251] eta: 0:04:15 lr: 0.000097 loss: 2.9323 (2.8640) grad_norm: 2.5721 (2.7001) time: 0.5319 [2021-03-27 00:02:34 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 760/1251] eta: 0:04:10 lr: 0.000097 loss: 3.0794 (2.8664) grad_norm: 2.6890 (2.6987) time: 0.5171 [2021-03-27 00:02:39 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 770/1251] eta: 0:04:05 lr: 0.000097 loss: 3.0366 (2.8686) grad_norm: 2.6061 (2.6985) time: 0.5032 [2021-03-27 00:02:44 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 780/1251] eta: 0:03:59 lr: 0.000097 loss: 2.9652 (2.8681) grad_norm: 2.5472 (2.6955) time: 0.5010 [2021-03-27 00:02:49 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 790/1251] eta: 0:03:54 lr: 0.000097 loss: 2.9605 (2.8688) grad_norm: 2.5840 (2.6958) time: 0.4955 [2021-03-27 00:02:54 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 800/1251] eta: 0:03:49 lr: 0.000097 loss: 2.9977 (2.8708) grad_norm: 2.7008 (2.7053) time: 0.5042 [2021-03-27 00:02:59 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 810/1251] eta: 0:03:44 lr: 0.000097 loss: 3.0032 (2.8721) grad_norm: 2.7177 (2.7066) time: 0.5125 [2021-03-27 00:03:04 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 820/1251] eta: 0:03:39 lr: 0.000097 loss: 2.9057 (2.8694) grad_norm: 2.7061 (2.7065) time: 0.5069 [2021-03-27 00:03:09 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 830/1251] eta: 0:03:34 lr: 0.000097 loss: 2.8622 (2.8698) grad_norm: 2.7839 (2.7116) time: 0.5077 [2021-03-27 00:03:14 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 840/1251] eta: 0:03:29 lr: 0.000097 loss: 3.0377 (2.8695) grad_norm: 2.6021 (2.7102) time: 0.5086 [2021-03-27 00:03:19 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 850/1251] eta: 0:03:24 lr: 0.000097 loss: 2.9251 (2.8660) grad_norm: 2.5243 (2.7098) time: 0.5018 [2021-03-27 00:03:24 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 860/1251] eta: 0:03:19 lr: 0.000097 loss: 2.9251 (2.8669) grad_norm: 2.5086 (2.7088) time: 0.5036 [2021-03-27 00:03:29 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 870/1251] eta: 0:03:13 lr: 0.000096 loss: 2.8989 (2.8644) grad_norm: 2.4537 (2.7070) time: 0.5053 [2021-03-27 00:03:34 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 880/1251] eta: 0:03:08 lr: 0.000096 loss: 2.6577 (2.8635) grad_norm: 2.4886 (2.7084) time: 0.5032 [2021-03-27 00:03:39 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 890/1251] eta: 0:03:03 lr: 0.000096 loss: 2.8511 (2.8621) grad_norm: 2.5159 (2.7061) time: 0.5038 [2021-03-27 00:03:44 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 900/1251] eta: 0:02:58 lr: 0.000096 loss: 2.8126 (2.8617) grad_norm: 2.5509 (2.7082) time: 0.5024 [2021-03-27 00:03:50 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 910/1251] eta: 0:02:53 lr: 0.000096 loss: 2.9647 (2.8614) grad_norm: 2.7752 (2.7093) time: 0.5050 [2021-03-27 00:03:55 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 920/1251] eta: 0:02:48 lr: 0.000096 loss: 2.9309 (2.8599) grad_norm: 2.6916 (2.7079) time: 0.5103 [2021-03-27 00:04:00 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 930/1251] eta: 0:02:43 lr: 0.000096 loss: 2.9015 (2.8598) grad_norm: 2.6560 (2.7095) time: 0.5093 [2021-03-27 00:04:05 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 940/1251] eta: 0:02:38 lr: 0.000096 loss: 2.8079 (2.8577) grad_norm: 2.6307 (2.7098) time: 0.5177 [2021-03-27 00:04:10 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 950/1251] eta: 0:02:33 lr: 0.000096 loss: 2.6251 (2.8572) grad_norm: 2.6307 (2.7139) time: 0.5215 [2021-03-27 00:04:15 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 960/1251] eta: 0:02:28 lr: 0.000096 loss: 3.0519 (2.8592) grad_norm: 2.6128 (2.7116) time: 0.5135 [2021-03-27 00:04:20 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 970/1251] eta: 0:02:23 lr: 0.000096 loss: 2.8939 (2.8597) grad_norm: 2.6010 (2.7100) time: 0.5023 [2021-03-27 00:04:25 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 980/1251] eta: 0:02:17 lr: 0.000096 loss: 2.8817 (2.8591) grad_norm: 2.4860 (2.7079) time: 0.4966 [2021-03-27 00:04:30 swin_small_patch4_window7_224] INFO: Epoch: [242] [ 990/1251] eta: 0:02:12 lr: 0.000096 loss: 2.9149 (2.8588) grad_norm: 2.4589 (2.7084) time: 0.4982 [2021-03-27 00:04:35 swin_small_patch4_window7_224] INFO: Epoch: [242] [1000/1251] eta: 0:02:07 lr: 0.000096 loss: 3.0092 (2.8607) grad_norm: 2.5030 (2.7079) time: 0.4971 [2021-03-27 00:04:40 swin_small_patch4_window7_224] INFO: Epoch: [242] [1010/1251] eta: 0:02:02 lr: 0.000096 loss: 2.8651 (2.8597) grad_norm: 2.5468 (2.7069) time: 0.5025 [2021-03-27 00:04:45 swin_small_patch4_window7_224] INFO: Epoch: [242] [1020/1251] eta: 0:01:57 lr: 0.000096 loss: 2.8093 (2.8591) grad_norm: 2.4574 (2.7052) time: 0.5038 [2021-03-27 00:04:50 swin_small_patch4_window7_224] INFO: Epoch: [242] [1030/1251] eta: 0:01:52 lr: 0.000096 loss: 2.9524 (2.8590) grad_norm: 2.5107 (2.7055) time: 0.4973 [2021-03-27 00:04:55 swin_small_patch4_window7_224] INFO: Epoch: [242] [1040/1251] eta: 0:01:47 lr: 0.000096 loss: 2.9524 (2.8590) grad_norm: 2.4896 (2.7040) time: 0.4994 [2021-03-27 00:05:00 swin_small_patch4_window7_224] INFO: Epoch: [242] [1050/1251] eta: 0:01:42 lr: 0.000096 loss: 2.8714 (2.8564) grad_norm: 2.4221 (2.7026) time: 0.5046 [2021-03-27 00:05:05 swin_small_patch4_window7_224] INFO: Epoch: [242] [1060/1251] eta: 0:01:37 lr: 0.000096 loss: 2.7905 (2.8553) grad_norm: 2.5655 (2.7019) time: 0.5070 [2021-03-27 00:05:10 swin_small_patch4_window7_224] INFO: Epoch: [242] [1070/1251] eta: 0:01:32 lr: 0.000096 loss: 2.8725 (2.8543) grad_norm: 2.4660 (2.6994) time: 0.5110 [2021-03-27 00:05:16 swin_small_patch4_window7_224] INFO: Epoch: [242] [1080/1251] eta: 0:01:26 lr: 0.000096 loss: 2.9428 (2.8551) grad_norm: 2.4660 (2.6993) time: 0.5094 [2021-03-27 00:05:21 swin_small_patch4_window7_224] INFO: Epoch: [242] [1090/1251] eta: 0:01:21 lr: 0.000096 loss: 3.0133 (2.8552) grad_norm: 2.5757 (2.6984) time: 0.5005 [2021-03-27 00:05:25 swin_small_patch4_window7_224] INFO: Epoch: [242] [1100/1251] eta: 0:01:16 lr: 0.000096 loss: 2.7344 (2.8522) grad_norm: 2.5757 (2.6984) time: 0.4938 [2021-03-27 00:05:30 swin_small_patch4_window7_224] INFO: Epoch: [242] [1110/1251] eta: 0:01:11 lr: 0.000096 loss: 2.6412 (2.8514) grad_norm: 2.6017 (2.6979) time: 0.4944 [2021-03-27 00:05:35 swin_small_patch4_window7_224] INFO: Epoch: [242] [1120/1251] eta: 0:01:06 lr: 0.000096 loss: 2.7236 (2.8503) grad_norm: 2.5968 (2.6977) time: 0.4984 [2021-03-27 00:05:40 swin_small_patch4_window7_224] INFO: Epoch: [242] [1130/1251] eta: 0:01:01 lr: 0.000096 loss: 2.8965 (2.8498) grad_norm: 2.4855 (2.6962) time: 0.5025 [2021-03-27 00:05:45 swin_small_patch4_window7_224] INFO: Epoch: [242] [1140/1251] eta: 0:00:56 lr: 0.000096 loss: 2.8300 (2.8487) grad_norm: 2.5457 (2.6957) time: 0.5036 [2021-03-27 00:05:50 swin_small_patch4_window7_224] INFO: Epoch: [242] [1150/1251] eta: 0:00:51 lr: 0.000096 loss: 2.7392 (2.8477) grad_norm: 2.5457 (inf) time: 0.5014 [2021-03-27 00:05:55 swin_small_patch4_window7_224] INFO: Epoch: [242] [1160/1251] eta: 0:00:46 lr: 0.000096 loss: 2.8038 (2.8474) grad_norm: 2.5007 (inf) time: 0.4997 [2021-03-27 00:06:00 swin_small_patch4_window7_224] INFO: Epoch: [242] [1170/1251] eta: 0:00:41 lr: 0.000096 loss: 2.8038 (2.8473) grad_norm: 2.5104 (inf) time: 0.4972 [2021-03-27 00:06:06 swin_small_patch4_window7_224] INFO: Epoch: [242] [1180/1251] eta: 0:00:36 lr: 0.000096 loss: 2.8943 (2.8469) grad_norm: 2.6316 (inf) time: 0.5011 [2021-03-27 00:06:11 swin_small_patch4_window7_224] INFO: Epoch: [242] [1190/1251] eta: 0:00:30 lr: 0.000096 loss: 2.7787 (2.8463) grad_norm: 2.6500 (inf) time: 0.5055 [2021-03-27 00:06:16 swin_small_patch4_window7_224] INFO: Epoch: [242] [1200/1251] eta: 0:00:25 lr: 0.000096 loss: 2.5894 (2.8446) grad_norm: 2.6979 (inf) time: 0.5008 [2021-03-27 00:06:20 swin_small_patch4_window7_224] INFO: Epoch: [242] [1210/1251] eta: 0:00:20 lr: 0.000096 loss: 2.9227 (2.8453) grad_norm: 2.5924 (inf) time: 0.4956 [2021-03-27 00:06:26 swin_small_patch4_window7_224] INFO: Epoch: [242] [1220/1251] eta: 0:00:15 lr: 0.000096 loss: 2.9754 (2.8460) grad_norm: 2.5266 (inf) time: 0.5006 [2021-03-27 00:06:30 swin_small_patch4_window7_224] INFO: Epoch: [242] [1230/1251] eta: 0:00:10 lr: 0.000096 loss: 2.9827 (2.8459) grad_norm: 2.4806 (inf) time: 0.5011 [2021-03-27 00:06:35 swin_small_patch4_window7_224] INFO: Epoch: [242] [1240/1251] eta: 0:00:05 lr: 0.000096 loss: 2.7471 (2.8439) grad_norm: 2.5177 (inf) time: 0.4944 [2021-03-27 00:06:40 swin_small_patch4_window7_224] INFO: Epoch: [242] [1250/1251] eta: 0:00:00 lr: 0.000096 loss: 2.5137 (2.8425) grad_norm: 2.4853 (inf) time: 0.4980 [2021-03-27 00:06:47 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 1.0479 (1.0479) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-27 00:06:50 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7701 (0.7490) acc1: 82.8125 (80.8239) acc5: 95.3125 (96.4489) [2021-03-27 00:06:52 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7462 (0.7877) acc1: 81.2500 (80.2083) acc5: 95.3125 (96.2798) [2021-03-27 00:06:54 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7421 (0.7883) acc1: 81.2500 (80.8972) acc5: 96.8750 (96.1694) [2021-03-27 00:06:56 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7362 (0.7908) acc1: 81.2500 (80.7927) acc5: 96.8750 (96.1890) [2021-03-27 00:06:57 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7072 (0.7730) acc1: 82.8125 (81.5360) acc5: 95.3125 (96.1280) [2021-03-27 00:07:08 swin_small_patch4_window7_224] INFO: * Acc@1 82.072 Acc@5 96.012 loss 0.763 [2021-03-27 00:07:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-27 00:07:08 swin_small_patch4_window7_224] INFO: Max accuracy: 82.11% [2021-03-27 00:07:11 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 0/1251] eta: 1:22:35 lr: 0.000096 loss: 2.7429 (2.7429) grad_norm: 2.7940 (2.7940) time: 3.9614 [2021-03-27 00:07:17 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 10/1251] eta: 0:17:25 lr: 0.000096 loss: 2.9991 (2.8967) grad_norm: 2.6442 (2.7915) time: 0.8422 [2021-03-27 00:07:22 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 20/1251] eta: 0:14:01 lr: 0.000096 loss: 3.0698 (3.0419) grad_norm: 2.6085 (2.7033) time: 0.5199 [2021-03-27 00:07:27 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 30/1251] eta: 0:12:45 lr: 0.000096 loss: 3.0843 (2.9853) grad_norm: 2.5876 (2.8252) time: 0.5084 [2021-03-27 00:07:32 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 40/1251] eta: 0:12:08 lr: 0.000096 loss: 2.8410 (2.9399) grad_norm: 2.6539 (2.8141) time: 0.5158 [2021-03-27 00:07:37 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 50/1251] eta: 0:11:37 lr: 0.000095 loss: 2.9455 (2.9543) grad_norm: 2.6828 (2.7691) time: 0.5102 [2021-03-27 00:07:42 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 60/1251] eta: 0:11:17 lr: 0.000095 loss: 3.0973 (2.9656) grad_norm: 2.6828 (2.7697) time: 0.5001 [2021-03-27 00:07:47 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 70/1251] eta: 0:10:59 lr: 0.000095 loss: 2.8856 (2.9059) grad_norm: 2.5814 (2.7391) time: 0.5019 [2021-03-27 00:07:52 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 80/1251] eta: 0:10:46 lr: 0.000095 loss: 2.7564 (2.9114) grad_norm: 2.4749 (2.7179) time: 0.5038 [2021-03-27 00:07:57 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 90/1251] eta: 0:10:36 lr: 0.000095 loss: 2.8950 (2.8983) grad_norm: 2.5839 (2.7187) time: 0.5127 [2021-03-27 00:08:03 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 100/1251] eta: 0:10:27 lr: 0.000095 loss: 2.8950 (2.9045) grad_norm: 2.4224 (2.7047) time: 0.5138 [2021-03-27 00:08:08 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 110/1251] eta: 0:10:19 lr: 0.000095 loss: 2.9450 (2.8890) grad_norm: 2.3736 (2.6831) time: 0.5185 [2021-03-27 00:08:13 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 120/1251] eta: 0:10:11 lr: 0.000095 loss: 2.7871 (2.8756) grad_norm: 2.3805 (2.7036) time: 0.5204 [2021-03-27 00:08:18 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 130/1251] eta: 0:10:04 lr: 0.000095 loss: 2.7756 (2.8765) grad_norm: 2.4533 (2.6906) time: 0.5157 [2021-03-27 00:08:23 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 140/1251] eta: 0:09:55 lr: 0.000095 loss: 3.0049 (2.8903) grad_norm: 2.4333 (2.6756) time: 0.5064 [2021-03-27 00:08:28 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 150/1251] eta: 0:09:47 lr: 0.000095 loss: 3.0343 (2.8872) grad_norm: 2.4867 (2.6721) time: 0.4975 [2021-03-27 00:08:33 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 160/1251] eta: 0:09:39 lr: 0.000095 loss: 2.8795 (2.8829) grad_norm: 2.6021 (nan) time: 0.4995 [2021-03-27 00:08:38 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 170/1251] eta: 0:09:32 lr: 0.000095 loss: 2.8610 (2.8793) grad_norm: 2.6021 (nan) time: 0.5040 [2021-03-27 00:08:43 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 180/1251] eta: 0:09:26 lr: 0.000095 loss: 2.9410 (2.8788) grad_norm: 2.5281 (nan) time: 0.5092 [2021-03-27 00:08:48 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 190/1251] eta: 0:09:19 lr: 0.000095 loss: 2.9804 (2.8832) grad_norm: 2.5393 (nan) time: 0.5028 [2021-03-27 00:08:53 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 200/1251] eta: 0:09:12 lr: 0.000095 loss: 2.9280 (2.8796) grad_norm: 2.5949 (nan) time: 0.4962 [2021-03-27 00:08:58 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 210/1251] eta: 0:09:06 lr: 0.000095 loss: 2.9280 (2.8891) grad_norm: 2.5367 (nan) time: 0.5070 [2021-03-27 00:09:03 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 220/1251] eta: 0:09:00 lr: 0.000095 loss: 3.1602 (2.8910) grad_norm: 2.5809 (nan) time: 0.5133 [2021-03-27 00:09:09 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 230/1251] eta: 0:08:54 lr: 0.000095 loss: 2.8668 (2.8783) grad_norm: 2.5768 (nan) time: 0.5061 [2021-03-27 00:09:14 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 240/1251] eta: 0:08:48 lr: 0.000095 loss: 2.6568 (2.8739) grad_norm: 2.4565 (nan) time: 0.5020 [2021-03-27 00:09:19 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 250/1251] eta: 0:08:42 lr: 0.000095 loss: 2.8391 (2.8762) grad_norm: 2.5484 (nan) time: 0.4988 [2021-03-27 00:09:23 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 260/1251] eta: 0:08:36 lr: 0.000095 loss: 2.9164 (2.8739) grad_norm: 2.6628 (nan) time: 0.4977 [2021-03-27 00:09:29 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 270/1251] eta: 0:08:30 lr: 0.000095 loss: 3.0758 (2.8797) grad_norm: 2.4655 (nan) time: 0.5001 [2021-03-27 00:09:33 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 280/1251] eta: 0:08:23 lr: 0.000095 loss: 3.0803 (2.8760) grad_norm: 2.5103 (nan) time: 0.4965 [2021-03-27 00:09:39 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 290/1251] eta: 0:08:18 lr: 0.000095 loss: 2.9577 (2.8780) grad_norm: 2.5613 (nan) time: 0.5024 [2021-03-27 00:09:44 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 300/1251] eta: 0:08:12 lr: 0.000095 loss: 3.0074 (2.8852) grad_norm: 2.5379 (nan) time: 0.5081 [2021-03-27 00:09:49 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 310/1251] eta: 0:08:07 lr: 0.000095 loss: 3.0565 (2.8855) grad_norm: 2.5379 (nan) time: 0.5061 [2021-03-27 00:09:54 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 320/1251] eta: 0:08:02 lr: 0.000095 loss: 2.9329 (2.8828) grad_norm: 2.5670 (nan) time: 0.5148 [2021-03-27 00:09:59 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 330/1251] eta: 0:07:57 lr: 0.000095 loss: 2.9329 (2.8874) grad_norm: 2.6432 (nan) time: 0.5172 [2021-03-27 00:10:04 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 340/1251] eta: 0:07:51 lr: 0.000095 loss: 2.8647 (2.8840) grad_norm: 2.4717 (nan) time: 0.5105 [2021-03-27 00:10:09 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 350/1251] eta: 0:07:45 lr: 0.000095 loss: 2.8647 (2.8860) grad_norm: 2.3452 (nan) time: 0.5027 [2021-03-27 00:10:14 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 360/1251] eta: 0:07:40 lr: 0.000095 loss: 2.9178 (2.8821) grad_norm: 2.5791 (nan) time: 0.4969 [2021-03-27 00:10:19 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 370/1251] eta: 0:07:34 lr: 0.000095 loss: 2.9810 (2.8855) grad_norm: 2.5228 (nan) time: 0.5036 [2021-03-27 00:10:24 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 380/1251] eta: 0:07:29 lr: 0.000095 loss: 3.1303 (2.8891) grad_norm: 2.3725 (nan) time: 0.5042 [2021-03-27 00:10:29 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 390/1251] eta: 0:07:23 lr: 0.000095 loss: 3.0900 (2.8919) grad_norm: 2.7159 (nan) time: 0.4996 [2021-03-27 00:10:34 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 400/1251] eta: 0:07:18 lr: 0.000095 loss: 3.0573 (2.8965) grad_norm: 2.7159 (nan) time: 0.5042 [2021-03-27 00:10:39 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 410/1251] eta: 0:07:13 lr: 0.000095 loss: 3.0573 (2.8993) grad_norm: 2.5014 (nan) time: 0.5033 [2021-03-27 00:10:44 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 420/1251] eta: 0:07:07 lr: 0.000095 loss: 2.8030 (2.8946) grad_norm: 2.5031 (nan) time: 0.4965 [2021-03-27 00:10:49 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 430/1251] eta: 0:07:01 lr: 0.000095 loss: 2.8013 (2.8923) grad_norm: 2.5940 (nan) time: 0.4928 [2021-03-27 00:10:54 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 440/1251] eta: 0:06:56 lr: 0.000095 loss: 2.8818 (2.8888) grad_norm: 2.5097 (nan) time: 0.4943 [2021-03-27 00:10:59 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 450/1251] eta: 0:06:51 lr: 0.000095 loss: 2.7628 (2.8837) grad_norm: 2.3191 (nan) time: 0.5025 [2021-03-27 00:11:04 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 460/1251] eta: 0:06:45 lr: 0.000095 loss: 2.7459 (2.8810) grad_norm: 2.4172 (nan) time: 0.5083 [2021-03-27 00:11:09 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 470/1251] eta: 0:06:40 lr: 0.000095 loss: 2.8260 (2.8785) grad_norm: 2.7327 (nan) time: 0.5058 [2021-03-27 00:11:14 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 480/1251] eta: 0:06:35 lr: 0.000094 loss: 2.8344 (2.8780) grad_norm: 2.8414 (nan) time: 0.5035 [2021-03-27 00:11:19 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 490/1251] eta: 0:06:30 lr: 0.000094 loss: 2.9093 (2.8773) grad_norm: 2.4874 (nan) time: 0.5031 [2021-03-27 00:11:24 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 500/1251] eta: 0:06:24 lr: 0.000094 loss: 3.0766 (2.8787) grad_norm: 2.4106 (nan) time: 0.5002 [2021-03-27 00:11:29 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 510/1251] eta: 0:06:19 lr: 0.000094 loss: 3.1611 (2.8818) grad_norm: 2.4308 (nan) time: 0.4971 [2021-03-27 00:11:34 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 520/1251] eta: 0:06:14 lr: 0.000094 loss: 3.0296 (2.8838) grad_norm: 2.4788 (nan) time: 0.4962 [2021-03-27 00:11:39 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 530/1251] eta: 0:06:08 lr: 0.000094 loss: 2.9751 (2.8844) grad_norm: 2.3356 (nan) time: 0.5000 [2021-03-27 00:11:44 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 540/1251] eta: 0:06:03 lr: 0.000094 loss: 2.9751 (2.8854) grad_norm: 2.3566 (nan) time: 0.5074 [2021-03-27 00:11:49 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 550/1251] eta: 0:05:58 lr: 0.000094 loss: 2.9188 (2.8854) grad_norm: 2.4841 (nan) time: 0.5049 [2021-03-27 00:11:54 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 560/1251] eta: 0:05:53 lr: 0.000094 loss: 2.6880 (2.8809) grad_norm: 2.4288 (nan) time: 0.5037 [2021-03-27 00:11:59 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 570/1251] eta: 0:05:48 lr: 0.000094 loss: 2.8137 (2.8788) grad_norm: 2.3654 (nan) time: 0.5037 [2021-03-27 00:12:04 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 580/1251] eta: 0:05:42 lr: 0.000094 loss: 2.8995 (2.8806) grad_norm: 2.4923 (nan) time: 0.5000 [2021-03-27 00:12:10 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 590/1251] eta: 0:05:37 lr: 0.000094 loss: 2.9281 (2.8806) grad_norm: 2.6435 (nan) time: 0.5049 [2021-03-27 00:12:15 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 600/1251] eta: 0:05:32 lr: 0.000094 loss: 2.9303 (2.8808) grad_norm: 2.7052 (nan) time: 0.5061 [2021-03-27 00:12:20 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 610/1251] eta: 0:05:27 lr: 0.000094 loss: 2.9605 (2.8784) grad_norm: 2.6189 (nan) time: 0.5086 [2021-03-27 00:12:25 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 620/1251] eta: 0:05:22 lr: 0.000094 loss: 2.9616 (2.8788) grad_norm: 2.4850 (nan) time: 0.5074 [2021-03-27 00:12:30 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 630/1251] eta: 0:05:17 lr: 0.000094 loss: 2.8380 (2.8779) grad_norm: 2.4121 (nan) time: 0.5026 [2021-03-27 00:12:35 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 640/1251] eta: 0:05:11 lr: 0.000094 loss: 2.8380 (2.8780) grad_norm: 2.3736 (nan) time: 0.5062 [2021-03-27 00:12:40 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 650/1251] eta: 0:05:06 lr: 0.000094 loss: 2.8386 (2.8750) grad_norm: 2.4062 (nan) time: 0.5083 [2021-03-27 00:12:45 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 660/1251] eta: 0:05:01 lr: 0.000094 loss: 2.8386 (2.8721) grad_norm: 2.4150 (nan) time: 0.5073 [2021-03-27 00:12:50 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 670/1251] eta: 0:04:56 lr: 0.000094 loss: 3.0738 (2.8739) grad_norm: 2.4150 (nan) time: 0.5055 [2021-03-27 00:12:55 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 680/1251] eta: 0:04:51 lr: 0.000094 loss: 2.9802 (2.8724) grad_norm: 2.4940 (nan) time: 0.5044 [2021-03-27 00:13:00 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 690/1251] eta: 0:04:46 lr: 0.000094 loss: 2.7946 (2.8722) grad_norm: 2.6036 (nan) time: 0.4992 [2021-03-27 00:13:05 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 700/1251] eta: 0:04:40 lr: 0.000094 loss: 2.7946 (2.8692) grad_norm: 2.5663 (nan) time: 0.4966 [2021-03-27 00:13:10 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 710/1251] eta: 0:04:35 lr: 0.000094 loss: 2.7599 (2.8667) grad_norm: 2.3805 (nan) time: 0.4993 [2021-03-27 00:13:15 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 720/1251] eta: 0:04:30 lr: 0.000094 loss: 2.7937 (2.8655) grad_norm: 2.3756 (nan) time: 0.5000 [2021-03-27 00:13:20 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 730/1251] eta: 0:04:25 lr: 0.000094 loss: 2.9593 (2.8657) grad_norm: 2.4893 (nan) time: 0.5062 [2021-03-27 00:13:25 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 740/1251] eta: 0:04:20 lr: 0.000094 loss: 2.8656 (2.8614) grad_norm: 2.5596 (nan) time: 0.5155 [2021-03-27 00:13:30 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 750/1251] eta: 0:04:15 lr: 0.000094 loss: 2.6722 (2.8587) grad_norm: 2.4767 (nan) time: 0.5145 [2021-03-27 00:13:36 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 760/1251] eta: 0:04:10 lr: 0.000094 loss: 2.7103 (2.8584) grad_norm: 2.7126 (nan) time: 0.5079 [2021-03-27 00:13:40 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 770/1251] eta: 0:04:05 lr: 0.000094 loss: 3.0089 (2.8599) grad_norm: 2.7960 (nan) time: 0.4981 [2021-03-27 00:13:46 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 780/1251] eta: 0:03:59 lr: 0.000094 loss: 2.8423 (2.8572) grad_norm: 2.6342 (nan) time: 0.5010 [2021-03-27 00:13:51 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 790/1251] eta: 0:03:54 lr: 0.000094 loss: 3.0710 (2.8588) grad_norm: 2.6487 (nan) time: 0.5075 [2021-03-27 00:13:56 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 800/1251] eta: 0:03:49 lr: 0.000094 loss: 3.1289 (2.8612) grad_norm: 2.7222 (nan) time: 0.5051 [2021-03-27 00:14:01 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 810/1251] eta: 0:03:44 lr: 0.000094 loss: 3.0174 (2.8624) grad_norm: 2.3483 (nan) time: 0.5020 [2021-03-27 00:14:06 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 820/1251] eta: 0:03:39 lr: 0.000094 loss: 2.8615 (2.8614) grad_norm: 2.3755 (nan) time: 0.4963 [2021-03-27 00:14:11 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 830/1251] eta: 0:03:34 lr: 0.000094 loss: 2.8615 (2.8608) grad_norm: 2.4590 (nan) time: 0.5022 [2021-03-27 00:14:16 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 840/1251] eta: 0:03:29 lr: 0.000094 loss: 2.8293 (2.8611) grad_norm: 2.4590 (nan) time: 0.5076 [2021-03-27 00:14:21 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 850/1251] eta: 0:03:24 lr: 0.000094 loss: 2.8832 (2.8622) grad_norm: 2.4623 (nan) time: 0.5144 [2021-03-27 00:14:26 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 860/1251] eta: 0:03:19 lr: 0.000094 loss: 2.8050 (2.8601) grad_norm: 2.5167 (nan) time: 0.5117 [2021-03-27 00:14:31 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 870/1251] eta: 0:03:13 lr: 0.000094 loss: 2.7138 (2.8591) grad_norm: 2.5310 (nan) time: 0.5094 [2021-03-27 00:14:36 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 880/1251] eta: 0:03:08 lr: 0.000094 loss: 2.7138 (2.8576) grad_norm: 2.5310 (nan) time: 0.5122 [2021-03-27 00:14:41 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 890/1251] eta: 0:03:03 lr: 0.000094 loss: 2.8526 (2.8606) grad_norm: 2.4955 (nan) time: 0.5007 [2021-03-27 00:14:46 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 900/1251] eta: 0:02:58 lr: 0.000094 loss: 3.0565 (2.8606) grad_norm: 2.5169 (nan) time: 0.4985 [2021-03-27 00:14:51 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 910/1251] eta: 0:02:53 lr: 0.000093 loss: 3.0350 (2.8628) grad_norm: 2.5966 (nan) time: 0.5028 [2021-03-27 00:14:56 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 920/1251] eta: 0:02:48 lr: 0.000093 loss: 3.0586 (2.8643) grad_norm: 2.8193 (nan) time: 0.4980 [2021-03-27 00:15:01 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 930/1251] eta: 0:02:43 lr: 0.000093 loss: 2.9745 (2.8649) grad_norm: 2.6748 (nan) time: 0.4985 [2021-03-27 00:15:06 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 940/1251] eta: 0:02:38 lr: 0.000093 loss: 3.0592 (2.8673) grad_norm: 2.4304 (nan) time: 0.5067 [2021-03-27 00:15:11 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 950/1251] eta: 0:02:33 lr: 0.000093 loss: 3.0253 (2.8654) grad_norm: 2.5539 (nan) time: 0.5097 [2021-03-27 00:15:16 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 960/1251] eta: 0:02:28 lr: 0.000093 loss: 2.8820 (2.8667) grad_norm: 2.5216 (nan) time: 0.5086 [2021-03-27 00:15:21 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 970/1251] eta: 0:02:22 lr: 0.000093 loss: 2.9239 (2.8667) grad_norm: 2.5133 (nan) time: 0.5027 [2021-03-27 00:15:27 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 980/1251] eta: 0:02:17 lr: 0.000093 loss: 2.9959 (2.8679) grad_norm: 2.6362 (nan) time: 0.5030 [2021-03-27 00:15:32 swin_small_patch4_window7_224] INFO: Epoch: [243] [ 990/1251] eta: 0:02:12 lr: 0.000093 loss: 3.0223 (2.8691) grad_norm: 2.4828 (nan) time: 0.5053 [2021-03-27 00:15:37 swin_small_patch4_window7_224] INFO: Epoch: [243] [1000/1251] eta: 0:02:07 lr: 0.000093 loss: 2.9703 (2.8691) grad_norm: 2.3902 (nan) time: 0.5027 [2021-03-27 00:15:42 swin_small_patch4_window7_224] INFO: Epoch: [243] [1010/1251] eta: 0:02:02 lr: 0.000093 loss: 2.9794 (2.8696) grad_norm: 2.5585 (nan) time: 0.5045 [2021-03-27 00:15:47 swin_small_patch4_window7_224] INFO: Epoch: [243] [1020/1251] eta: 0:01:57 lr: 0.000093 loss: 3.0166 (2.8707) grad_norm: 2.4704 (nan) time: 0.5052 [2021-03-27 00:15:52 swin_small_patch4_window7_224] INFO: Epoch: [243] [1030/1251] eta: 0:01:52 lr: 0.000093 loss: 3.0836 (2.8725) grad_norm: 2.4299 (nan) time: 0.5035 [2021-03-27 00:15:57 swin_small_patch4_window7_224] INFO: Epoch: [243] [1040/1251] eta: 0:01:47 lr: 0.000093 loss: 3.0928 (2.8751) grad_norm: 2.4309 (nan) time: 0.5069 [2021-03-27 00:16:02 swin_small_patch4_window7_224] INFO: Epoch: [243] [1050/1251] eta: 0:01:42 lr: 0.000093 loss: 2.9800 (2.8742) grad_norm: 2.4399 (nan) time: 0.5074 [2021-03-27 00:16:07 swin_small_patch4_window7_224] INFO: Epoch: [243] [1060/1251] eta: 0:01:37 lr: 0.000093 loss: 2.8116 (2.8731) grad_norm: 2.3434 (nan) time: 0.5099 [2021-03-27 00:16:12 swin_small_patch4_window7_224] INFO: Epoch: [243] [1070/1251] eta: 0:01:32 lr: 0.000093 loss: 2.9662 (2.8738) grad_norm: 2.3707 (nan) time: 0.5180 [2021-03-27 00:16:17 swin_small_patch4_window7_224] INFO: Epoch: [243] [1080/1251] eta: 0:01:26 lr: 0.000093 loss: 2.9662 (2.8751) grad_norm: 2.6620 (nan) time: 0.5144 [2021-03-27 00:16:22 swin_small_patch4_window7_224] INFO: Epoch: [243] [1090/1251] eta: 0:01:21 lr: 0.000093 loss: 2.9404 (2.8739) grad_norm: 2.6948 (nan) time: 0.5051 [2021-03-27 00:16:27 swin_small_patch4_window7_224] INFO: Epoch: [243] [1100/1251] eta: 0:01:16 lr: 0.000093 loss: 3.0519 (2.8728) grad_norm: 2.5142 (nan) time: 0.5037 [2021-03-27 00:16:32 swin_small_patch4_window7_224] INFO: Epoch: [243] [1110/1251] eta: 0:01:11 lr: 0.000093 loss: 3.1182 (2.8735) grad_norm: 2.6046 (nan) time: 0.4975 [2021-03-27 00:16:37 swin_small_patch4_window7_224] INFO: Epoch: [243] [1120/1251] eta: 0:01:06 lr: 0.000093 loss: 2.8344 (2.8695) grad_norm: 2.6398 (nan) time: 0.4964 [2021-03-27 00:16:42 swin_small_patch4_window7_224] INFO: Epoch: [243] [1130/1251] eta: 0:01:01 lr: 0.000093 loss: 2.8841 (2.8713) grad_norm: 2.4801 (nan) time: 0.5036 [2021-03-27 00:16:47 swin_small_patch4_window7_224] INFO: Epoch: [243] [1140/1251] eta: 0:00:56 lr: 0.000093 loss: 3.2104 (2.8714) grad_norm: 2.4801 (nan) time: 0.5023 [2021-03-27 00:16:52 swin_small_patch4_window7_224] INFO: Epoch: [243] [1150/1251] eta: 0:00:51 lr: 0.000093 loss: 3.0301 (2.8711) grad_norm: 2.5108 (nan) time: 0.5013 [2021-03-27 00:16:57 swin_small_patch4_window7_224] INFO: Epoch: [243] [1160/1251] eta: 0:00:46 lr: 0.000093 loss: 2.6982 (2.8681) grad_norm: 2.5656 (nan) time: 0.5024 [2021-03-27 00:17:02 swin_small_patch4_window7_224] INFO: Epoch: [243] [1170/1251] eta: 0:00:41 lr: 0.000093 loss: 2.6186 (2.8661) grad_norm: 2.7173 (nan) time: 0.5017 [2021-03-27 00:17:07 swin_small_patch4_window7_224] INFO: Epoch: [243] [1180/1251] eta: 0:00:36 lr: 0.000093 loss: 2.8112 (2.8654) grad_norm: 2.6166 (nan) time: 0.5009 [2021-03-27 00:17:12 swin_small_patch4_window7_224] INFO: Epoch: [243] [1190/1251] eta: 0:00:30 lr: 0.000093 loss: 2.5180 (2.8628) grad_norm: 2.4752 (nan) time: 0.4990 [2021-03-27 00:17:17 swin_small_patch4_window7_224] INFO: Epoch: [243] [1200/1251] eta: 0:00:25 lr: 0.000093 loss: 2.2561 (2.8602) grad_norm: 2.4752 (nan) time: 0.4974 [2021-03-27 00:17:22 swin_small_patch4_window7_224] INFO: Epoch: [243] [1210/1251] eta: 0:00:20 lr: 0.000093 loss: 2.6008 (2.8586) grad_norm: 2.6873 (nan) time: 0.5017 [2021-03-27 00:17:27 swin_small_patch4_window7_224] INFO: Epoch: [243] [1220/1251] eta: 0:00:15 lr: 0.000093 loss: 2.8536 (2.8582) grad_norm: 2.6488 (nan) time: 0.5009 [2021-03-27 00:17:32 swin_small_patch4_window7_224] INFO: Epoch: [243] [1230/1251] eta: 0:00:10 lr: 0.000093 loss: 2.8972 (2.8592) grad_norm: 2.3460 (nan) time: 0.5001 [2021-03-27 00:17:38 swin_small_patch4_window7_224] INFO: Epoch: [243] [1240/1251] eta: 0:00:05 lr: 0.000093 loss: 2.8718 (2.8584) grad_norm: 2.4775 (nan) time: 0.5057 [2021-03-27 00:17:42 swin_small_patch4_window7_224] INFO: Epoch: [243] [1250/1251] eta: 0:00:00 lr: 0.000093 loss: 2.8481 (2.8577) grad_norm: 2.5024 (nan) time: 0.4996 [2021-03-27 00:17:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:47 loss: 0.6581 (0.6581) acc1: 87.5000 (87.5000) acc5: 98.4375 (98.4375) [2021-03-27 00:17:54 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7868 (0.7445) acc1: 81.2500 (82.1023) acc5: 96.8750 (96.4489) [2021-03-27 00:17:56 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8326 (0.7973) acc1: 81.2500 (80.5804) acc5: 95.3125 (95.9077) [2021-03-27 00:17:58 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7932 (0.7756) acc1: 82.8125 (81.4516) acc5: 95.3125 (96.0685) [2021-03-27 00:18:00 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7154 (0.7664) acc1: 82.8125 (81.5168) acc5: 96.8750 (96.1128) [2021-03-27 00:18:01 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7355 (0.7705) acc1: 82.8125 (81.4080) acc5: 96.8750 (96.0960) [2021-03-27 00:18:08 swin_small_patch4_window7_224] INFO: * Acc@1 82.140 Acc@5 96.004 loss 0.757 [2021-03-27 00:18:08 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.1% [2021-03-27 00:18:08 swin_small_patch4_window7_224] INFO: Max accuracy: 82.14% [2021-03-27 00:18:13 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 0/1251] eta: 1:32:19 lr: 0.000093 loss: 2.5305 (2.5305) grad_norm: 2.2053 (2.2053) time: 4.4283 [2021-03-27 00:18:18 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 10/1251] eta: 0:18:05 lr: 0.000093 loss: 2.8979 (2.9053) grad_norm: 2.8794 (2.8846) time: 0.8744 [2021-03-27 00:18:23 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 20/1251] eta: 0:14:17 lr: 0.000093 loss: 3.0028 (2.9581) grad_norm: 2.6189 (2.7611) time: 0.5102 [2021-03-27 00:18:28 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 30/1251] eta: 0:12:54 lr: 0.000093 loss: 3.0600 (2.9799) grad_norm: 2.5571 (2.6880) time: 0.5023 [2021-03-27 00:18:33 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 40/1251] eta: 0:12:11 lr: 0.000093 loss: 3.0076 (2.9515) grad_norm: 2.5111 (2.7169) time: 0.5061 [2021-03-27 00:18:38 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 50/1251] eta: 0:11:42 lr: 0.000093 loss: 2.9150 (2.9156) grad_norm: 2.6873 (2.7396) time: 0.5091 [2021-03-27 00:18:43 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 60/1251] eta: 0:11:20 lr: 0.000093 loss: 2.9150 (2.9390) grad_norm: 2.7373 (2.7506) time: 0.5049 [2021-03-27 00:18:48 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 70/1251] eta: 0:11:02 lr: 0.000093 loss: 3.0212 (2.9530) grad_norm: 2.6886 (2.7928) time: 0.4979 [2021-03-27 00:18:53 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 80/1251] eta: 0:10:51 lr: 0.000093 loss: 2.9363 (2.9350) grad_norm: 2.7009 (2.8016) time: 0.5104 [2021-03-27 00:18:58 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 90/1251] eta: 0:10:40 lr: 0.000092 loss: 2.9316 (2.9146) grad_norm: 2.7727 (2.8305) time: 0.5202 [2021-03-27 00:19:04 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 100/1251] eta: 0:10:30 lr: 0.000092 loss: 2.9342 (2.9012) grad_norm: 2.7128 (2.8217) time: 0.5150 [2021-03-27 00:19:09 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 110/1251] eta: 0:10:20 lr: 0.000092 loss: 3.0576 (2.9149) grad_norm: 2.6835 (2.8109) time: 0.5063 [2021-03-27 00:19:14 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 120/1251] eta: 0:10:10 lr: 0.000092 loss: 3.1030 (2.9103) grad_norm: 2.6349 (2.7945) time: 0.4991 [2021-03-27 00:19:18 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 130/1251] eta: 0:10:01 lr: 0.000092 loss: 3.0866 (2.9099) grad_norm: 2.4652 (2.7767) time: 0.4977 [2021-03-27 00:19:24 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 140/1251] eta: 0:09:53 lr: 0.000092 loss: 2.8426 (2.8901) grad_norm: 2.4908 (2.7796) time: 0.5020 [2021-03-27 00:19:29 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 150/1251] eta: 0:09:46 lr: 0.000092 loss: 2.8358 (2.8858) grad_norm: 2.4908 (2.7739) time: 0.5062 [2021-03-27 00:19:34 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 160/1251] eta: 0:09:39 lr: 0.000092 loss: 2.9076 (2.8873) grad_norm: 2.5883 (2.7938) time: 0.5046 [2021-03-27 00:19:39 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 170/1251] eta: 0:09:32 lr: 0.000092 loss: 2.9076 (2.8909) grad_norm: 2.9211 (2.8301) time: 0.5043 [2021-03-27 00:19:44 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 180/1251] eta: 0:09:26 lr: 0.000092 loss: 2.8668 (2.8842) grad_norm: 2.8126 (2.8219) time: 0.5093 [2021-03-27 00:19:49 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 190/1251] eta: 0:09:19 lr: 0.000092 loss: 2.5654 (2.8751) grad_norm: 2.6115 (2.8548) time: 0.5085 [2021-03-27 00:19:54 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 200/1251] eta: 0:09:12 lr: 0.000092 loss: 2.5886 (2.8689) grad_norm: 2.6115 (2.8491) time: 0.5036 [2021-03-27 00:19:59 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 210/1251] eta: 0:09:06 lr: 0.000092 loss: 2.8831 (2.8745) grad_norm: 2.6065 (2.8380) time: 0.5063 [2021-03-27 00:20:04 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 220/1251] eta: 0:09:00 lr: 0.000092 loss: 2.8168 (2.8652) grad_norm: 2.6078 (2.8332) time: 0.5027 [2021-03-27 00:20:09 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 230/1251] eta: 0:08:53 lr: 0.000092 loss: 2.7669 (2.8589) grad_norm: 2.5187 (2.8261) time: 0.5008 [2021-03-27 00:20:14 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 240/1251] eta: 0:08:47 lr: 0.000092 loss: 2.9817 (2.8646) grad_norm: 2.6459 (2.8410) time: 0.5034 [2021-03-27 00:20:19 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 250/1251] eta: 0:08:42 lr: 0.000092 loss: 2.8982 (2.8588) grad_norm: 2.6924 (2.8340) time: 0.5044 [2021-03-27 00:20:24 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 260/1251] eta: 0:08:36 lr: 0.000092 loss: 2.8704 (2.8585) grad_norm: 2.6125 (2.8359) time: 0.5030 [2021-03-27 00:20:29 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 270/1251] eta: 0:08:30 lr: 0.000092 loss: 2.9942 (2.8667) grad_norm: 2.5408 (2.8478) time: 0.5036 [2021-03-27 00:20:34 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 280/1251] eta: 0:08:24 lr: 0.000092 loss: 2.9348 (2.8629) grad_norm: 2.5964 (2.8433) time: 0.5031 [2021-03-27 00:20:39 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 290/1251] eta: 0:08:18 lr: 0.000092 loss: 2.9348 (2.8705) grad_norm: 2.6187 (2.8386) time: 0.4997 [2021-03-27 00:20:44 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 300/1251] eta: 0:08:12 lr: 0.000092 loss: 2.9604 (2.8697) grad_norm: 2.5686 (2.8306) time: 0.5017 [2021-03-27 00:20:49 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 310/1251] eta: 0:08:07 lr: 0.000092 loss: 3.0687 (2.8731) grad_norm: 2.5437 (2.8285) time: 0.5037 [2021-03-27 00:20:54 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 320/1251] eta: 0:08:01 lr: 0.000092 loss: 3.0687 (2.8770) grad_norm: 2.7464 (2.8265) time: 0.5013 [2021-03-27 00:20:59 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 330/1251] eta: 0:07:55 lr: 0.000092 loss: 2.8655 (2.8712) grad_norm: 2.7109 (2.8240) time: 0.5016 [2021-03-27 00:21:04 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 340/1251] eta: 0:07:50 lr: 0.000092 loss: 2.6672 (2.8688) grad_norm: 2.6254 (2.8239) time: 0.5024 [2021-03-27 00:21:09 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 350/1251] eta: 0:07:44 lr: 0.000092 loss: 2.7995 (2.8665) grad_norm: 2.4646 (2.8168) time: 0.5024 [2021-03-27 00:21:14 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 360/1251] eta: 0:07:39 lr: 0.000092 loss: 3.0440 (2.8743) grad_norm: 2.4447 (2.8104) time: 0.5029 [2021-03-27 00:21:19 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 370/1251] eta: 0:07:34 lr: 0.000092 loss: 3.0083 (2.8667) grad_norm: 2.3734 (2.7982) time: 0.5057 [2021-03-27 00:21:24 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 380/1251] eta: 0:07:28 lr: 0.000092 loss: 2.9789 (2.8693) grad_norm: 2.4867 (2.7965) time: 0.5051 [2021-03-27 00:21:29 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 390/1251] eta: 0:07:23 lr: 0.000092 loss: 2.9789 (2.8644) grad_norm: 2.5352 (2.7886) time: 0.4974 [2021-03-27 00:21:34 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 400/1251] eta: 0:07:17 lr: 0.000092 loss: 2.5798 (2.8607) grad_norm: 2.4680 (2.7820) time: 0.4981 [2021-03-27 00:21:39 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 410/1251] eta: 0:07:12 lr: 0.000092 loss: 2.9190 (2.8660) grad_norm: 2.4226 (2.7746) time: 0.4989 [2021-03-27 00:21:44 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 420/1251] eta: 0:07:06 lr: 0.000092 loss: 2.9190 (2.8656) grad_norm: 2.3607 (2.7666) time: 0.4995 [2021-03-27 00:21:49 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 430/1251] eta: 0:07:01 lr: 0.000092 loss: 3.1040 (2.8727) grad_norm: 2.5344 (2.7676) time: 0.5039 [2021-03-27 00:21:54 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 440/1251] eta: 0:06:56 lr: 0.000092 loss: 3.1040 (2.8709) grad_norm: 2.5888 (2.7643) time: 0.5015 [2021-03-27 00:22:00 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 450/1251] eta: 0:06:50 lr: 0.000092 loss: 2.6563 (2.8638) grad_norm: 2.5442 (2.7584) time: 0.5047 [2021-03-27 00:22:05 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 460/1251] eta: 0:06:45 lr: 0.000092 loss: 2.6563 (2.8630) grad_norm: 2.4422 (2.7524) time: 0.5064 [2021-03-27 00:22:10 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 470/1251] eta: 0:06:40 lr: 0.000092 loss: 2.7663 (2.8607) grad_norm: 2.4318 (2.7464) time: 0.5055 [2021-03-27 00:22:15 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 480/1251] eta: 0:06:34 lr: 0.000092 loss: 2.9338 (2.8631) grad_norm: 2.4445 (2.7402) time: 0.5008 [2021-03-27 00:22:20 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 490/1251] eta: 0:06:29 lr: 0.000092 loss: 2.9690 (2.8621) grad_norm: 2.4368 (2.7353) time: 0.4949 [2021-03-27 00:22:25 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 500/1251] eta: 0:06:24 lr: 0.000092 loss: 2.9523 (2.8581) grad_norm: 2.4241 (2.7308) time: 0.5014 [2021-03-27 00:22:30 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 510/1251] eta: 0:06:19 lr: 0.000092 loss: 2.9787 (2.8629) grad_norm: 2.5742 (2.7333) time: 0.5106 [2021-03-27 00:22:35 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 520/1251] eta: 0:06:13 lr: 0.000092 loss: 3.1400 (2.8618) grad_norm: 2.5968 (2.7298) time: 0.5042 [2021-03-27 00:22:40 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 530/1251] eta: 0:06:08 lr: 0.000091 loss: 2.9217 (2.8597) grad_norm: 2.4783 (2.7249) time: 0.4970 [2021-03-27 00:22:45 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 540/1251] eta: 0:06:03 lr: 0.000091 loss: 2.8556 (2.8566) grad_norm: 2.4783 (2.7209) time: 0.5078 [2021-03-27 00:22:50 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 550/1251] eta: 0:05:58 lr: 0.000091 loss: 2.8655 (2.8569) grad_norm: 2.5332 (2.7180) time: 0.5188 [2021-03-27 00:22:55 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 560/1251] eta: 0:05:53 lr: 0.000091 loss: 2.8901 (2.8538) grad_norm: 2.6075 (2.7177) time: 0.5156 [2021-03-27 00:23:00 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 570/1251] eta: 0:05:48 lr: 0.000091 loss: 2.9424 (2.8551) grad_norm: 2.5640 (2.7139) time: 0.5122 [2021-03-27 00:23:05 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 580/1251] eta: 0:05:43 lr: 0.000091 loss: 2.8068 (2.8536) grad_norm: 2.5062 (2.7133) time: 0.5103 [2021-03-27 00:23:11 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 590/1251] eta: 0:05:38 lr: 0.000091 loss: 2.7704 (2.8534) grad_norm: 2.5085 (2.7112) time: 0.5072 [2021-03-27 00:23:16 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 600/1251] eta: 0:05:32 lr: 0.000091 loss: 2.9258 (2.8546) grad_norm: 2.6248 (2.7124) time: 0.5031 [2021-03-27 00:23:21 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 610/1251] eta: 0:05:27 lr: 0.000091 loss: 2.8605 (2.8522) grad_norm: 2.5390 (2.7089) time: 0.4982 [2021-03-27 00:23:26 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 620/1251] eta: 0:05:22 lr: 0.000091 loss: 3.0134 (2.8559) grad_norm: 2.5089 (2.7150) time: 0.5007 [2021-03-27 00:23:31 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 630/1251] eta: 0:05:17 lr: 0.000091 loss: 3.0572 (2.8538) grad_norm: 2.6640 (2.7159) time: 0.5033 [2021-03-27 00:23:36 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 640/1251] eta: 0:05:11 lr: 0.000091 loss: 2.7693 (2.8488) grad_norm: 2.6640 (2.7144) time: 0.5036 [2021-03-27 00:23:41 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 650/1251] eta: 0:05:06 lr: 0.000091 loss: 2.3863 (2.8457) grad_norm: 2.5930 (2.7141) time: 0.5054 [2021-03-27 00:23:46 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 660/1251] eta: 0:05:01 lr: 0.000091 loss: 2.5832 (2.8458) grad_norm: 2.5930 (2.7127) time: 0.5033 [2021-03-27 00:23:51 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 670/1251] eta: 0:04:56 lr: 0.000091 loss: 2.8072 (2.8437) grad_norm: 2.5118 (2.7099) time: 0.5001 [2021-03-27 00:23:56 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 680/1251] eta: 0:04:51 lr: 0.000091 loss: 2.8072 (2.8437) grad_norm: 2.5145 (2.7104) time: 0.4999 [2021-03-27 00:24:01 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 690/1251] eta: 0:04:45 lr: 0.000091 loss: 2.9804 (2.8436) grad_norm: 2.5929 (2.7083) time: 0.4940 [2021-03-27 00:24:06 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 700/1251] eta: 0:04:40 lr: 0.000091 loss: 3.0124 (2.8461) grad_norm: 2.6849 (2.7093) time: 0.4932 [2021-03-27 00:24:11 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 710/1251] eta: 0:04:35 lr: 0.000091 loss: 3.0387 (2.8456) grad_norm: 2.6849 (2.7135) time: 0.4998 [2021-03-27 00:24:16 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 720/1251] eta: 0:04:30 lr: 0.000091 loss: 2.9791 (2.8454) grad_norm: 2.6459 (2.7160) time: 0.5053 [2021-03-27 00:24:21 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 730/1251] eta: 0:04:25 lr: 0.000091 loss: 2.9647 (2.8422) grad_norm: 2.6482 (2.7144) time: 0.5130 [2021-03-27 00:24:26 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 740/1251] eta: 0:04:20 lr: 0.000091 loss: 2.4121 (2.8386) grad_norm: 2.5220 (2.7121) time: 0.5191 [2021-03-27 00:24:31 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 750/1251] eta: 0:04:15 lr: 0.000091 loss: 2.7627 (2.8372) grad_norm: 2.5667 (2.7126) time: 0.5196 [2021-03-27 00:24:36 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 760/1251] eta: 0:04:10 lr: 0.000091 loss: 2.7842 (2.8353) grad_norm: 2.6212 (2.7147) time: 0.5081 [2021-03-27 00:24:41 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 770/1251] eta: 0:04:05 lr: 0.000091 loss: 2.7842 (2.8364) grad_norm: 2.5156 (2.7118) time: 0.4948 [2021-03-27 00:24:46 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 780/1251] eta: 0:03:59 lr: 0.000091 loss: 2.9472 (2.8376) grad_norm: 2.5410 (2.7120) time: 0.4961 [2021-03-27 00:24:51 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 790/1251] eta: 0:03:54 lr: 0.000091 loss: 2.9673 (2.8400) grad_norm: 2.6136 (2.7123) time: 0.5042 [2021-03-27 00:24:56 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 800/1251] eta: 0:03:49 lr: 0.000091 loss: 2.9856 (2.8400) grad_norm: 2.6702 (2.7119) time: 0.5046 [2021-03-27 00:25:01 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 810/1251] eta: 0:03:44 lr: 0.000091 loss: 2.7337 (2.8403) grad_norm: 2.7378 (2.7199) time: 0.5043 [2021-03-27 00:25:06 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 820/1251] eta: 0:03:39 lr: 0.000091 loss: 2.7164 (2.8388) grad_norm: 2.5963 (2.7181) time: 0.5065 [2021-03-27 00:25:12 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 830/1251] eta: 0:03:34 lr: 0.000091 loss: 3.1210 (2.8430) grad_norm: 2.5963 (2.7173) time: 0.5148 [2021-03-27 00:25:17 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 840/1251] eta: 0:03:29 lr: 0.000091 loss: 3.1210 (2.8442) grad_norm: 2.6135 (2.7194) time: 0.5159 [2021-03-27 00:25:22 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 850/1251] eta: 0:03:24 lr: 0.000091 loss: 2.9505 (2.8423) grad_norm: 2.5475 (2.7204) time: 0.5041 [2021-03-27 00:25:27 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 860/1251] eta: 0:03:19 lr: 0.000091 loss: 2.9411 (2.8429) grad_norm: 2.5467 (2.7206) time: 0.5046 [2021-03-27 00:25:32 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 870/1251] eta: 0:03:13 lr: 0.000091 loss: 3.0598 (2.8435) grad_norm: 2.5825 (2.7190) time: 0.5000 [2021-03-27 00:25:37 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 880/1251] eta: 0:03:08 lr: 0.000091 loss: 2.8880 (2.8436) grad_norm: 2.6520 (2.7191) time: 0.4948 [2021-03-27 00:25:42 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 890/1251] eta: 0:03:03 lr: 0.000091 loss: 2.7384 (2.8408) grad_norm: 2.6520 (2.7225) time: 0.4987 [2021-03-27 00:25:47 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 900/1251] eta: 0:02:58 lr: 0.000091 loss: 2.7966 (2.8425) grad_norm: 2.5690 (2.7205) time: 0.4972 [2021-03-27 00:25:52 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 910/1251] eta: 0:02:53 lr: 0.000091 loss: 3.0572 (2.8450) grad_norm: 2.4706 (2.7203) time: 0.4929 [2021-03-27 00:25:57 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 920/1251] eta: 0:02:48 lr: 0.000091 loss: 3.0133 (2.8447) grad_norm: 2.5961 (2.7220) time: 0.4955 [2021-03-27 00:26:02 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 930/1251] eta: 0:02:43 lr: 0.000091 loss: 2.9802 (2.8473) grad_norm: 2.8881 (2.7231) time: 0.5086 [2021-03-27 00:26:07 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 940/1251] eta: 0:02:38 lr: 0.000091 loss: 2.9879 (2.8487) grad_norm: 2.6719 (2.7226) time: 0.5150 [2021-03-27 00:26:12 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 950/1251] eta: 0:02:33 lr: 0.000091 loss: 2.9906 (2.8489) grad_norm: 2.5854 (2.7212) time: 0.5091 [2021-03-27 00:26:17 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 960/1251] eta: 0:02:27 lr: 0.000091 loss: 2.9910 (2.8497) grad_norm: 2.6081 (2.7212) time: 0.5007 [2021-03-27 00:26:22 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 970/1251] eta: 0:02:22 lr: 0.000090 loss: 2.9382 (2.8498) grad_norm: 2.6777 (2.7239) time: 0.4983 [2021-03-27 00:26:27 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 980/1251] eta: 0:02:17 lr: 0.000090 loss: 2.8271 (2.8504) grad_norm: 2.6898 (2.7241) time: 0.4972 [2021-03-27 00:26:32 swin_small_patch4_window7_224] INFO: Epoch: [244] [ 990/1251] eta: 0:02:12 lr: 0.000090 loss: 3.0246 (2.8515) grad_norm: 2.6898 (2.7243) time: 0.4937 [2021-03-27 00:26:37 swin_small_patch4_window7_224] INFO: Epoch: [244] [1000/1251] eta: 0:02:07 lr: 0.000090 loss: 2.9095 (2.8513) grad_norm: 2.8331 (inf) time: 0.4997 [2021-03-27 00:26:42 swin_small_patch4_window7_224] INFO: Epoch: [244] [1010/1251] eta: 0:02:02 lr: 0.000090 loss: 2.6807 (2.8494) grad_norm: 2.6484 (inf) time: 0.5005 [2021-03-27 00:26:47 swin_small_patch4_window7_224] INFO: Epoch: [244] [1020/1251] eta: 0:01:57 lr: 0.000090 loss: 2.8759 (2.8508) grad_norm: 2.6051 (inf) time: 0.4969 [2021-03-27 00:26:52 swin_small_patch4_window7_224] INFO: Epoch: [244] [1030/1251] eta: 0:01:52 lr: 0.000090 loss: 2.9014 (2.8495) grad_norm: 2.5575 (inf) time: 0.4980 [2021-03-27 00:26:57 swin_small_patch4_window7_224] INFO: Epoch: [244] [1040/1251] eta: 0:01:47 lr: 0.000090 loss: 2.8227 (2.8486) grad_norm: 2.5466 (inf) time: 0.4990 [2021-03-27 00:27:02 swin_small_patch4_window7_224] INFO: Epoch: [244] [1050/1251] eta: 0:01:42 lr: 0.000090 loss: 2.8227 (2.8473) grad_norm: 2.4954 (inf) time: 0.5050 [2021-03-27 00:27:07 swin_small_patch4_window7_224] INFO: Epoch: [244] [1060/1251] eta: 0:01:36 lr: 0.000090 loss: 2.9540 (2.8491) grad_norm: 2.5159 (inf) time: 0.5079 [2021-03-27 00:27:12 swin_small_patch4_window7_224] INFO: Epoch: [244] [1070/1251] eta: 0:01:31 lr: 0.000090 loss: 2.9353 (2.8500) grad_norm: 2.5468 (inf) time: 0.5018 [2021-03-27 00:27:17 swin_small_patch4_window7_224] INFO: Epoch: [244] [1080/1251] eta: 0:01:26 lr: 0.000090 loss: 2.8620 (2.8498) grad_norm: 2.5468 (inf) time: 0.5004 [2021-03-27 00:27:22 swin_small_patch4_window7_224] INFO: Epoch: [244] [1090/1251] eta: 0:01:21 lr: 0.000090 loss: 2.7775 (2.8472) grad_norm: 2.4928 (inf) time: 0.5013 [2021-03-27 00:27:27 swin_small_patch4_window7_224] INFO: Epoch: [244] [1100/1251] eta: 0:01:16 lr: 0.000090 loss: 3.0041 (2.8496) grad_norm: 2.6227 (inf) time: 0.4984 [2021-03-27 00:27:32 swin_small_patch4_window7_224] INFO: Epoch: [244] [1110/1251] eta: 0:01:11 lr: 0.000090 loss: 3.0689 (2.8498) grad_norm: 2.5876 (inf) time: 0.4980 [2021-03-27 00:27:37 swin_small_patch4_window7_224] INFO: Epoch: [244] [1120/1251] eta: 0:01:06 lr: 0.000090 loss: 3.0472 (2.8515) grad_norm: 2.4989 (inf) time: 0.4995 [2021-03-27 00:27:42 swin_small_patch4_window7_224] INFO: Epoch: [244] [1130/1251] eta: 0:01:01 lr: 0.000090 loss: 3.1175 (2.8543) grad_norm: 2.6191 (inf) time: 0.5057 [2021-03-27 00:27:47 swin_small_patch4_window7_224] INFO: Epoch: [244] [1140/1251] eta: 0:00:56 lr: 0.000090 loss: 3.0579 (2.8545) grad_norm: 2.6238 (inf) time: 0.5057 [2021-03-27 00:27:52 swin_small_patch4_window7_224] INFO: Epoch: [244] [1150/1251] eta: 0:00:51 lr: 0.000090 loss: 2.9109 (2.8523) grad_norm: 2.5960 (inf) time: 0.5037 [2021-03-27 00:27:57 swin_small_patch4_window7_224] INFO: Epoch: [244] [1160/1251] eta: 0:00:46 lr: 0.000090 loss: 2.9109 (2.8526) grad_norm: 2.5960 (inf) time: 0.5025 [2021-03-27 00:28:02 swin_small_patch4_window7_224] INFO: Epoch: [244] [1170/1251] eta: 0:00:41 lr: 0.000090 loss: 2.9065 (2.8534) grad_norm: 2.5778 (inf) time: 0.5057 [2021-03-27 00:28:07 swin_small_patch4_window7_224] INFO: Epoch: [244] [1180/1251] eta: 0:00:35 lr: 0.000090 loss: 2.8624 (2.8530) grad_norm: 2.4618 (inf) time: 0.5078 [2021-03-27 00:28:12 swin_small_patch4_window7_224] INFO: Epoch: [244] [1190/1251] eta: 0:00:30 lr: 0.000090 loss: 2.8190 (2.8532) grad_norm: 2.5578 (inf) time: 0.5160 [2021-03-27 00:28:17 swin_small_patch4_window7_224] INFO: Epoch: [244] [1200/1251] eta: 0:00:25 lr: 0.000090 loss: 2.8130 (2.8526) grad_norm: 2.5877 (inf) time: 0.5140 [2021-03-27 00:28:22 swin_small_patch4_window7_224] INFO: Epoch: [244] [1210/1251] eta: 0:00:20 lr: 0.000090 loss: 2.8506 (2.8515) grad_norm: 2.5691 (inf) time: 0.4990 [2021-03-27 00:28:28 swin_small_patch4_window7_224] INFO: Epoch: [244] [1220/1251] eta: 0:00:15 lr: 0.000090 loss: 2.9213 (2.8533) grad_norm: 2.5691 (inf) time: 0.5025 [2021-03-27 00:28:33 swin_small_patch4_window7_224] INFO: Epoch: [244] [1230/1251] eta: 0:00:10 lr: 0.000090 loss: 3.0306 (2.8544) grad_norm: 2.6508 (inf) time: 0.5051 [2021-03-27 00:28:38 swin_small_patch4_window7_224] INFO: Epoch: [244] [1240/1251] eta: 0:00:05 lr: 0.000090 loss: 2.9914 (2.8549) grad_norm: 2.6340 (inf) time: 0.5082 [2021-03-27 00:28:43 swin_small_patch4_window7_224] INFO: Epoch: [244] [1250/1251] eta: 0:00:00 lr: 0.000090 loss: 2.9914 (2.8550) grad_norm: 2.4844 (inf) time: 0.5026 [2021-03-27 00:28:52 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:33 loss: 0.9452 (0.9452) acc1: 71.8750 (71.8750) acc5: 96.8750 (96.8750) [2021-03-27 00:28:54 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:13 loss: 0.8566 (0.8448) acc1: 79.6875 (79.2614) acc5: 95.3125 (95.7386) [2021-03-27 00:28:56 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8309 (0.8286) acc1: 81.2500 (80.1339) acc5: 95.3125 (95.7589) [2021-03-27 00:28:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7977 (0.8154) acc1: 81.2500 (80.6956) acc5: 95.3125 (95.7661) [2021-03-27 00:29:01 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7759 (0.7878) acc1: 82.8125 (81.0976) acc5: 95.3125 (95.9604) [2021-03-27 00:29:02 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6881 (0.7667) acc1: 82.8125 (81.5040) acc5: 96.8750 (96.0640) [2021-03-27 00:29:14 swin_small_patch4_window7_224] INFO: * Acc@1 82.288 Acc@5 96.084 loss 0.760 [2021-03-27 00:29:14 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-27 00:29:14 swin_small_patch4_window7_224] INFO: Max accuracy: 82.29% [2021-03-27 00:29:18 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 0/1251] eta: 1:29:13 lr: 0.000090 loss: 2.3901 (2.3901) grad_norm: 2.4575 (2.4575) time: 4.2798 [2021-03-27 00:29:23 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 10/1251] eta: 0:17:48 lr: 0.000090 loss: 3.0511 (2.8847) grad_norm: 2.6665 (2.7078) time: 0.8611 [2021-03-27 00:29:28 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 20/1251] eta: 0:14:17 lr: 0.000090 loss: 3.0341 (2.9015) grad_norm: 2.5931 (2.6358) time: 0.5173 [2021-03-27 00:29:33 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 30/1251] eta: 0:12:51 lr: 0.000090 loss: 2.9832 (2.9290) grad_norm: 2.5552 (2.6269) time: 0.5053 [2021-03-27 00:29:38 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 40/1251] eta: 0:12:09 lr: 0.000090 loss: 2.8437 (2.8980) grad_norm: 2.5469 (2.6312) time: 0.5035 [2021-03-27 00:29:44 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 50/1251] eta: 0:11:40 lr: 0.000090 loss: 2.9929 (2.9436) grad_norm: 2.5750 (2.6349) time: 0.5090 [2021-03-27 00:29:49 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 60/1251] eta: 0:11:18 lr: 0.000090 loss: 2.9775 (2.9008) grad_norm: 2.6642 (2.6609) time: 0.5038 [2021-03-27 00:29:54 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 70/1251] eta: 0:11:01 lr: 0.000090 loss: 2.7937 (2.8932) grad_norm: 2.6495 (2.6517) time: 0.5013 [2021-03-27 00:29:59 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 80/1251] eta: 0:10:47 lr: 0.000090 loss: 2.9908 (2.8885) grad_norm: 2.5554 (2.6353) time: 0.5020 [2021-03-27 00:30:04 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 90/1251] eta: 0:10:37 lr: 0.000090 loss: 3.0212 (2.9051) grad_norm: 2.5554 (2.6434) time: 0.5077 [2021-03-27 00:30:09 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 100/1251] eta: 0:10:25 lr: 0.000090 loss: 3.0050 (2.9019) grad_norm: 2.6172 (2.6897) time: 0.5046 [2021-03-27 00:30:14 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 110/1251] eta: 0:10:15 lr: 0.000090 loss: 2.9662 (2.8711) grad_norm: 2.7155 (2.7238) time: 0.4992 [2021-03-27 00:30:19 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 120/1251] eta: 0:10:08 lr: 0.000090 loss: 2.7114 (2.8662) grad_norm: 2.6375 (2.7170) time: 0.5109 [2021-03-27 00:30:24 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 130/1251] eta: 0:10:00 lr: 0.000090 loss: 3.0180 (2.8782) grad_norm: 2.5567 (2.7166) time: 0.5142 [2021-03-27 00:30:29 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 140/1251] eta: 0:09:52 lr: 0.000090 loss: 3.0180 (2.8728) grad_norm: 2.5565 (2.7040) time: 0.5068 [2021-03-27 00:30:34 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 150/1251] eta: 0:09:44 lr: 0.000090 loss: 2.8164 (2.8564) grad_norm: 2.5971 (2.7071) time: 0.4998 [2021-03-27 00:30:39 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 160/1251] eta: 0:09:37 lr: 0.000089 loss: 2.8899 (2.8553) grad_norm: 2.7648 (2.7657) time: 0.4989 [2021-03-27 00:30:44 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 170/1251] eta: 0:09:30 lr: 0.000089 loss: 2.9290 (2.8666) grad_norm: 2.5704 (2.7530) time: 0.5036 [2021-03-27 00:30:49 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 180/1251] eta: 0:09:24 lr: 0.000089 loss: 2.9202 (2.8572) grad_norm: 2.5702 (2.7577) time: 0.5088 [2021-03-27 00:30:54 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 190/1251] eta: 0:09:17 lr: 0.000089 loss: 2.8111 (2.8527) grad_norm: 2.6717 (2.7481) time: 0.5042 [2021-03-27 00:30:59 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 200/1251] eta: 0:09:11 lr: 0.000089 loss: 2.9016 (2.8511) grad_norm: 2.4862 (2.7335) time: 0.5030 [2021-03-27 00:31:04 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 210/1251] eta: 0:09:05 lr: 0.000089 loss: 2.8324 (2.8543) grad_norm: 2.5410 (2.7380) time: 0.5113 [2021-03-27 00:31:09 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 220/1251] eta: 0:08:59 lr: 0.000089 loss: 2.7804 (2.8518) grad_norm: 2.7353 (2.7412) time: 0.5083 [2021-03-27 00:31:14 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 230/1251] eta: 0:08:53 lr: 0.000089 loss: 2.7804 (2.8489) grad_norm: 2.6830 (2.7407) time: 0.5024 [2021-03-27 00:31:19 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 240/1251] eta: 0:08:47 lr: 0.000089 loss: 2.6818 (2.8390) grad_norm: 2.5403 (2.7447) time: 0.5042 [2021-03-27 00:31:25 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 250/1251] eta: 0:08:41 lr: 0.000089 loss: 2.5871 (2.8215) grad_norm: 2.5241 (2.7406) time: 0.5045 [2021-03-27 00:31:30 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 260/1251] eta: 0:08:35 lr: 0.000089 loss: 2.7244 (2.8211) grad_norm: 2.5719 (2.7355) time: 0.5056 [2021-03-27 00:31:35 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 270/1251] eta: 0:08:30 lr: 0.000089 loss: 2.8621 (2.8234) grad_norm: 2.4675 (2.7286) time: 0.5091 [2021-03-27 00:31:40 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 280/1251] eta: 0:08:24 lr: 0.000089 loss: 2.8328 (2.8242) grad_norm: 2.4675 (2.7240) time: 0.5078 [2021-03-27 00:31:45 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 290/1251] eta: 0:08:18 lr: 0.000089 loss: 2.9185 (2.8267) grad_norm: 2.5105 (2.7179) time: 0.5070 [2021-03-27 00:31:50 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 300/1251] eta: 0:08:12 lr: 0.000089 loss: 2.9871 (2.8329) grad_norm: 2.5105 (2.7234) time: 0.5009 [2021-03-27 00:31:55 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 310/1251] eta: 0:08:07 lr: 0.000089 loss: 2.9871 (2.8275) grad_norm: 2.6299 (2.7227) time: 0.5032 [2021-03-27 00:32:00 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 320/1251] eta: 0:08:01 lr: 0.000089 loss: 2.9478 (2.8342) grad_norm: 2.5689 (2.7175) time: 0.5088 [2021-03-27 00:32:05 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 330/1251] eta: 0:07:56 lr: 0.000089 loss: 3.0505 (2.8342) grad_norm: 2.4989 (2.7098) time: 0.5024 [2021-03-27 00:32:10 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 340/1251] eta: 0:07:50 lr: 0.000089 loss: 2.9413 (2.8334) grad_norm: 2.4584 (2.7034) time: 0.4990 [2021-03-27 00:32:15 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 350/1251] eta: 0:07:44 lr: 0.000089 loss: 2.9053 (2.8337) grad_norm: 2.5559 (2.7012) time: 0.4997 [2021-03-27 00:32:20 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 360/1251] eta: 0:07:39 lr: 0.000089 loss: 2.9660 (2.8392) grad_norm: 2.5104 (2.6945) time: 0.4976 [2021-03-27 00:32:25 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 370/1251] eta: 0:07:33 lr: 0.000089 loss: 2.9660 (2.8365) grad_norm: 2.4897 (2.6960) time: 0.4972 [2021-03-27 00:32:30 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 380/1251] eta: 0:07:28 lr: 0.000089 loss: 2.7719 (2.8315) grad_norm: 2.6116 (2.7029) time: 0.5071 [2021-03-27 00:32:35 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 390/1251] eta: 0:07:23 lr: 0.000089 loss: 2.7719 (2.8321) grad_norm: 2.6116 (2.7026) time: 0.5124 [2021-03-27 00:32:40 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 400/1251] eta: 0:07:17 lr: 0.000089 loss: 2.9513 (2.8340) grad_norm: 2.4529 (2.6952) time: 0.5014 [2021-03-27 00:32:45 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 410/1251] eta: 0:07:12 lr: 0.000089 loss: 2.9513 (2.8365) grad_norm: 2.4187 (2.6896) time: 0.5003 [2021-03-27 00:32:50 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 420/1251] eta: 0:07:07 lr: 0.000089 loss: 3.1290 (2.8397) grad_norm: 2.6439 (2.6995) time: 0.5019 [2021-03-27 00:32:55 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 430/1251] eta: 0:07:01 lr: 0.000089 loss: 2.6785 (2.8319) grad_norm: 2.8511 (2.7023) time: 0.4983 [2021-03-27 00:33:00 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 440/1251] eta: 0:06:56 lr: 0.000089 loss: 2.6785 (2.8334) grad_norm: 2.6373 (2.7046) time: 0.5013 [2021-03-27 00:33:05 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 450/1251] eta: 0:06:50 lr: 0.000089 loss: 2.9910 (2.8349) grad_norm: 2.4470 (2.6983) time: 0.4997 [2021-03-27 00:33:10 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 460/1251] eta: 0:06:45 lr: 0.000089 loss: 3.0638 (2.8390) grad_norm: 2.3627 (2.7046) time: 0.4950 [2021-03-27 00:33:15 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 470/1251] eta: 0:06:40 lr: 0.000089 loss: 2.8710 (2.8347) grad_norm: 2.4454 (2.7007) time: 0.5037 [2021-03-27 00:33:20 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 480/1251] eta: 0:06:34 lr: 0.000089 loss: 2.7361 (2.8347) grad_norm: 2.4362 (2.6946) time: 0.5069 [2021-03-27 00:33:25 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 490/1251] eta: 0:06:29 lr: 0.000089 loss: 2.8511 (2.8332) grad_norm: 2.4404 (2.6962) time: 0.5015 [2021-03-27 00:33:30 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 500/1251] eta: 0:06:24 lr: 0.000089 loss: 2.8944 (2.8329) grad_norm: 2.6145 (2.6990) time: 0.4993 [2021-03-27 00:33:35 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 510/1251] eta: 0:06:18 lr: 0.000089 loss: 2.6959 (2.8289) grad_norm: 2.6722 (2.6970) time: 0.4973 [2021-03-27 00:33:40 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 520/1251] eta: 0:06:13 lr: 0.000089 loss: 2.9135 (2.8329) grad_norm: 2.5948 (2.6968) time: 0.5034 [2021-03-27 00:33:45 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 530/1251] eta: 0:06:08 lr: 0.000089 loss: 3.0001 (2.8260) grad_norm: 2.4475 (2.6917) time: 0.5088 [2021-03-27 00:33:50 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 540/1251] eta: 0:06:03 lr: 0.000089 loss: 2.7392 (2.8260) grad_norm: 2.5635 (2.6936) time: 0.5101 [2021-03-27 00:33:56 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 550/1251] eta: 0:05:58 lr: 0.000089 loss: 2.8808 (2.8270) grad_norm: 2.6212 (2.6924) time: 0.5114 [2021-03-27 00:34:01 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 560/1251] eta: 0:05:53 lr: 0.000089 loss: 2.8119 (2.8265) grad_norm: 2.5899 (2.6921) time: 0.5079 [2021-03-27 00:34:06 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 570/1251] eta: 0:05:48 lr: 0.000089 loss: 2.8119 (2.8269) grad_norm: 2.5899 (2.6895) time: 0.5089 [2021-03-27 00:34:11 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 580/1251] eta: 0:05:42 lr: 0.000089 loss: 2.9421 (2.8251) grad_norm: 2.6077 (2.6935) time: 0.5083 [2021-03-27 00:34:16 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 590/1251] eta: 0:05:37 lr: 0.000089 loss: 2.8480 (2.8251) grad_norm: 2.6256 (2.6957) time: 0.5027 [2021-03-27 00:34:21 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 600/1251] eta: 0:05:32 lr: 0.000089 loss: 2.7894 (2.8244) grad_norm: 2.6199 (2.6943) time: 0.5050 [2021-03-27 00:34:26 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 610/1251] eta: 0:05:27 lr: 0.000088 loss: 2.7599 (2.8239) grad_norm: 2.5954 (2.6930) time: 0.5004 [2021-03-27 00:34:31 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 620/1251] eta: 0:05:22 lr: 0.000088 loss: 2.8493 (2.8262) grad_norm: 2.6014 (2.6939) time: 0.4936 [2021-03-27 00:34:36 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 630/1251] eta: 0:05:16 lr: 0.000088 loss: 2.8547 (2.8250) grad_norm: 2.4464 (2.6907) time: 0.4970 [2021-03-27 00:34:41 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 640/1251] eta: 0:05:11 lr: 0.000088 loss: 2.8724 (2.8282) grad_norm: 2.6289 (2.6936) time: 0.4975 [2021-03-27 00:34:46 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 650/1251] eta: 0:05:06 lr: 0.000088 loss: 3.1016 (2.8316) grad_norm: 2.6156 (2.6935) time: 0.5051 [2021-03-27 00:34:51 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 660/1251] eta: 0:05:01 lr: 0.000088 loss: 3.1016 (2.8348) grad_norm: 2.5186 (2.6961) time: 0.5097 [2021-03-27 00:34:56 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 670/1251] eta: 0:04:56 lr: 0.000088 loss: 3.0358 (2.8351) grad_norm: 2.5421 (2.6946) time: 0.5040 [2021-03-27 00:35:01 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 680/1251] eta: 0:04:51 lr: 0.000088 loss: 2.9778 (2.8342) grad_norm: 2.4797 (2.6918) time: 0.5000 [2021-03-27 00:35:06 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 690/1251] eta: 0:04:45 lr: 0.000088 loss: 2.9778 (2.8372) grad_norm: 2.4462 (2.6906) time: 0.5023 [2021-03-27 00:35:11 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 700/1251] eta: 0:04:40 lr: 0.000088 loss: 3.1573 (2.8427) grad_norm: 2.6205 (2.6904) time: 0.5038 [2021-03-27 00:35:16 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 710/1251] eta: 0:04:35 lr: 0.000088 loss: 2.9636 (2.8410) grad_norm: 2.7112 (2.6901) time: 0.5068 [2021-03-27 00:35:21 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 720/1251] eta: 0:04:30 lr: 0.000088 loss: 2.9133 (2.8421) grad_norm: 2.5372 (2.6874) time: 0.5070 [2021-03-27 00:35:26 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 730/1251] eta: 0:04:25 lr: 0.000088 loss: 3.0480 (2.8436) grad_norm: 2.5486 (2.6879) time: 0.5104 [2021-03-27 00:35:31 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 740/1251] eta: 0:04:20 lr: 0.000088 loss: 3.0545 (2.8442) grad_norm: 2.5486 (2.6888) time: 0.5146 [2021-03-27 00:35:37 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 750/1251] eta: 0:04:15 lr: 0.000088 loss: 2.9947 (2.8449) grad_norm: 2.6253 (2.6910) time: 0.5065 [2021-03-27 00:35:42 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 760/1251] eta: 0:04:10 lr: 0.000088 loss: 2.9947 (2.8451) grad_norm: 2.5691 (2.6887) time: 0.5140 [2021-03-27 00:35:47 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 770/1251] eta: 0:04:05 lr: 0.000088 loss: 2.8128 (2.8424) grad_norm: 2.5691 (2.6899) time: 0.5127 [2021-03-27 00:35:52 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 780/1251] eta: 0:03:59 lr: 0.000088 loss: 2.4392 (2.8394) grad_norm: 2.6344 (2.6901) time: 0.4983 [2021-03-27 00:35:57 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 790/1251] eta: 0:03:54 lr: 0.000088 loss: 2.5174 (2.8363) grad_norm: 2.5677 (2.6922) time: 0.5069 [2021-03-27 00:36:02 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 800/1251] eta: 0:03:49 lr: 0.000088 loss: 2.5174 (2.8329) grad_norm: 2.6697 (2.6915) time: 0.5089 [2021-03-27 00:36:07 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 810/1251] eta: 0:03:44 lr: 0.000088 loss: 2.6068 (2.8318) grad_norm: 2.4358 (2.6886) time: 0.5045 [2021-03-27 00:36:12 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 820/1251] eta: 0:03:39 lr: 0.000088 loss: 2.9430 (2.8339) grad_norm: 2.4991 (2.6875) time: 0.5034 [2021-03-27 00:36:17 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 830/1251] eta: 0:03:34 lr: 0.000088 loss: 3.0407 (2.8348) grad_norm: 2.5624 (2.6879) time: 0.4951 [2021-03-27 00:36:22 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 840/1251] eta: 0:03:29 lr: 0.000088 loss: 2.9554 (2.8344) grad_norm: 2.6798 (2.6890) time: 0.5038 [2021-03-27 00:36:27 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 850/1251] eta: 0:03:24 lr: 0.000088 loss: 2.8707 (2.8358) grad_norm: 2.6606 (2.6877) time: 0.5054 [2021-03-27 00:36:32 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 860/1251] eta: 0:03:18 lr: 0.000088 loss: 2.6381 (2.8325) grad_norm: 2.6189 (2.6880) time: 0.4983 [2021-03-27 00:36:37 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 870/1251] eta: 0:03:13 lr: 0.000088 loss: 2.8610 (2.8323) grad_norm: 2.4440 (2.6844) time: 0.5001 [2021-03-27 00:36:42 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 880/1251] eta: 0:03:08 lr: 0.000088 loss: 2.9414 (2.8331) grad_norm: 2.4894 (2.6888) time: 0.5021 [2021-03-27 00:36:47 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 890/1251] eta: 0:03:03 lr: 0.000088 loss: 2.9786 (2.8354) grad_norm: 2.6757 (2.6892) time: 0.5020 [2021-03-27 00:36:52 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 900/1251] eta: 0:02:58 lr: 0.000088 loss: 3.0749 (2.8357) grad_norm: 2.6369 (2.6879) time: 0.4988 [2021-03-27 00:36:57 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 910/1251] eta: 0:02:53 lr: 0.000088 loss: 3.1514 (2.8380) grad_norm: 2.6045 (2.6919) time: 0.4982 [2021-03-27 00:37:02 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 920/1251] eta: 0:02:48 lr: 0.000088 loss: 3.0038 (2.8384) grad_norm: 2.5741 (2.6900) time: 0.5010 [2021-03-27 00:37:07 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 930/1251] eta: 0:02:43 lr: 0.000088 loss: 3.0465 (2.8421) grad_norm: 2.5588 (2.6894) time: 0.5044 [2021-03-27 00:37:12 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 940/1251] eta: 0:02:38 lr: 0.000088 loss: 3.0465 (2.8398) grad_norm: 2.6555 (2.6896) time: 0.5048 [2021-03-27 00:37:17 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 950/1251] eta: 0:02:33 lr: 0.000088 loss: 2.6782 (2.8405) grad_norm: 2.8171 (2.6915) time: 0.5158 [2021-03-27 00:37:23 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 960/1251] eta: 0:02:27 lr: 0.000088 loss: 2.7329 (2.8394) grad_norm: 2.6897 (2.6923) time: 0.5178 [2021-03-27 00:37:28 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 970/1251] eta: 0:02:22 lr: 0.000088 loss: 2.7985 (2.8390) grad_norm: 2.5566 (2.6952) time: 0.5083 [2021-03-27 00:37:33 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 980/1251] eta: 0:02:17 lr: 0.000088 loss: 2.8248 (2.8381) grad_norm: 2.5853 (2.6934) time: 0.5035 [2021-03-27 00:37:38 swin_small_patch4_window7_224] INFO: Epoch: [245] [ 990/1251] eta: 0:02:12 lr: 0.000088 loss: 2.8751 (2.8392) grad_norm: 2.6085 (2.6927) time: 0.5026 [2021-03-27 00:37:43 swin_small_patch4_window7_224] INFO: Epoch: [245] [1000/1251] eta: 0:02:07 lr: 0.000088 loss: 2.8927 (2.8392) grad_norm: 2.6304 (2.6952) time: 0.5043 [2021-03-27 00:37:48 swin_small_patch4_window7_224] INFO: Epoch: [245] [1010/1251] eta: 0:02:02 lr: 0.000088 loss: 2.9205 (2.8399) grad_norm: 2.6304 (2.6954) time: 0.5009 [2021-03-27 00:37:53 swin_small_patch4_window7_224] INFO: Epoch: [245] [1020/1251] eta: 0:01:57 lr: 0.000088 loss: 2.9733 (2.8403) grad_norm: 2.5933 (2.6945) time: 0.4988 [2021-03-27 00:37:58 swin_small_patch4_window7_224] INFO: Epoch: [245] [1030/1251] eta: 0:01:52 lr: 0.000088 loss: 3.0071 (2.8412) grad_norm: 2.5258 (2.6931) time: 0.5007 [2021-03-27 00:38:03 swin_small_patch4_window7_224] INFO: Epoch: [245] [1040/1251] eta: 0:01:47 lr: 0.000088 loss: 3.0202 (2.8434) grad_norm: 2.6529 (2.6935) time: 0.5012 [2021-03-27 00:38:08 swin_small_patch4_window7_224] INFO: Epoch: [245] [1050/1251] eta: 0:01:42 lr: 0.000088 loss: 2.9261 (2.8431) grad_norm: 2.6601 (2.6942) time: 0.4999 [2021-03-27 00:38:13 swin_small_patch4_window7_224] INFO: Epoch: [245] [1060/1251] eta: 0:01:36 lr: 0.000087 loss: 2.8317 (2.8424) grad_norm: 2.6053 (2.6940) time: 0.4978 [2021-03-27 00:38:18 swin_small_patch4_window7_224] INFO: Epoch: [245] [1070/1251] eta: 0:01:31 lr: 0.000087 loss: 2.9988 (2.8431) grad_norm: 2.5910 (2.6929) time: 0.5002 [2021-03-27 00:38:23 swin_small_patch4_window7_224] INFO: Epoch: [245] [1080/1251] eta: 0:01:26 lr: 0.000087 loss: 2.7210 (2.8399) grad_norm: 2.6105 (2.6929) time: 0.4997 [2021-03-27 00:38:28 swin_small_patch4_window7_224] INFO: Epoch: [245] [1090/1251] eta: 0:01:21 lr: 0.000087 loss: 2.7210 (2.8408) grad_norm: 2.7058 (2.6931) time: 0.4936 [2021-03-27 00:38:33 swin_small_patch4_window7_224] INFO: Epoch: [245] [1100/1251] eta: 0:01:16 lr: 0.000087 loss: 2.8066 (2.8394) grad_norm: 2.6449 (2.6926) time: 0.4952 [2021-03-27 00:38:38 swin_small_patch4_window7_224] INFO: Epoch: [245] [1110/1251] eta: 0:01:11 lr: 0.000087 loss: 2.8073 (2.8392) grad_norm: 2.5651 (2.6916) time: 0.4981 [2021-03-27 00:38:43 swin_small_patch4_window7_224] INFO: Epoch: [245] [1120/1251] eta: 0:01:06 lr: 0.000087 loss: 2.8582 (2.8389) grad_norm: 2.5418 (2.6904) time: 0.4993 [2021-03-27 00:38:47 swin_small_patch4_window7_224] INFO: Epoch: [245] [1130/1251] eta: 0:01:01 lr: 0.000087 loss: 2.9085 (2.8387) grad_norm: 2.6059 (2.6920) time: 0.4975 [2021-03-27 00:38:52 swin_small_patch4_window7_224] INFO: Epoch: [245] [1140/1251] eta: 0:00:56 lr: 0.000087 loss: 2.9451 (2.8395) grad_norm: 2.6145 (2.6909) time: 0.4954 [2021-03-27 00:38:58 swin_small_patch4_window7_224] INFO: Epoch: [245] [1150/1251] eta: 0:00:51 lr: 0.000087 loss: 2.9573 (2.8386) grad_norm: 2.5655 (2.6906) time: 0.5007 [2021-03-27 00:39:03 swin_small_patch4_window7_224] INFO: Epoch: [245] [1160/1251] eta: 0:00:46 lr: 0.000087 loss: 3.0104 (2.8396) grad_norm: 2.7665 (2.6927) time: 0.5069 [2021-03-27 00:39:08 swin_small_patch4_window7_224] INFO: Epoch: [245] [1170/1251] eta: 0:00:41 lr: 0.000087 loss: 3.0104 (2.8393) grad_norm: 2.8800 (2.6939) time: 0.5026 [2021-03-27 00:39:13 swin_small_patch4_window7_224] INFO: Epoch: [245] [1180/1251] eta: 0:00:35 lr: 0.000087 loss: 2.9594 (2.8401) grad_norm: 2.6062 (2.6929) time: 0.4992 [2021-03-27 00:39:18 swin_small_patch4_window7_224] INFO: Epoch: [245] [1190/1251] eta: 0:00:30 lr: 0.000087 loss: 2.8656 (2.8387) grad_norm: 2.4897 (2.6909) time: 0.5001 [2021-03-27 00:39:23 swin_small_patch4_window7_224] INFO: Epoch: [245] [1200/1251] eta: 0:00:25 lr: 0.000087 loss: 2.8902 (2.8402) grad_norm: 2.4587 (2.6906) time: 0.4982 [2021-03-27 00:39:28 swin_small_patch4_window7_224] INFO: Epoch: [245] [1210/1251] eta: 0:00:20 lr: 0.000087 loss: 3.0754 (2.8412) grad_norm: 2.5943 (2.6908) time: 0.4969 [2021-03-27 00:39:33 swin_small_patch4_window7_224] INFO: Epoch: [245] [1220/1251] eta: 0:00:15 lr: 0.000087 loss: 3.2028 (2.8439) grad_norm: 2.6330 (2.6910) time: 0.4982 [2021-03-27 00:39:37 swin_small_patch4_window7_224] INFO: Epoch: [245] [1230/1251] eta: 0:00:10 lr: 0.000087 loss: 3.1654 (2.8441) grad_norm: 2.5679 (2.6907) time: 0.4976 [2021-03-27 00:39:42 swin_small_patch4_window7_224] INFO: Epoch: [245] [1240/1251] eta: 0:00:05 lr: 0.000087 loss: 2.8865 (2.8439) grad_norm: 2.5618 (2.6898) time: 0.4947 [2021-03-27 00:39:48 swin_small_patch4_window7_224] INFO: Epoch: [245] [1250/1251] eta: 0:00:00 lr: 0.000087 loss: 2.9209 (2.8441) grad_norm: 2.5618 (2.6914) time: 0.5032 [2021-03-27 00:40:32 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:17 loss: 0.6422 (0.6422) acc1: 89.0625 (89.0625) acc5: 96.8750 (96.8750) [2021-03-27 00:40:33 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7688 (0.7782) acc1: 81.2500 (81.6761) acc5: 96.8750 (96.3068) [2021-03-27 00:40:34 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7688 (0.7723) acc1: 81.2500 (81.3988) acc5: 96.8750 (96.5774) [2021-03-27 00:40:35 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:03 loss: 0.7217 (0.7600) acc1: 82.8125 (82.0060) acc5: 96.8750 (96.5726) [2021-03-27 00:40:36 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.6757 (0.7678) acc1: 82.8125 (81.5168) acc5: 96.8750 (96.2271) [2021-03-27 00:40:37 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6866 (0.7663) acc1: 81.2500 (81.6640) acc5: 96.8750 (96.2880) [2021-03-27 00:40:47 swin_small_patch4_window7_224] INFO: * Acc@1 82.168 Acc@5 96.066 loss 0.761 [2021-03-27 00:40:47 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.2% [2021-03-27 00:40:47 swin_small_patch4_window7_224] INFO: Max accuracy: 82.29% [2021-03-27 00:40:51 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 0/1251] eta: 1:26:44 lr: 0.000087 loss: 2.9327 (2.9327) grad_norm: 2.5046 (2.5046) time: 4.1602 [2021-03-27 00:40:56 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 10/1251] eta: 0:17:33 lr: 0.000087 loss: 3.0117 (3.0467) grad_norm: 2.7706 (2.6798) time: 0.8490 [2021-03-27 00:41:01 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 20/1251] eta: 0:13:59 lr: 0.000087 loss: 2.9621 (2.9188) grad_norm: 2.5331 (2.5689) time: 0.5076 [2021-03-27 00:41:07 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 30/1251] eta: 0:12:46 lr: 0.000087 loss: 2.9621 (2.9442) grad_norm: 2.5699 (2.6067) time: 0.5060 [2021-03-27 00:41:12 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 40/1251] eta: 0:12:05 lr: 0.000087 loss: 2.9621 (2.9024) grad_norm: 2.7180 (2.6651) time: 0.5132 [2021-03-27 00:41:17 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 50/1251] eta: 0:11:41 lr: 0.000087 loss: 2.8419 (2.8926) grad_norm: 2.5387 (2.6341) time: 0.5173 [2021-03-27 00:41:22 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 60/1251] eta: 0:11:18 lr: 0.000087 loss: 2.9197 (2.8938) grad_norm: 2.5487 (2.6482) time: 0.5094 [2021-03-27 00:41:27 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 70/1251] eta: 0:11:02 lr: 0.000087 loss: 2.9197 (2.8844) grad_norm: 2.6710 (2.6762) time: 0.5015 [2021-03-27 00:41:32 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 80/1251] eta: 0:10:47 lr: 0.000087 loss: 2.9013 (2.8787) grad_norm: 2.5835 (2.6593) time: 0.5001 [2021-03-27 00:41:37 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 90/1251] eta: 0:10:35 lr: 0.000087 loss: 2.6536 (2.8422) grad_norm: 2.5065 (2.6696) time: 0.4984 [2021-03-27 00:41:42 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 100/1251] eta: 0:10:25 lr: 0.000087 loss: 2.6195 (2.8450) grad_norm: 2.5884 (2.6670) time: 0.5046 [2021-03-27 00:41:47 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 110/1251] eta: 0:10:17 lr: 0.000087 loss: 2.9441 (2.8487) grad_norm: 2.7138 (2.6898) time: 0.5137 [2021-03-27 00:41:52 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 120/1251] eta: 0:10:07 lr: 0.000087 loss: 2.6425 (2.8345) grad_norm: 2.6385 (2.6778) time: 0.5095 [2021-03-27 00:41:57 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 130/1251] eta: 0:09:59 lr: 0.000087 loss: 2.7560 (2.8268) grad_norm: 2.6631 (2.7214) time: 0.4983 [2021-03-27 00:42:02 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 140/1251] eta: 0:09:52 lr: 0.000087 loss: 2.7560 (2.8212) grad_norm: 2.6953 (2.7125) time: 0.5070 [2021-03-27 00:42:07 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 150/1251] eta: 0:09:44 lr: 0.000087 loss: 2.5563 (2.8090) grad_norm: 2.5483 (2.7062) time: 0.5090 [2021-03-27 00:42:12 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 160/1251] eta: 0:09:37 lr: 0.000087 loss: 2.8776 (2.8172) grad_norm: 2.6370 (2.7122) time: 0.5046 [2021-03-27 00:42:17 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 170/1251] eta: 0:09:31 lr: 0.000087 loss: 2.8776 (2.8065) grad_norm: 2.5186 (2.7068) time: 0.5093 [2021-03-27 00:42:23 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 180/1251] eta: 0:09:25 lr: 0.000087 loss: 2.6495 (2.8095) grad_norm: 2.4844 (2.7022) time: 0.5160 [2021-03-27 00:42:28 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 190/1251] eta: 0:09:19 lr: 0.000087 loss: 2.6843 (2.8087) grad_norm: 2.4702 (2.6929) time: 0.5190 [2021-03-27 00:42:33 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 200/1251] eta: 0:09:13 lr: 0.000087 loss: 2.8193 (2.8065) grad_norm: 2.4782 (2.6979) time: 0.5127 [2021-03-27 00:42:38 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 210/1251] eta: 0:09:07 lr: 0.000087 loss: 2.9655 (2.8089) grad_norm: 2.6357 (2.7164) time: 0.5043 [2021-03-27 00:42:43 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 220/1251] eta: 0:09:00 lr: 0.000087 loss: 3.0572 (2.8187) grad_norm: 2.6472 (2.7183) time: 0.5051 [2021-03-27 00:42:48 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 230/1251] eta: 0:08:54 lr: 0.000087 loss: 2.9721 (2.8220) grad_norm: 2.6676 (2.7118) time: 0.4999 [2021-03-27 00:42:53 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 240/1251] eta: 0:08:47 lr: 0.000087 loss: 2.9721 (2.8233) grad_norm: 2.5009 (2.7050) time: 0.4931 [2021-03-27 00:42:58 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 250/1251] eta: 0:08:41 lr: 0.000087 loss: 3.0032 (2.8323) grad_norm: 2.5492 (2.7024) time: 0.4953 [2021-03-27 00:43:03 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 260/1251] eta: 0:08:36 lr: 0.000086 loss: 2.8948 (2.8354) grad_norm: 2.5638 (2.7056) time: 0.5055 [2021-03-27 00:43:08 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 270/1251] eta: 0:08:30 lr: 0.000086 loss: 2.7611 (2.8256) grad_norm: 2.8045 (2.7103) time: 0.5076 [2021-03-27 00:43:13 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 280/1251] eta: 0:08:24 lr: 0.000086 loss: 2.8954 (2.8356) grad_norm: 2.7224 (2.7286) time: 0.4985 [2021-03-27 00:43:18 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 290/1251] eta: 0:08:18 lr: 0.000086 loss: 3.0014 (2.8361) grad_norm: 2.5737 (2.7271) time: 0.4984 [2021-03-27 00:43:23 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 300/1251] eta: 0:08:13 lr: 0.000086 loss: 2.9683 (2.8352) grad_norm: 2.5707 (2.7518) time: 0.5071 [2021-03-27 00:43:28 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 310/1251] eta: 0:08:07 lr: 0.000086 loss: 2.9683 (2.8414) grad_norm: 2.6637 (2.7473) time: 0.5103 [2021-03-27 00:43:33 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 320/1251] eta: 0:08:01 lr: 0.000086 loss: 2.9661 (2.8402) grad_norm: 2.6637 (2.7446) time: 0.5050 [2021-03-27 00:43:38 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 330/1251] eta: 0:07:56 lr: 0.000086 loss: 2.9661 (2.8419) grad_norm: 2.6216 (2.7484) time: 0.5101 [2021-03-27 00:43:44 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 340/1251] eta: 0:07:51 lr: 0.000086 loss: 2.9953 (2.8445) grad_norm: 2.5769 (2.7418) time: 0.5141 [2021-03-27 00:43:48 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 350/1251] eta: 0:07:45 lr: 0.000086 loss: 2.9026 (2.8433) grad_norm: 2.5529 (2.7370) time: 0.5037 [2021-03-27 00:43:54 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 360/1251] eta: 0:07:40 lr: 0.000086 loss: 2.9049 (2.8471) grad_norm: 2.5083 (2.7310) time: 0.5047 [2021-03-27 00:43:59 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 370/1251] eta: 0:07:34 lr: 0.000086 loss: 3.1008 (2.8504) grad_norm: 2.5631 (2.7290) time: 0.5096 [2021-03-27 00:44:04 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 380/1251] eta: 0:07:29 lr: 0.000086 loss: 3.0384 (2.8519) grad_norm: 2.5631 (2.7281) time: 0.5054 [2021-03-27 00:44:09 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 390/1251] eta: 0:07:23 lr: 0.000086 loss: 2.9663 (2.8528) grad_norm: 2.5327 (2.7273) time: 0.5014 [2021-03-27 00:44:14 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 400/1251] eta: 0:07:18 lr: 0.000086 loss: 2.8718 (2.8486) grad_norm: 2.6082 (2.7510) time: 0.4988 [2021-03-27 00:44:19 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 410/1251] eta: 0:07:12 lr: 0.000086 loss: 2.8735 (2.8524) grad_norm: 2.7153 (2.7565) time: 0.4977 [2021-03-27 00:44:24 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 420/1251] eta: 0:07:07 lr: 0.000086 loss: 3.0401 (2.8520) grad_norm: 2.7610 (2.7557) time: 0.5000 [2021-03-27 00:44:29 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 430/1251] eta: 0:07:02 lr: 0.000086 loss: 2.9007 (2.8511) grad_norm: 2.7401 (2.7565) time: 0.5000 [2021-03-27 00:44:34 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 440/1251] eta: 0:06:56 lr: 0.000086 loss: 3.0316 (2.8527) grad_norm: 2.6587 (2.7566) time: 0.4963 [2021-03-27 00:44:39 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 450/1251] eta: 0:06:51 lr: 0.000086 loss: 3.0728 (2.8563) grad_norm: 2.5292 (2.7505) time: 0.4947 [2021-03-27 00:44:44 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 460/1251] eta: 0:06:45 lr: 0.000086 loss: 2.8518 (2.8574) grad_norm: 2.6139 (2.7527) time: 0.4995 [2021-03-27 00:44:49 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 470/1251] eta: 0:06:40 lr: 0.000086 loss: 2.9377 (2.8594) grad_norm: 2.6576 (2.7507) time: 0.5009 [2021-03-27 00:44:54 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 480/1251] eta: 0:06:35 lr: 0.000086 loss: 3.0593 (2.8640) grad_norm: 2.6379 (2.7486) time: 0.4977 [2021-03-27 00:44:59 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 490/1251] eta: 0:06:29 lr: 0.000086 loss: 3.1024 (2.8677) grad_norm: 2.6534 (2.7518) time: 0.4975 [2021-03-27 00:45:04 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 500/1251] eta: 0:06:24 lr: 0.000086 loss: 2.9952 (2.8648) grad_norm: 2.6732 (2.7551) time: 0.4992 [2021-03-27 00:45:09 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 510/1251] eta: 0:06:19 lr: 0.000086 loss: 2.8519 (2.8643) grad_norm: 2.5889 (2.7520) time: 0.5047 [2021-03-27 00:45:14 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 520/1251] eta: 0:06:13 lr: 0.000086 loss: 2.7987 (2.8608) grad_norm: 2.5240 (2.7471) time: 0.5013 [2021-03-27 00:45:19 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 530/1251] eta: 0:06:08 lr: 0.000086 loss: 2.7567 (2.8553) grad_norm: 2.5515 (2.7440) time: 0.5018 [2021-03-27 00:45:24 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 540/1251] eta: 0:06:03 lr: 0.000086 loss: 2.7567 (2.8530) grad_norm: 2.6459 (2.7428) time: 0.5058 [2021-03-27 00:45:29 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 550/1251] eta: 0:05:58 lr: 0.000086 loss: 2.6973 (2.8535) grad_norm: 2.4650 (2.7368) time: 0.5081 [2021-03-27 00:45:34 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 560/1251] eta: 0:05:53 lr: 0.000086 loss: 2.6034 (2.8491) grad_norm: 2.4220 (2.7339) time: 0.5108 [2021-03-27 00:45:39 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 570/1251] eta: 0:05:48 lr: 0.000086 loss: 2.5973 (2.8480) grad_norm: 2.4898 (2.7397) time: 0.5098 [2021-03-27 00:45:44 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 580/1251] eta: 0:05:43 lr: 0.000086 loss: 2.7230 (2.8471) grad_norm: 2.5841 (2.7406) time: 0.5104 [2021-03-27 00:45:49 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 590/1251] eta: 0:05:37 lr: 0.000086 loss: 2.5523 (2.8433) grad_norm: 2.6108 (2.7403) time: 0.5040 [2021-03-27 00:45:54 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 600/1251] eta: 0:05:32 lr: 0.000086 loss: 2.4407 (2.8412) grad_norm: 2.5433 (2.7397) time: 0.5072 [2021-03-27 00:45:59 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 610/1251] eta: 0:05:27 lr: 0.000086 loss: 3.0532 (2.8431) grad_norm: 2.5750 (2.7401) time: 0.5044 [2021-03-27 00:46:04 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 620/1251] eta: 0:05:22 lr: 0.000086 loss: 3.1092 (2.8473) grad_norm: 2.6527 (2.7398) time: 0.4936 [2021-03-27 00:46:09 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 630/1251] eta: 0:05:16 lr: 0.000086 loss: 2.8854 (2.8459) grad_norm: 2.6391 (2.7373) time: 0.4997 [2021-03-27 00:46:14 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 640/1251] eta: 0:05:11 lr: 0.000086 loss: 2.7496 (2.8439) grad_norm: 2.4802 (2.7331) time: 0.4986 [2021-03-27 00:46:19 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 650/1251] eta: 0:05:06 lr: 0.000086 loss: 2.8493 (2.8470) grad_norm: 2.4298 (2.7434) time: 0.4977 [2021-03-27 00:46:24 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 660/1251] eta: 0:05:01 lr: 0.000086 loss: 2.8239 (2.8414) grad_norm: 2.6661 (2.7415) time: 0.5025 [2021-03-27 00:46:29 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 670/1251] eta: 0:04:56 lr: 0.000086 loss: 2.5839 (2.8399) grad_norm: 2.6384 (2.7451) time: 0.5014 [2021-03-27 00:46:34 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 680/1251] eta: 0:04:50 lr: 0.000086 loss: 2.8503 (2.8405) grad_norm: 2.6384 (2.7424) time: 0.4998 [2021-03-27 00:46:39 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 690/1251] eta: 0:04:45 lr: 0.000086 loss: 2.8503 (2.8356) grad_norm: 2.5795 (2.7418) time: 0.4968 [2021-03-27 00:46:44 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 700/1251] eta: 0:04:40 lr: 0.000086 loss: 2.4495 (2.8323) grad_norm: 2.5209 (2.7399) time: 0.4977 [2021-03-27 00:46:49 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 710/1251] eta: 0:04:35 lr: 0.000085 loss: 2.4004 (2.8270) grad_norm: 2.4849 (2.7380) time: 0.4987 [2021-03-27 00:46:54 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 720/1251] eta: 0:04:30 lr: 0.000085 loss: 2.6270 (2.8275) grad_norm: 2.4766 (2.7341) time: 0.5067 [2021-03-27 00:46:59 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 730/1251] eta: 0:04:25 lr: 0.000085 loss: 2.9323 (2.8267) grad_norm: 2.4538 (2.7328) time: 0.5130 [2021-03-27 00:47:05 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 740/1251] eta: 0:04:20 lr: 0.000085 loss: 2.9775 (2.8288) grad_norm: 2.3922 (2.7282) time: 0.5207 [2021-03-27 00:47:10 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 750/1251] eta: 0:04:15 lr: 0.000085 loss: 2.9665 (2.8261) grad_norm: 2.4791 (2.7278) time: 0.5177 [2021-03-27 00:47:15 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 760/1251] eta: 0:04:10 lr: 0.000085 loss: 2.8272 (2.8257) grad_norm: 2.5569 (2.7253) time: 0.4999 [2021-03-27 00:47:20 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 770/1251] eta: 0:04:04 lr: 0.000085 loss: 2.9249 (2.8276) grad_norm: 2.4718 (2.7238) time: 0.5016 [2021-03-27 00:47:25 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 780/1251] eta: 0:03:59 lr: 0.000085 loss: 2.8023 (2.8258) grad_norm: 2.4655 (2.7209) time: 0.5029 [2021-03-27 00:47:30 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 790/1251] eta: 0:03:54 lr: 0.000085 loss: 2.8254 (2.8274) grad_norm: 2.5642 (2.7215) time: 0.5049 [2021-03-27 00:47:35 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 800/1251] eta: 0:03:49 lr: 0.000085 loss: 2.9988 (2.8290) grad_norm: 2.6560 (2.7200) time: 0.5111 [2021-03-27 00:47:40 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 810/1251] eta: 0:03:44 lr: 0.000085 loss: 3.0349 (2.8283) grad_norm: 2.5960 (2.7187) time: 0.5117 [2021-03-27 00:47:45 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 820/1251] eta: 0:03:39 lr: 0.000085 loss: 2.9861 (2.8298) grad_norm: 2.6043 (2.7170) time: 0.5045 [2021-03-27 00:47:50 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 830/1251] eta: 0:03:34 lr: 0.000085 loss: 2.7843 (2.8256) grad_norm: 2.4787 (2.7163) time: 0.4988 [2021-03-27 00:47:55 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 840/1251] eta: 0:03:29 lr: 0.000085 loss: 2.6271 (2.8271) grad_norm: 2.4787 (2.7191) time: 0.4957 [2021-03-27 00:48:00 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 850/1251] eta: 0:03:23 lr: 0.000085 loss: 2.9244 (2.8275) grad_norm: 2.5545 (2.7173) time: 0.4983 [2021-03-27 00:48:05 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 860/1251] eta: 0:03:18 lr: 0.000085 loss: 2.8429 (2.8285) grad_norm: 2.5434 (2.7173) time: 0.5047 [2021-03-27 00:48:10 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 870/1251] eta: 0:03:13 lr: 0.000085 loss: 2.9600 (2.8302) grad_norm: 2.5370 (2.7164) time: 0.5015 [2021-03-27 00:48:15 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 880/1251] eta: 0:03:08 lr: 0.000085 loss: 3.0825 (2.8310) grad_norm: 2.5083 (2.7166) time: 0.4987 [2021-03-27 00:48:20 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 890/1251] eta: 0:03:03 lr: 0.000085 loss: 3.0031 (2.8305) grad_norm: 2.6684 (2.7295) time: 0.5006 [2021-03-27 00:48:25 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 900/1251] eta: 0:02:58 lr: 0.000085 loss: 2.8765 (2.8307) grad_norm: 2.6989 (2.7296) time: 0.5028 [2021-03-27 00:48:30 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 910/1251] eta: 0:02:53 lr: 0.000085 loss: 2.8664 (2.8314) grad_norm: 2.6976 (2.7297) time: 0.5046 [2021-03-27 00:48:35 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 920/1251] eta: 0:02:48 lr: 0.000085 loss: 2.8349 (2.8327) grad_norm: 2.6823 (2.7303) time: 0.4994 [2021-03-27 00:48:40 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 930/1251] eta: 0:02:43 lr: 0.000085 loss: 2.8644 (2.8337) grad_norm: 2.6718 (2.7303) time: 0.5078 [2021-03-27 00:48:46 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 940/1251] eta: 0:02:38 lr: 0.000085 loss: 2.9073 (2.8341) grad_norm: 2.6537 (2.7330) time: 0.5195 [2021-03-27 00:48:50 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 950/1251] eta: 0:02:32 lr: 0.000085 loss: 2.9765 (2.8349) grad_norm: 2.6537 (2.7325) time: 0.5032 [2021-03-27 00:48:56 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 960/1251] eta: 0:02:27 lr: 0.000085 loss: 2.9765 (2.8363) grad_norm: 2.4744 (2.7310) time: 0.4990 [2021-03-27 00:49:01 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 970/1251] eta: 0:02:22 lr: 0.000085 loss: 3.0205 (2.8373) grad_norm: 2.4989 (2.7299) time: 0.5074 [2021-03-27 00:49:06 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 980/1251] eta: 0:02:17 lr: 0.000085 loss: 2.9519 (2.8378) grad_norm: 2.5594 (2.7317) time: 0.5056 [2021-03-27 00:49:11 swin_small_patch4_window7_224] INFO: Epoch: [246] [ 990/1251] eta: 0:02:12 lr: 0.000085 loss: 3.0841 (2.8404) grad_norm: 2.5745 (2.7320) time: 0.5043 [2021-03-27 00:49:16 swin_small_patch4_window7_224] INFO: Epoch: [246] [1000/1251] eta: 0:02:07 lr: 0.000085 loss: 2.8827 (2.8392) grad_norm: 2.5472 (2.7299) time: 0.5056 [2021-03-27 00:49:21 swin_small_patch4_window7_224] INFO: Epoch: [246] [1010/1251] eta: 0:02:02 lr: 0.000085 loss: 2.8495 (2.8396) grad_norm: 2.5480 (2.7279) time: 0.5034 [2021-03-27 00:49:26 swin_small_patch4_window7_224] INFO: Epoch: [246] [1020/1251] eta: 0:01:57 lr: 0.000085 loss: 2.8495 (2.8379) grad_norm: 2.5484 (2.7258) time: 0.5032 [2021-03-27 00:49:31 swin_small_patch4_window7_224] INFO: Epoch: [246] [1030/1251] eta: 0:01:52 lr: 0.000085 loss: 2.8719 (2.8395) grad_norm: 2.5956 (2.7245) time: 0.5030 [2021-03-27 00:49:36 swin_small_patch4_window7_224] INFO: Epoch: [246] [1040/1251] eta: 0:01:47 lr: 0.000085 loss: 2.8616 (2.8371) grad_norm: 2.6020 (2.7237) time: 0.5019 [2021-03-27 00:49:41 swin_small_patch4_window7_224] INFO: Epoch: [246] [1050/1251] eta: 0:01:42 lr: 0.000085 loss: 2.7237 (2.8372) grad_norm: 2.5980 (2.7239) time: 0.5054 [2021-03-27 00:49:46 swin_small_patch4_window7_224] INFO: Epoch: [246] [1060/1251] eta: 0:01:36 lr: 0.000085 loss: 2.8641 (2.8379) grad_norm: 2.5980 (2.7226) time: 0.4998 [2021-03-27 00:49:51 swin_small_patch4_window7_224] INFO: Epoch: [246] [1070/1251] eta: 0:01:31 lr: 0.000085 loss: 2.8618 (2.8369) grad_norm: 2.6188 (2.7225) time: 0.4986 [2021-03-27 00:49:56 swin_small_patch4_window7_224] INFO: Epoch: [246] [1080/1251] eta: 0:01:26 lr: 0.000085 loss: 2.6738 (2.8355) grad_norm: 2.5440 (2.7209) time: 0.5042 [2021-03-27 00:50:01 swin_small_patch4_window7_224] INFO: Epoch: [246] [1090/1251] eta: 0:01:21 lr: 0.000085 loss: 2.6738 (2.8350) grad_norm: 2.5440 (2.7221) time: 0.5001 [2021-03-27 00:50:06 swin_small_patch4_window7_224] INFO: Epoch: [246] [1100/1251] eta: 0:01:16 lr: 0.000085 loss: 2.7169 (2.8336) grad_norm: 2.6248 (2.7217) time: 0.4993 [2021-03-27 00:50:11 swin_small_patch4_window7_224] INFO: Epoch: [246] [1110/1251] eta: 0:01:11 lr: 0.000085 loss: 2.8574 (2.8327) grad_norm: 2.5309 (2.7212) time: 0.5019 [2021-03-27 00:50:16 swin_small_patch4_window7_224] INFO: Epoch: [246] [1120/1251] eta: 0:01:06 lr: 0.000085 loss: 2.9687 (2.8352) grad_norm: 2.5525 (2.7200) time: 0.5042 [2021-03-27 00:50:21 swin_small_patch4_window7_224] INFO: Epoch: [246] [1130/1251] eta: 0:01:01 lr: 0.000085 loss: 3.0359 (2.8374) grad_norm: 2.5242 (2.7178) time: 0.5039 [2021-03-27 00:50:26 swin_small_patch4_window7_224] INFO: Epoch: [246] [1140/1251] eta: 0:00:56 lr: 0.000085 loss: 3.0282 (2.8374) grad_norm: 2.5242 (2.7166) time: 0.5039 [2021-03-27 00:50:31 swin_small_patch4_window7_224] INFO: Epoch: [246] [1150/1251] eta: 0:00:51 lr: 0.000085 loss: 2.7647 (2.8365) grad_norm: 2.4628 (2.7142) time: 0.4999 [2021-03-27 00:50:36 swin_small_patch4_window7_224] INFO: Epoch: [246] [1160/1251] eta: 0:00:46 lr: 0.000085 loss: 2.8602 (2.8356) grad_norm: 2.4310 (2.7118) time: 0.5009 [2021-03-27 00:50:41 swin_small_patch4_window7_224] INFO: Epoch: [246] [1170/1251] eta: 0:00:41 lr: 0.000084 loss: 2.9655 (2.8362) grad_norm: 2.4167 (2.7120) time: 0.5051 [2021-03-27 00:50:46 swin_small_patch4_window7_224] INFO: Epoch: [246] [1180/1251] eta: 0:00:36 lr: 0.000084 loss: 3.0316 (2.8377) grad_norm: 2.5683 (2.7123) time: 0.5016 [2021-03-27 00:50:51 swin_small_patch4_window7_224] INFO: Epoch: [246] [1190/1251] eta: 0:00:30 lr: 0.000084 loss: 3.0316 (2.8377) grad_norm: 2.7077 (2.7161) time: 0.5052 [2021-03-27 00:50:56 swin_small_patch4_window7_224] INFO: Epoch: [246] [1200/1251] eta: 0:00:25 lr: 0.000084 loss: 3.0452 (2.8384) grad_norm: 2.7595 (2.7163) time: 0.5058 [2021-03-27 00:51:01 swin_small_patch4_window7_224] INFO: Epoch: [246] [1210/1251] eta: 0:00:20 lr: 0.000084 loss: 2.8547 (2.8370) grad_norm: 2.7368 (2.7163) time: 0.4993 [2021-03-27 00:51:06 swin_small_patch4_window7_224] INFO: Epoch: [246] [1220/1251] eta: 0:00:15 lr: 0.000084 loss: 2.9096 (2.8372) grad_norm: 2.5085 (2.7150) time: 0.4982 [2021-03-27 00:51:11 swin_small_patch4_window7_224] INFO: Epoch: [246] [1230/1251] eta: 0:00:10 lr: 0.000084 loss: 2.9850 (2.8362) grad_norm: 2.5085 (2.7171) time: 0.5026 [2021-03-27 00:51:16 swin_small_patch4_window7_224] INFO: Epoch: [246] [1240/1251] eta: 0:00:05 lr: 0.000084 loss: 3.0105 (2.8374) grad_norm: 2.6147 (2.7158) time: 0.4978 [2021-03-27 00:51:21 swin_small_patch4_window7_224] INFO: Epoch: [246] [1250/1251] eta: 0:00:00 lr: 0.000084 loss: 3.0327 (2.8385) grad_norm: 2.6147 (2.7154) time: 0.4979 [2021-03-27 00:51:32 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:21 loss: 0.8386 (0.8386) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-27 00:51:34 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.9540 (0.9377) acc1: 76.5625 (77.4148) acc5: 95.3125 (94.6023) [2021-03-27 00:51:37 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7491 (0.8139) acc1: 81.2500 (80.1339) acc5: 95.3125 (95.9077) [2021-03-27 00:51:39 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7124 (0.8090) acc1: 82.8125 (80.3931) acc5: 95.3125 (95.5645) [2021-03-27 00:51:40 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7124 (0.7715) acc1: 82.8125 (81.4024) acc5: 95.3125 (96.0366) [2021-03-27 00:51:41 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6960 (0.7671) acc1: 82.8125 (81.4080) acc5: 96.8750 (96.0640) [2021-03-27 00:51:52 swin_small_patch4_window7_224] INFO: * Acc@1 82.230 Acc@5 96.048 loss 0.758 [2021-03-27 00:51:52 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.2% [2021-03-27 00:51:52 swin_small_patch4_window7_224] INFO: Max accuracy: 82.29% [2021-03-27 00:51:57 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 0/1251] eta: 1:38:26 lr: 0.000084 loss: 2.5793 (2.5793) grad_norm: 3.0330 (3.0330) time: 4.7211 [2021-03-27 00:52:02 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 10/1251] eta: 0:18:18 lr: 0.000084 loss: 3.0705 (2.9933) grad_norm: 2.6535 (2.6488) time: 0.8852 [2021-03-27 00:52:07 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 20/1251] eta: 0:14:28 lr: 0.000084 loss: 3.0705 (3.0006) grad_norm: 2.6231 (2.9337) time: 0.5046 [2021-03-27 00:52:12 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 30/1251] eta: 0:13:01 lr: 0.000084 loss: 2.8229 (2.9103) grad_norm: 2.6231 (2.8514) time: 0.5047 [2021-03-27 00:52:17 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 40/1251] eta: 0:12:17 lr: 0.000084 loss: 2.7838 (2.8645) grad_norm: 2.6462 (2.7937) time: 0.5076 [2021-03-27 00:52:22 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 50/1251] eta: 0:11:47 lr: 0.000084 loss: 2.9198 (2.8275) grad_norm: 2.6331 (2.7904) time: 0.5104 [2021-03-27 00:52:27 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 60/1251] eta: 0:11:23 lr: 0.000084 loss: 2.9360 (2.8165) grad_norm: 2.6606 (2.8421) time: 0.5030 [2021-03-27 00:52:33 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 70/1251] eta: 0:11:07 lr: 0.000084 loss: 2.9360 (2.8182) grad_norm: 2.6584 (2.8323) time: 0.5050 [2021-03-27 00:52:38 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 80/1251] eta: 0:10:52 lr: 0.000084 loss: 2.7501 (2.8083) grad_norm: 2.6377 (2.8536) time: 0.5069 [2021-03-27 00:52:43 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 90/1251] eta: 0:10:40 lr: 0.000084 loss: 2.6577 (2.7912) grad_norm: 2.6377 (2.8478) time: 0.5047 [2021-03-27 00:52:48 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 100/1251] eta: 0:10:28 lr: 0.000084 loss: 2.6709 (2.8000) grad_norm: 2.6324 (2.8260) time: 0.5006 [2021-03-27 00:52:53 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 110/1251] eta: 0:10:19 lr: 0.000084 loss: 3.0326 (2.8091) grad_norm: 2.6940 (2.8861) time: 0.5010 [2021-03-27 00:52:58 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 120/1251] eta: 0:10:09 lr: 0.000084 loss: 2.7403 (2.7888) grad_norm: 2.6940 (2.8748) time: 0.5033 [2021-03-27 00:53:03 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 130/1251] eta: 0:10:02 lr: 0.000084 loss: 2.7447 (2.7909) grad_norm: 2.6907 (2.8668) time: 0.5078 [2021-03-27 00:53:08 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 140/1251] eta: 0:09:54 lr: 0.000084 loss: 3.0046 (2.8033) grad_norm: 2.6665 (2.8564) time: 0.5115 [2021-03-27 00:53:13 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 150/1251] eta: 0:09:48 lr: 0.000084 loss: 3.0516 (2.8115) grad_norm: 2.5568 (2.8343) time: 0.5135 [2021-03-27 00:53:18 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 160/1251] eta: 0:09:40 lr: 0.000084 loss: 2.9656 (2.8063) grad_norm: 2.4918 (2.8211) time: 0.5075 [2021-03-27 00:53:23 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 170/1251] eta: 0:09:32 lr: 0.000084 loss: 2.7811 (2.8136) grad_norm: 2.5914 (2.8093) time: 0.4981 [2021-03-27 00:53:28 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 180/1251] eta: 0:09:25 lr: 0.000084 loss: 2.8639 (2.8239) grad_norm: 2.5914 (2.8162) time: 0.4993 [2021-03-27 00:53:33 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 190/1251] eta: 0:09:18 lr: 0.000084 loss: 2.8376 (2.8125) grad_norm: 2.7116 (2.8183) time: 0.4987 [2021-03-27 00:53:38 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 200/1251] eta: 0:09:12 lr: 0.000084 loss: 2.8349 (2.8061) grad_norm: 2.8595 (2.8281) time: 0.4981 [2021-03-27 00:53:43 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 210/1251] eta: 0:09:05 lr: 0.000084 loss: 2.8349 (2.7983) grad_norm: 2.8455 (2.8228) time: 0.4943 [2021-03-27 00:53:48 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 220/1251] eta: 0:08:58 lr: 0.000084 loss: 2.9745 (2.8107) grad_norm: 2.6994 (2.8253) time: 0.4960 [2021-03-27 00:53:53 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 230/1251] eta: 0:08:53 lr: 0.000084 loss: 3.0480 (2.8154) grad_norm: 2.6994 (2.8222) time: 0.5066 [2021-03-27 00:53:58 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 240/1251] eta: 0:08:47 lr: 0.000084 loss: 2.9490 (2.8150) grad_norm: 2.6819 (2.8175) time: 0.5132 [2021-03-27 00:54:03 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 250/1251] eta: 0:08:41 lr: 0.000084 loss: 2.8870 (2.8119) grad_norm: 2.6099 (2.8138) time: 0.5072 [2021-03-27 00:54:08 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 260/1251] eta: 0:08:36 lr: 0.000084 loss: 2.8691 (2.8130) grad_norm: 2.6099 (2.8072) time: 0.5098 [2021-03-27 00:54:13 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 270/1251] eta: 0:08:30 lr: 0.000084 loss: 2.8753 (2.8146) grad_norm: 2.5981 (2.7981) time: 0.5070 [2021-03-27 00:54:18 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 280/1251] eta: 0:08:23 lr: 0.000084 loss: 2.8753 (2.8070) grad_norm: 2.5228 (2.7962) time: 0.4938 [2021-03-27 00:54:23 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 290/1251] eta: 0:08:18 lr: 0.000084 loss: 2.8415 (2.8086) grad_norm: 2.5158 (2.7900) time: 0.4941 [2021-03-27 00:54:28 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 300/1251] eta: 0:08:12 lr: 0.000084 loss: 3.0017 (2.8121) grad_norm: 2.5863 (2.7879) time: 0.4956 [2021-03-27 00:54:33 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 310/1251] eta: 0:08:06 lr: 0.000084 loss: 3.0971 (2.8164) grad_norm: 2.6496 (2.7860) time: 0.5012 [2021-03-27 00:54:38 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 320/1251] eta: 0:08:01 lr: 0.000084 loss: 2.8656 (2.8172) grad_norm: 2.7736 (2.7839) time: 0.5120 [2021-03-27 00:54:43 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 330/1251] eta: 0:07:55 lr: 0.000084 loss: 3.0033 (2.8232) grad_norm: 2.6892 (2.7795) time: 0.5091 [2021-03-27 00:54:48 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 340/1251] eta: 0:07:50 lr: 0.000084 loss: 3.0549 (2.8241) grad_norm: 2.6414 (2.7784) time: 0.5033 [2021-03-27 00:54:53 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 350/1251] eta: 0:07:44 lr: 0.000084 loss: 2.8355 (2.8232) grad_norm: 2.6753 (2.7802) time: 0.5021 [2021-03-27 00:54:58 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 360/1251] eta: 0:07:39 lr: 0.000084 loss: 2.9676 (2.8243) grad_norm: 2.5841 (2.7743) time: 0.4998 [2021-03-27 00:55:03 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 370/1251] eta: 0:07:33 lr: 0.000083 loss: 2.6389 (2.8171) grad_norm: 2.5536 (2.7693) time: 0.4948 [2021-03-27 00:55:08 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 380/1251] eta: 0:07:27 lr: 0.000083 loss: 2.6137 (2.8192) grad_norm: 2.5581 (2.7679) time: 0.4925 [2021-03-27 00:55:13 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 390/1251] eta: 0:07:22 lr: 0.000083 loss: 2.9294 (2.8174) grad_norm: 2.6586 (2.7682) time: 0.4988 [2021-03-27 00:55:18 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 400/1251] eta: 0:07:17 lr: 0.000083 loss: 2.8247 (2.8177) grad_norm: 2.6586 (2.7639) time: 0.5066 [2021-03-27 00:55:24 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 410/1251] eta: 0:07:11 lr: 0.000083 loss: 2.8272 (2.8202) grad_norm: 2.5918 (2.7617) time: 0.5090 [2021-03-27 00:55:29 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 420/1251] eta: 0:07:06 lr: 0.000083 loss: 2.7423 (2.8161) grad_norm: 2.5565 (2.7559) time: 0.5089 [2021-03-27 00:55:34 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 430/1251] eta: 0:07:01 lr: 0.000083 loss: 2.5699 (2.8124) grad_norm: 2.5270 (2.7581) time: 0.5048 [2021-03-27 00:55:39 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 440/1251] eta: 0:06:56 lr: 0.000083 loss: 2.9213 (2.8120) grad_norm: 2.4964 (2.7558) time: 0.5033 [2021-03-27 00:55:44 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 450/1251] eta: 0:06:50 lr: 0.000083 loss: 2.6481 (2.8079) grad_norm: 2.4686 (2.7511) time: 0.5081 [2021-03-27 00:55:49 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 460/1251] eta: 0:06:45 lr: 0.000083 loss: 2.4990 (2.8056) grad_norm: 2.4625 (2.7496) time: 0.5006 [2021-03-27 00:55:54 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 470/1251] eta: 0:06:39 lr: 0.000083 loss: 2.7008 (2.8021) grad_norm: 2.4797 (2.7459) time: 0.4934 [2021-03-27 00:55:59 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 480/1251] eta: 0:06:34 lr: 0.000083 loss: 2.7008 (2.8030) grad_norm: 2.5294 (2.7426) time: 0.4968 [2021-03-27 00:56:04 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 490/1251] eta: 0:06:29 lr: 0.000083 loss: 3.1072 (2.8056) grad_norm: 2.6940 (2.7421) time: 0.5022 [2021-03-27 00:56:09 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 500/1251] eta: 0:06:24 lr: 0.000083 loss: 3.0143 (2.8033) grad_norm: 2.5636 (2.7517) time: 0.5003 [2021-03-27 00:56:14 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 510/1251] eta: 0:06:18 lr: 0.000083 loss: 2.9219 (2.8033) grad_norm: 2.5636 (2.7537) time: 0.5035 [2021-03-27 00:56:19 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 520/1251] eta: 0:06:13 lr: 0.000083 loss: 2.7239 (2.8014) grad_norm: 2.5718 (2.7521) time: 0.5066 [2021-03-27 00:56:24 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 530/1251] eta: 0:06:08 lr: 0.000083 loss: 2.7364 (2.8030) grad_norm: 2.6600 (2.7527) time: 0.5015 [2021-03-27 00:56:29 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 540/1251] eta: 0:06:03 lr: 0.000083 loss: 3.0599 (2.8047) grad_norm: 2.6732 (2.7537) time: 0.5112 [2021-03-27 00:56:34 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 550/1251] eta: 0:05:58 lr: 0.000083 loss: 2.9929 (2.8085) grad_norm: 2.7097 (2.7541) time: 0.5151 [2021-03-27 00:56:39 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 560/1251] eta: 0:05:53 lr: 0.000083 loss: 2.8556 (2.8082) grad_norm: 2.6402 (2.7513) time: 0.5097 [2021-03-27 00:56:44 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 570/1251] eta: 0:05:47 lr: 0.000083 loss: 2.8520 (2.8092) grad_norm: 2.5357 (2.7504) time: 0.5045 [2021-03-27 00:56:49 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 580/1251] eta: 0:05:42 lr: 0.000083 loss: 2.9453 (2.8136) grad_norm: 2.6555 (2.7554) time: 0.5002 [2021-03-27 00:56:54 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 590/1251] eta: 0:05:37 lr: 0.000083 loss: 2.9527 (2.8125) grad_norm: 2.8739 (2.7595) time: 0.5067 [2021-03-27 00:56:59 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 600/1251] eta: 0:05:32 lr: 0.000083 loss: 2.9527 (2.8144) grad_norm: 2.8006 (2.7604) time: 0.5105 [2021-03-27 00:57:04 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 610/1251] eta: 0:05:27 lr: 0.000083 loss: 3.0333 (2.8152) grad_norm: 2.5661 (2.7563) time: 0.5017 [2021-03-27 00:57:09 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 620/1251] eta: 0:05:22 lr: 0.000083 loss: 2.8936 (2.8165) grad_norm: 2.5624 (2.7560) time: 0.4975 [2021-03-27 00:57:14 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 630/1251] eta: 0:05:16 lr: 0.000083 loss: 2.9412 (2.8147) grad_norm: 2.8064 (2.7599) time: 0.4999 [2021-03-27 00:57:19 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 640/1251] eta: 0:05:11 lr: 0.000083 loss: 2.8405 (2.8128) grad_norm: 2.8064 (2.7583) time: 0.4979 [2021-03-27 00:57:24 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 650/1251] eta: 0:05:06 lr: 0.000083 loss: 2.7841 (2.8124) grad_norm: 2.5631 (2.7574) time: 0.5005 [2021-03-27 00:57:29 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 660/1251] eta: 0:05:01 lr: 0.000083 loss: 2.7841 (2.8133) grad_norm: 2.5999 (2.7581) time: 0.4977 [2021-03-27 00:57:34 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 670/1251] eta: 0:04:55 lr: 0.000083 loss: 2.9417 (2.8142) grad_norm: 2.5355 (2.7548) time: 0.4911 [2021-03-27 00:57:39 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 680/1251] eta: 0:04:50 lr: 0.000083 loss: 2.9424 (2.8133) grad_norm: 2.4758 (2.7537) time: 0.4944 [2021-03-27 00:57:44 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 690/1251] eta: 0:04:45 lr: 0.000083 loss: 2.9424 (2.8140) grad_norm: 2.6113 (2.7550) time: 0.4969 [2021-03-27 00:57:49 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 700/1251] eta: 0:04:40 lr: 0.000083 loss: 2.8889 (2.8131) grad_norm: 2.6119 (2.7581) time: 0.5008 [2021-03-27 00:57:54 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 710/1251] eta: 0:04:35 lr: 0.000083 loss: 2.8959 (2.8138) grad_norm: 2.6434 (2.7590) time: 0.5031 [2021-03-27 00:57:59 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 720/1251] eta: 0:04:30 lr: 0.000083 loss: 2.8959 (2.8142) grad_norm: 2.5363 (2.7565) time: 0.5003 [2021-03-27 00:58:04 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 730/1251] eta: 0:04:24 lr: 0.000083 loss: 2.9337 (2.8159) grad_norm: 2.5327 (2.7587) time: 0.4966 [2021-03-27 00:58:09 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 740/1251] eta: 0:04:19 lr: 0.000083 loss: 3.0478 (2.8176) grad_norm: 2.5858 (2.7587) time: 0.5101 [2021-03-27 00:58:14 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 750/1251] eta: 0:04:14 lr: 0.000083 loss: 2.9430 (2.8177) grad_norm: 2.5291 (2.7559) time: 0.5114 [2021-03-27 00:58:19 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 760/1251] eta: 0:04:09 lr: 0.000083 loss: 2.9062 (2.8189) grad_norm: 2.4210 (2.7519) time: 0.4945 [2021-03-27 00:58:24 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 770/1251] eta: 0:04:04 lr: 0.000083 loss: 3.0551 (2.8216) grad_norm: 2.4210 (2.7486) time: 0.4975 [2021-03-27 00:58:29 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 780/1251] eta: 0:03:59 lr: 0.000083 loss: 3.1222 (2.8250) grad_norm: 2.4855 (2.7454) time: 0.5060 [2021-03-27 00:58:35 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 790/1251] eta: 0:03:54 lr: 0.000083 loss: 3.0051 (2.8268) grad_norm: 2.4582 (2.7429) time: 0.5145 [2021-03-27 00:58:40 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 800/1251] eta: 0:03:49 lr: 0.000083 loss: 2.9124 (2.8251) grad_norm: 2.4602 (2.7431) time: 0.5119 [2021-03-27 00:58:45 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 810/1251] eta: 0:03:44 lr: 0.000083 loss: 2.8819 (2.8262) grad_norm: 2.5757 (2.7424) time: 0.5058 [2021-03-27 00:58:50 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 820/1251] eta: 0:03:39 lr: 0.000083 loss: 2.8819 (2.8275) grad_norm: 2.4796 (2.7417) time: 0.5038 [2021-03-27 00:58:55 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 830/1251] eta: 0:03:33 lr: 0.000083 loss: 3.0348 (2.8304) grad_norm: 2.4796 (2.7411) time: 0.5019 [2021-03-27 00:59:00 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 840/1251] eta: 0:03:28 lr: 0.000082 loss: 3.0348 (2.8318) grad_norm: 2.5975 (2.7396) time: 0.5076 [2021-03-27 00:59:05 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 850/1251] eta: 0:03:23 lr: 0.000082 loss: 3.0082 (2.8324) grad_norm: 2.7285 (2.7411) time: 0.5124 [2021-03-27 00:59:10 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 860/1251] eta: 0:03:18 lr: 0.000082 loss: 3.0437 (2.8341) grad_norm: 2.7285 (2.7396) time: 0.5032 [2021-03-27 00:59:15 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 870/1251] eta: 0:03:13 lr: 0.000082 loss: 2.9304 (2.8346) grad_norm: 2.5616 (2.7393) time: 0.5032 [2021-03-27 00:59:20 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 880/1251] eta: 0:03:08 lr: 0.000082 loss: 3.0348 (2.8383) grad_norm: 2.4666 (2.7367) time: 0.5051 [2021-03-27 00:59:25 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 890/1251] eta: 0:03:03 lr: 0.000082 loss: 3.0248 (2.8394) grad_norm: 2.4989 (2.7347) time: 0.5012 [2021-03-27 00:59:30 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 900/1251] eta: 0:02:58 lr: 0.000082 loss: 2.8672 (2.8386) grad_norm: 2.5826 (2.7324) time: 0.4997 [2021-03-27 00:59:35 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 910/1251] eta: 0:02:53 lr: 0.000082 loss: 2.8210 (2.8379) grad_norm: 2.5631 (2.7330) time: 0.4975 [2021-03-27 00:59:40 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 920/1251] eta: 0:02:48 lr: 0.000082 loss: 3.0308 (2.8407) grad_norm: 2.5871 (2.7329) time: 0.5031 [2021-03-27 00:59:45 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 930/1251] eta: 0:02:42 lr: 0.000082 loss: 3.1010 (2.8408) grad_norm: 2.5902 (2.7314) time: 0.5054 [2021-03-27 00:59:50 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 940/1251] eta: 0:02:37 lr: 0.000082 loss: 2.9071 (2.8411) grad_norm: 2.5382 (2.7328) time: 0.5020 [2021-03-27 00:59:55 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 950/1251] eta: 0:02:32 lr: 0.000082 loss: 2.8728 (2.8413) grad_norm: 2.6269 (2.7327) time: 0.4972 [2021-03-27 01:00:00 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 960/1251] eta: 0:02:27 lr: 0.000082 loss: 3.0146 (2.8438) grad_norm: 2.6501 (2.7324) time: 0.4952 [2021-03-27 01:00:05 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 970/1251] eta: 0:02:22 lr: 0.000082 loss: 2.9033 (2.8424) grad_norm: 2.6869 (2.7327) time: 0.5013 [2021-03-27 01:00:10 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 980/1251] eta: 0:02:17 lr: 0.000082 loss: 2.8091 (2.8433) grad_norm: 2.7182 (2.7338) time: 0.5052 [2021-03-27 01:00:15 swin_small_patch4_window7_224] INFO: Epoch: [247] [ 990/1251] eta: 0:02:12 lr: 0.000082 loss: 2.8091 (2.8406) grad_norm: 2.7145 (2.7337) time: 0.5106 [2021-03-27 01:00:20 swin_small_patch4_window7_224] INFO: Epoch: [247] [1000/1251] eta: 0:02:07 lr: 0.000082 loss: 2.5966 (2.8378) grad_norm: 2.6041 (2.7323) time: 0.5096 [2021-03-27 01:00:25 swin_small_patch4_window7_224] INFO: Epoch: [247] [1010/1251] eta: 0:02:02 lr: 0.000082 loss: 2.7637 (2.8381) grad_norm: 2.6041 (2.7314) time: 0.5003 [2021-03-27 01:00:30 swin_small_patch4_window7_224] INFO: Epoch: [247] [1020/1251] eta: 0:01:57 lr: 0.000082 loss: 2.8388 (2.8378) grad_norm: 2.6431 (2.7301) time: 0.4996 [2021-03-27 01:00:35 swin_small_patch4_window7_224] INFO: Epoch: [247] [1030/1251] eta: 0:01:52 lr: 0.000082 loss: 2.7996 (2.8370) grad_norm: 2.5572 (2.7291) time: 0.4995 [2021-03-27 01:00:40 swin_small_patch4_window7_224] INFO: Epoch: [247] [1040/1251] eta: 0:01:46 lr: 0.000082 loss: 2.7505 (2.8375) grad_norm: 2.6029 (2.7307) time: 0.4987 [2021-03-27 01:00:46 swin_small_patch4_window7_224] INFO: Epoch: [247] [1050/1251] eta: 0:01:41 lr: 0.000082 loss: 2.9709 (2.8395) grad_norm: 2.6260 (2.7309) time: 0.5066 [2021-03-27 01:00:51 swin_small_patch4_window7_224] INFO: Epoch: [247] [1060/1251] eta: 0:01:36 lr: 0.000082 loss: 3.0490 (2.8405) grad_norm: 2.5237 (2.7290) time: 0.5118 [2021-03-27 01:00:56 swin_small_patch4_window7_224] INFO: Epoch: [247] [1070/1251] eta: 0:01:31 lr: 0.000082 loss: 3.0163 (2.8398) grad_norm: 2.5984 (2.7301) time: 0.5119 [2021-03-27 01:01:01 swin_small_patch4_window7_224] INFO: Epoch: [247] [1080/1251] eta: 0:01:26 lr: 0.000082 loss: 2.8171 (2.8398) grad_norm: 2.6733 (2.7298) time: 0.5090 [2021-03-27 01:01:06 swin_small_patch4_window7_224] INFO: Epoch: [247] [1090/1251] eta: 0:01:21 lr: 0.000082 loss: 2.7134 (2.8374) grad_norm: 2.4683 (2.7296) time: 0.4970 [2021-03-27 01:01:11 swin_small_patch4_window7_224] INFO: Epoch: [247] [1100/1251] eta: 0:01:16 lr: 0.000082 loss: 2.8957 (2.8388) grad_norm: 2.4381 (2.7280) time: 0.4970 [2021-03-27 01:01:16 swin_small_patch4_window7_224] INFO: Epoch: [247] [1110/1251] eta: 0:01:11 lr: 0.000082 loss: 3.0713 (2.8408) grad_norm: 2.5885 (2.7292) time: 0.5070 [2021-03-27 01:01:21 swin_small_patch4_window7_224] INFO: Epoch: [247] [1120/1251] eta: 0:01:06 lr: 0.000082 loss: 2.9789 (2.8405) grad_norm: 2.5249 (2.7271) time: 0.5092 [2021-03-27 01:01:26 swin_small_patch4_window7_224] INFO: Epoch: [247] [1130/1251] eta: 0:01:01 lr: 0.000082 loss: 2.8795 (2.8396) grad_norm: 2.4892 (2.7269) time: 0.5028 [2021-03-27 01:01:31 swin_small_patch4_window7_224] INFO: Epoch: [247] [1140/1251] eta: 0:00:56 lr: 0.000082 loss: 2.9481 (2.8380) grad_norm: 2.7158 (2.7271) time: 0.5023 [2021-03-27 01:01:36 swin_small_patch4_window7_224] INFO: Epoch: [247] [1150/1251] eta: 0:00:51 lr: 0.000082 loss: 2.8138 (2.8368) grad_norm: 2.6472 (2.7275) time: 0.5015 [2021-03-27 01:01:41 swin_small_patch4_window7_224] INFO: Epoch: [247] [1160/1251] eta: 0:00:46 lr: 0.000082 loss: 2.5840 (2.8351) grad_norm: 2.6162 (2.7267) time: 0.5028 [2021-03-27 01:01:46 swin_small_patch4_window7_224] INFO: Epoch: [247] [1170/1251] eta: 0:00:41 lr: 0.000082 loss: 2.6014 (2.8347) grad_norm: 2.6162 (2.7261) time: 0.5055 [2021-03-27 01:01:51 swin_small_patch4_window7_224] INFO: Epoch: [247] [1180/1251] eta: 0:00:35 lr: 0.000082 loss: 2.6014 (2.8320) grad_norm: 2.5460 (2.7254) time: 0.5052 [2021-03-27 01:01:56 swin_small_patch4_window7_224] INFO: Epoch: [247] [1190/1251] eta: 0:00:30 lr: 0.000082 loss: 2.6940 (2.8328) grad_norm: 2.5790 (2.7251) time: 0.5077 [2021-03-27 01:02:01 swin_small_patch4_window7_224] INFO: Epoch: [247] [1200/1251] eta: 0:00:25 lr: 0.000082 loss: 3.0107 (2.8352) grad_norm: 2.6725 (2.7253) time: 0.4982 [2021-03-27 01:02:06 swin_small_patch4_window7_224] INFO: Epoch: [247] [1210/1251] eta: 0:00:20 lr: 0.000082 loss: 2.9631 (2.8355) grad_norm: 2.6422 (2.7254) time: 0.5011 [2021-03-27 01:02:11 swin_small_patch4_window7_224] INFO: Epoch: [247] [1220/1251] eta: 0:00:15 lr: 0.000082 loss: 3.0213 (2.8361) grad_norm: 2.6991 (2.7266) time: 0.5049 [2021-03-27 01:02:16 swin_small_patch4_window7_224] INFO: Epoch: [247] [1230/1251] eta: 0:00:10 lr: 0.000082 loss: 3.0213 (2.8359) grad_norm: 2.6991 (2.7289) time: 0.5003 [2021-03-27 01:02:21 swin_small_patch4_window7_224] INFO: Epoch: [247] [1240/1251] eta: 0:00:05 lr: 0.000082 loss: 2.8298 (2.8353) grad_norm: 2.4588 (2.7267) time: 0.5045 [2021-03-27 01:02:26 swin_small_patch4_window7_224] INFO: Epoch: [247] [1250/1251] eta: 0:00:00 lr: 0.000082 loss: 2.8298 (2.8359) grad_norm: 2.4588 (2.7252) time: 0.4985 [2021-03-27 01:02:36 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 0.4799 (0.4799) acc1: 92.1875 (92.1875) acc5: 98.4375 (98.4375) [2021-03-27 01:02:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7721 (0.8010) acc1: 81.2500 (82.2443) acc5: 96.8750 (96.0227) [2021-03-27 01:02:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.8077 (0.8097) acc1: 79.6875 (81.1756) acc5: 96.8750 (96.1310) [2021-03-27 01:02:43 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7661 (0.7962) acc1: 81.2500 (81.4012) acc5: 96.8750 (95.9173) [2021-03-27 01:02:44 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7654 (0.7866) acc1: 82.8125 (81.5549) acc5: 95.3125 (95.9223) [2021-03-27 01:02:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7043 (0.7681) acc1: 82.8125 (81.9840) acc5: 96.8750 (96.2560) [2021-03-27 01:02:55 swin_small_patch4_window7_224] INFO: * Acc@1 82.222 Acc@5 96.094 loss 0.755 [2021-03-27 01:02:55 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.2% [2021-03-27 01:02:55 swin_small_patch4_window7_224] INFO: Max accuracy: 82.29% [2021-03-27 01:02:59 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 0/1251] eta: 1:31:25 lr: 0.000082 loss: 2.3084 (2.3084) grad_norm: 2.7589 (2.7589) time: 4.3846 [2021-03-27 01:03:04 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 10/1251] eta: 0:17:48 lr: 0.000082 loss: 2.8131 (2.8206) grad_norm: 2.4110 (2.4950) time: 0.8608 [2021-03-27 01:03:09 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 20/1251] eta: 0:14:16 lr: 0.000082 loss: 2.8621 (2.8503) grad_norm: 2.4110 (2.5202) time: 0.5114 [2021-03-27 01:03:14 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 30/1251] eta: 0:12:52 lr: 0.000082 loss: 2.8621 (2.8157) grad_norm: 2.6072 (2.5561) time: 0.5071 [2021-03-27 01:03:19 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 40/1251] eta: 0:12:05 lr: 0.000082 loss: 2.8740 (2.8253) grad_norm: 2.5540 (2.5982) time: 0.4983 [2021-03-27 01:03:24 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 50/1251] eta: 0:11:36 lr: 0.000081 loss: 2.7759 (2.7866) grad_norm: 2.3727 (2.5580) time: 0.4978 [2021-03-27 01:03:29 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 60/1251] eta: 0:11:16 lr: 0.000081 loss: 2.6252 (2.7633) grad_norm: 2.4236 (2.5812) time: 0.5041 [2021-03-27 01:03:34 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 70/1251] eta: 0:10:58 lr: 0.000081 loss: 2.9635 (2.7756) grad_norm: 2.6672 (2.5950) time: 0.5011 [2021-03-27 01:03:39 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 80/1251] eta: 0:10:43 lr: 0.000081 loss: 2.9832 (2.7954) grad_norm: 2.7274 (2.6081) time: 0.4938 [2021-03-27 01:03:44 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 90/1251] eta: 0:10:35 lr: 0.000081 loss: 2.9616 (2.8207) grad_norm: 2.6014 (2.6105) time: 0.5094 [2021-03-27 01:03:49 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 100/1251] eta: 0:10:25 lr: 0.000081 loss: 3.0420 (2.8085) grad_norm: 2.5787 (2.6361) time: 0.5162 [2021-03-27 01:03:54 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 110/1251] eta: 0:10:15 lr: 0.000081 loss: 2.9191 (2.8221) grad_norm: 2.5787 (2.6415) time: 0.5060 [2021-03-27 01:03:59 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 120/1251] eta: 0:10:06 lr: 0.000081 loss: 2.7880 (2.8075) grad_norm: 2.5199 (2.6300) time: 0.5004 [2021-03-27 01:04:05 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 130/1251] eta: 0:09:59 lr: 0.000081 loss: 2.4855 (2.7861) grad_norm: 2.5733 (2.6363) time: 0.5085 [2021-03-27 01:04:10 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 140/1251] eta: 0:09:51 lr: 0.000081 loss: 2.9864 (2.8040) grad_norm: 2.5802 (2.6308) time: 0.5105 [2021-03-27 01:04:15 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 150/1251] eta: 0:09:44 lr: 0.000081 loss: 3.0605 (2.8105) grad_norm: 2.5785 (2.6408) time: 0.5056 [2021-03-27 01:04:20 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 160/1251] eta: 0:09:37 lr: 0.000081 loss: 2.9600 (2.8158) grad_norm: 2.5785 (2.6357) time: 0.5085 [2021-03-27 01:04:25 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 170/1251] eta: 0:09:30 lr: 0.000081 loss: 2.9464 (2.8254) grad_norm: 2.5603 (2.6338) time: 0.5053 [2021-03-27 01:04:30 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 180/1251] eta: 0:09:23 lr: 0.000081 loss: 3.0122 (2.8314) grad_norm: 2.5422 (2.6288) time: 0.4987 [2021-03-27 01:04:35 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 190/1251] eta: 0:09:17 lr: 0.000081 loss: 3.0900 (2.8384) grad_norm: 2.5482 (2.6316) time: 0.5017 [2021-03-27 01:04:40 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 200/1251] eta: 0:09:12 lr: 0.000081 loss: 3.1251 (2.8458) grad_norm: 2.5748 (2.6261) time: 0.5193 [2021-03-27 01:04:45 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 210/1251] eta: 0:09:06 lr: 0.000081 loss: 3.1362 (2.8516) grad_norm: 2.5193 (2.6296) time: 0.5181 [2021-03-27 01:04:50 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 220/1251] eta: 0:08:59 lr: 0.000081 loss: 3.0232 (2.8558) grad_norm: 2.7519 (2.6366) time: 0.5067 [2021-03-27 01:04:55 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 230/1251] eta: 0:08:54 lr: 0.000081 loss: 2.8867 (2.8464) grad_norm: 2.6570 (2.6299) time: 0.5070 [2021-03-27 01:05:00 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 240/1251] eta: 0:08:47 lr: 0.000081 loss: 2.8491 (2.8452) grad_norm: 2.4114 (2.6284) time: 0.5060 [2021-03-27 01:05:05 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 250/1251] eta: 0:08:41 lr: 0.000081 loss: 2.8393 (2.8417) grad_norm: 2.4018 (2.6271) time: 0.5001 [2021-03-27 01:05:10 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 260/1251] eta: 0:08:35 lr: 0.000081 loss: 2.8359 (2.8435) grad_norm: 2.5971 (2.6293) time: 0.5012 [2021-03-27 01:05:16 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 270/1251] eta: 0:08:30 lr: 0.000081 loss: 2.8351 (2.8371) grad_norm: 2.5339 (2.6299) time: 0.5071 [2021-03-27 01:05:21 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 280/1251] eta: 0:08:24 lr: 0.000081 loss: 2.8031 (2.8402) grad_norm: 2.5160 (2.6257) time: 0.5074 [2021-03-27 01:05:26 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 290/1251] eta: 0:08:18 lr: 0.000081 loss: 2.8413 (2.8347) grad_norm: 2.4550 (2.6208) time: 0.5055 [2021-03-27 01:05:31 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 300/1251] eta: 0:08:13 lr: 0.000081 loss: 2.8104 (2.8294) grad_norm: 2.4550 (2.6212) time: 0.5031 [2021-03-27 01:05:36 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 310/1251] eta: 0:08:07 lr: 0.000081 loss: 2.8539 (2.8285) grad_norm: 2.6056 (2.6199) time: 0.4984 [2021-03-27 01:05:41 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 320/1251] eta: 0:08:01 lr: 0.000081 loss: 2.8913 (2.8319) grad_norm: 2.5159 (2.6230) time: 0.4986 [2021-03-27 01:05:46 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 330/1251] eta: 0:07:56 lr: 0.000081 loss: 2.8131 (2.8285) grad_norm: 2.5093 (2.6222) time: 0.5014 [2021-03-27 01:05:51 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 340/1251] eta: 0:07:50 lr: 0.000081 loss: 2.8211 (2.8325) grad_norm: 2.5055 (2.6190) time: 0.5031 [2021-03-27 01:05:56 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 350/1251] eta: 0:07:45 lr: 0.000081 loss: 2.8705 (2.8309) grad_norm: 2.5691 (2.6206) time: 0.5074 [2021-03-27 01:06:01 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 360/1251] eta: 0:07:39 lr: 0.000081 loss: 2.6922 (2.8272) grad_norm: 2.7125 (2.6397) time: 0.5105 [2021-03-27 01:06:06 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 370/1251] eta: 0:07:34 lr: 0.000081 loss: 2.9248 (2.8284) grad_norm: 2.7491 (2.6431) time: 0.5116 [2021-03-27 01:06:11 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 380/1251] eta: 0:07:28 lr: 0.000081 loss: 3.0439 (2.8345) grad_norm: 2.6770 (2.6508) time: 0.5025 [2021-03-27 01:06:16 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 390/1251] eta: 0:07:23 lr: 0.000081 loss: 3.0027 (2.8373) grad_norm: 2.8163 (2.6579) time: 0.4976 [2021-03-27 01:06:21 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 400/1251] eta: 0:07:18 lr: 0.000081 loss: 2.9165 (2.8349) grad_norm: 2.9608 (2.6619) time: 0.5039 [2021-03-27 01:06:26 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 410/1251] eta: 0:07:12 lr: 0.000081 loss: 2.8102 (2.8350) grad_norm: 2.7346 (2.6648) time: 0.5062 [2021-03-27 01:06:31 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 420/1251] eta: 0:07:07 lr: 0.000081 loss: 2.8743 (2.8367) grad_norm: 2.6792 (2.6651) time: 0.5019 [2021-03-27 01:06:36 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 430/1251] eta: 0:07:01 lr: 0.000081 loss: 3.0357 (2.8404) grad_norm: 2.6005 (2.6634) time: 0.5002 [2021-03-27 01:06:41 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 440/1251] eta: 0:06:56 lr: 0.000081 loss: 3.0441 (2.8382) grad_norm: 2.6170 (2.6655) time: 0.5024 [2021-03-27 01:06:46 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 450/1251] eta: 0:06:51 lr: 0.000081 loss: 2.8457 (2.8354) grad_norm: 2.6396 (2.6682) time: 0.5046 [2021-03-27 01:06:51 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 460/1251] eta: 0:06:46 lr: 0.000081 loss: 2.8114 (2.8338) grad_norm: 2.6610 (2.6737) time: 0.5058 [2021-03-27 01:06:56 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 470/1251] eta: 0:06:40 lr: 0.000081 loss: 2.9371 (2.8359) grad_norm: 2.7774 (2.6797) time: 0.5002 [2021-03-27 01:07:01 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 480/1251] eta: 0:06:35 lr: 0.000081 loss: 2.9406 (2.8356) grad_norm: 2.7901 (2.6837) time: 0.4997 [2021-03-27 01:07:06 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 490/1251] eta: 0:06:29 lr: 0.000081 loss: 3.0640 (2.8399) grad_norm: 2.7901 (2.6874) time: 0.4989 [2021-03-27 01:07:11 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 500/1251] eta: 0:06:24 lr: 0.000081 loss: 3.1223 (2.8446) grad_norm: 2.7304 (2.6898) time: 0.5036 [2021-03-27 01:07:16 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 510/1251] eta: 0:06:19 lr: 0.000081 loss: 3.0059 (2.8449) grad_norm: 2.6830 (2.6895) time: 0.5046 [2021-03-27 01:07:21 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 520/1251] eta: 0:06:14 lr: 0.000080 loss: 2.9798 (2.8445) grad_norm: 2.6253 (2.6889) time: 0.4983 [2021-03-27 01:07:26 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 530/1251] eta: 0:06:08 lr: 0.000080 loss: 2.8952 (2.8450) grad_norm: 2.6618 (2.6894) time: 0.5011 [2021-03-27 01:07:32 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 540/1251] eta: 0:06:03 lr: 0.000080 loss: 2.9040 (2.8479) grad_norm: 2.6750 (2.6896) time: 0.5130 [2021-03-27 01:07:37 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 550/1251] eta: 0:05:59 lr: 0.000080 loss: 2.9523 (2.8486) grad_norm: 2.6750 (2.6889) time: 0.5257 [2021-03-27 01:07:42 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 560/1251] eta: 0:05:53 lr: 0.000080 loss: 2.9431 (2.8481) grad_norm: 2.6384 (2.6880) time: 0.5165 [2021-03-27 01:07:47 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 570/1251] eta: 0:05:48 lr: 0.000080 loss: 2.8024 (2.8493) grad_norm: 2.5792 (2.6878) time: 0.5036 [2021-03-27 01:07:52 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 580/1251] eta: 0:05:43 lr: 0.000080 loss: 2.8460 (2.8520) grad_norm: 2.6070 (2.6875) time: 0.5013 [2021-03-27 01:07:57 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 590/1251] eta: 0:05:38 lr: 0.000080 loss: 2.8780 (2.8532) grad_norm: 2.6070 (2.6866) time: 0.4995 [2021-03-27 01:08:02 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 600/1251] eta: 0:05:32 lr: 0.000080 loss: 2.8780 (2.8519) grad_norm: 2.5262 (2.6869) time: 0.5049 [2021-03-27 01:08:07 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 610/1251] eta: 0:05:27 lr: 0.000080 loss: 2.8596 (2.8502) grad_norm: 2.6338 (2.6871) time: 0.5059 [2021-03-27 01:08:12 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 620/1251] eta: 0:05:22 lr: 0.000080 loss: 2.9710 (2.8519) grad_norm: 2.6338 (2.6876) time: 0.4970 [2021-03-27 01:08:17 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 630/1251] eta: 0:05:17 lr: 0.000080 loss: 2.7751 (2.8477) grad_norm: 2.5437 (2.6850) time: 0.4932 [2021-03-27 01:08:22 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 640/1251] eta: 0:05:11 lr: 0.000080 loss: 2.7751 (2.8489) grad_norm: 2.6489 (2.6859) time: 0.4971 [2021-03-27 01:08:27 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 650/1251] eta: 0:05:06 lr: 0.000080 loss: 3.0114 (2.8507) grad_norm: 2.6572 (2.6866) time: 0.5058 [2021-03-27 01:08:32 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 660/1251] eta: 0:05:01 lr: 0.000080 loss: 2.9745 (2.8506) grad_norm: 2.6688 (2.6876) time: 0.5076 [2021-03-27 01:08:37 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 670/1251] eta: 0:04:56 lr: 0.000080 loss: 2.6790 (2.8453) grad_norm: 2.5879 (2.6871) time: 0.5037 [2021-03-27 01:08:42 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 680/1251] eta: 0:04:51 lr: 0.000080 loss: 2.6790 (2.8453) grad_norm: 2.5879 (2.6855) time: 0.5045 [2021-03-27 01:08:47 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 690/1251] eta: 0:04:46 lr: 0.000080 loss: 2.9610 (2.8464) grad_norm: 2.6612 (2.6911) time: 0.5094 [2021-03-27 01:08:52 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 700/1251] eta: 0:04:41 lr: 0.000080 loss: 2.8705 (2.8453) grad_norm: 2.6612 (2.6905) time: 0.5025 [2021-03-27 01:08:57 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 710/1251] eta: 0:04:35 lr: 0.000080 loss: 2.8077 (2.8432) grad_norm: 2.5755 (2.6899) time: 0.4975 [2021-03-27 01:09:02 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 720/1251] eta: 0:04:30 lr: 0.000080 loss: 2.7981 (2.8393) grad_norm: 2.5886 (2.6904) time: 0.5055 [2021-03-27 01:09:08 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 730/1251] eta: 0:04:25 lr: 0.000080 loss: 2.4755 (2.8351) grad_norm: 2.6413 (2.6936) time: 0.5109 [2021-03-27 01:09:13 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 740/1251] eta: 0:04:20 lr: 0.000080 loss: 2.5488 (2.8312) grad_norm: 2.6800 (2.6950) time: 0.5231 [2021-03-27 01:09:18 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 750/1251] eta: 0:04:15 lr: 0.000080 loss: 2.7516 (2.8325) grad_norm: 2.6378 (2.6974) time: 0.5324 [2021-03-27 01:09:23 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 760/1251] eta: 0:04:10 lr: 0.000080 loss: 2.9533 (2.8328) grad_norm: 2.6357 (2.6956) time: 0.5153 [2021-03-27 01:09:28 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 770/1251] eta: 0:04:05 lr: 0.000080 loss: 2.9045 (2.8320) grad_norm: 2.4187 (2.6933) time: 0.4965 [2021-03-27 01:09:33 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 780/1251] eta: 0:04:00 lr: 0.000080 loss: 2.7605 (2.8307) grad_norm: 2.5147 (2.6945) time: 0.4935 [2021-03-27 01:09:38 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 790/1251] eta: 0:03:55 lr: 0.000080 loss: 2.8267 (2.8330) grad_norm: 2.6409 (2.6939) time: 0.4944 [2021-03-27 01:09:43 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 800/1251] eta: 0:03:49 lr: 0.000080 loss: 2.8970 (2.8320) grad_norm: 2.6020 (2.6941) time: 0.4938 [2021-03-27 01:09:48 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 810/1251] eta: 0:03:44 lr: 0.000080 loss: 2.8828 (2.8309) grad_norm: 2.5728 (2.6929) time: 0.5025 [2021-03-27 01:09:53 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 820/1251] eta: 0:03:39 lr: 0.000080 loss: 2.9109 (2.8313) grad_norm: 2.5386 (2.6952) time: 0.5076 [2021-03-27 01:09:58 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 830/1251] eta: 0:03:34 lr: 0.000080 loss: 2.9109 (2.8314) grad_norm: 2.6587 (2.7015) time: 0.5081 [2021-03-27 01:10:03 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 840/1251] eta: 0:03:29 lr: 0.000080 loss: 2.7921 (2.8315) grad_norm: 2.6939 (2.7092) time: 0.5118 [2021-03-27 01:10:08 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 850/1251] eta: 0:03:24 lr: 0.000080 loss: 3.0776 (2.8355) grad_norm: 2.9733 (2.7126) time: 0.5005 [2021-03-27 01:10:13 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 860/1251] eta: 0:03:19 lr: 0.000080 loss: 3.0776 (2.8347) grad_norm: 2.6836 (2.7111) time: 0.4946 [2021-03-27 01:10:18 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 870/1251] eta: 0:03:14 lr: 0.000080 loss: 2.8726 (2.8345) grad_norm: 2.7074 (2.7140) time: 0.5027 [2021-03-27 01:10:23 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 880/1251] eta: 0:03:08 lr: 0.000080 loss: 2.7941 (2.8342) grad_norm: 2.7242 (2.7166) time: 0.5128 [2021-03-27 01:10:28 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 890/1251] eta: 0:03:03 lr: 0.000080 loss: 2.7472 (2.8314) grad_norm: 2.6337 (2.7162) time: 0.5057 [2021-03-27 01:10:33 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 900/1251] eta: 0:02:58 lr: 0.000080 loss: 2.7331 (2.8329) grad_norm: 2.5649 (2.7148) time: 0.4932 [2021-03-27 01:10:38 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 910/1251] eta: 0:02:53 lr: 0.000080 loss: 2.9953 (2.8331) grad_norm: 2.6136 (2.7151) time: 0.4945 [2021-03-27 01:10:43 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 920/1251] eta: 0:02:48 lr: 0.000080 loss: 3.1128 (2.8348) grad_norm: 2.6155 (2.7143) time: 0.4968 [2021-03-27 01:10:48 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 930/1251] eta: 0:02:43 lr: 0.000080 loss: 2.9934 (2.8338) grad_norm: 2.6165 (2.7144) time: 0.4980 [2021-03-27 01:10:53 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 940/1251] eta: 0:02:38 lr: 0.000080 loss: 2.6883 (2.8325) grad_norm: 2.6792 (2.7139) time: 0.5091 [2021-03-27 01:10:58 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 950/1251] eta: 0:02:33 lr: 0.000080 loss: 2.7715 (2.8321) grad_norm: 2.6792 (2.7147) time: 0.5119 [2021-03-27 01:11:03 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 960/1251] eta: 0:02:27 lr: 0.000080 loss: 3.0168 (2.8343) grad_norm: 2.6706 (2.7140) time: 0.5010 [2021-03-27 01:11:08 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 970/1251] eta: 0:02:22 lr: 0.000080 loss: 3.0006 (2.8324) grad_norm: 2.5969 (2.7133) time: 0.4988 [2021-03-27 01:11:13 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 980/1251] eta: 0:02:17 lr: 0.000080 loss: 3.0006 (2.8352) grad_norm: 2.5535 (2.7118) time: 0.4990 [2021-03-27 01:11:19 swin_small_patch4_window7_224] INFO: Epoch: [248] [ 990/1251] eta: 0:02:12 lr: 0.000079 loss: 3.1466 (2.8364) grad_norm: 2.5535 (2.7104) time: 0.5017 [2021-03-27 01:11:24 swin_small_patch4_window7_224] INFO: Epoch: [248] [1000/1251] eta: 0:02:07 lr: 0.000079 loss: 3.0518 (2.8383) grad_norm: 2.6113 (2.7098) time: 0.5039 [2021-03-27 01:11:29 swin_small_patch4_window7_224] INFO: Epoch: [248] [1010/1251] eta: 0:02:02 lr: 0.000079 loss: 2.9873 (2.8400) grad_norm: 2.6532 (2.7126) time: 0.5086 [2021-03-27 01:11:34 swin_small_patch4_window7_224] INFO: Epoch: [248] [1020/1251] eta: 0:01:57 lr: 0.000079 loss: 2.9733 (2.8399) grad_norm: 2.7257 (2.7120) time: 0.5106 [2021-03-27 01:11:39 swin_small_patch4_window7_224] INFO: Epoch: [248] [1030/1251] eta: 0:01:52 lr: 0.000079 loss: 2.8177 (2.8391) grad_norm: 2.6267 (2.7124) time: 0.5103 [2021-03-27 01:11:44 swin_small_patch4_window7_224] INFO: Epoch: [248] [1040/1251] eta: 0:01:47 lr: 0.000079 loss: 2.8396 (2.8401) grad_norm: 2.5864 (2.7147) time: 0.5095 [2021-03-27 01:11:49 swin_small_patch4_window7_224] INFO: Epoch: [248] [1050/1251] eta: 0:01:42 lr: 0.000079 loss: 2.9876 (2.8411) grad_norm: 2.5864 (2.7143) time: 0.5051 [2021-03-27 01:11:54 swin_small_patch4_window7_224] INFO: Epoch: [248] [1060/1251] eta: 0:01:37 lr: 0.000079 loss: 2.9277 (2.8418) grad_norm: 2.6165 (nan) time: 0.4975 [2021-03-27 01:11:59 swin_small_patch4_window7_224] INFO: Epoch: [248] [1070/1251] eta: 0:01:31 lr: 0.000079 loss: 2.9277 (2.8427) grad_norm: 2.5920 (nan) time: 0.4976 [2021-03-27 01:12:04 swin_small_patch4_window7_224] INFO: Epoch: [248] [1080/1251] eta: 0:01:26 lr: 0.000079 loss: 3.0841 (2.8458) grad_norm: 2.4676 (nan) time: 0.4988 [2021-03-27 01:12:09 swin_small_patch4_window7_224] INFO: Epoch: [248] [1090/1251] eta: 0:01:21 lr: 0.000079 loss: 3.1326 (2.8483) grad_norm: 2.5032 (nan) time: 0.4980 [2021-03-27 01:12:14 swin_small_patch4_window7_224] INFO: Epoch: [248] [1100/1251] eta: 0:01:16 lr: 0.000079 loss: 3.1326 (2.8509) grad_norm: 2.5713 (nan) time: 0.4979 [2021-03-27 01:12:19 swin_small_patch4_window7_224] INFO: Epoch: [248] [1110/1251] eta: 0:01:11 lr: 0.000079 loss: 2.9843 (2.8495) grad_norm: 2.5815 (nan) time: 0.4999 [2021-03-27 01:12:24 swin_small_patch4_window7_224] INFO: Epoch: [248] [1120/1251] eta: 0:01:06 lr: 0.000079 loss: 2.9843 (2.8514) grad_norm: 2.6272 (nan) time: 0.5029 [2021-03-27 01:12:29 swin_small_patch4_window7_224] INFO: Epoch: [248] [1130/1251] eta: 0:01:01 lr: 0.000079 loss: 3.0639 (2.8519) grad_norm: 2.6960 (nan) time: 0.4975 [2021-03-27 01:12:34 swin_small_patch4_window7_224] INFO: Epoch: [248] [1140/1251] eta: 0:00:56 lr: 0.000079 loss: 2.8026 (2.8511) grad_norm: 2.6548 (nan) time: 0.4989 [2021-03-27 01:12:39 swin_small_patch4_window7_224] INFO: Epoch: [248] [1150/1251] eta: 0:00:51 lr: 0.000079 loss: 2.6951 (2.8506) grad_norm: 2.5657 (nan) time: 0.5017 [2021-03-27 01:12:44 swin_small_patch4_window7_224] INFO: Epoch: [248] [1160/1251] eta: 0:00:46 lr: 0.000079 loss: 2.8011 (2.8483) grad_norm: 2.5657 (nan) time: 0.5016 [2021-03-27 01:12:49 swin_small_patch4_window7_224] INFO: Epoch: [248] [1170/1251] eta: 0:00:41 lr: 0.000079 loss: 2.6428 (2.8466) grad_norm: 2.4917 (nan) time: 0.5013 [2021-03-27 01:12:54 swin_small_patch4_window7_224] INFO: Epoch: [248] [1180/1251] eta: 0:00:36 lr: 0.000079 loss: 2.6705 (2.8457) grad_norm: 2.4897 (nan) time: 0.5015 [2021-03-27 01:12:59 swin_small_patch4_window7_224] INFO: Epoch: [248] [1190/1251] eta: 0:00:30 lr: 0.000079 loss: 2.8727 (2.8433) grad_norm: 2.7188 (nan) time: 0.4980 [2021-03-27 01:13:04 swin_small_patch4_window7_224] INFO: Epoch: [248] [1200/1251] eta: 0:00:25 lr: 0.000079 loss: 2.7158 (2.8426) grad_norm: 2.6266 (nan) time: 0.4994 [2021-03-27 01:13:09 swin_small_patch4_window7_224] INFO: Epoch: [248] [1210/1251] eta: 0:00:20 lr: 0.000079 loss: 2.9479 (2.8432) grad_norm: 2.6166 (nan) time: 0.5039 [2021-03-27 01:13:14 swin_small_patch4_window7_224] INFO: Epoch: [248] [1220/1251] eta: 0:00:15 lr: 0.000079 loss: 2.9081 (2.8432) grad_norm: 2.6154 (nan) time: 0.5007 [2021-03-27 01:13:19 swin_small_patch4_window7_224] INFO: Epoch: [248] [1230/1251] eta: 0:00:10 lr: 0.000079 loss: 2.8791 (2.8445) grad_norm: 2.4860 (nan) time: 0.4999 [2021-03-27 01:13:24 swin_small_patch4_window7_224] INFO: Epoch: [248] [1240/1251] eta: 0:00:05 lr: 0.000079 loss: 2.8838 (2.8443) grad_norm: 2.4875 (nan) time: 0.5000 [2021-03-27 01:13:29 swin_small_patch4_window7_224] INFO: Epoch: [248] [1250/1251] eta: 0:00:00 lr: 0.000079 loss: 2.8307 (2.8437) grad_norm: 2.6356 (nan) time: 0.4946 [2021-03-27 01:13:42 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 0.8041 (0.8041) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 01:13:45 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.8119 (0.7970) acc1: 79.6875 (81.1080) acc5: 96.8750 (95.8807) [2021-03-27 01:13:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7561 (0.7800) acc1: 81.2500 (81.6220) acc5: 96.8750 (96.2054) [2021-03-27 01:13:50 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7279 (0.7645) acc1: 81.2500 (81.5020) acc5: 96.8750 (96.2702) [2021-03-27 01:13:51 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7394 (0.7810) acc1: 79.6875 (81.4787) acc5: 95.3125 (95.9985) [2021-03-27 01:13:52 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7078 (0.7651) acc1: 82.8125 (81.9200) acc5: 96.2264 (96.1280) [2021-03-27 01:14:05 swin_small_patch4_window7_224] INFO: * Acc@1 82.292 Acc@5 96.016 loss 0.762 [2021-03-27 01:14:05 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-27 01:14:05 swin_small_patch4_window7_224] INFO: Max accuracy: 82.29% [2021-03-27 01:14:09 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 0/1251] eta: 1:27:06 lr: 0.000079 loss: 2.9719 (2.9719) grad_norm: 2.5193 (2.5193) time: 4.1775 [2021-03-27 01:14:15 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 10/1251] eta: 0:17:37 lr: 0.000079 loss: 2.8386 (2.7624) grad_norm: 2.4721 (2.4132) time: 0.8523 [2021-03-27 01:14:20 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 20/1251] eta: 0:14:16 lr: 0.000079 loss: 2.6832 (2.6763) grad_norm: 2.4239 (2.4398) time: 0.5215 [2021-03-27 01:14:25 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 30/1251] eta: 0:12:59 lr: 0.000079 loss: 2.6982 (2.7341) grad_norm: 2.5099 (2.5030) time: 0.5204 [2021-03-27 01:14:30 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 40/1251] eta: 0:12:11 lr: 0.000079 loss: 2.9562 (2.7316) grad_norm: 2.6375 (2.5300) time: 0.5083 [2021-03-27 01:14:35 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 50/1251] eta: 0:11:41 lr: 0.000079 loss: 2.7106 (2.7158) grad_norm: 2.5691 (2.5341) time: 0.4994 [2021-03-27 01:14:40 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 60/1251] eta: 0:11:18 lr: 0.000079 loss: 2.7190 (2.7200) grad_norm: 2.5842 (2.5574) time: 0.4991 [2021-03-27 01:14:45 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 70/1251] eta: 0:11:01 lr: 0.000079 loss: 2.8553 (2.7186) grad_norm: 2.7527 (2.5821) time: 0.5013 [2021-03-27 01:14:50 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 80/1251] eta: 0:10:47 lr: 0.000079 loss: 2.5767 (2.7134) grad_norm: 2.7527 (2.6097) time: 0.5022 [2021-03-27 01:14:55 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 90/1251] eta: 0:10:35 lr: 0.000079 loss: 2.6911 (2.7204) grad_norm: 2.6403 (2.6108) time: 0.5017 [2021-03-27 01:15:00 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 100/1251] eta: 0:10:25 lr: 0.000079 loss: 2.7734 (2.7119) grad_norm: 2.6345 (2.6365) time: 0.5030 [2021-03-27 01:15:05 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 110/1251] eta: 0:10:16 lr: 0.000079 loss: 2.5406 (2.6903) grad_norm: 2.7439 (2.6529) time: 0.5059 [2021-03-27 01:15:10 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 120/1251] eta: 0:10:07 lr: 0.000079 loss: 2.5461 (2.6908) grad_norm: 2.7116 (2.6697) time: 0.5084 [2021-03-27 01:15:16 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 130/1251] eta: 0:10:01 lr: 0.000079 loss: 2.5983 (2.6859) grad_norm: 2.6580 (2.6921) time: 0.5162 [2021-03-27 01:15:21 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 140/1251] eta: 0:09:53 lr: 0.000079 loss: 2.7616 (2.6954) grad_norm: 2.6358 (2.6886) time: 0.5178 [2021-03-27 01:15:26 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 150/1251] eta: 0:09:46 lr: 0.000079 loss: 2.8528 (2.6883) grad_norm: 2.6358 (2.6851) time: 0.5070 [2021-03-27 01:15:31 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 160/1251] eta: 0:09:38 lr: 0.000079 loss: 2.9328 (2.6979) grad_norm: 2.4970 (2.6757) time: 0.4973 [2021-03-27 01:15:36 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 170/1251] eta: 0:09:30 lr: 0.000079 loss: 2.9328 (2.6973) grad_norm: 2.5917 (2.6867) time: 0.4924 [2021-03-27 01:15:41 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 180/1251] eta: 0:09:24 lr: 0.000079 loss: 2.7320 (2.7065) grad_norm: 2.6551 (2.7018) time: 0.5040 [2021-03-27 01:15:46 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 190/1251] eta: 0:09:17 lr: 0.000079 loss: 3.0350 (2.7238) grad_norm: 2.8344 (2.7059) time: 0.5093 [2021-03-27 01:15:51 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 200/1251] eta: 0:09:11 lr: 0.000079 loss: 3.1016 (2.7373) grad_norm: 2.8351 (2.7173) time: 0.5026 [2021-03-27 01:15:56 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 210/1251] eta: 0:09:05 lr: 0.000078 loss: 2.9282 (2.7367) grad_norm: 2.6897 (2.7189) time: 0.5078 [2021-03-27 01:16:01 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 220/1251] eta: 0:09:00 lr: 0.000078 loss: 2.9210 (2.7492) grad_norm: 2.6414 (2.7163) time: 0.5192 [2021-03-27 01:16:06 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 230/1251] eta: 0:08:54 lr: 0.000078 loss: 2.9547 (2.7528) grad_norm: 2.5535 (2.7408) time: 0.5120 [2021-03-27 01:16:11 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 240/1251] eta: 0:08:48 lr: 0.000078 loss: 2.9694 (2.7637) grad_norm: 2.6612 (2.7419) time: 0.5015 [2021-03-27 01:16:16 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 250/1251] eta: 0:08:41 lr: 0.000078 loss: 3.0258 (2.7631) grad_norm: 2.7805 (2.7449) time: 0.5005 [2021-03-27 01:16:21 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 260/1251] eta: 0:08:36 lr: 0.000078 loss: 2.6341 (2.7587) grad_norm: 2.8400 (2.7489) time: 0.5070 [2021-03-27 01:16:26 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 270/1251] eta: 0:08:30 lr: 0.000078 loss: 2.6964 (2.7578) grad_norm: 2.5910 (2.7420) time: 0.5067 [2021-03-27 01:16:31 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 280/1251] eta: 0:08:24 lr: 0.000078 loss: 2.9577 (2.7628) grad_norm: 2.6110 (2.7437) time: 0.4976 [2021-03-27 01:16:36 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 290/1251] eta: 0:08:18 lr: 0.000078 loss: 2.9440 (2.7747) grad_norm: 2.6278 (2.7387) time: 0.4974 [2021-03-27 01:16:41 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 300/1251] eta: 0:08:12 lr: 0.000078 loss: 2.7936 (2.7662) grad_norm: 2.5702 (2.7339) time: 0.4981 [2021-03-27 01:16:46 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 310/1251] eta: 0:08:06 lr: 0.000078 loss: 2.6448 (2.7662) grad_norm: 2.5708 (2.7300) time: 0.4990 [2021-03-27 01:16:51 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 320/1251] eta: 0:08:01 lr: 0.000078 loss: 2.8197 (2.7662) grad_norm: 2.6290 (2.7287) time: 0.5091 [2021-03-27 01:16:56 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 330/1251] eta: 0:07:56 lr: 0.000078 loss: 2.9289 (2.7703) grad_norm: 2.6150 (2.7241) time: 0.5098 [2021-03-27 01:17:02 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 340/1251] eta: 0:07:50 lr: 0.000078 loss: 2.8840 (2.7705) grad_norm: 2.6117 (2.7213) time: 0.5069 [2021-03-27 01:17:07 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 350/1251] eta: 0:07:45 lr: 0.000078 loss: 2.7856 (2.7725) grad_norm: 2.6284 (2.7204) time: 0.5058 [2021-03-27 01:17:12 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 360/1251] eta: 0:07:39 lr: 0.000078 loss: 2.7621 (2.7696) grad_norm: 2.6087 (2.7166) time: 0.5005 [2021-03-27 01:17:17 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 370/1251] eta: 0:07:34 lr: 0.000078 loss: 2.6630 (2.7648) grad_norm: 2.5830 (2.7155) time: 0.5015 [2021-03-27 01:17:22 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 380/1251] eta: 0:07:28 lr: 0.000078 loss: 2.6848 (2.7661) grad_norm: 2.8141 (2.7329) time: 0.5039 [2021-03-27 01:17:27 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 390/1251] eta: 0:07:23 lr: 0.000078 loss: 2.9324 (2.7659) grad_norm: 2.8141 (2.7328) time: 0.4995 [2021-03-27 01:17:32 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 400/1251] eta: 0:07:17 lr: 0.000078 loss: 2.8641 (2.7667) grad_norm: 2.7144 (2.7345) time: 0.4938 [2021-03-27 01:17:37 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 410/1251] eta: 0:07:12 lr: 0.000078 loss: 2.9045 (2.7667) grad_norm: 2.6623 (2.7325) time: 0.4982 [2021-03-27 01:17:41 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 420/1251] eta: 0:07:06 lr: 0.000078 loss: 2.8348 (2.7652) grad_norm: 2.6077 (2.7358) time: 0.4967 [2021-03-27 01:17:46 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 430/1251] eta: 0:07:01 lr: 0.000078 loss: 2.8619 (2.7698) grad_norm: 2.5638 (2.7418) time: 0.4959 [2021-03-27 01:17:51 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 440/1251] eta: 0:06:55 lr: 0.000078 loss: 2.7261 (2.7624) grad_norm: 2.5515 (2.7380) time: 0.4976 [2021-03-27 01:17:57 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 450/1251] eta: 0:06:50 lr: 0.000078 loss: 2.7330 (2.7671) grad_norm: 2.5559 (2.7358) time: 0.5015 [2021-03-27 01:18:01 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 460/1251] eta: 0:06:45 lr: 0.000078 loss: 3.0323 (2.7706) grad_norm: 2.5886 (2.7345) time: 0.4988 [2021-03-27 01:18:06 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 470/1251] eta: 0:06:39 lr: 0.000078 loss: 3.0323 (2.7754) grad_norm: 2.5231 (2.7281) time: 0.4956 [2021-03-27 01:18:11 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 480/1251] eta: 0:06:34 lr: 0.000078 loss: 2.9628 (2.7788) grad_norm: 2.5325 (2.7269) time: 0.5008 [2021-03-27 01:18:16 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 490/1251] eta: 0:06:29 lr: 0.000078 loss: 2.9114 (2.7762) grad_norm: 2.6915 (2.7285) time: 0.5002 [2021-03-27 01:18:22 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 500/1251] eta: 0:06:23 lr: 0.000078 loss: 2.7589 (2.7736) grad_norm: 2.6915 (2.7308) time: 0.5040 [2021-03-27 01:18:27 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 510/1251] eta: 0:06:18 lr: 0.000078 loss: 2.8837 (2.7754) grad_norm: 2.7113 (2.7309) time: 0.5059 [2021-03-27 01:18:32 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 520/1251] eta: 0:06:13 lr: 0.000078 loss: 2.9957 (2.7797) grad_norm: 2.7434 (2.7320) time: 0.5040 [2021-03-27 01:18:37 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 530/1251] eta: 0:06:08 lr: 0.000078 loss: 3.0389 (2.7816) grad_norm: 2.6722 (2.7317) time: 0.5028 [2021-03-27 01:18:42 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 540/1251] eta: 0:06:03 lr: 0.000078 loss: 3.0506 (2.7861) grad_norm: 2.7860 (2.7375) time: 0.5050 [2021-03-27 01:18:47 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 550/1251] eta: 0:05:57 lr: 0.000078 loss: 2.8440 (2.7866) grad_norm: 2.7860 (2.7369) time: 0.5062 [2021-03-27 01:18:52 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 560/1251] eta: 0:05:52 lr: 0.000078 loss: 2.8636 (2.7879) grad_norm: 2.6388 (2.7345) time: 0.5056 [2021-03-27 01:18:57 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 570/1251] eta: 0:05:47 lr: 0.000078 loss: 2.8021 (2.7845) grad_norm: 2.6235 (2.7315) time: 0.5115 [2021-03-27 01:19:02 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 580/1251] eta: 0:05:42 lr: 0.000078 loss: 2.7851 (2.7877) grad_norm: 2.6098 (2.7294) time: 0.5052 [2021-03-27 01:19:07 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 590/1251] eta: 0:05:37 lr: 0.000078 loss: 2.9684 (2.7904) grad_norm: 2.5292 (2.7245) time: 0.4973 [2021-03-27 01:19:12 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 600/1251] eta: 0:05:32 lr: 0.000078 loss: 2.9745 (2.7923) grad_norm: 2.5730 (2.7280) time: 0.4972 [2021-03-27 01:19:17 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 610/1251] eta: 0:05:26 lr: 0.000078 loss: 2.9017 (2.7911) grad_norm: 2.8058 (2.7314) time: 0.4966 [2021-03-27 01:19:22 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 620/1251] eta: 0:05:21 lr: 0.000078 loss: 2.7692 (2.7925) grad_norm: 2.8058 (2.7322) time: 0.4996 [2021-03-27 01:19:27 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 630/1251] eta: 0:05:16 lr: 0.000078 loss: 2.7692 (2.7923) grad_norm: 2.7099 (inf) time: 0.4993 [2021-03-27 01:19:32 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 640/1251] eta: 0:05:11 lr: 0.000078 loss: 2.6712 (2.7887) grad_norm: 2.8058 (inf) time: 0.4983 [2021-03-27 01:19:37 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 650/1251] eta: 0:05:05 lr: 0.000078 loss: 2.6547 (2.7863) grad_norm: 2.8658 (inf) time: 0.4961 [2021-03-27 01:19:42 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 660/1251] eta: 0:05:00 lr: 0.000078 loss: 2.7977 (2.7884) grad_norm: 2.8701 (inf) time: 0.4954 [2021-03-27 01:19:47 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 670/1251] eta: 0:04:55 lr: 0.000078 loss: 2.8819 (2.7896) grad_norm: 2.7572 (inf) time: 0.5026 [2021-03-27 01:19:52 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 680/1251] eta: 0:04:50 lr: 0.000078 loss: 2.9100 (2.7909) grad_norm: 2.5265 (inf) time: 0.5071 [2021-03-27 01:19:57 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 690/1251] eta: 0:04:45 lr: 0.000077 loss: 2.9094 (2.7919) grad_norm: 2.6590 (inf) time: 0.5061 [2021-03-27 01:20:02 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 700/1251] eta: 0:04:40 lr: 0.000077 loss: 2.8586 (2.7940) grad_norm: 2.8353 (inf) time: 0.5048 [2021-03-27 01:20:07 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 710/1251] eta: 0:04:35 lr: 0.000077 loss: 2.9719 (2.7963) grad_norm: 2.6766 (inf) time: 0.5011 [2021-03-27 01:20:12 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 720/1251] eta: 0:04:29 lr: 0.000077 loss: 2.9344 (2.7953) grad_norm: 2.6220 (inf) time: 0.4982 [2021-03-27 01:20:17 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 730/1251] eta: 0:04:24 lr: 0.000077 loss: 2.8416 (2.7968) grad_norm: 2.6700 (inf) time: 0.5090 [2021-03-27 01:20:22 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 740/1251] eta: 0:04:20 lr: 0.000077 loss: 2.8416 (2.7965) grad_norm: 2.6170 (inf) time: 0.5245 [2021-03-27 01:20:27 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 750/1251] eta: 0:04:14 lr: 0.000077 loss: 2.8872 (2.7965) grad_norm: 2.5469 (inf) time: 0.5140 [2021-03-27 01:20:33 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 760/1251] eta: 0:04:09 lr: 0.000077 loss: 2.8872 (2.7979) grad_norm: 2.6853 (inf) time: 0.5061 [2021-03-27 01:20:38 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 770/1251] eta: 0:04:04 lr: 0.000077 loss: 3.0476 (2.8018) grad_norm: 2.7528 (inf) time: 0.5210 [2021-03-27 01:20:43 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 780/1251] eta: 0:03:59 lr: 0.000077 loss: 3.0118 (2.8013) grad_norm: 2.6076 (inf) time: 0.5132 [2021-03-27 01:20:48 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 790/1251] eta: 0:03:54 lr: 0.000077 loss: 2.8486 (2.8033) grad_norm: 2.4789 (inf) time: 0.4988 [2021-03-27 01:20:53 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 800/1251] eta: 0:03:49 lr: 0.000077 loss: 2.9461 (2.8030) grad_norm: 2.6323 (inf) time: 0.4969 [2021-03-27 01:20:58 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 810/1251] eta: 0:03:44 lr: 0.000077 loss: 2.9493 (2.8043) grad_norm: 2.6018 (inf) time: 0.5009 [2021-03-27 01:21:03 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 820/1251] eta: 0:03:39 lr: 0.000077 loss: 2.9567 (2.8061) grad_norm: 2.7391 (inf) time: 0.5059 [2021-03-27 01:21:08 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 830/1251] eta: 0:03:34 lr: 0.000077 loss: 2.7044 (2.8043) grad_norm: 2.7693 (inf) time: 0.5027 [2021-03-27 01:21:13 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 840/1251] eta: 0:03:28 lr: 0.000077 loss: 2.7080 (2.8041) grad_norm: 2.6549 (inf) time: 0.4993 [2021-03-27 01:21:18 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 850/1251] eta: 0:03:23 lr: 0.000077 loss: 2.9214 (2.8040) grad_norm: 2.6549 (inf) time: 0.5014 [2021-03-27 01:21:23 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 860/1251] eta: 0:03:18 lr: 0.000077 loss: 2.9299 (2.8033) grad_norm: 2.6499 (inf) time: 0.5015 [2021-03-27 01:21:28 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 870/1251] eta: 0:03:13 lr: 0.000077 loss: 2.8904 (2.8047) grad_norm: 2.6499 (inf) time: 0.5026 [2021-03-27 01:21:33 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 880/1251] eta: 0:03:08 lr: 0.000077 loss: 2.9671 (2.8072) grad_norm: 2.6734 (inf) time: 0.5107 [2021-03-27 01:21:38 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 890/1251] eta: 0:03:03 lr: 0.000077 loss: 2.8952 (2.8071) grad_norm: 2.6802 (inf) time: 0.5076 [2021-03-27 01:21:43 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 900/1251] eta: 0:02:58 lr: 0.000077 loss: 2.8952 (2.8089) grad_norm: 2.6315 (inf) time: 0.4977 [2021-03-27 01:21:48 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 910/1251] eta: 0:02:53 lr: 0.000077 loss: 3.0751 (2.8091) grad_norm: 2.6808 (inf) time: 0.4952 [2021-03-27 01:21:53 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 920/1251] eta: 0:02:48 lr: 0.000077 loss: 2.8731 (2.8105) grad_norm: 2.6836 (inf) time: 0.5062 [2021-03-27 01:21:58 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 930/1251] eta: 0:02:43 lr: 0.000077 loss: 3.1019 (2.8137) grad_norm: 2.6211 (inf) time: 0.5116 [2021-03-27 01:22:03 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 940/1251] eta: 0:02:37 lr: 0.000077 loss: 3.1288 (2.8145) grad_norm: 2.6211 (inf) time: 0.5064 [2021-03-27 01:22:08 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 950/1251] eta: 0:02:32 lr: 0.000077 loss: 3.0034 (2.8155) grad_norm: 2.6356 (inf) time: 0.4987 [2021-03-27 01:22:13 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 960/1251] eta: 0:02:27 lr: 0.000077 loss: 2.9845 (2.8151) grad_norm: 2.6932 (inf) time: 0.5049 [2021-03-27 01:22:19 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 970/1251] eta: 0:02:22 lr: 0.000077 loss: 2.7638 (2.8127) grad_norm: 2.6650 (inf) time: 0.5128 [2021-03-27 01:22:23 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 980/1251] eta: 0:02:17 lr: 0.000077 loss: 2.1836 (2.8080) grad_norm: 2.6502 (inf) time: 0.5005 [2021-03-27 01:22:28 swin_small_patch4_window7_224] INFO: Epoch: [249] [ 990/1251] eta: 0:02:12 lr: 0.000077 loss: 2.6066 (2.8081) grad_norm: 2.6537 (inf) time: 0.4963 [2021-03-27 01:22:34 swin_small_patch4_window7_224] INFO: Epoch: [249] [1000/1251] eta: 0:02:07 lr: 0.000077 loss: 2.7445 (2.8063) grad_norm: 2.6334 (inf) time: 0.5009 [2021-03-27 01:22:38 swin_small_patch4_window7_224] INFO: Epoch: [249] [1010/1251] eta: 0:02:02 lr: 0.000077 loss: 2.8228 (2.8078) grad_norm: 2.6334 (inf) time: 0.4985 [2021-03-27 01:22:43 swin_small_patch4_window7_224] INFO: Epoch: [249] [1020/1251] eta: 0:01:57 lr: 0.000077 loss: 2.9635 (2.8102) grad_norm: 2.6958 (inf) time: 0.4956 [2021-03-27 01:22:48 swin_small_patch4_window7_224] INFO: Epoch: [249] [1030/1251] eta: 0:01:52 lr: 0.000077 loss: 2.8346 (2.8099) grad_norm: 2.5378 (inf) time: 0.4959 [2021-03-27 01:22:53 swin_small_patch4_window7_224] INFO: Epoch: [249] [1040/1251] eta: 0:01:47 lr: 0.000077 loss: 2.8346 (2.8094) grad_norm: 2.5712 (inf) time: 0.4961 [2021-03-27 01:22:58 swin_small_patch4_window7_224] INFO: Epoch: [249] [1050/1251] eta: 0:01:41 lr: 0.000077 loss: 2.8872 (2.8089) grad_norm: 2.6059 (inf) time: 0.4970 [2021-03-27 01:23:03 swin_small_patch4_window7_224] INFO: Epoch: [249] [1060/1251] eta: 0:01:36 lr: 0.000077 loss: 2.8512 (2.8094) grad_norm: 2.6747 (inf) time: 0.4972 [2021-03-27 01:23:08 swin_small_patch4_window7_224] INFO: Epoch: [249] [1070/1251] eta: 0:01:31 lr: 0.000077 loss: 2.8512 (2.8102) grad_norm: 2.7666 (inf) time: 0.5076 [2021-03-27 01:23:14 swin_small_patch4_window7_224] INFO: Epoch: [249] [1080/1251] eta: 0:01:26 lr: 0.000077 loss: 2.9731 (2.8117) grad_norm: 2.8005 (inf) time: 0.5124 [2021-03-27 01:23:19 swin_small_patch4_window7_224] INFO: Epoch: [249] [1090/1251] eta: 0:01:21 lr: 0.000077 loss: 2.9022 (2.8101) grad_norm: 2.7588 (inf) time: 0.5039 [2021-03-27 01:23:24 swin_small_patch4_window7_224] INFO: Epoch: [249] [1100/1251] eta: 0:01:16 lr: 0.000077 loss: 2.8134 (2.8105) grad_norm: 2.6500 (inf) time: 0.4985 [2021-03-27 01:23:29 swin_small_patch4_window7_224] INFO: Epoch: [249] [1110/1251] eta: 0:01:11 lr: 0.000077 loss: 2.9185 (2.8111) grad_norm: 2.7511 (inf) time: 0.4986 [2021-03-27 01:23:33 swin_small_patch4_window7_224] INFO: Epoch: [249] [1120/1251] eta: 0:01:06 lr: 0.000077 loss: 2.9780 (2.8121) grad_norm: 2.7580 (inf) time: 0.4963 [2021-03-27 01:23:38 swin_small_patch4_window7_224] INFO: Epoch: [249] [1130/1251] eta: 0:01:01 lr: 0.000077 loss: 2.8661 (2.8114) grad_norm: 2.7580 (inf) time: 0.4976 [2021-03-27 01:23:43 swin_small_patch4_window7_224] INFO: Epoch: [249] [1140/1251] eta: 0:00:56 lr: 0.000077 loss: 3.0234 (2.8131) grad_norm: 2.7443 (inf) time: 0.5021 [2021-03-27 01:23:49 swin_small_patch4_window7_224] INFO: Epoch: [249] [1150/1251] eta: 0:00:51 lr: 0.000077 loss: 2.8872 (2.8113) grad_norm: 2.5547 (inf) time: 0.5022 [2021-03-27 01:23:54 swin_small_patch4_window7_224] INFO: Epoch: [249] [1160/1251] eta: 0:00:46 lr: 0.000077 loss: 2.7259 (2.8107) grad_norm: 2.5352 (inf) time: 0.5035 [2021-03-27 01:23:59 swin_small_patch4_window7_224] INFO: Epoch: [249] [1170/1251] eta: 0:00:41 lr: 0.000076 loss: 2.8744 (2.8121) grad_norm: 2.5153 (inf) time: 0.4991 [2021-03-27 01:24:04 swin_small_patch4_window7_224] INFO: Epoch: [249] [1180/1251] eta: 0:00:35 lr: 0.000076 loss: 2.7345 (2.8100) grad_norm: 2.5153 (inf) time: 0.4973 [2021-03-27 01:24:09 swin_small_patch4_window7_224] INFO: Epoch: [249] [1190/1251] eta: 0:00:30 lr: 0.000076 loss: 2.7345 (2.8110) grad_norm: 2.8008 (inf) time: 0.5043 [2021-03-27 01:24:14 swin_small_patch4_window7_224] INFO: Epoch: [249] [1200/1251] eta: 0:00:25 lr: 0.000076 loss: 2.9466 (2.8100) grad_norm: 2.7140 (inf) time: 0.5046 [2021-03-27 01:24:19 swin_small_patch4_window7_224] INFO: Epoch: [249] [1210/1251] eta: 0:00:20 lr: 0.000076 loss: 2.9466 (2.8111) grad_norm: 2.7140 (inf) time: 0.5013 [2021-03-27 01:24:24 swin_small_patch4_window7_224] INFO: Epoch: [249] [1220/1251] eta: 0:00:15 lr: 0.000076 loss: 3.0689 (2.8128) grad_norm: 2.8692 (inf) time: 0.4999 [2021-03-27 01:24:29 swin_small_patch4_window7_224] INFO: Epoch: [249] [1230/1251] eta: 0:00:10 lr: 0.000076 loss: 2.8474 (2.8123) grad_norm: 2.6704 (inf) time: 0.4942 [2021-03-27 01:24:33 swin_small_patch4_window7_224] INFO: Epoch: [249] [1240/1251] eta: 0:00:05 lr: 0.000076 loss: 2.7005 (2.8100) grad_norm: 2.5349 (inf) time: 0.4890 [2021-03-27 01:24:38 swin_small_patch4_window7_224] INFO: Epoch: [249] [1250/1251] eta: 0:00:00 lr: 0.000076 loss: 2.6378 (2.8103) grad_norm: 2.6290 (inf) time: 0.4909 [2021-03-27 01:24:49 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:08 loss: 0.6447 (0.6447) acc1: 89.0625 (89.0625) acc5: 93.7500 (93.7500) [2021-03-27 01:24:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8116 (0.7710) acc1: 81.2500 (82.9545) acc5: 95.3125 (95.0284) [2021-03-27 01:24:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.8278 (0.7900) acc1: 81.2500 (81.6964) acc5: 95.3125 (95.4613) [2021-03-27 01:24:57 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7642 (0.7770) acc1: 81.2500 (81.8044) acc5: 96.8750 (95.8165) [2021-03-27 01:24:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7151 (0.7645) acc1: 82.8125 (82.2409) acc5: 96.8750 (95.9604) [2021-03-27 01:24:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7457 (0.7655) acc1: 82.8125 (82.2080) acc5: 96.8750 (95.8720) [2021-03-27 01:25:10 swin_small_patch4_window7_224] INFO: * Acc@1 82.320 Acc@5 95.986 loss 0.754 [2021-03-27 01:25:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-27 01:25:10 swin_small_patch4_window7_224] INFO: Max accuracy: 82.32% [2021-03-27 01:25:15 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 0/1251] eta: 1:25:27 lr: 0.000076 loss: 1.5865 (1.5865) grad_norm: 2.3945 (2.3945) time: 4.0990 [2021-03-27 01:25:20 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 10/1251] eta: 0:17:26 lr: 0.000076 loss: 2.6735 (2.6342) grad_norm: 2.7676 (2.7778) time: 0.8433 [2021-03-27 01:25:25 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 20/1251] eta: 0:13:52 lr: 0.000076 loss: 2.8158 (2.6890) grad_norm: 2.7656 (2.7984) time: 0.5054 [2021-03-27 01:25:30 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 30/1251] eta: 0:12:39 lr: 0.000076 loss: 2.9562 (2.7918) grad_norm: 2.6885 (2.8233) time: 0.4998 [2021-03-27 01:25:35 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 40/1251] eta: 0:12:01 lr: 0.000076 loss: 2.9687 (2.7760) grad_norm: 2.7049 (2.8052) time: 0.5107 [2021-03-27 01:25:40 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 50/1251] eta: 0:11:33 lr: 0.000076 loss: 2.9536 (2.7898) grad_norm: 2.7801 (2.8018) time: 0.5098 [2021-03-27 01:25:45 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 60/1251] eta: 0:11:13 lr: 0.000076 loss: 2.9356 (2.7547) grad_norm: 2.7060 (2.7950) time: 0.5046 [2021-03-27 01:25:50 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 70/1251] eta: 0:10:58 lr: 0.000076 loss: 2.8287 (2.7687) grad_norm: 2.6069 (2.7850) time: 0.5064 [2021-03-27 01:25:55 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 80/1251] eta: 0:10:43 lr: 0.000076 loss: 2.9546 (2.8008) grad_norm: 2.7307 (2.7735) time: 0.5000 [2021-03-27 01:26:00 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 90/1251] eta: 0:10:32 lr: 0.000076 loss: 3.0813 (2.8104) grad_norm: 2.6950 (2.7711) time: 0.5000 [2021-03-27 01:26:05 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 100/1251] eta: 0:10:24 lr: 0.000076 loss: 2.7814 (2.7971) grad_norm: 2.6603 (2.7794) time: 0.5151 [2021-03-27 01:26:10 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 110/1251] eta: 0:10:14 lr: 0.000076 loss: 2.9516 (2.8231) grad_norm: 2.6149 (2.7657) time: 0.5092 [2021-03-27 01:26:15 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 120/1251] eta: 0:10:06 lr: 0.000076 loss: 2.9182 (2.8227) grad_norm: 2.6956 (2.7690) time: 0.5044 [2021-03-27 01:26:20 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 130/1251] eta: 0:09:57 lr: 0.000076 loss: 2.8137 (2.8110) grad_norm: 2.6376 (2.7447) time: 0.5011 [2021-03-27 01:26:25 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 140/1251] eta: 0:09:50 lr: 0.000076 loss: 2.8120 (2.8076) grad_norm: 2.4594 (2.7328) time: 0.5025 [2021-03-27 01:26:31 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 150/1251] eta: 0:09:44 lr: 0.000076 loss: 2.8286 (2.8168) grad_norm: 2.6047 (2.7337) time: 0.5149 [2021-03-27 01:26:36 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 160/1251] eta: 0:09:37 lr: 0.000076 loss: 2.9974 (2.8167) grad_norm: 2.6704 (2.7368) time: 0.5116 [2021-03-27 01:26:41 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 170/1251] eta: 0:09:30 lr: 0.000076 loss: 2.9720 (2.8190) grad_norm: 2.7116 (2.7431) time: 0.5045 [2021-03-27 01:26:46 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 180/1251] eta: 0:09:23 lr: 0.000076 loss: 2.9829 (2.8317) grad_norm: 2.6641 (2.7414) time: 0.5058 [2021-03-27 01:26:51 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 190/1251] eta: 0:09:17 lr: 0.000076 loss: 2.9546 (2.8334) grad_norm: 2.6383 (2.7391) time: 0.5088 [2021-03-27 01:26:56 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 200/1251] eta: 0:09:11 lr: 0.000076 loss: 2.8129 (2.8347) grad_norm: 2.6431 (2.7477) time: 0.5129 [2021-03-27 01:27:01 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 210/1251] eta: 0:09:05 lr: 0.000076 loss: 2.9650 (2.8411) grad_norm: 2.6431 (2.7407) time: 0.5097 [2021-03-27 01:27:06 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 220/1251] eta: 0:08:59 lr: 0.000076 loss: 2.9297 (2.8426) grad_norm: 2.6453 (2.7388) time: 0.5012 [2021-03-27 01:27:11 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 230/1251] eta: 0:08:52 lr: 0.000076 loss: 2.9019 (2.8368) grad_norm: 2.6633 (2.7386) time: 0.4992 [2021-03-27 01:27:16 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 240/1251] eta: 0:08:46 lr: 0.000076 loss: 2.7788 (2.8336) grad_norm: 2.6192 (2.7335) time: 0.4957 [2021-03-27 01:27:21 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 250/1251] eta: 0:08:40 lr: 0.000076 loss: 2.6505 (2.8265) grad_norm: 2.5440 (2.7328) time: 0.5043 [2021-03-27 01:27:26 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 260/1251] eta: 0:08:35 lr: 0.000076 loss: 2.6643 (2.8257) grad_norm: 2.4347 (2.7299) time: 0.5112 [2021-03-27 01:27:31 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 270/1251] eta: 0:08:29 lr: 0.000076 loss: 2.9470 (2.8306) grad_norm: 2.6551 (2.7434) time: 0.5081 [2021-03-27 01:27:36 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 280/1251] eta: 0:08:24 lr: 0.000076 loss: 2.9470 (2.8254) grad_norm: 2.6345 (2.7377) time: 0.5103 [2021-03-27 01:27:41 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 290/1251] eta: 0:08:18 lr: 0.000076 loss: 2.9008 (2.8251) grad_norm: 2.6345 (2.7406) time: 0.5075 [2021-03-27 01:27:47 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 300/1251] eta: 0:08:12 lr: 0.000076 loss: 2.7479 (2.8210) grad_norm: 2.6930 (2.7409) time: 0.5028 [2021-03-27 01:27:52 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 310/1251] eta: 0:08:07 lr: 0.000076 loss: 2.8183 (2.8205) grad_norm: 2.5961 (2.7421) time: 0.5065 [2021-03-27 01:27:57 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 320/1251] eta: 0:08:01 lr: 0.000076 loss: 2.8183 (2.8131) grad_norm: 2.7614 (2.7435) time: 0.5039 [2021-03-27 01:28:02 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 330/1251] eta: 0:07:55 lr: 0.000076 loss: 2.8491 (2.8143) grad_norm: 2.7459 (2.7434) time: 0.4994 [2021-03-27 01:28:07 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 340/1251] eta: 0:07:51 lr: 0.000076 loss: 2.9228 (2.8161) grad_norm: 2.6380 (2.7405) time: 0.5149 [2021-03-27 01:28:12 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 350/1251] eta: 0:07:45 lr: 0.000076 loss: 2.7899 (2.8151) grad_norm: 2.6380 (2.7442) time: 0.5173 [2021-03-27 01:28:17 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 360/1251] eta: 0:07:40 lr: 0.000076 loss: 2.9371 (2.8198) grad_norm: 2.5406 (2.7429) time: 0.5014 [2021-03-27 01:28:22 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 370/1251] eta: 0:07:34 lr: 0.000076 loss: 2.8025 (2.8146) grad_norm: 2.6511 (2.7451) time: 0.5016 [2021-03-27 01:28:27 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 380/1251] eta: 0:07:29 lr: 0.000076 loss: 2.7967 (2.8180) grad_norm: 2.6318 (2.7551) time: 0.5041 [2021-03-27 01:28:32 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 390/1251] eta: 0:07:23 lr: 0.000076 loss: 2.9725 (2.8188) grad_norm: 2.6222 (2.7519) time: 0.5083 [2021-03-27 01:28:37 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 400/1251] eta: 0:07:18 lr: 0.000075 loss: 2.9725 (2.8197) grad_norm: 2.5439 (2.7462) time: 0.5074 [2021-03-27 01:28:42 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 410/1251] eta: 0:07:12 lr: 0.000075 loss: 2.9912 (2.8221) grad_norm: 2.5255 (2.7558) time: 0.5001 [2021-03-27 01:28:47 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 420/1251] eta: 0:07:07 lr: 0.000075 loss: 2.9477 (2.8217) grad_norm: 2.7325 (2.7570) time: 0.4983 [2021-03-27 01:28:52 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 430/1251] eta: 0:07:02 lr: 0.000075 loss: 2.9382 (2.8260) grad_norm: 2.6867 (2.7553) time: 0.5026 [2021-03-27 01:28:57 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 440/1251] eta: 0:06:56 lr: 0.000075 loss: 2.7355 (2.8226) grad_norm: 2.6311 (2.7526) time: 0.5062 [2021-03-27 01:29:02 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 450/1251] eta: 0:06:51 lr: 0.000075 loss: 2.8498 (2.8273) grad_norm: 2.6930 (2.7563) time: 0.5050 [2021-03-27 01:29:07 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 460/1251] eta: 0:06:46 lr: 0.000075 loss: 2.9542 (2.8296) grad_norm: 2.7571 (2.7543) time: 0.4999 [2021-03-27 01:29:12 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 470/1251] eta: 0:06:40 lr: 0.000075 loss: 2.8494 (2.8288) grad_norm: 2.6926 (2.7523) time: 0.4933 [2021-03-27 01:29:17 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 480/1251] eta: 0:06:35 lr: 0.000075 loss: 2.8518 (2.8280) grad_norm: 2.7280 (2.7529) time: 0.4969 [2021-03-27 01:29:22 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 490/1251] eta: 0:06:30 lr: 0.000075 loss: 2.7845 (2.8247) grad_norm: 2.8155 (2.7572) time: 0.5019 [2021-03-27 01:29:27 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 500/1251] eta: 0:06:24 lr: 0.000075 loss: 2.7845 (2.8282) grad_norm: 2.7912 (2.7552) time: 0.4988 [2021-03-27 01:29:32 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 510/1251] eta: 0:06:19 lr: 0.000075 loss: 2.8919 (2.8250) grad_norm: 2.5557 (2.7506) time: 0.5019 [2021-03-27 01:29:37 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 520/1251] eta: 0:06:14 lr: 0.000075 loss: 2.7073 (2.8230) grad_norm: 2.5615 (2.7521) time: 0.5146 [2021-03-27 01:29:43 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 530/1251] eta: 0:06:09 lr: 0.000075 loss: 2.7353 (2.8220) grad_norm: 2.6094 (2.7509) time: 0.5146 [2021-03-27 01:29:48 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 540/1251] eta: 0:06:04 lr: 0.000075 loss: 2.9463 (2.8268) grad_norm: 2.6198 (2.7508) time: 0.5029 [2021-03-27 01:29:53 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 550/1251] eta: 0:05:58 lr: 0.000075 loss: 3.0694 (2.8256) grad_norm: 2.6439 (2.7493) time: 0.5019 [2021-03-27 01:29:58 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 560/1251] eta: 0:05:53 lr: 0.000075 loss: 3.0039 (2.8299) grad_norm: 2.7273 (2.7496) time: 0.5018 [2021-03-27 01:30:03 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 570/1251] eta: 0:05:48 lr: 0.000075 loss: 2.9489 (2.8280) grad_norm: 2.6546 (2.7496) time: 0.5034 [2021-03-27 01:30:08 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 580/1251] eta: 0:05:43 lr: 0.000075 loss: 2.8575 (2.8290) grad_norm: 2.6878 (2.7492) time: 0.5042 [2021-03-27 01:30:13 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 590/1251] eta: 0:05:37 lr: 0.000075 loss: 2.9545 (2.8296) grad_norm: 2.7117 (2.7472) time: 0.5047 [2021-03-27 01:30:18 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 600/1251] eta: 0:05:32 lr: 0.000075 loss: 2.9014 (2.8288) grad_norm: 2.7048 (2.7493) time: 0.5032 [2021-03-27 01:30:23 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 610/1251] eta: 0:05:27 lr: 0.000075 loss: 2.9359 (2.8322) grad_norm: 2.8122 (2.7549) time: 0.5019 [2021-03-27 01:30:28 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 620/1251] eta: 0:05:22 lr: 0.000075 loss: 2.9943 (2.8316) grad_norm: 2.5530 (2.7537) time: 0.5086 [2021-03-27 01:30:33 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 630/1251] eta: 0:05:17 lr: 0.000075 loss: 3.0360 (2.8349) grad_norm: 2.6454 (2.7559) time: 0.5089 [2021-03-27 01:30:38 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 640/1251] eta: 0:05:12 lr: 0.000075 loss: 3.0360 (2.8360) grad_norm: 2.6674 (2.7537) time: 0.5103 [2021-03-27 01:30:43 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 650/1251] eta: 0:05:07 lr: 0.000075 loss: 2.8552 (2.8350) grad_norm: 2.5562 (2.7519) time: 0.5119 [2021-03-27 01:30:48 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 660/1251] eta: 0:05:01 lr: 0.000075 loss: 2.8349 (2.8367) grad_norm: 2.5559 (2.7496) time: 0.5051 [2021-03-27 01:30:53 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 670/1251] eta: 0:04:56 lr: 0.000075 loss: 2.8743 (2.8389) grad_norm: 2.5536 (2.7509) time: 0.4987 [2021-03-27 01:30:58 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 680/1251] eta: 0:04:51 lr: 0.000075 loss: 2.9034 (2.8381) grad_norm: 2.5588 (2.7493) time: 0.4971 [2021-03-27 01:31:03 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 690/1251] eta: 0:04:46 lr: 0.000075 loss: 2.9654 (2.8382) grad_norm: 2.6064 (2.7511) time: 0.5026 [2021-03-27 01:31:08 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 700/1251] eta: 0:04:41 lr: 0.000075 loss: 2.9012 (2.8354) grad_norm: 2.5982 (2.7494) time: 0.5065 [2021-03-27 01:31:13 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 710/1251] eta: 0:04:36 lr: 0.000075 loss: 2.5106 (2.8318) grad_norm: 2.7334 (2.7506) time: 0.5076 [2021-03-27 01:31:19 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 720/1251] eta: 0:04:30 lr: 0.000075 loss: 2.7624 (2.8326) grad_norm: 2.7628 (2.7505) time: 0.5099 [2021-03-27 01:31:24 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 730/1251] eta: 0:04:25 lr: 0.000075 loss: 2.9295 (2.8349) grad_norm: 2.6685 (2.7509) time: 0.5047 [2021-03-27 01:31:29 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 740/1251] eta: 0:04:20 lr: 0.000075 loss: 2.7263 (2.8323) grad_norm: 2.6673 (2.7510) time: 0.5013 [2021-03-27 01:31:34 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 750/1251] eta: 0:04:15 lr: 0.000075 loss: 2.7211 (2.8325) grad_norm: 2.5754 (2.7494) time: 0.5044 [2021-03-27 01:31:39 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 760/1251] eta: 0:04:10 lr: 0.000075 loss: 3.0827 (2.8349) grad_norm: 2.6208 (2.7497) time: 0.4997 [2021-03-27 01:31:44 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 770/1251] eta: 0:04:05 lr: 0.000075 loss: 3.1036 (2.8372) grad_norm: 2.6442 (2.7485) time: 0.4961 [2021-03-27 01:31:49 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 780/1251] eta: 0:03:59 lr: 0.000075 loss: 2.9883 (2.8386) grad_norm: 2.5397 (2.7497) time: 0.4994 [2021-03-27 01:31:54 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 790/1251] eta: 0:03:54 lr: 0.000075 loss: 2.8785 (2.8363) grad_norm: 2.7549 (2.7519) time: 0.5051 [2021-03-27 01:31:59 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 800/1251] eta: 0:03:49 lr: 0.000075 loss: 2.8990 (2.8398) grad_norm: 2.8095 (2.7521) time: 0.5113 [2021-03-27 01:32:04 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 810/1251] eta: 0:03:44 lr: 0.000075 loss: 3.1184 (2.8399) grad_norm: 2.6407 (2.7516) time: 0.5100 [2021-03-27 01:32:09 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 820/1251] eta: 0:03:39 lr: 0.000075 loss: 2.8832 (2.8400) grad_norm: 2.6407 (2.7535) time: 0.5074 [2021-03-27 01:32:14 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 830/1251] eta: 0:03:34 lr: 0.000075 loss: 2.6891 (2.8374) grad_norm: 2.7275 (2.7537) time: 0.5104 [2021-03-27 01:32:19 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 840/1251] eta: 0:03:29 lr: 0.000075 loss: 2.7512 (2.8385) grad_norm: 2.6943 (2.7537) time: 0.5138 [2021-03-27 01:32:24 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 850/1251] eta: 0:03:24 lr: 0.000075 loss: 2.9782 (2.8389) grad_norm: 2.6915 (2.7536) time: 0.5051 [2021-03-27 01:32:29 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 860/1251] eta: 0:03:19 lr: 0.000075 loss: 2.8753 (2.8387) grad_norm: 2.6915 (2.7536) time: 0.5012 [2021-03-27 01:32:34 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 870/1251] eta: 0:03:14 lr: 0.000075 loss: 2.9243 (2.8390) grad_norm: 2.6917 (2.7543) time: 0.5054 [2021-03-27 01:32:39 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 880/1251] eta: 0:03:08 lr: 0.000075 loss: 2.9535 (2.8381) grad_norm: 2.7480 (2.7540) time: 0.5070 [2021-03-27 01:32:45 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 890/1251] eta: 0:03:03 lr: 0.000074 loss: 2.9323 (2.8392) grad_norm: 2.7296 (2.7556) time: 0.5115 [2021-03-27 01:32:50 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 900/1251] eta: 0:02:58 lr: 0.000074 loss: 2.9323 (2.8384) grad_norm: 2.7548 (2.7564) time: 0.5122 [2021-03-27 01:32:55 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 910/1251] eta: 0:02:53 lr: 0.000074 loss: 2.9830 (2.8397) grad_norm: 2.6730 (2.7556) time: 0.5029 [2021-03-27 01:33:00 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 920/1251] eta: 0:02:48 lr: 0.000074 loss: 2.9830 (2.8389) grad_norm: 2.6416 (2.7560) time: 0.4979 [2021-03-27 01:33:05 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 930/1251] eta: 0:02:43 lr: 0.000074 loss: 2.8511 (2.8386) grad_norm: 2.7521 (2.7563) time: 0.5003 [2021-03-27 01:33:10 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 940/1251] eta: 0:02:38 lr: 0.000074 loss: 2.8571 (2.8403) grad_norm: 2.8264 (2.7584) time: 0.5060 [2021-03-27 01:33:15 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 950/1251] eta: 0:02:33 lr: 0.000074 loss: 2.9745 (2.8396) grad_norm: 2.5916 (2.7571) time: 0.5014 [2021-03-27 01:33:20 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 960/1251] eta: 0:02:28 lr: 0.000074 loss: 2.7115 (2.8377) grad_norm: 2.5039 (2.7571) time: 0.4978 [2021-03-27 01:33:25 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 970/1251] eta: 0:02:22 lr: 0.000074 loss: 2.8306 (2.8387) grad_norm: 2.6771 (2.7585) time: 0.5031 [2021-03-27 01:33:30 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 980/1251] eta: 0:02:17 lr: 0.000074 loss: 2.8621 (2.8372) grad_norm: 2.6771 (2.7598) time: 0.5038 [2021-03-27 01:33:35 swin_small_patch4_window7_224] INFO: Epoch: [250] [ 990/1251] eta: 0:02:12 lr: 0.000074 loss: 2.5644 (2.8354) grad_norm: 2.7003 (2.7608) time: 0.5024 [2021-03-27 01:33:40 swin_small_patch4_window7_224] INFO: Epoch: [250] [1000/1251] eta: 0:02:07 lr: 0.000074 loss: 2.8001 (2.8360) grad_norm: 2.8150 (2.7619) time: 0.5073 [2021-03-27 01:33:45 swin_small_patch4_window7_224] INFO: Epoch: [250] [1010/1251] eta: 0:02:02 lr: 0.000074 loss: 2.7998 (2.8341) grad_norm: 2.6958 (2.7608) time: 0.5104 [2021-03-27 01:33:50 swin_small_patch4_window7_224] INFO: Epoch: [250] [1020/1251] eta: 0:01:57 lr: 0.000074 loss: 2.5739 (2.8318) grad_norm: 2.6572 (2.7605) time: 0.5073 [2021-03-27 01:33:55 swin_small_patch4_window7_224] INFO: Epoch: [250] [1030/1251] eta: 0:01:52 lr: 0.000074 loss: 2.6262 (2.8315) grad_norm: 2.6572 (2.7606) time: 0.5038 [2021-03-27 01:34:00 swin_small_patch4_window7_224] INFO: Epoch: [250] [1040/1251] eta: 0:01:47 lr: 0.000074 loss: 2.9017 (2.8306) grad_norm: 2.6304 (2.7601) time: 0.5013 [2021-03-27 01:34:05 swin_small_patch4_window7_224] INFO: Epoch: [250] [1050/1251] eta: 0:01:42 lr: 0.000074 loss: 2.9017 (2.8308) grad_norm: 2.6374 (2.7594) time: 0.5023 [2021-03-27 01:34:10 swin_small_patch4_window7_224] INFO: Epoch: [250] [1060/1251] eta: 0:01:37 lr: 0.000074 loss: 2.9097 (2.8314) grad_norm: 2.7703 (2.7601) time: 0.5047 [2021-03-27 01:34:15 swin_small_patch4_window7_224] INFO: Epoch: [250] [1070/1251] eta: 0:01:32 lr: 0.000074 loss: 2.8500 (2.8301) grad_norm: 2.6270 (2.7585) time: 0.5049 [2021-03-27 01:34:20 swin_small_patch4_window7_224] INFO: Epoch: [250] [1080/1251] eta: 0:01:26 lr: 0.000074 loss: 2.6109 (2.8275) grad_norm: 2.6050 (2.7566) time: 0.5080 [2021-03-27 01:34:26 swin_small_patch4_window7_224] INFO: Epoch: [250] [1090/1251] eta: 0:01:21 lr: 0.000074 loss: 2.7621 (2.8276) grad_norm: 2.6457 (2.7574) time: 0.5226 [2021-03-27 01:34:31 swin_small_patch4_window7_224] INFO: Epoch: [250] [1100/1251] eta: 0:01:16 lr: 0.000074 loss: 2.8882 (2.8295) grad_norm: 2.7506 (2.7631) time: 0.5144 [2021-03-27 01:34:36 swin_small_patch4_window7_224] INFO: Epoch: [250] [1110/1251] eta: 0:01:11 lr: 0.000074 loss: 3.0480 (2.8308) grad_norm: 2.7182 (2.7633) time: 0.5018 [2021-03-27 01:34:41 swin_small_patch4_window7_224] INFO: Epoch: [250] [1120/1251] eta: 0:01:06 lr: 0.000074 loss: 2.9765 (2.8310) grad_norm: 2.8289 (2.7687) time: 0.5063 [2021-03-27 01:34:46 swin_small_patch4_window7_224] INFO: Epoch: [250] [1130/1251] eta: 0:01:01 lr: 0.000074 loss: 2.9765 (2.8321) grad_norm: 2.7805 (2.7708) time: 0.5068 [2021-03-27 01:34:51 swin_small_patch4_window7_224] INFO: Epoch: [250] [1140/1251] eta: 0:00:56 lr: 0.000074 loss: 2.9690 (2.8317) grad_norm: 2.7655 (2.7740) time: 0.5048 [2021-03-27 01:34:56 swin_small_patch4_window7_224] INFO: Epoch: [250] [1150/1251] eta: 0:00:51 lr: 0.000074 loss: 2.8205 (2.8317) grad_norm: 2.7655 (2.7747) time: 0.5027 [2021-03-27 01:35:01 swin_small_patch4_window7_224] INFO: Epoch: [250] [1160/1251] eta: 0:00:46 lr: 0.000074 loss: 2.8515 (2.8315) grad_norm: 2.6685 (2.7739) time: 0.5003 [2021-03-27 01:35:06 swin_small_patch4_window7_224] INFO: Epoch: [250] [1170/1251] eta: 0:00:41 lr: 0.000074 loss: 2.8619 (2.8324) grad_norm: 2.5566 (2.7740) time: 0.4995 [2021-03-27 01:35:11 swin_small_patch4_window7_224] INFO: Epoch: [250] [1180/1251] eta: 0:00:36 lr: 0.000074 loss: 2.8648 (2.8320) grad_norm: 2.5566 (2.7731) time: 0.5011 [2021-03-27 01:35:16 swin_small_patch4_window7_224] INFO: Epoch: [250] [1190/1251] eta: 0:00:30 lr: 0.000074 loss: 2.8648 (2.8323) grad_norm: 2.6933 (2.7739) time: 0.5036 [2021-03-27 01:35:21 swin_small_patch4_window7_224] INFO: Epoch: [250] [1200/1251] eta: 0:00:25 lr: 0.000074 loss: 2.6564 (2.8291) grad_norm: 2.6613 (2.7729) time: 0.5031 [2021-03-27 01:35:26 swin_small_patch4_window7_224] INFO: Epoch: [250] [1210/1251] eta: 0:00:20 lr: 0.000074 loss: 2.6132 (2.8286) grad_norm: 2.6335 (2.7715) time: 0.4982 [2021-03-27 01:35:31 swin_small_patch4_window7_224] INFO: Epoch: [250] [1220/1251] eta: 0:00:15 lr: 0.000074 loss: 2.7797 (2.8271) grad_norm: 2.6390 (2.7725) time: 0.4971 [2021-03-27 01:35:36 swin_small_patch4_window7_224] INFO: Epoch: [250] [1230/1251] eta: 0:00:10 lr: 0.000074 loss: 2.7797 (2.8274) grad_norm: 2.5756 (2.7712) time: 0.5013 [2021-03-27 01:35:41 swin_small_patch4_window7_224] INFO: Epoch: [250] [1240/1251] eta: 0:00:05 lr: 0.000074 loss: 2.9930 (2.8287) grad_norm: 2.5114 (2.7691) time: 0.4989 [2021-03-27 01:35:46 swin_small_patch4_window7_224] INFO: Epoch: [250] [1250/1251] eta: 0:00:00 lr: 0.000074 loss: 2.8451 (2.8280) grad_norm: 2.5137 (2.7680) time: 0.4939 [2021-03-27 01:36:42 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:08 loss: 0.8003 (0.8003) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-27 01:36:43 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.8273 (0.8628) acc1: 78.1250 (77.9830) acc5: 95.3125 (95.8807) [2021-03-27 01:36:44 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7605 (0.7843) acc1: 81.2500 (80.8780) acc5: 95.3125 (96.2054) [2021-03-27 01:36:45 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7041 (0.7611) acc1: 84.3750 (82.3589) acc5: 96.8750 (96.0685) [2021-03-27 01:36:46 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7647 (0.7798) acc1: 82.8125 (81.6692) acc5: 95.3125 (95.8079) [2021-03-27 01:36:47 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7647 (0.7640) acc1: 82.8125 (81.8560) acc5: 95.3125 (96.0320) [2021-03-27 01:37:03 swin_small_patch4_window7_224] INFO: * Acc@1 82.446 Acc@5 95.962 loss 0.754 [2021-03-27 01:37:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.4% [2021-03-27 01:37:03 swin_small_patch4_window7_224] INFO: Max accuracy: 82.45% [2021-03-27 01:37:07 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 0/1251] eta: 1:29:17 lr: 0.000074 loss: 3.3523 (3.3523) grad_norm: 2.6384 (2.6384) time: 4.2826 [2021-03-27 01:37:12 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 10/1251] eta: 0:17:48 lr: 0.000074 loss: 2.9359 (2.7679) grad_norm: 2.5548 (2.6547) time: 0.8609 [2021-03-27 01:37:17 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 20/1251] eta: 0:14:10 lr: 0.000074 loss: 2.8842 (2.8113) grad_norm: 2.5548 (2.7224) time: 0.5113 [2021-03-27 01:37:22 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 30/1251] eta: 0:12:53 lr: 0.000074 loss: 2.8842 (2.7997) grad_norm: 2.7087 (2.9229) time: 0.5078 [2021-03-27 01:37:27 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 40/1251] eta: 0:12:05 lr: 0.000074 loss: 2.9332 (2.7831) grad_norm: 2.8276 (2.9123) time: 0.5026 [2021-03-27 01:37:32 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 50/1251] eta: 0:11:36 lr: 0.000074 loss: 2.8953 (2.7877) grad_norm: 2.7425 (2.8880) time: 0.4965 [2021-03-27 01:37:37 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 60/1251] eta: 0:11:15 lr: 0.000074 loss: 2.7184 (2.7496) grad_norm: 2.7670 (2.8773) time: 0.5014 [2021-03-27 01:37:42 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 70/1251] eta: 0:11:01 lr: 0.000074 loss: 2.8979 (2.7792) grad_norm: 2.5476 (2.8307) time: 0.5095 [2021-03-27 01:37:48 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 80/1251] eta: 0:10:48 lr: 0.000074 loss: 2.9543 (2.7806) grad_norm: 2.6286 (3.0146) time: 0.5130 [2021-03-27 01:37:53 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 90/1251] eta: 0:10:35 lr: 0.000074 loss: 2.6644 (2.7660) grad_norm: 2.9157 (2.9995) time: 0.5032 [2021-03-27 01:37:58 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 100/1251] eta: 0:10:25 lr: 0.000074 loss: 2.7125 (2.7631) grad_norm: 2.7200 (2.9777) time: 0.5025 [2021-03-27 01:38:03 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 110/1251] eta: 0:10:17 lr: 0.000074 loss: 2.7660 (2.7652) grad_norm: 2.7082 (2.9507) time: 0.5128 [2021-03-27 01:38:08 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 120/1251] eta: 0:10:09 lr: 0.000074 loss: 2.8527 (2.7663) grad_norm: 2.6053 (2.9310) time: 0.5147 [2021-03-27 01:38:13 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 130/1251] eta: 0:10:00 lr: 0.000073 loss: 2.9821 (2.7850) grad_norm: 2.8458 (2.9311) time: 0.5048 [2021-03-27 01:38:18 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 140/1251] eta: 0:09:52 lr: 0.000073 loss: 2.9508 (2.7734) grad_norm: 2.8066 (2.9172) time: 0.5024 [2021-03-27 01:38:23 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 150/1251] eta: 0:09:45 lr: 0.000073 loss: 2.9312 (2.7770) grad_norm: 2.6089 (2.9086) time: 0.5041 [2021-03-27 01:38:28 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 160/1251] eta: 0:09:37 lr: 0.000073 loss: 2.9226 (2.7758) grad_norm: 2.8396 (2.9510) time: 0.5000 [2021-03-27 01:38:33 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 170/1251] eta: 0:09:30 lr: 0.000073 loss: 2.9080 (2.7912) grad_norm: 2.8396 (2.9475) time: 0.5022 [2021-03-27 01:38:38 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 180/1251] eta: 0:09:24 lr: 0.000073 loss: 2.9080 (2.7954) grad_norm: 2.6716 (2.9365) time: 0.5118 [2021-03-27 01:38:43 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 190/1251] eta: 0:09:18 lr: 0.000073 loss: 2.9807 (2.8017) grad_norm: 2.6225 (2.9192) time: 0.5117 [2021-03-27 01:38:48 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 200/1251] eta: 0:09:11 lr: 0.000073 loss: 2.9051 (2.8024) grad_norm: 2.6370 (2.9155) time: 0.5022 [2021-03-27 01:38:53 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 210/1251] eta: 0:09:05 lr: 0.000073 loss: 2.8825 (2.7941) grad_norm: 2.7101 (2.9039) time: 0.5033 [2021-03-27 01:38:58 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 220/1251] eta: 0:08:59 lr: 0.000073 loss: 2.4722 (2.7878) grad_norm: 2.6311 (2.8941) time: 0.5106 [2021-03-27 01:39:03 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 230/1251] eta: 0:08:53 lr: 0.000073 loss: 2.7967 (2.7957) grad_norm: 2.6311 (2.8921) time: 0.5060 [2021-03-27 01:39:09 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 240/1251] eta: 0:08:48 lr: 0.000073 loss: 2.7967 (2.7826) grad_norm: 2.5315 (2.8782) time: 0.5073 [2021-03-27 01:39:14 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 250/1251] eta: 0:08:41 lr: 0.000073 loss: 2.5328 (2.7767) grad_norm: 2.5573 (2.8683) time: 0.5089 [2021-03-27 01:39:19 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 260/1251] eta: 0:08:36 lr: 0.000073 loss: 2.9192 (2.7851) grad_norm: 2.6393 (2.8646) time: 0.5067 [2021-03-27 01:39:24 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 270/1251] eta: 0:08:30 lr: 0.000073 loss: 2.9303 (2.7930) grad_norm: 2.6600 (2.8637) time: 0.5063 [2021-03-27 01:39:29 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 280/1251] eta: 0:08:25 lr: 0.000073 loss: 2.9303 (2.7949) grad_norm: 2.8535 (2.8746) time: 0.5090 [2021-03-27 01:39:34 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 290/1251] eta: 0:08:19 lr: 0.000073 loss: 2.7900 (2.7948) grad_norm: 2.7494 (2.8727) time: 0.5061 [2021-03-27 01:39:39 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 300/1251] eta: 0:08:13 lr: 0.000073 loss: 2.8649 (2.7968) grad_norm: 2.6749 (2.8832) time: 0.4967 [2021-03-27 01:39:44 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 310/1251] eta: 0:08:07 lr: 0.000073 loss: 2.8470 (2.7923) grad_norm: 2.6749 (2.8776) time: 0.5022 [2021-03-27 01:39:49 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 320/1251] eta: 0:08:02 lr: 0.000073 loss: 2.9475 (2.7951) grad_norm: 2.6635 (2.8695) time: 0.5059 [2021-03-27 01:39:54 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 330/1251] eta: 0:07:56 lr: 0.000073 loss: 3.0043 (2.7969) grad_norm: 2.6516 (2.8630) time: 0.5042 [2021-03-27 01:39:59 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 340/1251] eta: 0:07:50 lr: 0.000073 loss: 2.8094 (2.7868) grad_norm: 2.6370 (2.8566) time: 0.5026 [2021-03-27 01:40:04 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 350/1251] eta: 0:07:45 lr: 0.000073 loss: 2.7673 (2.7894) grad_norm: 2.6471 (2.8557) time: 0.5074 [2021-03-27 01:40:09 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 360/1251] eta: 0:07:40 lr: 0.000073 loss: 3.0423 (2.7956) grad_norm: 2.6780 (2.8513) time: 0.5074 [2021-03-27 01:40:14 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 370/1251] eta: 0:07:34 lr: 0.000073 loss: 3.0423 (2.7961) grad_norm: 2.6640 (2.8454) time: 0.5088 [2021-03-27 01:40:19 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 380/1251] eta: 0:07:29 lr: 0.000073 loss: 2.7768 (2.7939) grad_norm: 2.6551 (2.8408) time: 0.5050 [2021-03-27 01:40:24 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 390/1251] eta: 0:07:24 lr: 0.000073 loss: 2.6872 (2.7903) grad_norm: 2.6497 (2.8378) time: 0.5022 [2021-03-27 01:40:29 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 400/1251] eta: 0:07:18 lr: 0.000073 loss: 2.8739 (2.7918) grad_norm: 2.6413 (2.8334) time: 0.5083 [2021-03-27 01:40:35 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 410/1251] eta: 0:07:13 lr: 0.000073 loss: 2.8779 (2.7947) grad_norm: 2.6413 (2.8310) time: 0.5054 [2021-03-27 01:40:40 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 420/1251] eta: 0:07:07 lr: 0.000073 loss: 2.9867 (2.8013) grad_norm: 2.6339 (2.8297) time: 0.5005 [2021-03-27 01:40:45 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 430/1251] eta: 0:07:02 lr: 0.000073 loss: 2.9812 (2.8014) grad_norm: 2.6339 (2.8275) time: 0.5053 [2021-03-27 01:40:50 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 440/1251] eta: 0:06:57 lr: 0.000073 loss: 2.8565 (2.8007) grad_norm: 2.6615 (2.8292) time: 0.5061 [2021-03-27 01:40:55 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 450/1251] eta: 0:06:51 lr: 0.000073 loss: 2.9315 (2.8039) grad_norm: 2.9744 (2.8373) time: 0.5035 [2021-03-27 01:41:00 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 460/1251] eta: 0:06:46 lr: 0.000073 loss: 2.9894 (2.8049) grad_norm: 2.8923 (2.8391) time: 0.5137 [2021-03-27 01:41:05 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 470/1251] eta: 0:06:41 lr: 0.000073 loss: 2.9688 (2.8058) grad_norm: 2.8360 (2.8420) time: 0.5174 [2021-03-27 01:41:10 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 480/1251] eta: 0:06:36 lr: 0.000073 loss: 2.8064 (2.8042) grad_norm: 2.6253 (2.8372) time: 0.5046 [2021-03-27 01:41:15 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 490/1251] eta: 0:06:30 lr: 0.000073 loss: 2.7665 (2.8038) grad_norm: 2.5740 (2.8315) time: 0.5001 [2021-03-27 01:41:20 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 500/1251] eta: 0:06:25 lr: 0.000073 loss: 2.7665 (2.8006) grad_norm: 2.5102 (2.8343) time: 0.5033 [2021-03-27 01:41:25 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 510/1251] eta: 0:06:20 lr: 0.000073 loss: 2.7377 (2.8028) grad_norm: 2.6078 (2.8312) time: 0.5060 [2021-03-27 01:41:30 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 520/1251] eta: 0:06:15 lr: 0.000073 loss: 3.0262 (2.8058) grad_norm: 2.6078 (2.8315) time: 0.5051 [2021-03-27 01:41:35 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 530/1251] eta: 0:06:09 lr: 0.000073 loss: 2.7642 (2.8044) grad_norm: 2.6932 (2.8294) time: 0.5000 [2021-03-27 01:41:40 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 540/1251] eta: 0:06:04 lr: 0.000073 loss: 2.8904 (2.8043) grad_norm: 2.6046 (2.8248) time: 0.5025 [2021-03-27 01:41:45 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 550/1251] eta: 0:05:59 lr: 0.000073 loss: 3.0488 (2.8060) grad_norm: 2.5964 (2.8235) time: 0.5096 [2021-03-27 01:41:50 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 560/1251] eta: 0:05:54 lr: 0.000073 loss: 2.9356 (2.8036) grad_norm: 2.7083 (2.8362) time: 0.5076 [2021-03-27 01:41:55 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 570/1251] eta: 0:05:48 lr: 0.000073 loss: 2.7182 (2.7998) grad_norm: 2.6315 (2.8344) time: 0.5022 [2021-03-27 01:42:01 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 580/1251] eta: 0:05:43 lr: 0.000073 loss: 2.6990 (2.7997) grad_norm: 2.6284 (2.8343) time: 0.5073 [2021-03-27 01:42:05 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 590/1251] eta: 0:05:38 lr: 0.000073 loss: 2.9204 (2.8004) grad_norm: 2.6455 (2.8314) time: 0.5021 [2021-03-27 01:42:10 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 600/1251] eta: 0:05:33 lr: 0.000073 loss: 2.8797 (2.8018) grad_norm: 2.6831 (2.8294) time: 0.4964 [2021-03-27 01:42:16 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 610/1251] eta: 0:05:28 lr: 0.000073 loss: 2.8797 (2.8036) grad_norm: 2.7416 (2.8301) time: 0.5007 [2021-03-27 01:42:21 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 620/1251] eta: 0:05:22 lr: 0.000072 loss: 2.8403 (2.8012) grad_norm: 2.7014 (2.8292) time: 0.5060 [2021-03-27 01:42:26 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 630/1251] eta: 0:05:17 lr: 0.000072 loss: 2.6744 (2.8004) grad_norm: 2.7014 (2.8323) time: 0.5049 [2021-03-27 01:42:31 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 640/1251] eta: 0:05:12 lr: 0.000072 loss: 2.6744 (2.7980) grad_norm: 2.7721 (2.8310) time: 0.5016 [2021-03-27 01:42:36 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 650/1251] eta: 0:05:07 lr: 0.000072 loss: 2.8141 (2.8013) grad_norm: 2.8494 (2.8350) time: 0.5021 [2021-03-27 01:42:41 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 660/1251] eta: 0:05:02 lr: 0.000072 loss: 2.9390 (2.8009) grad_norm: 2.8113 (2.8325) time: 0.5050 [2021-03-27 01:42:46 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 670/1251] eta: 0:04:56 lr: 0.000072 loss: 2.8467 (2.8005) grad_norm: 2.7545 (2.8311) time: 0.5073 [2021-03-27 01:42:51 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 680/1251] eta: 0:04:51 lr: 0.000072 loss: 2.8500 (2.7999) grad_norm: 2.6507 (2.8283) time: 0.5043 [2021-03-27 01:42:56 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 690/1251] eta: 0:04:46 lr: 0.000072 loss: 2.9344 (2.7990) grad_norm: 2.7656 (2.8316) time: 0.4983 [2021-03-27 01:43:01 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 700/1251] eta: 0:04:41 lr: 0.000072 loss: 2.8778 (2.7986) grad_norm: 2.9365 (2.8330) time: 0.5008 [2021-03-27 01:43:06 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 710/1251] eta: 0:04:36 lr: 0.000072 loss: 2.8232 (2.7994) grad_norm: 2.7007 (2.8299) time: 0.5131 [2021-03-27 01:43:11 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 720/1251] eta: 0:04:31 lr: 0.000072 loss: 2.8067 (2.7991) grad_norm: 2.6030 (2.8302) time: 0.5096 [2021-03-27 01:43:16 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 730/1251] eta: 0:04:26 lr: 0.000072 loss: 2.7804 (2.7978) grad_norm: 2.7219 (2.8305) time: 0.5054 [2021-03-27 01:43:21 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 740/1251] eta: 0:04:21 lr: 0.000072 loss: 2.9726 (2.8012) grad_norm: 2.6932 (2.8281) time: 0.5147 [2021-03-27 01:43:26 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 750/1251] eta: 0:04:15 lr: 0.000072 loss: 2.8195 (2.7979) grad_norm: 2.6078 (2.8298) time: 0.5098 [2021-03-27 01:43:31 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 760/1251] eta: 0:04:10 lr: 0.000072 loss: 2.8498 (2.8010) grad_norm: 2.6760 (2.8286) time: 0.5018 [2021-03-27 01:43:36 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 770/1251] eta: 0:04:05 lr: 0.000072 loss: 2.9445 (2.8023) grad_norm: 2.6875 (2.8265) time: 0.5034 [2021-03-27 01:43:41 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 780/1251] eta: 0:04:00 lr: 0.000072 loss: 2.8919 (2.8009) grad_norm: 2.6811 (2.8253) time: 0.5006 [2021-03-27 01:43:46 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 790/1251] eta: 0:03:55 lr: 0.000072 loss: 2.6776 (2.8003) grad_norm: 2.7066 (2.8230) time: 0.4993 [2021-03-27 01:43:51 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 800/1251] eta: 0:03:50 lr: 0.000072 loss: 2.9298 (2.8022) grad_norm: 2.7284 (2.8234) time: 0.5012 [2021-03-27 01:43:56 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 810/1251] eta: 0:03:44 lr: 0.000072 loss: 2.9298 (2.8034) grad_norm: 2.8990 (2.8268) time: 0.5041 [2021-03-27 01:44:02 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 820/1251] eta: 0:03:39 lr: 0.000072 loss: 2.9030 (2.8045) grad_norm: 2.8274 (2.8260) time: 0.5067 [2021-03-27 01:44:07 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 830/1251] eta: 0:03:34 lr: 0.000072 loss: 2.9844 (2.8077) grad_norm: 2.8080 (2.8266) time: 0.5038 [2021-03-27 01:44:12 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 840/1251] eta: 0:03:29 lr: 0.000072 loss: 2.8701 (2.8039) grad_norm: 2.8179 (2.8274) time: 0.4987 [2021-03-27 01:44:17 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 850/1251] eta: 0:03:24 lr: 0.000072 loss: 2.9898 (2.8067) grad_norm: 2.7747 (2.8301) time: 0.5051 [2021-03-27 01:44:22 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 860/1251] eta: 0:03:19 lr: 0.000072 loss: 3.0366 (2.8051) grad_norm: 2.7177 (2.8292) time: 0.5101 [2021-03-27 01:44:27 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 870/1251] eta: 0:03:14 lr: 0.000072 loss: 2.8415 (2.8061) grad_norm: 2.8420 (2.8297) time: 0.5143 [2021-03-27 01:44:32 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 880/1251] eta: 0:03:09 lr: 0.000072 loss: 2.7940 (2.8030) grad_norm: 2.7562 (2.8288) time: 0.5125 [2021-03-27 01:44:37 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 890/1251] eta: 0:03:03 lr: 0.000072 loss: 2.6999 (2.8037) grad_norm: 2.6544 (2.8286) time: 0.4962 [2021-03-27 01:44:42 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 900/1251] eta: 0:02:58 lr: 0.000072 loss: 3.0431 (2.8047) grad_norm: 2.6712 (2.8275) time: 0.4931 [2021-03-27 01:44:47 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 910/1251] eta: 0:02:53 lr: 0.000072 loss: 2.9197 (2.8026) grad_norm: 2.6485 (2.8260) time: 0.5006 [2021-03-27 01:44:52 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 920/1251] eta: 0:02:48 lr: 0.000072 loss: 2.8619 (2.8037) grad_norm: 2.5949 (2.8275) time: 0.5069 [2021-03-27 01:44:57 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 930/1251] eta: 0:02:43 lr: 0.000072 loss: 2.9838 (2.8046) grad_norm: 2.6950 (2.8305) time: 0.5068 [2021-03-27 01:45:02 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 940/1251] eta: 0:02:38 lr: 0.000072 loss: 2.9271 (2.8051) grad_norm: 2.6652 (2.8279) time: 0.5055 [2021-03-27 01:45:07 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 950/1251] eta: 0:02:33 lr: 0.000072 loss: 2.8476 (2.8035) grad_norm: 2.5660 (2.8256) time: 0.5043 [2021-03-27 01:45:12 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 960/1251] eta: 0:02:28 lr: 0.000072 loss: 2.7086 (2.8030) grad_norm: 2.7545 (2.8274) time: 0.5023 [2021-03-27 01:45:17 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 970/1251] eta: 0:02:23 lr: 0.000072 loss: 2.7358 (2.8024) grad_norm: 2.8318 (2.8277) time: 0.5027 [2021-03-27 01:45:22 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 980/1251] eta: 0:02:17 lr: 0.000072 loss: 2.8383 (2.8024) grad_norm: 2.7729 (2.8286) time: 0.5038 [2021-03-27 01:45:27 swin_small_patch4_window7_224] INFO: Epoch: [251] [ 990/1251] eta: 0:02:12 lr: 0.000072 loss: 2.9415 (2.8047) grad_norm: 2.6722 (2.8276) time: 0.5001 [2021-03-27 01:45:32 swin_small_patch4_window7_224] INFO: Epoch: [251] [1000/1251] eta: 0:02:07 lr: 0.000072 loss: 2.8890 (2.8030) grad_norm: 2.7505 (2.8301) time: 0.4964 [2021-03-27 01:45:37 swin_small_patch4_window7_224] INFO: Epoch: [251] [1010/1251] eta: 0:02:02 lr: 0.000072 loss: 2.7488 (2.8042) grad_norm: 2.7737 (2.8298) time: 0.5003 [2021-03-27 01:45:42 swin_small_patch4_window7_224] INFO: Epoch: [251] [1020/1251] eta: 0:01:57 lr: 0.000072 loss: 2.9203 (2.8031) grad_norm: 2.7250 (2.8297) time: 0.5043 [2021-03-27 01:45:47 swin_small_patch4_window7_224] INFO: Epoch: [251] [1030/1251] eta: 0:01:52 lr: 0.000072 loss: 2.8195 (2.8028) grad_norm: 2.6850 (2.8290) time: 0.5054 [2021-03-27 01:45:52 swin_small_patch4_window7_224] INFO: Epoch: [251] [1040/1251] eta: 0:01:47 lr: 0.000072 loss: 2.8583 (2.8039) grad_norm: 2.6850 (2.8305) time: 0.5054 [2021-03-27 01:45:57 swin_small_patch4_window7_224] INFO: Epoch: [251] [1050/1251] eta: 0:01:42 lr: 0.000072 loss: 2.8287 (2.8035) grad_norm: 2.6619 (2.8298) time: 0.5058 [2021-03-27 01:46:03 swin_small_patch4_window7_224] INFO: Epoch: [251] [1060/1251] eta: 0:01:37 lr: 0.000072 loss: 3.0381 (2.8060) grad_norm: 2.6184 (2.8280) time: 0.5067 [2021-03-27 01:46:07 swin_small_patch4_window7_224] INFO: Epoch: [251] [1070/1251] eta: 0:01:32 lr: 0.000072 loss: 2.9722 (2.8054) grad_norm: 2.5753 (2.8262) time: 0.5001 [2021-03-27 01:46:12 swin_small_patch4_window7_224] INFO: Epoch: [251] [1080/1251] eta: 0:01:26 lr: 0.000072 loss: 2.7796 (2.8043) grad_norm: 2.5334 (2.8245) time: 0.4962 [2021-03-27 01:46:18 swin_small_patch4_window7_224] INFO: Epoch: [251] [1090/1251] eta: 0:01:21 lr: 0.000072 loss: 2.9352 (2.8055) grad_norm: 2.7096 (2.8274) time: 0.5044 [2021-03-27 01:46:22 swin_small_patch4_window7_224] INFO: Epoch: [251] [1100/1251] eta: 0:01:16 lr: 0.000072 loss: 3.0657 (2.8070) grad_norm: 2.8904 (2.8314) time: 0.5022 [2021-03-27 01:46:28 swin_small_patch4_window7_224] INFO: Epoch: [251] [1110/1251] eta: 0:01:11 lr: 0.000072 loss: 3.0203 (2.8079) grad_norm: 2.8034 (2.8302) time: 0.5021 [2021-03-27 01:46:33 swin_small_patch4_window7_224] INFO: Epoch: [251] [1120/1251] eta: 0:01:06 lr: 0.000071 loss: 3.0243 (2.8089) grad_norm: 2.7588 (2.8308) time: 0.5086 [2021-03-27 01:46:38 swin_small_patch4_window7_224] INFO: Epoch: [251] [1130/1251] eta: 0:01:01 lr: 0.000071 loss: 3.0319 (2.8087) grad_norm: 2.6998 (2.8338) time: 0.5061 [2021-03-27 01:46:43 swin_small_patch4_window7_224] INFO: Epoch: [251] [1140/1251] eta: 0:00:56 lr: 0.000071 loss: 2.8302 (2.8084) grad_norm: 2.7544 (2.8338) time: 0.5034 [2021-03-27 01:46:48 swin_small_patch4_window7_224] INFO: Epoch: [251] [1150/1251] eta: 0:00:51 lr: 0.000071 loss: 2.8715 (2.8092) grad_norm: 2.6708 (2.8324) time: 0.5027 [2021-03-27 01:46:53 swin_small_patch4_window7_224] INFO: Epoch: [251] [1160/1251] eta: 0:00:46 lr: 0.000071 loss: 2.8966 (2.8082) grad_norm: 2.5598 (2.8298) time: 0.4995 [2021-03-27 01:46:58 swin_small_patch4_window7_224] INFO: Epoch: [251] [1170/1251] eta: 0:00:41 lr: 0.000071 loss: 2.6611 (2.8069) grad_norm: 2.5160 (2.8282) time: 0.5031 [2021-03-27 01:47:03 swin_small_patch4_window7_224] INFO: Epoch: [251] [1180/1251] eta: 0:00:36 lr: 0.000071 loss: 2.5864 (2.8044) grad_norm: 2.5160 (2.8266) time: 0.5066 [2021-03-27 01:47:08 swin_small_patch4_window7_224] INFO: Epoch: [251] [1190/1251] eta: 0:00:30 lr: 0.000071 loss: 2.7224 (2.8045) grad_norm: 2.6169 (2.8270) time: 0.5033 [2021-03-27 01:47:13 swin_small_patch4_window7_224] INFO: Epoch: [251] [1200/1251] eta: 0:00:25 lr: 0.000071 loss: 2.8796 (2.8059) grad_norm: 2.7193 (2.8268) time: 0.5075 [2021-03-27 01:47:18 swin_small_patch4_window7_224] INFO: Epoch: [251] [1210/1251] eta: 0:00:20 lr: 0.000071 loss: 2.7278 (2.8035) grad_norm: 2.7193 (2.8278) time: 0.5040 [2021-03-27 01:47:23 swin_small_patch4_window7_224] INFO: Epoch: [251] [1220/1251] eta: 0:00:15 lr: 0.000071 loss: 2.7282 (2.8048) grad_norm: 2.7439 (2.8281) time: 0.5044 [2021-03-27 01:47:28 swin_small_patch4_window7_224] INFO: Epoch: [251] [1230/1251] eta: 0:00:10 lr: 0.000071 loss: 2.9970 (2.8046) grad_norm: 2.7439 (2.8282) time: 0.5066 [2021-03-27 01:47:33 swin_small_patch4_window7_224] INFO: Epoch: [251] [1240/1251] eta: 0:00:05 lr: 0.000071 loss: 2.5456 (2.8020) grad_norm: 2.5567 (2.8281) time: 0.4987 [2021-03-27 01:47:38 swin_small_patch4_window7_224] INFO: Epoch: [251] [1250/1251] eta: 0:00:00 lr: 0.000071 loss: 2.5456 (2.8022) grad_norm: 2.5567 (2.8268) time: 0.4924 [2021-03-27 01:47:48 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:50 loss: 0.8327 (0.8327) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-27 01:47:50 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7607 (0.7336) acc1: 81.2500 (82.1023) acc5: 96.8750 (96.5909) [2021-03-27 01:47:53 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7256 (0.7492) acc1: 82.8125 (81.9196) acc5: 96.8750 (96.4286) [2021-03-27 01:47:55 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7553 (0.7690) acc1: 82.8125 (81.6532) acc5: 96.8750 (96.1694) [2021-03-27 01:47:57 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7381 (0.7542) acc1: 82.8125 (81.9360) acc5: 96.8750 (96.1890) [2021-03-27 01:47:58 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7381 (0.7590) acc1: 81.2500 (81.9200) acc5: 96.8750 (96.0640) [2021-03-27 01:48:12 swin_small_patch4_window7_224] INFO: * Acc@1 82.350 Acc@5 96.074 loss 0.756 [2021-03-27 01:48:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.4% [2021-03-27 01:48:12 swin_small_patch4_window7_224] INFO: Max accuracy: 82.45% [2021-03-27 01:48:16 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 0/1251] eta: 1:30:06 lr: 0.000071 loss: 3.3170 (3.3170) grad_norm: 2.8058 (2.8058) time: 4.3216 [2021-03-27 01:48:21 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 10/1251] eta: 0:17:48 lr: 0.000071 loss: 3.0120 (2.7642) grad_norm: 2.6586 (2.7008) time: 0.8610 [2021-03-27 01:48:26 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 20/1251] eta: 0:14:15 lr: 0.000071 loss: 2.7115 (2.7398) grad_norm: 2.6586 (2.7241) time: 0.5140 [2021-03-27 01:48:32 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 30/1251] eta: 0:12:56 lr: 0.000071 loss: 2.4650 (2.7260) grad_norm: 2.7848 (2.8454) time: 0.5123 [2021-03-27 01:48:37 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 40/1251] eta: 0:12:11 lr: 0.000071 loss: 2.8915 (2.7698) grad_norm: 2.8071 (2.8412) time: 0.5078 [2021-03-27 01:48:42 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 50/1251] eta: 0:11:38 lr: 0.000071 loss: 2.7624 (2.7142) grad_norm: 2.7059 (2.8375) time: 0.4974 [2021-03-27 01:48:47 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 60/1251] eta: 0:11:18 lr: 0.000071 loss: 2.6180 (2.7208) grad_norm: 2.6741 (2.8147) time: 0.5009 [2021-03-27 01:48:52 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 70/1251] eta: 0:11:00 lr: 0.000071 loss: 2.5843 (2.6899) grad_norm: 2.5933 (2.7836) time: 0.5017 [2021-03-27 01:48:57 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 80/1251] eta: 0:10:46 lr: 0.000071 loss: 2.9664 (2.7436) grad_norm: 2.7215 (2.7840) time: 0.4956 [2021-03-27 01:49:02 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 90/1251] eta: 0:10:35 lr: 0.000071 loss: 3.0908 (2.7602) grad_norm: 2.7215 (2.7823) time: 0.5048 [2021-03-27 01:49:07 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 100/1251] eta: 0:10:24 lr: 0.000071 loss: 2.9128 (2.7752) grad_norm: 2.7241 (2.7766) time: 0.5073 [2021-03-27 01:49:12 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 110/1251] eta: 0:10:16 lr: 0.000071 loss: 2.9128 (2.7845) grad_norm: 2.8530 (2.8244) time: 0.5110 [2021-03-27 01:49:17 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 120/1251] eta: 0:10:07 lr: 0.000071 loss: 2.7921 (2.7891) grad_norm: 3.0301 (2.8375) time: 0.5086 [2021-03-27 01:49:22 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 130/1251] eta: 0:09:59 lr: 0.000071 loss: 2.7565 (2.7850) grad_norm: 2.7421 (2.8267) time: 0.5017 [2021-03-27 01:49:27 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 140/1251] eta: 0:09:52 lr: 0.000071 loss: 2.6175 (2.7833) grad_norm: 2.5754 (2.8203) time: 0.5108 [2021-03-27 01:49:32 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 150/1251] eta: 0:09:44 lr: 0.000071 loss: 2.7864 (2.7744) grad_norm: 2.4966 (2.8225) time: 0.5078 [2021-03-27 01:49:37 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 160/1251] eta: 0:09:37 lr: 0.000071 loss: 2.7864 (2.7713) grad_norm: 2.6094 (2.8155) time: 0.5009 [2021-03-27 01:49:42 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 170/1251] eta: 0:09:30 lr: 0.000071 loss: 2.8862 (2.7721) grad_norm: 2.6466 (2.8052) time: 0.4985 [2021-03-27 01:49:47 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 180/1251] eta: 0:09:23 lr: 0.000071 loss: 3.0258 (2.7907) grad_norm: 2.5173 (2.8167) time: 0.4959 [2021-03-27 01:49:52 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 190/1251] eta: 0:09:16 lr: 0.000071 loss: 3.1350 (2.7976) grad_norm: 2.7306 (2.8238) time: 0.5040 [2021-03-27 01:49:57 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 200/1251] eta: 0:09:10 lr: 0.000071 loss: 3.0350 (2.8074) grad_norm: 2.7404 (2.8259) time: 0.5101 [2021-03-27 01:50:02 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 210/1251] eta: 0:09:04 lr: 0.000071 loss: 2.9655 (2.8114) grad_norm: 2.6420 (2.8254) time: 0.5043 [2021-03-27 01:50:07 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 220/1251] eta: 0:08:58 lr: 0.000071 loss: 2.8368 (2.8107) grad_norm: 2.8545 (2.8312) time: 0.4996 [2021-03-27 01:50:12 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 230/1251] eta: 0:08:52 lr: 0.000071 loss: 2.8368 (2.8070) grad_norm: 2.8420 (2.8298) time: 0.5057 [2021-03-27 01:50:17 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 240/1251] eta: 0:08:46 lr: 0.000071 loss: 2.8024 (2.8009) grad_norm: 2.7774 (2.8285) time: 0.5102 [2021-03-27 01:50:22 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 250/1251] eta: 0:08:40 lr: 0.000071 loss: 2.8024 (2.7962) grad_norm: 2.7112 (2.8260) time: 0.5050 [2021-03-27 01:50:27 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 260/1251] eta: 0:08:34 lr: 0.000071 loss: 2.9632 (2.8007) grad_norm: 2.6320 (2.8182) time: 0.4984 [2021-03-27 01:50:32 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 270/1251] eta: 0:08:28 lr: 0.000071 loss: 3.0266 (2.8043) grad_norm: 2.6081 (2.8181) time: 0.4983 [2021-03-27 01:50:38 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 280/1251] eta: 0:08:23 lr: 0.000071 loss: 2.9351 (2.8094) grad_norm: 2.6199 (2.8163) time: 0.5049 [2021-03-27 01:50:43 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 290/1251] eta: 0:08:17 lr: 0.000071 loss: 2.8686 (2.8073) grad_norm: 2.6091 (2.8100) time: 0.5049 [2021-03-27 01:50:47 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 300/1251] eta: 0:08:11 lr: 0.000071 loss: 2.8378 (2.8098) grad_norm: 2.6366 (2.8141) time: 0.4962 [2021-03-27 01:50:53 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 310/1251] eta: 0:08:06 lr: 0.000071 loss: 3.0351 (2.8170) grad_norm: 2.8843 (2.8244) time: 0.5012 [2021-03-27 01:50:57 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 320/1251] eta: 0:08:00 lr: 0.000071 loss: 3.0035 (2.8192) grad_norm: 2.8142 (2.8214) time: 0.5026 [2021-03-27 01:51:02 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 330/1251] eta: 0:07:54 lr: 0.000071 loss: 2.8692 (2.8159) grad_norm: 2.6463 (2.8162) time: 0.4976 [2021-03-27 01:51:08 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 340/1251] eta: 0:07:49 lr: 0.000071 loss: 2.7939 (2.8173) grad_norm: 2.6542 (2.8165) time: 0.5018 [2021-03-27 01:51:13 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 350/1251] eta: 0:07:44 lr: 0.000071 loss: 2.7939 (2.8179) grad_norm: 2.7288 (2.8165) time: 0.5113 [2021-03-27 01:51:18 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 360/1251] eta: 0:07:38 lr: 0.000071 loss: 2.9201 (2.8172) grad_norm: 2.8711 (2.8285) time: 0.5128 [2021-03-27 01:51:23 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 370/1251] eta: 0:07:33 lr: 0.000070 loss: 2.7909 (2.8083) grad_norm: 2.8835 (2.8340) time: 0.5079 [2021-03-27 01:51:28 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 380/1251] eta: 0:07:28 lr: 0.000070 loss: 2.7408 (2.8060) grad_norm: 2.7735 (2.8356) time: 0.5056 [2021-03-27 01:51:33 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 390/1251] eta: 0:07:22 lr: 0.000070 loss: 2.9303 (2.8092) grad_norm: 2.7393 (2.8323) time: 0.5081 [2021-03-27 01:51:38 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 400/1251] eta: 0:07:17 lr: 0.000070 loss: 3.0515 (2.8128) grad_norm: 2.6905 (2.8334) time: 0.5076 [2021-03-27 01:51:43 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 410/1251] eta: 0:07:12 lr: 0.000070 loss: 2.6820 (2.8031) grad_norm: 2.7820 (2.8356) time: 0.5006 [2021-03-27 01:51:48 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 420/1251] eta: 0:07:06 lr: 0.000070 loss: 2.7251 (2.8048) grad_norm: 2.8098 (2.8380) time: 0.4971 [2021-03-27 01:51:53 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 430/1251] eta: 0:07:01 lr: 0.000070 loss: 2.9791 (2.8054) grad_norm: 2.7285 (2.8374) time: 0.4963 [2021-03-27 01:51:58 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 440/1251] eta: 0:06:55 lr: 0.000070 loss: 2.8202 (2.8050) grad_norm: 2.7191 (2.8373) time: 0.5037 [2021-03-27 01:52:03 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 450/1251] eta: 0:06:50 lr: 0.000070 loss: 2.8202 (2.8079) grad_norm: 2.6612 (2.8342) time: 0.5069 [2021-03-27 01:52:08 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 460/1251] eta: 0:06:45 lr: 0.000070 loss: 2.8301 (2.8076) grad_norm: 2.6297 (2.8318) time: 0.5007 [2021-03-27 01:52:13 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 470/1251] eta: 0:06:39 lr: 0.000070 loss: 2.7680 (2.8081) grad_norm: 2.6944 (2.8321) time: 0.4995 [2021-03-27 01:52:18 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 480/1251] eta: 0:06:34 lr: 0.000070 loss: 2.7680 (2.8064) grad_norm: 2.6821 (2.8275) time: 0.5015 [2021-03-27 01:52:23 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 490/1251] eta: 0:06:29 lr: 0.000070 loss: 2.7033 (2.8044) grad_norm: 2.6890 (2.8302) time: 0.5004 [2021-03-27 01:52:28 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 500/1251] eta: 0:06:24 lr: 0.000070 loss: 2.7040 (2.8059) grad_norm: 2.7823 (2.8288) time: 0.4988 [2021-03-27 01:52:33 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 510/1251] eta: 0:06:18 lr: 0.000070 loss: 2.9555 (2.8106) grad_norm: 2.7726 (2.8286) time: 0.4967 [2021-03-27 01:52:38 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 520/1251] eta: 0:06:13 lr: 0.000070 loss: 2.9501 (2.8122) grad_norm: 2.7072 (2.8279) time: 0.4960 [2021-03-27 01:52:43 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 530/1251] eta: 0:06:08 lr: 0.000070 loss: 2.8117 (2.8092) grad_norm: 2.7463 (2.8270) time: 0.4986 [2021-03-27 01:52:48 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 540/1251] eta: 0:06:02 lr: 0.000070 loss: 2.5475 (2.8021) grad_norm: 2.6170 (2.8257) time: 0.5005 [2021-03-27 01:52:53 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 550/1251] eta: 0:05:57 lr: 0.000070 loss: 2.8641 (2.8052) grad_norm: 2.6170 (2.8267) time: 0.5107 [2021-03-27 01:52:58 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 560/1251] eta: 0:05:52 lr: 0.000070 loss: 2.7623 (2.8028) grad_norm: 2.8047 (2.8270) time: 0.5142 [2021-03-27 01:53:03 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 570/1251] eta: 0:05:47 lr: 0.000070 loss: 2.6985 (2.8020) grad_norm: 2.7356 (2.8247) time: 0.5085 [2021-03-27 01:53:09 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 580/1251] eta: 0:05:42 lr: 0.000070 loss: 2.9868 (2.8034) grad_norm: 2.7247 (2.8247) time: 0.5094 [2021-03-27 01:53:14 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 590/1251] eta: 0:05:37 lr: 0.000070 loss: 2.8575 (2.8013) grad_norm: 2.8190 (2.8303) time: 0.5030 [2021-03-27 01:53:18 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 600/1251] eta: 0:05:31 lr: 0.000070 loss: 2.7886 (2.8008) grad_norm: 2.8157 (2.8402) time: 0.4942 [2021-03-27 01:53:24 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 610/1251] eta: 0:05:26 lr: 0.000070 loss: 2.9012 (2.8024) grad_norm: 2.7926 (2.8402) time: 0.5014 [2021-03-27 01:53:29 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 620/1251] eta: 0:05:21 lr: 0.000070 loss: 2.7089 (2.7987) grad_norm: 2.7238 (2.8378) time: 0.5082 [2021-03-27 01:53:34 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 630/1251] eta: 0:05:16 lr: 0.000070 loss: 2.6317 (2.7952) grad_norm: 2.7540 (2.8369) time: 0.4999 [2021-03-27 01:53:38 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 640/1251] eta: 0:05:11 lr: 0.000070 loss: 2.8741 (2.7982) grad_norm: 2.7643 (2.8402) time: 0.4958 [2021-03-27 01:53:44 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 650/1251] eta: 0:05:06 lr: 0.000070 loss: 2.8709 (2.7989) grad_norm: 2.7496 (2.8391) time: 0.4979 [2021-03-27 01:53:49 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 660/1251] eta: 0:05:00 lr: 0.000070 loss: 2.8016 (2.7973) grad_norm: 2.6049 (2.8372) time: 0.5003 [2021-03-27 01:53:54 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 670/1251] eta: 0:04:55 lr: 0.000070 loss: 3.0840 (2.8000) grad_norm: 2.7094 (2.8444) time: 0.5008 [2021-03-27 01:53:59 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 680/1251] eta: 0:04:50 lr: 0.000070 loss: 3.0277 (2.7978) grad_norm: 2.7210 (2.8535) time: 0.4995 [2021-03-27 01:54:04 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 690/1251] eta: 0:04:45 lr: 0.000070 loss: 2.7482 (2.7972) grad_norm: 2.7636 (2.8535) time: 0.5043 [2021-03-27 01:54:09 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 700/1251] eta: 0:04:40 lr: 0.000070 loss: 2.5625 (2.7946) grad_norm: 2.7883 (2.8558) time: 0.5059 [2021-03-27 01:54:14 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 710/1251] eta: 0:04:35 lr: 0.000070 loss: 2.7326 (2.7975) grad_norm: 2.7495 (2.8596) time: 0.5007 [2021-03-27 01:54:19 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 720/1251] eta: 0:04:30 lr: 0.000070 loss: 3.0500 (2.7995) grad_norm: 2.7002 (2.8585) time: 0.4979 [2021-03-27 01:54:24 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 730/1251] eta: 0:04:24 lr: 0.000070 loss: 2.7694 (2.7961) grad_norm: 2.7002 (2.8581) time: 0.4978 [2021-03-27 01:54:29 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 740/1251] eta: 0:04:19 lr: 0.000070 loss: 2.7877 (2.7964) grad_norm: 2.6488 (2.8561) time: 0.5010 [2021-03-27 01:54:34 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 750/1251] eta: 0:04:14 lr: 0.000070 loss: 3.0248 (2.7993) grad_norm: 2.7766 (2.8592) time: 0.5065 [2021-03-27 01:54:39 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 760/1251] eta: 0:04:09 lr: 0.000070 loss: 2.9217 (2.7967) grad_norm: 2.9152 (2.8595) time: 0.5119 [2021-03-27 01:54:44 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 770/1251] eta: 0:04:04 lr: 0.000070 loss: 2.9790 (2.8007) grad_norm: 2.8394 (2.8607) time: 0.5039 [2021-03-27 01:54:49 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 780/1251] eta: 0:03:59 lr: 0.000070 loss: 3.1112 (2.8047) grad_norm: 2.7514 (2.8595) time: 0.4997 [2021-03-27 01:54:54 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 790/1251] eta: 0:03:54 lr: 0.000070 loss: 2.9413 (2.8048) grad_norm: 2.7419 (2.8586) time: 0.5022 [2021-03-27 01:54:59 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 800/1251] eta: 0:03:49 lr: 0.000070 loss: 2.8452 (2.8052) grad_norm: 2.7238 (2.8579) time: 0.5064 [2021-03-27 01:55:04 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 810/1251] eta: 0:03:44 lr: 0.000070 loss: 2.9791 (2.8076) grad_norm: 2.7257 (2.8570) time: 0.5040 [2021-03-27 01:55:09 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 820/1251] eta: 0:03:38 lr: 0.000070 loss: 2.9300 (2.8070) grad_norm: 2.7723 (2.8591) time: 0.5015 [2021-03-27 01:55:14 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 830/1251] eta: 0:03:33 lr: 0.000070 loss: 2.9031 (2.8087) grad_norm: 2.8658 (2.8596) time: 0.5083 [2021-03-27 01:55:19 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 840/1251] eta: 0:03:28 lr: 0.000070 loss: 3.1258 (2.8100) grad_norm: 2.8995 (2.8615) time: 0.5038 [2021-03-27 01:55:24 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 850/1251] eta: 0:03:23 lr: 0.000070 loss: 3.0605 (2.8108) grad_norm: 2.8158 (2.8612) time: 0.5063 [2021-03-27 01:55:29 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 860/1251] eta: 0:03:18 lr: 0.000070 loss: 2.9853 (2.8119) grad_norm: 2.7274 (2.8612) time: 0.5084 [2021-03-27 01:55:34 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 870/1251] eta: 0:03:13 lr: 0.000070 loss: 2.8125 (2.8117) grad_norm: 2.7116 (2.8611) time: 0.5076 [2021-03-27 01:55:40 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 880/1251] eta: 0:03:08 lr: 0.000069 loss: 2.8034 (2.8111) grad_norm: 2.6620 (2.8600) time: 0.5140 [2021-03-27 01:55:45 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 890/1251] eta: 0:03:03 lr: 0.000069 loss: 2.9686 (2.8092) grad_norm: 2.7007 (2.8637) time: 0.5098 [2021-03-27 01:55:50 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 900/1251] eta: 0:02:58 lr: 0.000069 loss: 3.1389 (2.8125) grad_norm: 2.8955 (2.8630) time: 0.5048 [2021-03-27 01:55:55 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 910/1251] eta: 0:02:53 lr: 0.000069 loss: 3.0491 (2.8121) grad_norm: 2.7977 (2.8622) time: 0.5009 [2021-03-27 01:56:00 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 920/1251] eta: 0:02:48 lr: 0.000069 loss: 2.9520 (2.8140) grad_norm: 2.6931 (2.8617) time: 0.4953 [2021-03-27 01:56:05 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 930/1251] eta: 0:02:42 lr: 0.000069 loss: 2.9420 (2.8123) grad_norm: 2.7123 (nan) time: 0.4952 [2021-03-27 01:56:10 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 940/1251] eta: 0:02:37 lr: 0.000069 loss: 2.7737 (2.8110) grad_norm: 2.8189 (nan) time: 0.4984 [2021-03-27 01:56:14 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 950/1251] eta: 0:02:32 lr: 0.000069 loss: 2.7640 (2.8106) grad_norm: 2.7394 (nan) time: 0.4961 [2021-03-27 01:56:19 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 960/1251] eta: 0:02:27 lr: 0.000069 loss: 2.9155 (2.8121) grad_norm: 2.7911 (nan) time: 0.4934 [2021-03-27 01:56:25 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 970/1251] eta: 0:02:22 lr: 0.000069 loss: 2.9277 (2.8131) grad_norm: 2.7911 (nan) time: 0.5046 [2021-03-27 01:56:29 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 980/1251] eta: 0:02:17 lr: 0.000069 loss: 2.9949 (2.8138) grad_norm: 2.7614 (nan) time: 0.5040 [2021-03-27 01:56:35 swin_small_patch4_window7_224] INFO: Epoch: [252] [ 990/1251] eta: 0:02:12 lr: 0.000069 loss: 2.9601 (2.8128) grad_norm: 2.7859 (nan) time: 0.4995 [2021-03-27 01:56:39 swin_small_patch4_window7_224] INFO: Epoch: [252] [1000/1251] eta: 0:02:07 lr: 0.000069 loss: 2.8320 (2.8120) grad_norm: 2.7859 (nan) time: 0.4977 [2021-03-27 01:56:44 swin_small_patch4_window7_224] INFO: Epoch: [252] [1010/1251] eta: 0:02:02 lr: 0.000069 loss: 2.7531 (2.8104) grad_norm: 2.6262 (nan) time: 0.4960 [2021-03-27 01:56:49 swin_small_patch4_window7_224] INFO: Epoch: [252] [1020/1251] eta: 0:01:57 lr: 0.000069 loss: 2.9231 (2.8127) grad_norm: 2.5978 (nan) time: 0.4997 [2021-03-27 01:56:55 swin_small_patch4_window7_224] INFO: Epoch: [252] [1030/1251] eta: 0:01:52 lr: 0.000069 loss: 2.9505 (2.8125) grad_norm: 2.6917 (nan) time: 0.5045 [2021-03-27 01:57:00 swin_small_patch4_window7_224] INFO: Epoch: [252] [1040/1251] eta: 0:01:46 lr: 0.000069 loss: 2.8404 (2.8121) grad_norm: 2.7716 (nan) time: 0.5037 [2021-03-27 01:57:05 swin_small_patch4_window7_224] INFO: Epoch: [252] [1050/1251] eta: 0:01:41 lr: 0.000069 loss: 2.8708 (2.8125) grad_norm: 2.7159 (nan) time: 0.5072 [2021-03-27 01:57:10 swin_small_patch4_window7_224] INFO: Epoch: [252] [1060/1251] eta: 0:01:36 lr: 0.000069 loss: 2.8411 (2.8114) grad_norm: 2.7159 (nan) time: 0.5108 [2021-03-27 01:57:15 swin_small_patch4_window7_224] INFO: Epoch: [252] [1070/1251] eta: 0:01:31 lr: 0.000069 loss: 2.8575 (2.8128) grad_norm: 2.6609 (nan) time: 0.5033 [2021-03-27 01:57:20 swin_small_patch4_window7_224] INFO: Epoch: [252] [1080/1251] eta: 0:01:26 lr: 0.000069 loss: 2.9326 (2.8129) grad_norm: 2.6549 (nan) time: 0.5018 [2021-03-27 01:57:25 swin_small_patch4_window7_224] INFO: Epoch: [252] [1090/1251] eta: 0:01:21 lr: 0.000069 loss: 2.9326 (2.8147) grad_norm: 2.6799 (nan) time: 0.5046 [2021-03-27 01:57:30 swin_small_patch4_window7_224] INFO: Epoch: [252] [1100/1251] eta: 0:01:16 lr: 0.000069 loss: 2.9268 (2.8146) grad_norm: 2.6530 (nan) time: 0.5053 [2021-03-27 01:57:35 swin_small_patch4_window7_224] INFO: Epoch: [252] [1110/1251] eta: 0:01:11 lr: 0.000069 loss: 2.7005 (2.8134) grad_norm: 2.6421 (nan) time: 0.5023 [2021-03-27 01:57:40 swin_small_patch4_window7_224] INFO: Epoch: [252] [1120/1251] eta: 0:01:06 lr: 0.000069 loss: 2.7005 (2.8127) grad_norm: 2.8811 (nan) time: 0.4998 [2021-03-27 01:57:45 swin_small_patch4_window7_224] INFO: Epoch: [252] [1130/1251] eta: 0:01:01 lr: 0.000069 loss: 2.9719 (2.8136) grad_norm: 2.6706 (nan) time: 0.4994 [2021-03-27 01:57:50 swin_small_patch4_window7_224] INFO: Epoch: [252] [1140/1251] eta: 0:00:56 lr: 0.000069 loss: 2.9780 (2.8151) grad_norm: 2.6151 (nan) time: 0.5044 [2021-03-27 01:57:55 swin_small_patch4_window7_224] INFO: Epoch: [252] [1150/1251] eta: 0:00:51 lr: 0.000069 loss: 2.9675 (2.8148) grad_norm: 2.5428 (nan) time: 0.5029 [2021-03-27 01:58:00 swin_small_patch4_window7_224] INFO: Epoch: [252] [1160/1251] eta: 0:00:46 lr: 0.000069 loss: 2.9337 (2.8135) grad_norm: 2.5656 (nan) time: 0.4980 [2021-03-27 01:58:05 swin_small_patch4_window7_224] INFO: Epoch: [252] [1170/1251] eta: 0:00:41 lr: 0.000069 loss: 2.6120 (2.8126) grad_norm: 2.6369 (nan) time: 0.5010 [2021-03-27 01:58:10 swin_small_patch4_window7_224] INFO: Epoch: [252] [1180/1251] eta: 0:00:35 lr: 0.000069 loss: 2.8014 (2.8130) grad_norm: 2.6646 (nan) time: 0.5082 [2021-03-27 01:58:15 swin_small_patch4_window7_224] INFO: Epoch: [252] [1190/1251] eta: 0:00:30 lr: 0.000069 loss: 2.9571 (2.8121) grad_norm: 2.6853 (nan) time: 0.5110 [2021-03-27 01:58:20 swin_small_patch4_window7_224] INFO: Epoch: [252] [1200/1251] eta: 0:00:25 lr: 0.000069 loss: 2.8109 (2.8130) grad_norm: 2.7451 (nan) time: 0.5054 [2021-03-27 01:58:25 swin_small_patch4_window7_224] INFO: Epoch: [252] [1210/1251] eta: 0:00:20 lr: 0.000069 loss: 2.7322 (2.8101) grad_norm: 2.7451 (nan) time: 0.4994 [2021-03-27 01:58:30 swin_small_patch4_window7_224] INFO: Epoch: [252] [1220/1251] eta: 0:00:15 lr: 0.000069 loss: 2.7325 (2.8100) grad_norm: 2.7315 (nan) time: 0.4983 [2021-03-27 01:58:35 swin_small_patch4_window7_224] INFO: Epoch: [252] [1230/1251] eta: 0:00:10 lr: 0.000069 loss: 2.8266 (2.8095) grad_norm: 2.7315 (nan) time: 0.4994 [2021-03-27 01:58:40 swin_small_patch4_window7_224] INFO: Epoch: [252] [1240/1251] eta: 0:00:05 lr: 0.000069 loss: 2.8616 (2.8103) grad_norm: 2.7159 (nan) time: 0.4974 [2021-03-27 01:58:45 swin_small_patch4_window7_224] INFO: Epoch: [252] [1250/1251] eta: 0:00:00 lr: 0.000069 loss: 2.9886 (2.8114) grad_norm: 2.8329 (nan) time: 0.4958 [2021-03-27 01:58:59 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:45 loss: 0.6566 (0.6566) acc1: 81.2500 (81.2500) acc5: 100.0000 (100.0000) [2021-03-27 01:59:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7650 (0.7568) acc1: 81.2500 (79.6875) acc5: 96.8750 (96.1648) [2021-03-27 01:59:04 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7048 (0.7586) acc1: 81.2500 (80.7292) acc5: 95.3125 (96.2054) [2021-03-27 01:59:06 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7857 (0.8084) acc1: 79.6875 (79.8891) acc5: 95.3125 (95.8669) [2021-03-27 01:59:08 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8291 (0.7822) acc1: 79.6875 (80.9070) acc5: 95.3125 (95.8460) [2021-03-27 01:59:09 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6569 (0.7640) acc1: 81.2500 (81.4720) acc5: 96.8750 (96.1280) [2021-03-27 01:59:25 swin_small_patch4_window7_224] INFO: * Acc@1 82.334 Acc@5 96.094 loss 0.752 [2021-03-27 01:59:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.3% [2021-03-27 01:59:25 swin_small_patch4_window7_224] INFO: Max accuracy: 82.45% [2021-03-27 01:59:29 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 0/1251] eta: 1:34:39 lr: 0.000069 loss: 3.0448 (3.0448) grad_norm: 3.1020 (3.1020) time: 4.5400 [2021-03-27 01:59:35 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 10/1251] eta: 0:18:25 lr: 0.000069 loss: 2.6618 (2.6754) grad_norm: 2.9304 (3.0226) time: 0.8910 [2021-03-27 01:59:40 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 20/1251] eta: 0:14:31 lr: 0.000069 loss: 2.6618 (2.7308) grad_norm: 2.9051 (3.0008) time: 0.5160 [2021-03-27 01:59:45 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 30/1251] eta: 0:13:06 lr: 0.000069 loss: 2.9016 (2.8368) grad_norm: 2.8756 (3.0108) time: 0.5078 [2021-03-27 01:59:50 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 40/1251] eta: 0:12:17 lr: 0.000069 loss: 2.9016 (2.7994) grad_norm: 2.8806 (3.0001) time: 0.5056 [2021-03-27 01:59:55 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 50/1251] eta: 0:11:46 lr: 0.000069 loss: 2.6846 (2.7509) grad_norm: 2.9859 (3.0198) time: 0.5019 [2021-03-27 02:00:00 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 60/1251] eta: 0:11:24 lr: 0.000069 loss: 2.9378 (2.7876) grad_norm: 2.7444 (3.0224) time: 0.5032 [2021-03-27 02:00:05 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 70/1251] eta: 0:11:08 lr: 0.000069 loss: 2.9872 (2.7839) grad_norm: 2.9654 (3.0338) time: 0.5083 [2021-03-27 02:00:10 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 80/1251] eta: 0:10:53 lr: 0.000069 loss: 2.7223 (2.7625) grad_norm: 2.9544 (3.0202) time: 0.5077 [2021-03-27 02:00:15 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 90/1251] eta: 0:10:42 lr: 0.000069 loss: 2.7674 (2.7580) grad_norm: 2.6139 (2.9804) time: 0.5091 [2021-03-27 02:00:20 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 100/1251] eta: 0:10:31 lr: 0.000069 loss: 2.8114 (2.7568) grad_norm: 2.6020 (2.9583) time: 0.5105 [2021-03-27 02:00:25 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 110/1251] eta: 0:10:20 lr: 0.000069 loss: 2.9660 (2.7673) grad_norm: 2.7102 (2.9351) time: 0.5024 [2021-03-27 02:00:30 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 120/1251] eta: 0:10:11 lr: 0.000069 loss: 2.9009 (2.7565) grad_norm: 2.5861 (2.9116) time: 0.4994 [2021-03-27 02:00:35 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 130/1251] eta: 0:10:04 lr: 0.000069 loss: 2.8725 (2.7550) grad_norm: 2.5879 (2.8928) time: 0.5097 [2021-03-27 02:00:40 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 140/1251] eta: 0:09:55 lr: 0.000068 loss: 2.9848 (2.7635) grad_norm: 2.5749 (2.8836) time: 0.5088 [2021-03-27 02:00:45 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 150/1251] eta: 0:09:48 lr: 0.000068 loss: 3.0122 (2.7663) grad_norm: 2.6695 (2.8999) time: 0.5063 [2021-03-27 02:00:51 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 160/1251] eta: 0:09:41 lr: 0.000068 loss: 2.8775 (2.7681) grad_norm: 2.7419 (2.8949) time: 0.5123 [2021-03-27 02:00:56 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 170/1251] eta: 0:09:33 lr: 0.000068 loss: 2.8387 (2.7746) grad_norm: 2.7081 (2.9113) time: 0.5036 [2021-03-27 02:01:01 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 180/1251] eta: 0:09:26 lr: 0.000068 loss: 2.8387 (2.7692) grad_norm: 2.7317 (2.9061) time: 0.4987 [2021-03-27 02:01:05 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 190/1251] eta: 0:09:19 lr: 0.000068 loss: 2.9231 (2.7771) grad_norm: 2.6409 (2.8909) time: 0.4981 [2021-03-27 02:01:11 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 200/1251] eta: 0:09:13 lr: 0.000068 loss: 2.8415 (2.7693) grad_norm: 2.5704 (2.8833) time: 0.5022 [2021-03-27 02:01:16 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 210/1251] eta: 0:09:06 lr: 0.000068 loss: 2.7639 (2.7728) grad_norm: 2.6154 (2.8756) time: 0.5055 [2021-03-27 02:01:21 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 220/1251] eta: 0:09:00 lr: 0.000068 loss: 2.9173 (2.7710) grad_norm: 2.6015 (2.8721) time: 0.4980 [2021-03-27 02:01:26 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 230/1251] eta: 0:08:54 lr: 0.000068 loss: 2.9743 (2.7723) grad_norm: 2.6015 (2.8703) time: 0.5003 [2021-03-27 02:01:31 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 240/1251] eta: 0:08:48 lr: 0.000068 loss: 2.9810 (2.7799) grad_norm: 2.7081 (2.8632) time: 0.5105 [2021-03-27 02:01:36 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 250/1251] eta: 0:08:42 lr: 0.000068 loss: 2.9316 (2.7707) grad_norm: 2.7194 (2.8635) time: 0.5097 [2021-03-27 02:01:41 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 260/1251] eta: 0:08:36 lr: 0.000068 loss: 2.9456 (2.7763) grad_norm: 2.7626 (2.8580) time: 0.5028 [2021-03-27 02:01:46 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 270/1251] eta: 0:08:30 lr: 0.000068 loss: 3.0050 (2.7889) grad_norm: 2.7640 (2.8608) time: 0.5048 [2021-03-27 02:01:51 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 280/1251] eta: 0:08:24 lr: 0.000068 loss: 2.9764 (2.7868) grad_norm: 2.8392 (2.8632) time: 0.5038 [2021-03-27 02:01:56 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 290/1251] eta: 0:08:19 lr: 0.000068 loss: 2.6926 (2.7857) grad_norm: 2.8427 (2.8656) time: 0.5060 [2021-03-27 02:02:01 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 300/1251] eta: 0:08:13 lr: 0.000068 loss: 2.9104 (2.7940) grad_norm: 2.8973 (2.8702) time: 0.5073 [2021-03-27 02:02:06 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 310/1251] eta: 0:08:08 lr: 0.000068 loss: 3.1038 (2.7964) grad_norm: 2.7659 (2.8702) time: 0.5019 [2021-03-27 02:02:11 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 320/1251] eta: 0:08:02 lr: 0.000068 loss: 3.0343 (2.8007) grad_norm: 2.7659 (2.8736) time: 0.5030 [2021-03-27 02:02:16 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 330/1251] eta: 0:07:57 lr: 0.000068 loss: 2.7277 (2.7927) grad_norm: 2.6652 (2.8713) time: 0.5083 [2021-03-27 02:02:21 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 340/1251] eta: 0:07:51 lr: 0.000068 loss: 2.5829 (2.7937) grad_norm: 2.6963 (2.8707) time: 0.5076 [2021-03-27 02:02:26 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 350/1251] eta: 0:07:46 lr: 0.000068 loss: 2.9060 (2.7927) grad_norm: 2.7750 (2.8733) time: 0.5073 [2021-03-27 02:02:31 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 360/1251] eta: 0:07:40 lr: 0.000068 loss: 2.9737 (2.8028) grad_norm: 2.7034 (2.8684) time: 0.5065 [2021-03-27 02:02:36 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 370/1251] eta: 0:07:34 lr: 0.000068 loss: 3.0151 (2.8052) grad_norm: 2.5568 (2.8596) time: 0.4971 [2021-03-27 02:02:41 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 380/1251] eta: 0:07:29 lr: 0.000068 loss: 3.0062 (2.8047) grad_norm: 2.6421 (2.8681) time: 0.4980 [2021-03-27 02:02:46 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 390/1251] eta: 0:07:23 lr: 0.000068 loss: 2.8676 (2.8031) grad_norm: 2.6928 (2.8659) time: 0.5034 [2021-03-27 02:02:52 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 400/1251] eta: 0:07:18 lr: 0.000068 loss: 2.6907 (2.8024) grad_norm: 2.7130 (2.8646) time: 0.5093 [2021-03-27 02:02:57 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 410/1251] eta: 0:07:13 lr: 0.000068 loss: 2.8108 (2.8044) grad_norm: 2.8157 (2.8632) time: 0.5053 [2021-03-27 02:03:01 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 420/1251] eta: 0:07:07 lr: 0.000068 loss: 2.9500 (2.8055) grad_norm: 2.7580 (2.8610) time: 0.4965 [2021-03-27 02:03:07 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 430/1251] eta: 0:07:02 lr: 0.000068 loss: 2.9434 (2.8050) grad_norm: 2.7036 (2.8603) time: 0.5036 [2021-03-27 02:03:12 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 440/1251] eta: 0:06:57 lr: 0.000068 loss: 2.9434 (2.8065) grad_norm: 2.8049 (2.8556) time: 0.5082 [2021-03-27 02:03:17 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 450/1251] eta: 0:06:51 lr: 0.000068 loss: 3.0917 (2.8097) grad_norm: 2.8057 (2.8604) time: 0.5017 [2021-03-27 02:03:22 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 460/1251] eta: 0:06:46 lr: 0.000068 loss: 3.0917 (2.8104) grad_norm: 2.8459 (2.8583) time: 0.4956 [2021-03-27 02:03:27 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 470/1251] eta: 0:06:40 lr: 0.000068 loss: 2.8330 (2.8119) grad_norm: 2.7333 (2.8558) time: 0.4983 [2021-03-27 02:03:32 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 480/1251] eta: 0:06:35 lr: 0.000068 loss: 2.7972 (2.8093) grad_norm: 2.7467 (2.8569) time: 0.5019 [2021-03-27 02:03:37 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 490/1251] eta: 0:06:30 lr: 0.000068 loss: 2.7558 (2.8096) grad_norm: 2.7781 (2.8559) time: 0.5015 [2021-03-27 02:03:42 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 500/1251] eta: 0:06:24 lr: 0.000068 loss: 2.8216 (2.8094) grad_norm: 2.6839 (2.8549) time: 0.5015 [2021-03-27 02:03:47 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 510/1251] eta: 0:06:19 lr: 0.000068 loss: 2.8756 (2.8110) grad_norm: 2.7689 (2.8567) time: 0.5008 [2021-03-27 02:03:52 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 520/1251] eta: 0:06:14 lr: 0.000068 loss: 2.9935 (2.8129) grad_norm: 2.8748 (2.8583) time: 0.4971 [2021-03-27 02:03:57 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 530/1251] eta: 0:06:09 lr: 0.000068 loss: 2.8059 (2.8092) grad_norm: 2.8707 (2.8609) time: 0.4963 [2021-03-27 02:04:02 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 540/1251] eta: 0:06:03 lr: 0.000068 loss: 2.6859 (2.8069) grad_norm: 2.8492 (2.8607) time: 0.4980 [2021-03-27 02:04:07 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 550/1251] eta: 0:05:58 lr: 0.000068 loss: 3.0733 (2.8124) grad_norm: 2.7880 (2.8641) time: 0.5086 [2021-03-27 02:04:12 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 560/1251] eta: 0:05:53 lr: 0.000068 loss: 3.1072 (2.8153) grad_norm: 2.8037 (2.8661) time: 0.5204 [2021-03-27 02:04:17 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 570/1251] eta: 0:05:48 lr: 0.000068 loss: 3.0659 (2.8175) grad_norm: 2.6679 (2.8621) time: 0.5070 [2021-03-27 02:04:22 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 580/1251] eta: 0:05:43 lr: 0.000068 loss: 3.0385 (2.8191) grad_norm: 2.6679 (2.8629) time: 0.5001 [2021-03-27 02:04:27 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 590/1251] eta: 0:05:38 lr: 0.000068 loss: 3.0145 (2.8203) grad_norm: 2.8138 (2.8686) time: 0.5063 [2021-03-27 02:04:32 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 600/1251] eta: 0:05:32 lr: 0.000068 loss: 2.9465 (2.8197) grad_norm: 2.6752 (2.8652) time: 0.5025 [2021-03-27 02:04:37 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 610/1251] eta: 0:05:27 lr: 0.000068 loss: 2.8611 (2.8185) grad_norm: 2.5699 (2.8617) time: 0.4939 [2021-03-27 02:04:42 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 620/1251] eta: 0:05:22 lr: 0.000068 loss: 2.7114 (2.8188) grad_norm: 2.6042 (2.8590) time: 0.4939 [2021-03-27 02:04:47 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 630/1251] eta: 0:05:16 lr: 0.000068 loss: 2.7791 (2.8200) grad_norm: 2.6285 (2.8566) time: 0.4997 [2021-03-27 02:04:52 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 640/1251] eta: 0:05:11 lr: 0.000068 loss: 3.0308 (2.8227) grad_norm: 2.6857 (2.8632) time: 0.5036 [2021-03-27 02:04:57 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 650/1251] eta: 0:05:06 lr: 0.000067 loss: 2.9863 (2.8200) grad_norm: 2.8670 (2.8689) time: 0.5083 [2021-03-27 02:05:02 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 660/1251] eta: 0:05:01 lr: 0.000067 loss: 2.8831 (2.8217) grad_norm: 2.7649 (2.8684) time: 0.5101 [2021-03-27 02:05:07 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 670/1251] eta: 0:04:56 lr: 0.000067 loss: 3.0106 (2.8241) grad_norm: 2.7304 (2.8810) time: 0.5063 [2021-03-27 02:05:12 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 680/1251] eta: 0:04:51 lr: 0.000067 loss: 3.1018 (2.8262) grad_norm: 2.9141 (2.8848) time: 0.5072 [2021-03-27 02:05:17 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 690/1251] eta: 0:04:46 lr: 0.000067 loss: 2.9322 (2.8251) grad_norm: 2.9680 (2.8901) time: 0.5055 [2021-03-27 02:05:22 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 700/1251] eta: 0:04:40 lr: 0.000067 loss: 2.8766 (2.8256) grad_norm: 3.0367 (2.8902) time: 0.4996 [2021-03-27 02:05:27 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 710/1251] eta: 0:04:35 lr: 0.000067 loss: 2.9144 (2.8232) grad_norm: 2.9494 (2.8930) time: 0.5007 [2021-03-27 02:05:32 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 720/1251] eta: 0:04:30 lr: 0.000067 loss: 2.7313 (2.8223) grad_norm: 2.8419 (2.8916) time: 0.4994 [2021-03-27 02:05:37 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 730/1251] eta: 0:04:25 lr: 0.000067 loss: 2.7550 (2.8204) grad_norm: 2.7058 (2.8891) time: 0.4976 [2021-03-27 02:05:43 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 740/1251] eta: 0:04:20 lr: 0.000067 loss: 2.8640 (2.8205) grad_norm: 2.6034 (2.8854) time: 0.5108 [2021-03-27 02:05:48 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 750/1251] eta: 0:04:15 lr: 0.000067 loss: 3.0162 (2.8213) grad_norm: 2.7018 (2.8843) time: 0.5244 [2021-03-27 02:05:53 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 760/1251] eta: 0:04:10 lr: 0.000067 loss: 2.8159 (2.8147) grad_norm: 2.7560 (2.8836) time: 0.5113 [2021-03-27 02:05:58 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 770/1251] eta: 0:04:05 lr: 0.000067 loss: 2.7314 (2.8152) grad_norm: 2.7686 (2.8847) time: 0.5009 [2021-03-27 02:06:03 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 780/1251] eta: 0:04:00 lr: 0.000067 loss: 2.8238 (2.8140) grad_norm: 2.7971 (2.8872) time: 0.5023 [2021-03-27 02:06:08 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 790/1251] eta: 0:03:54 lr: 0.000067 loss: 3.0311 (2.8171) grad_norm: 2.8284 (2.8866) time: 0.5057 [2021-03-27 02:06:13 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 800/1251] eta: 0:03:49 lr: 0.000067 loss: 2.9107 (2.8146) grad_norm: 2.7132 (2.8842) time: 0.5041 [2021-03-27 02:06:18 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 810/1251] eta: 0:03:44 lr: 0.000067 loss: 2.7541 (2.8138) grad_norm: 2.7854 (2.8880) time: 0.5005 [2021-03-27 02:06:23 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 820/1251] eta: 0:03:39 lr: 0.000067 loss: 2.8026 (2.8146) grad_norm: 2.9363 (2.8885) time: 0.5044 [2021-03-27 02:06:28 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 830/1251] eta: 0:03:34 lr: 0.000067 loss: 2.9441 (2.8158) grad_norm: 2.7884 (2.8869) time: 0.5070 [2021-03-27 02:06:33 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 840/1251] eta: 0:03:29 lr: 0.000067 loss: 2.9441 (2.8161) grad_norm: 2.7554 (2.8870) time: 0.5141 [2021-03-27 02:06:38 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 850/1251] eta: 0:03:24 lr: 0.000067 loss: 2.9707 (2.8191) grad_norm: 2.6211 (2.8849) time: 0.5092 [2021-03-27 02:06:43 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 860/1251] eta: 0:03:19 lr: 0.000067 loss: 2.9229 (2.8161) grad_norm: 2.6211 (2.8814) time: 0.5002 [2021-03-27 02:06:48 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 870/1251] eta: 0:03:14 lr: 0.000067 loss: 2.6254 (2.8149) grad_norm: 2.6430 (2.8818) time: 0.5044 [2021-03-27 02:06:53 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 880/1251] eta: 0:03:08 lr: 0.000067 loss: 2.7950 (2.8153) grad_norm: 2.8578 (2.8843) time: 0.5092 [2021-03-27 02:06:58 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 890/1251] eta: 0:03:03 lr: 0.000067 loss: 2.8000 (2.8140) grad_norm: 2.7558 (2.8842) time: 0.5049 [2021-03-27 02:07:03 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 900/1251] eta: 0:02:58 lr: 0.000067 loss: 2.7867 (2.8131) grad_norm: 2.7592 (2.8846) time: 0.5004 [2021-03-27 02:07:09 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 910/1251] eta: 0:02:53 lr: 0.000067 loss: 2.7287 (2.8106) grad_norm: 2.7685 (2.8847) time: 0.5045 [2021-03-27 02:07:14 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 920/1251] eta: 0:02:48 lr: 0.000067 loss: 2.7287 (2.8088) grad_norm: 2.7510 (2.8939) time: 0.5107 [2021-03-27 02:07:19 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 930/1251] eta: 0:02:43 lr: 0.000067 loss: 2.7986 (2.8068) grad_norm: 2.8350 (2.8998) time: 0.5084 [2021-03-27 02:07:24 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 940/1251] eta: 0:02:38 lr: 0.000067 loss: 2.8381 (2.8066) grad_norm: 2.8458 (2.8996) time: 0.5062 [2021-03-27 02:07:29 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 950/1251] eta: 0:02:33 lr: 0.000067 loss: 2.9002 (2.8076) grad_norm: 2.7990 (2.8992) time: 0.5056 [2021-03-27 02:07:34 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 960/1251] eta: 0:02:28 lr: 0.000067 loss: 2.8660 (2.8070) grad_norm: 2.7961 (2.8974) time: 0.5020 [2021-03-27 02:07:39 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 970/1251] eta: 0:02:22 lr: 0.000067 loss: 2.8433 (2.8079) grad_norm: 2.7040 (2.8963) time: 0.5005 [2021-03-27 02:07:44 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 980/1251] eta: 0:02:17 lr: 0.000067 loss: 2.9290 (2.8094) grad_norm: 2.7574 (2.8962) time: 0.5006 [2021-03-27 02:07:49 swin_small_patch4_window7_224] INFO: Epoch: [253] [ 990/1251] eta: 0:02:12 lr: 0.000067 loss: 2.8768 (2.8090) grad_norm: 2.7452 (2.8956) time: 0.5048 [2021-03-27 02:07:54 swin_small_patch4_window7_224] INFO: Epoch: [253] [1000/1251] eta: 0:02:07 lr: 0.000067 loss: 2.8768 (2.8092) grad_norm: 2.6831 (2.8942) time: 0.5021 [2021-03-27 02:07:59 swin_small_patch4_window7_224] INFO: Epoch: [253] [1010/1251] eta: 0:02:02 lr: 0.000067 loss: 3.0814 (2.8087) grad_norm: 2.7145 (2.8928) time: 0.5030 [2021-03-27 02:08:04 swin_small_patch4_window7_224] INFO: Epoch: [253] [1020/1251] eta: 0:01:57 lr: 0.000067 loss: 2.8689 (2.8094) grad_norm: 2.7750 (2.8926) time: 0.5053 [2021-03-27 02:08:09 swin_small_patch4_window7_224] INFO: Epoch: [253] [1030/1251] eta: 0:01:52 lr: 0.000067 loss: 2.8689 (2.8101) grad_norm: 2.7750 (2.8941) time: 0.5051 [2021-03-27 02:08:14 swin_small_patch4_window7_224] INFO: Epoch: [253] [1040/1251] eta: 0:01:47 lr: 0.000067 loss: 2.8283 (2.8107) grad_norm: 2.9929 (2.8974) time: 0.5058 [2021-03-27 02:08:19 swin_small_patch4_window7_224] INFO: Epoch: [253] [1050/1251] eta: 0:01:42 lr: 0.000067 loss: 2.8164 (2.8101) grad_norm: 2.9251 (2.8977) time: 0.5051 [2021-03-27 02:08:24 swin_small_patch4_window7_224] INFO: Epoch: [253] [1060/1251] eta: 0:01:37 lr: 0.000067 loss: 2.6445 (2.8082) grad_norm: 2.9056 (2.9018) time: 0.5058 [2021-03-27 02:08:29 swin_small_patch4_window7_224] INFO: Epoch: [253] [1070/1251] eta: 0:01:32 lr: 0.000067 loss: 2.6445 (2.8079) grad_norm: 2.9203 (2.9067) time: 0.5077 [2021-03-27 02:08:34 swin_small_patch4_window7_224] INFO: Epoch: [253] [1080/1251] eta: 0:01:26 lr: 0.000067 loss: 2.8162 (2.8082) grad_norm: 2.8858 (2.9053) time: 0.5065 [2021-03-27 02:08:39 swin_small_patch4_window7_224] INFO: Epoch: [253] [1090/1251] eta: 0:01:21 lr: 0.000067 loss: 2.7885 (2.8069) grad_norm: 2.7992 (2.9055) time: 0.5028 [2021-03-27 02:08:45 swin_small_patch4_window7_224] INFO: Epoch: [253] [1100/1251] eta: 0:01:16 lr: 0.000067 loss: 2.8509 (2.8070) grad_norm: 2.7991 (2.9051) time: 0.5069 [2021-03-27 02:08:50 swin_small_patch4_window7_224] INFO: Epoch: [253] [1110/1251] eta: 0:01:11 lr: 0.000067 loss: 2.8576 (2.8054) grad_norm: 2.7563 (2.9043) time: 0.5048 [2021-03-27 02:08:55 swin_small_patch4_window7_224] INFO: Epoch: [253] [1120/1251] eta: 0:01:06 lr: 0.000067 loss: 2.8576 (2.8053) grad_norm: 2.7356 (2.9048) time: 0.5026 [2021-03-27 02:09:00 swin_small_patch4_window7_224] INFO: Epoch: [253] [1130/1251] eta: 0:01:01 lr: 0.000067 loss: 2.9814 (2.8049) grad_norm: 2.7370 (2.9092) time: 0.4986 [2021-03-27 02:09:05 swin_small_patch4_window7_224] INFO: Epoch: [253] [1140/1251] eta: 0:00:56 lr: 0.000067 loss: 2.5453 (2.8030) grad_norm: 3.0625 (2.9122) time: 0.4957 [2021-03-27 02:09:10 swin_small_patch4_window7_224] INFO: Epoch: [253] [1150/1251] eta: 0:00:51 lr: 0.000067 loss: 2.7719 (2.8034) grad_norm: 2.8461 (2.9119) time: 0.5030 [2021-03-27 02:09:15 swin_small_patch4_window7_224] INFO: Epoch: [253] [1160/1251] eta: 0:00:46 lr: 0.000067 loss: 2.9444 (2.8031) grad_norm: 2.7916 (2.9119) time: 0.5011 [2021-03-27 02:09:20 swin_small_patch4_window7_224] INFO: Epoch: [253] [1170/1251] eta: 0:00:41 lr: 0.000066 loss: 2.7547 (2.8027) grad_norm: 2.9088 (2.9155) time: 0.4957 [2021-03-27 02:09:25 swin_small_patch4_window7_224] INFO: Epoch: [253] [1180/1251] eta: 0:00:36 lr: 0.000066 loss: 2.8610 (2.8041) grad_norm: 2.9725 (2.9158) time: 0.5033 [2021-03-27 02:09:30 swin_small_patch4_window7_224] INFO: Epoch: [253] [1190/1251] eta: 0:00:30 lr: 0.000066 loss: 2.7157 (2.8014) grad_norm: 2.8739 (2.9155) time: 0.5019 [2021-03-27 02:09:34 swin_small_patch4_window7_224] INFO: Epoch: [253] [1200/1251] eta: 0:00:25 lr: 0.000066 loss: 2.4551 (2.8000) grad_norm: 2.7584 (2.9140) time: 0.4930 [2021-03-27 02:09:40 swin_small_patch4_window7_224] INFO: Epoch: [253] [1210/1251] eta: 0:00:20 lr: 0.000066 loss: 2.7515 (2.7995) grad_norm: 2.7156 (2.9120) time: 0.4988 [2021-03-27 02:09:45 swin_small_patch4_window7_224] INFO: Epoch: [253] [1220/1251] eta: 0:00:15 lr: 0.000066 loss: 2.7602 (2.7972) grad_norm: 2.7829 (2.9128) time: 0.5030 [2021-03-27 02:09:50 swin_small_patch4_window7_224] INFO: Epoch: [253] [1230/1251] eta: 0:00:10 lr: 0.000066 loss: 2.7482 (2.7977) grad_norm: 2.9894 (2.9130) time: 0.5064 [2021-03-27 02:09:55 swin_small_patch4_window7_224] INFO: Epoch: [253] [1240/1251] eta: 0:00:05 lr: 0.000066 loss: 2.7993 (2.7967) grad_norm: 2.8817 (2.9133) time: 0.5082 [2021-03-27 02:10:00 swin_small_patch4_window7_224] INFO: Epoch: [253] [1250/1251] eta: 0:00:00 lr: 0.000066 loss: 2.8282 (2.7962) grad_norm: 2.7977 (2.9124) time: 0.5073 [2021-03-27 02:10:11 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.5649 (0.5649) acc1: 87.5000 (87.5000) acc5: 96.8750 (96.8750) [2021-03-27 02:10:13 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7552 (0.7802) acc1: 81.2500 (81.3920) acc5: 95.3125 (95.3125) [2021-03-27 02:10:15 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7144 (0.7184) acc1: 81.2500 (82.0685) acc5: 95.3125 (95.9821) [2021-03-27 02:10:16 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:04 loss: 0.6246 (0.7458) acc1: 84.3750 (82.1069) acc5: 96.8750 (95.9677) [2021-03-27 02:10:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7075 (0.7489) acc1: 84.3750 (82.2027) acc5: 96.8750 (96.0366) [2021-03-27 02:10:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7799 (0.7622) acc1: 81.2500 (81.8880) acc5: 96.8750 (96.0320) [2021-03-27 02:10:36 swin_small_patch4_window7_224] INFO: * Acc@1 82.478 Acc@5 96.060 loss 0.753 [2021-03-27 02:10:36 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-27 02:10:36 swin_small_patch4_window7_224] INFO: Max accuracy: 82.48% [2021-03-27 02:10:40 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 0/1251] eta: 1:37:50 lr: 0.000066 loss: 3.3590 (3.3590) grad_norm: 3.0439 (3.0439) time: 4.6924 [2021-03-27 02:10:45 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 10/1251] eta: 0:18:14 lr: 0.000066 loss: 3.1207 (3.0115) grad_norm: 3.0428 (3.0938) time: 0.8816 [2021-03-27 02:10:50 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 20/1251] eta: 0:14:27 lr: 0.000066 loss: 3.0118 (2.9693) grad_norm: 2.8576 (2.9826) time: 0.5052 [2021-03-27 02:10:55 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 30/1251] eta: 0:13:02 lr: 0.000066 loss: 2.8124 (2.8794) grad_norm: 2.7950 (2.9958) time: 0.5080 [2021-03-27 02:11:00 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 40/1251] eta: 0:12:12 lr: 0.000066 loss: 2.8243 (2.8763) grad_norm: 2.7950 (2.9840) time: 0.4995 [2021-03-27 02:11:05 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 50/1251] eta: 0:11:43 lr: 0.000066 loss: 2.8314 (2.8568) grad_norm: 2.6986 (2.9174) time: 0.5014 [2021-03-27 02:11:11 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 60/1251] eta: 0:11:23 lr: 0.000066 loss: 2.7814 (2.8370) grad_norm: 2.7719 (2.9360) time: 0.5114 [2021-03-27 02:11:16 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 70/1251] eta: 0:11:08 lr: 0.000066 loss: 2.8897 (2.8634) grad_norm: 2.8948 (2.9151) time: 0.5143 [2021-03-27 02:11:21 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 80/1251] eta: 0:10:53 lr: 0.000066 loss: 2.9872 (2.8579) grad_norm: 2.8005 (2.9564) time: 0.5105 [2021-03-27 02:11:26 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 90/1251] eta: 0:10:41 lr: 0.000066 loss: 2.8630 (2.8496) grad_norm: 2.8005 (2.9330) time: 0.5039 [2021-03-27 02:11:31 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 100/1251] eta: 0:10:29 lr: 0.000066 loss: 2.9059 (2.8457) grad_norm: 2.7373 (2.9248) time: 0.5027 [2021-03-27 02:11:36 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 110/1251] eta: 0:10:20 lr: 0.000066 loss: 2.9004 (2.8208) grad_norm: 2.8256 (2.9806) time: 0.5034 [2021-03-27 02:11:41 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 120/1251] eta: 0:10:12 lr: 0.000066 loss: 2.9572 (2.8323) grad_norm: 2.9656 (3.0007) time: 0.5122 [2021-03-27 02:11:46 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 130/1251] eta: 0:10:04 lr: 0.000066 loss: 2.7285 (2.8069) grad_norm: 2.7218 (2.9890) time: 0.5163 [2021-03-27 02:11:51 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 140/1251] eta: 0:09:56 lr: 0.000066 loss: 2.8606 (2.8301) grad_norm: 2.8981 (2.9873) time: 0.5061 [2021-03-27 02:11:56 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 150/1251] eta: 0:09:47 lr: 0.000066 loss: 2.9338 (2.8283) grad_norm: 2.7815 (2.9689) time: 0.4992 [2021-03-27 02:12:01 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 160/1251] eta: 0:09:40 lr: 0.000066 loss: 2.9184 (2.8319) grad_norm: 2.7360 (2.9601) time: 0.4986 [2021-03-27 02:12:06 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 170/1251] eta: 0:09:33 lr: 0.000066 loss: 2.9222 (2.8225) grad_norm: 2.7363 (2.9449) time: 0.5063 [2021-03-27 02:12:11 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 180/1251] eta: 0:09:26 lr: 0.000066 loss: 2.5952 (2.8094) grad_norm: 2.7363 (2.9661) time: 0.5091 [2021-03-27 02:12:16 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 190/1251] eta: 0:09:19 lr: 0.000066 loss: 2.5961 (2.8033) grad_norm: 2.7833 (2.9650) time: 0.4981 [2021-03-27 02:12:21 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 200/1251] eta: 0:09:12 lr: 0.000066 loss: 2.7502 (2.7930) grad_norm: 2.8578 (2.9677) time: 0.4965 [2021-03-27 02:12:26 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 210/1251] eta: 0:09:06 lr: 0.000066 loss: 2.8481 (2.8002) grad_norm: 2.7945 (2.9521) time: 0.5013 [2021-03-27 02:12:31 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 220/1251] eta: 0:09:00 lr: 0.000066 loss: 2.7359 (2.7944) grad_norm: 2.6756 (2.9536) time: 0.5031 [2021-03-27 02:12:36 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 230/1251] eta: 0:08:53 lr: 0.000066 loss: 2.5801 (2.7849) grad_norm: 2.6756 (2.9479) time: 0.5017 [2021-03-27 02:12:41 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 240/1251] eta: 0:08:47 lr: 0.000066 loss: 2.5392 (2.7713) grad_norm: 2.7034 (2.9403) time: 0.5011 [2021-03-27 02:12:46 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 250/1251] eta: 0:08:42 lr: 0.000066 loss: 2.5889 (2.7675) grad_norm: 2.6461 (2.9363) time: 0.5062 [2021-03-27 02:12:51 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 260/1251] eta: 0:08:35 lr: 0.000066 loss: 2.7482 (2.7677) grad_norm: 2.6461 (2.9315) time: 0.5020 [2021-03-27 02:12:56 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 270/1251] eta: 0:08:29 lr: 0.000066 loss: 2.6773 (2.7655) grad_norm: 2.7239 (2.9297) time: 0.4970 [2021-03-27 02:13:01 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 280/1251] eta: 0:08:24 lr: 0.000066 loss: 2.7218 (2.7629) grad_norm: 2.7680 (2.9295) time: 0.5011 [2021-03-27 02:13:06 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 290/1251] eta: 0:08:18 lr: 0.000066 loss: 2.8644 (2.7637) grad_norm: 2.8121 (2.9303) time: 0.5019 [2021-03-27 02:13:11 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 300/1251] eta: 0:08:12 lr: 0.000066 loss: 2.8638 (2.7603) grad_norm: 2.6962 (2.9176) time: 0.4987 [2021-03-27 02:13:17 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 310/1251] eta: 0:08:06 lr: 0.000066 loss: 2.7840 (2.7569) grad_norm: 2.5906 (2.9208) time: 0.5018 [2021-03-27 02:13:22 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 320/1251] eta: 0:08:01 lr: 0.000066 loss: 2.7209 (2.7560) grad_norm: 2.8281 (2.9236) time: 0.5063 [2021-03-27 02:13:27 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 330/1251] eta: 0:07:55 lr: 0.000066 loss: 2.7333 (2.7578) grad_norm: 2.8281 (2.9200) time: 0.5049 [2021-03-27 02:13:32 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 340/1251] eta: 0:07:50 lr: 0.000066 loss: 2.8054 (2.7537) grad_norm: 2.7957 (2.9228) time: 0.5024 [2021-03-27 02:13:37 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 350/1251] eta: 0:07:44 lr: 0.000066 loss: 2.9067 (2.7595) grad_norm: 2.8276 (2.9211) time: 0.5014 [2021-03-27 02:13:42 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 360/1251] eta: 0:07:39 lr: 0.000066 loss: 2.9067 (2.7569) grad_norm: 2.6229 (2.9163) time: 0.5017 [2021-03-27 02:13:47 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 370/1251] eta: 0:07:33 lr: 0.000066 loss: 2.8418 (2.7626) grad_norm: 2.6400 (2.9129) time: 0.5003 [2021-03-27 02:13:52 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 380/1251] eta: 0:07:28 lr: 0.000066 loss: 2.8418 (2.7588) grad_norm: 2.7751 (2.9075) time: 0.4988 [2021-03-27 02:13:57 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 390/1251] eta: 0:07:22 lr: 0.000066 loss: 2.5887 (2.7608) grad_norm: 2.7973 (2.9076) time: 0.4969 [2021-03-27 02:14:02 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 400/1251] eta: 0:07:17 lr: 0.000066 loss: 2.9195 (2.7629) grad_norm: 2.8282 (2.9053) time: 0.4953 [2021-03-27 02:14:07 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 410/1251] eta: 0:07:11 lr: 0.000066 loss: 2.9446 (2.7699) grad_norm: 2.7251 (2.9016) time: 0.4959 [2021-03-27 02:14:11 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 420/1251] eta: 0:07:06 lr: 0.000066 loss: 2.9288 (2.7663) grad_norm: 2.6577 (2.8948) time: 0.4953 [2021-03-27 02:14:16 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 430/1251] eta: 0:07:00 lr: 0.000066 loss: 2.9174 (2.7696) grad_norm: 2.6107 (2.8912) time: 0.4972 [2021-03-27 02:14:21 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 440/1251] eta: 0:06:55 lr: 0.000065 loss: 2.8491 (2.7631) grad_norm: 2.7504 (2.8945) time: 0.5010 [2021-03-27 02:14:26 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 450/1251] eta: 0:06:49 lr: 0.000065 loss: 2.5294 (2.7626) grad_norm: 2.7867 (2.8931) time: 0.4978 [2021-03-27 02:14:31 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 460/1251] eta: 0:06:44 lr: 0.000065 loss: 2.7168 (2.7574) grad_norm: 2.6698 (2.8912) time: 0.4940 [2021-03-27 02:14:36 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 470/1251] eta: 0:06:39 lr: 0.000065 loss: 2.7168 (2.7554) grad_norm: 2.6909 (2.8895) time: 0.4963 [2021-03-27 02:14:41 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 480/1251] eta: 0:06:33 lr: 0.000065 loss: 2.9169 (2.7589) grad_norm: 2.7429 (2.8889) time: 0.4969 [2021-03-27 02:14:46 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 490/1251] eta: 0:06:28 lr: 0.000065 loss: 3.0012 (2.7639) grad_norm: 2.7663 (2.8831) time: 0.4992 [2021-03-27 02:14:51 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 500/1251] eta: 0:06:23 lr: 0.000065 loss: 2.9434 (2.7625) grad_norm: 2.7663 (2.8817) time: 0.4995 [2021-03-27 02:14:56 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 510/1251] eta: 0:06:17 lr: 0.000065 loss: 2.7471 (2.7590) grad_norm: 2.7351 (2.8770) time: 0.4975 [2021-03-27 02:15:01 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 520/1251] eta: 0:06:12 lr: 0.000065 loss: 2.7251 (2.7573) grad_norm: 2.6502 (2.8744) time: 0.5009 [2021-03-27 02:15:06 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 530/1251] eta: 0:06:07 lr: 0.000065 loss: 2.6737 (2.7564) grad_norm: 2.6936 (2.8726) time: 0.5009 [2021-03-27 02:15:11 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 540/1251] eta: 0:06:02 lr: 0.000065 loss: 2.9026 (2.7571) grad_norm: 2.6201 (2.8732) time: 0.5017 [2021-03-27 02:15:17 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 550/1251] eta: 0:05:57 lr: 0.000065 loss: 2.9401 (2.7583) grad_norm: 2.4953 (2.8709) time: 0.5152 [2021-03-27 02:15:22 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 560/1251] eta: 0:05:52 lr: 0.000065 loss: 3.0235 (2.7621) grad_norm: 2.4659 (2.8657) time: 0.5153 [2021-03-27 02:15:27 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 570/1251] eta: 0:05:47 lr: 0.000065 loss: 2.9631 (2.7631) grad_norm: 2.6332 (2.8628) time: 0.5016 [2021-03-27 02:15:32 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 580/1251] eta: 0:05:41 lr: 0.000065 loss: 2.7943 (2.7615) grad_norm: 2.6919 (2.8608) time: 0.5031 [2021-03-27 02:15:37 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 590/1251] eta: 0:05:36 lr: 0.000065 loss: 2.6538 (2.7596) grad_norm: 2.8409 (2.8653) time: 0.5011 [2021-03-27 02:15:42 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 600/1251] eta: 0:05:31 lr: 0.000065 loss: 2.8558 (2.7607) grad_norm: 2.8706 (2.8658) time: 0.5022 [2021-03-27 02:15:47 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 610/1251] eta: 0:05:26 lr: 0.000065 loss: 2.9631 (2.7576) grad_norm: 2.7802 (2.8639) time: 0.5079 [2021-03-27 02:15:52 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 620/1251] eta: 0:05:21 lr: 0.000065 loss: 2.4693 (2.7550) grad_norm: 2.6167 (2.8627) time: 0.5070 [2021-03-27 02:15:57 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 630/1251] eta: 0:05:16 lr: 0.000065 loss: 2.8174 (2.7593) grad_norm: 2.6649 (2.8598) time: 0.5082 [2021-03-27 02:16:02 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 640/1251] eta: 0:05:11 lr: 0.000065 loss: 2.9935 (2.7614) grad_norm: 2.6228 (2.8555) time: 0.5047 [2021-03-27 02:16:07 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 650/1251] eta: 0:05:05 lr: 0.000065 loss: 3.0460 (2.7634) grad_norm: 2.7050 (2.8568) time: 0.5016 [2021-03-27 02:16:12 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 660/1251] eta: 0:05:00 lr: 0.000065 loss: 2.7948 (2.7606) grad_norm: 2.7803 (2.8555) time: 0.5052 [2021-03-27 02:16:17 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 670/1251] eta: 0:04:55 lr: 0.000065 loss: 2.8474 (2.7636) grad_norm: 2.7125 (2.8546) time: 0.5087 [2021-03-27 02:16:22 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 680/1251] eta: 0:04:50 lr: 0.000065 loss: 2.8474 (2.7605) grad_norm: 2.8932 (2.8580) time: 0.5070 [2021-03-27 02:16:27 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 690/1251] eta: 0:04:45 lr: 0.000065 loss: 2.8877 (2.7620) grad_norm: 2.7718 (2.8552) time: 0.5054 [2021-03-27 02:16:32 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 700/1251] eta: 0:04:40 lr: 0.000065 loss: 2.9887 (2.7645) grad_norm: 2.7718 (2.8559) time: 0.5052 [2021-03-27 02:16:37 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 710/1251] eta: 0:04:35 lr: 0.000065 loss: 2.9496 (2.7638) grad_norm: 2.7751 (2.8545) time: 0.5053 [2021-03-27 02:16:42 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 720/1251] eta: 0:04:30 lr: 0.000065 loss: 2.7151 (2.7607) grad_norm: 2.7434 (nan) time: 0.4985 [2021-03-27 02:16:47 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 730/1251] eta: 0:04:24 lr: 0.000065 loss: 2.7053 (2.7598) grad_norm: 2.7434 (nan) time: 0.4945 [2021-03-27 02:16:53 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 740/1251] eta: 0:04:19 lr: 0.000065 loss: 2.7552 (2.7598) grad_norm: 2.7491 (nan) time: 0.5163 [2021-03-27 02:16:58 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 750/1251] eta: 0:04:14 lr: 0.000065 loss: 2.7552 (2.7585) grad_norm: 2.8210 (nan) time: 0.5227 [2021-03-27 02:17:03 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 760/1251] eta: 0:04:09 lr: 0.000065 loss: 2.9307 (2.7618) grad_norm: 2.7409 (nan) time: 0.5112 [2021-03-27 02:17:08 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 770/1251] eta: 0:04:04 lr: 0.000065 loss: 2.7575 (2.7580) grad_norm: 2.7409 (nan) time: 0.5075 [2021-03-27 02:17:13 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 780/1251] eta: 0:03:59 lr: 0.000065 loss: 2.7261 (2.7595) grad_norm: 2.9723 (nan) time: 0.5081 [2021-03-27 02:17:18 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 790/1251] eta: 0:03:54 lr: 0.000065 loss: 2.8729 (2.7593) grad_norm: 2.9063 (nan) time: 0.5107 [2021-03-27 02:17:23 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 800/1251] eta: 0:03:49 lr: 0.000065 loss: 2.8600 (2.7611) grad_norm: 2.6109 (nan) time: 0.5136 [2021-03-27 02:17:29 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 810/1251] eta: 0:03:44 lr: 0.000065 loss: 2.9475 (2.7636) grad_norm: 2.5414 (nan) time: 0.5163 [2021-03-27 02:17:33 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 820/1251] eta: 0:03:39 lr: 0.000065 loss: 2.9475 (2.7641) grad_norm: 2.6245 (nan) time: 0.5029 [2021-03-27 02:17:39 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 830/1251] eta: 0:03:34 lr: 0.000065 loss: 2.8616 (2.7616) grad_norm: 2.6508 (nan) time: 0.5016 [2021-03-27 02:17:44 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 840/1251] eta: 0:03:29 lr: 0.000065 loss: 2.9291 (2.7639) grad_norm: 2.6818 (nan) time: 0.5107 [2021-03-27 02:17:49 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 850/1251] eta: 0:03:23 lr: 0.000065 loss: 3.0262 (2.7657) grad_norm: 2.7069 (nan) time: 0.5035 [2021-03-27 02:17:54 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 860/1251] eta: 0:03:18 lr: 0.000065 loss: 2.9382 (2.7661) grad_norm: 2.6208 (nan) time: 0.5007 [2021-03-27 02:17:59 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 870/1251] eta: 0:03:13 lr: 0.000065 loss: 2.7453 (2.7662) grad_norm: 2.5633 (nan) time: 0.5059 [2021-03-27 02:18:04 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 880/1251] eta: 0:03:08 lr: 0.000065 loss: 2.7571 (2.7666) grad_norm: 2.8882 (nan) time: 0.5064 [2021-03-27 02:18:09 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 890/1251] eta: 0:03:03 lr: 0.000065 loss: 2.9784 (2.7705) grad_norm: 2.9352 (nan) time: 0.4997 [2021-03-27 02:18:14 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 900/1251] eta: 0:02:58 lr: 0.000065 loss: 3.1538 (2.7737) grad_norm: 2.7679 (nan) time: 0.4953 [2021-03-27 02:18:19 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 910/1251] eta: 0:02:53 lr: 0.000065 loss: 2.8083 (2.7709) grad_norm: 2.8168 (nan) time: 0.4971 [2021-03-27 02:18:24 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 920/1251] eta: 0:02:48 lr: 0.000065 loss: 2.7773 (2.7720) grad_norm: 2.8795 (nan) time: 0.4976 [2021-03-27 02:18:29 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 930/1251] eta: 0:02:43 lr: 0.000065 loss: 2.9535 (2.7733) grad_norm: 2.7751 (nan) time: 0.4968 [2021-03-27 02:18:34 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 940/1251] eta: 0:02:37 lr: 0.000065 loss: 2.9263 (2.7735) grad_norm: 2.6771 (nan) time: 0.4981 [2021-03-27 02:18:39 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 950/1251] eta: 0:02:32 lr: 0.000065 loss: 2.8729 (2.7747) grad_norm: 2.5814 (nan) time: 0.5012 [2021-03-27 02:18:44 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 960/1251] eta: 0:02:27 lr: 0.000065 loss: 3.0069 (2.7768) grad_norm: 2.6760 (nan) time: 0.5022 [2021-03-27 02:18:49 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 970/1251] eta: 0:02:22 lr: 0.000064 loss: 2.9089 (2.7772) grad_norm: 2.9191 (nan) time: 0.5036 [2021-03-27 02:18:54 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 980/1251] eta: 0:02:17 lr: 0.000064 loss: 2.9089 (2.7783) grad_norm: 2.8706 (nan) time: 0.5001 [2021-03-27 02:18:59 swin_small_patch4_window7_224] INFO: Epoch: [254] [ 990/1251] eta: 0:02:12 lr: 0.000064 loss: 2.9870 (2.7798) grad_norm: 2.7674 (nan) time: 0.5011 [2021-03-27 02:19:04 swin_small_patch4_window7_224] INFO: Epoch: [254] [1000/1251] eta: 0:02:07 lr: 0.000064 loss: 3.0177 (2.7797) grad_norm: 2.7360 (nan) time: 0.5074 [2021-03-27 02:19:09 swin_small_patch4_window7_224] INFO: Epoch: [254] [1010/1251] eta: 0:02:02 lr: 0.000064 loss: 2.9483 (2.7803) grad_norm: 2.7587 (nan) time: 0.5037 [2021-03-27 02:19:14 swin_small_patch4_window7_224] INFO: Epoch: [254] [1020/1251] eta: 0:01:57 lr: 0.000064 loss: 2.8333 (2.7819) grad_norm: 2.8207 (nan) time: 0.4976 [2021-03-27 02:19:19 swin_small_patch4_window7_224] INFO: Epoch: [254] [1030/1251] eta: 0:01:52 lr: 0.000064 loss: 2.7874 (2.7797) grad_norm: 2.7654 (nan) time: 0.4991 [2021-03-27 02:19:24 swin_small_patch4_window7_224] INFO: Epoch: [254] [1040/1251] eta: 0:01:47 lr: 0.000064 loss: 2.7346 (2.7804) grad_norm: 2.7463 (nan) time: 0.4986 [2021-03-27 02:19:29 swin_small_patch4_window7_224] INFO: Epoch: [254] [1050/1251] eta: 0:01:41 lr: 0.000064 loss: 2.8382 (2.7814) grad_norm: 2.6488 (nan) time: 0.4988 [2021-03-27 02:19:34 swin_small_patch4_window7_224] INFO: Epoch: [254] [1060/1251] eta: 0:01:36 lr: 0.000064 loss: 2.8696 (2.7812) grad_norm: 2.6075 (nan) time: 0.5051 [2021-03-27 02:19:39 swin_small_patch4_window7_224] INFO: Epoch: [254] [1070/1251] eta: 0:01:31 lr: 0.000064 loss: 2.7627 (2.7804) grad_norm: 2.6537 (nan) time: 0.5064 [2021-03-27 02:19:44 swin_small_patch4_window7_224] INFO: Epoch: [254] [1080/1251] eta: 0:01:26 lr: 0.000064 loss: 2.8024 (2.7799) grad_norm: 2.7358 (nan) time: 0.5012 [2021-03-27 02:19:49 swin_small_patch4_window7_224] INFO: Epoch: [254] [1090/1251] eta: 0:01:21 lr: 0.000064 loss: 2.7606 (2.7796) grad_norm: 2.8090 (nan) time: 0.4967 [2021-03-27 02:19:54 swin_small_patch4_window7_224] INFO: Epoch: [254] [1100/1251] eta: 0:01:16 lr: 0.000064 loss: 2.7606 (2.7796) grad_norm: 2.8096 (nan) time: 0.5009 [2021-03-27 02:19:59 swin_small_patch4_window7_224] INFO: Epoch: [254] [1110/1251] eta: 0:01:11 lr: 0.000064 loss: 2.9307 (2.7806) grad_norm: 2.8779 (nan) time: 0.5042 [2021-03-27 02:20:04 swin_small_patch4_window7_224] INFO: Epoch: [254] [1120/1251] eta: 0:01:06 lr: 0.000064 loss: 2.8620 (2.7805) grad_norm: 2.9157 (nan) time: 0.4997 [2021-03-27 02:20:09 swin_small_patch4_window7_224] INFO: Epoch: [254] [1130/1251] eta: 0:01:01 lr: 0.000064 loss: 2.7381 (2.7789) grad_norm: 2.9157 (nan) time: 0.4952 [2021-03-27 02:20:14 swin_small_patch4_window7_224] INFO: Epoch: [254] [1140/1251] eta: 0:00:56 lr: 0.000064 loss: 2.7212 (2.7793) grad_norm: 2.9490 (nan) time: 0.4993 [2021-03-27 02:20:19 swin_small_patch4_window7_224] INFO: Epoch: [254] [1150/1251] eta: 0:00:51 lr: 0.000064 loss: 2.7406 (2.7784) grad_norm: 2.8376 (nan) time: 0.5023 [2021-03-27 02:20:24 swin_small_patch4_window7_224] INFO: Epoch: [254] [1160/1251] eta: 0:00:46 lr: 0.000064 loss: 2.7317 (2.7772) grad_norm: 2.8161 (nan) time: 0.4985 [2021-03-27 02:20:29 swin_small_patch4_window7_224] INFO: Epoch: [254] [1170/1251] eta: 0:00:41 lr: 0.000064 loss: 2.7499 (2.7778) grad_norm: 2.7110 (nan) time: 0.4978 [2021-03-27 02:20:34 swin_small_patch4_window7_224] INFO: Epoch: [254] [1180/1251] eta: 0:00:35 lr: 0.000064 loss: 2.8133 (2.7776) grad_norm: 2.7233 (nan) time: 0.4994 [2021-03-27 02:20:39 swin_small_patch4_window7_224] INFO: Epoch: [254] [1190/1251] eta: 0:00:30 lr: 0.000064 loss: 2.8633 (2.7788) grad_norm: 2.8645 (nan) time: 0.4969 [2021-03-27 02:20:44 swin_small_patch4_window7_224] INFO: Epoch: [254] [1200/1251] eta: 0:00:25 lr: 0.000064 loss: 2.9601 (2.7785) grad_norm: 2.7683 (nan) time: 0.4928 [2021-03-27 02:20:49 swin_small_patch4_window7_224] INFO: Epoch: [254] [1210/1251] eta: 0:00:20 lr: 0.000064 loss: 2.8696 (2.7798) grad_norm: 2.6728 (nan) time: 0.4968 [2021-03-27 02:20:54 swin_small_patch4_window7_224] INFO: Epoch: [254] [1220/1251] eta: 0:00:15 lr: 0.000064 loss: 2.8696 (2.7803) grad_norm: 2.6371 (nan) time: 0.5009 [2021-03-27 02:20:59 swin_small_patch4_window7_224] INFO: Epoch: [254] [1230/1251] eta: 0:00:10 lr: 0.000064 loss: 2.8524 (2.7799) grad_norm: 2.8450 (nan) time: 0.4967 [2021-03-27 02:21:04 swin_small_patch4_window7_224] INFO: Epoch: [254] [1240/1251] eta: 0:00:05 lr: 0.000064 loss: 2.9207 (2.7810) grad_norm: 2.8450 (nan) time: 0.4964 [2021-03-27 02:21:09 swin_small_patch4_window7_224] INFO: Epoch: [254] [1250/1251] eta: 0:00:00 lr: 0.000064 loss: 2.9964 (2.7809) grad_norm: 2.7144 (nan) time: 0.5007 [2021-03-27 02:21:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 0.5524 (0.5524) acc1: 85.9375 (85.9375) acc5: 98.4375 (98.4375) [2021-03-27 02:21:21 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.6664 (0.7130) acc1: 82.8125 (82.1023) acc5: 98.4375 (97.0170) [2021-03-27 02:21:23 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6862 (0.7431) acc1: 82.8125 (82.5893) acc5: 95.3125 (96.0565) [2021-03-27 02:21:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7050 (0.7207) acc1: 82.8125 (82.7621) acc5: 95.3125 (96.2702) [2021-03-27 02:21:28 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7122 (0.7443) acc1: 81.2500 (82.2790) acc5: 96.8750 (96.1509) [2021-03-27 02:21:29 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7968 (0.7646) acc1: 79.6875 (81.6640) acc5: 96.8750 (96.1600) [2021-03-27 02:21:42 swin_small_patch4_window7_224] INFO: * Acc@1 82.466 Acc@5 96.098 loss 0.755 [2021-03-27 02:21:42 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-27 02:21:42 swin_small_patch4_window7_224] INFO: Max accuracy: 82.48% [2021-03-27 02:21:47 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 0/1251] eta: 1:29:37 lr: 0.000064 loss: 3.4457 (3.4457) grad_norm: 3.3801 (3.3801) time: 4.2988 [2021-03-27 02:21:52 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 10/1251] eta: 0:17:49 lr: 0.000064 loss: 2.7868 (2.7504) grad_norm: 2.9049 (3.0701) time: 0.8616 [2021-03-27 02:21:57 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 20/1251] eta: 0:14:14 lr: 0.000064 loss: 2.8019 (2.8243) grad_norm: 2.7660 (2.9824) time: 0.5136 [2021-03-27 02:22:02 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 30/1251] eta: 0:12:57 lr: 0.000064 loss: 2.9122 (2.8117) grad_norm: 2.7192 (2.8879) time: 0.5135 [2021-03-27 02:22:07 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 40/1251] eta: 0:12:13 lr: 0.000064 loss: 2.9088 (2.7985) grad_norm: 2.7192 (2.8956) time: 0.5123 [2021-03-27 02:22:12 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 50/1251] eta: 0:11:44 lr: 0.000064 loss: 2.9887 (2.8213) grad_norm: 2.7979 (2.8894) time: 0.5094 [2021-03-27 02:22:17 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 60/1251] eta: 0:11:21 lr: 0.000064 loss: 3.0895 (2.8367) grad_norm: 2.7979 (2.8985) time: 0.5045 [2021-03-27 02:22:22 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 70/1251] eta: 0:11:04 lr: 0.000064 loss: 3.0527 (2.8518) grad_norm: 2.7782 (2.8968) time: 0.5022 [2021-03-27 02:22:27 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 80/1251] eta: 0:10:49 lr: 0.000064 loss: 2.9339 (2.8439) grad_norm: 2.7782 (2.8777) time: 0.5017 [2021-03-27 02:22:32 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 90/1251] eta: 0:10:36 lr: 0.000064 loss: 2.9221 (2.8503) grad_norm: 2.6060 (2.8715) time: 0.4963 [2021-03-27 02:22:37 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 100/1251] eta: 0:10:27 lr: 0.000064 loss: 2.9081 (2.8488) grad_norm: 2.8193 (2.8990) time: 0.5069 [2021-03-27 02:22:42 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 110/1251] eta: 0:10:17 lr: 0.000064 loss: 2.9081 (2.8489) grad_norm: 2.9692 (2.9131) time: 0.5097 [2021-03-27 02:22:47 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 120/1251] eta: 0:10:07 lr: 0.000064 loss: 3.0031 (2.8443) grad_norm: 2.6471 (2.9064) time: 0.4981 [2021-03-27 02:22:52 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 130/1251] eta: 0:09:59 lr: 0.000064 loss: 2.9660 (2.8483) grad_norm: 2.5896 (2.8906) time: 0.4996 [2021-03-27 02:22:58 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 140/1251] eta: 0:09:51 lr: 0.000064 loss: 2.9914 (2.8568) grad_norm: 2.7069 (2.8860) time: 0.5040 [2021-03-27 02:23:03 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 150/1251] eta: 0:09:44 lr: 0.000064 loss: 2.8363 (2.8390) grad_norm: 2.7365 (2.8885) time: 0.5014 [2021-03-27 02:23:08 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 160/1251] eta: 0:09:37 lr: 0.000064 loss: 2.7839 (2.8344) grad_norm: 2.7365 (2.8838) time: 0.5039 [2021-03-27 02:23:13 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 170/1251] eta: 0:09:30 lr: 0.000064 loss: 2.7839 (2.8175) grad_norm: 2.8215 (2.8888) time: 0.5055 [2021-03-27 02:23:18 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 180/1251] eta: 0:09:24 lr: 0.000064 loss: 2.7609 (2.8194) grad_norm: 2.7408 (2.8848) time: 0.5069 [2021-03-27 02:23:23 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 190/1251] eta: 0:09:17 lr: 0.000064 loss: 2.8186 (2.8142) grad_norm: 2.6582 (2.8841) time: 0.5047 [2021-03-27 02:23:28 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 200/1251] eta: 0:09:10 lr: 0.000064 loss: 2.8510 (2.8070) grad_norm: 2.8254 (2.8876) time: 0.4938 [2021-03-27 02:23:33 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 210/1251] eta: 0:09:04 lr: 0.000064 loss: 2.8730 (2.8121) grad_norm: 2.9239 (2.9105) time: 0.5025 [2021-03-27 02:23:38 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 220/1251] eta: 0:08:58 lr: 0.000064 loss: 2.8719 (2.8110) grad_norm: 2.8549 (2.9098) time: 0.5078 [2021-03-27 02:23:43 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 230/1251] eta: 0:08:52 lr: 0.000064 loss: 2.7530 (2.8064) grad_norm: 2.7368 (2.9090) time: 0.5039 [2021-03-27 02:23:48 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 240/1251] eta: 0:08:46 lr: 0.000064 loss: 2.7041 (2.8066) grad_norm: 2.7233 (2.9017) time: 0.5087 [2021-03-27 02:23:53 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 250/1251] eta: 0:08:40 lr: 0.000063 loss: 2.9082 (2.8055) grad_norm: 2.7772 (2.9244) time: 0.5088 [2021-03-27 02:23:58 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 260/1251] eta: 0:08:35 lr: 0.000063 loss: 2.6410 (2.7970) grad_norm: 2.9934 (2.9232) time: 0.5075 [2021-03-27 02:24:03 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 270/1251] eta: 0:08:29 lr: 0.000063 loss: 2.6410 (2.7946) grad_norm: 2.7941 (2.9222) time: 0.5018 [2021-03-27 02:24:08 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 280/1251] eta: 0:08:23 lr: 0.000063 loss: 2.7989 (2.7922) grad_norm: 2.7564 (2.9217) time: 0.4944 [2021-03-27 02:24:13 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 290/1251] eta: 0:08:17 lr: 0.000063 loss: 2.7350 (2.7844) grad_norm: 2.7926 (2.9257) time: 0.5029 [2021-03-27 02:24:18 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 300/1251] eta: 0:08:11 lr: 0.000063 loss: 2.8162 (2.7826) grad_norm: 2.8504 (2.9631) time: 0.5057 [2021-03-27 02:24:23 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 310/1251] eta: 0:08:06 lr: 0.000063 loss: 2.8259 (2.7820) grad_norm: 2.7604 (2.9611) time: 0.4995 [2021-03-27 02:24:28 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 320/1251] eta: 0:08:00 lr: 0.000063 loss: 2.9202 (2.7845) grad_norm: 2.7604 (2.9609) time: 0.5055 [2021-03-27 02:24:33 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 330/1251] eta: 0:07:55 lr: 0.000063 loss: 2.9080 (2.7847) grad_norm: 2.7038 (2.9582) time: 0.5017 [2021-03-27 02:24:38 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 340/1251] eta: 0:07:49 lr: 0.000063 loss: 2.8535 (2.7873) grad_norm: 2.6864 (2.9586) time: 0.5011 [2021-03-27 02:24:43 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 350/1251] eta: 0:07:44 lr: 0.000063 loss: 2.8632 (2.7862) grad_norm: 2.6045 (2.9516) time: 0.5157 [2021-03-27 02:24:49 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 360/1251] eta: 0:07:39 lr: 0.000063 loss: 2.7868 (2.7847) grad_norm: 2.6368 (2.9443) time: 0.5141 [2021-03-27 02:24:54 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 370/1251] eta: 0:07:33 lr: 0.000063 loss: 2.7343 (2.7870) grad_norm: 2.6797 (2.9418) time: 0.5053 [2021-03-27 02:24:59 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 380/1251] eta: 0:07:28 lr: 0.000063 loss: 2.8988 (2.7861) grad_norm: 2.8954 (2.9520) time: 0.5052 [2021-03-27 02:25:04 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 390/1251] eta: 0:07:23 lr: 0.000063 loss: 2.8988 (2.7894) grad_norm: 2.9314 (2.9617) time: 0.5046 [2021-03-27 02:25:09 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 400/1251] eta: 0:07:17 lr: 0.000063 loss: 2.8699 (2.7923) grad_norm: 2.7928 (2.9578) time: 0.5037 [2021-03-27 02:25:14 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 410/1251] eta: 0:07:12 lr: 0.000063 loss: 2.8699 (2.7936) grad_norm: 2.7669 (2.9519) time: 0.5010 [2021-03-27 02:25:19 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 420/1251] eta: 0:07:07 lr: 0.000063 loss: 2.8501 (2.7930) grad_norm: 2.7423 (2.9471) time: 0.5025 [2021-03-27 02:25:24 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 430/1251] eta: 0:07:01 lr: 0.000063 loss: 2.8501 (2.7913) grad_norm: 2.7557 (2.9446) time: 0.5008 [2021-03-27 02:25:29 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 440/1251] eta: 0:06:56 lr: 0.000063 loss: 2.5879 (2.7854) grad_norm: 2.6994 (2.9407) time: 0.4942 [2021-03-27 02:25:34 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 450/1251] eta: 0:06:50 lr: 0.000063 loss: 2.5879 (2.7855) grad_norm: 2.6750 (2.9397) time: 0.4965 [2021-03-27 02:25:39 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 460/1251] eta: 0:06:45 lr: 0.000063 loss: 2.8464 (2.7861) grad_norm: 2.8890 (2.9399) time: 0.4987 [2021-03-27 02:25:44 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 470/1251] eta: 0:06:40 lr: 0.000063 loss: 2.8404 (2.7834) grad_norm: 2.7322 (2.9338) time: 0.5035 [2021-03-27 02:25:49 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 480/1251] eta: 0:06:34 lr: 0.000063 loss: 2.6727 (2.7811) grad_norm: 2.6052 (2.9312) time: 0.5028 [2021-03-27 02:25:54 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 490/1251] eta: 0:06:29 lr: 0.000063 loss: 2.6727 (2.7775) grad_norm: 2.7253 (2.9284) time: 0.4994 [2021-03-27 02:25:59 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 500/1251] eta: 0:06:24 lr: 0.000063 loss: 2.9005 (2.7802) grad_norm: 2.6800 (2.9216) time: 0.5016 [2021-03-27 02:26:04 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 510/1251] eta: 0:06:18 lr: 0.000063 loss: 2.9123 (2.7798) grad_norm: 2.6061 (2.9185) time: 0.4984 [2021-03-27 02:26:09 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 520/1251] eta: 0:06:13 lr: 0.000063 loss: 2.9178 (2.7807) grad_norm: 2.8125 (2.9162) time: 0.4974 [2021-03-27 02:26:14 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 530/1251] eta: 0:06:08 lr: 0.000063 loss: 2.9495 (2.7831) grad_norm: 2.6179 (2.9123) time: 0.4988 [2021-03-27 02:26:19 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 540/1251] eta: 0:06:03 lr: 0.000063 loss: 2.8758 (2.7834) grad_norm: 2.6236 (2.9112) time: 0.5071 [2021-03-27 02:26:24 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 550/1251] eta: 0:05:58 lr: 0.000063 loss: 3.0367 (2.7894) grad_norm: 2.6242 (2.9074) time: 0.5236 [2021-03-27 02:26:29 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 560/1251] eta: 0:05:53 lr: 0.000063 loss: 3.0138 (2.7904) grad_norm: 2.6242 (2.9112) time: 0.5222 [2021-03-27 02:26:34 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 570/1251] eta: 0:05:47 lr: 0.000063 loss: 2.8966 (2.7885) grad_norm: 2.8246 (2.9078) time: 0.5041 [2021-03-27 02:26:39 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 580/1251] eta: 0:05:42 lr: 0.000063 loss: 2.7838 (2.7891) grad_norm: 2.7321 (2.9038) time: 0.5023 [2021-03-27 02:26:44 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 590/1251] eta: 0:05:37 lr: 0.000063 loss: 3.0211 (2.7930) grad_norm: 2.7321 (2.9018) time: 0.5015 [2021-03-27 02:26:49 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 600/1251] eta: 0:05:32 lr: 0.000063 loss: 2.8414 (2.7913) grad_norm: 2.8737 (2.9065) time: 0.4933 [2021-03-27 02:26:54 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 610/1251] eta: 0:05:27 lr: 0.000063 loss: 2.6201 (2.7866) grad_norm: 2.9822 (2.9112) time: 0.4988 [2021-03-27 02:26:59 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 620/1251] eta: 0:05:21 lr: 0.000063 loss: 2.6201 (2.7868) grad_norm: 2.9332 (2.9121) time: 0.5065 [2021-03-27 02:27:04 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 630/1251] eta: 0:05:16 lr: 0.000063 loss: 2.9002 (2.7872) grad_norm: 2.7863 (2.9120) time: 0.5075 [2021-03-27 02:27:09 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 640/1251] eta: 0:05:11 lr: 0.000063 loss: 2.9218 (2.7883) grad_norm: 2.9081 (2.9151) time: 0.5039 [2021-03-27 02:27:15 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 650/1251] eta: 0:05:06 lr: 0.000063 loss: 2.7933 (2.7876) grad_norm: 2.7816 (2.9192) time: 0.5060 [2021-03-27 02:27:20 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 660/1251] eta: 0:05:01 lr: 0.000063 loss: 2.6237 (2.7839) grad_norm: 2.7816 (2.9178) time: 0.5097 [2021-03-27 02:27:25 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 670/1251] eta: 0:04:56 lr: 0.000063 loss: 2.6872 (2.7850) grad_norm: 2.8489 (2.9223) time: 0.5073 [2021-03-27 02:27:30 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 680/1251] eta: 0:04:51 lr: 0.000063 loss: 2.9865 (2.7870) grad_norm: 2.8489 (2.9250) time: 0.5052 [2021-03-27 02:27:35 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 690/1251] eta: 0:04:45 lr: 0.000063 loss: 2.9239 (2.7851) grad_norm: 2.8067 (2.9243) time: 0.4989 [2021-03-27 02:27:40 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 700/1251] eta: 0:04:40 lr: 0.000063 loss: 2.8817 (2.7829) grad_norm: 2.7717 (2.9218) time: 0.4948 [2021-03-27 02:27:45 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 710/1251] eta: 0:04:35 lr: 0.000063 loss: 2.9423 (2.7838) grad_norm: 2.6635 (2.9198) time: 0.5000 [2021-03-27 02:27:50 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 720/1251] eta: 0:04:30 lr: 0.000063 loss: 2.9515 (2.7877) grad_norm: 2.8138 (2.9203) time: 0.5081 [2021-03-27 02:27:55 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 730/1251] eta: 0:04:25 lr: 0.000063 loss: 2.9609 (2.7893) grad_norm: 2.8362 (2.9187) time: 0.5188 [2021-03-27 02:28:00 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 740/1251] eta: 0:04:20 lr: 0.000063 loss: 3.0304 (2.7909) grad_norm: 2.7355 (2.9143) time: 0.5261 [2021-03-27 02:28:05 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 750/1251] eta: 0:04:15 lr: 0.000063 loss: 2.9727 (2.7904) grad_norm: 2.6367 (2.9141) time: 0.5200 [2021-03-27 02:28:11 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 760/1251] eta: 0:04:10 lr: 0.000063 loss: 2.8882 (2.7892) grad_norm: 2.5796 (2.9106) time: 0.5187 [2021-03-27 02:28:16 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 770/1251] eta: 0:04:05 lr: 0.000063 loss: 2.9101 (2.7892) grad_norm: 2.5796 (2.9075) time: 0.5170 [2021-03-27 02:28:21 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 780/1251] eta: 0:04:00 lr: 0.000062 loss: 2.8777 (2.7896) grad_norm: 2.6216 (2.9042) time: 0.5080 [2021-03-27 02:28:26 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 790/1251] eta: 0:03:55 lr: 0.000062 loss: 2.8395 (2.7874) grad_norm: 2.6716 (2.9014) time: 0.5040 [2021-03-27 02:28:31 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 800/1251] eta: 0:03:49 lr: 0.000062 loss: 2.8487 (2.7854) grad_norm: 2.6548 (2.8988) time: 0.5032 [2021-03-27 02:28:36 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 810/1251] eta: 0:03:44 lr: 0.000062 loss: 2.8635 (2.7856) grad_norm: 2.6351 (2.8981) time: 0.5058 [2021-03-27 02:28:41 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 820/1251] eta: 0:03:39 lr: 0.000062 loss: 2.9526 (2.7868) grad_norm: 2.8271 (2.8983) time: 0.5002 [2021-03-27 02:28:46 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 830/1251] eta: 0:03:34 lr: 0.000062 loss: 3.0937 (2.7876) grad_norm: 2.8102 (2.8948) time: 0.4947 [2021-03-27 02:28:51 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 840/1251] eta: 0:03:29 lr: 0.000062 loss: 2.6034 (2.7861) grad_norm: 2.8006 (2.8937) time: 0.5045 [2021-03-27 02:28:56 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 850/1251] eta: 0:03:24 lr: 0.000062 loss: 2.7097 (2.7853) grad_norm: 2.8170 (2.8920) time: 0.5064 [2021-03-27 02:29:01 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 860/1251] eta: 0:03:19 lr: 0.000062 loss: 2.9346 (2.7860) grad_norm: 2.7837 (2.8904) time: 0.5003 [2021-03-27 02:29:06 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 870/1251] eta: 0:03:14 lr: 0.000062 loss: 2.7219 (2.7839) grad_norm: 2.7837 (2.8911) time: 0.5014 [2021-03-27 02:29:11 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 880/1251] eta: 0:03:08 lr: 0.000062 loss: 2.6671 (2.7837) grad_norm: 2.7587 (2.8895) time: 0.4997 [2021-03-27 02:29:16 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 890/1251] eta: 0:03:03 lr: 0.000062 loss: 2.8658 (2.7852) grad_norm: 2.6539 (2.8883) time: 0.5046 [2021-03-27 02:29:21 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 900/1251] eta: 0:02:58 lr: 0.000062 loss: 2.9496 (2.7869) grad_norm: 2.6821 (2.8863) time: 0.5090 [2021-03-27 02:29:26 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 910/1251] eta: 0:02:53 lr: 0.000062 loss: 2.9358 (2.7892) grad_norm: 2.7046 (2.8861) time: 0.5034 [2021-03-27 02:29:31 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 920/1251] eta: 0:02:48 lr: 0.000062 loss: 2.8793 (2.7901) grad_norm: 2.8120 (2.8855) time: 0.5100 [2021-03-27 02:29:37 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 930/1251] eta: 0:02:43 lr: 0.000062 loss: 2.8312 (2.7897) grad_norm: 2.9376 (2.8867) time: 0.5162 [2021-03-27 02:29:42 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 940/1251] eta: 0:02:38 lr: 0.000062 loss: 2.8844 (2.7907) grad_norm: 2.7398 (2.8844) time: 0.5042 [2021-03-27 02:29:47 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 950/1251] eta: 0:02:33 lr: 0.000062 loss: 2.9586 (2.7925) grad_norm: 2.6887 (2.8881) time: 0.5073 [2021-03-27 02:29:52 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 960/1251] eta: 0:02:28 lr: 0.000062 loss: 2.9064 (2.7930) grad_norm: 2.7629 (2.8873) time: 0.5051 [2021-03-27 02:29:57 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 970/1251] eta: 0:02:23 lr: 0.000062 loss: 2.9305 (2.7947) grad_norm: 2.9143 (2.8876) time: 0.4995 [2021-03-27 02:30:02 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 980/1251] eta: 0:02:17 lr: 0.000062 loss: 3.0268 (2.7960) grad_norm: 2.9028 (2.8874) time: 0.5069 [2021-03-27 02:30:07 swin_small_patch4_window7_224] INFO: Epoch: [255] [ 990/1251] eta: 0:02:12 lr: 0.000062 loss: 2.7695 (2.7940) grad_norm: 2.8063 (2.8876) time: 0.5045 [2021-03-27 02:30:12 swin_small_patch4_window7_224] INFO: Epoch: [255] [1000/1251] eta: 0:02:07 lr: 0.000062 loss: 2.6475 (2.7938) grad_norm: 2.8063 (2.8873) time: 0.4997 [2021-03-27 02:30:17 swin_small_patch4_window7_224] INFO: Epoch: [255] [1010/1251] eta: 0:02:02 lr: 0.000062 loss: 2.8188 (2.7940) grad_norm: 2.7710 (2.8862) time: 0.4972 [2021-03-27 02:30:22 swin_small_patch4_window7_224] INFO: Epoch: [255] [1020/1251] eta: 0:01:57 lr: 0.000062 loss: 2.8612 (2.7944) grad_norm: 2.6731 (2.8854) time: 0.4994 [2021-03-27 02:30:27 swin_small_patch4_window7_224] INFO: Epoch: [255] [1030/1251] eta: 0:01:52 lr: 0.000062 loss: 2.9894 (2.7958) grad_norm: 2.6391 (2.8835) time: 0.4977 [2021-03-27 02:30:32 swin_small_patch4_window7_224] INFO: Epoch: [255] [1040/1251] eta: 0:01:47 lr: 0.000062 loss: 2.9081 (2.7949) grad_norm: 2.7702 (2.8836) time: 0.4954 [2021-03-27 02:30:37 swin_small_patch4_window7_224] INFO: Epoch: [255] [1050/1251] eta: 0:01:42 lr: 0.000062 loss: 2.9081 (2.7955) grad_norm: 2.7147 (2.8818) time: 0.4997 [2021-03-27 02:30:42 swin_small_patch4_window7_224] INFO: Epoch: [255] [1060/1251] eta: 0:01:37 lr: 0.000062 loss: 2.9126 (2.7951) grad_norm: 2.5911 (2.8808) time: 0.4999 [2021-03-27 02:30:47 swin_small_patch4_window7_224] INFO: Epoch: [255] [1070/1251] eta: 0:01:31 lr: 0.000062 loss: 2.8919 (2.7949) grad_norm: 2.7460 (2.8812) time: 0.5069 [2021-03-27 02:30:52 swin_small_patch4_window7_224] INFO: Epoch: [255] [1080/1251] eta: 0:01:26 lr: 0.000062 loss: 2.7223 (2.7931) grad_norm: 2.9001 (2.8812) time: 0.5115 [2021-03-27 02:30:57 swin_small_patch4_window7_224] INFO: Epoch: [255] [1090/1251] eta: 0:01:21 lr: 0.000062 loss: 2.8412 (2.7955) grad_norm: 2.9001 (2.8817) time: 0.5034 [2021-03-27 02:31:02 swin_small_patch4_window7_224] INFO: Epoch: [255] [1100/1251] eta: 0:01:16 lr: 0.000062 loss: 2.9250 (2.7939) grad_norm: 2.6794 (2.8797) time: 0.5002 [2021-03-27 02:31:07 swin_small_patch4_window7_224] INFO: Epoch: [255] [1110/1251] eta: 0:01:11 lr: 0.000062 loss: 2.6590 (2.7940) grad_norm: 2.6978 (2.8880) time: 0.5020 [2021-03-27 02:31:12 swin_small_patch4_window7_224] INFO: Epoch: [255] [1120/1251] eta: 0:01:06 lr: 0.000062 loss: 2.8746 (2.7961) grad_norm: 2.8439 (2.8898) time: 0.5034 [2021-03-27 02:31:17 swin_small_patch4_window7_224] INFO: Epoch: [255] [1130/1251] eta: 0:01:01 lr: 0.000062 loss: 3.0626 (2.7975) grad_norm: 3.0305 (2.8925) time: 0.4988 [2021-03-27 02:31:22 swin_small_patch4_window7_224] INFO: Epoch: [255] [1140/1251] eta: 0:00:56 lr: 0.000062 loss: 3.0047 (2.7985) grad_norm: 2.9642 (2.8917) time: 0.4991 [2021-03-27 02:31:27 swin_small_patch4_window7_224] INFO: Epoch: [255] [1150/1251] eta: 0:00:51 lr: 0.000062 loss: 2.9352 (2.7983) grad_norm: 2.7622 (2.8934) time: 0.5066 [2021-03-27 02:31:32 swin_small_patch4_window7_224] INFO: Epoch: [255] [1160/1251] eta: 0:00:46 lr: 0.000062 loss: 2.7400 (2.7983) grad_norm: 2.7806 (2.8924) time: 0.5033 [2021-03-27 02:31:37 swin_small_patch4_window7_224] INFO: Epoch: [255] [1170/1251] eta: 0:00:41 lr: 0.000062 loss: 2.8590 (2.7997) grad_norm: 2.7806 (2.8912) time: 0.4937 [2021-03-27 02:31:42 swin_small_patch4_window7_224] INFO: Epoch: [255] [1180/1251] eta: 0:00:36 lr: 0.000062 loss: 3.0179 (2.8010) grad_norm: 2.7820 (2.8902) time: 0.4956 [2021-03-27 02:31:47 swin_small_patch4_window7_224] INFO: Epoch: [255] [1190/1251] eta: 0:00:30 lr: 0.000062 loss: 2.9800 (2.8015) grad_norm: 2.7876 (2.8902) time: 0.4973 [2021-03-27 02:31:52 swin_small_patch4_window7_224] INFO: Epoch: [255] [1200/1251] eta: 0:00:25 lr: 0.000062 loss: 2.8251 (2.8006) grad_norm: 2.8704 (2.8905) time: 0.4995 [2021-03-27 02:31:57 swin_small_patch4_window7_224] INFO: Epoch: [255] [1210/1251] eta: 0:00:20 lr: 0.000062 loss: 2.7009 (2.8003) grad_norm: 2.7832 (2.8910) time: 0.5078 [2021-03-27 02:32:02 swin_small_patch4_window7_224] INFO: Epoch: [255] [1220/1251] eta: 0:00:15 lr: 0.000062 loss: 2.8927 (2.7997) grad_norm: 2.7109 (2.8897) time: 0.5078 [2021-03-27 02:32:07 swin_small_patch4_window7_224] INFO: Epoch: [255] [1230/1251] eta: 0:00:10 lr: 0.000062 loss: 2.8196 (2.7992) grad_norm: 2.6848 (2.8886) time: 0.5015 [2021-03-27 02:32:12 swin_small_patch4_window7_224] INFO: Epoch: [255] [1240/1251] eta: 0:00:05 lr: 0.000062 loss: 2.8041 (2.7986) grad_norm: 2.7851 (2.8882) time: 0.4976 [2021-03-27 02:32:17 swin_small_patch4_window7_224] INFO: Epoch: [255] [1250/1251] eta: 0:00:00 lr: 0.000062 loss: 2.9451 (2.8000) grad_norm: 2.8682 (2.8879) time: 0.4968 [2021-03-27 02:33:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:14 loss: 0.8996 (0.8996) acc1: 79.6875 (79.6875) acc5: 98.4375 (98.4375) [2021-03-27 02:33:06 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7162 (0.7922) acc1: 81.2500 (80.8239) acc5: 96.8750 (96.1648) [2021-03-27 02:33:07 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7162 (0.7505) acc1: 81.2500 (81.3988) acc5: 96.8750 (96.5030) [2021-03-27 02:33:08 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7459 (0.7817) acc1: 79.6875 (81.1996) acc5: 96.8750 (96.2702) [2021-03-27 02:33:09 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7027 (0.7682) acc1: 82.8125 (81.7454) acc5: 95.3125 (96.3034) [2021-03-27 02:33:10 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6922 (0.7593) acc1: 84.3750 (81.9520) acc5: 96.8750 (96.1600) [2021-03-27 02:33:24 swin_small_patch4_window7_224] INFO: * Acc@1 82.482 Acc@5 96.200 loss 0.752 [2021-03-27 02:33:24 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-27 02:33:24 swin_small_patch4_window7_224] INFO: Max accuracy: 82.48% [2021-03-27 02:33:28 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 0/1251] eta: 1:25:31 lr: 0.000062 loss: 3.5598 (3.5598) grad_norm: 2.5510 (2.5510) time: 4.1019 [2021-03-27 02:33:33 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 10/1251] eta: 0:17:28 lr: 0.000062 loss: 3.1214 (3.0448) grad_norm: 2.9441 (2.9174) time: 0.8447 [2021-03-27 02:33:38 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 20/1251] eta: 0:13:58 lr: 0.000062 loss: 2.9305 (2.8797) grad_norm: 2.7476 (2.8477) time: 0.5104 [2021-03-27 02:33:43 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 30/1251] eta: 0:12:46 lr: 0.000062 loss: 2.8357 (2.8525) grad_norm: 2.7091 (2.8795) time: 0.5080 [2021-03-27 02:33:48 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 40/1251] eta: 0:12:04 lr: 0.000062 loss: 2.8621 (2.8139) grad_norm: 2.8569 (2.9458) time: 0.5113 [2021-03-27 02:33:53 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 50/1251] eta: 0:11:37 lr: 0.000062 loss: 2.7199 (2.7469) grad_norm: 2.9927 (2.9565) time: 0.5080 [2021-03-27 02:33:58 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 60/1251] eta: 0:11:16 lr: 0.000062 loss: 2.4799 (2.7165) grad_norm: 2.9338 (2.9709) time: 0.5050 [2021-03-27 02:34:03 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 70/1251] eta: 0:10:58 lr: 0.000061 loss: 2.8167 (2.7254) grad_norm: 2.9444 (2.9766) time: 0.4993 [2021-03-27 02:34:08 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 80/1251] eta: 0:10:43 lr: 0.000061 loss: 2.9754 (2.7481) grad_norm: 2.9276 (2.9574) time: 0.4937 [2021-03-27 02:34:13 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 90/1251] eta: 0:10:32 lr: 0.000061 loss: 2.9935 (2.7518) grad_norm: 2.8099 (2.9414) time: 0.4977 [2021-03-27 02:34:18 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 100/1251] eta: 0:10:21 lr: 0.000061 loss: 2.7247 (2.7264) grad_norm: 2.7101 (2.9125) time: 0.5028 [2021-03-27 02:34:23 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 110/1251] eta: 0:10:13 lr: 0.000061 loss: 2.7247 (2.7300) grad_norm: 2.5875 (2.8937) time: 0.5050 [2021-03-27 02:34:28 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 120/1251] eta: 0:10:04 lr: 0.000061 loss: 2.9281 (2.7293) grad_norm: 2.6896 (2.8851) time: 0.5072 [2021-03-27 02:34:33 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 130/1251] eta: 0:09:56 lr: 0.000061 loss: 2.8820 (2.7365) grad_norm: 2.7018 (2.8949) time: 0.5040 [2021-03-27 02:34:39 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 140/1251] eta: 0:09:50 lr: 0.000061 loss: 2.8364 (2.7464) grad_norm: 2.8068 (2.8915) time: 0.5126 [2021-03-27 02:34:44 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 150/1251] eta: 0:09:42 lr: 0.000061 loss: 2.9175 (2.7601) grad_norm: 2.6716 (2.8893) time: 0.5104 [2021-03-27 02:34:49 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 160/1251] eta: 0:09:35 lr: 0.000061 loss: 2.9204 (2.7701) grad_norm: 2.9027 (2.8866) time: 0.5020 [2021-03-27 02:34:54 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 170/1251] eta: 0:09:28 lr: 0.000061 loss: 2.7759 (2.7669) grad_norm: 2.5995 (2.8703) time: 0.5020 [2021-03-27 02:34:59 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 180/1251] eta: 0:09:22 lr: 0.000061 loss: 2.7741 (2.7693) grad_norm: 2.6413 (2.8687) time: 0.5066 [2021-03-27 02:35:04 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 190/1251] eta: 0:09:15 lr: 0.000061 loss: 2.7741 (2.7713) grad_norm: 2.7770 (2.8753) time: 0.5037 [2021-03-27 02:35:09 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 200/1251] eta: 0:09:10 lr: 0.000061 loss: 2.7367 (2.7706) grad_norm: 2.7770 (2.8697) time: 0.5048 [2021-03-27 02:35:14 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 210/1251] eta: 0:09:03 lr: 0.000061 loss: 2.7012 (2.7641) grad_norm: 2.7741 (2.8732) time: 0.5085 [2021-03-27 02:35:19 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 220/1251] eta: 0:08:58 lr: 0.000061 loss: 2.8453 (2.7697) grad_norm: 2.8949 (2.8769) time: 0.5089 [2021-03-27 02:35:24 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 230/1251] eta: 0:08:52 lr: 0.000061 loss: 2.9687 (2.7697) grad_norm: 2.9010 (2.8844) time: 0.5073 [2021-03-27 02:35:29 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 240/1251] eta: 0:08:45 lr: 0.000061 loss: 2.9262 (2.7694) grad_norm: 2.8019 (2.9127) time: 0.4965 [2021-03-27 02:35:34 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 250/1251] eta: 0:08:40 lr: 0.000061 loss: 2.7335 (2.7601) grad_norm: 2.7525 (2.9093) time: 0.5019 [2021-03-27 02:35:39 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 260/1251] eta: 0:08:34 lr: 0.000061 loss: 2.7945 (2.7696) grad_norm: 2.7612 (2.9081) time: 0.5037 [2021-03-27 02:35:44 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 270/1251] eta: 0:08:28 lr: 0.000061 loss: 2.9395 (2.7646) grad_norm: 2.8469 (2.9042) time: 0.5058 [2021-03-27 02:35:49 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 280/1251] eta: 0:08:22 lr: 0.000061 loss: 2.8664 (2.7675) grad_norm: 2.8704 (2.9040) time: 0.5042 [2021-03-27 02:35:54 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 290/1251] eta: 0:08:16 lr: 0.000061 loss: 2.8360 (2.7628) grad_norm: 2.8830 (2.9044) time: 0.4955 [2021-03-27 02:35:59 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 300/1251] eta: 0:08:11 lr: 0.000061 loss: 2.8816 (2.7730) grad_norm: 2.8392 (2.9023) time: 0.4997 [2021-03-27 02:36:04 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 310/1251] eta: 0:08:05 lr: 0.000061 loss: 2.9503 (2.7713) grad_norm: 2.7270 (2.8990) time: 0.4998 [2021-03-27 02:36:09 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 320/1251] eta: 0:07:59 lr: 0.000061 loss: 2.7873 (2.7742) grad_norm: 2.7728 (2.9013) time: 0.4946 [2021-03-27 02:36:14 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 330/1251] eta: 0:07:54 lr: 0.000061 loss: 2.8141 (2.7772) grad_norm: 2.8224 (2.8975) time: 0.5060 [2021-03-27 02:36:19 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 340/1251] eta: 0:07:48 lr: 0.000061 loss: 2.8923 (2.7810) grad_norm: 2.8951 (2.9054) time: 0.5080 [2021-03-27 02:36:24 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 350/1251] eta: 0:07:43 lr: 0.000061 loss: 2.9378 (2.7895) grad_norm: 3.0029 (2.9112) time: 0.5023 [2021-03-27 02:36:29 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 360/1251] eta: 0:07:38 lr: 0.000061 loss: 2.9378 (2.7909) grad_norm: 2.6606 (2.9077) time: 0.5035 [2021-03-27 02:36:34 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 370/1251] eta: 0:07:32 lr: 0.000061 loss: 2.7710 (2.7901) grad_norm: 2.6507 (2.9042) time: 0.5028 [2021-03-27 02:36:39 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 380/1251] eta: 0:07:27 lr: 0.000061 loss: 2.9979 (2.7987) grad_norm: 2.7889 (2.9053) time: 0.5053 [2021-03-27 02:36:44 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 390/1251] eta: 0:07:21 lr: 0.000061 loss: 2.9979 (2.7961) grad_norm: 2.8196 (2.9058) time: 0.5018 [2021-03-27 02:36:49 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 400/1251] eta: 0:07:16 lr: 0.000061 loss: 2.8116 (2.7926) grad_norm: 2.8598 (2.9079) time: 0.4989 [2021-03-27 02:36:54 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 410/1251] eta: 0:07:11 lr: 0.000061 loss: 3.0325 (2.7945) grad_norm: 2.8666 (2.9120) time: 0.5025 [2021-03-27 02:36:59 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 420/1251] eta: 0:07:05 lr: 0.000061 loss: 2.8179 (2.7917) grad_norm: 2.8423 (2.9087) time: 0.4998 [2021-03-27 02:37:04 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 430/1251] eta: 0:07:00 lr: 0.000061 loss: 2.7737 (2.7953) grad_norm: 2.7981 (2.9100) time: 0.4964 [2021-03-27 02:37:09 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 440/1251] eta: 0:06:54 lr: 0.000061 loss: 2.9788 (2.7940) grad_norm: 2.7559 (2.9092) time: 0.4951 [2021-03-27 02:37:14 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 450/1251] eta: 0:06:49 lr: 0.000061 loss: 2.9788 (2.7981) grad_norm: 2.8066 (2.9092) time: 0.4994 [2021-03-27 02:37:19 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 460/1251] eta: 0:06:44 lr: 0.000061 loss: 2.9302 (2.7940) grad_norm: 2.8066 (2.9065) time: 0.5079 [2021-03-27 02:37:24 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 470/1251] eta: 0:06:39 lr: 0.000061 loss: 2.8351 (2.7989) grad_norm: 2.8204 (2.9111) time: 0.5016 [2021-03-27 02:37:29 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 480/1251] eta: 0:06:33 lr: 0.000061 loss: 3.0046 (2.8005) grad_norm: 3.0278 (2.9107) time: 0.4931 [2021-03-27 02:37:34 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 490/1251] eta: 0:06:28 lr: 0.000061 loss: 2.9975 (2.8016) grad_norm: 2.8341 (2.9095) time: 0.4956 [2021-03-27 02:37:39 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 500/1251] eta: 0:06:23 lr: 0.000061 loss: 2.9816 (2.8031) grad_norm: 2.7253 (2.9096) time: 0.5022 [2021-03-27 02:37:44 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 510/1251] eta: 0:06:18 lr: 0.000061 loss: 2.9816 (2.8030) grad_norm: 2.9055 (2.9389) time: 0.5086 [2021-03-27 02:37:49 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 520/1251] eta: 0:06:13 lr: 0.000061 loss: 2.9524 (2.8031) grad_norm: 2.8224 (2.9349) time: 0.5098 [2021-03-27 02:37:54 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 530/1251] eta: 0:06:07 lr: 0.000061 loss: 2.9050 (2.8043) grad_norm: 2.8224 (2.9338) time: 0.5023 [2021-03-27 02:37:59 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 540/1251] eta: 0:06:02 lr: 0.000061 loss: 2.9050 (2.8028) grad_norm: 2.7905 (2.9298) time: 0.4970 [2021-03-27 02:38:05 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 550/1251] eta: 0:05:57 lr: 0.000061 loss: 2.6143 (2.7978) grad_norm: 2.7133 (2.9375) time: 0.5062 [2021-03-27 02:38:10 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 560/1251] eta: 0:05:52 lr: 0.000061 loss: 2.5694 (2.7949) grad_norm: 2.9414 (2.9393) time: 0.5072 [2021-03-27 02:38:15 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 570/1251] eta: 0:05:46 lr: 0.000061 loss: 2.8530 (2.7906) grad_norm: 2.6545 (2.9366) time: 0.4993 [2021-03-27 02:38:20 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 580/1251] eta: 0:05:41 lr: 0.000061 loss: 2.8622 (2.7936) grad_norm: 2.6266 (2.9346) time: 0.5034 [2021-03-27 02:38:25 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 590/1251] eta: 0:05:36 lr: 0.000061 loss: 2.8810 (2.7946) grad_norm: 2.7562 (2.9372) time: 0.5102 [2021-03-27 02:38:30 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 600/1251] eta: 0:05:31 lr: 0.000061 loss: 2.9656 (2.7951) grad_norm: 2.7687 (2.9367) time: 0.5047 [2021-03-27 02:38:35 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 610/1251] eta: 0:05:26 lr: 0.000061 loss: 2.8197 (2.7942) grad_norm: 2.7721 (2.9332) time: 0.4958 [2021-03-27 02:38:40 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 620/1251] eta: 0:05:21 lr: 0.000060 loss: 2.8943 (2.7975) grad_norm: 2.7966 (2.9422) time: 0.4955 [2021-03-27 02:38:45 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 630/1251] eta: 0:05:15 lr: 0.000060 loss: 3.0511 (2.8015) grad_norm: 2.9064 (2.9413) time: 0.5020 [2021-03-27 02:38:50 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 640/1251] eta: 0:05:10 lr: 0.000060 loss: 3.0049 (2.7985) grad_norm: 2.8400 (2.9395) time: 0.5043 [2021-03-27 02:38:55 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 650/1251] eta: 0:05:05 lr: 0.000060 loss: 2.5090 (2.7952) grad_norm: 2.8400 (2.9397) time: 0.5016 [2021-03-27 02:39:00 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 660/1251] eta: 0:05:00 lr: 0.000060 loss: 2.6043 (2.7925) grad_norm: 2.9321 (2.9418) time: 0.4977 [2021-03-27 02:39:05 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 670/1251] eta: 0:04:55 lr: 0.000060 loss: 2.7711 (2.7914) grad_norm: 2.9321 (2.9428) time: 0.4967 [2021-03-27 02:39:10 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 680/1251] eta: 0:04:50 lr: 0.000060 loss: 2.8964 (2.7939) grad_norm: 2.8927 (2.9407) time: 0.5011 [2021-03-27 02:39:15 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 690/1251] eta: 0:04:45 lr: 0.000060 loss: 2.8799 (2.7953) grad_norm: 2.6206 (2.9370) time: 0.5043 [2021-03-27 02:39:20 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 700/1251] eta: 0:04:39 lr: 0.000060 loss: 2.8582 (2.7953) grad_norm: 2.6206 (2.9352) time: 0.5052 [2021-03-27 02:39:25 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 710/1251] eta: 0:04:34 lr: 0.000060 loss: 2.8774 (2.7975) grad_norm: 2.6501 (2.9318) time: 0.5023 [2021-03-27 02:39:30 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 720/1251] eta: 0:04:29 lr: 0.000060 loss: 2.8774 (2.7938) grad_norm: 2.6946 (nan) time: 0.4991 [2021-03-27 02:39:35 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 730/1251] eta: 0:04:24 lr: 0.000060 loss: 2.7246 (2.7950) grad_norm: 2.7469 (nan) time: 0.5025 [2021-03-27 02:39:40 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 740/1251] eta: 0:04:19 lr: 0.000060 loss: 2.9382 (2.7969) grad_norm: 2.7579 (nan) time: 0.5141 [2021-03-27 02:39:45 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 750/1251] eta: 0:04:14 lr: 0.000060 loss: 2.8438 (2.7966) grad_norm: 2.6971 (nan) time: 0.5251 [2021-03-27 02:39:50 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 760/1251] eta: 0:04:09 lr: 0.000060 loss: 2.7050 (2.7948) grad_norm: 2.6706 (nan) time: 0.5106 [2021-03-27 02:39:55 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 770/1251] eta: 0:04:04 lr: 0.000060 loss: 2.7050 (2.7954) grad_norm: 2.8370 (nan) time: 0.4981 [2021-03-27 02:40:00 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 780/1251] eta: 0:03:59 lr: 0.000060 loss: 2.9421 (2.7978) grad_norm: 2.7378 (nan) time: 0.4996 [2021-03-27 02:40:05 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 790/1251] eta: 0:03:54 lr: 0.000060 loss: 2.9044 (2.7951) grad_norm: 2.6873 (nan) time: 0.4953 [2021-03-27 02:40:10 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 800/1251] eta: 0:03:48 lr: 0.000060 loss: 2.8040 (2.7950) grad_norm: 2.6716 (nan) time: 0.4977 [2021-03-27 02:40:15 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 810/1251] eta: 0:03:43 lr: 0.000060 loss: 2.8154 (2.7932) grad_norm: 2.7200 (nan) time: 0.4976 [2021-03-27 02:40:20 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 820/1251] eta: 0:03:38 lr: 0.000060 loss: 2.8154 (2.7937) grad_norm: 2.6502 (nan) time: 0.4950 [2021-03-27 02:40:25 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 830/1251] eta: 0:03:33 lr: 0.000060 loss: 2.8063 (2.7933) grad_norm: 2.7613 (nan) time: 0.5035 [2021-03-27 02:40:30 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 840/1251] eta: 0:03:28 lr: 0.000060 loss: 2.7216 (2.7925) grad_norm: 2.7977 (nan) time: 0.5048 [2021-03-27 02:40:35 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 850/1251] eta: 0:03:23 lr: 0.000060 loss: 2.6432 (2.7905) grad_norm: 2.6693 (nan) time: 0.5012 [2021-03-27 02:40:40 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 860/1251] eta: 0:03:18 lr: 0.000060 loss: 2.8151 (2.7934) grad_norm: 2.6905 (nan) time: 0.5047 [2021-03-27 02:40:45 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 870/1251] eta: 0:03:13 lr: 0.000060 loss: 2.9639 (2.7927) grad_norm: 2.8502 (nan) time: 0.4992 [2021-03-27 02:40:50 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 880/1251] eta: 0:03:08 lr: 0.000060 loss: 2.8335 (2.7928) grad_norm: 2.7952 (nan) time: 0.5017 [2021-03-27 02:40:56 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 890/1251] eta: 0:03:03 lr: 0.000060 loss: 2.9003 (2.7944) grad_norm: 2.7108 (nan) time: 0.5096 [2021-03-27 02:41:01 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 900/1251] eta: 0:02:57 lr: 0.000060 loss: 2.9587 (2.7935) grad_norm: 2.6772 (nan) time: 0.5091 [2021-03-27 02:41:06 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 910/1251] eta: 0:02:52 lr: 0.000060 loss: 2.8926 (2.7929) grad_norm: 2.9276 (nan) time: 0.5045 [2021-03-27 02:41:11 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 920/1251] eta: 0:02:47 lr: 0.000060 loss: 2.7271 (2.7884) grad_norm: 2.8425 (nan) time: 0.5032 [2021-03-27 02:41:16 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 930/1251] eta: 0:02:42 lr: 0.000060 loss: 2.7420 (2.7885) grad_norm: 2.8425 (nan) time: 0.5090 [2021-03-27 02:41:21 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 940/1251] eta: 0:02:37 lr: 0.000060 loss: 2.9571 (2.7895) grad_norm: 2.9936 (nan) time: 0.5166 [2021-03-27 02:41:26 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 950/1251] eta: 0:02:32 lr: 0.000060 loss: 2.9571 (2.7906) grad_norm: 2.9626 (nan) time: 0.5082 [2021-03-27 02:41:31 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 960/1251] eta: 0:02:27 lr: 0.000060 loss: 2.9750 (2.7906) grad_norm: 2.8080 (nan) time: 0.5024 [2021-03-27 02:41:36 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 970/1251] eta: 0:02:22 lr: 0.000060 loss: 2.9373 (2.7910) grad_norm: 2.7716 (nan) time: 0.5043 [2021-03-27 02:41:41 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 980/1251] eta: 0:02:17 lr: 0.000060 loss: 2.8424 (2.7905) grad_norm: 2.9154 (nan) time: 0.4989 [2021-03-27 02:41:46 swin_small_patch4_window7_224] INFO: Epoch: [256] [ 990/1251] eta: 0:02:12 lr: 0.000060 loss: 2.7976 (2.7902) grad_norm: 2.9504 (nan) time: 0.4979 [2021-03-27 02:41:51 swin_small_patch4_window7_224] INFO: Epoch: [256] [1000/1251] eta: 0:02:07 lr: 0.000060 loss: 2.7884 (2.7914) grad_norm: 2.9654 (nan) time: 0.4974 [2021-03-27 02:41:56 swin_small_patch4_window7_224] INFO: Epoch: [256] [1010/1251] eta: 0:02:02 lr: 0.000060 loss: 2.7660 (2.7916) grad_norm: 2.8298 (nan) time: 0.5002 [2021-03-27 02:42:01 swin_small_patch4_window7_224] INFO: Epoch: [256] [1020/1251] eta: 0:01:57 lr: 0.000060 loss: 2.9403 (2.7931) grad_norm: 2.8298 (nan) time: 0.5035 [2021-03-27 02:42:06 swin_small_patch4_window7_224] INFO: Epoch: [256] [1030/1251] eta: 0:01:51 lr: 0.000060 loss: 2.9776 (2.7938) grad_norm: 2.7822 (nan) time: 0.5012 [2021-03-27 02:42:11 swin_small_patch4_window7_224] INFO: Epoch: [256] [1040/1251] eta: 0:01:46 lr: 0.000060 loss: 2.8474 (2.7946) grad_norm: 2.6888 (nan) time: 0.5048 [2021-03-27 02:42:16 swin_small_patch4_window7_224] INFO: Epoch: [256] [1050/1251] eta: 0:01:41 lr: 0.000060 loss: 2.8474 (2.7951) grad_norm: 2.7123 (nan) time: 0.5092 [2021-03-27 02:42:21 swin_small_patch4_window7_224] INFO: Epoch: [256] [1060/1251] eta: 0:01:36 lr: 0.000060 loss: 2.8299 (2.7938) grad_norm: 2.7123 (nan) time: 0.5059 [2021-03-27 02:42:26 swin_small_patch4_window7_224] INFO: Epoch: [256] [1070/1251] eta: 0:01:31 lr: 0.000060 loss: 2.8354 (2.7937) grad_norm: 2.7737 (nan) time: 0.5031 [2021-03-27 02:42:31 swin_small_patch4_window7_224] INFO: Epoch: [256] [1080/1251] eta: 0:01:26 lr: 0.000060 loss: 2.9861 (2.7956) grad_norm: 2.9289 (nan) time: 0.5071 [2021-03-27 02:42:36 swin_small_patch4_window7_224] INFO: Epoch: [256] [1090/1251] eta: 0:01:21 lr: 0.000060 loss: 2.9971 (2.7966) grad_norm: 2.7020 (nan) time: 0.5053 [2021-03-27 02:42:42 swin_small_patch4_window7_224] INFO: Epoch: [256] [1100/1251] eta: 0:01:16 lr: 0.000060 loss: 2.9117 (2.7968) grad_norm: 2.6908 (nan) time: 0.5049 [2021-03-27 02:42:47 swin_small_patch4_window7_224] INFO: Epoch: [256] [1110/1251] eta: 0:01:11 lr: 0.000060 loss: 2.9041 (2.7977) grad_norm: 2.7761 (nan) time: 0.5113 [2021-03-27 02:42:52 swin_small_patch4_window7_224] INFO: Epoch: [256] [1120/1251] eta: 0:01:06 lr: 0.000060 loss: 2.9041 (2.7976) grad_norm: 2.7545 (nan) time: 0.5063 [2021-03-27 02:42:57 swin_small_patch4_window7_224] INFO: Epoch: [256] [1130/1251] eta: 0:01:01 lr: 0.000060 loss: 2.6778 (2.7962) grad_norm: 2.6912 (nan) time: 0.4982 [2021-03-27 02:43:02 swin_small_patch4_window7_224] INFO: Epoch: [256] [1140/1251] eta: 0:00:56 lr: 0.000060 loss: 2.6749 (2.7960) grad_norm: 2.6870 (nan) time: 0.5001 [2021-03-27 02:43:07 swin_small_patch4_window7_224] INFO: Epoch: [256] [1150/1251] eta: 0:00:51 lr: 0.000060 loss: 2.7918 (2.7955) grad_norm: 2.6340 (nan) time: 0.5010 [2021-03-27 02:43:12 swin_small_patch4_window7_224] INFO: Epoch: [256] [1160/1251] eta: 0:00:46 lr: 0.000060 loss: 2.7157 (2.7930) grad_norm: 2.5869 (nan) time: 0.4971 [2021-03-27 02:43:17 swin_small_patch4_window7_224] INFO: Epoch: [256] [1170/1251] eta: 0:00:41 lr: 0.000059 loss: 2.7636 (2.7942) grad_norm: 2.6083 (nan) time: 0.5003 [2021-03-27 02:43:22 swin_small_patch4_window7_224] INFO: Epoch: [256] [1180/1251] eta: 0:00:35 lr: 0.000059 loss: 2.9013 (2.7952) grad_norm: 2.8046 (nan) time: 0.5002 [2021-03-27 02:43:27 swin_small_patch4_window7_224] INFO: Epoch: [256] [1190/1251] eta: 0:00:30 lr: 0.000059 loss: 2.8846 (2.7964) grad_norm: 2.7317 (nan) time: 0.5005 [2021-03-27 02:43:32 swin_small_patch4_window7_224] INFO: Epoch: [256] [1200/1251] eta: 0:00:25 lr: 0.000059 loss: 3.0996 (2.7988) grad_norm: 2.7026 (nan) time: 0.4986 [2021-03-27 02:43:37 swin_small_patch4_window7_224] INFO: Epoch: [256] [1210/1251] eta: 0:00:20 lr: 0.000059 loss: 2.9922 (2.7987) grad_norm: 2.6992 (nan) time: 0.4975 [2021-03-27 02:43:42 swin_small_patch4_window7_224] INFO: Epoch: [256] [1220/1251] eta: 0:00:15 lr: 0.000059 loss: 2.9719 (2.7994) grad_norm: 2.8143 (nan) time: 0.5036 [2021-03-27 02:43:47 swin_small_patch4_window7_224] INFO: Epoch: [256] [1230/1251] eta: 0:00:10 lr: 0.000059 loss: 3.0294 (2.8006) grad_norm: 2.7587 (nan) time: 0.4988 [2021-03-27 02:43:52 swin_small_patch4_window7_224] INFO: Epoch: [256] [1240/1251] eta: 0:00:05 lr: 0.000059 loss: 2.9604 (2.8006) grad_norm: 2.6161 (nan) time: 0.4977 [2021-03-27 02:43:57 swin_small_patch4_window7_224] INFO: Epoch: [256] [1250/1251] eta: 0:00:00 lr: 0.000059 loss: 2.8835 (2.8017) grad_norm: 2.7095 (nan) time: 0.5007 [2021-03-27 02:44:09 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:51 loss: 0.6127 (0.6127) acc1: 92.1875 (92.1875) acc5: 96.8750 (96.8750) [2021-03-27 02:44:11 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7134 (0.7154) acc1: 82.8125 (84.2330) acc5: 96.8750 (96.1648) [2021-03-27 02:44:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7371 (0.7503) acc1: 81.2500 (82.8125) acc5: 95.3125 (95.2381) [2021-03-27 02:44:16 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7967 (0.7656) acc1: 82.8125 (82.6613) acc5: 95.3125 (95.5645) [2021-03-27 02:44:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7928 (0.7599) acc1: 81.2500 (82.0884) acc5: 96.8750 (95.9604) [2021-03-27 02:44:18 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7928 (0.7564) acc1: 81.2500 (82.0160) acc5: 96.8750 (96.1280) [2021-03-27 02:44:29 swin_small_patch4_window7_224] INFO: * Acc@1 82.534 Acc@5 96.112 loss 0.751 [2021-03-27 02:44:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-27 02:44:29 swin_small_patch4_window7_224] INFO: Max accuracy: 82.53% [2021-03-27 02:44:33 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 0/1251] eta: 1:28:25 lr: 0.000059 loss: 3.2301 (3.2301) grad_norm: 2.7543 (2.7543) time: 4.2413 [2021-03-27 02:44:39 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 10/1251] eta: 0:17:47 lr: 0.000059 loss: 3.0959 (2.9381) grad_norm: 2.7543 (3.0115) time: 0.8600 [2021-03-27 02:44:44 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 20/1251] eta: 0:14:12 lr: 0.000059 loss: 2.9585 (2.8185) grad_norm: 2.7753 (3.1704) time: 0.5152 [2021-03-27 02:44:49 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 30/1251] eta: 0:12:49 lr: 0.000059 loss: 2.9585 (2.7873) grad_norm: 2.7675 (3.0471) time: 0.5042 [2021-03-27 02:44:54 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 40/1251] eta: 0:12:06 lr: 0.000059 loss: 2.8001 (2.7689) grad_norm: 2.7675 (3.0011) time: 0.5027 [2021-03-27 02:44:59 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 50/1251] eta: 0:11:36 lr: 0.000059 loss: 2.8271 (2.7799) grad_norm: 2.7712 (2.9749) time: 0.5018 [2021-03-27 02:45:04 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 60/1251] eta: 0:11:17 lr: 0.000059 loss: 2.9530 (2.7833) grad_norm: 2.8682 (2.9590) time: 0.5038 [2021-03-27 02:45:09 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 70/1251] eta: 0:11:00 lr: 0.000059 loss: 2.9135 (2.7702) grad_norm: 2.8168 (2.9393) time: 0.5062 [2021-03-27 02:45:14 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 80/1251] eta: 0:10:48 lr: 0.000059 loss: 2.7920 (2.7799) grad_norm: 2.8097 (2.9805) time: 0.5102 [2021-03-27 02:45:19 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 90/1251] eta: 0:10:38 lr: 0.000059 loss: 2.7606 (2.7724) grad_norm: 2.8097 (3.0274) time: 0.5172 [2021-03-27 02:45:24 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 100/1251] eta: 0:10:27 lr: 0.000059 loss: 2.6797 (2.7725) grad_norm: 2.7997 (3.0184) time: 0.5105 [2021-03-27 02:45:29 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 110/1251] eta: 0:10:18 lr: 0.000059 loss: 2.6873 (2.7609) grad_norm: 2.8187 (3.0490) time: 0.5053 [2021-03-27 02:45:34 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 120/1251] eta: 0:10:09 lr: 0.000059 loss: 2.7238 (2.7566) grad_norm: 2.7655 (3.0375) time: 0.5040 [2021-03-27 02:45:39 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 130/1251] eta: 0:10:02 lr: 0.000059 loss: 2.8367 (2.7554) grad_norm: 2.6201 (3.0062) time: 0.5104 [2021-03-27 02:45:45 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 140/1251] eta: 0:09:55 lr: 0.000059 loss: 2.8801 (2.7658) grad_norm: 2.6054 (2.9799) time: 0.5184 [2021-03-27 02:45:50 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 150/1251] eta: 0:09:47 lr: 0.000059 loss: 2.8016 (2.7600) grad_norm: 2.6250 (2.9659) time: 0.5098 [2021-03-27 02:45:55 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 160/1251] eta: 0:09:40 lr: 0.000059 loss: 2.8140 (2.7558) grad_norm: 2.7408 (2.9675) time: 0.5034 [2021-03-27 02:46:00 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 170/1251] eta: 0:09:33 lr: 0.000059 loss: 2.8768 (2.7685) grad_norm: 2.8655 (2.9594) time: 0.5045 [2021-03-27 02:46:05 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 180/1251] eta: 0:09:27 lr: 0.000059 loss: 2.9469 (2.7664) grad_norm: 2.7587 (2.9536) time: 0.5117 [2021-03-27 02:46:10 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 190/1251] eta: 0:09:20 lr: 0.000059 loss: 2.7987 (2.7604) grad_norm: 2.6537 (2.9578) time: 0.5102 [2021-03-27 02:46:15 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 200/1251] eta: 0:09:13 lr: 0.000059 loss: 2.6564 (2.7551) grad_norm: 2.6537 (2.9452) time: 0.5040 [2021-03-27 02:46:20 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 210/1251] eta: 0:09:07 lr: 0.000059 loss: 2.8870 (2.7609) grad_norm: 2.7881 (2.9427) time: 0.5025 [2021-03-27 02:46:25 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 220/1251] eta: 0:09:00 lr: 0.000059 loss: 2.9023 (2.7666) grad_norm: 2.7881 (2.9316) time: 0.4991 [2021-03-27 02:46:30 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 230/1251] eta: 0:08:54 lr: 0.000059 loss: 2.7710 (2.7639) grad_norm: 2.8109 (2.9301) time: 0.5007 [2021-03-27 02:46:35 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 240/1251] eta: 0:08:48 lr: 0.000059 loss: 2.7280 (2.7636) grad_norm: 2.7341 (2.9181) time: 0.5023 [2021-03-27 02:46:40 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 250/1251] eta: 0:08:42 lr: 0.000059 loss: 2.6101 (2.7556) grad_norm: 2.7520 (2.9206) time: 0.5009 [2021-03-27 02:46:45 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 260/1251] eta: 0:08:36 lr: 0.000059 loss: 2.7452 (2.7559) grad_norm: 2.7520 (2.9118) time: 0.5039 [2021-03-27 02:46:50 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 270/1251] eta: 0:08:30 lr: 0.000059 loss: 2.7799 (2.7555) grad_norm: 2.6233 (2.9085) time: 0.5093 [2021-03-27 02:46:55 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 280/1251] eta: 0:08:25 lr: 0.000059 loss: 2.8766 (2.7607) grad_norm: 2.7806 (2.9035) time: 0.5070 [2021-03-27 02:47:01 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 290/1251] eta: 0:08:19 lr: 0.000059 loss: 2.7309 (2.7604) grad_norm: 2.7416 (2.9082) time: 0.5122 [2021-03-27 02:47:06 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 300/1251] eta: 0:08:14 lr: 0.000059 loss: 2.8726 (2.7623) grad_norm: 2.7104 (2.9079) time: 0.5154 [2021-03-27 02:47:11 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 310/1251] eta: 0:08:08 lr: 0.000059 loss: 2.9836 (2.7673) grad_norm: 2.6815 (2.9007) time: 0.5077 [2021-03-27 02:47:16 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 320/1251] eta: 0:08:03 lr: 0.000059 loss: 2.8135 (2.7644) grad_norm: 2.6815 (2.8964) time: 0.5068 [2021-03-27 02:47:21 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 330/1251] eta: 0:07:57 lr: 0.000059 loss: 2.8365 (2.7658) grad_norm: 2.7041 (2.8918) time: 0.5093 [2021-03-27 02:47:26 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 340/1251] eta: 0:07:52 lr: 0.000059 loss: 2.8696 (2.7644) grad_norm: 2.7041 (2.8926) time: 0.5062 [2021-03-27 02:47:31 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 350/1251] eta: 0:07:46 lr: 0.000059 loss: 2.8621 (2.7635) grad_norm: 2.7441 (2.8973) time: 0.5003 [2021-03-27 02:47:36 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 360/1251] eta: 0:07:40 lr: 0.000059 loss: 2.9605 (2.7658) grad_norm: 2.8212 (2.8981) time: 0.4973 [2021-03-27 02:47:41 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 370/1251] eta: 0:07:35 lr: 0.000059 loss: 2.9605 (2.7630) grad_norm: 2.6854 (2.8890) time: 0.4992 [2021-03-27 02:47:46 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 380/1251] eta: 0:07:29 lr: 0.000059 loss: 2.8808 (2.7676) grad_norm: 2.6141 (2.8865) time: 0.5028 [2021-03-27 02:47:51 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 390/1251] eta: 0:07:24 lr: 0.000059 loss: 2.9164 (2.7682) grad_norm: 2.5879 (2.8804) time: 0.5035 [2021-03-27 02:47:56 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 400/1251] eta: 0:07:18 lr: 0.000059 loss: 2.5893 (2.7626) grad_norm: 2.8282 (2.8979) time: 0.5041 [2021-03-27 02:48:01 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 410/1251] eta: 0:07:13 lr: 0.000059 loss: 2.6958 (2.7633) grad_norm: 2.8015 (2.9012) time: 0.5012 [2021-03-27 02:48:06 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 420/1251] eta: 0:07:07 lr: 0.000059 loss: 2.8251 (2.7640) grad_norm: 2.8015 (2.9197) time: 0.5008 [2021-03-27 02:48:11 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 430/1251] eta: 0:07:02 lr: 0.000059 loss: 2.8251 (2.7622) grad_norm: 2.8110 (2.9163) time: 0.5033 [2021-03-27 02:48:16 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 440/1251] eta: 0:06:57 lr: 0.000059 loss: 2.7710 (2.7618) grad_norm: 2.8014 (2.9218) time: 0.5048 [2021-03-27 02:48:21 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 450/1251] eta: 0:06:51 lr: 0.000059 loss: 2.8796 (2.7634) grad_norm: 3.0100 (2.9259) time: 0.5051 [2021-03-27 02:48:26 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 460/1251] eta: 0:06:46 lr: 0.000059 loss: 2.9165 (2.7631) grad_norm: 2.7608 (2.9232) time: 0.5087 [2021-03-27 02:48:31 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 470/1251] eta: 0:06:41 lr: 0.000058 loss: 2.9165 (2.7678) grad_norm: 2.6910 (2.9177) time: 0.5054 [2021-03-27 02:48:36 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 480/1251] eta: 0:06:36 lr: 0.000058 loss: 2.8939 (2.7671) grad_norm: 2.7305 (2.9169) time: 0.4994 [2021-03-27 02:48:41 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 490/1251] eta: 0:06:30 lr: 0.000058 loss: 2.7123 (2.7644) grad_norm: 2.7305 (2.9147) time: 0.5064 [2021-03-27 02:48:46 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 500/1251] eta: 0:06:25 lr: 0.000058 loss: 2.7676 (2.7646) grad_norm: 2.6327 (2.9072) time: 0.5084 [2021-03-27 02:48:51 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 510/1251] eta: 0:06:20 lr: 0.000058 loss: 2.9431 (2.7687) grad_norm: 2.6257 (2.9152) time: 0.5020 [2021-03-27 02:48:56 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 520/1251] eta: 0:06:14 lr: 0.000058 loss: 2.9943 (2.7719) grad_norm: 2.8220 (2.9156) time: 0.5004 [2021-03-27 02:49:02 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 530/1251] eta: 0:06:09 lr: 0.000058 loss: 2.9845 (2.7714) grad_norm: 2.8220 (2.9136) time: 0.5057 [2021-03-27 02:49:07 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 540/1251] eta: 0:06:04 lr: 0.000058 loss: 2.8051 (2.7703) grad_norm: 2.8399 (2.9145) time: 0.5030 [2021-03-27 02:49:12 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 550/1251] eta: 0:05:59 lr: 0.000058 loss: 2.8288 (2.7727) grad_norm: 2.8399 (2.9141) time: 0.5172 [2021-03-27 02:49:17 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 560/1251] eta: 0:05:54 lr: 0.000058 loss: 2.8812 (2.7734) grad_norm: 2.6733 (2.9109) time: 0.5230 [2021-03-27 02:49:22 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 570/1251] eta: 0:05:49 lr: 0.000058 loss: 2.8543 (2.7755) grad_norm: 2.6459 (2.9095) time: 0.5107 [2021-03-27 02:49:27 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 580/1251] eta: 0:05:44 lr: 0.000058 loss: 2.7328 (2.7752) grad_norm: 2.7408 (2.9065) time: 0.5054 [2021-03-27 02:49:32 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 590/1251] eta: 0:05:38 lr: 0.000058 loss: 2.7892 (2.7735) grad_norm: 2.7300 (2.9018) time: 0.5067 [2021-03-27 02:49:37 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 600/1251] eta: 0:05:33 lr: 0.000058 loss: 2.7127 (2.7724) grad_norm: 2.6436 (2.8994) time: 0.5109 [2021-03-27 02:49:42 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 610/1251] eta: 0:05:28 lr: 0.000058 loss: 2.6107 (2.7683) grad_norm: 2.7920 (2.8976) time: 0.5051 [2021-03-27 02:49:47 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 620/1251] eta: 0:05:23 lr: 0.000058 loss: 2.6341 (2.7677) grad_norm: 2.7059 (2.9024) time: 0.5005 [2021-03-27 02:49:52 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 630/1251] eta: 0:05:18 lr: 0.000058 loss: 2.8143 (2.7662) grad_norm: 2.6762 (2.9034) time: 0.5016 [2021-03-27 02:49:57 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 640/1251] eta: 0:05:12 lr: 0.000058 loss: 2.8485 (2.7663) grad_norm: 3.0036 (2.9052) time: 0.5084 [2021-03-27 02:50:03 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 650/1251] eta: 0:05:07 lr: 0.000058 loss: 2.9421 (2.7702) grad_norm: 3.0248 (2.9052) time: 0.5137 [2021-03-27 02:50:08 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 660/1251] eta: 0:05:02 lr: 0.000058 loss: 2.9830 (2.7743) grad_norm: 2.8317 (2.9042) time: 0.5073 [2021-03-27 02:50:13 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 670/1251] eta: 0:04:57 lr: 0.000058 loss: 2.8435 (2.7728) grad_norm: 2.7529 (2.9143) time: 0.5001 [2021-03-27 02:50:18 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 680/1251] eta: 0:04:52 lr: 0.000058 loss: 2.7606 (2.7722) grad_norm: 2.8111 (2.9138) time: 0.5027 [2021-03-27 02:50:23 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 690/1251] eta: 0:04:47 lr: 0.000058 loss: 3.0140 (2.7772) grad_norm: 2.7311 (2.9198) time: 0.5064 [2021-03-27 02:50:28 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 700/1251] eta: 0:04:41 lr: 0.000058 loss: 3.1082 (2.7785) grad_norm: 2.7869 (2.9202) time: 0.5082 [2021-03-27 02:50:33 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 710/1251] eta: 0:04:36 lr: 0.000058 loss: 2.7327 (2.7743) grad_norm: 2.9565 (2.9196) time: 0.5073 [2021-03-27 02:50:38 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 720/1251] eta: 0:04:31 lr: 0.000058 loss: 2.6935 (2.7750) grad_norm: 2.8230 (2.9195) time: 0.5028 [2021-03-27 02:50:43 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 730/1251] eta: 0:04:26 lr: 0.000058 loss: 2.7685 (2.7772) grad_norm: 2.9046 (2.9220) time: 0.5047 [2021-03-27 02:50:48 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 740/1251] eta: 0:04:21 lr: 0.000058 loss: 2.8840 (2.7799) grad_norm: 3.0084 (2.9223) time: 0.5198 [2021-03-27 02:50:54 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 750/1251] eta: 0:04:16 lr: 0.000058 loss: 2.8840 (2.7794) grad_norm: 2.9322 (2.9216) time: 0.5263 [2021-03-27 02:50:59 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 760/1251] eta: 0:04:11 lr: 0.000058 loss: 2.8706 (2.7807) grad_norm: 2.7954 (2.9215) time: 0.5173 [2021-03-27 02:51:04 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 770/1251] eta: 0:04:06 lr: 0.000058 loss: 2.8837 (2.7810) grad_norm: 2.7214 (2.9189) time: 0.5052 [2021-03-27 02:51:09 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 780/1251] eta: 0:04:00 lr: 0.000058 loss: 2.9056 (2.7840) grad_norm: 2.6941 (2.9169) time: 0.5002 [2021-03-27 02:51:14 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 790/1251] eta: 0:03:55 lr: 0.000058 loss: 2.9089 (2.7846) grad_norm: 2.7976 (2.9154) time: 0.5024 [2021-03-27 02:51:19 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 800/1251] eta: 0:03:50 lr: 0.000058 loss: 2.8638 (2.7836) grad_norm: 2.7730 (2.9142) time: 0.5112 [2021-03-27 02:51:24 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 810/1251] eta: 0:03:45 lr: 0.000058 loss: 2.8782 (2.7846) grad_norm: 2.7141 (2.9152) time: 0.5135 [2021-03-27 02:51:29 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 820/1251] eta: 0:03:40 lr: 0.000058 loss: 2.7616 (2.7832) grad_norm: 2.7141 (2.9128) time: 0.5065 [2021-03-27 02:51:34 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 830/1251] eta: 0:03:35 lr: 0.000058 loss: 2.7485 (2.7839) grad_norm: 2.7131 (2.9091) time: 0.5058 [2021-03-27 02:51:39 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 840/1251] eta: 0:03:30 lr: 0.000058 loss: 2.8619 (2.7854) grad_norm: 2.6844 (2.9072) time: 0.5116 [2021-03-27 02:51:44 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 850/1251] eta: 0:03:24 lr: 0.000058 loss: 2.8619 (2.7854) grad_norm: 2.6844 (2.9062) time: 0.5086 [2021-03-27 02:51:49 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 860/1251] eta: 0:03:19 lr: 0.000058 loss: 2.6388 (2.7836) grad_norm: 2.9377 (2.9088) time: 0.5056 [2021-03-27 02:51:54 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 870/1251] eta: 0:03:14 lr: 0.000058 loss: 2.8994 (2.7853) grad_norm: 2.8378 (2.9069) time: 0.5068 [2021-03-27 02:51:59 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 880/1251] eta: 0:03:09 lr: 0.000058 loss: 2.9550 (2.7860) grad_norm: 2.6890 (2.9050) time: 0.5044 [2021-03-27 02:52:05 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 890/1251] eta: 0:03:04 lr: 0.000058 loss: 2.9550 (2.7878) grad_norm: 2.7127 (2.9054) time: 0.5052 [2021-03-27 02:52:10 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 900/1251] eta: 0:02:59 lr: 0.000058 loss: 2.9994 (2.7889) grad_norm: 2.8856 (2.9070) time: 0.5025 [2021-03-27 02:52:15 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 910/1251] eta: 0:02:54 lr: 0.000058 loss: 2.8823 (2.7883) grad_norm: 3.0163 (2.9117) time: 0.5025 [2021-03-27 02:52:20 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 920/1251] eta: 0:02:49 lr: 0.000058 loss: 2.8493 (2.7898) grad_norm: 2.9676 (2.9108) time: 0.5045 [2021-03-27 02:52:25 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 930/1251] eta: 0:02:43 lr: 0.000058 loss: 2.8493 (2.7893) grad_norm: 2.8072 (2.9107) time: 0.5025 [2021-03-27 02:52:30 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 940/1251] eta: 0:02:38 lr: 0.000058 loss: 2.8111 (2.7894) grad_norm: 2.7601 (2.9107) time: 0.4991 [2021-03-27 02:52:35 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 950/1251] eta: 0:02:33 lr: 0.000058 loss: 2.7840 (2.7884) grad_norm: 2.6965 (2.9101) time: 0.5019 [2021-03-27 02:52:40 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 960/1251] eta: 0:02:28 lr: 0.000058 loss: 2.7256 (2.7879) grad_norm: 2.7938 (2.9103) time: 0.5033 [2021-03-27 02:52:45 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 970/1251] eta: 0:02:23 lr: 0.000058 loss: 2.8886 (2.7893) grad_norm: 2.8267 (2.9093) time: 0.5046 [2021-03-27 02:52:50 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 980/1251] eta: 0:02:18 lr: 0.000058 loss: 2.9678 (2.7884) grad_norm: 2.7772 (2.9078) time: 0.5028 [2021-03-27 02:52:55 swin_small_patch4_window7_224] INFO: Epoch: [257] [ 990/1251] eta: 0:02:13 lr: 0.000058 loss: 2.6356 (2.7868) grad_norm: 2.7319 (2.9064) time: 0.4979 [2021-03-27 02:53:00 swin_small_patch4_window7_224] INFO: Epoch: [257] [1000/1251] eta: 0:02:08 lr: 0.000058 loss: 2.8497 (2.7874) grad_norm: 2.7358 (2.9053) time: 0.5024 [2021-03-27 02:53:05 swin_small_patch4_window7_224] INFO: Epoch: [257] [1010/1251] eta: 0:02:02 lr: 0.000058 loss: 2.8497 (2.7860) grad_norm: 2.6452 (2.9030) time: 0.5061 [2021-03-27 02:53:10 swin_small_patch4_window7_224] INFO: Epoch: [257] [1020/1251] eta: 0:01:57 lr: 0.000058 loss: 2.8088 (2.7867) grad_norm: 2.6505 (2.9019) time: 0.5086 [2021-03-27 02:53:15 swin_small_patch4_window7_224] INFO: Epoch: [257] [1030/1251] eta: 0:01:52 lr: 0.000058 loss: 2.8402 (2.7869) grad_norm: 2.8373 (2.9012) time: 0.5089 [2021-03-27 02:53:20 swin_small_patch4_window7_224] INFO: Epoch: [257] [1040/1251] eta: 0:01:47 lr: 0.000057 loss: 2.8087 (2.7867) grad_norm: 2.8373 (2.9024) time: 0.5092 [2021-03-27 02:53:25 swin_small_patch4_window7_224] INFO: Epoch: [257] [1050/1251] eta: 0:01:42 lr: 0.000057 loss: 2.7276 (2.7856) grad_norm: 2.8615 (2.9018) time: 0.5135 [2021-03-27 02:53:30 swin_small_patch4_window7_224] INFO: Epoch: [257] [1060/1251] eta: 0:01:37 lr: 0.000057 loss: 2.6794 (2.7857) grad_norm: 2.8982 (2.9039) time: 0.5071 [2021-03-27 02:53:36 swin_small_patch4_window7_224] INFO: Epoch: [257] [1070/1251] eta: 0:01:32 lr: 0.000057 loss: 2.8914 (2.7865) grad_norm: 2.9891 (2.9063) time: 0.5102 [2021-03-27 02:53:41 swin_small_patch4_window7_224] INFO: Epoch: [257] [1080/1251] eta: 0:01:27 lr: 0.000057 loss: 2.9579 (2.7861) grad_norm: 2.9041 (2.9065) time: 0.5141 [2021-03-27 02:53:46 swin_small_patch4_window7_224] INFO: Epoch: [257] [1090/1251] eta: 0:01:22 lr: 0.000057 loss: 2.7659 (2.7855) grad_norm: 2.7749 (2.9167) time: 0.5030 [2021-03-27 02:53:51 swin_small_patch4_window7_224] INFO: Epoch: [257] [1100/1251] eta: 0:01:16 lr: 0.000057 loss: 2.7659 (2.7851) grad_norm: 2.8162 (2.9184) time: 0.4997 [2021-03-27 02:53:56 swin_small_patch4_window7_224] INFO: Epoch: [257] [1110/1251] eta: 0:01:11 lr: 0.000057 loss: 2.7197 (2.7822) grad_norm: 2.9446 (2.9207) time: 0.5028 [2021-03-27 02:54:01 swin_small_patch4_window7_224] INFO: Epoch: [257] [1120/1251] eta: 0:01:06 lr: 0.000057 loss: 2.7496 (2.7845) grad_norm: 3.0269 (2.9246) time: 0.5023 [2021-03-27 02:54:06 swin_small_patch4_window7_224] INFO: Epoch: [257] [1130/1251] eta: 0:01:01 lr: 0.000057 loss: 2.9114 (2.7841) grad_norm: 3.0734 (2.9259) time: 0.4997 [2021-03-27 02:54:11 swin_small_patch4_window7_224] INFO: Epoch: [257] [1140/1251] eta: 0:00:56 lr: 0.000057 loss: 2.8120 (2.7834) grad_norm: 3.0291 (2.9261) time: 0.5051 [2021-03-27 02:54:16 swin_small_patch4_window7_224] INFO: Epoch: [257] [1150/1251] eta: 0:00:51 lr: 0.000057 loss: 2.8382 (2.7853) grad_norm: 3.0291 (2.9325) time: 0.5110 [2021-03-27 02:54:21 swin_small_patch4_window7_224] INFO: Epoch: [257] [1160/1251] eta: 0:00:46 lr: 0.000057 loss: 2.8068 (2.7846) grad_norm: 2.9061 (2.9312) time: 0.5087 [2021-03-27 02:54:26 swin_small_patch4_window7_224] INFO: Epoch: [257] [1170/1251] eta: 0:00:41 lr: 0.000057 loss: 2.6167 (2.7840) grad_norm: 2.9061 (2.9339) time: 0.5043 [2021-03-27 02:54:31 swin_small_patch4_window7_224] INFO: Epoch: [257] [1180/1251] eta: 0:00:36 lr: 0.000057 loss: 2.8527 (2.7856) grad_norm: 3.0665 (2.9336) time: 0.5077 [2021-03-27 02:54:36 swin_small_patch4_window7_224] INFO: Epoch: [257] [1190/1251] eta: 0:00:31 lr: 0.000057 loss: 2.9919 (2.7866) grad_norm: 2.9597 (2.9406) time: 0.5084 [2021-03-27 02:54:41 swin_small_patch4_window7_224] INFO: Epoch: [257] [1200/1251] eta: 0:00:25 lr: 0.000057 loss: 3.0250 (2.7870) grad_norm: 3.0016 (2.9429) time: 0.5140 [2021-03-27 02:54:46 swin_small_patch4_window7_224] INFO: Epoch: [257] [1210/1251] eta: 0:00:20 lr: 0.000057 loss: 3.0891 (2.7886) grad_norm: 2.8016 (2.9434) time: 0.5115 [2021-03-27 02:54:51 swin_small_patch4_window7_224] INFO: Epoch: [257] [1220/1251] eta: 0:00:15 lr: 0.000057 loss: 3.0983 (2.7904) grad_norm: 2.8857 (2.9434) time: 0.5024 [2021-03-27 02:54:57 swin_small_patch4_window7_224] INFO: Epoch: [257] [1230/1251] eta: 0:00:10 lr: 0.000057 loss: 3.0284 (2.7917) grad_norm: 2.9250 (2.9445) time: 0.5086 [2021-03-27 02:55:02 swin_small_patch4_window7_224] INFO: Epoch: [257] [1240/1251] eta: 0:00:05 lr: 0.000057 loss: 2.7857 (2.7888) grad_norm: 2.8229 (2.9438) time: 0.5090 [2021-03-27 02:55:07 swin_small_patch4_window7_224] INFO: Epoch: [257] [1250/1251] eta: 0:00:00 lr: 0.000057 loss: 2.8154 (2.7894) grad_norm: 2.7820 (2.9440) time: 0.5081 [2021-03-27 02:55:19 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 0.7496 (0.7496) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 02:55:22 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.8574 (0.8135) acc1: 79.6875 (79.4034) acc5: 96.8750 (96.1648) [2021-03-27 02:55:25 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7627 (0.7714) acc1: 79.6875 (81.3988) acc5: 96.8750 (96.5030) [2021-03-27 02:55:27 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7006 (0.7578) acc1: 82.8125 (81.7036) acc5: 96.8750 (96.4718) [2021-03-27 02:55:28 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7529 (0.7540) acc1: 81.2500 (81.9741) acc5: 95.3125 (96.2652) [2021-03-27 02:55:29 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7543 (0.7721) acc1: 82.8125 (81.6000) acc5: 95.3125 (96.0960) [2021-03-27 02:55:44 swin_small_patch4_window7_224] INFO: * Acc@1 82.484 Acc@5 96.134 loss 0.753 [2021-03-27 02:55:44 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-27 02:55:44 swin_small_patch4_window7_224] INFO: Max accuracy: 82.53% [2021-03-27 02:55:48 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 0/1251] eta: 1:22:41 lr: 0.000057 loss: 2.7963 (2.7963) grad_norm: 2.6062 (2.6062) time: 3.9662 [2021-03-27 02:55:53 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 10/1251] eta: 0:17:50 lr: 0.000057 loss: 2.6402 (2.7646) grad_norm: 2.6738 (2.7313) time: 0.8627 [2021-03-27 02:55:58 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 20/1251] eta: 0:14:12 lr: 0.000057 loss: 2.6402 (2.7143) grad_norm: 2.7004 (2.8342) time: 0.5292 [2021-03-27 02:56:03 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 30/1251] eta: 0:12:51 lr: 0.000057 loss: 2.8122 (2.7629) grad_norm: 2.8812 (2.8721) time: 0.5051 [2021-03-27 02:56:08 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 40/1251] eta: 0:12:06 lr: 0.000057 loss: 2.6939 (2.7333) grad_norm: 2.7931 (2.8749) time: 0.5019 [2021-03-27 02:56:13 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 50/1251] eta: 0:11:37 lr: 0.000057 loss: 2.7960 (2.7660) grad_norm: 2.8001 (2.9332) time: 0.5022 [2021-03-27 02:56:18 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 60/1251] eta: 0:11:17 lr: 0.000057 loss: 2.7631 (2.7397) grad_norm: 3.0949 (3.0353) time: 0.5063 [2021-03-27 02:56:24 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 70/1251] eta: 0:11:01 lr: 0.000057 loss: 2.6582 (2.7195) grad_norm: 2.9728 (3.0551) time: 0.5076 [2021-03-27 02:56:29 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 80/1251] eta: 0:10:49 lr: 0.000057 loss: 2.6586 (2.7214) grad_norm: 2.9046 (3.0345) time: 0.5115 [2021-03-27 02:56:34 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 90/1251] eta: 0:10:37 lr: 0.000057 loss: 2.6142 (2.7124) grad_norm: 2.7799 (3.0185) time: 0.5083 [2021-03-27 02:56:39 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 100/1251] eta: 0:10:25 lr: 0.000057 loss: 2.9421 (2.7324) grad_norm: 2.8175 (3.0181) time: 0.4977 [2021-03-27 02:56:44 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 110/1251] eta: 0:10:16 lr: 0.000057 loss: 2.9763 (2.7491) grad_norm: 2.8886 (3.0155) time: 0.4996 [2021-03-27 02:56:49 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 120/1251] eta: 0:10:07 lr: 0.000057 loss: 2.8007 (2.7373) grad_norm: 2.8886 (3.0180) time: 0.5034 [2021-03-27 02:56:54 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 130/1251] eta: 0:09:58 lr: 0.000057 loss: 2.7297 (2.7399) grad_norm: 2.8501 (3.0094) time: 0.5006 [2021-03-27 02:56:59 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 140/1251] eta: 0:09:51 lr: 0.000057 loss: 2.7297 (2.7361) grad_norm: 2.8102 (2.9977) time: 0.5074 [2021-03-27 02:57:04 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 150/1251] eta: 0:09:45 lr: 0.000057 loss: 2.8846 (2.7427) grad_norm: 2.7441 (2.9758) time: 0.5185 [2021-03-27 02:57:09 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 160/1251] eta: 0:09:37 lr: 0.000057 loss: 2.9827 (2.7456) grad_norm: 2.7441 (2.9821) time: 0.5081 [2021-03-27 02:57:14 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 170/1251] eta: 0:09:30 lr: 0.000057 loss: 2.9827 (2.7525) grad_norm: 2.9606 (2.9730) time: 0.4960 [2021-03-27 02:57:19 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 180/1251] eta: 0:09:23 lr: 0.000057 loss: 2.6997 (2.7410) grad_norm: 2.8674 (2.9869) time: 0.5010 [2021-03-27 02:57:24 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 190/1251] eta: 0:09:17 lr: 0.000057 loss: 2.8320 (2.7563) grad_norm: 2.8747 (2.9894) time: 0.5051 [2021-03-27 02:57:29 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 200/1251] eta: 0:09:11 lr: 0.000057 loss: 2.9360 (2.7577) grad_norm: 2.8220 (2.9746) time: 0.5058 [2021-03-27 02:57:34 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 210/1251] eta: 0:09:04 lr: 0.000057 loss: 2.9053 (2.7698) grad_norm: 2.7789 (2.9838) time: 0.5017 [2021-03-27 02:57:39 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 220/1251] eta: 0:08:58 lr: 0.000057 loss: 3.0652 (2.7749) grad_norm: 2.8429 (2.9774) time: 0.5029 [2021-03-27 02:57:44 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 230/1251] eta: 0:08:52 lr: 0.000057 loss: 2.6301 (2.7631) grad_norm: 2.8269 (2.9739) time: 0.5078 [2021-03-27 02:57:49 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 240/1251] eta: 0:08:47 lr: 0.000057 loss: 2.8537 (2.7714) grad_norm: 2.8269 (2.9695) time: 0.5084 [2021-03-27 02:57:54 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 250/1251] eta: 0:08:41 lr: 0.000057 loss: 2.8537 (2.7652) grad_norm: 2.8735 (2.9637) time: 0.5054 [2021-03-27 02:58:00 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 260/1251] eta: 0:08:35 lr: 0.000057 loss: 2.5257 (2.7598) grad_norm: 2.7679 (2.9604) time: 0.5082 [2021-03-27 02:58:05 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 270/1251] eta: 0:08:30 lr: 0.000057 loss: 2.5260 (2.7591) grad_norm: 2.9765 (2.9890) time: 0.5133 [2021-03-27 02:58:10 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 280/1251] eta: 0:08:24 lr: 0.000057 loss: 2.9623 (2.7646) grad_norm: 3.0373 (2.9901) time: 0.5032 [2021-03-27 02:58:15 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 290/1251] eta: 0:08:18 lr: 0.000057 loss: 3.0106 (2.7738) grad_norm: 2.9281 (2.9873) time: 0.5000 [2021-03-27 02:58:20 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 300/1251] eta: 0:08:12 lr: 0.000057 loss: 3.0106 (2.7712) grad_norm: 2.9281 (2.9932) time: 0.5039 [2021-03-27 02:58:25 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 310/1251] eta: 0:08:06 lr: 0.000057 loss: 2.8584 (2.7735) grad_norm: 2.7824 (2.9872) time: 0.4992 [2021-03-27 02:58:30 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 320/1251] eta: 0:08:01 lr: 0.000057 loss: 2.8688 (2.7720) grad_norm: 2.7613 (2.9860) time: 0.4993 [2021-03-27 02:58:35 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 330/1251] eta: 0:07:55 lr: 0.000057 loss: 2.8706 (2.7777) grad_norm: 2.7864 (2.9830) time: 0.5013 [2021-03-27 02:58:40 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 340/1251] eta: 0:07:50 lr: 0.000057 loss: 2.9415 (2.7781) grad_norm: 2.7959 (2.9805) time: 0.5002 [2021-03-27 02:58:45 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 350/1251] eta: 0:07:44 lr: 0.000056 loss: 2.9189 (2.7781) grad_norm: 2.7959 (2.9801) time: 0.5033 [2021-03-27 02:58:50 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 360/1251] eta: 0:07:39 lr: 0.000056 loss: 2.8567 (2.7770) grad_norm: 2.7698 (2.9759) time: 0.5063 [2021-03-27 02:58:55 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 370/1251] eta: 0:07:33 lr: 0.000056 loss: 2.6791 (2.7711) grad_norm: 2.7422 (2.9728) time: 0.5031 [2021-03-27 02:59:00 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 380/1251] eta: 0:07:28 lr: 0.000056 loss: 2.4505 (2.7680) grad_norm: 2.8248 (2.9729) time: 0.5018 [2021-03-27 02:59:05 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 390/1251] eta: 0:07:22 lr: 0.000056 loss: 2.7586 (2.7669) grad_norm: 2.8479 (2.9728) time: 0.5013 [2021-03-27 02:59:10 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 400/1251] eta: 0:07:17 lr: 0.000056 loss: 2.4988 (2.7578) grad_norm: 2.9171 (2.9813) time: 0.5036 [2021-03-27 02:59:15 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 410/1251] eta: 0:07:12 lr: 0.000056 loss: 2.7104 (2.7628) grad_norm: 2.9267 (2.9859) time: 0.5038 [2021-03-27 02:59:20 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 420/1251] eta: 0:07:06 lr: 0.000056 loss: 3.1026 (2.7700) grad_norm: 2.9267 (2.9849) time: 0.4997 [2021-03-27 02:59:25 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 430/1251] eta: 0:07:01 lr: 0.000056 loss: 2.8449 (2.7604) grad_norm: 2.7645 (2.9793) time: 0.5102 [2021-03-27 02:59:30 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 440/1251] eta: 0:06:56 lr: 0.000056 loss: 2.6490 (2.7608) grad_norm: 2.8736 (2.9886) time: 0.5094 [2021-03-27 02:59:35 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 450/1251] eta: 0:06:51 lr: 0.000056 loss: 2.8300 (2.7616) grad_norm: 2.9630 (3.0358) time: 0.5044 [2021-03-27 02:59:40 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 460/1251] eta: 0:06:45 lr: 0.000056 loss: 2.5789 (2.7577) grad_norm: 2.8554 (3.0333) time: 0.5041 [2021-03-27 02:59:45 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 470/1251] eta: 0:06:40 lr: 0.000056 loss: 2.5865 (2.7578) grad_norm: 2.8284 (3.0333) time: 0.4998 [2021-03-27 02:59:50 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 480/1251] eta: 0:06:35 lr: 0.000056 loss: 3.0306 (2.7645) grad_norm: 2.7607 (3.0308) time: 0.5000 [2021-03-27 02:59:55 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 490/1251] eta: 0:06:29 lr: 0.000056 loss: 2.9649 (2.7669) grad_norm: 2.7525 (3.0293) time: 0.5013 [2021-03-27 03:00:00 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 500/1251] eta: 0:06:24 lr: 0.000056 loss: 2.8543 (2.7640) grad_norm: 2.7699 (3.0287) time: 0.4980 [2021-03-27 03:00:05 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 510/1251] eta: 0:06:19 lr: 0.000056 loss: 2.6903 (2.7620) grad_norm: 2.8910 (3.0292) time: 0.4963 [2021-03-27 03:00:10 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 520/1251] eta: 0:06:13 lr: 0.000056 loss: 2.7953 (2.7628) grad_norm: 2.8991 (3.0281) time: 0.5075 [2021-03-27 03:00:15 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 530/1251] eta: 0:06:08 lr: 0.000056 loss: 2.8184 (2.7654) grad_norm: 2.8527 (3.0306) time: 0.5069 [2021-03-27 03:00:20 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 540/1251] eta: 0:06:03 lr: 0.000056 loss: 2.8690 (2.7677) grad_norm: 2.8448 (3.0342) time: 0.5058 [2021-03-27 03:00:26 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 550/1251] eta: 0:05:58 lr: 0.000056 loss: 2.8040 (2.7650) grad_norm: 2.8176 (3.0305) time: 0.5210 [2021-03-27 03:00:31 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 560/1251] eta: 0:05:53 lr: 0.000056 loss: 2.7294 (2.7639) grad_norm: 2.8632 (3.0282) time: 0.5150 [2021-03-27 03:00:36 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 570/1251] eta: 0:05:48 lr: 0.000056 loss: 2.5575 (2.7623) grad_norm: 2.9082 (3.0281) time: 0.5088 [2021-03-27 03:00:41 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 580/1251] eta: 0:05:43 lr: 0.000056 loss: 2.9663 (2.7644) grad_norm: 2.9941 (3.0317) time: 0.5075 [2021-03-27 03:00:46 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 590/1251] eta: 0:05:37 lr: 0.000056 loss: 2.9663 (2.7671) grad_norm: 2.8770 (3.0279) time: 0.4966 [2021-03-27 03:00:51 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 600/1251] eta: 0:05:32 lr: 0.000056 loss: 2.9313 (2.7681) grad_norm: 2.7243 (3.0248) time: 0.5010 [2021-03-27 03:00:56 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 610/1251] eta: 0:05:27 lr: 0.000056 loss: 2.7209 (2.7653) grad_norm: 2.9111 (3.0259) time: 0.5024 [2021-03-27 03:01:01 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 620/1251] eta: 0:05:22 lr: 0.000056 loss: 2.6941 (2.7631) grad_norm: 2.9170 (3.0257) time: 0.5018 [2021-03-27 03:01:06 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 630/1251] eta: 0:05:17 lr: 0.000056 loss: 2.9377 (2.7672) grad_norm: 2.7747 (3.0247) time: 0.5021 [2021-03-27 03:01:11 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 640/1251] eta: 0:05:11 lr: 0.000056 loss: 2.9519 (2.7700) grad_norm: 2.7747 (3.0238) time: 0.5017 [2021-03-27 03:01:16 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 650/1251] eta: 0:05:06 lr: 0.000056 loss: 2.9179 (2.7721) grad_norm: 2.6788 (3.0198) time: 0.5018 [2021-03-27 03:01:21 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 660/1251] eta: 0:05:01 lr: 0.000056 loss: 2.9484 (2.7748) grad_norm: 2.6540 (3.0169) time: 0.4966 [2021-03-27 03:01:26 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 670/1251] eta: 0:04:56 lr: 0.000056 loss: 2.9682 (2.7758) grad_norm: 2.8129 (3.0161) time: 0.4982 [2021-03-27 03:01:31 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 680/1251] eta: 0:04:51 lr: 0.000056 loss: 2.6558 (2.7731) grad_norm: 2.9278 (3.0157) time: 0.5017 [2021-03-27 03:01:36 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 690/1251] eta: 0:04:46 lr: 0.000056 loss: 2.5777 (2.7717) grad_norm: 2.8869 (3.0122) time: 0.5083 [2021-03-27 03:01:41 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 700/1251] eta: 0:04:40 lr: 0.000056 loss: 2.7040 (2.7704) grad_norm: 2.7965 (3.0131) time: 0.5131 [2021-03-27 03:01:46 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 710/1251] eta: 0:04:35 lr: 0.000056 loss: 2.7040 (2.7691) grad_norm: 3.0018 (3.0129) time: 0.5079 [2021-03-27 03:01:51 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 720/1251] eta: 0:04:30 lr: 0.000056 loss: 2.7097 (2.7682) grad_norm: 2.8399 (3.0095) time: 0.5031 [2021-03-27 03:01:56 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 730/1251] eta: 0:04:25 lr: 0.000056 loss: 2.7985 (2.7674) grad_norm: 2.7068 (3.0095) time: 0.4991 [2021-03-27 03:02:02 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 740/1251] eta: 0:04:20 lr: 0.000056 loss: 2.8770 (2.7677) grad_norm: 2.9443 (3.0072) time: 0.5123 [2021-03-27 03:02:07 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 750/1251] eta: 0:04:15 lr: 0.000056 loss: 2.8770 (2.7697) grad_norm: 2.8694 (3.0044) time: 0.5170 [2021-03-27 03:02:12 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 760/1251] eta: 0:04:10 lr: 0.000056 loss: 2.9542 (2.7719) grad_norm: 2.7613 (3.0004) time: 0.5130 [2021-03-27 03:02:17 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 770/1251] eta: 0:04:05 lr: 0.000056 loss: 2.9365 (2.7737) grad_norm: 2.7110 (2.9975) time: 0.5097 [2021-03-27 03:02:22 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 780/1251] eta: 0:04:00 lr: 0.000056 loss: 2.7766 (2.7689) grad_norm: 2.8441 (2.9963) time: 0.5046 [2021-03-27 03:02:27 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 790/1251] eta: 0:03:54 lr: 0.000056 loss: 2.7585 (2.7690) grad_norm: 2.9581 (3.0005) time: 0.5046 [2021-03-27 03:02:32 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 800/1251] eta: 0:03:49 lr: 0.000056 loss: 2.8174 (2.7700) grad_norm: 2.9614 (2.9996) time: 0.5016 [2021-03-27 03:02:37 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 810/1251] eta: 0:03:44 lr: 0.000056 loss: 2.9263 (2.7719) grad_norm: 2.9158 (2.9989) time: 0.5038 [2021-03-27 03:02:42 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 820/1251] eta: 0:03:39 lr: 0.000056 loss: 2.8352 (2.7696) grad_norm: 2.7657 (2.9966) time: 0.5063 [2021-03-27 03:02:47 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 830/1251] eta: 0:03:34 lr: 0.000056 loss: 2.6277 (2.7681) grad_norm: 2.7634 (2.9944) time: 0.5113 [2021-03-27 03:02:52 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 840/1251] eta: 0:03:29 lr: 0.000056 loss: 2.8860 (2.7696) grad_norm: 2.8881 (2.9959) time: 0.5072 [2021-03-27 03:02:57 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 850/1251] eta: 0:03:24 lr: 0.000056 loss: 2.9464 (2.7712) grad_norm: 3.1020 (3.0028) time: 0.5015 [2021-03-27 03:03:02 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 860/1251] eta: 0:03:19 lr: 0.000056 loss: 2.8211 (2.7713) grad_norm: 3.0194 (3.0097) time: 0.4992 [2021-03-27 03:03:07 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 870/1251] eta: 0:03:13 lr: 0.000056 loss: 2.8283 (2.7722) grad_norm: 2.8523 (3.0086) time: 0.4978 [2021-03-27 03:03:12 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 880/1251] eta: 0:03:08 lr: 0.000056 loss: 2.8334 (2.7722) grad_norm: 2.8311 (3.0083) time: 0.5090 [2021-03-27 03:03:18 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 890/1251] eta: 0:03:03 lr: 0.000056 loss: 2.8334 (2.7728) grad_norm: 2.7597 (3.0082) time: 0.5193 [2021-03-27 03:03:23 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 900/1251] eta: 0:02:58 lr: 0.000056 loss: 2.8334 (2.7738) grad_norm: 2.8015 (3.0086) time: 0.5167 [2021-03-27 03:03:28 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 910/1251] eta: 0:02:53 lr: 0.000056 loss: 2.8057 (2.7751) grad_norm: 2.8134 (3.0094) time: 0.5087 [2021-03-27 03:03:33 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 920/1251] eta: 0:02:48 lr: 0.000056 loss: 2.8818 (2.7751) grad_norm: 2.7935 (3.0086) time: 0.5066 [2021-03-27 03:03:38 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 930/1251] eta: 0:02:43 lr: 0.000055 loss: 2.9631 (2.7773) grad_norm: 2.7532 (3.0066) time: 0.5041 [2021-03-27 03:03:43 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 940/1251] eta: 0:02:38 lr: 0.000055 loss: 2.9464 (2.7770) grad_norm: 2.7128 (3.0030) time: 0.5033 [2021-03-27 03:03:48 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 950/1251] eta: 0:02:33 lr: 0.000055 loss: 2.8011 (2.7766) grad_norm: 2.7678 (3.0030) time: 0.5091 [2021-03-27 03:03:53 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 960/1251] eta: 0:02:28 lr: 0.000055 loss: 2.8599 (2.7780) grad_norm: 2.8426 (3.0026) time: 0.5071 [2021-03-27 03:03:58 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 970/1251] eta: 0:02:23 lr: 0.000055 loss: 2.8642 (2.7782) grad_norm: 2.8259 (3.0017) time: 0.5008 [2021-03-27 03:04:03 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 980/1251] eta: 0:02:17 lr: 0.000055 loss: 2.8642 (2.7778) grad_norm: 2.8380 (inf) time: 0.4958 [2021-03-27 03:04:08 swin_small_patch4_window7_224] INFO: Epoch: [258] [ 990/1251] eta: 0:02:12 lr: 0.000055 loss: 2.7838 (2.7786) grad_norm: 2.7487 (inf) time: 0.4992 [2021-03-27 03:04:13 swin_small_patch4_window7_224] INFO: Epoch: [258] [1000/1251] eta: 0:02:07 lr: 0.000055 loss: 2.7673 (2.7764) grad_norm: 2.9338 (inf) time: 0.5060 [2021-03-27 03:04:18 swin_small_patch4_window7_224] INFO: Epoch: [258] [1010/1251] eta: 0:02:02 lr: 0.000055 loss: 2.7201 (2.7774) grad_norm: 3.0370 (inf) time: 0.5056 [2021-03-27 03:04:23 swin_small_patch4_window7_224] INFO: Epoch: [258] [1020/1251] eta: 0:01:57 lr: 0.000055 loss: 2.7601 (2.7755) grad_norm: 2.8371 (inf) time: 0.5011 [2021-03-27 03:04:28 swin_small_patch4_window7_224] INFO: Epoch: [258] [1030/1251] eta: 0:01:52 lr: 0.000055 loss: 2.7997 (2.7744) grad_norm: 2.9223 (inf) time: 0.5049 [2021-03-27 03:04:33 swin_small_patch4_window7_224] INFO: Epoch: [258] [1040/1251] eta: 0:01:47 lr: 0.000055 loss: 2.6589 (2.7733) grad_norm: 3.0790 (inf) time: 0.5107 [2021-03-27 03:04:38 swin_small_patch4_window7_224] INFO: Epoch: [258] [1050/1251] eta: 0:01:42 lr: 0.000055 loss: 2.8469 (2.7756) grad_norm: 3.0444 (inf) time: 0.5071 [2021-03-27 03:04:44 swin_small_patch4_window7_224] INFO: Epoch: [258] [1060/1251] eta: 0:01:37 lr: 0.000055 loss: 3.0216 (2.7764) grad_norm: 2.8254 (inf) time: 0.5085 [2021-03-27 03:04:49 swin_small_patch4_window7_224] INFO: Epoch: [258] [1070/1251] eta: 0:01:32 lr: 0.000055 loss: 2.8555 (2.7767) grad_norm: 2.7842 (inf) time: 0.5044 [2021-03-27 03:04:54 swin_small_patch4_window7_224] INFO: Epoch: [258] [1080/1251] eta: 0:01:26 lr: 0.000055 loss: 2.8555 (2.7770) grad_norm: 2.8477 (inf) time: 0.4996 [2021-03-27 03:04:59 swin_small_patch4_window7_224] INFO: Epoch: [258] [1090/1251] eta: 0:01:21 lr: 0.000055 loss: 2.9568 (2.7790) grad_norm: 2.7439 (inf) time: 0.5035 [2021-03-27 03:05:04 swin_small_patch4_window7_224] INFO: Epoch: [258] [1100/1251] eta: 0:01:16 lr: 0.000055 loss: 2.9076 (2.7803) grad_norm: 2.7877 (inf) time: 0.5019 [2021-03-27 03:05:09 swin_small_patch4_window7_224] INFO: Epoch: [258] [1110/1251] eta: 0:01:11 lr: 0.000055 loss: 2.6958 (2.7782) grad_norm: 3.1367 (inf) time: 0.5044 [2021-03-27 03:05:14 swin_small_patch4_window7_224] INFO: Epoch: [258] [1120/1251] eta: 0:01:06 lr: 0.000055 loss: 2.7543 (2.7796) grad_norm: 2.9324 (inf) time: 0.5060 [2021-03-27 03:05:19 swin_small_patch4_window7_224] INFO: Epoch: [258] [1130/1251] eta: 0:01:01 lr: 0.000055 loss: 2.7892 (2.7786) grad_norm: 2.9121 (inf) time: 0.5037 [2021-03-27 03:05:24 swin_small_patch4_window7_224] INFO: Epoch: [258] [1140/1251] eta: 0:00:56 lr: 0.000055 loss: 2.7836 (2.7782) grad_norm: 2.7858 (inf) time: 0.4989 [2021-03-27 03:05:29 swin_small_patch4_window7_224] INFO: Epoch: [258] [1150/1251] eta: 0:00:51 lr: 0.000055 loss: 2.7927 (2.7772) grad_norm: 2.7685 (inf) time: 0.4948 [2021-03-27 03:05:34 swin_small_patch4_window7_224] INFO: Epoch: [258] [1160/1251] eta: 0:00:46 lr: 0.000055 loss: 2.8839 (2.7772) grad_norm: 2.9206 (inf) time: 0.4964 [2021-03-27 03:05:39 swin_small_patch4_window7_224] INFO: Epoch: [258] [1170/1251] eta: 0:00:41 lr: 0.000055 loss: 2.9924 (2.7772) grad_norm: 2.7703 (inf) time: 0.4953 [2021-03-27 03:05:44 swin_small_patch4_window7_224] INFO: Epoch: [258] [1180/1251] eta: 0:00:36 lr: 0.000055 loss: 2.9013 (2.7772) grad_norm: 2.7703 (inf) time: 0.5028 [2021-03-27 03:05:49 swin_small_patch4_window7_224] INFO: Epoch: [258] [1190/1251] eta: 0:00:30 lr: 0.000055 loss: 2.8275 (2.7759) grad_norm: 2.8944 (inf) time: 0.5033 [2021-03-27 03:05:54 swin_small_patch4_window7_224] INFO: Epoch: [258] [1200/1251] eta: 0:00:25 lr: 0.000055 loss: 2.7717 (2.7755) grad_norm: 3.0474 (inf) time: 0.5001 [2021-03-27 03:05:59 swin_small_patch4_window7_224] INFO: Epoch: [258] [1210/1251] eta: 0:00:20 lr: 0.000055 loss: 2.7966 (2.7757) grad_norm: 2.9233 (inf) time: 0.5031 [2021-03-27 03:06:04 swin_small_patch4_window7_224] INFO: Epoch: [258] [1220/1251] eta: 0:00:15 lr: 0.000055 loss: 2.9395 (2.7748) grad_norm: 2.8711 (inf) time: 0.5012 [2021-03-27 03:06:09 swin_small_patch4_window7_224] INFO: Epoch: [258] [1230/1251] eta: 0:00:10 lr: 0.000055 loss: 2.8571 (2.7749) grad_norm: 2.9079 (inf) time: 0.5031 [2021-03-27 03:06:14 swin_small_patch4_window7_224] INFO: Epoch: [258] [1240/1251] eta: 0:00:05 lr: 0.000055 loss: 2.9648 (2.7775) grad_norm: 2.8585 (inf) time: 0.5013 [2021-03-27 03:06:19 swin_small_patch4_window7_224] INFO: Epoch: [258] [1250/1251] eta: 0:00:00 lr: 0.000055 loss: 3.0845 (2.7784) grad_norm: 2.7679 (inf) time: 0.4934 [2021-03-27 03:06:29 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:56 loss: 0.8105 (0.8105) acc1: 79.6875 (79.6875) acc5: 95.3125 (95.3125) [2021-03-27 03:06:32 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.6429 (0.6549) acc1: 82.8125 (83.8068) acc5: 96.8750 (97.1591) [2021-03-27 03:06:34 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.6814 (0.7319) acc1: 81.2500 (82.4405) acc5: 96.8750 (96.5774) [2021-03-27 03:06:36 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7921 (0.7631) acc1: 81.2500 (81.7036) acc5: 95.3125 (95.9677) [2021-03-27 03:06:38 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7921 (0.7738) acc1: 81.2500 (81.5930) acc5: 95.3125 (95.9223) [2021-03-27 03:06:39 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7257 (0.7562) acc1: 82.8125 (81.7920) acc5: 96.8750 (96.2560) [2021-03-27 03:06:49 swin_small_patch4_window7_224] INFO: * Acc@1 82.492 Acc@5 96.184 loss 0.747 [2021-03-27 03:06:49 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.5% [2021-03-27 03:06:49 swin_small_patch4_window7_224] INFO: Max accuracy: 82.53% [2021-03-27 03:06:54 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 0/1251] eta: 1:31:30 lr: 0.000055 loss: 2.0986 (2.0986) grad_norm: 2.5017 (2.5017) time: 4.3889 [2021-03-27 03:06:59 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 10/1251] eta: 0:17:59 lr: 0.000055 loss: 2.6742 (2.5942) grad_norm: 2.7288 (2.8108) time: 0.8695 [2021-03-27 03:07:04 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 20/1251] eta: 0:14:20 lr: 0.000055 loss: 2.6742 (2.6629) grad_norm: 2.9970 (3.0267) time: 0.5149 [2021-03-27 03:07:09 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 30/1251] eta: 0:12:56 lr: 0.000055 loss: 2.8877 (2.7498) grad_norm: 3.1939 (3.2526) time: 0.5072 [2021-03-27 03:07:14 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 40/1251] eta: 0:12:08 lr: 0.000055 loss: 2.9388 (2.7712) grad_norm: 3.1761 (3.2557) time: 0.4989 [2021-03-27 03:07:19 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 50/1251] eta: 0:11:37 lr: 0.000055 loss: 2.8393 (2.7475) grad_norm: 2.8557 (3.1882) time: 0.4949 [2021-03-27 03:07:24 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 60/1251] eta: 0:11:14 lr: 0.000055 loss: 2.6799 (2.6988) grad_norm: 2.8557 (3.1793) time: 0.4943 [2021-03-27 03:07:29 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 70/1251] eta: 0:10:59 lr: 0.000055 loss: 2.7582 (2.7255) grad_norm: 3.0325 (3.1407) time: 0.5016 [2021-03-27 03:07:34 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 80/1251] eta: 0:10:45 lr: 0.000055 loss: 3.0283 (2.7594) grad_norm: 2.9162 (3.1122) time: 0.5065 [2021-03-27 03:07:39 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 90/1251] eta: 0:10:33 lr: 0.000055 loss: 3.0591 (2.7911) grad_norm: 2.9186 (3.1115) time: 0.4992 [2021-03-27 03:07:44 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 100/1251] eta: 0:10:22 lr: 0.000055 loss: 2.9613 (2.7801) grad_norm: 2.8333 (3.1418) time: 0.4985 [2021-03-27 03:07:49 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 110/1251] eta: 0:10:13 lr: 0.000055 loss: 2.8978 (2.7880) grad_norm: 2.8482 (3.1227) time: 0.5049 [2021-03-27 03:07:54 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 120/1251] eta: 0:10:05 lr: 0.000055 loss: 2.9434 (2.7961) grad_norm: 2.9192 (3.1184) time: 0.5040 [2021-03-27 03:08:00 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 130/1251] eta: 0:09:58 lr: 0.000055 loss: 2.9849 (2.7990) grad_norm: 2.8527 (3.1071) time: 0.5136 [2021-03-27 03:08:04 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 140/1251] eta: 0:09:50 lr: 0.000055 loss: 2.8907 (2.8014) grad_norm: 2.7983 (3.1343) time: 0.5122 [2021-03-27 03:08:09 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 150/1251] eta: 0:09:43 lr: 0.000055 loss: 2.8628 (2.8011) grad_norm: 2.8481 (3.1278) time: 0.4986 [2021-03-27 03:08:14 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 160/1251] eta: 0:09:35 lr: 0.000055 loss: 2.8246 (2.7987) grad_norm: 2.8135 (3.1104) time: 0.4990 [2021-03-27 03:08:20 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 170/1251] eta: 0:09:29 lr: 0.000055 loss: 2.8246 (2.7924) grad_norm: 2.8356 (3.1009) time: 0.5053 [2021-03-27 03:08:25 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 180/1251] eta: 0:09:23 lr: 0.000055 loss: 2.9154 (2.7971) grad_norm: 2.8999 (3.0950) time: 0.5110 [2021-03-27 03:08:30 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 190/1251] eta: 0:09:16 lr: 0.000055 loss: 2.8964 (2.7947) grad_norm: 2.8091 (3.0796) time: 0.5092 [2021-03-27 03:08:35 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 200/1251] eta: 0:09:10 lr: 0.000055 loss: 2.6306 (2.7839) grad_norm: 2.8319 (3.0737) time: 0.5076 [2021-03-27 03:08:40 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 210/1251] eta: 0:09:05 lr: 0.000055 loss: 2.6184 (2.7666) grad_norm: 2.9156 (3.0652) time: 0.5112 [2021-03-27 03:08:45 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 220/1251] eta: 0:08:59 lr: 0.000055 loss: 2.6794 (2.7587) grad_norm: 2.8545 (3.0543) time: 0.5121 [2021-03-27 03:08:50 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 230/1251] eta: 0:08:53 lr: 0.000055 loss: 2.7918 (2.7604) grad_norm: 2.8545 (3.0573) time: 0.5097 [2021-03-27 03:08:55 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 240/1251] eta: 0:08:47 lr: 0.000055 loss: 2.9257 (2.7635) grad_norm: 2.7856 (3.0517) time: 0.5082 [2021-03-27 03:09:00 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 250/1251] eta: 0:08:41 lr: 0.000054 loss: 2.8734 (2.7624) grad_norm: 2.7949 (3.0462) time: 0.4987 [2021-03-27 03:09:05 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 260/1251] eta: 0:08:35 lr: 0.000054 loss: 2.8868 (2.7707) grad_norm: 2.7815 (3.0477) time: 0.4988 [2021-03-27 03:09:10 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 270/1251] eta: 0:08:29 lr: 0.000054 loss: 2.9688 (2.7656) grad_norm: 2.7669 (3.0532) time: 0.5089 [2021-03-27 03:09:15 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 280/1251] eta: 0:08:24 lr: 0.000054 loss: 2.4525 (2.7589) grad_norm: 2.8798 (3.0777) time: 0.5086 [2021-03-27 03:09:20 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 290/1251] eta: 0:08:18 lr: 0.000054 loss: 2.8539 (2.7630) grad_norm: 2.6680 (3.0700) time: 0.5029 [2021-03-27 03:09:25 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 300/1251] eta: 0:08:12 lr: 0.000054 loss: 2.8680 (2.7590) grad_norm: 2.6650 (3.0699) time: 0.4996 [2021-03-27 03:09:30 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 310/1251] eta: 0:08:06 lr: 0.000054 loss: 2.5810 (2.7540) grad_norm: 2.9829 (3.0753) time: 0.4998 [2021-03-27 03:09:36 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 320/1251] eta: 0:08:01 lr: 0.000054 loss: 2.8136 (2.7532) grad_norm: 2.9574 (3.0718) time: 0.5041 [2021-03-27 03:09:40 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 330/1251] eta: 0:07:55 lr: 0.000054 loss: 2.7544 (2.7524) grad_norm: 2.9574 (3.0740) time: 0.5010 [2021-03-27 03:09:46 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 340/1251] eta: 0:07:50 lr: 0.000054 loss: 2.9165 (2.7591) grad_norm: 3.0291 (3.0755) time: 0.5000 [2021-03-27 03:09:51 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 350/1251] eta: 0:07:44 lr: 0.000054 loss: 2.9885 (2.7612) grad_norm: 2.9182 (3.0730) time: 0.5045 [2021-03-27 03:09:56 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 360/1251] eta: 0:07:38 lr: 0.000054 loss: 2.7400 (2.7597) grad_norm: 2.8954 (3.0761) time: 0.5002 [2021-03-27 03:10:00 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 370/1251] eta: 0:07:33 lr: 0.000054 loss: 2.7206 (2.7571) grad_norm: 2.9744 (3.1315) time: 0.4965 [2021-03-27 03:10:05 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 380/1251] eta: 0:07:27 lr: 0.000054 loss: 2.7133 (2.7556) grad_norm: 2.9744 (3.1296) time: 0.4966 [2021-03-27 03:10:11 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 390/1251] eta: 0:07:22 lr: 0.000054 loss: 2.7025 (2.7551) grad_norm: 3.0721 (3.1340) time: 0.5032 [2021-03-27 03:10:16 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 400/1251] eta: 0:07:17 lr: 0.000054 loss: 3.0493 (2.7583) grad_norm: 2.8340 (3.1229) time: 0.5068 [2021-03-27 03:10:21 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 410/1251] eta: 0:07:11 lr: 0.000054 loss: 2.9369 (2.7552) grad_norm: 2.7180 (3.1176) time: 0.5009 [2021-03-27 03:10:26 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 420/1251] eta: 0:07:06 lr: 0.000054 loss: 2.7127 (2.7563) grad_norm: 2.7180 (3.1076) time: 0.5074 [2021-03-27 03:10:31 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 430/1251] eta: 0:07:01 lr: 0.000054 loss: 3.0888 (2.7657) grad_norm: 2.7680 (3.1038) time: 0.5118 [2021-03-27 03:10:36 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 440/1251] eta: 0:06:56 lr: 0.000054 loss: 2.9711 (2.7648) grad_norm: 2.8035 (3.1006) time: 0.5036 [2021-03-27 03:10:41 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 450/1251] eta: 0:06:50 lr: 0.000054 loss: 2.7633 (2.7626) grad_norm: 2.8552 (3.1033) time: 0.4986 [2021-03-27 03:10:46 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 460/1251] eta: 0:06:45 lr: 0.000054 loss: 2.8185 (2.7655) grad_norm: 2.9887 (3.1001) time: 0.4986 [2021-03-27 03:10:51 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 470/1251] eta: 0:06:39 lr: 0.000054 loss: 2.8982 (2.7685) grad_norm: 2.8928 (3.1059) time: 0.4998 [2021-03-27 03:10:56 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 480/1251] eta: 0:06:34 lr: 0.000054 loss: 2.7777 (2.7677) grad_norm: 2.9602 (3.1016) time: 0.5009 [2021-03-27 03:11:01 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 490/1251] eta: 0:06:29 lr: 0.000054 loss: 2.7487 (2.7633) grad_norm: 2.9766 (3.1019) time: 0.5002 [2021-03-27 03:11:06 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 500/1251] eta: 0:06:24 lr: 0.000054 loss: 2.6494 (2.7618) grad_norm: 2.9766 (3.1033) time: 0.4997 [2021-03-27 03:11:11 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 510/1251] eta: 0:06:18 lr: 0.000054 loss: 2.7186 (2.7597) grad_norm: 3.0019 (3.1043) time: 0.5022 [2021-03-27 03:11:16 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 520/1251] eta: 0:06:13 lr: 0.000054 loss: 2.7220 (2.7571) grad_norm: 2.9923 (3.1007) time: 0.5111 [2021-03-27 03:11:21 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 530/1251] eta: 0:06:08 lr: 0.000054 loss: 2.7042 (2.7579) grad_norm: 2.7843 (3.0976) time: 0.5097 [2021-03-27 03:11:26 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 540/1251] eta: 0:06:03 lr: 0.000054 loss: 2.7533 (2.7571) grad_norm: 2.6975 (3.0928) time: 0.4959 [2021-03-27 03:11:31 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 550/1251] eta: 0:05:58 lr: 0.000054 loss: 2.7660 (2.7564) grad_norm: 2.6880 (3.0878) time: 0.5038 [2021-03-27 03:11:36 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 560/1251] eta: 0:05:52 lr: 0.000054 loss: 2.8688 (2.7589) grad_norm: 2.8146 (3.0845) time: 0.5050 [2021-03-27 03:11:41 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 570/1251] eta: 0:05:47 lr: 0.000054 loss: 2.8912 (2.7585) grad_norm: 2.8324 (3.0864) time: 0.4984 [2021-03-27 03:11:46 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 580/1251] eta: 0:05:42 lr: 0.000054 loss: 2.8044 (2.7574) grad_norm: 2.8272 (3.0802) time: 0.5078 [2021-03-27 03:11:51 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 590/1251] eta: 0:05:37 lr: 0.000054 loss: 2.7407 (2.7547) grad_norm: 2.6724 (3.0799) time: 0.5059 [2021-03-27 03:11:56 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 600/1251] eta: 0:05:32 lr: 0.000054 loss: 2.7290 (2.7536) grad_norm: 2.8613 (3.0766) time: 0.4994 [2021-03-27 03:12:01 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 610/1251] eta: 0:05:26 lr: 0.000054 loss: 2.7290 (2.7491) grad_norm: 2.8107 (3.0742) time: 0.5002 [2021-03-27 03:12:06 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 620/1251] eta: 0:05:21 lr: 0.000054 loss: 2.6474 (2.7468) grad_norm: 2.7158 (3.0668) time: 0.5015 [2021-03-27 03:12:11 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 630/1251] eta: 0:05:16 lr: 0.000054 loss: 2.7028 (2.7450) grad_norm: 2.6382 (3.0628) time: 0.4988 [2021-03-27 03:12:16 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 640/1251] eta: 0:05:11 lr: 0.000054 loss: 2.6073 (2.7422) grad_norm: 2.7485 (3.0699) time: 0.4976 [2021-03-27 03:12:21 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 650/1251] eta: 0:05:06 lr: 0.000054 loss: 2.6308 (2.7402) grad_norm: 2.8223 (3.0812) time: 0.5013 [2021-03-27 03:12:26 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 660/1251] eta: 0:05:00 lr: 0.000054 loss: 2.7800 (2.7415) grad_norm: 2.8031 (3.0768) time: 0.5028 [2021-03-27 03:12:31 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 670/1251] eta: 0:04:55 lr: 0.000054 loss: 2.8547 (2.7419) grad_norm: 2.6892 (3.0708) time: 0.5004 [2021-03-27 03:12:36 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 680/1251] eta: 0:04:50 lr: 0.000054 loss: 2.9321 (2.7441) grad_norm: 2.6727 (3.0691) time: 0.5073 [2021-03-27 03:12:41 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 690/1251] eta: 0:04:45 lr: 0.000054 loss: 2.9459 (2.7470) grad_norm: 2.6825 (3.0633) time: 0.5033 [2021-03-27 03:12:46 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 700/1251] eta: 0:04:40 lr: 0.000054 loss: 2.8591 (2.7455) grad_norm: 2.6477 (3.0589) time: 0.4899 [2021-03-27 03:12:51 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 710/1251] eta: 0:04:35 lr: 0.000054 loss: 2.7894 (2.7466) grad_norm: 2.6980 (3.0548) time: 0.5006 [2021-03-27 03:12:56 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 720/1251] eta: 0:04:30 lr: 0.000054 loss: 2.7894 (2.7459) grad_norm: 2.8733 (3.0550) time: 0.5123 [2021-03-27 03:13:02 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 730/1251] eta: 0:04:25 lr: 0.000054 loss: 2.5974 (2.7437) grad_norm: 2.8733 (3.0536) time: 0.5093 [2021-03-27 03:13:07 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 740/1251] eta: 0:04:20 lr: 0.000054 loss: 2.5823 (2.7436) grad_norm: 2.8581 (3.0517) time: 0.5168 [2021-03-27 03:13:12 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 750/1251] eta: 0:04:14 lr: 0.000054 loss: 2.9410 (2.7467) grad_norm: 2.8297 (3.0479) time: 0.5144 [2021-03-27 03:13:17 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 760/1251] eta: 0:04:09 lr: 0.000054 loss: 3.0348 (2.7481) grad_norm: 2.7850 (3.0503) time: 0.5030 [2021-03-27 03:13:22 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 770/1251] eta: 0:04:04 lr: 0.000054 loss: 2.8140 (2.7461) grad_norm: 2.8605 (3.0475) time: 0.5101 [2021-03-27 03:13:27 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 780/1251] eta: 0:03:59 lr: 0.000054 loss: 2.8140 (2.7478) grad_norm: 2.8605 (3.0451) time: 0.5097 [2021-03-27 03:13:32 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 790/1251] eta: 0:03:54 lr: 0.000054 loss: 2.8233 (2.7469) grad_norm: 2.8258 (3.0438) time: 0.5011 [2021-03-27 03:13:37 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 800/1251] eta: 0:03:49 lr: 0.000054 loss: 2.7443 (2.7440) grad_norm: 2.8652 (3.0427) time: 0.5009 [2021-03-27 03:13:42 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 810/1251] eta: 0:03:44 lr: 0.000054 loss: 2.7767 (2.7456) grad_norm: 2.8931 (3.0443) time: 0.5053 [2021-03-27 03:13:47 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 820/1251] eta: 0:03:39 lr: 0.000054 loss: 2.7966 (2.7456) grad_norm: 2.8672 (3.0436) time: 0.5099 [2021-03-27 03:13:52 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 830/1251] eta: 0:03:34 lr: 0.000054 loss: 2.8066 (2.7460) grad_norm: 2.8177 (3.0426) time: 0.5102 [2021-03-27 03:13:57 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 840/1251] eta: 0:03:29 lr: 0.000053 loss: 2.8863 (2.7452) grad_norm: 2.9607 (3.0452) time: 0.5072 [2021-03-27 03:14:02 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 850/1251] eta: 0:03:23 lr: 0.000053 loss: 2.7333 (2.7463) grad_norm: 3.0318 (3.0451) time: 0.5064 [2021-03-27 03:14:08 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 860/1251] eta: 0:03:18 lr: 0.000053 loss: 2.6958 (2.7432) grad_norm: 2.8061 (3.0468) time: 0.5061 [2021-03-27 03:14:13 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 870/1251] eta: 0:03:13 lr: 0.000053 loss: 2.5200 (2.7427) grad_norm: 2.8046 (3.0453) time: 0.5086 [2021-03-27 03:14:18 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 880/1251] eta: 0:03:08 lr: 0.000053 loss: 2.8044 (2.7442) grad_norm: 2.8010 (3.0428) time: 0.5093 [2021-03-27 03:14:23 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 890/1251] eta: 0:03:03 lr: 0.000053 loss: 2.9572 (2.7456) grad_norm: 2.8843 (3.0477) time: 0.5070 [2021-03-27 03:14:28 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 900/1251] eta: 0:02:58 lr: 0.000053 loss: 2.9280 (2.7470) grad_norm: 2.9291 (3.0564) time: 0.5080 [2021-03-27 03:14:33 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 910/1251] eta: 0:02:53 lr: 0.000053 loss: 2.8426 (2.7468) grad_norm: 2.7879 (3.0542) time: 0.5116 [2021-03-27 03:14:38 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 920/1251] eta: 0:02:48 lr: 0.000053 loss: 2.8894 (2.7475) grad_norm: 2.7879 (3.0511) time: 0.5068 [2021-03-27 03:14:43 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 930/1251] eta: 0:02:43 lr: 0.000053 loss: 2.7357 (2.7468) grad_norm: 2.7641 (3.0505) time: 0.5044 [2021-03-27 03:14:48 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 940/1251] eta: 0:02:38 lr: 0.000053 loss: 2.7357 (2.7471) grad_norm: 2.6989 (3.0475) time: 0.5049 [2021-03-27 03:14:53 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 950/1251] eta: 0:02:33 lr: 0.000053 loss: 2.9184 (2.7489) grad_norm: 2.7858 (3.0509) time: 0.5134 [2021-03-27 03:14:58 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 960/1251] eta: 0:02:28 lr: 0.000053 loss: 2.9184 (2.7503) grad_norm: 2.8523 (3.0481) time: 0.5172 [2021-03-27 03:15:04 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 970/1251] eta: 0:02:22 lr: 0.000053 loss: 2.9101 (2.7525) grad_norm: 2.8909 (3.0478) time: 0.5120 [2021-03-27 03:15:09 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 980/1251] eta: 0:02:17 lr: 0.000053 loss: 2.9101 (2.7531) grad_norm: 2.8208 (3.0453) time: 0.5052 [2021-03-27 03:15:14 swin_small_patch4_window7_224] INFO: Epoch: [259] [ 990/1251] eta: 0:02:12 lr: 0.000053 loss: 2.8556 (2.7530) grad_norm: 2.8330 (3.0454) time: 0.5015 [2021-03-27 03:15:19 swin_small_patch4_window7_224] INFO: Epoch: [259] [1000/1251] eta: 0:02:07 lr: 0.000053 loss: 2.8926 (2.7541) grad_norm: 2.9043 (3.0464) time: 0.5034 [2021-03-27 03:15:24 swin_small_patch4_window7_224] INFO: Epoch: [259] [1010/1251] eta: 0:02:02 lr: 0.000053 loss: 2.9430 (2.7540) grad_norm: 2.8586 (3.0462) time: 0.5032 [2021-03-27 03:15:29 swin_small_patch4_window7_224] INFO: Epoch: [259] [1020/1251] eta: 0:01:57 lr: 0.000053 loss: 2.7789 (2.7535) grad_norm: 2.7949 (3.0462) time: 0.5128 [2021-03-27 03:15:34 swin_small_patch4_window7_224] INFO: Epoch: [259] [1030/1251] eta: 0:01:52 lr: 0.000053 loss: 2.7617 (2.7533) grad_norm: 2.7164 (3.0437) time: 0.5102 [2021-03-27 03:15:39 swin_small_patch4_window7_224] INFO: Epoch: [259] [1040/1251] eta: 0:01:47 lr: 0.000053 loss: 2.7617 (2.7540) grad_norm: 2.8593 (3.0451) time: 0.5062 [2021-03-27 03:15:44 swin_small_patch4_window7_224] INFO: Epoch: [259] [1050/1251] eta: 0:01:42 lr: 0.000053 loss: 2.9962 (2.7567) grad_norm: 2.8924 (3.0434) time: 0.5031 [2021-03-27 03:15:49 swin_small_patch4_window7_224] INFO: Epoch: [259] [1060/1251] eta: 0:01:37 lr: 0.000053 loss: 2.9085 (2.7556) grad_norm: 2.8719 (3.0431) time: 0.4956 [2021-03-27 03:15:54 swin_small_patch4_window7_224] INFO: Epoch: [259] [1070/1251] eta: 0:01:31 lr: 0.000053 loss: 2.6518 (2.7554) grad_norm: 2.7368 (3.0405) time: 0.4982 [2021-03-27 03:15:59 swin_small_patch4_window7_224] INFO: Epoch: [259] [1080/1251] eta: 0:01:26 lr: 0.000053 loss: 2.8475 (2.7563) grad_norm: 2.6556 (3.0386) time: 0.5002 [2021-03-27 03:16:04 swin_small_patch4_window7_224] INFO: Epoch: [259] [1090/1251] eta: 0:01:21 lr: 0.000053 loss: 3.0101 (2.7567) grad_norm: 2.7674 (3.0376) time: 0.4991 [2021-03-27 03:16:09 swin_small_patch4_window7_224] INFO: Epoch: [259] [1100/1251] eta: 0:01:16 lr: 0.000053 loss: 2.8696 (2.7564) grad_norm: 2.7444 (3.0340) time: 0.4975 [2021-03-27 03:16:14 swin_small_patch4_window7_224] INFO: Epoch: [259] [1110/1251] eta: 0:01:11 lr: 0.000053 loss: 2.7722 (2.7578) grad_norm: 2.7138 (3.0326) time: 0.4966 [2021-03-27 03:16:19 swin_small_patch4_window7_224] INFO: Epoch: [259] [1120/1251] eta: 0:01:06 lr: 0.000053 loss: 2.8779 (2.7586) grad_norm: 2.8294 (3.0313) time: 0.4978 [2021-03-27 03:16:24 swin_small_patch4_window7_224] INFO: Epoch: [259] [1130/1251] eta: 0:01:01 lr: 0.000053 loss: 2.8314 (2.7585) grad_norm: 2.7323 (3.0287) time: 0.4969 [2021-03-27 03:16:29 swin_small_patch4_window7_224] INFO: Epoch: [259] [1140/1251] eta: 0:00:56 lr: 0.000053 loss: 2.7973 (2.7585) grad_norm: 2.6841 (3.0331) time: 0.5024 [2021-03-27 03:16:34 swin_small_patch4_window7_224] INFO: Epoch: [259] [1150/1251] eta: 0:00:51 lr: 0.000053 loss: 2.7973 (2.7584) grad_norm: 2.8999 (3.0317) time: 0.5032 [2021-03-27 03:16:39 swin_small_patch4_window7_224] INFO: Epoch: [259] [1160/1251] eta: 0:00:46 lr: 0.000053 loss: 2.7783 (2.7586) grad_norm: 2.7306 (3.0296) time: 0.5010 [2021-03-27 03:16:44 swin_small_patch4_window7_224] INFO: Epoch: [259] [1170/1251] eta: 0:00:41 lr: 0.000053 loss: 2.8757 (2.7584) grad_norm: 2.7306 (3.0271) time: 0.5028 [2021-03-27 03:16:49 swin_small_patch4_window7_224] INFO: Epoch: [259] [1180/1251] eta: 0:00:36 lr: 0.000053 loss: 2.8927 (2.7592) grad_norm: 2.6469 (3.0250) time: 0.4998 [2021-03-27 03:16:54 swin_small_patch4_window7_224] INFO: Epoch: [259] [1190/1251] eta: 0:00:30 lr: 0.000053 loss: 2.8857 (2.7589) grad_norm: 2.6469 (3.0250) time: 0.4990 [2021-03-27 03:16:59 swin_small_patch4_window7_224] INFO: Epoch: [259] [1200/1251] eta: 0:00:25 lr: 0.000053 loss: 2.8900 (2.7604) grad_norm: 2.7305 (3.0241) time: 0.4971 [2021-03-27 03:17:04 swin_small_patch4_window7_224] INFO: Epoch: [259] [1210/1251] eta: 0:00:20 lr: 0.000053 loss: 2.8557 (2.7589) grad_norm: 2.7305 (3.0222) time: 0.4956 [2021-03-27 03:17:09 swin_small_patch4_window7_224] INFO: Epoch: [259] [1220/1251] eta: 0:00:15 lr: 0.000053 loss: 2.8022 (2.7590) grad_norm: 2.7196 (3.0215) time: 0.4972 [2021-03-27 03:17:14 swin_small_patch4_window7_224] INFO: Epoch: [259] [1230/1251] eta: 0:00:10 lr: 0.000053 loss: 2.8471 (2.7600) grad_norm: 2.6910 (3.0192) time: 0.4993 [2021-03-27 03:17:19 swin_small_patch4_window7_224] INFO: Epoch: [259] [1240/1251] eta: 0:00:05 lr: 0.000053 loss: 2.8000 (2.7585) grad_norm: 2.7708 (3.0190) time: 0.5004 [2021-03-27 03:17:24 swin_small_patch4_window7_224] INFO: Epoch: [259] [1250/1251] eta: 0:00:00 lr: 0.000053 loss: 2.6772 (2.7583) grad_norm: 2.8210 (3.0198) time: 0.5055 [2021-03-27 03:17:36 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:42 loss: 0.7799 (0.7799) acc1: 76.5625 (76.5625) acc5: 96.8750 (96.8750) [2021-03-27 03:17:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.6772 (0.7271) acc1: 84.3750 (82.8125) acc5: 96.8750 (96.3068) [2021-03-27 03:17:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7514 (0.7671) acc1: 82.8125 (81.8452) acc5: 95.3125 (96.2054) [2021-03-27 03:17:42 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7427 (0.7355) acc1: 82.8125 (82.5101) acc5: 96.8750 (96.4214) [2021-03-27 03:17:44 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6992 (0.7483) acc1: 82.8125 (82.5076) acc5: 96.8750 (96.2271) [2021-03-27 03:17:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7907 (0.7611) acc1: 81.2500 (82.0480) acc5: 96.8750 (96.1920) [2021-03-27 03:17:59 swin_small_patch4_window7_224] INFO: * Acc@1 82.552 Acc@5 96.148 loss 0.753 [2021-03-27 03:17:59 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.6% [2021-03-27 03:17:59 swin_small_patch4_window7_224] INFO: Max accuracy: 82.55% [2021-03-27 03:18:03 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 0/1251] eta: 1:31:53 lr: 0.000053 loss: 3.2928 (3.2928) grad_norm: 2.3114 (2.3114) time: 4.4076 [2021-03-27 03:18:08 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 10/1251] eta: 0:17:44 lr: 0.000053 loss: 2.9262 (2.8285) grad_norm: 2.9122 (3.0615) time: 0.8580 [2021-03-27 03:18:13 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 20/1251] eta: 0:14:10 lr: 0.000053 loss: 2.9568 (2.7978) grad_norm: 2.9122 (3.0456) time: 0.5047 [2021-03-27 03:18:18 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 30/1251] eta: 0:12:52 lr: 0.000053 loss: 3.0071 (2.8698) grad_norm: 2.8082 (2.9314) time: 0.5088 [2021-03-27 03:18:23 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 40/1251] eta: 0:12:13 lr: 0.000053 loss: 2.9268 (2.8174) grad_norm: 2.7747 (2.9184) time: 0.5161 [2021-03-27 03:18:29 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 50/1251] eta: 0:11:46 lr: 0.000053 loss: 2.8516 (2.8051) grad_norm: 2.8052 (2.9112) time: 0.5195 [2021-03-27 03:18:34 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 60/1251] eta: 0:11:25 lr: 0.000053 loss: 2.8291 (2.8179) grad_norm: 2.8060 (2.9131) time: 0.5131 [2021-03-27 03:18:39 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 70/1251] eta: 0:11:08 lr: 0.000053 loss: 2.7900 (2.8015) grad_norm: 2.7517 (2.9046) time: 0.5098 [2021-03-27 03:18:44 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 80/1251] eta: 0:10:53 lr: 0.000053 loss: 2.6378 (2.7968) grad_norm: 2.6821 (2.8800) time: 0.5067 [2021-03-27 03:18:49 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 90/1251] eta: 0:10:41 lr: 0.000053 loss: 2.8284 (2.8004) grad_norm: 2.7231 (2.8681) time: 0.5029 [2021-03-27 03:18:54 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 100/1251] eta: 0:10:29 lr: 0.000053 loss: 3.0265 (2.8132) grad_norm: 2.9384 (2.8955) time: 0.4996 [2021-03-27 03:18:59 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 110/1251] eta: 0:10:19 lr: 0.000053 loss: 3.0480 (2.8201) grad_norm: 3.0594 (2.9677) time: 0.5003 [2021-03-27 03:19:04 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 120/1251] eta: 0:10:10 lr: 0.000053 loss: 3.0785 (2.8399) grad_norm: 3.0594 (2.9699) time: 0.5069 [2021-03-27 03:19:09 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 130/1251] eta: 0:10:02 lr: 0.000053 loss: 3.0779 (2.8470) grad_norm: 2.8778 (2.9738) time: 0.5091 [2021-03-27 03:19:14 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 140/1251] eta: 0:09:54 lr: 0.000053 loss: 2.9445 (2.8439) grad_norm: 2.8778 (2.9864) time: 0.5074 [2021-03-27 03:19:19 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 150/1251] eta: 0:09:47 lr: 0.000053 loss: 2.9445 (2.8418) grad_norm: 2.7634 (2.9852) time: 0.5059 [2021-03-27 03:19:24 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 160/1251] eta: 0:09:40 lr: 0.000053 loss: 2.7174 (2.8312) grad_norm: 2.7885 (2.9771) time: 0.5064 [2021-03-27 03:19:29 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 170/1251] eta: 0:09:33 lr: 0.000053 loss: 2.7113 (2.8257) grad_norm: 2.7885 (2.9944) time: 0.5086 [2021-03-27 03:19:34 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 180/1251] eta: 0:09:27 lr: 0.000052 loss: 2.7128 (2.8287) grad_norm: 2.6826 (2.9802) time: 0.5127 [2021-03-27 03:19:40 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 190/1251] eta: 0:09:21 lr: 0.000052 loss: 2.9116 (2.8258) grad_norm: 2.7032 (2.9867) time: 0.5132 [2021-03-27 03:19:45 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 200/1251] eta: 0:09:13 lr: 0.000052 loss: 2.5073 (2.8094) grad_norm: 2.7032 (2.9690) time: 0.5033 [2021-03-27 03:19:49 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 210/1251] eta: 0:09:07 lr: 0.000052 loss: 2.6555 (2.8139) grad_norm: 2.7730 (2.9694) time: 0.4967 [2021-03-27 03:19:54 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 220/1251] eta: 0:09:00 lr: 0.000052 loss: 2.7540 (2.8041) grad_norm: 2.7918 (2.9690) time: 0.4986 [2021-03-27 03:19:59 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 230/1251] eta: 0:08:54 lr: 0.000052 loss: 2.7981 (2.8036) grad_norm: 2.7774 (2.9725) time: 0.4988 [2021-03-27 03:20:04 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 240/1251] eta: 0:08:48 lr: 0.000052 loss: 2.8752 (2.8040) grad_norm: 2.8090 (2.9685) time: 0.4983 [2021-03-27 03:20:10 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 250/1251] eta: 0:08:42 lr: 0.000052 loss: 2.9023 (2.8056) grad_norm: 2.8359 (2.9639) time: 0.5018 [2021-03-27 03:20:15 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 260/1251] eta: 0:08:36 lr: 0.000052 loss: 2.8238 (2.7987) grad_norm: 2.8818 (2.9732) time: 0.5047 [2021-03-27 03:20:20 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 270/1251] eta: 0:08:30 lr: 0.000052 loss: 2.8238 (2.8018) grad_norm: 3.1420 (2.9804) time: 0.5010 [2021-03-27 03:20:24 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 280/1251] eta: 0:08:24 lr: 0.000052 loss: 2.8777 (2.7976) grad_norm: 2.9074 (2.9763) time: 0.4974 [2021-03-27 03:20:29 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 290/1251] eta: 0:08:18 lr: 0.000052 loss: 2.7896 (2.7931) grad_norm: 2.8371 (2.9724) time: 0.4972 [2021-03-27 03:20:34 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 300/1251] eta: 0:08:12 lr: 0.000052 loss: 2.7812 (2.7902) grad_norm: 2.8802 (2.9790) time: 0.4970 [2021-03-27 03:20:39 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 310/1251] eta: 0:08:06 lr: 0.000052 loss: 2.7950 (2.7880) grad_norm: 2.7756 (2.9742) time: 0.4979 [2021-03-27 03:20:44 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 320/1251] eta: 0:08:01 lr: 0.000052 loss: 2.7950 (2.7841) grad_norm: 2.7934 (2.9829) time: 0.5013 [2021-03-27 03:20:50 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 330/1251] eta: 0:07:55 lr: 0.000052 loss: 2.8033 (2.7769) grad_norm: 2.9341 (2.9819) time: 0.5061 [2021-03-27 03:20:55 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 340/1251] eta: 0:07:50 lr: 0.000052 loss: 2.9577 (2.7802) grad_norm: 2.8846 (2.9829) time: 0.5018 [2021-03-27 03:21:00 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 350/1251] eta: 0:07:44 lr: 0.000052 loss: 3.0345 (2.7818) grad_norm: 2.7870 (2.9781) time: 0.5013 [2021-03-27 03:21:05 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 360/1251] eta: 0:07:39 lr: 0.000052 loss: 2.9724 (2.7828) grad_norm: 2.9336 (2.9753) time: 0.5045 [2021-03-27 03:21:10 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 370/1251] eta: 0:07:33 lr: 0.000052 loss: 2.9724 (2.7889) grad_norm: 2.9680 (2.9809) time: 0.5019 [2021-03-27 03:21:15 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 380/1251] eta: 0:07:28 lr: 0.000052 loss: 2.8766 (2.7873) grad_norm: 2.8402 (2.9753) time: 0.5050 [2021-03-27 03:21:20 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 390/1251] eta: 0:07:23 lr: 0.000052 loss: 2.6417 (2.7825) grad_norm: 2.6838 (2.9721) time: 0.5065 [2021-03-27 03:21:25 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 400/1251] eta: 0:07:17 lr: 0.000052 loss: 2.8937 (2.7868) grad_norm: 2.8547 (2.9725) time: 0.5059 [2021-03-27 03:21:30 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 410/1251] eta: 0:07:12 lr: 0.000052 loss: 2.9789 (2.7863) grad_norm: 2.8666 (2.9682) time: 0.5056 [2021-03-27 03:21:35 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 420/1251] eta: 0:07:06 lr: 0.000052 loss: 2.9545 (2.7907) grad_norm: 2.8831 (2.9718) time: 0.5013 [2021-03-27 03:21:40 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 430/1251] eta: 0:07:01 lr: 0.000052 loss: 2.9071 (2.7920) grad_norm: 2.9087 (2.9695) time: 0.4999 [2021-03-27 03:21:45 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 440/1251] eta: 0:06:56 lr: 0.000052 loss: 2.7810 (2.7918) grad_norm: 2.9032 (2.9875) time: 0.5099 [2021-03-27 03:21:50 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 450/1251] eta: 0:06:51 lr: 0.000052 loss: 2.7502 (2.7875) grad_norm: 2.9539 (2.9935) time: 0.5141 [2021-03-27 03:21:55 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 460/1251] eta: 0:06:45 lr: 0.000052 loss: 2.5804 (2.7838) grad_norm: 2.9387 (2.9935) time: 0.5058 [2021-03-27 03:22:00 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 470/1251] eta: 0:06:40 lr: 0.000052 loss: 2.6738 (2.7848) grad_norm: 2.8761 (3.0025) time: 0.5010 [2021-03-27 03:22:05 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 480/1251] eta: 0:06:35 lr: 0.000052 loss: 2.7821 (2.7849) grad_norm: 2.6622 (3.0002) time: 0.5009 [2021-03-27 03:22:10 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 490/1251] eta: 0:06:30 lr: 0.000052 loss: 2.8203 (2.7872) grad_norm: 2.7941 (3.0013) time: 0.5036 [2021-03-27 03:22:15 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 500/1251] eta: 0:06:24 lr: 0.000052 loss: 2.8723 (2.7854) grad_norm: 2.8774 (3.0017) time: 0.5012 [2021-03-27 03:22:20 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 510/1251] eta: 0:06:19 lr: 0.000052 loss: 2.6988 (2.7813) grad_norm: 2.8580 (3.0028) time: 0.4975 [2021-03-27 03:22:25 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 520/1251] eta: 0:06:14 lr: 0.000052 loss: 2.8062 (2.7815) grad_norm: 2.8970 (2.9999) time: 0.4984 [2021-03-27 03:22:30 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 530/1251] eta: 0:06:08 lr: 0.000052 loss: 2.8255 (2.7806) grad_norm: 2.8410 (2.9987) time: 0.4975 [2021-03-27 03:22:35 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 540/1251] eta: 0:06:03 lr: 0.000052 loss: 2.7733 (2.7824) grad_norm: 2.8190 (2.9990) time: 0.5076 [2021-03-27 03:22:40 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 550/1251] eta: 0:05:58 lr: 0.000052 loss: 3.0503 (2.7860) grad_norm: 2.7167 (2.9958) time: 0.5140 [2021-03-27 03:22:45 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 560/1251] eta: 0:05:53 lr: 0.000052 loss: 2.9744 (2.7883) grad_norm: 2.6993 (2.9955) time: 0.5051 [2021-03-27 03:22:50 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 570/1251] eta: 0:05:48 lr: 0.000052 loss: 2.8170 (2.7853) grad_norm: 2.7431 (2.9924) time: 0.5007 [2021-03-27 03:22:55 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 580/1251] eta: 0:05:42 lr: 0.000052 loss: 2.6920 (2.7839) grad_norm: 2.7467 (2.9889) time: 0.4994 [2021-03-27 03:23:00 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 590/1251] eta: 0:05:37 lr: 0.000052 loss: 2.7689 (2.7852) grad_norm: 2.7491 (2.9887) time: 0.5004 [2021-03-27 03:23:06 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 600/1251] eta: 0:05:32 lr: 0.000052 loss: 2.8486 (2.7864) grad_norm: 2.9538 (2.9902) time: 0.5026 [2021-03-27 03:23:11 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 610/1251] eta: 0:05:27 lr: 0.000052 loss: 2.8061 (2.7842) grad_norm: 2.9494 (2.9883) time: 0.5007 [2021-03-27 03:23:16 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 620/1251] eta: 0:05:21 lr: 0.000052 loss: 2.7626 (2.7843) grad_norm: 2.9295 (2.9859) time: 0.5007 [2021-03-27 03:23:21 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 630/1251] eta: 0:05:16 lr: 0.000052 loss: 2.5946 (2.7797) grad_norm: 2.9874 (2.9892) time: 0.5085 [2021-03-27 03:23:26 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 640/1251] eta: 0:05:11 lr: 0.000052 loss: 2.5767 (2.7776) grad_norm: 3.0014 (2.9944) time: 0.5156 [2021-03-27 03:23:31 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 650/1251] eta: 0:05:06 lr: 0.000052 loss: 2.8985 (2.7784) grad_norm: 2.8814 (2.9923) time: 0.5085 [2021-03-27 03:23:36 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 660/1251] eta: 0:05:01 lr: 0.000052 loss: 2.8985 (2.7807) grad_norm: 2.7833 (2.9906) time: 0.5009 [2021-03-27 03:23:41 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 670/1251] eta: 0:04:56 lr: 0.000052 loss: 2.9026 (2.7837) grad_norm: 2.9080 (2.9939) time: 0.5076 [2021-03-27 03:23:46 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 680/1251] eta: 0:04:51 lr: 0.000052 loss: 2.9026 (2.7864) grad_norm: 2.9025 (2.9912) time: 0.5085 [2021-03-27 03:23:51 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 690/1251] eta: 0:04:46 lr: 0.000052 loss: 2.8753 (2.7873) grad_norm: 2.8153 (2.9918) time: 0.5004 [2021-03-27 03:23:56 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 700/1251] eta: 0:04:40 lr: 0.000052 loss: 2.9239 (2.7893) grad_norm: 2.8633 (2.9938) time: 0.5024 [2021-03-27 03:24:01 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 710/1251] eta: 0:04:35 lr: 0.000052 loss: 2.9519 (2.7895) grad_norm: 2.9941 (3.0269) time: 0.5055 [2021-03-27 03:24:06 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 720/1251] eta: 0:04:30 lr: 0.000052 loss: 2.8316 (2.7894) grad_norm: 3.0683 (3.0393) time: 0.5034 [2021-03-27 03:24:11 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 730/1251] eta: 0:04:25 lr: 0.000052 loss: 2.8316 (2.7887) grad_norm: 3.0496 (3.0380) time: 0.5088 [2021-03-27 03:24:16 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 740/1251] eta: 0:04:20 lr: 0.000052 loss: 2.9660 (2.7905) grad_norm: 3.0496 (3.0447) time: 0.5138 [2021-03-27 03:24:21 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 750/1251] eta: 0:04:15 lr: 0.000052 loss: 2.8141 (2.7883) grad_norm: 3.0024 (3.0418) time: 0.5081 [2021-03-27 03:24:26 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 760/1251] eta: 0:04:10 lr: 0.000052 loss: 2.7049 (2.7901) grad_norm: 2.8747 (3.0411) time: 0.5011 [2021-03-27 03:24:31 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 770/1251] eta: 0:04:05 lr: 0.000052 loss: 2.9163 (2.7896) grad_norm: 3.0664 (3.0426) time: 0.4989 [2021-03-27 03:24:37 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 780/1251] eta: 0:03:59 lr: 0.000051 loss: 2.8656 (2.7893) grad_norm: 3.0188 (3.0423) time: 0.5070 [2021-03-27 03:24:42 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 790/1251] eta: 0:03:54 lr: 0.000051 loss: 2.8227 (2.7903) grad_norm: 2.7301 (3.0398) time: 0.5121 [2021-03-27 03:24:47 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 800/1251] eta: 0:03:49 lr: 0.000051 loss: 2.9881 (2.7939) grad_norm: 2.9249 (3.0388) time: 0.5080 [2021-03-27 03:24:52 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 810/1251] eta: 0:03:44 lr: 0.000051 loss: 2.7306 (2.7912) grad_norm: 2.9404 (3.0360) time: 0.5031 [2021-03-27 03:24:57 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 820/1251] eta: 0:03:39 lr: 0.000051 loss: 2.6411 (2.7923) grad_norm: 2.7886 (3.0357) time: 0.5059 [2021-03-27 03:25:02 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 830/1251] eta: 0:03:34 lr: 0.000051 loss: 2.7196 (2.7913) grad_norm: 3.0698 (3.0378) time: 0.5141 [2021-03-27 03:25:07 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 840/1251] eta: 0:03:29 lr: 0.000051 loss: 2.7196 (2.7909) grad_norm: 3.0344 (3.0381) time: 0.5070 [2021-03-27 03:25:12 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 850/1251] eta: 0:03:24 lr: 0.000051 loss: 2.9240 (2.7928) grad_norm: 2.9908 (3.0425) time: 0.5014 [2021-03-27 03:25:17 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 860/1251] eta: 0:03:19 lr: 0.000051 loss: 2.8405 (2.7907) grad_norm: 3.0146 (3.0420) time: 0.5081 [2021-03-27 03:25:22 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 870/1251] eta: 0:03:14 lr: 0.000051 loss: 2.7952 (2.7905) grad_norm: 2.9263 (3.0412) time: 0.5134 [2021-03-27 03:25:27 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 880/1251] eta: 0:03:08 lr: 0.000051 loss: 2.8689 (2.7898) grad_norm: 2.8847 (3.0389) time: 0.5107 [2021-03-27 03:25:32 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 890/1251] eta: 0:03:03 lr: 0.000051 loss: 2.8689 (2.7903) grad_norm: 2.9220 (3.0376) time: 0.5071 [2021-03-27 03:25:38 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 900/1251] eta: 0:02:58 lr: 0.000051 loss: 2.8251 (2.7862) grad_norm: 2.9464 (3.0405) time: 0.5101 [2021-03-27 03:25:43 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 910/1251] eta: 0:02:53 lr: 0.000051 loss: 2.7391 (2.7860) grad_norm: 3.0561 (3.0474) time: 0.5110 [2021-03-27 03:25:48 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 920/1251] eta: 0:02:48 lr: 0.000051 loss: 2.7959 (2.7857) grad_norm: 3.0906 (3.0467) time: 0.5076 [2021-03-27 03:25:53 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 930/1251] eta: 0:02:43 lr: 0.000051 loss: 2.8236 (2.7859) grad_norm: 3.0320 (3.0477) time: 0.5066 [2021-03-27 03:25:58 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 940/1251] eta: 0:02:38 lr: 0.000051 loss: 2.8956 (2.7867) grad_norm: 2.9741 (3.0479) time: 0.5122 [2021-03-27 03:26:03 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 950/1251] eta: 0:02:33 lr: 0.000051 loss: 2.9146 (2.7870) grad_norm: 2.9348 (3.0499) time: 0.5072 [2021-03-27 03:26:08 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 960/1251] eta: 0:02:28 lr: 0.000051 loss: 2.8433 (2.7840) grad_norm: 2.9348 (3.0490) time: 0.4952 [2021-03-27 03:26:13 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 970/1251] eta: 0:02:23 lr: 0.000051 loss: 2.8174 (2.7851) grad_norm: 2.8065 (3.0527) time: 0.4974 [2021-03-27 03:26:18 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 980/1251] eta: 0:02:17 lr: 0.000051 loss: 2.8613 (2.7836) grad_norm: 2.8209 (3.0576) time: 0.5011 [2021-03-27 03:26:23 swin_small_patch4_window7_224] INFO: Epoch: [260] [ 990/1251] eta: 0:02:12 lr: 0.000051 loss: 2.8917 (2.7848) grad_norm: 2.8330 (3.0577) time: 0.5056 [2021-03-27 03:26:28 swin_small_patch4_window7_224] INFO: Epoch: [260] [1000/1251] eta: 0:02:07 lr: 0.000051 loss: 2.7786 (2.7832) grad_norm: 2.8330 (3.0555) time: 0.5089 [2021-03-27 03:26:33 swin_small_patch4_window7_224] INFO: Epoch: [260] [1010/1251] eta: 0:02:02 lr: 0.000051 loss: 2.7112 (2.7833) grad_norm: 2.9160 (3.0536) time: 0.5051 [2021-03-27 03:26:38 swin_small_patch4_window7_224] INFO: Epoch: [260] [1020/1251] eta: 0:01:57 lr: 0.000051 loss: 2.7589 (2.7831) grad_norm: 2.9160 (3.0529) time: 0.5073 [2021-03-27 03:26:43 swin_small_patch4_window7_224] INFO: Epoch: [260] [1030/1251] eta: 0:01:52 lr: 0.000051 loss: 3.0103 (2.7857) grad_norm: 2.9673 (3.0524) time: 0.5032 [2021-03-27 03:26:48 swin_small_patch4_window7_224] INFO: Epoch: [260] [1040/1251] eta: 0:01:47 lr: 0.000051 loss: 3.0103 (2.7871) grad_norm: 2.8065 (3.0488) time: 0.4978 [2021-03-27 03:26:53 swin_small_patch4_window7_224] INFO: Epoch: [260] [1050/1251] eta: 0:01:42 lr: 0.000051 loss: 2.9793 (2.7877) grad_norm: 2.6946 (3.0516) time: 0.5068 [2021-03-27 03:26:58 swin_small_patch4_window7_224] INFO: Epoch: [260] [1060/1251] eta: 0:01:37 lr: 0.000051 loss: 2.9650 (2.7877) grad_norm: 2.7993 (3.0513) time: 0.5053 [2021-03-27 03:27:03 swin_small_patch4_window7_224] INFO: Epoch: [260] [1070/1251] eta: 0:01:32 lr: 0.000051 loss: 2.8175 (2.7867) grad_norm: 2.9937 (3.0552) time: 0.5010 [2021-03-27 03:27:08 swin_small_patch4_window7_224] INFO: Epoch: [260] [1080/1251] eta: 0:01:26 lr: 0.000051 loss: 2.8175 (2.7859) grad_norm: 2.8804 (3.0532) time: 0.5048 [2021-03-27 03:27:13 swin_small_patch4_window7_224] INFO: Epoch: [260] [1090/1251] eta: 0:01:21 lr: 0.000051 loss: 2.7322 (2.7843) grad_norm: 2.7935 (3.0523) time: 0.5009 [2021-03-27 03:27:18 swin_small_patch4_window7_224] INFO: Epoch: [260] [1100/1251] eta: 0:01:16 lr: 0.000051 loss: 2.8415 (2.7853) grad_norm: 2.9756 (3.0528) time: 0.5010 [2021-03-27 03:27:23 swin_small_patch4_window7_224] INFO: Epoch: [260] [1110/1251] eta: 0:01:11 lr: 0.000051 loss: 2.8415 (2.7826) grad_norm: 3.0636 (3.0585) time: 0.5018 [2021-03-27 03:27:29 swin_small_patch4_window7_224] INFO: Epoch: [260] [1120/1251] eta: 0:01:06 lr: 0.000051 loss: 2.7122 (2.7816) grad_norm: 3.0058 (3.0598) time: 0.5018 [2021-03-27 03:27:34 swin_small_patch4_window7_224] INFO: Epoch: [260] [1130/1251] eta: 0:01:01 lr: 0.000051 loss: 2.8173 (2.7817) grad_norm: 2.7942 (3.0588) time: 0.5084 [2021-03-27 03:27:39 swin_small_patch4_window7_224] INFO: Epoch: [260] [1140/1251] eta: 0:00:56 lr: 0.000051 loss: 2.8329 (2.7822) grad_norm: 2.8167 (3.0587) time: 0.5091 [2021-03-27 03:27:44 swin_small_patch4_window7_224] INFO: Epoch: [260] [1150/1251] eta: 0:00:51 lr: 0.000051 loss: 2.8501 (2.7816) grad_norm: 2.8201 (3.0585) time: 0.5043 [2021-03-27 03:27:49 swin_small_patch4_window7_224] INFO: Epoch: [260] [1160/1251] eta: 0:00:46 lr: 0.000051 loss: 2.9396 (2.7828) grad_norm: 2.9123 (3.0623) time: 0.5024 [2021-03-27 03:27:54 swin_small_patch4_window7_224] INFO: Epoch: [260] [1170/1251] eta: 0:00:41 lr: 0.000051 loss: 3.0601 (2.7845) grad_norm: 3.1548 (3.0626) time: 0.5044 [2021-03-27 03:27:59 swin_small_patch4_window7_224] INFO: Epoch: [260] [1180/1251] eta: 0:00:36 lr: 0.000051 loss: 2.8609 (2.7815) grad_norm: 3.0833 (3.0634) time: 0.5046 [2021-03-27 03:28:04 swin_small_patch4_window7_224] INFO: Epoch: [260] [1190/1251] eta: 0:00:30 lr: 0.000051 loss: 2.7706 (2.7821) grad_norm: 3.0677 (3.0629) time: 0.5023 [2021-03-27 03:28:09 swin_small_patch4_window7_224] INFO: Epoch: [260] [1200/1251] eta: 0:00:25 lr: 0.000051 loss: 2.9015 (2.7826) grad_norm: 2.9711 (3.0636) time: 0.4969 [2021-03-27 03:28:14 swin_small_patch4_window7_224] INFO: Epoch: [260] [1210/1251] eta: 0:00:20 lr: 0.000051 loss: 2.8870 (2.7836) grad_norm: 2.9711 (3.0636) time: 0.4958 [2021-03-27 03:28:19 swin_small_patch4_window7_224] INFO: Epoch: [260] [1220/1251] eta: 0:00:15 lr: 0.000051 loss: 2.9118 (2.7834) grad_norm: 2.8502 (3.0616) time: 0.5037 [2021-03-27 03:28:24 swin_small_patch4_window7_224] INFO: Epoch: [260] [1230/1251] eta: 0:00:10 lr: 0.000051 loss: 2.9293 (2.7847) grad_norm: 2.8130 (3.0670) time: 0.5059 [2021-03-27 03:28:29 swin_small_patch4_window7_224] INFO: Epoch: [260] [1240/1251] eta: 0:00:05 lr: 0.000051 loss: 2.9293 (2.7849) grad_norm: 2.9421 (3.0670) time: 0.5036 [2021-03-27 03:28:34 swin_small_patch4_window7_224] INFO: Epoch: [260] [1250/1251] eta: 0:00:00 lr: 0.000051 loss: 2.6751 (2.7825) grad_norm: 2.8976 (3.0654) time: 0.4995 [2021-03-27 03:29:34 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.7320 (0.7320) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 03:29:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7320 (0.7362) acc1: 79.6875 (81.6761) acc5: 96.8750 (96.1648) [2021-03-27 03:29:36 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7560 (0.7707) acc1: 81.2500 (81.8452) acc5: 96.8750 (96.0565) [2021-03-27 03:29:37 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7560 (0.7720) acc1: 81.2500 (81.7036) acc5: 95.3125 (95.9677) [2021-03-27 03:29:38 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7324 (0.7648) acc1: 81.2500 (81.7454) acc5: 95.3125 (96.0366) [2021-03-27 03:29:39 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7267 (0.7562) acc1: 81.2500 (81.8560) acc5: 96.8750 (96.3200) [2021-03-27 03:29:57 swin_small_patch4_window7_224] INFO: * Acc@1 82.610 Acc@5 96.182 loss 0.743 [2021-03-27 03:29:57 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.6% [2021-03-27 03:29:57 swin_small_patch4_window7_224] INFO: Max accuracy: 82.61% [2021-03-27 03:30:01 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 0/1251] eta: 1:26:58 lr: 0.000051 loss: 3.1134 (3.1134) grad_norm: 2.7255 (2.7255) time: 4.1712 [2021-03-27 03:30:06 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 10/1251] eta: 0:17:38 lr: 0.000051 loss: 2.9809 (2.7519) grad_norm: 2.8271 (3.0581) time: 0.8528 [2021-03-27 03:30:11 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 20/1251] eta: 0:14:04 lr: 0.000051 loss: 2.9610 (2.8269) grad_norm: 2.8396 (3.1297) time: 0.5115 [2021-03-27 03:30:16 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 30/1251] eta: 0:12:42 lr: 0.000051 loss: 2.8744 (2.7811) grad_norm: 2.9389 (3.0597) time: 0.4996 [2021-03-27 03:30:21 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 40/1251] eta: 0:12:00 lr: 0.000051 loss: 2.7987 (2.7911) grad_norm: 2.9264 (3.0317) time: 0.4998 [2021-03-27 03:30:26 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 50/1251] eta: 0:11:36 lr: 0.000051 loss: 2.7152 (2.7446) grad_norm: 2.9072 (3.0654) time: 0.5099 [2021-03-27 03:30:31 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 60/1251] eta: 0:11:14 lr: 0.000051 loss: 2.5977 (2.7286) grad_norm: 2.8277 (3.0586) time: 0.5081 [2021-03-27 03:30:37 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 70/1251] eta: 0:11:01 lr: 0.000051 loss: 2.8728 (2.7245) grad_norm: 2.8277 (3.0404) time: 0.5103 [2021-03-27 03:30:42 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 80/1251] eta: 0:10:51 lr: 0.000051 loss: 2.6197 (2.6911) grad_norm: 2.8372 (3.0236) time: 0.5261 [2021-03-27 03:30:47 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 90/1251] eta: 0:10:39 lr: 0.000051 loss: 2.7609 (2.7081) grad_norm: 2.8475 (3.0344) time: 0.5169 [2021-03-27 03:30:52 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 100/1251] eta: 0:10:29 lr: 0.000051 loss: 2.8947 (2.7113) grad_norm: 2.8060 (3.0232) time: 0.5057 [2021-03-27 03:30:57 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 110/1251] eta: 0:10:21 lr: 0.000051 loss: 2.9132 (2.7172) grad_norm: 3.0485 (3.0505) time: 0.5166 [2021-03-27 03:31:02 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 120/1251] eta: 0:10:11 lr: 0.000051 loss: 2.7509 (2.7187) grad_norm: 3.0485 (3.0437) time: 0.5114 [2021-03-27 03:31:07 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 130/1251] eta: 0:10:02 lr: 0.000050 loss: 2.9352 (2.7275) grad_norm: 2.9801 (3.0524) time: 0.4986 [2021-03-27 03:31:12 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 140/1251] eta: 0:09:54 lr: 0.000050 loss: 2.8290 (2.7185) grad_norm: 3.0128 (3.0663) time: 0.5008 [2021-03-27 03:31:17 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 150/1251] eta: 0:09:47 lr: 0.000050 loss: 2.8243 (2.7288) grad_norm: 3.0128 (3.1058) time: 0.5049 [2021-03-27 03:31:22 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 160/1251] eta: 0:09:39 lr: 0.000050 loss: 2.9197 (2.7439) grad_norm: 2.8960 (3.0972) time: 0.5042 [2021-03-27 03:31:27 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 170/1251] eta: 0:09:32 lr: 0.000050 loss: 2.8496 (2.7431) grad_norm: 2.6881 (3.0671) time: 0.5019 [2021-03-27 03:31:32 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 180/1251] eta: 0:09:25 lr: 0.000050 loss: 2.7468 (2.7436) grad_norm: 2.7425 (3.0604) time: 0.5026 [2021-03-27 03:31:38 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 190/1251] eta: 0:09:19 lr: 0.000050 loss: 2.8881 (2.7494) grad_norm: 2.9141 (3.0619) time: 0.5107 [2021-03-27 03:31:43 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 200/1251] eta: 0:09:13 lr: 0.000050 loss: 2.8881 (2.7461) grad_norm: 3.0011 (3.0717) time: 0.5121 [2021-03-27 03:31:48 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 210/1251] eta: 0:09:06 lr: 0.000050 loss: 2.5609 (2.7372) grad_norm: 2.8048 (3.0684) time: 0.5016 [2021-03-27 03:31:53 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 220/1251] eta: 0:08:59 lr: 0.000050 loss: 2.8680 (2.7507) grad_norm: 2.7988 (inf) time: 0.4954 [2021-03-27 03:31:58 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 230/1251] eta: 0:08:53 lr: 0.000050 loss: 2.9525 (2.7512) grad_norm: 3.1532 (inf) time: 0.4973 [2021-03-27 03:32:03 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 240/1251] eta: 0:08:47 lr: 0.000050 loss: 2.6273 (2.7495) grad_norm: 3.0991 (inf) time: 0.5041 [2021-03-27 03:32:08 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 250/1251] eta: 0:08:41 lr: 0.000050 loss: 2.5802 (2.7421) grad_norm: 2.9118 (inf) time: 0.5029 [2021-03-27 03:32:13 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 260/1251] eta: 0:08:35 lr: 0.000050 loss: 2.5709 (2.7354) grad_norm: 2.7231 (inf) time: 0.5004 [2021-03-27 03:32:18 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 270/1251] eta: 0:08:29 lr: 0.000050 loss: 2.8221 (2.7388) grad_norm: 2.7560 (inf) time: 0.5037 [2021-03-27 03:32:23 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 280/1251] eta: 0:08:24 lr: 0.000050 loss: 2.8067 (2.7385) grad_norm: 2.8381 (inf) time: 0.5020 [2021-03-27 03:32:28 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 290/1251] eta: 0:08:18 lr: 0.000050 loss: 2.8148 (2.7456) grad_norm: 2.9076 (inf) time: 0.5054 [2021-03-27 03:32:33 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 300/1251] eta: 0:08:12 lr: 0.000050 loss: 2.8461 (2.7462) grad_norm: 3.0125 (inf) time: 0.5033 [2021-03-27 03:32:38 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 310/1251] eta: 0:08:07 lr: 0.000050 loss: 2.8107 (2.7503) grad_norm: 2.8984 (inf) time: 0.5017 [2021-03-27 03:32:43 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 320/1251] eta: 0:08:01 lr: 0.000050 loss: 2.9634 (2.7517) grad_norm: 2.8254 (inf) time: 0.5054 [2021-03-27 03:32:48 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 330/1251] eta: 0:07:55 lr: 0.000050 loss: 2.9634 (2.7539) grad_norm: 2.9504 (inf) time: 0.5013 [2021-03-27 03:32:53 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 340/1251] eta: 0:07:50 lr: 0.000050 loss: 2.8154 (2.7488) grad_norm: 3.0742 (inf) time: 0.5012 [2021-03-27 03:32:58 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 350/1251] eta: 0:07:44 lr: 0.000050 loss: 2.7949 (2.7535) grad_norm: 3.0080 (inf) time: 0.4994 [2021-03-27 03:33:03 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 360/1251] eta: 0:07:39 lr: 0.000050 loss: 2.7308 (2.7487) grad_norm: 2.8271 (inf) time: 0.4975 [2021-03-27 03:33:08 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 370/1251] eta: 0:07:33 lr: 0.000050 loss: 2.7258 (2.7474) grad_norm: 2.7875 (inf) time: 0.4970 [2021-03-27 03:33:13 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 380/1251] eta: 0:07:28 lr: 0.000050 loss: 2.8546 (2.7469) grad_norm: 2.7754 (inf) time: 0.5039 [2021-03-27 03:33:18 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 390/1251] eta: 0:07:22 lr: 0.000050 loss: 2.6038 (2.7391) grad_norm: 2.8602 (inf) time: 0.5023 [2021-03-27 03:33:23 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 400/1251] eta: 0:07:17 lr: 0.000050 loss: 2.7917 (2.7449) grad_norm: 2.9442 (inf) time: 0.5010 [2021-03-27 03:33:28 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 410/1251] eta: 0:07:12 lr: 0.000050 loss: 2.9502 (2.7420) grad_norm: 3.0587 (inf) time: 0.5056 [2021-03-27 03:33:33 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 420/1251] eta: 0:07:06 lr: 0.000050 loss: 2.8690 (2.7441) grad_norm: 3.0174 (inf) time: 0.4987 [2021-03-27 03:33:38 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 430/1251] eta: 0:07:01 lr: 0.000050 loss: 2.8690 (2.7454) grad_norm: 2.8263 (inf) time: 0.5027 [2021-03-27 03:33:43 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 440/1251] eta: 0:06:55 lr: 0.000050 loss: 2.8221 (2.7456) grad_norm: 2.6552 (inf) time: 0.5052 [2021-03-27 03:33:48 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 450/1251] eta: 0:06:50 lr: 0.000050 loss: 2.8227 (2.7465) grad_norm: 2.7161 (inf) time: 0.5009 [2021-03-27 03:33:53 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 460/1251] eta: 0:06:45 lr: 0.000050 loss: 2.7523 (2.7423) grad_norm: 2.9865 (inf) time: 0.5044 [2021-03-27 03:33:58 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 470/1251] eta: 0:06:39 lr: 0.000050 loss: 2.7239 (2.7436) grad_norm: 2.9865 (inf) time: 0.5010 [2021-03-27 03:34:03 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 480/1251] eta: 0:06:34 lr: 0.000050 loss: 2.8732 (2.7429) grad_norm: 2.9891 (inf) time: 0.4995 [2021-03-27 03:34:08 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 490/1251] eta: 0:06:29 lr: 0.000050 loss: 2.6320 (2.7418) grad_norm: 2.9891 (inf) time: 0.4990 [2021-03-27 03:34:13 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 500/1251] eta: 0:06:24 lr: 0.000050 loss: 2.9221 (2.7442) grad_norm: 3.1620 (inf) time: 0.4983 [2021-03-27 03:34:18 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 510/1251] eta: 0:06:18 lr: 0.000050 loss: 2.9221 (2.7426) grad_norm: 3.0361 (inf) time: 0.5045 [2021-03-27 03:34:23 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 520/1251] eta: 0:06:13 lr: 0.000050 loss: 2.9504 (2.7435) grad_norm: 2.7920 (inf) time: 0.5024 [2021-03-27 03:34:28 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 530/1251] eta: 0:06:08 lr: 0.000050 loss: 2.9504 (2.7493) grad_norm: 2.7930 (inf) time: 0.5005 [2021-03-27 03:34:33 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 540/1251] eta: 0:06:03 lr: 0.000050 loss: 2.8515 (2.7467) grad_norm: 2.8130 (inf) time: 0.4986 [2021-03-27 03:34:38 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 550/1251] eta: 0:05:58 lr: 0.000050 loss: 2.6653 (2.7474) grad_norm: 2.8893 (inf) time: 0.5050 [2021-03-27 03:34:43 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 560/1251] eta: 0:05:52 lr: 0.000050 loss: 2.9714 (2.7485) grad_norm: 3.0168 (inf) time: 0.5135 [2021-03-27 03:34:48 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 570/1251] eta: 0:05:47 lr: 0.000050 loss: 3.0031 (2.7512) grad_norm: 3.0201 (inf) time: 0.5035 [2021-03-27 03:34:53 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 580/1251] eta: 0:05:42 lr: 0.000050 loss: 2.8578 (2.7500) grad_norm: 2.8868 (inf) time: 0.4977 [2021-03-27 03:34:58 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 590/1251] eta: 0:05:37 lr: 0.000050 loss: 2.7488 (2.7505) grad_norm: 2.7183 (inf) time: 0.5008 [2021-03-27 03:35:04 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 600/1251] eta: 0:05:32 lr: 0.000050 loss: 2.8542 (2.7538) grad_norm: 2.8061 (inf) time: 0.5044 [2021-03-27 03:35:08 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 610/1251] eta: 0:05:26 lr: 0.000050 loss: 2.9093 (2.7539) grad_norm: 2.8839 (inf) time: 0.5008 [2021-03-27 03:35:14 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 620/1251] eta: 0:05:21 lr: 0.000050 loss: 2.9383 (2.7556) grad_norm: 2.7618 (inf) time: 0.5084 [2021-03-27 03:35:19 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 630/1251] eta: 0:05:16 lr: 0.000050 loss: 2.9713 (2.7566) grad_norm: 2.8235 (inf) time: 0.5096 [2021-03-27 03:35:24 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 640/1251] eta: 0:05:11 lr: 0.000050 loss: 3.0147 (2.7586) grad_norm: 3.0455 (inf) time: 0.5036 [2021-03-27 03:35:29 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 650/1251] eta: 0:05:06 lr: 0.000050 loss: 2.7527 (2.7568) grad_norm: 2.9924 (inf) time: 0.5003 [2021-03-27 03:35:34 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 660/1251] eta: 0:05:01 lr: 0.000050 loss: 2.6538 (2.7542) grad_norm: 3.0549 (inf) time: 0.4982 [2021-03-27 03:35:39 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 670/1251] eta: 0:04:55 lr: 0.000050 loss: 2.8247 (2.7553) grad_norm: 3.1350 (inf) time: 0.5025 [2021-03-27 03:35:44 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 680/1251] eta: 0:04:50 lr: 0.000050 loss: 2.8298 (2.7548) grad_norm: 3.0779 (inf) time: 0.5023 [2021-03-27 03:35:49 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 690/1251] eta: 0:04:45 lr: 0.000050 loss: 2.7438 (2.7549) grad_norm: 2.9383 (inf) time: 0.5020 [2021-03-27 03:35:54 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 700/1251] eta: 0:04:40 lr: 0.000050 loss: 2.8341 (2.7567) grad_norm: 2.7446 (inf) time: 0.4986 [2021-03-27 03:35:59 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 710/1251] eta: 0:04:35 lr: 0.000050 loss: 2.8341 (2.7566) grad_norm: 2.8697 (inf) time: 0.5001 [2021-03-27 03:36:04 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 720/1251] eta: 0:04:30 lr: 0.000050 loss: 2.9789 (2.7591) grad_norm: 2.9134 (inf) time: 0.5015 [2021-03-27 03:36:09 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 730/1251] eta: 0:04:25 lr: 0.000050 loss: 2.9534 (2.7605) grad_norm: 2.9326 (inf) time: 0.5121 [2021-03-27 03:36:14 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 740/1251] eta: 0:04:20 lr: 0.000050 loss: 2.8576 (2.7604) grad_norm: 2.9272 (inf) time: 0.5286 [2021-03-27 03:36:19 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 750/1251] eta: 0:04:15 lr: 0.000049 loss: 2.8502 (2.7590) grad_norm: 2.8618 (inf) time: 0.5223 [2021-03-27 03:36:24 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 760/1251] eta: 0:04:09 lr: 0.000049 loss: 2.6973 (2.7567) grad_norm: 2.8170 (inf) time: 0.5035 [2021-03-27 03:36:29 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 770/1251] eta: 0:04:04 lr: 0.000049 loss: 2.6800 (2.7560) grad_norm: 2.7504 (inf) time: 0.4957 [2021-03-27 03:36:34 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 780/1251] eta: 0:03:59 lr: 0.000049 loss: 2.7556 (2.7579) grad_norm: 2.8174 (inf) time: 0.4952 [2021-03-27 03:36:39 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 790/1251] eta: 0:03:54 lr: 0.000049 loss: 2.9092 (2.7589) grad_norm: 2.8703 (inf) time: 0.4933 [2021-03-27 03:36:44 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 800/1251] eta: 0:03:49 lr: 0.000049 loss: 2.8760 (2.7585) grad_norm: 2.7713 (inf) time: 0.4962 [2021-03-27 03:36:49 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 810/1251] eta: 0:03:44 lr: 0.000049 loss: 2.8325 (2.7584) grad_norm: 2.8320 (inf) time: 0.5059 [2021-03-27 03:36:54 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 820/1251] eta: 0:03:39 lr: 0.000049 loss: 2.9057 (2.7594) grad_norm: 2.8475 (inf) time: 0.5106 [2021-03-27 03:37:00 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 830/1251] eta: 0:03:34 lr: 0.000049 loss: 2.9207 (2.7610) grad_norm: 2.8475 (inf) time: 0.5078 [2021-03-27 03:37:05 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 840/1251] eta: 0:03:28 lr: 0.000049 loss: 2.8793 (2.7613) grad_norm: 2.8557 (inf) time: 0.5043 [2021-03-27 03:37:10 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 850/1251] eta: 0:03:23 lr: 0.000049 loss: 2.9624 (2.7637) grad_norm: 2.8956 (inf) time: 0.5105 [2021-03-27 03:37:15 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 860/1251] eta: 0:03:18 lr: 0.000049 loss: 2.9624 (2.7612) grad_norm: 2.9157 (inf) time: 0.5123 [2021-03-27 03:37:20 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 870/1251] eta: 0:03:13 lr: 0.000049 loss: 2.6346 (2.7618) grad_norm: 3.1206 (inf) time: 0.5049 [2021-03-27 03:37:25 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 880/1251] eta: 0:03:08 lr: 0.000049 loss: 2.6346 (2.7607) grad_norm: 3.1694 (inf) time: 0.5017 [2021-03-27 03:37:30 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 890/1251] eta: 0:03:03 lr: 0.000049 loss: 2.6876 (2.7600) grad_norm: 3.1895 (inf) time: 0.5032 [2021-03-27 03:37:35 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 900/1251] eta: 0:02:58 lr: 0.000049 loss: 3.0441 (2.7631) grad_norm: 2.8838 (inf) time: 0.5061 [2021-03-27 03:37:40 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 910/1251] eta: 0:02:53 lr: 0.000049 loss: 2.9958 (2.7637) grad_norm: 2.8753 (inf) time: 0.5035 [2021-03-27 03:37:45 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 920/1251] eta: 0:02:48 lr: 0.000049 loss: 2.8298 (2.7630) grad_norm: 3.0768 (inf) time: 0.5077 [2021-03-27 03:37:50 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 930/1251] eta: 0:02:43 lr: 0.000049 loss: 2.9517 (2.7649) grad_norm: 2.9555 (inf) time: 0.5098 [2021-03-27 03:37:55 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 940/1251] eta: 0:02:38 lr: 0.000049 loss: 2.9846 (2.7669) grad_norm: 2.8227 (inf) time: 0.5128 [2021-03-27 03:38:00 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 950/1251] eta: 0:02:33 lr: 0.000049 loss: 2.9557 (2.7670) grad_norm: 2.6053 (inf) time: 0.5115 [2021-03-27 03:38:05 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 960/1251] eta: 0:02:27 lr: 0.000049 loss: 3.0180 (2.7690) grad_norm: 2.7306 (inf) time: 0.4974 [2021-03-27 03:38:10 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 970/1251] eta: 0:02:22 lr: 0.000049 loss: 3.0044 (2.7702) grad_norm: 2.7306 (inf) time: 0.4963 [2021-03-27 03:38:15 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 980/1251] eta: 0:02:17 lr: 0.000049 loss: 2.7749 (2.7707) grad_norm: 2.7437 (inf) time: 0.5014 [2021-03-27 03:38:20 swin_small_patch4_window7_224] INFO: Epoch: [261] [ 990/1251] eta: 0:02:12 lr: 0.000049 loss: 2.9023 (2.7716) grad_norm: 2.8823 (inf) time: 0.5049 [2021-03-27 03:38:26 swin_small_patch4_window7_224] INFO: Epoch: [261] [1000/1251] eta: 0:02:07 lr: 0.000049 loss: 2.8903 (2.7726) grad_norm: 2.8262 (inf) time: 0.5078 [2021-03-27 03:38:31 swin_small_patch4_window7_224] INFO: Epoch: [261] [1010/1251] eta: 0:02:02 lr: 0.000049 loss: 2.8800 (2.7725) grad_norm: 2.8763 (inf) time: 0.5080 [2021-03-27 03:38:36 swin_small_patch4_window7_224] INFO: Epoch: [261] [1020/1251] eta: 0:01:57 lr: 0.000049 loss: 2.8332 (2.7729) grad_norm: 2.9010 (inf) time: 0.5059 [2021-03-27 03:38:41 swin_small_patch4_window7_224] INFO: Epoch: [261] [1030/1251] eta: 0:01:52 lr: 0.000049 loss: 2.9355 (2.7729) grad_norm: 2.9010 (inf) time: 0.4987 [2021-03-27 03:38:46 swin_small_patch4_window7_224] INFO: Epoch: [261] [1040/1251] eta: 0:01:47 lr: 0.000049 loss: 2.7936 (2.7724) grad_norm: 2.9303 (inf) time: 0.4987 [2021-03-27 03:38:51 swin_small_patch4_window7_224] INFO: Epoch: [261] [1050/1251] eta: 0:01:42 lr: 0.000049 loss: 2.7049 (2.7716) grad_norm: 2.7627 (inf) time: 0.5047 [2021-03-27 03:38:56 swin_small_patch4_window7_224] INFO: Epoch: [261] [1060/1251] eta: 0:01:36 lr: 0.000049 loss: 2.9467 (2.7730) grad_norm: 2.7459 (inf) time: 0.5000 [2021-03-27 03:39:01 swin_small_patch4_window7_224] INFO: Epoch: [261] [1070/1251] eta: 0:01:31 lr: 0.000049 loss: 2.8969 (2.7732) grad_norm: 2.9055 (inf) time: 0.5001 [2021-03-27 03:39:06 swin_small_patch4_window7_224] INFO: Epoch: [261] [1080/1251] eta: 0:01:26 lr: 0.000049 loss: 2.8969 (2.7756) grad_norm: 3.0192 (inf) time: 0.5026 [2021-03-27 03:39:11 swin_small_patch4_window7_224] INFO: Epoch: [261] [1090/1251] eta: 0:01:21 lr: 0.000049 loss: 2.9045 (2.7741) grad_norm: 2.9055 (inf) time: 0.5031 [2021-03-27 03:39:16 swin_small_patch4_window7_224] INFO: Epoch: [261] [1100/1251] eta: 0:01:16 lr: 0.000049 loss: 2.8177 (2.7748) grad_norm: 2.9382 (inf) time: 0.5022 [2021-03-27 03:39:21 swin_small_patch4_window7_224] INFO: Epoch: [261] [1110/1251] eta: 0:01:11 lr: 0.000049 loss: 2.8427 (2.7748) grad_norm: 2.9707 (inf) time: 0.4992 [2021-03-27 03:39:26 swin_small_patch4_window7_224] INFO: Epoch: [261] [1120/1251] eta: 0:01:06 lr: 0.000049 loss: 2.7877 (2.7739) grad_norm: 2.9707 (inf) time: 0.4999 [2021-03-27 03:39:31 swin_small_patch4_window7_224] INFO: Epoch: [261] [1130/1251] eta: 0:01:01 lr: 0.000049 loss: 2.8680 (2.7753) grad_norm: 2.7868 (inf) time: 0.4979 [2021-03-27 03:39:36 swin_small_patch4_window7_224] INFO: Epoch: [261] [1140/1251] eta: 0:00:56 lr: 0.000049 loss: 2.9075 (2.7748) grad_norm: 2.7868 (inf) time: 0.4952 [2021-03-27 03:39:41 swin_small_patch4_window7_224] INFO: Epoch: [261] [1150/1251] eta: 0:00:51 lr: 0.000049 loss: 2.8984 (2.7744) grad_norm: 2.8330 (inf) time: 0.5003 [2021-03-27 03:39:46 swin_small_patch4_window7_224] INFO: Epoch: [261] [1160/1251] eta: 0:00:46 lr: 0.000049 loss: 2.8984 (2.7750) grad_norm: 2.9469 (inf) time: 0.5085 [2021-03-27 03:39:51 swin_small_patch4_window7_224] INFO: Epoch: [261] [1170/1251] eta: 0:00:41 lr: 0.000049 loss: 2.9033 (2.7757) grad_norm: 2.9581 (inf) time: 0.5092 [2021-03-27 03:39:56 swin_small_patch4_window7_224] INFO: Epoch: [261] [1180/1251] eta: 0:00:35 lr: 0.000049 loss: 2.9695 (2.7775) grad_norm: 2.9040 (inf) time: 0.5010 [2021-03-27 03:40:01 swin_small_patch4_window7_224] INFO: Epoch: [261] [1190/1251] eta: 0:00:30 lr: 0.000049 loss: 2.9675 (2.7786) grad_norm: 2.9361 (inf) time: 0.4962 [2021-03-27 03:40:06 swin_small_patch4_window7_224] INFO: Epoch: [261] [1200/1251] eta: 0:00:25 lr: 0.000049 loss: 2.7792 (2.7779) grad_norm: 3.0784 (inf) time: 0.5031 [2021-03-27 03:40:11 swin_small_patch4_window7_224] INFO: Epoch: [261] [1210/1251] eta: 0:00:20 lr: 0.000049 loss: 2.7173 (2.7764) grad_norm: 2.9996 (inf) time: 0.5058 [2021-03-27 03:40:16 swin_small_patch4_window7_224] INFO: Epoch: [261] [1220/1251] eta: 0:00:15 lr: 0.000049 loss: 2.9666 (2.7784) grad_norm: 2.8206 (inf) time: 0.4998 [2021-03-27 03:40:21 swin_small_patch4_window7_224] INFO: Epoch: [261] [1230/1251] eta: 0:00:10 lr: 0.000049 loss: 2.9427 (2.7776) grad_norm: 2.7409 (inf) time: 0.5015 [2021-03-27 03:40:26 swin_small_patch4_window7_224] INFO: Epoch: [261] [1240/1251] eta: 0:00:05 lr: 0.000049 loss: 2.8003 (2.7788) grad_norm: 2.8273 (inf) time: 0.5055 [2021-03-27 03:40:31 swin_small_patch4_window7_224] INFO: Epoch: [261] [1250/1251] eta: 0:00:00 lr: 0.000049 loss: 2.8781 (2.7793) grad_norm: 2.9022 (inf) time: 0.4998 [2021-03-27 03:40:43 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:16 loss: 0.6466 (0.6466) acc1: 87.5000 (87.5000) acc5: 95.3125 (95.3125) [2021-03-27 03:40:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.6653 (0.7200) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.8807) [2021-03-27 03:40:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7127 (0.7466) acc1: 82.8125 (83.3333) acc5: 95.3125 (95.9077) [2021-03-27 03:40:51 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7550 (0.7515) acc1: 81.2500 (82.6109) acc5: 96.8750 (96.1190) [2021-03-27 03:40:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7550 (0.7525) acc1: 79.6875 (82.2027) acc5: 96.8750 (96.4558) [2021-03-27 03:40:54 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7567 (0.7560) acc1: 81.2500 (82.1440) acc5: 96.8750 (96.3200) [2021-03-27 03:41:06 swin_small_patch4_window7_224] INFO: * Acc@1 82.594 Acc@5 96.120 loss 0.744 [2021-03-27 03:41:06 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.6% [2021-03-27 03:41:06 swin_small_patch4_window7_224] INFO: Max accuracy: 82.61% [2021-03-27 03:41:11 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 0/1251] eta: 1:44:44 lr: 0.000049 loss: 2.8754 (2.8754) grad_norm: 3.0992 (3.0992) time: 5.0234 [2021-03-27 03:41:17 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 10/1251] eta: 0:19:04 lr: 0.000049 loss: 2.8754 (2.7451) grad_norm: 3.0992 (3.0499) time: 0.9223 [2021-03-27 03:41:22 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 20/1251] eta: 0:14:45 lr: 0.000049 loss: 2.8000 (2.7186) grad_norm: 2.8126 (3.0004) time: 0.5039 [2021-03-27 03:41:27 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 30/1251] eta: 0:13:13 lr: 0.000049 loss: 2.7962 (2.7757) grad_norm: 2.7830 (3.0054) time: 0.5003 [2021-03-27 03:41:32 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 40/1251] eta: 0:12:29 lr: 0.000049 loss: 2.8709 (2.7951) grad_norm: 2.9727 (3.0183) time: 0.5139 [2021-03-27 03:41:37 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 50/1251] eta: 0:11:59 lr: 0.000049 loss: 2.8709 (2.7807) grad_norm: 3.0244 (3.0236) time: 0.5194 [2021-03-27 03:41:42 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 60/1251] eta: 0:11:37 lr: 0.000049 loss: 2.6263 (2.7451) grad_norm: 2.8611 (3.0271) time: 0.5183 [2021-03-27 03:41:47 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 70/1251] eta: 0:11:17 lr: 0.000049 loss: 2.6263 (2.7372) grad_norm: 2.9895 (3.0308) time: 0.5104 [2021-03-27 03:41:52 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 80/1251] eta: 0:11:03 lr: 0.000049 loss: 2.7716 (2.7215) grad_norm: 3.0044 (3.0941) time: 0.5068 [2021-03-27 03:41:57 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 90/1251] eta: 0:10:48 lr: 0.000049 loss: 2.8365 (2.7220) grad_norm: 2.8604 (3.0746) time: 0.5043 [2021-03-27 03:42:02 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 100/1251] eta: 0:10:35 lr: 0.000049 loss: 2.8711 (2.7306) grad_norm: 2.7261 (3.0670) time: 0.4945 [2021-03-27 03:42:07 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 110/1251] eta: 0:10:24 lr: 0.000049 loss: 2.7574 (2.7036) grad_norm: 2.8069 (3.0676) time: 0.4982 [2021-03-27 03:42:12 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 120/1251] eta: 0:10:14 lr: 0.000048 loss: 2.5577 (2.7069) grad_norm: 2.9681 (3.0590) time: 0.4984 [2021-03-27 03:42:17 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 130/1251] eta: 0:10:05 lr: 0.000048 loss: 2.8407 (2.7169) grad_norm: 2.8265 (3.0838) time: 0.4988 [2021-03-27 03:42:22 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 140/1251] eta: 0:09:57 lr: 0.000048 loss: 2.8407 (2.7144) grad_norm: 2.8942 (3.1045) time: 0.5070 [2021-03-27 03:42:27 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 150/1251] eta: 0:09:49 lr: 0.000048 loss: 2.7744 (2.7172) grad_norm: 2.8566 (3.0923) time: 0.5029 [2021-03-27 03:42:32 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 160/1251] eta: 0:09:42 lr: 0.000048 loss: 2.8032 (2.7169) grad_norm: 2.7998 (3.0878) time: 0.5004 [2021-03-27 03:42:37 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 170/1251] eta: 0:09:34 lr: 0.000048 loss: 2.8289 (2.7192) grad_norm: 3.0206 (3.0850) time: 0.5010 [2021-03-27 03:42:42 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 180/1251] eta: 0:09:27 lr: 0.000048 loss: 2.9197 (2.7337) grad_norm: 3.0226 (3.1057) time: 0.4975 [2021-03-27 03:42:47 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 190/1251] eta: 0:09:19 lr: 0.000048 loss: 2.8949 (2.7425) grad_norm: 2.9654 (3.1078) time: 0.4976 [2021-03-27 03:42:52 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 200/1251] eta: 0:09:14 lr: 0.000048 loss: 2.8635 (2.7426) grad_norm: 2.8117 (3.0909) time: 0.5060 [2021-03-27 03:42:57 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 210/1251] eta: 0:09:07 lr: 0.000048 loss: 2.7820 (2.7329) grad_norm: 2.9653 (3.0940) time: 0.5056 [2021-03-27 03:43:02 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 220/1251] eta: 0:09:00 lr: 0.000048 loss: 2.7343 (2.7319) grad_norm: 3.0121 (3.0905) time: 0.4985 [2021-03-27 03:43:08 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 230/1251] eta: 0:08:55 lr: 0.000048 loss: 2.7343 (2.7306) grad_norm: 2.9060 (3.0876) time: 0.5086 [2021-03-27 03:43:13 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 240/1251] eta: 0:08:49 lr: 0.000048 loss: 2.6705 (2.7293) grad_norm: 2.8988 (3.0805) time: 0.5094 [2021-03-27 03:43:18 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 250/1251] eta: 0:08:42 lr: 0.000048 loss: 2.7482 (2.7241) grad_norm: 2.9570 (3.0788) time: 0.4999 [2021-03-27 03:43:23 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 260/1251] eta: 0:08:36 lr: 0.000048 loss: 2.9561 (2.7333) grad_norm: 3.1171 (3.0899) time: 0.4997 [2021-03-27 03:43:28 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 270/1251] eta: 0:08:31 lr: 0.000048 loss: 3.0387 (2.7441) grad_norm: 3.1372 (3.1111) time: 0.5098 [2021-03-27 03:43:33 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 280/1251] eta: 0:08:25 lr: 0.000048 loss: 2.9989 (2.7434) grad_norm: 2.9589 (3.1020) time: 0.5057 [2021-03-27 03:43:38 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 290/1251] eta: 0:08:19 lr: 0.000048 loss: 2.8219 (2.7404) grad_norm: 2.9098 (3.1094) time: 0.4992 [2021-03-27 03:43:43 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 300/1251] eta: 0:08:13 lr: 0.000048 loss: 2.8169 (2.7421) grad_norm: 3.2392 (3.1118) time: 0.5035 [2021-03-27 03:43:48 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 310/1251] eta: 0:08:07 lr: 0.000048 loss: 2.8226 (2.7466) grad_norm: 3.0337 (3.1109) time: 0.4982 [2021-03-27 03:43:53 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 320/1251] eta: 0:08:02 lr: 0.000048 loss: 2.9315 (2.7447) grad_norm: 2.9861 (3.1134) time: 0.5020 [2021-03-27 03:43:58 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 330/1251] eta: 0:07:57 lr: 0.000048 loss: 2.8748 (2.7442) grad_norm: 3.0600 (3.1206) time: 0.5102 [2021-03-27 03:44:03 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 340/1251] eta: 0:07:51 lr: 0.000048 loss: 2.8748 (2.7418) grad_norm: 3.0867 (3.1206) time: 0.5066 [2021-03-27 03:44:08 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 350/1251] eta: 0:07:45 lr: 0.000048 loss: 2.8967 (2.7475) grad_norm: 3.1305 (3.1321) time: 0.5039 [2021-03-27 03:44:13 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 360/1251] eta: 0:07:40 lr: 0.000048 loss: 2.8263 (2.7415) grad_norm: 3.1263 (3.1334) time: 0.5059 [2021-03-27 03:44:18 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 370/1251] eta: 0:07:34 lr: 0.000048 loss: 2.8158 (2.7456) grad_norm: 3.0267 (3.1351) time: 0.5010 [2021-03-27 03:44:23 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 380/1251] eta: 0:07:29 lr: 0.000048 loss: 2.8858 (2.7471) grad_norm: 2.9645 (3.1308) time: 0.5000 [2021-03-27 03:44:28 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 390/1251] eta: 0:07:24 lr: 0.000048 loss: 2.8314 (2.7478) grad_norm: 2.8929 (3.1271) time: 0.5096 [2021-03-27 03:44:33 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 400/1251] eta: 0:07:18 lr: 0.000048 loss: 2.8086 (2.7458) grad_norm: 2.8929 (3.1265) time: 0.5101 [2021-03-27 03:44:38 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 410/1251] eta: 0:07:13 lr: 0.000048 loss: 3.0153 (2.7539) grad_norm: 2.8552 (3.1188) time: 0.5009 [2021-03-27 03:44:43 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 420/1251] eta: 0:07:07 lr: 0.000048 loss: 2.9725 (2.7546) grad_norm: 2.8552 (3.1149) time: 0.4997 [2021-03-27 03:44:48 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 430/1251] eta: 0:07:02 lr: 0.000048 loss: 2.9798 (2.7591) grad_norm: 2.8625 (3.1132) time: 0.5005 [2021-03-27 03:44:53 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 440/1251] eta: 0:06:57 lr: 0.000048 loss: 2.9891 (2.7567) grad_norm: 2.9008 (3.1178) time: 0.5001 [2021-03-27 03:44:58 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 450/1251] eta: 0:06:51 lr: 0.000048 loss: 2.8590 (2.7568) grad_norm: 2.9109 (3.1167) time: 0.4981 [2021-03-27 03:45:03 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 460/1251] eta: 0:06:46 lr: 0.000048 loss: 2.8590 (2.7612) grad_norm: 2.9263 (3.1143) time: 0.4958 [2021-03-27 03:45:08 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 470/1251] eta: 0:06:40 lr: 0.000048 loss: 2.7998 (2.7585) grad_norm: 2.9512 (3.1129) time: 0.4985 [2021-03-27 03:45:13 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 480/1251] eta: 0:06:35 lr: 0.000048 loss: 2.7787 (2.7592) grad_norm: 2.7734 (3.1076) time: 0.4982 [2021-03-27 03:45:18 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 490/1251] eta: 0:06:30 lr: 0.000048 loss: 2.8646 (2.7622) grad_norm: 2.8174 (3.1069) time: 0.5004 [2021-03-27 03:45:23 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 500/1251] eta: 0:06:24 lr: 0.000048 loss: 2.9472 (2.7628) grad_norm: 2.8995 (3.1024) time: 0.5060 [2021-03-27 03:45:28 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 510/1251] eta: 0:06:19 lr: 0.000048 loss: 2.8995 (2.7633) grad_norm: 2.8914 (3.1007) time: 0.5036 [2021-03-27 03:45:33 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 520/1251] eta: 0:06:14 lr: 0.000048 loss: 2.8038 (2.7617) grad_norm: 3.0151 (3.0984) time: 0.4970 [2021-03-27 03:45:38 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 530/1251] eta: 0:06:08 lr: 0.000048 loss: 3.0036 (2.7652) grad_norm: 2.8117 (3.0982) time: 0.4952 [2021-03-27 03:45:43 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 540/1251] eta: 0:06:03 lr: 0.000048 loss: 2.8662 (2.7653) grad_norm: 2.7454 (3.0914) time: 0.5020 [2021-03-27 03:45:48 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 550/1251] eta: 0:05:58 lr: 0.000048 loss: 2.6628 (2.7613) grad_norm: 2.7546 (3.0897) time: 0.5147 [2021-03-27 03:45:54 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 560/1251] eta: 0:05:53 lr: 0.000048 loss: 2.6623 (2.7612) grad_norm: 2.8992 (3.0866) time: 0.5189 [2021-03-27 03:45:59 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 570/1251] eta: 0:05:48 lr: 0.000048 loss: 3.0102 (2.7650) grad_norm: 2.9726 (3.0876) time: 0.5083 [2021-03-27 03:46:04 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 580/1251] eta: 0:05:43 lr: 0.000048 loss: 3.0102 (2.7693) grad_norm: 3.0032 (3.0863) time: 0.5008 [2021-03-27 03:46:09 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 590/1251] eta: 0:05:38 lr: 0.000048 loss: 2.8843 (2.7691) grad_norm: 2.9786 (3.0885) time: 0.5076 [2021-03-27 03:46:14 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 600/1251] eta: 0:05:32 lr: 0.000048 loss: 2.8763 (2.7719) grad_norm: 2.9738 (3.0866) time: 0.5056 [2021-03-27 03:46:19 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 610/1251] eta: 0:05:27 lr: 0.000048 loss: 2.9409 (2.7754) grad_norm: 2.8310 (3.0823) time: 0.5038 [2021-03-27 03:46:24 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 620/1251] eta: 0:05:22 lr: 0.000048 loss: 3.0035 (2.7776) grad_norm: 2.8310 (3.1028) time: 0.5063 [2021-03-27 03:46:29 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 630/1251] eta: 0:05:17 lr: 0.000048 loss: 3.0035 (2.7792) grad_norm: 2.9923 (3.1014) time: 0.4995 [2021-03-27 03:46:34 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 640/1251] eta: 0:05:12 lr: 0.000048 loss: 2.8328 (2.7774) grad_norm: 3.0217 (3.1101) time: 0.5025 [2021-03-27 03:46:39 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 650/1251] eta: 0:05:06 lr: 0.000048 loss: 2.5007 (2.7717) grad_norm: 3.1371 (3.1132) time: 0.5053 [2021-03-27 03:46:44 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 660/1251] eta: 0:05:01 lr: 0.000048 loss: 2.7595 (2.7713) grad_norm: 3.2793 (3.1174) time: 0.4979 [2021-03-27 03:46:49 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 670/1251] eta: 0:04:56 lr: 0.000048 loss: 2.9018 (2.7728) grad_norm: 3.2793 (3.1185) time: 0.4991 [2021-03-27 03:46:54 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 680/1251] eta: 0:04:51 lr: 0.000048 loss: 2.7408 (2.7712) grad_norm: 2.9027 (3.1160) time: 0.5014 [2021-03-27 03:46:59 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 690/1251] eta: 0:04:46 lr: 0.000048 loss: 2.7408 (2.7716) grad_norm: 2.7742 (3.1149) time: 0.4962 [2021-03-27 03:47:04 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 700/1251] eta: 0:04:40 lr: 0.000048 loss: 2.6790 (2.7669) grad_norm: 2.7609 (3.1136) time: 0.4938 [2021-03-27 03:47:09 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 710/1251] eta: 0:04:35 lr: 0.000048 loss: 2.6221 (2.7664) grad_norm: 3.0169 (3.1173) time: 0.4987 [2021-03-27 03:47:14 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 720/1251] eta: 0:04:30 lr: 0.000048 loss: 2.7582 (2.7642) grad_norm: 3.0947 (3.1148) time: 0.5002 [2021-03-27 03:47:19 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 730/1251] eta: 0:04:25 lr: 0.000048 loss: 2.8603 (2.7664) grad_norm: 2.9630 (3.1133) time: 0.5017 [2021-03-27 03:47:24 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 740/1251] eta: 0:04:20 lr: 0.000047 loss: 2.8101 (2.7640) grad_norm: 3.0105 (3.1134) time: 0.5202 [2021-03-27 03:47:29 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 750/1251] eta: 0:04:15 lr: 0.000047 loss: 2.6857 (2.7619) grad_norm: 2.8413 (3.1100) time: 0.5260 [2021-03-27 03:47:34 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 760/1251] eta: 0:04:10 lr: 0.000047 loss: 2.7466 (2.7635) grad_norm: 2.8753 (3.1140) time: 0.5077 [2021-03-27 03:47:39 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 770/1251] eta: 0:04:05 lr: 0.000047 loss: 2.9561 (2.7638) grad_norm: 2.9438 (3.1107) time: 0.4991 [2021-03-27 03:47:44 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 780/1251] eta: 0:03:59 lr: 0.000047 loss: 2.8814 (2.7650) grad_norm: 2.9120 (3.1100) time: 0.4975 [2021-03-27 03:47:50 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 790/1251] eta: 0:03:54 lr: 0.000047 loss: 2.9013 (2.7657) grad_norm: 2.9755 (3.1128) time: 0.5092 [2021-03-27 03:47:55 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 800/1251] eta: 0:03:49 lr: 0.000047 loss: 2.8116 (2.7669) grad_norm: 2.8946 (3.1112) time: 0.5145 [2021-03-27 03:48:00 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 810/1251] eta: 0:03:44 lr: 0.000047 loss: 2.8438 (2.7690) grad_norm: 2.6435 (3.1078) time: 0.4984 [2021-03-27 03:48:05 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 820/1251] eta: 0:03:39 lr: 0.000047 loss: 3.0020 (2.7711) grad_norm: 2.6627 (3.1100) time: 0.4948 [2021-03-27 03:48:10 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 830/1251] eta: 0:03:34 lr: 0.000047 loss: 2.9795 (2.7734) grad_norm: 2.9369 (3.1085) time: 0.5007 [2021-03-27 03:48:15 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 840/1251] eta: 0:03:29 lr: 0.000047 loss: 2.9449 (2.7712) grad_norm: 3.0136 (3.1079) time: 0.4998 [2021-03-27 03:48:20 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 850/1251] eta: 0:03:24 lr: 0.000047 loss: 2.9088 (2.7725) grad_norm: 3.0147 (3.1060) time: 0.4987 [2021-03-27 03:48:25 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 860/1251] eta: 0:03:18 lr: 0.000047 loss: 3.0018 (2.7730) grad_norm: 3.0065 (3.1033) time: 0.5021 [2021-03-27 03:48:30 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 870/1251] eta: 0:03:13 lr: 0.000047 loss: 2.8770 (2.7730) grad_norm: 2.8123 (3.1002) time: 0.5021 [2021-03-27 03:48:35 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 880/1251] eta: 0:03:08 lr: 0.000047 loss: 2.8844 (2.7731) grad_norm: 2.8418 (3.1003) time: 0.5058 [2021-03-27 03:48:40 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 890/1251] eta: 0:03:03 lr: 0.000047 loss: 2.9008 (2.7723) grad_norm: 3.1690 (3.1381) time: 0.5064 [2021-03-27 03:48:45 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 900/1251] eta: 0:02:58 lr: 0.000047 loss: 2.7826 (2.7733) grad_norm: 3.2712 (3.1428) time: 0.4996 [2021-03-27 03:48:50 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 910/1251] eta: 0:02:53 lr: 0.000047 loss: 2.7718 (2.7737) grad_norm: 3.3021 (3.1418) time: 0.5028 [2021-03-27 03:48:55 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 920/1251] eta: 0:02:48 lr: 0.000047 loss: 2.7718 (2.7756) grad_norm: 2.9336 (3.1411) time: 0.5024 [2021-03-27 03:49:00 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 930/1251] eta: 0:02:43 lr: 0.000047 loss: 2.8332 (2.7773) grad_norm: 2.8866 (3.1422) time: 0.5031 [2021-03-27 03:49:05 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 940/1251] eta: 0:02:38 lr: 0.000047 loss: 2.8332 (2.7777) grad_norm: 3.0839 (3.1470) time: 0.5084 [2021-03-27 03:49:10 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 950/1251] eta: 0:02:33 lr: 0.000047 loss: 2.9258 (2.7794) grad_norm: 2.9557 (3.1427) time: 0.5064 [2021-03-27 03:49:15 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 960/1251] eta: 0:02:27 lr: 0.000047 loss: 2.8641 (2.7808) grad_norm: 2.8976 (3.1451) time: 0.5050 [2021-03-27 03:49:20 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 970/1251] eta: 0:02:22 lr: 0.000047 loss: 2.8628 (2.7815) grad_norm: 2.9791 (3.1451) time: 0.5079 [2021-03-27 03:49:25 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 980/1251] eta: 0:02:17 lr: 0.000047 loss: 2.8921 (2.7827) grad_norm: 3.1037 (3.1497) time: 0.5171 [2021-03-27 03:49:30 swin_small_patch4_window7_224] INFO: Epoch: [262] [ 990/1251] eta: 0:02:12 lr: 0.000047 loss: 2.8350 (2.7803) grad_norm: 2.8838 (3.1489) time: 0.5069 [2021-03-27 03:49:35 swin_small_patch4_window7_224] INFO: Epoch: [262] [1000/1251] eta: 0:02:07 lr: 0.000047 loss: 2.8031 (2.7816) grad_norm: 2.8727 (3.1484) time: 0.4981 [2021-03-27 03:49:40 swin_small_patch4_window7_224] INFO: Epoch: [262] [1010/1251] eta: 0:02:02 lr: 0.000047 loss: 2.9310 (2.7833) grad_norm: 2.9283 (3.1471) time: 0.5050 [2021-03-27 03:49:45 swin_small_patch4_window7_224] INFO: Epoch: [262] [1020/1251] eta: 0:01:57 lr: 0.000047 loss: 3.0511 (2.7854) grad_norm: 2.9268 (3.1442) time: 0.5004 [2021-03-27 03:49:50 swin_small_patch4_window7_224] INFO: Epoch: [262] [1030/1251] eta: 0:01:52 lr: 0.000047 loss: 2.9865 (2.7855) grad_norm: 3.0103 (3.1430) time: 0.4966 [2021-03-27 03:49:55 swin_small_patch4_window7_224] INFO: Epoch: [262] [1040/1251] eta: 0:01:47 lr: 0.000047 loss: 2.9101 (2.7869) grad_norm: 3.0351 (3.1435) time: 0.5000 [2021-03-27 03:50:00 swin_small_patch4_window7_224] INFO: Epoch: [262] [1050/1251] eta: 0:01:42 lr: 0.000047 loss: 2.8309 (2.7853) grad_norm: 3.1184 (3.1501) time: 0.4999 [2021-03-27 03:50:05 swin_small_patch4_window7_224] INFO: Epoch: [262] [1060/1251] eta: 0:01:36 lr: 0.000047 loss: 2.6773 (2.7841) grad_norm: 2.9316 (3.1484) time: 0.4963 [2021-03-27 03:50:10 swin_small_patch4_window7_224] INFO: Epoch: [262] [1070/1251] eta: 0:01:31 lr: 0.000047 loss: 2.6773 (2.7814) grad_norm: 2.8529 (3.1503) time: 0.5025 [2021-03-27 03:50:15 swin_small_patch4_window7_224] INFO: Epoch: [262] [1080/1251] eta: 0:01:26 lr: 0.000047 loss: 2.4349 (2.7788) grad_norm: 2.9191 (3.1515) time: 0.5078 [2021-03-27 03:50:20 swin_small_patch4_window7_224] INFO: Epoch: [262] [1090/1251] eta: 0:01:21 lr: 0.000047 loss: 2.6277 (2.7780) grad_norm: 3.1056 (3.1509) time: 0.5049 [2021-03-27 03:50:25 swin_small_patch4_window7_224] INFO: Epoch: [262] [1100/1251] eta: 0:01:16 lr: 0.000047 loss: 2.7412 (2.7775) grad_norm: 3.0943 (3.1513) time: 0.5019 [2021-03-27 03:50:31 swin_small_patch4_window7_224] INFO: Epoch: [262] [1110/1251] eta: 0:01:11 lr: 0.000047 loss: 2.7915 (2.7775) grad_norm: 3.1422 (3.1520) time: 0.5010 [2021-03-27 03:50:36 swin_small_patch4_window7_224] INFO: Epoch: [262] [1120/1251] eta: 0:01:06 lr: 0.000047 loss: 3.0427 (2.7789) grad_norm: 3.0370 (3.1512) time: 0.5013 [2021-03-27 03:50:41 swin_small_patch4_window7_224] INFO: Epoch: [262] [1130/1251] eta: 0:01:01 lr: 0.000047 loss: 3.0203 (2.7800) grad_norm: 2.9325 (3.1494) time: 0.5023 [2021-03-27 03:50:46 swin_small_patch4_window7_224] INFO: Epoch: [262] [1140/1251] eta: 0:00:56 lr: 0.000047 loss: 2.8841 (2.7800) grad_norm: 2.8845 (3.1470) time: 0.5032 [2021-03-27 03:50:51 swin_small_patch4_window7_224] INFO: Epoch: [262] [1150/1251] eta: 0:00:51 lr: 0.000047 loss: 2.7333 (2.7794) grad_norm: 2.9953 (3.1470) time: 0.5008 [2021-03-27 03:50:56 swin_small_patch4_window7_224] INFO: Epoch: [262] [1160/1251] eta: 0:00:46 lr: 0.000047 loss: 2.7333 (2.7790) grad_norm: 3.0654 (3.1455) time: 0.5015 [2021-03-27 03:51:01 swin_small_patch4_window7_224] INFO: Epoch: [262] [1170/1251] eta: 0:00:41 lr: 0.000047 loss: 2.8113 (2.7791) grad_norm: 2.9588 (3.1441) time: 0.5071 [2021-03-27 03:51:06 swin_small_patch4_window7_224] INFO: Epoch: [262] [1180/1251] eta: 0:00:36 lr: 0.000047 loss: 2.7234 (2.7786) grad_norm: 2.9833 (3.1456) time: 0.5074 [2021-03-27 03:51:11 swin_small_patch4_window7_224] INFO: Epoch: [262] [1190/1251] eta: 0:00:30 lr: 0.000047 loss: 2.6961 (2.7776) grad_norm: 2.9833 (3.1437) time: 0.5004 [2021-03-27 03:51:16 swin_small_patch4_window7_224] INFO: Epoch: [262] [1200/1251] eta: 0:00:25 lr: 0.000047 loss: 2.7984 (2.7770) grad_norm: 2.9686 (3.1442) time: 0.4965 [2021-03-27 03:51:21 swin_small_patch4_window7_224] INFO: Epoch: [262] [1210/1251] eta: 0:00:20 lr: 0.000047 loss: 2.8685 (2.7768) grad_norm: 2.9832 (3.1429) time: 0.4991 [2021-03-27 03:51:26 swin_small_patch4_window7_224] INFO: Epoch: [262] [1220/1251] eta: 0:00:15 lr: 0.000047 loss: 2.6998 (2.7756) grad_norm: 2.9468 (3.1407) time: 0.5011 [2021-03-27 03:51:31 swin_small_patch4_window7_224] INFO: Epoch: [262] [1230/1251] eta: 0:00:10 lr: 0.000047 loss: 2.6881 (2.7765) grad_norm: 2.8836 (3.1400) time: 0.5005 [2021-03-27 03:51:36 swin_small_patch4_window7_224] INFO: Epoch: [262] [1240/1251] eta: 0:00:05 lr: 0.000047 loss: 2.7599 (2.7766) grad_norm: 2.9441 (3.1391) time: 0.4999 [2021-03-27 03:51:41 swin_small_patch4_window7_224] INFO: Epoch: [262] [1250/1251] eta: 0:00:00 lr: 0.000047 loss: 2.7188 (2.7759) grad_norm: 2.9450 (3.1387) time: 0.4970 [2021-03-27 03:51:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:03:18 loss: 0.6582 (0.6582) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 03:51:59 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.8413 (0.8459) acc1: 79.6875 (78.4091) acc5: 96.8750 (96.0227) [2021-03-27 03:52:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7919 (0.7806) acc1: 82.8125 (81.5476) acc5: 96.8750 (96.2054) [2021-03-27 03:52:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7263 (0.7688) acc1: 84.3750 (81.7036) acc5: 96.8750 (96.2702) [2021-03-27 03:52:05 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7352 (0.7709) acc1: 81.2500 (81.6311) acc5: 95.3125 (96.0747) [2021-03-27 03:52:06 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7031 (0.7583) acc1: 84.3750 (82.1440) acc5: 96.8750 (96.2240) [2021-03-27 03:52:19 swin_small_patch4_window7_224] INFO: * Acc@1 82.738 Acc@5 96.132 loss 0.744 [2021-03-27 03:52:19 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-27 03:52:19 swin_small_patch4_window7_224] INFO: Max accuracy: 82.74% [2021-03-27 03:52:24 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 0/1251] eta: 1:36:56 lr: 0.000047 loss: 2.9277 (2.9277) grad_norm: 3.0341 (3.0341) time: 4.6494 [2021-03-27 03:52:29 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 10/1251] eta: 0:18:16 lr: 0.000047 loss: 2.9277 (2.6363) grad_norm: 3.0341 (3.3295) time: 0.8837 [2021-03-27 03:52:34 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 20/1251] eta: 0:14:28 lr: 0.000047 loss: 2.9386 (2.7548) grad_norm: 2.8842 (3.1335) time: 0.5082 [2021-03-27 03:52:39 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 30/1251] eta: 0:13:00 lr: 0.000047 loss: 2.9957 (2.7617) grad_norm: 2.8842 (3.1168) time: 0.5044 [2021-03-27 03:52:44 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 40/1251] eta: 0:12:12 lr: 0.000047 loss: 2.8122 (2.7852) grad_norm: 3.0382 (3.1368) time: 0.4991 [2021-03-27 03:52:49 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 50/1251] eta: 0:11:41 lr: 0.000047 loss: 2.9329 (2.7869) grad_norm: 3.0533 (3.1224) time: 0.4999 [2021-03-27 03:52:54 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 60/1251] eta: 0:11:19 lr: 0.000047 loss: 2.9919 (2.7877) grad_norm: 3.0252 (3.1654) time: 0.5013 [2021-03-27 03:52:59 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 70/1251] eta: 0:11:04 lr: 0.000047 loss: 2.8773 (2.7559) grad_norm: 2.9568 (3.1286) time: 0.5069 [2021-03-27 03:53:04 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 80/1251] eta: 0:10:50 lr: 0.000047 loss: 2.7443 (2.7535) grad_norm: 2.9611 (3.1368) time: 0.5079 [2021-03-27 03:53:09 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 90/1251] eta: 0:10:38 lr: 0.000047 loss: 2.9259 (2.7548) grad_norm: 2.9611 (3.1650) time: 0.5051 [2021-03-27 03:53:14 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 100/1251] eta: 0:10:28 lr: 0.000047 loss: 2.9259 (2.7604) grad_norm: 2.9603 (3.1533) time: 0.5089 [2021-03-27 03:53:20 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 110/1251] eta: 0:10:19 lr: 0.000047 loss: 2.8530 (2.7701) grad_norm: 3.0739 (3.1460) time: 0.5113 [2021-03-27 03:53:25 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 120/1251] eta: 0:10:11 lr: 0.000047 loss: 2.8530 (2.7685) grad_norm: 3.0890 (3.1556) time: 0.5122 [2021-03-27 03:53:30 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 130/1251] eta: 0:10:03 lr: 0.000046 loss: 2.9644 (2.7683) grad_norm: 3.0890 (3.1499) time: 0.5098 [2021-03-27 03:53:35 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 140/1251] eta: 0:09:54 lr: 0.000046 loss: 2.7171 (2.7634) grad_norm: 2.8958 (3.1257) time: 0.5027 [2021-03-27 03:53:40 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 150/1251] eta: 0:09:47 lr: 0.000046 loss: 2.7171 (2.7629) grad_norm: 2.8926 (3.1235) time: 0.5028 [2021-03-27 03:53:45 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 160/1251] eta: 0:09:39 lr: 0.000046 loss: 2.8379 (2.7632) grad_norm: 2.8230 (3.0993) time: 0.5030 [2021-03-27 03:53:50 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 170/1251] eta: 0:09:33 lr: 0.000046 loss: 2.8379 (2.7683) grad_norm: 2.7331 (3.0881) time: 0.5060 [2021-03-27 03:53:55 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 180/1251] eta: 0:09:26 lr: 0.000046 loss: 2.8602 (2.7675) grad_norm: 2.9832 (3.0920) time: 0.5071 [2021-03-27 03:54:00 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 190/1251] eta: 0:09:19 lr: 0.000046 loss: 2.8592 (2.7667) grad_norm: 3.1044 (3.0926) time: 0.5025 [2021-03-27 03:54:05 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 200/1251] eta: 0:09:13 lr: 0.000046 loss: 2.8018 (2.7718) grad_norm: 2.7946 (3.0755) time: 0.5052 [2021-03-27 03:54:10 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 210/1251] eta: 0:09:06 lr: 0.000046 loss: 2.7871 (2.7696) grad_norm: 2.7764 (3.0864) time: 0.5084 [2021-03-27 03:54:15 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 220/1251] eta: 0:09:00 lr: 0.000046 loss: 2.8416 (2.7727) grad_norm: 2.9707 (3.0856) time: 0.5027 [2021-03-27 03:54:20 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 230/1251] eta: 0:08:54 lr: 0.000046 loss: 2.8548 (2.7676) grad_norm: 3.1399 (3.0888) time: 0.5004 [2021-03-27 03:54:25 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 240/1251] eta: 0:08:47 lr: 0.000046 loss: 2.8353 (2.7646) grad_norm: 3.0698 (3.0885) time: 0.5022 [2021-03-27 03:54:30 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 250/1251] eta: 0:08:42 lr: 0.000046 loss: 2.7526 (2.7593) grad_norm: 2.9017 (3.0866) time: 0.5016 [2021-03-27 03:54:35 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 260/1251] eta: 0:08:36 lr: 0.000046 loss: 2.7663 (2.7557) grad_norm: 2.9017 (3.0787) time: 0.5130 [2021-03-27 03:54:40 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 270/1251] eta: 0:08:30 lr: 0.000046 loss: 2.8383 (2.7551) grad_norm: 2.9285 (3.0794) time: 0.5104 [2021-03-27 03:54:45 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 280/1251] eta: 0:08:24 lr: 0.000046 loss: 2.8484 (2.7618) grad_norm: 3.1395 (3.0825) time: 0.4977 [2021-03-27 03:54:50 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 290/1251] eta: 0:08:18 lr: 0.000046 loss: 2.8524 (2.7635) grad_norm: 2.9579 (3.0769) time: 0.4982 [2021-03-27 03:54:55 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 300/1251] eta: 0:08:13 lr: 0.000046 loss: 2.7996 (2.7628) grad_norm: 2.8377 (3.0711) time: 0.5031 [2021-03-27 03:55:00 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 310/1251] eta: 0:08:07 lr: 0.000046 loss: 2.7307 (2.7657) grad_norm: 2.9055 (3.0783) time: 0.5053 [2021-03-27 03:55:06 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 320/1251] eta: 0:08:02 lr: 0.000046 loss: 2.8987 (2.7707) grad_norm: 3.2545 (3.0901) time: 0.5055 [2021-03-27 03:55:11 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 330/1251] eta: 0:07:56 lr: 0.000046 loss: 2.8987 (2.7712) grad_norm: 3.0669 (3.0861) time: 0.5052 [2021-03-27 03:55:16 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 340/1251] eta: 0:07:50 lr: 0.000046 loss: 2.7945 (2.7737) grad_norm: 2.9170 (3.0835) time: 0.5026 [2021-03-27 03:55:21 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 350/1251] eta: 0:07:45 lr: 0.000046 loss: 2.8737 (2.7765) grad_norm: 2.9745 (3.0959) time: 0.5093 [2021-03-27 03:55:26 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 360/1251] eta: 0:07:40 lr: 0.000046 loss: 2.8737 (2.7767) grad_norm: 2.8815 (3.0919) time: 0.5182 [2021-03-27 03:55:31 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 370/1251] eta: 0:07:35 lr: 0.000046 loss: 2.7462 (2.7740) grad_norm: 2.8724 (3.0870) time: 0.5131 [2021-03-27 03:55:36 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 380/1251] eta: 0:07:29 lr: 0.000046 loss: 2.6235 (2.7719) grad_norm: 2.8861 (3.0822) time: 0.5049 [2021-03-27 03:55:41 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 390/1251] eta: 0:07:24 lr: 0.000046 loss: 2.7356 (2.7700) grad_norm: 3.1015 (3.1142) time: 0.5029 [2021-03-27 03:55:46 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 400/1251] eta: 0:07:18 lr: 0.000046 loss: 2.8104 (2.7738) grad_norm: 3.1734 (3.1130) time: 0.5036 [2021-03-27 03:55:51 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 410/1251] eta: 0:07:13 lr: 0.000046 loss: 2.7207 (2.7678) grad_norm: 2.9377 (3.1119) time: 0.5030 [2021-03-27 03:55:56 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 420/1251] eta: 0:07:08 lr: 0.000046 loss: 2.5745 (2.7630) grad_norm: 2.9254 (3.1062) time: 0.5070 [2021-03-27 03:56:01 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 430/1251] eta: 0:07:02 lr: 0.000046 loss: 2.8632 (2.7677) grad_norm: 2.9444 (3.1066) time: 0.5041 [2021-03-27 03:56:06 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 440/1251] eta: 0:06:57 lr: 0.000046 loss: 3.0457 (2.7690) grad_norm: 2.9444 (3.1121) time: 0.4996 [2021-03-27 03:56:11 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 450/1251] eta: 0:06:51 lr: 0.000046 loss: 2.8284 (2.7674) grad_norm: 3.0386 (3.1131) time: 0.5006 [2021-03-27 03:56:16 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 460/1251] eta: 0:06:46 lr: 0.000046 loss: 2.7413 (2.7636) grad_norm: 3.0907 (3.1226) time: 0.5045 [2021-03-27 03:56:21 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 470/1251] eta: 0:06:41 lr: 0.000046 loss: 2.7886 (2.7650) grad_norm: 2.9555 (3.1160) time: 0.5090 [2021-03-27 03:56:27 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 480/1251] eta: 0:06:36 lr: 0.000046 loss: 2.8596 (2.7669) grad_norm: 2.9048 (3.1147) time: 0.5084 [2021-03-27 03:56:32 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 490/1251] eta: 0:06:30 lr: 0.000046 loss: 2.9706 (2.7692) grad_norm: 3.0500 (3.1160) time: 0.5062 [2021-03-27 03:56:37 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 500/1251] eta: 0:06:25 lr: 0.000046 loss: 2.8083 (2.7693) grad_norm: 2.9602 (3.1152) time: 0.5059 [2021-03-27 03:56:42 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 510/1251] eta: 0:06:20 lr: 0.000046 loss: 2.8083 (2.7728) grad_norm: 2.9602 (3.1136) time: 0.5070 [2021-03-27 03:56:47 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 520/1251] eta: 0:06:15 lr: 0.000046 loss: 2.8299 (2.7702) grad_norm: 3.1553 (3.1156) time: 0.4993 [2021-03-27 03:56:52 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 530/1251] eta: 0:06:09 lr: 0.000046 loss: 2.7170 (2.7688) grad_norm: 3.0253 (3.1136) time: 0.4963 [2021-03-27 03:56:57 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 540/1251] eta: 0:06:04 lr: 0.000046 loss: 2.7170 (2.7684) grad_norm: 2.9061 (3.1191) time: 0.5089 [2021-03-27 03:57:02 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 550/1251] eta: 0:05:59 lr: 0.000046 loss: 2.7192 (2.7679) grad_norm: 3.0018 (3.1160) time: 0.5203 [2021-03-27 03:57:07 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 560/1251] eta: 0:05:54 lr: 0.000046 loss: 2.7719 (2.7723) grad_norm: 3.0018 (3.1207) time: 0.5124 [2021-03-27 03:57:12 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 570/1251] eta: 0:05:49 lr: 0.000046 loss: 2.9729 (2.7745) grad_norm: 2.8657 (3.1321) time: 0.5029 [2021-03-27 03:57:17 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 580/1251] eta: 0:05:43 lr: 0.000046 loss: 3.0134 (2.7759) grad_norm: 2.8733 (3.1298) time: 0.5043 [2021-03-27 03:57:22 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 590/1251] eta: 0:05:38 lr: 0.000046 loss: 2.8839 (2.7759) grad_norm: 3.0387 (3.1300) time: 0.5030 [2021-03-27 03:57:27 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 600/1251] eta: 0:05:33 lr: 0.000046 loss: 2.7585 (2.7708) grad_norm: 2.9455 (3.1270) time: 0.5045 [2021-03-27 03:57:32 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 610/1251] eta: 0:05:28 lr: 0.000046 loss: 2.7585 (2.7710) grad_norm: 2.9455 (3.1284) time: 0.5060 [2021-03-27 03:57:37 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 620/1251] eta: 0:05:23 lr: 0.000046 loss: 2.8161 (2.7715) grad_norm: 2.9470 (3.1254) time: 0.5040 [2021-03-27 03:57:42 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 630/1251] eta: 0:05:17 lr: 0.000046 loss: 2.7068 (2.7697) grad_norm: 2.8894 (3.1231) time: 0.5011 [2021-03-27 03:57:47 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 640/1251] eta: 0:05:12 lr: 0.000046 loss: 2.7641 (2.7686) grad_norm: 2.9912 (3.1241) time: 0.5005 [2021-03-27 03:57:52 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 650/1251] eta: 0:05:07 lr: 0.000046 loss: 2.9241 (2.7733) grad_norm: 2.9433 (3.1242) time: 0.5041 [2021-03-27 03:57:57 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 660/1251] eta: 0:05:02 lr: 0.000046 loss: 2.9305 (2.7722) grad_norm: 2.9319 (3.1230) time: 0.5017 [2021-03-27 03:58:02 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 670/1251] eta: 0:04:57 lr: 0.000046 loss: 2.9753 (2.7760) grad_norm: 2.9319 (3.1206) time: 0.4996 [2021-03-27 03:58:07 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 680/1251] eta: 0:04:51 lr: 0.000046 loss: 3.1212 (2.7792) grad_norm: 2.9065 (3.1227) time: 0.4992 [2021-03-27 03:58:12 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 690/1251] eta: 0:04:46 lr: 0.000046 loss: 2.9514 (2.7795) grad_norm: 2.8824 (3.1202) time: 0.4992 [2021-03-27 03:58:17 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 700/1251] eta: 0:04:41 lr: 0.000046 loss: 2.8450 (2.7777) grad_norm: 2.8824 (3.1212) time: 0.5026 [2021-03-27 03:58:22 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 710/1251] eta: 0:04:36 lr: 0.000046 loss: 2.6955 (2.7751) grad_norm: 3.0642 (3.1233) time: 0.5032 [2021-03-27 03:58:27 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 720/1251] eta: 0:04:31 lr: 0.000046 loss: 2.6955 (2.7726) grad_norm: 3.0642 (3.1227) time: 0.5025 [2021-03-27 03:58:33 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 730/1251] eta: 0:04:26 lr: 0.000046 loss: 2.7580 (2.7749) grad_norm: 3.0007 (3.1272) time: 0.5092 [2021-03-27 03:58:38 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 740/1251] eta: 0:04:21 lr: 0.000046 loss: 2.9947 (2.7765) grad_norm: 2.9678 (3.1268) time: 0.5233 [2021-03-27 03:58:43 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 750/1251] eta: 0:04:16 lr: 0.000046 loss: 3.0698 (2.7793) grad_norm: 2.9142 (3.1241) time: 0.5249 [2021-03-27 03:58:48 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 760/1251] eta: 0:04:10 lr: 0.000046 loss: 2.8918 (2.7790) grad_norm: 2.6611 (3.1227) time: 0.5172 [2021-03-27 03:58:53 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 770/1251] eta: 0:04:05 lr: 0.000045 loss: 2.7691 (2.7775) grad_norm: 2.8807 (3.1219) time: 0.5060 [2021-03-27 03:58:58 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 780/1251] eta: 0:04:00 lr: 0.000045 loss: 2.8645 (2.7781) grad_norm: 2.8514 (3.1174) time: 0.5006 [2021-03-27 03:59:03 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 790/1251] eta: 0:03:55 lr: 0.000045 loss: 2.8349 (2.7774) grad_norm: 2.8969 (3.1160) time: 0.5020 [2021-03-27 03:59:08 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 800/1251] eta: 0:03:50 lr: 0.000045 loss: 2.8014 (2.7784) grad_norm: 2.9927 (3.1325) time: 0.4997 [2021-03-27 03:59:13 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 810/1251] eta: 0:03:45 lr: 0.000045 loss: 2.6512 (2.7781) grad_norm: 3.0433 (3.1359) time: 0.5033 [2021-03-27 03:59:18 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 820/1251] eta: 0:03:39 lr: 0.000045 loss: 2.6261 (2.7737) grad_norm: 2.9434 (3.1321) time: 0.5035 [2021-03-27 03:59:23 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 830/1251] eta: 0:03:34 lr: 0.000045 loss: 2.5036 (2.7716) grad_norm: 2.8651 (3.1318) time: 0.5052 [2021-03-27 03:59:29 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 840/1251] eta: 0:03:29 lr: 0.000045 loss: 2.8687 (2.7719) grad_norm: 2.8651 (3.1293) time: 0.5102 [2021-03-27 03:59:34 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 850/1251] eta: 0:03:24 lr: 0.000045 loss: 2.7769 (2.7695) grad_norm: 2.9268 (3.1304) time: 0.5105 [2021-03-27 03:59:39 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 860/1251] eta: 0:03:19 lr: 0.000045 loss: 2.8614 (2.7692) grad_norm: 2.9765 (3.1292) time: 0.5049 [2021-03-27 03:59:44 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 870/1251] eta: 0:03:14 lr: 0.000045 loss: 2.8659 (2.7697) grad_norm: 2.6869 (3.1250) time: 0.5054 [2021-03-27 03:59:49 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 880/1251] eta: 0:03:09 lr: 0.000045 loss: 2.9897 (2.7701) grad_norm: 2.8221 (3.1337) time: 0.5092 [2021-03-27 03:59:54 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 890/1251] eta: 0:03:04 lr: 0.000045 loss: 2.7824 (2.7677) grad_norm: 2.8802 (3.1351) time: 0.5073 [2021-03-27 03:59:59 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 900/1251] eta: 0:02:59 lr: 0.000045 loss: 2.7824 (2.7678) grad_norm: 3.0168 (3.1344) time: 0.5038 [2021-03-27 04:00:04 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 910/1251] eta: 0:02:53 lr: 0.000045 loss: 2.6674 (2.7654) grad_norm: 2.9842 (3.1342) time: 0.5043 [2021-03-27 04:00:09 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 920/1251] eta: 0:02:48 lr: 0.000045 loss: 2.7083 (2.7646) grad_norm: 2.9055 (3.1321) time: 0.5026 [2021-03-27 04:00:14 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 930/1251] eta: 0:02:43 lr: 0.000045 loss: 2.8722 (2.7658) grad_norm: 2.9797 (3.1313) time: 0.4980 [2021-03-27 04:00:19 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 940/1251] eta: 0:02:38 lr: 0.000045 loss: 2.9346 (2.7662) grad_norm: 3.0454 (3.1323) time: 0.5053 [2021-03-27 04:00:24 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 950/1251] eta: 0:02:33 lr: 0.000045 loss: 2.9346 (2.7665) grad_norm: 3.0847 (3.1369) time: 0.5153 [2021-03-27 04:00:29 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 960/1251] eta: 0:02:28 lr: 0.000045 loss: 2.9472 (2.7678) grad_norm: 3.0418 (3.1349) time: 0.5084 [2021-03-27 04:00:34 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 970/1251] eta: 0:02:23 lr: 0.000045 loss: 2.7667 (2.7652) grad_norm: 2.9526 (3.1355) time: 0.5039 [2021-03-27 04:00:39 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 980/1251] eta: 0:02:18 lr: 0.000045 loss: 2.7596 (2.7651) grad_norm: 2.8845 (3.1318) time: 0.5069 [2021-03-27 04:00:44 swin_small_patch4_window7_224] INFO: Epoch: [263] [ 990/1251] eta: 0:02:13 lr: 0.000045 loss: 2.8290 (2.7655) grad_norm: 2.8173 (3.1294) time: 0.5034 [2021-03-27 04:00:50 swin_small_patch4_window7_224] INFO: Epoch: [263] [1000/1251] eta: 0:02:07 lr: 0.000045 loss: 2.9704 (2.7666) grad_norm: 2.8063 (3.1312) time: 0.5029 [2021-03-27 04:00:55 swin_small_patch4_window7_224] INFO: Epoch: [263] [1010/1251] eta: 0:02:02 lr: 0.000045 loss: 2.8395 (2.7658) grad_norm: 2.8061 (3.1284) time: 0.5055 [2021-03-27 04:01:00 swin_small_patch4_window7_224] INFO: Epoch: [263] [1020/1251] eta: 0:01:57 lr: 0.000045 loss: 2.7497 (2.7655) grad_norm: 2.7994 (3.1246) time: 0.5045 [2021-03-27 04:01:05 swin_small_patch4_window7_224] INFO: Epoch: [263] [1030/1251] eta: 0:01:52 lr: 0.000045 loss: 2.7809 (2.7659) grad_norm: 2.7994 (3.1212) time: 0.4963 [2021-03-27 04:01:09 swin_small_patch4_window7_224] INFO: Epoch: [263] [1040/1251] eta: 0:01:47 lr: 0.000045 loss: 2.8093 (2.7665) grad_norm: 2.8656 (3.1216) time: 0.4929 [2021-03-27 04:01:14 swin_small_patch4_window7_224] INFO: Epoch: [263] [1050/1251] eta: 0:01:42 lr: 0.000045 loss: 2.6861 (2.7630) grad_norm: 2.8547 (3.1182) time: 0.4982 [2021-03-27 04:01:20 swin_small_patch4_window7_224] INFO: Epoch: [263] [1060/1251] eta: 0:01:37 lr: 0.000045 loss: 2.7228 (2.7630) grad_norm: 2.8571 (3.1175) time: 0.5040 [2021-03-27 04:01:25 swin_small_patch4_window7_224] INFO: Epoch: [263] [1070/1251] eta: 0:01:32 lr: 0.000045 loss: 2.7280 (2.7628) grad_norm: 3.0651 (3.1184) time: 0.5006 [2021-03-27 04:01:30 swin_small_patch4_window7_224] INFO: Epoch: [263] [1080/1251] eta: 0:01:27 lr: 0.000045 loss: 2.7225 (2.7639) grad_norm: 3.1822 (3.1187) time: 0.4996 [2021-03-27 04:01:35 swin_small_patch4_window7_224] INFO: Epoch: [263] [1090/1251] eta: 0:01:21 lr: 0.000045 loss: 2.8492 (2.7632) grad_norm: 3.0440 (3.1169) time: 0.5042 [2021-03-27 04:01:40 swin_small_patch4_window7_224] INFO: Epoch: [263] [1100/1251] eta: 0:01:16 lr: 0.000045 loss: 2.8492 (2.7636) grad_norm: 2.8995 (3.1149) time: 0.5080 [2021-03-27 04:01:45 swin_small_patch4_window7_224] INFO: Epoch: [263] [1110/1251] eta: 0:01:11 lr: 0.000045 loss: 2.8501 (2.7635) grad_norm: 2.9183 (3.1160) time: 0.5086 [2021-03-27 04:01:50 swin_small_patch4_window7_224] INFO: Epoch: [263] [1120/1251] eta: 0:01:06 lr: 0.000045 loss: 2.8148 (2.7632) grad_norm: 2.9183 (3.1135) time: 0.5084 [2021-03-27 04:01:55 swin_small_patch4_window7_224] INFO: Epoch: [263] [1130/1251] eta: 0:01:01 lr: 0.000045 loss: 2.7094 (2.7619) grad_norm: 2.9195 (3.1138) time: 0.5036 [2021-03-27 04:02:00 swin_small_patch4_window7_224] INFO: Epoch: [263] [1140/1251] eta: 0:00:56 lr: 0.000045 loss: 2.7094 (2.7621) grad_norm: 2.9529 (3.1128) time: 0.4977 [2021-03-27 04:02:05 swin_small_patch4_window7_224] INFO: Epoch: [263] [1150/1251] eta: 0:00:51 lr: 0.000045 loss: 2.4999 (2.7600) grad_norm: 2.7902 (3.1122) time: 0.4988 [2021-03-27 04:02:10 swin_small_patch4_window7_224] INFO: Epoch: [263] [1160/1251] eta: 0:00:46 lr: 0.000045 loss: 2.4103 (2.7593) grad_norm: 2.8922 (3.1107) time: 0.4952 [2021-03-27 04:02:15 swin_small_patch4_window7_224] INFO: Epoch: [263] [1170/1251] eta: 0:00:41 lr: 0.000045 loss: 2.5967 (2.7576) grad_norm: 2.9352 (3.1097) time: 0.4967 [2021-03-27 04:02:20 swin_small_patch4_window7_224] INFO: Epoch: [263] [1180/1251] eta: 0:00:36 lr: 0.000045 loss: 2.7870 (2.7587) grad_norm: 2.8603 (3.1080) time: 0.5033 [2021-03-27 04:02:25 swin_small_patch4_window7_224] INFO: Epoch: [263] [1190/1251] eta: 0:00:31 lr: 0.000045 loss: 2.9431 (2.7596) grad_norm: 2.8861 (3.1082) time: 0.5048 [2021-03-27 04:02:30 swin_small_patch4_window7_224] INFO: Epoch: [263] [1200/1251] eta: 0:00:25 lr: 0.000045 loss: 2.9404 (2.7610) grad_norm: 2.8872 (3.1076) time: 0.5090 [2021-03-27 04:02:35 swin_small_patch4_window7_224] INFO: Epoch: [263] [1210/1251] eta: 0:00:20 lr: 0.000045 loss: 2.8875 (2.7610) grad_norm: 2.7852 (3.1054) time: 0.5092 [2021-03-27 04:02:40 swin_small_patch4_window7_224] INFO: Epoch: [263] [1220/1251] eta: 0:00:15 lr: 0.000045 loss: 2.7300 (2.7599) grad_norm: 2.8721 (3.1063) time: 0.5028 [2021-03-27 04:02:45 swin_small_patch4_window7_224] INFO: Epoch: [263] [1230/1251] eta: 0:00:10 lr: 0.000045 loss: 2.8432 (2.7606) grad_norm: 2.9936 (3.1045) time: 0.5040 [2021-03-27 04:02:50 swin_small_patch4_window7_224] INFO: Epoch: [263] [1240/1251] eta: 0:00:05 lr: 0.000045 loss: 2.9753 (2.7626) grad_norm: 2.8898 (3.1086) time: 0.5070 [2021-03-27 04:02:55 swin_small_patch4_window7_224] INFO: Epoch: [263] [1250/1251] eta: 0:00:00 lr: 0.000045 loss: 2.9973 (2.7632) grad_norm: 3.0600 (3.1090) time: 0.5082 [2021-03-27 04:03:07 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.7638 (0.7638) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-27 04:03:10 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7638 (0.7834) acc1: 82.8125 (82.6705) acc5: 95.3125 (96.1648) [2021-03-27 04:03:13 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7066 (0.7739) acc1: 82.8125 (82.5893) acc5: 96.8750 (96.2798) [2021-03-27 04:03:15 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.6640 (0.7609) acc1: 82.8125 (82.7117) acc5: 96.8750 (96.6230) [2021-03-27 04:03:17 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6716 (0.7585) acc1: 84.3750 (82.6982) acc5: 96.8750 (96.4558) [2021-03-27 04:03:17 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6752 (0.7569) acc1: 81.2500 (82.2400) acc5: 95.3125 (96.4160) [2021-03-27 04:03:32 swin_small_patch4_window7_224] INFO: * Acc@1 82.844 Acc@5 96.238 loss 0.747 [2021-03-27 04:03:32 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 04:03:32 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 04:03:36 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 0/1251] eta: 1:30:46 lr: 0.000045 loss: 2.8626 (2.8626) grad_norm: 2.3301 (2.3301) time: 4.3536 [2021-03-27 04:03:42 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 10/1251] eta: 0:18:02 lr: 0.000045 loss: 2.7567 (2.7060) grad_norm: 2.9654 (2.9384) time: 0.8723 [2021-03-27 04:03:47 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 20/1251] eta: 0:14:18 lr: 0.000045 loss: 2.7414 (2.6857) grad_norm: 2.9413 (2.9237) time: 0.5148 [2021-03-27 04:03:52 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 30/1251] eta: 0:12:51 lr: 0.000045 loss: 2.5620 (2.6404) grad_norm: 2.8162 (2.9317) time: 0.4996 [2021-03-27 04:03:57 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 40/1251] eta: 0:12:07 lr: 0.000045 loss: 2.7272 (2.6527) grad_norm: 2.9548 (2.9989) time: 0.4993 [2021-03-27 04:04:02 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 50/1251] eta: 0:11:41 lr: 0.000045 loss: 2.7323 (2.6761) grad_norm: 2.9927 (2.9955) time: 0.5094 [2021-03-27 04:04:07 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 60/1251] eta: 0:11:18 lr: 0.000045 loss: 2.5081 (2.6384) grad_norm: 2.8522 (2.9792) time: 0.5058 [2021-03-27 04:04:12 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 70/1251] eta: 0:11:01 lr: 0.000045 loss: 2.5081 (2.6356) grad_norm: 2.8350 (2.9787) time: 0.4983 [2021-03-27 04:04:17 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 80/1251] eta: 0:10:48 lr: 0.000045 loss: 2.8915 (2.6758) grad_norm: 2.8830 (2.9998) time: 0.5046 [2021-03-27 04:04:22 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 90/1251] eta: 0:10:36 lr: 0.000045 loss: 2.9594 (2.7056) grad_norm: 2.9602 (3.0084) time: 0.5091 [2021-03-27 04:04:27 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 100/1251] eta: 0:10:26 lr: 0.000045 loss: 2.9590 (2.7182) grad_norm: 3.0447 (3.0633) time: 0.5082 [2021-03-27 04:04:32 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 110/1251] eta: 0:10:17 lr: 0.000045 loss: 2.7955 (2.7142) grad_norm: 2.9680 (3.0515) time: 0.5082 [2021-03-27 04:04:37 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 120/1251] eta: 0:10:08 lr: 0.000045 loss: 2.7870 (2.7101) grad_norm: 2.9842 (3.0604) time: 0.5056 [2021-03-27 04:04:42 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 130/1251] eta: 0:10:00 lr: 0.000045 loss: 2.7870 (2.7131) grad_norm: 2.9112 (3.0315) time: 0.5053 [2021-03-27 04:04:47 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 140/1251] eta: 0:09:53 lr: 0.000045 loss: 2.7002 (2.7154) grad_norm: 2.6697 (3.0403) time: 0.5091 [2021-03-27 04:04:52 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 150/1251] eta: 0:09:45 lr: 0.000045 loss: 2.9761 (2.7302) grad_norm: 3.0052 (3.0573) time: 0.5038 [2021-03-27 04:04:57 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 160/1251] eta: 0:09:37 lr: 0.000045 loss: 3.0073 (2.7324) grad_norm: 3.0305 (3.0802) time: 0.4970 [2021-03-27 04:05:02 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 170/1251] eta: 0:09:30 lr: 0.000045 loss: 2.8314 (2.7356) grad_norm: 2.7929 (3.0569) time: 0.5019 [2021-03-27 04:05:07 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 180/1251] eta: 0:09:24 lr: 0.000044 loss: 2.9003 (2.7463) grad_norm: 2.7637 (3.0549) time: 0.5058 [2021-03-27 04:05:12 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 190/1251] eta: 0:09:17 lr: 0.000044 loss: 2.8733 (2.7429) grad_norm: 2.8289 (3.0445) time: 0.5006 [2021-03-27 04:05:17 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 200/1251] eta: 0:09:11 lr: 0.000044 loss: 2.5451 (2.7424) grad_norm: 2.8247 (3.0356) time: 0.5017 [2021-03-27 04:05:23 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 210/1251] eta: 0:09:05 lr: 0.000044 loss: 2.5420 (2.7330) grad_norm: 2.7507 (3.0189) time: 0.5123 [2021-03-27 04:05:28 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 220/1251] eta: 0:08:59 lr: 0.000044 loss: 2.7871 (2.7395) grad_norm: 2.7507 (3.0151) time: 0.5076 [2021-03-27 04:05:33 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 230/1251] eta: 0:08:52 lr: 0.000044 loss: 2.9827 (2.7443) grad_norm: 2.9981 (3.0236) time: 0.5007 [2021-03-27 04:05:38 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 240/1251] eta: 0:08:46 lr: 0.000044 loss: 2.7643 (2.7443) grad_norm: 2.9981 (3.0264) time: 0.5033 [2021-03-27 04:05:43 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 250/1251] eta: 0:08:41 lr: 0.000044 loss: 2.8409 (2.7549) grad_norm: 2.7043 (3.0161) time: 0.5037 [2021-03-27 04:05:48 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 260/1251] eta: 0:08:35 lr: 0.000044 loss: 2.8584 (2.7547) grad_norm: 2.7746 (3.0140) time: 0.5021 [2021-03-27 04:05:53 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 270/1251] eta: 0:08:28 lr: 0.000044 loss: 2.8584 (2.7524) grad_norm: 2.7746 (3.0072) time: 0.4968 [2021-03-27 04:05:58 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 280/1251] eta: 0:08:23 lr: 0.000044 loss: 2.8256 (2.7496) grad_norm: 2.7719 (3.0359) time: 0.5027 [2021-03-27 04:06:03 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 290/1251] eta: 0:08:17 lr: 0.000044 loss: 2.7719 (2.7523) grad_norm: 3.1117 (3.0307) time: 0.5043 [2021-03-27 04:06:08 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 300/1251] eta: 0:08:12 lr: 0.000044 loss: 2.7192 (2.7492) grad_norm: 3.0509 (3.0543) time: 0.5048 [2021-03-27 04:06:13 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 310/1251] eta: 0:08:06 lr: 0.000044 loss: 2.8251 (2.7498) grad_norm: 3.0509 (3.0538) time: 0.5067 [2021-03-27 04:06:18 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 320/1251] eta: 0:08:01 lr: 0.000044 loss: 2.9270 (2.7529) grad_norm: 3.1818 (3.0649) time: 0.5082 [2021-03-27 04:06:23 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 330/1251] eta: 0:07:55 lr: 0.000044 loss: 2.7965 (2.7509) grad_norm: 3.0435 (3.0620) time: 0.5089 [2021-03-27 04:06:28 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 340/1251] eta: 0:07:50 lr: 0.000044 loss: 2.6918 (2.7510) grad_norm: 3.0263 (3.0733) time: 0.5029 [2021-03-27 04:06:33 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 350/1251] eta: 0:07:44 lr: 0.000044 loss: 2.7091 (2.7474) grad_norm: 3.0033 (3.0691) time: 0.5013 [2021-03-27 04:06:38 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 360/1251] eta: 0:07:39 lr: 0.000044 loss: 2.7091 (2.7462) grad_norm: 2.8626 (3.0648) time: 0.5012 [2021-03-27 04:06:43 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 370/1251] eta: 0:07:33 lr: 0.000044 loss: 2.7936 (2.7491) grad_norm: 2.8053 (3.0586) time: 0.4998 [2021-03-27 04:06:48 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 380/1251] eta: 0:07:28 lr: 0.000044 loss: 2.9664 (2.7560) grad_norm: 2.6517 (3.0482) time: 0.5001 [2021-03-27 04:06:53 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 390/1251] eta: 0:07:22 lr: 0.000044 loss: 2.9285 (2.7589) grad_norm: 2.6930 (3.0610) time: 0.5020 [2021-03-27 04:06:58 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 400/1251] eta: 0:07:17 lr: 0.000044 loss: 2.9332 (2.7621) grad_norm: 2.8378 (3.0596) time: 0.5038 [2021-03-27 04:07:03 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 410/1251] eta: 0:07:12 lr: 0.000044 loss: 2.8621 (2.7595) grad_norm: 2.9708 (3.0585) time: 0.5051 [2021-03-27 04:07:08 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 420/1251] eta: 0:07:06 lr: 0.000044 loss: 2.8269 (2.7619) grad_norm: 2.9961 (inf) time: 0.4974 [2021-03-27 04:07:13 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 430/1251] eta: 0:07:01 lr: 0.000044 loss: 2.9537 (2.7670) grad_norm: 2.7356 (inf) time: 0.4990 [2021-03-27 04:07:18 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 440/1251] eta: 0:06:55 lr: 0.000044 loss: 2.7984 (2.7597) grad_norm: 2.8890 (inf) time: 0.4999 [2021-03-27 04:07:23 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 450/1251] eta: 0:06:50 lr: 0.000044 loss: 2.7611 (2.7631) grad_norm: 2.8722 (inf) time: 0.4969 [2021-03-27 04:07:28 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 460/1251] eta: 0:06:44 lr: 0.000044 loss: 2.9504 (2.7664) grad_norm: 2.8647 (inf) time: 0.4972 [2021-03-27 04:07:33 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 470/1251] eta: 0:06:39 lr: 0.000044 loss: 2.9339 (2.7683) grad_norm: 2.9728 (inf) time: 0.4998 [2021-03-27 04:07:38 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 480/1251] eta: 0:06:34 lr: 0.000044 loss: 2.7843 (2.7608) grad_norm: 2.9885 (inf) time: 0.5010 [2021-03-27 04:07:43 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 490/1251] eta: 0:06:29 lr: 0.000044 loss: 2.0265 (2.7506) grad_norm: 2.8605 (inf) time: 0.4972 [2021-03-27 04:07:48 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 500/1251] eta: 0:06:23 lr: 0.000044 loss: 2.3446 (2.7500) grad_norm: 2.8127 (inf) time: 0.5007 [2021-03-27 04:07:53 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 510/1251] eta: 0:06:18 lr: 0.000044 loss: 2.8262 (2.7526) grad_norm: 3.0379 (inf) time: 0.5012 [2021-03-27 04:07:58 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 520/1251] eta: 0:06:13 lr: 0.000044 loss: 2.8262 (2.7513) grad_norm: 2.7843 (inf) time: 0.4996 [2021-03-27 04:08:03 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 530/1251] eta: 0:06:07 lr: 0.000044 loss: 2.8152 (2.7511) grad_norm: 2.7551 (inf) time: 0.4968 [2021-03-27 04:08:08 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 540/1251] eta: 0:06:02 lr: 0.000044 loss: 3.0011 (2.7533) grad_norm: 2.8353 (inf) time: 0.5013 [2021-03-27 04:08:13 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 550/1251] eta: 0:05:57 lr: 0.000044 loss: 2.7484 (2.7516) grad_norm: 2.8257 (inf) time: 0.5159 [2021-03-27 04:08:19 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 560/1251] eta: 0:05:52 lr: 0.000044 loss: 2.8763 (2.7547) grad_norm: 2.7302 (inf) time: 0.5149 [2021-03-27 04:08:24 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 570/1251] eta: 0:05:47 lr: 0.000044 loss: 2.8794 (2.7542) grad_norm: 2.7957 (inf) time: 0.5049 [2021-03-27 04:08:29 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 580/1251] eta: 0:05:42 lr: 0.000044 loss: 2.9218 (2.7567) grad_norm: 2.9008 (inf) time: 0.5034 [2021-03-27 04:08:34 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 590/1251] eta: 0:05:37 lr: 0.000044 loss: 2.8541 (2.7572) grad_norm: 2.9783 (inf) time: 0.4995 [2021-03-27 04:08:39 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 600/1251] eta: 0:05:31 lr: 0.000044 loss: 2.8227 (2.7566) grad_norm: 3.0412 (inf) time: 0.4972 [2021-03-27 04:08:44 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 610/1251] eta: 0:05:26 lr: 0.000044 loss: 2.8227 (2.7560) grad_norm: 2.8485 (inf) time: 0.5025 [2021-03-27 04:08:49 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 620/1251] eta: 0:05:21 lr: 0.000044 loss: 2.7716 (2.7551) grad_norm: 2.8110 (inf) time: 0.5024 [2021-03-27 04:08:54 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 630/1251] eta: 0:05:16 lr: 0.000044 loss: 2.7716 (2.7568) grad_norm: 2.9458 (inf) time: 0.5024 [2021-03-27 04:08:59 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 640/1251] eta: 0:05:11 lr: 0.000044 loss: 2.9363 (2.7575) grad_norm: 2.9182 (inf) time: 0.5139 [2021-03-27 04:09:04 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 650/1251] eta: 0:05:06 lr: 0.000044 loss: 2.8954 (2.7579) grad_norm: 2.8797 (inf) time: 0.5186 [2021-03-27 04:09:09 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 660/1251] eta: 0:05:01 lr: 0.000044 loss: 2.6024 (2.7517) grad_norm: 2.8474 (inf) time: 0.5115 [2021-03-27 04:09:14 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 670/1251] eta: 0:04:56 lr: 0.000044 loss: 2.7966 (2.7533) grad_norm: 2.7913 (inf) time: 0.5064 [2021-03-27 04:09:19 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 680/1251] eta: 0:04:50 lr: 0.000044 loss: 2.8710 (2.7518) grad_norm: 2.8372 (inf) time: 0.5029 [2021-03-27 04:09:24 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 690/1251] eta: 0:04:45 lr: 0.000044 loss: 2.8173 (2.7523) grad_norm: 2.8072 (inf) time: 0.5061 [2021-03-27 04:09:29 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 700/1251] eta: 0:04:40 lr: 0.000044 loss: 2.8619 (2.7548) grad_norm: 2.8679 (inf) time: 0.5042 [2021-03-27 04:09:34 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 710/1251] eta: 0:04:35 lr: 0.000044 loss: 2.8687 (2.7536) grad_norm: 2.9093 (inf) time: 0.4991 [2021-03-27 04:09:39 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 720/1251] eta: 0:04:30 lr: 0.000044 loss: 2.8807 (2.7557) grad_norm: 3.0675 (inf) time: 0.5056 [2021-03-27 04:09:45 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 730/1251] eta: 0:04:25 lr: 0.000044 loss: 2.8807 (2.7532) grad_norm: 3.0675 (inf) time: 0.5126 [2021-03-27 04:09:50 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 740/1251] eta: 0:04:20 lr: 0.000044 loss: 2.7475 (2.7514) grad_norm: 2.8303 (inf) time: 0.5316 [2021-03-27 04:09:55 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 750/1251] eta: 0:04:15 lr: 0.000044 loss: 2.6178 (2.7501) grad_norm: 2.8093 (inf) time: 0.5290 [2021-03-27 04:10:00 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 760/1251] eta: 0:04:10 lr: 0.000044 loss: 2.6145 (2.7481) grad_norm: 2.8093 (inf) time: 0.5156 [2021-03-27 04:10:05 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 770/1251] eta: 0:04:05 lr: 0.000044 loss: 2.7273 (2.7487) grad_norm: 3.0106 (inf) time: 0.5109 [2021-03-27 04:10:10 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 780/1251] eta: 0:04:00 lr: 0.000044 loss: 2.7273 (2.7472) grad_norm: 2.9761 (inf) time: 0.5017 [2021-03-27 04:10:15 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 790/1251] eta: 0:03:54 lr: 0.000044 loss: 2.6371 (2.7464) grad_norm: 3.0359 (inf) time: 0.4996 [2021-03-27 04:10:20 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 800/1251] eta: 0:03:49 lr: 0.000044 loss: 2.6840 (2.7454) grad_norm: 3.0150 (inf) time: 0.5031 [2021-03-27 04:10:25 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 810/1251] eta: 0:03:44 lr: 0.000044 loss: 2.9277 (2.7475) grad_norm: 3.0150 (inf) time: 0.5031 [2021-03-27 04:10:30 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 820/1251] eta: 0:03:39 lr: 0.000044 loss: 2.9720 (2.7455) grad_norm: 3.3101 (inf) time: 0.4976 [2021-03-27 04:10:36 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 830/1251] eta: 0:03:34 lr: 0.000044 loss: 2.6074 (2.7434) grad_norm: 3.0680 (inf) time: 0.5062 [2021-03-27 04:10:41 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 840/1251] eta: 0:03:29 lr: 0.000043 loss: 2.6357 (2.7424) grad_norm: 3.0871 (inf) time: 0.5118 [2021-03-27 04:10:46 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 850/1251] eta: 0:03:24 lr: 0.000043 loss: 2.8963 (2.7452) grad_norm: 3.2053 (inf) time: 0.5038 [2021-03-27 04:10:51 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 860/1251] eta: 0:03:19 lr: 0.000043 loss: 2.8685 (2.7438) grad_norm: 3.0043 (inf) time: 0.4992 [2021-03-27 04:10:56 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 870/1251] eta: 0:03:13 lr: 0.000043 loss: 2.7061 (2.7430) grad_norm: 2.7978 (inf) time: 0.5015 [2021-03-27 04:11:01 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 880/1251] eta: 0:03:08 lr: 0.000043 loss: 2.9639 (2.7458) grad_norm: 2.8760 (inf) time: 0.5057 [2021-03-27 04:11:06 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 890/1251] eta: 0:03:03 lr: 0.000043 loss: 2.9232 (2.7454) grad_norm: 2.8760 (inf) time: 0.5035 [2021-03-27 04:11:11 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 900/1251] eta: 0:02:58 lr: 0.000043 loss: 2.8702 (2.7477) grad_norm: 2.9997 (inf) time: 0.4958 [2021-03-27 04:11:16 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 910/1251] eta: 0:02:53 lr: 0.000043 loss: 2.9969 (2.7485) grad_norm: 3.0443 (inf) time: 0.5011 [2021-03-27 04:11:21 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 920/1251] eta: 0:02:48 lr: 0.000043 loss: 3.0589 (2.7518) grad_norm: 2.9105 (inf) time: 0.5069 [2021-03-27 04:11:26 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 930/1251] eta: 0:02:43 lr: 0.000043 loss: 2.9941 (2.7527) grad_norm: 2.9783 (inf) time: 0.5075 [2021-03-27 04:11:31 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 940/1251] eta: 0:02:38 lr: 0.000043 loss: 2.8722 (2.7525) grad_norm: 2.9817 (inf) time: 0.5139 [2021-03-27 04:11:36 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 950/1251] eta: 0:02:33 lr: 0.000043 loss: 2.8874 (2.7532) grad_norm: 2.9513 (inf) time: 0.5130 [2021-03-27 04:11:41 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 960/1251] eta: 0:02:28 lr: 0.000043 loss: 2.5655 (2.7516) grad_norm: 2.9314 (inf) time: 0.5058 [2021-03-27 04:11:46 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 970/1251] eta: 0:02:22 lr: 0.000043 loss: 2.6539 (2.7524) grad_norm: 2.9953 (inf) time: 0.5016 [2021-03-27 04:11:51 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 980/1251] eta: 0:02:17 lr: 0.000043 loss: 2.9457 (2.7538) grad_norm: 2.9572 (inf) time: 0.4979 [2021-03-27 04:11:56 swin_small_patch4_window7_224] INFO: Epoch: [264] [ 990/1251] eta: 0:02:12 lr: 0.000043 loss: 2.6202 (2.7520) grad_norm: 3.0572 (inf) time: 0.4977 [2021-03-27 04:12:01 swin_small_patch4_window7_224] INFO: Epoch: [264] [1000/1251] eta: 0:02:07 lr: 0.000043 loss: 2.6202 (2.7530) grad_norm: 2.9511 (inf) time: 0.4993 [2021-03-27 04:12:06 swin_small_patch4_window7_224] INFO: Epoch: [264] [1010/1251] eta: 0:02:02 lr: 0.000043 loss: 2.7828 (2.7520) grad_norm: 2.8448 (inf) time: 0.5057 [2021-03-27 04:12:11 swin_small_patch4_window7_224] INFO: Epoch: [264] [1020/1251] eta: 0:01:57 lr: 0.000043 loss: 2.6816 (2.7513) grad_norm: 2.8557 (inf) time: 0.5030 [2021-03-27 04:12:16 swin_small_patch4_window7_224] INFO: Epoch: [264] [1030/1251] eta: 0:01:52 lr: 0.000043 loss: 2.6293 (2.7499) grad_norm: 2.8785 (inf) time: 0.4980 [2021-03-27 04:12:21 swin_small_patch4_window7_224] INFO: Epoch: [264] [1040/1251] eta: 0:01:47 lr: 0.000043 loss: 2.7843 (2.7515) grad_norm: 2.8307 (inf) time: 0.5011 [2021-03-27 04:12:26 swin_small_patch4_window7_224] INFO: Epoch: [264] [1050/1251] eta: 0:01:42 lr: 0.000043 loss: 2.9537 (2.7528) grad_norm: 2.6903 (inf) time: 0.5019 [2021-03-27 04:12:31 swin_small_patch4_window7_224] INFO: Epoch: [264] [1060/1251] eta: 0:01:37 lr: 0.000043 loss: 2.9944 (2.7536) grad_norm: 2.6932 (inf) time: 0.5006 [2021-03-27 04:12:36 swin_small_patch4_window7_224] INFO: Epoch: [264] [1070/1251] eta: 0:01:31 lr: 0.000043 loss: 2.9157 (2.7544) grad_norm: 2.8011 (inf) time: 0.5046 [2021-03-27 04:12:41 swin_small_patch4_window7_224] INFO: Epoch: [264] [1080/1251] eta: 0:01:26 lr: 0.000043 loss: 2.8744 (2.7542) grad_norm: 2.9481 (inf) time: 0.5067 [2021-03-27 04:12:46 swin_small_patch4_window7_224] INFO: Epoch: [264] [1090/1251] eta: 0:01:21 lr: 0.000043 loss: 2.8935 (2.7553) grad_norm: 3.0954 (inf) time: 0.5055 [2021-03-27 04:12:51 swin_small_patch4_window7_224] INFO: Epoch: [264] [1100/1251] eta: 0:01:16 lr: 0.000043 loss: 2.9596 (2.7560) grad_norm: 3.2009 (inf) time: 0.5013 [2021-03-27 04:12:56 swin_small_patch4_window7_224] INFO: Epoch: [264] [1110/1251] eta: 0:01:11 lr: 0.000043 loss: 2.7860 (2.7558) grad_norm: 2.9496 (inf) time: 0.5011 [2021-03-27 04:13:01 swin_small_patch4_window7_224] INFO: Epoch: [264] [1120/1251] eta: 0:01:06 lr: 0.000043 loss: 2.8242 (2.7559) grad_norm: 2.8201 (inf) time: 0.4983 [2021-03-27 04:13:06 swin_small_patch4_window7_224] INFO: Epoch: [264] [1130/1251] eta: 0:01:01 lr: 0.000043 loss: 2.8370 (2.7555) grad_norm: 2.7935 (inf) time: 0.4950 [2021-03-27 04:13:11 swin_small_patch4_window7_224] INFO: Epoch: [264] [1140/1251] eta: 0:00:56 lr: 0.000043 loss: 2.6182 (2.7548) grad_norm: 2.8573 (inf) time: 0.5005 [2021-03-27 04:13:16 swin_small_patch4_window7_224] INFO: Epoch: [264] [1150/1251] eta: 0:00:51 lr: 0.000043 loss: 2.8718 (2.7561) grad_norm: 2.9432 (inf) time: 0.4995 [2021-03-27 04:13:21 swin_small_patch4_window7_224] INFO: Epoch: [264] [1160/1251] eta: 0:00:46 lr: 0.000043 loss: 2.8718 (2.7563) grad_norm: 2.9631 (inf) time: 0.4960 [2021-03-27 04:13:26 swin_small_patch4_window7_224] INFO: Epoch: [264] [1170/1251] eta: 0:00:41 lr: 0.000043 loss: 2.7449 (2.7552) grad_norm: 3.0023 (inf) time: 0.4970 [2021-03-27 04:13:31 swin_small_patch4_window7_224] INFO: Epoch: [264] [1180/1251] eta: 0:00:36 lr: 0.000043 loss: 2.6849 (2.7548) grad_norm: 2.7922 (inf) time: 0.4986 [2021-03-27 04:13:36 swin_small_patch4_window7_224] INFO: Epoch: [264] [1190/1251] eta: 0:00:30 lr: 0.000043 loss: 2.9432 (2.7550) grad_norm: 2.9587 (inf) time: 0.4977 [2021-03-27 04:13:41 swin_small_patch4_window7_224] INFO: Epoch: [264] [1200/1251] eta: 0:00:25 lr: 0.000043 loss: 2.9458 (2.7555) grad_norm: 2.9190 (inf) time: 0.5001 [2021-03-27 04:13:46 swin_small_patch4_window7_224] INFO: Epoch: [264] [1210/1251] eta: 0:00:20 lr: 0.000043 loss: 2.8006 (2.7539) grad_norm: 2.8088 (inf) time: 0.4992 [2021-03-27 04:13:51 swin_small_patch4_window7_224] INFO: Epoch: [264] [1220/1251] eta: 0:00:15 lr: 0.000043 loss: 2.7602 (2.7554) grad_norm: 2.8088 (inf) time: 0.4991 [2021-03-27 04:13:56 swin_small_patch4_window7_224] INFO: Epoch: [264] [1230/1251] eta: 0:00:10 lr: 0.000043 loss: 2.8903 (2.7553) grad_norm: 2.7665 (inf) time: 0.5014 [2021-03-27 04:14:01 swin_small_patch4_window7_224] INFO: Epoch: [264] [1240/1251] eta: 0:00:05 lr: 0.000043 loss: 2.8903 (2.7561) grad_norm: 2.9021 (inf) time: 0.4964 [2021-03-27 04:14:06 swin_small_patch4_window7_224] INFO: Epoch: [264] [1250/1251] eta: 0:00:00 lr: 0.000043 loss: 2.9727 (2.7571) grad_norm: 2.9976 (inf) time: 0.4990 [2021-03-27 04:14:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:55 loss: 0.7840 (0.7840) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-27 04:14:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7840 (0.7986) acc1: 81.2500 (81.5341) acc5: 96.8750 (96.1648) [2021-03-27 04:14:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7142 (0.7331) acc1: 82.8125 (82.5149) acc5: 96.8750 (96.7262) [2021-03-27 04:14:23 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.6520 (0.7463) acc1: 82.8125 (82.4597) acc5: 96.8750 (96.3206) [2021-03-27 04:14:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7408 (0.7535) acc1: 81.2500 (82.2409) acc5: 95.3125 (96.2271) [2021-03-27 04:14:26 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7536 (0.7570) acc1: 82.8125 (82.0800) acc5: 95.3125 (96.2560) [2021-03-27 04:14:40 swin_small_patch4_window7_224] INFO: * Acc@1 82.682 Acc@5 96.140 loss 0.747 [2021-03-27 04:14:40 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-27 04:14:40 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 04:14:44 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 0/1251] eta: 1:26:05 lr: 0.000043 loss: 3.4751 (3.4751) grad_norm: 2.9905 (2.9905) time: 4.1293 [2021-03-27 04:14:49 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 10/1251] eta: 0:17:38 lr: 0.000043 loss: 3.0385 (2.9793) grad_norm: 2.9905 (2.9219) time: 0.8532 [2021-03-27 04:14:54 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 20/1251] eta: 0:14:12 lr: 0.000043 loss: 2.8747 (2.8793) grad_norm: 2.8242 (2.9124) time: 0.5204 [2021-03-27 04:14:59 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 30/1251] eta: 0:12:54 lr: 0.000043 loss: 2.8067 (2.8905) grad_norm: 2.8733 (3.1145) time: 0.5134 [2021-03-27 04:15:04 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 40/1251] eta: 0:12:09 lr: 0.000043 loss: 2.8282 (2.8884) grad_norm: 2.9149 (3.0653) time: 0.5088 [2021-03-27 04:15:09 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 50/1251] eta: 0:11:39 lr: 0.000043 loss: 2.8468 (2.8836) grad_norm: 2.9149 (3.0502) time: 0.5029 [2021-03-27 04:15:14 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 60/1251] eta: 0:11:18 lr: 0.000043 loss: 2.8468 (2.8754) grad_norm: 2.9268 (3.0286) time: 0.5018 [2021-03-27 04:15:19 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 70/1251] eta: 0:11:02 lr: 0.000043 loss: 2.9117 (2.8603) grad_norm: 2.8118 (2.9937) time: 0.5063 [2021-03-27 04:15:24 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 80/1251] eta: 0:10:49 lr: 0.000043 loss: 2.7494 (2.8171) grad_norm: 2.8240 (2.9900) time: 0.5072 [2021-03-27 04:15:29 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 90/1251] eta: 0:10:36 lr: 0.000043 loss: 2.8068 (2.8350) grad_norm: 2.9190 (3.0020) time: 0.5035 [2021-03-27 04:15:35 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 100/1251] eta: 0:10:26 lr: 0.000043 loss: 2.8083 (2.8171) grad_norm: 3.1777 (3.0509) time: 0.5025 [2021-03-27 04:15:40 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 110/1251] eta: 0:10:17 lr: 0.000043 loss: 2.7183 (2.8214) grad_norm: 3.1657 (3.0912) time: 0.5078 [2021-03-27 04:15:45 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 120/1251] eta: 0:10:08 lr: 0.000043 loss: 2.7925 (2.8141) grad_norm: 3.1526 (3.0997) time: 0.5098 [2021-03-27 04:15:50 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 130/1251] eta: 0:10:00 lr: 0.000043 loss: 2.7672 (2.8110) grad_norm: 2.9782 (3.0805) time: 0.5030 [2021-03-27 04:15:55 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 140/1251] eta: 0:09:51 lr: 0.000043 loss: 2.7950 (2.7985) grad_norm: 2.8761 (3.0943) time: 0.4995 [2021-03-27 04:16:00 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 150/1251] eta: 0:09:43 lr: 0.000043 loss: 2.5584 (2.7803) grad_norm: 3.0899 (3.1000) time: 0.4981 [2021-03-27 04:16:05 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 160/1251] eta: 0:09:36 lr: 0.000043 loss: 2.6076 (2.7809) grad_norm: 3.0263 (3.0953) time: 0.5003 [2021-03-27 04:16:10 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 170/1251] eta: 0:09:29 lr: 0.000043 loss: 2.6280 (2.7644) grad_norm: 2.9809 (3.0866) time: 0.5035 [2021-03-27 04:16:15 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 180/1251] eta: 0:09:23 lr: 0.000043 loss: 2.6280 (2.7633) grad_norm: 3.1507 (3.1062) time: 0.5057 [2021-03-27 04:16:20 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 190/1251] eta: 0:09:16 lr: 0.000043 loss: 2.8137 (2.7624) grad_norm: 2.9759 (3.1050) time: 0.5034 [2021-03-27 04:16:25 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 200/1251] eta: 0:09:11 lr: 0.000043 loss: 2.8090 (2.7591) grad_norm: 2.9100 (3.1066) time: 0.5079 [2021-03-27 04:16:30 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 210/1251] eta: 0:09:05 lr: 0.000043 loss: 2.7795 (2.7541) grad_norm: 2.8904 (3.0947) time: 0.5170 [2021-03-27 04:16:35 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 220/1251] eta: 0:08:59 lr: 0.000043 loss: 2.7105 (2.7538) grad_norm: 2.8904 (3.1074) time: 0.5125 [2021-03-27 04:16:40 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 230/1251] eta: 0:08:53 lr: 0.000043 loss: 2.6651 (2.7466) grad_norm: 3.0379 (3.1049) time: 0.5097 [2021-03-27 04:16:45 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 240/1251] eta: 0:08:47 lr: 0.000043 loss: 2.5009 (2.7395) grad_norm: 2.8757 (3.0970) time: 0.5028 [2021-03-27 04:16:50 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 250/1251] eta: 0:08:41 lr: 0.000043 loss: 2.9149 (2.7425) grad_norm: 2.7883 (3.0923) time: 0.5059 [2021-03-27 04:16:56 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 260/1251] eta: 0:08:36 lr: 0.000042 loss: 2.9656 (2.7483) grad_norm: 2.8197 (3.0932) time: 0.5116 [2021-03-27 04:17:01 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 270/1251] eta: 0:08:30 lr: 0.000042 loss: 2.9764 (2.7574) grad_norm: 2.8656 (3.0900) time: 0.5022 [2021-03-27 04:17:06 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 280/1251] eta: 0:08:24 lr: 0.000042 loss: 2.9019 (2.7561) grad_norm: 2.8159 (3.0840) time: 0.5014 [2021-03-27 04:17:11 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 290/1251] eta: 0:08:19 lr: 0.000042 loss: 2.8468 (2.7570) grad_norm: 2.7884 (3.0810) time: 0.5137 [2021-03-27 04:17:16 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 300/1251] eta: 0:08:13 lr: 0.000042 loss: 2.9483 (2.7617) grad_norm: 2.8044 (3.0760) time: 0.5145 [2021-03-27 04:17:21 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 310/1251] eta: 0:08:07 lr: 0.000042 loss: 2.8021 (2.7572) grad_norm: 2.8044 (3.0679) time: 0.5000 [2021-03-27 04:17:26 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 320/1251] eta: 0:08:02 lr: 0.000042 loss: 2.8342 (2.7651) grad_norm: 2.8983 (3.0795) time: 0.5040 [2021-03-27 04:17:31 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 330/1251] eta: 0:07:56 lr: 0.000042 loss: 2.8304 (2.7623) grad_norm: 2.9879 (3.0821) time: 0.5085 [2021-03-27 04:17:36 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 340/1251] eta: 0:07:51 lr: 0.000042 loss: 2.8104 (2.7663) grad_norm: 3.0080 (3.0860) time: 0.5042 [2021-03-27 04:17:41 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 350/1251] eta: 0:07:45 lr: 0.000042 loss: 2.9796 (2.7660) grad_norm: 2.9898 (3.0860) time: 0.5033 [2021-03-27 04:17:46 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 360/1251] eta: 0:07:40 lr: 0.000042 loss: 2.8967 (2.7674) grad_norm: 2.8557 (3.0799) time: 0.5084 [2021-03-27 04:17:51 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 370/1251] eta: 0:07:35 lr: 0.000042 loss: 2.9042 (2.7696) grad_norm: 2.8550 (3.0795) time: 0.5103 [2021-03-27 04:17:56 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 380/1251] eta: 0:07:29 lr: 0.000042 loss: 3.0228 (2.7737) grad_norm: 2.8433 (3.0724) time: 0.5067 [2021-03-27 04:18:01 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 390/1251] eta: 0:07:24 lr: 0.000042 loss: 3.0286 (2.7797) grad_norm: 2.8916 (3.0764) time: 0.5019 [2021-03-27 04:18:06 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 400/1251] eta: 0:07:18 lr: 0.000042 loss: 2.9774 (2.7812) grad_norm: 3.0397 (3.0788) time: 0.4999 [2021-03-27 04:18:11 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 410/1251] eta: 0:07:13 lr: 0.000042 loss: 2.7157 (2.7771) grad_norm: 2.8668 (3.0808) time: 0.5022 [2021-03-27 04:18:16 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 420/1251] eta: 0:07:07 lr: 0.000042 loss: 2.5000 (2.7719) grad_norm: 2.8930 (3.0764) time: 0.5002 [2021-03-27 04:18:21 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 430/1251] eta: 0:07:02 lr: 0.000042 loss: 2.5597 (2.7688) grad_norm: 2.9557 (3.0829) time: 0.5026 [2021-03-27 04:18:27 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 440/1251] eta: 0:06:57 lr: 0.000042 loss: 2.6837 (2.7685) grad_norm: 2.9557 (3.0811) time: 0.5107 [2021-03-27 04:18:32 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 450/1251] eta: 0:06:51 lr: 0.000042 loss: 2.8398 (2.7664) grad_norm: 2.9459 (3.0812) time: 0.5070 [2021-03-27 04:18:37 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 460/1251] eta: 0:06:46 lr: 0.000042 loss: 2.8289 (2.7651) grad_norm: 2.9519 (3.0833) time: 0.4966 [2021-03-27 04:18:41 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 470/1251] eta: 0:06:41 lr: 0.000042 loss: 2.7656 (2.7622) grad_norm: 2.8740 (3.0813) time: 0.4973 [2021-03-27 04:18:46 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 480/1251] eta: 0:06:35 lr: 0.000042 loss: 2.5983 (2.7555) grad_norm: 2.9073 (3.0760) time: 0.4971 [2021-03-27 04:18:52 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 490/1251] eta: 0:06:30 lr: 0.000042 loss: 2.8832 (2.7583) grad_norm: 2.9132 (3.0743) time: 0.5007 [2021-03-27 04:18:56 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 500/1251] eta: 0:06:24 lr: 0.000042 loss: 2.8872 (2.7586) grad_norm: 3.0099 (3.0948) time: 0.5007 [2021-03-27 04:19:01 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 510/1251] eta: 0:06:19 lr: 0.000042 loss: 2.5486 (2.7554) grad_norm: 3.0334 (3.0958) time: 0.4968 [2021-03-27 04:19:06 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 520/1251] eta: 0:06:14 lr: 0.000042 loss: 2.4875 (2.7516) grad_norm: 3.0075 (3.0959) time: 0.4971 [2021-03-27 04:19:11 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 530/1251] eta: 0:06:09 lr: 0.000042 loss: 2.7699 (2.7526) grad_norm: 2.9936 (3.1024) time: 0.4996 [2021-03-27 04:19:17 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 540/1251] eta: 0:06:03 lr: 0.000042 loss: 2.8986 (2.7522) grad_norm: 3.0067 (3.1015) time: 0.5063 [2021-03-27 04:19:22 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 550/1251] eta: 0:05:58 lr: 0.000042 loss: 2.7040 (2.7492) grad_norm: 3.0067 (3.1008) time: 0.5183 [2021-03-27 04:19:27 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 560/1251] eta: 0:05:53 lr: 0.000042 loss: 2.5978 (2.7458) grad_norm: 3.1117 (3.1039) time: 0.5163 [2021-03-27 04:19:32 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 570/1251] eta: 0:05:48 lr: 0.000042 loss: 2.7441 (2.7460) grad_norm: 3.1561 (3.1013) time: 0.5007 [2021-03-27 04:19:37 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 580/1251] eta: 0:05:43 lr: 0.000042 loss: 2.7827 (2.7446) grad_norm: 2.8793 (3.0984) time: 0.4973 [2021-03-27 04:19:42 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 590/1251] eta: 0:05:38 lr: 0.000042 loss: 2.7698 (2.7419) grad_norm: 2.9178 (3.0970) time: 0.5054 [2021-03-27 04:19:47 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 600/1251] eta: 0:05:32 lr: 0.000042 loss: 2.8823 (2.7444) grad_norm: 2.9595 (3.0946) time: 0.5053 [2021-03-27 04:19:52 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 610/1251] eta: 0:05:27 lr: 0.000042 loss: 2.8823 (2.7447) grad_norm: 2.9152 (3.0916) time: 0.4983 [2021-03-27 04:19:57 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 620/1251] eta: 0:05:22 lr: 0.000042 loss: 2.6801 (2.7426) grad_norm: 2.7928 (3.0909) time: 0.4985 [2021-03-27 04:20:02 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 630/1251] eta: 0:05:17 lr: 0.000042 loss: 2.8419 (2.7451) grad_norm: 2.8096 (3.0922) time: 0.4977 [2021-03-27 04:20:07 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 640/1251] eta: 0:05:11 lr: 0.000042 loss: 2.9677 (2.7444) grad_norm: 2.9942 (3.0960) time: 0.5023 [2021-03-27 04:20:12 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 650/1251] eta: 0:05:06 lr: 0.000042 loss: 2.9435 (2.7458) grad_norm: 3.0221 (3.0955) time: 0.5100 [2021-03-27 04:20:17 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 660/1251] eta: 0:05:01 lr: 0.000042 loss: 2.8492 (2.7468) grad_norm: 2.9707 (3.0943) time: 0.5074 [2021-03-27 04:20:22 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 670/1251] eta: 0:04:56 lr: 0.000042 loss: 2.8672 (2.7465) grad_norm: 2.9587 (3.0926) time: 0.5015 [2021-03-27 04:20:27 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 680/1251] eta: 0:04:51 lr: 0.000042 loss: 2.9110 (2.7481) grad_norm: 2.8340 (3.0880) time: 0.4989 [2021-03-27 04:20:32 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 690/1251] eta: 0:04:46 lr: 0.000042 loss: 2.8481 (2.7445) grad_norm: 2.7568 (3.0878) time: 0.5016 [2021-03-27 04:20:37 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 700/1251] eta: 0:04:40 lr: 0.000042 loss: 2.6244 (2.7457) grad_norm: 2.8495 (3.0872) time: 0.5010 [2021-03-27 04:20:42 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 710/1251] eta: 0:04:35 lr: 0.000042 loss: 2.9539 (2.7464) grad_norm: 2.8845 (3.0901) time: 0.5003 [2021-03-27 04:20:47 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 720/1251] eta: 0:04:30 lr: 0.000042 loss: 2.7235 (2.7455) grad_norm: 2.8616 (3.0875) time: 0.4996 [2021-03-27 04:20:52 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 730/1251] eta: 0:04:25 lr: 0.000042 loss: 2.6121 (2.7435) grad_norm: 2.7825 (3.0906) time: 0.5068 [2021-03-27 04:20:58 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 740/1251] eta: 0:04:20 lr: 0.000042 loss: 2.7841 (2.7432) grad_norm: 2.9613 (3.0955) time: 0.5329 [2021-03-27 04:21:03 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 750/1251] eta: 0:04:15 lr: 0.000042 loss: 2.8634 (2.7441) grad_norm: 2.9613 (3.0953) time: 0.5269 [2021-03-27 04:21:08 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 760/1251] eta: 0:04:10 lr: 0.000042 loss: 2.6605 (2.7423) grad_norm: 2.9750 (3.0947) time: 0.5142 [2021-03-27 04:21:13 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 770/1251] eta: 0:04:05 lr: 0.000042 loss: 2.7947 (2.7442) grad_norm: 2.9269 (3.0916) time: 0.5103 [2021-03-27 04:21:18 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 780/1251] eta: 0:04:00 lr: 0.000042 loss: 2.7443 (2.7418) grad_norm: 2.9453 (3.0896) time: 0.5016 [2021-03-27 04:21:23 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 790/1251] eta: 0:03:55 lr: 0.000042 loss: 2.7125 (2.7422) grad_norm: 2.9257 (3.0896) time: 0.5056 [2021-03-27 04:21:28 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 800/1251] eta: 0:03:50 lr: 0.000042 loss: 2.9297 (2.7412) grad_norm: 2.8910 (3.0930) time: 0.5092 [2021-03-27 04:21:33 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 810/1251] eta: 0:03:44 lr: 0.000042 loss: 2.8559 (2.7432) grad_norm: 3.1217 (3.0976) time: 0.5110 [2021-03-27 04:21:38 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 820/1251] eta: 0:03:39 lr: 0.000042 loss: 2.8856 (2.7446) grad_norm: 2.9143 (3.0949) time: 0.5059 [2021-03-27 04:21:43 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 830/1251] eta: 0:03:34 lr: 0.000042 loss: 2.8344 (2.7433) grad_norm: 2.8062 (3.0919) time: 0.5010 [2021-03-27 04:21:48 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 840/1251] eta: 0:03:29 lr: 0.000042 loss: 2.6899 (2.7441) grad_norm: 2.9162 (3.0922) time: 0.4982 [2021-03-27 04:21:53 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 850/1251] eta: 0:03:24 lr: 0.000042 loss: 2.8672 (2.7434) grad_norm: 2.9831 (3.0903) time: 0.5021 [2021-03-27 04:21:59 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 860/1251] eta: 0:03:19 lr: 0.000042 loss: 2.8973 (2.7457) grad_norm: 2.9089 (3.1007) time: 0.5079 [2021-03-27 04:22:04 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 870/1251] eta: 0:03:14 lr: 0.000042 loss: 2.9139 (2.7448) grad_norm: 3.0391 (3.1017) time: 0.5058 [2021-03-27 04:22:09 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 880/1251] eta: 0:03:09 lr: 0.000042 loss: 2.8579 (2.7462) grad_norm: 3.1712 (3.1049) time: 0.5037 [2021-03-27 04:22:14 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 890/1251] eta: 0:03:03 lr: 0.000042 loss: 2.7607 (2.7450) grad_norm: 3.1617 (3.1054) time: 0.5032 [2021-03-27 04:22:19 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 900/1251] eta: 0:02:58 lr: 0.000042 loss: 2.5693 (2.7424) grad_norm: 3.0268 (3.1090) time: 0.5049 [2021-03-27 04:22:24 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 910/1251] eta: 0:02:53 lr: 0.000042 loss: 2.5693 (2.7419) grad_norm: 3.0055 (3.1079) time: 0.5068 [2021-03-27 04:22:29 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 920/1251] eta: 0:02:48 lr: 0.000042 loss: 2.8171 (2.7415) grad_norm: 3.0579 (3.1124) time: 0.5072 [2021-03-27 04:22:34 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 930/1251] eta: 0:02:43 lr: 0.000042 loss: 2.7177 (2.7392) grad_norm: 3.1301 (3.1113) time: 0.5014 [2021-03-27 04:22:39 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 940/1251] eta: 0:02:38 lr: 0.000041 loss: 2.8014 (2.7410) grad_norm: 3.0672 (3.1112) time: 0.4989 [2021-03-27 04:22:44 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 950/1251] eta: 0:02:33 lr: 0.000041 loss: 2.9271 (2.7418) grad_norm: 3.0704 (3.1131) time: 0.5069 [2021-03-27 04:22:49 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 960/1251] eta: 0:02:28 lr: 0.000041 loss: 2.8545 (2.7415) grad_norm: 3.0269 (3.1121) time: 0.5094 [2021-03-27 04:22:54 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 970/1251] eta: 0:02:23 lr: 0.000041 loss: 2.7067 (2.7416) grad_norm: 2.9996 (3.1136) time: 0.5104 [2021-03-27 04:22:59 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 980/1251] eta: 0:02:17 lr: 0.000041 loss: 2.8480 (2.7425) grad_norm: 2.9426 (3.1132) time: 0.5060 [2021-03-27 04:23:04 swin_small_patch4_window7_224] INFO: Epoch: [265] [ 990/1251] eta: 0:02:12 lr: 0.000041 loss: 2.8480 (2.7434) grad_norm: 2.8971 (3.1142) time: 0.5065 [2021-03-27 04:23:09 swin_small_patch4_window7_224] INFO: Epoch: [265] [1000/1251] eta: 0:02:07 lr: 0.000041 loss: 2.8427 (2.7441) grad_norm: 2.8112 (3.1123) time: 0.5050 [2021-03-27 04:23:14 swin_small_patch4_window7_224] INFO: Epoch: [265] [1010/1251] eta: 0:02:02 lr: 0.000041 loss: 2.7919 (2.7432) grad_norm: 2.8049 (3.1106) time: 0.5016 [2021-03-27 04:23:19 swin_small_patch4_window7_224] INFO: Epoch: [265] [1020/1251] eta: 0:01:57 lr: 0.000041 loss: 2.8203 (2.7438) grad_norm: 2.8385 (3.1093) time: 0.5018 [2021-03-27 04:23:24 swin_small_patch4_window7_224] INFO: Epoch: [265] [1030/1251] eta: 0:01:52 lr: 0.000041 loss: 2.7047 (2.7420) grad_norm: 2.8271 (3.1074) time: 0.5001 [2021-03-27 04:23:30 swin_small_patch4_window7_224] INFO: Epoch: [265] [1040/1251] eta: 0:01:47 lr: 0.000041 loss: 2.6693 (2.7416) grad_norm: 2.9873 (3.1109) time: 0.5099 [2021-03-27 04:23:35 swin_small_patch4_window7_224] INFO: Epoch: [265] [1050/1251] eta: 0:01:42 lr: 0.000041 loss: 2.9026 (2.7436) grad_norm: 3.0929 (3.1125) time: 0.5095 [2021-03-27 04:23:40 swin_small_patch4_window7_224] INFO: Epoch: [265] [1060/1251] eta: 0:01:37 lr: 0.000041 loss: 2.9635 (2.7448) grad_norm: 3.0934 (3.1146) time: 0.5009 [2021-03-27 04:23:45 swin_small_patch4_window7_224] INFO: Epoch: [265] [1070/1251] eta: 0:01:32 lr: 0.000041 loss: 2.8969 (2.7459) grad_norm: 2.9494 (3.1117) time: 0.4995 [2021-03-27 04:23:50 swin_small_patch4_window7_224] INFO: Epoch: [265] [1080/1251] eta: 0:01:26 lr: 0.000041 loss: 2.8335 (2.7459) grad_norm: 2.7729 (3.1095) time: 0.5000 [2021-03-27 04:23:55 swin_small_patch4_window7_224] INFO: Epoch: [265] [1090/1251] eta: 0:01:21 lr: 0.000041 loss: 2.8335 (2.7468) grad_norm: 2.7318 (3.1064) time: 0.4996 [2021-03-27 04:23:59 swin_small_patch4_window7_224] INFO: Epoch: [265] [1100/1251] eta: 0:01:16 lr: 0.000041 loss: 2.8785 (2.7478) grad_norm: 2.7318 (3.1046) time: 0.4981 [2021-03-27 04:24:05 swin_small_patch4_window7_224] INFO: Epoch: [265] [1110/1251] eta: 0:01:11 lr: 0.000041 loss: 3.0038 (2.7487) grad_norm: 2.9077 (3.1037) time: 0.4993 [2021-03-27 04:24:09 swin_small_patch4_window7_224] INFO: Epoch: [265] [1120/1251] eta: 0:01:06 lr: 0.000041 loss: 2.8362 (2.7502) grad_norm: 2.9419 (3.1030) time: 0.4983 [2021-03-27 04:24:15 swin_small_patch4_window7_224] INFO: Epoch: [265] [1130/1251] eta: 0:01:01 lr: 0.000041 loss: 2.8256 (2.7505) grad_norm: 2.9133 (3.1002) time: 0.5032 [2021-03-27 04:24:20 swin_small_patch4_window7_224] INFO: Epoch: [265] [1140/1251] eta: 0:00:56 lr: 0.000041 loss: 2.8256 (2.7510) grad_norm: 2.9133 (3.0978) time: 0.5067 [2021-03-27 04:24:25 swin_small_patch4_window7_224] INFO: Epoch: [265] [1150/1251] eta: 0:00:51 lr: 0.000041 loss: 2.6308 (2.7489) grad_norm: 2.8133 (3.0956) time: 0.5025 [2021-03-27 04:24:30 swin_small_patch4_window7_224] INFO: Epoch: [265] [1160/1251] eta: 0:00:46 lr: 0.000041 loss: 2.6602 (2.7500) grad_norm: 2.8186 (3.0959) time: 0.4998 [2021-03-27 04:24:35 swin_small_patch4_window7_224] INFO: Epoch: [265] [1170/1251] eta: 0:00:41 lr: 0.000041 loss: 2.7016 (2.7489) grad_norm: 2.8281 (3.0939) time: 0.4962 [2021-03-27 04:24:40 swin_small_patch4_window7_224] INFO: Epoch: [265] [1180/1251] eta: 0:00:36 lr: 0.000041 loss: 2.6894 (2.7497) grad_norm: 2.7663 (3.0991) time: 0.5017 [2021-03-27 04:24:45 swin_small_patch4_window7_224] INFO: Epoch: [265] [1190/1251] eta: 0:00:30 lr: 0.000041 loss: 2.8657 (2.7501) grad_norm: 2.9397 (3.0988) time: 0.5109 [2021-03-27 04:24:50 swin_small_patch4_window7_224] INFO: Epoch: [265] [1200/1251] eta: 0:00:25 lr: 0.000041 loss: 2.9167 (2.7517) grad_norm: 3.0788 (3.1016) time: 0.5066 [2021-03-27 04:24:55 swin_small_patch4_window7_224] INFO: Epoch: [265] [1210/1251] eta: 0:00:20 lr: 0.000041 loss: 2.8790 (2.7521) grad_norm: 3.0588 (3.1010) time: 0.5025 [2021-03-27 04:25:00 swin_small_patch4_window7_224] INFO: Epoch: [265] [1220/1251] eta: 0:00:15 lr: 0.000041 loss: 2.8415 (2.7523) grad_norm: 3.0380 (3.1030) time: 0.5032 [2021-03-27 04:25:05 swin_small_patch4_window7_224] INFO: Epoch: [265] [1230/1251] eta: 0:00:10 lr: 0.000041 loss: 2.8512 (2.7532) grad_norm: 3.0254 (3.1022) time: 0.4998 [2021-03-27 04:25:10 swin_small_patch4_window7_224] INFO: Epoch: [265] [1240/1251] eta: 0:00:05 lr: 0.000041 loss: 2.8458 (2.7528) grad_norm: 2.9753 (3.1010) time: 0.5022 [2021-03-27 04:25:15 swin_small_patch4_window7_224] INFO: Epoch: [265] [1250/1251] eta: 0:00:00 lr: 0.000041 loss: 2.7711 (2.7516) grad_norm: 2.9860 (3.1016) time: 0.4970 [2021-03-27 04:26:08 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:05 loss: 0.7917 (0.7917) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-27 04:26:10 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7917 (0.7770) acc1: 82.8125 (81.6761) acc5: 95.3125 (96.5909) [2021-03-27 04:26:11 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7747 (0.7205) acc1: 84.3750 (83.2589) acc5: 96.8750 (96.5774) [2021-03-27 04:26:12 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7261 (0.7409) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.3206) [2021-03-27 04:26:13 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7261 (0.7400) acc1: 82.8125 (82.6601) acc5: 95.3125 (96.1128) [2021-03-27 04:26:14 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7448 (0.7613) acc1: 82.8125 (82.2080) acc5: 95.3125 (95.9360) [2021-03-27 04:26:28 swin_small_patch4_window7_224] INFO: * Acc@1 82.730 Acc@5 96.126 loss 0.746 [2021-03-27 04:26:28 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-27 04:26:28 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 04:26:32 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 0/1251] eta: 1:24:44 lr: 0.000041 loss: 2.8226 (2.8226) grad_norm: 3.7210 (3.7210) time: 4.0640 [2021-03-27 04:26:37 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 10/1251] eta: 0:17:23 lr: 0.000041 loss: 2.8226 (2.8662) grad_norm: 3.0099 (3.1630) time: 0.8408 [2021-03-27 04:26:42 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 20/1251] eta: 0:13:53 lr: 0.000041 loss: 2.8993 (2.8503) grad_norm: 2.9590 (3.0910) time: 0.5079 [2021-03-27 04:26:47 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 30/1251] eta: 0:12:37 lr: 0.000041 loss: 2.6872 (2.7340) grad_norm: 2.8372 (3.1498) time: 0.4992 [2021-03-27 04:26:53 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 40/1251] eta: 0:12:00 lr: 0.000041 loss: 2.5038 (2.6967) grad_norm: 2.9462 (3.1287) time: 0.5086 [2021-03-27 04:26:58 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 50/1251] eta: 0:11:36 lr: 0.000041 loss: 2.7450 (2.7340) grad_norm: 3.0568 (3.2195) time: 0.5172 [2021-03-27 04:27:03 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 60/1251] eta: 0:11:16 lr: 0.000041 loss: 2.9081 (2.7424) grad_norm: 3.0779 (3.1949) time: 0.5134 [2021-03-27 04:27:08 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 70/1251] eta: 0:10:59 lr: 0.000041 loss: 2.5898 (2.6905) grad_norm: 3.0458 (3.1866) time: 0.5037 [2021-03-27 04:27:13 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 80/1251] eta: 0:10:45 lr: 0.000041 loss: 2.5347 (2.6826) grad_norm: 3.0477 (3.1723) time: 0.4999 [2021-03-27 04:27:18 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 90/1251] eta: 0:10:34 lr: 0.000041 loss: 2.5732 (2.6894) grad_norm: 3.0422 (3.1726) time: 0.5045 [2021-03-27 04:27:23 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 100/1251] eta: 0:10:24 lr: 0.000041 loss: 2.7889 (2.7019) grad_norm: 2.9621 (3.1784) time: 0.5089 [2021-03-27 04:27:28 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 110/1251] eta: 0:10:15 lr: 0.000041 loss: 2.8744 (2.7051) grad_norm: 3.0552 (3.1725) time: 0.5060 [2021-03-27 04:27:33 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 120/1251] eta: 0:10:06 lr: 0.000041 loss: 2.7579 (2.7126) grad_norm: 3.1156 (3.1687) time: 0.5002 [2021-03-27 04:27:38 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 130/1251] eta: 0:09:59 lr: 0.000041 loss: 2.7493 (2.7078) grad_norm: 3.1439 (3.1751) time: 0.5074 [2021-03-27 04:27:43 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 140/1251] eta: 0:09:51 lr: 0.000041 loss: 2.8001 (2.7140) grad_norm: 3.1263 (3.1804) time: 0.5105 [2021-03-27 04:27:48 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 150/1251] eta: 0:09:43 lr: 0.000041 loss: 2.9937 (2.7311) grad_norm: 2.9637 (3.1674) time: 0.5022 [2021-03-27 04:27:53 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 160/1251] eta: 0:09:36 lr: 0.000041 loss: 2.9959 (2.7432) grad_norm: 2.7941 (3.1449) time: 0.5006 [2021-03-27 04:27:58 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 170/1251] eta: 0:09:29 lr: 0.000041 loss: 2.8933 (2.7471) grad_norm: 2.8308 (3.1477) time: 0.5011 [2021-03-27 04:28:03 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 180/1251] eta: 0:09:22 lr: 0.000041 loss: 2.6536 (2.7399) grad_norm: 2.9852 (3.1425) time: 0.5030 [2021-03-27 04:28:08 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 190/1251] eta: 0:09:16 lr: 0.000041 loss: 2.8050 (2.7450) grad_norm: 2.9581 (3.1328) time: 0.5078 [2021-03-27 04:28:14 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 200/1251] eta: 0:09:10 lr: 0.000041 loss: 2.8050 (2.7430) grad_norm: 2.8732 (3.1248) time: 0.5126 [2021-03-27 04:28:19 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 210/1251] eta: 0:09:04 lr: 0.000041 loss: 2.6939 (2.7389) grad_norm: 2.8660 (3.1442) time: 0.5094 [2021-03-27 04:28:24 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 220/1251] eta: 0:08:58 lr: 0.000041 loss: 2.7557 (2.7391) grad_norm: 2.9837 (3.1527) time: 0.4984 [2021-03-27 04:28:29 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 230/1251] eta: 0:08:52 lr: 0.000041 loss: 2.8066 (2.7361) grad_norm: 2.8698 (3.1479) time: 0.5040 [2021-03-27 04:28:34 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 240/1251] eta: 0:08:47 lr: 0.000041 loss: 2.8313 (2.7435) grad_norm: 2.7325 (3.1291) time: 0.5157 [2021-03-27 04:28:39 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 250/1251] eta: 0:08:41 lr: 0.000041 loss: 2.9014 (2.7497) grad_norm: 2.7403 (3.1193) time: 0.5109 [2021-03-27 04:28:44 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 260/1251] eta: 0:08:35 lr: 0.000041 loss: 2.8926 (2.7551) grad_norm: 2.8608 (3.1151) time: 0.5012 [2021-03-27 04:28:49 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 270/1251] eta: 0:08:29 lr: 0.000041 loss: 2.8926 (2.7655) grad_norm: 2.8425 (3.1032) time: 0.4978 [2021-03-27 04:28:54 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 280/1251] eta: 0:08:23 lr: 0.000041 loss: 2.8536 (2.7592) grad_norm: 2.8425 (3.1147) time: 0.5023 [2021-03-27 04:28:59 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 290/1251] eta: 0:08:17 lr: 0.000041 loss: 2.8516 (2.7589) grad_norm: 3.0338 (3.1097) time: 0.4991 [2021-03-27 04:29:04 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 300/1251] eta: 0:08:11 lr: 0.000041 loss: 2.4191 (2.7454) grad_norm: 3.0338 (3.1150) time: 0.4951 [2021-03-27 04:29:09 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 310/1251] eta: 0:08:05 lr: 0.000041 loss: 2.4191 (2.7495) grad_norm: 2.8797 (3.1076) time: 0.4962 [2021-03-27 04:29:14 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 320/1251] eta: 0:08:00 lr: 0.000041 loss: 3.0006 (2.7534) grad_norm: 2.9738 (3.1076) time: 0.5027 [2021-03-27 04:29:19 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 330/1251] eta: 0:07:54 lr: 0.000041 loss: 2.8806 (2.7524) grad_norm: 2.9738 (3.1026) time: 0.5037 [2021-03-27 04:29:24 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 340/1251] eta: 0:07:49 lr: 0.000041 loss: 2.7094 (2.7514) grad_norm: 2.9224 (3.1018) time: 0.4983 [2021-03-27 04:29:29 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 350/1251] eta: 0:07:43 lr: 0.000041 loss: 2.7057 (2.7484) grad_norm: 2.9267 (3.0985) time: 0.4960 [2021-03-27 04:29:34 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 360/1251] eta: 0:07:37 lr: 0.000041 loss: 2.8089 (2.7513) grad_norm: 2.8953 (3.0956) time: 0.4945 [2021-03-27 04:29:39 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 370/1251] eta: 0:07:32 lr: 0.000041 loss: 2.7629 (2.7428) grad_norm: 2.8953 (3.0894) time: 0.4982 [2021-03-27 04:29:44 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 380/1251] eta: 0:07:27 lr: 0.000040 loss: 2.7668 (2.7494) grad_norm: 2.9515 (3.1014) time: 0.5043 [2021-03-27 04:29:49 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 390/1251] eta: 0:07:21 lr: 0.000040 loss: 2.9386 (2.7499) grad_norm: 3.0098 (inf) time: 0.4998 [2021-03-27 04:29:54 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 400/1251] eta: 0:07:16 lr: 0.000040 loss: 2.8721 (2.7503) grad_norm: 3.0098 (inf) time: 0.4972 [2021-03-27 04:29:59 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 410/1251] eta: 0:07:11 lr: 0.000040 loss: 2.8659 (2.7504) grad_norm: 2.9711 (inf) time: 0.5053 [2021-03-27 04:30:04 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 420/1251] eta: 0:07:05 lr: 0.000040 loss: 2.7104 (2.7481) grad_norm: 2.9113 (inf) time: 0.5104 [2021-03-27 04:30:09 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 430/1251] eta: 0:07:00 lr: 0.000040 loss: 2.7104 (2.7502) grad_norm: 2.9021 (inf) time: 0.5095 [2021-03-27 04:30:14 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 440/1251] eta: 0:06:55 lr: 0.000040 loss: 2.8176 (2.7541) grad_norm: 2.9243 (inf) time: 0.5097 [2021-03-27 04:30:19 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 450/1251] eta: 0:06:50 lr: 0.000040 loss: 2.8372 (2.7560) grad_norm: 2.9066 (inf) time: 0.5144 [2021-03-27 04:30:24 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 460/1251] eta: 0:06:45 lr: 0.000040 loss: 2.8372 (2.7529) grad_norm: 2.8787 (inf) time: 0.5044 [2021-03-27 04:30:29 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 470/1251] eta: 0:06:39 lr: 0.000040 loss: 2.6320 (2.7498) grad_norm: 2.9961 (inf) time: 0.4937 [2021-03-27 04:30:34 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 480/1251] eta: 0:06:34 lr: 0.000040 loss: 2.6226 (2.7471) grad_norm: 3.0682 (inf) time: 0.4997 [2021-03-27 04:30:39 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 490/1251] eta: 0:06:29 lr: 0.000040 loss: 2.4905 (2.7377) grad_norm: 3.0606 (inf) time: 0.5101 [2021-03-27 04:30:45 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 500/1251] eta: 0:06:24 lr: 0.000040 loss: 2.4905 (2.7345) grad_norm: 2.9683 (inf) time: 0.5135 [2021-03-27 04:30:50 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 510/1251] eta: 0:06:18 lr: 0.000040 loss: 2.6905 (2.7312) grad_norm: 2.9521 (inf) time: 0.5041 [2021-03-27 04:30:55 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 520/1251] eta: 0:06:13 lr: 0.000040 loss: 2.8246 (2.7336) grad_norm: 3.0668 (inf) time: 0.5027 [2021-03-27 04:31:00 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 530/1251] eta: 0:06:08 lr: 0.000040 loss: 2.9664 (2.7328) grad_norm: 3.1342 (inf) time: 0.5058 [2021-03-27 04:31:05 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 540/1251] eta: 0:06:03 lr: 0.000040 loss: 2.7375 (2.7318) grad_norm: 3.1090 (inf) time: 0.5054 [2021-03-27 04:31:10 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 550/1251] eta: 0:05:58 lr: 0.000040 loss: 2.7375 (2.7317) grad_norm: 3.0850 (inf) time: 0.5099 [2021-03-27 04:31:15 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 560/1251] eta: 0:05:52 lr: 0.000040 loss: 2.6922 (2.7298) grad_norm: 2.9218 (inf) time: 0.5044 [2021-03-27 04:31:20 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 570/1251] eta: 0:05:47 lr: 0.000040 loss: 2.6502 (2.7286) grad_norm: 2.8986 (inf) time: 0.4953 [2021-03-27 04:31:25 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 580/1251] eta: 0:05:42 lr: 0.000040 loss: 2.9198 (2.7308) grad_norm: 2.8235 (inf) time: 0.4924 [2021-03-27 04:31:30 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 590/1251] eta: 0:05:37 lr: 0.000040 loss: 2.7365 (2.7272) grad_norm: 2.8730 (inf) time: 0.4994 [2021-03-27 04:31:35 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 600/1251] eta: 0:05:32 lr: 0.000040 loss: 2.5633 (2.7242) grad_norm: 3.2332 (inf) time: 0.5076 [2021-03-27 04:31:40 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 610/1251] eta: 0:05:26 lr: 0.000040 loss: 2.8135 (2.7265) grad_norm: 3.1766 (inf) time: 0.5059 [2021-03-27 04:31:45 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 620/1251] eta: 0:05:21 lr: 0.000040 loss: 2.7510 (2.7220) grad_norm: 3.0108 (inf) time: 0.5014 [2021-03-27 04:31:50 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 630/1251] eta: 0:05:16 lr: 0.000040 loss: 2.5830 (2.7218) grad_norm: 2.8991 (inf) time: 0.4990 [2021-03-27 04:31:55 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 640/1251] eta: 0:05:11 lr: 0.000040 loss: 2.8324 (2.7211) grad_norm: 3.0057 (inf) time: 0.5018 [2021-03-27 04:32:00 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 650/1251] eta: 0:05:06 lr: 0.000040 loss: 2.8306 (2.7205) grad_norm: 2.7705 (inf) time: 0.5003 [2021-03-27 04:32:05 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 660/1251] eta: 0:05:00 lr: 0.000040 loss: 2.7071 (2.7171) grad_norm: 2.7686 (inf) time: 0.4972 [2021-03-27 04:32:10 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 670/1251] eta: 0:04:55 lr: 0.000040 loss: 2.9095 (2.7227) grad_norm: 2.8386 (inf) time: 0.4990 [2021-03-27 04:32:15 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 680/1251] eta: 0:04:50 lr: 0.000040 loss: 2.9642 (2.7231) grad_norm: 2.9060 (inf) time: 0.5021 [2021-03-27 04:32:20 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 690/1251] eta: 0:04:45 lr: 0.000040 loss: 2.8403 (2.7223) grad_norm: 3.0408 (inf) time: 0.5055 [2021-03-27 04:32:25 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 700/1251] eta: 0:04:40 lr: 0.000040 loss: 2.7549 (2.7202) grad_norm: 3.0408 (inf) time: 0.5005 [2021-03-27 04:32:30 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 710/1251] eta: 0:04:35 lr: 0.000040 loss: 2.8504 (2.7251) grad_norm: 3.0280 (inf) time: 0.5029 [2021-03-27 04:32:35 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 720/1251] eta: 0:04:30 lr: 0.000040 loss: 2.8704 (2.7216) grad_norm: 3.0293 (inf) time: 0.5113 [2021-03-27 04:32:40 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 730/1251] eta: 0:04:25 lr: 0.000040 loss: 2.5535 (2.7209) grad_norm: 3.2154 (inf) time: 0.5170 [2021-03-27 04:32:46 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 740/1251] eta: 0:04:20 lr: 0.000040 loss: 2.6543 (2.7213) grad_norm: 3.0542 (inf) time: 0.5223 [2021-03-27 04:32:51 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 750/1251] eta: 0:04:15 lr: 0.000040 loss: 3.0028 (2.7224) grad_norm: 2.9889 (inf) time: 0.5156 [2021-03-27 04:32:56 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 760/1251] eta: 0:04:09 lr: 0.000040 loss: 2.8460 (2.7229) grad_norm: 2.8351 (inf) time: 0.5061 [2021-03-27 04:33:01 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 770/1251] eta: 0:04:04 lr: 0.000040 loss: 2.6965 (2.7211) grad_norm: 2.9442 (inf) time: 0.5056 [2021-03-27 04:33:06 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 780/1251] eta: 0:03:59 lr: 0.000040 loss: 2.6455 (2.7187) grad_norm: 2.9442 (inf) time: 0.5036 [2021-03-27 04:33:11 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 790/1251] eta: 0:03:54 lr: 0.000040 loss: 2.6995 (2.7192) grad_norm: 2.9145 (inf) time: 0.5013 [2021-03-27 04:33:16 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 800/1251] eta: 0:03:49 lr: 0.000040 loss: 2.8506 (2.7178) grad_norm: 2.8061 (inf) time: 0.5187 [2021-03-27 04:33:21 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 810/1251] eta: 0:03:44 lr: 0.000040 loss: 2.8345 (2.7181) grad_norm: 2.8993 (inf) time: 0.5197 [2021-03-27 04:33:26 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 820/1251] eta: 0:03:39 lr: 0.000040 loss: 2.7119 (2.7172) grad_norm: 3.0731 (inf) time: 0.5041 [2021-03-27 04:33:31 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 830/1251] eta: 0:03:34 lr: 0.000040 loss: 2.7119 (2.7205) grad_norm: 2.8811 (inf) time: 0.4993 [2021-03-27 04:33:36 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 840/1251] eta: 0:03:29 lr: 0.000040 loss: 2.8966 (2.7235) grad_norm: 2.8826 (inf) time: 0.5015 [2021-03-27 04:33:41 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 850/1251] eta: 0:03:24 lr: 0.000040 loss: 2.9743 (2.7251) grad_norm: 2.9890 (inf) time: 0.5028 [2021-03-27 04:33:46 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 860/1251] eta: 0:03:18 lr: 0.000040 loss: 2.9258 (2.7256) grad_norm: 3.0017 (inf) time: 0.5022 [2021-03-27 04:33:51 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 870/1251] eta: 0:03:13 lr: 0.000040 loss: 2.9099 (2.7264) grad_norm: 3.1588 (inf) time: 0.5084 [2021-03-27 04:33:56 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 880/1251] eta: 0:03:08 lr: 0.000040 loss: 2.8832 (2.7261) grad_norm: 3.2445 (inf) time: 0.5033 [2021-03-27 04:34:01 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 890/1251] eta: 0:03:03 lr: 0.000040 loss: 3.0130 (2.7296) grad_norm: 2.9718 (inf) time: 0.4934 [2021-03-27 04:34:06 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 900/1251] eta: 0:02:58 lr: 0.000040 loss: 2.9256 (2.7316) grad_norm: 2.8772 (inf) time: 0.4942 [2021-03-27 04:34:11 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 910/1251] eta: 0:02:53 lr: 0.000040 loss: 2.8550 (2.7327) grad_norm: 2.7902 (inf) time: 0.4969 [2021-03-27 04:34:16 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 920/1251] eta: 0:02:48 lr: 0.000040 loss: 2.8120 (2.7321) grad_norm: 2.7757 (inf) time: 0.5009 [2021-03-27 04:34:21 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 930/1251] eta: 0:02:43 lr: 0.000040 loss: 2.8979 (2.7327) grad_norm: 3.0194 (inf) time: 0.5063 [2021-03-27 04:34:27 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 940/1251] eta: 0:02:38 lr: 0.000040 loss: 2.9189 (2.7343) grad_norm: 3.0459 (inf) time: 0.5136 [2021-03-27 04:34:32 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 950/1251] eta: 0:02:32 lr: 0.000040 loss: 2.8121 (2.7330) grad_norm: 3.1835 (inf) time: 0.5098 [2021-03-27 04:34:37 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 960/1251] eta: 0:02:27 lr: 0.000040 loss: 2.7563 (2.7338) grad_norm: 3.1083 (inf) time: 0.5042 [2021-03-27 04:34:42 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 970/1251] eta: 0:02:22 lr: 0.000040 loss: 2.7994 (2.7350) grad_norm: 2.9880 (inf) time: 0.5082 [2021-03-27 04:34:47 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 980/1251] eta: 0:02:17 lr: 0.000040 loss: 2.7137 (2.7328) grad_norm: 2.8847 (inf) time: 0.5021 [2021-03-27 04:34:52 swin_small_patch4_window7_224] INFO: Epoch: [266] [ 990/1251] eta: 0:02:12 lr: 0.000040 loss: 2.6460 (2.7326) grad_norm: 2.8484 (inf) time: 0.5016 [2021-03-27 04:34:57 swin_small_patch4_window7_224] INFO: Epoch: [266] [1000/1251] eta: 0:02:07 lr: 0.000040 loss: 2.6473 (2.7320) grad_norm: 2.9549 (inf) time: 0.5022 [2021-03-27 04:35:02 swin_small_patch4_window7_224] INFO: Epoch: [266] [1010/1251] eta: 0:02:02 lr: 0.000040 loss: 2.6248 (2.7318) grad_norm: 3.0646 (inf) time: 0.4967 [2021-03-27 04:35:07 swin_small_patch4_window7_224] INFO: Epoch: [266] [1020/1251] eta: 0:01:57 lr: 0.000040 loss: 2.6160 (2.7320) grad_norm: 3.0244 (inf) time: 0.5009 [2021-03-27 04:35:12 swin_small_patch4_window7_224] INFO: Epoch: [266] [1030/1251] eta: 0:01:52 lr: 0.000040 loss: 2.8304 (2.7315) grad_norm: 2.9239 (inf) time: 0.5044 [2021-03-27 04:35:17 swin_small_patch4_window7_224] INFO: Epoch: [266] [1040/1251] eta: 0:01:47 lr: 0.000040 loss: 2.8136 (2.7330) grad_norm: 2.8226 (inf) time: 0.4971 [2021-03-27 04:35:22 swin_small_patch4_window7_224] INFO: Epoch: [266] [1050/1251] eta: 0:01:42 lr: 0.000040 loss: 2.8022 (2.7339) grad_norm: 2.7775 (inf) time: 0.4960 [2021-03-27 04:35:27 swin_small_patch4_window7_224] INFO: Epoch: [266] [1060/1251] eta: 0:01:36 lr: 0.000040 loss: 2.8937 (2.7358) grad_norm: 2.8656 (inf) time: 0.5001 [2021-03-27 04:35:32 swin_small_patch4_window7_224] INFO: Epoch: [266] [1070/1251] eta: 0:01:31 lr: 0.000040 loss: 2.9415 (2.7363) grad_norm: 3.0060 (inf) time: 0.5090 [2021-03-27 04:35:37 swin_small_patch4_window7_224] INFO: Epoch: [266] [1080/1251] eta: 0:01:26 lr: 0.000040 loss: 2.9696 (2.7379) grad_norm: 2.9903 (inf) time: 0.5079 [2021-03-27 04:35:42 swin_small_patch4_window7_224] INFO: Epoch: [266] [1090/1251] eta: 0:01:21 lr: 0.000039 loss: 3.0079 (2.7379) grad_norm: 2.9903 (inf) time: 0.4998 [2021-03-27 04:35:47 swin_small_patch4_window7_224] INFO: Epoch: [266] [1100/1251] eta: 0:01:16 lr: 0.000039 loss: 2.8617 (2.7375) grad_norm: 3.0176 (inf) time: 0.5062 [2021-03-27 04:35:52 swin_small_patch4_window7_224] INFO: Epoch: [266] [1110/1251] eta: 0:01:11 lr: 0.000039 loss: 2.9084 (2.7389) grad_norm: 2.9710 (inf) time: 0.5049 [2021-03-27 04:35:57 swin_small_patch4_window7_224] INFO: Epoch: [266] [1120/1251] eta: 0:01:06 lr: 0.000039 loss: 2.8863 (2.7390) grad_norm: 2.9710 (inf) time: 0.5007 [2021-03-27 04:36:02 swin_small_patch4_window7_224] INFO: Epoch: [266] [1130/1251] eta: 0:01:01 lr: 0.000039 loss: 2.7816 (2.7389) grad_norm: 3.0700 (inf) time: 0.5091 [2021-03-27 04:36:07 swin_small_patch4_window7_224] INFO: Epoch: [266] [1140/1251] eta: 0:00:56 lr: 0.000039 loss: 2.7816 (2.7385) grad_norm: 3.0476 (inf) time: 0.5062 [2021-03-27 04:36:12 swin_small_patch4_window7_224] INFO: Epoch: [266] [1150/1251] eta: 0:00:51 lr: 0.000039 loss: 2.8614 (2.7389) grad_norm: 3.0063 (inf) time: 0.4990 [2021-03-27 04:36:17 swin_small_patch4_window7_224] INFO: Epoch: [266] [1160/1251] eta: 0:00:46 lr: 0.000039 loss: 2.8614 (2.7390) grad_norm: 2.9799 (inf) time: 0.5071 [2021-03-27 04:36:22 swin_small_patch4_window7_224] INFO: Epoch: [266] [1170/1251] eta: 0:00:41 lr: 0.000039 loss: 2.8312 (2.7400) grad_norm: 2.9229 (inf) time: 0.5086 [2021-03-27 04:36:27 swin_small_patch4_window7_224] INFO: Epoch: [266] [1180/1251] eta: 0:00:36 lr: 0.000039 loss: 2.8635 (2.7395) grad_norm: 2.9229 (inf) time: 0.5041 [2021-03-27 04:36:32 swin_small_patch4_window7_224] INFO: Epoch: [266] [1190/1251] eta: 0:00:30 lr: 0.000039 loss: 2.9641 (2.7413) grad_norm: 2.9457 (inf) time: 0.5018 [2021-03-27 04:36:37 swin_small_patch4_window7_224] INFO: Epoch: [266] [1200/1251] eta: 0:00:25 lr: 0.000039 loss: 2.9609 (2.7422) grad_norm: 3.0658 (inf) time: 0.4980 [2021-03-27 04:36:42 swin_small_patch4_window7_224] INFO: Epoch: [266] [1210/1251] eta: 0:00:20 lr: 0.000039 loss: 2.9534 (2.7447) grad_norm: 3.0666 (inf) time: 0.4948 [2021-03-27 04:36:47 swin_small_patch4_window7_224] INFO: Epoch: [266] [1220/1251] eta: 0:00:15 lr: 0.000039 loss: 2.9147 (2.7432) grad_norm: 3.0389 (inf) time: 0.4997 [2021-03-27 04:36:53 swin_small_patch4_window7_224] INFO: Epoch: [266] [1230/1251] eta: 0:00:10 lr: 0.000039 loss: 2.6960 (2.7440) grad_norm: 3.0389 (inf) time: 0.5127 [2021-03-27 04:36:58 swin_small_patch4_window7_224] INFO: Epoch: [266] [1240/1251] eta: 0:00:05 lr: 0.000039 loss: 3.0062 (2.7439) grad_norm: 3.1326 (inf) time: 0.5059 [2021-03-27 04:37:03 swin_small_patch4_window7_224] INFO: Epoch: [266] [1250/1251] eta: 0:00:00 lr: 0.000039 loss: 2.8903 (2.7432) grad_norm: 2.9425 (inf) time: 0.5003 [2021-03-27 04:37:12 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:15 loss: 0.7839 (0.7839) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 04:37:14 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8154 (0.8278) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.5909) [2021-03-27 04:37:16 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7985 (0.8107) acc1: 79.6875 (80.3571) acc5: 96.8750 (96.1310) [2021-03-27 04:37:18 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7289 (0.7808) acc1: 82.8125 (81.0988) acc5: 95.3125 (96.0685) [2021-03-27 04:37:20 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6471 (0.7603) acc1: 82.8125 (81.7454) acc5: 96.8750 (96.2271) [2021-03-27 04:37:21 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7088 (0.7569) acc1: 82.8125 (81.9200) acc5: 96.8750 (96.2880) [2021-03-27 04:37:33 swin_small_patch4_window7_224] INFO: * Acc@1 82.792 Acc@5 96.174 loss 0.740 [2021-03-27 04:37:33 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 04:37:33 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 04:37:38 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 0/1251] eta: 1:31:42 lr: 0.000039 loss: 3.1536 (3.1536) grad_norm: 2.5782 (2.5782) time: 4.3986 [2021-03-27 04:37:43 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 10/1251] eta: 0:17:37 lr: 0.000039 loss: 2.9871 (2.7712) grad_norm: 2.6527 (2.7361) time: 0.8524 [2021-03-27 04:37:48 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 20/1251] eta: 0:14:02 lr: 0.000039 loss: 2.9001 (2.8181) grad_norm: 2.7956 (2.8817) time: 0.4988 [2021-03-27 04:37:53 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 30/1251] eta: 0:12:43 lr: 0.000039 loss: 2.9001 (2.7776) grad_norm: 2.8630 (2.9275) time: 0.5005 [2021-03-27 04:37:58 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 40/1251] eta: 0:12:06 lr: 0.000039 loss: 2.6829 (2.7406) grad_norm: 2.9208 (2.9653) time: 0.5115 [2021-03-27 04:38:03 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 50/1251] eta: 0:11:36 lr: 0.000039 loss: 2.7359 (2.7549) grad_norm: 2.8617 (2.9593) time: 0.5099 [2021-03-27 04:38:08 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 60/1251] eta: 0:11:17 lr: 0.000039 loss: 2.7748 (2.7937) grad_norm: 2.8708 (2.9573) time: 0.5045 [2021-03-27 04:38:13 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 70/1251] eta: 0:10:59 lr: 0.000039 loss: 2.9844 (2.7931) grad_norm: 2.7328 (2.9412) time: 0.5041 [2021-03-27 04:38:18 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 80/1251] eta: 0:10:45 lr: 0.000039 loss: 2.9377 (2.7978) grad_norm: 2.7697 (2.9567) time: 0.4973 [2021-03-27 04:38:23 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 90/1251] eta: 0:10:34 lr: 0.000039 loss: 2.8408 (2.7985) grad_norm: 2.9148 (2.9716) time: 0.5026 [2021-03-27 04:38:28 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 100/1251] eta: 0:10:23 lr: 0.000039 loss: 2.8411 (2.8069) grad_norm: 2.9277 (2.9703) time: 0.5028 [2021-03-27 04:38:33 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 110/1251] eta: 0:10:14 lr: 0.000039 loss: 2.8179 (2.7837) grad_norm: 2.8482 (3.0307) time: 0.5031 [2021-03-27 04:38:38 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 120/1251] eta: 0:10:05 lr: 0.000039 loss: 2.6550 (2.7790) grad_norm: 2.8785 (3.0246) time: 0.5059 [2021-03-27 04:38:43 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 130/1251] eta: 0:09:58 lr: 0.000039 loss: 2.8490 (2.7856) grad_norm: 2.8785 (3.0524) time: 0.5067 [2021-03-27 04:38:48 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 140/1251] eta: 0:09:49 lr: 0.000039 loss: 2.9106 (2.7876) grad_norm: 3.0391 (3.0616) time: 0.5000 [2021-03-27 04:38:53 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 150/1251] eta: 0:09:42 lr: 0.000039 loss: 2.9434 (2.8034) grad_norm: 3.0391 (3.0621) time: 0.4987 [2021-03-27 04:38:58 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 160/1251] eta: 0:09:35 lr: 0.000039 loss: 2.9778 (2.8044) grad_norm: 2.9340 (3.0625) time: 0.5033 [2021-03-27 04:39:03 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 170/1251] eta: 0:09:28 lr: 0.000039 loss: 2.8532 (2.7949) grad_norm: 2.8861 (3.0592) time: 0.5027 [2021-03-27 04:39:08 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 180/1251] eta: 0:09:22 lr: 0.000039 loss: 2.7029 (2.7862) grad_norm: 3.0012 (3.0708) time: 0.5058 [2021-03-27 04:39:13 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 190/1251] eta: 0:09:15 lr: 0.000039 loss: 2.8584 (2.7910) grad_norm: 2.9908 (3.0694) time: 0.5046 [2021-03-27 04:39:18 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 200/1251] eta: 0:09:09 lr: 0.000039 loss: 2.8949 (2.7837) grad_norm: 2.9452 (3.0683) time: 0.5006 [2021-03-27 04:39:23 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 210/1251] eta: 0:09:02 lr: 0.000039 loss: 2.6637 (2.7750) grad_norm: 2.8532 (3.0599) time: 0.4972 [2021-03-27 04:39:28 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 220/1251] eta: 0:08:56 lr: 0.000039 loss: 2.7754 (2.7820) grad_norm: 2.8823 (3.0720) time: 0.4956 [2021-03-27 04:39:33 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 230/1251] eta: 0:08:49 lr: 0.000039 loss: 2.8737 (2.7823) grad_norm: 2.8823 (3.0629) time: 0.4951 [2021-03-27 04:39:38 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 240/1251] eta: 0:08:43 lr: 0.000039 loss: 2.9265 (2.7840) grad_norm: 2.8675 (3.0645) time: 0.4971 [2021-03-27 04:39:43 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 250/1251] eta: 0:08:38 lr: 0.000039 loss: 2.7894 (2.7846) grad_norm: 2.9643 (3.0595) time: 0.5052 [2021-03-27 04:39:48 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 260/1251] eta: 0:08:32 lr: 0.000039 loss: 2.7705 (2.7817) grad_norm: 2.9332 (3.0565) time: 0.5034 [2021-03-27 04:39:53 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 270/1251] eta: 0:08:26 lr: 0.000039 loss: 2.7757 (2.7812) grad_norm: 2.8642 (3.0541) time: 0.5022 [2021-03-27 04:39:58 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 280/1251] eta: 0:08:21 lr: 0.000039 loss: 3.0071 (2.7851) grad_norm: 2.8642 (3.0643) time: 0.5077 [2021-03-27 04:40:03 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 290/1251] eta: 0:08:15 lr: 0.000039 loss: 2.7729 (2.7757) grad_norm: 3.2589 (3.0709) time: 0.5038 [2021-03-27 04:40:08 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 300/1251] eta: 0:08:10 lr: 0.000039 loss: 2.7667 (2.7747) grad_norm: 3.0026 (3.0670) time: 0.5005 [2021-03-27 04:40:13 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 310/1251] eta: 0:08:04 lr: 0.000039 loss: 2.8882 (2.7739) grad_norm: 2.9078 (3.0634) time: 0.4999 [2021-03-27 04:40:18 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 320/1251] eta: 0:07:59 lr: 0.000039 loss: 2.8473 (2.7720) grad_norm: 2.9161 (3.0669) time: 0.5056 [2021-03-27 04:40:23 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 330/1251] eta: 0:07:53 lr: 0.000039 loss: 2.8473 (2.7683) grad_norm: 2.9879 (3.0763) time: 0.5036 [2021-03-27 04:40:28 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 340/1251] eta: 0:07:47 lr: 0.000039 loss: 2.8306 (2.7687) grad_norm: 2.8987 (3.0864) time: 0.4987 [2021-03-27 04:40:33 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 350/1251] eta: 0:07:42 lr: 0.000039 loss: 2.8250 (2.7710) grad_norm: 3.0461 (3.0867) time: 0.4991 [2021-03-27 04:40:39 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 360/1251] eta: 0:07:37 lr: 0.000039 loss: 2.7857 (2.7651) grad_norm: 3.0524 (3.1019) time: 0.5043 [2021-03-27 04:40:43 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 370/1251] eta: 0:07:31 lr: 0.000039 loss: 2.7559 (2.7646) grad_norm: 3.0524 (3.1054) time: 0.5030 [2021-03-27 04:40:48 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 380/1251] eta: 0:07:26 lr: 0.000039 loss: 2.6835 (2.7581) grad_norm: 3.0067 (3.1017) time: 0.4956 [2021-03-27 04:40:53 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 390/1251] eta: 0:07:20 lr: 0.000039 loss: 2.6700 (2.7532) grad_norm: 3.0903 (3.1057) time: 0.4951 [2021-03-27 04:40:58 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 400/1251] eta: 0:07:15 lr: 0.000039 loss: 2.7118 (2.7507) grad_norm: 3.1128 (3.1071) time: 0.4984 [2021-03-27 04:41:03 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 410/1251] eta: 0:07:09 lr: 0.000039 loss: 2.7522 (2.7496) grad_norm: 3.1414 (3.1159) time: 0.4976 [2021-03-27 04:41:08 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 420/1251] eta: 0:07:04 lr: 0.000039 loss: 2.8499 (2.7499) grad_norm: 3.2934 (3.1200) time: 0.4976 [2021-03-27 04:41:13 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 430/1251] eta: 0:06:59 lr: 0.000039 loss: 2.8605 (2.7505) grad_norm: 2.9367 (3.1177) time: 0.5028 [2021-03-27 04:41:18 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 440/1251] eta: 0:06:53 lr: 0.000039 loss: 2.7680 (2.7505) grad_norm: 2.8426 (3.1104) time: 0.4968 [2021-03-27 04:41:23 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 450/1251] eta: 0:06:48 lr: 0.000039 loss: 2.6945 (2.7513) grad_norm: 2.8499 (3.1085) time: 0.4939 [2021-03-27 04:41:28 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 460/1251] eta: 0:06:43 lr: 0.000039 loss: 2.8735 (2.7516) grad_norm: 2.9815 (3.1098) time: 0.4986 [2021-03-27 04:41:33 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 470/1251] eta: 0:06:37 lr: 0.000039 loss: 2.7140 (2.7441) grad_norm: 3.1384 (3.1138) time: 0.4964 [2021-03-27 04:41:38 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 480/1251] eta: 0:06:32 lr: 0.000039 loss: 2.7140 (2.7449) grad_norm: 3.1384 (3.1135) time: 0.4960 [2021-03-27 04:41:43 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 490/1251] eta: 0:06:27 lr: 0.000039 loss: 2.7525 (2.7430) grad_norm: 3.0556 (3.1159) time: 0.4999 [2021-03-27 04:41:48 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 500/1251] eta: 0:06:21 lr: 0.000039 loss: 2.7930 (2.7449) grad_norm: 3.0556 (3.1157) time: 0.4953 [2021-03-27 04:41:53 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 510/1251] eta: 0:06:16 lr: 0.000039 loss: 2.8408 (2.7466) grad_norm: 2.9500 (3.1225) time: 0.4921 [2021-03-27 04:41:58 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 520/1251] eta: 0:06:11 lr: 0.000039 loss: 2.9552 (2.7534) grad_norm: 2.8830 (3.1193) time: 0.5020 [2021-03-27 04:42:03 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 530/1251] eta: 0:06:06 lr: 0.000039 loss: 2.9552 (2.7563) grad_norm: 2.8650 (3.1148) time: 0.5035 [2021-03-27 04:42:08 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 540/1251] eta: 0:06:01 lr: 0.000039 loss: 2.8389 (2.7539) grad_norm: 2.8625 (3.1112) time: 0.5017 [2021-03-27 04:42:13 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 550/1251] eta: 0:05:56 lr: 0.000038 loss: 2.8743 (2.7577) grad_norm: 2.9403 (3.1109) time: 0.5173 [2021-03-27 04:42:19 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 560/1251] eta: 0:05:51 lr: 0.000038 loss: 2.8956 (2.7572) grad_norm: 2.9861 (3.1128) time: 0.5188 [2021-03-27 04:42:24 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 570/1251] eta: 0:05:46 lr: 0.000038 loss: 2.8566 (2.7593) grad_norm: 3.0279 (3.1144) time: 0.5043 [2021-03-27 04:42:29 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 580/1251] eta: 0:05:41 lr: 0.000038 loss: 2.9013 (2.7597) grad_norm: 2.8672 (3.1096) time: 0.4996 [2021-03-27 04:42:34 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 590/1251] eta: 0:05:35 lr: 0.000038 loss: 2.9013 (2.7639) grad_norm: 2.7035 (3.1074) time: 0.4973 [2021-03-27 04:42:39 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 600/1251] eta: 0:05:30 lr: 0.000038 loss: 2.9503 (2.7678) grad_norm: 3.1129 (3.1094) time: 0.4994 [2021-03-27 04:42:44 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 610/1251] eta: 0:05:25 lr: 0.000038 loss: 3.1065 (2.7709) grad_norm: 3.0088 (3.1083) time: 0.4992 [2021-03-27 04:42:48 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 620/1251] eta: 0:05:20 lr: 0.000038 loss: 2.9090 (2.7715) grad_norm: 2.9646 (3.1104) time: 0.4961 [2021-03-27 04:42:54 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 630/1251] eta: 0:05:15 lr: 0.000038 loss: 2.7670 (2.7720) grad_norm: 2.9863 (3.1069) time: 0.4998 [2021-03-27 04:42:58 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 640/1251] eta: 0:05:09 lr: 0.000038 loss: 2.7837 (2.7728) grad_norm: 2.8610 (3.1060) time: 0.4990 [2021-03-27 04:43:04 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 650/1251] eta: 0:05:04 lr: 0.000038 loss: 2.7129 (2.7704) grad_norm: 2.9615 (3.1034) time: 0.5028 [2021-03-27 04:43:09 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 660/1251] eta: 0:04:59 lr: 0.000038 loss: 2.6119 (2.7690) grad_norm: 3.0167 (3.1040) time: 0.5059 [2021-03-27 04:43:14 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 670/1251] eta: 0:04:54 lr: 0.000038 loss: 2.6119 (2.7655) grad_norm: 3.0258 (3.1069) time: 0.4991 [2021-03-27 04:43:19 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 680/1251] eta: 0:04:49 lr: 0.000038 loss: 2.7542 (2.7668) grad_norm: 2.9351 (3.1037) time: 0.5002 [2021-03-27 04:43:24 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 690/1251] eta: 0:04:44 lr: 0.000038 loss: 3.0069 (2.7717) grad_norm: 3.0411 (3.1030) time: 0.5019 [2021-03-27 04:43:29 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 700/1251] eta: 0:04:39 lr: 0.000038 loss: 2.9173 (2.7733) grad_norm: 2.8564 (3.0999) time: 0.4986 [2021-03-27 04:43:34 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 710/1251] eta: 0:04:34 lr: 0.000038 loss: 2.8047 (2.7720) grad_norm: 2.8564 (3.1012) time: 0.4957 [2021-03-27 04:43:39 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 720/1251] eta: 0:04:29 lr: 0.000038 loss: 2.7291 (2.7696) grad_norm: 2.9713 (3.0995) time: 0.5046 [2021-03-27 04:43:44 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 730/1251] eta: 0:04:24 lr: 0.000038 loss: 2.5653 (2.7670) grad_norm: 2.8923 (3.1007) time: 0.5125 [2021-03-27 04:43:49 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 740/1251] eta: 0:04:19 lr: 0.000038 loss: 2.8784 (2.7659) grad_norm: 3.0497 (3.0982) time: 0.5280 [2021-03-27 04:43:54 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 750/1251] eta: 0:04:14 lr: 0.000038 loss: 2.8542 (2.7658) grad_norm: 2.9098 (3.0958) time: 0.5216 [2021-03-27 04:43:59 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 760/1251] eta: 0:04:08 lr: 0.000038 loss: 2.7683 (2.7663) grad_norm: 2.8956 (3.0963) time: 0.4948 [2021-03-27 04:44:04 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 770/1251] eta: 0:04:03 lr: 0.000038 loss: 2.7608 (2.7643) grad_norm: 3.0400 (3.1031) time: 0.4991 [2021-03-27 04:44:09 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 780/1251] eta: 0:03:58 lr: 0.000038 loss: 2.8970 (2.7666) grad_norm: 3.0091 (3.1035) time: 0.5005 [2021-03-27 04:44:14 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 790/1251] eta: 0:03:53 lr: 0.000038 loss: 2.9675 (2.7682) grad_norm: 2.8672 (3.0999) time: 0.4996 [2021-03-27 04:44:19 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 800/1251] eta: 0:03:48 lr: 0.000038 loss: 2.8640 (2.7672) grad_norm: 2.7441 (3.0974) time: 0.5037 [2021-03-27 04:44:24 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 810/1251] eta: 0:03:43 lr: 0.000038 loss: 2.9916 (2.7684) grad_norm: 2.9444 (3.0980) time: 0.5006 [2021-03-27 04:44:29 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 820/1251] eta: 0:03:38 lr: 0.000038 loss: 2.8345 (2.7674) grad_norm: 2.9749 (3.0971) time: 0.5016 [2021-03-27 04:44:34 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 830/1251] eta: 0:03:33 lr: 0.000038 loss: 2.8220 (2.7682) grad_norm: 2.9285 (3.0955) time: 0.5068 [2021-03-27 04:44:39 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 840/1251] eta: 0:03:28 lr: 0.000038 loss: 2.8395 (2.7695) grad_norm: 3.0102 (3.0963) time: 0.5089 [2021-03-27 04:44:44 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 850/1251] eta: 0:03:23 lr: 0.000038 loss: 2.8535 (2.7700) grad_norm: 3.0438 (3.0981) time: 0.5061 [2021-03-27 04:44:49 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 860/1251] eta: 0:03:18 lr: 0.000038 loss: 2.7402 (2.7672) grad_norm: 3.0379 (3.0977) time: 0.4990 [2021-03-27 04:44:54 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 870/1251] eta: 0:03:12 lr: 0.000038 loss: 2.7402 (2.7669) grad_norm: 3.0379 (3.0999) time: 0.4986 [2021-03-27 04:44:59 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 880/1251] eta: 0:03:07 lr: 0.000038 loss: 2.8466 (2.7661) grad_norm: 2.9967 (3.1033) time: 0.4993 [2021-03-27 04:45:04 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 890/1251] eta: 0:03:02 lr: 0.000038 loss: 2.7847 (2.7675) grad_norm: 2.8886 (3.1011) time: 0.4974 [2021-03-27 04:45:09 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 900/1251] eta: 0:02:57 lr: 0.000038 loss: 2.8023 (2.7676) grad_norm: 2.9032 (3.0996) time: 0.5006 [2021-03-27 04:45:14 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 910/1251] eta: 0:02:52 lr: 0.000038 loss: 2.7947 (2.7671) grad_norm: 3.0197 (3.1116) time: 0.5034 [2021-03-27 04:45:19 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 920/1251] eta: 0:02:47 lr: 0.000038 loss: 2.8439 (2.7670) grad_norm: 3.1387 (3.1131) time: 0.4979 [2021-03-27 04:45:25 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 930/1251] eta: 0:02:42 lr: 0.000038 loss: 2.9864 (2.7670) grad_norm: 3.0851 (3.1146) time: 0.5042 [2021-03-27 04:45:29 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 940/1251] eta: 0:02:37 lr: 0.000038 loss: 2.7051 (2.7649) grad_norm: 2.9050 (3.1115) time: 0.5057 [2021-03-27 04:45:35 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 950/1251] eta: 0:02:32 lr: 0.000038 loss: 2.6705 (2.7661) grad_norm: 2.8542 (3.1103) time: 0.4982 [2021-03-27 04:45:39 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 960/1251] eta: 0:02:27 lr: 0.000038 loss: 2.9123 (2.7660) grad_norm: 2.9514 (3.1094) time: 0.5000 [2021-03-27 04:45:44 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 970/1251] eta: 0:02:22 lr: 0.000038 loss: 2.8988 (2.7676) grad_norm: 2.9573 (3.1090) time: 0.4991 [2021-03-27 04:45:49 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 980/1251] eta: 0:02:17 lr: 0.000038 loss: 2.8174 (2.7662) grad_norm: 2.9944 (3.1071) time: 0.4973 [2021-03-27 04:45:55 swin_small_patch4_window7_224] INFO: Epoch: [267] [ 990/1251] eta: 0:02:12 lr: 0.000038 loss: 2.7580 (2.7654) grad_norm: 3.1332 (3.1101) time: 0.5053 [2021-03-27 04:46:00 swin_small_patch4_window7_224] INFO: Epoch: [267] [1000/1251] eta: 0:02:06 lr: 0.000038 loss: 2.8630 (2.7674) grad_norm: 3.2889 (3.1109) time: 0.5055 [2021-03-27 04:46:05 swin_small_patch4_window7_224] INFO: Epoch: [267] [1010/1251] eta: 0:02:01 lr: 0.000038 loss: 2.8859 (2.7685) grad_norm: 2.9361 (3.1125) time: 0.4967 [2021-03-27 04:46:10 swin_small_patch4_window7_224] INFO: Epoch: [267] [1020/1251] eta: 0:01:56 lr: 0.000038 loss: 2.8941 (2.7707) grad_norm: 3.0894 (3.1184) time: 0.4987 [2021-03-27 04:46:15 swin_small_patch4_window7_224] INFO: Epoch: [267] [1030/1251] eta: 0:01:51 lr: 0.000038 loss: 2.8981 (2.7712) grad_norm: 3.0732 (3.1244) time: 0.5022 [2021-03-27 04:46:20 swin_small_patch4_window7_224] INFO: Epoch: [267] [1040/1251] eta: 0:01:46 lr: 0.000038 loss: 2.9260 (2.7717) grad_norm: 3.0092 (3.1253) time: 0.4998 [2021-03-27 04:46:25 swin_small_patch4_window7_224] INFO: Epoch: [267] [1050/1251] eta: 0:01:41 lr: 0.000038 loss: 2.9558 (2.7724) grad_norm: 2.9316 (3.1227) time: 0.5013 [2021-03-27 04:46:30 swin_small_patch4_window7_224] INFO: Epoch: [267] [1060/1251] eta: 0:01:36 lr: 0.000038 loss: 2.8356 (2.7719) grad_norm: 2.8772 (3.1199) time: 0.5026 [2021-03-27 04:46:35 swin_small_patch4_window7_224] INFO: Epoch: [267] [1070/1251] eta: 0:01:31 lr: 0.000038 loss: 2.8291 (2.7718) grad_norm: 2.8043 (3.1235) time: 0.5007 [2021-03-27 04:46:40 swin_small_patch4_window7_224] INFO: Epoch: [267] [1080/1251] eta: 0:01:26 lr: 0.000038 loss: 2.7985 (2.7709) grad_norm: 2.7980 (3.1235) time: 0.4973 [2021-03-27 04:46:44 swin_small_patch4_window7_224] INFO: Epoch: [267] [1090/1251] eta: 0:01:21 lr: 0.000038 loss: 2.7706 (2.7710) grad_norm: 2.7999 (3.1214) time: 0.4931 [2021-03-27 04:46:49 swin_small_patch4_window7_224] INFO: Epoch: [267] [1100/1251] eta: 0:01:16 lr: 0.000038 loss: 2.7706 (2.7704) grad_norm: 2.8982 (3.1226) time: 0.4953 [2021-03-27 04:46:54 swin_small_patch4_window7_224] INFO: Epoch: [267] [1110/1251] eta: 0:01:11 lr: 0.000038 loss: 2.7872 (2.7708) grad_norm: 2.9766 (3.1209) time: 0.4991 [2021-03-27 04:46:59 swin_small_patch4_window7_224] INFO: Epoch: [267] [1120/1251] eta: 0:01:06 lr: 0.000038 loss: 2.7605 (2.7700) grad_norm: 2.7856 (3.1197) time: 0.5004 [2021-03-27 04:47:04 swin_small_patch4_window7_224] INFO: Epoch: [267] [1130/1251] eta: 0:01:01 lr: 0.000038 loss: 2.5990 (2.7687) grad_norm: 2.9609 (3.1232) time: 0.4970 [2021-03-27 04:47:09 swin_small_patch4_window7_224] INFO: Epoch: [267] [1140/1251] eta: 0:00:56 lr: 0.000038 loss: 2.6049 (2.7681) grad_norm: 2.9609 (3.1234) time: 0.4948 [2021-03-27 04:47:14 swin_small_patch4_window7_224] INFO: Epoch: [267] [1150/1251] eta: 0:00:50 lr: 0.000038 loss: 2.9185 (2.7678) grad_norm: 2.9446 (3.1223) time: 0.4935 [2021-03-27 04:47:19 swin_small_patch4_window7_224] INFO: Epoch: [267] [1160/1251] eta: 0:00:45 lr: 0.000038 loss: 2.8307 (2.7673) grad_norm: 2.9446 (3.1202) time: 0.4989 [2021-03-27 04:47:24 swin_small_patch4_window7_224] INFO: Epoch: [267] [1170/1251] eta: 0:00:40 lr: 0.000038 loss: 2.9044 (2.7684) grad_norm: 2.9369 (3.1196) time: 0.5010 [2021-03-27 04:47:29 swin_small_patch4_window7_224] INFO: Epoch: [267] [1180/1251] eta: 0:00:35 lr: 0.000038 loss: 2.8973 (2.7684) grad_norm: 2.8665 (3.1181) time: 0.4971 [2021-03-27 04:47:34 swin_small_patch4_window7_224] INFO: Epoch: [267] [1190/1251] eta: 0:00:30 lr: 0.000038 loss: 2.8642 (2.7690) grad_norm: 2.8658 (3.1155) time: 0.4934 [2021-03-27 04:47:39 swin_small_patch4_window7_224] INFO: Epoch: [267] [1200/1251] eta: 0:00:25 lr: 0.000038 loss: 2.9043 (2.7693) grad_norm: 2.8658 (3.1159) time: 0.4925 [2021-03-27 04:47:44 swin_small_patch4_window7_224] INFO: Epoch: [267] [1210/1251] eta: 0:00:20 lr: 0.000038 loss: 2.7824 (2.7664) grad_norm: 2.8752 (3.1153) time: 0.4999 [2021-03-27 04:47:49 swin_small_patch4_window7_224] INFO: Epoch: [267] [1220/1251] eta: 0:00:15 lr: 0.000038 loss: 2.7824 (2.7674) grad_norm: 2.8752 (3.1186) time: 0.5027 [2021-03-27 04:47:54 swin_small_patch4_window7_224] INFO: Epoch: [267] [1230/1251] eta: 0:00:10 lr: 0.000038 loss: 2.9364 (2.7678) grad_norm: 2.8039 (3.1163) time: 0.5001 [2021-03-27 04:47:59 swin_small_patch4_window7_224] INFO: Epoch: [267] [1240/1251] eta: 0:00:05 lr: 0.000038 loss: 2.8533 (2.7662) grad_norm: 2.8039 (3.1189) time: 0.4975 [2021-03-27 04:48:04 swin_small_patch4_window7_224] INFO: Epoch: [267] [1250/1251] eta: 0:00:00 lr: 0.000038 loss: 2.6908 (2.7662) grad_norm: 2.9256 (3.1171) time: 0.4990 [2021-03-27 04:48:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:50 loss: 0.8985 (0.8985) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 04:48:19 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.7474 (0.7423) acc1: 82.8125 (83.6648) acc5: 96.8750 (96.4489) [2021-03-27 04:48:21 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7455 (0.7115) acc1: 82.8125 (83.7054) acc5: 96.8750 (96.9494) [2021-03-27 04:48:25 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7720 (0.7623) acc1: 81.2500 (82.6109) acc5: 96.8750 (96.5222) [2021-03-27 04:48:26 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8214 (0.7729) acc1: 81.2500 (81.9741) acc5: 95.3125 (96.2271) [2021-03-27 04:48:27 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7965 (0.7657) acc1: 81.2500 (82.0160) acc5: 95.3125 (96.1280) [2021-03-27 04:48:39 swin_small_patch4_window7_224] INFO: * Acc@1 82.706 Acc@5 96.184 loss 0.746 [2021-03-27 04:48:39 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-27 04:48:39 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 04:48:43 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 0/1251] eta: 1:22:47 lr: 0.000038 loss: 3.2922 (3.2922) grad_norm: 2.8003 (2.8003) time: 3.9706 [2021-03-27 04:48:48 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 10/1251] eta: 0:17:46 lr: 0.000038 loss: 2.8128 (2.7410) grad_norm: 2.8409 (2.8710) time: 0.8594 [2021-03-27 04:48:53 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 20/1251] eta: 0:14:06 lr: 0.000038 loss: 2.8651 (2.8265) grad_norm: 2.7667 (2.8726) time: 0.5239 [2021-03-27 04:48:59 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 30/1251] eta: 0:12:50 lr: 0.000037 loss: 2.8885 (2.7981) grad_norm: 2.7667 (3.0656) time: 0.5060 [2021-03-27 04:49:04 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 40/1251] eta: 0:12:06 lr: 0.000037 loss: 2.8464 (2.7927) grad_norm: 3.0616 (3.1241) time: 0.5070 [2021-03-27 04:49:09 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 50/1251] eta: 0:11:39 lr: 0.000037 loss: 2.7837 (2.7670) grad_norm: 2.9937 (3.1115) time: 0.5063 [2021-03-27 04:49:14 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 60/1251] eta: 0:11:16 lr: 0.000037 loss: 2.7837 (2.7763) grad_norm: 2.9937 (3.1505) time: 0.5027 [2021-03-27 04:49:19 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 70/1251] eta: 0:10:58 lr: 0.000037 loss: 2.8165 (2.7680) grad_norm: 3.0591 (3.1529) time: 0.4945 [2021-03-27 04:49:24 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 80/1251] eta: 0:10:44 lr: 0.000037 loss: 2.7341 (2.7564) grad_norm: 3.0329 (3.1324) time: 0.4961 [2021-03-27 04:49:29 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 90/1251] eta: 0:10:32 lr: 0.000037 loss: 2.7223 (2.7552) grad_norm: 2.8275 (3.1099) time: 0.4993 [2021-03-27 04:49:34 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 100/1251] eta: 0:10:22 lr: 0.000037 loss: 2.5283 (2.7108) grad_norm: 2.8275 (3.0876) time: 0.5030 [2021-03-27 04:49:39 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 110/1251] eta: 0:10:14 lr: 0.000037 loss: 2.7161 (2.7266) grad_norm: 3.0244 (3.0989) time: 0.5114 [2021-03-27 04:49:44 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 120/1251] eta: 0:10:05 lr: 0.000037 loss: 2.8455 (2.7242) grad_norm: 3.1094 (3.0985) time: 0.5075 [2021-03-27 04:49:49 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 130/1251] eta: 0:09:57 lr: 0.000037 loss: 2.8582 (2.7406) grad_norm: 2.8883 (3.0953) time: 0.4997 [2021-03-27 04:49:54 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 140/1251] eta: 0:09:48 lr: 0.000037 loss: 2.8643 (2.7330) grad_norm: 3.1603 (3.1085) time: 0.4982 [2021-03-27 04:49:59 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 150/1251] eta: 0:09:41 lr: 0.000037 loss: 2.6849 (2.7250) grad_norm: 3.1603 (3.1077) time: 0.4991 [2021-03-27 04:50:04 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 160/1251] eta: 0:09:34 lr: 0.000037 loss: 2.7669 (2.7356) grad_norm: 2.9599 (3.1013) time: 0.5011 [2021-03-27 04:50:09 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 170/1251] eta: 0:09:27 lr: 0.000037 loss: 2.7096 (2.7352) grad_norm: 3.0806 (3.1091) time: 0.5019 [2021-03-27 04:50:14 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 180/1251] eta: 0:09:22 lr: 0.000037 loss: 2.5878 (2.7278) grad_norm: 3.0690 (3.1502) time: 0.5188 [2021-03-27 04:50:19 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 190/1251] eta: 0:09:16 lr: 0.000037 loss: 2.8215 (2.7350) grad_norm: 3.0304 (3.1418) time: 0.5183 [2021-03-27 04:50:24 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 200/1251] eta: 0:09:09 lr: 0.000037 loss: 2.7184 (2.7190) grad_norm: 3.0868 (3.1425) time: 0.5018 [2021-03-27 04:50:29 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 210/1251] eta: 0:09:03 lr: 0.000037 loss: 2.7184 (2.7206) grad_norm: 3.0868 (3.1546) time: 0.4969 [2021-03-27 04:50:34 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 220/1251] eta: 0:08:56 lr: 0.000037 loss: 2.8051 (2.7235) grad_norm: 2.9772 (3.1454) time: 0.4945 [2021-03-27 04:50:39 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 230/1251] eta: 0:08:51 lr: 0.000037 loss: 2.9745 (2.7298) grad_norm: 2.9772 (3.1446) time: 0.5023 [2021-03-27 04:50:44 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 240/1251] eta: 0:08:45 lr: 0.000037 loss: 2.9818 (2.7334) grad_norm: 2.9586 (3.1370) time: 0.5113 [2021-03-27 04:50:49 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 250/1251] eta: 0:08:39 lr: 0.000037 loss: 2.6391 (2.7262) grad_norm: 2.9253 (3.1299) time: 0.5093 [2021-03-27 04:50:54 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 260/1251] eta: 0:08:34 lr: 0.000037 loss: 2.7578 (2.7289) grad_norm: 2.9787 (3.1252) time: 0.5054 [2021-03-27 04:50:59 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 270/1251] eta: 0:08:28 lr: 0.000037 loss: 2.8043 (2.7295) grad_norm: 2.9515 (3.1152) time: 0.5030 [2021-03-27 04:51:05 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 280/1251] eta: 0:08:22 lr: 0.000037 loss: 2.8347 (2.7358) grad_norm: 2.9710 (3.1164) time: 0.5050 [2021-03-27 04:51:10 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 290/1251] eta: 0:08:17 lr: 0.000037 loss: 2.7967 (2.7293) grad_norm: 3.0419 (3.1201) time: 0.5056 [2021-03-27 04:51:15 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 300/1251] eta: 0:08:11 lr: 0.000037 loss: 2.9225 (2.7394) grad_norm: 2.9685 (3.1318) time: 0.5082 [2021-03-27 04:51:20 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 310/1251] eta: 0:08:06 lr: 0.000037 loss: 2.9197 (2.7315) grad_norm: 2.7944 (3.1237) time: 0.5090 [2021-03-27 04:51:25 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 320/1251] eta: 0:08:00 lr: 0.000037 loss: 2.8357 (2.7392) grad_norm: 2.9286 (3.1224) time: 0.5020 [2021-03-27 04:51:30 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 330/1251] eta: 0:07:54 lr: 0.000037 loss: 2.9032 (2.7429) grad_norm: 2.9336 (3.1144) time: 0.4962 [2021-03-27 04:51:35 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 340/1251] eta: 0:07:49 lr: 0.000037 loss: 2.8942 (2.7474) grad_norm: 2.8847 (3.1226) time: 0.4953 [2021-03-27 04:51:40 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 350/1251] eta: 0:07:43 lr: 0.000037 loss: 2.8367 (2.7482) grad_norm: 2.9954 (3.1295) time: 0.5001 [2021-03-27 04:51:45 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 360/1251] eta: 0:07:38 lr: 0.000037 loss: 2.8367 (2.7412) grad_norm: 2.9954 (3.1284) time: 0.5007 [2021-03-27 04:51:50 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 370/1251] eta: 0:07:32 lr: 0.000037 loss: 2.9413 (2.7445) grad_norm: 2.8510 (3.1231) time: 0.5028 [2021-03-27 04:51:55 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 380/1251] eta: 0:07:27 lr: 0.000037 loss: 2.9505 (2.7460) grad_norm: 2.7990 (3.1195) time: 0.5037 [2021-03-27 04:52:00 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 390/1251] eta: 0:07:21 lr: 0.000037 loss: 2.9450 (2.7502) grad_norm: 3.0035 (3.1208) time: 0.5008 [2021-03-27 04:52:05 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 400/1251] eta: 0:07:16 lr: 0.000037 loss: 3.0218 (2.7565) grad_norm: 3.0254 (3.1245) time: 0.4997 [2021-03-27 04:52:10 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 410/1251] eta: 0:07:10 lr: 0.000037 loss: 2.9486 (2.7536) grad_norm: 3.1103 (3.1249) time: 0.4962 [2021-03-27 04:52:15 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 420/1251] eta: 0:07:05 lr: 0.000037 loss: 2.6882 (2.7530) grad_norm: 3.0752 (3.1342) time: 0.4976 [2021-03-27 04:52:20 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 430/1251] eta: 0:07:00 lr: 0.000037 loss: 2.7120 (2.7560) grad_norm: 3.0103 (3.1347) time: 0.5026 [2021-03-27 04:52:25 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 440/1251] eta: 0:06:54 lr: 0.000037 loss: 2.8809 (2.7554) grad_norm: 3.2535 (3.1470) time: 0.5009 [2021-03-27 04:52:30 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 450/1251] eta: 0:06:49 lr: 0.000037 loss: 2.4710 (2.7462) grad_norm: 3.1859 (3.1445) time: 0.4956 [2021-03-27 04:52:35 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 460/1251] eta: 0:06:44 lr: 0.000037 loss: 2.7547 (2.7514) grad_norm: 2.8402 (3.1397) time: 0.4980 [2021-03-27 04:52:40 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 470/1251] eta: 0:06:39 lr: 0.000037 loss: 2.9343 (2.7481) grad_norm: 2.9239 (3.1359) time: 0.5070 [2021-03-27 04:52:45 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 480/1251] eta: 0:06:33 lr: 0.000037 loss: 2.5019 (2.7444) grad_norm: 2.9500 (3.1317) time: 0.5068 [2021-03-27 04:52:50 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 490/1251] eta: 0:06:28 lr: 0.000037 loss: 2.7260 (2.7461) grad_norm: 2.9205 (3.1313) time: 0.4983 [2021-03-27 04:52:55 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 500/1251] eta: 0:06:23 lr: 0.000037 loss: 2.8855 (2.7500) grad_norm: 2.8626 (3.1267) time: 0.4964 [2021-03-27 04:53:00 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 510/1251] eta: 0:06:17 lr: 0.000037 loss: 2.8264 (2.7491) grad_norm: 2.8084 (3.1207) time: 0.4953 [2021-03-27 04:53:05 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 520/1251] eta: 0:06:12 lr: 0.000037 loss: 2.8264 (2.7522) grad_norm: 2.8552 (3.1269) time: 0.4916 [2021-03-27 04:53:10 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 530/1251] eta: 0:06:07 lr: 0.000037 loss: 2.7505 (2.7498) grad_norm: 3.0946 (3.1252) time: 0.4950 [2021-03-27 04:53:15 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 540/1251] eta: 0:06:02 lr: 0.000037 loss: 2.9129 (2.7533) grad_norm: 3.0769 (3.1262) time: 0.5025 [2021-03-27 04:53:20 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 550/1251] eta: 0:05:57 lr: 0.000037 loss: 2.9129 (2.7535) grad_norm: 3.0350 (3.1287) time: 0.5144 [2021-03-27 04:53:25 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 560/1251] eta: 0:05:52 lr: 0.000037 loss: 2.8073 (2.7542) grad_norm: 2.9655 (3.1332) time: 0.5190 [2021-03-27 04:53:30 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 570/1251] eta: 0:05:47 lr: 0.000037 loss: 2.8897 (2.7557) grad_norm: 2.9556 (3.1329) time: 0.5113 [2021-03-27 04:53:35 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 580/1251] eta: 0:05:41 lr: 0.000037 loss: 2.8897 (2.7556) grad_norm: 3.0556 (3.1339) time: 0.5027 [2021-03-27 04:53:40 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 590/1251] eta: 0:05:36 lr: 0.000037 loss: 2.7061 (2.7547) grad_norm: 3.0403 (3.1343) time: 0.5025 [2021-03-27 04:53:45 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 600/1251] eta: 0:05:31 lr: 0.000037 loss: 2.6546 (2.7512) grad_norm: 2.8704 (3.1336) time: 0.5023 [2021-03-27 04:53:50 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 610/1251] eta: 0:05:26 lr: 0.000037 loss: 2.6612 (2.7510) grad_norm: 2.9409 (3.1312) time: 0.5001 [2021-03-27 04:53:55 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 620/1251] eta: 0:05:21 lr: 0.000037 loss: 2.9545 (2.7547) grad_norm: 2.9370 (3.1326) time: 0.5020 [2021-03-27 04:54:00 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 630/1251] eta: 0:05:16 lr: 0.000037 loss: 3.0396 (2.7578) grad_norm: 2.9925 (3.1321) time: 0.5009 [2021-03-27 04:54:05 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 640/1251] eta: 0:05:10 lr: 0.000037 loss: 2.9790 (2.7573) grad_norm: 2.9077 (3.1316) time: 0.5016 [2021-03-27 04:54:10 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 650/1251] eta: 0:05:05 lr: 0.000037 loss: 2.9208 (2.7581) grad_norm: 2.9186 (3.1320) time: 0.4978 [2021-03-27 04:54:15 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 660/1251] eta: 0:05:00 lr: 0.000037 loss: 2.8898 (2.7579) grad_norm: 3.0903 (3.1317) time: 0.5003 [2021-03-27 04:54:20 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 670/1251] eta: 0:04:55 lr: 0.000037 loss: 2.8229 (2.7567) grad_norm: 3.0386 (3.1398) time: 0.5027 [2021-03-27 04:54:25 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 680/1251] eta: 0:04:50 lr: 0.000037 loss: 2.7246 (2.7523) grad_norm: 3.0211 (3.1396) time: 0.5027 [2021-03-27 04:54:30 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 690/1251] eta: 0:04:45 lr: 0.000037 loss: 2.7246 (2.7522) grad_norm: 2.9523 (3.1398) time: 0.4997 [2021-03-27 04:54:35 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 700/1251] eta: 0:04:39 lr: 0.000037 loss: 2.8208 (2.7527) grad_norm: 2.9543 (3.1390) time: 0.4983 [2021-03-27 04:54:40 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 710/1251] eta: 0:04:34 lr: 0.000037 loss: 2.8510 (2.7537) grad_norm: 3.0223 (3.1380) time: 0.4976 [2021-03-27 04:54:45 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 720/1251] eta: 0:04:29 lr: 0.000037 loss: 2.9228 (2.7554) grad_norm: 3.0223 (3.1376) time: 0.4941 [2021-03-27 04:54:50 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 730/1251] eta: 0:04:24 lr: 0.000037 loss: 2.8687 (2.7580) grad_norm: 3.1697 (3.1400) time: 0.5093 [2021-03-27 04:54:56 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 740/1251] eta: 0:04:19 lr: 0.000037 loss: 2.9031 (2.7582) grad_norm: 3.0220 (3.1375) time: 0.5295 [2021-03-27 04:55:01 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 750/1251] eta: 0:04:14 lr: 0.000037 loss: 2.8020 (2.7582) grad_norm: 3.0121 (3.1404) time: 0.5284 [2021-03-27 04:55:06 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 760/1251] eta: 0:04:09 lr: 0.000037 loss: 2.8020 (2.7572) grad_norm: 3.2931 (3.1409) time: 0.5148 [2021-03-27 04:55:11 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 770/1251] eta: 0:04:04 lr: 0.000036 loss: 2.6781 (2.7542) grad_norm: 3.2192 (3.1439) time: 0.5015 [2021-03-27 04:55:16 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 780/1251] eta: 0:03:59 lr: 0.000036 loss: 2.8640 (2.7553) grad_norm: 3.0687 (3.1453) time: 0.4977 [2021-03-27 04:55:21 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 790/1251] eta: 0:03:54 lr: 0.000036 loss: 2.8885 (2.7530) grad_norm: 3.0616 (3.1472) time: 0.5027 [2021-03-27 04:55:26 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 800/1251] eta: 0:03:49 lr: 0.000036 loss: 2.9398 (2.7552) grad_norm: 2.9791 (3.1439) time: 0.5030 [2021-03-27 04:55:31 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 810/1251] eta: 0:03:43 lr: 0.000036 loss: 2.9436 (2.7559) grad_norm: 2.8524 (3.1422) time: 0.4997 [2021-03-27 04:55:36 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 820/1251] eta: 0:03:38 lr: 0.000036 loss: 2.9436 (2.7552) grad_norm: 3.0579 (3.1411) time: 0.4975 [2021-03-27 04:55:41 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 830/1251] eta: 0:03:33 lr: 0.000036 loss: 2.7538 (2.7547) grad_norm: 3.0442 (3.1387) time: 0.4988 [2021-03-27 04:55:46 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 840/1251] eta: 0:03:28 lr: 0.000036 loss: 2.6503 (2.7519) grad_norm: 3.0060 (3.1394) time: 0.5016 [2021-03-27 04:55:51 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 850/1251] eta: 0:03:23 lr: 0.000036 loss: 2.6503 (2.7509) grad_norm: 2.9437 (3.1371) time: 0.5050 [2021-03-27 04:55:56 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 860/1251] eta: 0:03:18 lr: 0.000036 loss: 2.7029 (2.7479) grad_norm: 2.8316 (3.1359) time: 0.5030 [2021-03-27 04:56:01 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 870/1251] eta: 0:03:13 lr: 0.000036 loss: 2.5997 (2.7477) grad_norm: 3.1239 (3.1374) time: 0.4989 [2021-03-27 04:56:06 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 880/1251] eta: 0:03:08 lr: 0.000036 loss: 2.7822 (2.7475) grad_norm: 3.1575 (3.1410) time: 0.4961 [2021-03-27 04:56:11 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 890/1251] eta: 0:03:03 lr: 0.000036 loss: 2.7822 (2.7484) grad_norm: 3.0652 (3.1392) time: 0.4967 [2021-03-27 04:56:16 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 900/1251] eta: 0:02:57 lr: 0.000036 loss: 2.9173 (2.7501) grad_norm: 3.0285 (3.1388) time: 0.4957 [2021-03-27 04:56:21 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 910/1251] eta: 0:02:52 lr: 0.000036 loss: 2.8374 (2.7495) grad_norm: 3.0285 (3.1396) time: 0.4928 [2021-03-27 04:56:26 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 920/1251] eta: 0:02:47 lr: 0.000036 loss: 2.7171 (2.7468) grad_norm: 3.1023 (3.1404) time: 0.5068 [2021-03-27 04:56:31 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 930/1251] eta: 0:02:42 lr: 0.000036 loss: 2.5168 (2.7456) grad_norm: 3.0762 (3.1415) time: 0.5096 [2021-03-27 04:56:36 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 940/1251] eta: 0:02:37 lr: 0.000036 loss: 2.5248 (2.7441) grad_norm: 3.0762 (3.1426) time: 0.5041 [2021-03-27 04:56:41 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 950/1251] eta: 0:02:32 lr: 0.000036 loss: 2.8170 (2.7447) grad_norm: 3.0483 (3.1446) time: 0.5064 [2021-03-27 04:56:46 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 960/1251] eta: 0:02:27 lr: 0.000036 loss: 2.8327 (2.7460) grad_norm: 3.0370 (3.1442) time: 0.4977 [2021-03-27 04:56:51 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 970/1251] eta: 0:02:22 lr: 0.000036 loss: 2.7668 (2.7445) grad_norm: 3.0394 (3.1457) time: 0.5020 [2021-03-27 04:56:56 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 980/1251] eta: 0:02:17 lr: 0.000036 loss: 2.6174 (2.7433) grad_norm: 3.0343 (3.1441) time: 0.5082 [2021-03-27 04:57:01 swin_small_patch4_window7_224] INFO: Epoch: [268] [ 990/1251] eta: 0:02:12 lr: 0.000036 loss: 2.6174 (2.7426) grad_norm: 3.0311 (3.1439) time: 0.5077 [2021-03-27 04:57:06 swin_small_patch4_window7_224] INFO: Epoch: [268] [1000/1251] eta: 0:02:07 lr: 0.000036 loss: 2.7628 (2.7425) grad_norm: 3.0027 (3.1433) time: 0.5018 [2021-03-27 04:57:11 swin_small_patch4_window7_224] INFO: Epoch: [268] [1010/1251] eta: 0:02:02 lr: 0.000036 loss: 2.7715 (2.7414) grad_norm: 3.0534 (3.1426) time: 0.4962 [2021-03-27 04:57:16 swin_small_patch4_window7_224] INFO: Epoch: [268] [1020/1251] eta: 0:01:57 lr: 0.000036 loss: 2.8556 (2.7426) grad_norm: 2.9908 (3.1406) time: 0.4998 [2021-03-27 04:57:21 swin_small_patch4_window7_224] INFO: Epoch: [268] [1030/1251] eta: 0:01:51 lr: 0.000036 loss: 2.8944 (2.7434) grad_norm: 2.9153 (3.1403) time: 0.5040 [2021-03-27 04:57:26 swin_small_patch4_window7_224] INFO: Epoch: [268] [1040/1251] eta: 0:01:46 lr: 0.000036 loss: 2.8712 (2.7427) grad_norm: 2.8319 (3.1373) time: 0.5042 [2021-03-27 04:57:31 swin_small_patch4_window7_224] INFO: Epoch: [268] [1050/1251] eta: 0:01:41 lr: 0.000036 loss: 2.8693 (2.7434) grad_norm: 2.8906 (3.1440) time: 0.5005 [2021-03-27 04:57:36 swin_small_patch4_window7_224] INFO: Epoch: [268] [1060/1251] eta: 0:01:36 lr: 0.000036 loss: 2.8450 (2.7445) grad_norm: 3.0462 (3.1435) time: 0.5011 [2021-03-27 04:57:42 swin_small_patch4_window7_224] INFO: Epoch: [268] [1070/1251] eta: 0:01:31 lr: 0.000036 loss: 2.8084 (2.7452) grad_norm: 2.9015 (3.1429) time: 0.5035 [2021-03-27 04:57:46 swin_small_patch4_window7_224] INFO: Epoch: [268] [1080/1251] eta: 0:01:26 lr: 0.000036 loss: 2.7682 (2.7443) grad_norm: 3.0456 (3.1433) time: 0.4993 [2021-03-27 04:57:51 swin_small_patch4_window7_224] INFO: Epoch: [268] [1090/1251] eta: 0:01:21 lr: 0.000036 loss: 2.8162 (2.7442) grad_norm: 3.0456 (3.1430) time: 0.4958 [2021-03-27 04:57:56 swin_small_patch4_window7_224] INFO: Epoch: [268] [1100/1251] eta: 0:01:16 lr: 0.000036 loss: 2.7221 (2.7422) grad_norm: 3.1787 (3.1437) time: 0.4984 [2021-03-27 04:58:02 swin_small_patch4_window7_224] INFO: Epoch: [268] [1110/1251] eta: 0:01:11 lr: 0.000036 loss: 2.7330 (2.7428) grad_norm: 3.0229 (3.1417) time: 0.5044 [2021-03-27 04:58:07 swin_small_patch4_window7_224] INFO: Epoch: [268] [1120/1251] eta: 0:01:06 lr: 0.000036 loss: 2.9145 (2.7439) grad_norm: 2.9989 (3.1411) time: 0.5052 [2021-03-27 04:58:11 swin_small_patch4_window7_224] INFO: Epoch: [268] [1130/1251] eta: 0:01:01 lr: 0.000036 loss: 2.9190 (2.7449) grad_norm: 3.0693 (3.1409) time: 0.4949 [2021-03-27 04:58:16 swin_small_patch4_window7_224] INFO: Epoch: [268] [1140/1251] eta: 0:00:56 lr: 0.000036 loss: 2.9190 (2.7458) grad_norm: 2.9627 (3.1390) time: 0.4900 [2021-03-27 04:58:21 swin_small_patch4_window7_224] INFO: Epoch: [268] [1150/1251] eta: 0:00:51 lr: 0.000036 loss: 2.8761 (2.7446) grad_norm: 2.7234 (3.1369) time: 0.4925 [2021-03-27 04:58:26 swin_small_patch4_window7_224] INFO: Epoch: [268] [1160/1251] eta: 0:00:46 lr: 0.000036 loss: 2.6318 (2.7426) grad_norm: 2.7121 (3.1386) time: 0.4968 [2021-03-27 04:58:31 swin_small_patch4_window7_224] INFO: Epoch: [268] [1170/1251] eta: 0:00:40 lr: 0.000036 loss: 2.6395 (2.7425) grad_norm: 2.8481 (3.1360) time: 0.4979 [2021-03-27 04:58:36 swin_small_patch4_window7_224] INFO: Epoch: [268] [1180/1251] eta: 0:00:35 lr: 0.000036 loss: 2.8361 (2.7422) grad_norm: 2.8769 (3.1387) time: 0.4957 [2021-03-27 04:58:41 swin_small_patch4_window7_224] INFO: Epoch: [268] [1190/1251] eta: 0:00:30 lr: 0.000036 loss: 2.8077 (2.7416) grad_norm: 3.1752 (3.1378) time: 0.4976 [2021-03-27 04:58:46 swin_small_patch4_window7_224] INFO: Epoch: [268] [1200/1251] eta: 0:00:25 lr: 0.000036 loss: 2.7248 (2.7395) grad_norm: 3.1752 (inf) time: 0.4996 [2021-03-27 04:58:51 swin_small_patch4_window7_224] INFO: Epoch: [268] [1210/1251] eta: 0:00:20 lr: 0.000036 loss: 2.6142 (2.7391) grad_norm: 3.1573 (inf) time: 0.4950 [2021-03-27 04:58:56 swin_small_patch4_window7_224] INFO: Epoch: [268] [1220/1251] eta: 0:00:15 lr: 0.000036 loss: 2.6142 (2.7385) grad_norm: 3.0312 (inf) time: 0.5042 [2021-03-27 04:59:01 swin_small_patch4_window7_224] INFO: Epoch: [268] [1230/1251] eta: 0:00:10 lr: 0.000036 loss: 2.7214 (2.7381) grad_norm: 3.0312 (inf) time: 0.5098 [2021-03-27 04:59:06 swin_small_patch4_window7_224] INFO: Epoch: [268] [1240/1251] eta: 0:00:05 lr: 0.000036 loss: 2.8284 (2.7396) grad_norm: 3.0408 (inf) time: 0.4983 [2021-03-27 04:59:11 swin_small_patch4_window7_224] INFO: Epoch: [268] [1250/1251] eta: 0:00:00 lr: 0.000036 loss: 2.8602 (2.7408) grad_norm: 2.9019 (inf) time: 0.4982 [2021-03-27 04:59:24 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:23 loss: 0.7946 (0.7946) acc1: 79.6875 (79.6875) acc5: 96.8750 (96.8750) [2021-03-27 04:59:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7313 (0.7164) acc1: 82.8125 (82.9545) acc5: 95.3125 (95.3125) [2021-03-27 04:59:29 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:11 loss: 0.7187 (0.7152) acc1: 84.3750 (83.5565) acc5: 95.3125 (95.6101) [2021-03-27 04:59:31 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7186 (0.7413) acc1: 81.2500 (82.8125) acc5: 96.8750 (95.7661) [2021-03-27 04:59:33 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.8182 (0.7649) acc1: 79.6875 (82.0503) acc5: 96.8750 (95.8841) [2021-03-27 04:59:34 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8074 (0.7568) acc1: 79.6875 (82.0160) acc5: 96.2264 (95.9680) [2021-03-27 04:59:47 swin_small_patch4_window7_224] INFO: * Acc@1 82.718 Acc@5 96.192 loss 0.740 [2021-03-27 04:59:47 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-27 04:59:47 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 04:59:51 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 0/1251] eta: 1:35:49 lr: 0.000036 loss: 3.0076 (3.0076) grad_norm: 3.4409 (3.4409) time: 4.5957 [2021-03-27 04:59:56 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 10/1251] eta: 0:18:01 lr: 0.000036 loss: 2.4916 (2.5865) grad_norm: 3.0510 (3.0903) time: 0.8715 [2021-03-27 05:00:01 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 20/1251] eta: 0:14:11 lr: 0.000036 loss: 2.9315 (2.8129) grad_norm: 2.9197 (3.1611) time: 0.4969 [2021-03-27 05:00:06 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 30/1251] eta: 0:12:53 lr: 0.000036 loss: 3.0508 (2.8319) grad_norm: 2.9305 (3.1139) time: 0.5022 [2021-03-27 05:00:12 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 40/1251] eta: 0:12:13 lr: 0.000036 loss: 2.9225 (2.8251) grad_norm: 3.0209 (3.1423) time: 0.5143 [2021-03-27 05:00:17 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 50/1251] eta: 0:11:43 lr: 0.000036 loss: 2.8202 (2.8034) grad_norm: 3.0678 (3.1374) time: 0.5125 [2021-03-27 05:00:22 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 60/1251] eta: 0:11:20 lr: 0.000036 loss: 2.8333 (2.8043) grad_norm: 2.9628 (3.1006) time: 0.5006 [2021-03-27 05:00:27 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 70/1251] eta: 0:11:02 lr: 0.000036 loss: 2.7820 (2.7725) grad_norm: 2.9859 (3.1007) time: 0.4972 [2021-03-27 05:00:32 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 80/1251] eta: 0:10:50 lr: 0.000036 loss: 2.7820 (2.7775) grad_norm: 3.1529 (3.0849) time: 0.5089 [2021-03-27 05:00:37 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 90/1251] eta: 0:10:37 lr: 0.000036 loss: 2.7884 (2.7507) grad_norm: 3.1529 (3.1078) time: 0.5085 [2021-03-27 05:00:42 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 100/1251] eta: 0:10:26 lr: 0.000036 loss: 2.8201 (2.7531) grad_norm: 2.9050 (3.0977) time: 0.5003 [2021-03-27 05:00:47 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 110/1251] eta: 0:10:18 lr: 0.000036 loss: 2.8365 (2.7488) grad_norm: 2.9406 (3.1067) time: 0.5109 [2021-03-27 05:00:52 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 120/1251] eta: 0:10:10 lr: 0.000036 loss: 2.8365 (2.7465) grad_norm: 2.9406 (3.0880) time: 0.5148 [2021-03-27 05:00:57 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 130/1251] eta: 0:10:01 lr: 0.000036 loss: 2.8063 (2.7551) grad_norm: 2.8304 (3.0726) time: 0.5031 [2021-03-27 05:01:02 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 140/1251] eta: 0:09:52 lr: 0.000036 loss: 2.8063 (2.7603) grad_norm: 2.8335 (3.0645) time: 0.4950 [2021-03-27 05:01:07 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 150/1251] eta: 0:09:45 lr: 0.000036 loss: 2.8472 (2.7583) grad_norm: 3.0110 (3.0608) time: 0.5026 [2021-03-27 05:01:12 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 160/1251] eta: 0:09:37 lr: 0.000036 loss: 2.9303 (2.7559) grad_norm: 3.1454 (3.0790) time: 0.5039 [2021-03-27 05:01:17 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 170/1251] eta: 0:09:31 lr: 0.000036 loss: 2.8245 (2.7514) grad_norm: 3.1724 (3.0830) time: 0.5026 [2021-03-27 05:01:22 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 180/1251] eta: 0:09:24 lr: 0.000036 loss: 2.6825 (2.7412) grad_norm: 2.7508 (3.0692) time: 0.5075 [2021-03-27 05:01:27 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 190/1251] eta: 0:09:17 lr: 0.000036 loss: 2.8765 (2.7517) grad_norm: 2.7334 (3.0755) time: 0.5023 [2021-03-27 05:01:32 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 200/1251] eta: 0:09:11 lr: 0.000036 loss: 2.8995 (2.7555) grad_norm: 2.9074 (3.0784) time: 0.4996 [2021-03-27 05:01:37 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 210/1251] eta: 0:09:04 lr: 0.000036 loss: 2.8018 (2.7545) grad_norm: 2.9107 (3.0646) time: 0.5006 [2021-03-27 05:01:42 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 220/1251] eta: 0:08:58 lr: 0.000036 loss: 2.8018 (2.7586) grad_norm: 2.8328 (3.0710) time: 0.5023 [2021-03-27 05:01:47 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 230/1251] eta: 0:08:52 lr: 0.000036 loss: 2.8071 (2.7551) grad_norm: 3.0670 (3.0924) time: 0.5027 [2021-03-27 05:01:52 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 240/1251] eta: 0:08:46 lr: 0.000036 loss: 2.9240 (2.7650) grad_norm: 3.1414 (3.1032) time: 0.5028 [2021-03-27 05:01:57 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 250/1251] eta: 0:08:40 lr: 0.000036 loss: 2.9382 (2.7695) grad_norm: 3.0814 (3.0985) time: 0.5032 [2021-03-27 05:02:02 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 260/1251] eta: 0:08:34 lr: 0.000036 loss: 2.8460 (2.7686) grad_norm: 2.9492 (3.1025) time: 0.5015 [2021-03-27 05:02:07 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 270/1251] eta: 0:08:28 lr: 0.000035 loss: 2.8344 (2.7686) grad_norm: 2.9366 (3.0985) time: 0.4999 [2021-03-27 05:02:12 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 280/1251] eta: 0:08:22 lr: 0.000035 loss: 2.5450 (2.7531) grad_norm: 2.8908 (3.0949) time: 0.4965 [2021-03-27 05:02:17 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 290/1251] eta: 0:08:17 lr: 0.000035 loss: 2.2936 (2.7394) grad_norm: 2.8908 (3.0893) time: 0.4981 [2021-03-27 05:02:22 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 300/1251] eta: 0:08:11 lr: 0.000035 loss: 2.4758 (2.7361) grad_norm: 2.8317 (3.0884) time: 0.5000 [2021-03-27 05:02:27 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 310/1251] eta: 0:08:05 lr: 0.000035 loss: 2.7446 (2.7359) grad_norm: 2.9622 (3.0886) time: 0.5044 [2021-03-27 05:02:32 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 320/1251] eta: 0:08:00 lr: 0.000035 loss: 2.7740 (2.7391) grad_norm: 3.1716 (3.0969) time: 0.5080 [2021-03-27 05:02:37 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 330/1251] eta: 0:07:54 lr: 0.000035 loss: 2.7097 (2.7313) grad_norm: 3.0077 (3.0975) time: 0.5041 [2021-03-27 05:02:42 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 340/1251] eta: 0:07:49 lr: 0.000035 loss: 2.6007 (2.7304) grad_norm: 2.9558 (3.0919) time: 0.5023 [2021-03-27 05:02:47 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 350/1251] eta: 0:07:43 lr: 0.000035 loss: 2.6135 (2.7212) grad_norm: 2.9558 (3.0879) time: 0.4966 [2021-03-27 05:02:52 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 360/1251] eta: 0:07:38 lr: 0.000035 loss: 2.4863 (2.7193) grad_norm: 2.7696 (3.0810) time: 0.4962 [2021-03-27 05:02:58 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 370/1251] eta: 0:07:33 lr: 0.000035 loss: 2.8111 (2.7249) grad_norm: 2.8239 (3.0786) time: 0.5078 [2021-03-27 05:03:03 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 380/1251] eta: 0:07:27 lr: 0.000035 loss: 2.7957 (2.7201) grad_norm: 2.9561 (3.0859) time: 0.5057 [2021-03-27 05:03:08 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 390/1251] eta: 0:07:22 lr: 0.000035 loss: 2.5210 (2.7200) grad_norm: 3.0704 (3.0863) time: 0.5021 [2021-03-27 05:03:13 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 400/1251] eta: 0:07:16 lr: 0.000035 loss: 2.5496 (2.7150) grad_norm: 2.8988 (3.0791) time: 0.5052 [2021-03-27 05:03:18 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 410/1251] eta: 0:07:11 lr: 0.000035 loss: 2.5496 (2.7122) grad_norm: 2.8785 (3.0762) time: 0.4981 [2021-03-27 05:03:23 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 420/1251] eta: 0:07:05 lr: 0.000035 loss: 2.8322 (2.7132) grad_norm: 2.9450 (3.0755) time: 0.4979 [2021-03-27 05:03:28 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 430/1251] eta: 0:07:00 lr: 0.000035 loss: 2.9181 (2.7200) grad_norm: 3.0578 (3.0784) time: 0.4994 [2021-03-27 05:03:33 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 440/1251] eta: 0:06:55 lr: 0.000035 loss: 2.9090 (2.7189) grad_norm: 2.8578 (3.0767) time: 0.4965 [2021-03-27 05:03:38 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 450/1251] eta: 0:06:49 lr: 0.000035 loss: 2.7236 (2.7194) grad_norm: 2.7444 (3.0845) time: 0.4970 [2021-03-27 05:03:43 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 460/1251] eta: 0:06:44 lr: 0.000035 loss: 2.9047 (2.7220) grad_norm: 2.9622 (3.0881) time: 0.4991 [2021-03-27 05:03:47 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 470/1251] eta: 0:06:39 lr: 0.000035 loss: 2.9047 (2.7213) grad_norm: 3.0717 (3.0900) time: 0.4983 [2021-03-27 05:03:53 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 480/1251] eta: 0:06:33 lr: 0.000035 loss: 2.9348 (2.7247) grad_norm: 2.9609 (3.0879) time: 0.4995 [2021-03-27 05:03:57 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 490/1251] eta: 0:06:28 lr: 0.000035 loss: 2.9181 (2.7242) grad_norm: 3.0920 (3.0922) time: 0.4992 [2021-03-27 05:04:02 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 500/1251] eta: 0:06:23 lr: 0.000035 loss: 2.6137 (2.7221) grad_norm: 3.1686 (3.0979) time: 0.4958 [2021-03-27 05:04:07 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 510/1251] eta: 0:06:17 lr: 0.000035 loss: 2.8899 (2.7289) grad_norm: 3.0873 (3.0999) time: 0.4941 [2021-03-27 05:04:12 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 520/1251] eta: 0:06:12 lr: 0.000035 loss: 2.7942 (2.7257) grad_norm: 3.1611 (3.1029) time: 0.4984 [2021-03-27 05:04:17 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 530/1251] eta: 0:06:07 lr: 0.000035 loss: 2.7405 (2.7258) grad_norm: 3.0250 (3.0998) time: 0.5033 [2021-03-27 05:04:23 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 540/1251] eta: 0:06:02 lr: 0.000035 loss: 2.6845 (2.7231) grad_norm: 3.0090 (3.1015) time: 0.5068 [2021-03-27 05:04:28 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 550/1251] eta: 0:05:57 lr: 0.000035 loss: 2.6800 (2.7241) grad_norm: 2.9929 (3.1048) time: 0.5149 [2021-03-27 05:04:33 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 560/1251] eta: 0:05:52 lr: 0.000035 loss: 2.9705 (2.7274) grad_norm: 2.9613 (3.1036) time: 0.5092 [2021-03-27 05:04:38 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 570/1251] eta: 0:05:46 lr: 0.000035 loss: 3.0172 (2.7328) grad_norm: 2.8780 (3.1011) time: 0.5021 [2021-03-27 05:04:43 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 580/1251] eta: 0:05:41 lr: 0.000035 loss: 2.9229 (2.7276) grad_norm: 2.8780 (3.0996) time: 0.5053 [2021-03-27 05:04:48 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 590/1251] eta: 0:05:36 lr: 0.000035 loss: 2.7058 (2.7262) grad_norm: 2.9238 (3.1019) time: 0.5071 [2021-03-27 05:04:53 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 600/1251] eta: 0:05:31 lr: 0.000035 loss: 2.7361 (2.7254) grad_norm: 3.0822 (3.1035) time: 0.5005 [2021-03-27 05:04:58 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 610/1251] eta: 0:05:26 lr: 0.000035 loss: 2.7152 (2.7233) grad_norm: 3.0396 (3.1008) time: 0.4945 [2021-03-27 05:05:03 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 620/1251] eta: 0:05:21 lr: 0.000035 loss: 2.8589 (2.7279) grad_norm: 2.9626 (3.1029) time: 0.4972 [2021-03-27 05:05:08 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 630/1251] eta: 0:05:15 lr: 0.000035 loss: 3.0124 (2.7296) grad_norm: 2.9393 (3.0998) time: 0.4979 [2021-03-27 05:05:13 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 640/1251] eta: 0:05:10 lr: 0.000035 loss: 2.9785 (2.7324) grad_norm: 2.8339 (3.1170) time: 0.5052 [2021-03-27 05:05:18 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 650/1251] eta: 0:05:05 lr: 0.000035 loss: 2.8775 (2.7354) grad_norm: 2.8608 (3.1144) time: 0.5120 [2021-03-27 05:05:23 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 660/1251] eta: 0:05:00 lr: 0.000035 loss: 2.8750 (2.7345) grad_norm: 2.8500 (3.1125) time: 0.5066 [2021-03-27 05:05:28 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 670/1251] eta: 0:04:55 lr: 0.000035 loss: 2.8224 (2.7352) grad_norm: 2.8500 (3.1098) time: 0.5020 [2021-03-27 05:05:33 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 680/1251] eta: 0:04:50 lr: 0.000035 loss: 2.8224 (2.7355) grad_norm: 2.9154 (3.1099) time: 0.4993 [2021-03-27 05:05:38 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 690/1251] eta: 0:04:45 lr: 0.000035 loss: 2.8959 (2.7384) grad_norm: 2.9154 (3.1070) time: 0.4973 [2021-03-27 05:05:43 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 700/1251] eta: 0:04:39 lr: 0.000035 loss: 2.9155 (2.7398) grad_norm: 2.8733 (3.1040) time: 0.4956 [2021-03-27 05:05:48 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 710/1251] eta: 0:04:34 lr: 0.000035 loss: 2.8835 (2.7425) grad_norm: 2.8892 (3.1047) time: 0.5008 [2021-03-27 05:05:53 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 720/1251] eta: 0:04:29 lr: 0.000035 loss: 2.9422 (2.7462) grad_norm: 2.8892 (3.1047) time: 0.5027 [2021-03-27 05:05:58 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 730/1251] eta: 0:04:24 lr: 0.000035 loss: 2.9797 (2.7475) grad_norm: 2.9447 (3.1044) time: 0.5019 [2021-03-27 05:06:03 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 740/1251] eta: 0:04:19 lr: 0.000035 loss: 2.9621 (2.7481) grad_norm: 2.9859 (3.1003) time: 0.5210 [2021-03-27 05:06:08 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 750/1251] eta: 0:04:14 lr: 0.000035 loss: 2.9325 (2.7497) grad_norm: 2.9690 (3.1010) time: 0.5190 [2021-03-27 05:06:13 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 760/1251] eta: 0:04:09 lr: 0.000035 loss: 2.9538 (2.7506) grad_norm: 2.9816 (3.1010) time: 0.4990 [2021-03-27 05:06:18 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 770/1251] eta: 0:04:04 lr: 0.000035 loss: 2.8659 (2.7502) grad_norm: 2.9381 (3.0983) time: 0.4976 [2021-03-27 05:06:23 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 780/1251] eta: 0:03:59 lr: 0.000035 loss: 2.7522 (2.7488) grad_norm: 3.0070 (3.0987) time: 0.4981 [2021-03-27 05:06:28 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 790/1251] eta: 0:03:54 lr: 0.000035 loss: 2.7014 (2.7480) grad_norm: 3.0813 (3.0985) time: 0.5030 [2021-03-27 05:06:34 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 800/1251] eta: 0:03:48 lr: 0.000035 loss: 2.6427 (2.7453) grad_norm: 3.1943 (3.1038) time: 0.5064 [2021-03-27 05:06:38 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 810/1251] eta: 0:03:43 lr: 0.000035 loss: 2.8006 (2.7470) grad_norm: 2.9440 (3.1009) time: 0.5009 [2021-03-27 05:06:44 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 820/1251] eta: 0:03:38 lr: 0.000035 loss: 2.9893 (2.7500) grad_norm: 2.9037 (3.0990) time: 0.5001 [2021-03-27 05:06:49 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 830/1251] eta: 0:03:33 lr: 0.000035 loss: 2.9612 (2.7491) grad_norm: 2.9171 (3.1028) time: 0.5057 [2021-03-27 05:06:54 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 840/1251] eta: 0:03:28 lr: 0.000035 loss: 2.6424 (2.7473) grad_norm: 2.8580 (3.1004) time: 0.5024 [2021-03-27 05:06:59 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 850/1251] eta: 0:03:23 lr: 0.000035 loss: 2.6151 (2.7443) grad_norm: 3.0160 (3.1062) time: 0.4993 [2021-03-27 05:07:04 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 860/1251] eta: 0:03:18 lr: 0.000035 loss: 2.7814 (2.7445) grad_norm: 3.0393 (3.1065) time: 0.5049 [2021-03-27 05:07:09 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 870/1251] eta: 0:03:13 lr: 0.000035 loss: 2.9611 (2.7462) grad_norm: 2.9429 (3.1074) time: 0.5048 [2021-03-27 05:07:14 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 880/1251] eta: 0:03:08 lr: 0.000035 loss: 2.9149 (2.7458) grad_norm: 2.9069 (3.1054) time: 0.4999 [2021-03-27 05:07:19 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 890/1251] eta: 0:03:03 lr: 0.000035 loss: 2.5884 (2.7436) grad_norm: 2.7927 (3.1025) time: 0.4978 [2021-03-27 05:07:24 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 900/1251] eta: 0:02:57 lr: 0.000035 loss: 2.7748 (2.7433) grad_norm: 2.8831 (3.1028) time: 0.4985 [2021-03-27 05:07:29 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 910/1251] eta: 0:02:52 lr: 0.000035 loss: 2.8081 (2.7432) grad_norm: 2.9551 (3.1027) time: 0.4953 [2021-03-27 05:07:34 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 920/1251] eta: 0:02:47 lr: 0.000035 loss: 2.8358 (2.7446) grad_norm: 2.9387 (3.1006) time: 0.5036 [2021-03-27 05:07:39 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 930/1251] eta: 0:02:42 lr: 0.000035 loss: 3.0205 (2.7475) grad_norm: 2.8973 (3.0989) time: 0.5147 [2021-03-27 05:07:44 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 940/1251] eta: 0:02:37 lr: 0.000035 loss: 2.9011 (2.7475) grad_norm: 2.8827 (3.0952) time: 0.5062 [2021-03-27 05:07:49 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 950/1251] eta: 0:02:32 lr: 0.000035 loss: 2.9011 (2.7465) grad_norm: 2.9327 (3.0975) time: 0.4999 [2021-03-27 05:07:54 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 960/1251] eta: 0:02:27 lr: 0.000035 loss: 2.9360 (2.7474) grad_norm: 3.1216 (3.0979) time: 0.5054 [2021-03-27 05:07:59 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 970/1251] eta: 0:02:22 lr: 0.000035 loss: 2.7864 (2.7460) grad_norm: 2.8910 (3.0965) time: 0.5008 [2021-03-27 05:08:04 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 980/1251] eta: 0:02:17 lr: 0.000035 loss: 2.6888 (2.7449) grad_norm: 3.0563 (3.0979) time: 0.4926 [2021-03-27 05:08:09 swin_small_patch4_window7_224] INFO: Epoch: [269] [ 990/1251] eta: 0:02:12 lr: 0.000035 loss: 2.6888 (2.7431) grad_norm: 3.1647 (3.0981) time: 0.4936 [2021-03-27 05:08:14 swin_small_patch4_window7_224] INFO: Epoch: [269] [1000/1251] eta: 0:02:07 lr: 0.000035 loss: 2.3801 (2.7409) grad_norm: 3.0068 (3.0979) time: 0.4962 [2021-03-27 05:08:19 swin_small_patch4_window7_224] INFO: Epoch: [269] [1010/1251] eta: 0:02:02 lr: 0.000035 loss: 2.6874 (2.7408) grad_norm: 3.1812 (3.0994) time: 0.4987 [2021-03-27 05:08:24 swin_small_patch4_window7_224] INFO: Epoch: [269] [1020/1251] eta: 0:01:56 lr: 0.000035 loss: 2.7938 (2.7400) grad_norm: 3.0625 (3.0976) time: 0.4996 [2021-03-27 05:08:29 swin_small_patch4_window7_224] INFO: Epoch: [269] [1030/1251] eta: 0:01:51 lr: 0.000035 loss: 2.7938 (2.7411) grad_norm: 2.9184 (3.0966) time: 0.5009 [2021-03-27 05:08:34 swin_small_patch4_window7_224] INFO: Epoch: [269] [1040/1251] eta: 0:01:46 lr: 0.000034 loss: 2.7530 (2.7409) grad_norm: 2.9753 (3.0964) time: 0.4992 [2021-03-27 05:08:39 swin_small_patch4_window7_224] INFO: Epoch: [269] [1050/1251] eta: 0:01:41 lr: 0.000034 loss: 2.7192 (2.7396) grad_norm: 2.9753 (3.0939) time: 0.5022 [2021-03-27 05:08:44 swin_small_patch4_window7_224] INFO: Epoch: [269] [1060/1251] eta: 0:01:36 lr: 0.000034 loss: 2.7349 (2.7404) grad_norm: 2.9613 (3.0941) time: 0.5059 [2021-03-27 05:08:49 swin_small_patch4_window7_224] INFO: Epoch: [269] [1070/1251] eta: 0:01:31 lr: 0.000034 loss: 2.9451 (2.7416) grad_norm: 3.0390 (3.0929) time: 0.4996 [2021-03-27 05:08:54 swin_small_patch4_window7_224] INFO: Epoch: [269] [1080/1251] eta: 0:01:26 lr: 0.000034 loss: 3.0353 (2.7430) grad_norm: 2.8850 (3.0916) time: 0.4981 [2021-03-27 05:08:59 swin_small_patch4_window7_224] INFO: Epoch: [269] [1090/1251] eta: 0:01:21 lr: 0.000034 loss: 2.8513 (2.7435) grad_norm: 2.9732 (3.0910) time: 0.4992 [2021-03-27 05:09:04 swin_small_patch4_window7_224] INFO: Epoch: [269] [1100/1251] eta: 0:01:16 lr: 0.000034 loss: 2.8081 (2.7440) grad_norm: 3.0094 (3.0903) time: 0.4998 [2021-03-27 05:09:09 swin_small_patch4_window7_224] INFO: Epoch: [269] [1110/1251] eta: 0:01:11 lr: 0.000034 loss: 2.6990 (2.7425) grad_norm: 3.1216 (3.0912) time: 0.5037 [2021-03-27 05:09:14 swin_small_patch4_window7_224] INFO: Epoch: [269] [1120/1251] eta: 0:01:06 lr: 0.000034 loss: 2.6733 (2.7404) grad_norm: 2.9508 (3.0890) time: 0.5010 [2021-03-27 05:09:19 swin_small_patch4_window7_224] INFO: Epoch: [269] [1130/1251] eta: 0:01:01 lr: 0.000034 loss: 2.6196 (2.7395) grad_norm: 2.9182 (3.0897) time: 0.4997 [2021-03-27 05:09:24 swin_small_patch4_window7_224] INFO: Epoch: [269] [1140/1251] eta: 0:00:56 lr: 0.000034 loss: 2.8267 (2.7410) grad_norm: 3.0828 (3.0949) time: 0.5036 [2021-03-27 05:09:29 swin_small_patch4_window7_224] INFO: Epoch: [269] [1150/1251] eta: 0:00:51 lr: 0.000034 loss: 2.8712 (2.7410) grad_norm: 3.0496 (3.0957) time: 0.5011 [2021-03-27 05:09:34 swin_small_patch4_window7_224] INFO: Epoch: [269] [1160/1251] eta: 0:00:46 lr: 0.000034 loss: 2.7517 (2.7407) grad_norm: 2.8959 (3.0929) time: 0.4955 [2021-03-27 05:09:39 swin_small_patch4_window7_224] INFO: Epoch: [269] [1170/1251] eta: 0:00:40 lr: 0.000034 loss: 2.9983 (2.7431) grad_norm: 2.8646 (3.0922) time: 0.4935 [2021-03-27 05:09:44 swin_small_patch4_window7_224] INFO: Epoch: [269] [1180/1251] eta: 0:00:35 lr: 0.000034 loss: 2.9598 (2.7418) grad_norm: 2.9472 (3.0941) time: 0.4961 [2021-03-27 05:09:49 swin_small_patch4_window7_224] INFO: Epoch: [269] [1190/1251] eta: 0:00:30 lr: 0.000034 loss: 2.8189 (2.7417) grad_norm: 2.9080 (3.1002) time: 0.4979 [2021-03-27 05:09:54 swin_small_patch4_window7_224] INFO: Epoch: [269] [1200/1251] eta: 0:00:25 lr: 0.000034 loss: 2.9121 (2.7418) grad_norm: 2.9436 (3.1007) time: 0.4961 [2021-03-27 05:09:59 swin_small_patch4_window7_224] INFO: Epoch: [269] [1210/1251] eta: 0:00:20 lr: 0.000034 loss: 2.8091 (2.7426) grad_norm: 2.9770 (3.1009) time: 0.4961 [2021-03-27 05:10:04 swin_small_patch4_window7_224] INFO: Epoch: [269] [1220/1251] eta: 0:00:15 lr: 0.000034 loss: 2.7391 (2.7413) grad_norm: 2.9770 (3.0997) time: 0.4972 [2021-03-27 05:10:09 swin_small_patch4_window7_224] INFO: Epoch: [269] [1230/1251] eta: 0:00:10 lr: 0.000034 loss: 2.7981 (2.7415) grad_norm: 3.1115 (3.1012) time: 0.4968 [2021-03-27 05:10:14 swin_small_patch4_window7_224] INFO: Epoch: [269] [1240/1251] eta: 0:00:05 lr: 0.000034 loss: 2.8164 (2.7408) grad_norm: 3.1093 (3.1018) time: 0.4959 [2021-03-27 05:10:18 swin_small_patch4_window7_224] INFO: Epoch: [269] [1250/1251] eta: 0:00:00 lr: 0.000034 loss: 2.7178 (2.7414) grad_norm: 2.9494 (3.1008) time: 0.4944 [2021-03-27 05:10:29 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:19 loss: 0.8459 (0.8459) acc1: 76.5625 (76.5625) acc5: 95.3125 (95.3125) [2021-03-27 05:10:32 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:20 loss: 0.7532 (0.7359) acc1: 84.3750 (83.2386) acc5: 95.3125 (95.5966) [2021-03-27 05:10:34 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7806 (0.7876) acc1: 82.8125 (81.8452) acc5: 95.3125 (95.6845) [2021-03-27 05:10:36 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7806 (0.7486) acc1: 79.6875 (81.9556) acc5: 95.3125 (96.2702) [2021-03-27 05:10:37 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7333 (0.7523) acc1: 81.2500 (82.0122) acc5: 96.8750 (96.3034) [2021-03-27 05:10:38 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7738 (0.7613) acc1: 79.6875 (82.0160) acc5: 95.3125 (96.1920) [2021-03-27 05:10:53 swin_small_patch4_window7_224] INFO: * Acc@1 82.824 Acc@5 96.212 loss 0.740 [2021-03-27 05:10:53 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 05:10:53 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 05:10:57 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 0/1251] eta: 1:28:50 lr: 0.000034 loss: 2.9364 (2.9364) grad_norm: 3.5513 (3.5513) time: 4.2609 [2021-03-27 05:11:02 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 10/1251] eta: 0:18:02 lr: 0.000034 loss: 3.0235 (2.7829) grad_norm: 3.0350 (2.9610) time: 0.8727 [2021-03-27 05:11:07 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 20/1251] eta: 0:14:19 lr: 0.000034 loss: 2.9015 (2.8008) grad_norm: 2.9051 (2.9305) time: 0.5201 [2021-03-27 05:11:12 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 30/1251] eta: 0:12:53 lr: 0.000034 loss: 2.8905 (2.8117) grad_norm: 3.0131 (2.9633) time: 0.5016 [2021-03-27 05:11:17 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 40/1251] eta: 0:12:14 lr: 0.000034 loss: 2.7504 (2.7665) grad_norm: 3.1221 (2.9894) time: 0.5106 [2021-03-27 05:11:23 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 50/1251] eta: 0:11:46 lr: 0.000034 loss: 2.7160 (2.7613) grad_norm: 3.1807 (3.0304) time: 0.5187 [2021-03-27 05:11:28 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 60/1251] eta: 0:11:24 lr: 0.000034 loss: 2.8409 (2.7826) grad_norm: 3.1273 (3.0555) time: 0.5082 [2021-03-27 05:11:33 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 70/1251] eta: 0:11:06 lr: 0.000034 loss: 2.8758 (2.7656) grad_norm: 2.8858 (3.0448) time: 0.5041 [2021-03-27 05:11:38 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 80/1251] eta: 0:10:52 lr: 0.000034 loss: 2.7020 (2.7563) grad_norm: 2.8858 (3.0783) time: 0.5041 [2021-03-27 05:11:43 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 90/1251] eta: 0:10:38 lr: 0.000034 loss: 2.7020 (2.7507) grad_norm: 2.8959 (3.0555) time: 0.4992 [2021-03-27 05:11:48 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 100/1251] eta: 0:10:27 lr: 0.000034 loss: 2.7993 (2.7468) grad_norm: 2.9652 (3.0838) time: 0.4959 [2021-03-27 05:11:53 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 110/1251] eta: 0:10:19 lr: 0.000034 loss: 2.6939 (2.7368) grad_norm: 3.0930 (3.0924) time: 0.5122 [2021-03-27 05:11:58 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 120/1251] eta: 0:10:11 lr: 0.000034 loss: 2.6939 (2.7407) grad_norm: 2.9981 (3.0797) time: 0.5200 [2021-03-27 05:12:03 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 130/1251] eta: 0:10:02 lr: 0.000034 loss: 2.6162 (2.7179) grad_norm: 2.9607 (3.0783) time: 0.5027 [2021-03-27 05:12:08 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 140/1251] eta: 0:09:53 lr: 0.000034 loss: 2.6162 (2.7201) grad_norm: 2.9451 (3.0818) time: 0.4940 [2021-03-27 05:12:13 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 150/1251] eta: 0:09:45 lr: 0.000034 loss: 2.7690 (2.7240) grad_norm: 3.1035 (3.0902) time: 0.4949 [2021-03-27 05:12:18 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 160/1251] eta: 0:09:37 lr: 0.000034 loss: 2.7800 (2.7284) grad_norm: 3.1035 (3.0884) time: 0.4984 [2021-03-27 05:12:23 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 170/1251] eta: 0:09:30 lr: 0.000034 loss: 2.9637 (2.7430) grad_norm: 3.0358 (3.0898) time: 0.4999 [2021-03-27 05:12:28 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 180/1251] eta: 0:09:24 lr: 0.000034 loss: 2.9494 (2.7540) grad_norm: 3.0735 (3.0954) time: 0.5019 [2021-03-27 05:12:33 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 190/1251] eta: 0:09:17 lr: 0.000034 loss: 2.8131 (2.7454) grad_norm: 3.0430 (3.0976) time: 0.5066 [2021-03-27 05:12:38 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 200/1251] eta: 0:09:12 lr: 0.000034 loss: 2.6649 (2.7522) grad_norm: 3.0362 (3.0989) time: 0.5124 [2021-03-27 05:12:43 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 210/1251] eta: 0:09:05 lr: 0.000034 loss: 2.6649 (2.7441) grad_norm: 2.9824 (3.1021) time: 0.5135 [2021-03-27 05:12:48 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 220/1251] eta: 0:08:59 lr: 0.000034 loss: 2.5907 (2.7343) grad_norm: 2.9903 (3.1136) time: 0.5063 [2021-03-27 05:12:53 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 230/1251] eta: 0:08:53 lr: 0.000034 loss: 2.6161 (2.7323) grad_norm: 3.1036 (3.1104) time: 0.5007 [2021-03-27 05:12:58 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 240/1251] eta: 0:08:47 lr: 0.000034 loss: 2.8891 (2.7358) grad_norm: 3.0296 (3.1140) time: 0.5048 [2021-03-27 05:13:03 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 250/1251] eta: 0:08:42 lr: 0.000034 loss: 2.8580 (2.7351) grad_norm: 3.0448 (3.1109) time: 0.5116 [2021-03-27 05:13:09 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 260/1251] eta: 0:08:36 lr: 0.000034 loss: 2.7568 (2.7366) grad_norm: 2.8586 (3.1023) time: 0.5129 [2021-03-27 05:13:14 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 270/1251] eta: 0:08:30 lr: 0.000034 loss: 2.7568 (2.7384) grad_norm: 2.8469 (3.0968) time: 0.5107 [2021-03-27 05:13:19 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 280/1251] eta: 0:08:24 lr: 0.000034 loss: 2.8035 (2.7440) grad_norm: 2.8469 (3.1000) time: 0.5015 [2021-03-27 05:13:24 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 290/1251] eta: 0:08:18 lr: 0.000034 loss: 2.8613 (2.7367) grad_norm: 3.1226 (3.1024) time: 0.4971 [2021-03-27 05:13:29 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 300/1251] eta: 0:08:13 lr: 0.000034 loss: 2.8461 (2.7370) grad_norm: 3.2010 (3.1036) time: 0.5059 [2021-03-27 05:13:34 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 310/1251] eta: 0:08:08 lr: 0.000034 loss: 2.9490 (2.7451) grad_norm: 2.9126 (3.0991) time: 0.5128 [2021-03-27 05:13:39 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 320/1251] eta: 0:08:02 lr: 0.000034 loss: 2.9438 (2.7420) grad_norm: 2.8889 (3.1014) time: 0.5047 [2021-03-27 05:13:44 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 330/1251] eta: 0:07:56 lr: 0.000034 loss: 2.6407 (2.7313) grad_norm: 2.8936 (3.1053) time: 0.4956 [2021-03-27 05:13:49 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 340/1251] eta: 0:07:50 lr: 0.000034 loss: 2.7403 (2.7303) grad_norm: 2.8936 (3.1182) time: 0.4955 [2021-03-27 05:13:54 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 350/1251] eta: 0:07:45 lr: 0.000034 loss: 2.7403 (2.7295) grad_norm: 3.0041 (3.1188) time: 0.4971 [2021-03-27 05:13:59 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 360/1251] eta: 0:07:39 lr: 0.000034 loss: 2.7346 (2.7305) grad_norm: 3.0871 (3.1185) time: 0.4995 [2021-03-27 05:14:04 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 370/1251] eta: 0:07:33 lr: 0.000034 loss: 2.8997 (2.7321) grad_norm: 3.0809 (3.1184) time: 0.4970 [2021-03-27 05:14:09 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 380/1251] eta: 0:07:28 lr: 0.000034 loss: 2.7776 (2.7317) grad_norm: 2.8873 (3.1168) time: 0.4951 [2021-03-27 05:14:14 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 390/1251] eta: 0:07:22 lr: 0.000034 loss: 2.6290 (2.7321) grad_norm: 2.8873 (3.1139) time: 0.4963 [2021-03-27 05:14:19 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 400/1251] eta: 0:07:17 lr: 0.000034 loss: 2.8677 (2.7385) grad_norm: 2.9540 (3.1132) time: 0.4972 [2021-03-27 05:14:24 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 410/1251] eta: 0:07:12 lr: 0.000034 loss: 2.8979 (2.7403) grad_norm: 2.9657 (3.1119) time: 0.5056 [2021-03-27 05:14:29 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 420/1251] eta: 0:07:06 lr: 0.000034 loss: 2.7432 (2.7385) grad_norm: 2.9407 (3.1112) time: 0.5053 [2021-03-27 05:14:34 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 430/1251] eta: 0:07:01 lr: 0.000034 loss: 2.8727 (2.7415) grad_norm: 2.9178 (3.1219) time: 0.5011 [2021-03-27 05:14:39 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 440/1251] eta: 0:06:56 lr: 0.000034 loss: 2.8191 (2.7414) grad_norm: 2.8694 (3.1173) time: 0.5049 [2021-03-27 05:14:44 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 450/1251] eta: 0:06:50 lr: 0.000034 loss: 2.7687 (2.7418) grad_norm: 2.8564 (3.1126) time: 0.5046 [2021-03-27 05:14:49 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 460/1251] eta: 0:06:45 lr: 0.000034 loss: 2.7687 (2.7392) grad_norm: 2.8604 (3.1078) time: 0.5022 [2021-03-27 05:14:54 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 470/1251] eta: 0:06:40 lr: 0.000034 loss: 2.7163 (2.7353) grad_norm: 2.9803 (3.1276) time: 0.5086 [2021-03-27 05:14:59 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 480/1251] eta: 0:06:35 lr: 0.000034 loss: 2.6082 (2.7309) grad_norm: 3.0678 (3.1265) time: 0.5076 [2021-03-27 05:15:04 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 490/1251] eta: 0:06:29 lr: 0.000034 loss: 2.6913 (2.7342) grad_norm: 2.8905 (3.1217) time: 0.5012 [2021-03-27 05:15:09 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 500/1251] eta: 0:06:24 lr: 0.000034 loss: 2.8702 (2.7337) grad_norm: 2.7317 (3.1192) time: 0.4995 [2021-03-27 05:15:14 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 510/1251] eta: 0:06:19 lr: 0.000034 loss: 2.6001 (2.7308) grad_norm: 2.7317 (3.1173) time: 0.4982 [2021-03-27 05:15:19 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 520/1251] eta: 0:06:13 lr: 0.000034 loss: 2.6750 (2.7295) grad_norm: 2.9827 (3.1166) time: 0.4967 [2021-03-27 05:15:24 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 530/1251] eta: 0:06:08 lr: 0.000034 loss: 2.7810 (2.7297) grad_norm: 2.9107 (3.1154) time: 0.4963 [2021-03-27 05:15:29 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 540/1251] eta: 0:06:03 lr: 0.000034 loss: 2.6632 (2.7254) grad_norm: 3.0487 (3.1146) time: 0.4993 [2021-03-27 05:15:34 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 550/1251] eta: 0:05:58 lr: 0.000034 loss: 2.6266 (2.7254) grad_norm: 3.0528 (3.1164) time: 0.5091 [2021-03-27 05:15:39 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 560/1251] eta: 0:05:52 lr: 0.000034 loss: 2.8013 (2.7312) grad_norm: 2.9908 (3.1178) time: 0.5062 [2021-03-27 05:15:44 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 570/1251] eta: 0:05:47 lr: 0.000034 loss: 2.8279 (2.7302) grad_norm: 2.9967 (3.1180) time: 0.4932 [2021-03-27 05:15:49 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 580/1251] eta: 0:05:42 lr: 0.000033 loss: 2.7996 (2.7312) grad_norm: 3.0037 (3.1190) time: 0.4945 [2021-03-27 05:15:54 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 590/1251] eta: 0:05:37 lr: 0.000033 loss: 2.7213 (2.7306) grad_norm: 2.8146 (3.1148) time: 0.4982 [2021-03-27 05:15:59 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 600/1251] eta: 0:05:31 lr: 0.000033 loss: 2.7224 (2.7334) grad_norm: 2.8146 (3.1151) time: 0.4951 [2021-03-27 05:16:04 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 610/1251] eta: 0:05:26 lr: 0.000033 loss: 2.8493 (2.7339) grad_norm: 2.8957 (3.1111) time: 0.4910 [2021-03-27 05:16:09 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 620/1251] eta: 0:05:21 lr: 0.000033 loss: 2.7545 (2.7335) grad_norm: 2.8957 (3.1090) time: 0.4981 [2021-03-27 05:16:14 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 630/1251] eta: 0:05:16 lr: 0.000033 loss: 2.7855 (2.7363) grad_norm: 2.8957 (3.1075) time: 0.4993 [2021-03-27 05:16:19 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 640/1251] eta: 0:05:10 lr: 0.000033 loss: 2.9336 (2.7407) grad_norm: 2.8857 (3.1083) time: 0.5009 [2021-03-27 05:16:24 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 650/1251] eta: 0:05:05 lr: 0.000033 loss: 2.9384 (2.7398) grad_norm: 2.8831 (3.1146) time: 0.5068 [2021-03-27 05:16:29 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 660/1251] eta: 0:05:00 lr: 0.000033 loss: 2.7108 (2.7391) grad_norm: 3.2011 (3.1183) time: 0.5047 [2021-03-27 05:16:34 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 670/1251] eta: 0:04:55 lr: 0.000033 loss: 2.5843 (2.7344) grad_norm: 3.2011 (3.1201) time: 0.5011 [2021-03-27 05:16:39 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 680/1251] eta: 0:04:50 lr: 0.000033 loss: 2.5708 (2.7350) grad_norm: 2.9905 (3.1168) time: 0.4978 [2021-03-27 05:16:44 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 690/1251] eta: 0:04:45 lr: 0.000033 loss: 3.0111 (2.7383) grad_norm: 2.8997 (3.1176) time: 0.4982 [2021-03-27 05:16:49 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 700/1251] eta: 0:04:40 lr: 0.000033 loss: 2.8098 (2.7350) grad_norm: 2.8502 (3.1151) time: 0.5026 [2021-03-27 05:16:54 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 710/1251] eta: 0:04:34 lr: 0.000033 loss: 2.6790 (2.7366) grad_norm: 2.8806 (3.1166) time: 0.5003 [2021-03-27 05:16:59 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 720/1251] eta: 0:04:29 lr: 0.000033 loss: 2.8767 (2.7380) grad_norm: 2.9003 (3.1133) time: 0.4960 [2021-03-27 05:17:04 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 730/1251] eta: 0:04:24 lr: 0.000033 loss: 2.9084 (2.7385) grad_norm: 2.8449 (3.1119) time: 0.5075 [2021-03-27 05:17:09 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 740/1251] eta: 0:04:19 lr: 0.000033 loss: 2.9579 (2.7401) grad_norm: 3.0332 (3.1132) time: 0.5178 [2021-03-27 05:17:14 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 750/1251] eta: 0:04:14 lr: 0.000033 loss: 2.9024 (2.7422) grad_norm: 3.1360 (3.1157) time: 0.5094 [2021-03-27 05:17:19 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 760/1251] eta: 0:04:09 lr: 0.000033 loss: 2.9132 (2.7428) grad_norm: 3.0246 (3.1165) time: 0.5092 [2021-03-27 05:17:24 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 770/1251] eta: 0:04:04 lr: 0.000033 loss: 2.7269 (2.7395) grad_norm: 2.9805 (3.1156) time: 0.5077 [2021-03-27 05:17:29 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 780/1251] eta: 0:03:59 lr: 0.000033 loss: 2.7693 (2.7405) grad_norm: 2.9960 (3.1189) time: 0.4997 [2021-03-27 05:17:35 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 790/1251] eta: 0:03:54 lr: 0.000033 loss: 2.8836 (2.7434) grad_norm: 2.9833 (3.1168) time: 0.5047 [2021-03-27 05:17:40 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 800/1251] eta: 0:03:49 lr: 0.000033 loss: 2.8965 (2.7447) grad_norm: 2.9833 (3.1181) time: 0.5049 [2021-03-27 05:17:45 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 810/1251] eta: 0:03:44 lr: 0.000033 loss: 2.9117 (2.7480) grad_norm: 3.0314 (3.1172) time: 0.5023 [2021-03-27 05:17:50 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 820/1251] eta: 0:03:38 lr: 0.000033 loss: 3.0118 (2.7495) grad_norm: 3.0314 (3.1181) time: 0.5029 [2021-03-27 05:17:55 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 830/1251] eta: 0:03:33 lr: 0.000033 loss: 2.9939 (2.7507) grad_norm: 3.1266 (3.1174) time: 0.5001 [2021-03-27 05:18:00 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 840/1251] eta: 0:03:28 lr: 0.000033 loss: 2.8663 (2.7505) grad_norm: 3.0791 (3.1195) time: 0.4990 [2021-03-27 05:18:05 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 850/1251] eta: 0:03:23 lr: 0.000033 loss: 2.6028 (2.7474) grad_norm: 3.0062 (3.1215) time: 0.5093 [2021-03-27 05:18:10 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 860/1251] eta: 0:03:18 lr: 0.000033 loss: 2.4796 (2.7461) grad_norm: 3.0062 (3.1215) time: 0.5103 [2021-03-27 05:18:15 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 870/1251] eta: 0:03:13 lr: 0.000033 loss: 2.8541 (2.7473) grad_norm: 3.1814 (3.1245) time: 0.5012 [2021-03-27 05:18:20 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 880/1251] eta: 0:03:08 lr: 0.000033 loss: 2.8894 (2.7478) grad_norm: 3.2087 (3.1247) time: 0.4970 [2021-03-27 05:18:25 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 890/1251] eta: 0:03:03 lr: 0.000033 loss: 2.7707 (2.7473) grad_norm: 3.0367 (3.1240) time: 0.4976 [2021-03-27 05:18:30 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 900/1251] eta: 0:02:58 lr: 0.000033 loss: 2.6504 (2.7454) grad_norm: 3.0367 (3.1249) time: 0.5031 [2021-03-27 05:18:35 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 910/1251] eta: 0:02:52 lr: 0.000033 loss: 2.6504 (2.7452) grad_norm: 3.0188 (3.1230) time: 0.4996 [2021-03-27 05:18:40 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 920/1251] eta: 0:02:47 lr: 0.000033 loss: 2.8226 (2.7446) grad_norm: 2.9949 (3.1252) time: 0.4994 [2021-03-27 05:18:45 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 930/1251] eta: 0:02:42 lr: 0.000033 loss: 2.8176 (2.7440) grad_norm: 3.0630 (3.1292) time: 0.5099 [2021-03-27 05:18:50 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 940/1251] eta: 0:02:37 lr: 0.000033 loss: 2.8467 (2.7457) grad_norm: 2.9337 (3.1266) time: 0.5052 [2021-03-27 05:18:55 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 950/1251] eta: 0:02:32 lr: 0.000033 loss: 2.9029 (2.7476) grad_norm: 2.9423 (3.1277) time: 0.5015 [2021-03-27 05:19:00 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 960/1251] eta: 0:02:27 lr: 0.000033 loss: 2.8719 (2.7471) grad_norm: 2.8770 (3.1248) time: 0.4993 [2021-03-27 05:19:05 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 970/1251] eta: 0:02:22 lr: 0.000033 loss: 2.5750 (2.7446) grad_norm: 2.8281 (3.1292) time: 0.4968 [2021-03-27 05:19:10 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 980/1251] eta: 0:02:17 lr: 0.000033 loss: 2.6110 (2.7442) grad_norm: 3.0310 (3.1284) time: 0.5055 [2021-03-27 05:19:15 swin_small_patch4_window7_224] INFO: Epoch: [270] [ 990/1251] eta: 0:02:12 lr: 0.000033 loss: 2.7910 (2.7445) grad_norm: 3.0290 (3.1291) time: 0.5102 [2021-03-27 05:19:20 swin_small_patch4_window7_224] INFO: Epoch: [270] [1000/1251] eta: 0:02:07 lr: 0.000033 loss: 2.7397 (2.7435) grad_norm: 3.0290 (inf) time: 0.5080 [2021-03-27 05:19:25 swin_small_patch4_window7_224] INFO: Epoch: [270] [1010/1251] eta: 0:02:02 lr: 0.000033 loss: 2.7593 (2.7452) grad_norm: 3.0872 (inf) time: 0.5000 [2021-03-27 05:19:30 swin_small_patch4_window7_224] INFO: Epoch: [270] [1020/1251] eta: 0:01:57 lr: 0.000033 loss: 2.6047 (2.7428) grad_norm: 3.0494 (inf) time: 0.4979 [2021-03-27 05:19:35 swin_small_patch4_window7_224] INFO: Epoch: [270] [1030/1251] eta: 0:01:51 lr: 0.000033 loss: 2.6075 (2.7451) grad_norm: 3.0647 (inf) time: 0.4979 [2021-03-27 05:19:40 swin_small_patch4_window7_224] INFO: Epoch: [270] [1040/1251] eta: 0:01:46 lr: 0.000033 loss: 2.8488 (2.7429) grad_norm: 3.1357 (inf) time: 0.4976 [2021-03-27 05:19:45 swin_small_patch4_window7_224] INFO: Epoch: [270] [1050/1251] eta: 0:01:41 lr: 0.000033 loss: 2.6592 (2.7435) grad_norm: 2.9085 (inf) time: 0.5068 [2021-03-27 05:19:50 swin_small_patch4_window7_224] INFO: Epoch: [270] [1060/1251] eta: 0:01:36 lr: 0.000033 loss: 2.8272 (2.7461) grad_norm: 2.8686 (inf) time: 0.5052 [2021-03-27 05:19:55 swin_small_patch4_window7_224] INFO: Epoch: [270] [1070/1251] eta: 0:01:31 lr: 0.000033 loss: 2.8298 (2.7460) grad_norm: 2.7600 (inf) time: 0.5037 [2021-03-27 05:20:00 swin_small_patch4_window7_224] INFO: Epoch: [270] [1080/1251] eta: 0:01:26 lr: 0.000033 loss: 2.7862 (2.7455) grad_norm: 2.9591 (inf) time: 0.5027 [2021-03-27 05:20:05 swin_small_patch4_window7_224] INFO: Epoch: [270] [1090/1251] eta: 0:01:21 lr: 0.000033 loss: 2.8361 (2.7458) grad_norm: 3.0796 (inf) time: 0.4963 [2021-03-27 05:20:10 swin_small_patch4_window7_224] INFO: Epoch: [270] [1100/1251] eta: 0:01:16 lr: 0.000033 loss: 2.8076 (2.7462) grad_norm: 2.9158 (inf) time: 0.4954 [2021-03-27 05:20:15 swin_small_patch4_window7_224] INFO: Epoch: [270] [1110/1251] eta: 0:01:11 lr: 0.000033 loss: 2.9470 (2.7484) grad_norm: 2.9158 (inf) time: 0.4972 [2021-03-27 05:20:20 swin_small_patch4_window7_224] INFO: Epoch: [270] [1120/1251] eta: 0:01:06 lr: 0.000033 loss: 2.9470 (2.7493) grad_norm: 2.9929 (inf) time: 0.4998 [2021-03-27 05:20:25 swin_small_patch4_window7_224] INFO: Epoch: [270] [1130/1251] eta: 0:01:01 lr: 0.000033 loss: 2.7712 (2.7482) grad_norm: 2.8386 (inf) time: 0.4996 [2021-03-27 05:20:30 swin_small_patch4_window7_224] INFO: Epoch: [270] [1140/1251] eta: 0:00:56 lr: 0.000033 loss: 2.7121 (2.7479) grad_norm: 2.8438 (inf) time: 0.4979 [2021-03-27 05:20:35 swin_small_patch4_window7_224] INFO: Epoch: [270] [1150/1251] eta: 0:00:51 lr: 0.000033 loss: 2.5867 (2.7466) grad_norm: 2.9669 (inf) time: 0.4955 [2021-03-27 05:20:40 swin_small_patch4_window7_224] INFO: Epoch: [270] [1160/1251] eta: 0:00:46 lr: 0.000033 loss: 2.8274 (2.7482) grad_norm: 3.0779 (inf) time: 0.5062 [2021-03-27 05:20:45 swin_small_patch4_window7_224] INFO: Epoch: [270] [1170/1251] eta: 0:00:40 lr: 0.000033 loss: 2.8274 (2.7475) grad_norm: 3.1571 (inf) time: 0.5142 [2021-03-27 05:20:50 swin_small_patch4_window7_224] INFO: Epoch: [270] [1180/1251] eta: 0:00:35 lr: 0.000033 loss: 2.7403 (2.7460) grad_norm: 3.2483 (inf) time: 0.5058 [2021-03-27 05:20:55 swin_small_patch4_window7_224] INFO: Epoch: [270] [1190/1251] eta: 0:00:30 lr: 0.000033 loss: 2.7849 (2.7457) grad_norm: 3.1135 (inf) time: 0.5015 [2021-03-27 05:21:00 swin_small_patch4_window7_224] INFO: Epoch: [270] [1200/1251] eta: 0:00:25 lr: 0.000033 loss: 2.7849 (2.7465) grad_norm: 3.0697 (inf) time: 0.5016 [2021-03-27 05:21:05 swin_small_patch4_window7_224] INFO: Epoch: [270] [1210/1251] eta: 0:00:20 lr: 0.000033 loss: 2.7897 (2.7448) grad_norm: 2.8690 (inf) time: 0.4995 [2021-03-27 05:21:10 swin_small_patch4_window7_224] INFO: Epoch: [270] [1220/1251] eta: 0:00:15 lr: 0.000033 loss: 2.7514 (2.7439) grad_norm: 2.9492 (inf) time: 0.5012 [2021-03-27 05:21:15 swin_small_patch4_window7_224] INFO: Epoch: [270] [1230/1251] eta: 0:00:10 lr: 0.000033 loss: 2.8024 (2.7446) grad_norm: 2.9901 (inf) time: 0.5012 [2021-03-27 05:21:21 swin_small_patch4_window7_224] INFO: Epoch: [270] [1240/1251] eta: 0:00:05 lr: 0.000033 loss: 2.9262 (2.7452) grad_norm: 2.8738 (inf) time: 0.5063 [2021-03-27 05:21:26 swin_small_patch4_window7_224] INFO: Epoch: [270] [1250/1251] eta: 0:00:00 lr: 0.000033 loss: 3.0157 (2.7465) grad_norm: 2.8738 (inf) time: 0.5099 [2021-03-27 05:22:15 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:13 loss: 0.6320 (0.6320) acc1: 87.5000 (87.5000) acc5: 95.3125 (95.3125) [2021-03-27 05:22:16 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.6956 (0.7413) acc1: 81.2500 (82.2443) acc5: 96.8750 (96.7330) [2021-03-27 05:22:17 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.6470 (0.6859) acc1: 82.8125 (83.6310) acc5: 96.8750 (96.9494) [2021-03-27 05:22:19 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.6470 (0.6900) acc1: 84.3750 (83.7198) acc5: 96.8750 (96.7742) [2021-03-27 05:22:20 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7218 (0.7433) acc1: 81.2500 (82.6220) acc5: 95.3125 (96.2271) [2021-03-27 05:22:20 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8733 (0.7526) acc1: 81.1321 (82.1120) acc5: 95.3125 (96.1280) [2021-03-27 05:22:33 swin_small_patch4_window7_224] INFO: * Acc@1 82.816 Acc@5 96.248 loss 0.739 [2021-03-27 05:22:33 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 05:22:33 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 05:22:37 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 0/1251] eta: 1:29:51 lr: 0.000033 loss: 3.3486 (3.3486) grad_norm: 3.5473 (3.5473) time: 4.3098 [2021-03-27 05:22:42 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 10/1251] eta: 0:17:41 lr: 0.000033 loss: 2.8538 (2.8212) grad_norm: 2.9814 (2.9791) time: 0.8553 [2021-03-27 05:22:47 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 20/1251] eta: 0:14:07 lr: 0.000033 loss: 2.8372 (2.8145) grad_norm: 3.0075 (3.0869) time: 0.5072 [2021-03-27 05:22:53 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 30/1251] eta: 0:12:53 lr: 0.000033 loss: 2.7535 (2.7969) grad_norm: 3.1223 (3.0788) time: 0.5115 [2021-03-27 05:22:58 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 40/1251] eta: 0:12:12 lr: 0.000033 loss: 2.7168 (2.7720) grad_norm: 3.0626 (3.0877) time: 0.5175 [2021-03-27 05:23:03 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 50/1251] eta: 0:11:43 lr: 0.000033 loss: 2.7168 (2.7397) grad_norm: 3.0626 (3.2868) time: 0.5113 [2021-03-27 05:23:08 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 60/1251] eta: 0:11:21 lr: 0.000033 loss: 2.6369 (2.7158) grad_norm: 3.1462 (3.3197) time: 0.5054 [2021-03-27 05:23:13 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 70/1251] eta: 0:11:03 lr: 0.000033 loss: 2.8130 (2.7182) grad_norm: 3.1008 (3.2980) time: 0.5017 [2021-03-27 05:23:18 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 80/1251] eta: 0:10:48 lr: 0.000033 loss: 2.8130 (2.7229) grad_norm: 3.0585 (3.2665) time: 0.4985 [2021-03-27 05:23:23 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 90/1251] eta: 0:10:36 lr: 0.000033 loss: 2.9360 (2.7405) grad_norm: 2.8752 (3.2638) time: 0.5000 [2021-03-27 05:23:28 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 100/1251] eta: 0:10:25 lr: 0.000033 loss: 3.0290 (2.7598) grad_norm: 2.9482 (3.2506) time: 0.4991 [2021-03-27 05:23:33 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 110/1251] eta: 0:10:17 lr: 0.000033 loss: 2.8778 (2.7538) grad_norm: 2.9500 (3.2464) time: 0.5063 [2021-03-27 05:23:38 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 120/1251] eta: 0:10:08 lr: 0.000033 loss: 2.6117 (2.7518) grad_norm: 3.0772 (3.2409) time: 0.5108 [2021-03-27 05:23:43 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 130/1251] eta: 0:10:00 lr: 0.000032 loss: 2.9060 (2.7699) grad_norm: 3.2001 (3.2344) time: 0.5062 [2021-03-27 05:23:48 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 140/1251] eta: 0:09:51 lr: 0.000032 loss: 3.0214 (2.7784) grad_norm: 3.2231 (3.2804) time: 0.5009 [2021-03-27 05:23:53 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 150/1251] eta: 0:09:44 lr: 0.000032 loss: 2.9787 (2.7809) grad_norm: 3.1862 (3.2695) time: 0.4996 [2021-03-27 05:23:58 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 160/1251] eta: 0:09:36 lr: 0.000032 loss: 2.8413 (2.7876) grad_norm: 3.0294 (3.2508) time: 0.5002 [2021-03-27 05:24:03 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 170/1251] eta: 0:09:31 lr: 0.000032 loss: 2.8413 (2.7817) grad_norm: 2.9337 (3.2362) time: 0.5098 [2021-03-27 05:24:08 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 180/1251] eta: 0:09:25 lr: 0.000032 loss: 2.6631 (2.7728) grad_norm: 2.8969 (3.2502) time: 0.5220 [2021-03-27 05:24:14 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 190/1251] eta: 0:09:18 lr: 0.000032 loss: 2.5695 (2.7632) grad_norm: 2.9083 (3.2374) time: 0.5138 [2021-03-27 05:24:19 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 200/1251] eta: 0:09:12 lr: 0.000032 loss: 2.8119 (2.7611) grad_norm: 3.0011 (3.2342) time: 0.5044 [2021-03-27 05:24:24 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 210/1251] eta: 0:09:06 lr: 0.000032 loss: 2.8119 (2.7620) grad_norm: 2.9364 (3.2277) time: 0.5122 [2021-03-27 05:24:29 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 220/1251] eta: 0:09:00 lr: 0.000032 loss: 2.7395 (2.7539) grad_norm: 3.0162 (3.2270) time: 0.5136 [2021-03-27 05:24:34 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 230/1251] eta: 0:08:55 lr: 0.000032 loss: 2.7395 (2.7564) grad_norm: 3.1911 (3.2281) time: 0.5143 [2021-03-27 05:24:39 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 240/1251] eta: 0:08:49 lr: 0.000032 loss: 2.7871 (2.7542) grad_norm: 3.1911 (3.2481) time: 0.5189 [2021-03-27 05:24:44 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 250/1251] eta: 0:08:43 lr: 0.000032 loss: 2.7480 (2.7506) grad_norm: 3.1262 (3.2435) time: 0.5058 [2021-03-27 05:24:49 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 260/1251] eta: 0:08:37 lr: 0.000032 loss: 2.7622 (2.7433) grad_norm: 3.3046 (3.2452) time: 0.4971 [2021-03-27 05:24:54 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 270/1251] eta: 0:08:31 lr: 0.000032 loss: 2.7169 (2.7372) grad_norm: 3.0876 (3.2388) time: 0.5006 [2021-03-27 05:24:59 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 280/1251] eta: 0:08:25 lr: 0.000032 loss: 2.6586 (2.7318) grad_norm: 3.0124 (3.2358) time: 0.5019 [2021-03-27 05:25:04 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 290/1251] eta: 0:08:19 lr: 0.000032 loss: 2.7462 (2.7289) grad_norm: 3.1079 (3.2395) time: 0.4980 [2021-03-27 05:25:09 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 300/1251] eta: 0:08:13 lr: 0.000032 loss: 2.8040 (2.7333) grad_norm: 3.1800 (3.2467) time: 0.5025 [2021-03-27 05:25:14 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 310/1251] eta: 0:08:08 lr: 0.000032 loss: 2.8503 (2.7298) grad_norm: 3.0793 (3.2394) time: 0.5068 [2021-03-27 05:25:19 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 320/1251] eta: 0:08:02 lr: 0.000032 loss: 2.8834 (2.7349) grad_norm: 2.9521 (3.2350) time: 0.5056 [2021-03-27 05:25:24 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 330/1251] eta: 0:07:56 lr: 0.000032 loss: 2.9010 (2.7379) grad_norm: 3.0641 (3.2402) time: 0.5024 [2021-03-27 05:25:29 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 340/1251] eta: 0:07:51 lr: 0.000032 loss: 2.8767 (2.7393) grad_norm: 3.1138 (3.2354) time: 0.5017 [2021-03-27 05:25:34 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 350/1251] eta: 0:07:45 lr: 0.000032 loss: 2.7838 (2.7382) grad_norm: 3.1373 (3.2328) time: 0.4990 [2021-03-27 05:25:39 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 360/1251] eta: 0:07:40 lr: 0.000032 loss: 2.7931 (2.7413) grad_norm: 2.9071 (3.2301) time: 0.5004 [2021-03-27 05:25:45 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 370/1251] eta: 0:07:34 lr: 0.000032 loss: 2.7931 (2.7385) grad_norm: 2.8926 (3.2244) time: 0.5082 [2021-03-27 05:25:50 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 380/1251] eta: 0:07:29 lr: 0.000032 loss: 2.7115 (2.7347) grad_norm: 2.7523 (3.2145) time: 0.5052 [2021-03-27 05:25:55 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 390/1251] eta: 0:07:23 lr: 0.000032 loss: 2.6479 (2.7318) grad_norm: 2.9547 (3.2124) time: 0.5007 [2021-03-27 05:25:59 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 400/1251] eta: 0:07:18 lr: 0.000032 loss: 2.6764 (2.7327) grad_norm: 3.1736 (3.2124) time: 0.4986 [2021-03-27 05:26:04 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 410/1251] eta: 0:07:12 lr: 0.000032 loss: 2.7885 (2.7350) grad_norm: 3.1437 (3.2075) time: 0.4953 [2021-03-27 05:26:09 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 420/1251] eta: 0:07:07 lr: 0.000032 loss: 2.8870 (2.7360) grad_norm: 2.9521 (3.2033) time: 0.4952 [2021-03-27 05:26:15 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 430/1251] eta: 0:07:02 lr: 0.000032 loss: 2.8562 (2.7412) grad_norm: 2.9730 (3.2954) time: 0.5074 [2021-03-27 05:26:20 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 440/1251] eta: 0:06:56 lr: 0.000032 loss: 2.8562 (2.7419) grad_norm: 3.0258 (3.2899) time: 0.5060 [2021-03-27 05:26:25 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 450/1251] eta: 0:06:51 lr: 0.000032 loss: 2.6925 (2.7391) grad_norm: 3.0484 (3.2909) time: 0.4977 [2021-03-27 05:26:30 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 460/1251] eta: 0:06:45 lr: 0.000032 loss: 2.6925 (2.7376) grad_norm: 3.0709 (3.2851) time: 0.5010 [2021-03-27 05:26:35 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 470/1251] eta: 0:06:40 lr: 0.000032 loss: 2.7062 (2.7345) grad_norm: 2.7268 (3.2741) time: 0.5011 [2021-03-27 05:26:40 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 480/1251] eta: 0:06:35 lr: 0.000032 loss: 2.7062 (2.7329) grad_norm: 2.8878 (3.2715) time: 0.5035 [2021-03-27 05:26:45 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 490/1251] eta: 0:06:29 lr: 0.000032 loss: 2.5405 (2.7289) grad_norm: 2.9919 (3.2698) time: 0.5014 [2021-03-27 05:26:50 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 500/1251] eta: 0:06:24 lr: 0.000032 loss: 2.5581 (2.7251) grad_norm: 2.9915 (3.2651) time: 0.4943 [2021-03-27 05:26:55 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 510/1251] eta: 0:06:19 lr: 0.000032 loss: 2.8513 (2.7276) grad_norm: 3.0225 (3.2614) time: 0.4974 [2021-03-27 05:26:59 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 520/1251] eta: 0:06:13 lr: 0.000032 loss: 2.9001 (2.7301) grad_norm: 3.1386 (3.2588) time: 0.4966 [2021-03-27 05:27:04 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 530/1251] eta: 0:06:08 lr: 0.000032 loss: 2.8682 (2.7344) grad_norm: 3.0094 (3.2532) time: 0.4964 [2021-03-27 05:27:09 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 540/1251] eta: 0:06:03 lr: 0.000032 loss: 2.8578 (2.7343) grad_norm: 3.1022 (3.2521) time: 0.4981 [2021-03-27 05:27:14 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 550/1251] eta: 0:05:58 lr: 0.000032 loss: 2.6445 (2.7315) grad_norm: 3.1022 (3.2503) time: 0.5001 [2021-03-27 05:27:20 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 560/1251] eta: 0:05:52 lr: 0.000032 loss: 2.7267 (2.7341) grad_norm: 3.1562 (3.2506) time: 0.5061 [2021-03-27 05:27:25 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 570/1251] eta: 0:05:47 lr: 0.000032 loss: 2.9721 (2.7358) grad_norm: 3.0883 (3.2472) time: 0.5037 [2021-03-27 05:27:29 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 580/1251] eta: 0:05:42 lr: 0.000032 loss: 2.7684 (2.7337) grad_norm: 3.1172 (3.2517) time: 0.4977 [2021-03-27 05:27:35 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 590/1251] eta: 0:05:37 lr: 0.000032 loss: 2.7650 (2.7352) grad_norm: 3.2281 (3.2492) time: 0.4983 [2021-03-27 05:27:40 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 600/1251] eta: 0:05:32 lr: 0.000032 loss: 2.9780 (2.7360) grad_norm: 3.0076 (3.2515) time: 0.5025 [2021-03-27 05:27:45 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 610/1251] eta: 0:05:26 lr: 0.000032 loss: 2.8580 (2.7335) grad_norm: 2.9880 (3.2501) time: 0.4995 [2021-03-27 05:27:50 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 620/1251] eta: 0:05:21 lr: 0.000032 loss: 2.7083 (2.7321) grad_norm: 3.0858 (3.2483) time: 0.5047 [2021-03-27 05:27:55 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 630/1251] eta: 0:05:16 lr: 0.000032 loss: 2.7747 (2.7314) grad_norm: 2.9752 (3.2474) time: 0.5053 [2021-03-27 05:28:00 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 640/1251] eta: 0:05:11 lr: 0.000032 loss: 2.8627 (2.7348) grad_norm: 2.9138 (3.2466) time: 0.5000 [2021-03-27 05:28:05 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 650/1251] eta: 0:05:06 lr: 0.000032 loss: 2.9697 (2.7364) grad_norm: 2.9362 (3.2446) time: 0.4991 [2021-03-27 05:28:10 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 660/1251] eta: 0:05:00 lr: 0.000032 loss: 2.8996 (2.7377) grad_norm: 3.1591 (3.2428) time: 0.4966 [2021-03-27 05:28:15 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 670/1251] eta: 0:04:55 lr: 0.000032 loss: 2.7550 (2.7402) grad_norm: 2.9181 (3.2408) time: 0.5067 [2021-03-27 05:28:20 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 680/1251] eta: 0:04:50 lr: 0.000032 loss: 2.7662 (2.7405) grad_norm: 2.8957 (3.2548) time: 0.5133 [2021-03-27 05:28:25 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 690/1251] eta: 0:04:45 lr: 0.000032 loss: 2.9132 (2.7432) grad_norm: 3.2015 (3.2551) time: 0.5024 [2021-03-27 05:28:30 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 700/1251] eta: 0:04:40 lr: 0.000032 loss: 2.9443 (2.7447) grad_norm: 3.1216 (3.2522) time: 0.4971 [2021-03-27 05:28:35 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 710/1251] eta: 0:04:35 lr: 0.000032 loss: 2.9458 (2.7474) grad_norm: 3.0591 (3.2492) time: 0.4967 [2021-03-27 05:28:40 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 720/1251] eta: 0:04:30 lr: 0.000032 loss: 2.8428 (2.7444) grad_norm: 2.9623 (3.2441) time: 0.4979 [2021-03-27 05:28:45 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 730/1251] eta: 0:04:25 lr: 0.000032 loss: 2.6001 (2.7446) grad_norm: 3.0408 (3.2462) time: 0.5076 [2021-03-27 05:28:50 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 740/1251] eta: 0:04:19 lr: 0.000032 loss: 2.7220 (2.7424) grad_norm: 3.0748 (3.2441) time: 0.5117 [2021-03-27 05:28:55 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 750/1251] eta: 0:04:14 lr: 0.000032 loss: 2.5506 (2.7398) grad_norm: 3.0667 (3.2433) time: 0.5106 [2021-03-27 05:29:00 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 760/1251] eta: 0:04:09 lr: 0.000032 loss: 2.5968 (2.7398) grad_norm: 3.1142 (3.2410) time: 0.5036 [2021-03-27 05:29:05 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 770/1251] eta: 0:04:04 lr: 0.000032 loss: 2.6783 (2.7410) grad_norm: 2.9964 (3.2413) time: 0.5035 [2021-03-27 05:29:10 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 780/1251] eta: 0:03:59 lr: 0.000032 loss: 2.8396 (2.7401) grad_norm: 3.0251 (3.2423) time: 0.5053 [2021-03-27 05:29:15 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 790/1251] eta: 0:03:54 lr: 0.000032 loss: 2.6626 (2.7380) grad_norm: 3.0884 (3.2412) time: 0.5014 [2021-03-27 05:29:20 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 800/1251] eta: 0:03:49 lr: 0.000032 loss: 2.8244 (2.7376) grad_norm: 3.1130 (3.2422) time: 0.5013 [2021-03-27 05:29:25 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 810/1251] eta: 0:03:44 lr: 0.000032 loss: 2.6632 (2.7346) grad_norm: 3.1130 (3.2459) time: 0.5031 [2021-03-27 05:29:30 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 820/1251] eta: 0:03:39 lr: 0.000032 loss: 2.8843 (2.7390) grad_norm: 3.0602 (3.2438) time: 0.5047 [2021-03-27 05:29:35 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 830/1251] eta: 0:03:33 lr: 0.000032 loss: 2.9866 (2.7394) grad_norm: 3.1068 (3.2489) time: 0.5035 [2021-03-27 05:29:40 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 840/1251] eta: 0:03:28 lr: 0.000032 loss: 2.8885 (2.7401) grad_norm: 3.0902 (3.2473) time: 0.4998 [2021-03-27 05:29:45 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 850/1251] eta: 0:03:23 lr: 0.000032 loss: 2.7648 (2.7405) grad_norm: 3.1552 (3.2492) time: 0.4968 [2021-03-27 05:29:50 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 860/1251] eta: 0:03:18 lr: 0.000032 loss: 2.6700 (2.7385) grad_norm: 3.1552 (3.2493) time: 0.5009 [2021-03-27 05:29:55 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 870/1251] eta: 0:03:13 lr: 0.000032 loss: 2.6516 (2.7353) grad_norm: 3.1174 (3.2481) time: 0.4984 [2021-03-27 05:30:00 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 880/1251] eta: 0:03:08 lr: 0.000032 loss: 2.4983 (2.7324) grad_norm: 3.1312 (3.2505) time: 0.5022 [2021-03-27 05:30:05 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 890/1251] eta: 0:03:03 lr: 0.000032 loss: 2.6424 (2.7337) grad_norm: 3.1228 (3.2494) time: 0.5028 [2021-03-27 05:30:10 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 900/1251] eta: 0:02:58 lr: 0.000032 loss: 2.8564 (2.7354) grad_norm: 3.0210 (3.2470) time: 0.4933 [2021-03-27 05:30:15 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 910/1251] eta: 0:02:53 lr: 0.000032 loss: 2.7830 (2.7325) grad_norm: 2.9421 (3.2446) time: 0.4970 [2021-03-27 05:30:20 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 920/1251] eta: 0:02:47 lr: 0.000032 loss: 2.7830 (2.7331) grad_norm: 3.0635 (3.2436) time: 0.5123 [2021-03-27 05:30:26 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 930/1251] eta: 0:02:42 lr: 0.000032 loss: 2.6348 (2.7304) grad_norm: 3.1010 (3.2427) time: 0.5140 [2021-03-27 05:30:31 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 940/1251] eta: 0:02:37 lr: 0.000032 loss: 2.5863 (2.7297) grad_norm: 3.1010 (3.2501) time: 0.5043 [2021-03-27 05:30:36 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 950/1251] eta: 0:02:32 lr: 0.000031 loss: 2.8398 (2.7317) grad_norm: 3.0632 (3.2492) time: 0.5026 [2021-03-27 05:30:41 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 960/1251] eta: 0:02:27 lr: 0.000031 loss: 2.9003 (2.7302) grad_norm: 2.9106 (3.2478) time: 0.5045 [2021-03-27 05:30:46 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 970/1251] eta: 0:02:22 lr: 0.000031 loss: 2.8242 (2.7320) grad_norm: 2.8854 (3.2452) time: 0.5134 [2021-03-27 05:30:51 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 980/1251] eta: 0:02:17 lr: 0.000031 loss: 2.8445 (2.7315) grad_norm: 2.8856 (3.2435) time: 0.5137 [2021-03-27 05:30:56 swin_small_patch4_window7_224] INFO: Epoch: [271] [ 990/1251] eta: 0:02:12 lr: 0.000031 loss: 2.6625 (2.7293) grad_norm: 2.8572 (3.2404) time: 0.5015 [2021-03-27 05:31:01 swin_small_patch4_window7_224] INFO: Epoch: [271] [1000/1251] eta: 0:02:07 lr: 0.000031 loss: 2.4378 (2.7261) grad_norm: 2.9930 (3.2406) time: 0.4979 [2021-03-27 05:31:06 swin_small_patch4_window7_224] INFO: Epoch: [271] [1010/1251] eta: 0:02:02 lr: 0.000031 loss: 2.5393 (2.7268) grad_norm: 3.0606 (3.2387) time: 0.5030 [2021-03-27 05:31:11 swin_small_patch4_window7_224] INFO: Epoch: [271] [1020/1251] eta: 0:01:57 lr: 0.000031 loss: 2.7643 (2.7249) grad_norm: 2.8897 (3.2360) time: 0.5085 [2021-03-27 05:31:16 swin_small_patch4_window7_224] INFO: Epoch: [271] [1030/1251] eta: 0:01:52 lr: 0.000031 loss: 2.4618 (2.7223) grad_norm: 2.8446 (3.2347) time: 0.5062 [2021-03-27 05:31:21 swin_small_patch4_window7_224] INFO: Epoch: [271] [1040/1251] eta: 0:01:47 lr: 0.000031 loss: 2.6332 (2.7219) grad_norm: 2.9544 (3.2328) time: 0.5003 [2021-03-27 05:31:26 swin_small_patch4_window7_224] INFO: Epoch: [271] [1050/1251] eta: 0:01:41 lr: 0.000031 loss: 2.8446 (2.7228) grad_norm: 3.0275 (3.2323) time: 0.5074 [2021-03-27 05:31:31 swin_small_patch4_window7_224] INFO: Epoch: [271] [1060/1251] eta: 0:01:36 lr: 0.000031 loss: 2.8479 (2.7219) grad_norm: 3.1072 (3.2327) time: 0.5058 [2021-03-27 05:31:36 swin_small_patch4_window7_224] INFO: Epoch: [271] [1070/1251] eta: 0:01:31 lr: 0.000031 loss: 2.7772 (2.7214) grad_norm: 2.9915 (3.2304) time: 0.5010 [2021-03-27 05:31:41 swin_small_patch4_window7_224] INFO: Epoch: [271] [1080/1251] eta: 0:01:26 lr: 0.000031 loss: 2.8250 (2.7217) grad_norm: 2.9736 (3.2282) time: 0.5031 [2021-03-27 05:31:46 swin_small_patch4_window7_224] INFO: Epoch: [271] [1090/1251] eta: 0:01:21 lr: 0.000031 loss: 2.8412 (2.7222) grad_norm: 3.0952 (3.2268) time: 0.5002 [2021-03-27 05:31:51 swin_small_patch4_window7_224] INFO: Epoch: [271] [1100/1251] eta: 0:01:16 lr: 0.000031 loss: 2.9075 (2.7241) grad_norm: 2.8973 (3.2240) time: 0.4991 [2021-03-27 05:31:56 swin_small_patch4_window7_224] INFO: Epoch: [271] [1110/1251] eta: 0:01:11 lr: 0.000031 loss: 2.7670 (2.7234) grad_norm: 2.7857 (3.2219) time: 0.5017 [2021-03-27 05:32:01 swin_small_patch4_window7_224] INFO: Epoch: [271] [1120/1251] eta: 0:01:06 lr: 0.000031 loss: 2.7400 (2.7224) grad_norm: 2.8701 (3.2211) time: 0.5003 [2021-03-27 05:32:06 swin_small_patch4_window7_224] INFO: Epoch: [271] [1130/1251] eta: 0:01:01 lr: 0.000031 loss: 2.7773 (2.7238) grad_norm: 2.9658 (3.2186) time: 0.4978 [2021-03-27 05:32:11 swin_small_patch4_window7_224] INFO: Epoch: [271] [1140/1251] eta: 0:00:56 lr: 0.000031 loss: 2.9009 (2.7237) grad_norm: 3.0258 (3.2179) time: 0.4961 [2021-03-27 05:32:16 swin_small_patch4_window7_224] INFO: Epoch: [271] [1150/1251] eta: 0:00:51 lr: 0.000031 loss: 2.5522 (2.7212) grad_norm: 3.0547 (3.2180) time: 0.4966 [2021-03-27 05:32:21 swin_small_patch4_window7_224] INFO: Epoch: [271] [1160/1251] eta: 0:00:46 lr: 0.000031 loss: 2.4981 (2.7198) grad_norm: 3.0018 (3.2172) time: 0.5050 [2021-03-27 05:32:26 swin_small_patch4_window7_224] INFO: Epoch: [271] [1170/1251] eta: 0:00:41 lr: 0.000031 loss: 2.8770 (2.7209) grad_norm: 2.8519 (3.2156) time: 0.5076 [2021-03-27 05:32:31 swin_small_patch4_window7_224] INFO: Epoch: [271] [1180/1251] eta: 0:00:35 lr: 0.000031 loss: 2.7989 (2.7197) grad_norm: 2.9263 (3.2157) time: 0.5010 [2021-03-27 05:32:36 swin_small_patch4_window7_224] INFO: Epoch: [271] [1190/1251] eta: 0:00:30 lr: 0.000031 loss: 2.7735 (2.7204) grad_norm: 2.9858 (3.2151) time: 0.4964 [2021-03-27 05:32:41 swin_small_patch4_window7_224] INFO: Epoch: [271] [1200/1251] eta: 0:00:25 lr: 0.000031 loss: 2.8853 (2.7211) grad_norm: 2.9618 (3.2169) time: 0.4988 [2021-03-27 05:32:46 swin_small_patch4_window7_224] INFO: Epoch: [271] [1210/1251] eta: 0:00:20 lr: 0.000031 loss: 2.7934 (2.7198) grad_norm: 2.9490 (3.2145) time: 0.4976 [2021-03-27 05:32:51 swin_small_patch4_window7_224] INFO: Epoch: [271] [1220/1251] eta: 0:00:15 lr: 0.000031 loss: 2.8182 (2.7212) grad_norm: 2.9490 (3.2135) time: 0.4948 [2021-03-27 05:32:56 swin_small_patch4_window7_224] INFO: Epoch: [271] [1230/1251] eta: 0:00:10 lr: 0.000031 loss: 2.8543 (2.7211) grad_norm: 3.0046 (3.2126) time: 0.4971 [2021-03-27 05:33:01 swin_small_patch4_window7_224] INFO: Epoch: [271] [1240/1251] eta: 0:00:05 lr: 0.000031 loss: 2.5721 (2.7184) grad_norm: 3.0977 (3.2144) time: 0.4987 [2021-03-27 05:33:06 swin_small_patch4_window7_224] INFO: Epoch: [271] [1250/1251] eta: 0:00:00 lr: 0.000031 loss: 2.7546 (2.7193) grad_norm: 3.0977 (3.2133) time: 0.4983 [2021-03-27 05:33:21 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.7464 (0.7464) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 05:33:23 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7168 (0.7087) acc1: 82.8125 (82.9545) acc5: 96.8750 (96.4489) [2021-03-27 05:33:26 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7168 (0.7485) acc1: 81.2500 (82.1429) acc5: 95.3125 (96.0565) [2021-03-27 05:33:29 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7638 (0.7494) acc1: 79.6875 (81.8548) acc5: 95.3125 (96.0685) [2021-03-27 05:33:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7346 (0.7508) acc1: 81.2500 (82.0122) acc5: 95.3125 (96.0747) [2021-03-27 05:33:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7346 (0.7610) acc1: 81.2500 (81.8240) acc5: 96.8750 (96.0320) [2021-03-27 05:33:45 swin_small_patch4_window7_224] INFO: * Acc@1 82.744 Acc@5 96.186 loss 0.746 [2021-03-27 05:33:45 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.7% [2021-03-27 05:33:45 swin_small_patch4_window7_224] INFO: Max accuracy: 82.84% [2021-03-27 05:33:49 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 0/1251] eta: 1:28:31 lr: 0.000031 loss: 3.2159 (3.2159) grad_norm: 2.8121 (2.8121) time: 4.2459 [2021-03-27 05:33:55 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 10/1251] eta: 0:17:41 lr: 0.000031 loss: 2.8912 (2.8764) grad_norm: 2.9032 (3.1377) time: 0.8550 [2021-03-27 05:34:00 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 20/1251] eta: 0:14:04 lr: 0.000031 loss: 2.7824 (2.8057) grad_norm: 2.9032 (3.2871) time: 0.5079 [2021-03-27 05:34:05 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 30/1251] eta: 0:12:45 lr: 0.000031 loss: 2.6336 (2.7042) grad_norm: 2.9455 (3.2054) time: 0.5019 [2021-03-27 05:34:10 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 40/1251] eta: 0:12:08 lr: 0.000031 loss: 2.6910 (2.7441) grad_norm: 2.9990 (3.2034) time: 0.5137 [2021-03-27 05:34:15 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 50/1251] eta: 0:11:38 lr: 0.000031 loss: 2.7409 (2.6980) grad_norm: 3.0490 (3.1883) time: 0.5108 [2021-03-27 05:34:20 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 60/1251] eta: 0:11:22 lr: 0.000031 loss: 2.6321 (2.6946) grad_norm: 3.1758 (3.2692) time: 0.5142 [2021-03-27 05:34:25 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 70/1251] eta: 0:11:04 lr: 0.000031 loss: 2.6642 (2.7012) grad_norm: 3.1758 (3.2598) time: 0.5153 [2021-03-27 05:34:30 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 80/1251] eta: 0:10:51 lr: 0.000031 loss: 2.6642 (2.6953) grad_norm: 2.9317 (3.2617) time: 0.5043 [2021-03-27 05:34:35 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 90/1251] eta: 0:10:40 lr: 0.000031 loss: 2.5516 (2.6582) grad_norm: 2.9508 (3.2329) time: 0.5116 [2021-03-27 05:34:40 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 100/1251] eta: 0:10:29 lr: 0.000031 loss: 2.6596 (2.6765) grad_norm: 3.0091 (3.2121) time: 0.5115 [2021-03-27 05:34:46 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 110/1251] eta: 0:10:21 lr: 0.000031 loss: 2.9088 (2.6825) grad_norm: 2.9621 (3.1904) time: 0.5118 [2021-03-27 05:34:51 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 120/1251] eta: 0:10:12 lr: 0.000031 loss: 2.8766 (2.7087) grad_norm: 2.8813 (3.1746) time: 0.5111 [2021-03-27 05:34:56 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 130/1251] eta: 0:10:04 lr: 0.000031 loss: 3.1694 (2.7352) grad_norm: 2.8813 (3.1623) time: 0.5093 [2021-03-27 05:35:01 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 140/1251] eta: 0:09:55 lr: 0.000031 loss: 2.7945 (2.7148) grad_norm: 2.8697 (3.1462) time: 0.5047 [2021-03-27 05:35:06 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 150/1251] eta: 0:09:47 lr: 0.000031 loss: 2.5635 (2.7163) grad_norm: 2.9155 (3.1430) time: 0.4988 [2021-03-27 05:35:11 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 160/1251] eta: 0:09:40 lr: 0.000031 loss: 2.9112 (2.7195) grad_norm: 3.1210 (3.1665) time: 0.5032 [2021-03-27 05:35:16 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 170/1251] eta: 0:09:33 lr: 0.000031 loss: 2.9112 (2.7258) grad_norm: 3.1210 (3.1901) time: 0.5036 [2021-03-27 05:35:21 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 180/1251] eta: 0:09:25 lr: 0.000031 loss: 2.7244 (2.7210) grad_norm: 3.1050 (3.1824) time: 0.4989 [2021-03-27 05:35:26 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 190/1251] eta: 0:09:19 lr: 0.000031 loss: 2.6201 (2.7122) grad_norm: 3.0291 (3.1712) time: 0.5019 [2021-03-27 05:35:31 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 200/1251] eta: 0:09:13 lr: 0.000031 loss: 2.7539 (2.7114) grad_norm: 3.0291 (3.1695) time: 0.5096 [2021-03-27 05:35:36 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 210/1251] eta: 0:09:06 lr: 0.000031 loss: 2.8730 (2.7231) grad_norm: 3.2230 (3.1730) time: 0.5043 [2021-03-27 05:35:41 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 220/1251] eta: 0:09:00 lr: 0.000031 loss: 2.8902 (2.7271) grad_norm: 3.2162 (3.1785) time: 0.4981 [2021-03-27 05:35:46 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 230/1251] eta: 0:08:54 lr: 0.000031 loss: 2.8085 (2.7263) grad_norm: 3.2626 (3.2051) time: 0.5032 [2021-03-27 05:35:51 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 240/1251] eta: 0:08:48 lr: 0.000031 loss: 2.8202 (2.7361) grad_norm: 3.2762 (3.2067) time: 0.5132 [2021-03-27 05:35:56 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 250/1251] eta: 0:08:42 lr: 0.000031 loss: 2.8513 (2.7308) grad_norm: 3.0278 (3.2003) time: 0.5104 [2021-03-27 05:36:01 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 260/1251] eta: 0:08:36 lr: 0.000031 loss: 2.8513 (2.7382) grad_norm: 3.0124 (3.1952) time: 0.5024 [2021-03-27 05:36:06 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 270/1251] eta: 0:08:30 lr: 0.000031 loss: 3.0028 (2.7369) grad_norm: 3.0960 (3.1958) time: 0.4974 [2021-03-27 05:36:11 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 280/1251] eta: 0:08:24 lr: 0.000031 loss: 2.7858 (2.7379) grad_norm: 3.1309 (3.1975) time: 0.4940 [2021-03-27 05:36:16 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 290/1251] eta: 0:08:18 lr: 0.000031 loss: 2.8374 (2.7334) grad_norm: 3.2059 (3.2023) time: 0.4994 [2021-03-27 05:36:21 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 300/1251] eta: 0:08:13 lr: 0.000031 loss: 2.6575 (2.7289) grad_norm: 3.0662 (3.1943) time: 0.5098 [2021-03-27 05:36:26 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 310/1251] eta: 0:08:07 lr: 0.000031 loss: 2.7168 (2.7288) grad_norm: 2.9982 (3.1970) time: 0.5062 [2021-03-27 05:36:31 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 320/1251] eta: 0:08:01 lr: 0.000031 loss: 2.7908 (2.7305) grad_norm: 3.0336 (3.1959) time: 0.4990 [2021-03-27 05:36:36 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 330/1251] eta: 0:07:56 lr: 0.000031 loss: 2.8474 (2.7332) grad_norm: 3.0163 (3.2089) time: 0.5017 [2021-03-27 05:36:41 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 340/1251] eta: 0:07:50 lr: 0.000031 loss: 2.8652 (2.7365) grad_norm: 2.9366 (3.2208) time: 0.5014 [2021-03-27 05:36:46 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 350/1251] eta: 0:07:45 lr: 0.000031 loss: 2.9372 (2.7402) grad_norm: 2.9190 (3.2138) time: 0.4999 [2021-03-27 05:36:51 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 360/1251] eta: 0:07:39 lr: 0.000031 loss: 2.9475 (2.7465) grad_norm: 2.9821 (3.2093) time: 0.5004 [2021-03-27 05:36:56 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 370/1251] eta: 0:07:34 lr: 0.000031 loss: 2.9776 (2.7474) grad_norm: 3.0266 (3.2073) time: 0.5046 [2021-03-27 05:37:01 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 380/1251] eta: 0:07:28 lr: 0.000031 loss: 2.9752 (2.7475) grad_norm: 3.1640 (3.2264) time: 0.5025 [2021-03-27 05:37:07 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 390/1251] eta: 0:07:23 lr: 0.000031 loss: 2.5346 (2.7377) grad_norm: 2.9969 (3.2202) time: 0.5023 [2021-03-27 05:37:11 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 400/1251] eta: 0:07:17 lr: 0.000031 loss: 2.4444 (2.7339) grad_norm: 2.9381 (3.2159) time: 0.5004 [2021-03-27 05:37:16 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 410/1251] eta: 0:07:12 lr: 0.000031 loss: 2.6155 (2.7309) grad_norm: 2.9264 (3.2105) time: 0.4994 [2021-03-27 05:37:21 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 420/1251] eta: 0:07:06 lr: 0.000031 loss: 2.7034 (2.7330) grad_norm: 3.0482 (3.2083) time: 0.4985 [2021-03-27 05:37:27 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 430/1251] eta: 0:07:01 lr: 0.000031 loss: 2.7171 (2.7286) grad_norm: 3.0736 (3.2108) time: 0.5005 [2021-03-27 05:37:31 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 440/1251] eta: 0:06:56 lr: 0.000031 loss: 2.6487 (2.7276) grad_norm: 2.9875 (3.2025) time: 0.5016 [2021-03-27 05:37:36 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 450/1251] eta: 0:06:50 lr: 0.000031 loss: 2.8584 (2.7314) grad_norm: 2.9568 (3.1979) time: 0.4959 [2021-03-27 05:37:41 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 460/1251] eta: 0:06:45 lr: 0.000031 loss: 2.9245 (2.7296) grad_norm: 3.0339 (3.1947) time: 0.4983 [2021-03-27 05:37:46 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 470/1251] eta: 0:06:39 lr: 0.000031 loss: 2.7717 (2.7291) grad_norm: 2.9755 (3.1969) time: 0.5008 [2021-03-27 05:37:52 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 480/1251] eta: 0:06:34 lr: 0.000031 loss: 2.7332 (2.7289) grad_norm: 3.0584 (3.2036) time: 0.5034 [2021-03-27 05:37:57 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 490/1251] eta: 0:06:29 lr: 0.000031 loss: 2.9129 (2.7360) grad_norm: 3.1129 (3.2099) time: 0.5045 [2021-03-27 05:38:02 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 500/1251] eta: 0:06:24 lr: 0.000031 loss: 2.9129 (2.7380) grad_norm: 2.9890 (3.2123) time: 0.5048 [2021-03-27 05:38:07 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 510/1251] eta: 0:06:19 lr: 0.000031 loss: 2.8151 (2.7350) grad_norm: 3.1689 (3.2158) time: 0.5072 [2021-03-27 05:38:12 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 520/1251] eta: 0:06:13 lr: 0.000031 loss: 2.8241 (2.7343) grad_norm: 3.1015 (3.2182) time: 0.5045 [2021-03-27 05:38:17 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 530/1251] eta: 0:06:08 lr: 0.000030 loss: 2.8336 (2.7334) grad_norm: 3.1237 (3.2163) time: 0.5002 [2021-03-27 05:38:22 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 540/1251] eta: 0:06:03 lr: 0.000030 loss: 2.7603 (2.7345) grad_norm: 3.2874 (3.2208) time: 0.5049 [2021-03-27 05:38:27 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 550/1251] eta: 0:05:58 lr: 0.000030 loss: 2.6300 (2.7335) grad_norm: 3.1309 (3.2183) time: 0.5155 [2021-03-27 05:38:32 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 560/1251] eta: 0:05:53 lr: 0.000030 loss: 2.8644 (2.7340) grad_norm: 3.0433 (3.2200) time: 0.5107 [2021-03-27 05:38:37 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 570/1251] eta: 0:05:48 lr: 0.000030 loss: 2.7800 (2.7334) grad_norm: 3.3185 (3.2231) time: 0.5042 [2021-03-27 05:38:42 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 580/1251] eta: 0:05:42 lr: 0.000030 loss: 2.7392 (2.7361) grad_norm: 3.2227 (3.2236) time: 0.5053 [2021-03-27 05:38:47 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 590/1251] eta: 0:05:37 lr: 0.000030 loss: 2.7802 (2.7367) grad_norm: 3.2767 (3.2265) time: 0.5098 [2021-03-27 05:38:52 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 600/1251] eta: 0:05:32 lr: 0.000030 loss: 2.7084 (2.7338) grad_norm: 3.1378 (3.2258) time: 0.5149 [2021-03-27 05:38:57 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 610/1251] eta: 0:05:27 lr: 0.000030 loss: 2.6207 (2.7326) grad_norm: 3.1374 (3.2239) time: 0.5065 [2021-03-27 05:39:02 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 620/1251] eta: 0:05:22 lr: 0.000030 loss: 2.7238 (2.7315) grad_norm: 3.2081 (3.2396) time: 0.4989 [2021-03-27 05:39:07 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 630/1251] eta: 0:05:17 lr: 0.000030 loss: 2.8566 (2.7323) grad_norm: 3.2081 (3.2406) time: 0.5008 [2021-03-27 05:39:13 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 640/1251] eta: 0:05:11 lr: 0.000030 loss: 2.7885 (2.7329) grad_norm: 3.2159 (3.2413) time: 0.5041 [2021-03-27 05:39:18 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 650/1251] eta: 0:05:06 lr: 0.000030 loss: 2.7640 (2.7321) grad_norm: 3.1156 (3.2462) time: 0.5091 [2021-03-27 05:39:23 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 660/1251] eta: 0:05:01 lr: 0.000030 loss: 2.7640 (2.7320) grad_norm: 2.9613 (3.2415) time: 0.5134 [2021-03-27 05:39:28 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 670/1251] eta: 0:04:56 lr: 0.000030 loss: 2.7146 (2.7315) grad_norm: 2.9613 (3.2400) time: 0.5080 [2021-03-27 05:39:33 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 680/1251] eta: 0:04:51 lr: 0.000030 loss: 2.6753 (2.7304) grad_norm: 3.0390 (3.2507) time: 0.5091 [2021-03-27 05:39:38 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 690/1251] eta: 0:04:46 lr: 0.000030 loss: 2.6989 (2.7315) grad_norm: 3.0390 (3.2492) time: 0.5084 [2021-03-27 05:39:43 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 700/1251] eta: 0:04:41 lr: 0.000030 loss: 2.6997 (2.7294) grad_norm: 3.1048 (3.2492) time: 0.5002 [2021-03-27 05:39:48 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 710/1251] eta: 0:04:35 lr: 0.000030 loss: 2.5809 (2.7282) grad_norm: 3.0588 (3.2453) time: 0.5007 [2021-03-27 05:39:53 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 720/1251] eta: 0:04:30 lr: 0.000030 loss: 2.6553 (2.7311) grad_norm: 2.9291 (3.2453) time: 0.4999 [2021-03-27 05:39:58 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 730/1251] eta: 0:04:25 lr: 0.000030 loss: 2.7745 (2.7289) grad_norm: 2.8617 (3.2441) time: 0.4968 [2021-03-27 05:40:03 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 740/1251] eta: 0:04:20 lr: 0.000030 loss: 2.7745 (2.7299) grad_norm: 2.9363 (3.2428) time: 0.5039 [2021-03-27 05:40:08 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 750/1251] eta: 0:04:15 lr: 0.000030 loss: 2.7428 (2.7271) grad_norm: 3.1500 (3.2475) time: 0.5126 [2021-03-27 05:40:13 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 760/1251] eta: 0:04:10 lr: 0.000030 loss: 2.7844 (2.7275) grad_norm: 3.1597 (3.2533) time: 0.5092 [2021-03-27 05:40:18 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 770/1251] eta: 0:04:05 lr: 0.000030 loss: 2.8516 (2.7252) grad_norm: 2.9387 (3.2496) time: 0.5049 [2021-03-27 05:40:23 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 780/1251] eta: 0:04:00 lr: 0.000030 loss: 2.7507 (2.7252) grad_norm: 2.9686 (3.2467) time: 0.5054 [2021-03-27 05:40:28 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 790/1251] eta: 0:03:54 lr: 0.000030 loss: 2.6772 (2.7239) grad_norm: 2.8936 (3.2417) time: 0.5099 [2021-03-27 05:40:34 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 800/1251] eta: 0:03:49 lr: 0.000030 loss: 2.4889 (2.7222) grad_norm: 2.8544 (3.2377) time: 0.5182 [2021-03-27 05:40:39 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 810/1251] eta: 0:03:44 lr: 0.000030 loss: 2.5565 (2.7193) grad_norm: 2.9459 (3.2372) time: 0.5144 [2021-03-27 05:40:44 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 820/1251] eta: 0:03:39 lr: 0.000030 loss: 2.7329 (2.7177) grad_norm: 3.0091 (3.2355) time: 0.5037 [2021-03-27 05:40:49 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 830/1251] eta: 0:03:34 lr: 0.000030 loss: 2.8779 (2.7194) grad_norm: 3.0091 (3.2357) time: 0.5061 [2021-03-27 05:40:54 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 840/1251] eta: 0:03:29 lr: 0.000030 loss: 2.7319 (2.7187) grad_norm: 3.1365 (3.2339) time: 0.5076 [2021-03-27 05:40:59 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 850/1251] eta: 0:03:24 lr: 0.000030 loss: 2.6435 (2.7192) grad_norm: 3.1203 (3.2363) time: 0.5150 [2021-03-27 05:41:04 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 860/1251] eta: 0:03:19 lr: 0.000030 loss: 2.7928 (2.7210) grad_norm: 3.1203 (3.2374) time: 0.5148 [2021-03-27 05:41:09 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 870/1251] eta: 0:03:14 lr: 0.000030 loss: 2.9026 (2.7220) grad_norm: 3.0215 (3.2370) time: 0.5113 [2021-03-27 05:41:14 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 880/1251] eta: 0:03:09 lr: 0.000030 loss: 2.8498 (2.7227) grad_norm: 2.8383 (3.2321) time: 0.5086 [2021-03-27 05:41:19 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 890/1251] eta: 0:03:03 lr: 0.000030 loss: 2.6830 (2.7184) grad_norm: 2.7505 (3.2287) time: 0.4994 [2021-03-27 05:41:24 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 900/1251] eta: 0:02:58 lr: 0.000030 loss: 2.5361 (2.7179) grad_norm: 2.8590 (3.2259) time: 0.4990 [2021-03-27 05:41:29 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 910/1251] eta: 0:02:53 lr: 0.000030 loss: 2.9571 (2.7205) grad_norm: 2.8479 (3.2221) time: 0.4954 [2021-03-27 05:41:34 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 920/1251] eta: 0:02:48 lr: 0.000030 loss: 2.8037 (2.7196) grad_norm: 2.9080 (3.2222) time: 0.4934 [2021-03-27 05:41:39 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 930/1251] eta: 0:02:43 lr: 0.000030 loss: 2.6945 (2.7198) grad_norm: 3.0893 (3.2211) time: 0.4971 [2021-03-27 05:41:44 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 940/1251] eta: 0:02:38 lr: 0.000030 loss: 2.7642 (2.7211) grad_norm: 3.0079 (3.2194) time: 0.5041 [2021-03-27 05:41:49 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 950/1251] eta: 0:02:33 lr: 0.000030 loss: 3.0112 (2.7232) grad_norm: 2.9624 (3.2203) time: 0.5100 [2021-03-27 05:41:54 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 960/1251] eta: 0:02:28 lr: 0.000030 loss: 2.9176 (2.7227) grad_norm: 2.9455 (3.2185) time: 0.5011 [2021-03-27 05:41:59 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 970/1251] eta: 0:02:22 lr: 0.000030 loss: 2.6336 (2.7209) grad_norm: 2.8192 (3.2152) time: 0.4974 [2021-03-27 05:42:05 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 980/1251] eta: 0:02:17 lr: 0.000030 loss: 2.7494 (2.7225) grad_norm: 2.8673 (3.2148) time: 0.5086 [2021-03-27 05:42:10 swin_small_patch4_window7_224] INFO: Epoch: [272] [ 990/1251] eta: 0:02:12 lr: 0.000030 loss: 2.8103 (2.7222) grad_norm: 2.9801 (3.2155) time: 0.5034 [2021-03-27 05:42:15 swin_small_patch4_window7_224] INFO: Epoch: [272] [1000/1251] eta: 0:02:07 lr: 0.000030 loss: 2.8379 (2.7220) grad_norm: 3.1299 (3.2140) time: 0.5028 [2021-03-27 05:42:20 swin_small_patch4_window7_224] INFO: Epoch: [272] [1010/1251] eta: 0:02:02 lr: 0.000030 loss: 2.7037 (2.7211) grad_norm: 2.9320 (3.2150) time: 0.5075 [2021-03-27 05:42:25 swin_small_patch4_window7_224] INFO: Epoch: [272] [1020/1251] eta: 0:01:57 lr: 0.000030 loss: 2.8106 (2.7218) grad_norm: 2.8956 (3.2131) time: 0.5027 [2021-03-27 05:42:30 swin_small_patch4_window7_224] INFO: Epoch: [272] [1030/1251] eta: 0:01:52 lr: 0.000030 loss: 2.8106 (2.7209) grad_norm: 2.9288 (3.2114) time: 0.5003 [2021-03-27 05:42:35 swin_small_patch4_window7_224] INFO: Epoch: [272] [1040/1251] eta: 0:01:47 lr: 0.000030 loss: 2.7901 (2.7221) grad_norm: 2.9603 (3.2109) time: 0.4998 [2021-03-27 05:42:40 swin_small_patch4_window7_224] INFO: Epoch: [272] [1050/1251] eta: 0:01:42 lr: 0.000030 loss: 2.9115 (2.7222) grad_norm: 2.9531 (3.2083) time: 0.5004 [2021-03-27 05:42:45 swin_small_patch4_window7_224] INFO: Epoch: [272] [1060/1251] eta: 0:01:37 lr: 0.000030 loss: 2.5598 (2.7205) grad_norm: 2.8615 (3.2057) time: 0.4960 [2021-03-27 05:42:50 swin_small_patch4_window7_224] INFO: Epoch: [272] [1070/1251] eta: 0:01:31 lr: 0.000030 loss: 2.4841 (2.7195) grad_norm: 2.8615 (3.2044) time: 0.4953 [2021-03-27 05:42:55 swin_small_patch4_window7_224] INFO: Epoch: [272] [1080/1251] eta: 0:01:26 lr: 0.000030 loss: 2.7164 (2.7219) grad_norm: 3.0775 (3.2036) time: 0.4967 [2021-03-27 05:43:00 swin_small_patch4_window7_224] INFO: Epoch: [272] [1090/1251] eta: 0:01:21 lr: 0.000030 loss: 2.7164 (2.7218) grad_norm: 3.1302 (3.2064) time: 0.4964 [2021-03-27 05:43:04 swin_small_patch4_window7_224] INFO: Epoch: [272] [1100/1251] eta: 0:01:16 lr: 0.000030 loss: 2.7147 (2.7215) grad_norm: 3.2835 (3.2075) time: 0.4967 [2021-03-27 05:43:09 swin_small_patch4_window7_224] INFO: Epoch: [272] [1110/1251] eta: 0:01:11 lr: 0.000030 loss: 2.8927 (2.7227) grad_norm: 3.1297 (3.2082) time: 0.4963 [2021-03-27 05:43:14 swin_small_patch4_window7_224] INFO: Epoch: [272] [1120/1251] eta: 0:01:06 lr: 0.000030 loss: 2.9146 (2.7243) grad_norm: 2.9856 (3.2059) time: 0.4992 [2021-03-27 05:43:19 swin_small_patch4_window7_224] INFO: Epoch: [272] [1130/1251] eta: 0:01:01 lr: 0.000030 loss: 2.7318 (2.7233) grad_norm: 2.8839 (3.2038) time: 0.5013 [2021-03-27 05:43:24 swin_small_patch4_window7_224] INFO: Epoch: [272] [1140/1251] eta: 0:00:56 lr: 0.000030 loss: 2.5961 (2.7221) grad_norm: 3.0139 (3.2044) time: 0.5012 [2021-03-27 05:43:29 swin_small_patch4_window7_224] INFO: Epoch: [272] [1150/1251] eta: 0:00:51 lr: 0.000030 loss: 2.3046 (2.7201) grad_norm: 3.0084 (3.2030) time: 0.4979 [2021-03-27 05:43:34 swin_small_patch4_window7_224] INFO: Epoch: [272] [1160/1251] eta: 0:00:46 lr: 0.000030 loss: 2.7175 (2.7197) grad_norm: 2.9380 (3.2054) time: 0.4956 [2021-03-27 05:43:39 swin_small_patch4_window7_224] INFO: Epoch: [272] [1170/1251] eta: 0:00:41 lr: 0.000030 loss: 2.7101 (2.7198) grad_norm: 3.0562 (3.2077) time: 0.5010 [2021-03-27 05:43:45 swin_small_patch4_window7_224] INFO: Epoch: [272] [1180/1251] eta: 0:00:36 lr: 0.000030 loss: 2.6823 (2.7195) grad_norm: 3.0447 (3.2067) time: 0.5054 [2021-03-27 05:43:50 swin_small_patch4_window7_224] INFO: Epoch: [272] [1190/1251] eta: 0:00:30 lr: 0.000030 loss: 2.7735 (2.7200) grad_norm: 2.9176 (3.2050) time: 0.5033 [2021-03-27 05:43:55 swin_small_patch4_window7_224] INFO: Epoch: [272] [1200/1251] eta: 0:00:25 lr: 0.000030 loss: 2.7989 (2.7189) grad_norm: 3.0924 (3.2069) time: 0.5051 [2021-03-27 05:44:00 swin_small_patch4_window7_224] INFO: Epoch: [272] [1210/1251] eta: 0:00:20 lr: 0.000030 loss: 2.5700 (2.7169) grad_norm: 3.0924 (3.2055) time: 0.5080 [2021-03-27 05:44:05 swin_small_patch4_window7_224] INFO: Epoch: [272] [1220/1251] eta: 0:00:15 lr: 0.000030 loss: 2.6767 (2.7175) grad_norm: 2.9507 (3.2044) time: 0.4995 [2021-03-27 05:44:10 swin_small_patch4_window7_224] INFO: Epoch: [272] [1230/1251] eta: 0:00:10 lr: 0.000030 loss: 2.7076 (2.7160) grad_norm: 3.0654 (3.2047) time: 0.4958 [2021-03-27 05:44:15 swin_small_patch4_window7_224] INFO: Epoch: [272] [1240/1251] eta: 0:00:05 lr: 0.000030 loss: 2.5421 (2.7164) grad_norm: 3.0693 (3.2039) time: 0.5030 [2021-03-27 05:44:20 swin_small_patch4_window7_224] INFO: Epoch: [272] [1250/1251] eta: 0:00:00 lr: 0.000030 loss: 2.8373 (2.7168) grad_norm: 2.9907 (3.2033) time: 0.5018 [2021-03-27 05:44:35 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:33 loss: 0.7613 (0.7613) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-27 05:44:38 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7613 (0.8047) acc1: 81.2500 (81.9602) acc5: 96.8750 (95.5966) [2021-03-27 05:44:40 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7370 (0.7831) acc1: 81.2500 (82.1429) acc5: 96.8750 (95.9821) [2021-03-27 05:44:42 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7290 (0.7441) acc1: 81.2500 (82.3085) acc5: 96.8750 (96.5726) [2021-03-27 05:44:44 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7634 (0.7579) acc1: 81.2500 (81.7454) acc5: 96.8750 (96.3034) [2021-03-27 05:44:45 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7311 (0.7509) acc1: 81.2500 (81.8560) acc5: 95.3125 (96.1920) [2021-03-27 05:45:00 swin_small_patch4_window7_224] INFO: * Acc@1 82.860 Acc@5 96.164 loss 0.733 [2021-03-27 05:45:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-27 05:45:00 swin_small_patch4_window7_224] INFO: Max accuracy: 82.86% [2021-03-27 05:45:05 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 0/1251] eta: 1:43:09 lr: 0.000030 loss: 3.0361 (3.0361) grad_norm: 2.4294 (2.4294) time: 4.9477 [2021-03-27 05:45:10 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 10/1251] eta: 0:18:48 lr: 0.000030 loss: 2.7267 (2.6007) grad_norm: 3.0152 (2.9651) time: 0.9093 [2021-03-27 05:45:15 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 20/1251] eta: 0:14:55 lr: 0.000030 loss: 2.7119 (2.6456) grad_norm: 3.0783 (3.4550) time: 0.5168 [2021-03-27 05:45:20 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 30/1251] eta: 0:13:19 lr: 0.000030 loss: 2.8203 (2.7003) grad_norm: 3.2891 (3.4796) time: 0.5151 [2021-03-27 05:45:25 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 40/1251] eta: 0:12:27 lr: 0.000030 loss: 2.9134 (2.6789) grad_norm: 3.0481 (3.3426) time: 0.5021 [2021-03-27 05:45:30 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 50/1251] eta: 0:11:53 lr: 0.000030 loss: 2.4996 (2.6444) grad_norm: 2.8609 (3.3424) time: 0.5007 [2021-03-27 05:45:35 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 60/1251] eta: 0:11:30 lr: 0.000030 loss: 2.7086 (2.6740) grad_norm: 2.8454 (3.3358) time: 0.5028 [2021-03-27 05:45:40 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 70/1251] eta: 0:11:12 lr: 0.000030 loss: 2.7889 (2.6769) grad_norm: 2.8454 (3.2889) time: 0.5054 [2021-03-27 05:45:45 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 80/1251] eta: 0:10:56 lr: 0.000030 loss: 2.7889 (2.6849) grad_norm: 2.9586 (3.2637) time: 0.5017 [2021-03-27 05:45:50 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 90/1251] eta: 0:10:42 lr: 0.000030 loss: 2.7863 (2.6947) grad_norm: 3.0368 (3.2794) time: 0.4978 [2021-03-27 05:45:55 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 100/1251] eta: 0:10:31 lr: 0.000030 loss: 2.7564 (2.6747) grad_norm: 3.0368 (3.2461) time: 0.4996 [2021-03-27 05:46:00 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 110/1251] eta: 0:10:20 lr: 0.000030 loss: 2.6809 (2.6707) grad_norm: 2.8684 (3.2303) time: 0.4992 [2021-03-27 05:46:05 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 120/1251] eta: 0:10:11 lr: 0.000030 loss: 2.7724 (2.6934) grad_norm: 2.9422 (3.2216) time: 0.4988 [2021-03-27 05:46:10 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 130/1251] eta: 0:10:02 lr: 0.000030 loss: 2.6009 (2.6724) grad_norm: 2.7460 (3.1900) time: 0.5028 [2021-03-27 05:46:15 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 140/1251] eta: 0:09:55 lr: 0.000029 loss: 2.4499 (2.6810) grad_norm: 2.8792 (3.1939) time: 0.5081 [2021-03-27 05:46:21 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 150/1251] eta: 0:09:47 lr: 0.000029 loss: 2.9700 (2.7004) grad_norm: 2.9945 (3.1805) time: 0.5082 [2021-03-27 05:46:26 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 160/1251] eta: 0:09:39 lr: 0.000029 loss: 2.8485 (2.6867) grad_norm: 2.8659 (3.1648) time: 0.5013 [2021-03-27 05:46:31 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 170/1251] eta: 0:09:32 lr: 0.000029 loss: 2.5743 (2.6893) grad_norm: 2.9872 (3.1856) time: 0.5024 [2021-03-27 05:46:36 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 180/1251] eta: 0:09:25 lr: 0.000029 loss: 2.4436 (2.6732) grad_norm: 3.2504 (3.1778) time: 0.5028 [2021-03-27 05:46:41 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 190/1251] eta: 0:09:19 lr: 0.000029 loss: 2.4436 (2.6731) grad_norm: 3.2030 (3.1873) time: 0.5028 [2021-03-27 05:46:46 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 200/1251] eta: 0:09:13 lr: 0.000029 loss: 2.9405 (2.6815) grad_norm: 3.1746 (3.1909) time: 0.5089 [2021-03-27 05:46:51 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 210/1251] eta: 0:09:06 lr: 0.000029 loss: 2.9912 (2.6918) grad_norm: 3.1312 (3.1885) time: 0.5009 [2021-03-27 05:46:56 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 220/1251] eta: 0:09:00 lr: 0.000029 loss: 2.8546 (2.6890) grad_norm: 3.1312 (3.1994) time: 0.4977 [2021-03-27 05:47:01 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 230/1251] eta: 0:08:54 lr: 0.000029 loss: 2.7462 (2.6851) grad_norm: 3.0021 (3.1884) time: 0.5104 [2021-03-27 05:47:06 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 240/1251] eta: 0:08:48 lr: 0.000029 loss: 2.8028 (2.6885) grad_norm: 2.9852 (3.2138) time: 0.5076 [2021-03-27 05:47:11 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 250/1251] eta: 0:08:42 lr: 0.000029 loss: 2.8028 (2.6843) grad_norm: 3.0869 (3.2158) time: 0.4996 [2021-03-27 05:47:16 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 260/1251] eta: 0:08:36 lr: 0.000029 loss: 2.8222 (2.6890) grad_norm: 3.0402 (3.2127) time: 0.5008 [2021-03-27 05:47:21 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 270/1251] eta: 0:08:30 lr: 0.000029 loss: 2.9177 (2.6980) grad_norm: 3.0654 (3.2141) time: 0.5039 [2021-03-27 05:47:26 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 280/1251] eta: 0:08:24 lr: 0.000029 loss: 2.8505 (2.6954) grad_norm: 3.2842 (3.2204) time: 0.5061 [2021-03-27 05:47:31 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 290/1251] eta: 0:08:18 lr: 0.000029 loss: 2.8033 (2.6942) grad_norm: 3.1583 (3.2240) time: 0.5037 [2021-03-27 05:47:36 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 300/1251] eta: 0:08:13 lr: 0.000029 loss: 2.8033 (2.6928) grad_norm: 3.0984 (3.2198) time: 0.5015 [2021-03-27 05:47:41 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 310/1251] eta: 0:08:07 lr: 0.000029 loss: 2.8411 (2.6984) grad_norm: 3.1789 (3.2239) time: 0.4990 [2021-03-27 05:47:46 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 320/1251] eta: 0:08:01 lr: 0.000029 loss: 2.8411 (2.7012) grad_norm: 3.2979 (3.2282) time: 0.5029 [2021-03-27 05:47:51 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 330/1251] eta: 0:07:56 lr: 0.000029 loss: 2.9020 (2.7020) grad_norm: 3.2812 (3.2265) time: 0.5051 [2021-03-27 05:47:56 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 340/1251] eta: 0:07:50 lr: 0.000029 loss: 2.8263 (2.7036) grad_norm: 3.1078 (3.2222) time: 0.4998 [2021-03-27 05:48:01 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 350/1251] eta: 0:07:44 lr: 0.000029 loss: 2.7709 (2.7049) grad_norm: 3.0273 (3.2186) time: 0.4964 [2021-03-27 05:48:06 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 360/1251] eta: 0:07:39 lr: 0.000029 loss: 2.6308 (2.7007) grad_norm: 3.1406 (3.2276) time: 0.5057 [2021-03-27 05:48:11 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 370/1251] eta: 0:07:34 lr: 0.000029 loss: 2.6802 (2.6974) grad_norm: 3.1669 (3.2282) time: 0.5079 [2021-03-27 05:48:16 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 380/1251] eta: 0:07:28 lr: 0.000029 loss: 2.7283 (2.6955) grad_norm: 3.1074 (3.2364) time: 0.5063 [2021-03-27 05:48:21 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 390/1251] eta: 0:07:23 lr: 0.000029 loss: 2.7650 (2.7001) grad_norm: 3.0930 (3.2388) time: 0.5045 [2021-03-27 05:48:26 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 400/1251] eta: 0:07:18 lr: 0.000029 loss: 2.8633 (2.7026) grad_norm: 3.0273 (3.2504) time: 0.5028 [2021-03-27 05:48:31 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 410/1251] eta: 0:07:12 lr: 0.000029 loss: 2.7879 (2.7015) grad_norm: 3.0705 (3.2567) time: 0.5030 [2021-03-27 05:48:36 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 420/1251] eta: 0:07:07 lr: 0.000029 loss: 2.6624 (2.6976) grad_norm: 3.1816 (3.2628) time: 0.4951 [2021-03-27 05:48:41 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 430/1251] eta: 0:07:01 lr: 0.000029 loss: 2.6522 (2.6984) grad_norm: 3.3028 (3.2663) time: 0.5040 [2021-03-27 05:48:47 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 440/1251] eta: 0:06:56 lr: 0.000029 loss: 2.7156 (2.7007) grad_norm: 3.2104 (3.2610) time: 0.5089 [2021-03-27 05:48:51 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 450/1251] eta: 0:06:51 lr: 0.000029 loss: 2.7366 (2.7004) grad_norm: 2.9570 (3.2595) time: 0.4991 [2021-03-27 05:48:56 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 460/1251] eta: 0:06:45 lr: 0.000029 loss: 2.7691 (2.7019) grad_norm: 3.0394 (3.2559) time: 0.4952 [2021-03-27 05:49:01 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 470/1251] eta: 0:06:40 lr: 0.000029 loss: 2.8441 (2.7036) grad_norm: 3.0394 (3.2523) time: 0.5002 [2021-03-27 05:49:06 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 480/1251] eta: 0:06:35 lr: 0.000029 loss: 2.9636 (2.7048) grad_norm: 3.1198 (3.2652) time: 0.5021 [2021-03-27 05:49:12 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 490/1251] eta: 0:06:29 lr: 0.000029 loss: 2.8157 (2.7041) grad_norm: 3.4494 (3.2737) time: 0.5060 [2021-03-27 05:49:17 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 500/1251] eta: 0:06:24 lr: 0.000029 loss: 2.7472 (2.7054) grad_norm: 3.0695 (3.2697) time: 0.5119 [2021-03-27 05:49:22 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 510/1251] eta: 0:06:19 lr: 0.000029 loss: 2.8265 (2.7105) grad_norm: 3.0785 (3.2711) time: 0.5048 [2021-03-27 05:49:27 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 520/1251] eta: 0:06:14 lr: 0.000029 loss: 3.0545 (2.7129) grad_norm: 3.0734 (3.2768) time: 0.4995 [2021-03-27 05:49:32 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 530/1251] eta: 0:06:08 lr: 0.000029 loss: 2.8618 (2.7110) grad_norm: 3.0734 (inf) time: 0.4980 [2021-03-27 05:49:37 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 540/1251] eta: 0:06:03 lr: 0.000029 loss: 2.7678 (2.7104) grad_norm: 3.4447 (inf) time: 0.5005 [2021-03-27 05:49:42 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 550/1251] eta: 0:05:58 lr: 0.000029 loss: 2.7936 (2.7098) grad_norm: 3.4512 (inf) time: 0.5165 [2021-03-27 05:49:47 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 560/1251] eta: 0:05:53 lr: 0.000029 loss: 2.7936 (2.7135) grad_norm: 3.3245 (inf) time: 0.5142 [2021-03-27 05:49:52 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 570/1251] eta: 0:05:48 lr: 0.000029 loss: 2.5647 (2.7093) grad_norm: 3.0670 (inf) time: 0.5076 [2021-03-27 05:49:57 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 580/1251] eta: 0:05:43 lr: 0.000029 loss: 2.6050 (2.7095) grad_norm: 3.0520 (inf) time: 0.5079 [2021-03-27 05:50:02 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 590/1251] eta: 0:05:37 lr: 0.000029 loss: 2.6836 (2.7104) grad_norm: 3.2282 (inf) time: 0.5009 [2021-03-27 05:50:07 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 600/1251] eta: 0:05:32 lr: 0.000029 loss: 2.5860 (2.7075) grad_norm: 3.1682 (nan) time: 0.4991 [2021-03-27 05:50:12 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 610/1251] eta: 0:05:27 lr: 0.000029 loss: 2.6907 (2.7103) grad_norm: 2.9306 (nan) time: 0.5047 [2021-03-27 05:50:17 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 620/1251] eta: 0:05:22 lr: 0.000029 loss: 2.8060 (2.7091) grad_norm: 2.8939 (nan) time: 0.5016 [2021-03-27 05:50:22 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 630/1251] eta: 0:05:17 lr: 0.000029 loss: 2.5607 (2.7074) grad_norm: 2.9987 (nan) time: 0.4997 [2021-03-27 05:50:27 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 640/1251] eta: 0:05:11 lr: 0.000029 loss: 2.7332 (2.7081) grad_norm: 3.0160 (nan) time: 0.4998 [2021-03-27 05:50:32 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 650/1251] eta: 0:05:06 lr: 0.000029 loss: 2.9252 (2.7101) grad_norm: 3.0160 (nan) time: 0.5006 [2021-03-27 05:50:37 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 660/1251] eta: 0:05:01 lr: 0.000029 loss: 2.7743 (2.7091) grad_norm: 3.0875 (nan) time: 0.5064 [2021-03-27 05:50:42 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 670/1251] eta: 0:04:56 lr: 0.000029 loss: 2.7549 (2.7097) grad_norm: 3.1131 (nan) time: 0.5025 [2021-03-27 05:50:47 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 680/1251] eta: 0:04:51 lr: 0.000029 loss: 2.7655 (2.7111) grad_norm: 3.0984 (nan) time: 0.4952 [2021-03-27 05:50:52 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 690/1251] eta: 0:04:46 lr: 0.000029 loss: 2.5827 (2.7086) grad_norm: 3.0626 (nan) time: 0.5025 [2021-03-27 05:50:57 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 700/1251] eta: 0:04:40 lr: 0.000029 loss: 2.5827 (2.7066) grad_norm: 3.1466 (nan) time: 0.5122 [2021-03-27 05:51:02 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 710/1251] eta: 0:04:35 lr: 0.000029 loss: 2.8990 (2.7083) grad_norm: 3.0252 (nan) time: 0.5041 [2021-03-27 05:51:07 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 720/1251] eta: 0:04:30 lr: 0.000029 loss: 2.8799 (2.7086) grad_norm: 3.0294 (nan) time: 0.4965 [2021-03-27 05:51:12 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 730/1251] eta: 0:04:25 lr: 0.000029 loss: 2.8290 (2.7091) grad_norm: 2.9982 (nan) time: 0.4964 [2021-03-27 05:51:18 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 740/1251] eta: 0:04:20 lr: 0.000029 loss: 2.6733 (2.7056) grad_norm: 2.9282 (nan) time: 0.5125 [2021-03-27 05:51:23 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 750/1251] eta: 0:04:15 lr: 0.000029 loss: 2.7328 (2.7064) grad_norm: 3.0463 (nan) time: 0.5165 [2021-03-27 05:51:28 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 760/1251] eta: 0:04:10 lr: 0.000029 loss: 2.7252 (2.7036) grad_norm: 3.0972 (nan) time: 0.5132 [2021-03-27 05:51:33 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 770/1251] eta: 0:04:05 lr: 0.000029 loss: 2.4439 (2.7011) grad_norm: 3.1450 (nan) time: 0.5142 [2021-03-27 05:51:38 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 780/1251] eta: 0:04:00 lr: 0.000029 loss: 2.6779 (2.7006) grad_norm: 3.3125 (nan) time: 0.5058 [2021-03-27 05:51:43 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 790/1251] eta: 0:03:54 lr: 0.000029 loss: 2.9154 (2.7025) grad_norm: 3.0922 (nan) time: 0.5022 [2021-03-27 05:51:48 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 800/1251] eta: 0:03:49 lr: 0.000029 loss: 2.9214 (2.7009) grad_norm: 3.0525 (nan) time: 0.4996 [2021-03-27 05:51:53 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 810/1251] eta: 0:03:44 lr: 0.000029 loss: 2.6229 (2.6997) grad_norm: 3.2054 (nan) time: 0.4993 [2021-03-27 05:51:58 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 820/1251] eta: 0:03:39 lr: 0.000029 loss: 2.6229 (2.7000) grad_norm: 3.2727 (nan) time: 0.5001 [2021-03-27 05:52:03 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 830/1251] eta: 0:03:34 lr: 0.000029 loss: 2.5799 (2.6991) grad_norm: 3.3185 (nan) time: 0.4991 [2021-03-27 05:52:08 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 840/1251] eta: 0:03:29 lr: 0.000029 loss: 2.6919 (2.7002) grad_norm: 3.3185 (nan) time: 0.4992 [2021-03-27 05:52:13 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 850/1251] eta: 0:03:23 lr: 0.000029 loss: 2.8023 (2.7012) grad_norm: 3.0205 (nan) time: 0.4983 [2021-03-27 05:52:18 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 860/1251] eta: 0:03:18 lr: 0.000029 loss: 2.8732 (2.7024) grad_norm: 3.0610 (nan) time: 0.4992 [2021-03-27 05:52:23 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 870/1251] eta: 0:03:13 lr: 0.000029 loss: 2.8732 (2.7030) grad_norm: 3.1584 (nan) time: 0.5053 [2021-03-27 05:52:28 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 880/1251] eta: 0:03:08 lr: 0.000029 loss: 2.9054 (2.7067) grad_norm: 3.1750 (nan) time: 0.5050 [2021-03-27 05:52:33 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 890/1251] eta: 0:03:03 lr: 0.000029 loss: 2.9054 (2.7075) grad_norm: 2.9315 (nan) time: 0.4994 [2021-03-27 05:52:38 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 900/1251] eta: 0:02:58 lr: 0.000029 loss: 2.8891 (2.7079) grad_norm: 2.9074 (nan) time: 0.4941 [2021-03-27 05:52:43 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 910/1251] eta: 0:02:53 lr: 0.000029 loss: 2.8313 (2.7075) grad_norm: 3.3545 (nan) time: 0.4973 [2021-03-27 05:52:48 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 920/1251] eta: 0:02:48 lr: 0.000029 loss: 2.7076 (2.7084) grad_norm: 3.1246 (nan) time: 0.4998 [2021-03-27 05:52:53 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 930/1251] eta: 0:02:43 lr: 0.000029 loss: 2.6826 (2.7072) grad_norm: 2.9734 (nan) time: 0.4994 [2021-03-27 05:52:58 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 940/1251] eta: 0:02:37 lr: 0.000029 loss: 2.7193 (2.7067) grad_norm: 3.1605 (nan) time: 0.5047 [2021-03-27 05:53:03 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 950/1251] eta: 0:02:32 lr: 0.000029 loss: 2.8461 (2.7099) grad_norm: 3.1704 (nan) time: 0.5087 [2021-03-27 05:53:08 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 960/1251] eta: 0:02:27 lr: 0.000029 loss: 2.7573 (2.7079) grad_norm: 3.0979 (nan) time: 0.5025 [2021-03-27 05:53:13 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 970/1251] eta: 0:02:22 lr: 0.000029 loss: 2.4335 (2.7054) grad_norm: 3.1093 (nan) time: 0.5050 [2021-03-27 05:53:18 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 980/1251] eta: 0:02:17 lr: 0.000029 loss: 2.7995 (2.7071) grad_norm: 3.0558 (nan) time: 0.5067 [2021-03-27 05:53:23 swin_small_patch4_window7_224] INFO: Epoch: [273] [ 990/1251] eta: 0:02:12 lr: 0.000029 loss: 2.8441 (2.7074) grad_norm: 3.1382 (nan) time: 0.4996 [2021-03-27 05:53:28 swin_small_patch4_window7_224] INFO: Epoch: [273] [1000/1251] eta: 0:02:07 lr: 0.000029 loss: 2.8549 (2.7090) grad_norm: 3.1382 (nan) time: 0.5013 [2021-03-27 05:53:33 swin_small_patch4_window7_224] INFO: Epoch: [273] [1010/1251] eta: 0:02:02 lr: 0.000029 loss: 2.8549 (2.7088) grad_norm: 3.0914 (nan) time: 0.4974 [2021-03-27 05:53:38 swin_small_patch4_window7_224] INFO: Epoch: [273] [1020/1251] eta: 0:01:57 lr: 0.000028 loss: 2.7637 (2.7074) grad_norm: 3.0914 (nan) time: 0.4983 [2021-03-27 05:53:43 swin_small_patch4_window7_224] INFO: Epoch: [273] [1030/1251] eta: 0:01:52 lr: 0.000028 loss: 2.8082 (2.7074) grad_norm: 3.0589 (nan) time: 0.5046 [2021-03-27 05:53:48 swin_small_patch4_window7_224] INFO: Epoch: [273] [1040/1251] eta: 0:01:47 lr: 0.000028 loss: 2.7161 (2.7071) grad_norm: 2.9883 (nan) time: 0.4986 [2021-03-27 05:53:53 swin_small_patch4_window7_224] INFO: Epoch: [273] [1050/1251] eta: 0:01:41 lr: 0.000028 loss: 2.8352 (2.7077) grad_norm: 2.9324 (nan) time: 0.4944 [2021-03-27 05:53:58 swin_small_patch4_window7_224] INFO: Epoch: [273] [1060/1251] eta: 0:01:36 lr: 0.000028 loss: 2.8533 (2.7080) grad_norm: 2.9636 (nan) time: 0.5038 [2021-03-27 05:54:03 swin_small_patch4_window7_224] INFO: Epoch: [273] [1070/1251] eta: 0:01:31 lr: 0.000028 loss: 2.7668 (2.7072) grad_norm: 2.9682 (nan) time: 0.5113 [2021-03-27 05:54:08 swin_small_patch4_window7_224] INFO: Epoch: [273] [1080/1251] eta: 0:01:26 lr: 0.000028 loss: 2.7668 (2.7089) grad_norm: 3.0410 (nan) time: 0.5067 [2021-03-27 05:54:14 swin_small_patch4_window7_224] INFO: Epoch: [273] [1090/1251] eta: 0:01:21 lr: 0.000028 loss: 2.9249 (2.7096) grad_norm: 2.9884 (nan) time: 0.5060 [2021-03-27 05:54:19 swin_small_patch4_window7_224] INFO: Epoch: [273] [1100/1251] eta: 0:01:16 lr: 0.000028 loss: 2.8988 (2.7102) grad_norm: 3.1605 (nan) time: 0.5059 [2021-03-27 05:54:24 swin_small_patch4_window7_224] INFO: Epoch: [273] [1110/1251] eta: 0:01:11 lr: 0.000028 loss: 2.7592 (2.7082) grad_norm: 3.2942 (nan) time: 0.4978 [2021-03-27 05:54:29 swin_small_patch4_window7_224] INFO: Epoch: [273] [1120/1251] eta: 0:01:06 lr: 0.000028 loss: 2.7174 (2.7067) grad_norm: 3.2112 (nan) time: 0.4987 [2021-03-27 05:54:34 swin_small_patch4_window7_224] INFO: Epoch: [273] [1130/1251] eta: 0:01:01 lr: 0.000028 loss: 2.7174 (2.7061) grad_norm: 3.0545 (nan) time: 0.5026 [2021-03-27 05:54:39 swin_small_patch4_window7_224] INFO: Epoch: [273] [1140/1251] eta: 0:00:56 lr: 0.000028 loss: 2.8692 (2.7078) grad_norm: 3.2153 (nan) time: 0.4998 [2021-03-27 05:54:44 swin_small_patch4_window7_224] INFO: Epoch: [273] [1150/1251] eta: 0:00:51 lr: 0.000028 loss: 2.8270 (2.7062) grad_norm: 3.2531 (nan) time: 0.4960 [2021-03-27 05:54:49 swin_small_patch4_window7_224] INFO: Epoch: [273] [1160/1251] eta: 0:00:46 lr: 0.000028 loss: 2.6650 (2.7073) grad_norm: 3.1843 (nan) time: 0.4964 [2021-03-27 05:54:54 swin_small_patch4_window7_224] INFO: Epoch: [273] [1170/1251] eta: 0:00:41 lr: 0.000028 loss: 2.9382 (2.7080) grad_norm: 3.1843 (nan) time: 0.5055 [2021-03-27 05:54:59 swin_small_patch4_window7_224] INFO: Epoch: [273] [1180/1251] eta: 0:00:35 lr: 0.000028 loss: 2.9160 (2.7085) grad_norm: 3.4972 (nan) time: 0.5112 [2021-03-27 05:55:04 swin_small_patch4_window7_224] INFO: Epoch: [273] [1190/1251] eta: 0:00:30 lr: 0.000028 loss: 2.5335 (2.7065) grad_norm: 3.1191 (nan) time: 0.5124 [2021-03-27 05:55:09 swin_small_patch4_window7_224] INFO: Epoch: [273] [1200/1251] eta: 0:00:25 lr: 0.000028 loss: 2.6909 (2.7082) grad_norm: 3.0928 (nan) time: 0.5096 [2021-03-27 05:55:14 swin_small_patch4_window7_224] INFO: Epoch: [273] [1210/1251] eta: 0:00:20 lr: 0.000028 loss: 2.9887 (2.7100) grad_norm: 3.2463 (nan) time: 0.5009 [2021-03-27 05:55:19 swin_small_patch4_window7_224] INFO: Epoch: [273] [1220/1251] eta: 0:00:15 lr: 0.000028 loss: 2.8372 (2.7101) grad_norm: 3.2003 (nan) time: 0.5001 [2021-03-27 05:55:24 swin_small_patch4_window7_224] INFO: Epoch: [273] [1230/1251] eta: 0:00:10 lr: 0.000028 loss: 2.8333 (2.7105) grad_norm: 3.1254 (nan) time: 0.5000 [2021-03-27 05:55:29 swin_small_patch4_window7_224] INFO: Epoch: [273] [1240/1251] eta: 0:00:05 lr: 0.000028 loss: 2.8286 (2.7107) grad_norm: 3.1156 (nan) time: 0.4988 [2021-03-27 05:55:34 swin_small_patch4_window7_224] INFO: Epoch: [273] [1250/1251] eta: 0:00:00 lr: 0.000028 loss: 2.8286 (2.7117) grad_norm: 3.0416 (nan) time: 0.5028 [2021-03-27 05:55:46 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:17 loss: 0.8904 (0.8904) acc1: 78.1250 (78.1250) acc5: 98.4375 (98.4375) [2021-03-27 05:55:48 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.6466 (0.7203) acc1: 84.3750 (83.5227) acc5: 96.8750 (96.4489) [2021-03-27 05:55:50 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7596 (0.7473) acc1: 82.8125 (82.7381) acc5: 95.3125 (96.0565) [2021-03-27 05:55:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7596 (0.7565) acc1: 82.8125 (82.1573) acc5: 95.3125 (96.1190) [2021-03-27 05:55:55 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7351 (0.7576) acc1: 81.2500 (82.0884) acc5: 96.8750 (96.2652) [2021-03-27 05:55:56 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7521 (0.7525) acc1: 79.6875 (81.7920) acc5: 96.8750 (96.2880) [2021-03-27 05:56:11 swin_small_patch4_window7_224] INFO: * Acc@1 82.876 Acc@5 96.258 loss 0.737 [2021-03-27 05:56:11 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-27 05:56:11 swin_small_patch4_window7_224] INFO: Max accuracy: 82.88% [2021-03-27 05:56:15 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 0/1251] eta: 1:30:07 lr: 0.000028 loss: 2.9725 (2.9725) grad_norm: 2.4613 (2.4613) time: 4.3227 [2021-03-27 05:56:20 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 10/1251] eta: 0:17:34 lr: 0.000028 loss: 2.7259 (2.6728) grad_norm: 3.3437 (3.3415) time: 0.8501 [2021-03-27 05:56:25 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 20/1251] eta: 0:14:03 lr: 0.000028 loss: 2.8085 (2.6917) grad_norm: 3.2992 (3.3842) time: 0.5034 [2021-03-27 05:56:30 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 30/1251] eta: 0:12:43 lr: 0.000028 loss: 2.8085 (2.6957) grad_norm: 2.9992 (3.3215) time: 0.5014 [2021-03-27 05:56:35 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 40/1251] eta: 0:12:00 lr: 0.000028 loss: 2.6245 (2.6589) grad_norm: 3.0390 (3.3252) time: 0.5006 [2021-03-27 05:56:40 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 50/1251] eta: 0:11:33 lr: 0.000028 loss: 2.6436 (2.6998) grad_norm: 2.9968 (3.2902) time: 0.5027 [2021-03-27 05:56:45 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 60/1251] eta: 0:11:13 lr: 0.000028 loss: 2.7498 (2.7007) grad_norm: 2.9818 (3.2916) time: 0.5041 [2021-03-27 05:56:50 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 70/1251] eta: 0:10:58 lr: 0.000028 loss: 2.6771 (2.6925) grad_norm: 3.0378 (3.3044) time: 0.5079 [2021-03-27 05:56:55 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 80/1251] eta: 0:10:44 lr: 0.000028 loss: 2.5607 (2.6598) grad_norm: 3.0921 (3.2892) time: 0.5035 [2021-03-27 05:57:00 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 90/1251] eta: 0:10:33 lr: 0.000028 loss: 2.5932 (2.6627) grad_norm: 3.0921 (3.2715) time: 0.5021 [2021-03-27 05:57:05 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 100/1251] eta: 0:10:22 lr: 0.000028 loss: 2.8380 (2.6867) grad_norm: 3.0856 (3.2640) time: 0.5057 [2021-03-27 05:57:10 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 110/1251] eta: 0:10:13 lr: 0.000028 loss: 2.8389 (2.6883) grad_norm: 3.0856 (3.2395) time: 0.5040 [2021-03-27 05:57:15 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 120/1251] eta: 0:10:05 lr: 0.000028 loss: 2.7028 (2.6815) grad_norm: 2.9324 (3.2261) time: 0.5074 [2021-03-27 05:57:21 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 130/1251] eta: 0:09:58 lr: 0.000028 loss: 2.4535 (2.6590) grad_norm: 2.9382 (3.2121) time: 0.5117 [2021-03-27 05:57:26 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 140/1251] eta: 0:09:51 lr: 0.000028 loss: 2.3275 (2.6626) grad_norm: 2.8893 (3.1888) time: 0.5126 [2021-03-27 05:57:31 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 150/1251] eta: 0:09:44 lr: 0.000028 loss: 2.6891 (2.6594) grad_norm: 2.9898 (3.2038) time: 0.5109 [2021-03-27 05:57:36 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 160/1251] eta: 0:09:36 lr: 0.000028 loss: 2.8833 (2.6660) grad_norm: 3.1415 (3.2150) time: 0.5019 [2021-03-27 05:57:41 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 170/1251] eta: 0:09:29 lr: 0.000028 loss: 2.5648 (2.6517) grad_norm: 2.8794 (3.2067) time: 0.4992 [2021-03-27 05:57:46 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 180/1251] eta: 0:09:23 lr: 0.000028 loss: 2.3319 (2.6450) grad_norm: 3.1307 (3.2245) time: 0.5067 [2021-03-27 05:57:51 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 190/1251] eta: 0:09:16 lr: 0.000028 loss: 2.4693 (2.6453) grad_norm: 3.2324 (3.2319) time: 0.5049 [2021-03-27 05:57:56 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 200/1251] eta: 0:09:11 lr: 0.000028 loss: 2.6151 (2.6478) grad_norm: 3.2324 (3.2252) time: 0.5158 [2021-03-27 05:58:01 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 210/1251] eta: 0:09:05 lr: 0.000028 loss: 2.8135 (2.6547) grad_norm: 3.2321 (3.2408) time: 0.5184 [2021-03-27 05:58:06 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 220/1251] eta: 0:08:59 lr: 0.000028 loss: 2.9002 (2.6612) grad_norm: 3.2084 (3.2371) time: 0.5067 [2021-03-27 05:58:11 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 230/1251] eta: 0:08:53 lr: 0.000028 loss: 2.9002 (2.6647) grad_norm: 3.0867 (3.2364) time: 0.5026 [2021-03-27 05:58:17 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 240/1251] eta: 0:08:47 lr: 0.000028 loss: 2.7339 (2.6652) grad_norm: 3.1448 (3.2357) time: 0.5066 [2021-03-27 05:58:22 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 250/1251] eta: 0:08:42 lr: 0.000028 loss: 2.8784 (2.6760) grad_norm: 3.1339 (3.2568) time: 0.5204 [2021-03-27 05:58:27 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 260/1251] eta: 0:08:37 lr: 0.000028 loss: 2.8291 (2.6673) grad_norm: 3.0845 (3.2513) time: 0.5193 [2021-03-27 05:58:32 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 270/1251] eta: 0:08:31 lr: 0.000028 loss: 2.5898 (2.6695) grad_norm: 3.0868 (3.2879) time: 0.5093 [2021-03-27 05:58:37 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 280/1251] eta: 0:08:25 lr: 0.000028 loss: 2.6294 (2.6702) grad_norm: 3.2981 (3.3113) time: 0.5039 [2021-03-27 05:58:42 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 290/1251] eta: 0:08:19 lr: 0.000028 loss: 2.7806 (2.6710) grad_norm: 3.1922 (3.2999) time: 0.5021 [2021-03-27 05:58:47 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 300/1251] eta: 0:08:14 lr: 0.000028 loss: 2.8442 (2.6756) grad_norm: 3.0516 (3.3023) time: 0.5041 [2021-03-27 05:58:52 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 310/1251] eta: 0:08:08 lr: 0.000028 loss: 2.8193 (2.6715) grad_norm: 3.0915 (3.3030) time: 0.5089 [2021-03-27 05:58:57 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 320/1251] eta: 0:08:03 lr: 0.000028 loss: 2.8901 (2.6817) grad_norm: 3.2572 (3.3061) time: 0.5125 [2021-03-27 05:59:02 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 330/1251] eta: 0:07:57 lr: 0.000028 loss: 2.9166 (2.6836) grad_norm: 3.2672 (3.3032) time: 0.5104 [2021-03-27 05:59:07 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 340/1251] eta: 0:07:52 lr: 0.000028 loss: 2.7358 (2.6868) grad_norm: 3.1641 (3.2965) time: 0.5038 [2021-03-27 05:59:12 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 350/1251] eta: 0:07:46 lr: 0.000028 loss: 2.8707 (2.6934) grad_norm: 2.9377 (3.2911) time: 0.5041 [2021-03-27 05:59:17 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 360/1251] eta: 0:07:40 lr: 0.000028 loss: 2.8867 (2.6983) grad_norm: 3.0445 (3.2864) time: 0.5002 [2021-03-27 05:59:22 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 370/1251] eta: 0:07:35 lr: 0.000028 loss: 2.8487 (2.7009) grad_norm: 3.1133 (3.2857) time: 0.4949 [2021-03-27 05:59:27 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 380/1251] eta: 0:07:29 lr: 0.000028 loss: 2.8268 (2.7027) grad_norm: 3.1133 (3.2847) time: 0.4984 [2021-03-27 05:59:32 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 390/1251] eta: 0:07:24 lr: 0.000028 loss: 2.8491 (2.7038) grad_norm: 3.0557 (3.2799) time: 0.4990 [2021-03-27 05:59:37 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 400/1251] eta: 0:07:18 lr: 0.000028 loss: 2.8121 (2.7071) grad_norm: 2.9911 (3.2767) time: 0.4985 [2021-03-27 05:59:42 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 410/1251] eta: 0:07:13 lr: 0.000028 loss: 2.7858 (2.7091) grad_norm: 2.9319 (3.2754) time: 0.5001 [2021-03-27 05:59:48 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 420/1251] eta: 0:07:07 lr: 0.000028 loss: 2.7858 (2.7099) grad_norm: 2.9736 (3.3239) time: 0.5080 [2021-03-27 05:59:53 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 430/1251] eta: 0:07:02 lr: 0.000028 loss: 2.7308 (2.7064) grad_norm: 2.9736 (3.3184) time: 0.5099 [2021-03-27 05:59:58 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 440/1251] eta: 0:06:57 lr: 0.000028 loss: 2.7180 (2.7089) grad_norm: 3.1733 (3.3265) time: 0.5116 [2021-03-27 06:00:03 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 450/1251] eta: 0:06:52 lr: 0.000028 loss: 2.7689 (2.7081) grad_norm: 3.2029 (3.3277) time: 0.5108 [2021-03-27 06:00:08 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 460/1251] eta: 0:06:47 lr: 0.000028 loss: 2.7569 (2.7100) grad_norm: 3.1702 (3.3809) time: 0.5089 [2021-03-27 06:00:13 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 470/1251] eta: 0:06:41 lr: 0.000028 loss: 2.9415 (2.7155) grad_norm: 3.1702 (3.3786) time: 0.5075 [2021-03-27 06:00:18 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 480/1251] eta: 0:06:36 lr: 0.000028 loss: 2.9707 (2.7171) grad_norm: 3.2416 (3.3786) time: 0.5014 [2021-03-27 06:00:23 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 490/1251] eta: 0:06:30 lr: 0.000028 loss: 2.9492 (2.7204) grad_norm: 3.1331 (3.3715) time: 0.5006 [2021-03-27 06:00:28 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 500/1251] eta: 0:06:25 lr: 0.000028 loss: 2.7822 (2.7206) grad_norm: 3.0653 (3.3701) time: 0.5024 [2021-03-27 06:00:33 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 510/1251] eta: 0:06:20 lr: 0.000028 loss: 2.7896 (2.7231) grad_norm: 3.1099 (3.3728) time: 0.5030 [2021-03-27 06:00:38 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 520/1251] eta: 0:06:15 lr: 0.000028 loss: 2.7621 (2.7226) grad_norm: 3.1099 (3.3709) time: 0.5016 [2021-03-27 06:00:43 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 530/1251] eta: 0:06:09 lr: 0.000028 loss: 2.7535 (2.7213) grad_norm: 3.1774 (3.3703) time: 0.5031 [2021-03-27 06:00:48 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 540/1251] eta: 0:06:04 lr: 0.000028 loss: 2.7658 (2.7228) grad_norm: 3.1774 (3.3669) time: 0.5088 [2021-03-27 06:00:53 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 550/1251] eta: 0:05:59 lr: 0.000028 loss: 2.9487 (2.7252) grad_norm: 2.9681 (3.3631) time: 0.5160 [2021-03-27 06:00:58 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 560/1251] eta: 0:05:54 lr: 0.000028 loss: 2.8408 (2.7229) grad_norm: 2.9767 (3.3624) time: 0.5102 [2021-03-27 06:01:03 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 570/1251] eta: 0:05:49 lr: 0.000028 loss: 2.6143 (2.7210) grad_norm: 2.9444 (3.3526) time: 0.4996 [2021-03-27 06:01:08 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 580/1251] eta: 0:05:43 lr: 0.000028 loss: 2.6851 (2.7210) grad_norm: 2.8777 (3.3576) time: 0.5017 [2021-03-27 06:01:13 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 590/1251] eta: 0:05:38 lr: 0.000028 loss: 2.7390 (2.7207) grad_norm: 3.0401 (3.3552) time: 0.5025 [2021-03-27 06:01:18 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 600/1251] eta: 0:05:33 lr: 0.000028 loss: 2.6801 (2.7171) grad_norm: 3.1726 (3.3552) time: 0.4942 [2021-03-27 06:01:23 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 610/1251] eta: 0:05:27 lr: 0.000028 loss: 2.6801 (2.7174) grad_norm: 3.1978 (3.3541) time: 0.4964 [2021-03-27 06:01:28 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 620/1251] eta: 0:05:22 lr: 0.000028 loss: 2.7724 (2.7171) grad_norm: 3.1742 (3.3535) time: 0.4999 [2021-03-27 06:01:33 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 630/1251] eta: 0:05:17 lr: 0.000028 loss: 2.7766 (2.7202) grad_norm: 3.2450 (3.3526) time: 0.5044 [2021-03-27 06:01:39 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 640/1251] eta: 0:05:12 lr: 0.000028 loss: 2.7513 (2.7169) grad_norm: 3.1804 (3.3477) time: 0.5120 [2021-03-27 06:01:44 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 650/1251] eta: 0:05:07 lr: 0.000028 loss: 2.6893 (2.7168) grad_norm: 3.0758 (3.3424) time: 0.5048 [2021-03-27 06:01:49 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 660/1251] eta: 0:05:02 lr: 0.000028 loss: 2.8150 (2.7177) grad_norm: 2.8875 (3.3373) time: 0.5041 [2021-03-27 06:01:54 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 670/1251] eta: 0:04:56 lr: 0.000027 loss: 2.7940 (2.7160) grad_norm: 2.9280 (3.3330) time: 0.5058 [2021-03-27 06:01:59 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 680/1251] eta: 0:04:51 lr: 0.000027 loss: 2.8662 (2.7179) grad_norm: 2.9365 (3.3280) time: 0.5069 [2021-03-27 06:02:04 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 690/1251] eta: 0:04:46 lr: 0.000027 loss: 2.9012 (2.7153) grad_norm: 2.9023 (3.3272) time: 0.5081 [2021-03-27 06:02:09 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 700/1251] eta: 0:04:41 lr: 0.000027 loss: 2.7971 (2.7151) grad_norm: 2.9621 (3.3256) time: 0.5026 [2021-03-27 06:02:14 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 710/1251] eta: 0:04:36 lr: 0.000027 loss: 2.7930 (2.7140) grad_norm: 2.9621 (3.3210) time: 0.5013 [2021-03-27 06:02:19 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 720/1251] eta: 0:04:31 lr: 0.000027 loss: 2.7930 (2.7158) grad_norm: 3.0182 (3.3200) time: 0.4995 [2021-03-27 06:02:24 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 730/1251] eta: 0:04:26 lr: 0.000027 loss: 2.8983 (2.7191) grad_norm: 3.0265 (3.3186) time: 0.5052 [2021-03-27 06:02:29 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 740/1251] eta: 0:04:20 lr: 0.000027 loss: 2.9201 (2.7182) grad_norm: 3.0103 (3.3154) time: 0.5135 [2021-03-27 06:02:34 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 750/1251] eta: 0:04:15 lr: 0.000027 loss: 2.8501 (2.7196) grad_norm: 3.0365 (3.3178) time: 0.5175 [2021-03-27 06:02:39 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 760/1251] eta: 0:04:10 lr: 0.000027 loss: 2.8482 (2.7202) grad_norm: 3.1395 (3.3157) time: 0.5087 [2021-03-27 06:02:44 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 770/1251] eta: 0:04:05 lr: 0.000027 loss: 2.8556 (2.7229) grad_norm: 3.0055 (3.3118) time: 0.5018 [2021-03-27 06:02:49 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 780/1251] eta: 0:04:00 lr: 0.000027 loss: 2.8556 (2.7217) grad_norm: 3.0394 (3.3152) time: 0.5017 [2021-03-27 06:02:54 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 790/1251] eta: 0:03:55 lr: 0.000027 loss: 2.9409 (2.7248) grad_norm: 3.2193 (3.3111) time: 0.4973 [2021-03-27 06:02:59 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 800/1251] eta: 0:03:50 lr: 0.000027 loss: 2.9695 (2.7267) grad_norm: 2.8598 (3.3068) time: 0.4999 [2021-03-27 06:03:04 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 810/1251] eta: 0:03:44 lr: 0.000027 loss: 2.9890 (2.7285) grad_norm: 2.8253 (3.3014) time: 0.5053 [2021-03-27 06:03:09 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 820/1251] eta: 0:03:39 lr: 0.000027 loss: 2.8918 (2.7289) grad_norm: 2.8387 (3.2982) time: 0.5031 [2021-03-27 06:03:14 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 830/1251] eta: 0:03:34 lr: 0.000027 loss: 2.8165 (2.7288) grad_norm: 2.9990 (3.2979) time: 0.5023 [2021-03-27 06:03:19 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 840/1251] eta: 0:03:29 lr: 0.000027 loss: 2.7637 (2.7283) grad_norm: 2.9990 (3.2975) time: 0.5025 [2021-03-27 06:03:24 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 850/1251] eta: 0:03:24 lr: 0.000027 loss: 2.7637 (2.7268) grad_norm: 2.9954 (3.2965) time: 0.4962 [2021-03-27 06:03:29 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 860/1251] eta: 0:03:19 lr: 0.000027 loss: 2.9084 (2.7294) grad_norm: 3.1517 (3.2957) time: 0.4973 [2021-03-27 06:03:35 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 870/1251] eta: 0:03:14 lr: 0.000027 loss: 2.9126 (2.7295) grad_norm: 3.1398 (3.2979) time: 0.5040 [2021-03-27 06:03:40 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 880/1251] eta: 0:03:09 lr: 0.000027 loss: 2.6900 (2.7286) grad_norm: 3.1723 (3.3033) time: 0.5097 [2021-03-27 06:03:45 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 890/1251] eta: 0:03:03 lr: 0.000027 loss: 2.6894 (2.7278) grad_norm: 3.2991 (3.3046) time: 0.5081 [2021-03-27 06:03:50 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 900/1251] eta: 0:02:58 lr: 0.000027 loss: 2.6410 (2.7277) grad_norm: 3.2311 (3.3016) time: 0.4994 [2021-03-27 06:03:55 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 910/1251] eta: 0:02:53 lr: 0.000027 loss: 2.7670 (2.7286) grad_norm: 3.0835 (3.3030) time: 0.5012 [2021-03-27 06:04:00 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 920/1251] eta: 0:02:48 lr: 0.000027 loss: 2.8539 (2.7279) grad_norm: 3.1884 (3.3012) time: 0.5096 [2021-03-27 06:04:05 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 930/1251] eta: 0:02:43 lr: 0.000027 loss: 2.7736 (2.7281) grad_norm: 3.0181 (3.3000) time: 0.5023 [2021-03-27 06:04:10 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 940/1251] eta: 0:02:38 lr: 0.000027 loss: 2.7736 (2.7267) grad_norm: 3.2526 (3.3011) time: 0.5025 [2021-03-27 06:04:15 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 950/1251] eta: 0:02:33 lr: 0.000027 loss: 2.8069 (2.7280) grad_norm: 3.3525 (3.3003) time: 0.5025 [2021-03-27 06:04:20 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 960/1251] eta: 0:02:28 lr: 0.000027 loss: 2.8505 (2.7283) grad_norm: 3.0673 (3.3002) time: 0.4967 [2021-03-27 06:04:25 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 970/1251] eta: 0:02:22 lr: 0.000027 loss: 2.8395 (2.7284) grad_norm: 3.0398 (3.2975) time: 0.5023 [2021-03-27 06:04:30 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 980/1251] eta: 0:02:17 lr: 0.000027 loss: 2.7673 (2.7285) grad_norm: 3.0398 (3.2942) time: 0.5045 [2021-03-27 06:04:35 swin_small_patch4_window7_224] INFO: Epoch: [274] [ 990/1251] eta: 0:02:12 lr: 0.000027 loss: 2.6773 (2.7282) grad_norm: 2.9439 (3.2928) time: 0.5095 [2021-03-27 06:04:40 swin_small_patch4_window7_224] INFO: Epoch: [274] [1000/1251] eta: 0:02:07 lr: 0.000027 loss: 2.6405 (2.7276) grad_norm: 3.1017 (3.2944) time: 0.5145 [2021-03-27 06:04:45 swin_small_patch4_window7_224] INFO: Epoch: [274] [1010/1251] eta: 0:02:02 lr: 0.000027 loss: 2.7342 (2.7267) grad_norm: 3.1889 (3.2935) time: 0.5057 [2021-03-27 06:04:50 swin_small_patch4_window7_224] INFO: Epoch: [274] [1020/1251] eta: 0:01:57 lr: 0.000027 loss: 2.6963 (2.7265) grad_norm: 3.1889 (3.2964) time: 0.4981 [2021-03-27 06:04:55 swin_small_patch4_window7_224] INFO: Epoch: [274] [1030/1251] eta: 0:01:52 lr: 0.000027 loss: 2.6963 (2.7281) grad_norm: 2.9029 (3.2946) time: 0.5003 [2021-03-27 06:05:00 swin_small_patch4_window7_224] INFO: Epoch: [274] [1040/1251] eta: 0:01:47 lr: 0.000027 loss: 2.9575 (2.7303) grad_norm: 3.1234 (3.2941) time: 0.5026 [2021-03-27 06:05:05 swin_small_patch4_window7_224] INFO: Epoch: [274] [1050/1251] eta: 0:01:42 lr: 0.000027 loss: 2.9127 (2.7302) grad_norm: 3.1234 (3.2930) time: 0.5038 [2021-03-27 06:05:10 swin_small_patch4_window7_224] INFO: Epoch: [274] [1060/1251] eta: 0:01:37 lr: 0.000027 loss: 2.8379 (2.7302) grad_norm: 2.9845 (3.2907) time: 0.5078 [2021-03-27 06:05:16 swin_small_patch4_window7_224] INFO: Epoch: [274] [1070/1251] eta: 0:01:32 lr: 0.000027 loss: 2.8602 (2.7321) grad_norm: 2.9305 (3.2888) time: 0.5165 [2021-03-27 06:05:21 swin_small_patch4_window7_224] INFO: Epoch: [274] [1080/1251] eta: 0:01:26 lr: 0.000027 loss: 2.8540 (2.7291) grad_norm: 2.9163 (3.2881) time: 0.5106 [2021-03-27 06:05:26 swin_small_patch4_window7_224] INFO: Epoch: [274] [1090/1251] eta: 0:01:21 lr: 0.000027 loss: 2.7179 (2.7293) grad_norm: 3.0967 (3.2940) time: 0.5070 [2021-03-27 06:05:31 swin_small_patch4_window7_224] INFO: Epoch: [274] [1100/1251] eta: 0:01:16 lr: 0.000027 loss: 2.5399 (2.7251) grad_norm: 3.0056 (3.2922) time: 0.5062 [2021-03-27 06:05:36 swin_small_patch4_window7_224] INFO: Epoch: [274] [1110/1251] eta: 0:01:11 lr: 0.000027 loss: 2.4871 (2.7228) grad_norm: 3.0056 (3.2952) time: 0.5038 [2021-03-27 06:05:41 swin_small_patch4_window7_224] INFO: Epoch: [274] [1120/1251] eta: 0:01:06 lr: 0.000027 loss: 2.5813 (2.7228) grad_norm: 2.9348 (3.2926) time: 0.5077 [2021-03-27 06:05:46 swin_small_patch4_window7_224] INFO: Epoch: [274] [1130/1251] eta: 0:01:01 lr: 0.000027 loss: 2.8931 (2.7238) grad_norm: 3.0513 (3.2916) time: 0.5033 [2021-03-27 06:05:51 swin_small_patch4_window7_224] INFO: Epoch: [274] [1140/1251] eta: 0:00:56 lr: 0.000027 loss: 2.9237 (2.7237) grad_norm: 3.0513 (3.2914) time: 0.5049 [2021-03-27 06:05:56 swin_small_patch4_window7_224] INFO: Epoch: [274] [1150/1251] eta: 0:00:51 lr: 0.000027 loss: 2.6705 (2.7214) grad_norm: 2.9326 (3.2890) time: 0.5055 [2021-03-27 06:06:01 swin_small_patch4_window7_224] INFO: Epoch: [274] [1160/1251] eta: 0:00:46 lr: 0.000027 loss: 2.6914 (2.7219) grad_norm: 2.9896 (3.2904) time: 0.5037 [2021-03-27 06:06:06 swin_small_patch4_window7_224] INFO: Epoch: [274] [1170/1251] eta: 0:00:41 lr: 0.000027 loss: 2.7502 (2.7218) grad_norm: 2.9350 (3.2878) time: 0.5029 [2021-03-27 06:06:11 swin_small_patch4_window7_224] INFO: Epoch: [274] [1180/1251] eta: 0:00:36 lr: 0.000027 loss: 2.7369 (2.7199) grad_norm: 3.0718 (3.2866) time: 0.4986 [2021-03-27 06:06:16 swin_small_patch4_window7_224] INFO: Epoch: [274] [1190/1251] eta: 0:00:31 lr: 0.000027 loss: 2.7212 (2.7204) grad_norm: 3.0718 (3.2859) time: 0.5081 [2021-03-27 06:06:21 swin_small_patch4_window7_224] INFO: Epoch: [274] [1200/1251] eta: 0:00:25 lr: 0.000027 loss: 2.7212 (2.7196) grad_norm: 2.8021 (3.2816) time: 0.5107 [2021-03-27 06:06:26 swin_small_patch4_window7_224] INFO: Epoch: [274] [1210/1251] eta: 0:00:20 lr: 0.000027 loss: 2.7797 (2.7201) grad_norm: 2.8831 (3.2794) time: 0.4994 [2021-03-27 06:06:31 swin_small_patch4_window7_224] INFO: Epoch: [274] [1220/1251] eta: 0:00:15 lr: 0.000027 loss: 2.8088 (2.7209) grad_norm: 2.9106 (3.2771) time: 0.4971 [2021-03-27 06:06:36 swin_small_patch4_window7_224] INFO: Epoch: [274] [1230/1251] eta: 0:00:10 lr: 0.000027 loss: 2.7973 (2.7204) grad_norm: 3.0199 (3.2767) time: 0.4982 [2021-03-27 06:06:41 swin_small_patch4_window7_224] INFO: Epoch: [274] [1240/1251] eta: 0:00:05 lr: 0.000027 loss: 2.8017 (2.7227) grad_norm: 3.0348 (3.2760) time: 0.5032 [2021-03-27 06:06:46 swin_small_patch4_window7_224] INFO: Epoch: [274] [1250/1251] eta: 0:00:00 lr: 0.000027 loss: 2.8765 (2.7224) grad_norm: 3.0320 (3.2760) time: 0.5102 [2021-03-27 06:06:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:17 loss: 0.8146 (0.8146) acc1: 81.2500 (81.2500) acc5: 93.7500 (93.7500) [2021-03-27 06:07:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.6900 (0.7294) acc1: 84.3750 (83.2386) acc5: 96.8750 (96.5909) [2021-03-27 06:07:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6900 (0.7688) acc1: 82.8125 (81.5476) acc5: 96.8750 (96.2054) [2021-03-27 06:07:04 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6881 (0.7481) acc1: 82.8125 (82.1069) acc5: 95.3125 (96.2198) [2021-03-27 06:07:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7101 (0.7655) acc1: 81.2500 (81.5930) acc5: 95.3125 (96.0366) [2021-03-27 06:07:08 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7550 (0.7537) acc1: 81.2500 (82.0480) acc5: 96.8750 (96.1280) [2021-03-27 06:07:22 swin_small_patch4_window7_224] INFO: * Acc@1 82.770 Acc@5 96.212 loss 0.743 [2021-03-27 06:07:22 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 06:07:22 swin_small_patch4_window7_224] INFO: Max accuracy: 82.88% [2021-03-27 06:07:26 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 0/1251] eta: 1:30:55 lr: 0.000027 loss: 2.9575 (2.9575) grad_norm: 3.1466 (3.1466) time: 4.3608 [2021-03-27 06:07:31 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 10/1251] eta: 0:17:45 lr: 0.000027 loss: 2.8735 (2.8680) grad_norm: 3.3688 (3.7147) time: 0.8588 [2021-03-27 06:07:37 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 20/1251] eta: 0:14:14 lr: 0.000027 loss: 2.7584 (2.8625) grad_norm: 3.2943 (3.5463) time: 0.5104 [2021-03-27 06:07:42 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 30/1251] eta: 0:12:51 lr: 0.000027 loss: 2.7868 (2.8437) grad_norm: 3.0876 (3.4060) time: 0.5073 [2021-03-27 06:07:47 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 40/1251] eta: 0:12:09 lr: 0.000027 loss: 2.8671 (2.8339) grad_norm: 3.0876 (3.3938) time: 0.5070 [2021-03-27 06:07:52 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 50/1251] eta: 0:11:41 lr: 0.000027 loss: 2.8951 (2.8477) grad_norm: 3.2657 (3.3607) time: 0.5105 [2021-03-27 06:07:57 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 60/1251] eta: 0:11:21 lr: 0.000027 loss: 2.8402 (2.8515) grad_norm: 3.1345 (3.3129) time: 0.5102 [2021-03-27 06:08:02 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 70/1251] eta: 0:11:04 lr: 0.000027 loss: 2.8402 (2.8456) grad_norm: 3.0314 (3.2801) time: 0.5085 [2021-03-27 06:08:07 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 80/1251] eta: 0:10:50 lr: 0.000027 loss: 2.8257 (2.8128) grad_norm: 2.9347 (3.2512) time: 0.5032 [2021-03-27 06:08:12 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 90/1251] eta: 0:10:37 lr: 0.000027 loss: 2.8257 (2.8026) grad_norm: 2.9637 (3.2678) time: 0.5010 [2021-03-27 06:08:17 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 100/1251] eta: 0:10:27 lr: 0.000027 loss: 2.8656 (2.8080) grad_norm: 3.1142 (3.2598) time: 0.5025 [2021-03-27 06:08:22 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 110/1251] eta: 0:10:16 lr: 0.000027 loss: 2.8263 (2.8016) grad_norm: 3.2095 (3.2576) time: 0.4990 [2021-03-27 06:08:27 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 120/1251] eta: 0:10:07 lr: 0.000027 loss: 2.6204 (2.7831) grad_norm: 3.2306 (3.2588) time: 0.4968 [2021-03-27 06:08:32 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 130/1251] eta: 0:10:00 lr: 0.000027 loss: 2.6101 (2.7725) grad_norm: 3.0015 (3.2525) time: 0.5122 [2021-03-27 06:08:37 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 140/1251] eta: 0:09:53 lr: 0.000027 loss: 2.3851 (2.7434) grad_norm: 2.9592 (3.2504) time: 0.5165 [2021-03-27 06:08:42 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 150/1251] eta: 0:09:46 lr: 0.000027 loss: 2.3851 (2.7380) grad_norm: 2.9588 (3.2348) time: 0.5079 [2021-03-27 06:08:47 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 160/1251] eta: 0:09:38 lr: 0.000027 loss: 2.6624 (2.7305) grad_norm: 3.0540 (3.2316) time: 0.5016 [2021-03-27 06:08:52 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 170/1251] eta: 0:09:31 lr: 0.000027 loss: 2.7240 (2.7306) grad_norm: 3.1114 (3.2264) time: 0.5005 [2021-03-27 06:08:57 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 180/1251] eta: 0:09:24 lr: 0.000027 loss: 2.8714 (2.7316) grad_norm: 3.0703 (3.2228) time: 0.5051 [2021-03-27 06:09:03 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 190/1251] eta: 0:09:18 lr: 0.000027 loss: 2.7779 (2.7291) grad_norm: 3.0703 (3.2176) time: 0.5088 [2021-03-27 06:09:08 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 200/1251] eta: 0:09:11 lr: 0.000027 loss: 2.8584 (2.7380) grad_norm: 3.1347 (3.2120) time: 0.5068 [2021-03-27 06:09:13 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 210/1251] eta: 0:09:05 lr: 0.000027 loss: 2.8147 (2.7345) grad_norm: 3.0958 (3.2124) time: 0.5039 [2021-03-27 06:09:18 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 220/1251] eta: 0:08:59 lr: 0.000027 loss: 2.7302 (2.7364) grad_norm: 2.9918 (3.2048) time: 0.5039 [2021-03-27 06:09:23 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 230/1251] eta: 0:08:53 lr: 0.000027 loss: 2.7597 (2.7297) grad_norm: 2.9980 (3.2121) time: 0.5008 [2021-03-27 06:09:28 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 240/1251] eta: 0:08:47 lr: 0.000027 loss: 2.8556 (2.7304) grad_norm: 2.9675 (3.2072) time: 0.5045 [2021-03-27 06:09:33 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 250/1251] eta: 0:08:41 lr: 0.000027 loss: 2.8751 (2.7314) grad_norm: 2.9342 (3.1961) time: 0.5090 [2021-03-27 06:09:38 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 260/1251] eta: 0:08:36 lr: 0.000027 loss: 2.6297 (2.7234) grad_norm: 3.0996 (3.2123) time: 0.5083 [2021-03-27 06:09:43 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 270/1251] eta: 0:08:29 lr: 0.000027 loss: 2.7586 (2.7278) grad_norm: 3.1868 (3.2470) time: 0.5011 [2021-03-27 06:09:48 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 280/1251] eta: 0:08:23 lr: 0.000027 loss: 2.7638 (2.7243) grad_norm: 3.0750 (3.2395) time: 0.4957 [2021-03-27 06:09:53 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 290/1251] eta: 0:08:17 lr: 0.000027 loss: 2.6297 (2.7243) grad_norm: 3.0203 (3.2409) time: 0.4966 [2021-03-27 06:09:58 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 300/1251] eta: 0:08:12 lr: 0.000027 loss: 2.5850 (2.7192) grad_norm: 2.9564 (3.2307) time: 0.5002 [2021-03-27 06:10:03 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 310/1251] eta: 0:08:06 lr: 0.000027 loss: 2.7411 (2.7186) grad_norm: 2.9100 (3.2407) time: 0.5025 [2021-03-27 06:10:08 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 320/1251] eta: 0:08:01 lr: 0.000027 loss: 2.7195 (2.7134) grad_norm: 2.9070 (3.2307) time: 0.5121 [2021-03-27 06:10:13 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 330/1251] eta: 0:07:55 lr: 0.000027 loss: 2.6870 (2.7135) grad_norm: 2.9868 (3.2333) time: 0.5093 [2021-03-27 06:10:18 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 340/1251] eta: 0:07:50 lr: 0.000027 loss: 2.6770 (2.7115) grad_norm: 3.1488 (3.2423) time: 0.5036 [2021-03-27 06:10:23 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 350/1251] eta: 0:07:45 lr: 0.000026 loss: 2.6555 (2.7138) grad_norm: 3.1942 (3.2510) time: 0.5092 [2021-03-27 06:10:28 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 360/1251] eta: 0:07:39 lr: 0.000026 loss: 2.7721 (2.7128) grad_norm: 3.1372 (3.2432) time: 0.5098 [2021-03-27 06:10:33 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 370/1251] eta: 0:07:34 lr: 0.000026 loss: 2.9031 (2.7172) grad_norm: 3.0149 (3.2416) time: 0.5042 [2021-03-27 06:10:38 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 380/1251] eta: 0:07:29 lr: 0.000026 loss: 2.9749 (2.7176) grad_norm: 3.0194 (3.2384) time: 0.5065 [2021-03-27 06:10:43 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 390/1251] eta: 0:07:23 lr: 0.000026 loss: 2.9225 (2.7226) grad_norm: 3.0194 (3.2339) time: 0.5053 [2021-03-27 06:10:48 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 400/1251] eta: 0:07:18 lr: 0.000026 loss: 2.8444 (2.7202) grad_norm: 3.0714 (3.2314) time: 0.4988 [2021-03-27 06:10:53 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 410/1251] eta: 0:07:12 lr: 0.000026 loss: 2.8140 (2.7204) grad_norm: 3.1392 (3.2289) time: 0.5030 [2021-03-27 06:10:59 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 420/1251] eta: 0:07:07 lr: 0.000026 loss: 2.9727 (2.7257) grad_norm: 3.0739 (3.2250) time: 0.5074 [2021-03-27 06:11:04 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 430/1251] eta: 0:07:02 lr: 0.000026 loss: 2.8493 (2.7226) grad_norm: 3.1296 (3.2285) time: 0.5053 [2021-03-27 06:11:09 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 440/1251] eta: 0:06:56 lr: 0.000026 loss: 2.6852 (2.7214) grad_norm: 3.4448 (3.2838) time: 0.4986 [2021-03-27 06:11:14 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 450/1251] eta: 0:06:51 lr: 0.000026 loss: 2.9056 (2.7227) grad_norm: 3.2846 (3.2802) time: 0.5058 [2021-03-27 06:11:19 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 460/1251] eta: 0:06:46 lr: 0.000026 loss: 2.9581 (2.7245) grad_norm: 3.1492 (3.2938) time: 0.5087 [2021-03-27 06:11:24 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 470/1251] eta: 0:06:40 lr: 0.000026 loss: 2.7478 (2.7229) grad_norm: 3.2088 (3.2922) time: 0.5060 [2021-03-27 06:11:29 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 480/1251] eta: 0:06:35 lr: 0.000026 loss: 2.7318 (2.7222) grad_norm: 2.9550 (3.2902) time: 0.5003 [2021-03-27 06:11:34 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 490/1251] eta: 0:06:30 lr: 0.000026 loss: 2.6735 (2.7197) grad_norm: 2.9550 (3.2955) time: 0.4969 [2021-03-27 06:11:39 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 500/1251] eta: 0:06:24 lr: 0.000026 loss: 2.3854 (2.7116) grad_norm: 2.9721 (3.2944) time: 0.4985 [2021-03-27 06:11:44 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 510/1251] eta: 0:06:19 lr: 0.000026 loss: 2.5683 (2.7125) grad_norm: 2.9852 (3.2930) time: 0.4973 [2021-03-27 06:11:49 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 520/1251] eta: 0:06:14 lr: 0.000026 loss: 2.8155 (2.7140) grad_norm: 3.2346 (3.2948) time: 0.5022 [2021-03-27 06:11:54 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 530/1251] eta: 0:06:09 lr: 0.000026 loss: 2.9372 (2.7149) grad_norm: 3.3492 (3.3048) time: 0.5084 [2021-03-27 06:11:59 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 540/1251] eta: 0:06:03 lr: 0.000026 loss: 2.7704 (2.7144) grad_norm: 3.2177 (3.3003) time: 0.5103 [2021-03-27 06:12:04 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 550/1251] eta: 0:05:58 lr: 0.000026 loss: 2.8266 (2.7154) grad_norm: 3.0754 (3.3012) time: 0.5104 [2021-03-27 06:12:09 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 560/1251] eta: 0:05:53 lr: 0.000026 loss: 2.8981 (2.7155) grad_norm: 3.0317 (3.2962) time: 0.5046 [2021-03-27 06:12:14 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 570/1251] eta: 0:05:48 lr: 0.000026 loss: 2.8981 (2.7181) grad_norm: 3.0079 (3.2994) time: 0.4999 [2021-03-27 06:12:19 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 580/1251] eta: 0:05:43 lr: 0.000026 loss: 2.7766 (2.7182) grad_norm: 3.0214 (3.2960) time: 0.4993 [2021-03-27 06:12:24 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 590/1251] eta: 0:05:37 lr: 0.000026 loss: 2.9018 (2.7194) grad_norm: 3.1438 (3.2937) time: 0.5067 [2021-03-27 06:12:29 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 600/1251] eta: 0:05:32 lr: 0.000026 loss: 2.7135 (2.7164) grad_norm: 3.1273 (3.2968) time: 0.5109 [2021-03-27 06:12:34 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 610/1251] eta: 0:05:27 lr: 0.000026 loss: 2.5793 (2.7141) grad_norm: 3.1222 (3.2944) time: 0.5000 [2021-03-27 06:12:39 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 620/1251] eta: 0:05:22 lr: 0.000026 loss: 2.8006 (2.7158) grad_norm: 3.1139 (3.2937) time: 0.4994 [2021-03-27 06:12:44 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 630/1251] eta: 0:05:17 lr: 0.000026 loss: 2.8006 (2.7173) grad_norm: 3.1676 (3.2998) time: 0.5052 [2021-03-27 06:12:49 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 640/1251] eta: 0:05:11 lr: 0.000026 loss: 2.7227 (2.7151) grad_norm: 3.3039 (3.3021) time: 0.5029 [2021-03-27 06:12:54 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 650/1251] eta: 0:05:06 lr: 0.000026 loss: 2.8897 (2.7180) grad_norm: 3.3039 (3.3050) time: 0.5035 [2021-03-27 06:12:59 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 660/1251] eta: 0:05:01 lr: 0.000026 loss: 2.8378 (2.7145) grad_norm: 3.0698 (3.3027) time: 0.5057 [2021-03-27 06:13:04 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 670/1251] eta: 0:04:56 lr: 0.000026 loss: 2.8077 (2.7154) grad_norm: 3.0610 (3.3003) time: 0.5028 [2021-03-27 06:13:10 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 680/1251] eta: 0:04:51 lr: 0.000026 loss: 2.9782 (2.7162) grad_norm: 3.0867 (3.2975) time: 0.5083 [2021-03-27 06:13:15 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 690/1251] eta: 0:04:46 lr: 0.000026 loss: 2.8589 (2.7165) grad_norm: 3.0098 (3.2941) time: 0.5119 [2021-03-27 06:13:20 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 700/1251] eta: 0:04:41 lr: 0.000026 loss: 2.8963 (2.7168) grad_norm: 2.9740 (3.2899) time: 0.5037 [2021-03-27 06:13:25 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 710/1251] eta: 0:04:36 lr: 0.000026 loss: 2.6990 (2.7167) grad_norm: 3.0242 (3.2881) time: 0.5053 [2021-03-27 06:13:30 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 720/1251] eta: 0:04:30 lr: 0.000026 loss: 2.7746 (2.7192) grad_norm: 3.1381 (3.2898) time: 0.5085 [2021-03-27 06:13:35 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 730/1251] eta: 0:04:25 lr: 0.000026 loss: 2.8653 (2.7198) grad_norm: 3.2252 (3.2899) time: 0.5074 [2021-03-27 06:13:40 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 740/1251] eta: 0:04:20 lr: 0.000026 loss: 2.8653 (2.7220) grad_norm: 3.1485 (3.3011) time: 0.5176 [2021-03-27 06:13:45 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 750/1251] eta: 0:04:15 lr: 0.000026 loss: 2.8627 (2.7210) grad_norm: 3.1759 (3.3063) time: 0.5177 [2021-03-27 06:13:50 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 760/1251] eta: 0:04:10 lr: 0.000026 loss: 2.7774 (2.7207) grad_norm: 3.0888 (3.3035) time: 0.5042 [2021-03-27 06:13:55 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 770/1251] eta: 0:04:05 lr: 0.000026 loss: 2.8771 (2.7232) grad_norm: 2.9357 (3.2981) time: 0.5023 [2021-03-27 06:14:00 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 780/1251] eta: 0:04:00 lr: 0.000026 loss: 2.7605 (2.7229) grad_norm: 3.0380 (3.3017) time: 0.5020 [2021-03-27 06:14:05 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 790/1251] eta: 0:03:55 lr: 0.000026 loss: 2.7605 (2.7232) grad_norm: 3.1592 (3.3006) time: 0.5040 [2021-03-27 06:14:11 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 800/1251] eta: 0:03:49 lr: 0.000026 loss: 2.8340 (2.7243) grad_norm: 3.2824 (3.3017) time: 0.5088 [2021-03-27 06:14:16 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 810/1251] eta: 0:03:44 lr: 0.000026 loss: 2.8982 (2.7260) grad_norm: 3.1341 (3.2978) time: 0.5041 [2021-03-27 06:14:21 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 820/1251] eta: 0:03:39 lr: 0.000026 loss: 2.9338 (2.7270) grad_norm: 3.0436 (3.2972) time: 0.4997 [2021-03-27 06:14:26 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 830/1251] eta: 0:03:34 lr: 0.000026 loss: 2.9112 (2.7261) grad_norm: 3.1483 (3.3000) time: 0.5018 [2021-03-27 06:14:31 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 840/1251] eta: 0:03:29 lr: 0.000026 loss: 2.7575 (2.7261) grad_norm: 3.1613 (3.2979) time: 0.5034 [2021-03-27 06:14:36 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 850/1251] eta: 0:03:24 lr: 0.000026 loss: 2.7575 (2.7242) grad_norm: 3.0617 (3.2945) time: 0.5041 [2021-03-27 06:14:41 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 860/1251] eta: 0:03:19 lr: 0.000026 loss: 2.7645 (2.7234) grad_norm: 3.0540 (3.2918) time: 0.5088 [2021-03-27 06:14:46 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 870/1251] eta: 0:03:14 lr: 0.000026 loss: 2.5800 (2.7223) grad_norm: 3.0977 (3.2965) time: 0.5221 [2021-03-27 06:14:51 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 880/1251] eta: 0:03:09 lr: 0.000026 loss: 2.5800 (2.7212) grad_norm: 3.0412 (3.2942) time: 0.5179 [2021-03-27 06:14:56 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 890/1251] eta: 0:03:04 lr: 0.000026 loss: 2.7815 (2.7219) grad_norm: 3.0517 (3.2927) time: 0.5055 [2021-03-27 06:15:01 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 900/1251] eta: 0:02:58 lr: 0.000026 loss: 2.7840 (2.7232) grad_norm: 3.0711 (3.2901) time: 0.5106 [2021-03-27 06:15:06 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 910/1251] eta: 0:02:53 lr: 0.000026 loss: 2.7881 (2.7241) grad_norm: 2.9718 (3.2902) time: 0.5069 [2021-03-27 06:15:11 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 920/1251] eta: 0:02:48 lr: 0.000026 loss: 2.8114 (2.7247) grad_norm: 3.1823 (3.2881) time: 0.4993 [2021-03-27 06:15:16 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 930/1251] eta: 0:02:43 lr: 0.000026 loss: 2.7904 (2.7240) grad_norm: 3.2484 (3.2874) time: 0.4988 [2021-03-27 06:15:21 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 940/1251] eta: 0:02:38 lr: 0.000026 loss: 2.7904 (2.7254) grad_norm: 3.0646 (3.2884) time: 0.5062 [2021-03-27 06:15:27 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 950/1251] eta: 0:02:33 lr: 0.000026 loss: 2.8560 (2.7258) grad_norm: 3.0765 (3.2884) time: 0.5082 [2021-03-27 06:15:32 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 960/1251] eta: 0:02:28 lr: 0.000026 loss: 2.9052 (2.7266) grad_norm: 3.2206 (3.2895) time: 0.5047 [2021-03-27 06:15:37 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 970/1251] eta: 0:02:23 lr: 0.000026 loss: 2.8119 (2.7253) grad_norm: 3.1730 (3.2931) time: 0.5039 [2021-03-27 06:15:42 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 980/1251] eta: 0:02:18 lr: 0.000026 loss: 2.8119 (2.7247) grad_norm: 2.8623 (3.2901) time: 0.5045 [2021-03-27 06:15:47 swin_small_patch4_window7_224] INFO: Epoch: [275] [ 990/1251] eta: 0:02:12 lr: 0.000026 loss: 2.8704 (2.7244) grad_norm: 3.1949 (3.2950) time: 0.5020 [2021-03-27 06:15:52 swin_small_patch4_window7_224] INFO: Epoch: [275] [1000/1251] eta: 0:02:07 lr: 0.000026 loss: 2.7059 (2.7236) grad_norm: 3.2302 (3.2940) time: 0.5059 [2021-03-27 06:15:57 swin_small_patch4_window7_224] INFO: Epoch: [275] [1010/1251] eta: 0:02:02 lr: 0.000026 loss: 2.7033 (2.7238) grad_norm: 3.1351 (3.2976) time: 0.5071 [2021-03-27 06:16:02 swin_small_patch4_window7_224] INFO: Epoch: [275] [1020/1251] eta: 0:01:57 lr: 0.000026 loss: 2.7898 (2.7249) grad_norm: 3.1176 (3.2987) time: 0.5009 [2021-03-27 06:16:07 swin_small_patch4_window7_224] INFO: Epoch: [275] [1030/1251] eta: 0:01:52 lr: 0.000026 loss: 2.8900 (2.7246) grad_norm: 3.2075 (3.2988) time: 0.4989 [2021-03-27 06:16:12 swin_small_patch4_window7_224] INFO: Epoch: [275] [1040/1251] eta: 0:01:47 lr: 0.000026 loss: 2.8419 (2.7249) grad_norm: 3.1115 (3.2960) time: 0.5014 [2021-03-27 06:16:17 swin_small_patch4_window7_224] INFO: Epoch: [275] [1050/1251] eta: 0:01:42 lr: 0.000026 loss: 2.5737 (2.7229) grad_norm: 3.2104 (3.2976) time: 0.5035 [2021-03-27 06:16:22 swin_small_patch4_window7_224] INFO: Epoch: [275] [1060/1251] eta: 0:01:37 lr: 0.000026 loss: 2.6510 (2.7235) grad_norm: 3.2743 (3.2972) time: 0.5069 [2021-03-27 06:16:27 swin_small_patch4_window7_224] INFO: Epoch: [275] [1070/1251] eta: 0:01:32 lr: 0.000026 loss: 2.8616 (2.7243) grad_norm: 3.2407 (3.2979) time: 0.5118 [2021-03-27 06:16:32 swin_small_patch4_window7_224] INFO: Epoch: [275] [1080/1251] eta: 0:01:27 lr: 0.000026 loss: 2.6428 (2.7229) grad_norm: 3.1903 (3.2983) time: 0.5095 [2021-03-27 06:16:37 swin_small_patch4_window7_224] INFO: Epoch: [275] [1090/1251] eta: 0:01:21 lr: 0.000026 loss: 2.8715 (2.7253) grad_norm: 3.3183 (3.3037) time: 0.5108 [2021-03-27 06:16:42 swin_small_patch4_window7_224] INFO: Epoch: [275] [1100/1251] eta: 0:01:16 lr: 0.000026 loss: 2.9734 (2.7269) grad_norm: 3.1194 (3.3024) time: 0.5081 [2021-03-27 06:16:47 swin_small_patch4_window7_224] INFO: Epoch: [275] [1110/1251] eta: 0:01:11 lr: 0.000026 loss: 2.9570 (2.7274) grad_norm: 3.0887 (3.3015) time: 0.5017 [2021-03-27 06:16:52 swin_small_patch4_window7_224] INFO: Epoch: [275] [1120/1251] eta: 0:01:06 lr: 0.000026 loss: 2.8380 (2.7276) grad_norm: 3.1417 (3.2994) time: 0.4996 [2021-03-27 06:16:57 swin_small_patch4_window7_224] INFO: Epoch: [275] [1130/1251] eta: 0:01:01 lr: 0.000026 loss: 2.7139 (2.7264) grad_norm: 3.0585 (3.2996) time: 0.5050 [2021-03-27 06:17:02 swin_small_patch4_window7_224] INFO: Epoch: [275] [1140/1251] eta: 0:00:56 lr: 0.000026 loss: 2.6642 (2.7253) grad_norm: 3.4439 (3.3038) time: 0.5070 [2021-03-27 06:17:07 swin_small_patch4_window7_224] INFO: Epoch: [275] [1150/1251] eta: 0:00:51 lr: 0.000026 loss: 2.8775 (2.7273) grad_norm: 3.3155 (3.3044) time: 0.5004 [2021-03-27 06:17:13 swin_small_patch4_window7_224] INFO: Epoch: [275] [1160/1251] eta: 0:00:46 lr: 0.000026 loss: 2.9932 (2.7279) grad_norm: 3.1260 (3.3051) time: 0.5031 [2021-03-27 06:17:17 swin_small_patch4_window7_224] INFO: Epoch: [275] [1170/1251] eta: 0:00:41 lr: 0.000026 loss: 2.8560 (2.7279) grad_norm: 3.0277 (3.3039) time: 0.5018 [2021-03-27 06:17:22 swin_small_patch4_window7_224] INFO: Epoch: [275] [1180/1251] eta: 0:00:36 lr: 0.000026 loss: 2.9408 (2.7304) grad_norm: 3.0930 (3.3030) time: 0.4974 [2021-03-27 06:17:28 swin_small_patch4_window7_224] INFO: Epoch: [275] [1190/1251] eta: 0:00:31 lr: 0.000026 loss: 2.7821 (2.7290) grad_norm: 3.1219 (3.3036) time: 0.5107 [2021-03-27 06:17:33 swin_small_patch4_window7_224] INFO: Epoch: [275] [1200/1251] eta: 0:00:25 lr: 0.000026 loss: 2.6179 (2.7290) grad_norm: 3.1915 (3.3088) time: 0.5124 [2021-03-27 06:17:38 swin_small_patch4_window7_224] INFO: Epoch: [275] [1210/1251] eta: 0:00:20 lr: 0.000026 loss: 2.7613 (2.7288) grad_norm: 3.1121 (3.3095) time: 0.5092 [2021-03-27 06:17:43 swin_small_patch4_window7_224] INFO: Epoch: [275] [1220/1251] eta: 0:00:15 lr: 0.000026 loss: 2.5309 (2.7270) grad_norm: 3.0842 (3.3074) time: 0.5097 [2021-03-27 06:17:48 swin_small_patch4_window7_224] INFO: Epoch: [275] [1230/1251] eta: 0:00:10 lr: 0.000026 loss: 2.6116 (2.7267) grad_norm: 2.9405 (3.3045) time: 0.5033 [2021-03-27 06:17:53 swin_small_patch4_window7_224] INFO: Epoch: [275] [1240/1251] eta: 0:00:05 lr: 0.000026 loss: 2.7780 (2.7272) grad_norm: 3.1460 (3.3108) time: 0.5003 [2021-03-27 06:17:58 swin_small_patch4_window7_224] INFO: Epoch: [275] [1250/1251] eta: 0:00:00 lr: 0.000026 loss: 2.7221 (2.7265) grad_norm: 3.4221 (3.3101) time: 0.5035 [2021-03-27 06:18:56 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:11 loss: 0.6241 (0.6241) acc1: 89.0625 (89.0625) acc5: 96.8750 (96.8750) [2021-03-27 06:18:57 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.6920 (0.7323) acc1: 81.2500 (81.6761) acc5: 96.8750 (96.3068) [2021-03-27 06:18:58 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.6972 (0.7316) acc1: 81.2500 (82.0685) acc5: 96.8750 (96.5030) [2021-03-27 06:18:59 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7193 (0.7553) acc1: 81.2500 (82.0565) acc5: 96.8750 (96.4214) [2021-03-27 06:19:00 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7082 (0.7608) acc1: 81.2500 (81.7835) acc5: 95.3125 (95.8841) [2021-03-27 06:19:01 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7082 (0.7576) acc1: 81.2500 (81.9840) acc5: 95.3125 (96.0960) [2021-03-27 06:19:14 swin_small_patch4_window7_224] INFO: * Acc@1 82.844 Acc@5 96.224 loss 0.742 [2021-03-27 06:19:14 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 06:19:14 swin_small_patch4_window7_224] INFO: Max accuracy: 82.88% [2021-03-27 06:19:18 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 0/1251] eta: 1:27:16 lr: 0.000026 loss: 3.0566 (3.0566) grad_norm: 3.0959 (3.0959) time: 4.1856 [2021-03-27 06:19:23 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 10/1251] eta: 0:17:47 lr: 0.000026 loss: 2.3800 (2.5960) grad_norm: 3.1706 (3.3655) time: 0.8603 [2021-03-27 06:19:28 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 20/1251] eta: 0:14:08 lr: 0.000026 loss: 2.3800 (2.5611) grad_norm: 3.1908 (3.2839) time: 0.5143 [2021-03-27 06:19:34 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 30/1251] eta: 0:12:56 lr: 0.000026 loss: 2.8726 (2.6602) grad_norm: 3.1206 (3.2558) time: 0.5127 [2021-03-27 06:19:39 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 40/1251] eta: 0:12:13 lr: 0.000026 loss: 2.9069 (2.6967) grad_norm: 3.1322 (3.2385) time: 0.5186 [2021-03-27 06:19:44 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 50/1251] eta: 0:11:44 lr: 0.000025 loss: 2.8140 (2.7182) grad_norm: 3.1322 (3.2436) time: 0.5107 [2021-03-27 06:19:49 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 60/1251] eta: 0:11:22 lr: 0.000025 loss: 2.7881 (2.6832) grad_norm: 3.2262 (3.4250) time: 0.5064 [2021-03-27 06:19:54 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 70/1251] eta: 0:11:06 lr: 0.000025 loss: 2.6530 (2.6992) grad_norm: 3.2316 (3.3973) time: 0.5062 [2021-03-27 06:19:59 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 80/1251] eta: 0:10:51 lr: 0.000025 loss: 2.8203 (2.7042) grad_norm: 3.0557 (3.3570) time: 0.5044 [2021-03-27 06:20:04 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 90/1251] eta: 0:10:38 lr: 0.000025 loss: 2.7615 (2.7013) grad_norm: 3.0747 (3.3382) time: 0.5012 [2021-03-27 06:20:09 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 100/1251] eta: 0:10:27 lr: 0.000025 loss: 2.6920 (2.7063) grad_norm: 3.0594 (3.3139) time: 0.5012 [2021-03-27 06:20:14 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 110/1251] eta: 0:10:19 lr: 0.000025 loss: 2.6920 (2.6991) grad_norm: 2.9207 (3.2857) time: 0.5084 [2021-03-27 06:20:19 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 120/1251] eta: 0:10:09 lr: 0.000025 loss: 2.5251 (2.6906) grad_norm: 2.8747 (3.2563) time: 0.5068 [2021-03-27 06:20:24 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 130/1251] eta: 0:10:02 lr: 0.000025 loss: 2.7241 (2.6953) grad_norm: 2.8590 (3.2798) time: 0.5100 [2021-03-27 06:20:29 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 140/1251] eta: 0:09:54 lr: 0.000025 loss: 2.8045 (2.7060) grad_norm: 3.1855 (3.2797) time: 0.5137 [2021-03-27 06:20:34 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 150/1251] eta: 0:09:47 lr: 0.000025 loss: 2.7461 (2.6999) grad_norm: 3.1861 (3.3057) time: 0.5048 [2021-03-27 06:20:39 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 160/1251] eta: 0:09:40 lr: 0.000025 loss: 2.6347 (2.7049) grad_norm: 3.3335 (3.3482) time: 0.5059 [2021-03-27 06:20:44 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 170/1251] eta: 0:09:32 lr: 0.000025 loss: 2.6509 (2.7056) grad_norm: 3.3376 (3.3465) time: 0.5017 [2021-03-27 06:20:50 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 180/1251] eta: 0:09:25 lr: 0.000025 loss: 2.5556 (2.7011) grad_norm: 3.0987 (3.3354) time: 0.5020 [2021-03-27 06:20:55 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 190/1251] eta: 0:09:19 lr: 0.000025 loss: 2.6830 (2.7056) grad_norm: 3.3189 (3.3353) time: 0.5116 [2021-03-27 06:21:00 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 200/1251] eta: 0:09:13 lr: 0.000025 loss: 2.9233 (2.7185) grad_norm: 3.2879 (3.3306) time: 0.5094 [2021-03-27 06:21:05 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 210/1251] eta: 0:09:07 lr: 0.000025 loss: 2.8316 (2.7159) grad_norm: 3.0931 (3.3222) time: 0.5043 [2021-03-27 06:21:10 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 220/1251] eta: 0:09:00 lr: 0.000025 loss: 2.7569 (2.7223) grad_norm: 3.0724 (3.3100) time: 0.5027 [2021-03-27 06:21:15 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 230/1251] eta: 0:08:54 lr: 0.000025 loss: 2.8567 (2.7286) grad_norm: 3.1899 (3.3230) time: 0.4986 [2021-03-27 06:21:20 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 240/1251] eta: 0:08:48 lr: 0.000025 loss: 2.8567 (2.7283) grad_norm: 3.2995 (3.3168) time: 0.4988 [2021-03-27 06:21:25 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 250/1251] eta: 0:08:42 lr: 0.000025 loss: 2.6846 (2.7208) grad_norm: 3.1006 (3.3078) time: 0.5031 [2021-03-27 06:21:30 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 260/1251] eta: 0:08:35 lr: 0.000025 loss: 2.8544 (2.7294) grad_norm: 3.1934 (3.3097) time: 0.4986 [2021-03-27 06:21:35 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 270/1251] eta: 0:08:30 lr: 0.000025 loss: 2.7562 (2.7176) grad_norm: 3.2156 (3.3031) time: 0.4985 [2021-03-27 06:21:40 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 280/1251] eta: 0:08:24 lr: 0.000025 loss: 2.5916 (2.7113) grad_norm: 3.0949 (3.3235) time: 0.5053 [2021-03-27 06:21:45 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 290/1251] eta: 0:08:18 lr: 0.000025 loss: 2.5640 (2.7011) grad_norm: 3.0529 (3.3188) time: 0.5036 [2021-03-27 06:21:50 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 300/1251] eta: 0:08:12 lr: 0.000025 loss: 2.6971 (2.7038) grad_norm: 3.1339 (3.3137) time: 0.4986 [2021-03-27 06:21:55 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 310/1251] eta: 0:08:07 lr: 0.000025 loss: 2.8325 (2.7093) grad_norm: 3.0162 (3.3098) time: 0.5042 [2021-03-27 06:22:00 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 320/1251] eta: 0:08:02 lr: 0.000025 loss: 2.7536 (2.7080) grad_norm: 3.0069 (3.3033) time: 0.5137 [2021-03-27 06:22:05 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 330/1251] eta: 0:07:56 lr: 0.000025 loss: 2.7536 (2.7115) grad_norm: 3.0400 (3.2932) time: 0.5068 [2021-03-27 06:22:10 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 340/1251] eta: 0:07:50 lr: 0.000025 loss: 2.9326 (2.7132) grad_norm: 2.9529 (3.2860) time: 0.5024 [2021-03-27 06:22:15 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 350/1251] eta: 0:07:45 lr: 0.000025 loss: 3.0829 (2.7269) grad_norm: 2.9529 (3.2826) time: 0.5021 [2021-03-27 06:22:20 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 360/1251] eta: 0:07:39 lr: 0.000025 loss: 2.9698 (2.7260) grad_norm: 3.1801 (3.2839) time: 0.5013 [2021-03-27 06:22:25 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 370/1251] eta: 0:07:34 lr: 0.000025 loss: 2.8754 (2.7256) grad_norm: 3.2092 (3.2934) time: 0.5132 [2021-03-27 06:22:31 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 380/1251] eta: 0:07:29 lr: 0.000025 loss: 2.8877 (2.7310) grad_norm: 3.1361 (3.2881) time: 0.5238 [2021-03-27 06:22:36 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 390/1251] eta: 0:07:24 lr: 0.000025 loss: 2.7077 (2.7244) grad_norm: 3.0307 (3.2797) time: 0.5120 [2021-03-27 06:22:41 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 400/1251] eta: 0:07:18 lr: 0.000025 loss: 2.6885 (2.7231) grad_norm: 3.0371 (3.2749) time: 0.5035 [2021-03-27 06:22:46 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 410/1251] eta: 0:07:13 lr: 0.000025 loss: 2.7175 (2.7259) grad_norm: 2.9825 (3.2678) time: 0.5106 [2021-03-27 06:22:51 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 420/1251] eta: 0:07:08 lr: 0.000025 loss: 2.7403 (2.7203) grad_norm: 2.8763 (3.2604) time: 0.5096 [2021-03-27 06:22:56 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 430/1251] eta: 0:07:02 lr: 0.000025 loss: 2.6314 (2.7213) grad_norm: 3.0291 (3.2579) time: 0.5019 [2021-03-27 06:23:01 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 440/1251] eta: 0:06:57 lr: 0.000025 loss: 2.7945 (2.7238) grad_norm: 3.1674 (3.2577) time: 0.5059 [2021-03-27 06:23:06 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 450/1251] eta: 0:06:52 lr: 0.000025 loss: 2.8306 (2.7253) grad_norm: 3.2080 (3.2647) time: 0.5099 [2021-03-27 06:23:11 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 460/1251] eta: 0:06:46 lr: 0.000025 loss: 2.8057 (2.7255) grad_norm: 3.1768 (3.2608) time: 0.5033 [2021-03-27 06:23:16 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 470/1251] eta: 0:06:41 lr: 0.000025 loss: 2.7373 (2.7228) grad_norm: 3.1016 (3.2577) time: 0.5065 [2021-03-27 06:23:21 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 480/1251] eta: 0:06:36 lr: 0.000025 loss: 2.7466 (2.7227) grad_norm: 3.1632 (3.2618) time: 0.5110 [2021-03-27 06:23:26 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 490/1251] eta: 0:06:31 lr: 0.000025 loss: 2.8417 (2.7233) grad_norm: 3.6216 (3.2713) time: 0.5051 [2021-03-27 06:23:31 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 500/1251] eta: 0:06:26 lr: 0.000025 loss: 2.8417 (2.7226) grad_norm: 3.3962 (3.2684) time: 0.5049 [2021-03-27 06:23:37 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 510/1251] eta: 0:06:20 lr: 0.000025 loss: 2.5995 (2.7210) grad_norm: 2.9565 (3.2612) time: 0.5109 [2021-03-27 06:23:42 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 520/1251] eta: 0:06:15 lr: 0.000025 loss: 2.8057 (2.7222) grad_norm: 2.9939 (3.2643) time: 0.5087 [2021-03-27 06:23:47 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 530/1251] eta: 0:06:10 lr: 0.000025 loss: 2.8236 (2.7224) grad_norm: 3.1369 (3.2750) time: 0.5035 [2021-03-27 06:23:52 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 540/1251] eta: 0:06:05 lr: 0.000025 loss: 2.8585 (2.7269) grad_norm: 3.0796 (3.2763) time: 0.5028 [2021-03-27 06:23:57 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 550/1251] eta: 0:05:59 lr: 0.000025 loss: 2.8912 (2.7242) grad_norm: 3.1448 (3.2770) time: 0.5110 [2021-03-27 06:24:02 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 560/1251] eta: 0:05:54 lr: 0.000025 loss: 2.6864 (2.7238) grad_norm: 3.2519 (3.2778) time: 0.5106 [2021-03-27 06:24:07 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 570/1251] eta: 0:05:49 lr: 0.000025 loss: 2.8289 (2.7263) grad_norm: 3.0950 (3.2733) time: 0.5092 [2021-03-27 06:24:12 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 580/1251] eta: 0:05:44 lr: 0.000025 loss: 2.9174 (2.7301) grad_norm: 3.0876 (3.2736) time: 0.5137 [2021-03-27 06:24:17 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 590/1251] eta: 0:05:39 lr: 0.000025 loss: 2.6772 (2.7293) grad_norm: 3.2536 (3.2841) time: 0.5134 [2021-03-27 06:24:22 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 600/1251] eta: 0:05:34 lr: 0.000025 loss: 2.6199 (2.7306) grad_norm: 3.3737 (3.2853) time: 0.5125 [2021-03-27 06:24:27 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 610/1251] eta: 0:05:28 lr: 0.000025 loss: 2.6919 (2.7267) grad_norm: 3.3236 (3.2864) time: 0.5040 [2021-03-27 06:24:32 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 620/1251] eta: 0:05:23 lr: 0.000025 loss: 2.6679 (2.7254) grad_norm: 3.2304 (3.2985) time: 0.5025 [2021-03-27 06:24:37 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 630/1251] eta: 0:05:18 lr: 0.000025 loss: 2.8162 (2.7275) grad_norm: 3.1665 (3.2978) time: 0.5021 [2021-03-27 06:24:42 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 640/1251] eta: 0:05:13 lr: 0.000025 loss: 2.8243 (2.7286) grad_norm: 3.2257 (3.3000) time: 0.5005 [2021-03-27 06:24:48 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 650/1251] eta: 0:05:07 lr: 0.000025 loss: 2.7332 (2.7245) grad_norm: 3.2044 (3.2955) time: 0.5036 [2021-03-27 06:24:53 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 660/1251] eta: 0:05:02 lr: 0.000025 loss: 2.8090 (2.7275) grad_norm: 3.1116 (3.2947) time: 0.5015 [2021-03-27 06:24:58 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 670/1251] eta: 0:04:57 lr: 0.000025 loss: 2.8090 (2.7277) grad_norm: 3.0107 (3.2942) time: 0.4998 [2021-03-27 06:25:02 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 680/1251] eta: 0:04:52 lr: 0.000025 loss: 2.6629 (2.7245) grad_norm: 3.1007 (3.2946) time: 0.4993 [2021-03-27 06:25:08 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 690/1251] eta: 0:04:47 lr: 0.000025 loss: 2.7069 (2.7248) grad_norm: 3.1636 (3.2911) time: 0.5009 [2021-03-27 06:25:13 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 700/1251] eta: 0:04:41 lr: 0.000025 loss: 2.8664 (2.7255) grad_norm: 3.1636 (3.2898) time: 0.5003 [2021-03-27 06:25:18 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 710/1251] eta: 0:04:36 lr: 0.000025 loss: 2.8863 (2.7283) grad_norm: 3.1945 (3.2937) time: 0.4994 [2021-03-27 06:25:23 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 720/1251] eta: 0:04:31 lr: 0.000025 loss: 2.9103 (2.7296) grad_norm: 3.2771 (3.2971) time: 0.5009 [2021-03-27 06:25:28 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 730/1251] eta: 0:04:26 lr: 0.000025 loss: 2.9429 (2.7316) grad_norm: 3.2771 (3.2977) time: 0.5039 [2021-03-27 06:25:33 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 740/1251] eta: 0:04:21 lr: 0.000025 loss: 2.9441 (2.7331) grad_norm: 3.0371 (3.2988) time: 0.5150 [2021-03-27 06:25:38 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 750/1251] eta: 0:04:16 lr: 0.000025 loss: 2.7783 (2.7324) grad_norm: 3.1295 (3.3020) time: 0.5099 [2021-03-27 06:25:43 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 760/1251] eta: 0:04:10 lr: 0.000025 loss: 2.6826 (2.7333) grad_norm: 3.2827 (3.3058) time: 0.4983 [2021-03-27 06:25:48 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 770/1251] eta: 0:04:05 lr: 0.000025 loss: 2.7717 (2.7333) grad_norm: 2.9767 (3.3077) time: 0.5035 [2021-03-27 06:25:53 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 780/1251] eta: 0:04:00 lr: 0.000025 loss: 2.7128 (2.7319) grad_norm: 2.9767 (3.3047) time: 0.5097 [2021-03-27 06:25:58 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 790/1251] eta: 0:03:55 lr: 0.000025 loss: 2.8987 (2.7361) grad_norm: 3.0328 (3.3083) time: 0.5128 [2021-03-27 06:26:03 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 800/1251] eta: 0:03:50 lr: 0.000025 loss: 2.9792 (2.7353) grad_norm: 3.2497 (3.3096) time: 0.5143 [2021-03-27 06:26:08 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 810/1251] eta: 0:03:45 lr: 0.000025 loss: 2.8204 (2.7355) grad_norm: 3.0654 (3.3073) time: 0.5091 [2021-03-27 06:26:13 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 820/1251] eta: 0:03:40 lr: 0.000025 loss: 2.5639 (2.7332) grad_norm: 3.1112 (3.3079) time: 0.5031 [2021-03-27 06:26:18 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 830/1251] eta: 0:03:35 lr: 0.000025 loss: 2.5285 (2.7313) grad_norm: 3.3365 (3.3120) time: 0.5039 [2021-03-27 06:26:24 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 840/1251] eta: 0:03:29 lr: 0.000025 loss: 2.5033 (2.7298) grad_norm: 3.2070 (3.3084) time: 0.5081 [2021-03-27 06:26:29 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 850/1251] eta: 0:03:24 lr: 0.000025 loss: 2.7911 (2.7308) grad_norm: 3.0801 (3.3069) time: 0.5080 [2021-03-27 06:26:34 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 860/1251] eta: 0:03:19 lr: 0.000025 loss: 2.9242 (2.7326) grad_norm: 3.1297 (3.3066) time: 0.5031 [2021-03-27 06:26:39 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 870/1251] eta: 0:03:14 lr: 0.000025 loss: 2.9242 (2.7335) grad_norm: 2.9886 (3.3023) time: 0.5058 [2021-03-27 06:26:44 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 880/1251] eta: 0:03:09 lr: 0.000025 loss: 2.9115 (2.7366) grad_norm: 2.9947 (3.3033) time: 0.5027 [2021-03-27 06:26:49 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 890/1251] eta: 0:03:04 lr: 0.000025 loss: 2.9115 (2.7376) grad_norm: 2.9947 (3.2995) time: 0.5024 [2021-03-27 06:26:54 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 900/1251] eta: 0:02:59 lr: 0.000025 loss: 2.8206 (2.7382) grad_norm: 2.9834 (3.2964) time: 0.5040 [2021-03-27 06:26:59 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 910/1251] eta: 0:02:53 lr: 0.000025 loss: 2.8157 (2.7366) grad_norm: 3.0321 (3.2943) time: 0.5037 [2021-03-27 06:27:04 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 920/1251] eta: 0:02:48 lr: 0.000025 loss: 2.6847 (2.7352) grad_norm: 2.9412 (3.2931) time: 0.5081 [2021-03-27 06:27:09 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 930/1251] eta: 0:02:43 lr: 0.000025 loss: 2.6111 (2.7334) grad_norm: 3.0153 (3.2922) time: 0.5072 [2021-03-27 06:27:14 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 940/1251] eta: 0:02:38 lr: 0.000025 loss: 2.6111 (2.7319) grad_norm: 3.0707 (3.2911) time: 0.5046 [2021-03-27 06:27:19 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 950/1251] eta: 0:02:33 lr: 0.000025 loss: 2.8459 (2.7336) grad_norm: 3.1857 (3.2921) time: 0.5049 [2021-03-27 06:27:24 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 960/1251] eta: 0:02:28 lr: 0.000025 loss: 2.8639 (2.7330) grad_norm: 3.3273 (3.2955) time: 0.5035 [2021-03-27 06:27:29 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 970/1251] eta: 0:02:23 lr: 0.000025 loss: 2.7065 (2.7320) grad_norm: 3.0907 (3.2925) time: 0.5019 [2021-03-27 06:27:34 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 980/1251] eta: 0:02:18 lr: 0.000025 loss: 2.8751 (2.7336) grad_norm: 3.0907 (3.2910) time: 0.5024 [2021-03-27 06:27:39 swin_small_patch4_window7_224] INFO: Epoch: [276] [ 990/1251] eta: 0:02:13 lr: 0.000025 loss: 2.7570 (2.7325) grad_norm: 3.1299 (3.2954) time: 0.5064 [2021-03-27 06:27:44 swin_small_patch4_window7_224] INFO: Epoch: [276] [1000/1251] eta: 0:02:07 lr: 0.000025 loss: 2.7363 (2.7324) grad_norm: 3.1181 (3.2957) time: 0.5041 [2021-03-27 06:27:49 swin_small_patch4_window7_224] INFO: Epoch: [276] [1010/1251] eta: 0:02:02 lr: 0.000025 loss: 2.8957 (2.7337) grad_norm: 3.0838 (3.2934) time: 0.4935 [2021-03-27 06:27:54 swin_small_patch4_window7_224] INFO: Epoch: [276] [1020/1251] eta: 0:01:57 lr: 0.000025 loss: 2.6752 (2.7332) grad_norm: 3.0953 (3.2955) time: 0.4972 [2021-03-27 06:27:59 swin_small_patch4_window7_224] INFO: Epoch: [276] [1030/1251] eta: 0:01:52 lr: 0.000025 loss: 2.6816 (2.7327) grad_norm: 3.0200 (3.2923) time: 0.5039 [2021-03-27 06:28:04 swin_small_patch4_window7_224] INFO: Epoch: [276] [1040/1251] eta: 0:01:47 lr: 0.000024 loss: 2.8273 (2.7327) grad_norm: 3.1273 (3.2947) time: 0.5061 [2021-03-27 06:28:09 swin_small_patch4_window7_224] INFO: Epoch: [276] [1050/1251] eta: 0:01:42 lr: 0.000024 loss: 2.5873 (2.7321) grad_norm: 3.4150 (3.2972) time: 0.5064 [2021-03-27 06:28:14 swin_small_patch4_window7_224] INFO: Epoch: [276] [1060/1251] eta: 0:01:37 lr: 0.000024 loss: 2.7138 (2.7330) grad_norm: 3.2214 (3.2954) time: 0.5077 [2021-03-27 06:28:19 swin_small_patch4_window7_224] INFO: Epoch: [276] [1070/1251] eta: 0:01:32 lr: 0.000024 loss: 2.7280 (2.7318) grad_norm: 3.0486 (3.2937) time: 0.5049 [2021-03-27 06:28:25 swin_small_patch4_window7_224] INFO: Epoch: [276] [1080/1251] eta: 0:01:27 lr: 0.000024 loss: 2.7322 (2.7322) grad_norm: 3.0131 (nan) time: 0.5057 [2021-03-27 06:28:30 swin_small_patch4_window7_224] INFO: Epoch: [276] [1090/1251] eta: 0:01:21 lr: 0.000024 loss: 2.8537 (2.7331) grad_norm: 3.1688 (nan) time: 0.5070 [2021-03-27 06:28:34 swin_small_patch4_window7_224] INFO: Epoch: [276] [1100/1251] eta: 0:01:16 lr: 0.000024 loss: 2.8698 (2.7327) grad_norm: 3.1097 (nan) time: 0.4964 [2021-03-27 06:28:40 swin_small_patch4_window7_224] INFO: Epoch: [276] [1110/1251] eta: 0:01:11 lr: 0.000024 loss: 2.5957 (2.7324) grad_norm: 3.0643 (nan) time: 0.4973 [2021-03-27 06:28:45 swin_small_patch4_window7_224] INFO: Epoch: [276] [1120/1251] eta: 0:01:06 lr: 0.000024 loss: 2.9285 (2.7340) grad_norm: 3.0233 (nan) time: 0.5050 [2021-03-27 06:28:50 swin_small_patch4_window7_224] INFO: Epoch: [276] [1130/1251] eta: 0:01:01 lr: 0.000024 loss: 2.9344 (2.7332) grad_norm: 3.1373 (nan) time: 0.5104 [2021-03-27 06:28:55 swin_small_patch4_window7_224] INFO: Epoch: [276] [1140/1251] eta: 0:00:56 lr: 0.000024 loss: 2.8686 (2.7343) grad_norm: 3.1373 (nan) time: 0.5112 [2021-03-27 06:29:00 swin_small_patch4_window7_224] INFO: Epoch: [276] [1150/1251] eta: 0:00:51 lr: 0.000024 loss: 2.8838 (2.7333) grad_norm: 3.0870 (nan) time: 0.5069 [2021-03-27 06:29:05 swin_small_patch4_window7_224] INFO: Epoch: [276] [1160/1251] eta: 0:00:46 lr: 0.000024 loss: 2.8665 (2.7329) grad_norm: 3.1229 (nan) time: 0.5065 [2021-03-27 06:29:10 swin_small_patch4_window7_224] INFO: Epoch: [276] [1170/1251] eta: 0:00:41 lr: 0.000024 loss: 2.7061 (2.7334) grad_norm: 3.0850 (nan) time: 0.5072 [2021-03-27 06:29:15 swin_small_patch4_window7_224] INFO: Epoch: [276] [1180/1251] eta: 0:00:36 lr: 0.000024 loss: 2.6413 (2.7327) grad_norm: 3.0850 (nan) time: 0.5090 [2021-03-27 06:29:20 swin_small_patch4_window7_224] INFO: Epoch: [276] [1190/1251] eta: 0:00:31 lr: 0.000024 loss: 2.8002 (2.7336) grad_norm: 3.2174 (nan) time: 0.5079 [2021-03-27 06:29:25 swin_small_patch4_window7_224] INFO: Epoch: [276] [1200/1251] eta: 0:00:25 lr: 0.000024 loss: 2.9792 (2.7327) grad_norm: 3.2302 (nan) time: 0.5029 [2021-03-27 06:29:30 swin_small_patch4_window7_224] INFO: Epoch: [276] [1210/1251] eta: 0:00:20 lr: 0.000024 loss: 2.7222 (2.7322) grad_norm: 3.0631 (nan) time: 0.4989 [2021-03-27 06:29:35 swin_small_patch4_window7_224] INFO: Epoch: [276] [1220/1251] eta: 0:00:15 lr: 0.000024 loss: 2.8139 (2.7333) grad_norm: 3.0631 (nan) time: 0.4980 [2021-03-27 06:29:40 swin_small_patch4_window7_224] INFO: Epoch: [276] [1230/1251] eta: 0:00:10 lr: 0.000024 loss: 2.8061 (2.7328) grad_norm: 3.1721 (nan) time: 0.5000 [2021-03-27 06:29:45 swin_small_patch4_window7_224] INFO: Epoch: [276] [1240/1251] eta: 0:00:05 lr: 0.000024 loss: 2.6224 (2.7317) grad_norm: 3.4472 (nan) time: 0.5029 [2021-03-27 06:29:50 swin_small_patch4_window7_224] INFO: Epoch: [276] [1250/1251] eta: 0:00:00 lr: 0.000024 loss: 2.6224 (2.7306) grad_norm: 3.3038 (nan) time: 0.5045 [2021-03-27 06:30:04 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:53 loss: 0.7080 (0.7080) acc1: 85.9375 (85.9375) acc5: 96.8750 (96.8750) [2021-03-27 06:30:06 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7012 (0.6588) acc1: 84.3750 (84.8011) acc5: 96.8750 (96.7330) [2021-03-27 06:30:09 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7212 (0.7001) acc1: 82.8125 (83.1101) acc5: 96.8750 (96.6518) [2021-03-27 06:30:10 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7504 (0.7151) acc1: 81.2500 (82.9637) acc5: 96.8750 (96.7238) [2021-03-27 06:30:12 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7711 (0.7446) acc1: 82.8125 (82.2027) acc5: 96.8750 (96.3796) [2021-03-27 06:30:14 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8288 (0.7528) acc1: 81.2500 (82.0800) acc5: 95.3125 (96.0640) [2021-03-27 06:30:29 swin_small_patch4_window7_224] INFO: * Acc@1 82.848 Acc@5 96.230 loss 0.740 [2021-03-27 06:30:29 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 06:30:29 swin_small_patch4_window7_224] INFO: Max accuracy: 82.88% [2021-03-27 06:30:33 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 0/1251] eta: 1:31:21 lr: 0.000024 loss: 2.1203 (2.1203) grad_norm: 2.6727 (2.6727) time: 4.3821 [2021-03-27 06:30:38 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 10/1251] eta: 0:17:40 lr: 0.000024 loss: 2.6095 (2.6389) grad_norm: 3.1724 (3.2727) time: 0.8546 [2021-03-27 06:30:43 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 20/1251] eta: 0:14:09 lr: 0.000024 loss: 2.7644 (2.6929) grad_norm: 3.2813 (3.2786) time: 0.5059 [2021-03-27 06:30:48 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 30/1251] eta: 0:12:56 lr: 0.000024 loss: 2.7375 (2.6755) grad_norm: 3.3038 (3.4562) time: 0.5152 [2021-03-27 06:30:53 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 40/1251] eta: 0:12:15 lr: 0.000024 loss: 2.6484 (2.6914) grad_norm: 3.3073 (3.4519) time: 0.5199 [2021-03-27 06:30:59 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 50/1251] eta: 0:11:46 lr: 0.000024 loss: 2.6795 (2.6637) grad_norm: 3.2529 (3.4058) time: 0.5156 [2021-03-27 06:31:04 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 60/1251] eta: 0:11:22 lr: 0.000024 loss: 2.8242 (2.6900) grad_norm: 3.2529 (3.4106) time: 0.5035 [2021-03-27 06:31:09 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 70/1251] eta: 0:11:05 lr: 0.000024 loss: 2.8987 (2.7137) grad_norm: 3.2644 (3.4125) time: 0.5010 [2021-03-27 06:31:14 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 80/1251] eta: 0:10:52 lr: 0.000024 loss: 2.7653 (2.7064) grad_norm: 3.1496 (3.4238) time: 0.5099 [2021-03-27 06:31:19 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 90/1251] eta: 0:10:40 lr: 0.000024 loss: 2.7728 (2.7106) grad_norm: 2.9919 (3.3694) time: 0.5092 [2021-03-27 06:31:24 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 100/1251] eta: 0:10:29 lr: 0.000024 loss: 2.7728 (2.6976) grad_norm: 3.0049 (3.4087) time: 0.5039 [2021-03-27 06:31:29 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 110/1251] eta: 0:10:20 lr: 0.000024 loss: 2.6005 (2.6895) grad_norm: 3.1566 (3.3906) time: 0.5060 [2021-03-27 06:31:34 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 120/1251] eta: 0:10:11 lr: 0.000024 loss: 2.7312 (2.6887) grad_norm: 3.0887 (3.3811) time: 0.5080 [2021-03-27 06:31:39 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 130/1251] eta: 0:10:04 lr: 0.000024 loss: 2.8327 (2.6943) grad_norm: 3.4617 (3.4383) time: 0.5122 [2021-03-27 06:31:44 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 140/1251] eta: 0:09:55 lr: 0.000024 loss: 2.8091 (2.6965) grad_norm: 3.4735 (3.4151) time: 0.5081 [2021-03-27 06:31:49 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 150/1251] eta: 0:09:48 lr: 0.000024 loss: 2.7946 (2.6975) grad_norm: 3.1711 (3.4006) time: 0.5036 [2021-03-27 06:31:54 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 160/1251] eta: 0:09:40 lr: 0.000024 loss: 2.8636 (2.7058) grad_norm: 3.0955 (3.3818) time: 0.5045 [2021-03-27 06:31:59 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 170/1251] eta: 0:09:33 lr: 0.000024 loss: 2.8636 (2.6955) grad_norm: 3.1265 (3.3789) time: 0.5002 [2021-03-27 06:32:04 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 180/1251] eta: 0:09:25 lr: 0.000024 loss: 2.5475 (2.6904) grad_norm: 3.0442 (3.3736) time: 0.4992 [2021-03-27 06:32:09 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 190/1251] eta: 0:09:19 lr: 0.000024 loss: 2.5227 (2.6799) grad_norm: 3.0069 (3.3655) time: 0.5001 [2021-03-27 06:32:14 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 200/1251] eta: 0:09:13 lr: 0.000024 loss: 2.5812 (2.6754) grad_norm: 3.0105 (3.3517) time: 0.5086 [2021-03-27 06:32:19 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 210/1251] eta: 0:09:06 lr: 0.000024 loss: 2.6985 (2.6774) grad_norm: 3.1182 (3.3500) time: 0.5049 [2021-03-27 06:32:24 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 220/1251] eta: 0:09:00 lr: 0.000024 loss: 2.7769 (2.6812) grad_norm: 3.1182 (3.3394) time: 0.4973 [2021-03-27 06:32:29 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 230/1251] eta: 0:08:54 lr: 0.000024 loss: 2.8121 (2.6897) grad_norm: 3.0314 (3.3351) time: 0.5057 [2021-03-27 06:32:35 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 240/1251] eta: 0:08:48 lr: 0.000024 loss: 2.8832 (2.6970) grad_norm: 3.0225 (3.3331) time: 0.5085 [2021-03-27 06:32:40 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 250/1251] eta: 0:08:43 lr: 0.000024 loss: 2.8093 (2.6984) grad_norm: 3.1445 (3.3489) time: 0.5141 [2021-03-27 06:32:45 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 260/1251] eta: 0:08:37 lr: 0.000024 loss: 2.8071 (2.6968) grad_norm: 3.2987 (3.3505) time: 0.5130 [2021-03-27 06:32:50 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 270/1251] eta: 0:08:31 lr: 0.000024 loss: 2.7168 (2.6937) grad_norm: 3.2987 (3.3796) time: 0.5020 [2021-03-27 06:32:55 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 280/1251] eta: 0:08:25 lr: 0.000024 loss: 2.8204 (2.7025) grad_norm: 3.2873 (3.3790) time: 0.5047 [2021-03-27 06:33:00 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 290/1251] eta: 0:08:19 lr: 0.000024 loss: 2.8271 (2.7032) grad_norm: 3.3698 (3.3808) time: 0.5058 [2021-03-27 06:33:05 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 300/1251] eta: 0:08:14 lr: 0.000024 loss: 2.7347 (2.7036) grad_norm: 3.1426 (3.3731) time: 0.5096 [2021-03-27 06:33:10 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 310/1251] eta: 0:08:08 lr: 0.000024 loss: 2.8081 (2.7037) grad_norm: 3.1426 (3.3684) time: 0.5092 [2021-03-27 06:33:15 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 320/1251] eta: 0:08:02 lr: 0.000024 loss: 2.7783 (2.7011) grad_norm: 3.1723 (3.3667) time: 0.4973 [2021-03-27 06:33:20 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 330/1251] eta: 0:07:57 lr: 0.000024 loss: 2.6975 (2.6976) grad_norm: 3.3147 (3.3700) time: 0.4983 [2021-03-27 06:33:25 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 340/1251] eta: 0:07:51 lr: 0.000024 loss: 2.8176 (2.7050) grad_norm: 3.1444 (3.3686) time: 0.5024 [2021-03-27 06:33:30 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 350/1251] eta: 0:07:45 lr: 0.000024 loss: 2.9342 (2.7118) grad_norm: 2.9730 (3.3787) time: 0.4989 [2021-03-27 06:33:35 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 360/1251] eta: 0:07:39 lr: 0.000024 loss: 2.9342 (2.7179) grad_norm: 3.0497 (3.3719) time: 0.4951 [2021-03-27 06:33:40 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 370/1251] eta: 0:07:34 lr: 0.000024 loss: 2.8851 (2.7186) grad_norm: 3.1749 (3.3921) time: 0.4979 [2021-03-27 06:33:45 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 380/1251] eta: 0:07:29 lr: 0.000024 loss: 2.8490 (2.7199) grad_norm: 3.3121 (3.3941) time: 0.5031 [2021-03-27 06:33:50 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 390/1251] eta: 0:07:23 lr: 0.000024 loss: 2.8856 (2.7238) grad_norm: 3.1510 (3.3937) time: 0.5001 [2021-03-27 06:33:55 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 400/1251] eta: 0:07:18 lr: 0.000024 loss: 2.6915 (2.7170) grad_norm: 2.8871 (3.3829) time: 0.4989 [2021-03-27 06:34:00 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 410/1251] eta: 0:07:12 lr: 0.000024 loss: 2.5797 (2.7121) grad_norm: 2.9304 (3.3793) time: 0.5009 [2021-03-27 06:34:05 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 420/1251] eta: 0:07:07 lr: 0.000024 loss: 2.7539 (2.7141) grad_norm: 2.9545 (3.3716) time: 0.4993 [2021-03-27 06:34:10 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 430/1251] eta: 0:07:01 lr: 0.000024 loss: 2.8618 (2.7098) grad_norm: 2.9742 (3.3719) time: 0.5038 [2021-03-27 06:34:15 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 440/1251] eta: 0:06:56 lr: 0.000024 loss: 2.7788 (2.7092) grad_norm: 2.9962 (3.3642) time: 0.5064 [2021-03-27 06:34:20 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 450/1251] eta: 0:06:51 lr: 0.000024 loss: 2.8373 (2.7121) grad_norm: 3.0389 (3.3632) time: 0.5047 [2021-03-27 06:34:25 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 460/1251] eta: 0:06:45 lr: 0.000024 loss: 2.8683 (2.7153) grad_norm: 3.1925 (3.3608) time: 0.5041 [2021-03-27 06:34:30 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 470/1251] eta: 0:06:40 lr: 0.000024 loss: 2.8244 (2.7186) grad_norm: 3.3717 (3.3648) time: 0.5047 [2021-03-27 06:34:35 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 480/1251] eta: 0:06:35 lr: 0.000024 loss: 2.8443 (2.7198) grad_norm: 3.4223 (3.3639) time: 0.5033 [2021-03-27 06:34:40 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 490/1251] eta: 0:06:29 lr: 0.000024 loss: 2.8201 (2.7218) grad_norm: 3.1327 (3.3558) time: 0.4960 [2021-03-27 06:34:45 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 500/1251] eta: 0:06:24 lr: 0.000024 loss: 2.7093 (2.7171) grad_norm: 2.9280 (3.3545) time: 0.4975 [2021-03-27 06:34:50 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 510/1251] eta: 0:06:19 lr: 0.000024 loss: 2.6060 (2.7170) grad_norm: 2.9977 (3.3543) time: 0.5010 [2021-03-27 06:34:55 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 520/1251] eta: 0:06:14 lr: 0.000024 loss: 2.6967 (2.7166) grad_norm: 3.0590 (3.3532) time: 0.4974 [2021-03-27 06:35:00 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 530/1251] eta: 0:06:08 lr: 0.000024 loss: 2.7071 (2.7171) grad_norm: 3.0590 (3.3500) time: 0.4978 [2021-03-27 06:35:05 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 540/1251] eta: 0:06:03 lr: 0.000024 loss: 2.8608 (2.7210) grad_norm: 3.1360 (3.3506) time: 0.4991 [2021-03-27 06:35:10 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 550/1251] eta: 0:05:58 lr: 0.000024 loss: 2.9169 (2.7212) grad_norm: 3.0931 (3.3473) time: 0.5114 [2021-03-27 06:35:16 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 560/1251] eta: 0:05:53 lr: 0.000024 loss: 2.7964 (2.7199) grad_norm: 3.0543 (3.3439) time: 0.5156 [2021-03-27 06:35:21 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 570/1251] eta: 0:05:48 lr: 0.000024 loss: 2.8091 (2.7214) grad_norm: 3.2093 (3.3415) time: 0.5023 [2021-03-27 06:35:26 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 580/1251] eta: 0:05:42 lr: 0.000024 loss: 2.8160 (2.7205) grad_norm: 3.2223 (3.3408) time: 0.5028 [2021-03-27 06:35:31 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 590/1251] eta: 0:05:37 lr: 0.000024 loss: 2.7211 (2.7194) grad_norm: 3.0086 (3.3386) time: 0.5075 [2021-03-27 06:35:36 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 600/1251] eta: 0:05:32 lr: 0.000024 loss: 2.6196 (2.7165) grad_norm: 3.1027 (3.3365) time: 0.5028 [2021-03-27 06:35:41 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 610/1251] eta: 0:05:27 lr: 0.000024 loss: 2.6605 (2.7145) grad_norm: 3.1027 (3.3332) time: 0.4969 [2021-03-27 06:35:46 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 620/1251] eta: 0:05:22 lr: 0.000024 loss: 2.8547 (2.7173) grad_norm: 3.1468 (3.3308) time: 0.5005 [2021-03-27 06:35:51 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 630/1251] eta: 0:05:16 lr: 0.000024 loss: 2.8431 (2.7160) grad_norm: 3.1761 (3.3312) time: 0.5070 [2021-03-27 06:35:56 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 640/1251] eta: 0:05:11 lr: 0.000024 loss: 2.6736 (2.7136) grad_norm: 3.2129 (3.3332) time: 0.5065 [2021-03-27 06:36:01 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 650/1251] eta: 0:05:06 lr: 0.000024 loss: 2.7078 (2.7132) grad_norm: 3.3255 (3.3310) time: 0.4996 [2021-03-27 06:36:06 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 660/1251] eta: 0:05:01 lr: 0.000024 loss: 2.6913 (2.7106) grad_norm: 3.0375 (3.3277) time: 0.4991 [2021-03-27 06:36:11 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 670/1251] eta: 0:04:56 lr: 0.000024 loss: 2.5984 (2.7107) grad_norm: 3.0375 (3.3344) time: 0.5043 [2021-03-27 06:36:16 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 680/1251] eta: 0:04:51 lr: 0.000024 loss: 2.6448 (2.7112) grad_norm: 3.2961 (3.3355) time: 0.5054 [2021-03-27 06:36:21 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 690/1251] eta: 0:04:46 lr: 0.000024 loss: 2.9333 (2.7147) grad_norm: 3.2064 (3.3354) time: 0.5073 [2021-03-27 06:36:26 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 700/1251] eta: 0:04:40 lr: 0.000024 loss: 2.9333 (2.7165) grad_norm: 3.1853 (3.3323) time: 0.5054 [2021-03-27 06:36:31 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 710/1251] eta: 0:04:35 lr: 0.000024 loss: 2.7437 (2.7153) grad_norm: 3.1277 (3.3324) time: 0.5028 [2021-03-27 06:36:36 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 720/1251] eta: 0:04:30 lr: 0.000024 loss: 2.6878 (2.7160) grad_norm: 3.1277 (3.3295) time: 0.5047 [2021-03-27 06:36:41 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 730/1251] eta: 0:04:25 lr: 0.000024 loss: 2.8071 (2.7181) grad_norm: 2.9917 (3.3277) time: 0.4995 [2021-03-27 06:36:46 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 740/1251] eta: 0:04:20 lr: 0.000024 loss: 2.8431 (2.7200) grad_norm: 3.1875 (3.3290) time: 0.5084 [2021-03-27 06:36:51 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 750/1251] eta: 0:04:15 lr: 0.000024 loss: 2.8543 (2.7203) grad_norm: 3.4638 (3.3309) time: 0.5131 [2021-03-27 06:36:56 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 760/1251] eta: 0:04:10 lr: 0.000024 loss: 2.8154 (2.7200) grad_norm: 3.2036 (3.3276) time: 0.5018 [2021-03-27 06:37:02 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 770/1251] eta: 0:04:05 lr: 0.000024 loss: 2.8405 (2.7225) grad_norm: 3.1072 (3.3252) time: 0.5088 [2021-03-27 06:37:07 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 780/1251] eta: 0:03:59 lr: 0.000024 loss: 2.8405 (2.7218) grad_norm: 3.0452 (3.3232) time: 0.5102 [2021-03-27 06:37:12 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 790/1251] eta: 0:03:54 lr: 0.000024 loss: 2.6883 (2.7195) grad_norm: 3.1369 (3.3214) time: 0.5101 [2021-03-27 06:37:17 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 800/1251] eta: 0:03:49 lr: 0.000024 loss: 2.6137 (2.7187) grad_norm: 3.2008 (3.3244) time: 0.5086 [2021-03-27 06:37:22 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 810/1251] eta: 0:03:44 lr: 0.000023 loss: 2.6076 (2.7165) grad_norm: 3.1429 (3.3223) time: 0.4993 [2021-03-27 06:37:27 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 820/1251] eta: 0:03:39 lr: 0.000023 loss: 2.6038 (2.7159) grad_norm: 3.2412 (3.3316) time: 0.5039 [2021-03-27 06:37:32 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 830/1251] eta: 0:03:34 lr: 0.000023 loss: 2.8896 (2.7184) grad_norm: 3.2412 (3.3299) time: 0.5060 [2021-03-27 06:37:37 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 840/1251] eta: 0:03:29 lr: 0.000023 loss: 2.8896 (2.7187) grad_norm: 3.1658 (3.3283) time: 0.5060 [2021-03-27 06:37:42 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 850/1251] eta: 0:03:24 lr: 0.000023 loss: 2.7443 (2.7187) grad_norm: 3.1658 (3.3324) time: 0.5090 [2021-03-27 06:37:47 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 860/1251] eta: 0:03:19 lr: 0.000023 loss: 2.7854 (2.7184) grad_norm: 3.1620 (3.3358) time: 0.5032 [2021-03-27 06:37:52 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 870/1251] eta: 0:03:13 lr: 0.000023 loss: 2.6525 (2.7176) grad_norm: 3.0064 (3.3391) time: 0.5032 [2021-03-27 06:37:57 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 880/1251] eta: 0:03:08 lr: 0.000023 loss: 2.8201 (2.7195) grad_norm: 2.9115 (3.3348) time: 0.5105 [2021-03-27 06:38:02 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 890/1251] eta: 0:03:03 lr: 0.000023 loss: 2.8526 (2.7206) grad_norm: 2.8939 (3.3326) time: 0.5067 [2021-03-27 06:38:07 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 900/1251] eta: 0:02:58 lr: 0.000023 loss: 2.7821 (2.7202) grad_norm: 3.2364 (3.3322) time: 0.5074 [2021-03-27 06:38:12 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 910/1251] eta: 0:02:53 lr: 0.000023 loss: 2.7127 (2.7187) grad_norm: 3.0521 (3.3325) time: 0.5079 [2021-03-27 06:38:17 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 920/1251] eta: 0:02:48 lr: 0.000023 loss: 2.5973 (2.7162) grad_norm: 3.0521 (3.3318) time: 0.5012 [2021-03-27 06:38:22 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 930/1251] eta: 0:02:43 lr: 0.000023 loss: 2.6922 (2.7170) grad_norm: 3.2535 (3.3370) time: 0.5015 [2021-03-27 06:38:28 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 940/1251] eta: 0:02:38 lr: 0.000023 loss: 2.9361 (2.7196) grad_norm: 3.2557 (3.3380) time: 0.5098 [2021-03-27 06:38:33 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 950/1251] eta: 0:02:33 lr: 0.000023 loss: 2.9361 (2.7198) grad_norm: 3.0291 (3.3339) time: 0.5102 [2021-03-27 06:38:38 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 960/1251] eta: 0:02:28 lr: 0.000023 loss: 2.6933 (2.7164) grad_norm: 3.0085 (3.3331) time: 0.5091 [2021-03-27 06:38:43 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 970/1251] eta: 0:02:23 lr: 0.000023 loss: 2.7481 (2.7178) grad_norm: 3.1330 (3.3312) time: 0.5149 [2021-03-27 06:38:48 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 980/1251] eta: 0:02:17 lr: 0.000023 loss: 2.8776 (2.7162) grad_norm: 3.1330 (3.3311) time: 0.5199 [2021-03-27 06:38:53 swin_small_patch4_window7_224] INFO: Epoch: [277] [ 990/1251] eta: 0:02:12 lr: 0.000023 loss: 2.5891 (2.7149) grad_norm: 3.1964 (3.3350) time: 0.5157 [2021-03-27 06:38:58 swin_small_patch4_window7_224] INFO: Epoch: [277] [1000/1251] eta: 0:02:07 lr: 0.000023 loss: 2.5511 (2.7142) grad_norm: 3.1964 (3.3406) time: 0.5099 [2021-03-27 06:39:03 swin_small_patch4_window7_224] INFO: Epoch: [277] [1010/1251] eta: 0:02:02 lr: 0.000023 loss: 2.5511 (2.7121) grad_norm: 3.0749 (3.3406) time: 0.5103 [2021-03-27 06:39:08 swin_small_patch4_window7_224] INFO: Epoch: [277] [1020/1251] eta: 0:01:57 lr: 0.000023 loss: 2.7267 (2.7117) grad_norm: 3.0635 (3.3384) time: 0.5030 [2021-03-27 06:39:13 swin_small_patch4_window7_224] INFO: Epoch: [277] [1030/1251] eta: 0:01:52 lr: 0.000023 loss: 2.7267 (2.7117) grad_norm: 3.0549 (3.3386) time: 0.4964 [2021-03-27 06:39:18 swin_small_patch4_window7_224] INFO: Epoch: [277] [1040/1251] eta: 0:01:47 lr: 0.000023 loss: 2.4795 (2.7100) grad_norm: 3.2912 (3.3377) time: 0.4996 [2021-03-27 06:39:23 swin_small_patch4_window7_224] INFO: Epoch: [277] [1050/1251] eta: 0:01:42 lr: 0.000023 loss: 2.5550 (2.7097) grad_norm: 3.1784 (3.3374) time: 0.5018 [2021-03-27 06:39:28 swin_small_patch4_window7_224] INFO: Epoch: [277] [1060/1251] eta: 0:01:37 lr: 0.000023 loss: 2.8692 (2.7114) grad_norm: 3.0023 (3.3381) time: 0.4987 [2021-03-27 06:39:33 swin_small_patch4_window7_224] INFO: Epoch: [277] [1070/1251] eta: 0:01:32 lr: 0.000023 loss: 2.8692 (2.7109) grad_norm: 3.0023 (3.3374) time: 0.4977 [2021-03-27 06:39:38 swin_small_patch4_window7_224] INFO: Epoch: [277] [1080/1251] eta: 0:01:26 lr: 0.000023 loss: 2.7158 (2.7115) grad_norm: 3.1138 (3.3361) time: 0.4970 [2021-03-27 06:39:43 swin_small_patch4_window7_224] INFO: Epoch: [277] [1090/1251] eta: 0:01:21 lr: 0.000023 loss: 2.7466 (2.7109) grad_norm: 3.0804 (3.3340) time: 0.4980 [2021-03-27 06:39:48 swin_small_patch4_window7_224] INFO: Epoch: [277] [1100/1251] eta: 0:01:16 lr: 0.000023 loss: 2.5681 (2.7103) grad_norm: 3.2279 (3.3330) time: 0.5042 [2021-03-27 06:39:53 swin_small_patch4_window7_224] INFO: Epoch: [277] [1110/1251] eta: 0:01:11 lr: 0.000023 loss: 2.7096 (2.7114) grad_norm: 3.2265 (3.3314) time: 0.5074 [2021-03-27 06:39:59 swin_small_patch4_window7_224] INFO: Epoch: [277] [1120/1251] eta: 0:01:06 lr: 0.000023 loss: 2.7564 (2.7127) grad_norm: 3.1570 (3.3317) time: 0.5071 [2021-03-27 06:40:04 swin_small_patch4_window7_224] INFO: Epoch: [277] [1130/1251] eta: 0:01:01 lr: 0.000023 loss: 2.7922 (2.7121) grad_norm: 3.0337 (3.3304) time: 0.5071 [2021-03-27 06:40:09 swin_small_patch4_window7_224] INFO: Epoch: [277] [1140/1251] eta: 0:00:56 lr: 0.000023 loss: 2.5621 (2.7105) grad_norm: 2.9213 (3.3313) time: 0.5081 [2021-03-27 06:40:14 swin_small_patch4_window7_224] INFO: Epoch: [277] [1150/1251] eta: 0:00:51 lr: 0.000023 loss: 2.5621 (2.7112) grad_norm: 2.9759 (3.3296) time: 0.5060 [2021-03-27 06:40:19 swin_small_patch4_window7_224] INFO: Epoch: [277] [1160/1251] eta: 0:00:46 lr: 0.000023 loss: 2.5157 (2.7099) grad_norm: 2.8614 (3.3317) time: 0.5003 [2021-03-27 06:40:24 swin_small_patch4_window7_224] INFO: Epoch: [277] [1170/1251] eta: 0:00:41 lr: 0.000023 loss: 2.5736 (2.7101) grad_norm: 2.8506 (3.3310) time: 0.5049 [2021-03-27 06:40:29 swin_small_patch4_window7_224] INFO: Epoch: [277] [1180/1251] eta: 0:00:36 lr: 0.000023 loss: 2.8406 (2.7128) grad_norm: 3.1523 (3.3302) time: 0.5043 [2021-03-27 06:40:34 swin_small_patch4_window7_224] INFO: Epoch: [277] [1190/1251] eta: 0:00:30 lr: 0.000023 loss: 2.8622 (2.7128) grad_norm: 3.2332 (3.3298) time: 0.5043 [2021-03-27 06:40:39 swin_small_patch4_window7_224] INFO: Epoch: [277] [1200/1251] eta: 0:00:25 lr: 0.000023 loss: 2.7368 (2.7114) grad_norm: 2.9740 (3.3268) time: 0.5044 [2021-03-27 06:40:44 swin_small_patch4_window7_224] INFO: Epoch: [277] [1210/1251] eta: 0:00:20 lr: 0.000023 loss: 2.7368 (2.7118) grad_norm: 2.9740 (3.3280) time: 0.5011 [2021-03-27 06:40:49 swin_small_patch4_window7_224] INFO: Epoch: [277] [1220/1251] eta: 0:00:15 lr: 0.000023 loss: 2.7157 (2.7114) grad_norm: 3.2276 (3.3270) time: 0.5055 [2021-03-27 06:40:54 swin_small_patch4_window7_224] INFO: Epoch: [277] [1230/1251] eta: 0:00:10 lr: 0.000023 loss: 2.7549 (2.7116) grad_norm: 3.0715 (3.3252) time: 0.5064 [2021-03-27 06:40:59 swin_small_patch4_window7_224] INFO: Epoch: [277] [1240/1251] eta: 0:00:05 lr: 0.000023 loss: 3.0081 (2.7148) grad_norm: 3.0715 (3.3248) time: 0.5027 [2021-03-27 06:41:04 swin_small_patch4_window7_224] INFO: Epoch: [277] [1250/1251] eta: 0:00:00 lr: 0.000023 loss: 2.9264 (2.7132) grad_norm: 3.2081 (3.3266) time: 0.4987 [2021-03-27 06:41:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:39 loss: 0.7021 (0.7021) acc1: 85.9375 (85.9375) acc5: 96.8750 (96.8750) [2021-03-27 06:41:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.6854 (0.7083) acc1: 84.3750 (83.0966) acc5: 96.8750 (96.8750) [2021-03-27 06:41:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7251 (0.7358) acc1: 81.2500 (81.8452) acc5: 96.8750 (96.7262) [2021-03-27 06:41:23 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7251 (0.7267) acc1: 82.8125 (82.5101) acc5: 96.8750 (96.6734) [2021-03-27 06:41:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7135 (0.7506) acc1: 82.8125 (82.0503) acc5: 96.8750 (96.5320) [2021-03-27 06:41:26 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7460 (0.7546) acc1: 81.2500 (81.9200) acc5: 96.8750 (96.2880) [2021-03-27 06:41:41 swin_small_patch4_window7_224] INFO: * Acc@1 82.832 Acc@5 96.268 loss 0.742 [2021-03-27 06:41:41 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.8% [2021-03-27 06:41:41 swin_small_patch4_window7_224] INFO: Max accuracy: 82.88% [2021-03-27 06:41:46 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 0/1251] eta: 1:27:48 lr: 0.000023 loss: 3.1720 (3.1720) grad_norm: 3.6637 (3.6637) time: 4.2116 [2021-03-27 06:41:51 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 10/1251] eta: 0:17:44 lr: 0.000023 loss: 3.0634 (2.8998) grad_norm: 2.9889 (3.1675) time: 0.8575 [2021-03-27 06:41:56 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 20/1251] eta: 0:14:06 lr: 0.000023 loss: 2.8649 (2.7853) grad_norm: 3.0837 (3.2942) time: 0.5115 [2021-03-27 06:42:01 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 30/1251] eta: 0:12:52 lr: 0.000023 loss: 2.8086 (2.7306) grad_norm: 3.1197 (3.3166) time: 0.5089 [2021-03-27 06:42:06 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 40/1251] eta: 0:12:06 lr: 0.000023 loss: 2.8341 (2.7434) grad_norm: 3.1197 (3.3246) time: 0.5075 [2021-03-27 06:42:11 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 50/1251] eta: 0:11:36 lr: 0.000023 loss: 2.7944 (2.7154) grad_norm: 3.2276 (3.3219) time: 0.4984 [2021-03-27 06:42:16 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 60/1251] eta: 0:11:21 lr: 0.000023 loss: 2.6154 (2.6950) grad_norm: 3.0109 (3.3612) time: 0.5145 [2021-03-27 06:42:21 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 70/1251] eta: 0:11:03 lr: 0.000023 loss: 2.8136 (2.7233) grad_norm: 3.2749 (3.3555) time: 0.5154 [2021-03-27 06:42:27 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 80/1251] eta: 0:10:50 lr: 0.000023 loss: 2.8182 (2.7099) grad_norm: 3.1785 (3.3135) time: 0.5056 [2021-03-27 06:42:32 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 90/1251] eta: 0:10:37 lr: 0.000023 loss: 2.6441 (2.7015) grad_norm: 3.1439 (3.3168) time: 0.5055 [2021-03-27 06:42:37 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 100/1251] eta: 0:10:27 lr: 0.000023 loss: 2.8847 (2.7218) grad_norm: 3.1439 (3.2859) time: 0.5040 [2021-03-27 06:42:42 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 110/1251] eta: 0:10:18 lr: 0.000023 loss: 2.9542 (2.7321) grad_norm: 3.1775 (3.4439) time: 0.5062 [2021-03-27 06:42:47 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 120/1251] eta: 0:10:08 lr: 0.000023 loss: 2.8607 (2.7315) grad_norm: 3.0593 (3.4034) time: 0.5017 [2021-03-27 06:42:52 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 130/1251] eta: 0:10:01 lr: 0.000023 loss: 2.7389 (2.7259) grad_norm: 2.9202 (3.3859) time: 0.5080 [2021-03-27 06:42:57 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 140/1251] eta: 0:09:54 lr: 0.000023 loss: 2.6860 (2.7171) grad_norm: 3.1379 (3.3867) time: 0.5159 [2021-03-27 06:43:02 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 150/1251] eta: 0:09:47 lr: 0.000023 loss: 2.6144 (2.7152) grad_norm: 3.0680 (3.3619) time: 0.5140 [2021-03-27 06:43:07 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 160/1251] eta: 0:09:39 lr: 0.000023 loss: 2.7513 (2.7195) grad_norm: 2.9635 (3.3453) time: 0.5048 [2021-03-27 06:43:12 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 170/1251] eta: 0:09:33 lr: 0.000023 loss: 2.7513 (2.7113) grad_norm: 3.1915 (3.3491) time: 0.5043 [2021-03-27 06:43:17 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 180/1251] eta: 0:09:26 lr: 0.000023 loss: 2.6610 (2.7040) grad_norm: 3.2125 (3.3482) time: 0.5100 [2021-03-27 06:43:22 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 190/1251] eta: 0:09:20 lr: 0.000023 loss: 2.7003 (2.7082) grad_norm: 3.0956 (3.3357) time: 0.5142 [2021-03-27 06:43:28 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 200/1251] eta: 0:09:14 lr: 0.000023 loss: 2.7003 (2.7059) grad_norm: 3.0980 (3.3270) time: 0.5130 [2021-03-27 06:43:32 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 210/1251] eta: 0:09:07 lr: 0.000023 loss: 2.7427 (2.7134) grad_norm: 2.9755 (3.3107) time: 0.5008 [2021-03-27 06:43:38 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 220/1251] eta: 0:09:01 lr: 0.000023 loss: 2.8598 (2.7077) grad_norm: 2.9755 (3.3174) time: 0.5034 [2021-03-27 06:43:43 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 230/1251] eta: 0:08:55 lr: 0.000023 loss: 2.6886 (2.7060) grad_norm: 3.2313 (3.3169) time: 0.5061 [2021-03-27 06:43:48 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 240/1251] eta: 0:08:48 lr: 0.000023 loss: 2.5172 (2.6942) grad_norm: 3.2874 (3.3221) time: 0.5000 [2021-03-27 06:43:53 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 250/1251] eta: 0:08:42 lr: 0.000023 loss: 2.8242 (2.7049) grad_norm: 3.2411 (3.3208) time: 0.5002 [2021-03-27 06:43:58 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 260/1251] eta: 0:08:36 lr: 0.000023 loss: 2.9548 (2.7084) grad_norm: 2.9353 (3.3104) time: 0.5021 [2021-03-27 06:44:03 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 270/1251] eta: 0:08:31 lr: 0.000023 loss: 2.8298 (2.7101) grad_norm: 2.9960 (3.3060) time: 0.5050 [2021-03-27 06:44:08 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 280/1251] eta: 0:08:25 lr: 0.000023 loss: 2.8293 (2.7078) grad_norm: 3.1070 (3.3501) time: 0.5070 [2021-03-27 06:44:13 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 290/1251] eta: 0:08:19 lr: 0.000023 loss: 2.7977 (2.7088) grad_norm: 3.1070 (3.3436) time: 0.5032 [2021-03-27 06:44:18 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 300/1251] eta: 0:08:13 lr: 0.000023 loss: 2.7977 (2.7058) grad_norm: 3.1513 (3.3350) time: 0.5052 [2021-03-27 06:44:23 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 310/1251] eta: 0:08:08 lr: 0.000023 loss: 2.8865 (2.7130) grad_norm: 3.1638 (3.3457) time: 0.5085 [2021-03-27 06:44:28 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 320/1251] eta: 0:08:02 lr: 0.000023 loss: 2.8726 (2.7139) grad_norm: 3.2425 (3.3498) time: 0.5077 [2021-03-27 06:44:33 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 330/1251] eta: 0:07:57 lr: 0.000023 loss: 2.9558 (2.7219) grad_norm: 3.1218 (3.3586) time: 0.5076 [2021-03-27 06:44:38 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 340/1251] eta: 0:07:52 lr: 0.000023 loss: 2.8253 (2.7206) grad_norm: 3.1953 (3.3569) time: 0.5099 [2021-03-27 06:44:43 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 350/1251] eta: 0:07:46 lr: 0.000023 loss: 2.7155 (2.7234) grad_norm: 3.1589 (3.3500) time: 0.5164 [2021-03-27 06:44:49 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 360/1251] eta: 0:07:41 lr: 0.000023 loss: 2.8499 (2.7257) grad_norm: 3.0574 (3.3454) time: 0.5141 [2021-03-27 06:44:54 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 370/1251] eta: 0:07:35 lr: 0.000023 loss: 2.7850 (2.7285) grad_norm: 3.1947 (3.3486) time: 0.5027 [2021-03-27 06:44:58 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 380/1251] eta: 0:07:30 lr: 0.000023 loss: 2.7125 (2.7206) grad_norm: 3.3061 (3.3473) time: 0.4953 [2021-03-27 06:45:04 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 390/1251] eta: 0:07:24 lr: 0.000023 loss: 2.5324 (2.7191) grad_norm: 3.1576 (3.3499) time: 0.5000 [2021-03-27 06:45:09 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 400/1251] eta: 0:07:19 lr: 0.000023 loss: 2.7537 (2.7202) grad_norm: 3.4215 (3.3550) time: 0.5074 [2021-03-27 06:45:14 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 410/1251] eta: 0:07:13 lr: 0.000023 loss: 2.7393 (2.7127) grad_norm: 3.3983 (3.3535) time: 0.5070 [2021-03-27 06:45:19 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 420/1251] eta: 0:07:08 lr: 0.000023 loss: 2.7393 (2.7113) grad_norm: 3.1855 (3.3544) time: 0.5028 [2021-03-27 06:45:24 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 430/1251] eta: 0:07:03 lr: 0.000023 loss: 2.9396 (2.7153) grad_norm: 3.2631 (3.3514) time: 0.5058 [2021-03-27 06:45:29 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 440/1251] eta: 0:06:57 lr: 0.000023 loss: 2.9766 (2.7155) grad_norm: 3.1355 (3.3488) time: 0.5078 [2021-03-27 06:45:34 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 450/1251] eta: 0:06:52 lr: 0.000023 loss: 2.7535 (2.7181) grad_norm: 3.0441 (3.3458) time: 0.5010 [2021-03-27 06:45:39 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 460/1251] eta: 0:06:47 lr: 0.000023 loss: 2.8899 (2.7226) grad_norm: 3.0441 (3.3487) time: 0.5000 [2021-03-27 06:45:44 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 470/1251] eta: 0:06:41 lr: 0.000023 loss: 2.8586 (2.7245) grad_norm: 3.1924 (3.3530) time: 0.5025 [2021-03-27 06:45:49 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 480/1251] eta: 0:06:36 lr: 0.000023 loss: 2.8586 (2.7257) grad_norm: 3.1127 (3.3491) time: 0.4992 [2021-03-27 06:45:54 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 490/1251] eta: 0:06:30 lr: 0.000023 loss: 2.7791 (2.7239) grad_norm: 3.1438 (3.3492) time: 0.4975 [2021-03-27 06:45:59 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 500/1251] eta: 0:06:25 lr: 0.000023 loss: 2.7036 (2.7262) grad_norm: 3.1438 (3.3426) time: 0.4975 [2021-03-27 06:46:04 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 510/1251] eta: 0:06:20 lr: 0.000023 loss: 2.6904 (2.7271) grad_norm: 3.0851 (3.3388) time: 0.4959 [2021-03-27 06:46:09 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 520/1251] eta: 0:06:14 lr: 0.000023 loss: 2.5688 (2.7219) grad_norm: 3.1739 (3.3651) time: 0.4984 [2021-03-27 06:46:14 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 530/1251] eta: 0:06:09 lr: 0.000023 loss: 2.5886 (2.7196) grad_norm: 3.1656 (3.3632) time: 0.5037 [2021-03-27 06:46:19 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 540/1251] eta: 0:06:04 lr: 0.000023 loss: 2.6391 (2.7193) grad_norm: 3.1210 (3.3670) time: 0.5073 [2021-03-27 06:46:24 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 550/1251] eta: 0:05:59 lr: 0.000023 loss: 2.7135 (2.7186) grad_norm: 3.1684 (3.3653) time: 0.5239 [2021-03-27 06:46:29 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 560/1251] eta: 0:05:54 lr: 0.000023 loss: 2.8302 (2.7209) grad_norm: 3.1782 (3.3628) time: 0.5179 [2021-03-27 06:46:34 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 570/1251] eta: 0:05:49 lr: 0.000023 loss: 2.9258 (2.7253) grad_norm: 3.0002 (3.3596) time: 0.5023 [2021-03-27 06:46:40 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 580/1251] eta: 0:05:44 lr: 0.000023 loss: 2.8557 (2.7251) grad_norm: 3.0094 (3.3569) time: 0.5154 [2021-03-27 06:46:45 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 590/1251] eta: 0:05:38 lr: 0.000023 loss: 2.5231 (2.7227) grad_norm: 3.1780 (3.3579) time: 0.5091 [2021-03-27 06:46:50 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 600/1251] eta: 0:05:33 lr: 0.000023 loss: 2.6574 (2.7223) grad_norm: 3.3919 (3.3574) time: 0.5018 [2021-03-27 06:46:55 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 610/1251] eta: 0:05:28 lr: 0.000023 loss: 2.8307 (2.7220) grad_norm: 3.2123 (3.3536) time: 0.4999 [2021-03-27 06:47:00 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 620/1251] eta: 0:05:23 lr: 0.000022 loss: 2.7468 (2.7192) grad_norm: 2.9544 (3.3503) time: 0.5090 [2021-03-27 06:47:05 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 630/1251] eta: 0:05:18 lr: 0.000022 loss: 2.7468 (2.7227) grad_norm: 3.1470 (3.3497) time: 0.5138 [2021-03-27 06:47:10 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 640/1251] eta: 0:05:12 lr: 0.000022 loss: 2.7595 (2.7191) grad_norm: 3.2712 (3.3484) time: 0.5072 [2021-03-27 06:47:15 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 650/1251] eta: 0:05:07 lr: 0.000022 loss: 2.7595 (2.7206) grad_norm: 3.2425 (3.3458) time: 0.5091 [2021-03-27 06:47:20 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 660/1251] eta: 0:05:02 lr: 0.000022 loss: 2.9604 (2.7216) grad_norm: 3.1294 (3.3444) time: 0.5067 [2021-03-27 06:47:25 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 670/1251] eta: 0:04:57 lr: 0.000022 loss: 2.6953 (2.7186) grad_norm: 3.0996 (3.3439) time: 0.5042 [2021-03-27 06:47:30 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 680/1251] eta: 0:04:52 lr: 0.000022 loss: 2.6666 (2.7168) grad_norm: 3.0145 (3.3391) time: 0.5019 [2021-03-27 06:47:35 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 690/1251] eta: 0:04:47 lr: 0.000022 loss: 2.6666 (2.7176) grad_norm: 2.9810 (3.3357) time: 0.5041 [2021-03-27 06:47:40 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 700/1251] eta: 0:04:41 lr: 0.000022 loss: 2.8089 (2.7181) grad_norm: 3.0303 (3.3353) time: 0.5034 [2021-03-27 06:47:45 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 710/1251] eta: 0:04:36 lr: 0.000022 loss: 2.7184 (2.7164) grad_norm: 3.0439 (3.3331) time: 0.5020 [2021-03-27 06:47:50 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 720/1251] eta: 0:04:31 lr: 0.000022 loss: 2.6646 (2.7151) grad_norm: 3.1361 (3.3357) time: 0.4995 [2021-03-27 06:47:55 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 730/1251] eta: 0:04:26 lr: 0.000022 loss: 2.6809 (2.7113) grad_norm: 3.1716 (3.3363) time: 0.5012 [2021-03-27 06:48:00 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 740/1251] eta: 0:04:21 lr: 0.000022 loss: 2.6809 (2.7112) grad_norm: 3.1495 (3.3338) time: 0.5165 [2021-03-27 06:48:06 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 750/1251] eta: 0:04:16 lr: 0.000022 loss: 2.8495 (2.7120) grad_norm: 3.3273 (3.3447) time: 0.5185 [2021-03-27 06:48:11 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 760/1251] eta: 0:04:11 lr: 0.000022 loss: 2.8192 (2.7115) grad_norm: 3.7695 (3.3492) time: 0.5133 [2021-03-27 06:48:16 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 770/1251] eta: 0:04:05 lr: 0.000022 loss: 2.8600 (2.7142) grad_norm: 3.4269 (3.3508) time: 0.5141 [2021-03-27 06:48:21 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 780/1251] eta: 0:04:00 lr: 0.000022 loss: 2.8394 (2.7131) grad_norm: 3.0859 (3.3483) time: 0.5124 [2021-03-27 06:48:26 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 790/1251] eta: 0:03:55 lr: 0.000022 loss: 2.7818 (2.7137) grad_norm: 3.0076 (3.3520) time: 0.5044 [2021-03-27 06:48:31 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 800/1251] eta: 0:03:50 lr: 0.000022 loss: 2.8313 (2.7168) grad_norm: 3.0622 (3.3558) time: 0.4977 [2021-03-27 06:48:36 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 810/1251] eta: 0:03:45 lr: 0.000022 loss: 2.9790 (2.7191) grad_norm: 3.1371 (3.3540) time: 0.5062 [2021-03-27 06:48:41 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 820/1251] eta: 0:03:40 lr: 0.000022 loss: 2.8962 (2.7210) grad_norm: 3.1573 (3.3513) time: 0.5084 [2021-03-27 06:48:46 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 830/1251] eta: 0:03:35 lr: 0.000022 loss: 2.7103 (2.7205) grad_norm: 3.0857 (3.3477) time: 0.5066 [2021-03-27 06:48:51 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 840/1251] eta: 0:03:29 lr: 0.000022 loss: 2.6793 (2.7211) grad_norm: 3.0611 (3.3459) time: 0.5034 [2021-03-27 06:48:56 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 850/1251] eta: 0:03:24 lr: 0.000022 loss: 2.6793 (2.7185) grad_norm: 3.1609 (3.3481) time: 0.5019 [2021-03-27 06:49:01 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 860/1251] eta: 0:03:19 lr: 0.000022 loss: 2.8340 (2.7187) grad_norm: 3.2010 (3.3497) time: 0.5081 [2021-03-27 06:49:06 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 870/1251] eta: 0:03:14 lr: 0.000022 loss: 2.8441 (2.7180) grad_norm: 3.0990 (3.3454) time: 0.5051 [2021-03-27 06:49:12 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 880/1251] eta: 0:03:09 lr: 0.000022 loss: 2.8289 (2.7190) grad_norm: 2.9966 (3.3417) time: 0.5059 [2021-03-27 06:49:17 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 890/1251] eta: 0:03:04 lr: 0.000022 loss: 2.8586 (2.7196) grad_norm: 3.2021 (3.3407) time: 0.5066 [2021-03-27 06:49:22 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 900/1251] eta: 0:02:59 lr: 0.000022 loss: 2.9429 (2.7206) grad_norm: 3.2237 (3.3381) time: 0.5068 [2021-03-27 06:49:27 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 910/1251] eta: 0:02:54 lr: 0.000022 loss: 2.9045 (2.7219) grad_norm: 3.3258 (3.3423) time: 0.5066 [2021-03-27 06:49:32 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 920/1251] eta: 0:02:48 lr: 0.000022 loss: 2.9045 (2.7240) grad_norm: 3.1858 (3.3391) time: 0.4967 [2021-03-27 06:49:37 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 930/1251] eta: 0:02:43 lr: 0.000022 loss: 2.7630 (2.7226) grad_norm: 3.1578 (3.3413) time: 0.5003 [2021-03-27 06:49:42 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 940/1251] eta: 0:02:38 lr: 0.000022 loss: 2.6314 (2.7222) grad_norm: 3.3502 (3.3412) time: 0.5070 [2021-03-27 06:49:47 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 950/1251] eta: 0:02:33 lr: 0.000022 loss: 2.6669 (2.7229) grad_norm: 3.2122 (3.3401) time: 0.5053 [2021-03-27 06:49:52 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 960/1251] eta: 0:02:28 lr: 0.000022 loss: 2.8279 (2.7230) grad_norm: 3.1294 (3.3370) time: 0.5076 [2021-03-27 06:49:57 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 970/1251] eta: 0:02:23 lr: 0.000022 loss: 2.8279 (2.7223) grad_norm: 3.1294 (3.3378) time: 0.5041 [2021-03-27 06:50:02 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 980/1251] eta: 0:02:18 lr: 0.000022 loss: 2.9587 (2.7238) grad_norm: 3.2585 (3.3392) time: 0.4987 [2021-03-27 06:50:07 swin_small_patch4_window7_224] INFO: Epoch: [278] [ 990/1251] eta: 0:02:13 lr: 0.000022 loss: 2.9662 (2.7232) grad_norm: 3.2422 (3.3452) time: 0.5035 [2021-03-27 06:50:12 swin_small_patch4_window7_224] INFO: Epoch: [278] [1000/1251] eta: 0:02:07 lr: 0.000022 loss: 2.8687 (2.7241) grad_norm: 3.1902 (3.3433) time: 0.5010 [2021-03-27 06:50:17 swin_small_patch4_window7_224] INFO: Epoch: [278] [1010/1251] eta: 0:02:02 lr: 0.000022 loss: 2.8956 (2.7253) grad_norm: 3.0478 (3.3411) time: 0.4964 [2021-03-27 06:50:22 swin_small_patch4_window7_224] INFO: Epoch: [278] [1020/1251] eta: 0:01:57 lr: 0.000022 loss: 3.0168 (2.7273) grad_norm: 2.9715 (3.3388) time: 0.5038 [2021-03-27 06:50:27 swin_small_patch4_window7_224] INFO: Epoch: [278] [1030/1251] eta: 0:01:52 lr: 0.000022 loss: 3.0050 (2.7260) grad_norm: 3.0715 (3.3434) time: 0.5059 [2021-03-27 06:50:32 swin_small_patch4_window7_224] INFO: Epoch: [278] [1040/1251] eta: 0:01:47 lr: 0.000022 loss: 2.6221 (2.7255) grad_norm: 3.2829 (3.3430) time: 0.5074 [2021-03-27 06:50:37 swin_small_patch4_window7_224] INFO: Epoch: [278] [1050/1251] eta: 0:01:42 lr: 0.000022 loss: 2.6494 (2.7255) grad_norm: 3.2203 (3.3438) time: 0.5123 [2021-03-27 06:50:42 swin_small_patch4_window7_224] INFO: Epoch: [278] [1060/1251] eta: 0:01:37 lr: 0.000022 loss: 2.8922 (2.7259) grad_norm: 3.0238 (3.3408) time: 0.5050 [2021-03-27 06:50:47 swin_small_patch4_window7_224] INFO: Epoch: [278] [1070/1251] eta: 0:01:32 lr: 0.000022 loss: 2.8922 (2.7270) grad_norm: 2.9897 (3.3376) time: 0.5016 [2021-03-27 06:50:52 swin_small_patch4_window7_224] INFO: Epoch: [278] [1080/1251] eta: 0:01:27 lr: 0.000022 loss: 2.8439 (2.7258) grad_norm: 3.1724 (3.3367) time: 0.5021 [2021-03-27 06:50:57 swin_small_patch4_window7_224] INFO: Epoch: [278] [1090/1251] eta: 0:01:22 lr: 0.000022 loss: 2.7700 (2.7271) grad_norm: 2.9411 (3.3327) time: 0.5085 [2021-03-27 06:51:02 swin_small_patch4_window7_224] INFO: Epoch: [278] [1100/1251] eta: 0:01:16 lr: 0.000022 loss: 2.8496 (2.7277) grad_norm: 3.0893 (3.3330) time: 0.5101 [2021-03-27 06:51:07 swin_small_patch4_window7_224] INFO: Epoch: [278] [1110/1251] eta: 0:01:11 lr: 0.000022 loss: 2.8496 (2.7276) grad_norm: 3.1837 (3.3306) time: 0.5026 [2021-03-27 06:51:13 swin_small_patch4_window7_224] INFO: Epoch: [278] [1120/1251] eta: 0:01:06 lr: 0.000022 loss: 2.6956 (2.7277) grad_norm: 3.1837 (3.3299) time: 0.5054 [2021-03-27 06:51:18 swin_small_patch4_window7_224] INFO: Epoch: [278] [1130/1251] eta: 0:01:01 lr: 0.000022 loss: 2.7908 (2.7286) grad_norm: 3.1885 (3.3285) time: 0.5011 [2021-03-27 06:51:22 swin_small_patch4_window7_224] INFO: Epoch: [278] [1140/1251] eta: 0:00:56 lr: 0.000022 loss: 2.7962 (2.7291) grad_norm: 3.0792 (3.3279) time: 0.4950 [2021-03-27 06:51:28 swin_small_patch4_window7_224] INFO: Epoch: [278] [1150/1251] eta: 0:00:51 lr: 0.000022 loss: 2.8819 (2.7295) grad_norm: 3.0467 (3.3256) time: 0.4994 [2021-03-27 06:51:33 swin_small_patch4_window7_224] INFO: Epoch: [278] [1160/1251] eta: 0:00:46 lr: 0.000022 loss: 2.8681 (2.7294) grad_norm: 3.1121 (3.3245) time: 0.5046 [2021-03-27 06:51:38 swin_small_patch4_window7_224] INFO: Epoch: [278] [1170/1251] eta: 0:00:41 lr: 0.000022 loss: 2.6079 (2.7284) grad_norm: 3.2985 (3.3273) time: 0.5062 [2021-03-27 06:51:43 swin_small_patch4_window7_224] INFO: Epoch: [278] [1180/1251] eta: 0:00:36 lr: 0.000022 loss: 2.5792 (2.7265) grad_norm: 3.2712 (3.3301) time: 0.5051 [2021-03-27 06:51:48 swin_small_patch4_window7_224] INFO: Epoch: [278] [1190/1251] eta: 0:00:31 lr: 0.000022 loss: 2.6647 (2.7255) grad_norm: 3.2415 (3.3293) time: 0.5069 [2021-03-27 06:51:53 swin_small_patch4_window7_224] INFO: Epoch: [278] [1200/1251] eta: 0:00:25 lr: 0.000022 loss: 2.6647 (2.7259) grad_norm: 3.1303 (3.3298) time: 0.5020 [2021-03-27 06:51:58 swin_small_patch4_window7_224] INFO: Epoch: [278] [1210/1251] eta: 0:00:20 lr: 0.000022 loss: 2.9613 (2.7282) grad_norm: 3.1697 (3.3288) time: 0.4980 [2021-03-27 06:52:03 swin_small_patch4_window7_224] INFO: Epoch: [278] [1220/1251] eta: 0:00:15 lr: 0.000022 loss: 2.9746 (2.7287) grad_norm: 3.1880 (3.3284) time: 0.4972 [2021-03-27 06:52:08 swin_small_patch4_window7_224] INFO: Epoch: [278] [1230/1251] eta: 0:00:10 lr: 0.000022 loss: 2.7490 (2.7273) grad_norm: 3.1242 (3.3248) time: 0.4962 [2021-03-27 06:52:13 swin_small_patch4_window7_224] INFO: Epoch: [278] [1240/1251] eta: 0:00:05 lr: 0.000022 loss: 2.9407 (2.7294) grad_norm: 2.9706 (3.3230) time: 0.5033 [2021-03-27 06:52:18 swin_small_patch4_window7_224] INFO: Epoch: [278] [1250/1251] eta: 0:00:00 lr: 0.000022 loss: 2.8676 (2.7287) grad_norm: 3.0479 (3.3243) time: 0.4987 [2021-03-27 06:52:27 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:21 loss: 0.8936 (0.8936) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 06:52:31 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.8681 (0.8149) acc1: 82.8125 (82.3864) acc5: 95.3125 (95.4545) [2021-03-27 06:52:33 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7877 (0.7744) acc1: 82.8125 (82.3661) acc5: 95.3125 (95.6845) [2021-03-27 06:52:35 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7590 (0.7518) acc1: 81.2500 (82.7117) acc5: 96.8750 (95.9677) [2021-03-27 06:52:37 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7382 (0.7527) acc1: 81.2500 (82.1646) acc5: 95.3125 (96.0366) [2021-03-27 06:52:38 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7382 (0.7552) acc1: 81.2500 (82.2400) acc5: 95.3125 (96.0000) [2021-03-27 06:52:50 swin_small_patch4_window7_224] INFO: * Acc@1 82.988 Acc@5 96.268 loss 0.740 [2021-03-27 06:52:50 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 06:52:50 swin_small_patch4_window7_224] INFO: Max accuracy: 82.99% [2021-03-27 06:52:54 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 0/1251] eta: 1:31:41 lr: 0.000022 loss: 2.7090 (2.7090) grad_norm: 2.6632 (2.6632) time: 4.3974 [2021-03-27 06:53:00 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 10/1251] eta: 0:17:53 lr: 0.000022 loss: 2.7258 (2.7246) grad_norm: 3.1378 (3.0971) time: 0.8649 [2021-03-27 06:53:05 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 20/1251] eta: 0:14:15 lr: 0.000022 loss: 2.7788 (2.7960) grad_norm: 3.0911 (3.1702) time: 0.5095 [2021-03-27 06:53:10 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 30/1251] eta: 0:12:56 lr: 0.000022 loss: 2.7788 (2.6736) grad_norm: 3.0610 (3.2467) time: 0.5106 [2021-03-27 06:53:15 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 40/1251] eta: 0:12:11 lr: 0.000022 loss: 2.4624 (2.6552) grad_norm: 3.1394 (3.2547) time: 0.5092 [2021-03-27 06:53:20 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 50/1251] eta: 0:11:43 lr: 0.000022 loss: 2.6469 (2.6639) grad_norm: 3.1428 (3.2563) time: 0.5072 [2021-03-27 06:53:25 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 60/1251] eta: 0:11:22 lr: 0.000022 loss: 2.8208 (2.6914) grad_norm: 3.1466 (3.2896) time: 0.5088 [2021-03-27 06:53:30 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 70/1251] eta: 0:11:05 lr: 0.000022 loss: 2.8442 (2.7052) grad_norm: 3.2250 (3.2780) time: 0.5078 [2021-03-27 06:53:35 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 80/1251] eta: 0:10:52 lr: 0.000022 loss: 2.8718 (2.7085) grad_norm: 3.1783 (3.2706) time: 0.5080 [2021-03-27 06:53:40 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 90/1251] eta: 0:10:40 lr: 0.000022 loss: 2.8566 (2.7146) grad_norm: 3.0614 (3.2537) time: 0.5079 [2021-03-27 06:53:45 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 100/1251] eta: 0:10:30 lr: 0.000022 loss: 2.6589 (2.7166) grad_norm: 3.0562 (3.2726) time: 0.5106 [2021-03-27 06:53:50 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 110/1251] eta: 0:10:20 lr: 0.000022 loss: 2.7328 (2.7193) grad_norm: 3.1775 (3.3256) time: 0.5089 [2021-03-27 06:53:55 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 120/1251] eta: 0:10:10 lr: 0.000022 loss: 2.8102 (2.7182) grad_norm: 3.1827 (3.3237) time: 0.5015 [2021-03-27 06:54:00 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 130/1251] eta: 0:10:01 lr: 0.000022 loss: 2.8268 (2.7211) grad_norm: 3.2056 (3.3291) time: 0.4963 [2021-03-27 06:54:05 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 140/1251] eta: 0:09:53 lr: 0.000022 loss: 2.6897 (2.7045) grad_norm: 3.1503 (3.3126) time: 0.5007 [2021-03-27 06:54:10 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 150/1251] eta: 0:09:46 lr: 0.000022 loss: 2.8429 (2.7125) grad_norm: 3.1288 (3.3193) time: 0.5045 [2021-03-27 06:54:15 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 160/1251] eta: 0:09:38 lr: 0.000022 loss: 2.8060 (2.7007) grad_norm: 3.2055 (3.3083) time: 0.5017 [2021-03-27 06:54:20 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 170/1251] eta: 0:09:31 lr: 0.000022 loss: 2.5538 (2.6927) grad_norm: 3.0976 (3.2920) time: 0.5016 [2021-03-27 06:54:26 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 180/1251] eta: 0:09:25 lr: 0.000022 loss: 2.6909 (2.6983) grad_norm: 3.2542 (3.2920) time: 0.5124 [2021-03-27 06:54:31 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 190/1251] eta: 0:09:19 lr: 0.000022 loss: 2.9396 (2.7057) grad_norm: 3.1790 (3.2814) time: 0.5194 [2021-03-27 06:54:36 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 200/1251] eta: 0:09:13 lr: 0.000022 loss: 2.9288 (2.7088) grad_norm: 3.1790 (3.2938) time: 0.5096 [2021-03-27 06:54:41 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 210/1251] eta: 0:09:07 lr: 0.000022 loss: 2.5657 (2.6887) grad_norm: 3.1455 (3.2824) time: 0.5125 [2021-03-27 06:54:46 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 220/1251] eta: 0:09:01 lr: 0.000022 loss: 2.5686 (2.6994) grad_norm: 3.0423 (3.2710) time: 0.5099 [2021-03-27 06:54:51 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 230/1251] eta: 0:08:55 lr: 0.000022 loss: 2.8445 (2.6910) grad_norm: 3.0423 (3.2660) time: 0.5010 [2021-03-27 06:54:56 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 240/1251] eta: 0:08:48 lr: 0.000022 loss: 2.8275 (2.6959) grad_norm: 3.0644 (3.2618) time: 0.5002 [2021-03-27 06:55:01 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 250/1251] eta: 0:08:42 lr: 0.000022 loss: 2.6973 (2.6864) grad_norm: 3.1051 (3.2633) time: 0.4995 [2021-03-27 06:55:06 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 260/1251] eta: 0:08:37 lr: 0.000022 loss: 2.6070 (2.6863) grad_norm: 3.3115 (3.2723) time: 0.5083 [2021-03-27 06:55:11 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 270/1251] eta: 0:08:31 lr: 0.000022 loss: 2.7750 (2.6903) grad_norm: 3.2253 (3.2732) time: 0.5061 [2021-03-27 06:55:16 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 280/1251] eta: 0:08:25 lr: 0.000022 loss: 2.8522 (2.6960) grad_norm: 3.1098 (3.2740) time: 0.5009 [2021-03-27 06:55:21 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 290/1251] eta: 0:08:19 lr: 0.000022 loss: 2.7974 (2.6968) grad_norm: 3.1113 (3.2746) time: 0.5016 [2021-03-27 06:55:26 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 300/1251] eta: 0:08:13 lr: 0.000022 loss: 2.8419 (2.7009) grad_norm: 3.1113 (3.2761) time: 0.5027 [2021-03-27 06:55:31 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 310/1251] eta: 0:08:08 lr: 0.000022 loss: 2.7111 (2.6952) grad_norm: 3.0763 (3.2747) time: 0.5047 [2021-03-27 06:55:36 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 320/1251] eta: 0:08:02 lr: 0.000022 loss: 2.5021 (2.6976) grad_norm: 3.3185 (3.2768) time: 0.4999 [2021-03-27 06:55:41 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 330/1251] eta: 0:07:56 lr: 0.000022 loss: 2.7970 (2.6981) grad_norm: 3.3831 (3.2846) time: 0.4999 [2021-03-27 06:55:46 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 340/1251] eta: 0:07:51 lr: 0.000022 loss: 2.7970 (2.7002) grad_norm: 3.1931 (3.2883) time: 0.5039 [2021-03-27 06:55:52 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 350/1251] eta: 0:07:45 lr: 0.000022 loss: 2.8360 (2.6986) grad_norm: 3.2476 (3.2924) time: 0.5103 [2021-03-27 06:55:57 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 360/1251] eta: 0:07:40 lr: 0.000022 loss: 2.5890 (2.6969) grad_norm: 3.2042 (3.2857) time: 0.5066 [2021-03-27 06:56:02 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 370/1251] eta: 0:07:34 lr: 0.000022 loss: 2.6697 (2.6972) grad_norm: 3.0576 (3.2883) time: 0.4989 [2021-03-27 06:56:07 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 380/1251] eta: 0:07:29 lr: 0.000022 loss: 2.8045 (2.7029) grad_norm: 3.1236 (3.2973) time: 0.5050 [2021-03-27 06:56:12 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 390/1251] eta: 0:07:23 lr: 0.000022 loss: 2.8950 (2.7013) grad_norm: 3.0941 (3.2926) time: 0.5029 [2021-03-27 06:56:17 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 400/1251] eta: 0:07:18 lr: 0.000022 loss: 2.5664 (2.6964) grad_norm: 3.0149 (3.2900) time: 0.4960 [2021-03-27 06:56:22 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 410/1251] eta: 0:07:12 lr: 0.000022 loss: 2.6062 (2.6908) grad_norm: 3.0053 (3.2852) time: 0.5009 [2021-03-27 06:56:27 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 420/1251] eta: 0:07:07 lr: 0.000022 loss: 2.7075 (2.6932) grad_norm: 3.2606 (3.2915) time: 0.5043 [2021-03-27 06:56:32 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 430/1251] eta: 0:07:02 lr: 0.000022 loss: 2.8378 (2.6957) grad_norm: 3.3274 (3.2946) time: 0.5024 [2021-03-27 06:56:37 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 440/1251] eta: 0:06:56 lr: 0.000022 loss: 2.9282 (2.6979) grad_norm: 3.3792 (3.3025) time: 0.5066 [2021-03-27 06:56:42 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 450/1251] eta: 0:06:51 lr: 0.000022 loss: 2.8973 (2.7004) grad_norm: 3.2331 (3.3122) time: 0.5097 [2021-03-27 06:56:47 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 460/1251] eta: 0:06:46 lr: 0.000022 loss: 2.9502 (2.7042) grad_norm: 3.2303 (3.3132) time: 0.5042 [2021-03-27 06:56:52 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 470/1251] eta: 0:06:41 lr: 0.000022 loss: 2.7617 (2.6988) grad_norm: 2.9876 (3.3043) time: 0.5018 [2021-03-27 06:56:57 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 480/1251] eta: 0:06:35 lr: 0.000021 loss: 2.3745 (2.6944) grad_norm: 3.0590 (3.3031) time: 0.4980 [2021-03-27 06:57:02 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 490/1251] eta: 0:06:30 lr: 0.000021 loss: 2.4514 (2.6942) grad_norm: 3.1302 (3.2975) time: 0.4939 [2021-03-27 06:57:07 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 500/1251] eta: 0:06:24 lr: 0.000021 loss: 2.6372 (2.6923) grad_norm: 3.2387 (3.3059) time: 0.4966 [2021-03-27 06:57:12 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 510/1251] eta: 0:06:19 lr: 0.000021 loss: 2.8615 (2.6950) grad_norm: 3.1445 (3.3036) time: 0.4978 [2021-03-27 06:57:17 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 520/1251] eta: 0:06:14 lr: 0.000021 loss: 2.9013 (2.6959) grad_norm: 3.1445 (3.3041) time: 0.5047 [2021-03-27 06:57:22 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 530/1251] eta: 0:06:09 lr: 0.000021 loss: 2.8608 (2.6997) grad_norm: 3.1370 (3.3004) time: 0.5065 [2021-03-27 06:57:27 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 540/1251] eta: 0:06:03 lr: 0.000021 loss: 2.7559 (2.6990) grad_norm: 3.0209 (3.2971) time: 0.5018 [2021-03-27 06:57:32 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 550/1251] eta: 0:05:58 lr: 0.000021 loss: 2.6526 (2.6970) grad_norm: 3.0315 (3.2979) time: 0.5176 [2021-03-27 06:57:37 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 560/1251] eta: 0:05:53 lr: 0.000021 loss: 2.6728 (2.6962) grad_norm: 3.2729 (3.3128) time: 0.5215 [2021-03-27 06:57:42 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 570/1251] eta: 0:05:48 lr: 0.000021 loss: 2.9837 (2.7009) grad_norm: 3.3471 (3.3139) time: 0.5039 [2021-03-27 06:57:47 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 580/1251] eta: 0:05:43 lr: 0.000021 loss: 2.9251 (2.7013) grad_norm: 3.2128 (3.3132) time: 0.5026 [2021-03-27 06:57:52 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 590/1251] eta: 0:05:38 lr: 0.000021 loss: 2.7996 (2.7035) grad_norm: 2.9995 (3.3082) time: 0.5049 [2021-03-27 06:57:58 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 600/1251] eta: 0:05:32 lr: 0.000021 loss: 2.7256 (2.7048) grad_norm: 2.9967 (3.3182) time: 0.5049 [2021-03-27 06:58:03 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 610/1251] eta: 0:05:27 lr: 0.000021 loss: 2.8087 (2.7070) grad_norm: 3.1215 (3.3140) time: 0.5066 [2021-03-27 06:58:08 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 620/1251] eta: 0:05:22 lr: 0.000021 loss: 2.8988 (2.7081) grad_norm: 2.9146 (3.3129) time: 0.5046 [2021-03-27 06:58:13 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 630/1251] eta: 0:05:17 lr: 0.000021 loss: 2.8988 (2.7118) grad_norm: 2.9885 (3.3160) time: 0.5024 [2021-03-27 06:58:18 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 640/1251] eta: 0:05:12 lr: 0.000021 loss: 2.8784 (2.7133) grad_norm: 3.3163 (3.3177) time: 0.5032 [2021-03-27 06:58:23 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 650/1251] eta: 0:05:07 lr: 0.000021 loss: 2.8192 (2.7116) grad_norm: 3.3568 (3.3176) time: 0.5083 [2021-03-27 06:58:28 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 660/1251] eta: 0:05:01 lr: 0.000021 loss: 2.8183 (2.7125) grad_norm: 3.2719 (3.3141) time: 0.5095 [2021-03-27 06:58:33 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 670/1251] eta: 0:04:56 lr: 0.000021 loss: 2.8183 (2.7126) grad_norm: 2.9528 (3.3105) time: 0.5056 [2021-03-27 06:58:38 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 680/1251] eta: 0:04:51 lr: 0.000021 loss: 2.8217 (2.7142) grad_norm: 3.1319 (3.3121) time: 0.4999 [2021-03-27 06:58:43 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 690/1251] eta: 0:04:46 lr: 0.000021 loss: 2.7781 (2.7134) grad_norm: 3.2897 (3.3128) time: 0.5001 [2021-03-27 06:58:48 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 700/1251] eta: 0:04:41 lr: 0.000021 loss: 2.7606 (2.7147) grad_norm: 3.3346 (3.3121) time: 0.5003 [2021-03-27 06:58:53 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 710/1251] eta: 0:04:36 lr: 0.000021 loss: 2.6734 (2.7153) grad_norm: 3.1023 (3.3096) time: 0.5021 [2021-03-27 06:58:58 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 720/1251] eta: 0:04:30 lr: 0.000021 loss: 2.6379 (2.7139) grad_norm: 3.3154 (3.3196) time: 0.5023 [2021-03-27 06:59:03 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 730/1251] eta: 0:04:25 lr: 0.000021 loss: 2.5432 (2.7102) grad_norm: 3.2690 (3.3205) time: 0.5088 [2021-03-27 06:59:09 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 740/1251] eta: 0:04:21 lr: 0.000021 loss: 2.6388 (2.7123) grad_norm: 3.2690 (3.3196) time: 0.5421 [2021-03-27 06:59:14 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 750/1251] eta: 0:04:16 lr: 0.000021 loss: 2.9168 (2.7145) grad_norm: 3.2858 (3.3223) time: 0.5467 [2021-03-27 06:59:19 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 760/1251] eta: 0:04:11 lr: 0.000021 loss: 2.7588 (2.7130) grad_norm: 3.3509 (3.3223) time: 0.5222 [2021-03-27 06:59:24 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 770/1251] eta: 0:04:05 lr: 0.000021 loss: 2.7317 (2.7125) grad_norm: 3.1273 (3.3190) time: 0.5127 [2021-03-27 06:59:29 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 780/1251] eta: 0:04:00 lr: 0.000021 loss: 2.7292 (2.7123) grad_norm: 2.9559 (3.3158) time: 0.5042 [2021-03-27 06:59:34 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 790/1251] eta: 0:03:55 lr: 0.000021 loss: 2.8473 (2.7123) grad_norm: 3.0725 (3.3142) time: 0.5029 [2021-03-27 06:59:39 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 800/1251] eta: 0:03:50 lr: 0.000021 loss: 2.9170 (2.7154) grad_norm: 3.0942 (3.3337) time: 0.5026 [2021-03-27 06:59:44 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 810/1251] eta: 0:03:45 lr: 0.000021 loss: 2.9281 (2.7170) grad_norm: 3.1506 (3.3321) time: 0.5019 [2021-03-27 06:59:49 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 820/1251] eta: 0:03:40 lr: 0.000021 loss: 2.9281 (2.7188) grad_norm: 3.1506 (3.3491) time: 0.5048 [2021-03-27 06:59:54 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 830/1251] eta: 0:03:34 lr: 0.000021 loss: 2.8506 (2.7206) grad_norm: 3.0764 (3.3469) time: 0.4994 [2021-03-27 07:00:00 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 840/1251] eta: 0:03:29 lr: 0.000021 loss: 2.8506 (2.7203) grad_norm: 3.1159 (3.3439) time: 0.5021 [2021-03-27 07:00:05 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 850/1251] eta: 0:03:24 lr: 0.000021 loss: 2.6758 (2.7171) grad_norm: 3.1990 (3.3441) time: 0.5040 [2021-03-27 07:00:10 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 860/1251] eta: 0:03:19 lr: 0.000021 loss: 2.5508 (2.7174) grad_norm: 3.2196 (3.3467) time: 0.5051 [2021-03-27 07:00:15 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 870/1251] eta: 0:03:14 lr: 0.000021 loss: 2.7007 (2.7162) grad_norm: 3.0522 (3.3444) time: 0.5054 [2021-03-27 07:00:20 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 880/1251] eta: 0:03:09 lr: 0.000021 loss: 2.7234 (2.7174) grad_norm: 3.1648 (3.3452) time: 0.5054 [2021-03-27 07:00:25 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 890/1251] eta: 0:03:04 lr: 0.000021 loss: 2.9364 (2.7191) grad_norm: 3.1754 (3.3416) time: 0.5111 [2021-03-27 07:00:30 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 900/1251] eta: 0:02:59 lr: 0.000021 loss: 2.9155 (2.7209) grad_norm: 3.0317 (3.3376) time: 0.5088 [2021-03-27 07:00:35 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 910/1251] eta: 0:02:53 lr: 0.000021 loss: 2.8465 (2.7203) grad_norm: 2.8454 (3.3341) time: 0.5029 [2021-03-27 07:00:40 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 920/1251] eta: 0:02:48 lr: 0.000021 loss: 2.8827 (2.7215) grad_norm: 3.0356 (3.3352) time: 0.5009 [2021-03-27 07:00:45 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 930/1251] eta: 0:02:43 lr: 0.000021 loss: 2.9142 (2.7212) grad_norm: 3.1017 (3.3334) time: 0.5116 [2021-03-27 07:00:50 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 940/1251] eta: 0:02:38 lr: 0.000021 loss: 2.7751 (2.7228) grad_norm: 3.0316 (3.3384) time: 0.5131 [2021-03-27 07:00:55 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 950/1251] eta: 0:02:33 lr: 0.000021 loss: 2.8674 (2.7233) grad_norm: 3.0316 (3.3399) time: 0.5092 [2021-03-27 07:01:00 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 960/1251] eta: 0:02:28 lr: 0.000021 loss: 2.8005 (2.7216) grad_norm: 3.2569 (3.3510) time: 0.5070 [2021-03-27 07:01:05 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 970/1251] eta: 0:02:23 lr: 0.000021 loss: 2.7753 (2.7220) grad_norm: 3.3778 (3.3530) time: 0.5001 [2021-03-27 07:01:10 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 980/1251] eta: 0:02:18 lr: 0.000021 loss: 2.7753 (2.7203) grad_norm: 3.1976 (3.3518) time: 0.5015 [2021-03-27 07:01:16 swin_small_patch4_window7_224] INFO: Epoch: [279] [ 990/1251] eta: 0:02:13 lr: 0.000021 loss: 2.5964 (2.7187) grad_norm: 3.1387 (3.3510) time: 0.5073 [2021-03-27 07:01:21 swin_small_patch4_window7_224] INFO: Epoch: [279] [1000/1251] eta: 0:02:07 lr: 0.000021 loss: 2.5831 (2.7180) grad_norm: 3.1851 (3.3506) time: 0.5070 [2021-03-27 07:01:26 swin_small_patch4_window7_224] INFO: Epoch: [279] [1010/1251] eta: 0:02:02 lr: 0.000021 loss: 2.5831 (2.7165) grad_norm: 3.4446 (3.3522) time: 0.5073 [2021-03-27 07:01:31 swin_small_patch4_window7_224] INFO: Epoch: [279] [1020/1251] eta: 0:01:57 lr: 0.000021 loss: 2.8479 (2.7191) grad_norm: 3.5759 (3.3680) time: 0.5129 [2021-03-27 07:01:36 swin_small_patch4_window7_224] INFO: Epoch: [279] [1030/1251] eta: 0:01:52 lr: 0.000021 loss: 2.9323 (2.7181) grad_norm: 3.3418 (3.3662) time: 0.5085 [2021-03-27 07:01:41 swin_small_patch4_window7_224] INFO: Epoch: [279] [1040/1251] eta: 0:01:47 lr: 0.000021 loss: 2.7725 (2.7184) grad_norm: 2.9842 (3.3639) time: 0.5017 [2021-03-27 07:01:46 swin_small_patch4_window7_224] INFO: Epoch: [279] [1050/1251] eta: 0:01:42 lr: 0.000021 loss: 2.9261 (2.7201) grad_norm: 3.0639 (3.3713) time: 0.5006 [2021-03-27 07:01:51 swin_small_patch4_window7_224] INFO: Epoch: [279] [1060/1251] eta: 0:01:37 lr: 0.000021 loss: 2.8452 (2.7201) grad_norm: 3.0639 (3.3690) time: 0.4967 [2021-03-27 07:01:56 swin_small_patch4_window7_224] INFO: Epoch: [279] [1070/1251] eta: 0:01:32 lr: 0.000021 loss: 2.8452 (2.7205) grad_norm: 3.0350 (3.3661) time: 0.4979 [2021-03-27 07:02:01 swin_small_patch4_window7_224] INFO: Epoch: [279] [1080/1251] eta: 0:01:27 lr: 0.000021 loss: 2.9293 (2.7203) grad_norm: 3.0350 (3.3699) time: 0.5030 [2021-03-27 07:02:06 swin_small_patch4_window7_224] INFO: Epoch: [279] [1090/1251] eta: 0:01:21 lr: 0.000021 loss: 2.7923 (2.7202) grad_norm: 3.1669 (3.3679) time: 0.5017 [2021-03-27 07:02:11 swin_small_patch4_window7_224] INFO: Epoch: [279] [1100/1251] eta: 0:01:16 lr: 0.000021 loss: 2.7319 (2.7196) grad_norm: 3.2263 (3.3661) time: 0.5007 [2021-03-27 07:02:16 swin_small_patch4_window7_224] INFO: Epoch: [279] [1110/1251] eta: 0:01:11 lr: 0.000021 loss: 2.6782 (2.7204) grad_norm: 3.2063 (3.3642) time: 0.5023 [2021-03-27 07:02:21 swin_small_patch4_window7_224] INFO: Epoch: [279] [1120/1251] eta: 0:01:06 lr: 0.000021 loss: 2.5396 (2.7180) grad_norm: 3.0770 (3.3649) time: 0.5038 [2021-03-27 07:02:26 swin_small_patch4_window7_224] INFO: Epoch: [279] [1130/1251] eta: 0:01:01 lr: 0.000021 loss: 2.6532 (2.7180) grad_norm: 3.0770 (3.3692) time: 0.5040 [2021-03-27 07:02:31 swin_small_patch4_window7_224] INFO: Epoch: [279] [1140/1251] eta: 0:00:56 lr: 0.000021 loss: 2.6618 (2.7175) grad_norm: 3.2390 (3.3689) time: 0.5070 [2021-03-27 07:02:36 swin_small_patch4_window7_224] INFO: Epoch: [279] [1150/1251] eta: 0:00:51 lr: 0.000021 loss: 2.8829 (2.7181) grad_norm: 3.0543 (3.3661) time: 0.5113 [2021-03-27 07:02:41 swin_small_patch4_window7_224] INFO: Epoch: [279] [1160/1251] eta: 0:00:46 lr: 0.000021 loss: 2.8824 (2.7174) grad_norm: 3.2013 (3.3675) time: 0.5122 [2021-03-27 07:02:46 swin_small_patch4_window7_224] INFO: Epoch: [279] [1170/1251] eta: 0:00:41 lr: 0.000021 loss: 2.6697 (2.7177) grad_norm: 3.4248 (3.3675) time: 0.5063 [2021-03-27 07:02:51 swin_small_patch4_window7_224] INFO: Epoch: [279] [1180/1251] eta: 0:00:36 lr: 0.000021 loss: 2.8638 (2.7190) grad_norm: 3.0222 (3.3652) time: 0.4987 [2021-03-27 07:02:56 swin_small_patch4_window7_224] INFO: Epoch: [279] [1190/1251] eta: 0:00:31 lr: 0.000021 loss: 2.9420 (2.7199) grad_norm: 3.0537 (3.3646) time: 0.5064 [2021-03-27 07:03:01 swin_small_patch4_window7_224] INFO: Epoch: [279] [1200/1251] eta: 0:00:25 lr: 0.000021 loss: 2.9941 (2.7217) grad_norm: 3.2095 (3.3633) time: 0.5046 [2021-03-27 07:03:06 swin_small_patch4_window7_224] INFO: Epoch: [279] [1210/1251] eta: 0:00:20 lr: 0.000021 loss: 2.8395 (2.7212) grad_norm: 3.1506 (3.3609) time: 0.4969 [2021-03-27 07:03:11 swin_small_patch4_window7_224] INFO: Epoch: [279] [1220/1251] eta: 0:00:15 lr: 0.000021 loss: 2.8201 (2.7224) grad_norm: 3.1506 (3.3593) time: 0.5013 [2021-03-27 07:03:16 swin_small_patch4_window7_224] INFO: Epoch: [279] [1230/1251] eta: 0:00:10 lr: 0.000021 loss: 2.7858 (2.7231) grad_norm: 3.1245 (3.3749) time: 0.5034 [2021-03-27 07:03:21 swin_small_patch4_window7_224] INFO: Epoch: [279] [1240/1251] eta: 0:00:05 lr: 0.000021 loss: 2.7712 (2.7234) grad_norm: 3.0719 (3.3727) time: 0.5029 [2021-03-27 07:03:26 swin_small_patch4_window7_224] INFO: Epoch: [279] [1250/1251] eta: 0:00:00 lr: 0.000021 loss: 2.7939 (2.7229) grad_norm: 2.9797 (3.3695) time: 0.5002 [2021-03-27 07:03:37 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:43 loss: 0.7282 (0.7282) acc1: 84.3750 (84.3750) acc5: 93.7500 (93.7500) [2021-03-27 07:03:40 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7012 (0.6887) acc1: 82.8125 (84.0909) acc5: 96.8750 (97.1591) [2021-03-27 07:03:42 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7109 (0.7190) acc1: 81.2500 (82.8869) acc5: 96.8750 (96.5030) [2021-03-27 07:03:44 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7539 (0.7398) acc1: 81.2500 (82.3085) acc5: 95.3125 (96.5222) [2021-03-27 07:03:46 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7750 (0.7428) acc1: 82.8125 (82.3552) acc5: 95.3125 (96.2652) [2021-03-27 07:03:47 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7750 (0.7500) acc1: 82.8125 (82.3040) acc5: 95.3125 (96.0320) [2021-03-27 07:04:02 swin_small_patch4_window7_224] INFO: * Acc@1 82.924 Acc@5 96.200 loss 0.739 [2021-03-27 07:04:02 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-27 07:04:02 swin_small_patch4_window7_224] INFO: Max accuracy: 82.99% [2021-03-27 07:04:06 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 0/1251] eta: 1:30:23 lr: 0.000021 loss: 2.6715 (2.6715) grad_norm: 3.7845 (3.7845) time: 4.3357 [2021-03-27 07:04:11 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 10/1251] eta: 0:17:58 lr: 0.000021 loss: 2.6940 (2.6025) grad_norm: 3.4048 (3.4716) time: 0.8691 [2021-03-27 07:04:16 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 20/1251] eta: 0:14:10 lr: 0.000021 loss: 2.7963 (2.6763) grad_norm: 3.1501 (3.3727) time: 0.5088 [2021-03-27 07:04:21 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 30/1251] eta: 0:12:47 lr: 0.000021 loss: 2.7431 (2.6953) grad_norm: 3.0216 (3.3432) time: 0.4969 [2021-03-27 07:04:26 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 40/1251] eta: 0:12:03 lr: 0.000021 loss: 2.7385 (2.6909) grad_norm: 3.3451 (3.4574) time: 0.4995 [2021-03-27 07:04:31 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 50/1251] eta: 0:11:35 lr: 0.000021 loss: 2.8238 (2.6891) grad_norm: 3.4040 (3.4299) time: 0.5014 [2021-03-27 07:04:36 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 60/1251] eta: 0:11:14 lr: 0.000021 loss: 2.7770 (2.7010) grad_norm: 3.1930 (3.4084) time: 0.5010 [2021-03-27 07:04:41 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 70/1251] eta: 0:10:58 lr: 0.000021 loss: 2.7770 (2.7154) grad_norm: 3.1930 (3.3794) time: 0.5032 [2021-03-27 07:04:46 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 80/1251] eta: 0:10:45 lr: 0.000021 loss: 2.9417 (2.7450) grad_norm: 3.1575 (3.3417) time: 0.5058 [2021-03-27 07:04:51 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 90/1251] eta: 0:10:33 lr: 0.000021 loss: 2.8803 (2.7333) grad_norm: 3.0528 (3.3310) time: 0.5026 [2021-03-27 07:04:56 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 100/1251] eta: 0:10:22 lr: 0.000021 loss: 2.5345 (2.7160) grad_norm: 3.0528 (3.3140) time: 0.4973 [2021-03-27 07:05:02 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 110/1251] eta: 0:10:14 lr: 0.000021 loss: 2.7486 (2.7095) grad_norm: 3.0405 (3.2830) time: 0.5060 [2021-03-27 07:05:07 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 120/1251] eta: 0:10:05 lr: 0.000021 loss: 2.6427 (2.6897) grad_norm: 2.9350 (3.2863) time: 0.5071 [2021-03-27 07:05:12 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 130/1251] eta: 0:09:57 lr: 0.000021 loss: 2.7494 (2.6943) grad_norm: 3.1477 (3.2800) time: 0.5010 [2021-03-27 07:05:17 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 140/1251] eta: 0:09:49 lr: 0.000021 loss: 2.7494 (2.6970) grad_norm: 3.1310 (inf) time: 0.5064 [2021-03-27 07:05:22 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 150/1251] eta: 0:09:42 lr: 0.000021 loss: 2.7683 (2.6950) grad_norm: 2.9816 (inf) time: 0.5041 [2021-03-27 07:05:27 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 160/1251] eta: 0:09:35 lr: 0.000021 loss: 2.8608 (2.7109) grad_norm: 3.0469 (inf) time: 0.5026 [2021-03-27 07:05:32 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 170/1251] eta: 0:09:28 lr: 0.000021 loss: 2.8608 (2.7171) grad_norm: 3.1806 (inf) time: 0.5026 [2021-03-27 07:05:37 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 180/1251] eta: 0:09:22 lr: 0.000021 loss: 2.8445 (2.7041) grad_norm: 3.1073 (inf) time: 0.5065 [2021-03-27 07:05:42 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 190/1251] eta: 0:09:16 lr: 0.000021 loss: 2.5675 (2.7055) grad_norm: 3.1073 (inf) time: 0.5164 [2021-03-27 07:05:47 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 200/1251] eta: 0:09:10 lr: 0.000021 loss: 2.8437 (2.7065) grad_norm: 3.2578 (inf) time: 0.5167 [2021-03-27 07:05:52 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 210/1251] eta: 0:09:04 lr: 0.000021 loss: 2.7603 (2.7090) grad_norm: 3.2961 (inf) time: 0.5046 [2021-03-27 07:05:57 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 220/1251] eta: 0:08:57 lr: 0.000021 loss: 2.7950 (2.7120) grad_norm: 3.2968 (inf) time: 0.4964 [2021-03-27 07:06:02 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 230/1251] eta: 0:08:51 lr: 0.000021 loss: 2.8178 (2.7193) grad_norm: 3.3697 (inf) time: 0.5012 [2021-03-27 07:06:07 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 240/1251] eta: 0:08:45 lr: 0.000021 loss: 2.7850 (2.7121) grad_norm: 3.0651 (inf) time: 0.5037 [2021-03-27 07:06:12 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 250/1251] eta: 0:08:40 lr: 0.000021 loss: 2.6594 (2.7080) grad_norm: 3.0403 (inf) time: 0.5077 [2021-03-27 07:06:17 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 260/1251] eta: 0:08:34 lr: 0.000021 loss: 2.7853 (2.7091) grad_norm: 3.0946 (inf) time: 0.5103 [2021-03-27 07:06:22 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 270/1251] eta: 0:08:28 lr: 0.000021 loss: 2.7853 (2.7056) grad_norm: 3.2935 (inf) time: 0.5037 [2021-03-27 07:06:28 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 280/1251] eta: 0:08:23 lr: 0.000021 loss: 2.5812 (2.7052) grad_norm: 3.2570 (inf) time: 0.5054 [2021-03-27 07:06:33 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 290/1251] eta: 0:08:17 lr: 0.000021 loss: 2.8309 (2.7095) grad_norm: 2.9971 (inf) time: 0.5047 [2021-03-27 07:06:38 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 300/1251] eta: 0:08:11 lr: 0.000021 loss: 2.7740 (2.7076) grad_norm: 3.2156 (inf) time: 0.5018 [2021-03-27 07:06:43 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 310/1251] eta: 0:08:06 lr: 0.000021 loss: 2.6396 (2.7048) grad_norm: 3.0220 (inf) time: 0.5089 [2021-03-27 07:06:48 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 320/1251] eta: 0:08:01 lr: 0.000021 loss: 2.7369 (2.7059) grad_norm: 3.0370 (inf) time: 0.5081 [2021-03-27 07:06:53 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 330/1251] eta: 0:07:55 lr: 0.000021 loss: 2.8915 (2.7106) grad_norm: 3.1159 (inf) time: 0.4996 [2021-03-27 07:06:58 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 340/1251] eta: 0:07:50 lr: 0.000021 loss: 2.8659 (2.7127) grad_norm: 2.9048 (inf) time: 0.5044 [2021-03-27 07:07:03 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 350/1251] eta: 0:07:44 lr: 0.000021 loss: 2.8430 (2.7146) grad_norm: 3.0730 (inf) time: 0.5081 [2021-03-27 07:07:08 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 360/1251] eta: 0:07:39 lr: 0.000021 loss: 2.9462 (2.7208) grad_norm: 3.2097 (inf) time: 0.5007 [2021-03-27 07:07:13 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 370/1251] eta: 0:07:33 lr: 0.000021 loss: 2.9102 (2.7177) grad_norm: 3.1250 (inf) time: 0.5019 [2021-03-27 07:07:18 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 380/1251] eta: 0:07:28 lr: 0.000020 loss: 2.7900 (2.7193) grad_norm: 3.1407 (inf) time: 0.5058 [2021-03-27 07:07:23 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 390/1251] eta: 0:07:22 lr: 0.000020 loss: 2.7134 (2.7169) grad_norm: 3.1864 (inf) time: 0.5050 [2021-03-27 07:07:28 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 400/1251] eta: 0:07:17 lr: 0.000020 loss: 2.7431 (2.7171) grad_norm: 3.1830 (inf) time: 0.5047 [2021-03-27 07:07:33 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 410/1251] eta: 0:07:12 lr: 0.000020 loss: 2.7724 (2.7128) grad_norm: 3.2078 (inf) time: 0.4992 [2021-03-27 07:07:38 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 420/1251] eta: 0:07:06 lr: 0.000020 loss: 2.5529 (2.7095) grad_norm: 3.1571 (inf) time: 0.4931 [2021-03-27 07:07:43 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 430/1251] eta: 0:07:01 lr: 0.000020 loss: 2.8731 (2.7120) grad_norm: 3.0501 (inf) time: 0.4988 [2021-03-27 07:07:48 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 440/1251] eta: 0:06:55 lr: 0.000020 loss: 2.8850 (2.7114) grad_norm: 3.0501 (inf) time: 0.5023 [2021-03-27 07:07:53 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 450/1251] eta: 0:06:50 lr: 0.000020 loss: 2.8658 (2.7121) grad_norm: 3.2418 (inf) time: 0.4973 [2021-03-27 07:07:58 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 460/1251] eta: 0:06:45 lr: 0.000020 loss: 2.6893 (2.7082) grad_norm: 3.0577 (inf) time: 0.5004 [2021-03-27 07:08:03 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 470/1251] eta: 0:06:40 lr: 0.000020 loss: 2.6893 (2.7080) grad_norm: 2.9595 (inf) time: 0.5119 [2021-03-27 07:08:08 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 480/1251] eta: 0:06:34 lr: 0.000020 loss: 2.9452 (2.7082) grad_norm: 3.0765 (inf) time: 0.5109 [2021-03-27 07:08:13 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 490/1251] eta: 0:06:29 lr: 0.000020 loss: 2.8456 (2.7086) grad_norm: 3.1142 (inf) time: 0.5002 [2021-03-27 07:08:18 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 500/1251] eta: 0:06:24 lr: 0.000020 loss: 2.6687 (2.7066) grad_norm: 3.3722 (inf) time: 0.5010 [2021-03-27 07:08:23 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 510/1251] eta: 0:06:19 lr: 0.000020 loss: 2.6890 (2.7099) grad_norm: 3.2685 (inf) time: 0.5051 [2021-03-27 07:08:28 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 520/1251] eta: 0:06:13 lr: 0.000020 loss: 2.8167 (2.7061) grad_norm: 3.1166 (inf) time: 0.4991 [2021-03-27 07:08:33 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 530/1251] eta: 0:06:08 lr: 0.000020 loss: 2.4669 (2.7031) grad_norm: 3.1166 (inf) time: 0.4954 [2021-03-27 07:08:38 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 540/1251] eta: 0:06:03 lr: 0.000020 loss: 2.7231 (2.7056) grad_norm: 3.3765 (inf) time: 0.5098 [2021-03-27 07:08:44 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 550/1251] eta: 0:05:58 lr: 0.000020 loss: 2.8116 (2.7051) grad_norm: 3.4237 (inf) time: 0.5291 [2021-03-27 07:08:49 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 560/1251] eta: 0:05:53 lr: 0.000020 loss: 2.7838 (2.7052) grad_norm: 3.3484 (inf) time: 0.5174 [2021-03-27 07:08:54 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 570/1251] eta: 0:05:48 lr: 0.000020 loss: 2.8949 (2.7091) grad_norm: 3.2115 (inf) time: 0.5030 [2021-03-27 07:08:59 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 580/1251] eta: 0:05:42 lr: 0.000020 loss: 2.9352 (2.7104) grad_norm: 3.5146 (inf) time: 0.5057 [2021-03-27 07:09:04 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 590/1251] eta: 0:05:37 lr: 0.000020 loss: 2.8206 (2.7099) grad_norm: 3.1917 (inf) time: 0.5121 [2021-03-27 07:09:09 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 600/1251] eta: 0:05:32 lr: 0.000020 loss: 2.7385 (2.7111) grad_norm: 3.0796 (inf) time: 0.5112 [2021-03-27 07:09:14 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 610/1251] eta: 0:05:27 lr: 0.000020 loss: 2.7385 (2.7103) grad_norm: 3.0132 (inf) time: 0.5048 [2021-03-27 07:09:19 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 620/1251] eta: 0:05:22 lr: 0.000020 loss: 2.7832 (2.7090) grad_norm: 3.0132 (inf) time: 0.5040 [2021-03-27 07:09:24 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 630/1251] eta: 0:05:17 lr: 0.000020 loss: 2.8017 (2.7066) grad_norm: 3.0618 (inf) time: 0.5072 [2021-03-27 07:09:29 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 640/1251] eta: 0:05:12 lr: 0.000020 loss: 2.8444 (2.7100) grad_norm: 3.0106 (inf) time: 0.5063 [2021-03-27 07:09:34 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 650/1251] eta: 0:05:06 lr: 0.000020 loss: 2.6888 (2.7055) grad_norm: 3.2474 (inf) time: 0.4997 [2021-03-27 07:09:39 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 660/1251] eta: 0:05:01 lr: 0.000020 loss: 2.6843 (2.7076) grad_norm: 3.2549 (inf) time: 0.5002 [2021-03-27 07:09:44 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 670/1251] eta: 0:04:56 lr: 0.000020 loss: 2.7607 (2.7060) grad_norm: 3.1606 (inf) time: 0.5020 [2021-03-27 07:09:49 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 680/1251] eta: 0:04:51 lr: 0.000020 loss: 2.5100 (2.7033) grad_norm: 3.3622 (inf) time: 0.5017 [2021-03-27 07:09:54 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 690/1251] eta: 0:04:46 lr: 0.000020 loss: 2.6598 (2.7040) grad_norm: 3.1723 (inf) time: 0.5028 [2021-03-27 07:09:59 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 700/1251] eta: 0:04:41 lr: 0.000020 loss: 3.0007 (2.7072) grad_norm: 3.1212 (inf) time: 0.5054 [2021-03-27 07:10:04 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 710/1251] eta: 0:04:35 lr: 0.000020 loss: 2.9315 (2.7077) grad_norm: 3.0955 (inf) time: 0.5008 [2021-03-27 07:10:10 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 720/1251] eta: 0:04:30 lr: 0.000020 loss: 2.8187 (2.7083) grad_norm: 3.2828 (inf) time: 0.5034 [2021-03-27 07:10:15 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 730/1251] eta: 0:04:25 lr: 0.000020 loss: 2.7646 (2.7067) grad_norm: 3.2261 (inf) time: 0.5165 [2021-03-27 07:10:20 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 740/1251] eta: 0:04:20 lr: 0.000020 loss: 2.8821 (2.7081) grad_norm: 3.0427 (inf) time: 0.5395 [2021-03-27 07:10:26 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 750/1251] eta: 0:04:15 lr: 0.000020 loss: 2.8741 (2.7064) grad_norm: 2.9651 (inf) time: 0.5384 [2021-03-27 07:10:31 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 760/1251] eta: 0:04:10 lr: 0.000020 loss: 2.8702 (2.7085) grad_norm: 3.0212 (inf) time: 0.5147 [2021-03-27 07:10:36 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 770/1251] eta: 0:04:05 lr: 0.000020 loss: 2.8714 (2.7064) grad_norm: 3.1968 (inf) time: 0.5057 [2021-03-27 07:10:41 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 780/1251] eta: 0:04:00 lr: 0.000020 loss: 2.7571 (2.7061) grad_norm: 3.1968 (inf) time: 0.5039 [2021-03-27 07:10:46 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 790/1251] eta: 0:03:55 lr: 0.000020 loss: 2.7426 (2.7046) grad_norm: 3.1809 (inf) time: 0.4992 [2021-03-27 07:10:51 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 800/1251] eta: 0:03:50 lr: 0.000020 loss: 2.6631 (2.7030) grad_norm: 3.1701 (inf) time: 0.5009 [2021-03-27 07:10:56 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 810/1251] eta: 0:03:44 lr: 0.000020 loss: 2.7701 (2.7076) grad_norm: 3.0862 (inf) time: 0.5013 [2021-03-27 07:11:01 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 820/1251] eta: 0:03:39 lr: 0.000020 loss: 3.0151 (2.7098) grad_norm: 3.0394 (inf) time: 0.4999 [2021-03-27 07:11:06 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 830/1251] eta: 0:03:34 lr: 0.000020 loss: 2.6625 (2.7097) grad_norm: 3.0415 (inf) time: 0.5075 [2021-03-27 07:11:11 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 840/1251] eta: 0:03:29 lr: 0.000020 loss: 2.6625 (2.7108) grad_norm: 3.1511 (inf) time: 0.5033 [2021-03-27 07:11:16 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 850/1251] eta: 0:03:24 lr: 0.000020 loss: 2.9288 (2.7126) grad_norm: 3.1318 (inf) time: 0.4971 [2021-03-27 07:11:21 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 860/1251] eta: 0:03:19 lr: 0.000020 loss: 2.6633 (2.7112) grad_norm: 3.1774 (inf) time: 0.5035 [2021-03-27 07:11:26 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 870/1251] eta: 0:03:14 lr: 0.000020 loss: 2.5999 (2.7110) grad_norm: 3.1970 (inf) time: 0.5058 [2021-03-27 07:11:31 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 880/1251] eta: 0:03:09 lr: 0.000020 loss: 2.9053 (2.7123) grad_norm: 3.1594 (inf) time: 0.5043 [2021-03-27 07:11:36 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 890/1251] eta: 0:03:03 lr: 0.000020 loss: 2.9062 (2.7124) grad_norm: 3.3796 (inf) time: 0.5074 [2021-03-27 07:11:41 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 900/1251] eta: 0:02:58 lr: 0.000020 loss: 2.8265 (2.7119) grad_norm: 3.3796 (inf) time: 0.5105 [2021-03-27 07:11:46 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 910/1251] eta: 0:02:53 lr: 0.000020 loss: 2.8403 (2.7128) grad_norm: 3.2085 (inf) time: 0.5074 [2021-03-27 07:11:51 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 920/1251] eta: 0:02:48 lr: 0.000020 loss: 2.8403 (2.7127) grad_norm: 3.1596 (inf) time: 0.5055 [2021-03-27 07:11:56 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 930/1251] eta: 0:02:43 lr: 0.000020 loss: 2.7018 (2.7115) grad_norm: 3.0609 (inf) time: 0.5116 [2021-03-27 07:12:02 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 940/1251] eta: 0:02:38 lr: 0.000020 loss: 2.7857 (2.7113) grad_norm: 3.0743 (inf) time: 0.5194 [2021-03-27 07:12:07 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 950/1251] eta: 0:02:33 lr: 0.000020 loss: 2.5643 (2.7087) grad_norm: 3.1293 (inf) time: 0.5091 [2021-03-27 07:12:12 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 960/1251] eta: 0:02:28 lr: 0.000020 loss: 2.6557 (2.7101) grad_norm: 3.1388 (inf) time: 0.4978 [2021-03-27 07:12:17 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 970/1251] eta: 0:02:23 lr: 0.000020 loss: 2.8296 (2.7088) grad_norm: 3.1388 (inf) time: 0.5031 [2021-03-27 07:12:22 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 980/1251] eta: 0:02:18 lr: 0.000020 loss: 2.7233 (2.7103) grad_norm: 2.9764 (inf) time: 0.5059 [2021-03-27 07:12:27 swin_small_patch4_window7_224] INFO: Epoch: [280] [ 990/1251] eta: 0:02:12 lr: 0.000020 loss: 2.7143 (2.7092) grad_norm: 2.9780 (inf) time: 0.5074 [2021-03-27 07:12:32 swin_small_patch4_window7_224] INFO: Epoch: [280] [1000/1251] eta: 0:02:07 lr: 0.000020 loss: 2.7656 (2.7118) grad_norm: 3.1813 (inf) time: 0.5077 [2021-03-27 07:12:37 swin_small_patch4_window7_224] INFO: Epoch: [280] [1010/1251] eta: 0:02:02 lr: 0.000020 loss: 2.9793 (2.7139) grad_norm: 3.3981 (inf) time: 0.5058 [2021-03-27 07:12:42 swin_small_patch4_window7_224] INFO: Epoch: [280] [1020/1251] eta: 0:01:57 lr: 0.000020 loss: 2.8565 (2.7142) grad_norm: 3.2507 (inf) time: 0.5093 [2021-03-27 07:12:47 swin_small_patch4_window7_224] INFO: Epoch: [280] [1030/1251] eta: 0:01:52 lr: 0.000020 loss: 2.8292 (2.7146) grad_norm: 3.1492 (inf) time: 0.5107 [2021-03-27 07:12:52 swin_small_patch4_window7_224] INFO: Epoch: [280] [1040/1251] eta: 0:01:47 lr: 0.000020 loss: 2.7905 (2.7150) grad_norm: 3.3423 (inf) time: 0.5133 [2021-03-27 07:12:58 swin_small_patch4_window7_224] INFO: Epoch: [280] [1050/1251] eta: 0:01:42 lr: 0.000020 loss: 2.6993 (2.7147) grad_norm: 3.3501 (inf) time: 0.5213 [2021-03-27 07:13:03 swin_small_patch4_window7_224] INFO: Epoch: [280] [1060/1251] eta: 0:01:37 lr: 0.000020 loss: 2.5844 (2.7126) grad_norm: 3.2251 (inf) time: 0.5174 [2021-03-27 07:13:08 swin_small_patch4_window7_224] INFO: Epoch: [280] [1070/1251] eta: 0:01:32 lr: 0.000020 loss: 2.5844 (2.7127) grad_norm: 3.0456 (inf) time: 0.5046 [2021-03-27 07:13:13 swin_small_patch4_window7_224] INFO: Epoch: [280] [1080/1251] eta: 0:01:27 lr: 0.000020 loss: 2.7626 (2.7129) grad_norm: 3.2256 (inf) time: 0.5024 [2021-03-27 07:13:18 swin_small_patch4_window7_224] INFO: Epoch: [280] [1090/1251] eta: 0:01:22 lr: 0.000020 loss: 2.7894 (2.7132) grad_norm: 3.1643 (inf) time: 0.5043 [2021-03-27 07:13:23 swin_small_patch4_window7_224] INFO: Epoch: [280] [1100/1251] eta: 0:01:16 lr: 0.000020 loss: 2.7894 (2.7134) grad_norm: 3.1608 (inf) time: 0.5008 [2021-03-27 07:13:28 swin_small_patch4_window7_224] INFO: Epoch: [280] [1110/1251] eta: 0:01:11 lr: 0.000020 loss: 2.8708 (2.7137) grad_norm: 3.2082 (inf) time: 0.5043 [2021-03-27 07:13:33 swin_small_patch4_window7_224] INFO: Epoch: [280] [1120/1251] eta: 0:01:06 lr: 0.000020 loss: 2.8163 (2.7131) grad_norm: 3.0054 (inf) time: 0.5052 [2021-03-27 07:13:38 swin_small_patch4_window7_224] INFO: Epoch: [280] [1130/1251] eta: 0:01:01 lr: 0.000020 loss: 2.8035 (2.7138) grad_norm: 3.0054 (inf) time: 0.4979 [2021-03-27 07:13:43 swin_small_patch4_window7_224] INFO: Epoch: [280] [1140/1251] eta: 0:00:56 lr: 0.000020 loss: 2.8360 (2.7131) grad_norm: 2.9920 (inf) time: 0.4964 [2021-03-27 07:13:48 swin_small_patch4_window7_224] INFO: Epoch: [280] [1150/1251] eta: 0:00:51 lr: 0.000020 loss: 2.8431 (2.7138) grad_norm: 2.9920 (inf) time: 0.5004 [2021-03-27 07:13:53 swin_small_patch4_window7_224] INFO: Epoch: [280] [1160/1251] eta: 0:00:46 lr: 0.000020 loss: 2.8695 (2.7129) grad_norm: 3.0209 (inf) time: 0.4988 [2021-03-27 07:13:58 swin_small_patch4_window7_224] INFO: Epoch: [280] [1170/1251] eta: 0:00:41 lr: 0.000020 loss: 2.8349 (2.7127) grad_norm: 3.0737 (inf) time: 0.5001 [2021-03-27 07:14:03 swin_small_patch4_window7_224] INFO: Epoch: [280] [1180/1251] eta: 0:00:36 lr: 0.000020 loss: 2.7878 (2.7122) grad_norm: 3.1074 (inf) time: 0.5059 [2021-03-27 07:14:08 swin_small_patch4_window7_224] INFO: Epoch: [280] [1190/1251] eta: 0:00:31 lr: 0.000020 loss: 2.7081 (2.7118) grad_norm: 2.9521 (inf) time: 0.5089 [2021-03-27 07:14:13 swin_small_patch4_window7_224] INFO: Epoch: [280] [1200/1251] eta: 0:00:25 lr: 0.000020 loss: 2.7081 (2.7112) grad_norm: 3.1390 (inf) time: 0.5039 [2021-03-27 07:14:18 swin_small_patch4_window7_224] INFO: Epoch: [280] [1210/1251] eta: 0:00:20 lr: 0.000020 loss: 2.6762 (2.7098) grad_norm: 3.1362 (inf) time: 0.4952 [2021-03-27 07:14:23 swin_small_patch4_window7_224] INFO: Epoch: [280] [1220/1251] eta: 0:00:15 lr: 0.000020 loss: 2.7399 (2.7104) grad_norm: 3.0395 (inf) time: 0.5015 [2021-03-27 07:14:28 swin_small_patch4_window7_224] INFO: Epoch: [280] [1230/1251] eta: 0:00:10 lr: 0.000020 loss: 2.7222 (2.7106) grad_norm: 3.0084 (inf) time: 0.5078 [2021-03-27 07:14:33 swin_small_patch4_window7_224] INFO: Epoch: [280] [1240/1251] eta: 0:00:05 lr: 0.000020 loss: 2.6686 (2.7107) grad_norm: 3.1105 (inf) time: 0.4994 [2021-03-27 07:14:38 swin_small_patch4_window7_224] INFO: Epoch: [280] [1250/1251] eta: 0:00:00 lr: 0.000020 loss: 2.7412 (2.7116) grad_norm: 3.1536 (inf) time: 0.4906 [2021-03-27 07:15:26 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:09 loss: 0.6480 (0.6480) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-27 07:15:27 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7101 (0.7279) acc1: 82.8125 (82.6705) acc5: 96.8750 (96.3068) [2021-03-27 07:15:28 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7101 (0.7271) acc1: 82.8125 (82.8125) acc5: 96.8750 (95.8333) [2021-03-27 07:15:29 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7389 (0.7385) acc1: 82.8125 (82.4597) acc5: 95.3125 (95.7661) [2021-03-27 07:15:30 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7298 (0.7347) acc1: 81.2500 (82.4695) acc5: 95.3125 (95.9985) [2021-03-27 07:15:31 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7142 (0.7519) acc1: 82.8125 (82.0480) acc5: 96.2264 (96.0320) [2021-03-27 07:15:42 swin_small_patch4_window7_224] INFO: * Acc@1 82.992 Acc@5 96.194 loss 0.738 [2021-03-27 07:15:42 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 07:15:42 swin_small_patch4_window7_224] INFO: Max accuracy: 82.99% [2021-03-27 07:15:46 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 0/1251] eta: 1:29:50 lr: 0.000020 loss: 3.0856 (3.0856) grad_norm: 3.3848 (3.3848) time: 4.3093 [2021-03-27 07:15:51 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 10/1251] eta: 0:17:37 lr: 0.000020 loss: 2.6615 (2.6526) grad_norm: 3.1324 (3.2236) time: 0.8523 [2021-03-27 07:15:56 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 20/1251] eta: 0:14:10 lr: 0.000020 loss: 2.6615 (2.6799) grad_norm: 3.2119 (3.2959) time: 0.5100 [2021-03-27 07:16:01 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 30/1251] eta: 0:12:52 lr: 0.000020 loss: 2.6621 (2.6217) grad_norm: 3.1734 (3.2916) time: 0.5121 [2021-03-27 07:16:07 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 40/1251] eta: 0:12:09 lr: 0.000020 loss: 2.5948 (2.6117) grad_norm: 3.0656 (3.2793) time: 0.5090 [2021-03-27 07:16:12 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 50/1251] eta: 0:11:39 lr: 0.000020 loss: 2.7470 (2.6707) grad_norm: 3.1710 (3.2626) time: 0.5041 [2021-03-27 07:16:17 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 60/1251] eta: 0:11:17 lr: 0.000020 loss: 2.8919 (2.6937) grad_norm: 3.2001 (3.2916) time: 0.5002 [2021-03-27 07:16:22 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 70/1251] eta: 0:11:01 lr: 0.000020 loss: 2.8567 (2.7036) grad_norm: 3.1524 (3.3029) time: 0.5028 [2021-03-27 07:16:27 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 80/1251] eta: 0:10:46 lr: 0.000020 loss: 2.9233 (2.7118) grad_norm: 3.1847 (3.2932) time: 0.5022 [2021-03-27 07:16:32 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 90/1251] eta: 0:10:38 lr: 0.000020 loss: 2.8942 (2.7247) grad_norm: 3.1847 (3.3257) time: 0.5148 [2021-03-27 07:16:37 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 100/1251] eta: 0:10:27 lr: 0.000020 loss: 2.8119 (2.7317) grad_norm: 3.2925 (3.3485) time: 0.5177 [2021-03-27 07:16:42 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 110/1251] eta: 0:10:19 lr: 0.000020 loss: 2.9004 (2.7401) grad_norm: 3.3557 (3.3371) time: 0.5092 [2021-03-27 07:16:47 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 120/1251] eta: 0:10:10 lr: 0.000020 loss: 2.7571 (2.7360) grad_norm: 3.2225 (3.3706) time: 0.5102 [2021-03-27 07:16:52 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 130/1251] eta: 0:10:02 lr: 0.000020 loss: 2.7571 (2.7392) grad_norm: 2.9764 (3.3374) time: 0.5077 [2021-03-27 07:16:57 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 140/1251] eta: 0:09:54 lr: 0.000020 loss: 2.6068 (2.7266) grad_norm: 2.9750 (3.3514) time: 0.5048 [2021-03-27 07:17:02 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 150/1251] eta: 0:09:46 lr: 0.000020 loss: 2.7897 (2.7384) grad_norm: 3.2376 (3.3494) time: 0.5022 [2021-03-27 07:17:07 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 160/1251] eta: 0:09:38 lr: 0.000020 loss: 2.7752 (2.7338) grad_norm: 3.1468 (3.3472) time: 0.4994 [2021-03-27 07:17:12 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 170/1251] eta: 0:09:31 lr: 0.000020 loss: 2.7167 (2.7427) grad_norm: 2.9862 (3.3452) time: 0.4984 [2021-03-27 07:17:17 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 180/1251] eta: 0:09:25 lr: 0.000020 loss: 2.8557 (2.7408) grad_norm: 2.8995 (3.3374) time: 0.5073 [2021-03-27 07:17:22 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 190/1251] eta: 0:09:18 lr: 0.000020 loss: 2.6789 (2.7335) grad_norm: 3.1449 (3.3545) time: 0.5112 [2021-03-27 07:17:28 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 200/1251] eta: 0:09:12 lr: 0.000020 loss: 2.8020 (2.7399) grad_norm: 3.1709 (3.3433) time: 0.5074 [2021-03-27 07:17:33 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 210/1251] eta: 0:09:06 lr: 0.000020 loss: 2.8020 (2.7310) grad_norm: 3.1327 (3.3411) time: 0.5044 [2021-03-27 07:17:38 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 220/1251] eta: 0:09:00 lr: 0.000020 loss: 2.9068 (2.7411) grad_norm: 3.1327 (3.3386) time: 0.5053 [2021-03-27 07:17:43 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 230/1251] eta: 0:08:53 lr: 0.000020 loss: 2.9206 (2.7385) grad_norm: 3.1787 (3.3393) time: 0.5045 [2021-03-27 07:17:48 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 240/1251] eta: 0:08:48 lr: 0.000020 loss: 2.6601 (2.7298) grad_norm: 3.0778 (3.3317) time: 0.5060 [2021-03-27 07:17:53 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 250/1251] eta: 0:08:42 lr: 0.000020 loss: 2.6326 (2.7262) grad_norm: 3.0592 (3.3332) time: 0.5074 [2021-03-27 07:17:58 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 260/1251] eta: 0:08:36 lr: 0.000020 loss: 2.6326 (2.7187) grad_norm: 3.0842 (3.3273) time: 0.5056 [2021-03-27 07:18:03 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 270/1251] eta: 0:08:30 lr: 0.000020 loss: 2.5559 (2.7147) grad_norm: 3.2562 (3.3498) time: 0.5024 [2021-03-27 07:18:08 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 280/1251] eta: 0:08:24 lr: 0.000020 loss: 2.7168 (2.7159) grad_norm: 3.2562 (3.3534) time: 0.5019 [2021-03-27 07:18:13 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 290/1251] eta: 0:08:18 lr: 0.000020 loss: 2.9075 (2.7209) grad_norm: 3.2065 (3.3506) time: 0.5036 [2021-03-27 07:18:18 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 300/1251] eta: 0:08:13 lr: 0.000020 loss: 2.6690 (2.7176) grad_norm: 3.1176 (3.3446) time: 0.5091 [2021-03-27 07:18:23 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 310/1251] eta: 0:08:07 lr: 0.000020 loss: 2.6226 (2.7139) grad_norm: 3.1190 (3.3382) time: 0.5083 [2021-03-27 07:18:28 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 320/1251] eta: 0:08:02 lr: 0.000020 loss: 2.7120 (2.7119) grad_norm: 3.1123 (3.3470) time: 0.5056 [2021-03-27 07:18:33 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 330/1251] eta: 0:07:56 lr: 0.000019 loss: 2.7531 (2.7120) grad_norm: 3.0816 (3.3386) time: 0.5052 [2021-03-27 07:18:38 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 340/1251] eta: 0:07:51 lr: 0.000019 loss: 2.8505 (2.7168) grad_norm: 3.0815 (3.3382) time: 0.5070 [2021-03-27 07:18:43 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 350/1251] eta: 0:07:45 lr: 0.000019 loss: 2.9530 (2.7205) grad_norm: 3.1154 (3.3330) time: 0.5067 [2021-03-27 07:18:48 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 360/1251] eta: 0:07:40 lr: 0.000019 loss: 2.8035 (2.7185) grad_norm: 3.0817 (3.3321) time: 0.5023 [2021-03-27 07:18:53 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 370/1251] eta: 0:07:34 lr: 0.000019 loss: 2.8035 (2.7201) grad_norm: 3.0860 (3.3411) time: 0.5057 [2021-03-27 07:18:59 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 380/1251] eta: 0:07:29 lr: 0.000019 loss: 2.7877 (2.7177) grad_norm: 3.4272 (3.3673) time: 0.5043 [2021-03-27 07:19:03 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 390/1251] eta: 0:07:23 lr: 0.000019 loss: 2.6534 (2.7168) grad_norm: 3.2810 (3.3652) time: 0.5004 [2021-03-27 07:19:08 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 400/1251] eta: 0:07:18 lr: 0.000019 loss: 2.6986 (2.7122) grad_norm: 3.0673 (3.3742) time: 0.4980 [2021-03-27 07:19:14 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 410/1251] eta: 0:07:13 lr: 0.000019 loss: 2.5025 (2.7054) grad_norm: 3.0400 (3.3661) time: 0.5035 [2021-03-27 07:19:19 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 420/1251] eta: 0:07:07 lr: 0.000019 loss: 2.5231 (2.7053) grad_norm: 3.0400 (3.3626) time: 0.5032 [2021-03-27 07:19:24 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 430/1251] eta: 0:07:02 lr: 0.000019 loss: 2.7054 (2.7064) grad_norm: 3.1622 (3.3576) time: 0.5022 [2021-03-27 07:19:29 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 440/1251] eta: 0:06:56 lr: 0.000019 loss: 2.7616 (2.7080) grad_norm: 3.1622 (3.3560) time: 0.5021 [2021-03-27 07:19:34 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 450/1251] eta: 0:06:51 lr: 0.000019 loss: 2.5800 (2.7026) grad_norm: 3.1682 (3.3549) time: 0.4955 [2021-03-27 07:19:39 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 460/1251] eta: 0:06:46 lr: 0.000019 loss: 2.4456 (2.6995) grad_norm: 3.0831 (3.3482) time: 0.4994 [2021-03-27 07:19:44 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 470/1251] eta: 0:06:40 lr: 0.000019 loss: 2.7092 (2.7035) grad_norm: 3.0913 (3.3463) time: 0.5036 [2021-03-27 07:19:49 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 480/1251] eta: 0:06:35 lr: 0.000019 loss: 2.8318 (2.7030) grad_norm: 3.1190 (3.3424) time: 0.5016 [2021-03-27 07:19:54 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 490/1251] eta: 0:06:30 lr: 0.000019 loss: 2.7562 (2.7029) grad_norm: 3.2133 (3.3453) time: 0.5039 [2021-03-27 07:19:59 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 500/1251] eta: 0:06:24 lr: 0.000019 loss: 2.7562 (2.7029) grad_norm: 3.2678 (3.3486) time: 0.5024 [2021-03-27 07:20:04 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 510/1251] eta: 0:06:19 lr: 0.000019 loss: 2.6810 (2.7022) grad_norm: 3.2773 (3.3622) time: 0.5006 [2021-03-27 07:20:09 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 520/1251] eta: 0:06:14 lr: 0.000019 loss: 2.7335 (2.7048) grad_norm: 3.2277 (3.3585) time: 0.5015 [2021-03-27 07:20:14 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 530/1251] eta: 0:06:09 lr: 0.000019 loss: 2.7335 (2.7037) grad_norm: 3.1403 (3.3637) time: 0.5020 [2021-03-27 07:20:19 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 540/1251] eta: 0:06:03 lr: 0.000019 loss: 2.3832 (2.6963) grad_norm: 3.0985 (3.3624) time: 0.5006 [2021-03-27 07:20:24 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 550/1251] eta: 0:05:58 lr: 0.000019 loss: 2.6406 (2.6947) grad_norm: 3.0667 (3.3578) time: 0.5144 [2021-03-27 07:20:29 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 560/1251] eta: 0:05:53 lr: 0.000019 loss: 2.7562 (2.6931) grad_norm: 3.3281 (3.3604) time: 0.5202 [2021-03-27 07:20:34 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 570/1251] eta: 0:05:48 lr: 0.000019 loss: 2.7539 (2.6924) grad_norm: 3.3376 (3.3598) time: 0.5018 [2021-03-27 07:20:39 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 580/1251] eta: 0:05:43 lr: 0.000019 loss: 2.6735 (2.6909) grad_norm: 3.1852 (3.3569) time: 0.4957 [2021-03-27 07:20:44 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 590/1251] eta: 0:05:38 lr: 0.000019 loss: 2.6398 (2.6909) grad_norm: 3.2162 (3.3579) time: 0.5046 [2021-03-27 07:20:49 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 600/1251] eta: 0:05:32 lr: 0.000019 loss: 2.8475 (2.6933) grad_norm: 3.2162 (3.3574) time: 0.5109 [2021-03-27 07:20:54 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 610/1251] eta: 0:05:27 lr: 0.000019 loss: 2.8409 (2.6923) grad_norm: 3.2433 (3.3542) time: 0.5050 [2021-03-27 07:20:59 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 620/1251] eta: 0:05:22 lr: 0.000019 loss: 2.5765 (2.6890) grad_norm: 3.2433 (3.3529) time: 0.5035 [2021-03-27 07:21:04 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 630/1251] eta: 0:05:17 lr: 0.000019 loss: 2.7239 (2.6915) grad_norm: 3.2080 (3.3512) time: 0.5081 [2021-03-27 07:21:10 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 640/1251] eta: 0:05:12 lr: 0.000019 loss: 2.7786 (2.6912) grad_norm: 3.1468 (3.3478) time: 0.5109 [2021-03-27 07:21:15 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 650/1251] eta: 0:05:07 lr: 0.000019 loss: 2.7786 (2.6929) grad_norm: 3.0053 (3.3448) time: 0.5087 [2021-03-27 07:21:20 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 660/1251] eta: 0:05:01 lr: 0.000019 loss: 2.7227 (2.6931) grad_norm: 3.0323 (3.3430) time: 0.5033 [2021-03-27 07:21:25 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 670/1251] eta: 0:04:56 lr: 0.000019 loss: 2.6711 (2.6940) grad_norm: 3.1045 (3.3458) time: 0.5042 [2021-03-27 07:21:30 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 680/1251] eta: 0:04:51 lr: 0.000019 loss: 2.8208 (2.6938) grad_norm: 3.2762 (3.3506) time: 0.5055 [2021-03-27 07:21:35 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 690/1251] eta: 0:04:46 lr: 0.000019 loss: 2.5223 (2.6908) grad_norm: 3.2713 (3.3508) time: 0.5022 [2021-03-27 07:21:40 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 700/1251] eta: 0:04:41 lr: 0.000019 loss: 2.5338 (2.6922) grad_norm: 3.1826 (3.3503) time: 0.5044 [2021-03-27 07:21:45 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 710/1251] eta: 0:04:36 lr: 0.000019 loss: 2.6508 (2.6926) grad_norm: 3.1103 (3.3501) time: 0.5037 [2021-03-27 07:21:50 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 720/1251] eta: 0:04:30 lr: 0.000019 loss: 2.8386 (2.6940) grad_norm: 3.3690 (3.3592) time: 0.5013 [2021-03-27 07:21:55 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 730/1251] eta: 0:04:25 lr: 0.000019 loss: 2.8222 (2.6934) grad_norm: 3.2878 (3.3583) time: 0.5104 [2021-03-27 07:22:00 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 740/1251] eta: 0:04:20 lr: 0.000019 loss: 2.8220 (2.6937) grad_norm: 3.1717 (3.3577) time: 0.5248 [2021-03-27 07:22:05 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 750/1251] eta: 0:04:15 lr: 0.000019 loss: 2.7923 (2.6961) grad_norm: 3.3544 (3.3590) time: 0.5137 [2021-03-27 07:22:10 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 760/1251] eta: 0:04:10 lr: 0.000019 loss: 2.7923 (2.6954) grad_norm: 3.1418 (3.3582) time: 0.4990 [2021-03-27 07:22:15 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 770/1251] eta: 0:04:05 lr: 0.000019 loss: 2.8176 (2.6979) grad_norm: 3.1418 (3.3583) time: 0.5023 [2021-03-27 07:22:20 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 780/1251] eta: 0:04:00 lr: 0.000019 loss: 2.8176 (2.7003) grad_norm: 3.2749 (3.3580) time: 0.5041 [2021-03-27 07:22:25 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 790/1251] eta: 0:03:55 lr: 0.000019 loss: 2.8694 (2.7031) grad_norm: 3.2281 (3.3581) time: 0.5049 [2021-03-27 07:22:30 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 800/1251] eta: 0:03:49 lr: 0.000019 loss: 2.8066 (2.7027) grad_norm: 3.3239 (3.3606) time: 0.5009 [2021-03-27 07:22:36 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 810/1251] eta: 0:03:44 lr: 0.000019 loss: 2.6424 (2.7041) grad_norm: 3.2884 (3.3589) time: 0.5035 [2021-03-27 07:22:41 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 820/1251] eta: 0:03:39 lr: 0.000019 loss: 2.8286 (2.7037) grad_norm: 3.1447 (3.3564) time: 0.5079 [2021-03-27 07:22:46 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 830/1251] eta: 0:03:34 lr: 0.000019 loss: 2.7273 (2.7044) grad_norm: 3.1447 (3.3576) time: 0.5077 [2021-03-27 07:22:51 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 840/1251] eta: 0:03:29 lr: 0.000019 loss: 2.6823 (2.7021) grad_norm: 3.2503 (3.3613) time: 0.5091 [2021-03-27 07:22:56 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 850/1251] eta: 0:03:24 lr: 0.000019 loss: 2.4465 (2.7010) grad_norm: 3.2772 (3.3639) time: 0.5116 [2021-03-27 07:23:01 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 860/1251] eta: 0:03:19 lr: 0.000019 loss: 2.7330 (2.7017) grad_norm: 3.1826 (3.3642) time: 0.5051 [2021-03-27 07:23:06 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 870/1251] eta: 0:03:14 lr: 0.000019 loss: 2.8697 (2.7034) grad_norm: 3.4611 (3.3670) time: 0.5008 [2021-03-27 07:23:11 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 880/1251] eta: 0:03:09 lr: 0.000019 loss: 2.7580 (2.6999) grad_norm: 3.5022 (3.3690) time: 0.5044 [2021-03-27 07:23:16 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 890/1251] eta: 0:03:03 lr: 0.000019 loss: 2.6942 (2.7005) grad_norm: 3.2156 (3.3673) time: 0.5018 [2021-03-27 07:23:21 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 900/1251] eta: 0:02:58 lr: 0.000019 loss: 2.6944 (2.6994) grad_norm: 3.0174 (3.3647) time: 0.5020 [2021-03-27 07:23:26 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 910/1251] eta: 0:02:53 lr: 0.000019 loss: 2.7214 (2.7008) grad_norm: 3.1975 (3.3638) time: 0.5025 [2021-03-27 07:23:31 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 920/1251] eta: 0:02:48 lr: 0.000019 loss: 2.7375 (2.6979) grad_norm: 3.1889 (3.3659) time: 0.5110 [2021-03-27 07:23:36 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 930/1251] eta: 0:02:43 lr: 0.000019 loss: 2.6382 (2.6985) grad_norm: 3.2634 (3.3655) time: 0.5077 [2021-03-27 07:23:41 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 940/1251] eta: 0:02:38 lr: 0.000019 loss: 2.7204 (2.6991) grad_norm: 3.4179 (3.3668) time: 0.4967 [2021-03-27 07:23:46 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 950/1251] eta: 0:02:33 lr: 0.000019 loss: 2.7711 (2.7005) grad_norm: 2.9337 (3.3639) time: 0.4985 [2021-03-27 07:23:51 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 960/1251] eta: 0:02:28 lr: 0.000019 loss: 2.7711 (2.6998) grad_norm: 2.9176 (3.3636) time: 0.4971 [2021-03-27 07:23:56 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 970/1251] eta: 0:02:23 lr: 0.000019 loss: 2.9978 (2.7015) grad_norm: 3.1217 (3.3616) time: 0.5017 [2021-03-27 07:24:01 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 980/1251] eta: 0:02:17 lr: 0.000019 loss: 3.0143 (2.7037) grad_norm: 3.1390 (3.3596) time: 0.5057 [2021-03-27 07:24:06 swin_small_patch4_window7_224] INFO: Epoch: [281] [ 990/1251] eta: 0:02:12 lr: 0.000019 loss: 2.8328 (2.7036) grad_norm: 3.1817 (3.3593) time: 0.5081 [2021-03-27 07:24:11 swin_small_patch4_window7_224] INFO: Epoch: [281] [1000/1251] eta: 0:02:07 lr: 0.000019 loss: 2.5701 (2.7030) grad_norm: 3.2991 (3.3633) time: 0.5076 [2021-03-27 07:24:17 swin_small_patch4_window7_224] INFO: Epoch: [281] [1010/1251] eta: 0:02:02 lr: 0.000019 loss: 2.6267 (2.7016) grad_norm: 3.2770 (3.3645) time: 0.5074 [2021-03-27 07:24:21 swin_small_patch4_window7_224] INFO: Epoch: [281] [1020/1251] eta: 0:01:57 lr: 0.000019 loss: 2.7423 (2.7024) grad_norm: 3.3333 (3.3658) time: 0.5046 [2021-03-27 07:24:27 swin_small_patch4_window7_224] INFO: Epoch: [281] [1030/1251] eta: 0:01:52 lr: 0.000019 loss: 2.7501 (2.7023) grad_norm: 3.3385 (3.3656) time: 0.5023 [2021-03-27 07:24:32 swin_small_patch4_window7_224] INFO: Epoch: [281] [1040/1251] eta: 0:01:47 lr: 0.000019 loss: 2.7371 (2.7017) grad_norm: 3.1524 (3.3623) time: 0.5055 [2021-03-27 07:24:37 swin_small_patch4_window7_224] INFO: Epoch: [281] [1050/1251] eta: 0:01:42 lr: 0.000019 loss: 2.5847 (2.7020) grad_norm: 3.0233 (3.3619) time: 0.5039 [2021-03-27 07:24:42 swin_small_patch4_window7_224] INFO: Epoch: [281] [1060/1251] eta: 0:01:37 lr: 0.000019 loss: 2.5356 (2.7004) grad_norm: 3.1287 (3.3602) time: 0.5014 [2021-03-27 07:24:47 swin_small_patch4_window7_224] INFO: Epoch: [281] [1070/1251] eta: 0:01:32 lr: 0.000019 loss: 2.7347 (2.7012) grad_norm: 3.1368 (3.3595) time: 0.5022 [2021-03-27 07:24:52 swin_small_patch4_window7_224] INFO: Epoch: [281] [1080/1251] eta: 0:01:26 lr: 0.000019 loss: 2.8165 (2.7026) grad_norm: 3.1987 (3.3598) time: 0.5046 [2021-03-27 07:24:57 swin_small_patch4_window7_224] INFO: Epoch: [281] [1090/1251] eta: 0:01:21 lr: 0.000019 loss: 2.9201 (2.7034) grad_norm: 3.1987 (3.3578) time: 0.5045 [2021-03-27 07:25:02 swin_small_patch4_window7_224] INFO: Epoch: [281] [1100/1251] eta: 0:01:16 lr: 0.000019 loss: 2.9201 (2.7029) grad_norm: 3.2633 (3.3582) time: 0.5055 [2021-03-27 07:25:07 swin_small_patch4_window7_224] INFO: Epoch: [281] [1110/1251] eta: 0:01:11 lr: 0.000019 loss: 2.9450 (2.7047) grad_norm: 3.2768 (3.3585) time: 0.5043 [2021-03-27 07:25:12 swin_small_patch4_window7_224] INFO: Epoch: [281] [1120/1251] eta: 0:01:06 lr: 0.000019 loss: 2.7501 (2.7050) grad_norm: 3.2389 (3.3568) time: 0.5063 [2021-03-27 07:25:17 swin_small_patch4_window7_224] INFO: Epoch: [281] [1130/1251] eta: 0:01:01 lr: 0.000019 loss: 2.7501 (2.7062) grad_norm: 3.2660 (3.3582) time: 0.5041 [2021-03-27 07:25:22 swin_small_patch4_window7_224] INFO: Epoch: [281] [1140/1251] eta: 0:00:56 lr: 0.000019 loss: 2.6220 (2.7031) grad_norm: 3.1783 (3.3567) time: 0.5023 [2021-03-27 07:25:27 swin_small_patch4_window7_224] INFO: Epoch: [281] [1150/1251] eta: 0:00:51 lr: 0.000019 loss: 2.6148 (2.7034) grad_norm: 2.9693 (3.3541) time: 0.4993 [2021-03-27 07:25:32 swin_small_patch4_window7_224] INFO: Epoch: [281] [1160/1251] eta: 0:00:46 lr: 0.000019 loss: 2.6651 (2.7008) grad_norm: 2.8890 (3.3514) time: 0.5032 [2021-03-27 07:25:37 swin_small_patch4_window7_224] INFO: Epoch: [281] [1170/1251] eta: 0:00:41 lr: 0.000019 loss: 2.7813 (2.7031) grad_norm: 3.0096 (3.3544) time: 0.5100 [2021-03-27 07:25:42 swin_small_patch4_window7_224] INFO: Epoch: [281] [1180/1251] eta: 0:00:36 lr: 0.000019 loss: 2.8293 (2.7028) grad_norm: 3.0593 (3.3517) time: 0.5116 [2021-03-27 07:25:47 swin_small_patch4_window7_224] INFO: Epoch: [281] [1190/1251] eta: 0:00:31 lr: 0.000019 loss: 2.6986 (2.7035) grad_norm: 3.0593 (3.3517) time: 0.5107 [2021-03-27 07:25:52 swin_small_patch4_window7_224] INFO: Epoch: [281] [1200/1251] eta: 0:00:25 lr: 0.000019 loss: 2.6162 (2.7030) grad_norm: 3.1754 (3.3512) time: 0.5025 [2021-03-27 07:25:57 swin_small_patch4_window7_224] INFO: Epoch: [281] [1210/1251] eta: 0:00:20 lr: 0.000019 loss: 2.5603 (2.7023) grad_norm: 3.3141 (3.3549) time: 0.5017 [2021-03-27 07:26:02 swin_small_patch4_window7_224] INFO: Epoch: [281] [1220/1251] eta: 0:00:15 lr: 0.000019 loss: 2.5569 (2.7016) grad_norm: 3.3370 (3.3553) time: 0.5014 [2021-03-27 07:26:07 swin_small_patch4_window7_224] INFO: Epoch: [281] [1230/1251] eta: 0:00:10 lr: 0.000019 loss: 2.5569 (2.7019) grad_norm: 3.2362 (3.3546) time: 0.4996 [2021-03-27 07:26:12 swin_small_patch4_window7_224] INFO: Epoch: [281] [1240/1251] eta: 0:00:05 lr: 0.000019 loss: 2.7611 (2.7033) grad_norm: 3.3351 (3.3565) time: 0.5019 [2021-03-27 07:26:17 swin_small_patch4_window7_224] INFO: Epoch: [281] [1250/1251] eta: 0:00:00 lr: 0.000019 loss: 2.9318 (2.7045) grad_norm: 3.3351 (3.3572) time: 0.5015 [2021-03-27 07:26:31 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:07 loss: 0.7924 (0.7924) acc1: 81.2500 (81.2500) acc5: 95.3125 (95.3125) [2021-03-27 07:26:33 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7924 (0.7659) acc1: 81.2500 (81.1080) acc5: 95.3125 (96.0227) [2021-03-27 07:26:35 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7579 (0.7514) acc1: 82.8125 (82.2917) acc5: 95.3125 (96.0565) [2021-03-27 07:26:37 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6816 (0.7328) acc1: 82.8125 (82.4093) acc5: 96.8750 (96.2198) [2021-03-27 07:26:40 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7242 (0.7608) acc1: 82.8125 (81.8979) acc5: 96.8750 (95.9985) [2021-03-27 07:26:40 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6979 (0.7520) acc1: 82.8125 (82.2080) acc5: 96.8750 (96.0320) [2021-03-27 07:27:00 swin_small_patch4_window7_224] INFO: * Acc@1 82.976 Acc@5 96.258 loss 0.738 [2021-03-27 07:27:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 07:27:00 swin_small_patch4_window7_224] INFO: Max accuracy: 82.99% [2021-03-27 07:27:05 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 0/1251] eta: 1:34:57 lr: 0.000019 loss: 2.8985 (2.8985) grad_norm: 3.2120 (3.2120) time: 4.5546 [2021-03-27 07:27:10 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 10/1251] eta: 0:17:57 lr: 0.000019 loss: 2.8985 (2.7879) grad_norm: 3.2120 (3.2583) time: 0.8681 [2021-03-27 07:27:15 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 20/1251] eta: 0:14:17 lr: 0.000019 loss: 2.8973 (2.7065) grad_norm: 3.2608 (3.2946) time: 0.5037 [2021-03-27 07:27:20 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 30/1251] eta: 0:12:58 lr: 0.000019 loss: 2.7779 (2.7568) grad_norm: 3.2998 (3.3013) time: 0.5108 [2021-03-27 07:27:25 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 40/1251] eta: 0:12:13 lr: 0.000019 loss: 2.7359 (2.6861) grad_norm: 3.2046 (3.3209) time: 0.5107 [2021-03-27 07:27:30 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 50/1251] eta: 0:11:42 lr: 0.000019 loss: 2.5327 (2.6373) grad_norm: 3.1714 (3.2758) time: 0.5043 [2021-03-27 07:27:35 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 60/1251] eta: 0:11:19 lr: 0.000019 loss: 2.6031 (2.6554) grad_norm: 3.0943 (3.2716) time: 0.4983 [2021-03-27 07:27:40 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 70/1251] eta: 0:11:01 lr: 0.000019 loss: 2.7942 (2.6594) grad_norm: 3.2852 (3.2876) time: 0.4959 [2021-03-27 07:27:45 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 80/1251] eta: 0:10:48 lr: 0.000019 loss: 2.7449 (2.6419) grad_norm: 3.3924 (3.2998) time: 0.5039 [2021-03-27 07:27:51 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 90/1251] eta: 0:10:38 lr: 0.000019 loss: 2.6844 (2.6474) grad_norm: 3.0857 (3.2644) time: 0.5138 [2021-03-27 07:27:56 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 100/1251] eta: 0:10:27 lr: 0.000019 loss: 2.5769 (2.6425) grad_norm: 3.1299 (3.2694) time: 0.5101 [2021-03-27 07:28:01 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 110/1251] eta: 0:10:18 lr: 0.000019 loss: 2.8422 (2.6621) grad_norm: 3.2494 (3.2726) time: 0.5074 [2021-03-27 07:28:06 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 120/1251] eta: 0:10:08 lr: 0.000019 loss: 2.8959 (2.6679) grad_norm: 3.1751 (3.2663) time: 0.5020 [2021-03-27 07:28:11 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 130/1251] eta: 0:10:01 lr: 0.000019 loss: 2.9500 (2.6692) grad_norm: 3.0935 (3.2534) time: 0.5035 [2021-03-27 07:28:16 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 140/1251] eta: 0:09:53 lr: 0.000019 loss: 2.7001 (2.6744) grad_norm: 3.0521 (3.2473) time: 0.5069 [2021-03-27 07:28:21 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 150/1251] eta: 0:09:44 lr: 0.000019 loss: 2.6873 (2.6766) grad_norm: 3.0753 (3.2926) time: 0.4969 [2021-03-27 07:28:26 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 160/1251] eta: 0:09:37 lr: 0.000019 loss: 2.6526 (2.6759) grad_norm: 3.2228 (3.2853) time: 0.4982 [2021-03-27 07:28:31 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 170/1251] eta: 0:09:30 lr: 0.000019 loss: 2.4778 (2.6680) grad_norm: 3.1735 (3.2960) time: 0.5026 [2021-03-27 07:28:36 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 180/1251] eta: 0:09:24 lr: 0.000019 loss: 2.7780 (2.6696) grad_norm: 3.2013 (3.3057) time: 0.5087 [2021-03-27 07:28:41 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 190/1251] eta: 0:09:18 lr: 0.000019 loss: 2.7024 (2.6663) grad_norm: 3.0525 (3.2866) time: 0.5108 [2021-03-27 07:28:46 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 200/1251] eta: 0:09:12 lr: 0.000019 loss: 2.6708 (2.6655) grad_norm: 3.0525 (3.2961) time: 0.5128 [2021-03-27 07:28:51 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 210/1251] eta: 0:09:06 lr: 0.000019 loss: 2.6708 (2.6715) grad_norm: 3.1391 (3.2892) time: 0.5136 [2021-03-27 07:28:56 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 220/1251] eta: 0:09:00 lr: 0.000019 loss: 2.8858 (2.6810) grad_norm: 2.9433 (3.2739) time: 0.5106 [2021-03-27 07:29:01 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 230/1251] eta: 0:08:54 lr: 0.000019 loss: 2.7559 (2.6737) grad_norm: 3.0402 (3.2958) time: 0.5134 [2021-03-27 07:29:07 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 240/1251] eta: 0:08:48 lr: 0.000019 loss: 2.5255 (2.6668) grad_norm: 3.0207 (3.2796) time: 0.5080 [2021-03-27 07:29:12 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 250/1251] eta: 0:08:42 lr: 0.000019 loss: 2.7163 (2.6725) grad_norm: 2.9796 (3.2740) time: 0.5032 [2021-03-27 07:29:16 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 260/1251] eta: 0:08:36 lr: 0.000019 loss: 2.7291 (2.6720) grad_norm: 3.0477 (nan) time: 0.4977 [2021-03-27 07:29:21 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 270/1251] eta: 0:08:30 lr: 0.000019 loss: 2.7365 (2.6701) grad_norm: 3.0398 (nan) time: 0.4952 [2021-03-27 07:29:27 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 280/1251] eta: 0:08:24 lr: 0.000019 loss: 2.7656 (2.6618) grad_norm: 3.0398 (nan) time: 0.5032 [2021-03-27 07:29:32 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 290/1251] eta: 0:08:19 lr: 0.000019 loss: 2.7398 (2.6637) grad_norm: 2.9879 (nan) time: 0.5088 [2021-03-27 07:29:37 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 300/1251] eta: 0:08:13 lr: 0.000019 loss: 2.8783 (2.6750) grad_norm: 2.9879 (nan) time: 0.5104 [2021-03-27 07:29:42 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 310/1251] eta: 0:08:08 lr: 0.000019 loss: 2.8783 (2.6755) grad_norm: 3.0860 (nan) time: 0.5076 [2021-03-27 07:29:47 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 320/1251] eta: 0:08:02 lr: 0.000019 loss: 2.7876 (2.6793) grad_norm: 3.0860 (nan) time: 0.5010 [2021-03-27 07:29:52 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 330/1251] eta: 0:07:56 lr: 0.000019 loss: 2.9416 (2.6901) grad_norm: 3.0456 (nan) time: 0.5016 [2021-03-27 07:29:57 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 340/1251] eta: 0:07:51 lr: 0.000019 loss: 2.8829 (2.6903) grad_norm: 3.1609 (nan) time: 0.5038 [2021-03-27 07:30:02 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 350/1251] eta: 0:07:45 lr: 0.000018 loss: 2.7210 (2.6936) grad_norm: 3.2791 (nan) time: 0.4993 [2021-03-27 07:30:07 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 360/1251] eta: 0:07:39 lr: 0.000018 loss: 2.7210 (2.6925) grad_norm: 3.3137 (nan) time: 0.4982 [2021-03-27 07:30:12 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 370/1251] eta: 0:07:34 lr: 0.000018 loss: 2.6720 (2.6872) grad_norm: 3.2813 (nan) time: 0.4968 [2021-03-27 07:30:17 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 380/1251] eta: 0:07:28 lr: 0.000018 loss: 2.7044 (2.6900) grad_norm: 3.3213 (nan) time: 0.4965 [2021-03-27 07:30:22 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 390/1251] eta: 0:07:23 lr: 0.000018 loss: 2.7030 (2.6853) grad_norm: 3.1376 (nan) time: 0.5048 [2021-03-27 07:30:27 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 400/1251] eta: 0:07:18 lr: 0.000018 loss: 2.7030 (2.6882) grad_norm: 3.1376 (nan) time: 0.5108 [2021-03-27 07:30:32 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 410/1251] eta: 0:07:12 lr: 0.000018 loss: 2.7239 (2.6891) grad_norm: 3.1789 (nan) time: 0.5028 [2021-03-27 07:30:37 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 420/1251] eta: 0:07:07 lr: 0.000018 loss: 2.8131 (2.6924) grad_norm: 3.2263 (nan) time: 0.5017 [2021-03-27 07:30:42 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 430/1251] eta: 0:07:01 lr: 0.000018 loss: 2.8298 (2.6905) grad_norm: 3.1510 (nan) time: 0.5037 [2021-03-27 07:30:47 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 440/1251] eta: 0:06:56 lr: 0.000018 loss: 2.4237 (2.6828) grad_norm: 3.0411 (nan) time: 0.4979 [2021-03-27 07:30:52 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 450/1251] eta: 0:06:51 lr: 0.000018 loss: 2.4501 (2.6813) grad_norm: 3.0671 (nan) time: 0.4984 [2021-03-27 07:30:57 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 460/1251] eta: 0:06:45 lr: 0.000018 loss: 2.7740 (2.6828) grad_norm: 3.0396 (nan) time: 0.4979 [2021-03-27 07:31:02 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 470/1251] eta: 0:06:40 lr: 0.000018 loss: 2.6656 (2.6770) grad_norm: 3.2318 (nan) time: 0.4994 [2021-03-27 07:31:07 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 480/1251] eta: 0:06:35 lr: 0.000018 loss: 2.6722 (2.6806) grad_norm: 3.2674 (nan) time: 0.5006 [2021-03-27 07:31:12 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 490/1251] eta: 0:06:29 lr: 0.000018 loss: 2.9136 (2.6855) grad_norm: 3.2477 (nan) time: 0.4978 [2021-03-27 07:31:17 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 500/1251] eta: 0:06:24 lr: 0.000018 loss: 2.9136 (2.6904) grad_norm: 3.2052 (nan) time: 0.5004 [2021-03-27 07:31:22 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 510/1251] eta: 0:06:19 lr: 0.000018 loss: 2.7982 (2.6911) grad_norm: 3.1112 (nan) time: 0.5010 [2021-03-27 07:31:27 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 520/1251] eta: 0:06:13 lr: 0.000018 loss: 2.6009 (2.6875) grad_norm: 3.1494 (nan) time: 0.5032 [2021-03-27 07:31:32 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 530/1251] eta: 0:06:08 lr: 0.000018 loss: 2.6473 (2.6890) grad_norm: 3.1988 (nan) time: 0.5040 [2021-03-27 07:31:37 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 540/1251] eta: 0:06:03 lr: 0.000018 loss: 2.8532 (2.6914) grad_norm: 3.3160 (nan) time: 0.5083 [2021-03-27 07:31:42 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 550/1251] eta: 0:05:58 lr: 0.000018 loss: 2.8055 (2.6871) grad_norm: 3.3544 (nan) time: 0.5199 [2021-03-27 07:31:47 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 560/1251] eta: 0:05:53 lr: 0.000018 loss: 2.8055 (2.6888) grad_norm: 3.2191 (nan) time: 0.5105 [2021-03-27 07:31:52 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 570/1251] eta: 0:05:48 lr: 0.000018 loss: 2.9064 (2.6933) grad_norm: 3.1409 (nan) time: 0.5017 [2021-03-27 07:31:58 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 580/1251] eta: 0:05:42 lr: 0.000018 loss: 2.7510 (2.6908) grad_norm: 3.0929 (nan) time: 0.5052 [2021-03-27 07:32:03 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 590/1251] eta: 0:05:37 lr: 0.000018 loss: 2.6708 (2.6914) grad_norm: 3.1599 (nan) time: 0.5073 [2021-03-27 07:32:08 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 600/1251] eta: 0:05:32 lr: 0.000018 loss: 2.6764 (2.6914) grad_norm: 3.1615 (nan) time: 0.5051 [2021-03-27 07:32:13 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 610/1251] eta: 0:05:27 lr: 0.000018 loss: 2.8497 (2.6922) grad_norm: 3.1615 (nan) time: 0.4994 [2021-03-27 07:32:18 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 620/1251] eta: 0:05:22 lr: 0.000018 loss: 2.6191 (2.6857) grad_norm: 3.1354 (nan) time: 0.4973 [2021-03-27 07:32:23 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 630/1251] eta: 0:05:17 lr: 0.000018 loss: 2.5019 (2.6832) grad_norm: 3.1516 (nan) time: 0.5026 [2021-03-27 07:32:28 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 640/1251] eta: 0:05:11 lr: 0.000018 loss: 2.7167 (2.6848) grad_norm: 3.1516 (nan) time: 0.5093 [2021-03-27 07:32:33 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 650/1251] eta: 0:05:06 lr: 0.000018 loss: 2.7724 (2.6850) grad_norm: 3.1749 (nan) time: 0.5064 [2021-03-27 07:32:38 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 660/1251] eta: 0:05:01 lr: 0.000018 loss: 2.7815 (2.6848) grad_norm: 3.0348 (nan) time: 0.5050 [2021-03-27 07:32:43 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 670/1251] eta: 0:04:56 lr: 0.000018 loss: 2.8198 (2.6864) grad_norm: 3.0194 (nan) time: 0.5037 [2021-03-27 07:32:48 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 680/1251] eta: 0:04:51 lr: 0.000018 loss: 2.8145 (2.6855) grad_norm: 3.1313 (nan) time: 0.5019 [2021-03-27 07:32:53 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 690/1251] eta: 0:04:46 lr: 0.000018 loss: 2.7617 (2.6876) grad_norm: 3.1993 (nan) time: 0.5024 [2021-03-27 07:32:58 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 700/1251] eta: 0:04:40 lr: 0.000018 loss: 2.8371 (2.6885) grad_norm: 3.6108 (nan) time: 0.5053 [2021-03-27 07:33:03 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 710/1251] eta: 0:04:35 lr: 0.000018 loss: 2.7938 (2.6881) grad_norm: 3.4686 (nan) time: 0.5074 [2021-03-27 07:33:08 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 720/1251] eta: 0:04:30 lr: 0.000018 loss: 2.8243 (2.6901) grad_norm: 3.2140 (nan) time: 0.5019 [2021-03-27 07:33:13 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 730/1251] eta: 0:04:25 lr: 0.000018 loss: 2.8892 (2.6907) grad_norm: 3.1811 (nan) time: 0.5023 [2021-03-27 07:33:18 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 740/1251] eta: 0:04:20 lr: 0.000018 loss: 2.7808 (2.6890) grad_norm: 3.1811 (nan) time: 0.5220 [2021-03-27 07:33:24 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 750/1251] eta: 0:04:15 lr: 0.000018 loss: 2.9277 (2.6917) grad_norm: 3.1871 (nan) time: 0.5306 [2021-03-27 07:33:29 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 760/1251] eta: 0:04:10 lr: 0.000018 loss: 2.8007 (2.6901) grad_norm: 3.1268 (nan) time: 0.5190 [2021-03-27 07:33:34 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 770/1251] eta: 0:04:05 lr: 0.000018 loss: 2.8007 (2.6918) grad_norm: 3.1268 (nan) time: 0.5142 [2021-03-27 07:33:39 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 780/1251] eta: 0:04:00 lr: 0.000018 loss: 2.8603 (2.6909) grad_norm: 3.0246 (nan) time: 0.5162 [2021-03-27 07:33:44 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 790/1251] eta: 0:03:55 lr: 0.000018 loss: 2.7811 (2.6914) grad_norm: 2.9601 (nan) time: 0.5115 [2021-03-27 07:33:49 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 800/1251] eta: 0:03:50 lr: 0.000018 loss: 2.7558 (2.6906) grad_norm: 3.2810 (nan) time: 0.5019 [2021-03-27 07:33:54 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 810/1251] eta: 0:03:44 lr: 0.000018 loss: 2.7045 (2.6904) grad_norm: 3.1830 (nan) time: 0.5008 [2021-03-27 07:33:59 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 820/1251] eta: 0:03:39 lr: 0.000018 loss: 2.7673 (2.6919) grad_norm: 3.1373 (nan) time: 0.5027 [2021-03-27 07:34:04 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 830/1251] eta: 0:03:34 lr: 0.000018 loss: 2.8416 (2.6929) grad_norm: 3.3365 (nan) time: 0.5068 [2021-03-27 07:34:10 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 840/1251] eta: 0:03:29 lr: 0.000018 loss: 2.8189 (2.6933) grad_norm: 3.3346 (nan) time: 0.5103 [2021-03-27 07:34:15 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 850/1251] eta: 0:03:24 lr: 0.000018 loss: 2.8515 (2.6954) grad_norm: 3.0379 (nan) time: 0.5061 [2021-03-27 07:34:20 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 860/1251] eta: 0:03:19 lr: 0.000018 loss: 2.7431 (2.6940) grad_norm: 3.0761 (nan) time: 0.5046 [2021-03-27 07:34:25 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 870/1251] eta: 0:03:14 lr: 0.000018 loss: 2.6417 (2.6940) grad_norm: 3.0761 (nan) time: 0.5031 [2021-03-27 07:34:30 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 880/1251] eta: 0:03:09 lr: 0.000018 loss: 2.8378 (2.6942) grad_norm: 3.1073 (nan) time: 0.5062 [2021-03-27 07:34:35 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 890/1251] eta: 0:03:04 lr: 0.000018 loss: 2.8378 (2.6954) grad_norm: 3.1503 (nan) time: 0.5066 [2021-03-27 07:34:40 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 900/1251] eta: 0:02:58 lr: 0.000018 loss: 2.8580 (2.6976) grad_norm: 3.2816 (nan) time: 0.4995 [2021-03-27 07:34:45 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 910/1251] eta: 0:02:53 lr: 0.000018 loss: 2.8580 (2.6990) grad_norm: 3.2442 (nan) time: 0.4977 [2021-03-27 07:34:50 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 920/1251] eta: 0:02:48 lr: 0.000018 loss: 2.8351 (2.6982) grad_norm: 3.2208 (nan) time: 0.4959 [2021-03-27 07:34:55 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 930/1251] eta: 0:02:43 lr: 0.000018 loss: 2.6004 (2.6982) grad_norm: 3.1974 (nan) time: 0.5030 [2021-03-27 07:35:00 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 940/1251] eta: 0:02:38 lr: 0.000018 loss: 2.9244 (2.6976) grad_norm: 3.2086 (nan) time: 0.5092 [2021-03-27 07:35:05 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 950/1251] eta: 0:02:33 lr: 0.000018 loss: 2.7323 (2.6986) grad_norm: 3.3136 (nan) time: 0.5094 [2021-03-27 07:35:10 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 960/1251] eta: 0:02:28 lr: 0.000018 loss: 2.7569 (2.7000) grad_norm: 3.3642 (nan) time: 0.5066 [2021-03-27 07:35:15 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 970/1251] eta: 0:02:23 lr: 0.000018 loss: 2.7365 (2.6984) grad_norm: 3.2216 (nan) time: 0.5079 [2021-03-27 07:35:20 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 980/1251] eta: 0:02:17 lr: 0.000018 loss: 2.5808 (2.6978) grad_norm: 3.0705 (nan) time: 0.5065 [2021-03-27 07:35:25 swin_small_patch4_window7_224] INFO: Epoch: [282] [ 990/1251] eta: 0:02:12 lr: 0.000018 loss: 2.7861 (2.6978) grad_norm: 3.1810 (nan) time: 0.5018 [2021-03-27 07:35:30 swin_small_patch4_window7_224] INFO: Epoch: [282] [1000/1251] eta: 0:02:07 lr: 0.000018 loss: 2.8057 (2.6987) grad_norm: 3.3765 (nan) time: 0.5010 [2021-03-27 07:35:35 swin_small_patch4_window7_224] INFO: Epoch: [282] [1010/1251] eta: 0:02:02 lr: 0.000018 loss: 2.7409 (2.6983) grad_norm: 3.4436 (nan) time: 0.4973 [2021-03-27 07:35:40 swin_small_patch4_window7_224] INFO: Epoch: [282] [1020/1251] eta: 0:01:57 lr: 0.000018 loss: 2.5679 (2.6980) grad_norm: 3.2472 (nan) time: 0.5003 [2021-03-27 07:35:45 swin_small_patch4_window7_224] INFO: Epoch: [282] [1030/1251] eta: 0:01:52 lr: 0.000018 loss: 2.6740 (2.6977) grad_norm: 3.2244 (nan) time: 0.4997 [2021-03-27 07:35:50 swin_small_patch4_window7_224] INFO: Epoch: [282] [1040/1251] eta: 0:01:47 lr: 0.000018 loss: 2.7449 (2.6977) grad_norm: 3.2244 (nan) time: 0.4946 [2021-03-27 07:35:55 swin_small_patch4_window7_224] INFO: Epoch: [282] [1050/1251] eta: 0:01:42 lr: 0.000018 loss: 2.8438 (2.6982) grad_norm: 3.1452 (nan) time: 0.5031 [2021-03-27 07:36:00 swin_small_patch4_window7_224] INFO: Epoch: [282] [1060/1251] eta: 0:01:37 lr: 0.000018 loss: 2.8133 (2.6982) grad_norm: 3.1452 (nan) time: 0.5061 [2021-03-27 07:36:05 swin_small_patch4_window7_224] INFO: Epoch: [282] [1070/1251] eta: 0:01:32 lr: 0.000018 loss: 2.8133 (2.6971) grad_norm: 3.2760 (nan) time: 0.4982 [2021-03-27 07:36:10 swin_small_patch4_window7_224] INFO: Epoch: [282] [1080/1251] eta: 0:01:26 lr: 0.000018 loss: 2.9449 (2.6992) grad_norm: 3.1067 (nan) time: 0.5002 [2021-03-27 07:36:15 swin_small_patch4_window7_224] INFO: Epoch: [282] [1090/1251] eta: 0:01:21 lr: 0.000018 loss: 2.7782 (2.6981) grad_norm: 3.0187 (nan) time: 0.5044 [2021-03-27 07:36:20 swin_small_patch4_window7_224] INFO: Epoch: [282] [1100/1251] eta: 0:01:16 lr: 0.000018 loss: 2.6127 (2.6975) grad_norm: 3.3017 (nan) time: 0.5075 [2021-03-27 07:36:25 swin_small_patch4_window7_224] INFO: Epoch: [282] [1110/1251] eta: 0:01:11 lr: 0.000018 loss: 2.6396 (2.6973) grad_norm: 3.1274 (nan) time: 0.5055 [2021-03-27 07:36:30 swin_small_patch4_window7_224] INFO: Epoch: [282] [1120/1251] eta: 0:01:06 lr: 0.000018 loss: 2.6488 (2.6978) grad_norm: 3.1704 (nan) time: 0.5020 [2021-03-27 07:36:35 swin_small_patch4_window7_224] INFO: Epoch: [282] [1130/1251] eta: 0:01:01 lr: 0.000018 loss: 2.7067 (2.6986) grad_norm: 3.2668 (nan) time: 0.5049 [2021-03-27 07:36:40 swin_small_patch4_window7_224] INFO: Epoch: [282] [1140/1251] eta: 0:00:56 lr: 0.000018 loss: 2.7942 (2.6991) grad_norm: 3.2668 (nan) time: 0.5059 [2021-03-27 07:36:46 swin_small_patch4_window7_224] INFO: Epoch: [282] [1150/1251] eta: 0:00:51 lr: 0.000018 loss: 2.8439 (2.6989) grad_norm: 3.3437 (nan) time: 0.5035 [2021-03-27 07:36:51 swin_small_patch4_window7_224] INFO: Epoch: [282] [1160/1251] eta: 0:00:46 lr: 0.000018 loss: 2.8088 (2.6980) grad_norm: 3.2405 (nan) time: 0.5026 [2021-03-27 07:36:56 swin_small_patch4_window7_224] INFO: Epoch: [282] [1170/1251] eta: 0:00:41 lr: 0.000018 loss: 2.6154 (2.6969) grad_norm: 3.0136 (nan) time: 0.5041 [2021-03-27 07:37:01 swin_small_patch4_window7_224] INFO: Epoch: [282] [1180/1251] eta: 0:00:36 lr: 0.000018 loss: 2.8311 (2.6984) grad_norm: 3.3101 (nan) time: 0.5045 [2021-03-27 07:37:06 swin_small_patch4_window7_224] INFO: Epoch: [282] [1190/1251] eta: 0:00:30 lr: 0.000018 loss: 2.8684 (2.6985) grad_norm: 3.1960 (nan) time: 0.5022 [2021-03-27 07:37:11 swin_small_patch4_window7_224] INFO: Epoch: [282] [1200/1251] eta: 0:00:25 lr: 0.000018 loss: 2.7074 (2.6999) grad_norm: 3.1441 (nan) time: 0.4988 [2021-03-27 07:37:16 swin_small_patch4_window7_224] INFO: Epoch: [282] [1210/1251] eta: 0:00:20 lr: 0.000018 loss: 2.7575 (2.6985) grad_norm: 3.3198 (nan) time: 0.4985 [2021-03-27 07:37:21 swin_small_patch4_window7_224] INFO: Epoch: [282] [1220/1251] eta: 0:00:15 lr: 0.000018 loss: 2.5472 (2.6979) grad_norm: 3.3198 (nan) time: 0.4993 [2021-03-27 07:37:26 swin_small_patch4_window7_224] INFO: Epoch: [282] [1230/1251] eta: 0:00:10 lr: 0.000018 loss: 2.4553 (2.6962) grad_norm: 3.1635 (nan) time: 0.5005 [2021-03-27 07:37:31 swin_small_patch4_window7_224] INFO: Epoch: [282] [1240/1251] eta: 0:00:05 lr: 0.000018 loss: 2.7197 (2.6968) grad_norm: 3.0262 (nan) time: 0.4989 [2021-03-27 07:37:36 swin_small_patch4_window7_224] INFO: Epoch: [282] [1250/1251] eta: 0:00:00 lr: 0.000018 loss: 2.8885 (2.6981) grad_norm: 3.3066 (nan) time: 0.4935 [2021-03-27 07:37:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:30 loss: 0.7652 (0.7652) acc1: 85.9375 (85.9375) acc5: 96.8750 (96.8750) [2021-03-27 07:37:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8301 (0.8463) acc1: 79.6875 (79.6875) acc5: 96.8750 (95.4545) [2021-03-27 07:37:49 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7468 (0.7889) acc1: 81.2500 (81.6964) acc5: 95.3125 (95.6101) [2021-03-27 07:37:52 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.6963 (0.7778) acc1: 82.8125 (81.6532) acc5: 95.3125 (95.9173) [2021-03-27 07:37:54 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7268 (0.7622) acc1: 82.8125 (81.8598) acc5: 96.8750 (96.0366) [2021-03-27 07:37:55 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6654 (0.7525) acc1: 82.8125 (82.1120) acc5: 96.8750 (96.1280) [2021-03-27 07:38:09 swin_small_patch4_window7_224] INFO: * Acc@1 82.940 Acc@5 96.274 loss 0.737 [2021-03-27 07:38:09 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 82.9% [2021-03-27 07:38:09 swin_small_patch4_window7_224] INFO: Max accuracy: 82.99% [2021-03-27 07:38:13 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 0/1251] eta: 1:27:52 lr: 0.000018 loss: 2.0551 (2.0551) grad_norm: 3.0005 (3.0005) time: 4.2150 [2021-03-27 07:38:19 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 10/1251] eta: 0:18:06 lr: 0.000018 loss: 2.7904 (2.6999) grad_norm: 3.2886 (3.2424) time: 0.8754 [2021-03-27 07:38:24 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 20/1251] eta: 0:14:23 lr: 0.000018 loss: 2.7473 (2.6562) grad_norm: 3.2463 (3.3829) time: 0.5256 [2021-03-27 07:38:29 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 30/1251] eta: 0:13:03 lr: 0.000018 loss: 2.6601 (2.6820) grad_norm: 3.1418 (3.3127) time: 0.5136 [2021-03-27 07:38:34 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 40/1251] eta: 0:12:18 lr: 0.000018 loss: 2.6601 (2.6578) grad_norm: 3.0915 (3.3953) time: 0.5133 [2021-03-27 07:38:39 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 50/1251] eta: 0:11:49 lr: 0.000018 loss: 2.6495 (2.6548) grad_norm: 3.2539 (3.4042) time: 0.5115 [2021-03-27 07:38:44 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 60/1251] eta: 0:11:27 lr: 0.000018 loss: 2.7007 (2.6785) grad_norm: 3.0636 (3.3484) time: 0.5110 [2021-03-27 07:38:49 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 70/1251] eta: 0:11:09 lr: 0.000018 loss: 2.8519 (2.6849) grad_norm: 3.0718 (3.3393) time: 0.5067 [2021-03-27 07:38:54 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 80/1251] eta: 0:10:54 lr: 0.000018 loss: 2.9461 (2.6978) grad_norm: 3.0527 (3.3963) time: 0.5022 [2021-03-27 07:38:59 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 90/1251] eta: 0:10:41 lr: 0.000018 loss: 2.6737 (2.6873) grad_norm: 3.0430 (3.4654) time: 0.5008 [2021-03-27 07:39:04 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 100/1251] eta: 0:10:30 lr: 0.000018 loss: 2.6602 (2.6780) grad_norm: 3.1129 (3.4372) time: 0.5034 [2021-03-27 07:39:09 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 110/1251] eta: 0:10:21 lr: 0.000018 loss: 2.8433 (2.6811) grad_norm: 3.1129 (3.4222) time: 0.5114 [2021-03-27 07:39:15 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 120/1251] eta: 0:10:12 lr: 0.000018 loss: 2.5933 (2.6658) grad_norm: 3.1374 (3.4078) time: 0.5121 [2021-03-27 07:39:20 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 130/1251] eta: 0:10:04 lr: 0.000018 loss: 2.5292 (2.6454) grad_norm: 3.1696 (3.3913) time: 0.5046 [2021-03-27 07:39:25 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 140/1251] eta: 0:09:56 lr: 0.000018 loss: 2.6185 (2.6428) grad_norm: 3.2454 (3.3914) time: 0.5051 [2021-03-27 07:39:30 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 150/1251] eta: 0:09:49 lr: 0.000018 loss: 2.7491 (2.6484) grad_norm: 3.3635 (3.3901) time: 0.5099 [2021-03-27 07:39:35 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 160/1251] eta: 0:09:41 lr: 0.000018 loss: 2.7491 (2.6450) grad_norm: 3.1371 (3.3719) time: 0.5040 [2021-03-27 07:39:40 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 170/1251] eta: 0:09:35 lr: 0.000018 loss: 2.7351 (2.6507) grad_norm: 3.0313 (3.3619) time: 0.5083 [2021-03-27 07:39:45 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 180/1251] eta: 0:09:28 lr: 0.000018 loss: 2.8601 (2.6621) grad_norm: 2.9353 (3.3404) time: 0.5128 [2021-03-27 07:39:50 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 190/1251] eta: 0:09:21 lr: 0.000018 loss: 2.8879 (2.6731) grad_norm: 3.1597 (3.3447) time: 0.5016 [2021-03-27 07:39:55 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 200/1251] eta: 0:09:15 lr: 0.000018 loss: 2.8551 (2.6809) grad_norm: 3.1902 (3.3445) time: 0.5090 [2021-03-27 07:40:00 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 210/1251] eta: 0:09:08 lr: 0.000018 loss: 2.7629 (2.6784) grad_norm: 3.1174 (3.3399) time: 0.5119 [2021-03-27 07:40:05 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 220/1251] eta: 0:09:02 lr: 0.000018 loss: 2.5806 (2.6759) grad_norm: 3.1660 (3.3343) time: 0.5039 [2021-03-27 07:40:10 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 230/1251] eta: 0:08:56 lr: 0.000018 loss: 2.6597 (2.6816) grad_norm: 3.2129 (3.3324) time: 0.5056 [2021-03-27 07:40:15 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 240/1251] eta: 0:08:50 lr: 0.000018 loss: 2.8360 (2.6858) grad_norm: 3.2154 (3.3277) time: 0.5054 [2021-03-27 07:40:20 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 250/1251] eta: 0:08:44 lr: 0.000018 loss: 2.8425 (2.6819) grad_norm: 3.2154 (3.3232) time: 0.5040 [2021-03-27 07:40:25 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 260/1251] eta: 0:08:37 lr: 0.000018 loss: 2.7329 (2.6802) grad_norm: 3.2876 (3.3378) time: 0.5014 [2021-03-27 07:40:30 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 270/1251] eta: 0:08:31 lr: 0.000018 loss: 2.8598 (2.6875) grad_norm: 3.2642 (3.3330) time: 0.5003 [2021-03-27 07:40:35 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 280/1251] eta: 0:08:25 lr: 0.000018 loss: 2.8094 (2.6866) grad_norm: 3.1852 (3.3300) time: 0.4991 [2021-03-27 07:40:40 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 290/1251] eta: 0:08:20 lr: 0.000018 loss: 2.6576 (2.6860) grad_norm: 3.1969 (3.3423) time: 0.5006 [2021-03-27 07:40:45 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 300/1251] eta: 0:08:14 lr: 0.000018 loss: 2.7201 (2.6913) grad_norm: 3.2597 (3.3572) time: 0.5055 [2021-03-27 07:40:51 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 310/1251] eta: 0:08:08 lr: 0.000018 loss: 2.6969 (2.6852) grad_norm: 3.2597 (3.3528) time: 0.5059 [2021-03-27 07:40:56 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 320/1251] eta: 0:08:02 lr: 0.000018 loss: 2.7577 (2.6908) grad_norm: 3.1425 (3.3504) time: 0.5023 [2021-03-27 07:41:01 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 330/1251] eta: 0:07:58 lr: 0.000018 loss: 2.7577 (2.6921) grad_norm: 3.1391 (3.3608) time: 0.5134 [2021-03-27 07:41:06 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 340/1251] eta: 0:07:52 lr: 0.000018 loss: 2.7510 (2.6981) grad_norm: 3.1805 (3.3592) time: 0.5170 [2021-03-27 07:41:11 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 350/1251] eta: 0:07:47 lr: 0.000018 loss: 2.6411 (2.6910) grad_norm: 3.2740 (3.3598) time: 0.5101 [2021-03-27 07:41:16 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 360/1251] eta: 0:07:41 lr: 0.000018 loss: 2.5958 (2.6934) grad_norm: 3.0853 (3.3590) time: 0.5120 [2021-03-27 07:41:21 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 370/1251] eta: 0:07:36 lr: 0.000018 loss: 2.8057 (2.6957) grad_norm: 3.1202 (3.3565) time: 0.5073 [2021-03-27 07:41:26 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 380/1251] eta: 0:07:30 lr: 0.000018 loss: 2.6448 (2.6886) grad_norm: 3.3606 (3.3647) time: 0.5028 [2021-03-27 07:41:31 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 390/1251] eta: 0:07:25 lr: 0.000018 loss: 2.6430 (2.6884) grad_norm: 3.3807 (3.3657) time: 0.4975 [2021-03-27 07:41:36 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 400/1251] eta: 0:07:19 lr: 0.000018 loss: 2.8399 (2.6909) grad_norm: 3.2944 (3.3713) time: 0.4984 [2021-03-27 07:41:41 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 410/1251] eta: 0:07:14 lr: 0.000018 loss: 2.8624 (2.6891) grad_norm: 3.3530 (3.3776) time: 0.5031 [2021-03-27 07:41:46 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 420/1251] eta: 0:07:08 lr: 0.000018 loss: 2.6702 (2.6895) grad_norm: 3.3218 (3.3810) time: 0.5040 [2021-03-27 07:41:51 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 430/1251] eta: 0:07:03 lr: 0.000018 loss: 2.6702 (2.6856) grad_norm: 3.1683 (3.3782) time: 0.5034 [2021-03-27 07:41:56 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 440/1251] eta: 0:06:58 lr: 0.000018 loss: 2.9023 (2.6911) grad_norm: 3.2162 (3.3876) time: 0.5057 [2021-03-27 07:42:01 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 450/1251] eta: 0:06:52 lr: 0.000017 loss: 2.8851 (2.6938) grad_norm: 3.2162 (3.3790) time: 0.5034 [2021-03-27 07:42:06 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 460/1251] eta: 0:06:47 lr: 0.000017 loss: 2.6903 (2.6920) grad_norm: 3.0799 (3.3804) time: 0.5005 [2021-03-27 07:42:12 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 470/1251] eta: 0:06:42 lr: 0.000017 loss: 2.6903 (2.6927) grad_norm: 3.0799 (3.3797) time: 0.5094 [2021-03-27 07:42:16 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 480/1251] eta: 0:06:36 lr: 0.000017 loss: 2.6878 (2.6884) grad_norm: 3.0984 (3.3808) time: 0.5054 [2021-03-27 07:42:21 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 490/1251] eta: 0:06:31 lr: 0.000017 loss: 2.8144 (2.6941) grad_norm: 3.2102 (3.3871) time: 0.4967 [2021-03-27 07:42:27 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 500/1251] eta: 0:06:25 lr: 0.000017 loss: 2.8936 (2.6931) grad_norm: 3.1410 (3.3916) time: 0.5022 [2021-03-27 07:42:31 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 510/1251] eta: 0:06:20 lr: 0.000017 loss: 2.7567 (2.6952) grad_norm: 3.1362 (3.3897) time: 0.5002 [2021-03-27 07:42:37 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 520/1251] eta: 0:06:15 lr: 0.000017 loss: 2.9465 (2.7000) grad_norm: 3.2938 (3.3872) time: 0.5106 [2021-03-27 07:42:42 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 530/1251] eta: 0:06:10 lr: 0.000017 loss: 2.8697 (2.6993) grad_norm: 3.3072 (3.3921) time: 0.5157 [2021-03-27 07:42:47 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 540/1251] eta: 0:06:05 lr: 0.000017 loss: 2.6431 (2.6966) grad_norm: 3.3827 (3.3972) time: 0.5090 [2021-03-27 07:42:52 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 550/1251] eta: 0:06:00 lr: 0.000017 loss: 2.7296 (2.6976) grad_norm: 3.1828 (3.3931) time: 0.5157 [2021-03-27 07:42:57 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 560/1251] eta: 0:05:55 lr: 0.000017 loss: 2.7374 (2.6986) grad_norm: 3.0595 (3.3909) time: 0.5224 [2021-03-27 07:43:02 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 570/1251] eta: 0:05:49 lr: 0.000017 loss: 2.6341 (2.6952) grad_norm: 3.1500 (3.3988) time: 0.5114 [2021-03-27 07:43:07 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 580/1251] eta: 0:05:44 lr: 0.000017 loss: 2.6341 (2.6946) grad_norm: 3.3107 (3.3954) time: 0.5017 [2021-03-27 07:43:13 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 590/1251] eta: 0:05:39 lr: 0.000017 loss: 2.7856 (2.6947) grad_norm: 3.1093 (3.3945) time: 0.5080 [2021-03-27 07:43:18 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 600/1251] eta: 0:05:34 lr: 0.000017 loss: 2.8310 (2.6984) grad_norm: 3.2331 (3.3938) time: 0.5092 [2021-03-27 07:43:23 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 610/1251] eta: 0:05:28 lr: 0.000017 loss: 2.9364 (2.6994) grad_norm: 3.2331 (3.3912) time: 0.5063 [2021-03-27 07:43:28 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 620/1251] eta: 0:05:23 lr: 0.000017 loss: 2.7928 (2.6998) grad_norm: 3.1774 (3.3899) time: 0.5036 [2021-03-27 07:43:33 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 630/1251] eta: 0:05:18 lr: 0.000017 loss: 2.7211 (2.7000) grad_norm: 3.0772 (3.3864) time: 0.5018 [2021-03-27 07:43:38 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 640/1251] eta: 0:05:13 lr: 0.000017 loss: 2.6693 (2.6980) grad_norm: 3.0966 (3.3853) time: 0.5029 [2021-03-27 07:43:43 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 650/1251] eta: 0:05:08 lr: 0.000017 loss: 2.6210 (2.6988) grad_norm: 3.1543 (3.3837) time: 0.5042 [2021-03-27 07:43:48 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 660/1251] eta: 0:05:02 lr: 0.000017 loss: 2.5738 (2.6980) grad_norm: 3.1594 (3.3848) time: 0.5054 [2021-03-27 07:43:53 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 670/1251] eta: 0:04:57 lr: 0.000017 loss: 2.7038 (2.6979) grad_norm: 3.2773 (3.3855) time: 0.5061 [2021-03-27 07:43:58 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 680/1251] eta: 0:04:52 lr: 0.000017 loss: 2.6728 (2.6968) grad_norm: 3.1802 (3.3848) time: 0.4994 [2021-03-27 07:44:03 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 690/1251] eta: 0:04:47 lr: 0.000017 loss: 2.5473 (2.6944) grad_norm: 3.1802 (3.3853) time: 0.4966 [2021-03-27 07:44:08 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 700/1251] eta: 0:04:41 lr: 0.000017 loss: 2.7209 (2.6950) grad_norm: 3.2550 (3.3837) time: 0.4982 [2021-03-27 07:44:13 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 710/1251] eta: 0:04:36 lr: 0.000017 loss: 2.7218 (2.6954) grad_norm: 3.1475 (3.3848) time: 0.5094 [2021-03-27 07:44:18 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 720/1251] eta: 0:04:31 lr: 0.000017 loss: 2.9901 (2.6967) grad_norm: 3.1475 (3.3828) time: 0.5186 [2021-03-27 07:44:23 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 730/1251] eta: 0:04:26 lr: 0.000017 loss: 3.0998 (2.7020) grad_norm: 3.2105 (3.3841) time: 0.5169 [2021-03-27 07:44:28 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 740/1251] eta: 0:04:21 lr: 0.000017 loss: 2.9788 (2.7046) grad_norm: 3.3714 (3.3943) time: 0.5126 [2021-03-27 07:44:34 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 750/1251] eta: 0:04:16 lr: 0.000017 loss: 2.7395 (2.7005) grad_norm: 3.5091 (3.3931) time: 0.5135 [2021-03-27 07:44:39 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 760/1251] eta: 0:04:11 lr: 0.000017 loss: 2.7434 (2.7031) grad_norm: 3.1296 (3.3935) time: 0.5155 [2021-03-27 07:44:44 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 770/1251] eta: 0:04:06 lr: 0.000017 loss: 2.8068 (2.7028) grad_norm: 3.6337 (3.3972) time: 0.5103 [2021-03-27 07:44:49 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 780/1251] eta: 0:04:01 lr: 0.000017 loss: 2.7122 (2.7034) grad_norm: 3.3487 (3.3952) time: 0.5062 [2021-03-27 07:44:54 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 790/1251] eta: 0:03:55 lr: 0.000017 loss: 2.7388 (2.7040) grad_norm: 3.1849 (3.3930) time: 0.5034 [2021-03-27 07:44:59 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 800/1251] eta: 0:03:50 lr: 0.000017 loss: 2.7388 (2.7052) grad_norm: 3.3055 (3.3946) time: 0.5068 [2021-03-27 07:45:04 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 810/1251] eta: 0:03:45 lr: 0.000017 loss: 2.8465 (2.7044) grad_norm: 3.2948 (3.3929) time: 0.5048 [2021-03-27 07:45:09 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 820/1251] eta: 0:03:40 lr: 0.000017 loss: 2.7544 (2.7046) grad_norm: 3.1765 (3.3915) time: 0.5026 [2021-03-27 07:45:14 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 830/1251] eta: 0:03:35 lr: 0.000017 loss: 2.7044 (2.7024) grad_norm: 2.9830 (3.3868) time: 0.5040 [2021-03-27 07:45:19 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 840/1251] eta: 0:03:30 lr: 0.000017 loss: 2.6437 (2.7020) grad_norm: 3.0426 (3.3864) time: 0.5014 [2021-03-27 07:45:24 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 850/1251] eta: 0:03:24 lr: 0.000017 loss: 2.7183 (2.7006) grad_norm: 3.2087 (3.3841) time: 0.4996 [2021-03-27 07:45:29 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 860/1251] eta: 0:03:19 lr: 0.000017 loss: 2.9114 (2.7033) grad_norm: 3.3070 (3.3853) time: 0.5063 [2021-03-27 07:45:34 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 870/1251] eta: 0:03:14 lr: 0.000017 loss: 2.9356 (2.7052) grad_norm: 3.0845 (3.3863) time: 0.5072 [2021-03-27 07:45:39 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 880/1251] eta: 0:03:09 lr: 0.000017 loss: 2.8315 (2.7058) grad_norm: 3.0568 (3.3853) time: 0.5042 [2021-03-27 07:45:44 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 890/1251] eta: 0:03:04 lr: 0.000017 loss: 2.7521 (2.7060) grad_norm: 3.1461 (3.3863) time: 0.5105 [2021-03-27 07:45:49 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 900/1251] eta: 0:02:59 lr: 0.000017 loss: 2.7111 (2.7046) grad_norm: 3.2801 (3.3872) time: 0.5039 [2021-03-27 07:45:54 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 910/1251] eta: 0:02:54 lr: 0.000017 loss: 2.6253 (2.7030) grad_norm: 3.3119 (3.3874) time: 0.5016 [2021-03-27 07:46:00 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 920/1251] eta: 0:02:49 lr: 0.000017 loss: 2.6124 (2.7025) grad_norm: 3.3119 (3.3989) time: 0.5097 [2021-03-27 07:46:05 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 930/1251] eta: 0:02:43 lr: 0.000017 loss: 2.7211 (2.7027) grad_norm: 3.3340 (3.3978) time: 0.5081 [2021-03-27 07:46:10 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 940/1251] eta: 0:02:38 lr: 0.000017 loss: 2.6004 (2.7005) grad_norm: 3.1114 (3.3956) time: 0.5116 [2021-03-27 07:46:15 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 950/1251] eta: 0:02:33 lr: 0.000017 loss: 2.6004 (2.7002) grad_norm: 3.0573 (3.3982) time: 0.5132 [2021-03-27 07:46:20 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 960/1251] eta: 0:02:28 lr: 0.000017 loss: 2.8271 (2.7009) grad_norm: 3.2040 (3.4071) time: 0.5076 [2021-03-27 07:46:25 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 970/1251] eta: 0:02:23 lr: 0.000017 loss: 2.8536 (2.7016) grad_norm: 3.2533 (3.4060) time: 0.5066 [2021-03-27 07:46:30 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 980/1251] eta: 0:02:18 lr: 0.000017 loss: 2.8536 (2.7016) grad_norm: 3.0590 (3.4030) time: 0.5056 [2021-03-27 07:46:35 swin_small_patch4_window7_224] INFO: Epoch: [283] [ 990/1251] eta: 0:02:13 lr: 0.000017 loss: 2.8259 (2.7023) grad_norm: 3.1110 (3.4099) time: 0.5020 [2021-03-27 07:46:40 swin_small_patch4_window7_224] INFO: Epoch: [283] [1000/1251] eta: 0:02:08 lr: 0.000017 loss: 2.7296 (2.7010) grad_norm: 3.2341 (3.4102) time: 0.5003 [2021-03-27 07:46:45 swin_small_patch4_window7_224] INFO: Epoch: [283] [1010/1251] eta: 0:02:03 lr: 0.000017 loss: 2.8368 (2.7034) grad_norm: 3.2758 (3.4114) time: 0.5003 [2021-03-27 07:46:50 swin_small_patch4_window7_224] INFO: Epoch: [283] [1020/1251] eta: 0:01:57 lr: 0.000017 loss: 2.8665 (2.7019) grad_norm: 3.2758 (3.4125) time: 0.5033 [2021-03-27 07:46:55 swin_small_patch4_window7_224] INFO: Epoch: [283] [1030/1251] eta: 0:01:52 lr: 0.000017 loss: 2.8665 (2.7037) grad_norm: 3.3190 (3.4118) time: 0.5040 [2021-03-27 07:47:00 swin_small_patch4_window7_224] INFO: Epoch: [283] [1040/1251] eta: 0:01:47 lr: 0.000017 loss: 2.9186 (2.7013) grad_norm: 3.2573 (3.4092) time: 0.5051 [2021-03-27 07:47:05 swin_small_patch4_window7_224] INFO: Epoch: [283] [1050/1251] eta: 0:01:42 lr: 0.000017 loss: 2.7683 (2.7022) grad_norm: 3.1052 (3.4058) time: 0.5088 [2021-03-27 07:47:10 swin_small_patch4_window7_224] INFO: Epoch: [283] [1060/1251] eta: 0:01:37 lr: 0.000017 loss: 2.7683 (2.7032) grad_norm: 3.0273 (3.4025) time: 0.5027 [2021-03-27 07:47:16 swin_small_patch4_window7_224] INFO: Epoch: [283] [1070/1251] eta: 0:01:32 lr: 0.000017 loss: 2.7236 (2.7024) grad_norm: 3.0201 (3.3997) time: 0.5065 [2021-03-27 07:47:21 swin_small_patch4_window7_224] INFO: Epoch: [283] [1080/1251] eta: 0:01:27 lr: 0.000017 loss: 2.6003 (2.7017) grad_norm: 3.0559 (3.3970) time: 0.5101 [2021-03-27 07:47:26 swin_small_patch4_window7_224] INFO: Epoch: [283] [1090/1251] eta: 0:01:22 lr: 0.000017 loss: 2.6067 (2.7010) grad_norm: 3.0345 (3.3935) time: 0.5108 [2021-03-27 07:47:31 swin_small_patch4_window7_224] INFO: Epoch: [283] [1100/1251] eta: 0:01:17 lr: 0.000017 loss: 2.6067 (2.6987) grad_norm: 3.1546 (3.3945) time: 0.5109 [2021-03-27 07:47:36 swin_small_patch4_window7_224] INFO: Epoch: [283] [1110/1251] eta: 0:01:11 lr: 0.000017 loss: 2.7333 (2.6999) grad_norm: 3.2466 (3.3959) time: 0.5025 [2021-03-27 07:47:41 swin_small_patch4_window7_224] INFO: Epoch: [283] [1120/1251] eta: 0:01:06 lr: 0.000017 loss: 2.8743 (2.7009) grad_norm: 3.2169 (3.3962) time: 0.5023 [2021-03-27 07:47:46 swin_small_patch4_window7_224] INFO: Epoch: [283] [1130/1251] eta: 0:01:01 lr: 0.000017 loss: 2.8743 (2.7013) grad_norm: 3.3247 (3.3959) time: 0.5024 [2021-03-27 07:47:51 swin_small_patch4_window7_224] INFO: Epoch: [283] [1140/1251] eta: 0:00:56 lr: 0.000017 loss: 2.7633 (2.7007) grad_norm: 3.4633 (3.3976) time: 0.4983 [2021-03-27 07:47:56 swin_small_patch4_window7_224] INFO: Epoch: [283] [1150/1251] eta: 0:00:51 lr: 0.000017 loss: 2.7443 (2.7009) grad_norm: 3.3116 (3.3952) time: 0.4988 [2021-03-27 07:48:01 swin_small_patch4_window7_224] INFO: Epoch: [283] [1160/1251] eta: 0:00:46 lr: 0.000017 loss: 2.7190 (2.6995) grad_norm: 3.1120 (3.3945) time: 0.4970 [2021-03-27 07:48:06 swin_small_patch4_window7_224] INFO: Epoch: [283] [1170/1251] eta: 0:00:41 lr: 0.000017 loss: 2.5535 (2.6987) grad_norm: 3.0304 (3.3947) time: 0.5066 [2021-03-27 07:48:11 swin_small_patch4_window7_224] INFO: Epoch: [283] [1180/1251] eta: 0:00:36 lr: 0.000017 loss: 2.7800 (2.6986) grad_norm: 3.2673 (3.3934) time: 0.5109 [2021-03-27 07:48:16 swin_small_patch4_window7_224] INFO: Epoch: [283] [1190/1251] eta: 0:00:31 lr: 0.000017 loss: 2.8373 (2.6991) grad_norm: 3.2884 (nan) time: 0.4965 [2021-03-27 07:48:21 swin_small_patch4_window7_224] INFO: Epoch: [283] [1200/1251] eta: 0:00:25 lr: 0.000017 loss: 2.8177 (2.6994) grad_norm: 3.3055 (nan) time: 0.4946 [2021-03-27 07:48:26 swin_small_patch4_window7_224] INFO: Epoch: [283] [1210/1251] eta: 0:00:20 lr: 0.000017 loss: 2.8177 (2.7008) grad_norm: 3.3001 (nan) time: 0.4972 [2021-03-27 07:48:31 swin_small_patch4_window7_224] INFO: Epoch: [283] [1220/1251] eta: 0:00:15 lr: 0.000017 loss: 2.7849 (2.6998) grad_norm: 3.1977 (nan) time: 0.5025 [2021-03-27 07:48:36 swin_small_patch4_window7_224] INFO: Epoch: [283] [1230/1251] eta: 0:00:10 lr: 0.000017 loss: 2.7101 (2.6997) grad_norm: 3.1119 (nan) time: 0.5041 [2021-03-27 07:48:41 swin_small_patch4_window7_224] INFO: Epoch: [283] [1240/1251] eta: 0:00:05 lr: 0.000017 loss: 2.9629 (2.7002) grad_norm: 3.0995 (nan) time: 0.5095 [2021-03-27 07:48:46 swin_small_patch4_window7_224] INFO: Epoch: [283] [1250/1251] eta: 0:00:00 lr: 0.000017 loss: 2.9604 (2.7009) grad_norm: 3.1508 (nan) time: 0.5149 [2021-03-27 07:48:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:31 loss: 0.8694 (0.8694) acc1: 82.8125 (82.8125) acc5: 92.1875 (92.1875) [2021-03-27 07:49:01 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7520 (0.7576) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.0227) [2021-03-27 07:49:03 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7520 (0.7543) acc1: 84.3750 (82.8869) acc5: 96.8750 (96.4286) [2021-03-27 07:49:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7425 (0.7265) acc1: 82.8125 (83.1149) acc5: 96.8750 (96.3710) [2021-03-27 07:49:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7425 (0.7512) acc1: 81.2500 (82.4695) acc5: 95.3125 (96.0747) [2021-03-27 07:49:07 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7753 (0.7563) acc1: 82.8125 (82.1760) acc5: 95.3125 (95.9680) [2021-03-27 07:49:23 swin_small_patch4_window7_224] INFO: * Acc@1 82.974 Acc@5 96.206 loss 0.740 [2021-03-27 07:49:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 07:49:23 swin_small_patch4_window7_224] INFO: Max accuracy: 82.99% [2021-03-27 07:49:28 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 0/1251] eta: 1:37:05 lr: 0.000017 loss: 2.9843 (2.9843) grad_norm: 3.1081 (3.1081) time: 4.6564 [2021-03-27 07:49:33 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 10/1251] eta: 0:18:11 lr: 0.000017 loss: 2.8966 (2.8132) grad_norm: 3.3472 (3.3339) time: 0.8797 [2021-03-27 07:49:38 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 20/1251] eta: 0:14:19 lr: 0.000017 loss: 2.7284 (2.6232) grad_norm: 3.1615 (3.2175) time: 0.5006 [2021-03-27 07:49:43 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 30/1251] eta: 0:12:54 lr: 0.000017 loss: 2.5137 (2.6162) grad_norm: 3.0772 (3.2728) time: 0.4995 [2021-03-27 07:49:48 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 40/1251] eta: 0:12:11 lr: 0.000017 loss: 2.7368 (2.6257) grad_norm: 3.0108 (3.2415) time: 0.5045 [2021-03-27 07:49:53 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 50/1251] eta: 0:11:42 lr: 0.000017 loss: 2.7368 (2.6330) grad_norm: 3.0936 (3.2391) time: 0.5074 [2021-03-27 07:49:58 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 60/1251] eta: 0:11:22 lr: 0.000017 loss: 2.5957 (2.6242) grad_norm: 3.0936 (3.2493) time: 0.5088 [2021-03-27 07:50:03 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 70/1251] eta: 0:11:04 lr: 0.000017 loss: 2.7931 (2.6565) grad_norm: 3.1399 (3.2950) time: 0.5071 [2021-03-27 07:50:08 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 80/1251] eta: 0:10:50 lr: 0.000017 loss: 2.8556 (2.6654) grad_norm: 3.2404 (3.3180) time: 0.5014 [2021-03-27 07:50:13 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 90/1251] eta: 0:10:38 lr: 0.000017 loss: 2.7495 (2.6887) grad_norm: 3.2024 (3.3875) time: 0.5038 [2021-03-27 07:50:18 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 100/1251] eta: 0:10:29 lr: 0.000017 loss: 2.8063 (2.6772) grad_norm: 3.1373 (3.3578) time: 0.5125 [2021-03-27 07:50:23 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 110/1251] eta: 0:10:19 lr: 0.000017 loss: 2.6198 (2.6773) grad_norm: 3.0584 (3.3289) time: 0.5101 [2021-03-27 07:50:28 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 120/1251] eta: 0:10:10 lr: 0.000017 loss: 2.7391 (2.6748) grad_norm: 3.2381 (3.3415) time: 0.5030 [2021-03-27 07:50:34 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 130/1251] eta: 0:10:02 lr: 0.000017 loss: 2.8649 (2.6807) grad_norm: 3.3038 (3.3429) time: 0.5112 [2021-03-27 07:50:39 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 140/1251] eta: 0:09:54 lr: 0.000017 loss: 2.9108 (2.6994) grad_norm: 3.0968 (3.3223) time: 0.5077 [2021-03-27 07:50:44 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 150/1251] eta: 0:09:46 lr: 0.000017 loss: 2.7804 (2.6893) grad_norm: 3.0020 (3.3194) time: 0.5007 [2021-03-27 07:50:49 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 160/1251] eta: 0:09:39 lr: 0.000017 loss: 2.7339 (2.6873) grad_norm: 3.1746 (3.4004) time: 0.5055 [2021-03-27 07:50:54 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 170/1251] eta: 0:09:32 lr: 0.000017 loss: 2.7578 (2.6935) grad_norm: 3.2390 (3.3960) time: 0.5066 [2021-03-27 07:50:59 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 180/1251] eta: 0:09:26 lr: 0.000017 loss: 2.8660 (2.7098) grad_norm: 3.2272 (3.3854) time: 0.5066 [2021-03-27 07:51:04 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 190/1251] eta: 0:09:19 lr: 0.000017 loss: 2.8505 (2.7094) grad_norm: 3.1139 (3.3783) time: 0.5071 [2021-03-27 07:51:09 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 200/1251] eta: 0:09:13 lr: 0.000017 loss: 2.7222 (2.7138) grad_norm: 3.0586 (3.3697) time: 0.5127 [2021-03-27 07:51:14 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 210/1251] eta: 0:09:07 lr: 0.000017 loss: 2.7222 (2.7148) grad_norm: 3.3904 (3.3996) time: 0.5102 [2021-03-27 07:51:19 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 220/1251] eta: 0:09:00 lr: 0.000017 loss: 2.6498 (2.7076) grad_norm: 3.4164 (3.4373) time: 0.5010 [2021-03-27 07:51:24 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 230/1251] eta: 0:08:54 lr: 0.000017 loss: 2.7515 (2.7116) grad_norm: 3.2678 (3.4319) time: 0.5018 [2021-03-27 07:51:29 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 240/1251] eta: 0:08:48 lr: 0.000017 loss: 2.8072 (2.7067) grad_norm: 3.0893 (3.4172) time: 0.5052 [2021-03-27 07:51:34 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 250/1251] eta: 0:08:42 lr: 0.000017 loss: 2.6247 (2.6918) grad_norm: 3.0507 (3.4164) time: 0.5006 [2021-03-27 07:51:39 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 260/1251] eta: 0:08:36 lr: 0.000017 loss: 2.6356 (2.6898) grad_norm: 3.1213 (3.4043) time: 0.5021 [2021-03-27 07:51:44 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 270/1251] eta: 0:08:31 lr: 0.000017 loss: 2.7488 (2.6846) grad_norm: 3.3451 (3.4135) time: 0.5083 [2021-03-27 07:51:49 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 280/1251] eta: 0:08:25 lr: 0.000017 loss: 2.7587 (2.6857) grad_norm: 3.3451 (3.4053) time: 0.5044 [2021-03-27 07:51:54 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 290/1251] eta: 0:08:19 lr: 0.000017 loss: 2.8665 (2.6870) grad_norm: 3.0965 (3.4005) time: 0.5084 [2021-03-27 07:52:00 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 300/1251] eta: 0:08:14 lr: 0.000017 loss: 2.9177 (2.6945) grad_norm: 3.3251 (3.4050) time: 0.5113 [2021-03-27 07:52:04 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 310/1251] eta: 0:08:08 lr: 0.000017 loss: 2.8006 (2.6890) grad_norm: 3.3979 (3.4004) time: 0.5019 [2021-03-27 07:52:10 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 320/1251] eta: 0:08:02 lr: 0.000017 loss: 2.5780 (2.6842) grad_norm: 3.2755 (3.3954) time: 0.5044 [2021-03-27 07:52:15 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 330/1251] eta: 0:07:57 lr: 0.000017 loss: 2.7532 (2.6848) grad_norm: 3.1874 (3.3895) time: 0.5058 [2021-03-27 07:52:20 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 340/1251] eta: 0:07:51 lr: 0.000017 loss: 2.7532 (2.6831) grad_norm: 3.1854 (3.3987) time: 0.4987 [2021-03-27 07:52:25 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 350/1251] eta: 0:07:45 lr: 0.000017 loss: 2.7697 (2.6843) grad_norm: 3.2581 (3.3972) time: 0.4998 [2021-03-27 07:52:30 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 360/1251] eta: 0:07:40 lr: 0.000017 loss: 2.7873 (2.6884) grad_norm: 3.2309 (3.3997) time: 0.4992 [2021-03-27 07:52:34 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 370/1251] eta: 0:07:34 lr: 0.000017 loss: 2.7734 (2.6889) grad_norm: 3.2376 (3.3958) time: 0.4940 [2021-03-27 07:52:39 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 380/1251] eta: 0:07:28 lr: 0.000017 loss: 2.8117 (2.6874) grad_norm: 3.3671 (3.4047) time: 0.4938 [2021-03-27 07:52:44 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 390/1251] eta: 0:07:23 lr: 0.000017 loss: 2.8117 (2.6900) grad_norm: 3.3166 (3.4040) time: 0.4976 [2021-03-27 07:52:49 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 400/1251] eta: 0:07:17 lr: 0.000017 loss: 2.6249 (2.6817) grad_norm: 3.1585 (3.4001) time: 0.5021 [2021-03-27 07:52:54 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 410/1251] eta: 0:07:12 lr: 0.000017 loss: 2.6448 (2.6830) grad_norm: 3.0779 (3.3940) time: 0.5011 [2021-03-27 07:53:00 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 420/1251] eta: 0:07:07 lr: 0.000017 loss: 2.7407 (2.6827) grad_norm: 2.9521 (3.3815) time: 0.5006 [2021-03-27 07:53:05 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 430/1251] eta: 0:07:02 lr: 0.000017 loss: 2.7973 (2.6837) grad_norm: 2.9521 (3.3871) time: 0.5124 [2021-03-27 07:53:10 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 440/1251] eta: 0:06:56 lr: 0.000017 loss: 2.8744 (2.6899) grad_norm: 3.2242 (3.3843) time: 0.5114 [2021-03-27 07:53:15 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 450/1251] eta: 0:06:51 lr: 0.000017 loss: 2.8963 (2.6896) grad_norm: 3.2229 (3.3862) time: 0.5087 [2021-03-27 07:53:20 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 460/1251] eta: 0:06:46 lr: 0.000017 loss: 2.8485 (2.6894) grad_norm: 3.3295 (3.3896) time: 0.5070 [2021-03-27 07:53:25 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 470/1251] eta: 0:06:41 lr: 0.000017 loss: 2.7176 (2.6876) grad_norm: 3.5298 (3.3972) time: 0.5088 [2021-03-27 07:53:30 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 480/1251] eta: 0:06:35 lr: 0.000017 loss: 2.7176 (2.6902) grad_norm: 3.5057 (3.4051) time: 0.5086 [2021-03-27 07:53:35 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 490/1251] eta: 0:06:30 lr: 0.000017 loss: 2.9874 (2.6926) grad_norm: 3.2754 (3.4024) time: 0.5011 [2021-03-27 07:53:40 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 500/1251] eta: 0:06:25 lr: 0.000017 loss: 2.8566 (2.6901) grad_norm: 3.2279 (3.4037) time: 0.5006 [2021-03-27 07:53:45 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 510/1251] eta: 0:06:19 lr: 0.000017 loss: 2.7701 (2.6928) grad_norm: 3.1720 (3.4029) time: 0.5003 [2021-03-27 07:53:50 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 520/1251] eta: 0:06:14 lr: 0.000017 loss: 2.7701 (2.6919) grad_norm: 3.1720 (3.3998) time: 0.5133 [2021-03-27 07:53:55 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 530/1251] eta: 0:06:09 lr: 0.000017 loss: 2.7682 (2.6935) grad_norm: 3.1070 (3.4016) time: 0.5114 [2021-03-27 07:54:00 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 540/1251] eta: 0:06:04 lr: 0.000017 loss: 2.7184 (2.6930) grad_norm: 3.1070 (3.3965) time: 0.5054 [2021-03-27 07:54:06 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 550/1251] eta: 0:05:59 lr: 0.000017 loss: 2.7184 (2.6950) grad_norm: 3.3110 (3.4008) time: 0.5166 [2021-03-27 07:54:11 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 560/1251] eta: 0:05:54 lr: 0.000017 loss: 2.7450 (2.6919) grad_norm: 3.3557 (3.3982) time: 0.5108 [2021-03-27 07:54:16 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 570/1251] eta: 0:05:48 lr: 0.000017 loss: 2.7080 (2.6908) grad_norm: 3.1330 (3.3928) time: 0.4978 [2021-03-27 07:54:21 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 580/1251] eta: 0:05:43 lr: 0.000017 loss: 2.7086 (2.6916) grad_norm: 3.1339 (3.4071) time: 0.5020 [2021-03-27 07:54:26 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 590/1251] eta: 0:05:38 lr: 0.000017 loss: 2.7463 (2.6920) grad_norm: 3.4000 (3.4121) time: 0.5025 [2021-03-27 07:54:31 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 600/1251] eta: 0:05:33 lr: 0.000017 loss: 2.6862 (2.6918) grad_norm: 3.3928 (3.4113) time: 0.4997 [2021-03-27 07:54:36 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 610/1251] eta: 0:05:27 lr: 0.000017 loss: 2.6300 (2.6917) grad_norm: 3.2152 (3.4090) time: 0.5014 [2021-03-27 07:54:41 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 620/1251] eta: 0:05:22 lr: 0.000017 loss: 2.7297 (2.6902) grad_norm: 3.2765 (3.4110) time: 0.5046 [2021-03-27 07:54:46 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 630/1251] eta: 0:05:17 lr: 0.000017 loss: 2.7172 (2.6910) grad_norm: 3.2765 (3.4077) time: 0.5046 [2021-03-27 07:54:51 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 640/1251] eta: 0:05:12 lr: 0.000016 loss: 2.7172 (2.6920) grad_norm: 3.2053 (3.4035) time: 0.5048 [2021-03-27 07:54:56 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 650/1251] eta: 0:05:07 lr: 0.000016 loss: 2.7096 (2.6913) grad_norm: 3.0325 (3.3967) time: 0.5059 [2021-03-27 07:55:01 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 660/1251] eta: 0:05:01 lr: 0.000016 loss: 2.5521 (2.6922) grad_norm: 3.0325 (3.3948) time: 0.4992 [2021-03-27 07:55:06 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 670/1251] eta: 0:04:56 lr: 0.000016 loss: 2.6911 (2.6934) grad_norm: 3.3248 (3.3967) time: 0.4978 [2021-03-27 07:55:11 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 680/1251] eta: 0:04:51 lr: 0.000016 loss: 2.6952 (2.6922) grad_norm: 3.3248 (3.3960) time: 0.5019 [2021-03-27 07:55:16 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 690/1251] eta: 0:04:46 lr: 0.000016 loss: 2.7663 (2.6945) grad_norm: 3.2709 (3.3947) time: 0.4995 [2021-03-27 07:55:21 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 700/1251] eta: 0:04:41 lr: 0.000016 loss: 2.8916 (2.6965) grad_norm: 3.1489 (3.3953) time: 0.4991 [2021-03-27 07:55:26 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 710/1251] eta: 0:04:36 lr: 0.000016 loss: 2.7980 (2.6962) grad_norm: 3.1655 (3.3931) time: 0.5041 [2021-03-27 07:55:31 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 720/1251] eta: 0:04:30 lr: 0.000016 loss: 2.8731 (2.6998) grad_norm: 3.1988 (3.3948) time: 0.5099 [2021-03-27 07:55:36 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 730/1251] eta: 0:04:25 lr: 0.000016 loss: 2.8951 (2.6988) grad_norm: 3.1988 (3.3895) time: 0.5057 [2021-03-27 07:55:42 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 740/1251] eta: 0:04:20 lr: 0.000016 loss: 2.8495 (2.7004) grad_norm: 3.0516 (3.3995) time: 0.5209 [2021-03-27 07:55:47 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 750/1251] eta: 0:04:15 lr: 0.000016 loss: 2.8600 (2.7001) grad_norm: 3.1635 (3.3970) time: 0.5311 [2021-03-27 07:55:52 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 760/1251] eta: 0:04:10 lr: 0.000016 loss: 2.6521 (2.6981) grad_norm: 3.0596 (3.3937) time: 0.5127 [2021-03-27 07:55:57 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 770/1251] eta: 0:04:05 lr: 0.000016 loss: 2.5318 (2.6967) grad_norm: 3.4300 (3.4031) time: 0.5044 [2021-03-27 07:56:02 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 780/1251] eta: 0:04:00 lr: 0.000016 loss: 2.6763 (2.6974) grad_norm: 3.3896 (3.4023) time: 0.5003 [2021-03-27 07:56:07 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 790/1251] eta: 0:03:55 lr: 0.000016 loss: 2.5475 (2.6951) grad_norm: 3.1593 (3.3984) time: 0.5004 [2021-03-27 07:56:12 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 800/1251] eta: 0:03:50 lr: 0.000016 loss: 2.5475 (2.6940) grad_norm: 3.1593 (3.4009) time: 0.5024 [2021-03-27 07:56:17 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 810/1251] eta: 0:03:44 lr: 0.000016 loss: 2.8013 (2.6955) grad_norm: 3.2565 (3.3994) time: 0.5023 [2021-03-27 07:56:22 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 820/1251] eta: 0:03:39 lr: 0.000016 loss: 2.8914 (2.6953) grad_norm: 3.2156 (3.3955) time: 0.5040 [2021-03-27 07:56:27 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 830/1251] eta: 0:03:34 lr: 0.000016 loss: 2.8750 (2.6971) grad_norm: 3.2001 (3.3991) time: 0.5051 [2021-03-27 07:56:32 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 840/1251] eta: 0:03:29 lr: 0.000016 loss: 2.8921 (2.6987) grad_norm: 3.2297 (3.3973) time: 0.5077 [2021-03-27 07:56:37 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 850/1251] eta: 0:03:24 lr: 0.000016 loss: 2.8891 (2.6996) grad_norm: 3.1892 (3.3953) time: 0.5073 [2021-03-27 07:56:42 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 860/1251] eta: 0:03:19 lr: 0.000016 loss: 2.8997 (2.7028) grad_norm: 3.1872 (3.3967) time: 0.5042 [2021-03-27 07:56:47 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 870/1251] eta: 0:03:14 lr: 0.000016 loss: 2.8997 (2.7040) grad_norm: 3.2046 (3.3949) time: 0.5139 [2021-03-27 07:56:52 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 880/1251] eta: 0:03:09 lr: 0.000016 loss: 2.7220 (2.7041) grad_norm: 3.1674 (3.3986) time: 0.5127 [2021-03-27 07:56:57 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 890/1251] eta: 0:03:04 lr: 0.000016 loss: 2.7198 (2.7034) grad_norm: 3.3584 (3.4001) time: 0.5015 [2021-03-27 07:57:02 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 900/1251] eta: 0:02:58 lr: 0.000016 loss: 2.7275 (2.7032) grad_norm: 3.4579 (3.4007) time: 0.4996 [2021-03-27 07:57:08 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 910/1251] eta: 0:02:53 lr: 0.000016 loss: 2.8681 (2.7046) grad_norm: 3.4428 (3.4024) time: 0.5108 [2021-03-27 07:57:13 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 920/1251] eta: 0:02:48 lr: 0.000016 loss: 2.9392 (2.7066) grad_norm: 3.2629 (3.4001) time: 0.5128 [2021-03-27 07:57:18 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 930/1251] eta: 0:02:43 lr: 0.000016 loss: 2.7788 (2.7070) grad_norm: 3.2215 (3.3997) time: 0.5118 [2021-03-27 07:57:23 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 940/1251] eta: 0:02:38 lr: 0.000016 loss: 2.7788 (2.7066) grad_norm: 3.1451 (3.3977) time: 0.5135 [2021-03-27 07:57:28 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 950/1251] eta: 0:02:33 lr: 0.000016 loss: 2.7979 (2.7065) grad_norm: 3.0299 (3.3954) time: 0.5065 [2021-03-27 07:57:33 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 960/1251] eta: 0:02:28 lr: 0.000016 loss: 2.9045 (2.7070) grad_norm: 3.0964 (3.3938) time: 0.5007 [2021-03-27 07:57:38 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 970/1251] eta: 0:02:23 lr: 0.000016 loss: 2.8879 (2.7080) grad_norm: 3.2209 (3.3930) time: 0.4938 [2021-03-27 07:57:43 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 980/1251] eta: 0:02:18 lr: 0.000016 loss: 2.7874 (2.7062) grad_norm: 3.2344 (3.3923) time: 0.4991 [2021-03-27 07:57:48 swin_small_patch4_window7_224] INFO: Epoch: [284] [ 990/1251] eta: 0:02:12 lr: 0.000016 loss: 2.6859 (2.7071) grad_norm: 3.2788 (3.3954) time: 0.5078 [2021-03-27 07:57:53 swin_small_patch4_window7_224] INFO: Epoch: [284] [1000/1251] eta: 0:02:07 lr: 0.000016 loss: 2.7518 (2.7073) grad_norm: 3.3154 (3.3989) time: 0.5130 [2021-03-27 07:57:58 swin_small_patch4_window7_224] INFO: Epoch: [284] [1010/1251] eta: 0:02:02 lr: 0.000016 loss: 2.7518 (2.7081) grad_norm: 3.2216 (3.4017) time: 0.5134 [2021-03-27 07:58:03 swin_small_patch4_window7_224] INFO: Epoch: [284] [1020/1251] eta: 0:01:57 lr: 0.000016 loss: 2.8989 (2.7087) grad_norm: 3.2216 (3.4016) time: 0.5132 [2021-03-27 07:58:09 swin_small_patch4_window7_224] INFO: Epoch: [284] [1030/1251] eta: 0:01:52 lr: 0.000016 loss: 2.8101 (2.7060) grad_norm: 3.1784 (3.4007) time: 0.5086 [2021-03-27 07:58:14 swin_small_patch4_window7_224] INFO: Epoch: [284] [1040/1251] eta: 0:01:47 lr: 0.000016 loss: 2.3577 (2.7046) grad_norm: 3.1784 (3.4005) time: 0.5023 [2021-03-27 07:58:19 swin_small_patch4_window7_224] INFO: Epoch: [284] [1050/1251] eta: 0:01:42 lr: 0.000016 loss: 2.8167 (2.7050) grad_norm: 3.1466 (3.3988) time: 0.5038 [2021-03-27 07:58:24 swin_small_patch4_window7_224] INFO: Epoch: [284] [1060/1251] eta: 0:01:37 lr: 0.000016 loss: 2.7579 (2.7028) grad_norm: 3.1395 (3.3968) time: 0.5028 [2021-03-27 07:58:29 swin_small_patch4_window7_224] INFO: Epoch: [284] [1070/1251] eta: 0:01:32 lr: 0.000016 loss: 2.6074 (2.7031) grad_norm: 3.2336 (3.4016) time: 0.5137 [2021-03-27 07:58:34 swin_small_patch4_window7_224] INFO: Epoch: [284] [1080/1251] eta: 0:01:27 lr: 0.000016 loss: 2.8498 (2.7034) grad_norm: 3.6722 (3.4038) time: 0.5162 [2021-03-27 07:58:39 swin_small_patch4_window7_224] INFO: Epoch: [284] [1090/1251] eta: 0:01:22 lr: 0.000016 loss: 2.8990 (2.7047) grad_norm: 3.5084 (3.4025) time: 0.5104 [2021-03-27 07:58:44 swin_small_patch4_window7_224] INFO: Epoch: [284] [1100/1251] eta: 0:01:16 lr: 0.000016 loss: 2.9217 (2.7068) grad_norm: 3.0592 (3.3994) time: 0.5075 [2021-03-27 07:58:49 swin_small_patch4_window7_224] INFO: Epoch: [284] [1110/1251] eta: 0:01:11 lr: 0.000016 loss: 2.8603 (2.7059) grad_norm: 3.1133 (3.3980) time: 0.5028 [2021-03-27 07:58:54 swin_small_patch4_window7_224] INFO: Epoch: [284] [1120/1251] eta: 0:01:06 lr: 0.000016 loss: 2.8437 (2.7079) grad_norm: 3.2838 (3.3994) time: 0.4989 [2021-03-27 07:58:59 swin_small_patch4_window7_224] INFO: Epoch: [284] [1130/1251] eta: 0:01:01 lr: 0.000016 loss: 2.8437 (2.7072) grad_norm: 3.3814 (3.3987) time: 0.4977 [2021-03-27 07:59:04 swin_small_patch4_window7_224] INFO: Epoch: [284] [1140/1251] eta: 0:00:56 lr: 0.000016 loss: 2.6508 (2.7057) grad_norm: 3.1471 (3.3977) time: 0.5046 [2021-03-27 07:59:09 swin_small_patch4_window7_224] INFO: Epoch: [284] [1150/1251] eta: 0:00:51 lr: 0.000016 loss: 2.7527 (2.7057) grad_norm: 3.1471 (3.3965) time: 0.5088 [2021-03-27 07:59:14 swin_small_patch4_window7_224] INFO: Epoch: [284] [1160/1251] eta: 0:00:46 lr: 0.000016 loss: 2.7798 (2.7052) grad_norm: 3.3029 (3.3960) time: 0.5065 [2021-03-27 07:59:19 swin_small_patch4_window7_224] INFO: Epoch: [284] [1170/1251] eta: 0:00:41 lr: 0.000016 loss: 2.6267 (2.7054) grad_norm: 3.1168 (3.3950) time: 0.5050 [2021-03-27 07:59:24 swin_small_patch4_window7_224] INFO: Epoch: [284] [1180/1251] eta: 0:00:36 lr: 0.000016 loss: 2.6615 (2.7049) grad_norm: 2.9927 (3.3914) time: 0.5051 [2021-03-27 07:59:29 swin_small_patch4_window7_224] INFO: Epoch: [284] [1190/1251] eta: 0:00:31 lr: 0.000016 loss: 2.6943 (2.7060) grad_norm: 3.0294 (3.3906) time: 0.5032 [2021-03-27 07:59:34 swin_small_patch4_window7_224] INFO: Epoch: [284] [1200/1251] eta: 0:00:25 lr: 0.000016 loss: 2.7100 (2.7058) grad_norm: 3.2365 (3.3881) time: 0.5045 [2021-03-27 07:59:40 swin_small_patch4_window7_224] INFO: Epoch: [284] [1210/1251] eta: 0:00:20 lr: 0.000016 loss: 2.6341 (2.7048) grad_norm: 3.2365 (3.3892) time: 0.5078 [2021-03-27 07:59:45 swin_small_patch4_window7_224] INFO: Epoch: [284] [1220/1251] eta: 0:00:15 lr: 0.000016 loss: 2.6341 (2.7049) grad_norm: 3.3677 (3.3879) time: 0.5076 [2021-03-27 07:59:50 swin_small_patch4_window7_224] INFO: Epoch: [284] [1230/1251] eta: 0:00:10 lr: 0.000016 loss: 2.5526 (2.7039) grad_norm: 3.2121 (3.3876) time: 0.5020 [2021-03-27 07:59:55 swin_small_patch4_window7_224] INFO: Epoch: [284] [1240/1251] eta: 0:00:05 lr: 0.000016 loss: 2.5057 (2.7020) grad_norm: 3.2094 (3.3870) time: 0.4935 [2021-03-27 07:59:59 swin_small_patch4_window7_224] INFO: Epoch: [284] [1250/1251] eta: 0:00:00 lr: 0.000016 loss: 2.6086 (2.7015) grad_norm: 3.1530 (3.3871) time: 0.4872 [2021-03-27 08:00:10 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:24 loss: 0.8365 (0.8365) acc1: 78.1250 (78.1250) acc5: 95.3125 (95.3125) [2021-03-27 08:00:12 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7350 (0.7604) acc1: 78.1250 (80.8239) acc5: 95.3125 (95.7386) [2021-03-27 08:00:14 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6857 (0.7247) acc1: 82.8125 (81.6220) acc5: 96.8750 (96.3542) [2021-03-27 08:00:16 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7122 (0.7604) acc1: 81.2500 (81.6532) acc5: 96.8750 (96.0181) [2021-03-27 08:00:19 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7134 (0.7388) acc1: 82.8125 (82.5457) acc5: 96.8750 (96.0747) [2021-03-27 08:00:19 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7178 (0.7506) acc1: 82.8125 (82.1760) acc5: 96.8750 (96.0320) [2021-03-27 08:00:33 swin_small_patch4_window7_224] INFO: * Acc@1 83.056 Acc@5 96.152 loss 0.737 [2021-03-27 08:00:33 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 08:00:33 swin_small_patch4_window7_224] INFO: Max accuracy: 83.06% [2021-03-27 08:00:38 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 0/1251] eta: 1:30:04 lr: 0.000016 loss: 2.6898 (2.6898) grad_norm: 3.3825 (3.3825) time: 4.3199 [2021-03-27 08:00:43 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 10/1251] eta: 0:17:57 lr: 0.000016 loss: 2.7328 (2.6691) grad_norm: 3.0265 (3.2905) time: 0.8683 [2021-03-27 08:00:48 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 20/1251] eta: 0:14:16 lr: 0.000016 loss: 2.6899 (2.6416) grad_norm: 3.0740 (3.2412) time: 0.5145 [2021-03-27 08:00:53 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 30/1251] eta: 0:12:51 lr: 0.000016 loss: 2.7531 (2.6870) grad_norm: 3.0971 (3.2915) time: 0.5012 [2021-03-27 08:00:58 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 40/1251] eta: 0:12:11 lr: 0.000016 loss: 2.8409 (2.7123) grad_norm: 3.2800 (3.3830) time: 0.5077 [2021-03-27 08:01:03 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 50/1251] eta: 0:11:42 lr: 0.000016 loss: 2.8116 (2.7174) grad_norm: 3.3820 (3.3986) time: 0.5118 [2021-03-27 08:01:08 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 60/1251] eta: 0:11:20 lr: 0.000016 loss: 2.7709 (2.7221) grad_norm: 3.3820 (3.3887) time: 0.5033 [2021-03-27 08:01:13 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 70/1251] eta: 0:11:02 lr: 0.000016 loss: 2.6905 (2.7085) grad_norm: 3.1307 (3.3281) time: 0.5016 [2021-03-27 08:01:18 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 80/1251] eta: 0:10:48 lr: 0.000016 loss: 2.7590 (2.7116) grad_norm: 2.9623 (3.3022) time: 0.5015 [2021-03-27 08:01:23 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 90/1251] eta: 0:10:37 lr: 0.000016 loss: 2.7262 (2.7047) grad_norm: 3.1640 (3.2897) time: 0.5060 [2021-03-27 08:01:29 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 100/1251] eta: 0:10:27 lr: 0.000016 loss: 2.6751 (2.7028) grad_norm: 3.2165 (3.2885) time: 0.5121 [2021-03-27 08:01:34 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 110/1251] eta: 0:10:17 lr: 0.000016 loss: 2.8608 (2.7212) grad_norm: 3.3731 (inf) time: 0.5050 [2021-03-27 08:01:39 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 120/1251] eta: 0:10:08 lr: 0.000016 loss: 2.9183 (2.7240) grad_norm: 3.4455 (inf) time: 0.5012 [2021-03-27 08:01:44 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 130/1251] eta: 0:10:01 lr: 0.000016 loss: 2.7920 (2.7252) grad_norm: 3.1605 (inf) time: 0.5096 [2021-03-27 08:01:49 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 140/1251] eta: 0:09:55 lr: 0.000016 loss: 2.7739 (2.7134) grad_norm: 3.0974 (inf) time: 0.5241 [2021-03-27 08:01:54 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 150/1251] eta: 0:09:48 lr: 0.000016 loss: 2.6141 (2.6924) grad_norm: 3.2819 (inf) time: 0.5223 [2021-03-27 08:01:59 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 160/1251] eta: 0:09:40 lr: 0.000016 loss: 2.6143 (2.6938) grad_norm: 3.1671 (inf) time: 0.5021 [2021-03-27 08:02:04 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 170/1251] eta: 0:09:34 lr: 0.000016 loss: 2.8721 (2.7092) grad_norm: 3.1671 (inf) time: 0.5078 [2021-03-27 08:02:09 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 180/1251] eta: 0:09:27 lr: 0.000016 loss: 2.7424 (2.6918) grad_norm: 3.4530 (inf) time: 0.5156 [2021-03-27 08:02:14 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 190/1251] eta: 0:09:20 lr: 0.000016 loss: 2.5365 (2.6938) grad_norm: 3.1785 (inf) time: 0.5052 [2021-03-27 08:02:19 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 200/1251] eta: 0:09:14 lr: 0.000016 loss: 2.5403 (2.6794) grad_norm: 3.0329 (inf) time: 0.5015 [2021-03-27 08:02:25 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 210/1251] eta: 0:09:07 lr: 0.000016 loss: 2.6563 (2.6876) grad_norm: 3.0311 (inf) time: 0.5051 [2021-03-27 08:02:30 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 220/1251] eta: 0:09:01 lr: 0.000016 loss: 2.6783 (2.6806) grad_norm: 3.2450 (inf) time: 0.5037 [2021-03-27 08:02:35 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 230/1251] eta: 0:08:55 lr: 0.000016 loss: 2.8443 (2.6953) grad_norm: 3.3215 (inf) time: 0.5019 [2021-03-27 08:02:40 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 240/1251] eta: 0:08:49 lr: 0.000016 loss: 2.9861 (2.7011) grad_norm: 3.3102 (inf) time: 0.5055 [2021-03-27 08:02:45 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 250/1251] eta: 0:08:43 lr: 0.000016 loss: 2.6385 (2.6918) grad_norm: 3.2318 (inf) time: 0.5097 [2021-03-27 08:02:50 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 260/1251] eta: 0:08:37 lr: 0.000016 loss: 2.6385 (2.6964) grad_norm: 3.3367 (inf) time: 0.5045 [2021-03-27 08:02:55 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 270/1251] eta: 0:08:31 lr: 0.000016 loss: 2.8935 (2.6974) grad_norm: 3.3367 (inf) time: 0.4985 [2021-03-27 08:03:00 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 280/1251] eta: 0:08:25 lr: 0.000016 loss: 2.9014 (2.7034) grad_norm: 3.2975 (inf) time: 0.4986 [2021-03-27 08:03:05 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 290/1251] eta: 0:08:19 lr: 0.000016 loss: 2.7419 (2.6932) grad_norm: 3.2783 (inf) time: 0.5042 [2021-03-27 08:03:10 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 300/1251] eta: 0:08:14 lr: 0.000016 loss: 2.7089 (2.6975) grad_norm: 3.1455 (inf) time: 0.5063 [2021-03-27 08:03:15 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 310/1251] eta: 0:08:08 lr: 0.000016 loss: 2.8786 (2.6982) grad_norm: 3.1371 (inf) time: 0.4972 [2021-03-27 08:03:20 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 320/1251] eta: 0:08:02 lr: 0.000016 loss: 2.7791 (2.7014) grad_norm: 3.2017 (inf) time: 0.5021 [2021-03-27 08:03:25 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 330/1251] eta: 0:07:56 lr: 0.000016 loss: 2.9387 (2.7055) grad_norm: 3.2763 (inf) time: 0.5041 [2021-03-27 08:03:30 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 340/1251] eta: 0:07:51 lr: 0.000016 loss: 2.9386 (2.7118) grad_norm: 3.1264 (inf) time: 0.4992 [2021-03-27 08:03:35 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 350/1251] eta: 0:07:45 lr: 0.000016 loss: 2.8168 (2.7149) grad_norm: 3.1564 (inf) time: 0.5012 [2021-03-27 08:03:40 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 360/1251] eta: 0:07:39 lr: 0.000016 loss: 2.7022 (2.7139) grad_norm: 3.2926 (inf) time: 0.4975 [2021-03-27 08:03:45 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 370/1251] eta: 0:07:34 lr: 0.000016 loss: 2.7795 (2.7143) grad_norm: 3.3625 (inf) time: 0.4981 [2021-03-27 08:03:50 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 380/1251] eta: 0:07:29 lr: 0.000016 loss: 2.9068 (2.7198) grad_norm: 3.2950 (inf) time: 0.5063 [2021-03-27 08:03:55 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 390/1251] eta: 0:07:23 lr: 0.000016 loss: 2.9279 (2.7188) grad_norm: 3.1959 (inf) time: 0.5058 [2021-03-27 08:04:00 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 400/1251] eta: 0:07:18 lr: 0.000016 loss: 2.6236 (2.7124) grad_norm: 3.0542 (inf) time: 0.4973 [2021-03-27 08:04:05 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 410/1251] eta: 0:07:12 lr: 0.000016 loss: 2.5519 (2.7052) grad_norm: 3.2265 (inf) time: 0.4974 [2021-03-27 08:04:10 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 420/1251] eta: 0:07:07 lr: 0.000016 loss: 2.7836 (2.7090) grad_norm: 3.2144 (inf) time: 0.5031 [2021-03-27 08:04:15 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 430/1251] eta: 0:07:01 lr: 0.000016 loss: 2.7836 (2.7058) grad_norm: 3.1652 (inf) time: 0.5003 [2021-03-27 08:04:20 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 440/1251] eta: 0:06:56 lr: 0.000016 loss: 2.7008 (2.7016) grad_norm: 3.1383 (inf) time: 0.5000 [2021-03-27 08:04:25 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 450/1251] eta: 0:06:51 lr: 0.000016 loss: 2.7604 (2.7027) grad_norm: 3.2110 (inf) time: 0.5004 [2021-03-27 08:04:30 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 460/1251] eta: 0:06:45 lr: 0.000016 loss: 2.7604 (2.7002) grad_norm: 3.0158 (inf) time: 0.5026 [2021-03-27 08:04:35 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 470/1251] eta: 0:06:40 lr: 0.000016 loss: 2.5692 (2.6986) grad_norm: 3.0158 (inf) time: 0.5062 [2021-03-27 08:04:40 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 480/1251] eta: 0:06:35 lr: 0.000016 loss: 2.6219 (2.6948) grad_norm: 2.8685 (inf) time: 0.5062 [2021-03-27 08:04:45 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 490/1251] eta: 0:06:29 lr: 0.000016 loss: 2.6341 (2.6926) grad_norm: 2.8567 (inf) time: 0.5031 [2021-03-27 08:04:50 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 500/1251] eta: 0:06:24 lr: 0.000016 loss: 2.6492 (2.6917) grad_norm: 2.9094 (inf) time: 0.5018 [2021-03-27 08:04:55 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 510/1251] eta: 0:06:19 lr: 0.000016 loss: 2.6668 (2.6926) grad_norm: 2.9815 (inf) time: 0.5091 [2021-03-27 08:05:00 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 520/1251] eta: 0:06:14 lr: 0.000016 loss: 2.6518 (2.6893) grad_norm: 3.1008 (inf) time: 0.5051 [2021-03-27 08:05:05 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 530/1251] eta: 0:06:09 lr: 0.000016 loss: 2.8184 (2.6933) grad_norm: 3.1665 (inf) time: 0.5036 [2021-03-27 08:05:11 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 540/1251] eta: 0:06:04 lr: 0.000016 loss: 2.8152 (2.6939) grad_norm: 3.1949 (inf) time: 0.5108 [2021-03-27 08:05:16 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 550/1251] eta: 0:05:59 lr: 0.000016 loss: 2.7265 (2.6940) grad_norm: 3.1244 (inf) time: 0.5225 [2021-03-27 08:05:21 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 560/1251] eta: 0:05:54 lr: 0.000016 loss: 2.7877 (2.6969) grad_norm: 3.0207 (inf) time: 0.5209 [2021-03-27 08:05:26 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 570/1251] eta: 0:05:48 lr: 0.000016 loss: 2.8872 (2.6954) grad_norm: 3.1965 (inf) time: 0.5062 [2021-03-27 08:05:31 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 580/1251] eta: 0:05:43 lr: 0.000016 loss: 2.8286 (2.6946) grad_norm: 3.2067 (inf) time: 0.5028 [2021-03-27 08:05:36 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 590/1251] eta: 0:05:38 lr: 0.000016 loss: 2.4673 (2.6910) grad_norm: 3.1777 (inf) time: 0.5036 [2021-03-27 08:05:41 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 600/1251] eta: 0:05:33 lr: 0.000016 loss: 2.6007 (2.6922) grad_norm: 3.1924 (inf) time: 0.5078 [2021-03-27 08:05:46 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 610/1251] eta: 0:05:28 lr: 0.000016 loss: 2.7445 (2.6902) grad_norm: 3.2911 (inf) time: 0.5091 [2021-03-27 08:05:51 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 620/1251] eta: 0:05:22 lr: 0.000016 loss: 2.6926 (2.6906) grad_norm: 3.2169 (inf) time: 0.5028 [2021-03-27 08:05:56 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 630/1251] eta: 0:05:17 lr: 0.000016 loss: 2.8243 (2.6908) grad_norm: 3.2090 (inf) time: 0.5030 [2021-03-27 08:06:01 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 640/1251] eta: 0:05:12 lr: 0.000016 loss: 2.9022 (2.6906) grad_norm: 3.2364 (inf) time: 0.5068 [2021-03-27 08:06:06 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 650/1251] eta: 0:05:07 lr: 0.000016 loss: 2.7031 (2.6884) grad_norm: 3.1879 (inf) time: 0.5066 [2021-03-27 08:06:12 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 660/1251] eta: 0:05:02 lr: 0.000016 loss: 2.4035 (2.6868) grad_norm: 3.1913 (inf) time: 0.5075 [2021-03-27 08:06:17 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 670/1251] eta: 0:04:57 lr: 0.000016 loss: 2.6672 (2.6865) grad_norm: 3.1913 (inf) time: 0.5088 [2021-03-27 08:06:22 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 680/1251] eta: 0:04:51 lr: 0.000016 loss: 2.6672 (2.6851) grad_norm: 3.0395 (inf) time: 0.5135 [2021-03-27 08:06:27 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 690/1251] eta: 0:04:46 lr: 0.000016 loss: 2.6413 (2.6843) grad_norm: 3.1192 (inf) time: 0.5164 [2021-03-27 08:06:32 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 700/1251] eta: 0:04:41 lr: 0.000016 loss: 2.7913 (2.6857) grad_norm: 3.2111 (inf) time: 0.5073 [2021-03-27 08:06:37 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 710/1251] eta: 0:04:36 lr: 0.000016 loss: 2.8579 (2.6887) grad_norm: 3.1541 (inf) time: 0.5024 [2021-03-27 08:06:42 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 720/1251] eta: 0:04:31 lr: 0.000016 loss: 2.8043 (2.6881) grad_norm: 3.1541 (inf) time: 0.5069 [2021-03-27 08:06:47 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 730/1251] eta: 0:04:26 lr: 0.000016 loss: 2.9161 (2.6906) grad_norm: 3.1093 (inf) time: 0.5012 [2021-03-27 08:06:52 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 740/1251] eta: 0:04:21 lr: 0.000016 loss: 2.8163 (2.6904) grad_norm: 3.2555 (inf) time: 0.5161 [2021-03-27 08:06:57 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 750/1251] eta: 0:04:16 lr: 0.000016 loss: 2.8163 (2.6932) grad_norm: 3.2555 (inf) time: 0.5211 [2021-03-27 08:07:02 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 760/1251] eta: 0:04:10 lr: 0.000016 loss: 2.8948 (2.6930) grad_norm: 3.1825 (inf) time: 0.5001 [2021-03-27 08:07:07 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 770/1251] eta: 0:04:05 lr: 0.000016 loss: 2.9094 (2.6947) grad_norm: 3.2572 (inf) time: 0.5007 [2021-03-27 08:07:13 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 780/1251] eta: 0:04:00 lr: 0.000016 loss: 2.9520 (2.6988) grad_norm: 3.3186 (inf) time: 0.5045 [2021-03-27 08:07:18 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 790/1251] eta: 0:03:55 lr: 0.000016 loss: 2.9829 (2.6977) grad_norm: 3.3186 (inf) time: 0.5109 [2021-03-27 08:07:23 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 800/1251] eta: 0:03:50 lr: 0.000016 loss: 2.8462 (2.6990) grad_norm: 3.3017 (inf) time: 0.5174 [2021-03-27 08:07:28 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 810/1251] eta: 0:03:45 lr: 0.000016 loss: 2.7163 (2.6973) grad_norm: 3.3903 (inf) time: 0.5120 [2021-03-27 08:07:33 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 820/1251] eta: 0:03:40 lr: 0.000016 loss: 2.7925 (2.7004) grad_norm: 3.3903 (inf) time: 0.5066 [2021-03-27 08:07:38 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 830/1251] eta: 0:03:35 lr: 0.000016 loss: 3.0007 (2.7011) grad_norm: 3.2587 (inf) time: 0.5065 [2021-03-27 08:07:43 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 840/1251] eta: 0:03:29 lr: 0.000016 loss: 2.6413 (2.6991) grad_norm: 3.2697 (inf) time: 0.5068 [2021-03-27 08:07:48 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 850/1251] eta: 0:03:24 lr: 0.000016 loss: 2.5893 (2.6997) grad_norm: 3.3079 (inf) time: 0.5123 [2021-03-27 08:07:53 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 860/1251] eta: 0:03:19 lr: 0.000016 loss: 2.8346 (2.6995) grad_norm: 3.3079 (inf) time: 0.5070 [2021-03-27 08:07:58 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 870/1251] eta: 0:03:14 lr: 0.000016 loss: 2.6749 (2.6992) grad_norm: 3.2795 (inf) time: 0.5023 [2021-03-27 08:08:03 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 880/1251] eta: 0:03:09 lr: 0.000016 loss: 2.8097 (2.7003) grad_norm: 3.3032 (inf) time: 0.5096 [2021-03-27 08:08:09 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 890/1251] eta: 0:03:04 lr: 0.000016 loss: 2.8028 (2.6993) grad_norm: 3.2581 (inf) time: 0.5072 [2021-03-27 08:08:13 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 900/1251] eta: 0:02:59 lr: 0.000016 loss: 2.8020 (2.6987) grad_norm: 3.2198 (inf) time: 0.4976 [2021-03-27 08:08:19 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 910/1251] eta: 0:02:54 lr: 0.000016 loss: 2.8208 (2.6997) grad_norm: 3.2149 (inf) time: 0.5000 [2021-03-27 08:08:24 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 920/1251] eta: 0:02:48 lr: 0.000016 loss: 2.7818 (2.7015) grad_norm: 3.2919 (inf) time: 0.5045 [2021-03-27 08:08:28 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 930/1251] eta: 0:02:43 lr: 0.000016 loss: 2.7627 (2.7010) grad_norm: 3.1805 (inf) time: 0.4978 [2021-03-27 08:08:33 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 940/1251] eta: 0:02:38 lr: 0.000016 loss: 2.7893 (2.7013) grad_norm: 3.1805 (inf) time: 0.4971 [2021-03-27 08:08:38 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 950/1251] eta: 0:02:33 lr: 0.000015 loss: 2.8529 (2.6999) grad_norm: 3.3316 (inf) time: 0.4955 [2021-03-27 08:08:43 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 960/1251] eta: 0:02:28 lr: 0.000015 loss: 2.6127 (2.6999) grad_norm: 2.9471 (inf) time: 0.4967 [2021-03-27 08:08:48 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 970/1251] eta: 0:02:23 lr: 0.000015 loss: 2.6448 (2.7000) grad_norm: 3.2510 (inf) time: 0.5038 [2021-03-27 08:08:54 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 980/1251] eta: 0:02:18 lr: 0.000015 loss: 2.6946 (2.6997) grad_norm: 3.4034 (inf) time: 0.5123 [2021-03-27 08:08:59 swin_small_patch4_window7_224] INFO: Epoch: [285] [ 990/1251] eta: 0:02:13 lr: 0.000015 loss: 2.8044 (2.7023) grad_norm: 3.4178 (inf) time: 0.5118 [2021-03-27 08:09:04 swin_small_patch4_window7_224] INFO: Epoch: [285] [1000/1251] eta: 0:02:07 lr: 0.000015 loss: 2.9252 (2.7017) grad_norm: 3.4178 (inf) time: 0.5043 [2021-03-27 08:09:09 swin_small_patch4_window7_224] INFO: Epoch: [285] [1010/1251] eta: 0:02:02 lr: 0.000015 loss: 2.6916 (2.7016) grad_norm: 3.2191 (inf) time: 0.5007 [2021-03-27 08:09:14 swin_small_patch4_window7_224] INFO: Epoch: [285] [1020/1251] eta: 0:01:57 lr: 0.000015 loss: 2.8333 (2.7035) grad_norm: 3.2496 (inf) time: 0.5064 [2021-03-27 08:09:19 swin_small_patch4_window7_224] INFO: Epoch: [285] [1030/1251] eta: 0:01:52 lr: 0.000015 loss: 2.9444 (2.7048) grad_norm: 3.4692 (inf) time: 0.5118 [2021-03-27 08:09:24 swin_small_patch4_window7_224] INFO: Epoch: [285] [1040/1251] eta: 0:01:47 lr: 0.000015 loss: 2.8565 (2.7051) grad_norm: 3.1383 (inf) time: 0.5108 [2021-03-27 08:09:29 swin_small_patch4_window7_224] INFO: Epoch: [285] [1050/1251] eta: 0:01:42 lr: 0.000015 loss: 2.7691 (2.7059) grad_norm: 3.0823 (inf) time: 0.5087 [2021-03-27 08:09:34 swin_small_patch4_window7_224] INFO: Epoch: [285] [1060/1251] eta: 0:01:37 lr: 0.000015 loss: 2.7691 (2.7059) grad_norm: 3.2373 (inf) time: 0.5055 [2021-03-27 08:09:39 swin_small_patch4_window7_224] INFO: Epoch: [285] [1070/1251] eta: 0:01:32 lr: 0.000015 loss: 2.8215 (2.7081) grad_norm: 3.2060 (inf) time: 0.5065 [2021-03-27 08:09:44 swin_small_patch4_window7_224] INFO: Epoch: [285] [1080/1251] eta: 0:01:27 lr: 0.000015 loss: 2.9450 (2.7086) grad_norm: 3.2488 (inf) time: 0.5086 [2021-03-27 08:09:49 swin_small_patch4_window7_224] INFO: Epoch: [285] [1090/1251] eta: 0:01:22 lr: 0.000015 loss: 2.8099 (2.7086) grad_norm: 3.2488 (inf) time: 0.5082 [2021-03-27 08:09:55 swin_small_patch4_window7_224] INFO: Epoch: [285] [1100/1251] eta: 0:01:16 lr: 0.000015 loss: 2.6897 (2.7079) grad_norm: 3.3161 (inf) time: 0.5100 [2021-03-27 08:10:00 swin_small_patch4_window7_224] INFO: Epoch: [285] [1110/1251] eta: 0:01:11 lr: 0.000015 loss: 2.6897 (2.7074) grad_norm: 3.3161 (inf) time: 0.5048 [2021-03-27 08:10:04 swin_small_patch4_window7_224] INFO: Epoch: [285] [1120/1251] eta: 0:01:06 lr: 0.000015 loss: 2.7285 (2.7057) grad_norm: 3.0977 (inf) time: 0.4952 [2021-03-27 08:10:10 swin_small_patch4_window7_224] INFO: Epoch: [285] [1130/1251] eta: 0:01:01 lr: 0.000015 loss: 2.5282 (2.7055) grad_norm: 3.0050 (inf) time: 0.5015 [2021-03-27 08:10:15 swin_small_patch4_window7_224] INFO: Epoch: [285] [1140/1251] eta: 0:00:56 lr: 0.000015 loss: 2.6697 (2.7057) grad_norm: 3.0894 (inf) time: 0.5066 [2021-03-27 08:10:20 swin_small_patch4_window7_224] INFO: Epoch: [285] [1150/1251] eta: 0:00:51 lr: 0.000015 loss: 2.7319 (2.7054) grad_norm: 3.2769 (inf) time: 0.5021 [2021-03-27 08:10:25 swin_small_patch4_window7_224] INFO: Epoch: [285] [1160/1251] eta: 0:00:46 lr: 0.000015 loss: 2.7889 (2.7068) grad_norm: 3.4723 (inf) time: 0.5017 [2021-03-27 08:10:30 swin_small_patch4_window7_224] INFO: Epoch: [285] [1170/1251] eta: 0:00:41 lr: 0.000015 loss: 2.7946 (2.7071) grad_norm: 3.2690 (inf) time: 0.5059 [2021-03-27 08:10:35 swin_small_patch4_window7_224] INFO: Epoch: [285] [1180/1251] eta: 0:00:36 lr: 0.000015 loss: 2.7781 (2.7078) grad_norm: 3.2284 (inf) time: 0.5052 [2021-03-27 08:10:40 swin_small_patch4_window7_224] INFO: Epoch: [285] [1190/1251] eta: 0:00:31 lr: 0.000015 loss: 2.7211 (2.7082) grad_norm: 3.2179 (inf) time: 0.5040 [2021-03-27 08:10:45 swin_small_patch4_window7_224] INFO: Epoch: [285] [1200/1251] eta: 0:00:25 lr: 0.000015 loss: 2.7089 (2.7077) grad_norm: 3.2727 (inf) time: 0.5053 [2021-03-27 08:10:50 swin_small_patch4_window7_224] INFO: Epoch: [285] [1210/1251] eta: 0:00:20 lr: 0.000015 loss: 2.8087 (2.7092) grad_norm: 3.1716 (inf) time: 0.5034 [2021-03-27 08:10:55 swin_small_patch4_window7_224] INFO: Epoch: [285] [1220/1251] eta: 0:00:15 lr: 0.000015 loss: 2.8087 (2.7085) grad_norm: 3.1716 (inf) time: 0.5051 [2021-03-27 08:11:00 swin_small_patch4_window7_224] INFO: Epoch: [285] [1230/1251] eta: 0:00:10 lr: 0.000015 loss: 2.6562 (2.7076) grad_norm: 3.4062 (inf) time: 0.5043 [2021-03-27 08:11:05 swin_small_patch4_window7_224] INFO: Epoch: [285] [1240/1251] eta: 0:00:05 lr: 0.000015 loss: 2.5712 (2.7061) grad_norm: 3.3065 (inf) time: 0.4976 [2021-03-27 08:11:10 swin_small_patch4_window7_224] INFO: Epoch: [285] [1250/1251] eta: 0:00:00 lr: 0.000015 loss: 2.9102 (2.7082) grad_norm: 3.3065 (inf) time: 0.4910 [2021-03-27 08:12:01 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:06 loss: 0.7695 (0.7695) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 08:12:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7695 (0.7365) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.8750) [2021-03-27 08:12:04 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7630 (0.7625) acc1: 81.2500 (82.7381) acc5: 95.3125 (95.9821) [2021-03-27 08:12:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7630 (0.7552) acc1: 82.8125 (82.6613) acc5: 95.3125 (95.8165) [2021-03-27 08:12:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7063 (0.7493) acc1: 81.2500 (82.3171) acc5: 96.8750 (96.1128) [2021-03-27 08:12:07 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7518 (0.7504) acc1: 81.1321 (82.2720) acc5: 96.8750 (96.0960) [2021-03-27 08:12:25 swin_small_patch4_window7_224] INFO: * Acc@1 83.050 Acc@5 96.214 loss 0.733 [2021-03-27 08:12:25 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 08:12:25 swin_small_patch4_window7_224] INFO: Max accuracy: 83.06% [2021-03-27 08:12:30 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 0/1251] eta: 1:29:27 lr: 0.000015 loss: 2.8513 (2.8513) grad_norm: 2.9738 (2.9738) time: 4.2903 [2021-03-27 08:12:35 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 10/1251] eta: 0:17:38 lr: 0.000015 loss: 2.7459 (2.6059) grad_norm: 3.2334 (3.2482) time: 0.8533 [2021-03-27 08:12:40 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 20/1251] eta: 0:14:16 lr: 0.000015 loss: 2.8353 (2.7453) grad_norm: 3.2577 (3.3004) time: 0.5160 [2021-03-27 08:12:45 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 30/1251] eta: 0:12:57 lr: 0.000015 loss: 2.8495 (2.7310) grad_norm: 3.3879 (3.3114) time: 0.5183 [2021-03-27 08:12:50 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 40/1251] eta: 0:12:11 lr: 0.000015 loss: 2.7380 (2.7190) grad_norm: 3.2146 (3.2806) time: 0.5083 [2021-03-27 08:12:55 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 50/1251] eta: 0:11:41 lr: 0.000015 loss: 2.7625 (2.7409) grad_norm: 3.2544 (3.3406) time: 0.5027 [2021-03-27 08:13:00 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 60/1251] eta: 0:11:21 lr: 0.000015 loss: 2.7870 (2.7234) grad_norm: 3.2286 (3.3412) time: 0.5068 [2021-03-27 08:13:05 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 70/1251] eta: 0:11:06 lr: 0.000015 loss: 2.7875 (2.7125) grad_norm: 3.0670 (3.2945) time: 0.5130 [2021-03-27 08:13:10 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 80/1251] eta: 0:10:51 lr: 0.000015 loss: 2.7875 (2.7130) grad_norm: 3.0515 (3.3169) time: 0.5062 [2021-03-27 08:13:15 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 90/1251] eta: 0:10:39 lr: 0.000015 loss: 2.7267 (2.7266) grad_norm: 3.2888 (3.3294) time: 0.5010 [2021-03-27 08:13:20 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 100/1251] eta: 0:10:29 lr: 0.000015 loss: 2.6552 (2.7122) grad_norm: 3.2878 (3.3316) time: 0.5097 [2021-03-27 08:13:25 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 110/1251] eta: 0:10:19 lr: 0.000015 loss: 2.6454 (2.7062) grad_norm: 3.2878 (3.3612) time: 0.5076 [2021-03-27 08:13:31 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 120/1251] eta: 0:10:10 lr: 0.000015 loss: 2.6615 (2.7015) grad_norm: 3.3171 (3.3470) time: 0.5026 [2021-03-27 08:13:36 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 130/1251] eta: 0:10:01 lr: 0.000015 loss: 2.8483 (2.7115) grad_norm: 3.3515 (3.3750) time: 0.5027 [2021-03-27 08:13:40 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 140/1251] eta: 0:09:52 lr: 0.000015 loss: 2.8746 (2.7270) grad_norm: 3.3223 (3.3654) time: 0.4982 [2021-03-27 08:13:46 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 150/1251] eta: 0:09:45 lr: 0.000015 loss: 2.8862 (2.7243) grad_norm: 3.0874 (3.3462) time: 0.5010 [2021-03-27 08:13:51 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 160/1251] eta: 0:09:38 lr: 0.000015 loss: 2.9022 (2.7197) grad_norm: 3.1597 (3.3979) time: 0.5030 [2021-03-27 08:13:56 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 170/1251] eta: 0:09:31 lr: 0.000015 loss: 2.7331 (2.7168) grad_norm: 3.2772 (3.3856) time: 0.5019 [2021-03-27 08:14:01 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 180/1251] eta: 0:09:24 lr: 0.000015 loss: 2.7331 (2.7110) grad_norm: 3.1733 (3.3800) time: 0.5023 [2021-03-27 08:14:06 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 190/1251] eta: 0:09:17 lr: 0.000015 loss: 2.8869 (2.7218) grad_norm: 3.1886 (3.3835) time: 0.5035 [2021-03-27 08:14:11 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 200/1251] eta: 0:09:12 lr: 0.000015 loss: 2.9127 (2.7228) grad_norm: 3.0976 (3.3682) time: 0.5144 [2021-03-27 08:14:16 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 210/1251] eta: 0:09:05 lr: 0.000015 loss: 2.8407 (2.7172) grad_norm: 3.0976 (3.3654) time: 0.5099 [2021-03-27 08:14:21 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 220/1251] eta: 0:08:59 lr: 0.000015 loss: 2.7216 (2.7176) grad_norm: 3.2778 (3.3710) time: 0.5027 [2021-03-27 08:14:26 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 230/1251] eta: 0:08:53 lr: 0.000015 loss: 2.7216 (2.7202) grad_norm: 3.2981 (3.3633) time: 0.5085 [2021-03-27 08:14:31 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 240/1251] eta: 0:08:47 lr: 0.000015 loss: 2.7517 (2.7215) grad_norm: 3.2533 (3.3709) time: 0.5027 [2021-03-27 08:14:36 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 250/1251] eta: 0:08:41 lr: 0.000015 loss: 2.7846 (2.7279) grad_norm: 3.3161 (3.3675) time: 0.4950 [2021-03-27 08:14:41 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 260/1251] eta: 0:08:35 lr: 0.000015 loss: 2.8170 (2.7275) grad_norm: 3.2688 (3.3641) time: 0.4997 [2021-03-27 08:14:46 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 270/1251] eta: 0:08:29 lr: 0.000015 loss: 2.7442 (2.7289) grad_norm: 3.2688 (3.3637) time: 0.5016 [2021-03-27 08:14:51 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 280/1251] eta: 0:08:23 lr: 0.000015 loss: 2.7100 (2.7222) grad_norm: 3.3658 (3.3642) time: 0.5047 [2021-03-27 08:14:56 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 290/1251] eta: 0:08:18 lr: 0.000015 loss: 2.6364 (2.7200) grad_norm: 3.2525 (3.3652) time: 0.5100 [2021-03-27 08:15:01 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 300/1251] eta: 0:08:12 lr: 0.000015 loss: 2.7805 (2.7268) grad_norm: 3.1651 (3.3843) time: 0.5078 [2021-03-27 08:15:06 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 310/1251] eta: 0:08:07 lr: 0.000015 loss: 2.7805 (2.7261) grad_norm: 3.1729 (3.3916) time: 0.5027 [2021-03-27 08:15:11 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 320/1251] eta: 0:08:01 lr: 0.000015 loss: 2.7788 (2.7245) grad_norm: 3.0633 (3.3791) time: 0.5001 [2021-03-27 08:15:16 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 330/1251] eta: 0:07:55 lr: 0.000015 loss: 2.8100 (2.7232) grad_norm: 3.0372 (3.3746) time: 0.5041 [2021-03-27 08:15:21 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 340/1251] eta: 0:07:50 lr: 0.000015 loss: 2.5821 (2.7188) grad_norm: 3.1203 (3.3712) time: 0.5048 [2021-03-27 08:15:26 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 350/1251] eta: 0:07:44 lr: 0.000015 loss: 2.5821 (2.7161) grad_norm: 3.1230 (3.3725) time: 0.5012 [2021-03-27 08:15:31 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 360/1251] eta: 0:07:39 lr: 0.000015 loss: 2.6968 (2.7180) grad_norm: 3.1389 (3.3734) time: 0.4988 [2021-03-27 08:15:36 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 370/1251] eta: 0:07:33 lr: 0.000015 loss: 2.7193 (2.7182) grad_norm: 3.2694 (3.3738) time: 0.5000 [2021-03-27 08:15:41 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 380/1251] eta: 0:07:28 lr: 0.000015 loss: 2.6766 (2.7162) grad_norm: 3.2874 (3.3722) time: 0.5007 [2021-03-27 08:15:46 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 390/1251] eta: 0:07:22 lr: 0.000015 loss: 2.6549 (2.7158) grad_norm: 3.3680 (3.3816) time: 0.5026 [2021-03-27 08:15:51 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 400/1251] eta: 0:07:17 lr: 0.000015 loss: 2.6230 (2.7148) grad_norm: 3.3663 (3.3889) time: 0.5031 [2021-03-27 08:15:56 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 410/1251] eta: 0:07:12 lr: 0.000015 loss: 2.7851 (2.7154) grad_norm: 3.2700 (3.3884) time: 0.4997 [2021-03-27 08:16:02 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 420/1251] eta: 0:07:06 lr: 0.000015 loss: 2.8690 (2.7174) grad_norm: 3.2750 (3.3885) time: 0.5067 [2021-03-27 08:16:07 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 430/1251] eta: 0:07:01 lr: 0.000015 loss: 2.7443 (2.7141) grad_norm: 3.2760 (3.3906) time: 0.5080 [2021-03-27 08:16:12 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 440/1251] eta: 0:06:56 lr: 0.000015 loss: 2.8343 (2.7185) grad_norm: 3.3578 (3.3913) time: 0.5013 [2021-03-27 08:16:17 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 450/1251] eta: 0:06:50 lr: 0.000015 loss: 2.8343 (2.7133) grad_norm: 3.4307 (3.3972) time: 0.4978 [2021-03-27 08:16:22 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 460/1251] eta: 0:06:45 lr: 0.000015 loss: 2.7250 (2.7140) grad_norm: 3.2935 (3.3927) time: 0.4959 [2021-03-27 08:16:27 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 470/1251] eta: 0:06:40 lr: 0.000015 loss: 2.7250 (2.7139) grad_norm: 3.2552 (3.3913) time: 0.5010 [2021-03-27 08:16:32 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 480/1251] eta: 0:06:34 lr: 0.000015 loss: 2.7130 (2.7149) grad_norm: 3.2280 (3.3967) time: 0.5064 [2021-03-27 08:16:37 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 490/1251] eta: 0:06:29 lr: 0.000015 loss: 2.8181 (2.7153) grad_norm: 3.1281 (3.3932) time: 0.5045 [2021-03-27 08:16:42 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 500/1251] eta: 0:06:24 lr: 0.000015 loss: 2.8023 (2.7170) grad_norm: 3.0954 (3.3885) time: 0.5020 [2021-03-27 08:16:47 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 510/1251] eta: 0:06:19 lr: 0.000015 loss: 2.9155 (2.7190) grad_norm: 3.0732 (3.3936) time: 0.5077 [2021-03-27 08:16:52 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 520/1251] eta: 0:06:13 lr: 0.000015 loss: 2.7197 (2.7185) grad_norm: 3.0610 (3.3873) time: 0.5053 [2021-03-27 08:16:57 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 530/1251] eta: 0:06:08 lr: 0.000015 loss: 2.7267 (2.7229) grad_norm: 2.9883 (3.3806) time: 0.4983 [2021-03-27 08:17:02 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 540/1251] eta: 0:06:03 lr: 0.000015 loss: 2.9084 (2.7177) grad_norm: 3.2912 (3.3867) time: 0.5011 [2021-03-27 08:17:07 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 550/1251] eta: 0:05:58 lr: 0.000015 loss: 2.5604 (2.7144) grad_norm: 3.3403 (3.3845) time: 0.5167 [2021-03-27 08:17:12 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 560/1251] eta: 0:05:53 lr: 0.000015 loss: 2.7692 (2.7173) grad_norm: 3.2560 (3.3876) time: 0.5155 [2021-03-27 08:17:17 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 570/1251] eta: 0:05:48 lr: 0.000015 loss: 2.8585 (2.7184) grad_norm: 3.2325 (3.3856) time: 0.5068 [2021-03-27 08:17:22 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 580/1251] eta: 0:05:42 lr: 0.000015 loss: 2.7496 (2.7182) grad_norm: 3.1500 (3.3868) time: 0.5078 [2021-03-27 08:17:27 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 590/1251] eta: 0:05:37 lr: 0.000015 loss: 2.6229 (2.7165) grad_norm: 3.2275 (3.3844) time: 0.5036 [2021-03-27 08:17:32 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 600/1251] eta: 0:05:32 lr: 0.000015 loss: 2.6082 (2.7149) grad_norm: 3.2762 (3.3870) time: 0.5019 [2021-03-27 08:17:37 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 610/1251] eta: 0:05:27 lr: 0.000015 loss: 2.7427 (2.7154) grad_norm: 3.2683 (3.3823) time: 0.5038 [2021-03-27 08:17:42 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 620/1251] eta: 0:05:22 lr: 0.000015 loss: 2.8549 (2.7193) grad_norm: 3.0824 (3.3835) time: 0.5034 [2021-03-27 08:17:48 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 630/1251] eta: 0:05:17 lr: 0.000015 loss: 2.8677 (2.7197) grad_norm: 3.1733 (3.3819) time: 0.5047 [2021-03-27 08:17:53 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 640/1251] eta: 0:05:11 lr: 0.000015 loss: 2.6062 (2.7187) grad_norm: 3.1207 (3.3790) time: 0.5069 [2021-03-27 08:17:58 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 650/1251] eta: 0:05:06 lr: 0.000015 loss: 2.7551 (2.7192) grad_norm: 3.1207 (3.3782) time: 0.5033 [2021-03-27 08:18:03 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 660/1251] eta: 0:05:01 lr: 0.000015 loss: 2.9132 (2.7215) grad_norm: 3.0919 (3.3751) time: 0.5012 [2021-03-27 08:18:08 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 670/1251] eta: 0:04:56 lr: 0.000015 loss: 2.8730 (2.7199) grad_norm: 3.0919 (3.3735) time: 0.5016 [2021-03-27 08:18:13 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 680/1251] eta: 0:04:51 lr: 0.000015 loss: 2.5562 (2.7175) grad_norm: 3.4183 (3.3768) time: 0.4993 [2021-03-27 08:18:18 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 690/1251] eta: 0:04:45 lr: 0.000015 loss: 2.6198 (2.7169) grad_norm: 3.4183 (3.3759) time: 0.4995 [2021-03-27 08:18:23 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 700/1251] eta: 0:04:40 lr: 0.000015 loss: 2.4551 (2.7138) grad_norm: 3.2001 (3.3728) time: 0.5047 [2021-03-27 08:18:28 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 710/1251] eta: 0:04:35 lr: 0.000015 loss: 2.7356 (2.7159) grad_norm: 3.0547 (3.3712) time: 0.5018 [2021-03-27 08:18:33 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 720/1251] eta: 0:04:30 lr: 0.000015 loss: 2.8449 (2.7166) grad_norm: 3.0875 (3.3748) time: 0.5016 [2021-03-27 08:18:38 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 730/1251] eta: 0:04:25 lr: 0.000015 loss: 2.7972 (2.7170) grad_norm: 3.1842 (3.3723) time: 0.5064 [2021-03-27 08:18:43 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 740/1251] eta: 0:04:20 lr: 0.000015 loss: 2.7812 (2.7181) grad_norm: 3.1842 (3.3754) time: 0.5095 [2021-03-27 08:18:48 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 750/1251] eta: 0:04:15 lr: 0.000015 loss: 2.8161 (2.7183) grad_norm: 3.2156 (3.3742) time: 0.5109 [2021-03-27 08:18:53 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 760/1251] eta: 0:04:10 lr: 0.000015 loss: 2.8446 (2.7186) grad_norm: 3.1562 (3.3748) time: 0.5063 [2021-03-27 08:18:58 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 770/1251] eta: 0:04:05 lr: 0.000015 loss: 2.7832 (2.7212) grad_norm: 3.1556 (3.3721) time: 0.5126 [2021-03-27 08:19:03 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 780/1251] eta: 0:04:00 lr: 0.000015 loss: 2.8763 (2.7221) grad_norm: 2.9882 (3.3685) time: 0.5145 [2021-03-27 08:19:08 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 790/1251] eta: 0:03:54 lr: 0.000015 loss: 2.8763 (2.7239) grad_norm: 3.1882 (3.3679) time: 0.5014 [2021-03-27 08:19:13 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 800/1251] eta: 0:03:49 lr: 0.000015 loss: 2.7555 (2.7219) grad_norm: 3.2991 (3.3685) time: 0.5048 [2021-03-27 08:19:18 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 810/1251] eta: 0:03:44 lr: 0.000015 loss: 2.7952 (2.7237) grad_norm: 3.3781 (3.3691) time: 0.5077 [2021-03-27 08:19:24 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 820/1251] eta: 0:03:39 lr: 0.000015 loss: 2.7952 (2.7239) grad_norm: 3.3483 (3.3682) time: 0.5045 [2021-03-27 08:19:29 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 830/1251] eta: 0:03:34 lr: 0.000015 loss: 2.6678 (2.7241) grad_norm: 3.1923 (3.3669) time: 0.5043 [2021-03-27 08:19:34 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 840/1251] eta: 0:03:29 lr: 0.000015 loss: 2.7504 (2.7225) grad_norm: 3.0951 (3.3632) time: 0.5063 [2021-03-27 08:19:39 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 850/1251] eta: 0:03:24 lr: 0.000015 loss: 2.7381 (2.7226) grad_norm: 3.1907 (3.3646) time: 0.5048 [2021-03-27 08:19:44 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 860/1251] eta: 0:03:19 lr: 0.000015 loss: 2.7719 (2.7230) grad_norm: 3.2228 (3.3631) time: 0.4984 [2021-03-27 08:19:49 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 870/1251] eta: 0:03:13 lr: 0.000015 loss: 2.8337 (2.7247) grad_norm: 3.2123 (3.3618) time: 0.5009 [2021-03-27 08:19:54 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 880/1251] eta: 0:03:08 lr: 0.000015 loss: 2.8235 (2.7246) grad_norm: 3.0431 (3.3580) time: 0.5037 [2021-03-27 08:19:59 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 890/1251] eta: 0:03:03 lr: 0.000015 loss: 2.6852 (2.7241) grad_norm: 3.0389 (3.3570) time: 0.5041 [2021-03-27 08:20:04 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 900/1251] eta: 0:02:58 lr: 0.000015 loss: 2.8281 (2.7275) grad_norm: 3.2468 (3.3589) time: 0.5027 [2021-03-27 08:20:09 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 910/1251] eta: 0:02:53 lr: 0.000015 loss: 2.9111 (2.7266) grad_norm: 3.3017 (3.3580) time: 0.4971 [2021-03-27 08:20:14 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 920/1251] eta: 0:02:48 lr: 0.000015 loss: 2.8106 (2.7271) grad_norm: 3.1790 (3.3581) time: 0.5045 [2021-03-27 08:20:19 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 930/1251] eta: 0:02:43 lr: 0.000015 loss: 2.7600 (2.7263) grad_norm: 3.1821 (3.3599) time: 0.5093 [2021-03-27 08:20:24 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 940/1251] eta: 0:02:38 lr: 0.000015 loss: 2.7092 (2.7259) grad_norm: 3.1821 (3.3580) time: 0.5115 [2021-03-27 08:20:29 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 950/1251] eta: 0:02:33 lr: 0.000015 loss: 2.7092 (2.7255) grad_norm: 3.1630 (3.3574) time: 0.5116 [2021-03-27 08:20:34 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 960/1251] eta: 0:02:28 lr: 0.000015 loss: 2.7841 (2.7256) grad_norm: 3.2424 (3.3582) time: 0.5083 [2021-03-27 08:20:39 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 970/1251] eta: 0:02:22 lr: 0.000015 loss: 2.7286 (2.7238) grad_norm: 3.0958 (3.3564) time: 0.5111 [2021-03-27 08:20:44 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 980/1251] eta: 0:02:17 lr: 0.000015 loss: 2.7197 (2.7233) grad_norm: 2.9642 (3.3542) time: 0.5051 [2021-03-27 08:20:49 swin_small_patch4_window7_224] INFO: Epoch: [286] [ 990/1251] eta: 0:02:12 lr: 0.000015 loss: 2.7843 (2.7236) grad_norm: 3.0402 (3.3523) time: 0.5062 [2021-03-27 08:20:54 swin_small_patch4_window7_224] INFO: Epoch: [286] [1000/1251] eta: 0:02:07 lr: 0.000015 loss: 2.6722 (2.7215) grad_norm: 3.1025 (3.3532) time: 0.5029 [2021-03-27 08:21:00 swin_small_patch4_window7_224] INFO: Epoch: [286] [1010/1251] eta: 0:02:02 lr: 0.000015 loss: 2.6846 (2.7207) grad_norm: 3.1690 (3.3538) time: 0.5071 [2021-03-27 08:21:05 swin_small_patch4_window7_224] INFO: Epoch: [286] [1020/1251] eta: 0:01:57 lr: 0.000015 loss: 2.7169 (2.7208) grad_norm: 3.1644 (3.3525) time: 0.5104 [2021-03-27 08:21:10 swin_small_patch4_window7_224] INFO: Epoch: [286] [1030/1251] eta: 0:01:52 lr: 0.000015 loss: 2.7362 (2.7216) grad_norm: 3.1750 (3.3510) time: 0.5080 [2021-03-27 08:21:15 swin_small_patch4_window7_224] INFO: Epoch: [286] [1040/1251] eta: 0:01:47 lr: 0.000015 loss: 2.8558 (2.7228) grad_norm: 3.2340 (3.3500) time: 0.5035 [2021-03-27 08:21:20 swin_small_patch4_window7_224] INFO: Epoch: [286] [1050/1251] eta: 0:01:42 lr: 0.000015 loss: 2.8314 (2.7225) grad_norm: 3.2065 (3.3518) time: 0.4962 [2021-03-27 08:21:25 swin_small_patch4_window7_224] INFO: Epoch: [286] [1060/1251] eta: 0:01:37 lr: 0.000015 loss: 2.8028 (2.7234) grad_norm: 3.2065 (3.3528) time: 0.5072 [2021-03-27 08:21:30 swin_small_patch4_window7_224] INFO: Epoch: [286] [1070/1251] eta: 0:01:32 lr: 0.000015 loss: 2.7588 (2.7225) grad_norm: 3.1987 (3.3515) time: 0.5087 [2021-03-27 08:21:35 swin_small_patch4_window7_224] INFO: Epoch: [286] [1080/1251] eta: 0:01:26 lr: 0.000015 loss: 2.7556 (2.7220) grad_norm: 3.3915 (3.3522) time: 0.5032 [2021-03-27 08:21:40 swin_small_patch4_window7_224] INFO: Epoch: [286] [1090/1251] eta: 0:01:21 lr: 0.000015 loss: 2.7556 (2.7226) grad_norm: 3.3759 (3.3532) time: 0.5006 [2021-03-27 08:21:45 swin_small_patch4_window7_224] INFO: Epoch: [286] [1100/1251] eta: 0:01:16 lr: 0.000015 loss: 2.7076 (2.7208) grad_norm: 3.0892 (3.3508) time: 0.4967 [2021-03-27 08:21:50 swin_small_patch4_window7_224] INFO: Epoch: [286] [1110/1251] eta: 0:01:11 lr: 0.000015 loss: 2.7383 (2.7208) grad_norm: 3.2261 (3.3512) time: 0.4966 [2021-03-27 08:21:55 swin_small_patch4_window7_224] INFO: Epoch: [286] [1120/1251] eta: 0:01:06 lr: 0.000015 loss: 2.7178 (2.7190) grad_norm: 3.0189 (3.3488) time: 0.5036 [2021-03-27 08:22:00 swin_small_patch4_window7_224] INFO: Epoch: [286] [1130/1251] eta: 0:01:01 lr: 0.000015 loss: 2.5899 (2.7178) grad_norm: 3.1834 (3.3504) time: 0.5010 [2021-03-27 08:22:05 swin_small_patch4_window7_224] INFO: Epoch: [286] [1140/1251] eta: 0:00:56 lr: 0.000015 loss: 2.8905 (2.7195) grad_norm: 3.3514 (3.3494) time: 0.4925 [2021-03-27 08:22:10 swin_small_patch4_window7_224] INFO: Epoch: [286] [1150/1251] eta: 0:00:51 lr: 0.000015 loss: 2.8908 (2.7187) grad_norm: 3.2350 (3.3502) time: 0.5003 [2021-03-27 08:22:15 swin_small_patch4_window7_224] INFO: Epoch: [286] [1160/1251] eta: 0:00:46 lr: 0.000015 loss: 2.6667 (2.7166) grad_norm: 3.4366 (3.3516) time: 0.5125 [2021-03-27 08:22:20 swin_small_patch4_window7_224] INFO: Epoch: [286] [1170/1251] eta: 0:00:41 lr: 0.000015 loss: 2.6788 (2.7176) grad_norm: 3.3983 (3.3516) time: 0.5143 [2021-03-27 08:22:25 swin_small_patch4_window7_224] INFO: Epoch: [286] [1180/1251] eta: 0:00:36 lr: 0.000015 loss: 2.8011 (2.7177) grad_norm: 3.0276 (3.3526) time: 0.5029 [2021-03-27 08:22:30 swin_small_patch4_window7_224] INFO: Epoch: [286] [1190/1251] eta: 0:00:30 lr: 0.000015 loss: 2.8060 (2.7181) grad_norm: 3.3668 (3.3533) time: 0.4961 [2021-03-27 08:22:35 swin_small_patch4_window7_224] INFO: Epoch: [286] [1200/1251] eta: 0:00:25 lr: 0.000015 loss: 2.7685 (2.7173) grad_norm: 3.4720 (3.3554) time: 0.4994 [2021-03-27 08:22:40 swin_small_patch4_window7_224] INFO: Epoch: [286] [1210/1251] eta: 0:00:20 lr: 0.000015 loss: 2.8573 (2.7178) grad_norm: 3.2806 (3.3564) time: 0.5010 [2021-03-27 08:22:45 swin_small_patch4_window7_224] INFO: Epoch: [286] [1220/1251] eta: 0:00:15 lr: 0.000015 loss: 2.6797 (2.7162) grad_norm: 3.3095 (3.3646) time: 0.5022 [2021-03-27 08:22:50 swin_small_patch4_window7_224] INFO: Epoch: [286] [1230/1251] eta: 0:00:10 lr: 0.000015 loss: 2.7473 (2.7168) grad_norm: 3.4393 (3.3638) time: 0.5050 [2021-03-27 08:22:55 swin_small_patch4_window7_224] INFO: Epoch: [286] [1240/1251] eta: 0:00:05 lr: 0.000015 loss: 2.6927 (2.7141) grad_norm: 3.2326 (3.3637) time: 0.5031 [2021-03-27 08:23:00 swin_small_patch4_window7_224] INFO: Epoch: [286] [1250/1251] eta: 0:00:00 lr: 0.000015 loss: 2.9123 (2.7165) grad_norm: 3.2820 (3.3633) time: 0.5007 [2021-03-27 08:23:18 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:01 loss: 0.7395 (0.7395) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-27 08:23:21 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:18 loss: 0.6865 (0.6534) acc1: 82.8125 (84.3750) acc5: 96.8750 (97.1591) [2021-03-27 08:23:23 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6654 (0.6749) acc1: 82.8125 (84.1518) acc5: 96.8750 (96.7262) [2021-03-27 08:23:25 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7872 (0.7590) acc1: 81.2500 (82.1069) acc5: 96.8750 (96.1190) [2021-03-27 08:23:26 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7522 (0.7483) acc1: 81.2500 (82.2027) acc5: 96.8750 (96.0747) [2021-03-27 08:23:27 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7137 (0.7539) acc1: 81.2500 (82.1440) acc5: 95.3125 (96.1280) [2021-03-27 08:23:49 swin_small_patch4_window7_224] INFO: * Acc@1 83.032 Acc@5 96.210 loss 0.739 [2021-03-27 08:23:49 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 08:23:49 swin_small_patch4_window7_224] INFO: Max accuracy: 83.06% [2021-03-27 08:23:54 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 0/1251] eta: 1:27:13 lr: 0.000015 loss: 2.2891 (2.2891) grad_norm: 3.0324 (3.0324) time: 4.1833 [2021-03-27 08:23:59 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 10/1251] eta: 0:17:39 lr: 0.000015 loss: 2.6386 (2.6490) grad_norm: 3.4920 (3.9648) time: 0.8535 [2021-03-27 08:24:04 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 20/1251] eta: 0:14:06 lr: 0.000015 loss: 2.7186 (2.7057) grad_norm: 3.3835 (3.7032) time: 0.5127 [2021-03-27 08:24:09 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 30/1251] eta: 0:12:49 lr: 0.000015 loss: 2.7505 (2.6915) grad_norm: 3.2952 (3.5951) time: 0.5070 [2021-03-27 08:24:14 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 40/1251] eta: 0:12:07 lr: 0.000015 loss: 2.7701 (2.7500) grad_norm: 3.2447 (3.5292) time: 0.5094 [2021-03-27 08:24:19 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 50/1251] eta: 0:11:36 lr: 0.000015 loss: 2.8936 (2.7595) grad_norm: 3.1481 (3.4705) time: 0.5035 [2021-03-27 08:24:24 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 60/1251] eta: 0:11:19 lr: 0.000015 loss: 2.6782 (2.7105) grad_norm: 3.1683 (3.5314) time: 0.5079 [2021-03-27 08:24:29 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 70/1251] eta: 0:11:00 lr: 0.000015 loss: 2.7845 (2.7227) grad_norm: 3.1040 (3.4646) time: 0.5069 [2021-03-27 08:24:34 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 80/1251] eta: 0:10:47 lr: 0.000015 loss: 2.8008 (2.7064) grad_norm: 3.0732 (3.4380) time: 0.5016 [2021-03-27 08:24:39 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 90/1251] eta: 0:10:36 lr: 0.000015 loss: 2.5149 (2.6895) grad_norm: 3.2312 (3.4061) time: 0.5063 [2021-03-27 08:24:44 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 100/1251] eta: 0:10:25 lr: 0.000015 loss: 2.6891 (2.7012) grad_norm: 3.2236 (3.4239) time: 0.5045 [2021-03-27 08:24:49 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 110/1251] eta: 0:10:15 lr: 0.000015 loss: 2.8155 (2.6876) grad_norm: 3.2236 (3.4198) time: 0.5028 [2021-03-27 08:24:54 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 120/1251] eta: 0:10:07 lr: 0.000015 loss: 2.8028 (2.6900) grad_norm: 3.2195 (3.4153) time: 0.5031 [2021-03-27 08:24:59 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 130/1251] eta: 0:09:59 lr: 0.000015 loss: 2.6440 (2.6713) grad_norm: 3.1459 (3.3979) time: 0.5068 [2021-03-27 08:25:04 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 140/1251] eta: 0:09:51 lr: 0.000015 loss: 2.8376 (2.6877) grad_norm: 2.9754 (3.3816) time: 0.5053 [2021-03-27 08:25:10 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 150/1251] eta: 0:09:45 lr: 0.000014 loss: 2.9490 (2.6935) grad_norm: 3.3338 (3.4305) time: 0.5107 [2021-03-27 08:25:15 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 160/1251] eta: 0:09:37 lr: 0.000014 loss: 2.7651 (2.6917) grad_norm: 3.1672 (3.4224) time: 0.5099 [2021-03-27 08:25:20 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 170/1251] eta: 0:09:30 lr: 0.000014 loss: 2.8277 (2.6972) grad_norm: 3.1014 (3.4089) time: 0.5007 [2021-03-27 08:25:25 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 180/1251] eta: 0:09:24 lr: 0.000014 loss: 2.8742 (2.7053) grad_norm: 3.1020 (3.4010) time: 0.5060 [2021-03-27 08:25:30 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 190/1251] eta: 0:09:17 lr: 0.000014 loss: 2.8201 (2.7035) grad_norm: 3.2306 (3.3980) time: 0.5074 [2021-03-27 08:25:35 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 200/1251] eta: 0:09:11 lr: 0.000014 loss: 2.7868 (2.7130) grad_norm: 3.1660 (3.3867) time: 0.5049 [2021-03-27 08:25:40 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 210/1251] eta: 0:09:05 lr: 0.000014 loss: 2.6988 (2.7053) grad_norm: 3.0942 (3.3827) time: 0.5027 [2021-03-27 08:25:45 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 220/1251] eta: 0:08:58 lr: 0.000014 loss: 2.6057 (2.7064) grad_norm: 3.1180 (3.3786) time: 0.4989 [2021-03-27 08:25:50 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 230/1251] eta: 0:08:52 lr: 0.000014 loss: 2.5543 (2.6993) grad_norm: 3.1967 (3.3841) time: 0.5038 [2021-03-27 08:25:55 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 240/1251] eta: 0:08:46 lr: 0.000014 loss: 2.8214 (2.7090) grad_norm: 3.3382 (3.3889) time: 0.5064 [2021-03-27 08:26:00 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 250/1251] eta: 0:08:40 lr: 0.000014 loss: 2.8879 (2.7157) grad_norm: 3.2040 (3.3892) time: 0.4996 [2021-03-27 08:26:05 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 260/1251] eta: 0:08:34 lr: 0.000014 loss: 2.8743 (2.7114) grad_norm: 3.2572 (3.3927) time: 0.5003 [2021-03-27 08:26:10 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 270/1251] eta: 0:08:28 lr: 0.000014 loss: 2.9028 (2.7163) grad_norm: 3.5081 (3.3978) time: 0.4990 [2021-03-27 08:26:15 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 280/1251] eta: 0:08:22 lr: 0.000014 loss: 2.8382 (2.7176) grad_norm: 3.3176 (3.3889) time: 0.4936 [2021-03-27 08:26:20 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 290/1251] eta: 0:08:16 lr: 0.000014 loss: 2.7574 (2.7156) grad_norm: 3.1110 (3.3823) time: 0.4942 [2021-03-27 08:26:25 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 300/1251] eta: 0:08:11 lr: 0.000014 loss: 2.6610 (2.7157) grad_norm: 3.1028 (3.3798) time: 0.4979 [2021-03-27 08:26:30 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 310/1251] eta: 0:08:05 lr: 0.000014 loss: 2.6343 (2.7082) grad_norm: 3.1942 (3.3797) time: 0.4991 [2021-03-27 08:26:35 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 320/1251] eta: 0:08:00 lr: 0.000014 loss: 2.6301 (2.7063) grad_norm: 3.2426 (3.3778) time: 0.5125 [2021-03-27 08:26:40 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 330/1251] eta: 0:07:54 lr: 0.000014 loss: 2.6991 (2.7056) grad_norm: 3.2426 (3.3759) time: 0.5139 [2021-03-27 08:26:45 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 340/1251] eta: 0:07:49 lr: 0.000014 loss: 2.7332 (2.7043) grad_norm: 3.1625 (3.3770) time: 0.5083 [2021-03-27 08:26:50 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 350/1251] eta: 0:07:44 lr: 0.000014 loss: 2.6668 (2.7044) grad_norm: 3.0243 (3.3686) time: 0.5140 [2021-03-27 08:26:55 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 360/1251] eta: 0:07:39 lr: 0.000014 loss: 2.7016 (2.7042) grad_norm: 3.0753 (3.3635) time: 0.5108 [2021-03-27 08:27:00 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 370/1251] eta: 0:07:33 lr: 0.000014 loss: 2.7991 (2.7064) grad_norm: 3.1573 (3.3632) time: 0.5029 [2021-03-27 08:27:06 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 380/1251] eta: 0:07:28 lr: 0.000014 loss: 2.9256 (2.7137) grad_norm: 3.5195 (3.3914) time: 0.5001 [2021-03-27 08:27:11 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 390/1251] eta: 0:07:22 lr: 0.000014 loss: 2.9256 (2.7173) grad_norm: 3.3499 (3.3892) time: 0.5061 [2021-03-27 08:27:16 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 400/1251] eta: 0:07:17 lr: 0.000014 loss: 2.8610 (2.7167) grad_norm: 3.3176 (3.3971) time: 0.5068 [2021-03-27 08:27:21 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 410/1251] eta: 0:07:12 lr: 0.000014 loss: 2.8610 (2.7214) grad_norm: 3.3369 (3.3944) time: 0.5047 [2021-03-27 08:27:26 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 420/1251] eta: 0:07:06 lr: 0.000014 loss: 2.8509 (2.7221) grad_norm: 3.3181 (3.3933) time: 0.5037 [2021-03-27 08:27:31 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 430/1251] eta: 0:07:01 lr: 0.000014 loss: 2.7657 (2.7191) grad_norm: 3.2233 (3.3887) time: 0.5053 [2021-03-27 08:27:36 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 440/1251] eta: 0:06:56 lr: 0.000014 loss: 2.7678 (2.7167) grad_norm: 3.2174 (3.3861) time: 0.5016 [2021-03-27 08:27:41 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 450/1251] eta: 0:06:50 lr: 0.000014 loss: 2.8526 (2.7197) grad_norm: 3.2629 (3.3833) time: 0.4991 [2021-03-27 08:27:46 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 460/1251] eta: 0:06:45 lr: 0.000014 loss: 2.9033 (2.7232) grad_norm: 3.2814 (3.3871) time: 0.4995 [2021-03-27 08:27:51 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 470/1251] eta: 0:06:40 lr: 0.000014 loss: 2.8546 (2.7235) grad_norm: 3.2105 (3.3897) time: 0.5041 [2021-03-27 08:27:56 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 480/1251] eta: 0:06:35 lr: 0.000014 loss: 2.8391 (2.7242) grad_norm: 3.1479 (3.3897) time: 0.5089 [2021-03-27 08:28:01 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 490/1251] eta: 0:06:29 lr: 0.000014 loss: 2.7939 (2.7207) grad_norm: 3.1761 (3.3879) time: 0.5026 [2021-03-27 08:28:06 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 500/1251] eta: 0:06:24 lr: 0.000014 loss: 2.7939 (2.7240) grad_norm: 3.2011 (3.3866) time: 0.4958 [2021-03-27 08:28:11 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 510/1251] eta: 0:06:19 lr: 0.000014 loss: 2.8492 (2.7231) grad_norm: 3.0714 (3.3797) time: 0.5009 [2021-03-27 08:28:16 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 520/1251] eta: 0:06:14 lr: 0.000014 loss: 2.4548 (2.7165) grad_norm: 3.1943 (3.3815) time: 0.5107 [2021-03-27 08:28:21 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 530/1251] eta: 0:06:08 lr: 0.000014 loss: 2.5872 (2.7183) grad_norm: 3.2378 (3.3868) time: 0.5137 [2021-03-27 08:28:26 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 540/1251] eta: 0:06:03 lr: 0.000014 loss: 2.7588 (2.7214) grad_norm: 3.2378 (3.3891) time: 0.5099 [2021-03-27 08:28:31 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 550/1251] eta: 0:05:58 lr: 0.000014 loss: 2.9000 (2.7237) grad_norm: 3.1187 (3.3863) time: 0.5124 [2021-03-27 08:28:37 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 560/1251] eta: 0:05:53 lr: 0.000014 loss: 2.8123 (2.7228) grad_norm: 3.1187 (3.3915) time: 0.5205 [2021-03-27 08:28:42 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 570/1251] eta: 0:05:48 lr: 0.000014 loss: 2.6453 (2.7224) grad_norm: 3.1860 (3.3901) time: 0.5138 [2021-03-27 08:28:47 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 580/1251] eta: 0:05:43 lr: 0.000014 loss: 2.7339 (2.7212) grad_norm: 3.1773 (3.3930) time: 0.5044 [2021-03-27 08:28:52 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 590/1251] eta: 0:05:38 lr: 0.000014 loss: 2.7380 (2.7212) grad_norm: 2.9814 (3.3985) time: 0.5066 [2021-03-27 08:28:57 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 600/1251] eta: 0:05:32 lr: 0.000014 loss: 2.9176 (2.7227) grad_norm: 3.1616 (nan) time: 0.5006 [2021-03-27 08:29:02 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 610/1251] eta: 0:05:27 lr: 0.000014 loss: 2.9176 (2.7234) grad_norm: 3.2190 (nan) time: 0.4941 [2021-03-27 08:29:07 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 620/1251] eta: 0:05:22 lr: 0.000014 loss: 2.6759 (2.7215) grad_norm: 3.1814 (nan) time: 0.5005 [2021-03-27 08:29:12 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 630/1251] eta: 0:05:17 lr: 0.000014 loss: 2.6995 (2.7219) grad_norm: 3.0857 (nan) time: 0.5094 [2021-03-27 08:29:17 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 640/1251] eta: 0:05:12 lr: 0.000014 loss: 2.7313 (2.7202) grad_norm: 3.0623 (nan) time: 0.5110 [2021-03-27 08:29:22 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 650/1251] eta: 0:05:07 lr: 0.000014 loss: 2.7661 (2.7205) grad_norm: 3.0458 (nan) time: 0.5070 [2021-03-27 08:29:27 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 660/1251] eta: 0:05:01 lr: 0.000014 loss: 2.9199 (2.7227) grad_norm: 2.9488 (nan) time: 0.5016 [2021-03-27 08:29:32 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 670/1251] eta: 0:04:56 lr: 0.000014 loss: 2.7965 (2.7244) grad_norm: 3.2923 (nan) time: 0.4950 [2021-03-27 08:29:37 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 680/1251] eta: 0:04:51 lr: 0.000014 loss: 2.7425 (2.7241) grad_norm: 3.4097 (nan) time: 0.4963 [2021-03-27 08:29:42 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 690/1251] eta: 0:04:46 lr: 0.000014 loss: 2.7145 (2.7248) grad_norm: 3.2102 (nan) time: 0.4964 [2021-03-27 08:29:47 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 700/1251] eta: 0:04:40 lr: 0.000014 loss: 2.9020 (2.7284) grad_norm: 3.2234 (nan) time: 0.4980 [2021-03-27 08:29:52 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 710/1251] eta: 0:04:35 lr: 0.000014 loss: 2.8484 (2.7269) grad_norm: 3.4052 (nan) time: 0.5067 [2021-03-27 08:29:57 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 720/1251] eta: 0:04:30 lr: 0.000014 loss: 2.6794 (2.7271) grad_norm: 3.3856 (nan) time: 0.5057 [2021-03-27 08:30:02 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 730/1251] eta: 0:04:25 lr: 0.000014 loss: 2.6794 (2.7261) grad_norm: 3.1004 (nan) time: 0.5050 [2021-03-27 08:30:08 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 740/1251] eta: 0:04:20 lr: 0.000014 loss: 2.6409 (2.7255) grad_norm: 3.1382 (nan) time: 0.5228 [2021-03-27 08:30:13 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 750/1251] eta: 0:04:15 lr: 0.000014 loss: 2.6748 (2.7262) grad_norm: 3.3012 (nan) time: 0.5239 [2021-03-27 08:30:18 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 760/1251] eta: 0:04:10 lr: 0.000014 loss: 2.7977 (2.7273) grad_norm: 3.6538 (nan) time: 0.5089 [2021-03-27 08:30:23 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 770/1251] eta: 0:04:05 lr: 0.000014 loss: 2.8473 (2.7274) grad_norm: 3.6535 (nan) time: 0.5040 [2021-03-27 08:30:28 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 780/1251] eta: 0:04:00 lr: 0.000014 loss: 2.8473 (2.7290) grad_norm: 3.2415 (nan) time: 0.5070 [2021-03-27 08:30:33 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 790/1251] eta: 0:03:55 lr: 0.000014 loss: 2.9081 (2.7289) grad_norm: 3.2415 (nan) time: 0.5146 [2021-03-27 08:30:38 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 800/1251] eta: 0:03:49 lr: 0.000014 loss: 2.7347 (2.7291) grad_norm: 3.2702 (nan) time: 0.5062 [2021-03-27 08:30:43 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 810/1251] eta: 0:03:44 lr: 0.000014 loss: 2.7780 (2.7305) grad_norm: 3.1407 (nan) time: 0.4978 [2021-03-27 08:30:48 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 820/1251] eta: 0:03:39 lr: 0.000014 loss: 2.7647 (2.7277) grad_norm: 3.3435 (nan) time: 0.5005 [2021-03-27 08:30:53 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 830/1251] eta: 0:03:34 lr: 0.000014 loss: 2.6070 (2.7255) grad_norm: 3.3138 (nan) time: 0.5014 [2021-03-27 08:30:58 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 840/1251] eta: 0:03:29 lr: 0.000014 loss: 2.5522 (2.7229) grad_norm: 3.0646 (nan) time: 0.4985 [2021-03-27 08:31:03 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 850/1251] eta: 0:03:24 lr: 0.000014 loss: 2.7251 (2.7221) grad_norm: 3.2082 (nan) time: 0.4970 [2021-03-27 08:31:08 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 860/1251] eta: 0:03:19 lr: 0.000014 loss: 2.8235 (2.7207) grad_norm: 3.3759 (nan) time: 0.5011 [2021-03-27 08:31:13 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 870/1251] eta: 0:03:14 lr: 0.000014 loss: 2.7416 (2.7214) grad_norm: 3.4144 (nan) time: 0.5070 [2021-03-27 08:31:18 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 880/1251] eta: 0:03:08 lr: 0.000014 loss: 2.7399 (2.7200) grad_norm: 3.3124 (nan) time: 0.5067 [2021-03-27 08:31:23 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 890/1251] eta: 0:03:03 lr: 0.000014 loss: 2.7491 (2.7215) grad_norm: 3.2476 (nan) time: 0.5035 [2021-03-27 08:31:28 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 900/1251] eta: 0:02:58 lr: 0.000014 loss: 2.8518 (2.7225) grad_norm: 3.2555 (nan) time: 0.4989 [2021-03-27 08:31:33 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 910/1251] eta: 0:02:53 lr: 0.000014 loss: 2.8518 (2.7227) grad_norm: 3.2106 (nan) time: 0.4968 [2021-03-27 08:31:38 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 920/1251] eta: 0:02:48 lr: 0.000014 loss: 2.6249 (2.7213) grad_norm: 3.1968 (nan) time: 0.5015 [2021-03-27 08:31:43 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 930/1251] eta: 0:02:43 lr: 0.000014 loss: 2.7287 (2.7218) grad_norm: 3.2381 (nan) time: 0.5012 [2021-03-27 08:31:48 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 940/1251] eta: 0:02:38 lr: 0.000014 loss: 2.8883 (2.7231) grad_norm: 3.0870 (nan) time: 0.5006 [2021-03-27 08:31:53 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 950/1251] eta: 0:02:33 lr: 0.000014 loss: 2.8013 (2.7213) grad_norm: 3.0515 (nan) time: 0.5053 [2021-03-27 08:31:58 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 960/1251] eta: 0:02:27 lr: 0.000014 loss: 2.3518 (2.7185) grad_norm: 3.2341 (nan) time: 0.5043 [2021-03-27 08:32:03 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 970/1251] eta: 0:02:22 lr: 0.000014 loss: 2.2729 (2.7165) grad_norm: 3.1964 (nan) time: 0.5027 [2021-03-27 08:32:08 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 980/1251] eta: 0:02:17 lr: 0.000014 loss: 2.8087 (2.7171) grad_norm: 3.2341 (nan) time: 0.5016 [2021-03-27 08:32:13 swin_small_patch4_window7_224] INFO: Epoch: [287] [ 990/1251] eta: 0:02:12 lr: 0.000014 loss: 2.8087 (2.7166) grad_norm: 3.3769 (nan) time: 0.4965 [2021-03-27 08:32:18 swin_small_patch4_window7_224] INFO: Epoch: [287] [1000/1251] eta: 0:02:07 lr: 0.000014 loss: 2.6471 (2.7149) grad_norm: 3.4009 (nan) time: 0.5030 [2021-03-27 08:32:23 swin_small_patch4_window7_224] INFO: Epoch: [287] [1010/1251] eta: 0:02:02 lr: 0.000014 loss: 2.5367 (2.7119) grad_norm: 3.3023 (nan) time: 0.5101 [2021-03-27 08:32:29 swin_small_patch4_window7_224] INFO: Epoch: [287] [1020/1251] eta: 0:01:57 lr: 0.000014 loss: 2.5335 (2.7117) grad_norm: 3.2386 (nan) time: 0.5111 [2021-03-27 08:32:34 swin_small_patch4_window7_224] INFO: Epoch: [287] [1030/1251] eta: 0:01:52 lr: 0.000014 loss: 2.6274 (2.7112) grad_norm: 3.3162 (nan) time: 0.5070 [2021-03-27 08:32:39 swin_small_patch4_window7_224] INFO: Epoch: [287] [1040/1251] eta: 0:01:47 lr: 0.000014 loss: 2.6539 (2.7095) grad_norm: 3.3332 (nan) time: 0.4990 [2021-03-27 08:32:44 swin_small_patch4_window7_224] INFO: Epoch: [287] [1050/1251] eta: 0:01:42 lr: 0.000014 loss: 2.7861 (2.7097) grad_norm: 3.1411 (nan) time: 0.5002 [2021-03-27 08:32:49 swin_small_patch4_window7_224] INFO: Epoch: [287] [1060/1251] eta: 0:01:37 lr: 0.000014 loss: 2.7013 (2.7081) grad_norm: 3.0831 (nan) time: 0.5060 [2021-03-27 08:32:54 swin_small_patch4_window7_224] INFO: Epoch: [287] [1070/1251] eta: 0:01:31 lr: 0.000014 loss: 2.6203 (2.7065) grad_norm: 3.0831 (nan) time: 0.5149 [2021-03-27 08:32:59 swin_small_patch4_window7_224] INFO: Epoch: [287] [1080/1251] eta: 0:01:26 lr: 0.000014 loss: 2.7405 (2.7063) grad_norm: 3.4318 (nan) time: 0.5145 [2021-03-27 08:33:04 swin_small_patch4_window7_224] INFO: Epoch: [287] [1090/1251] eta: 0:01:21 lr: 0.000014 loss: 2.7965 (2.7063) grad_norm: 3.4925 (nan) time: 0.5105 [2021-03-27 08:33:09 swin_small_patch4_window7_224] INFO: Epoch: [287] [1100/1251] eta: 0:01:16 lr: 0.000014 loss: 2.6074 (2.7048) grad_norm: 3.3879 (nan) time: 0.5081 [2021-03-27 08:33:14 swin_small_patch4_window7_224] INFO: Epoch: [287] [1110/1251] eta: 0:01:11 lr: 0.000014 loss: 2.5921 (2.7056) grad_norm: 3.3435 (nan) time: 0.5006 [2021-03-27 08:33:19 swin_small_patch4_window7_224] INFO: Epoch: [287] [1120/1251] eta: 0:01:06 lr: 0.000014 loss: 2.7184 (2.7059) grad_norm: 3.2740 (nan) time: 0.5029 [2021-03-27 08:33:24 swin_small_patch4_window7_224] INFO: Epoch: [287] [1130/1251] eta: 0:01:01 lr: 0.000014 loss: 2.7184 (2.7056) grad_norm: 3.1806 (nan) time: 0.5096 [2021-03-27 08:33:29 swin_small_patch4_window7_224] INFO: Epoch: [287] [1140/1251] eta: 0:00:56 lr: 0.000014 loss: 2.7068 (2.7045) grad_norm: 3.1569 (nan) time: 0.5068 [2021-03-27 08:33:34 swin_small_patch4_window7_224] INFO: Epoch: [287] [1150/1251] eta: 0:00:51 lr: 0.000014 loss: 2.7068 (2.7051) grad_norm: 3.3020 (nan) time: 0.5005 [2021-03-27 08:33:39 swin_small_patch4_window7_224] INFO: Epoch: [287] [1160/1251] eta: 0:00:46 lr: 0.000014 loss: 2.9433 (2.7057) grad_norm: 3.2816 (nan) time: 0.4981 [2021-03-27 08:33:44 swin_small_patch4_window7_224] INFO: Epoch: [287] [1170/1251] eta: 0:00:41 lr: 0.000014 loss: 3.0020 (2.7075) grad_norm: 3.2131 (nan) time: 0.5006 [2021-03-27 08:33:49 swin_small_patch4_window7_224] INFO: Epoch: [287] [1180/1251] eta: 0:00:36 lr: 0.000014 loss: 2.8419 (2.7072) grad_norm: 3.2098 (nan) time: 0.5020 [2021-03-27 08:33:54 swin_small_patch4_window7_224] INFO: Epoch: [287] [1190/1251] eta: 0:00:30 lr: 0.000014 loss: 2.7191 (2.7078) grad_norm: 3.2739 (nan) time: 0.4996 [2021-03-27 08:33:59 swin_small_patch4_window7_224] INFO: Epoch: [287] [1200/1251] eta: 0:00:25 lr: 0.000014 loss: 2.8439 (2.7073) grad_norm: 3.2173 (nan) time: 0.4985 [2021-03-27 08:34:04 swin_small_patch4_window7_224] INFO: Epoch: [287] [1210/1251] eta: 0:00:20 lr: 0.000014 loss: 2.7555 (2.7078) grad_norm: 3.0652 (nan) time: 0.4958 [2021-03-27 08:34:09 swin_small_patch4_window7_224] INFO: Epoch: [287] [1220/1251] eta: 0:00:15 lr: 0.000014 loss: 2.7188 (2.7079) grad_norm: 3.1790 (nan) time: 0.4958 [2021-03-27 08:34:14 swin_small_patch4_window7_224] INFO: Epoch: [287] [1230/1251] eta: 0:00:10 lr: 0.000014 loss: 2.7304 (2.7076) grad_norm: 3.2170 (nan) time: 0.4956 [2021-03-27 08:34:19 swin_small_patch4_window7_224] INFO: Epoch: [287] [1240/1251] eta: 0:00:05 lr: 0.000014 loss: 2.8102 (2.7090) grad_norm: 3.2170 (nan) time: 0.5028 [2021-03-27 08:34:24 swin_small_patch4_window7_224] INFO: Epoch: [287] [1250/1251] eta: 0:00:00 lr: 0.000014 loss: 2.8996 (2.7098) grad_norm: 3.3337 (nan) time: 0.5091 [2021-03-27 08:34:33 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:58 loss: 0.7384 (0.7384) acc1: 84.3750 (84.3750) acc5: 96.8750 (96.8750) [2021-03-27 08:34:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7384 (0.8178) acc1: 82.8125 (81.6761) acc5: 95.3125 (95.4545) [2021-03-27 08:34:37 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7203 (0.8029) acc1: 82.8125 (81.5476) acc5: 95.3125 (95.6845) [2021-03-27 08:34:39 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7196 (0.7716) acc1: 82.8125 (82.1069) acc5: 95.3125 (95.8165) [2021-03-27 08:34:41 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7015 (0.7431) acc1: 82.8125 (82.5838) acc5: 96.8750 (96.1128) [2021-03-27 08:34:42 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7015 (0.7589) acc1: 82.8125 (82.3680) acc5: 96.8750 (96.0000) [2021-03-27 08:34:54 swin_small_patch4_window7_224] INFO: * Acc@1 82.982 Acc@5 96.208 loss 0.744 [2021-03-27 08:34:54 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 08:34:54 swin_small_patch4_window7_224] INFO: Max accuracy: 83.06% [2021-03-27 08:34:59 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 0/1251] eta: 1:26:56 lr: 0.000014 loss: 2.6268 (2.6268) grad_norm: 5.3401 (5.3401) time: 4.1695 [2021-03-27 08:35:04 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 10/1251] eta: 0:17:28 lr: 0.000014 loss: 2.6623 (2.7182) grad_norm: 3.2200 (3.4619) time: 0.8451 [2021-03-27 08:35:09 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 20/1251] eta: 0:13:54 lr: 0.000014 loss: 2.7694 (2.6783) grad_norm: 3.3438 (3.5124) time: 0.5032 [2021-03-27 08:35:14 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 30/1251] eta: 0:12:36 lr: 0.000014 loss: 2.9371 (2.7312) grad_norm: 3.3996 (3.5977) time: 0.4956 [2021-03-27 08:35:19 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 40/1251] eta: 0:11:59 lr: 0.000014 loss: 2.7857 (2.7022) grad_norm: 3.3775 (3.6863) time: 0.5068 [2021-03-27 08:35:24 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 50/1251] eta: 0:11:34 lr: 0.000014 loss: 2.6294 (2.6890) grad_norm: 3.3896 (3.6592) time: 0.5136 [2021-03-27 08:35:29 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 60/1251] eta: 0:11:15 lr: 0.000014 loss: 2.5927 (2.6728) grad_norm: 3.1734 (3.6038) time: 0.5108 [2021-03-27 08:35:34 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 70/1251] eta: 0:10:58 lr: 0.000014 loss: 2.6653 (2.6831) grad_norm: 3.0825 (3.5582) time: 0.5051 [2021-03-27 08:35:39 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 80/1251] eta: 0:10:44 lr: 0.000014 loss: 2.6653 (2.6617) grad_norm: 3.0763 (3.5273) time: 0.4992 [2021-03-27 08:35:44 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 90/1251] eta: 0:10:35 lr: 0.000014 loss: 2.6657 (2.6742) grad_norm: 3.1600 (3.5237) time: 0.5096 [2021-03-27 08:35:49 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 100/1251] eta: 0:10:23 lr: 0.000014 loss: 2.7663 (2.6816) grad_norm: 3.2095 (3.4922) time: 0.5074 [2021-03-27 08:35:54 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 110/1251] eta: 0:10:15 lr: 0.000014 loss: 2.8876 (2.6834) grad_norm: 3.1594 (3.4667) time: 0.5027 [2021-03-27 08:35:59 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 120/1251] eta: 0:10:06 lr: 0.000014 loss: 2.9123 (2.6959) grad_norm: 3.1594 (3.4861) time: 0.5078 [2021-03-27 08:36:04 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 130/1251] eta: 0:09:57 lr: 0.000014 loss: 2.8537 (2.6880) grad_norm: 3.0590 (3.4508) time: 0.4999 [2021-03-27 08:36:09 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 140/1251] eta: 0:09:49 lr: 0.000014 loss: 2.7598 (2.6934) grad_norm: 3.1003 (3.4416) time: 0.4962 [2021-03-27 08:36:14 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 150/1251] eta: 0:09:41 lr: 0.000014 loss: 2.8072 (2.7104) grad_norm: 3.1667 (3.4246) time: 0.4987 [2021-03-27 08:36:19 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 160/1251] eta: 0:09:34 lr: 0.000014 loss: 2.8273 (2.7071) grad_norm: 3.0749 (3.4123) time: 0.5025 [2021-03-27 08:36:25 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 170/1251] eta: 0:09:29 lr: 0.000014 loss: 2.7246 (2.7046) grad_norm: 3.1337 (3.4486) time: 0.5181 [2021-03-27 08:36:30 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 180/1251] eta: 0:09:23 lr: 0.000014 loss: 2.6745 (2.7055) grad_norm: 3.1624 (3.4343) time: 0.5175 [2021-03-27 08:36:35 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 190/1251] eta: 0:09:16 lr: 0.000014 loss: 2.5796 (2.6947) grad_norm: 3.0521 (3.4096) time: 0.5028 [2021-03-27 08:36:40 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 200/1251] eta: 0:09:11 lr: 0.000014 loss: 2.5796 (2.7005) grad_norm: 3.0930 (3.4181) time: 0.5100 [2021-03-27 08:36:45 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 210/1251] eta: 0:09:04 lr: 0.000014 loss: 2.8191 (2.7044) grad_norm: 3.2256 (3.4104) time: 0.5100 [2021-03-27 08:36:50 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 220/1251] eta: 0:08:58 lr: 0.000014 loss: 2.7983 (2.7091) grad_norm: 3.3251 (3.4136) time: 0.4987 [2021-03-27 08:36:55 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 230/1251] eta: 0:08:51 lr: 0.000014 loss: 2.7983 (2.7066) grad_norm: 3.3253 (3.4088) time: 0.4953 [2021-03-27 08:37:00 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 240/1251] eta: 0:08:46 lr: 0.000014 loss: 2.7565 (2.7065) grad_norm: 3.0794 (3.4262) time: 0.5055 [2021-03-27 08:37:05 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 250/1251] eta: 0:08:40 lr: 0.000014 loss: 2.7906 (2.7131) grad_norm: 3.1989 (3.4291) time: 0.5127 [2021-03-27 08:37:10 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 260/1251] eta: 0:08:34 lr: 0.000014 loss: 2.8187 (2.7093) grad_norm: 3.2933 (3.4263) time: 0.5048 [2021-03-27 08:37:15 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 270/1251] eta: 0:08:29 lr: 0.000014 loss: 2.6286 (2.7063) grad_norm: 3.0544 (3.4157) time: 0.5069 [2021-03-27 08:37:20 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 280/1251] eta: 0:08:23 lr: 0.000014 loss: 2.8161 (2.7020) grad_norm: 3.1718 (3.4073) time: 0.5109 [2021-03-27 08:37:25 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 290/1251] eta: 0:08:18 lr: 0.000014 loss: 2.7145 (2.7003) grad_norm: 3.2333 (3.4075) time: 0.5105 [2021-03-27 08:37:31 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 300/1251] eta: 0:08:12 lr: 0.000014 loss: 2.7325 (2.7002) grad_norm: 3.2333 (3.4053) time: 0.5100 [2021-03-27 08:37:36 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 310/1251] eta: 0:08:07 lr: 0.000014 loss: 2.6906 (2.6957) grad_norm: 3.2714 (3.4211) time: 0.5119 [2021-03-27 08:37:41 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 320/1251] eta: 0:08:02 lr: 0.000014 loss: 2.6192 (2.6966) grad_norm: 3.3555 (3.4179) time: 0.5151 [2021-03-27 08:37:46 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 330/1251] eta: 0:07:56 lr: 0.000014 loss: 2.8256 (2.6953) grad_norm: 3.1786 (3.4206) time: 0.5084 [2021-03-27 08:37:51 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 340/1251] eta: 0:07:51 lr: 0.000014 loss: 2.8256 (2.6931) grad_norm: 3.2119 (3.4157) time: 0.5008 [2021-03-27 08:37:56 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 350/1251] eta: 0:07:45 lr: 0.000014 loss: 2.6442 (2.6949) grad_norm: 3.2547 (3.4169) time: 0.5003 [2021-03-27 08:38:01 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 360/1251] eta: 0:07:39 lr: 0.000014 loss: 2.7632 (2.6963) grad_norm: 3.2267 (3.4087) time: 0.5013 [2021-03-27 08:38:06 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 370/1251] eta: 0:07:34 lr: 0.000014 loss: 2.8535 (2.6987) grad_norm: 3.2097 (3.4138) time: 0.5032 [2021-03-27 08:38:11 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 380/1251] eta: 0:07:29 lr: 0.000014 loss: 2.7847 (2.6976) grad_norm: 3.3832 (3.4128) time: 0.5044 [2021-03-27 08:38:16 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 390/1251] eta: 0:07:23 lr: 0.000014 loss: 2.7847 (2.6976) grad_norm: 3.2931 (3.4122) time: 0.5028 [2021-03-27 08:38:21 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 400/1251] eta: 0:07:18 lr: 0.000014 loss: 2.7450 (2.6964) grad_norm: 3.2296 (3.4104) time: 0.5047 [2021-03-27 08:38:26 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 410/1251] eta: 0:07:12 lr: 0.000014 loss: 2.7337 (2.6988) grad_norm: 3.1411 (3.4130) time: 0.5045 [2021-03-27 08:38:31 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 420/1251] eta: 0:07:07 lr: 0.000014 loss: 2.7855 (2.7034) grad_norm: 3.2515 (3.4175) time: 0.4990 [2021-03-27 08:38:36 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 430/1251] eta: 0:07:01 lr: 0.000014 loss: 2.9311 (2.7082) grad_norm: 3.5710 (3.4223) time: 0.4953 [2021-03-27 08:38:41 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 440/1251] eta: 0:06:56 lr: 0.000014 loss: 2.8909 (2.7100) grad_norm: 3.4459 (3.4260) time: 0.5049 [2021-03-27 08:38:46 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 450/1251] eta: 0:06:51 lr: 0.000014 loss: 2.7046 (2.7059) grad_norm: 3.3798 (3.4240) time: 0.5103 [2021-03-27 08:38:51 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 460/1251] eta: 0:06:46 lr: 0.000014 loss: 2.6577 (2.7045) grad_norm: 3.3350 (3.4202) time: 0.5109 [2021-03-27 08:38:56 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 470/1251] eta: 0:06:40 lr: 0.000014 loss: 2.7803 (2.7058) grad_norm: 3.3350 (3.4210) time: 0.5076 [2021-03-27 08:39:01 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 480/1251] eta: 0:06:35 lr: 0.000014 loss: 2.8146 (2.7066) grad_norm: 3.1082 (3.4185) time: 0.5022 [2021-03-27 08:39:06 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 490/1251] eta: 0:06:30 lr: 0.000014 loss: 2.9015 (2.7059) grad_norm: 3.3471 (3.4229) time: 0.5043 [2021-03-27 08:39:11 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 500/1251] eta: 0:06:25 lr: 0.000014 loss: 2.7247 (2.7038) grad_norm: 3.3641 (3.4216) time: 0.5020 [2021-03-27 08:39:17 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 510/1251] eta: 0:06:19 lr: 0.000014 loss: 2.6948 (2.7018) grad_norm: 3.2138 (3.4187) time: 0.5065 [2021-03-27 08:39:22 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 520/1251] eta: 0:06:14 lr: 0.000014 loss: 2.7476 (2.7009) grad_norm: 3.2483 (3.4168) time: 0.5068 [2021-03-27 08:39:27 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 530/1251] eta: 0:06:09 lr: 0.000014 loss: 2.8205 (2.7022) grad_norm: 3.3334 (3.4209) time: 0.5022 [2021-03-27 08:39:32 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 540/1251] eta: 0:06:04 lr: 0.000014 loss: 2.7863 (2.7041) grad_norm: 3.3334 (3.4174) time: 0.5022 [2021-03-27 08:39:37 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 550/1251] eta: 0:05:59 lr: 0.000014 loss: 2.7177 (2.7022) grad_norm: 3.1571 (3.4223) time: 0.5148 [2021-03-27 08:39:42 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 560/1251] eta: 0:05:53 lr: 0.000014 loss: 2.5616 (2.7015) grad_norm: 3.1571 (3.4204) time: 0.5108 [2021-03-27 08:39:47 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 570/1251] eta: 0:05:48 lr: 0.000014 loss: 2.6975 (2.7022) grad_norm: 3.1271 (3.4210) time: 0.4972 [2021-03-27 08:39:52 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 580/1251] eta: 0:05:43 lr: 0.000014 loss: 2.8179 (2.7059) grad_norm: 3.3611 (3.4196) time: 0.5027 [2021-03-27 08:39:57 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 590/1251] eta: 0:05:38 lr: 0.000014 loss: 2.7816 (2.7050) grad_norm: 3.3593 (3.4254) time: 0.5012 [2021-03-27 08:40:02 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 600/1251] eta: 0:05:32 lr: 0.000014 loss: 2.7706 (2.7063) grad_norm: 3.2266 (3.4232) time: 0.4976 [2021-03-27 08:40:07 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 610/1251] eta: 0:05:27 lr: 0.000014 loss: 2.8250 (2.7060) grad_norm: 3.1920 (3.4204) time: 0.4948 [2021-03-27 08:40:12 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 620/1251] eta: 0:05:22 lr: 0.000014 loss: 2.8583 (2.7087) grad_norm: 3.0002 (3.4146) time: 0.4950 [2021-03-27 08:40:17 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 630/1251] eta: 0:05:17 lr: 0.000014 loss: 2.9853 (2.7110) grad_norm: 2.9755 (3.4225) time: 0.4990 [2021-03-27 08:40:22 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 640/1251] eta: 0:05:11 lr: 0.000014 loss: 2.9384 (2.7106) grad_norm: 3.4495 (3.4223) time: 0.5020 [2021-03-27 08:40:27 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 650/1251] eta: 0:05:06 lr: 0.000014 loss: 2.8056 (2.7115) grad_norm: 3.1468 (3.4205) time: 0.5044 [2021-03-27 08:40:32 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 660/1251] eta: 0:05:01 lr: 0.000014 loss: 2.8056 (2.7094) grad_norm: 3.0917 (3.4201) time: 0.5037 [2021-03-27 08:40:37 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 670/1251] eta: 0:04:56 lr: 0.000014 loss: 2.7703 (2.7078) grad_norm: 3.2620 (3.4213) time: 0.5000 [2021-03-27 08:40:42 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 680/1251] eta: 0:04:51 lr: 0.000014 loss: 2.7113 (2.7052) grad_norm: 3.4439 (3.4543) time: 0.4965 [2021-03-27 08:40:47 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 690/1251] eta: 0:04:45 lr: 0.000014 loss: 2.7479 (2.7073) grad_norm: 3.1445 (3.4501) time: 0.4982 [2021-03-27 08:40:52 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 700/1251] eta: 0:04:40 lr: 0.000014 loss: 2.8065 (2.7040) grad_norm: 2.9411 (3.4464) time: 0.5013 [2021-03-27 08:40:57 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 710/1251] eta: 0:04:35 lr: 0.000014 loss: 2.8025 (2.7057) grad_norm: 3.2437 (3.4473) time: 0.4964 [2021-03-27 08:41:02 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 720/1251] eta: 0:04:30 lr: 0.000014 loss: 2.8025 (2.7039) grad_norm: 3.2564 (3.4434) time: 0.4996 [2021-03-27 08:41:07 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 730/1251] eta: 0:04:25 lr: 0.000014 loss: 2.8698 (2.7063) grad_norm: 3.2648 (3.4413) time: 0.5145 [2021-03-27 08:41:12 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 740/1251] eta: 0:04:20 lr: 0.000014 loss: 2.8459 (2.7039) grad_norm: 3.4037 (3.4424) time: 0.5266 [2021-03-27 08:41:17 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 750/1251] eta: 0:04:15 lr: 0.000014 loss: 2.7620 (2.7050) grad_norm: 3.4428 (3.4438) time: 0.5183 [2021-03-27 08:41:23 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 760/1251] eta: 0:04:10 lr: 0.000014 loss: 2.7598 (2.7055) grad_norm: 3.2246 (3.4411) time: 0.5102 [2021-03-27 08:41:28 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 770/1251] eta: 0:04:05 lr: 0.000014 loss: 2.7116 (2.7034) grad_norm: 3.2380 (3.4399) time: 0.5122 [2021-03-27 08:41:33 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 780/1251] eta: 0:04:00 lr: 0.000014 loss: 2.7178 (2.7058) grad_norm: 3.3266 (3.4386) time: 0.5111 [2021-03-27 08:41:38 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 790/1251] eta: 0:03:55 lr: 0.000014 loss: 2.7745 (2.7066) grad_norm: 3.3266 (3.4408) time: 0.5075 [2021-03-27 08:41:43 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 800/1251] eta: 0:03:49 lr: 0.000013 loss: 2.7300 (2.7038) grad_norm: 3.4406 (3.4439) time: 0.5032 [2021-03-27 08:41:48 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 810/1251] eta: 0:03:44 lr: 0.000013 loss: 2.4539 (2.7028) grad_norm: 3.2214 (3.4401) time: 0.5031 [2021-03-27 08:41:53 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 820/1251] eta: 0:03:39 lr: 0.000013 loss: 2.8897 (2.7031) grad_norm: 3.0955 (3.4369) time: 0.5025 [2021-03-27 08:41:58 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 830/1251] eta: 0:03:34 lr: 0.000013 loss: 2.7859 (2.7032) grad_norm: 3.0832 (3.4333) time: 0.5008 [2021-03-27 08:42:03 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 840/1251] eta: 0:03:29 lr: 0.000013 loss: 2.7837 (2.7042) grad_norm: 3.1108 (3.4305) time: 0.5062 [2021-03-27 08:42:08 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 850/1251] eta: 0:03:24 lr: 0.000013 loss: 2.8239 (2.7031) grad_norm: 3.1053 (3.4272) time: 0.5090 [2021-03-27 08:42:13 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 860/1251] eta: 0:03:19 lr: 0.000013 loss: 2.7164 (2.7034) grad_norm: 3.1053 (3.4353) time: 0.5081 [2021-03-27 08:42:18 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 870/1251] eta: 0:03:14 lr: 0.000013 loss: 2.7547 (2.7054) grad_norm: 3.2353 (3.4370) time: 0.5063 [2021-03-27 08:42:23 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 880/1251] eta: 0:03:08 lr: 0.000013 loss: 2.6469 (2.7048) grad_norm: 3.4817 (3.4373) time: 0.4990 [2021-03-27 08:42:28 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 890/1251] eta: 0:03:03 lr: 0.000013 loss: 2.7319 (2.7070) grad_norm: 3.3748 (3.4419) time: 0.5010 [2021-03-27 08:42:33 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 900/1251] eta: 0:02:58 lr: 0.000013 loss: 2.8680 (2.7058) grad_norm: 3.2431 (3.4405) time: 0.5031 [2021-03-27 08:42:38 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 910/1251] eta: 0:02:53 lr: 0.000013 loss: 2.8242 (2.7082) grad_norm: 3.2431 (3.4476) time: 0.5071 [2021-03-27 08:42:44 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 920/1251] eta: 0:02:48 lr: 0.000013 loss: 2.9392 (2.7100) grad_norm: 3.3210 (3.4500) time: 0.5135 [2021-03-27 08:42:49 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 930/1251] eta: 0:02:43 lr: 0.000013 loss: 2.8801 (2.7101) grad_norm: 3.3079 (3.4498) time: 0.5045 [2021-03-27 08:42:54 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 940/1251] eta: 0:02:38 lr: 0.000013 loss: 2.7444 (2.7106) grad_norm: 3.2569 (3.4486) time: 0.5017 [2021-03-27 08:42:59 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 950/1251] eta: 0:02:33 lr: 0.000013 loss: 2.7074 (2.7102) grad_norm: 3.3474 (3.4494) time: 0.5081 [2021-03-27 08:43:04 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 960/1251] eta: 0:02:28 lr: 0.000013 loss: 2.7074 (2.7085) grad_norm: 3.1441 (3.4465) time: 0.5068 [2021-03-27 08:43:09 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 970/1251] eta: 0:02:22 lr: 0.000013 loss: 2.4292 (2.7070) grad_norm: 3.1441 (3.4456) time: 0.4983 [2021-03-27 08:43:14 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 980/1251] eta: 0:02:17 lr: 0.000013 loss: 2.5436 (2.7050) grad_norm: 3.0696 (3.4432) time: 0.4948 [2021-03-27 08:43:19 swin_small_patch4_window7_224] INFO: Epoch: [288] [ 990/1251] eta: 0:02:12 lr: 0.000013 loss: 2.5436 (2.7035) grad_norm: 3.0481 (3.4410) time: 0.5034 [2021-03-27 08:43:24 swin_small_patch4_window7_224] INFO: Epoch: [288] [1000/1251] eta: 0:02:07 lr: 0.000013 loss: 2.2573 (2.7000) grad_norm: 3.1074 (3.4419) time: 0.5011 [2021-03-27 08:43:29 swin_small_patch4_window7_224] INFO: Epoch: [288] [1010/1251] eta: 0:02:02 lr: 0.000013 loss: 2.5135 (2.6996) grad_norm: 3.3030 (3.4417) time: 0.5021 [2021-03-27 08:43:34 swin_small_patch4_window7_224] INFO: Epoch: [288] [1020/1251] eta: 0:01:57 lr: 0.000013 loss: 2.5135 (2.6980) grad_norm: 3.3030 (3.4404) time: 0.5025 [2021-03-27 08:43:39 swin_small_patch4_window7_224] INFO: Epoch: [288] [1030/1251] eta: 0:01:52 lr: 0.000013 loss: 2.7840 (2.6995) grad_norm: 3.3761 (3.4418) time: 0.4966 [2021-03-27 08:43:44 swin_small_patch4_window7_224] INFO: Epoch: [288] [1040/1251] eta: 0:01:47 lr: 0.000013 loss: 2.8519 (2.6993) grad_norm: 3.3136 (3.4438) time: 0.5084 [2021-03-27 08:43:49 swin_small_patch4_window7_224] INFO: Epoch: [288] [1050/1251] eta: 0:01:42 lr: 0.000013 loss: 2.8257 (2.6978) grad_norm: 3.0423 (3.4400) time: 0.5085 [2021-03-27 08:43:54 swin_small_patch4_window7_224] INFO: Epoch: [288] [1060/1251] eta: 0:01:37 lr: 0.000013 loss: 2.6849 (2.6966) grad_norm: 3.0423 (3.4401) time: 0.4993 [2021-03-27 08:43:59 swin_small_patch4_window7_224] INFO: Epoch: [288] [1070/1251] eta: 0:01:31 lr: 0.000013 loss: 2.7855 (2.6978) grad_norm: 3.3019 (3.4402) time: 0.5038 [2021-03-27 08:44:04 swin_small_patch4_window7_224] INFO: Epoch: [288] [1080/1251] eta: 0:01:26 lr: 0.000013 loss: 2.7577 (2.6974) grad_norm: 3.2757 (3.4395) time: 0.5031 [2021-03-27 08:44:09 swin_small_patch4_window7_224] INFO: Epoch: [288] [1090/1251] eta: 0:01:21 lr: 0.000013 loss: 2.6635 (2.6986) grad_norm: 3.2757 (3.4411) time: 0.4996 [2021-03-27 08:44:14 swin_small_patch4_window7_224] INFO: Epoch: [288] [1100/1251] eta: 0:01:16 lr: 0.000013 loss: 2.7249 (2.6990) grad_norm: 3.3885 (3.4414) time: 0.4997 [2021-03-27 08:44:19 swin_small_patch4_window7_224] INFO: Epoch: [288] [1110/1251] eta: 0:01:11 lr: 0.000013 loss: 2.6674 (2.6978) grad_norm: 3.3281 (3.4395) time: 0.5003 [2021-03-27 08:44:24 swin_small_patch4_window7_224] INFO: Epoch: [288] [1120/1251] eta: 0:01:06 lr: 0.000013 loss: 2.6674 (2.6973) grad_norm: 3.1867 (3.4429) time: 0.5023 [2021-03-27 08:44:29 swin_small_patch4_window7_224] INFO: Epoch: [288] [1130/1251] eta: 0:01:01 lr: 0.000013 loss: 2.9798 (2.6979) grad_norm: 3.1604 (3.4400) time: 0.5032 [2021-03-27 08:44:34 swin_small_patch4_window7_224] INFO: Epoch: [288] [1140/1251] eta: 0:00:56 lr: 0.000013 loss: 2.7455 (2.6967) grad_norm: 3.1716 (3.4469) time: 0.5027 [2021-03-27 08:44:39 swin_small_patch4_window7_224] INFO: Epoch: [288] [1150/1251] eta: 0:00:51 lr: 0.000013 loss: 2.5977 (2.6948) grad_norm: 3.3409 (3.4691) time: 0.5055 [2021-03-27 08:44:44 swin_small_patch4_window7_224] INFO: Epoch: [288] [1160/1251] eta: 0:00:46 lr: 0.000013 loss: 2.6284 (2.6938) grad_norm: 3.3409 (3.4694) time: 0.5023 [2021-03-27 08:44:49 swin_small_patch4_window7_224] INFO: Epoch: [288] [1170/1251] eta: 0:00:41 lr: 0.000013 loss: 2.6827 (2.6944) grad_norm: 3.2878 (3.4679) time: 0.5031 [2021-03-27 08:44:54 swin_small_patch4_window7_224] INFO: Epoch: [288] [1180/1251] eta: 0:00:36 lr: 0.000013 loss: 2.8030 (2.6959) grad_norm: 3.1269 (3.4653) time: 0.5025 [2021-03-27 08:44:59 swin_small_patch4_window7_224] INFO: Epoch: [288] [1190/1251] eta: 0:00:30 lr: 0.000013 loss: 2.8030 (2.6963) grad_norm: 3.1186 (3.4629) time: 0.5001 [2021-03-27 08:45:04 swin_small_patch4_window7_224] INFO: Epoch: [288] [1200/1251] eta: 0:00:25 lr: 0.000013 loss: 2.8662 (2.6984) grad_norm: 3.1455 (3.4626) time: 0.5046 [2021-03-27 08:45:09 swin_small_patch4_window7_224] INFO: Epoch: [288] [1210/1251] eta: 0:00:20 lr: 0.000013 loss: 2.8871 (2.6997) grad_norm: 3.2661 (3.4616) time: 0.5036 [2021-03-27 08:45:14 swin_small_patch4_window7_224] INFO: Epoch: [288] [1220/1251] eta: 0:00:15 lr: 0.000013 loss: 2.7932 (2.7001) grad_norm: 3.2446 (3.4595) time: 0.5029 [2021-03-27 08:45:19 swin_small_patch4_window7_224] INFO: Epoch: [288] [1230/1251] eta: 0:00:10 lr: 0.000013 loss: 2.7577 (2.7000) grad_norm: 3.1445 (3.4597) time: 0.4973 [2021-03-27 08:45:24 swin_small_patch4_window7_224] INFO: Epoch: [288] [1240/1251] eta: 0:00:05 lr: 0.000013 loss: 2.7738 (2.7015) grad_norm: 3.2173 (3.4631) time: 0.4939 [2021-03-27 08:45:29 swin_small_patch4_window7_224] INFO: Epoch: [288] [1250/1251] eta: 0:00:00 lr: 0.000013 loss: 2.8325 (2.7006) grad_norm: 3.3348 (3.4808) time: 0.4916 [2021-03-27 08:45:39 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:55 loss: 0.5727 (0.5727) acc1: 84.3750 (84.3750) acc5: 98.4375 (98.4375) [2021-03-27 08:45:41 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:17 loss: 0.7326 (0.7218) acc1: 82.8125 (82.2443) acc5: 96.8750 (96.4489) [2021-03-27 08:45:44 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7326 (0.7341) acc1: 81.2500 (82.2173) acc5: 96.8750 (95.6101) [2021-03-27 08:45:47 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7165 (0.7374) acc1: 81.2500 (82.6109) acc5: 95.3125 (95.5645) [2021-03-27 08:45:48 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7568 (0.7496) acc1: 81.2500 (82.2409) acc5: 96.8750 (95.7698) [2021-03-27 08:45:49 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7762 (0.7497) acc1: 81.2500 (82.3040) acc5: 96.8750 (95.9360) [2021-03-27 08:46:01 swin_small_patch4_window7_224] INFO: * Acc@1 83.162 Acc@5 96.212 loss 0.736 [2021-03-27 08:46:01 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-27 08:46:01 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 08:46:06 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 0/1251] eta: 1:44:30 lr: 0.000013 loss: 2.6161 (2.6161) grad_norm: 3.4019 (3.4019) time: 5.0127 [2021-03-27 08:46:11 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 10/1251] eta: 0:18:43 lr: 0.000013 loss: 2.6161 (2.7013) grad_norm: 3.3094 (3.2787) time: 0.9054 [2021-03-27 08:46:16 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 20/1251] eta: 0:14:36 lr: 0.000013 loss: 2.8621 (2.7058) grad_norm: 3.3094 (3.2955) time: 0.4968 [2021-03-27 08:46:21 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 30/1251] eta: 0:13:07 lr: 0.000013 loss: 2.7585 (2.6480) grad_norm: 3.2492 (3.2564) time: 0.5023 [2021-03-27 08:46:26 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 40/1251] eta: 0:12:22 lr: 0.000013 loss: 2.5030 (2.6051) grad_norm: 3.1186 (3.2700) time: 0.5103 [2021-03-27 08:46:31 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 50/1251] eta: 0:11:49 lr: 0.000013 loss: 2.3709 (2.5725) grad_norm: 3.1275 (3.2408) time: 0.5052 [2021-03-27 08:46:36 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 60/1251] eta: 0:11:26 lr: 0.000013 loss: 2.5997 (2.5883) grad_norm: 3.0868 (3.2226) time: 0.5000 [2021-03-27 08:46:41 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 70/1251] eta: 0:11:10 lr: 0.000013 loss: 2.8088 (2.6079) grad_norm: 2.9980 (3.3617) time: 0.5086 [2021-03-27 08:46:46 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 80/1251] eta: 0:10:54 lr: 0.000013 loss: 2.7503 (2.6242) grad_norm: 3.3078 (3.3896) time: 0.5075 [2021-03-27 08:46:51 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 90/1251] eta: 0:10:41 lr: 0.000013 loss: 2.7503 (2.6057) grad_norm: 3.3607 (3.4095) time: 0.5017 [2021-03-27 08:46:56 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 100/1251] eta: 0:10:31 lr: 0.000013 loss: 2.6858 (2.6113) grad_norm: 3.2306 (3.3852) time: 0.5056 [2021-03-27 08:47:01 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 110/1251] eta: 0:10:22 lr: 0.000013 loss: 2.7154 (2.6218) grad_norm: 3.2288 (3.4172) time: 0.5117 [2021-03-27 08:47:06 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 120/1251] eta: 0:10:13 lr: 0.000013 loss: 2.8075 (2.6206) grad_norm: 3.3314 (3.4139) time: 0.5085 [2021-03-27 08:47:11 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 130/1251] eta: 0:10:05 lr: 0.000013 loss: 2.8075 (2.6147) grad_norm: 3.2074 (3.3943) time: 0.5090 [2021-03-27 08:47:17 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 140/1251] eta: 0:09:57 lr: 0.000013 loss: 2.7882 (2.6342) grad_norm: 3.1915 (3.3741) time: 0.5141 [2021-03-27 08:47:22 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 150/1251] eta: 0:09:49 lr: 0.000013 loss: 2.7660 (2.6304) grad_norm: 3.0453 (3.3605) time: 0.5078 [2021-03-27 08:47:27 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 160/1251] eta: 0:09:41 lr: 0.000013 loss: 2.7605 (2.6330) grad_norm: 3.1806 (3.3552) time: 0.4987 [2021-03-27 08:47:32 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 170/1251] eta: 0:09:34 lr: 0.000013 loss: 2.8596 (2.6404) grad_norm: 3.1728 (3.3429) time: 0.4984 [2021-03-27 08:47:37 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 180/1251] eta: 0:09:28 lr: 0.000013 loss: 2.9501 (2.6442) grad_norm: 3.1307 (3.3776) time: 0.5104 [2021-03-27 08:47:42 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 190/1251] eta: 0:09:21 lr: 0.000013 loss: 2.6829 (2.6470) grad_norm: 3.2036 (3.3829) time: 0.5140 [2021-03-27 08:47:47 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 200/1251] eta: 0:09:15 lr: 0.000013 loss: 2.6360 (2.6459) grad_norm: 3.3330 (3.3877) time: 0.5117 [2021-03-27 08:47:52 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 210/1251] eta: 0:09:09 lr: 0.000013 loss: 2.7566 (2.6487) grad_norm: 3.2094 (3.3864) time: 0.5112 [2021-03-27 08:47:57 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 220/1251] eta: 0:09:03 lr: 0.000013 loss: 2.8255 (2.6596) grad_norm: 3.2063 (3.3850) time: 0.5079 [2021-03-27 08:48:02 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 230/1251] eta: 0:08:56 lr: 0.000013 loss: 2.9024 (2.6705) grad_norm: 3.0756 (3.3696) time: 0.5065 [2021-03-27 08:48:07 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 240/1251] eta: 0:08:50 lr: 0.000013 loss: 2.8491 (2.6762) grad_norm: 3.1025 (3.3827) time: 0.5012 [2021-03-27 08:48:12 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 250/1251] eta: 0:08:44 lr: 0.000013 loss: 2.7980 (2.6753) grad_norm: 3.5819 (3.3927) time: 0.4979 [2021-03-27 08:48:17 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 260/1251] eta: 0:08:38 lr: 0.000013 loss: 2.5987 (2.6737) grad_norm: 3.5199 (3.4026) time: 0.5066 [2021-03-27 08:48:22 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 270/1251] eta: 0:08:32 lr: 0.000013 loss: 2.5024 (2.6683) grad_norm: 3.2741 (3.4033) time: 0.5098 [2021-03-27 08:48:27 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 280/1251] eta: 0:08:26 lr: 0.000013 loss: 2.4902 (2.6718) grad_norm: 3.1248 (3.3931) time: 0.5027 [2021-03-27 08:48:32 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 290/1251] eta: 0:08:20 lr: 0.000013 loss: 2.7006 (2.6758) grad_norm: 3.1335 (3.3944) time: 0.5029 [2021-03-27 08:48:38 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 300/1251] eta: 0:08:15 lr: 0.000013 loss: 2.8982 (2.6822) grad_norm: 3.3407 (3.4022) time: 0.5066 [2021-03-27 08:48:43 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 310/1251] eta: 0:08:09 lr: 0.000013 loss: 2.7899 (2.6785) grad_norm: 3.1841 (3.4146) time: 0.5059 [2021-03-27 08:48:48 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 320/1251] eta: 0:08:03 lr: 0.000013 loss: 2.6458 (2.6764) grad_norm: 3.1585 (3.4095) time: 0.5019 [2021-03-27 08:48:53 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 330/1251] eta: 0:07:58 lr: 0.000013 loss: 2.6604 (2.6799) grad_norm: 3.3857 (3.4191) time: 0.5095 [2021-03-27 08:48:58 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 340/1251] eta: 0:07:52 lr: 0.000013 loss: 2.7809 (2.6785) grad_norm: 3.5029 (3.4232) time: 0.5099 [2021-03-27 08:49:03 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 350/1251] eta: 0:07:47 lr: 0.000013 loss: 2.7809 (2.6784) grad_norm: 3.4577 (3.4351) time: 0.5017 [2021-03-27 08:49:08 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 360/1251] eta: 0:07:41 lr: 0.000013 loss: 2.7550 (2.6763) grad_norm: 3.4066 (3.4342) time: 0.5018 [2021-03-27 08:49:13 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 370/1251] eta: 0:07:36 lr: 0.000013 loss: 2.7550 (2.6794) grad_norm: 3.4256 (3.4441) time: 0.5056 [2021-03-27 08:49:18 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 380/1251] eta: 0:07:30 lr: 0.000013 loss: 2.7597 (2.6757) grad_norm: 3.3015 (3.4391) time: 0.5084 [2021-03-27 08:49:23 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 390/1251] eta: 0:07:25 lr: 0.000013 loss: 2.8467 (2.6779) grad_norm: 3.1843 (3.4354) time: 0.5062 [2021-03-27 08:49:28 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 400/1251] eta: 0:07:20 lr: 0.000013 loss: 2.8869 (2.6775) grad_norm: 3.1994 (3.4326) time: 0.5100 [2021-03-27 08:49:33 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 410/1251] eta: 0:07:14 lr: 0.000013 loss: 2.7863 (2.6776) grad_norm: 3.1280 (3.4300) time: 0.5051 [2021-03-27 08:49:38 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 420/1251] eta: 0:07:09 lr: 0.000013 loss: 2.7361 (2.6732) grad_norm: 3.0492 (3.4193) time: 0.5009 [2021-03-27 08:49:43 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 430/1251] eta: 0:07:03 lr: 0.000013 loss: 2.5930 (2.6742) grad_norm: 3.0187 (3.4179) time: 0.5070 [2021-03-27 08:49:48 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 440/1251] eta: 0:06:58 lr: 0.000013 loss: 2.5715 (2.6720) grad_norm: 3.3554 (3.4181) time: 0.5066 [2021-03-27 08:49:53 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 450/1251] eta: 0:06:53 lr: 0.000013 loss: 2.5991 (2.6739) grad_norm: 3.2881 (3.4173) time: 0.5087 [2021-03-27 08:49:58 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 460/1251] eta: 0:06:47 lr: 0.000013 loss: 2.8488 (2.6728) grad_norm: 3.2881 (3.4195) time: 0.5080 [2021-03-27 08:50:04 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 470/1251] eta: 0:06:42 lr: 0.000013 loss: 2.7554 (2.6771) grad_norm: 3.4338 (3.4243) time: 0.5072 [2021-03-27 08:50:09 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 480/1251] eta: 0:06:37 lr: 0.000013 loss: 2.8835 (2.6795) grad_norm: 3.4338 (3.4229) time: 0.5047 [2021-03-27 08:50:13 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 490/1251] eta: 0:06:31 lr: 0.000013 loss: 2.6084 (2.6738) grad_norm: 3.1732 (nan) time: 0.4946 [2021-03-27 08:50:18 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 500/1251] eta: 0:06:26 lr: 0.000013 loss: 2.8078 (2.6795) grad_norm: 3.2780 (nan) time: 0.4914 [2021-03-27 08:50:23 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 510/1251] eta: 0:06:20 lr: 0.000013 loss: 2.8924 (2.6803) grad_norm: 3.2957 (nan) time: 0.4934 [2021-03-27 08:50:28 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 520/1251] eta: 0:06:15 lr: 0.000013 loss: 2.8164 (2.6822) grad_norm: 3.2598 (nan) time: 0.5020 [2021-03-27 08:50:33 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 530/1251] eta: 0:06:10 lr: 0.000013 loss: 2.8042 (2.6808) grad_norm: 3.1604 (nan) time: 0.5053 [2021-03-27 08:50:39 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 540/1251] eta: 0:06:05 lr: 0.000013 loss: 2.7455 (2.6823) grad_norm: 3.3103 (nan) time: 0.5090 [2021-03-27 08:50:44 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 550/1251] eta: 0:06:00 lr: 0.000013 loss: 2.7195 (2.6846) grad_norm: 3.3027 (nan) time: 0.5172 [2021-03-27 08:50:49 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 560/1251] eta: 0:05:54 lr: 0.000013 loss: 2.7624 (2.6844) grad_norm: 3.2121 (nan) time: 0.5127 [2021-03-27 08:50:54 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 570/1251] eta: 0:05:49 lr: 0.000013 loss: 2.6442 (2.6838) grad_norm: 3.2121 (nan) time: 0.5069 [2021-03-27 08:50:59 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 580/1251] eta: 0:05:44 lr: 0.000013 loss: 2.9319 (2.6865) grad_norm: 3.2704 (nan) time: 0.5033 [2021-03-27 08:51:04 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 590/1251] eta: 0:05:39 lr: 0.000013 loss: 2.9360 (2.6876) grad_norm: 3.3813 (nan) time: 0.5039 [2021-03-27 08:51:09 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 600/1251] eta: 0:05:34 lr: 0.000013 loss: 2.8174 (2.6858) grad_norm: 3.1351 (nan) time: 0.5084 [2021-03-27 08:51:14 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 610/1251] eta: 0:05:28 lr: 0.000013 loss: 2.7591 (2.6871) grad_norm: 3.3470 (nan) time: 0.5083 [2021-03-27 08:51:19 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 620/1251] eta: 0:05:23 lr: 0.000013 loss: 2.7591 (2.6867) grad_norm: 3.4070 (nan) time: 0.5033 [2021-03-27 08:51:24 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 630/1251] eta: 0:05:18 lr: 0.000013 loss: 2.4049 (2.6814) grad_norm: 3.3150 (nan) time: 0.5002 [2021-03-27 08:51:29 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 640/1251] eta: 0:05:13 lr: 0.000013 loss: 2.4049 (2.6805) grad_norm: 3.5035 (nan) time: 0.4988 [2021-03-27 08:51:34 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 650/1251] eta: 0:05:07 lr: 0.000013 loss: 2.5598 (2.6797) grad_norm: 3.3880 (nan) time: 0.4987 [2021-03-27 08:51:39 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 660/1251] eta: 0:05:02 lr: 0.000013 loss: 2.7877 (2.6807) grad_norm: 3.2888 (nan) time: 0.5003 [2021-03-27 08:51:44 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 670/1251] eta: 0:04:57 lr: 0.000013 loss: 2.8081 (2.6823) grad_norm: 3.3101 (nan) time: 0.5019 [2021-03-27 08:51:49 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 680/1251] eta: 0:04:52 lr: 0.000013 loss: 2.7608 (2.6802) grad_norm: 3.2248 (nan) time: 0.5006 [2021-03-27 08:51:54 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 690/1251] eta: 0:04:47 lr: 0.000013 loss: 2.7608 (2.6811) grad_norm: 3.1125 (nan) time: 0.5065 [2021-03-27 08:51:59 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 700/1251] eta: 0:04:41 lr: 0.000013 loss: 2.7991 (2.6814) grad_norm: 3.2626 (nan) time: 0.5098 [2021-03-27 08:52:05 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 710/1251] eta: 0:04:36 lr: 0.000013 loss: 2.6999 (2.6797) grad_norm: 3.2626 (nan) time: 0.5098 [2021-03-27 08:52:10 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 720/1251] eta: 0:04:31 lr: 0.000013 loss: 2.5587 (2.6802) grad_norm: 3.2699 (nan) time: 0.5100 [2021-03-27 08:52:15 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 730/1251] eta: 0:04:26 lr: 0.000013 loss: 2.8342 (2.6818) grad_norm: 3.2489 (nan) time: 0.5037 [2021-03-27 08:52:20 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 740/1251] eta: 0:04:21 lr: 0.000013 loss: 2.7773 (2.6806) grad_norm: 3.1045 (nan) time: 0.5067 [2021-03-27 08:52:25 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 750/1251] eta: 0:04:16 lr: 0.000013 loss: 2.8121 (2.6822) grad_norm: 3.4042 (nan) time: 0.5120 [2021-03-27 08:52:30 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 760/1251] eta: 0:04:11 lr: 0.000013 loss: 2.9658 (2.6842) grad_norm: 3.2925 (nan) time: 0.5084 [2021-03-27 08:52:35 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 770/1251] eta: 0:04:05 lr: 0.000013 loss: 2.7759 (2.6813) grad_norm: 3.2528 (nan) time: 0.5092 [2021-03-27 08:52:40 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 780/1251] eta: 0:04:00 lr: 0.000013 loss: 2.7897 (2.6838) grad_norm: 3.2528 (nan) time: 0.5126 [2021-03-27 08:52:45 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 790/1251] eta: 0:03:55 lr: 0.000013 loss: 2.8565 (2.6823) grad_norm: 3.2976 (nan) time: 0.5140 [2021-03-27 08:52:50 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 800/1251] eta: 0:03:50 lr: 0.000013 loss: 2.5145 (2.6814) grad_norm: 3.3618 (nan) time: 0.5131 [2021-03-27 08:52:55 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 810/1251] eta: 0:03:45 lr: 0.000013 loss: 2.8386 (2.6835) grad_norm: 3.1940 (nan) time: 0.4998 [2021-03-27 08:53:00 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 820/1251] eta: 0:03:40 lr: 0.000013 loss: 2.8637 (2.6851) grad_norm: 3.1599 (nan) time: 0.4970 [2021-03-27 08:53:05 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 830/1251] eta: 0:03:35 lr: 0.000013 loss: 2.7010 (2.6836) grad_norm: 3.2793 (nan) time: 0.5009 [2021-03-27 08:53:11 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 840/1251] eta: 0:03:30 lr: 0.000013 loss: 2.5685 (2.6822) grad_norm: 3.3058 (nan) time: 0.5070 [2021-03-27 08:53:16 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 850/1251] eta: 0:03:24 lr: 0.000013 loss: 2.6891 (2.6837) grad_norm: 3.4274 (nan) time: 0.5130 [2021-03-27 08:53:21 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 860/1251] eta: 0:03:19 lr: 0.000013 loss: 2.8590 (2.6864) grad_norm: 3.4274 (nan) time: 0.5051 [2021-03-27 08:53:26 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 870/1251] eta: 0:03:14 lr: 0.000013 loss: 2.7989 (2.6861) grad_norm: 3.2811 (nan) time: 0.5107 [2021-03-27 08:53:31 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 880/1251] eta: 0:03:09 lr: 0.000013 loss: 2.6951 (2.6868) grad_norm: 3.2811 (nan) time: 0.5205 [2021-03-27 08:53:36 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 890/1251] eta: 0:03:04 lr: 0.000013 loss: 2.7256 (2.6872) grad_norm: 3.2342 (nan) time: 0.5086 [2021-03-27 08:53:41 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 900/1251] eta: 0:02:59 lr: 0.000013 loss: 2.6613 (2.6854) grad_norm: 3.2341 (nan) time: 0.5038 [2021-03-27 08:53:46 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 910/1251] eta: 0:02:54 lr: 0.000013 loss: 2.6661 (2.6849) grad_norm: 3.1610 (nan) time: 0.5069 [2021-03-27 08:53:51 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 920/1251] eta: 0:02:49 lr: 0.000013 loss: 2.8366 (2.6878) grad_norm: 3.1610 (nan) time: 0.5103 [2021-03-27 08:53:56 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 930/1251] eta: 0:02:43 lr: 0.000013 loss: 2.9922 (2.6905) grad_norm: 3.2246 (nan) time: 0.5135 [2021-03-27 08:54:02 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 940/1251] eta: 0:02:38 lr: 0.000013 loss: 2.9295 (2.6909) grad_norm: 3.2733 (nan) time: 0.5132 [2021-03-27 08:54:07 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 950/1251] eta: 0:02:33 lr: 0.000013 loss: 2.7911 (2.6918) grad_norm: 3.2103 (nan) time: 0.5090 [2021-03-27 08:54:12 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 960/1251] eta: 0:02:28 lr: 0.000013 loss: 2.7443 (2.6893) grad_norm: 3.0581 (nan) time: 0.5068 [2021-03-27 08:54:17 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 970/1251] eta: 0:02:23 lr: 0.000013 loss: 2.6765 (2.6891) grad_norm: 3.1375 (nan) time: 0.5071 [2021-03-27 08:54:22 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 980/1251] eta: 0:02:18 lr: 0.000013 loss: 2.8548 (2.6899) grad_norm: 3.2854 (nan) time: 0.5018 [2021-03-27 08:54:27 swin_small_patch4_window7_224] INFO: Epoch: [289] [ 990/1251] eta: 0:02:13 lr: 0.000013 loss: 2.9102 (2.6902) grad_norm: 3.2743 (nan) time: 0.4993 [2021-03-27 08:54:32 swin_small_patch4_window7_224] INFO: Epoch: [289] [1000/1251] eta: 0:02:08 lr: 0.000013 loss: 2.7177 (2.6896) grad_norm: 3.2672 (nan) time: 0.5010 [2021-03-27 08:54:37 swin_small_patch4_window7_224] INFO: Epoch: [289] [1010/1251] eta: 0:02:03 lr: 0.000013 loss: 2.7177 (2.6901) grad_norm: 3.1301 (nan) time: 0.5039 [2021-03-27 08:54:42 swin_small_patch4_window7_224] INFO: Epoch: [289] [1020/1251] eta: 0:01:57 lr: 0.000013 loss: 2.6950 (2.6902) grad_norm: 3.1482 (nan) time: 0.5039 [2021-03-27 08:54:47 swin_small_patch4_window7_224] INFO: Epoch: [289] [1030/1251] eta: 0:01:52 lr: 0.000013 loss: 2.8080 (2.6898) grad_norm: 3.1753 (nan) time: 0.5100 [2021-03-27 08:54:52 swin_small_patch4_window7_224] INFO: Epoch: [289] [1040/1251] eta: 0:01:47 lr: 0.000013 loss: 2.8080 (2.6897) grad_norm: 3.1654 (nan) time: 0.5089 [2021-03-27 08:54:57 swin_small_patch4_window7_224] INFO: Epoch: [289] [1050/1251] eta: 0:01:42 lr: 0.000013 loss: 2.7896 (2.6892) grad_norm: 3.1410 (nan) time: 0.5052 [2021-03-27 08:55:02 swin_small_patch4_window7_224] INFO: Epoch: [289] [1060/1251] eta: 0:01:37 lr: 0.000013 loss: 2.8290 (2.6900) grad_norm: 3.5525 (nan) time: 0.5094 [2021-03-27 08:55:07 swin_small_patch4_window7_224] INFO: Epoch: [289] [1070/1251] eta: 0:01:32 lr: 0.000013 loss: 2.8290 (2.6873) grad_norm: 3.3378 (nan) time: 0.5082 [2021-03-27 08:55:12 swin_small_patch4_window7_224] INFO: Epoch: [289] [1080/1251] eta: 0:01:27 lr: 0.000013 loss: 2.8164 (2.6896) grad_norm: 3.1835 (nan) time: 0.5036 [2021-03-27 08:55:17 swin_small_patch4_window7_224] INFO: Epoch: [289] [1090/1251] eta: 0:01:22 lr: 0.000013 loss: 2.8582 (2.6904) grad_norm: 3.0697 (nan) time: 0.5000 [2021-03-27 08:55:22 swin_small_patch4_window7_224] INFO: Epoch: [289] [1100/1251] eta: 0:01:17 lr: 0.000013 loss: 2.7565 (2.6905) grad_norm: 3.1438 (nan) time: 0.5012 [2021-03-27 08:55:27 swin_small_patch4_window7_224] INFO: Epoch: [289] [1110/1251] eta: 0:01:11 lr: 0.000013 loss: 2.6759 (2.6904) grad_norm: 3.6136 (nan) time: 0.5026 [2021-03-27 08:55:32 swin_small_patch4_window7_224] INFO: Epoch: [289] [1120/1251] eta: 0:01:06 lr: 0.000013 loss: 2.6894 (2.6902) grad_norm: 3.3473 (nan) time: 0.5031 [2021-03-27 08:55:37 swin_small_patch4_window7_224] INFO: Epoch: [289] [1130/1251] eta: 0:01:01 lr: 0.000013 loss: 2.7304 (2.6908) grad_norm: 3.3034 (nan) time: 0.5044 [2021-03-27 08:55:42 swin_small_patch4_window7_224] INFO: Epoch: [289] [1140/1251] eta: 0:00:56 lr: 0.000013 loss: 2.7237 (2.6896) grad_norm: 2.9706 (nan) time: 0.4985 [2021-03-27 08:55:47 swin_small_patch4_window7_224] INFO: Epoch: [289] [1150/1251] eta: 0:00:51 lr: 0.000013 loss: 2.6149 (2.6879) grad_norm: 3.1409 (nan) time: 0.4970 [2021-03-27 08:55:52 swin_small_patch4_window7_224] INFO: Epoch: [289] [1160/1251] eta: 0:00:46 lr: 0.000013 loss: 2.6905 (2.6881) grad_norm: 3.2447 (nan) time: 0.5004 [2021-03-27 08:55:58 swin_small_patch4_window7_224] INFO: Epoch: [289] [1170/1251] eta: 0:00:41 lr: 0.000013 loss: 2.7140 (2.6876) grad_norm: 3.1847 (nan) time: 0.5044 [2021-03-27 08:56:02 swin_small_patch4_window7_224] INFO: Epoch: [289] [1180/1251] eta: 0:00:36 lr: 0.000013 loss: 2.7795 (2.6875) grad_norm: 3.2129 (nan) time: 0.5033 [2021-03-27 08:56:08 swin_small_patch4_window7_224] INFO: Epoch: [289] [1190/1251] eta: 0:00:31 lr: 0.000013 loss: 2.8346 (2.6880) grad_norm: 3.1055 (nan) time: 0.5005 [2021-03-27 08:56:13 swin_small_patch4_window7_224] INFO: Epoch: [289] [1200/1251] eta: 0:00:25 lr: 0.000013 loss: 2.8736 (2.6896) grad_norm: 3.1055 (nan) time: 0.5030 [2021-03-27 08:56:18 swin_small_patch4_window7_224] INFO: Epoch: [289] [1210/1251] eta: 0:00:20 lr: 0.000013 loss: 2.8095 (2.6886) grad_norm: 3.0871 (nan) time: 0.5073 [2021-03-27 08:56:23 swin_small_patch4_window7_224] INFO: Epoch: [289] [1220/1251] eta: 0:00:15 lr: 0.000013 loss: 2.7022 (2.6888) grad_norm: 3.1704 (nan) time: 0.5057 [2021-03-27 08:56:28 swin_small_patch4_window7_224] INFO: Epoch: [289] [1230/1251] eta: 0:00:10 lr: 0.000013 loss: 2.6865 (2.6890) grad_norm: 3.2229 (nan) time: 0.5020 [2021-03-27 08:56:33 swin_small_patch4_window7_224] INFO: Epoch: [289] [1240/1251] eta: 0:00:05 lr: 0.000013 loss: 2.5548 (2.6881) grad_norm: 3.2709 (nan) time: 0.4971 [2021-03-27 08:56:38 swin_small_patch4_window7_224] INFO: Epoch: [289] [1250/1251] eta: 0:00:00 lr: 0.000013 loss: 2.8876 (2.6891) grad_norm: 3.1819 (nan) time: 0.4920 [2021-03-27 08:56:50 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:09 loss: 0.7542 (0.7542) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 08:56:53 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7253 (0.7348) acc1: 81.2500 (81.1080) acc5: 96.8750 (95.8807) [2021-03-27 08:56:55 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7464 (0.7877) acc1: 81.2500 (80.9524) acc5: 95.3125 (95.3125) [2021-03-27 08:56:58 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7464 (0.7505) acc1: 81.2500 (81.6028) acc5: 95.3125 (96.0685) [2021-03-27 08:56:59 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7115 (0.7554) acc1: 82.8125 (81.9360) acc5: 96.8750 (95.8460) [2021-03-27 08:57:00 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7115 (0.7491) acc1: 84.3750 (82.1440) acc5: 95.3125 (95.9360) [2021-03-27 08:57:16 swin_small_patch4_window7_224] INFO: * Acc@1 83.030 Acc@5 96.228 loss 0.735 [2021-03-27 08:57:16 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 08:57:16 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 08:57:20 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 0/1251] eta: 1:29:33 lr: 0.000013 loss: 2.9060 (2.9060) grad_norm: 3.4862 (3.4862) time: 4.2951 [2021-03-27 08:57:25 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 10/1251] eta: 0:17:46 lr: 0.000013 loss: 2.8114 (2.8013) grad_norm: 3.2679 (3.2509) time: 0.8595 [2021-03-27 08:57:30 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 20/1251] eta: 0:14:07 lr: 0.000013 loss: 2.7688 (2.7191) grad_norm: 3.1212 (3.1820) time: 0.5082 [2021-03-27 08:57:35 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 30/1251] eta: 0:12:49 lr: 0.000013 loss: 2.6306 (2.6675) grad_norm: 3.0861 (3.2406) time: 0.5041 [2021-03-27 08:57:40 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 40/1251] eta: 0:12:11 lr: 0.000013 loss: 2.7394 (2.6763) grad_norm: 3.1450 (3.2456) time: 0.5151 [2021-03-27 08:57:45 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 50/1251] eta: 0:11:42 lr: 0.000013 loss: 2.7148 (2.6447) grad_norm: 3.2128 (3.3320) time: 0.5157 [2021-03-27 08:57:51 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 60/1251] eta: 0:11:24 lr: 0.000013 loss: 2.6428 (2.6165) grad_norm: 3.1882 (3.3357) time: 0.5136 [2021-03-27 08:57:56 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 70/1251] eta: 0:11:08 lr: 0.000013 loss: 2.6017 (2.5967) grad_norm: 2.9491 (3.3550) time: 0.5167 [2021-03-27 08:58:01 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 80/1251] eta: 0:10:53 lr: 0.000013 loss: 2.7784 (2.6141) grad_norm: 2.9435 (3.3234) time: 0.5091 [2021-03-27 08:58:06 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 90/1251] eta: 0:10:40 lr: 0.000013 loss: 2.8338 (2.6423) grad_norm: 3.0106 (3.3134) time: 0.5004 [2021-03-27 08:58:11 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 100/1251] eta: 0:10:28 lr: 0.000013 loss: 2.7361 (2.6504) grad_norm: 3.3043 (3.3345) time: 0.4962 [2021-03-27 08:58:16 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 110/1251] eta: 0:10:19 lr: 0.000013 loss: 2.6710 (2.6567) grad_norm: 3.3290 (3.3390) time: 0.5046 [2021-03-27 08:58:21 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 120/1251] eta: 0:10:11 lr: 0.000013 loss: 2.7572 (2.6573) grad_norm: 3.3714 (3.3541) time: 0.5137 [2021-03-27 08:58:26 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 130/1251] eta: 0:10:02 lr: 0.000013 loss: 2.7572 (2.6493) grad_norm: 3.4541 (3.3599) time: 0.5059 [2021-03-27 08:58:31 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 140/1251] eta: 0:09:54 lr: 0.000013 loss: 2.7164 (2.6567) grad_norm: 3.2245 (3.3482) time: 0.5040 [2021-03-27 08:58:36 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 150/1251] eta: 0:09:47 lr: 0.000013 loss: 2.9105 (2.6649) grad_norm: 3.1568 (3.3643) time: 0.5084 [2021-03-27 08:58:41 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 160/1251] eta: 0:09:39 lr: 0.000013 loss: 2.9309 (2.6706) grad_norm: 3.2871 (3.3677) time: 0.5034 [2021-03-27 08:58:46 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 170/1251] eta: 0:09:32 lr: 0.000013 loss: 2.9321 (2.6855) grad_norm: 3.4932 (3.3861) time: 0.5020 [2021-03-27 08:58:51 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 180/1251] eta: 0:09:26 lr: 0.000013 loss: 2.8273 (2.6880) grad_norm: 3.3836 (3.3751) time: 0.5058 [2021-03-27 08:58:56 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 190/1251] eta: 0:09:19 lr: 0.000013 loss: 2.8273 (2.6880) grad_norm: 2.9185 (3.3515) time: 0.5077 [2021-03-27 08:59:01 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 200/1251] eta: 0:09:13 lr: 0.000013 loss: 2.7090 (2.6794) grad_norm: 2.8504 (3.3543) time: 0.5078 [2021-03-27 08:59:06 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 210/1251] eta: 0:09:06 lr: 0.000013 loss: 2.7393 (2.6787) grad_norm: 3.3249 (3.3541) time: 0.5023 [2021-03-27 08:59:12 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 220/1251] eta: 0:09:00 lr: 0.000013 loss: 2.5731 (2.6689) grad_norm: 3.3476 (3.3613) time: 0.5058 [2021-03-27 08:59:17 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 230/1251] eta: 0:08:55 lr: 0.000013 loss: 2.5731 (2.6646) grad_norm: 3.3476 (3.3663) time: 0.5163 [2021-03-27 08:59:22 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 240/1251] eta: 0:08:49 lr: 0.000013 loss: 2.6929 (2.6603) grad_norm: 3.1682 (3.3617) time: 0.5085 [2021-03-27 08:59:27 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 250/1251] eta: 0:08:42 lr: 0.000013 loss: 2.6984 (2.6617) grad_norm: 3.3482 (3.3638) time: 0.4980 [2021-03-27 08:59:32 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 260/1251] eta: 0:08:37 lr: 0.000013 loss: 2.8231 (2.6677) grad_norm: 3.3499 (3.3589) time: 0.5063 [2021-03-27 08:59:37 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 270/1251] eta: 0:08:31 lr: 0.000013 loss: 2.8451 (2.6654) grad_norm: 3.4049 (3.3675) time: 0.5049 [2021-03-27 08:59:42 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 280/1251] eta: 0:08:24 lr: 0.000013 loss: 2.7189 (2.6695) grad_norm: 3.4600 (3.3718) time: 0.4946 [2021-03-27 08:59:47 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 290/1251] eta: 0:08:19 lr: 0.000013 loss: 2.6187 (2.6571) grad_norm: 2.9551 (3.3664) time: 0.4994 [2021-03-27 08:59:52 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 300/1251] eta: 0:08:13 lr: 0.000013 loss: 2.5087 (2.6549) grad_norm: 3.0132 (3.3561) time: 0.5088 [2021-03-27 08:59:57 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 310/1251] eta: 0:08:08 lr: 0.000013 loss: 2.7103 (2.6584) grad_norm: 3.1406 (3.3786) time: 0.5087 [2021-03-27 09:00:02 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 320/1251] eta: 0:08:02 lr: 0.000013 loss: 2.7485 (2.6615) grad_norm: 3.1990 (3.3756) time: 0.5061 [2021-03-27 09:00:07 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 330/1251] eta: 0:07:57 lr: 0.000013 loss: 2.9493 (2.6640) grad_norm: 3.2998 (3.3994) time: 0.5038 [2021-03-27 09:00:12 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 340/1251] eta: 0:07:51 lr: 0.000013 loss: 2.9059 (2.6693) grad_norm: 3.4912 (3.4033) time: 0.5030 [2021-03-27 09:00:17 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 350/1251] eta: 0:07:45 lr: 0.000013 loss: 2.9059 (2.6744) grad_norm: 3.4690 (3.4126) time: 0.5047 [2021-03-27 09:00:22 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 360/1251] eta: 0:07:40 lr: 0.000013 loss: 2.7801 (2.6729) grad_norm: 3.5514 (3.4251) time: 0.5035 [2021-03-27 09:00:27 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 370/1251] eta: 0:07:34 lr: 0.000013 loss: 2.7821 (2.6735) grad_norm: 3.5514 (3.4362) time: 0.5029 [2021-03-27 09:00:32 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 380/1251] eta: 0:07:29 lr: 0.000013 loss: 2.8769 (2.6803) grad_norm: 3.3674 (3.4346) time: 0.4963 [2021-03-27 09:00:37 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 390/1251] eta: 0:07:23 lr: 0.000013 loss: 2.8361 (2.6794) grad_norm: 3.3856 (3.4373) time: 0.4939 [2021-03-27 09:00:42 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 400/1251] eta: 0:07:18 lr: 0.000013 loss: 2.7509 (2.6761) grad_norm: 3.1350 (3.4297) time: 0.4970 [2021-03-27 09:00:47 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 410/1251] eta: 0:07:12 lr: 0.000013 loss: 2.6832 (2.6762) grad_norm: 3.2113 (3.4343) time: 0.5055 [2021-03-27 09:00:52 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 420/1251] eta: 0:07:07 lr: 0.000013 loss: 2.7269 (2.6759) grad_norm: 3.3059 (3.4320) time: 0.5064 [2021-03-27 09:00:57 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 430/1251] eta: 0:07:02 lr: 0.000013 loss: 2.7641 (2.6790) grad_norm: 3.2002 (3.4302) time: 0.4986 [2021-03-27 09:01:02 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 440/1251] eta: 0:06:56 lr: 0.000013 loss: 2.8025 (2.6802) grad_norm: 3.2002 (3.4258) time: 0.5016 [2021-03-27 09:01:07 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 450/1251] eta: 0:06:51 lr: 0.000013 loss: 2.8025 (2.6794) grad_norm: 3.2933 (3.4301) time: 0.5050 [2021-03-27 09:01:12 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 460/1251] eta: 0:06:46 lr: 0.000013 loss: 2.7994 (2.6812) grad_norm: 3.2876 (3.4352) time: 0.5079 [2021-03-27 09:01:18 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 470/1251] eta: 0:06:41 lr: 0.000013 loss: 2.7762 (2.6806) grad_norm: 3.3361 (3.4448) time: 0.5114 [2021-03-27 09:01:23 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 480/1251] eta: 0:06:35 lr: 0.000013 loss: 2.7762 (2.6833) grad_norm: 3.5462 (3.4549) time: 0.5086 [2021-03-27 09:01:28 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 490/1251] eta: 0:06:30 lr: 0.000013 loss: 2.7247 (2.6828) grad_norm: 3.3061 (3.4596) time: 0.5007 [2021-03-27 09:01:33 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 500/1251] eta: 0:06:25 lr: 0.000012 loss: 2.7498 (2.6813) grad_norm: 3.3061 (3.4575) time: 0.4988 [2021-03-27 09:01:38 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 510/1251] eta: 0:06:19 lr: 0.000012 loss: 2.7498 (2.6811) grad_norm: 3.3144 (3.4621) time: 0.5016 [2021-03-27 09:01:43 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 520/1251] eta: 0:06:14 lr: 0.000012 loss: 2.7328 (2.6782) grad_norm: 3.2703 (3.4591) time: 0.5047 [2021-03-27 09:01:48 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 530/1251] eta: 0:06:09 lr: 0.000012 loss: 2.7690 (2.6781) grad_norm: 3.2703 (3.4584) time: 0.5037 [2021-03-27 09:01:53 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 540/1251] eta: 0:06:04 lr: 0.000012 loss: 2.7610 (2.6748) grad_norm: 3.3164 (3.4605) time: 0.5011 [2021-03-27 09:01:58 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 550/1251] eta: 0:05:59 lr: 0.000012 loss: 2.7372 (2.6752) grad_norm: 3.4546 (3.4566) time: 0.5102 [2021-03-27 09:02:03 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 560/1251] eta: 0:05:53 lr: 0.000012 loss: 2.8493 (2.6777) grad_norm: 3.3644 (3.4608) time: 0.5080 [2021-03-27 09:02:08 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 570/1251] eta: 0:05:48 lr: 0.000012 loss: 2.8278 (2.6797) grad_norm: 3.3260 (3.4587) time: 0.5007 [2021-03-27 09:02:13 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 580/1251] eta: 0:05:43 lr: 0.000012 loss: 2.7980 (2.6805) grad_norm: 3.2417 (3.4590) time: 0.5021 [2021-03-27 09:02:18 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 590/1251] eta: 0:05:38 lr: 0.000012 loss: 2.7980 (2.6824) grad_norm: 3.2985 (3.4672) time: 0.5051 [2021-03-27 09:02:23 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 600/1251] eta: 0:05:32 lr: 0.000012 loss: 2.8869 (2.6845) grad_norm: 3.4052 (3.4679) time: 0.5078 [2021-03-27 09:02:28 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 610/1251] eta: 0:05:27 lr: 0.000012 loss: 2.6871 (2.6817) grad_norm: 3.2710 (3.4625) time: 0.5043 [2021-03-27 09:02:33 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 620/1251] eta: 0:05:22 lr: 0.000012 loss: 2.7097 (2.6825) grad_norm: 3.1991 (3.4613) time: 0.5013 [2021-03-27 09:02:38 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 630/1251] eta: 0:05:17 lr: 0.000012 loss: 2.8535 (2.6823) grad_norm: 3.2437 (3.4591) time: 0.5003 [2021-03-27 09:02:43 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 640/1251] eta: 0:05:12 lr: 0.000012 loss: 2.8315 (2.6815) grad_norm: 3.4204 (3.4592) time: 0.5026 [2021-03-27 09:02:48 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 650/1251] eta: 0:05:06 lr: 0.000012 loss: 2.8315 (2.6825) grad_norm: 3.2442 (3.4573) time: 0.5041 [2021-03-27 09:02:53 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 660/1251] eta: 0:05:01 lr: 0.000012 loss: 2.7459 (2.6812) grad_norm: 3.1568 (3.4523) time: 0.5035 [2021-03-27 09:02:58 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 670/1251] eta: 0:04:56 lr: 0.000012 loss: 2.6889 (2.6803) grad_norm: 3.1514 (3.4573) time: 0.5093 [2021-03-27 09:03:03 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 680/1251] eta: 0:04:51 lr: 0.000012 loss: 2.5996 (2.6774) grad_norm: 3.2896 (3.4631) time: 0.5101 [2021-03-27 09:03:09 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 690/1251] eta: 0:04:46 lr: 0.000012 loss: 2.7458 (2.6805) grad_norm: 3.3364 (3.4610) time: 0.5057 [2021-03-27 09:03:14 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 700/1251] eta: 0:04:41 lr: 0.000012 loss: 2.9586 (2.6835) grad_norm: 3.2451 (3.4578) time: 0.5043 [2021-03-27 09:03:19 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 710/1251] eta: 0:04:36 lr: 0.000012 loss: 2.7887 (2.6840) grad_norm: 3.2462 (3.4557) time: 0.5014 [2021-03-27 09:03:24 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 720/1251] eta: 0:04:30 lr: 0.000012 loss: 2.7887 (2.6850) grad_norm: 3.3041 (3.4569) time: 0.5034 [2021-03-27 09:03:29 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 730/1251] eta: 0:04:25 lr: 0.000012 loss: 2.5529 (2.6810) grad_norm: 3.3041 (3.4549) time: 0.5043 [2021-03-27 09:03:34 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 740/1251] eta: 0:04:20 lr: 0.000012 loss: 2.5218 (2.6803) grad_norm: 3.2143 (3.4544) time: 0.5101 [2021-03-27 09:03:39 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 750/1251] eta: 0:04:15 lr: 0.000012 loss: 2.6198 (2.6812) grad_norm: 3.2629 (3.4534) time: 0.5093 [2021-03-27 09:03:44 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 760/1251] eta: 0:04:10 lr: 0.000012 loss: 2.7974 (2.6808) grad_norm: 3.2678 (3.4525) time: 0.5052 [2021-03-27 09:03:49 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 770/1251] eta: 0:04:05 lr: 0.000012 loss: 2.6436 (2.6787) grad_norm: 3.2632 (3.4490) time: 0.5111 [2021-03-27 09:03:54 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 780/1251] eta: 0:04:00 lr: 0.000012 loss: 2.6911 (2.6792) grad_norm: 3.1864 (3.4456) time: 0.5102 [2021-03-27 09:03:59 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 790/1251] eta: 0:03:55 lr: 0.000012 loss: 2.7600 (2.6778) grad_norm: 3.2134 (3.4450) time: 0.5115 [2021-03-27 09:04:04 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 800/1251] eta: 0:03:50 lr: 0.000012 loss: 2.7153 (2.6783) grad_norm: 3.0310 (3.4397) time: 0.5094 [2021-03-27 09:04:09 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 810/1251] eta: 0:03:44 lr: 0.000012 loss: 2.7782 (2.6803) grad_norm: 3.0310 (3.4402) time: 0.5096 [2021-03-27 09:04:15 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 820/1251] eta: 0:03:39 lr: 0.000012 loss: 2.8170 (2.6812) grad_norm: 3.0454 (3.4377) time: 0.5124 [2021-03-27 09:04:20 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 830/1251] eta: 0:03:34 lr: 0.000012 loss: 2.8744 (2.6829) grad_norm: 3.1310 (3.4373) time: 0.5098 [2021-03-27 09:04:25 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 840/1251] eta: 0:03:29 lr: 0.000012 loss: 2.8532 (2.6828) grad_norm: 3.2466 (3.4419) time: 0.5069 [2021-03-27 09:04:30 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 850/1251] eta: 0:03:24 lr: 0.000012 loss: 2.8799 (2.6846) grad_norm: 3.1594 (3.4453) time: 0.5070 [2021-03-27 09:04:35 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 860/1251] eta: 0:03:19 lr: 0.000012 loss: 2.8857 (2.6850) grad_norm: 3.1443 (3.4417) time: 0.5055 [2021-03-27 09:04:40 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 870/1251] eta: 0:03:14 lr: 0.000012 loss: 2.9154 (2.6860) grad_norm: 3.0453 (3.4417) time: 0.5074 [2021-03-27 09:04:45 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 880/1251] eta: 0:03:09 lr: 0.000012 loss: 2.8963 (2.6837) grad_norm: 3.0707 (3.4395) time: 0.5083 [2021-03-27 09:04:50 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 890/1251] eta: 0:03:04 lr: 0.000012 loss: 2.5840 (2.6823) grad_norm: 3.2393 (3.4411) time: 0.5043 [2021-03-27 09:04:55 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 900/1251] eta: 0:02:58 lr: 0.000012 loss: 2.6670 (2.6837) grad_norm: 3.2525 (3.4392) time: 0.5018 [2021-03-27 09:05:00 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 910/1251] eta: 0:02:53 lr: 0.000012 loss: 2.7404 (2.6833) grad_norm: 3.0735 (3.4340) time: 0.5045 [2021-03-27 09:05:05 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 920/1251] eta: 0:02:48 lr: 0.000012 loss: 2.8038 (2.6858) grad_norm: 3.0948 (3.4317) time: 0.5073 [2021-03-27 09:05:10 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 930/1251] eta: 0:02:43 lr: 0.000012 loss: 2.9162 (2.6868) grad_norm: 3.2047 (3.4303) time: 0.5102 [2021-03-27 09:05:15 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 940/1251] eta: 0:02:38 lr: 0.000012 loss: 2.7199 (2.6865) grad_norm: 3.2141 (3.4310) time: 0.5067 [2021-03-27 09:05:20 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 950/1251] eta: 0:02:33 lr: 0.000012 loss: 2.7039 (2.6875) grad_norm: 3.5057 (3.4329) time: 0.4973 [2021-03-27 09:05:25 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 960/1251] eta: 0:02:28 lr: 0.000012 loss: 2.8378 (2.6883) grad_norm: 3.5270 (3.4328) time: 0.4995 [2021-03-27 09:05:31 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 970/1251] eta: 0:02:23 lr: 0.000012 loss: 2.8144 (2.6887) grad_norm: 3.2582 (3.4306) time: 0.5145 [2021-03-27 09:05:36 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 980/1251] eta: 0:02:18 lr: 0.000012 loss: 2.8559 (2.6898) grad_norm: 3.3985 (3.4337) time: 0.5143 [2021-03-27 09:05:41 swin_small_patch4_window7_224] INFO: Epoch: [290] [ 990/1251] eta: 0:02:12 lr: 0.000012 loss: 2.7576 (2.6879) grad_norm: 3.6684 (3.4368) time: 0.4967 [2021-03-27 09:05:45 swin_small_patch4_window7_224] INFO: Epoch: [290] [1000/1251] eta: 0:02:07 lr: 0.000012 loss: 2.4754 (2.6859) grad_norm: 3.4494 (3.4374) time: 0.4936 [2021-03-27 09:05:51 swin_small_patch4_window7_224] INFO: Epoch: [290] [1010/1251] eta: 0:02:02 lr: 0.000012 loss: 2.5938 (2.6865) grad_norm: 3.2675 (3.4359) time: 0.5038 [2021-03-27 09:05:56 swin_small_patch4_window7_224] INFO: Epoch: [290] [1020/1251] eta: 0:01:57 lr: 0.000012 loss: 2.6225 (2.6844) grad_norm: 3.2546 (3.4423) time: 0.5104 [2021-03-27 09:06:01 swin_small_patch4_window7_224] INFO: Epoch: [290] [1030/1251] eta: 0:01:52 lr: 0.000012 loss: 2.6798 (2.6837) grad_norm: 3.0836 (3.4396) time: 0.5005 [2021-03-27 09:06:06 swin_small_patch4_window7_224] INFO: Epoch: [290] [1040/1251] eta: 0:01:47 lr: 0.000012 loss: 2.6512 (2.6832) grad_norm: 3.2996 (3.4405) time: 0.4955 [2021-03-27 09:06:11 swin_small_patch4_window7_224] INFO: Epoch: [290] [1050/1251] eta: 0:01:42 lr: 0.000012 loss: 2.6261 (2.6837) grad_norm: 3.4041 (3.4392) time: 0.4988 [2021-03-27 09:06:16 swin_small_patch4_window7_224] INFO: Epoch: [290] [1060/1251] eta: 0:01:37 lr: 0.000012 loss: 2.7984 (2.6845) grad_norm: 3.2878 (3.4408) time: 0.5087 [2021-03-27 09:06:21 swin_small_patch4_window7_224] INFO: Epoch: [290] [1070/1251] eta: 0:01:32 lr: 0.000012 loss: 2.7787 (2.6833) grad_norm: 3.2589 (3.4414) time: 0.5115 [2021-03-27 09:06:26 swin_small_patch4_window7_224] INFO: Epoch: [290] [1080/1251] eta: 0:01:27 lr: 0.000012 loss: 2.7142 (2.6835) grad_norm: 3.2054 (3.4389) time: 0.5039 [2021-03-27 09:06:31 swin_small_patch4_window7_224] INFO: Epoch: [290] [1090/1251] eta: 0:01:21 lr: 0.000012 loss: 2.7142 (2.6837) grad_norm: 3.1385 (3.4382) time: 0.5058 [2021-03-27 09:06:36 swin_small_patch4_window7_224] INFO: Epoch: [290] [1100/1251] eta: 0:01:16 lr: 0.000012 loss: 2.6226 (2.6827) grad_norm: 3.3385 (3.4420) time: 0.5107 [2021-03-27 09:06:41 swin_small_patch4_window7_224] INFO: Epoch: [290] [1110/1251] eta: 0:01:11 lr: 0.000012 loss: 2.6432 (2.6832) grad_norm: 3.2927 (3.4404) time: 0.5009 [2021-03-27 09:06:46 swin_small_patch4_window7_224] INFO: Epoch: [290] [1120/1251] eta: 0:01:06 lr: 0.000012 loss: 2.6432 (2.6806) grad_norm: 3.3971 (3.4423) time: 0.4974 [2021-03-27 09:06:51 swin_small_patch4_window7_224] INFO: Epoch: [290] [1130/1251] eta: 0:01:01 lr: 0.000012 loss: 2.6102 (2.6815) grad_norm: 3.3971 (3.4415) time: 0.5035 [2021-03-27 09:06:56 swin_small_patch4_window7_224] INFO: Epoch: [290] [1140/1251] eta: 0:00:56 lr: 0.000012 loss: 2.8015 (2.6816) grad_norm: 3.0679 (3.4434) time: 0.5044 [2021-03-27 09:07:01 swin_small_patch4_window7_224] INFO: Epoch: [290] [1150/1251] eta: 0:00:51 lr: 0.000012 loss: 2.8056 (2.6821) grad_norm: 3.0679 (3.4411) time: 0.5054 [2021-03-27 09:07:06 swin_small_patch4_window7_224] INFO: Epoch: [290] [1160/1251] eta: 0:00:46 lr: 0.000012 loss: 2.5868 (2.6798) grad_norm: 3.1414 (3.4387) time: 0.5103 [2021-03-27 09:07:11 swin_small_patch4_window7_224] INFO: Epoch: [290] [1170/1251] eta: 0:00:41 lr: 0.000012 loss: 2.5868 (2.6798) grad_norm: 3.1198 (3.4374) time: 0.5153 [2021-03-27 09:07:16 swin_small_patch4_window7_224] INFO: Epoch: [290] [1180/1251] eta: 0:00:36 lr: 0.000012 loss: 2.6451 (2.6805) grad_norm: 3.1274 (3.4389) time: 0.5080 [2021-03-27 09:07:22 swin_small_patch4_window7_224] INFO: Epoch: [290] [1190/1251] eta: 0:00:31 lr: 0.000012 loss: 2.6062 (2.6793) grad_norm: 3.2982 (3.4380) time: 0.5028 [2021-03-27 09:07:27 swin_small_patch4_window7_224] INFO: Epoch: [290] [1200/1251] eta: 0:00:25 lr: 0.000012 loss: 2.5106 (2.6794) grad_norm: 3.2000 (3.4373) time: 0.5126 [2021-03-27 09:07:32 swin_small_patch4_window7_224] INFO: Epoch: [290] [1210/1251] eta: 0:00:20 lr: 0.000012 loss: 2.7706 (2.6808) grad_norm: 3.0534 (3.4399) time: 0.5143 [2021-03-27 09:07:37 swin_small_patch4_window7_224] INFO: Epoch: [290] [1220/1251] eta: 0:00:15 lr: 0.000012 loss: 2.7706 (2.6814) grad_norm: 3.3684 (3.4441) time: 0.5070 [2021-03-27 09:07:42 swin_small_patch4_window7_224] INFO: Epoch: [290] [1230/1251] eta: 0:00:10 lr: 0.000012 loss: 2.7345 (2.6813) grad_norm: 3.3605 (3.4440) time: 0.5023 [2021-03-27 09:07:47 swin_small_patch4_window7_224] INFO: Epoch: [290] [1240/1251] eta: 0:00:05 lr: 0.000012 loss: 2.6969 (2.6818) grad_norm: 3.4606 (3.4447) time: 0.5006 [2021-03-27 09:07:52 swin_small_patch4_window7_224] INFO: Epoch: [290] [1250/1251] eta: 0:00:00 lr: 0.000012 loss: 2.6423 (2.6801) grad_norm: 3.4606 (3.4435) time: 0.4966 [2021-03-27 09:08:43 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:12 loss: 0.5462 (0.5462) acc1: 89.0625 (89.0625) acc5: 96.8750 (96.8750) [2021-03-27 09:08:44 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:09 loss: 0.7645 (0.8264) acc1: 81.2500 (81.9602) acc5: 96.8750 (95.0284) [2021-03-27 09:08:45 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:05 loss: 0.7526 (0.7730) acc1: 81.2500 (82.4405) acc5: 96.8750 (95.6101) [2021-03-27 09:08:46 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7215 (0.7913) acc1: 81.2500 (81.5524) acc5: 96.8750 (95.6149) [2021-03-27 09:08:47 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7116 (0.7710) acc1: 81.2500 (82.2409) acc5: 96.8750 (95.8079) [2021-03-27 09:08:48 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6243 (0.7531) acc1: 84.3750 (82.3680) acc5: 96.8750 (96.0640) [2021-03-27 09:09:03 swin_small_patch4_window7_224] INFO: * Acc@1 83.128 Acc@5 96.258 loss 0.738 [2021-03-27 09:09:03 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 09:09:03 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 09:09:07 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 0/1251] eta: 1:37:22 lr: 0.000012 loss: 2.4600 (2.4600) grad_norm: 3.3116 (3.3116) time: 4.6705 [2021-03-27 09:09:12 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 10/1251] eta: 0:18:21 lr: 0.000012 loss: 2.9571 (2.8169) grad_norm: 3.1014 (3.1396) time: 0.8876 [2021-03-27 09:09:17 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 20/1251] eta: 0:14:23 lr: 0.000012 loss: 2.9647 (2.7640) grad_norm: 3.0817 (3.1576) time: 0.5028 [2021-03-27 09:09:22 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 30/1251] eta: 0:12:58 lr: 0.000012 loss: 2.7344 (2.7240) grad_norm: 3.2715 (3.3582) time: 0.5004 [2021-03-27 09:09:27 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 40/1251] eta: 0:12:15 lr: 0.000012 loss: 2.7344 (2.6892) grad_norm: 3.2412 (3.4036) time: 0.5087 [2021-03-27 09:09:33 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 50/1251] eta: 0:11:46 lr: 0.000012 loss: 2.7706 (2.6613) grad_norm: 3.1279 (3.3826) time: 0.5119 [2021-03-27 09:09:38 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 60/1251] eta: 0:11:24 lr: 0.000012 loss: 2.7547 (2.6537) grad_norm: 3.1874 (3.3710) time: 0.5079 [2021-03-27 09:09:43 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 70/1251] eta: 0:11:05 lr: 0.000012 loss: 2.8236 (2.6844) grad_norm: 3.1275 (3.6132) time: 0.5014 [2021-03-27 09:09:48 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 80/1251] eta: 0:10:53 lr: 0.000012 loss: 2.8263 (2.7077) grad_norm: 3.1395 (3.5688) time: 0.5056 [2021-03-27 09:09:53 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 90/1251] eta: 0:10:40 lr: 0.000012 loss: 2.7274 (2.6671) grad_norm: 3.2638 (3.5495) time: 0.5087 [2021-03-27 09:09:58 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 100/1251] eta: 0:10:29 lr: 0.000012 loss: 2.6108 (2.6753) grad_norm: 3.1041 (3.5334) time: 0.5044 [2021-03-27 09:10:03 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 110/1251] eta: 0:10:20 lr: 0.000012 loss: 2.7383 (2.6733) grad_norm: 3.1045 (3.5004) time: 0.5072 [2021-03-27 09:10:08 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 120/1251] eta: 0:10:11 lr: 0.000012 loss: 2.6963 (2.6657) grad_norm: 3.1045 (3.4799) time: 0.5107 [2021-03-27 09:10:13 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 130/1251] eta: 0:10:03 lr: 0.000012 loss: 2.8489 (2.6844) grad_norm: 3.1296 (3.4637) time: 0.5097 [2021-03-27 09:10:18 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 140/1251] eta: 0:09:56 lr: 0.000012 loss: 2.8430 (2.6867) grad_norm: 3.3449 (3.5222) time: 0.5119 [2021-03-27 09:10:23 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 150/1251] eta: 0:09:49 lr: 0.000012 loss: 2.7739 (2.6888) grad_norm: 3.3570 (3.4970) time: 0.5132 [2021-03-27 09:10:28 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 160/1251] eta: 0:09:41 lr: 0.000012 loss: 2.7454 (2.6800) grad_norm: 3.1639 (3.4848) time: 0.5036 [2021-03-27 09:10:34 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 170/1251] eta: 0:09:34 lr: 0.000012 loss: 2.7663 (2.6887) grad_norm: 3.3750 (3.4915) time: 0.5056 [2021-03-27 09:10:39 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 180/1251] eta: 0:09:27 lr: 0.000012 loss: 2.8019 (2.6950) grad_norm: 3.2872 (3.4789) time: 0.5105 [2021-03-27 09:10:44 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 190/1251] eta: 0:09:21 lr: 0.000012 loss: 2.7864 (2.7004) grad_norm: 3.2325 (3.4758) time: 0.5090 [2021-03-27 09:10:49 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 200/1251] eta: 0:09:15 lr: 0.000012 loss: 2.7384 (2.6938) grad_norm: 3.2377 (3.4728) time: 0.5081 [2021-03-27 09:10:54 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 210/1251] eta: 0:09:08 lr: 0.000012 loss: 2.8208 (2.7001) grad_norm: 3.3132 (3.4719) time: 0.5028 [2021-03-27 09:10:59 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 220/1251] eta: 0:09:02 lr: 0.000012 loss: 2.7894 (2.6998) grad_norm: 3.3998 (3.4666) time: 0.5014 [2021-03-27 09:11:04 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 230/1251] eta: 0:08:55 lr: 0.000012 loss: 2.7569 (2.7043) grad_norm: 3.2561 (3.4666) time: 0.4990 [2021-03-27 09:11:09 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 240/1251] eta: 0:08:49 lr: 0.000012 loss: 2.8816 (2.7054) grad_norm: 3.2324 (3.4558) time: 0.4976 [2021-03-27 09:11:14 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 250/1251] eta: 0:08:43 lr: 0.000012 loss: 2.9041 (2.7125) grad_norm: 3.1465 (3.4491) time: 0.5026 [2021-03-27 09:11:19 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 260/1251] eta: 0:08:36 lr: 0.000012 loss: 2.9041 (2.7190) grad_norm: 3.4322 (3.4557) time: 0.5014 [2021-03-27 09:11:24 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 270/1251] eta: 0:08:31 lr: 0.000012 loss: 2.9022 (2.7214) grad_norm: 3.4045 (3.4542) time: 0.5001 [2021-03-27 09:11:29 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 280/1251] eta: 0:08:25 lr: 0.000012 loss: 2.7476 (2.7172) grad_norm: 3.3946 (3.4597) time: 0.5087 [2021-03-27 09:11:34 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 290/1251] eta: 0:08:19 lr: 0.000012 loss: 2.7370 (2.7212) grad_norm: 3.3243 (3.4603) time: 0.5073 [2021-03-27 09:11:39 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 300/1251] eta: 0:08:13 lr: 0.000012 loss: 2.6459 (2.7167) grad_norm: 3.2794 (3.4678) time: 0.4994 [2021-03-27 09:11:44 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 310/1251] eta: 0:08:08 lr: 0.000012 loss: 2.6105 (2.7140) grad_norm: 3.5497 (3.4728) time: 0.4977 [2021-03-27 09:11:49 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 320/1251] eta: 0:08:02 lr: 0.000012 loss: 2.7064 (2.7174) grad_norm: 3.5497 (3.4741) time: 0.4992 [2021-03-27 09:11:54 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 330/1251] eta: 0:07:56 lr: 0.000012 loss: 2.6673 (2.7113) grad_norm: 3.4677 (3.4725) time: 0.5016 [2021-03-27 09:11:59 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 340/1251] eta: 0:07:50 lr: 0.000012 loss: 2.5985 (2.7050) grad_norm: 3.2231 (3.4662) time: 0.4994 [2021-03-27 09:12:04 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 350/1251] eta: 0:07:45 lr: 0.000012 loss: 2.3328 (2.6957) grad_norm: 3.2231 (3.4686) time: 0.5037 [2021-03-27 09:12:09 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 360/1251] eta: 0:07:39 lr: 0.000012 loss: 2.4874 (2.6971) grad_norm: 3.3668 (3.4694) time: 0.5007 [2021-03-27 09:12:14 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 370/1251] eta: 0:07:34 lr: 0.000012 loss: 2.7367 (2.6958) grad_norm: 3.2530 (3.4567) time: 0.4992 [2021-03-27 09:12:19 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 380/1251] eta: 0:07:29 lr: 0.000012 loss: 2.7466 (2.6983) grad_norm: 3.1220 (3.4541) time: 0.5096 [2021-03-27 09:12:24 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 390/1251] eta: 0:07:23 lr: 0.000012 loss: 2.7832 (2.6945) grad_norm: 3.4141 (3.4610) time: 0.5123 [2021-03-27 09:12:29 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 400/1251] eta: 0:07:18 lr: 0.000012 loss: 2.7832 (2.6942) grad_norm: 3.4118 (3.4596) time: 0.5055 [2021-03-27 09:12:34 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 410/1251] eta: 0:07:13 lr: 0.000012 loss: 2.7866 (2.6922) grad_norm: 3.3091 (3.4869) time: 0.5014 [2021-03-27 09:12:39 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 420/1251] eta: 0:07:07 lr: 0.000012 loss: 2.7866 (2.6956) grad_norm: 3.2548 (3.4896) time: 0.5046 [2021-03-27 09:12:44 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 430/1251] eta: 0:07:02 lr: 0.000012 loss: 2.7487 (2.6923) grad_norm: 3.3063 (3.4868) time: 0.5052 [2021-03-27 09:12:50 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 440/1251] eta: 0:06:57 lr: 0.000012 loss: 2.6495 (2.6943) grad_norm: 3.3063 (3.4853) time: 0.5094 [2021-03-27 09:12:54 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 450/1251] eta: 0:06:51 lr: 0.000012 loss: 2.7841 (2.6923) grad_norm: 3.3185 (3.4834) time: 0.5057 [2021-03-27 09:13:00 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 460/1251] eta: 0:06:46 lr: 0.000012 loss: 2.5376 (2.6915) grad_norm: 3.3273 (3.4838) time: 0.4993 [2021-03-27 09:13:05 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 470/1251] eta: 0:06:41 lr: 0.000012 loss: 2.5523 (2.6933) grad_norm: 3.1297 (3.4906) time: 0.5018 [2021-03-27 09:13:10 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 480/1251] eta: 0:06:35 lr: 0.000012 loss: 2.5260 (2.6929) grad_norm: 3.3222 (3.4966) time: 0.5000 [2021-03-27 09:13:14 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 490/1251] eta: 0:06:30 lr: 0.000012 loss: 2.5260 (2.6900) grad_norm: 3.4249 (3.4993) time: 0.4963 [2021-03-27 09:13:19 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 500/1251] eta: 0:06:24 lr: 0.000012 loss: 2.7334 (2.6895) grad_norm: 3.5352 (3.5040) time: 0.4948 [2021-03-27 09:13:24 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 510/1251] eta: 0:06:19 lr: 0.000012 loss: 2.7701 (2.6899) grad_norm: 3.5352 (3.5045) time: 0.5012 [2021-03-27 09:13:30 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 520/1251] eta: 0:06:14 lr: 0.000012 loss: 2.5451 (2.6836) grad_norm: 3.3196 (3.5015) time: 0.5113 [2021-03-27 09:13:35 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 530/1251] eta: 0:06:09 lr: 0.000012 loss: 2.2438 (2.6818) grad_norm: 3.2578 (3.4989) time: 0.5059 [2021-03-27 09:13:40 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 540/1251] eta: 0:06:03 lr: 0.000012 loss: 2.7613 (2.6819) grad_norm: 3.2809 (3.4994) time: 0.4965 [2021-03-27 09:13:45 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 550/1251] eta: 0:05:59 lr: 0.000012 loss: 2.7800 (2.6845) grad_norm: 3.5244 (3.5051) time: 0.5149 [2021-03-27 09:13:50 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 560/1251] eta: 0:05:53 lr: 0.000012 loss: 2.7874 (2.6828) grad_norm: 3.4178 (3.5043) time: 0.5142 [2021-03-27 09:13:55 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 570/1251] eta: 0:05:48 lr: 0.000012 loss: 2.6111 (2.6777) grad_norm: 3.3526 (3.5000) time: 0.4958 [2021-03-27 09:14:00 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 580/1251] eta: 0:05:43 lr: 0.000012 loss: 2.6111 (2.6781) grad_norm: 3.2015 (3.4976) time: 0.4999 [2021-03-27 09:14:05 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 590/1251] eta: 0:05:38 lr: 0.000012 loss: 2.7998 (2.6797) grad_norm: 3.4061 (3.5008) time: 0.5055 [2021-03-27 09:14:10 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 600/1251] eta: 0:05:32 lr: 0.000012 loss: 2.7985 (2.6807) grad_norm: 3.5365 (3.5090) time: 0.5068 [2021-03-27 09:14:15 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 610/1251] eta: 0:05:27 lr: 0.000012 loss: 2.7983 (2.6810) grad_norm: 3.2942 (3.5095) time: 0.5046 [2021-03-27 09:14:20 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 620/1251] eta: 0:05:22 lr: 0.000012 loss: 2.5523 (2.6782) grad_norm: 3.1083 (3.5083) time: 0.5038 [2021-03-27 09:14:25 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 630/1251] eta: 0:05:17 lr: 0.000012 loss: 2.7808 (2.6793) grad_norm: 3.3475 (3.5079) time: 0.5042 [2021-03-27 09:14:30 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 640/1251] eta: 0:05:12 lr: 0.000012 loss: 2.7955 (2.6792) grad_norm: 3.4306 (3.5108) time: 0.5063 [2021-03-27 09:14:35 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 650/1251] eta: 0:05:07 lr: 0.000012 loss: 2.7077 (2.6788) grad_norm: 3.4024 (3.5071) time: 0.5044 [2021-03-27 09:14:40 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 660/1251] eta: 0:05:01 lr: 0.000012 loss: 2.9176 (2.6826) grad_norm: 3.4254 (3.5194) time: 0.5046 [2021-03-27 09:14:45 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 670/1251] eta: 0:04:56 lr: 0.000012 loss: 2.8117 (2.6818) grad_norm: 3.2908 (3.5145) time: 0.5081 [2021-03-27 09:14:50 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 680/1251] eta: 0:04:51 lr: 0.000012 loss: 2.6090 (2.6795) grad_norm: 3.2908 (3.5129) time: 0.5081 [2021-03-27 09:14:56 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 690/1251] eta: 0:04:46 lr: 0.000012 loss: 2.7554 (2.6813) grad_norm: 3.2830 (3.5099) time: 0.5062 [2021-03-27 09:15:00 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 700/1251] eta: 0:04:41 lr: 0.000012 loss: 2.8806 (2.6840) grad_norm: 3.2830 (3.5078) time: 0.5005 [2021-03-27 09:15:06 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 710/1251] eta: 0:04:36 lr: 0.000012 loss: 2.9349 (2.6876) grad_norm: 3.4161 (3.5067) time: 0.5013 [2021-03-27 09:15:11 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 720/1251] eta: 0:04:31 lr: 0.000012 loss: 2.7664 (2.6854) grad_norm: 3.4625 (3.5118) time: 0.5098 [2021-03-27 09:15:16 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 730/1251] eta: 0:04:26 lr: 0.000012 loss: 2.7369 (2.6886) grad_norm: 3.3066 (3.5145) time: 0.5182 [2021-03-27 09:15:21 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 740/1251] eta: 0:04:21 lr: 0.000012 loss: 2.8166 (2.6871) grad_norm: 3.3066 (3.5166) time: 0.5260 [2021-03-27 09:15:26 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 750/1251] eta: 0:04:15 lr: 0.000012 loss: 2.7481 (2.6870) grad_norm: 3.4916 (3.5208) time: 0.5193 [2021-03-27 09:15:31 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 760/1251] eta: 0:04:10 lr: 0.000012 loss: 2.9018 (2.6903) grad_norm: 3.5122 (3.5195) time: 0.5098 [2021-03-27 09:15:36 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 770/1251] eta: 0:04:05 lr: 0.000012 loss: 2.8883 (2.6875) grad_norm: 3.1942 (3.5154) time: 0.5071 [2021-03-27 09:15:41 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 780/1251] eta: 0:04:00 lr: 0.000012 loss: 2.7921 (2.6890) grad_norm: 3.3247 (3.5141) time: 0.5045 [2021-03-27 09:15:47 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 790/1251] eta: 0:03:55 lr: 0.000012 loss: 2.8211 (2.6892) grad_norm: 3.3505 (3.5159) time: 0.5039 [2021-03-27 09:15:52 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 800/1251] eta: 0:03:50 lr: 0.000012 loss: 2.8420 (2.6906) grad_norm: 3.3168 (3.5121) time: 0.5017 [2021-03-27 09:15:57 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 810/1251] eta: 0:03:45 lr: 0.000012 loss: 2.7570 (2.6899) grad_norm: 3.1300 (3.5066) time: 0.5003 [2021-03-27 09:16:02 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 820/1251] eta: 0:03:39 lr: 0.000012 loss: 2.7570 (2.6906) grad_norm: 3.0774 (3.5030) time: 0.5014 [2021-03-27 09:16:07 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 830/1251] eta: 0:03:34 lr: 0.000012 loss: 2.8363 (2.6919) grad_norm: 3.1387 (3.5003) time: 0.5123 [2021-03-27 09:16:12 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 840/1251] eta: 0:03:29 lr: 0.000012 loss: 2.7453 (2.6906) grad_norm: 3.0937 (3.4962) time: 0.5125 [2021-03-27 09:16:17 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 850/1251] eta: 0:03:24 lr: 0.000012 loss: 2.4706 (2.6885) grad_norm: 3.1710 (3.4978) time: 0.5033 [2021-03-27 09:16:22 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 860/1251] eta: 0:03:19 lr: 0.000012 loss: 2.7720 (2.6900) grad_norm: 3.4917 (3.4995) time: 0.4999 [2021-03-27 09:16:27 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 870/1251] eta: 0:03:14 lr: 0.000012 loss: 2.8479 (2.6914) grad_norm: 3.3998 (3.4999) time: 0.5064 [2021-03-27 09:16:32 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 880/1251] eta: 0:03:09 lr: 0.000012 loss: 2.7755 (2.6928) grad_norm: 3.3285 (3.4988) time: 0.5154 [2021-03-27 09:16:37 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 890/1251] eta: 0:03:04 lr: 0.000012 loss: 2.7755 (2.6935) grad_norm: 3.2304 (3.4956) time: 0.5085 [2021-03-27 09:16:42 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 900/1251] eta: 0:02:58 lr: 0.000012 loss: 2.8018 (2.6933) grad_norm: 3.2212 (3.4949) time: 0.5022 [2021-03-27 09:16:47 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 910/1251] eta: 0:02:53 lr: 0.000012 loss: 2.8189 (2.6958) grad_norm: 3.2212 (3.4919) time: 0.5053 [2021-03-27 09:16:52 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 920/1251] eta: 0:02:48 lr: 0.000012 loss: 2.8780 (2.6957) grad_norm: 3.2040 (3.4916) time: 0.5124 [2021-03-27 09:16:58 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 930/1251] eta: 0:02:43 lr: 0.000012 loss: 2.9401 (2.6955) grad_norm: 3.1829 (3.4894) time: 0.5127 [2021-03-27 09:17:03 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 940/1251] eta: 0:02:38 lr: 0.000012 loss: 2.9401 (2.6966) grad_norm: 3.3311 (3.4913) time: 0.5060 [2021-03-27 09:17:08 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 950/1251] eta: 0:02:33 lr: 0.000012 loss: 2.8890 (2.6982) grad_norm: 3.4500 (3.4907) time: 0.5079 [2021-03-27 09:17:13 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 960/1251] eta: 0:02:28 lr: 0.000012 loss: 2.7205 (2.6956) grad_norm: 3.1930 (3.4864) time: 0.5133 [2021-03-27 09:17:18 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 970/1251] eta: 0:02:23 lr: 0.000012 loss: 2.5735 (2.6962) grad_norm: 3.1930 (3.4858) time: 0.5060 [2021-03-27 09:17:23 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 980/1251] eta: 0:02:18 lr: 0.000012 loss: 2.8650 (2.6985) grad_norm: 3.3863 (3.4856) time: 0.5010 [2021-03-27 09:17:28 swin_small_patch4_window7_224] INFO: Epoch: [291] [ 990/1251] eta: 0:02:13 lr: 0.000012 loss: 3.0233 (2.7005) grad_norm: 3.3852 (3.4862) time: 0.5089 [2021-03-27 09:17:33 swin_small_patch4_window7_224] INFO: Epoch: [291] [1000/1251] eta: 0:02:07 lr: 0.000012 loss: 2.8262 (2.7004) grad_norm: 3.0986 (3.4823) time: 0.5063 [2021-03-27 09:17:38 swin_small_patch4_window7_224] INFO: Epoch: [291] [1010/1251] eta: 0:02:02 lr: 0.000012 loss: 2.7528 (2.7008) grad_norm: 3.1071 (3.4806) time: 0.5042 [2021-03-27 09:17:43 swin_small_patch4_window7_224] INFO: Epoch: [291] [1020/1251] eta: 0:01:57 lr: 0.000012 loss: 2.7818 (2.7024) grad_norm: 3.1071 (3.4771) time: 0.5062 [2021-03-27 09:17:48 swin_small_patch4_window7_224] INFO: Epoch: [291] [1030/1251] eta: 0:01:52 lr: 0.000012 loss: 2.7826 (2.7023) grad_norm: 3.1415 (3.4822) time: 0.5084 [2021-03-27 09:17:53 swin_small_patch4_window7_224] INFO: Epoch: [291] [1040/1251] eta: 0:01:47 lr: 0.000012 loss: 2.8317 (2.7043) grad_norm: 3.1857 (3.4822) time: 0.5090 [2021-03-27 09:17:58 swin_small_patch4_window7_224] INFO: Epoch: [291] [1050/1251] eta: 0:01:42 lr: 0.000012 loss: 2.8317 (2.7055) grad_norm: 3.0664 (3.4791) time: 0.5037 [2021-03-27 09:18:03 swin_small_patch4_window7_224] INFO: Epoch: [291] [1060/1251] eta: 0:01:37 lr: 0.000012 loss: 2.8829 (2.7071) grad_norm: 3.1102 (3.4802) time: 0.5020 [2021-03-27 09:18:08 swin_small_patch4_window7_224] INFO: Epoch: [291] [1070/1251] eta: 0:01:32 lr: 0.000012 loss: 2.8212 (2.7064) grad_norm: 3.1351 (3.4771) time: 0.5050 [2021-03-27 09:18:13 swin_small_patch4_window7_224] INFO: Epoch: [291] [1080/1251] eta: 0:01:27 lr: 0.000012 loss: 2.6938 (2.7053) grad_norm: 3.0347 (3.4741) time: 0.5041 [2021-03-27 09:18:19 swin_small_patch4_window7_224] INFO: Epoch: [291] [1090/1251] eta: 0:01:22 lr: 0.000012 loss: 2.6938 (2.7046) grad_norm: 3.3898 (3.4768) time: 0.5049 [2021-03-27 09:18:24 swin_small_patch4_window7_224] INFO: Epoch: [291] [1100/1251] eta: 0:01:16 lr: 0.000012 loss: 2.5188 (2.7026) grad_norm: 3.4315 (3.4781) time: 0.5107 [2021-03-27 09:18:29 swin_small_patch4_window7_224] INFO: Epoch: [291] [1110/1251] eta: 0:01:11 lr: 0.000012 loss: 2.5119 (2.7009) grad_norm: 3.3153 (3.4776) time: 0.5037 [2021-03-27 09:18:34 swin_small_patch4_window7_224] INFO: Epoch: [291] [1120/1251] eta: 0:01:06 lr: 0.000012 loss: 2.6780 (2.7021) grad_norm: 3.1567 (3.4759) time: 0.5000 [2021-03-27 09:18:39 swin_small_patch4_window7_224] INFO: Epoch: [291] [1130/1251] eta: 0:01:01 lr: 0.000012 loss: 2.8050 (2.7022) grad_norm: 3.1567 (3.4750) time: 0.5000 [2021-03-27 09:18:44 swin_small_patch4_window7_224] INFO: Epoch: [291] [1140/1251] eta: 0:00:56 lr: 0.000012 loss: 2.6437 (2.7016) grad_norm: 3.1401 (3.4725) time: 0.4977 [2021-03-27 09:18:49 swin_small_patch4_window7_224] INFO: Epoch: [291] [1150/1251] eta: 0:00:51 lr: 0.000012 loss: 2.7887 (2.7028) grad_norm: 3.2924 (3.4742) time: 0.5011 [2021-03-27 09:18:54 swin_small_patch4_window7_224] INFO: Epoch: [291] [1160/1251] eta: 0:00:46 lr: 0.000012 loss: 2.8719 (2.7030) grad_norm: 3.4878 (3.4748) time: 0.5034 [2021-03-27 09:18:59 swin_small_patch4_window7_224] INFO: Epoch: [291] [1170/1251] eta: 0:00:41 lr: 0.000012 loss: 2.8055 (2.7032) grad_norm: 3.2966 (3.4736) time: 0.4995 [2021-03-27 09:19:04 swin_small_patch4_window7_224] INFO: Epoch: [291] [1180/1251] eta: 0:00:36 lr: 0.000012 loss: 2.8704 (2.7036) grad_norm: 3.1363 (3.4792) time: 0.5043 [2021-03-27 09:19:09 swin_small_patch4_window7_224] INFO: Epoch: [291] [1190/1251] eta: 0:00:31 lr: 0.000012 loss: 2.7511 (2.7017) grad_norm: 3.2790 (3.4804) time: 0.5078 [2021-03-27 09:19:14 swin_small_patch4_window7_224] INFO: Epoch: [291] [1200/1251] eta: 0:00:25 lr: 0.000012 loss: 2.7324 (2.7033) grad_norm: 3.0894 (3.4771) time: 0.4997 [2021-03-27 09:19:19 swin_small_patch4_window7_224] INFO: Epoch: [291] [1210/1251] eta: 0:00:20 lr: 0.000012 loss: 2.8271 (2.7032) grad_norm: 3.0752 (3.4756) time: 0.5005 [2021-03-27 09:19:24 swin_small_patch4_window7_224] INFO: Epoch: [291] [1220/1251] eta: 0:00:15 lr: 0.000012 loss: 2.6576 (2.7016) grad_norm: 3.1971 (3.4758) time: 0.5032 [2021-03-27 09:19:29 swin_small_patch4_window7_224] INFO: Epoch: [291] [1230/1251] eta: 0:00:10 lr: 0.000012 loss: 2.6011 (2.7019) grad_norm: 3.3055 (3.4762) time: 0.4967 [2021-03-27 09:19:34 swin_small_patch4_window7_224] INFO: Epoch: [291] [1240/1251] eta: 0:00:05 lr: 0.000012 loss: 2.7811 (2.7034) grad_norm: 3.2162 (3.4758) time: 0.4949 [2021-03-27 09:19:39 swin_small_patch4_window7_224] INFO: Epoch: [291] [1250/1251] eta: 0:00:00 lr: 0.000012 loss: 2.7736 (2.7036) grad_norm: 3.1547 (3.4751) time: 0.4925 [2021-03-27 09:19:49 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:53 loss: 0.7353 (0.7353) acc1: 78.1250 (78.1250) acc5: 100.0000 (100.0000) [2021-03-27 09:19:52 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.6973 (0.6936) acc1: 84.3750 (83.5227) acc5: 98.4375 (97.4432) [2021-03-27 09:19:54 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.6672 (0.6972) acc1: 82.8125 (83.1101) acc5: 96.8750 (96.9494) [2021-03-27 09:19:57 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7344 (0.7298) acc1: 81.2500 (82.7117) acc5: 95.3125 (96.4718) [2021-03-27 09:19:58 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7981 (0.7692) acc1: 79.6875 (81.6692) acc5: 95.3125 (95.8460) [2021-03-27 09:19:59 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.8115 (0.7520) acc1: 81.2500 (82.3680) acc5: 95.3125 (96.0320) [2021-03-27 09:20:12 swin_small_patch4_window7_224] INFO: * Acc@1 83.084 Acc@5 96.266 loss 0.737 [2021-03-27 09:20:12 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 09:20:12 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 09:20:17 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 0/1251] eta: 1:29:30 lr: 0.000012 loss: 2.7109 (2.7109) grad_norm: 3.4567 (3.4567) time: 4.2927 [2021-03-27 09:20:22 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 10/1251] eta: 0:17:32 lr: 0.000012 loss: 2.8523 (2.7696) grad_norm: 3.0602 (3.2581) time: 0.8485 [2021-03-27 09:20:27 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 20/1251] eta: 0:14:09 lr: 0.000012 loss: 2.8523 (2.7830) grad_norm: 3.0602 (3.2732) time: 0.5099 [2021-03-27 09:20:32 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 30/1251] eta: 0:12:45 lr: 0.000012 loss: 2.8323 (2.7363) grad_norm: 3.2577 (3.2637) time: 0.5051 [2021-03-27 09:20:37 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 40/1251] eta: 0:12:06 lr: 0.000012 loss: 2.7244 (2.6900) grad_norm: 3.3973 (3.3482) time: 0.5058 [2021-03-27 09:20:42 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 50/1251] eta: 0:11:37 lr: 0.000012 loss: 2.7244 (2.6885) grad_norm: 3.3506 (3.3396) time: 0.5102 [2021-03-27 09:20:47 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 60/1251] eta: 0:11:16 lr: 0.000012 loss: 2.7988 (2.7079) grad_norm: 3.2408 (3.3300) time: 0.5022 [2021-03-27 09:20:52 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 70/1251] eta: 0:11:02 lr: 0.000012 loss: 2.8990 (2.7212) grad_norm: 3.2967 (3.3389) time: 0.5083 [2021-03-27 09:20:57 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 80/1251] eta: 0:10:47 lr: 0.000012 loss: 2.8979 (2.7258) grad_norm: 3.2967 (3.3928) time: 0.5063 [2021-03-27 09:21:02 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 90/1251] eta: 0:10:35 lr: 0.000012 loss: 2.8552 (2.7335) grad_norm: 3.2014 (3.4368) time: 0.5014 [2021-03-27 09:21:07 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 100/1251] eta: 0:10:24 lr: 0.000012 loss: 2.8401 (2.7439) grad_norm: 3.9028 (3.4632) time: 0.5028 [2021-03-27 09:21:12 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 110/1251] eta: 0:10:16 lr: 0.000012 loss: 2.8084 (2.7331) grad_norm: 3.3471 (3.4446) time: 0.5079 [2021-03-27 09:21:17 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 120/1251] eta: 0:10:08 lr: 0.000012 loss: 2.8160 (2.7402) grad_norm: 3.0574 (3.4126) time: 0.5140 [2021-03-27 09:21:22 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 130/1251] eta: 0:10:00 lr: 0.000012 loss: 2.8485 (2.7439) grad_norm: 3.1131 (3.4245) time: 0.5063 [2021-03-27 09:21:27 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 140/1251] eta: 0:09:51 lr: 0.000012 loss: 2.8662 (2.7560) grad_norm: 3.1818 (3.4177) time: 0.5007 [2021-03-27 09:21:32 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 150/1251] eta: 0:09:44 lr: 0.000012 loss: 2.7907 (2.7494) grad_norm: 3.0964 (3.4050) time: 0.5011 [2021-03-27 09:21:37 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 160/1251] eta: 0:09:36 lr: 0.000012 loss: 2.6576 (2.7442) grad_norm: 3.0987 (3.3946) time: 0.5009 [2021-03-27 09:21:42 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 170/1251] eta: 0:09:29 lr: 0.000012 loss: 2.7471 (2.7443) grad_norm: 3.0826 (3.4048) time: 0.4997 [2021-03-27 09:21:48 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 180/1251] eta: 0:09:23 lr: 0.000012 loss: 2.7471 (2.7458) grad_norm: 3.1174 (3.4257) time: 0.5036 [2021-03-27 09:21:53 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 190/1251] eta: 0:09:17 lr: 0.000012 loss: 2.8435 (2.7435) grad_norm: 3.2331 (3.4342) time: 0.5139 [2021-03-27 09:21:58 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 200/1251] eta: 0:09:11 lr: 0.000012 loss: 2.8523 (2.7446) grad_norm: 3.1369 (3.4326) time: 0.5116 [2021-03-27 09:22:03 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 210/1251] eta: 0:09:05 lr: 0.000012 loss: 2.7867 (2.7403) grad_norm: 3.2635 (3.4375) time: 0.5106 [2021-03-27 09:22:08 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 220/1251] eta: 0:09:00 lr: 0.000012 loss: 2.7737 (2.7436) grad_norm: 3.2635 (3.4382) time: 0.5175 [2021-03-27 09:22:13 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 230/1251] eta: 0:08:53 lr: 0.000012 loss: 2.6898 (2.7390) grad_norm: 3.1834 (3.4268) time: 0.5093 [2021-03-27 09:22:18 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 240/1251] eta: 0:08:48 lr: 0.000012 loss: 2.9234 (2.7478) grad_norm: 3.2056 (3.4290) time: 0.5052 [2021-03-27 09:22:23 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 250/1251] eta: 0:08:42 lr: 0.000012 loss: 2.8913 (2.7481) grad_norm: 3.2209 (3.4233) time: 0.5075 [2021-03-27 09:22:28 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 260/1251] eta: 0:08:36 lr: 0.000012 loss: 2.7855 (2.7453) grad_norm: 3.0354 (3.4110) time: 0.5082 [2021-03-27 09:22:33 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 270/1251] eta: 0:08:30 lr: 0.000012 loss: 2.7542 (2.7437) grad_norm: 3.1302 (3.4174) time: 0.5067 [2021-03-27 09:22:38 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 280/1251] eta: 0:08:25 lr: 0.000012 loss: 2.7939 (2.7452) grad_norm: 3.3828 (3.4271) time: 0.5047 [2021-03-27 09:22:44 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 290/1251] eta: 0:08:19 lr: 0.000012 loss: 2.9817 (2.7495) grad_norm: 3.2560 (3.4238) time: 0.5074 [2021-03-27 09:22:49 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 300/1251] eta: 0:08:14 lr: 0.000012 loss: 2.8723 (2.7477) grad_norm: 3.2560 (3.4242) time: 0.5179 [2021-03-27 09:22:54 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 310/1251] eta: 0:08:09 lr: 0.000012 loss: 2.8015 (2.7448) grad_norm: 3.4416 (3.4323) time: 0.5241 [2021-03-27 09:22:59 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 320/1251] eta: 0:08:03 lr: 0.000012 loss: 2.6989 (2.7435) grad_norm: 3.4217 (3.4387) time: 0.5141 [2021-03-27 09:23:04 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 330/1251] eta: 0:07:58 lr: 0.000012 loss: 2.6498 (2.7378) grad_norm: 3.3532 (3.4407) time: 0.5038 [2021-03-27 09:23:09 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 340/1251] eta: 0:07:52 lr: 0.000012 loss: 2.7009 (2.7364) grad_norm: 3.2276 (3.4361) time: 0.5055 [2021-03-27 09:23:14 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 350/1251] eta: 0:07:47 lr: 0.000012 loss: 2.8189 (2.7329) grad_norm: 3.2150 (3.4469) time: 0.5139 [2021-03-27 09:23:20 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 360/1251] eta: 0:07:41 lr: 0.000012 loss: 2.7690 (2.7344) grad_norm: 3.2847 (3.4540) time: 0.5125 [2021-03-27 09:23:25 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 370/1251] eta: 0:07:36 lr: 0.000012 loss: 2.7812 (2.7384) grad_norm: 3.3305 (3.4571) time: 0.5054 [2021-03-27 09:23:30 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 380/1251] eta: 0:07:31 lr: 0.000012 loss: 2.8466 (2.7355) grad_norm: 3.5073 (3.4549) time: 0.5073 [2021-03-27 09:23:35 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 390/1251] eta: 0:07:25 lr: 0.000012 loss: 2.7827 (2.7329) grad_norm: 3.2566 (3.4526) time: 0.5106 [2021-03-27 09:23:40 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 400/1251] eta: 0:07:20 lr: 0.000012 loss: 2.6994 (2.7319) grad_norm: 3.2632 (3.4514) time: 0.5047 [2021-03-27 09:23:45 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 410/1251] eta: 0:07:14 lr: 0.000012 loss: 2.7250 (2.7333) grad_norm: 3.2632 (3.4657) time: 0.5050 [2021-03-27 09:23:50 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 420/1251] eta: 0:07:09 lr: 0.000012 loss: 2.8746 (2.7352) grad_norm: 3.1758 (3.4622) time: 0.5070 [2021-03-27 09:23:55 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 430/1251] eta: 0:07:03 lr: 0.000012 loss: 2.8729 (2.7375) grad_norm: 3.1885 (3.4819) time: 0.5009 [2021-03-27 09:24:00 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 440/1251] eta: 0:06:58 lr: 0.000012 loss: 2.8535 (2.7408) grad_norm: 3.1372 (3.4740) time: 0.4979 [2021-03-27 09:24:05 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 450/1251] eta: 0:06:52 lr: 0.000012 loss: 2.8544 (2.7420) grad_norm: 3.1851 (3.4731) time: 0.5003 [2021-03-27 09:24:10 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 460/1251] eta: 0:06:47 lr: 0.000012 loss: 2.7945 (2.7400) grad_norm: 3.1851 (3.4647) time: 0.4989 [2021-03-27 09:24:15 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 470/1251] eta: 0:06:42 lr: 0.000012 loss: 2.8142 (2.7449) grad_norm: 3.1403 (3.4610) time: 0.4989 [2021-03-27 09:24:20 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 480/1251] eta: 0:06:36 lr: 0.000012 loss: 2.8756 (2.7444) grad_norm: 3.2817 (3.4734) time: 0.5017 [2021-03-27 09:24:25 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 490/1251] eta: 0:06:31 lr: 0.000012 loss: 2.8756 (2.7467) grad_norm: 3.2817 (3.4694) time: 0.5025 [2021-03-27 09:24:30 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 500/1251] eta: 0:06:25 lr: 0.000012 loss: 2.8050 (2.7460) grad_norm: 3.1368 (3.4636) time: 0.4990 [2021-03-27 09:24:35 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 510/1251] eta: 0:06:20 lr: 0.000012 loss: 2.7694 (2.7464) grad_norm: 3.1944 (3.4675) time: 0.5021 [2021-03-27 09:24:40 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 520/1251] eta: 0:06:15 lr: 0.000012 loss: 2.8015 (2.7484) grad_norm: 3.1944 (3.4594) time: 0.5056 [2021-03-27 09:24:45 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 530/1251] eta: 0:06:10 lr: 0.000012 loss: 2.7861 (2.7476) grad_norm: 3.1032 (3.4626) time: 0.4966 [2021-03-27 09:24:50 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 540/1251] eta: 0:06:04 lr: 0.000012 loss: 2.7007 (2.7481) grad_norm: 3.3726 (3.4628) time: 0.4912 [2021-03-27 09:24:55 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 550/1251] eta: 0:05:59 lr: 0.000012 loss: 2.8584 (2.7508) grad_norm: 3.2402 (3.4584) time: 0.5019 [2021-03-27 09:25:00 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 560/1251] eta: 0:05:54 lr: 0.000012 loss: 2.8327 (2.7491) grad_norm: 3.0946 (3.4532) time: 0.5110 [2021-03-27 09:25:05 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 570/1251] eta: 0:05:49 lr: 0.000012 loss: 2.7726 (2.7503) grad_norm: 3.1388 (3.4521) time: 0.5138 [2021-03-27 09:25:10 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 580/1251] eta: 0:05:44 lr: 0.000012 loss: 2.9021 (2.7482) grad_norm: 3.1882 (3.4508) time: 0.5113 [2021-03-27 09:25:15 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 590/1251] eta: 0:05:38 lr: 0.000012 loss: 2.8473 (2.7473) grad_norm: 3.2730 (3.4517) time: 0.5071 [2021-03-27 09:25:20 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 600/1251] eta: 0:05:33 lr: 0.000012 loss: 2.6805 (2.7442) grad_norm: 3.4119 (3.4584) time: 0.5088 [2021-03-27 09:25:25 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 610/1251] eta: 0:05:28 lr: 0.000012 loss: 2.5047 (2.7399) grad_norm: 3.2034 (3.4537) time: 0.5036 [2021-03-27 09:25:30 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 620/1251] eta: 0:05:23 lr: 0.000012 loss: 2.5835 (2.7361) grad_norm: 3.0814 (3.4487) time: 0.4972 [2021-03-27 09:25:35 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 630/1251] eta: 0:05:17 lr: 0.000012 loss: 2.7597 (2.7358) grad_norm: 2.9704 (3.4453) time: 0.4936 [2021-03-27 09:25:40 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 640/1251] eta: 0:05:12 lr: 0.000012 loss: 2.7597 (2.7341) grad_norm: 3.0765 (3.4526) time: 0.4954 [2021-03-27 09:25:45 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 650/1251] eta: 0:05:07 lr: 0.000012 loss: 2.6476 (2.7325) grad_norm: 3.2072 (3.4768) time: 0.5055 [2021-03-27 09:25:50 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 660/1251] eta: 0:05:02 lr: 0.000012 loss: 2.6476 (2.7322) grad_norm: 3.2894 (3.4735) time: 0.5105 [2021-03-27 09:25:56 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 670/1251] eta: 0:04:57 lr: 0.000012 loss: 2.5683 (2.7281) grad_norm: 3.3048 (3.4743) time: 0.5100 [2021-03-27 09:26:01 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 680/1251] eta: 0:04:51 lr: 0.000012 loss: 2.6106 (2.7276) grad_norm: 3.4212 (3.4767) time: 0.5072 [2021-03-27 09:26:06 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 690/1251] eta: 0:04:46 lr: 0.000012 loss: 2.7714 (2.7266) grad_norm: 3.3506 (3.4742) time: 0.5048 [2021-03-27 09:26:11 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 700/1251] eta: 0:04:41 lr: 0.000012 loss: 2.9305 (2.7260) grad_norm: 3.3133 (3.4781) time: 0.5098 [2021-03-27 09:26:16 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 710/1251] eta: 0:04:36 lr: 0.000011 loss: 2.9392 (2.7268) grad_norm: 3.3405 (3.4758) time: 0.5075 [2021-03-27 09:26:21 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 720/1251] eta: 0:04:31 lr: 0.000011 loss: 2.5535 (2.7228) grad_norm: 3.2149 (3.4721) time: 0.5038 [2021-03-27 09:26:26 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 730/1251] eta: 0:04:26 lr: 0.000011 loss: 2.5535 (2.7250) grad_norm: 3.3068 (3.4728) time: 0.5094 [2021-03-27 09:26:31 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 740/1251] eta: 0:04:21 lr: 0.000011 loss: 2.9410 (2.7246) grad_norm: 3.4136 (3.4773) time: 0.5214 [2021-03-27 09:26:36 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 750/1251] eta: 0:04:16 lr: 0.000011 loss: 2.5579 (2.7225) grad_norm: 3.3112 (3.4775) time: 0.5182 [2021-03-27 09:26:42 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 760/1251] eta: 0:04:11 lr: 0.000011 loss: 2.3852 (2.7187) grad_norm: 3.1180 (3.4725) time: 0.5083 [2021-03-27 09:26:47 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 770/1251] eta: 0:04:05 lr: 0.000011 loss: 2.3758 (2.7140) grad_norm: 3.0408 (3.4664) time: 0.5083 [2021-03-27 09:26:52 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 780/1251] eta: 0:04:00 lr: 0.000011 loss: 2.6117 (2.7138) grad_norm: 3.0830 (3.4696) time: 0.5031 [2021-03-27 09:26:57 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 790/1251] eta: 0:03:55 lr: 0.000011 loss: 2.7302 (2.7154) grad_norm: 3.4388 (3.4715) time: 0.5123 [2021-03-27 09:27:02 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 800/1251] eta: 0:03:50 lr: 0.000011 loss: 2.7026 (2.7145) grad_norm: 3.4201 (3.4714) time: 0.5138 [2021-03-27 09:27:07 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 810/1251] eta: 0:03:45 lr: 0.000011 loss: 2.6356 (2.7120) grad_norm: 3.2954 (3.4704) time: 0.5106 [2021-03-27 09:27:12 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 820/1251] eta: 0:03:40 lr: 0.000011 loss: 2.6924 (2.7114) grad_norm: 3.2219 (3.4680) time: 0.5122 [2021-03-27 09:27:17 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 830/1251] eta: 0:03:35 lr: 0.000011 loss: 2.7391 (2.7104) grad_norm: 3.1927 (3.4693) time: 0.5063 [2021-03-27 09:27:22 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 840/1251] eta: 0:03:30 lr: 0.000011 loss: 2.7747 (2.7118) grad_norm: 3.3069 (3.4674) time: 0.5043 [2021-03-27 09:27:27 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 850/1251] eta: 0:03:24 lr: 0.000011 loss: 2.7477 (2.7099) grad_norm: 3.3256 (3.4772) time: 0.5029 [2021-03-27 09:27:32 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 860/1251] eta: 0:03:19 lr: 0.000011 loss: 2.7477 (2.7099) grad_norm: 3.5525 (3.4856) time: 0.5091 [2021-03-27 09:27:38 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 870/1251] eta: 0:03:14 lr: 0.000011 loss: 2.7368 (2.7087) grad_norm: 3.3410 (3.4875) time: 0.5130 [2021-03-27 09:27:43 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 880/1251] eta: 0:03:09 lr: 0.000011 loss: 2.7417 (2.7096) grad_norm: 3.3045 (3.4885) time: 0.5069 [2021-03-27 09:27:48 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 890/1251] eta: 0:03:04 lr: 0.000011 loss: 2.8230 (2.7095) grad_norm: 3.2095 (3.4849) time: 0.4990 [2021-03-27 09:27:52 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 900/1251] eta: 0:02:59 lr: 0.000011 loss: 2.7851 (2.7085) grad_norm: 3.2624 (3.4843) time: 0.4953 [2021-03-27 09:27:57 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 910/1251] eta: 0:02:54 lr: 0.000011 loss: 2.7057 (2.7080) grad_norm: 3.2791 (3.4820) time: 0.4971 [2021-03-27 09:28:03 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 920/1251] eta: 0:02:48 lr: 0.000011 loss: 2.6633 (2.7066) grad_norm: 3.2229 (3.4803) time: 0.5056 [2021-03-27 09:28:08 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 930/1251] eta: 0:02:43 lr: 0.000011 loss: 2.6652 (2.7049) grad_norm: 3.2229 (3.4776) time: 0.5068 [2021-03-27 09:28:13 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 940/1251] eta: 0:02:38 lr: 0.000011 loss: 2.5813 (2.7035) grad_norm: 3.1103 (3.4753) time: 0.5053 [2021-03-27 09:28:18 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 950/1251] eta: 0:02:33 lr: 0.000011 loss: 2.5834 (2.7034) grad_norm: 3.1103 (3.4738) time: 0.5107 [2021-03-27 09:28:23 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 960/1251] eta: 0:02:28 lr: 0.000011 loss: 2.6062 (2.7030) grad_norm: 3.1960 (3.4770) time: 0.5053 [2021-03-27 09:28:28 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 970/1251] eta: 0:02:23 lr: 0.000011 loss: 2.7843 (2.7036) grad_norm: 3.1534 (3.4751) time: 0.5019 [2021-03-27 09:28:33 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 980/1251] eta: 0:02:18 lr: 0.000011 loss: 2.6780 (2.7024) grad_norm: 3.1908 (3.4745) time: 0.5029 [2021-03-27 09:28:38 swin_small_patch4_window7_224] INFO: Epoch: [292] [ 990/1251] eta: 0:02:13 lr: 0.000011 loss: 2.5611 (2.7026) grad_norm: 3.2702 (nan) time: 0.4986 [2021-03-27 09:28:43 swin_small_patch4_window7_224] INFO: Epoch: [292] [1000/1251] eta: 0:02:07 lr: 0.000011 loss: 2.6008 (2.7022) grad_norm: 3.3486 (nan) time: 0.5015 [2021-03-27 09:28:48 swin_small_patch4_window7_224] INFO: Epoch: [292] [1010/1251] eta: 0:02:02 lr: 0.000011 loss: 2.6640 (2.7010) grad_norm: 3.3638 (nan) time: 0.5120 [2021-03-27 09:28:53 swin_small_patch4_window7_224] INFO: Epoch: [292] [1020/1251] eta: 0:01:57 lr: 0.000011 loss: 2.6640 (2.7010) grad_norm: 3.0729 (nan) time: 0.5099 [2021-03-27 09:28:58 swin_small_patch4_window7_224] INFO: Epoch: [292] [1030/1251] eta: 0:01:52 lr: 0.000011 loss: 2.8224 (2.7018) grad_norm: 3.0413 (nan) time: 0.4986 [2021-03-27 09:29:03 swin_small_patch4_window7_224] INFO: Epoch: [292] [1040/1251] eta: 0:01:47 lr: 0.000011 loss: 2.7839 (2.7005) grad_norm: 3.3729 (nan) time: 0.4988 [2021-03-27 09:29:08 swin_small_patch4_window7_224] INFO: Epoch: [292] [1050/1251] eta: 0:01:42 lr: 0.000011 loss: 2.6610 (2.6983) grad_norm: 3.4273 (nan) time: 0.5046 [2021-03-27 09:29:13 swin_small_patch4_window7_224] INFO: Epoch: [292] [1060/1251] eta: 0:01:37 lr: 0.000011 loss: 2.6634 (2.6974) grad_norm: 3.5387 (nan) time: 0.5077 [2021-03-27 09:29:18 swin_small_patch4_window7_224] INFO: Epoch: [292] [1070/1251] eta: 0:01:32 lr: 0.000011 loss: 2.7638 (2.6981) grad_norm: 3.3051 (nan) time: 0.5039 [2021-03-27 09:29:23 swin_small_patch4_window7_224] INFO: Epoch: [292] [1080/1251] eta: 0:01:27 lr: 0.000011 loss: 2.7400 (2.6985) grad_norm: 3.1193 (nan) time: 0.5016 [2021-03-27 09:29:28 swin_small_patch4_window7_224] INFO: Epoch: [292] [1090/1251] eta: 0:01:22 lr: 0.000011 loss: 2.4813 (2.6946) grad_norm: 3.2089 (nan) time: 0.5027 [2021-03-27 09:29:33 swin_small_patch4_window7_224] INFO: Epoch: [292] [1100/1251] eta: 0:01:16 lr: 0.000011 loss: 2.3030 (2.6944) grad_norm: 3.3533 (nan) time: 0.5041 [2021-03-27 09:29:38 swin_small_patch4_window7_224] INFO: Epoch: [292] [1110/1251] eta: 0:01:11 lr: 0.000011 loss: 2.5837 (2.6934) grad_norm: 3.3235 (nan) time: 0.5012 [2021-03-27 09:29:43 swin_small_patch4_window7_224] INFO: Epoch: [292] [1120/1251] eta: 0:01:06 lr: 0.000011 loss: 2.7167 (2.6936) grad_norm: 3.3883 (nan) time: 0.5030 [2021-03-27 09:29:48 swin_small_patch4_window7_224] INFO: Epoch: [292] [1130/1251] eta: 0:01:01 lr: 0.000011 loss: 2.9352 (2.6956) grad_norm: 3.4204 (nan) time: 0.5065 [2021-03-27 09:29:53 swin_small_patch4_window7_224] INFO: Epoch: [292] [1140/1251] eta: 0:00:56 lr: 0.000011 loss: 2.9512 (2.6974) grad_norm: 3.2429 (nan) time: 0.5052 [2021-03-27 09:29:58 swin_small_patch4_window7_224] INFO: Epoch: [292] [1150/1251] eta: 0:00:51 lr: 0.000011 loss: 2.9407 (2.6972) grad_norm: 3.1099 (nan) time: 0.5028 [2021-03-27 09:30:04 swin_small_patch4_window7_224] INFO: Epoch: [292] [1160/1251] eta: 0:00:46 lr: 0.000011 loss: 2.9131 (2.6970) grad_norm: 3.1521 (nan) time: 0.5014 [2021-03-27 09:30:09 swin_small_patch4_window7_224] INFO: Epoch: [292] [1170/1251] eta: 0:00:41 lr: 0.000011 loss: 2.5311 (2.6963) grad_norm: 3.1521 (nan) time: 0.5023 [2021-03-27 09:30:14 swin_small_patch4_window7_224] INFO: Epoch: [292] [1180/1251] eta: 0:00:36 lr: 0.000011 loss: 2.5684 (2.6957) grad_norm: 3.0043 (nan) time: 0.5065 [2021-03-27 09:30:19 swin_small_patch4_window7_224] INFO: Epoch: [292] [1190/1251] eta: 0:00:31 lr: 0.000011 loss: 2.5893 (2.6945) grad_norm: 3.1711 (nan) time: 0.5023 [2021-03-27 09:30:24 swin_small_patch4_window7_224] INFO: Epoch: [292] [1200/1251] eta: 0:00:25 lr: 0.000011 loss: 2.6928 (2.6945) grad_norm: 3.1711 (nan) time: 0.4986 [2021-03-27 09:30:29 swin_small_patch4_window7_224] INFO: Epoch: [292] [1210/1251] eta: 0:00:20 lr: 0.000011 loss: 2.8548 (2.6962) grad_norm: 3.1710 (nan) time: 0.5029 [2021-03-27 09:30:34 swin_small_patch4_window7_224] INFO: Epoch: [292] [1220/1251] eta: 0:00:15 lr: 0.000011 loss: 2.8940 (2.6974) grad_norm: 3.2482 (nan) time: 0.5002 [2021-03-27 09:30:39 swin_small_patch4_window7_224] INFO: Epoch: [292] [1230/1251] eta: 0:00:10 lr: 0.000011 loss: 2.7799 (2.6970) grad_norm: 3.3129 (nan) time: 0.5004 [2021-03-27 09:30:44 swin_small_patch4_window7_224] INFO: Epoch: [292] [1240/1251] eta: 0:00:05 lr: 0.000011 loss: 2.7323 (2.6977) grad_norm: 3.2544 (nan) time: 0.5039 [2021-03-27 09:30:49 swin_small_patch4_window7_224] INFO: Epoch: [292] [1250/1251] eta: 0:00:00 lr: 0.000011 loss: 2.7267 (2.6961) grad_norm: 3.1873 (nan) time: 0.5073 [2021-03-27 09:31:00 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:02 loss: 0.6051 (0.6051) acc1: 84.3750 (84.3750) acc5: 95.3125 (95.3125) [2021-03-27 09:31:02 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.8418 (0.8351) acc1: 79.6875 (80.1136) acc5: 96.8750 (95.3125) [2021-03-27 09:31:04 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.8239 (0.8063) acc1: 79.6875 (80.3571) acc5: 96.8750 (95.6845) [2021-03-27 09:31:06 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.8143 (0.7778) acc1: 81.2500 (81.5524) acc5: 95.3125 (95.6653) [2021-03-27 09:31:08 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7313 (0.7679) acc1: 82.8125 (81.5549) acc5: 95.3125 (95.7698) [2021-03-27 09:31:10 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6862 (0.7487) acc1: 84.3750 (82.2080) acc5: 96.2264 (95.9360) [2021-03-27 09:31:27 swin_small_patch4_window7_224] INFO: * Acc@1 83.082 Acc@5 96.226 loss 0.734 [2021-03-27 09:31:27 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 09:31:27 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 09:31:31 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 0/1251] eta: 1:24:14 lr: 0.000011 loss: 2.7132 (2.7132) grad_norm: 3.7438 (3.7438) time: 4.0402 [2021-03-27 09:31:36 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 10/1251] eta: 0:17:16 lr: 0.000011 loss: 2.7132 (2.6845) grad_norm: 3.3967 (3.3469) time: 0.8354 [2021-03-27 09:31:42 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 20/1251] eta: 0:13:55 lr: 0.000011 loss: 2.8271 (2.7266) grad_norm: 3.2908 (3.5999) time: 0.5109 [2021-03-27 09:31:47 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 30/1251] eta: 0:12:47 lr: 0.000011 loss: 2.7833 (2.6473) grad_norm: 3.3203 (3.8425) time: 0.5150 [2021-03-27 09:31:52 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 40/1251] eta: 0:12:03 lr: 0.000011 loss: 2.5689 (2.6283) grad_norm: 3.4813 (3.7384) time: 0.5111 [2021-03-27 09:31:57 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 50/1251] eta: 0:11:35 lr: 0.000011 loss: 2.7236 (2.6565) grad_norm: 3.2977 (3.6875) time: 0.5032 [2021-03-27 09:32:02 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 60/1251] eta: 0:11:16 lr: 0.000011 loss: 2.7650 (2.6710) grad_norm: 3.3150 (3.7944) time: 0.5090 [2021-03-27 09:32:07 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 70/1251] eta: 0:11:04 lr: 0.000011 loss: 2.7668 (2.7033) grad_norm: 3.3392 (3.7913) time: 0.5195 [2021-03-27 09:32:12 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 80/1251] eta: 0:10:51 lr: 0.000011 loss: 2.8632 (2.7153) grad_norm: 3.3269 (3.7413) time: 0.5196 [2021-03-27 09:32:17 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 90/1251] eta: 0:10:39 lr: 0.000011 loss: 2.8013 (2.7211) grad_norm: 3.3269 (3.7238) time: 0.5104 [2021-03-27 09:32:22 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 100/1251] eta: 0:10:28 lr: 0.000011 loss: 2.6670 (2.6974) grad_norm: 3.4001 (3.6931) time: 0.5058 [2021-03-27 09:32:27 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 110/1251] eta: 0:10:19 lr: 0.000011 loss: 2.4794 (2.6950) grad_norm: 3.4292 (3.6883) time: 0.5043 [2021-03-27 09:32:33 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 120/1251] eta: 0:10:10 lr: 0.000011 loss: 2.6241 (2.6818) grad_norm: 3.4133 (3.6621) time: 0.5061 [2021-03-27 09:32:38 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 130/1251] eta: 0:10:02 lr: 0.000011 loss: 2.7086 (2.6853) grad_norm: 3.1901 (3.6367) time: 0.5056 [2021-03-27 09:32:43 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 140/1251] eta: 0:09:54 lr: 0.000011 loss: 2.7710 (2.6939) grad_norm: 3.1372 (3.6158) time: 0.5052 [2021-03-27 09:32:48 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 150/1251] eta: 0:09:47 lr: 0.000011 loss: 2.7206 (2.6829) grad_norm: 3.2029 (3.6052) time: 0.5103 [2021-03-27 09:32:53 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 160/1251] eta: 0:09:40 lr: 0.000011 loss: 2.5744 (2.6788) grad_norm: 3.1605 (3.5745) time: 0.5138 [2021-03-27 09:32:58 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 170/1251] eta: 0:09:33 lr: 0.000011 loss: 2.4513 (2.6743) grad_norm: 3.2306 (3.5672) time: 0.5070 [2021-03-27 09:33:03 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 180/1251] eta: 0:09:25 lr: 0.000011 loss: 2.4853 (2.6687) grad_norm: 3.3078 (3.5517) time: 0.4981 [2021-03-27 09:33:08 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 190/1251] eta: 0:09:19 lr: 0.000011 loss: 2.6900 (2.6596) grad_norm: 3.3720 (3.5445) time: 0.5040 [2021-03-27 09:33:13 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 200/1251] eta: 0:09:13 lr: 0.000011 loss: 2.7939 (2.6675) grad_norm: 3.3821 (3.5398) time: 0.5142 [2021-03-27 09:33:18 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 210/1251] eta: 0:09:07 lr: 0.000011 loss: 2.6515 (2.6598) grad_norm: 3.3821 (3.5541) time: 0.5108 [2021-03-27 09:33:23 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 220/1251] eta: 0:09:01 lr: 0.000011 loss: 2.5649 (2.6647) grad_norm: 3.1988 (3.5438) time: 0.5052 [2021-03-27 09:33:28 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 230/1251] eta: 0:08:55 lr: 0.000011 loss: 2.7068 (2.6648) grad_norm: 3.1870 (3.5321) time: 0.5088 [2021-03-27 09:33:33 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 240/1251] eta: 0:08:49 lr: 0.000011 loss: 2.7542 (2.6671) grad_norm: 3.2533 (3.5187) time: 0.5084 [2021-03-27 09:33:38 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 250/1251] eta: 0:08:43 lr: 0.000011 loss: 2.8752 (2.6794) grad_norm: 3.3136 (3.5281) time: 0.5012 [2021-03-27 09:33:43 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 260/1251] eta: 0:08:37 lr: 0.000011 loss: 2.9619 (2.6855) grad_norm: 3.5054 (3.5396) time: 0.5001 [2021-03-27 09:33:49 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 270/1251] eta: 0:08:31 lr: 0.000011 loss: 2.7731 (2.6855) grad_norm: 3.3003 (3.5246) time: 0.5022 [2021-03-27 09:33:53 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 280/1251] eta: 0:08:25 lr: 0.000011 loss: 2.7731 (2.6883) grad_norm: 3.2833 (3.5212) time: 0.4982 [2021-03-27 09:33:58 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 290/1251] eta: 0:08:19 lr: 0.000011 loss: 2.7877 (2.6904) grad_norm: 3.2420 (3.5062) time: 0.4948 [2021-03-27 09:34:03 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 300/1251] eta: 0:08:13 lr: 0.000011 loss: 2.7792 (2.6889) grad_norm: 3.1007 (3.4987) time: 0.5022 [2021-03-27 09:34:09 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 310/1251] eta: 0:08:08 lr: 0.000011 loss: 2.8163 (2.6893) grad_norm: 3.2438 (3.4929) time: 0.5085 [2021-03-27 09:34:14 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 320/1251] eta: 0:08:02 lr: 0.000011 loss: 2.8500 (2.6932) grad_norm: 3.3478 (3.4878) time: 0.5038 [2021-03-27 09:34:19 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 330/1251] eta: 0:07:56 lr: 0.000011 loss: 2.9534 (2.7025) grad_norm: 3.4637 (3.4903) time: 0.4986 [2021-03-27 09:34:24 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 340/1251] eta: 0:07:50 lr: 0.000011 loss: 2.9925 (2.7065) grad_norm: 3.4450 (3.4871) time: 0.5011 [2021-03-27 09:34:29 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 350/1251] eta: 0:07:45 lr: 0.000011 loss: 2.8811 (2.7085) grad_norm: 3.1963 (3.4968) time: 0.5006 [2021-03-27 09:34:34 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 360/1251] eta: 0:07:39 lr: 0.000011 loss: 2.8787 (2.7117) grad_norm: 3.3161 (3.4901) time: 0.5023 [2021-03-27 09:34:39 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 370/1251] eta: 0:07:34 lr: 0.000011 loss: 2.8787 (2.7123) grad_norm: 3.3372 (3.4844) time: 0.5017 [2021-03-27 09:34:44 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 380/1251] eta: 0:07:29 lr: 0.000011 loss: 2.8823 (2.7120) grad_norm: 3.3372 (3.4903) time: 0.5043 [2021-03-27 09:34:49 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 390/1251] eta: 0:07:23 lr: 0.000011 loss: 2.8823 (2.7082) grad_norm: 3.3409 (3.4866) time: 0.5107 [2021-03-27 09:34:54 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 400/1251] eta: 0:07:18 lr: 0.000011 loss: 2.9130 (2.7129) grad_norm: 3.2627 (3.4867) time: 0.5135 [2021-03-27 09:34:59 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 410/1251] eta: 0:07:13 lr: 0.000011 loss: 2.9345 (2.7116) grad_norm: 3.2627 (3.4843) time: 0.5097 [2021-03-27 09:35:04 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 420/1251] eta: 0:07:07 lr: 0.000011 loss: 2.7653 (2.7088) grad_norm: 3.0922 (3.4892) time: 0.5063 [2021-03-27 09:35:09 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 430/1251] eta: 0:07:02 lr: 0.000011 loss: 2.7113 (2.7122) grad_norm: 3.3264 (3.4981) time: 0.5102 [2021-03-27 09:35:14 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 440/1251] eta: 0:06:57 lr: 0.000011 loss: 2.8785 (2.7146) grad_norm: 3.3965 (3.5340) time: 0.5054 [2021-03-27 09:35:19 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 450/1251] eta: 0:06:51 lr: 0.000011 loss: 2.8785 (2.7154) grad_norm: 3.3483 (3.5291) time: 0.5016 [2021-03-27 09:35:24 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 460/1251] eta: 0:06:46 lr: 0.000011 loss: 2.8004 (2.7159) grad_norm: 3.3483 (3.5267) time: 0.5070 [2021-03-27 09:35:29 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 470/1251] eta: 0:06:41 lr: 0.000011 loss: 2.8217 (2.7184) grad_norm: 3.4700 (3.5290) time: 0.5057 [2021-03-27 09:35:34 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 480/1251] eta: 0:06:36 lr: 0.000011 loss: 2.8890 (2.7185) grad_norm: 3.5740 (3.5298) time: 0.5038 [2021-03-27 09:35:39 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 490/1251] eta: 0:06:30 lr: 0.000011 loss: 2.6719 (2.7177) grad_norm: 3.4240 (3.5345) time: 0.4999 [2021-03-27 09:35:44 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 500/1251] eta: 0:06:25 lr: 0.000011 loss: 2.5850 (2.7138) grad_norm: 3.2503 (3.5314) time: 0.4996 [2021-03-27 09:35:50 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 510/1251] eta: 0:06:20 lr: 0.000011 loss: 2.6995 (2.7147) grad_norm: 3.1531 (3.5292) time: 0.5079 [2021-03-27 09:35:55 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 520/1251] eta: 0:06:15 lr: 0.000011 loss: 2.7417 (2.7130) grad_norm: 3.1531 (3.5242) time: 0.5089 [2021-03-27 09:36:00 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 530/1251] eta: 0:06:09 lr: 0.000011 loss: 2.7417 (2.7137) grad_norm: 3.5368 (3.5281) time: 0.5072 [2021-03-27 09:36:05 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 540/1251] eta: 0:06:04 lr: 0.000011 loss: 2.7721 (2.7099) grad_norm: 3.6560 (3.5302) time: 0.5012 [2021-03-27 09:36:10 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 550/1251] eta: 0:05:59 lr: 0.000011 loss: 2.8841 (2.7119) grad_norm: 3.4592 (3.5384) time: 0.5142 [2021-03-27 09:36:15 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 560/1251] eta: 0:05:54 lr: 0.000011 loss: 2.7924 (2.7108) grad_norm: 3.4502 (3.5430) time: 0.5210 [2021-03-27 09:36:20 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 570/1251] eta: 0:05:49 lr: 0.000011 loss: 2.7852 (2.7120) grad_norm: 3.3389 (3.5384) time: 0.5072 [2021-03-27 09:36:25 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 580/1251] eta: 0:05:44 lr: 0.000011 loss: 2.8780 (2.7142) grad_norm: 3.2766 (3.5343) time: 0.5078 [2021-03-27 09:36:30 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 590/1251] eta: 0:05:38 lr: 0.000011 loss: 2.8006 (2.7125) grad_norm: 3.2766 (3.5464) time: 0.5096 [2021-03-27 09:36:35 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 600/1251] eta: 0:05:33 lr: 0.000011 loss: 2.6503 (2.7113) grad_norm: 3.3707 (3.5464) time: 0.5058 [2021-03-27 09:36:40 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 610/1251] eta: 0:05:28 lr: 0.000011 loss: 2.5604 (2.7038) grad_norm: 3.5446 (3.5483) time: 0.5013 [2021-03-27 09:36:45 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 620/1251] eta: 0:05:23 lr: 0.000011 loss: 2.5604 (2.7021) grad_norm: 3.5137 (3.5443) time: 0.5032 [2021-03-27 09:36:51 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 630/1251] eta: 0:05:18 lr: 0.000011 loss: 2.7817 (2.7043) grad_norm: 3.2142 (3.5404) time: 0.5070 [2021-03-27 09:36:56 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 640/1251] eta: 0:05:12 lr: 0.000011 loss: 2.7817 (2.7022) grad_norm: 3.2642 (3.5354) time: 0.5070 [2021-03-27 09:37:01 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 650/1251] eta: 0:05:07 lr: 0.000011 loss: 2.6463 (2.7006) grad_norm: 3.2992 (3.5317) time: 0.5060 [2021-03-27 09:37:06 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 660/1251] eta: 0:05:02 lr: 0.000011 loss: 2.8189 (2.7009) grad_norm: 3.2992 (3.5275) time: 0.5040 [2021-03-27 09:37:11 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 670/1251] eta: 0:04:57 lr: 0.000011 loss: 2.8715 (2.7026) grad_norm: 3.2243 (3.5247) time: 0.5062 [2021-03-27 09:37:16 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 680/1251] eta: 0:04:52 lr: 0.000011 loss: 2.8715 (2.7030) grad_norm: 3.1656 (3.5193) time: 0.5105 [2021-03-27 09:37:21 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 690/1251] eta: 0:04:46 lr: 0.000011 loss: 2.8524 (2.7047) grad_norm: 3.1656 (3.5208) time: 0.5030 [2021-03-27 09:37:26 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 700/1251] eta: 0:04:41 lr: 0.000011 loss: 2.8048 (2.7029) grad_norm: 3.2390 (3.5184) time: 0.5016 [2021-03-27 09:37:31 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 710/1251] eta: 0:04:36 lr: 0.000011 loss: 2.7886 (2.7028) grad_norm: 3.1013 (3.5158) time: 0.5105 [2021-03-27 09:37:36 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 720/1251] eta: 0:04:31 lr: 0.000011 loss: 2.6457 (2.7005) grad_norm: 3.2367 (3.5138) time: 0.5071 [2021-03-27 09:37:41 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 730/1251] eta: 0:04:26 lr: 0.000011 loss: 2.5350 (2.6964) grad_norm: 3.3889 (3.5122) time: 0.4997 [2021-03-27 09:37:46 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 740/1251] eta: 0:04:21 lr: 0.000011 loss: 2.4047 (2.6952) grad_norm: 3.1518 (3.5066) time: 0.5180 [2021-03-27 09:37:51 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 750/1251] eta: 0:04:16 lr: 0.000011 loss: 2.6703 (2.6966) grad_norm: 3.1067 (3.5026) time: 0.5226 [2021-03-27 09:37:56 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 760/1251] eta: 0:04:11 lr: 0.000011 loss: 2.7724 (2.6946) grad_norm: 3.1345 (3.5034) time: 0.5034 [2021-03-27 09:38:02 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 770/1251] eta: 0:04:05 lr: 0.000011 loss: 2.7174 (2.6969) grad_norm: 3.3197 (3.5007) time: 0.5030 [2021-03-27 09:38:07 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 780/1251] eta: 0:04:00 lr: 0.000011 loss: 2.7999 (2.6976) grad_norm: 3.2785 (3.4976) time: 0.5068 [2021-03-27 09:38:12 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 790/1251] eta: 0:03:55 lr: 0.000011 loss: 2.4962 (2.6937) grad_norm: 3.2785 (3.4985) time: 0.5093 [2021-03-27 09:38:17 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 800/1251] eta: 0:03:50 lr: 0.000011 loss: 2.5941 (2.6954) grad_norm: 3.2610 (3.4954) time: 0.5063 [2021-03-27 09:38:22 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 810/1251] eta: 0:03:45 lr: 0.000011 loss: 2.8095 (2.6966) grad_norm: 3.2140 (3.4926) time: 0.5035 [2021-03-27 09:38:27 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 820/1251] eta: 0:03:40 lr: 0.000011 loss: 2.7770 (2.6976) grad_norm: 3.3537 (3.4895) time: 0.5049 [2021-03-27 09:38:32 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 830/1251] eta: 0:03:35 lr: 0.000011 loss: 2.7373 (2.6959) grad_norm: 3.3370 (3.4873) time: 0.5077 [2021-03-27 09:38:37 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 840/1251] eta: 0:03:29 lr: 0.000011 loss: 2.6458 (2.6938) grad_norm: 3.1736 (3.4840) time: 0.5044 [2021-03-27 09:38:42 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 850/1251] eta: 0:03:24 lr: 0.000011 loss: 2.7024 (2.6950) grad_norm: 3.1674 (3.4802) time: 0.5081 [2021-03-27 09:38:47 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 860/1251] eta: 0:03:19 lr: 0.000011 loss: 2.8368 (2.6955) grad_norm: 3.3546 (3.4900) time: 0.5102 [2021-03-27 09:38:52 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 870/1251] eta: 0:03:14 lr: 0.000011 loss: 2.6716 (2.6943) grad_norm: 3.3691 (3.4874) time: 0.5008 [2021-03-27 09:38:57 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 880/1251] eta: 0:03:09 lr: 0.000011 loss: 2.6368 (2.6946) grad_norm: 3.2911 (3.4872) time: 0.4984 [2021-03-27 09:39:02 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 890/1251] eta: 0:03:04 lr: 0.000011 loss: 2.8115 (2.6948) grad_norm: 3.2911 (3.4837) time: 0.5012 [2021-03-27 09:39:07 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 900/1251] eta: 0:02:59 lr: 0.000011 loss: 2.7790 (2.6933) grad_norm: 3.1822 (3.4801) time: 0.5087 [2021-03-27 09:39:12 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 910/1251] eta: 0:02:54 lr: 0.000011 loss: 2.7483 (2.6921) grad_norm: 3.1462 (3.4773) time: 0.5077 [2021-03-27 09:39:17 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 920/1251] eta: 0:02:48 lr: 0.000011 loss: 2.6762 (2.6919) grad_norm: 3.1779 (3.4778) time: 0.5034 [2021-03-27 09:39:22 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 930/1251] eta: 0:02:43 lr: 0.000011 loss: 2.7439 (2.6934) grad_norm: 3.2000 (3.4747) time: 0.5064 [2021-03-27 09:39:28 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 940/1251] eta: 0:02:38 lr: 0.000011 loss: 2.8571 (2.6956) grad_norm: 3.1463 (3.4763) time: 0.5122 [2021-03-27 09:39:33 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 950/1251] eta: 0:02:33 lr: 0.000011 loss: 2.9152 (2.6964) grad_norm: 3.3388 (3.4749) time: 0.5089 [2021-03-27 09:39:38 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 960/1251] eta: 0:02:28 lr: 0.000011 loss: 2.7548 (2.6953) grad_norm: 3.3388 (3.4742) time: 0.5010 [2021-03-27 09:39:43 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 970/1251] eta: 0:02:23 lr: 0.000011 loss: 2.6143 (2.6944) grad_norm: 3.3126 (3.4761) time: 0.5020 [2021-03-27 09:39:48 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 980/1251] eta: 0:02:18 lr: 0.000011 loss: 2.7251 (2.6956) grad_norm: 3.3177 (3.4791) time: 0.4993 [2021-03-27 09:39:53 swin_small_patch4_window7_224] INFO: Epoch: [293] [ 990/1251] eta: 0:02:13 lr: 0.000011 loss: 2.8230 (2.6958) grad_norm: 3.4480 (3.4781) time: 0.4996 [2021-03-27 09:39:58 swin_small_patch4_window7_224] INFO: Epoch: [293] [1000/1251] eta: 0:02:07 lr: 0.000011 loss: 2.6366 (2.6939) grad_norm: 3.2822 (3.4765) time: 0.4987 [2021-03-27 09:40:03 swin_small_patch4_window7_224] INFO: Epoch: [293] [1010/1251] eta: 0:02:02 lr: 0.000011 loss: 2.6292 (2.6926) grad_norm: 3.2728 (3.4734) time: 0.4958 [2021-03-27 09:40:08 swin_small_patch4_window7_224] INFO: Epoch: [293] [1020/1251] eta: 0:01:57 lr: 0.000011 loss: 2.6353 (2.6910) grad_norm: 3.2549 (3.4737) time: 0.5090 [2021-03-27 09:40:13 swin_small_patch4_window7_224] INFO: Epoch: [293] [1030/1251] eta: 0:01:52 lr: 0.000011 loss: 2.6353 (2.6899) grad_norm: 3.3322 (3.4752) time: 0.5119 [2021-03-27 09:40:18 swin_small_patch4_window7_224] INFO: Epoch: [293] [1040/1251] eta: 0:01:47 lr: 0.000011 loss: 2.6653 (2.6891) grad_norm: 3.3374 (nan) time: 0.4997 [2021-03-27 09:40:23 swin_small_patch4_window7_224] INFO: Epoch: [293] [1050/1251] eta: 0:01:42 lr: 0.000011 loss: 2.5397 (2.6868) grad_norm: 3.3485 (nan) time: 0.4991 [2021-03-27 09:40:28 swin_small_patch4_window7_224] INFO: Epoch: [293] [1060/1251] eta: 0:01:37 lr: 0.000011 loss: 2.3616 (2.6862) grad_norm: 3.2450 (nan) time: 0.5082 [2021-03-27 09:40:33 swin_small_patch4_window7_224] INFO: Epoch: [293] [1070/1251] eta: 0:01:32 lr: 0.000011 loss: 2.5971 (2.6856) grad_norm: 3.1783 (nan) time: 0.5084 [2021-03-27 09:40:38 swin_small_patch4_window7_224] INFO: Epoch: [293] [1080/1251] eta: 0:01:27 lr: 0.000011 loss: 2.6831 (2.6853) grad_norm: 3.1206 (nan) time: 0.5016 [2021-03-27 09:40:43 swin_small_patch4_window7_224] INFO: Epoch: [293] [1090/1251] eta: 0:01:21 lr: 0.000011 loss: 2.5514 (2.6841) grad_norm: 3.2219 (nan) time: 0.4998 [2021-03-27 09:40:48 swin_small_patch4_window7_224] INFO: Epoch: [293] [1100/1251] eta: 0:01:16 lr: 0.000011 loss: 2.6731 (2.6844) grad_norm: 3.1337 (nan) time: 0.5068 [2021-03-27 09:40:53 swin_small_patch4_window7_224] INFO: Epoch: [293] [1110/1251] eta: 0:01:11 lr: 0.000011 loss: 2.7948 (2.6837) grad_norm: 3.3257 (nan) time: 0.5062 [2021-03-27 09:40:58 swin_small_patch4_window7_224] INFO: Epoch: [293] [1120/1251] eta: 0:01:06 lr: 0.000011 loss: 2.7184 (2.6835) grad_norm: 3.2434 (nan) time: 0.5018 [2021-03-27 09:41:03 swin_small_patch4_window7_224] INFO: Epoch: [293] [1130/1251] eta: 0:01:01 lr: 0.000011 loss: 2.7238 (2.6830) grad_norm: 3.2287 (nan) time: 0.5098 [2021-03-27 09:41:08 swin_small_patch4_window7_224] INFO: Epoch: [293] [1140/1251] eta: 0:00:56 lr: 0.000011 loss: 2.7175 (2.6825) grad_norm: 3.9025 (nan) time: 0.5086 [2021-03-27 09:41:13 swin_small_patch4_window7_224] INFO: Epoch: [293] [1150/1251] eta: 0:00:51 lr: 0.000011 loss: 2.8538 (2.6830) grad_norm: 3.3738 (nan) time: 0.5012 [2021-03-27 09:41:18 swin_small_patch4_window7_224] INFO: Epoch: [293] [1160/1251] eta: 0:00:46 lr: 0.000011 loss: 2.8200 (2.6812) grad_norm: 3.2460 (nan) time: 0.5041 [2021-03-27 09:41:23 swin_small_patch4_window7_224] INFO: Epoch: [293] [1170/1251] eta: 0:00:41 lr: 0.000011 loss: 2.5464 (2.6800) grad_norm: 3.1597 (nan) time: 0.5068 [2021-03-27 09:41:28 swin_small_patch4_window7_224] INFO: Epoch: [293] [1180/1251] eta: 0:00:36 lr: 0.000011 loss: 2.7047 (2.6795) grad_norm: 3.3377 (nan) time: 0.5028 [2021-03-27 09:41:34 swin_small_patch4_window7_224] INFO: Epoch: [293] [1190/1251] eta: 0:00:31 lr: 0.000011 loss: 2.8871 (2.6802) grad_norm: 3.3377 (nan) time: 0.5031 [2021-03-27 09:41:39 swin_small_patch4_window7_224] INFO: Epoch: [293] [1200/1251] eta: 0:00:25 lr: 0.000011 loss: 2.9175 (2.6796) grad_norm: 3.2680 (nan) time: 0.5044 [2021-03-27 09:41:44 swin_small_patch4_window7_224] INFO: Epoch: [293] [1210/1251] eta: 0:00:20 lr: 0.000011 loss: 2.6472 (2.6778) grad_norm: 3.2791 (nan) time: 0.5008 [2021-03-27 09:41:49 swin_small_patch4_window7_224] INFO: Epoch: [293] [1220/1251] eta: 0:00:15 lr: 0.000011 loss: 2.7277 (2.6788) grad_norm: 3.3290 (nan) time: 0.4975 [2021-03-27 09:41:54 swin_small_patch4_window7_224] INFO: Epoch: [293] [1230/1251] eta: 0:00:10 lr: 0.000011 loss: 2.8400 (2.6774) grad_norm: 3.4330 (nan) time: 0.5044 [2021-03-27 09:41:59 swin_small_patch4_window7_224] INFO: Epoch: [293] [1240/1251] eta: 0:00:05 lr: 0.000011 loss: 2.8494 (2.6787) grad_norm: 3.2678 (nan) time: 0.5123 [2021-03-27 09:42:04 swin_small_patch4_window7_224] INFO: Epoch: [293] [1250/1251] eta: 0:00:00 lr: 0.000011 loss: 2.7475 (2.6766) grad_norm: 3.2488 (nan) time: 0.5108 [2021-03-27 09:42:18 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:32 loss: 1.0161 (1.0161) acc1: 81.2500 (81.2500) acc5: 92.1875 (92.1875) [2021-03-27 09:42:20 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.7242 (0.7535) acc1: 84.3750 (83.2386) acc5: 96.8750 (95.8807) [2021-03-27 09:42:22 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7021 (0.7455) acc1: 84.3750 (82.4405) acc5: 96.8750 (95.9077) [2021-03-27 09:42:24 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7026 (0.7420) acc1: 79.6875 (82.1573) acc5: 96.8750 (96.1190) [2021-03-27 09:42:26 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7432 (0.7533) acc1: 81.2500 (82.0122) acc5: 95.3125 (95.9604) [2021-03-27 09:42:27 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7332 (0.7474) acc1: 82.8125 (82.1440) acc5: 95.3125 (96.0000) [2021-03-27 09:42:44 swin_small_patch4_window7_224] INFO: * Acc@1 83.100 Acc@5 96.256 loss 0.732 [2021-03-27 09:42:44 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 09:42:44 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 09:42:49 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 0/1251] eta: 1:43:57 lr: 0.000011 loss: 2.8059 (2.8059) grad_norm: 3.4908 (3.4908) time: 4.9860 [2021-03-27 09:42:54 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 10/1251] eta: 0:19:05 lr: 0.000011 loss: 3.0573 (2.9058) grad_norm: 3.2040 (3.2966) time: 0.9231 [2021-03-27 09:42:59 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 20/1251] eta: 0:14:53 lr: 0.000011 loss: 3.0257 (2.8543) grad_norm: 3.2222 (3.2543) time: 0.5127 [2021-03-27 09:43:04 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 30/1251] eta: 0:13:18 lr: 0.000011 loss: 2.9120 (2.8381) grad_norm: 3.2751 (3.3245) time: 0.5063 [2021-03-27 09:43:09 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 40/1251] eta: 0:12:28 lr: 0.000011 loss: 2.7809 (2.8072) grad_norm: 3.0817 (3.2744) time: 0.5051 [2021-03-27 09:43:14 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 50/1251] eta: 0:11:57 lr: 0.000011 loss: 2.7903 (2.8013) grad_norm: 3.1405 (3.3034) time: 0.5088 [2021-03-27 09:43:20 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 60/1251] eta: 0:11:33 lr: 0.000011 loss: 2.7932 (2.7501) grad_norm: 3.1892 (3.3027) time: 0.5101 [2021-03-27 09:43:24 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 70/1251] eta: 0:11:14 lr: 0.000011 loss: 2.7638 (2.7639) grad_norm: 3.1135 (3.2889) time: 0.5039 [2021-03-27 09:43:30 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 80/1251] eta: 0:10:59 lr: 0.000011 loss: 2.7090 (2.7517) grad_norm: 3.1834 (3.3060) time: 0.5021 [2021-03-27 09:43:35 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 90/1251] eta: 0:10:46 lr: 0.000011 loss: 2.4960 (2.7410) grad_norm: 3.2719 (3.3031) time: 0.5083 [2021-03-27 09:43:40 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 100/1251] eta: 0:10:34 lr: 0.000011 loss: 2.6389 (2.7402) grad_norm: 3.2719 (3.3018) time: 0.5065 [2021-03-27 09:43:45 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 110/1251] eta: 0:10:25 lr: 0.000011 loss: 2.6918 (2.7240) grad_norm: 3.3161 (3.3199) time: 0.5060 [2021-03-27 09:43:50 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 120/1251] eta: 0:10:15 lr: 0.000011 loss: 2.7953 (2.7315) grad_norm: 3.4008 (3.3367) time: 0.5067 [2021-03-27 09:43:55 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 130/1251] eta: 0:10:08 lr: 0.000011 loss: 2.6697 (2.7077) grad_norm: 3.2600 (3.3294) time: 0.5127 [2021-03-27 09:44:00 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 140/1251] eta: 0:10:00 lr: 0.000011 loss: 2.7207 (2.7216) grad_norm: 3.1824 (3.3338) time: 0.5175 [2021-03-27 09:44:05 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 150/1251] eta: 0:09:51 lr: 0.000011 loss: 2.7341 (2.7121) grad_norm: 3.1886 (3.3292) time: 0.5051 [2021-03-27 09:44:10 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 160/1251] eta: 0:09:44 lr: 0.000011 loss: 2.7276 (2.7146) grad_norm: 3.2735 (3.3299) time: 0.5000 [2021-03-27 09:44:15 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 170/1251] eta: 0:09:36 lr: 0.000011 loss: 2.7276 (2.7107) grad_norm: 3.3464 (3.3389) time: 0.5034 [2021-03-27 09:44:20 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 180/1251] eta: 0:09:30 lr: 0.000011 loss: 2.8042 (2.7134) grad_norm: 3.4173 (3.3572) time: 0.5068 [2021-03-27 09:44:25 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 190/1251] eta: 0:09:23 lr: 0.000011 loss: 2.8291 (2.7161) grad_norm: 3.4865 (3.3749) time: 0.5064 [2021-03-27 09:44:30 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 200/1251] eta: 0:09:16 lr: 0.000011 loss: 2.6434 (2.7123) grad_norm: 3.2297 (3.3662) time: 0.5046 [2021-03-27 09:44:35 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 210/1251] eta: 0:09:09 lr: 0.000011 loss: 2.5087 (2.6939) grad_norm: 3.0993 (3.3740) time: 0.5040 [2021-03-27 09:44:40 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 220/1251] eta: 0:09:03 lr: 0.000011 loss: 2.5087 (2.6947) grad_norm: 3.2559 (3.3716) time: 0.4995 [2021-03-27 09:44:45 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 230/1251] eta: 0:08:56 lr: 0.000011 loss: 2.7255 (2.6891) grad_norm: 3.1659 (3.3627) time: 0.4987 [2021-03-27 09:44:50 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 240/1251] eta: 0:08:50 lr: 0.000011 loss: 2.7423 (2.6882) grad_norm: 3.2614 (3.4158) time: 0.4996 [2021-03-27 09:44:55 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 250/1251] eta: 0:08:44 lr: 0.000011 loss: 2.7423 (2.6830) grad_norm: 3.2807 (3.4361) time: 0.5001 [2021-03-27 09:45:00 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 260/1251] eta: 0:08:38 lr: 0.000011 loss: 2.6459 (2.6838) grad_norm: 3.3770 (3.4388) time: 0.5012 [2021-03-27 09:45:05 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 270/1251] eta: 0:08:31 lr: 0.000011 loss: 2.7324 (2.6843) grad_norm: 3.3207 (3.4374) time: 0.5000 [2021-03-27 09:45:10 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 280/1251] eta: 0:08:26 lr: 0.000011 loss: 2.8154 (2.6906) grad_norm: 3.1042 (3.4296) time: 0.5030 [2021-03-27 09:45:16 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 290/1251] eta: 0:08:20 lr: 0.000011 loss: 2.7616 (2.6899) grad_norm: 3.1276 (3.4525) time: 0.5054 [2021-03-27 09:45:20 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 300/1251] eta: 0:08:14 lr: 0.000011 loss: 2.6483 (2.6900) grad_norm: 3.2694 (3.4550) time: 0.5004 [2021-03-27 09:45:26 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 310/1251] eta: 0:08:08 lr: 0.000011 loss: 2.6551 (2.6895) grad_norm: 3.2694 (3.4479) time: 0.5000 [2021-03-27 09:45:31 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 320/1251] eta: 0:08:03 lr: 0.000011 loss: 2.6814 (2.6903) grad_norm: 3.1953 (3.4541) time: 0.5123 [2021-03-27 09:45:36 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 330/1251] eta: 0:07:57 lr: 0.000011 loss: 2.7287 (2.6920) grad_norm: 3.2188 (3.4520) time: 0.5100 [2021-03-27 09:45:41 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 340/1251] eta: 0:07:52 lr: 0.000011 loss: 2.7287 (2.6896) grad_norm: 3.2188 (3.4496) time: 0.4973 [2021-03-27 09:45:46 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 350/1251] eta: 0:07:46 lr: 0.000011 loss: 2.7876 (2.6950) grad_norm: 3.1861 (3.4573) time: 0.4950 [2021-03-27 09:45:51 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 360/1251] eta: 0:07:40 lr: 0.000011 loss: 2.7876 (2.6929) grad_norm: 3.3105 (3.4625) time: 0.4977 [2021-03-27 09:45:56 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 370/1251] eta: 0:07:35 lr: 0.000011 loss: 2.6315 (2.6874) grad_norm: 3.1485 (3.4554) time: 0.5031 [2021-03-27 09:46:01 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 380/1251] eta: 0:07:29 lr: 0.000011 loss: 2.6663 (2.6870) grad_norm: 3.0619 (3.4494) time: 0.5010 [2021-03-27 09:46:06 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 390/1251] eta: 0:07:24 lr: 0.000011 loss: 2.8789 (2.6909) grad_norm: 2.9769 (3.4475) time: 0.4969 [2021-03-27 09:46:11 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 400/1251] eta: 0:07:18 lr: 0.000011 loss: 2.7245 (2.6900) grad_norm: 3.2352 (3.4478) time: 0.4982 [2021-03-27 09:46:16 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 410/1251] eta: 0:07:12 lr: 0.000011 loss: 2.7245 (2.6932) grad_norm: 3.3394 (3.4450) time: 0.4981 [2021-03-27 09:46:21 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 420/1251] eta: 0:07:07 lr: 0.000011 loss: 2.8430 (2.6948) grad_norm: 3.0797 (3.4366) time: 0.5006 [2021-03-27 09:46:26 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 430/1251] eta: 0:07:02 lr: 0.000011 loss: 2.8741 (2.6945) grad_norm: 3.0506 (3.4285) time: 0.5042 [2021-03-27 09:46:31 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 440/1251] eta: 0:06:56 lr: 0.000011 loss: 2.5931 (2.6927) grad_norm: 3.1367 (3.4383) time: 0.5004 [2021-03-27 09:46:36 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 450/1251] eta: 0:06:51 lr: 0.000011 loss: 2.5931 (2.6884) grad_norm: 3.4166 (3.4546) time: 0.5006 [2021-03-27 09:46:41 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 460/1251] eta: 0:06:46 lr: 0.000011 loss: 2.4886 (2.6806) grad_norm: 3.4032 (3.4532) time: 0.5083 [2021-03-27 09:46:46 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 470/1251] eta: 0:06:40 lr: 0.000011 loss: 2.4969 (2.6806) grad_norm: 3.3311 (3.4476) time: 0.5065 [2021-03-27 09:46:51 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 480/1251] eta: 0:06:35 lr: 0.000011 loss: 2.7222 (2.6766) grad_norm: 3.1114 (3.4414) time: 0.5008 [2021-03-27 09:46:56 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 490/1251] eta: 0:06:30 lr: 0.000011 loss: 2.7222 (2.6783) grad_norm: 3.1114 (3.4373) time: 0.5001 [2021-03-27 09:47:01 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 500/1251] eta: 0:06:25 lr: 0.000011 loss: 2.7324 (2.6782) grad_norm: 3.2790 (3.4429) time: 0.5050 [2021-03-27 09:47:06 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 510/1251] eta: 0:06:19 lr: 0.000011 loss: 2.8194 (2.6773) grad_norm: 3.3948 (3.4451) time: 0.5059 [2021-03-27 09:47:11 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 520/1251] eta: 0:06:14 lr: 0.000011 loss: 2.6451 (2.6746) grad_norm: 3.4628 (3.4442) time: 0.5054 [2021-03-27 09:47:16 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 530/1251] eta: 0:06:09 lr: 0.000011 loss: 2.6719 (2.6744) grad_norm: 3.3757 (3.4431) time: 0.5030 [2021-03-27 09:47:21 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 540/1251] eta: 0:06:04 lr: 0.000011 loss: 2.8230 (2.6791) grad_norm: 3.1920 (3.4383) time: 0.5029 [2021-03-27 09:47:27 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 550/1251] eta: 0:05:59 lr: 0.000011 loss: 2.9294 (2.6831) grad_norm: 3.1363 (3.4361) time: 0.5239 [2021-03-27 09:47:32 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 560/1251] eta: 0:05:54 lr: 0.000011 loss: 2.8994 (2.6821) grad_norm: 3.2226 (3.4355) time: 0.5297 [2021-03-27 09:47:37 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 570/1251] eta: 0:05:49 lr: 0.000011 loss: 2.8762 (2.6843) grad_norm: 3.4198 (3.4404) time: 0.5179 [2021-03-27 09:47:42 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 580/1251] eta: 0:05:43 lr: 0.000011 loss: 2.5789 (2.6798) grad_norm: 3.4359 (3.4369) time: 0.5077 [2021-03-27 09:47:47 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 590/1251] eta: 0:05:38 lr: 0.000011 loss: 2.5789 (2.6798) grad_norm: 3.3939 (3.4363) time: 0.5035 [2021-03-27 09:47:52 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 600/1251] eta: 0:05:33 lr: 0.000011 loss: 2.6399 (2.6782) grad_norm: 3.4330 (3.4404) time: 0.5020 [2021-03-27 09:47:57 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 610/1251] eta: 0:05:28 lr: 0.000011 loss: 2.8719 (2.6792) grad_norm: 3.4330 (3.4455) time: 0.4994 [2021-03-27 09:48:02 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 620/1251] eta: 0:05:23 lr: 0.000011 loss: 2.7041 (2.6771) grad_norm: 3.4116 (3.4489) time: 0.5011 [2021-03-27 09:48:07 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 630/1251] eta: 0:05:17 lr: 0.000011 loss: 2.6517 (2.6751) grad_norm: 3.4021 (3.4487) time: 0.5051 [2021-03-27 09:48:12 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 640/1251] eta: 0:05:12 lr: 0.000011 loss: 2.8780 (2.6789) grad_norm: 3.3665 (3.4507) time: 0.5053 [2021-03-27 09:48:17 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 650/1251] eta: 0:05:07 lr: 0.000011 loss: 2.7797 (2.6755) grad_norm: 3.4610 (3.4512) time: 0.5052 [2021-03-27 09:48:22 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 660/1251] eta: 0:05:02 lr: 0.000011 loss: 2.5543 (2.6769) grad_norm: 3.4610 (3.4526) time: 0.5060 [2021-03-27 09:48:27 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 670/1251] eta: 0:04:57 lr: 0.000011 loss: 2.8755 (2.6799) grad_norm: 3.3414 (3.4622) time: 0.5025 [2021-03-27 09:48:32 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 680/1251] eta: 0:04:51 lr: 0.000011 loss: 2.8380 (2.6809) grad_norm: 3.3023 (3.4638) time: 0.5009 [2021-03-27 09:48:37 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 690/1251] eta: 0:04:46 lr: 0.000011 loss: 2.8638 (2.6811) grad_norm: 3.3816 (3.4653) time: 0.4964 [2021-03-27 09:48:42 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 700/1251] eta: 0:04:41 lr: 0.000011 loss: 2.5042 (2.6800) grad_norm: 3.4187 (3.4665) time: 0.4939 [2021-03-27 09:48:47 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 710/1251] eta: 0:04:36 lr: 0.000011 loss: 2.4852 (2.6787) grad_norm: 3.3718 (3.4646) time: 0.4981 [2021-03-27 09:48:52 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 720/1251] eta: 0:04:31 lr: 0.000011 loss: 2.7417 (2.6810) grad_norm: 3.3787 (3.4677) time: 0.5046 [2021-03-27 09:48:57 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 730/1251] eta: 0:04:25 lr: 0.000011 loss: 2.7929 (2.6813) grad_norm: 3.3723 (3.4652) time: 0.5059 [2021-03-27 09:49:03 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 740/1251] eta: 0:04:21 lr: 0.000011 loss: 2.8121 (2.6845) grad_norm: 3.2399 (3.4653) time: 0.5261 [2021-03-27 09:49:08 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 750/1251] eta: 0:04:16 lr: 0.000011 loss: 2.8630 (2.6841) grad_norm: 3.2208 (3.4627) time: 0.5436 [2021-03-27 09:49:13 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 760/1251] eta: 0:04:10 lr: 0.000011 loss: 2.7429 (2.6839) grad_norm: 3.3025 (3.4635) time: 0.5160 [2021-03-27 09:49:18 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 770/1251] eta: 0:04:05 lr: 0.000011 loss: 2.8095 (2.6853) grad_norm: 3.3234 (3.4626) time: 0.5022 [2021-03-27 09:49:23 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 780/1251] eta: 0:04:00 lr: 0.000011 loss: 2.7113 (2.6827) grad_norm: 3.3084 (3.4817) time: 0.5131 [2021-03-27 09:49:28 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 790/1251] eta: 0:03:55 lr: 0.000011 loss: 2.5968 (2.6827) grad_norm: 3.3084 (3.4891) time: 0.5071 [2021-03-27 09:49:33 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 800/1251] eta: 0:03:50 lr: 0.000011 loss: 2.6688 (2.6817) grad_norm: 3.2600 (3.4858) time: 0.5070 [2021-03-27 09:49:39 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 810/1251] eta: 0:03:45 lr: 0.000011 loss: 2.7559 (2.6821) grad_norm: 3.4149 (3.4881) time: 0.5129 [2021-03-27 09:49:44 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 820/1251] eta: 0:03:40 lr: 0.000011 loss: 2.7559 (2.6834) grad_norm: 3.6613 (3.4971) time: 0.5098 [2021-03-27 09:49:49 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 830/1251] eta: 0:03:35 lr: 0.000011 loss: 2.8203 (2.6847) grad_norm: 3.4242 (3.4955) time: 0.5094 [2021-03-27 09:49:54 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 840/1251] eta: 0:03:29 lr: 0.000011 loss: 2.8296 (2.6864) grad_norm: 3.1454 (3.4929) time: 0.5053 [2021-03-27 09:49:59 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 850/1251] eta: 0:03:24 lr: 0.000011 loss: 2.9771 (2.6892) grad_norm: 3.1449 (3.4949) time: 0.5016 [2021-03-27 09:50:04 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 860/1251] eta: 0:03:19 lr: 0.000011 loss: 2.9022 (2.6871) grad_norm: 3.2647 (3.4963) time: 0.5010 [2021-03-27 09:50:09 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 870/1251] eta: 0:03:14 lr: 0.000011 loss: 2.6344 (2.6856) grad_norm: 3.2877 (3.4964) time: 0.5031 [2021-03-27 09:50:14 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 880/1251] eta: 0:03:09 lr: 0.000011 loss: 2.6515 (2.6838) grad_norm: 3.1841 (3.4922) time: 0.5010 [2021-03-27 09:50:19 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 890/1251] eta: 0:03:04 lr: 0.000011 loss: 2.6793 (2.6851) grad_norm: 3.0579 (3.4909) time: 0.4940 [2021-03-27 09:50:24 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 900/1251] eta: 0:02:59 lr: 0.000011 loss: 2.6793 (2.6841) grad_norm: 3.1766 (3.4900) time: 0.4958 [2021-03-27 09:50:29 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 910/1251] eta: 0:02:53 lr: 0.000011 loss: 2.7574 (2.6861) grad_norm: 3.4597 (3.4930) time: 0.5065 [2021-03-27 09:50:34 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 920/1251] eta: 0:02:48 lr: 0.000011 loss: 2.6691 (2.6819) grad_norm: 3.4597 (3.4947) time: 0.5068 [2021-03-27 09:50:39 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 930/1251] eta: 0:02:43 lr: 0.000011 loss: 2.3737 (2.6824) grad_norm: 3.4303 (3.4954) time: 0.4974 [2021-03-27 09:50:44 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 940/1251] eta: 0:02:38 lr: 0.000011 loss: 2.7139 (2.6827) grad_norm: 3.3130 (3.4940) time: 0.5024 [2021-03-27 09:50:49 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 950/1251] eta: 0:02:33 lr: 0.000011 loss: 2.7517 (2.6851) grad_norm: 3.1674 (3.4923) time: 0.4994 [2021-03-27 09:50:54 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 960/1251] eta: 0:02:28 lr: 0.000011 loss: 2.8063 (2.6850) grad_norm: 3.2955 (3.4935) time: 0.4943 [2021-03-27 09:50:59 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 970/1251] eta: 0:02:23 lr: 0.000011 loss: 2.7504 (2.6833) grad_norm: 3.2973 (3.4989) time: 0.5059 [2021-03-27 09:51:04 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 980/1251] eta: 0:02:18 lr: 0.000011 loss: 2.6776 (2.6830) grad_norm: 3.2101 (3.4994) time: 0.5158 [2021-03-27 09:51:09 swin_small_patch4_window7_224] INFO: Epoch: [294] [ 990/1251] eta: 0:02:13 lr: 0.000011 loss: 2.6776 (2.6842) grad_norm: 3.1885 (3.5002) time: 0.5153 [2021-03-27 09:51:14 swin_small_patch4_window7_224] INFO: Epoch: [294] [1000/1251] eta: 0:02:07 lr: 0.000011 loss: 2.6759 (2.6840) grad_norm: 3.3612 (3.5024) time: 0.5128 [2021-03-27 09:51:19 swin_small_patch4_window7_224] INFO: Epoch: [294] [1010/1251] eta: 0:02:02 lr: 0.000011 loss: 2.6697 (2.6834) grad_norm: 3.4760 (3.5027) time: 0.5102 [2021-03-27 09:51:25 swin_small_patch4_window7_224] INFO: Epoch: [294] [1020/1251] eta: 0:01:57 lr: 0.000011 loss: 2.7136 (2.6831) grad_norm: 3.2478 (3.5008) time: 0.5088 [2021-03-27 09:51:30 swin_small_patch4_window7_224] INFO: Epoch: [294] [1030/1251] eta: 0:01:52 lr: 0.000011 loss: 2.7723 (2.6831) grad_norm: 3.2478 (3.5022) time: 0.5093 [2021-03-27 09:51:35 swin_small_patch4_window7_224] INFO: Epoch: [294] [1040/1251] eta: 0:01:47 lr: 0.000011 loss: 2.7183 (2.6823) grad_norm: 3.3124 (3.5022) time: 0.5039 [2021-03-27 09:51:40 swin_small_patch4_window7_224] INFO: Epoch: [294] [1050/1251] eta: 0:01:42 lr: 0.000011 loss: 2.8394 (2.6843) grad_norm: 3.2779 (3.5026) time: 0.5081 [2021-03-27 09:51:45 swin_small_patch4_window7_224] INFO: Epoch: [294] [1060/1251] eta: 0:01:37 lr: 0.000011 loss: 2.8835 (2.6841) grad_norm: 3.2183 (3.4997) time: 0.5071 [2021-03-27 09:51:50 swin_small_patch4_window7_224] INFO: Epoch: [294] [1070/1251] eta: 0:01:32 lr: 0.000011 loss: 2.6752 (2.6832) grad_norm: 3.0546 (3.4961) time: 0.5033 [2021-03-27 09:51:55 swin_small_patch4_window7_224] INFO: Epoch: [294] [1080/1251] eta: 0:01:27 lr: 0.000011 loss: 2.8849 (2.6843) grad_norm: 3.1548 (3.4973) time: 0.5032 [2021-03-27 09:52:00 swin_small_patch4_window7_224] INFO: Epoch: [294] [1090/1251] eta: 0:01:22 lr: 0.000011 loss: 2.7664 (2.6848) grad_norm: 3.5839 (3.4978) time: 0.4984 [2021-03-27 09:52:05 swin_small_patch4_window7_224] INFO: Epoch: [294] [1100/1251] eta: 0:01:16 lr: 0.000011 loss: 2.7126 (2.6832) grad_norm: 3.4492 (3.4996) time: 0.5018 [2021-03-27 09:52:10 swin_small_patch4_window7_224] INFO: Epoch: [294] [1110/1251] eta: 0:01:11 lr: 0.000011 loss: 2.4916 (2.6827) grad_norm: 3.3469 (3.5080) time: 0.5061 [2021-03-27 09:52:15 swin_small_patch4_window7_224] INFO: Epoch: [294] [1120/1251] eta: 0:01:06 lr: 0.000011 loss: 2.7007 (2.6824) grad_norm: 3.1220 (3.5050) time: 0.5047 [2021-03-27 09:52:20 swin_small_patch4_window7_224] INFO: Epoch: [294] [1130/1251] eta: 0:01:01 lr: 0.000011 loss: 2.7007 (2.6806) grad_norm: 3.2135 (3.5059) time: 0.4988 [2021-03-27 09:52:25 swin_small_patch4_window7_224] INFO: Epoch: [294] [1140/1251] eta: 0:00:56 lr: 0.000011 loss: 2.4771 (2.6805) grad_norm: 3.4629 (3.5072) time: 0.4993 [2021-03-27 09:52:30 swin_small_patch4_window7_224] INFO: Epoch: [294] [1150/1251] eta: 0:00:51 lr: 0.000011 loss: 2.7368 (2.6801) grad_norm: 3.6091 (3.5082) time: 0.4993 [2021-03-27 09:52:35 swin_small_patch4_window7_224] INFO: Epoch: [294] [1160/1251] eta: 0:00:46 lr: 0.000011 loss: 2.8430 (2.6822) grad_norm: 3.2777 (3.5082) time: 0.4951 [2021-03-27 09:52:40 swin_small_patch4_window7_224] INFO: Epoch: [294] [1170/1251] eta: 0:00:41 lr: 0.000011 loss: 2.8369 (2.6824) grad_norm: 3.2549 (3.5064) time: 0.4950 [2021-03-27 09:52:45 swin_small_patch4_window7_224] INFO: Epoch: [294] [1180/1251] eta: 0:00:36 lr: 0.000011 loss: 2.8129 (2.6816) grad_norm: 3.2969 (3.5059) time: 0.4998 [2021-03-27 09:52:50 swin_small_patch4_window7_224] INFO: Epoch: [294] [1190/1251] eta: 0:00:31 lr: 0.000011 loss: 2.8667 (2.6829) grad_norm: 3.3521 (3.5051) time: 0.5024 [2021-03-27 09:52:55 swin_small_patch4_window7_224] INFO: Epoch: [294] [1200/1251] eta: 0:00:25 lr: 0.000011 loss: 2.8985 (2.6844) grad_norm: 3.3521 (3.5029) time: 0.5007 [2021-03-27 09:53:00 swin_small_patch4_window7_224] INFO: Epoch: [294] [1210/1251] eta: 0:00:20 lr: 0.000011 loss: 2.7381 (2.6836) grad_norm: 3.3959 (3.5038) time: 0.5019 [2021-03-27 09:53:05 swin_small_patch4_window7_224] INFO: Epoch: [294] [1220/1251] eta: 0:00:15 lr: 0.000011 loss: 2.7038 (2.6843) grad_norm: 3.4743 (3.5051) time: 0.5088 [2021-03-27 09:53:10 swin_small_patch4_window7_224] INFO: Epoch: [294] [1230/1251] eta: 0:00:10 lr: 0.000011 loss: 2.8441 (2.6845) grad_norm: 3.3305 (3.5033) time: 0.5054 [2021-03-27 09:53:15 swin_small_patch4_window7_224] INFO: Epoch: [294] [1240/1251] eta: 0:00:05 lr: 0.000011 loss: 2.8099 (2.6846) grad_norm: 3.2648 (3.5082) time: 0.4991 [2021-03-27 09:53:20 swin_small_patch4_window7_224] INFO: Epoch: [294] [1250/1251] eta: 0:00:00 lr: 0.000011 loss: 2.8099 (2.6856) grad_norm: 3.4108 (3.5079) time: 0.4940 [2021-03-27 09:53:33 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:57 loss: 0.7640 (0.7640) acc1: 81.2500 (81.2500) acc5: 96.8750 (96.8750) [2021-03-27 09:53:35 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:15 loss: 0.7479 (0.7692) acc1: 82.8125 (82.8125) acc5: 96.8750 (96.3068) [2021-03-27 09:53:37 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7783 (0.7926) acc1: 79.6875 (81.8452) acc5: 95.3125 (95.8333) [2021-03-27 09:53:39 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7995 (0.7731) acc1: 81.2500 (82.4093) acc5: 95.3125 (95.8165) [2021-03-27 09:53:42 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7386 (0.7514) acc1: 82.8125 (82.4314) acc5: 96.8750 (96.0366) [2021-03-27 09:53:43 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.6947 (0.7523) acc1: 81.2500 (82.0160) acc5: 96.8750 (96.0000) [2021-03-27 09:54:00 swin_small_patch4_window7_224] INFO: * Acc@1 83.104 Acc@5 96.270 loss 0.737 [2021-03-27 09:54:00 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 09:54:00 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 09:54:04 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 0/1251] eta: 1:27:43 lr: 0.000011 loss: 2.1237 (2.1237) grad_norm: 3.0286 (3.0286) time: 4.2073 [2021-03-27 09:54:09 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 10/1251] eta: 0:17:41 lr: 0.000011 loss: 2.8802 (2.8281) grad_norm: 3.1932 (3.2824) time: 0.8553 [2021-03-27 09:54:15 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 20/1251] eta: 0:14:14 lr: 0.000011 loss: 2.8802 (2.8118) grad_norm: 3.3566 (3.5194) time: 0.5182 [2021-03-27 09:54:20 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 30/1251] eta: 0:12:48 lr: 0.000011 loss: 2.8522 (2.7495) grad_norm: 3.2565 (3.4261) time: 0.5052 [2021-03-27 09:54:25 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 40/1251] eta: 0:12:04 lr: 0.000011 loss: 2.4920 (2.6687) grad_norm: 3.0764 (3.3517) time: 0.4984 [2021-03-27 09:54:30 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 50/1251] eta: 0:11:39 lr: 0.000011 loss: 2.5847 (2.6835) grad_norm: 3.0198 (3.3614) time: 0.5092 [2021-03-27 09:54:35 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 60/1251] eta: 0:11:18 lr: 0.000011 loss: 2.7672 (2.6689) grad_norm: 3.3418 (3.4443) time: 0.5110 [2021-03-27 09:54:40 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 70/1251] eta: 0:11:01 lr: 0.000011 loss: 2.8228 (2.6715) grad_norm: 3.3748 (3.4678) time: 0.5025 [2021-03-27 09:54:45 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 80/1251] eta: 0:10:46 lr: 0.000011 loss: 2.6913 (2.6623) grad_norm: 3.3512 (3.4641) time: 0.4987 [2021-03-27 09:54:50 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 90/1251] eta: 0:10:35 lr: 0.000011 loss: 2.6797 (2.6473) grad_norm: 3.3175 (3.4571) time: 0.5020 [2021-03-27 09:54:55 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 100/1251] eta: 0:10:24 lr: 0.000011 loss: 2.5788 (2.6539) grad_norm: 3.3175 (3.5102) time: 0.5044 [2021-03-27 09:55:00 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 110/1251] eta: 0:10:14 lr: 0.000011 loss: 2.7904 (2.6639) grad_norm: 3.4230 (3.5035) time: 0.5017 [2021-03-27 09:55:05 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 120/1251] eta: 0:10:06 lr: 0.000011 loss: 2.8384 (2.6800) grad_norm: 3.2787 (3.4976) time: 0.5013 [2021-03-27 09:55:10 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 130/1251] eta: 0:09:57 lr: 0.000011 loss: 2.7464 (2.6781) grad_norm: 3.2744 (3.5025) time: 0.5007 [2021-03-27 09:55:15 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 140/1251] eta: 0:09:49 lr: 0.000011 loss: 2.7102 (2.6815) grad_norm: 3.5015 (3.5182) time: 0.4963 [2021-03-27 09:55:20 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 150/1251] eta: 0:09:41 lr: 0.000011 loss: 2.7648 (2.6922) grad_norm: 3.7563 (3.5386) time: 0.4985 [2021-03-27 09:55:25 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 160/1251] eta: 0:09:34 lr: 0.000011 loss: 2.8143 (2.7015) grad_norm: 3.3706 (3.5254) time: 0.5034 [2021-03-27 09:55:30 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 170/1251] eta: 0:09:27 lr: 0.000011 loss: 2.7173 (2.6942) grad_norm: 3.2171 (3.5063) time: 0.4995 [2021-03-27 09:55:35 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 180/1251] eta: 0:09:21 lr: 0.000011 loss: 2.6987 (2.7012) grad_norm: 3.1708 (3.5067) time: 0.5028 [2021-03-27 09:55:40 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 190/1251] eta: 0:09:15 lr: 0.000011 loss: 2.8857 (2.7081) grad_norm: 3.1708 (3.5054) time: 0.5116 [2021-03-27 09:55:45 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 200/1251] eta: 0:09:08 lr: 0.000011 loss: 2.8430 (2.7092) grad_norm: 3.3041 (3.5063) time: 0.5032 [2021-03-27 09:55:50 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 210/1251] eta: 0:09:02 lr: 0.000011 loss: 2.4392 (2.6960) grad_norm: 3.1131 (3.4886) time: 0.5008 [2021-03-27 09:55:55 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 220/1251] eta: 0:08:56 lr: 0.000011 loss: 2.4392 (2.6930) grad_norm: 3.1015 (3.4768) time: 0.5072 [2021-03-27 09:56:00 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 230/1251] eta: 0:08:51 lr: 0.000011 loss: 2.7645 (2.6820) grad_norm: 3.2397 (3.4675) time: 0.5048 [2021-03-27 09:56:05 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 240/1251] eta: 0:08:45 lr: 0.000011 loss: 2.5183 (2.6789) grad_norm: 3.2397 (3.4623) time: 0.5045 [2021-03-27 09:56:10 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 250/1251] eta: 0:08:39 lr: 0.000011 loss: 2.8350 (2.6775) grad_norm: 3.3810 (3.5142) time: 0.5023 [2021-03-27 09:56:15 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 260/1251] eta: 0:08:33 lr: 0.000011 loss: 2.8470 (2.6823) grad_norm: 3.2907 (3.4982) time: 0.5040 [2021-03-27 09:56:20 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 270/1251] eta: 0:08:28 lr: 0.000011 loss: 2.8634 (2.6904) grad_norm: 3.2907 (3.4975) time: 0.5078 [2021-03-27 09:56:25 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 280/1251] eta: 0:08:22 lr: 0.000011 loss: 2.9494 (2.6958) grad_norm: 3.2687 (3.4841) time: 0.5087 [2021-03-27 09:56:30 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 290/1251] eta: 0:08:16 lr: 0.000011 loss: 2.9169 (2.7032) grad_norm: 3.1737 (3.4779) time: 0.5050 [2021-03-27 09:56:35 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 300/1251] eta: 0:08:11 lr: 0.000011 loss: 2.8875 (2.6981) grad_norm: 3.2649 (3.4740) time: 0.4995 [2021-03-27 09:56:40 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 310/1251] eta: 0:08:05 lr: 0.000011 loss: 2.7612 (2.6994) grad_norm: 3.2649 (3.4722) time: 0.4976 [2021-03-27 09:56:45 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 320/1251] eta: 0:07:59 lr: 0.000011 loss: 2.8387 (2.7022) grad_norm: 3.1785 (3.4621) time: 0.4967 [2021-03-27 09:56:50 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 330/1251] eta: 0:07:54 lr: 0.000011 loss: 2.8610 (2.7027) grad_norm: 3.2202 (3.4613) time: 0.5014 [2021-03-27 09:56:55 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 340/1251] eta: 0:07:48 lr: 0.000011 loss: 2.8035 (2.7055) grad_norm: 3.3285 (3.4628) time: 0.5031 [2021-03-27 09:57:00 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 350/1251] eta: 0:07:43 lr: 0.000011 loss: 2.6900 (2.7043) grad_norm: 3.3285 (3.4604) time: 0.4994 [2021-03-27 09:57:05 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 360/1251] eta: 0:07:37 lr: 0.000011 loss: 2.6220 (2.6995) grad_norm: 3.5501 (3.4738) time: 0.4969 [2021-03-27 09:57:10 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 370/1251] eta: 0:07:32 lr: 0.000011 loss: 2.4316 (2.6976) grad_norm: 3.7540 (3.4947) time: 0.5011 [2021-03-27 09:57:16 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 380/1251] eta: 0:07:27 lr: 0.000011 loss: 2.5295 (2.6943) grad_norm: 3.4214 (3.4947) time: 0.5085 [2021-03-27 09:57:21 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 390/1251] eta: 0:07:21 lr: 0.000011 loss: 2.5295 (2.6896) grad_norm: 3.3330 (3.4964) time: 0.5060 [2021-03-27 09:57:26 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 400/1251] eta: 0:07:16 lr: 0.000011 loss: 2.4825 (2.6835) grad_norm: 3.2007 (3.4974) time: 0.4984 [2021-03-27 09:57:31 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 410/1251] eta: 0:07:11 lr: 0.000011 loss: 2.6685 (2.6852) grad_norm: 3.4078 (3.4998) time: 0.5052 [2021-03-27 09:57:36 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 420/1251] eta: 0:07:05 lr: 0.000011 loss: 2.6668 (2.6792) grad_norm: 3.3494 (3.4961) time: 0.5113 [2021-03-27 09:57:41 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 430/1251] eta: 0:07:00 lr: 0.000011 loss: 2.5908 (2.6787) grad_norm: 3.3029 (3.4932) time: 0.5067 [2021-03-27 09:57:46 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 440/1251] eta: 0:06:55 lr: 0.000011 loss: 2.5908 (2.6761) grad_norm: 3.3170 (3.4946) time: 0.5038 [2021-03-27 09:57:51 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 450/1251] eta: 0:06:49 lr: 0.000011 loss: 2.6704 (2.6796) grad_norm: 3.2960 (3.4879) time: 0.5009 [2021-03-27 09:57:56 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 460/1251] eta: 0:06:44 lr: 0.000011 loss: 2.7661 (2.6812) grad_norm: 3.1588 (3.4857) time: 0.4975 [2021-03-27 09:58:01 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 470/1251] eta: 0:06:39 lr: 0.000011 loss: 2.7525 (2.6839) grad_norm: 3.2137 (3.4843) time: 0.4974 [2021-03-27 09:58:06 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 480/1251] eta: 0:06:33 lr: 0.000011 loss: 2.7033 (2.6817) grad_norm: 3.2138 (3.4829) time: 0.5012 [2021-03-27 09:58:11 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 490/1251] eta: 0:06:28 lr: 0.000011 loss: 2.6713 (2.6805) grad_norm: 3.2138 (3.5000) time: 0.5025 [2021-03-27 09:58:16 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 500/1251] eta: 0:06:23 lr: 0.000011 loss: 2.6132 (2.6768) grad_norm: 3.1857 (3.4966) time: 0.5009 [2021-03-27 09:58:21 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 510/1251] eta: 0:06:18 lr: 0.000011 loss: 2.8892 (2.6802) grad_norm: 3.1546 (3.4939) time: 0.4991 [2021-03-27 09:58:26 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 520/1251] eta: 0:06:13 lr: 0.000011 loss: 2.9062 (2.6855) grad_norm: 3.4505 (3.4970) time: 0.5025 [2021-03-27 09:58:31 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 530/1251] eta: 0:06:07 lr: 0.000011 loss: 2.8702 (2.6882) grad_norm: 3.3632 (3.4960) time: 0.4991 [2021-03-27 09:58:36 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 540/1251] eta: 0:06:02 lr: 0.000011 loss: 2.7492 (2.6886) grad_norm: 3.2931 (3.4942) time: 0.5045 [2021-03-27 09:58:41 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 550/1251] eta: 0:05:57 lr: 0.000011 loss: 2.6880 (2.6882) grad_norm: 3.3335 (3.4948) time: 0.5209 [2021-03-27 09:58:46 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 560/1251] eta: 0:05:52 lr: 0.000011 loss: 2.7811 (2.6896) grad_norm: 3.4855 (3.4942) time: 0.5150 [2021-03-27 09:58:51 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 570/1251] eta: 0:05:47 lr: 0.000011 loss: 2.7942 (2.6891) grad_norm: 3.4855 (3.4954) time: 0.5021 [2021-03-27 09:58:56 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 580/1251] eta: 0:05:42 lr: 0.000011 loss: 2.6162 (2.6838) grad_norm: 3.3735 (3.4946) time: 0.5034 [2021-03-27 09:59:01 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 590/1251] eta: 0:05:36 lr: 0.000011 loss: 2.5719 (2.6848) grad_norm: 3.2993 (3.4951) time: 0.5033 [2021-03-27 09:59:06 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 600/1251] eta: 0:05:31 lr: 0.000011 loss: 2.8462 (2.6843) grad_norm: 3.1336 (3.4929) time: 0.4994 [2021-03-27 09:59:11 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 610/1251] eta: 0:05:26 lr: 0.000011 loss: 2.8030 (2.6835) grad_norm: 3.1337 (3.4924) time: 0.5048 [2021-03-27 09:59:17 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 620/1251] eta: 0:05:21 lr: 0.000011 loss: 2.6051 (2.6839) grad_norm: 3.3883 (3.4935) time: 0.5082 [2021-03-27 09:59:22 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 630/1251] eta: 0:05:16 lr: 0.000011 loss: 2.8042 (2.6860) grad_norm: 3.2597 (3.4918) time: 0.5058 [2021-03-27 09:59:27 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 640/1251] eta: 0:05:11 lr: 0.000011 loss: 2.8645 (2.6853) grad_norm: 3.4989 (3.4974) time: 0.5018 [2021-03-27 09:59:32 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 650/1251] eta: 0:05:06 lr: 0.000011 loss: 3.0076 (2.6871) grad_norm: 3.7032 (3.5008) time: 0.5012 [2021-03-27 09:59:37 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 660/1251] eta: 0:05:00 lr: 0.000011 loss: 3.0046 (2.6884) grad_norm: 3.3373 (3.4983) time: 0.4998 [2021-03-27 09:59:42 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 670/1251] eta: 0:04:55 lr: 0.000011 loss: 2.5843 (2.6846) grad_norm: 3.2314 (3.4999) time: 0.4965 [2021-03-27 09:59:47 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 680/1251] eta: 0:04:50 lr: 0.000011 loss: 2.6533 (2.6873) grad_norm: 3.5453 (3.5033) time: 0.4979 [2021-03-27 09:59:52 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 690/1251] eta: 0:04:45 lr: 0.000011 loss: 2.7250 (2.6856) grad_norm: 3.4739 (3.5027) time: 0.5049 [2021-03-27 09:59:57 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 700/1251] eta: 0:04:40 lr: 0.000011 loss: 2.7250 (2.6881) grad_norm: 3.4739 (3.5056) time: 0.5080 [2021-03-27 10:00:02 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 710/1251] eta: 0:04:35 lr: 0.000011 loss: 2.7680 (2.6869) grad_norm: 3.3811 (3.5014) time: 0.5109 [2021-03-27 10:00:07 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 720/1251] eta: 0:04:30 lr: 0.000011 loss: 2.4397 (2.6825) grad_norm: 3.2862 (3.5000) time: 0.5104 [2021-03-27 10:00:12 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 730/1251] eta: 0:04:25 lr: 0.000011 loss: 2.5385 (2.6838) grad_norm: 3.3599 (3.5026) time: 0.5129 [2021-03-27 10:00:18 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 740/1251] eta: 0:04:20 lr: 0.000011 loss: 2.8160 (2.6846) grad_norm: 3.3075 (3.5001) time: 0.5320 [2021-03-27 10:00:23 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 750/1251] eta: 0:04:15 lr: 0.000011 loss: 2.8791 (2.6866) grad_norm: 3.2113 (3.5027) time: 0.5240 [2021-03-27 10:00:28 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 760/1251] eta: 0:04:10 lr: 0.000011 loss: 2.8416 (2.6871) grad_norm: 3.2939 (3.5039) time: 0.5138 [2021-03-27 10:00:33 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 770/1251] eta: 0:04:05 lr: 0.000011 loss: 2.6135 (2.6873) grad_norm: 3.3384 (3.5112) time: 0.5111 [2021-03-27 10:00:38 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 780/1251] eta: 0:03:59 lr: 0.000011 loss: 2.4971 (2.6851) grad_norm: 3.5889 (3.5132) time: 0.4977 [2021-03-27 10:00:43 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 790/1251] eta: 0:03:54 lr: 0.000011 loss: 2.7216 (2.6856) grad_norm: 3.5889 (3.5218) time: 0.5014 [2021-03-27 10:00:48 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 800/1251] eta: 0:03:49 lr: 0.000011 loss: 2.8156 (2.6859) grad_norm: 3.5503 (3.5244) time: 0.5037 [2021-03-27 10:00:53 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 810/1251] eta: 0:03:44 lr: 0.000011 loss: 2.8206 (2.6853) grad_norm: 3.6707 (3.5302) time: 0.5058 [2021-03-27 10:00:58 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 820/1251] eta: 0:03:39 lr: 0.000011 loss: 2.6547 (2.6826) grad_norm: 3.6707 (3.5300) time: 0.5124 [2021-03-27 10:01:03 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 830/1251] eta: 0:03:34 lr: 0.000011 loss: 2.7997 (2.6854) grad_norm: 3.3645 (3.5321) time: 0.5121 [2021-03-27 10:01:08 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 840/1251] eta: 0:03:29 lr: 0.000011 loss: 2.8103 (2.6832) grad_norm: 3.4094 (3.5326) time: 0.5108 [2021-03-27 10:01:13 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 850/1251] eta: 0:03:24 lr: 0.000011 loss: 2.7627 (2.6845) grad_norm: 3.5386 (3.5342) time: 0.5035 [2021-03-27 10:01:18 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 860/1251] eta: 0:03:18 lr: 0.000011 loss: 2.7627 (2.6833) grad_norm: 3.5274 (3.5351) time: 0.4978 [2021-03-27 10:01:23 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 870/1251] eta: 0:03:13 lr: 0.000011 loss: 2.7568 (2.6859) grad_norm: 3.2718 (3.5346) time: 0.5016 [2021-03-27 10:01:28 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 880/1251] eta: 0:03:08 lr: 0.000011 loss: 2.7568 (2.6858) grad_norm: 3.3654 (3.5352) time: 0.5033 [2021-03-27 10:01:33 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 890/1251] eta: 0:03:03 lr: 0.000010 loss: 2.7643 (2.6875) grad_norm: 3.3343 (3.5329) time: 0.4996 [2021-03-27 10:01:38 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 900/1251] eta: 0:02:58 lr: 0.000010 loss: 2.8139 (2.6870) grad_norm: 3.3078 (3.5308) time: 0.4989 [2021-03-27 10:01:44 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 910/1251] eta: 0:02:53 lr: 0.000010 loss: 2.6394 (2.6860) grad_norm: 3.3737 (3.5340) time: 0.5096 [2021-03-27 10:01:49 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 920/1251] eta: 0:02:48 lr: 0.000010 loss: 2.6394 (2.6861) grad_norm: 3.4781 (3.5405) time: 0.5236 [2021-03-27 10:01:54 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 930/1251] eta: 0:02:43 lr: 0.000010 loss: 2.7046 (2.6865) grad_norm: 3.2623 (3.5424) time: 0.5182 [2021-03-27 10:01:59 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 940/1251] eta: 0:02:38 lr: 0.000010 loss: 2.7781 (2.6875) grad_norm: 3.3217 (3.5420) time: 0.5074 [2021-03-27 10:02:04 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 950/1251] eta: 0:02:33 lr: 0.000010 loss: 2.7666 (2.6862) grad_norm: 3.2271 (3.5383) time: 0.5076 [2021-03-27 10:02:09 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 960/1251] eta: 0:02:28 lr: 0.000010 loss: 2.7304 (2.6858) grad_norm: 3.2128 (3.5362) time: 0.5041 [2021-03-27 10:02:14 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 970/1251] eta: 0:02:22 lr: 0.000010 loss: 2.8426 (2.6878) grad_norm: 3.2310 (3.5343) time: 0.5012 [2021-03-27 10:02:19 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 980/1251] eta: 0:02:17 lr: 0.000010 loss: 2.8561 (2.6879) grad_norm: 3.2641 (3.5310) time: 0.5050 [2021-03-27 10:02:24 swin_small_patch4_window7_224] INFO: Epoch: [295] [ 990/1251] eta: 0:02:12 lr: 0.000010 loss: 2.6797 (2.6879) grad_norm: 3.2600 (3.5290) time: 0.5055 [2021-03-27 10:02:29 swin_small_patch4_window7_224] INFO: Epoch: [295] [1000/1251] eta: 0:02:07 lr: 0.000010 loss: 2.8087 (2.6893) grad_norm: 3.3092 (3.5284) time: 0.5049 [2021-03-27 10:02:34 swin_small_patch4_window7_224] INFO: Epoch: [295] [1010/1251] eta: 0:02:02 lr: 0.000010 loss: 2.9084 (2.6891) grad_norm: 3.3976 (3.5280) time: 0.5067 [2021-03-27 10:02:39 swin_small_patch4_window7_224] INFO: Epoch: [295] [1020/1251] eta: 0:01:57 lr: 0.000010 loss: 2.7345 (2.6891) grad_norm: 3.4867 (3.5286) time: 0.5058 [2021-03-27 10:02:44 swin_small_patch4_window7_224] INFO: Epoch: [295] [1030/1251] eta: 0:01:52 lr: 0.000010 loss: 2.7697 (2.6916) grad_norm: 3.3806 (3.5349) time: 0.5026 [2021-03-27 10:02:49 swin_small_patch4_window7_224] INFO: Epoch: [295] [1040/1251] eta: 0:01:47 lr: 0.000010 loss: 2.9219 (2.6925) grad_norm: 3.3435 (3.5324) time: 0.5027 [2021-03-27 10:02:54 swin_small_patch4_window7_224] INFO: Epoch: [295] [1050/1251] eta: 0:01:42 lr: 0.000010 loss: 2.6984 (2.6910) grad_norm: 3.3302 (3.5311) time: 0.5016 [2021-03-27 10:02:59 swin_small_patch4_window7_224] INFO: Epoch: [295] [1060/1251] eta: 0:01:37 lr: 0.000010 loss: 2.6984 (2.6912) grad_norm: 3.3770 (3.5301) time: 0.4973 [2021-03-27 10:03:04 swin_small_patch4_window7_224] INFO: Epoch: [295] [1070/1251] eta: 0:01:31 lr: 0.000010 loss: 2.7118 (2.6906) grad_norm: 3.1998 (3.5288) time: 0.4973 [2021-03-27 10:03:09 swin_small_patch4_window7_224] INFO: Epoch: [295] [1080/1251] eta: 0:01:26 lr: 0.000010 loss: 2.7248 (2.6909) grad_norm: 3.1148 (3.5250) time: 0.5011 [2021-03-27 10:03:14 swin_small_patch4_window7_224] INFO: Epoch: [295] [1090/1251] eta: 0:01:21 lr: 0.000010 loss: 2.8808 (2.6926) grad_norm: 3.1741 (3.5222) time: 0.4992 [2021-03-27 10:03:19 swin_small_patch4_window7_224] INFO: Epoch: [295] [1100/1251] eta: 0:01:16 lr: 0.000010 loss: 2.8596 (2.6933) grad_norm: 3.2270 (3.5258) time: 0.4960 [2021-03-27 10:03:24 swin_small_patch4_window7_224] INFO: Epoch: [295] [1110/1251] eta: 0:01:11 lr: 0.000010 loss: 2.7248 (2.6934) grad_norm: 3.3361 (3.5251) time: 0.5002 [2021-03-27 10:03:29 swin_small_patch4_window7_224] INFO: Epoch: [295] [1120/1251] eta: 0:01:06 lr: 0.000010 loss: 2.7722 (2.6936) grad_norm: 3.3591 (3.5243) time: 0.5019 [2021-03-27 10:03:34 swin_small_patch4_window7_224] INFO: Epoch: [295] [1130/1251] eta: 0:01:01 lr: 0.000010 loss: 2.8744 (2.6951) grad_norm: 3.3888 (3.5238) time: 0.5035 [2021-03-27 10:03:40 swin_small_patch4_window7_224] INFO: Epoch: [295] [1140/1251] eta: 0:00:56 lr: 0.000010 loss: 2.8232 (2.6938) grad_norm: 3.3888 (3.5250) time: 0.5063 [2021-03-27 10:03:45 swin_small_patch4_window7_224] INFO: Epoch: [295] [1150/1251] eta: 0:00:51 lr: 0.000010 loss: 2.6556 (2.6935) grad_norm: 3.2401 (3.5224) time: 0.5027 [2021-03-27 10:03:50 swin_small_patch4_window7_224] INFO: Epoch: [295] [1160/1251] eta: 0:00:46 lr: 0.000010 loss: 2.7614 (2.6914) grad_norm: 3.2542 (3.5209) time: 0.5062 [2021-03-27 10:03:55 swin_small_patch4_window7_224] INFO: Epoch: [295] [1170/1251] eta: 0:00:41 lr: 0.000010 loss: 2.3439 (2.6892) grad_norm: 3.3419 (3.5229) time: 0.5095 [2021-03-27 10:04:00 swin_small_patch4_window7_224] INFO: Epoch: [295] [1180/1251] eta: 0:00:36 lr: 0.000010 loss: 2.7519 (2.6907) grad_norm: 3.3467 (3.5292) time: 0.5051 [2021-03-27 10:04:05 swin_small_patch4_window7_224] INFO: Epoch: [295] [1190/1251] eta: 0:00:30 lr: 0.000010 loss: 2.7395 (2.6886) grad_norm: 3.4002 (3.5296) time: 0.5048 [2021-03-27 10:04:10 swin_small_patch4_window7_224] INFO: Epoch: [295] [1200/1251] eta: 0:00:25 lr: 0.000010 loss: 2.7017 (2.6889) grad_norm: 3.6137 (3.5319) time: 0.5081 [2021-03-27 10:04:15 swin_small_patch4_window7_224] INFO: Epoch: [295] [1210/1251] eta: 0:00:20 lr: 0.000010 loss: 2.8224 (2.6899) grad_norm: 3.5655 (3.5320) time: 0.5057 [2021-03-27 10:04:20 swin_small_patch4_window7_224] INFO: Epoch: [295] [1220/1251] eta: 0:00:15 lr: 0.000010 loss: 2.6709 (2.6887) grad_norm: 3.3254 (3.5337) time: 0.5085 [2021-03-27 10:04:25 swin_small_patch4_window7_224] INFO: Epoch: [295] [1230/1251] eta: 0:00:10 lr: 0.000010 loss: 2.6709 (2.6882) grad_norm: 3.2751 (3.5318) time: 0.5106 [2021-03-27 10:04:30 swin_small_patch4_window7_224] INFO: Epoch: [295] [1240/1251] eta: 0:00:05 lr: 0.000010 loss: 2.7880 (2.6891) grad_norm: 3.2121 (3.5312) time: 0.5047 [2021-03-27 10:04:35 swin_small_patch4_window7_224] INFO: Epoch: [295] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.8216 (2.6880) grad_norm: 3.3224 (3.5350) time: 0.5050 [2021-03-27 10:05:29 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:04 loss: 0.5275 (0.5275) acc1: 87.5000 (87.5000) acc5: 96.8750 (96.8750) [2021-03-27 10:05:30 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.6701 (0.6841) acc1: 84.3750 (83.3807) acc5: 96.8750 (96.4489) [2021-03-27 10:05:31 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7183 (0.7207) acc1: 82.8125 (82.2917) acc5: 95.3125 (96.5774) [2021-03-27 10:05:32 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.6849 (0.7159) acc1: 82.8125 (82.5101) acc5: 96.8750 (96.5222) [2021-03-27 10:05:33 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.7065 (0.7468) acc1: 82.8125 (81.8598) acc5: 96.8750 (96.1890) [2021-03-27 10:05:34 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7596 (0.7520) acc1: 81.2500 (81.9200) acc5: 96.8750 (96.0320) [2021-03-27 10:05:49 swin_small_patch4_window7_224] INFO: * Acc@1 83.090 Acc@5 96.234 loss 0.735 [2021-03-27 10:05:49 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 10:05:49 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 10:05:53 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 0/1251] eta: 1:29:29 lr: 0.000010 loss: 2.9661 (2.9661) grad_norm: 3.2716 (3.2716) time: 4.2919 [2021-03-27 10:05:58 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 10/1251] eta: 0:17:53 lr: 0.000010 loss: 2.9661 (2.7515) grad_norm: 3.2716 (3.3225) time: 0.8650 [2021-03-27 10:06:03 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 20/1251] eta: 0:14:11 lr: 0.000010 loss: 2.6926 (2.6812) grad_norm: 3.2756 (3.3520) time: 0.5121 [2021-03-27 10:06:09 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 30/1251] eta: 0:12:57 lr: 0.000010 loss: 2.6710 (2.6442) grad_norm: 3.2811 (3.3343) time: 0.5106 [2021-03-27 10:06:14 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 40/1251] eta: 0:12:13 lr: 0.000010 loss: 2.8720 (2.7052) grad_norm: 3.4677 (3.4108) time: 0.5152 [2021-03-27 10:06:19 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 50/1251] eta: 0:11:45 lr: 0.000010 loss: 2.8986 (2.7393) grad_norm: 3.5396 (3.4534) time: 0.5108 [2021-03-27 10:06:24 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 60/1251] eta: 0:11:23 lr: 0.000010 loss: 2.8503 (2.7560) grad_norm: 3.2401 (3.4504) time: 0.5075 [2021-03-27 10:06:29 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 70/1251] eta: 0:11:04 lr: 0.000010 loss: 2.8444 (2.7541) grad_norm: 3.0704 (3.4938) time: 0.5010 [2021-03-27 10:06:34 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 80/1251] eta: 0:10:51 lr: 0.000010 loss: 2.7766 (2.7367) grad_norm: 3.0704 (3.5076) time: 0.5038 [2021-03-27 10:06:39 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 90/1251] eta: 0:10:38 lr: 0.000010 loss: 2.7176 (2.7030) grad_norm: 3.5473 (3.5633) time: 0.5035 [2021-03-27 10:06:44 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 100/1251] eta: 0:10:27 lr: 0.000010 loss: 2.7015 (2.6793) grad_norm: 3.5717 (3.5632) time: 0.4978 [2021-03-27 10:06:49 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 110/1251] eta: 0:10:17 lr: 0.000010 loss: 2.4810 (2.6685) grad_norm: 3.5019 (3.5545) time: 0.4997 [2021-03-27 10:06:54 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 120/1251] eta: 0:10:08 lr: 0.000010 loss: 2.7118 (2.6851) grad_norm: 3.3258 (3.5535) time: 0.5047 [2021-03-27 10:06:59 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 130/1251] eta: 0:10:01 lr: 0.000010 loss: 2.7565 (2.6742) grad_norm: 3.3001 (3.5405) time: 0.5115 [2021-03-27 10:07:04 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 140/1251] eta: 0:09:52 lr: 0.000010 loss: 2.6769 (2.6780) grad_norm: 3.4830 (3.5370) time: 0.5047 [2021-03-27 10:07:09 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 150/1251] eta: 0:09:45 lr: 0.000010 loss: 2.7588 (2.6889) grad_norm: 3.3648 (3.5312) time: 0.4991 [2021-03-27 10:07:14 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 160/1251] eta: 0:09:37 lr: 0.000010 loss: 2.7806 (2.6885) grad_norm: 3.3405 (3.5191) time: 0.5021 [2021-03-27 10:07:19 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 170/1251] eta: 0:09:31 lr: 0.000010 loss: 2.7214 (2.6918) grad_norm: 3.3405 (3.5151) time: 0.5043 [2021-03-27 10:07:24 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 180/1251] eta: 0:09:24 lr: 0.000010 loss: 2.7214 (2.6912) grad_norm: 3.5548 (3.5308) time: 0.5070 [2021-03-27 10:07:29 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 190/1251] eta: 0:09:18 lr: 0.000010 loss: 2.7027 (2.6915) grad_norm: 3.3863 (3.5278) time: 0.5067 [2021-03-27 10:07:35 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 200/1251] eta: 0:09:12 lr: 0.000010 loss: 2.6404 (2.6809) grad_norm: 3.1657 (3.5213) time: 0.5121 [2021-03-27 10:07:40 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 210/1251] eta: 0:09:06 lr: 0.000010 loss: 2.5911 (2.6758) grad_norm: 3.2252 (3.5241) time: 0.5118 [2021-03-27 10:07:45 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 220/1251] eta: 0:09:00 lr: 0.000010 loss: 2.6753 (2.6734) grad_norm: 3.4605 (3.5283) time: 0.5088 [2021-03-27 10:07:50 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 230/1251] eta: 0:08:54 lr: 0.000010 loss: 2.7308 (2.6759) grad_norm: 3.4605 (3.5249) time: 0.5069 [2021-03-27 10:07:55 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 240/1251] eta: 0:08:47 lr: 0.000010 loss: 2.6623 (2.6782) grad_norm: 3.4301 (3.5232) time: 0.5024 [2021-03-27 10:08:00 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 250/1251] eta: 0:08:41 lr: 0.000010 loss: 2.6817 (2.6800) grad_norm: 3.3722 (3.5143) time: 0.5026 [2021-03-27 10:08:05 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 260/1251] eta: 0:08:36 lr: 0.000010 loss: 2.8322 (2.6843) grad_norm: 3.4006 (3.5136) time: 0.5044 [2021-03-27 10:08:10 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 270/1251] eta: 0:08:30 lr: 0.000010 loss: 2.9055 (2.6921) grad_norm: 3.4083 (3.5082) time: 0.5036 [2021-03-27 10:08:15 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 280/1251] eta: 0:08:24 lr: 0.000010 loss: 2.9338 (2.6949) grad_norm: 3.3243 (3.5066) time: 0.5022 [2021-03-27 10:08:20 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 290/1251] eta: 0:08:19 lr: 0.000010 loss: 2.9338 (2.6937) grad_norm: 3.2212 (3.5005) time: 0.5084 [2021-03-27 10:08:25 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 300/1251] eta: 0:08:13 lr: 0.000010 loss: 2.6882 (2.6946) grad_norm: 3.2779 (3.4993) time: 0.5075 [2021-03-27 10:08:30 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 310/1251] eta: 0:08:07 lr: 0.000010 loss: 2.5965 (2.6877) grad_norm: 3.2779 (3.4962) time: 0.5038 [2021-03-27 10:08:35 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 320/1251] eta: 0:08:01 lr: 0.000010 loss: 2.6458 (2.6886) grad_norm: 3.2707 (3.4975) time: 0.5010 [2021-03-27 10:08:40 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 330/1251] eta: 0:07:56 lr: 0.000010 loss: 2.6430 (2.6850) grad_norm: 3.2202 (3.4952) time: 0.4976 [2021-03-27 10:08:45 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 340/1251] eta: 0:07:50 lr: 0.000010 loss: 2.6175 (2.6849) grad_norm: 3.2202 (3.4920) time: 0.5050 [2021-03-27 10:08:50 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 350/1251] eta: 0:07:45 lr: 0.000010 loss: 2.6371 (2.6843) grad_norm: 3.3404 (3.4912) time: 0.5071 [2021-03-27 10:08:55 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 360/1251] eta: 0:07:40 lr: 0.000010 loss: 2.8413 (2.6860) grad_norm: 3.3885 (3.4890) time: 0.5076 [2021-03-27 10:09:00 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 370/1251] eta: 0:07:34 lr: 0.000010 loss: 2.7609 (2.6878) grad_norm: 3.4960 (3.4910) time: 0.5076 [2021-03-27 10:09:05 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 380/1251] eta: 0:07:29 lr: 0.000010 loss: 2.7285 (2.6894) grad_norm: 3.3006 (3.5290) time: 0.5059 [2021-03-27 10:09:10 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 390/1251] eta: 0:07:23 lr: 0.000010 loss: 2.8285 (2.6862) grad_norm: 3.3006 (3.5356) time: 0.5037 [2021-03-27 10:09:15 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 400/1251] eta: 0:07:18 lr: 0.000010 loss: 2.7337 (2.6856) grad_norm: 3.4237 (3.5353) time: 0.5015 [2021-03-27 10:09:21 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 410/1251] eta: 0:07:13 lr: 0.000010 loss: 2.7337 (2.6844) grad_norm: 3.3109 (3.5258) time: 0.5056 [2021-03-27 10:09:26 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 420/1251] eta: 0:07:07 lr: 0.000010 loss: 2.7396 (2.6808) grad_norm: 3.3109 (3.5285) time: 0.5082 [2021-03-27 10:09:31 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 430/1251] eta: 0:07:02 lr: 0.000010 loss: 2.8211 (2.6839) grad_norm: 3.3713 (3.5239) time: 0.5044 [2021-03-27 10:09:36 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 440/1251] eta: 0:06:57 lr: 0.000010 loss: 2.8211 (2.6822) grad_norm: 3.4369 (3.5257) time: 0.5037 [2021-03-27 10:09:41 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 450/1251] eta: 0:06:51 lr: 0.000010 loss: 2.7190 (2.6832) grad_norm: 3.3394 (3.5189) time: 0.5063 [2021-03-27 10:09:46 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 460/1251] eta: 0:06:46 lr: 0.000010 loss: 2.7281 (2.6842) grad_norm: 3.2068 (3.5328) time: 0.5014 [2021-03-27 10:09:51 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 470/1251] eta: 0:06:40 lr: 0.000010 loss: 2.7656 (2.6859) grad_norm: 3.2006 (3.5262) time: 0.4973 [2021-03-27 10:09:56 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 480/1251] eta: 0:06:35 lr: 0.000010 loss: 2.7916 (2.6861) grad_norm: 3.5180 (3.5321) time: 0.5003 [2021-03-27 10:10:01 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 490/1251] eta: 0:06:30 lr: 0.000010 loss: 2.8353 (2.6902) grad_norm: 3.4049 (3.5291) time: 0.5034 [2021-03-27 10:10:06 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 500/1251] eta: 0:06:24 lr: 0.000010 loss: 2.8634 (2.6896) grad_norm: 3.2866 (3.5307) time: 0.5004 [2021-03-27 10:10:11 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 510/1251] eta: 0:06:19 lr: 0.000010 loss: 2.7069 (2.6878) grad_norm: 3.2968 (3.5259) time: 0.5023 [2021-03-27 10:10:16 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 520/1251] eta: 0:06:14 lr: 0.000010 loss: 2.7544 (2.6916) grad_norm: 3.2769 (3.5212) time: 0.5064 [2021-03-27 10:10:21 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 530/1251] eta: 0:06:09 lr: 0.000010 loss: 2.7544 (2.6893) grad_norm: 3.2769 (3.5195) time: 0.5022 [2021-03-27 10:10:26 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 540/1251] eta: 0:06:04 lr: 0.000010 loss: 2.5648 (2.6881) grad_norm: 3.4923 (3.5254) time: 0.5101 [2021-03-27 10:10:31 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 550/1251] eta: 0:05:59 lr: 0.000010 loss: 2.4381 (2.6825) grad_norm: 3.4923 (3.5249) time: 0.5224 [2021-03-27 10:10:36 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 560/1251] eta: 0:05:53 lr: 0.000010 loss: 2.5554 (2.6822) grad_norm: 3.4311 (3.5261) time: 0.5107 [2021-03-27 10:10:41 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 570/1251] eta: 0:05:48 lr: 0.000010 loss: 2.7279 (2.6826) grad_norm: 3.1875 (3.5213) time: 0.4988 [2021-03-27 10:10:46 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 580/1251] eta: 0:05:43 lr: 0.000010 loss: 2.6750 (2.6823) grad_norm: 3.2756 (3.5212) time: 0.5010 [2021-03-27 10:10:52 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 590/1251] eta: 0:05:38 lr: 0.000010 loss: 2.6229 (2.6821) grad_norm: 3.4164 (3.5192) time: 0.5094 [2021-03-27 10:10:57 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 600/1251] eta: 0:05:33 lr: 0.000010 loss: 2.8249 (2.6846) grad_norm: 3.1567 (3.5188) time: 0.5140 [2021-03-27 10:11:02 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 610/1251] eta: 0:05:28 lr: 0.000010 loss: 2.9382 (2.6873) grad_norm: 3.1411 (3.5150) time: 0.5081 [2021-03-27 10:11:07 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 620/1251] eta: 0:05:22 lr: 0.000010 loss: 2.8674 (2.6884) grad_norm: 3.1959 (3.5128) time: 0.5012 [2021-03-27 10:11:12 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 630/1251] eta: 0:05:17 lr: 0.000010 loss: 2.7076 (2.6886) grad_norm: 3.3424 (3.5162) time: 0.4990 [2021-03-27 10:11:17 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 640/1251] eta: 0:05:12 lr: 0.000010 loss: 2.7076 (2.6895) grad_norm: 3.2390 (3.5133) time: 0.5025 [2021-03-27 10:11:22 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 650/1251] eta: 0:05:07 lr: 0.000010 loss: 2.9391 (2.6925) grad_norm: 3.2225 (3.5076) time: 0.5012 [2021-03-27 10:11:27 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 660/1251] eta: 0:05:02 lr: 0.000010 loss: 2.8380 (2.6893) grad_norm: 3.1484 (3.5095) time: 0.5023 [2021-03-27 10:11:32 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 670/1251] eta: 0:04:56 lr: 0.000010 loss: 2.6843 (2.6870) grad_norm: 3.2887 (3.5098) time: 0.5054 [2021-03-27 10:11:37 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 680/1251] eta: 0:04:51 lr: 0.000010 loss: 2.7129 (2.6883) grad_norm: 3.3486 (3.5116) time: 0.5059 [2021-03-27 10:11:42 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 690/1251] eta: 0:04:46 lr: 0.000010 loss: 2.7131 (2.6843) grad_norm: 3.5444 (3.5161) time: 0.5066 [2021-03-27 10:11:47 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 700/1251] eta: 0:04:41 lr: 0.000010 loss: 2.3379 (2.6782) grad_norm: 3.3491 (3.5167) time: 0.5006 [2021-03-27 10:11:52 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 710/1251] eta: 0:04:36 lr: 0.000010 loss: 2.4072 (2.6781) grad_norm: 3.1020 (3.5120) time: 0.5014 [2021-03-27 10:11:57 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 720/1251] eta: 0:04:31 lr: 0.000010 loss: 2.6229 (2.6768) grad_norm: 3.4031 (3.5405) time: 0.5160 [2021-03-27 10:12:03 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 730/1251] eta: 0:04:26 lr: 0.000010 loss: 2.6851 (2.6770) grad_norm: 3.6910 (3.5428) time: 0.5312 [2021-03-27 10:12:08 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 740/1251] eta: 0:04:21 lr: 0.000010 loss: 2.8861 (2.6792) grad_norm: 3.3431 (3.5425) time: 0.5325 [2021-03-27 10:12:13 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 750/1251] eta: 0:04:16 lr: 0.000010 loss: 2.7007 (2.6790) grad_norm: 3.2663 (3.5437) time: 0.5192 [2021-03-27 10:12:18 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 760/1251] eta: 0:04:10 lr: 0.000010 loss: 2.7007 (2.6791) grad_norm: 3.2757 (3.5462) time: 0.5054 [2021-03-27 10:12:23 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 770/1251] eta: 0:04:05 lr: 0.000010 loss: 2.7779 (2.6813) grad_norm: 3.4136 (3.5479) time: 0.5031 [2021-03-27 10:12:28 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 780/1251] eta: 0:04:00 lr: 0.000010 loss: 2.8265 (2.6835) grad_norm: 3.4506 (3.5456) time: 0.5057 [2021-03-27 10:12:33 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 790/1251] eta: 0:03:55 lr: 0.000010 loss: 2.7442 (2.6828) grad_norm: 3.3916 (3.5461) time: 0.5104 [2021-03-27 10:12:38 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 800/1251] eta: 0:03:50 lr: 0.000010 loss: 2.7442 (2.6828) grad_norm: 3.3869 (3.5473) time: 0.5163 [2021-03-27 10:12:43 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 810/1251] eta: 0:03:45 lr: 0.000010 loss: 2.7796 (2.6848) grad_norm: 3.4858 (3.5520) time: 0.5087 [2021-03-27 10:12:48 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 820/1251] eta: 0:03:40 lr: 0.000010 loss: 2.8616 (2.6846) grad_norm: 3.4932 (3.5540) time: 0.5035 [2021-03-27 10:12:54 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 830/1251] eta: 0:03:35 lr: 0.000010 loss: 2.8304 (2.6840) grad_norm: 3.6233 (3.5580) time: 0.5059 [2021-03-27 10:12:59 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 840/1251] eta: 0:03:29 lr: 0.000010 loss: 2.5747 (2.6792) grad_norm: 3.7065 (3.5703) time: 0.5024 [2021-03-27 10:13:04 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 850/1251] eta: 0:03:24 lr: 0.000010 loss: 2.2977 (2.6771) grad_norm: 3.5831 (3.5707) time: 0.5034 [2021-03-27 10:13:09 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 860/1251] eta: 0:03:19 lr: 0.000010 loss: 2.4438 (2.6753) grad_norm: 3.4954 (3.5769) time: 0.5089 [2021-03-27 10:13:14 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 870/1251] eta: 0:03:14 lr: 0.000010 loss: 2.7548 (2.6767) grad_norm: 3.4954 (3.5768) time: 0.5067 [2021-03-27 10:13:19 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 880/1251] eta: 0:03:09 lr: 0.000010 loss: 2.7069 (2.6758) grad_norm: 3.3420 (3.5767) time: 0.5032 [2021-03-27 10:13:24 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 890/1251] eta: 0:03:04 lr: 0.000010 loss: 2.7069 (2.6763) grad_norm: 3.3410 (3.5752) time: 0.5003 [2021-03-27 10:13:29 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 900/1251] eta: 0:02:59 lr: 0.000010 loss: 2.7465 (2.6757) grad_norm: 3.3263 (3.5734) time: 0.4990 [2021-03-27 10:13:34 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 910/1251] eta: 0:02:54 lr: 0.000010 loss: 2.9301 (2.6784) grad_norm: 3.3410 (3.5731) time: 0.5103 [2021-03-27 10:13:39 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 920/1251] eta: 0:02:48 lr: 0.000010 loss: 2.9301 (2.6799) grad_norm: 3.3997 (3.5708) time: 0.5136 [2021-03-27 10:13:44 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 930/1251] eta: 0:02:43 lr: 0.000010 loss: 2.7581 (2.6794) grad_norm: 3.3373 (3.5672) time: 0.5065 [2021-03-27 10:13:49 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 940/1251] eta: 0:02:38 lr: 0.000010 loss: 2.7697 (2.6797) grad_norm: 3.3111 (3.5654) time: 0.5091 [2021-03-27 10:13:54 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 950/1251] eta: 0:02:33 lr: 0.000010 loss: 2.8421 (2.6813) grad_norm: 3.3111 (3.5639) time: 0.5076 [2021-03-27 10:13:59 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 960/1251] eta: 0:02:28 lr: 0.000010 loss: 2.7281 (2.6808) grad_norm: 3.2390 (3.5655) time: 0.5023 [2021-03-27 10:14:04 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 970/1251] eta: 0:02:23 lr: 0.000010 loss: 2.7271 (2.6811) grad_norm: 3.4648 (3.5650) time: 0.4993 [2021-03-27 10:14:09 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 980/1251] eta: 0:02:18 lr: 0.000010 loss: 2.6662 (2.6799) grad_norm: 3.4373 (3.5647) time: 0.4978 [2021-03-27 10:14:14 swin_small_patch4_window7_224] INFO: Epoch: [296] [ 990/1251] eta: 0:02:13 lr: 0.000010 loss: 2.6076 (2.6804) grad_norm: 3.5814 (3.5721) time: 0.5018 [2021-03-27 10:14:19 swin_small_patch4_window7_224] INFO: Epoch: [296] [1000/1251] eta: 0:02:07 lr: 0.000010 loss: 2.9253 (2.6834) grad_norm: 3.3469 (3.5684) time: 0.5062 [2021-03-27 10:14:24 swin_small_patch4_window7_224] INFO: Epoch: [296] [1010/1251] eta: 0:02:02 lr: 0.000010 loss: 2.8994 (2.6822) grad_norm: 3.1837 (3.5669) time: 0.5077 [2021-03-27 10:14:29 swin_small_patch4_window7_224] INFO: Epoch: [296] [1020/1251] eta: 0:01:57 lr: 0.000010 loss: 2.8085 (2.6828) grad_norm: 3.2547 (3.5642) time: 0.5024 [2021-03-27 10:14:35 swin_small_patch4_window7_224] INFO: Epoch: [296] [1030/1251] eta: 0:01:52 lr: 0.000010 loss: 2.7621 (2.6817) grad_norm: 3.2927 (3.5645) time: 0.5056 [2021-03-27 10:14:40 swin_small_patch4_window7_224] INFO: Epoch: [296] [1040/1251] eta: 0:01:47 lr: 0.000010 loss: 2.6201 (2.6816) grad_norm: 3.4687 (3.5646) time: 0.5094 [2021-03-27 10:14:45 swin_small_patch4_window7_224] INFO: Epoch: [296] [1050/1251] eta: 0:01:42 lr: 0.000010 loss: 2.6746 (2.6815) grad_norm: 3.5474 (3.5644) time: 0.5045 [2021-03-27 10:14:50 swin_small_patch4_window7_224] INFO: Epoch: [296] [1060/1251] eta: 0:01:37 lr: 0.000010 loss: 2.6420 (2.6814) grad_norm: 3.2794 (3.5613) time: 0.5041 [2021-03-27 10:14:55 swin_small_patch4_window7_224] INFO: Epoch: [296] [1070/1251] eta: 0:01:32 lr: 0.000010 loss: 2.7213 (2.6816) grad_norm: 3.2956 (3.5608) time: 0.5018 [2021-03-27 10:15:00 swin_small_patch4_window7_224] INFO: Epoch: [296] [1080/1251] eta: 0:01:27 lr: 0.000010 loss: 2.7515 (2.6830) grad_norm: 3.2555 (3.5574) time: 0.5042 [2021-03-27 10:15:05 swin_small_patch4_window7_224] INFO: Epoch: [296] [1090/1251] eta: 0:01:22 lr: 0.000010 loss: 2.7528 (2.6831) grad_norm: 3.1960 (3.5544) time: 0.5042 [2021-03-27 10:15:10 swin_small_patch4_window7_224] INFO: Epoch: [296] [1100/1251] eta: 0:01:16 lr: 0.000010 loss: 2.8241 (2.6828) grad_norm: 3.3494 (3.5547) time: 0.4955 [2021-03-27 10:15:15 swin_small_patch4_window7_224] INFO: Epoch: [296] [1110/1251] eta: 0:01:11 lr: 0.000010 loss: 2.4836 (2.6787) grad_norm: 3.4292 (3.5543) time: 0.4957 [2021-03-27 10:15:20 swin_small_patch4_window7_224] INFO: Epoch: [296] [1120/1251] eta: 0:01:06 lr: 0.000010 loss: 2.4836 (2.6782) grad_norm: 3.4427 (3.5539) time: 0.5010 [2021-03-27 10:15:25 swin_small_patch4_window7_224] INFO: Epoch: [296] [1130/1251] eta: 0:01:01 lr: 0.000010 loss: 2.6688 (2.6781) grad_norm: 3.5844 (3.5565) time: 0.5063 [2021-03-27 10:15:30 swin_small_patch4_window7_224] INFO: Epoch: [296] [1140/1251] eta: 0:00:56 lr: 0.000010 loss: 2.7155 (2.6776) grad_norm: 3.4118 (3.5562) time: 0.5069 [2021-03-27 10:15:35 swin_small_patch4_window7_224] INFO: Epoch: [296] [1150/1251] eta: 0:00:51 lr: 0.000010 loss: 2.6927 (2.6760) grad_norm: 3.3151 (3.5596) time: 0.5045 [2021-03-27 10:15:40 swin_small_patch4_window7_224] INFO: Epoch: [296] [1160/1251] eta: 0:00:46 lr: 0.000010 loss: 2.6927 (2.6755) grad_norm: 3.4689 (3.5615) time: 0.5019 [2021-03-27 10:15:45 swin_small_patch4_window7_224] INFO: Epoch: [296] [1170/1251] eta: 0:00:41 lr: 0.000010 loss: 2.7150 (2.6768) grad_norm: 3.3518 (3.5608) time: 0.5007 [2021-03-27 10:15:50 swin_small_patch4_window7_224] INFO: Epoch: [296] [1180/1251] eta: 0:00:36 lr: 0.000010 loss: 2.7772 (2.6784) grad_norm: 3.3158 (3.5608) time: 0.5073 [2021-03-27 10:15:55 swin_small_patch4_window7_224] INFO: Epoch: [296] [1190/1251] eta: 0:00:31 lr: 0.000010 loss: 2.7772 (2.6784) grad_norm: 3.3351 (3.5611) time: 0.5041 [2021-03-27 10:16:00 swin_small_patch4_window7_224] INFO: Epoch: [296] [1200/1251] eta: 0:00:25 lr: 0.000010 loss: 2.8091 (2.6787) grad_norm: 3.3351 (3.5626) time: 0.5018 [2021-03-27 10:16:05 swin_small_patch4_window7_224] INFO: Epoch: [296] [1210/1251] eta: 0:00:20 lr: 0.000010 loss: 2.7497 (2.6786) grad_norm: 3.2798 (3.5606) time: 0.5038 [2021-03-27 10:16:10 swin_small_patch4_window7_224] INFO: Epoch: [296] [1220/1251] eta: 0:00:15 lr: 0.000010 loss: 2.7497 (2.6783) grad_norm: 3.1423 (3.5588) time: 0.5014 [2021-03-27 10:16:15 swin_small_patch4_window7_224] INFO: Epoch: [296] [1230/1251] eta: 0:00:10 lr: 0.000010 loss: 2.8494 (2.6786) grad_norm: 3.2985 (3.5570) time: 0.5014 [2021-03-27 10:16:20 swin_small_patch4_window7_224] INFO: Epoch: [296] [1240/1251] eta: 0:00:05 lr: 0.000010 loss: 2.8627 (2.6806) grad_norm: 3.3306 (3.5550) time: 0.4966 [2021-03-27 10:16:25 swin_small_patch4_window7_224] INFO: Epoch: [296] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.8627 (2.6814) grad_norm: 3.2266 (3.5529) time: 0.4920 [2021-03-27 10:16:45 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:28 loss: 0.7802 (0.7802) acc1: 79.6875 (79.6875) acc5: 93.7500 (93.7500) [2021-03-27 10:16:47 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8082 (0.7648) acc1: 79.6875 (81.3920) acc5: 95.3125 (95.7386) [2021-03-27 10:16:48 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:08 loss: 0.7694 (0.7544) acc1: 79.6875 (81.7708) acc5: 95.3125 (95.3125) [2021-03-27 10:16:50 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:05 loss: 0.7388 (0.7577) acc1: 82.8125 (82.0060) acc5: 95.3125 (95.5645) [2021-03-27 10:16:52 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7493 (0.7492) acc1: 82.8125 (82.2027) acc5: 96.8750 (95.8079) [2021-03-27 10:16:53 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7968 (0.7543) acc1: 81.2500 (81.9520) acc5: 95.3125 (95.8400) [2021-03-27 10:17:10 swin_small_patch4_window7_224] INFO: * Acc@1 83.094 Acc@5 96.226 loss 0.738 [2021-03-27 10:17:10 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 10:17:10 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 10:17:14 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 0/1251] eta: 1:25:48 lr: 0.000010 loss: 2.9920 (2.9920) grad_norm: 3.7797 (3.7797) time: 4.1159 [2021-03-27 10:17:19 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 10/1251] eta: 0:17:32 lr: 0.000010 loss: 2.8295 (2.7186) grad_norm: 3.5193 (3.4339) time: 0.8482 [2021-03-27 10:17:24 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 20/1251] eta: 0:13:58 lr: 0.000010 loss: 2.7883 (2.7137) grad_norm: 3.3236 (3.5044) time: 0.5094 [2021-03-27 10:17:29 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 30/1251] eta: 0:12:39 lr: 0.000010 loss: 2.9074 (2.8176) grad_norm: 3.3505 (3.5590) time: 0.4972 [2021-03-27 10:17:34 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 40/1251] eta: 0:11:58 lr: 0.000010 loss: 2.9101 (2.7901) grad_norm: 3.3505 (3.5293) time: 0.5009 [2021-03-27 10:17:39 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 50/1251] eta: 0:11:30 lr: 0.000010 loss: 2.9017 (2.7978) grad_norm: 3.2887 (3.4785) time: 0.5017 [2021-03-27 10:17:44 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 60/1251] eta: 0:11:14 lr: 0.000010 loss: 2.9167 (2.7971) grad_norm: 3.3812 (3.5878) time: 0.5107 [2021-03-27 10:17:49 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 70/1251] eta: 0:10:56 lr: 0.000010 loss: 2.9167 (2.8187) grad_norm: 3.4976 (3.5844) time: 0.5092 [2021-03-27 10:17:54 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 80/1251] eta: 0:10:44 lr: 0.000010 loss: 2.9523 (2.8154) grad_norm: 3.2484 (3.5647) time: 0.5037 [2021-03-27 10:18:00 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 90/1251] eta: 0:10:34 lr: 0.000010 loss: 2.6989 (2.7912) grad_norm: 3.2153 (3.5210) time: 0.5120 [2021-03-27 10:18:05 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 100/1251] eta: 0:10:23 lr: 0.000010 loss: 2.6244 (2.7717) grad_norm: 3.2196 (3.5585) time: 0.5048 [2021-03-27 10:18:10 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 110/1251] eta: 0:10:15 lr: 0.000010 loss: 2.5638 (2.7620) grad_norm: 3.2533 (3.5294) time: 0.5090 [2021-03-27 10:18:15 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 120/1251] eta: 0:10:07 lr: 0.000010 loss: 2.7881 (2.7540) grad_norm: 3.3612 (3.5509) time: 0.5132 [2021-03-27 10:18:20 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 130/1251] eta: 0:09:59 lr: 0.000010 loss: 2.7881 (2.7476) grad_norm: 3.3239 (3.5302) time: 0.5058 [2021-03-27 10:18:25 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 140/1251] eta: 0:09:51 lr: 0.000010 loss: 2.7785 (2.7452) grad_norm: 3.2468 (3.5366) time: 0.5023 [2021-03-27 10:18:30 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 150/1251] eta: 0:09:43 lr: 0.000010 loss: 2.7471 (2.7416) grad_norm: 3.2533 (3.5147) time: 0.5008 [2021-03-27 10:18:35 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 160/1251] eta: 0:09:36 lr: 0.000010 loss: 2.7471 (2.7401) grad_norm: 3.2095 (3.5018) time: 0.5040 [2021-03-27 10:18:40 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 170/1251] eta: 0:09:29 lr: 0.000010 loss: 2.7898 (2.7272) grad_norm: 3.2479 (3.4931) time: 0.5058 [2021-03-27 10:18:45 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 180/1251] eta: 0:09:23 lr: 0.000010 loss: 2.5464 (2.7200) grad_norm: 3.3152 (3.4899) time: 0.5088 [2021-03-27 10:18:50 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 190/1251] eta: 0:09:17 lr: 0.000010 loss: 2.5464 (2.7069) grad_norm: 3.2442 (3.4796) time: 0.5080 [2021-03-27 10:18:55 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 200/1251] eta: 0:09:11 lr: 0.000010 loss: 2.6885 (2.7166) grad_norm: 3.3260 (3.5104) time: 0.5129 [2021-03-27 10:19:00 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 210/1251] eta: 0:09:05 lr: 0.000010 loss: 2.8950 (2.7176) grad_norm: 3.6663 (3.5195) time: 0.5161 [2021-03-27 10:19:06 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 220/1251] eta: 0:08:59 lr: 0.000010 loss: 2.7675 (2.7136) grad_norm: 3.2709 (3.5042) time: 0.5063 [2021-03-27 10:19:11 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 230/1251] eta: 0:08:53 lr: 0.000010 loss: 2.6544 (2.7077) grad_norm: 3.1402 (3.4911) time: 0.5007 [2021-03-27 10:19:15 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 240/1251] eta: 0:08:46 lr: 0.000010 loss: 2.7440 (2.7042) grad_norm: 3.2015 (3.4814) time: 0.4982 [2021-03-27 10:19:21 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 250/1251] eta: 0:08:41 lr: 0.000010 loss: 2.4985 (2.6914) grad_norm: 3.2589 (3.4769) time: 0.4999 [2021-03-27 10:19:26 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 260/1251] eta: 0:08:35 lr: 0.000010 loss: 2.3408 (2.6888) grad_norm: 3.4073 (3.5178) time: 0.5025 [2021-03-27 10:19:31 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 270/1251] eta: 0:08:29 lr: 0.000010 loss: 2.6507 (2.6890) grad_norm: 3.4950 (3.5207) time: 0.4995 [2021-03-27 10:19:36 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 280/1251] eta: 0:08:23 lr: 0.000010 loss: 2.7200 (2.6934) grad_norm: 3.5062 (3.5373) time: 0.4993 [2021-03-27 10:19:41 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 290/1251] eta: 0:08:17 lr: 0.000010 loss: 2.7351 (2.6879) grad_norm: 3.4682 (3.5380) time: 0.5060 [2021-03-27 10:19:46 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 300/1251] eta: 0:08:12 lr: 0.000010 loss: 2.6781 (2.6905) grad_norm: 3.4682 (3.5617) time: 0.5136 [2021-03-27 10:19:51 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 310/1251] eta: 0:08:07 lr: 0.000010 loss: 2.7404 (2.6921) grad_norm: 3.5208 (3.5857) time: 0.5167 [2021-03-27 10:19:56 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 320/1251] eta: 0:08:02 lr: 0.000010 loss: 2.7103 (2.6876) grad_norm: 3.3374 (3.5729) time: 0.5152 [2021-03-27 10:20:01 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 330/1251] eta: 0:07:56 lr: 0.000010 loss: 2.7103 (2.6856) grad_norm: 3.2407 (3.5685) time: 0.5128 [2021-03-27 10:20:06 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 340/1251] eta: 0:07:51 lr: 0.000010 loss: 3.0026 (2.6943) grad_norm: 3.2756 (3.5924) time: 0.5039 [2021-03-27 10:20:11 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 350/1251] eta: 0:07:45 lr: 0.000010 loss: 3.0026 (2.6957) grad_norm: 3.3678 (3.6079) time: 0.5035 [2021-03-27 10:20:16 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 360/1251] eta: 0:07:40 lr: 0.000010 loss: 2.7003 (2.6939) grad_norm: 3.2816 (3.6020) time: 0.5099 [2021-03-27 10:20:21 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 370/1251] eta: 0:07:34 lr: 0.000010 loss: 2.5617 (2.6885) grad_norm: 3.1907 (3.5944) time: 0.5039 [2021-03-27 10:20:26 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 380/1251] eta: 0:07:29 lr: 0.000010 loss: 2.6337 (2.6910) grad_norm: 3.2153 (3.5931) time: 0.5007 [2021-03-27 10:20:31 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 390/1251] eta: 0:07:23 lr: 0.000010 loss: 2.7269 (2.6914) grad_norm: 3.4834 (3.5932) time: 0.5022 [2021-03-27 10:20:36 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 400/1251] eta: 0:07:18 lr: 0.000010 loss: 2.7269 (2.6910) grad_norm: 3.3116 (3.5877) time: 0.5024 [2021-03-27 10:20:42 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 410/1251] eta: 0:07:13 lr: 0.000010 loss: 2.6042 (2.6882) grad_norm: 3.3746 (3.6004) time: 0.5050 [2021-03-27 10:20:47 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 420/1251] eta: 0:07:07 lr: 0.000010 loss: 2.6507 (2.6906) grad_norm: 3.3861 (3.6005) time: 0.5053 [2021-03-27 10:20:52 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 430/1251] eta: 0:07:02 lr: 0.000010 loss: 2.7563 (2.6927) grad_norm: 3.3129 (3.6049) time: 0.5084 [2021-03-27 10:20:57 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 440/1251] eta: 0:06:57 lr: 0.000010 loss: 2.8074 (2.6959) grad_norm: 3.3072 (3.6109) time: 0.5065 [2021-03-27 10:21:02 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 450/1251] eta: 0:06:51 lr: 0.000010 loss: 2.9279 (2.7005) grad_norm: 3.1716 (3.6074) time: 0.5035 [2021-03-27 10:21:07 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 460/1251] eta: 0:06:46 lr: 0.000010 loss: 2.9018 (2.7011) grad_norm: 3.3284 (3.6074) time: 0.5037 [2021-03-27 10:21:12 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 470/1251] eta: 0:06:41 lr: 0.000010 loss: 2.9018 (2.7062) grad_norm: 3.3193 (3.6014) time: 0.5007 [2021-03-27 10:21:17 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 480/1251] eta: 0:06:35 lr: 0.000010 loss: 2.7285 (2.6999) grad_norm: 3.3068 (3.6071) time: 0.5025 [2021-03-27 10:21:22 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 490/1251] eta: 0:06:30 lr: 0.000010 loss: 2.5281 (2.6967) grad_norm: 3.1949 (3.6110) time: 0.5038 [2021-03-27 10:21:27 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 500/1251] eta: 0:06:25 lr: 0.000010 loss: 2.6433 (2.6929) grad_norm: 3.1949 (3.6112) time: 0.4983 [2021-03-27 10:21:32 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 510/1251] eta: 0:06:19 lr: 0.000010 loss: 2.6433 (2.6917) grad_norm: 3.2785 (3.6112) time: 0.4946 [2021-03-27 10:21:37 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 520/1251] eta: 0:06:14 lr: 0.000010 loss: 2.8003 (2.6941) grad_norm: 3.2853 (3.6083) time: 0.5049 [2021-03-27 10:21:42 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 530/1251] eta: 0:06:09 lr: 0.000010 loss: 2.8473 (2.6946) grad_norm: 3.3769 (3.6082) time: 0.5072 [2021-03-27 10:21:47 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 540/1251] eta: 0:06:04 lr: 0.000010 loss: 2.7370 (2.6903) grad_norm: 3.4590 (3.6074) time: 0.5031 [2021-03-27 10:21:52 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 550/1251] eta: 0:05:59 lr: 0.000010 loss: 2.8937 (2.6961) grad_norm: 3.4590 (3.6064) time: 0.5172 [2021-03-27 10:21:57 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 560/1251] eta: 0:05:53 lr: 0.000010 loss: 2.9695 (2.6987) grad_norm: 3.4028 (3.6047) time: 0.5137 [2021-03-27 10:22:02 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 570/1251] eta: 0:05:48 lr: 0.000010 loss: 2.9087 (2.6984) grad_norm: 3.2457 (3.5988) time: 0.5028 [2021-03-27 10:22:07 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 580/1251] eta: 0:05:43 lr: 0.000010 loss: 2.7525 (2.6946) grad_norm: 3.2100 (3.5922) time: 0.5052 [2021-03-27 10:22:12 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 590/1251] eta: 0:05:38 lr: 0.000010 loss: 2.5075 (2.6921) grad_norm: 3.2895 (3.5903) time: 0.5063 [2021-03-27 10:22:17 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 600/1251] eta: 0:05:33 lr: 0.000010 loss: 2.6441 (2.6954) grad_norm: 3.3431 (3.5843) time: 0.5039 [2021-03-27 10:22:23 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 610/1251] eta: 0:05:28 lr: 0.000010 loss: 2.7802 (2.6932) grad_norm: 3.2765 (3.5800) time: 0.5063 [2021-03-27 10:22:28 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 620/1251] eta: 0:05:22 lr: 0.000010 loss: 2.7951 (2.6954) grad_norm: 3.2765 (3.5786) time: 0.5111 [2021-03-27 10:22:33 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 630/1251] eta: 0:05:17 lr: 0.000010 loss: 2.8239 (2.6980) grad_norm: 3.4426 (3.5800) time: 0.5009 [2021-03-27 10:22:38 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 640/1251] eta: 0:05:12 lr: 0.000010 loss: 2.7562 (2.6953) grad_norm: 3.3114 (3.5853) time: 0.5027 [2021-03-27 10:22:43 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 650/1251] eta: 0:05:07 lr: 0.000010 loss: 2.4812 (2.6913) grad_norm: 3.1718 (3.5801) time: 0.5076 [2021-03-27 10:22:48 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 660/1251] eta: 0:05:02 lr: 0.000010 loss: 2.6828 (2.6922) grad_norm: 3.3788 (3.5791) time: 0.5034 [2021-03-27 10:22:53 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 670/1251] eta: 0:04:56 lr: 0.000010 loss: 2.8292 (2.6929) grad_norm: 3.3788 (3.5794) time: 0.5066 [2021-03-27 10:22:58 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 680/1251] eta: 0:04:51 lr: 0.000010 loss: 2.8287 (2.6918) grad_norm: 3.4496 (3.5866) time: 0.5091 [2021-03-27 10:23:03 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 690/1251] eta: 0:04:46 lr: 0.000010 loss: 2.8287 (2.6912) grad_norm: 3.5323 (3.5943) time: 0.5058 [2021-03-27 10:23:08 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 700/1251] eta: 0:04:41 lr: 0.000010 loss: 2.7758 (2.6901) grad_norm: 3.3974 (3.5912) time: 0.5070 [2021-03-27 10:23:13 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 710/1251] eta: 0:04:36 lr: 0.000010 loss: 2.7008 (2.6908) grad_norm: 3.2967 (3.5875) time: 0.5058 [2021-03-27 10:23:18 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 720/1251] eta: 0:04:31 lr: 0.000010 loss: 2.6615 (2.6888) grad_norm: 3.2542 (3.5866) time: 0.5030 [2021-03-27 10:23:23 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 730/1251] eta: 0:04:26 lr: 0.000010 loss: 2.5719 (2.6867) grad_norm: 3.3514 (3.5832) time: 0.5115 [2021-03-27 10:23:29 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 740/1251] eta: 0:04:21 lr: 0.000010 loss: 2.8420 (2.6921) grad_norm: 3.4177 (3.5864) time: 0.5334 [2021-03-27 10:23:34 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 750/1251] eta: 0:04:16 lr: 0.000010 loss: 2.8420 (2.6933) grad_norm: 3.5734 (3.5863) time: 0.5296 [2021-03-27 10:23:39 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 760/1251] eta: 0:04:11 lr: 0.000010 loss: 2.7855 (2.6955) grad_norm: 3.5734 (3.5839) time: 0.5061 [2021-03-27 10:23:44 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 770/1251] eta: 0:04:05 lr: 0.000010 loss: 2.8140 (2.6938) grad_norm: 3.4031 (3.5856) time: 0.5037 [2021-03-27 10:23:49 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 780/1251] eta: 0:04:00 lr: 0.000010 loss: 2.7158 (2.6965) grad_norm: 3.3191 (3.5888) time: 0.5015 [2021-03-27 10:23:54 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 790/1251] eta: 0:03:55 lr: 0.000010 loss: 2.7158 (2.6947) grad_norm: 3.4527 (3.5886) time: 0.4995 [2021-03-27 10:23:59 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 800/1251] eta: 0:03:50 lr: 0.000010 loss: 2.6209 (2.6929) grad_norm: 3.4527 (3.5849) time: 0.5038 [2021-03-27 10:24:04 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 810/1251] eta: 0:03:45 lr: 0.000010 loss: 2.3180 (2.6902) grad_norm: 3.2980 (3.5818) time: 0.5067 [2021-03-27 10:24:09 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 820/1251] eta: 0:03:40 lr: 0.000010 loss: 2.7566 (2.6932) grad_norm: 3.3157 (3.5817) time: 0.5085 [2021-03-27 10:24:14 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 830/1251] eta: 0:03:34 lr: 0.000010 loss: 2.7714 (2.6917) grad_norm: 3.3705 (3.5779) time: 0.5059 [2021-03-27 10:24:19 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 840/1251] eta: 0:03:29 lr: 0.000010 loss: 2.5130 (2.6890) grad_norm: 3.3147 (3.5803) time: 0.5054 [2021-03-27 10:24:25 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 850/1251] eta: 0:03:24 lr: 0.000010 loss: 2.1186 (2.6825) grad_norm: 3.3147 (3.5766) time: 0.5144 [2021-03-27 10:24:30 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 860/1251] eta: 0:03:19 lr: 0.000010 loss: 2.6715 (2.6827) grad_norm: 3.2234 (3.5737) time: 0.5142 [2021-03-27 10:24:35 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 870/1251] eta: 0:03:14 lr: 0.000010 loss: 2.6411 (2.6816) grad_norm: 3.3332 (3.5731) time: 0.5069 [2021-03-27 10:24:40 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 880/1251] eta: 0:03:09 lr: 0.000010 loss: 2.5749 (2.6795) grad_norm: 3.2488 (3.5674) time: 0.5022 [2021-03-27 10:24:45 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 890/1251] eta: 0:03:04 lr: 0.000010 loss: 2.5749 (2.6797) grad_norm: 3.0804 (3.5647) time: 0.5006 [2021-03-27 10:24:50 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 900/1251] eta: 0:02:59 lr: 0.000010 loss: 2.5184 (2.6783) grad_norm: 3.3230 (3.5723) time: 0.5025 [2021-03-27 10:24:55 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 910/1251] eta: 0:02:54 lr: 0.000010 loss: 2.6235 (2.6793) grad_norm: 3.3366 (3.5730) time: 0.5056 [2021-03-27 10:25:00 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 920/1251] eta: 0:02:48 lr: 0.000010 loss: 2.9648 (2.6811) grad_norm: 3.2305 (3.5688) time: 0.5111 [2021-03-27 10:25:05 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 930/1251] eta: 0:02:43 lr: 0.000010 loss: 2.8759 (2.6810) grad_norm: 3.1968 (3.5702) time: 0.5127 [2021-03-27 10:25:10 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 940/1251] eta: 0:02:38 lr: 0.000010 loss: 2.7878 (2.6823) grad_norm: 3.4304 (3.5688) time: 0.5051 [2021-03-27 10:25:15 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 950/1251] eta: 0:02:33 lr: 0.000010 loss: 2.7705 (2.6808) grad_norm: 3.3213 (3.5660) time: 0.5022 [2021-03-27 10:25:20 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 960/1251] eta: 0:02:28 lr: 0.000010 loss: 2.6307 (2.6799) grad_norm: 3.1866 (3.5635) time: 0.5046 [2021-03-27 10:25:25 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 970/1251] eta: 0:02:23 lr: 0.000010 loss: 2.7375 (2.6795) grad_norm: 3.1866 (3.5616) time: 0.5038 [2021-03-27 10:25:30 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 980/1251] eta: 0:02:18 lr: 0.000010 loss: 2.5630 (2.6787) grad_norm: 3.3023 (3.5619) time: 0.5098 [2021-03-27 10:25:35 swin_small_patch4_window7_224] INFO: Epoch: [297] [ 990/1251] eta: 0:02:13 lr: 0.000010 loss: 2.7461 (2.6795) grad_norm: 3.3350 (3.5605) time: 0.5053 [2021-03-27 10:25:40 swin_small_patch4_window7_224] INFO: Epoch: [297] [1000/1251] eta: 0:02:07 lr: 0.000010 loss: 2.7461 (2.6798) grad_norm: 3.3577 (3.5640) time: 0.4960 [2021-03-27 10:25:45 swin_small_patch4_window7_224] INFO: Epoch: [297] [1010/1251] eta: 0:02:02 lr: 0.000010 loss: 2.6660 (2.6791) grad_norm: 3.4625 (3.5645) time: 0.4974 [2021-03-27 10:25:50 swin_small_patch4_window7_224] INFO: Epoch: [297] [1020/1251] eta: 0:01:57 lr: 0.000010 loss: 2.6668 (2.6787) grad_norm: 3.3333 (3.5629) time: 0.5018 [2021-03-27 10:25:55 swin_small_patch4_window7_224] INFO: Epoch: [297] [1030/1251] eta: 0:01:52 lr: 0.000010 loss: 2.6668 (2.6774) grad_norm: 3.3333 (3.5643) time: 0.5054 [2021-03-27 10:26:01 swin_small_patch4_window7_224] INFO: Epoch: [297] [1040/1251] eta: 0:01:47 lr: 0.000010 loss: 2.6542 (2.6775) grad_norm: 3.1518 (3.5610) time: 0.5107 [2021-03-27 10:26:06 swin_small_patch4_window7_224] INFO: Epoch: [297] [1050/1251] eta: 0:01:42 lr: 0.000010 loss: 2.7350 (2.6783) grad_norm: 3.1103 (3.5591) time: 0.5183 [2021-03-27 10:26:11 swin_small_patch4_window7_224] INFO: Epoch: [297] [1060/1251] eta: 0:01:37 lr: 0.000010 loss: 2.8603 (2.6797) grad_norm: 3.4079 (3.5599) time: 0.5122 [2021-03-27 10:26:16 swin_small_patch4_window7_224] INFO: Epoch: [297] [1070/1251] eta: 0:01:32 lr: 0.000010 loss: 2.7675 (2.6790) grad_norm: 3.4549 (3.5601) time: 0.5104 [2021-03-27 10:26:21 swin_small_patch4_window7_224] INFO: Epoch: [297] [1080/1251] eta: 0:01:27 lr: 0.000010 loss: 2.5905 (2.6775) grad_norm: 3.3246 (3.5566) time: 0.5073 [2021-03-27 10:26:26 swin_small_patch4_window7_224] INFO: Epoch: [297] [1090/1251] eta: 0:01:22 lr: 0.000010 loss: 2.6095 (2.6777) grad_norm: 3.1627 (3.5562) time: 0.4982 [2021-03-27 10:26:31 swin_small_patch4_window7_224] INFO: Epoch: [297] [1100/1251] eta: 0:01:16 lr: 0.000010 loss: 2.9398 (2.6794) grad_norm: 3.1158 (3.5536) time: 0.4993 [2021-03-27 10:26:36 swin_small_patch4_window7_224] INFO: Epoch: [297] [1110/1251] eta: 0:01:11 lr: 0.000010 loss: 2.7017 (2.6781) grad_norm: 3.1291 (3.5512) time: 0.5027 [2021-03-27 10:26:41 swin_small_patch4_window7_224] INFO: Epoch: [297] [1120/1251] eta: 0:01:06 lr: 0.000010 loss: 2.5260 (2.6758) grad_norm: 3.3943 (3.5516) time: 0.5022 [2021-03-27 10:26:46 swin_small_patch4_window7_224] INFO: Epoch: [297] [1130/1251] eta: 0:01:01 lr: 0.000010 loss: 2.8080 (2.6777) grad_norm: 3.3439 (3.5497) time: 0.5064 [2021-03-27 10:26:51 swin_small_patch4_window7_224] INFO: Epoch: [297] [1140/1251] eta: 0:00:56 lr: 0.000010 loss: 2.8597 (2.6780) grad_norm: 3.3005 (3.5509) time: 0.5098 [2021-03-27 10:26:56 swin_small_patch4_window7_224] INFO: Epoch: [297] [1150/1251] eta: 0:00:51 lr: 0.000010 loss: 2.6810 (2.6768) grad_norm: 3.4039 (3.5505) time: 0.5031 [2021-03-27 10:27:01 swin_small_patch4_window7_224] INFO: Epoch: [297] [1160/1251] eta: 0:00:46 lr: 0.000010 loss: 2.6711 (2.6776) grad_norm: 3.5562 (3.5516) time: 0.5042 [2021-03-27 10:27:06 swin_small_patch4_window7_224] INFO: Epoch: [297] [1170/1251] eta: 0:00:41 lr: 0.000010 loss: 2.7639 (2.6782) grad_norm: 3.3123 (3.5494) time: 0.4999 [2021-03-27 10:27:11 swin_small_patch4_window7_224] INFO: Epoch: [297] [1180/1251] eta: 0:00:36 lr: 0.000010 loss: 2.6919 (2.6773) grad_norm: 3.3123 (3.5473) time: 0.4914 [2021-03-27 10:27:16 swin_small_patch4_window7_224] INFO: Epoch: [297] [1190/1251] eta: 0:00:31 lr: 0.000010 loss: 2.5624 (2.6749) grad_norm: 3.4198 (3.5483) time: 0.4949 [2021-03-27 10:27:21 swin_small_patch4_window7_224] INFO: Epoch: [297] [1200/1251] eta: 0:00:25 lr: 0.000010 loss: 2.6280 (2.6750) grad_norm: 3.3833 (3.5472) time: 0.5010 [2021-03-27 10:27:26 swin_small_patch4_window7_224] INFO: Epoch: [297] [1210/1251] eta: 0:00:20 lr: 0.000010 loss: 2.7265 (2.6751) grad_norm: 3.2833 (3.5510) time: 0.5015 [2021-03-27 10:27:31 swin_small_patch4_window7_224] INFO: Epoch: [297] [1220/1251] eta: 0:00:15 lr: 0.000010 loss: 2.7853 (2.6773) grad_norm: 3.4877 (3.5516) time: 0.5023 [2021-03-27 10:27:36 swin_small_patch4_window7_224] INFO: Epoch: [297] [1230/1251] eta: 0:00:10 lr: 0.000010 loss: 2.9952 (2.6765) grad_norm: 3.2998 (3.5486) time: 0.5034 [2021-03-27 10:27:41 swin_small_patch4_window7_224] INFO: Epoch: [297] [1240/1251] eta: 0:00:05 lr: 0.000010 loss: 2.7307 (2.6755) grad_norm: 3.1986 (3.5477) time: 0.5033 [2021-03-27 10:27:46 swin_small_patch4_window7_224] INFO: Epoch: [297] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.7307 (2.6744) grad_norm: 3.4027 (3.5472) time: 0.4940 [2021-03-27 10:27:57 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:39 loss: 0.8767 (0.8767) acc1: 78.1250 (78.1250) acc5: 96.8750 (96.8750) [2021-03-27 10:28:00 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:16 loss: 0.8067 (0.7469) acc1: 79.6875 (80.8239) acc5: 96.8750 (96.7330) [2021-03-27 10:28:02 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:09 loss: 0.7149 (0.7192) acc1: 81.2500 (82.5149) acc5: 96.8750 (96.4286) [2021-03-27 10:28:05 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.6854 (0.7419) acc1: 81.2500 (82.0565) acc5: 96.8750 (96.1694) [2021-03-27 10:28:06 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.7985 (0.7499) acc1: 81.2500 (82.0503) acc5: 96.8750 (96.1128) [2021-03-27 10:28:07 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7517 (0.7544) acc1: 81.2500 (81.9200) acc5: 96.8750 (96.1280) [2021-03-27 10:28:23 swin_small_patch4_window7_224] INFO: * Acc@1 83.048 Acc@5 96.248 loss 0.736 [2021-03-27 10:28:23 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.0% [2021-03-27 10:28:23 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 10:28:28 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 0/1251] eta: 1:44:56 lr: 0.000010 loss: 2.7709 (2.7709) grad_norm: 3.4533 (3.4533) time: 5.0328 [2021-03-27 10:28:33 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 10/1251] eta: 0:19:15 lr: 0.000010 loss: 2.7727 (2.5515) grad_norm: 3.3843 (3.3445) time: 0.9311 [2021-03-27 10:28:38 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 20/1251] eta: 0:14:57 lr: 0.000010 loss: 2.5619 (2.5849) grad_norm: 3.2775 (4.0041) time: 0.5141 [2021-03-27 10:28:43 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 30/1251] eta: 0:13:23 lr: 0.000010 loss: 2.6175 (2.6428) grad_norm: 3.1492 (3.8608) time: 0.5074 [2021-03-27 10:28:48 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 40/1251] eta: 0:12:33 lr: 0.000010 loss: 2.7127 (2.6847) grad_norm: 3.0833 (3.7535) time: 0.5095 [2021-03-27 10:28:53 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 50/1251] eta: 0:11:59 lr: 0.000010 loss: 2.7485 (2.6937) grad_norm: 3.1368 (3.6674) time: 0.5089 [2021-03-27 10:28:58 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 60/1251] eta: 0:11:35 lr: 0.000010 loss: 2.5394 (2.6412) grad_norm: 3.3417 (3.6165) time: 0.5054 [2021-03-27 10:29:03 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 70/1251] eta: 0:11:15 lr: 0.000010 loss: 2.5252 (2.6419) grad_norm: 3.5166 (3.7128) time: 0.5027 [2021-03-27 10:29:08 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 80/1251] eta: 0:11:02 lr: 0.000010 loss: 2.6366 (2.6294) grad_norm: 3.5484 (3.6839) time: 0.5094 [2021-03-27 10:29:14 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 90/1251] eta: 0:10:50 lr: 0.000010 loss: 2.6757 (2.6359) grad_norm: 3.2469 (3.6592) time: 0.5169 [2021-03-27 10:29:19 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 100/1251] eta: 0:10:38 lr: 0.000010 loss: 2.8143 (2.6530) grad_norm: 3.5873 (3.6580) time: 0.5102 [2021-03-27 10:29:24 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 110/1251] eta: 0:10:28 lr: 0.000010 loss: 2.7684 (2.6615) grad_norm: 3.4289 (3.6302) time: 0.5094 [2021-03-27 10:29:29 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 120/1251] eta: 0:10:18 lr: 0.000010 loss: 2.6016 (2.6475) grad_norm: 3.2759 (3.6279) time: 0.5108 [2021-03-27 10:29:34 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 130/1251] eta: 0:10:10 lr: 0.000010 loss: 2.7260 (2.6514) grad_norm: 3.2117 (3.6034) time: 0.5117 [2021-03-27 10:29:39 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 140/1251] eta: 0:10:02 lr: 0.000010 loss: 2.7260 (2.6511) grad_norm: 3.0412 (3.5932) time: 0.5147 [2021-03-27 10:29:44 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 150/1251] eta: 0:09:54 lr: 0.000010 loss: 2.8074 (2.6614) grad_norm: 3.3817 (3.5795) time: 0.5056 [2021-03-27 10:29:49 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 160/1251] eta: 0:09:46 lr: 0.000010 loss: 2.8272 (2.6712) grad_norm: 3.4185 (3.5943) time: 0.5005 [2021-03-27 10:29:54 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 170/1251] eta: 0:09:39 lr: 0.000010 loss: 2.7480 (2.6666) grad_norm: 3.3120 (3.5807) time: 0.5071 [2021-03-27 10:29:59 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 180/1251] eta: 0:09:32 lr: 0.000010 loss: 2.8142 (2.6799) grad_norm: 3.3159 (3.5664) time: 0.5104 [2021-03-27 10:30:04 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 190/1251] eta: 0:09:24 lr: 0.000010 loss: 2.8414 (2.6840) grad_norm: 3.3765 (3.5621) time: 0.5027 [2021-03-27 10:30:10 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 200/1251] eta: 0:09:19 lr: 0.000010 loss: 2.8020 (2.6839) grad_norm: 3.3816 (3.5616) time: 0.5142 [2021-03-27 10:30:15 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 210/1251] eta: 0:09:12 lr: 0.000010 loss: 2.8020 (2.6818) grad_norm: 3.4987 (3.5555) time: 0.5195 [2021-03-27 10:30:20 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 220/1251] eta: 0:09:05 lr: 0.000010 loss: 2.6761 (2.6809) grad_norm: 3.2594 (3.5408) time: 0.5007 [2021-03-27 10:30:25 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 230/1251] eta: 0:09:00 lr: 0.000010 loss: 2.6061 (2.6745) grad_norm: 3.2932 (3.5344) time: 0.5046 [2021-03-27 10:30:30 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 240/1251] eta: 0:08:53 lr: 0.000010 loss: 2.6333 (2.6721) grad_norm: 3.3859 (3.5529) time: 0.5120 [2021-03-27 10:30:35 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 250/1251] eta: 0:08:47 lr: 0.000010 loss: 2.7061 (2.6736) grad_norm: 3.4144 (3.5860) time: 0.5075 [2021-03-27 10:30:40 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 260/1251] eta: 0:08:41 lr: 0.000010 loss: 2.7218 (2.6723) grad_norm: 3.4091 (3.5874) time: 0.5046 [2021-03-27 10:30:45 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 270/1251] eta: 0:08:35 lr: 0.000010 loss: 2.8785 (2.6792) grad_norm: 3.1458 (3.5880) time: 0.5055 [2021-03-27 10:30:50 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 280/1251] eta: 0:08:29 lr: 0.000010 loss: 2.8785 (2.6864) grad_norm: 3.3324 (3.5818) time: 0.5087 [2021-03-27 10:30:55 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 290/1251] eta: 0:08:23 lr: 0.000010 loss: 2.7168 (2.6844) grad_norm: 3.5227 (3.5902) time: 0.5083 [2021-03-27 10:31:00 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 300/1251] eta: 0:08:18 lr: 0.000010 loss: 2.7532 (2.6870) grad_norm: 3.4179 (3.5790) time: 0.5078 [2021-03-27 10:31:05 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 310/1251] eta: 0:08:12 lr: 0.000010 loss: 2.8586 (2.6939) grad_norm: 3.3756 (3.5807) time: 0.5104 [2021-03-27 10:31:10 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 320/1251] eta: 0:08:06 lr: 0.000010 loss: 2.8082 (2.6938) grad_norm: 3.3292 (3.5739) time: 0.5074 [2021-03-27 10:31:16 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 330/1251] eta: 0:08:01 lr: 0.000010 loss: 2.7233 (2.6953) grad_norm: 3.3250 (3.5643) time: 0.5061 [2021-03-27 10:31:21 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 340/1251] eta: 0:07:55 lr: 0.000010 loss: 2.7233 (2.6982) grad_norm: 3.2816 (3.5567) time: 0.5021 [2021-03-27 10:31:26 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 350/1251] eta: 0:07:49 lr: 0.000010 loss: 2.7086 (2.6966) grad_norm: 3.2925 (3.5519) time: 0.5001 [2021-03-27 10:31:31 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 360/1251] eta: 0:07:43 lr: 0.000010 loss: 2.7086 (2.6980) grad_norm: 3.3780 (3.5431) time: 0.5021 [2021-03-27 10:31:36 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 370/1251] eta: 0:07:38 lr: 0.000010 loss: 2.7622 (2.6984) grad_norm: 3.1131 (3.5350) time: 0.4989 [2021-03-27 10:31:41 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 380/1251] eta: 0:07:32 lr: 0.000010 loss: 2.7709 (2.7033) grad_norm: 3.2568 (3.5381) time: 0.4990 [2021-03-27 10:31:46 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 390/1251] eta: 0:07:26 lr: 0.000010 loss: 2.7274 (2.7039) grad_norm: 3.3931 (3.5497) time: 0.5030 [2021-03-27 10:31:51 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 400/1251] eta: 0:07:21 lr: 0.000010 loss: 2.9073 (2.7087) grad_norm: 3.3913 (3.5413) time: 0.5067 [2021-03-27 10:31:56 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 410/1251] eta: 0:07:16 lr: 0.000010 loss: 2.9104 (2.7087) grad_norm: 3.1972 (3.5396) time: 0.5133 [2021-03-27 10:32:01 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 420/1251] eta: 0:07:11 lr: 0.000010 loss: 2.7148 (2.7043) grad_norm: 3.2695 (3.5393) time: 0.5191 [2021-03-27 10:32:06 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 430/1251] eta: 0:07:05 lr: 0.000010 loss: 2.7008 (2.7065) grad_norm: 3.2754 (3.5340) time: 0.5179 [2021-03-27 10:32:11 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 440/1251] eta: 0:07:00 lr: 0.000010 loss: 2.8004 (2.7045) grad_norm: 3.2828 (3.5275) time: 0.5127 [2021-03-27 10:32:16 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 450/1251] eta: 0:06:55 lr: 0.000010 loss: 2.7399 (2.7043) grad_norm: 3.3381 (3.5290) time: 0.5035 [2021-03-27 10:32:21 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 460/1251] eta: 0:06:49 lr: 0.000010 loss: 2.7190 (2.7035) grad_norm: 3.6756 (3.5364) time: 0.4994 [2021-03-27 10:32:26 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 470/1251] eta: 0:06:44 lr: 0.000010 loss: 2.5721 (2.6970) grad_norm: 3.4758 (3.5336) time: 0.5000 [2021-03-27 10:32:31 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 480/1251] eta: 0:06:38 lr: 0.000010 loss: 2.2687 (2.6920) grad_norm: 3.1958 (3.5422) time: 0.5038 [2021-03-27 10:32:36 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 490/1251] eta: 0:06:33 lr: 0.000010 loss: 2.4931 (2.6912) grad_norm: 3.5980 (3.5549) time: 0.5040 [2021-03-27 10:32:41 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 500/1251] eta: 0:06:27 lr: 0.000010 loss: 2.7064 (2.6905) grad_norm: 3.4365 (3.5514) time: 0.4963 [2021-03-27 10:32:46 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 510/1251] eta: 0:06:22 lr: 0.000010 loss: 2.7705 (2.6894) grad_norm: 3.2716 (3.5537) time: 0.4962 [2021-03-27 10:32:51 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 520/1251] eta: 0:06:17 lr: 0.000010 loss: 2.7124 (2.6881) grad_norm: 3.2188 (3.5482) time: 0.5071 [2021-03-27 10:32:57 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 530/1251] eta: 0:06:11 lr: 0.000010 loss: 2.7649 (2.6910) grad_norm: 3.3596 (3.5508) time: 0.5079 [2021-03-27 10:33:01 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 540/1251] eta: 0:06:06 lr: 0.000010 loss: 2.7369 (2.6852) grad_norm: 3.4433 (3.5495) time: 0.4994 [2021-03-27 10:33:07 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 550/1251] eta: 0:06:01 lr: 0.000010 loss: 2.5386 (2.6847) grad_norm: 3.3306 (3.5424) time: 0.5067 [2021-03-27 10:33:12 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 560/1251] eta: 0:05:55 lr: 0.000010 loss: 2.7039 (2.6843) grad_norm: 3.4269 (3.5536) time: 0.5108 [2021-03-27 10:33:17 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 570/1251] eta: 0:05:50 lr: 0.000010 loss: 2.5739 (2.6824) grad_norm: 3.5202 (3.5580) time: 0.5035 [2021-03-27 10:33:22 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 580/1251] eta: 0:05:45 lr: 0.000010 loss: 2.7502 (2.6838) grad_norm: 3.6261 (3.5617) time: 0.5058 [2021-03-27 10:33:27 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 590/1251] eta: 0:05:40 lr: 0.000010 loss: 2.7297 (2.6836) grad_norm: 3.4782 (3.5573) time: 0.5130 [2021-03-27 10:33:32 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 600/1251] eta: 0:05:35 lr: 0.000010 loss: 2.6480 (2.6830) grad_norm: 3.2844 (3.5623) time: 0.5091 [2021-03-27 10:33:37 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 610/1251] eta: 0:05:29 lr: 0.000010 loss: 2.6995 (2.6847) grad_norm: 3.1350 (3.5619) time: 0.5011 [2021-03-27 10:33:42 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 620/1251] eta: 0:05:24 lr: 0.000010 loss: 2.8237 (2.6848) grad_norm: 3.1350 (3.5594) time: 0.4985 [2021-03-27 10:33:47 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 630/1251] eta: 0:05:19 lr: 0.000010 loss: 2.7836 (2.6827) grad_norm: 3.3338 (3.5593) time: 0.5075 [2021-03-27 10:33:52 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 640/1251] eta: 0:05:14 lr: 0.000010 loss: 2.5213 (2.6800) grad_norm: 3.3338 (3.5572) time: 0.5141 [2021-03-27 10:33:57 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 650/1251] eta: 0:05:08 lr: 0.000010 loss: 2.5802 (2.6775) grad_norm: 3.1427 (3.5537) time: 0.5056 [2021-03-27 10:34:02 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 660/1251] eta: 0:05:03 lr: 0.000010 loss: 2.5831 (2.6733) grad_norm: 3.3663 (3.5571) time: 0.5011 [2021-03-27 10:34:07 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 670/1251] eta: 0:04:58 lr: 0.000010 loss: 2.6788 (2.6749) grad_norm: 3.3399 (3.5544) time: 0.5007 [2021-03-27 10:34:12 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 680/1251] eta: 0:04:53 lr: 0.000010 loss: 2.8412 (2.6744) grad_norm: 3.1398 (3.5509) time: 0.5058 [2021-03-27 10:34:17 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 690/1251] eta: 0:04:47 lr: 0.000010 loss: 2.7016 (2.6732) grad_norm: 3.2988 (3.5513) time: 0.5058 [2021-03-27 10:34:22 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 700/1251] eta: 0:04:42 lr: 0.000010 loss: 2.4952 (2.6717) grad_norm: 3.6046 (3.5567) time: 0.5013 [2021-03-27 10:34:27 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 710/1251] eta: 0:04:37 lr: 0.000010 loss: 2.7479 (2.6712) grad_norm: 3.3781 (3.5521) time: 0.5018 [2021-03-27 10:34:32 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 720/1251] eta: 0:04:32 lr: 0.000010 loss: 2.7521 (2.6718) grad_norm: 3.2838 (3.5563) time: 0.5011 [2021-03-27 10:34:38 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 730/1251] eta: 0:04:27 lr: 0.000010 loss: 2.8143 (2.6730) grad_norm: 3.2739 (3.5537) time: 0.5035 [2021-03-27 10:34:43 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 740/1251] eta: 0:04:22 lr: 0.000010 loss: 2.7312 (2.6735) grad_norm: 3.4641 (3.5547) time: 0.5162 [2021-03-27 10:34:48 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 750/1251] eta: 0:04:17 lr: 0.000010 loss: 2.7348 (2.6735) grad_norm: 3.4641 (3.5529) time: 0.5260 [2021-03-27 10:34:53 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 760/1251] eta: 0:04:11 lr: 0.000010 loss: 2.6886 (2.6745) grad_norm: 3.3350 (3.5556) time: 0.5179 [2021-03-27 10:34:58 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 770/1251] eta: 0:04:06 lr: 0.000010 loss: 2.6400 (2.6725) grad_norm: 3.3821 (3.5554) time: 0.5024 [2021-03-27 10:35:03 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 780/1251] eta: 0:04:01 lr: 0.000010 loss: 2.7766 (2.6751) grad_norm: 3.2978 (3.5504) time: 0.4970 [2021-03-27 10:35:08 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 790/1251] eta: 0:03:56 lr: 0.000010 loss: 2.7918 (2.6738) grad_norm: 3.1718 (3.5533) time: 0.5021 [2021-03-27 10:35:13 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 800/1251] eta: 0:03:51 lr: 0.000010 loss: 2.7918 (2.6774) grad_norm: 3.2864 (3.5506) time: 0.5025 [2021-03-27 10:35:18 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 810/1251] eta: 0:03:45 lr: 0.000010 loss: 2.7548 (2.6765) grad_norm: 3.3519 (3.5486) time: 0.5015 [2021-03-27 10:35:23 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 820/1251] eta: 0:03:40 lr: 0.000010 loss: 2.5716 (2.6749) grad_norm: 3.3729 (3.5509) time: 0.5126 [2021-03-27 10:35:28 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 830/1251] eta: 0:03:35 lr: 0.000010 loss: 2.6119 (2.6752) grad_norm: 3.3566 (3.5472) time: 0.5115 [2021-03-27 10:35:34 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 840/1251] eta: 0:03:30 lr: 0.000010 loss: 2.7565 (2.6735) grad_norm: 3.2945 (3.5519) time: 0.5092 [2021-03-27 10:35:39 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 850/1251] eta: 0:03:25 lr: 0.000010 loss: 2.5441 (2.6724) grad_norm: 3.3858 (3.5509) time: 0.5147 [2021-03-27 10:35:44 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 860/1251] eta: 0:03:20 lr: 0.000010 loss: 2.5441 (2.6712) grad_norm: 3.4035 (nan) time: 0.5034 [2021-03-27 10:35:49 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 870/1251] eta: 0:03:15 lr: 0.000010 loss: 2.5952 (2.6707) grad_norm: 3.4393 (nan) time: 0.5004 [2021-03-27 10:35:54 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 880/1251] eta: 0:03:09 lr: 0.000010 loss: 2.5952 (2.6700) grad_norm: 3.3517 (nan) time: 0.5035 [2021-03-27 10:35:59 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 890/1251] eta: 0:03:04 lr: 0.000010 loss: 2.7772 (2.6716) grad_norm: 3.4798 (nan) time: 0.5051 [2021-03-27 10:36:04 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 900/1251] eta: 0:02:59 lr: 0.000010 loss: 2.7027 (2.6707) grad_norm: 3.4798 (nan) time: 0.5035 [2021-03-27 10:36:09 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 910/1251] eta: 0:02:54 lr: 0.000010 loss: 2.7892 (2.6719) grad_norm: 3.2023 (nan) time: 0.4952 [2021-03-27 10:36:14 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 920/1251] eta: 0:02:49 lr: 0.000010 loss: 2.6847 (2.6699) grad_norm: 3.3008 (nan) time: 0.5042 [2021-03-27 10:36:19 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 930/1251] eta: 0:02:44 lr: 0.000010 loss: 2.6006 (2.6700) grad_norm: 3.3114 (nan) time: 0.5106 [2021-03-27 10:36:24 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 940/1251] eta: 0:02:39 lr: 0.000010 loss: 2.7645 (2.6703) grad_norm: 3.1695 (nan) time: 0.5196 [2021-03-27 10:36:29 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 950/1251] eta: 0:02:33 lr: 0.000010 loss: 2.7645 (2.6693) grad_norm: 3.1880 (nan) time: 0.5159 [2021-03-27 10:36:34 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 960/1251] eta: 0:02:28 lr: 0.000010 loss: 2.8491 (2.6715) grad_norm: 3.1880 (nan) time: 0.4979 [2021-03-27 10:36:39 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 970/1251] eta: 0:02:23 lr: 0.000010 loss: 2.7412 (2.6706) grad_norm: 3.1831 (nan) time: 0.5017 [2021-03-27 10:36:44 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 980/1251] eta: 0:02:18 lr: 0.000010 loss: 2.5579 (2.6694) grad_norm: 3.3438 (nan) time: 0.5000 [2021-03-27 10:36:49 swin_small_patch4_window7_224] INFO: Epoch: [298] [ 990/1251] eta: 0:02:13 lr: 0.000010 loss: 2.7882 (2.6703) grad_norm: 3.3665 (nan) time: 0.5038 [2021-03-27 10:36:54 swin_small_patch4_window7_224] INFO: Epoch: [298] [1000/1251] eta: 0:02:08 lr: 0.000010 loss: 2.8038 (2.6683) grad_norm: 3.3254 (nan) time: 0.5056 [2021-03-27 10:36:59 swin_small_patch4_window7_224] INFO: Epoch: [298] [1010/1251] eta: 0:02:03 lr: 0.000010 loss: 2.6517 (2.6686) grad_norm: 3.4815 (nan) time: 0.5014 [2021-03-27 10:37:04 swin_small_patch4_window7_224] INFO: Epoch: [298] [1020/1251] eta: 0:01:58 lr: 0.000010 loss: 2.7559 (2.6692) grad_norm: 3.4815 (nan) time: 0.5035 [2021-03-27 10:37:09 swin_small_patch4_window7_224] INFO: Epoch: [298] [1030/1251] eta: 0:01:52 lr: 0.000010 loss: 2.7968 (2.6692) grad_norm: 3.4691 (nan) time: 0.5030 [2021-03-27 10:37:15 swin_small_patch4_window7_224] INFO: Epoch: [298] [1040/1251] eta: 0:01:47 lr: 0.000010 loss: 2.7759 (2.6683) grad_norm: 3.4618 (nan) time: 0.5114 [2021-03-27 10:37:20 swin_small_patch4_window7_224] INFO: Epoch: [298] [1050/1251] eta: 0:01:42 lr: 0.000010 loss: 2.6046 (2.6666) grad_norm: 3.2540 (nan) time: 0.5162 [2021-03-27 10:37:25 swin_small_patch4_window7_224] INFO: Epoch: [298] [1060/1251] eta: 0:01:37 lr: 0.000010 loss: 2.6421 (2.6681) grad_norm: 3.4440 (nan) time: 0.5070 [2021-03-27 10:37:30 swin_small_patch4_window7_224] INFO: Epoch: [298] [1070/1251] eta: 0:01:32 lr: 0.000010 loss: 2.9281 (2.6694) grad_norm: 3.5203 (nan) time: 0.5044 [2021-03-27 10:37:35 swin_small_patch4_window7_224] INFO: Epoch: [298] [1080/1251] eta: 0:01:27 lr: 0.000010 loss: 2.8655 (2.6708) grad_norm: 3.2509 (nan) time: 0.5004 [2021-03-27 10:37:40 swin_small_patch4_window7_224] INFO: Epoch: [298] [1090/1251] eta: 0:01:22 lr: 0.000010 loss: 2.8277 (2.6712) grad_norm: 3.2509 (nan) time: 0.5027 [2021-03-27 10:37:45 swin_small_patch4_window7_224] INFO: Epoch: [298] [1100/1251] eta: 0:01:17 lr: 0.000010 loss: 2.8000 (2.6725) grad_norm: 3.2742 (nan) time: 0.5062 [2021-03-27 10:37:50 swin_small_patch4_window7_224] INFO: Epoch: [298] [1110/1251] eta: 0:01:11 lr: 0.000010 loss: 2.8767 (2.6717) grad_norm: 3.4801 (nan) time: 0.4990 [2021-03-27 10:37:55 swin_small_patch4_window7_224] INFO: Epoch: [298] [1120/1251] eta: 0:01:06 lr: 0.000010 loss: 2.7735 (2.6723) grad_norm: 3.5825 (nan) time: 0.4961 [2021-03-27 10:38:00 swin_small_patch4_window7_224] INFO: Epoch: [298] [1130/1251] eta: 0:01:01 lr: 0.000010 loss: 2.8516 (2.6723) grad_norm: 3.6614 (nan) time: 0.5013 [2021-03-27 10:38:05 swin_small_patch4_window7_224] INFO: Epoch: [298] [1140/1251] eta: 0:00:56 lr: 0.000010 loss: 2.7953 (2.6717) grad_norm: 3.4490 (nan) time: 0.5028 [2021-03-27 10:38:10 swin_small_patch4_window7_224] INFO: Epoch: [298] [1150/1251] eta: 0:00:51 lr: 0.000010 loss: 2.4705 (2.6703) grad_norm: 3.4118 (nan) time: 0.4965 [2021-03-27 10:38:15 swin_small_patch4_window7_224] INFO: Epoch: [298] [1160/1251] eta: 0:00:46 lr: 0.000010 loss: 2.6782 (2.6711) grad_norm: 3.7920 (nan) time: 0.5108 [2021-03-27 10:38:20 swin_small_patch4_window7_224] INFO: Epoch: [298] [1170/1251] eta: 0:00:41 lr: 0.000010 loss: 2.6782 (2.6711) grad_norm: 4.0221 (nan) time: 0.5118 [2021-03-27 10:38:25 swin_small_patch4_window7_224] INFO: Epoch: [298] [1180/1251] eta: 0:00:36 lr: 0.000010 loss: 2.9186 (2.6738) grad_norm: 3.2489 (nan) time: 0.5001 [2021-03-27 10:38:30 swin_small_patch4_window7_224] INFO: Epoch: [298] [1190/1251] eta: 0:00:31 lr: 0.000010 loss: 2.8708 (2.6733) grad_norm: 3.2489 (nan) time: 0.5059 [2021-03-27 10:38:35 swin_small_patch4_window7_224] INFO: Epoch: [298] [1200/1251] eta: 0:00:26 lr: 0.000010 loss: 2.7711 (2.6741) grad_norm: 3.3016 (nan) time: 0.5042 [2021-03-27 10:38:40 swin_small_patch4_window7_224] INFO: Epoch: [298] [1210/1251] eta: 0:00:20 lr: 0.000010 loss: 2.7503 (2.6747) grad_norm: 3.3016 (nan) time: 0.5007 [2021-03-27 10:38:45 swin_small_patch4_window7_224] INFO: Epoch: [298] [1220/1251] eta: 0:00:15 lr: 0.000010 loss: 2.8436 (2.6746) grad_norm: 3.3021 (nan) time: 0.5039 [2021-03-27 10:38:50 swin_small_patch4_window7_224] INFO: Epoch: [298] [1230/1251] eta: 0:00:10 lr: 0.000010 loss: 2.7826 (2.6760) grad_norm: 3.3021 (nan) time: 0.5014 [2021-03-27 10:38:55 swin_small_patch4_window7_224] INFO: Epoch: [298] [1240/1251] eta: 0:00:05 lr: 0.000010 loss: 2.7660 (2.6766) grad_norm: 3.3712 (nan) time: 0.5069 [2021-03-27 10:39:01 swin_small_patch4_window7_224] INFO: Epoch: [298] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.6871 (2.6759) grad_norm: 3.3186 (nan) time: 0.5111 [2021-03-27 10:39:16 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:02:30 loss: 0.7531 (0.7531) acc1: 82.8125 (82.8125) acc5: 95.3125 (95.3125) [2021-03-27 10:39:18 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:19 loss: 0.7521 (0.7077) acc1: 82.8125 (82.3864) acc5: 96.8750 (97.3011) [2021-03-27 10:39:20 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:10 loss: 0.7521 (0.7525) acc1: 81.2500 (81.9940) acc5: 96.8750 (96.4286) [2021-03-27 10:39:23 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:06 loss: 0.7142 (0.7371) acc1: 82.8125 (82.2077) acc5: 96.8750 (96.3710) [2021-03-27 10:39:25 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:02 loss: 0.6708 (0.7256) acc1: 82.8125 (82.3552) acc5: 96.8750 (96.5701) [2021-03-27 10:39:25 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7297 (0.7495) acc1: 82.8125 (82.0800) acc5: 95.3125 (96.1600) [2021-03-27 10:39:45 swin_small_patch4_window7_224] INFO: * Acc@1 83.118 Acc@5 96.240 loss 0.734 [2021-03-27 10:39:45 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.1% [2021-03-27 10:39:45 swin_small_patch4_window7_224] INFO: Max accuracy: 83.16% [2021-03-27 10:39:49 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 0/1251] eta: 1:35:33 lr: 0.000010 loss: 2.7894 (2.7894) grad_norm: 3.6724 (3.6724) time: 4.5835 [2021-03-27 10:39:55 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 10/1251] eta: 0:18:20 lr: 0.000010 loss: 2.9864 (2.9439) grad_norm: 3.6689 (4.2510) time: 0.8864 [2021-03-27 10:40:00 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 20/1251] eta: 0:14:27 lr: 0.000010 loss: 2.8845 (2.9070) grad_norm: 3.4265 (3.7980) time: 0.5105 [2021-03-27 10:40:05 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 30/1251] eta: 0:13:07 lr: 0.000010 loss: 2.8372 (2.8504) grad_norm: 3.1676 (3.7572) time: 0.5117 [2021-03-27 10:40:10 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 40/1251] eta: 0:12:20 lr: 0.000010 loss: 2.8140 (2.8201) grad_norm: 3.2712 (3.6688) time: 0.5142 [2021-03-27 10:40:15 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 50/1251] eta: 0:11:48 lr: 0.000010 loss: 2.7965 (2.7670) grad_norm: 3.2712 (3.6518) time: 0.5053 [2021-03-27 10:40:20 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 60/1251] eta: 0:11:25 lr: 0.000010 loss: 2.4313 (2.6938) grad_norm: 3.2229 (3.6228) time: 0.5022 [2021-03-27 10:40:25 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 70/1251] eta: 0:11:08 lr: 0.000010 loss: 2.4806 (2.7089) grad_norm: 3.1498 (3.5932) time: 0.5046 [2021-03-27 10:40:30 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 80/1251] eta: 0:10:52 lr: 0.000010 loss: 2.8579 (2.7070) grad_norm: 3.3359 (3.5556) time: 0.5010 [2021-03-27 10:40:35 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 90/1251] eta: 0:10:40 lr: 0.000010 loss: 2.8209 (2.7085) grad_norm: 3.3760 (3.5475) time: 0.4999 [2021-03-27 10:40:40 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 100/1251] eta: 0:10:27 lr: 0.000010 loss: 2.7684 (2.6982) grad_norm: 3.2984 (3.5277) time: 0.4979 [2021-03-27 10:40:45 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 110/1251] eta: 0:10:18 lr: 0.000010 loss: 2.8555 (2.7099) grad_norm: 3.1915 (3.5044) time: 0.4989 [2021-03-27 10:40:50 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 120/1251] eta: 0:10:09 lr: 0.000010 loss: 2.9104 (2.7290) grad_norm: 3.3225 (3.6009) time: 0.5046 [2021-03-27 10:40:55 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 130/1251] eta: 0:10:03 lr: 0.000010 loss: 2.8152 (2.7180) grad_norm: 3.3488 (3.5849) time: 0.5209 [2021-03-27 10:41:01 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 140/1251] eta: 0:09:55 lr: 0.000010 loss: 2.7543 (2.7257) grad_norm: 3.1944 (3.5822) time: 0.5214 [2021-03-27 10:41:06 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 150/1251] eta: 0:09:48 lr: 0.000010 loss: 2.7747 (2.7210) grad_norm: 3.2275 (3.5870) time: 0.5040 [2021-03-27 10:41:11 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 160/1251] eta: 0:09:40 lr: 0.000010 loss: 2.6011 (2.7078) grad_norm: 3.1908 (3.6038) time: 0.5012 [2021-03-27 10:41:16 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 170/1251] eta: 0:09:33 lr: 0.000010 loss: 2.5647 (2.7077) grad_norm: 3.1908 (3.5930) time: 0.5057 [2021-03-27 10:41:21 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 180/1251] eta: 0:09:26 lr: 0.000010 loss: 2.6784 (2.6982) grad_norm: 3.3027 (3.5774) time: 0.5035 [2021-03-27 10:41:26 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 190/1251] eta: 0:09:19 lr: 0.000010 loss: 2.5375 (2.6935) grad_norm: 3.3027 (3.5706) time: 0.5014 [2021-03-27 10:41:31 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 200/1251] eta: 0:09:13 lr: 0.000010 loss: 2.6251 (2.6924) grad_norm: 3.2855 (3.5597) time: 0.5094 [2021-03-27 10:41:36 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 210/1251] eta: 0:09:07 lr: 0.000010 loss: 2.6251 (2.6888) grad_norm: 3.2953 (3.5516) time: 0.5058 [2021-03-27 10:41:41 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 220/1251] eta: 0:09:01 lr: 0.000010 loss: 2.5385 (2.6776) grad_norm: 3.3026 (3.5413) time: 0.5044 [2021-03-27 10:41:46 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 230/1251] eta: 0:08:55 lr: 0.000010 loss: 2.5997 (2.6790) grad_norm: 3.2846 (3.5330) time: 0.5081 [2021-03-27 10:41:51 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 240/1251] eta: 0:08:49 lr: 0.000010 loss: 2.6667 (2.6737) grad_norm: 3.2846 (3.5379) time: 0.5069 [2021-03-27 10:41:56 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 250/1251] eta: 0:08:42 lr: 0.000010 loss: 2.8029 (2.6861) grad_norm: 3.3098 (3.5340) time: 0.5013 [2021-03-27 10:42:01 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 260/1251] eta: 0:08:37 lr: 0.000010 loss: 2.7912 (2.6849) grad_norm: 3.3584 (3.5297) time: 0.5033 [2021-03-27 10:42:06 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 270/1251] eta: 0:08:31 lr: 0.000010 loss: 2.6779 (2.6801) grad_norm: 3.4129 (3.5185) time: 0.5040 [2021-03-27 10:42:11 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 280/1251] eta: 0:08:25 lr: 0.000010 loss: 2.8052 (2.6804) grad_norm: 3.4129 (3.5161) time: 0.5038 [2021-03-27 10:42:16 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 290/1251] eta: 0:08:19 lr: 0.000010 loss: 2.9163 (2.6786) grad_norm: 3.4716 (3.5504) time: 0.5049 [2021-03-27 10:42:21 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 300/1251] eta: 0:08:13 lr: 0.000010 loss: 2.5864 (2.6725) grad_norm: 3.4476 (3.5459) time: 0.5008 [2021-03-27 10:42:26 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 310/1251] eta: 0:08:08 lr: 0.000010 loss: 2.6331 (2.6744) grad_norm: 3.5878 (3.5561) time: 0.5085 [2021-03-27 10:42:31 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 320/1251] eta: 0:08:02 lr: 0.000010 loss: 2.7725 (2.6705) grad_norm: 3.4527 (3.5449) time: 0.5091 [2021-03-27 10:42:37 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 330/1251] eta: 0:07:57 lr: 0.000010 loss: 2.7119 (2.6712) grad_norm: 3.0965 (3.5424) time: 0.5081 [2021-03-27 10:42:41 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 340/1251] eta: 0:07:51 lr: 0.000010 loss: 2.8437 (2.6712) grad_norm: 3.5607 (inf) time: 0.5037 [2021-03-27 10:42:47 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 350/1251] eta: 0:07:46 lr: 0.000010 loss: 2.8375 (2.6728) grad_norm: 3.4144 (inf) time: 0.5001 [2021-03-27 10:42:52 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 360/1251] eta: 0:07:40 lr: 0.000010 loss: 2.6926 (2.6747) grad_norm: 3.3184 (inf) time: 0.5041 [2021-03-27 10:42:57 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 370/1251] eta: 0:07:35 lr: 0.000010 loss: 2.7452 (2.6763) grad_norm: 3.3608 (inf) time: 0.5015 [2021-03-27 10:43:02 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 380/1251] eta: 0:07:29 lr: 0.000010 loss: 2.7453 (2.6722) grad_norm: 3.3858 (inf) time: 0.5007 [2021-03-27 10:43:07 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 390/1251] eta: 0:07:24 lr: 0.000010 loss: 2.8102 (2.6796) grad_norm: 3.3858 (inf) time: 0.5014 [2021-03-27 10:43:12 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 400/1251] eta: 0:07:18 lr: 0.000010 loss: 2.8718 (2.6800) grad_norm: 3.5451 (inf) time: 0.5046 [2021-03-27 10:43:17 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 410/1251] eta: 0:07:13 lr: 0.000010 loss: 2.6614 (2.6823) grad_norm: 3.4153 (inf) time: 0.5018 [2021-03-27 10:43:22 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 420/1251] eta: 0:07:08 lr: 0.000010 loss: 2.7619 (2.6823) grad_norm: 3.2479 (inf) time: 0.5067 [2021-03-27 10:43:27 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 430/1251] eta: 0:07:02 lr: 0.000010 loss: 2.7619 (2.6839) grad_norm: 3.3652 (inf) time: 0.5158 [2021-03-27 10:43:32 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 440/1251] eta: 0:06:57 lr: 0.000010 loss: 2.6188 (2.6797) grad_norm: 3.3652 (inf) time: 0.5111 [2021-03-27 10:43:37 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 450/1251] eta: 0:06:52 lr: 0.000010 loss: 2.5639 (2.6743) grad_norm: 3.3002 (inf) time: 0.5085 [2021-03-27 10:43:42 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 460/1251] eta: 0:06:46 lr: 0.000010 loss: 2.5947 (2.6745) grad_norm: 3.5825 (inf) time: 0.5042 [2021-03-27 10:43:47 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 470/1251] eta: 0:06:41 lr: 0.000010 loss: 2.6824 (2.6756) grad_norm: 3.5467 (inf) time: 0.4986 [2021-03-27 10:43:52 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 480/1251] eta: 0:06:36 lr: 0.000010 loss: 2.6824 (2.6736) grad_norm: 3.4481 (inf) time: 0.5108 [2021-03-27 10:43:57 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 490/1251] eta: 0:06:31 lr: 0.000010 loss: 2.7096 (2.6735) grad_norm: 3.2372 (inf) time: 0.5119 [2021-03-27 10:44:02 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 500/1251] eta: 0:06:25 lr: 0.000010 loss: 2.7158 (2.6692) grad_norm: 3.2903 (inf) time: 0.5024 [2021-03-27 10:44:07 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 510/1251] eta: 0:06:20 lr: 0.000010 loss: 2.7158 (2.6710) grad_norm: 3.3570 (inf) time: 0.5051 [2021-03-27 10:44:13 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 520/1251] eta: 0:06:15 lr: 0.000010 loss: 2.7613 (2.6724) grad_norm: 3.2779 (inf) time: 0.5079 [2021-03-27 10:44:18 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 530/1251] eta: 0:06:10 lr: 0.000010 loss: 2.6280 (2.6687) grad_norm: 3.2766 (inf) time: 0.5052 [2021-03-27 10:44:23 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 540/1251] eta: 0:06:04 lr: 0.000010 loss: 2.6293 (2.6679) grad_norm: 3.2383 (inf) time: 0.5014 [2021-03-27 10:44:28 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 550/1251] eta: 0:05:59 lr: 0.000010 loss: 2.7282 (2.6715) grad_norm: 3.3068 (inf) time: 0.5105 [2021-03-27 10:44:33 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 560/1251] eta: 0:05:54 lr: 0.000010 loss: 2.8567 (2.6755) grad_norm: 3.4516 (inf) time: 0.5199 [2021-03-27 10:44:38 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 570/1251] eta: 0:05:49 lr: 0.000010 loss: 2.7910 (2.6754) grad_norm: 3.5096 (inf) time: 0.5164 [2021-03-27 10:44:43 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 580/1251] eta: 0:05:44 lr: 0.000010 loss: 2.7898 (2.6799) grad_norm: 3.3235 (inf) time: 0.5074 [2021-03-27 10:44:48 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 590/1251] eta: 0:05:39 lr: 0.000010 loss: 2.7950 (2.6778) grad_norm: 3.3522 (inf) time: 0.5121 [2021-03-27 10:44:54 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 600/1251] eta: 0:05:34 lr: 0.000010 loss: 2.7950 (2.6797) grad_norm: 3.3156 (inf) time: 0.5196 [2021-03-27 10:44:59 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 610/1251] eta: 0:05:28 lr: 0.000010 loss: 2.8735 (2.6810) grad_norm: 3.4444 (inf) time: 0.5076 [2021-03-27 10:45:03 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 620/1251] eta: 0:05:23 lr: 0.000010 loss: 2.7731 (2.6821) grad_norm: 3.4444 (inf) time: 0.4976 [2021-03-27 10:45:09 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 630/1251] eta: 0:05:18 lr: 0.000010 loss: 2.7073 (2.6813) grad_norm: 3.3793 (inf) time: 0.5001 [2021-03-27 10:45:14 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 640/1251] eta: 0:05:13 lr: 0.000010 loss: 2.7073 (2.6826) grad_norm: 3.4014 (inf) time: 0.5022 [2021-03-27 10:45:19 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 650/1251] eta: 0:05:07 lr: 0.000010 loss: 2.8833 (2.6844) grad_norm: 3.7442 (inf) time: 0.5037 [2021-03-27 10:45:24 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 660/1251] eta: 0:05:02 lr: 0.000010 loss: 2.8383 (2.6858) grad_norm: 3.7680 (inf) time: 0.5038 [2021-03-27 10:45:29 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 670/1251] eta: 0:04:57 lr: 0.000010 loss: 2.6678 (2.6815) grad_norm: 3.7125 (inf) time: 0.5076 [2021-03-27 10:45:34 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 680/1251] eta: 0:04:52 lr: 0.000010 loss: 2.3672 (2.6816) grad_norm: 3.2621 (inf) time: 0.5152 [2021-03-27 10:45:39 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 690/1251] eta: 0:04:47 lr: 0.000010 loss: 2.7342 (2.6810) grad_norm: 3.2100 (inf) time: 0.5061 [2021-03-27 10:45:44 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 700/1251] eta: 0:04:42 lr: 0.000010 loss: 2.7495 (2.6814) grad_norm: 3.1428 (inf) time: 0.5009 [2021-03-27 10:45:49 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 710/1251] eta: 0:04:37 lr: 0.000010 loss: 2.8417 (2.6819) grad_norm: 3.1505 (inf) time: 0.5087 [2021-03-27 10:45:54 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 720/1251] eta: 0:04:31 lr: 0.000010 loss: 2.8364 (2.6823) grad_norm: 3.3552 (inf) time: 0.5042 [2021-03-27 10:45:59 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 730/1251] eta: 0:04:26 lr: 0.000010 loss: 2.7098 (2.6810) grad_norm: 3.3975 (inf) time: 0.5002 [2021-03-27 10:46:04 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 740/1251] eta: 0:04:21 lr: 0.000010 loss: 2.8897 (2.6835) grad_norm: 3.2880 (inf) time: 0.5163 [2021-03-27 10:46:10 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 750/1251] eta: 0:04:16 lr: 0.000010 loss: 2.8592 (2.6820) grad_norm: 3.2577 (inf) time: 0.5228 [2021-03-27 10:46:15 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 760/1251] eta: 0:04:11 lr: 0.000010 loss: 2.7681 (2.6834) grad_norm: 3.1928 (inf) time: 0.5121 [2021-03-27 10:46:20 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 770/1251] eta: 0:04:06 lr: 0.000010 loss: 2.7741 (2.6841) grad_norm: 3.1391 (inf) time: 0.5069 [2021-03-27 10:46:25 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 780/1251] eta: 0:04:01 lr: 0.000010 loss: 2.7741 (2.6844) grad_norm: 3.1646 (inf) time: 0.5111 [2021-03-27 10:46:30 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 790/1251] eta: 0:03:56 lr: 0.000010 loss: 2.7436 (2.6838) grad_norm: 3.0610 (inf) time: 0.5153 [2021-03-27 10:46:35 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 800/1251] eta: 0:03:50 lr: 0.000010 loss: 2.5232 (2.6828) grad_norm: 3.2166 (inf) time: 0.5096 [2021-03-27 10:46:40 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 810/1251] eta: 0:03:45 lr: 0.000010 loss: 2.6898 (2.6844) grad_norm: 3.2599 (inf) time: 0.5035 [2021-03-27 10:46:45 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 820/1251] eta: 0:03:40 lr: 0.000010 loss: 2.6891 (2.6827) grad_norm: 3.2077 (inf) time: 0.5060 [2021-03-27 10:46:50 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 830/1251] eta: 0:03:35 lr: 0.000010 loss: 2.6891 (2.6845) grad_norm: 3.2077 (inf) time: 0.5076 [2021-03-27 10:46:55 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 840/1251] eta: 0:03:30 lr: 0.000010 loss: 2.8232 (2.6849) grad_norm: 3.3070 (inf) time: 0.5034 [2021-03-27 10:47:00 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 850/1251] eta: 0:03:25 lr: 0.000010 loss: 2.7143 (2.6838) grad_norm: 3.3401 (inf) time: 0.5016 [2021-03-27 10:47:05 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 860/1251] eta: 0:03:19 lr: 0.000010 loss: 2.6462 (2.6839) grad_norm: 3.2660 (inf) time: 0.5004 [2021-03-27 10:47:11 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 870/1251] eta: 0:03:14 lr: 0.000010 loss: 2.6782 (2.6831) grad_norm: 3.2828 (inf) time: 0.5136 [2021-03-27 10:47:16 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 880/1251] eta: 0:03:09 lr: 0.000010 loss: 2.6991 (2.6836) grad_norm: 3.2828 (inf) time: 0.5239 [2021-03-27 10:47:21 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 890/1251] eta: 0:03:04 lr: 0.000010 loss: 2.6009 (2.6820) grad_norm: 3.3123 (inf) time: 0.5125 [2021-03-27 10:47:26 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 900/1251] eta: 0:02:59 lr: 0.000010 loss: 2.6880 (2.6833) grad_norm: 3.3618 (inf) time: 0.5051 [2021-03-27 10:47:31 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 910/1251] eta: 0:02:54 lr: 0.000010 loss: 2.6880 (2.6823) grad_norm: 3.2347 (inf) time: 0.5025 [2021-03-27 10:47:36 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 920/1251] eta: 0:02:49 lr: 0.000010 loss: 2.6612 (2.6823) grad_norm: 3.2745 (inf) time: 0.4973 [2021-03-27 10:47:41 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 930/1251] eta: 0:02:44 lr: 0.000010 loss: 2.8522 (2.6825) grad_norm: 3.4913 (inf) time: 0.4969 [2021-03-27 10:47:46 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 940/1251] eta: 0:02:38 lr: 0.000010 loss: 2.6479 (2.6792) grad_norm: 3.5257 (inf) time: 0.4998 [2021-03-27 10:47:51 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 950/1251] eta: 0:02:33 lr: 0.000010 loss: 2.6479 (2.6772) grad_norm: 3.5577 (inf) time: 0.5090 [2021-03-27 10:47:56 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 960/1251] eta: 0:02:28 lr: 0.000010 loss: 2.7267 (2.6760) grad_norm: 3.1804 (inf) time: 0.5124 [2021-03-27 10:48:01 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 970/1251] eta: 0:02:23 lr: 0.000010 loss: 2.7267 (2.6756) grad_norm: 3.1472 (inf) time: 0.5053 [2021-03-27 10:48:06 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 980/1251] eta: 0:02:18 lr: 0.000010 loss: 2.7095 (2.6758) grad_norm: 3.2341 (nan) time: 0.4976 [2021-03-27 10:48:11 swin_small_patch4_window7_224] INFO: Epoch: [299] [ 990/1251] eta: 0:02:13 lr: 0.000010 loss: 2.6243 (2.6756) grad_norm: 3.3721 (nan) time: 0.4996 [2021-03-27 10:48:16 swin_small_patch4_window7_224] INFO: Epoch: [299] [1000/1251] eta: 0:02:08 lr: 0.000010 loss: 2.5829 (2.6735) grad_norm: 3.4106 (nan) time: 0.5077 [2021-03-27 10:48:21 swin_small_patch4_window7_224] INFO: Epoch: [299] [1010/1251] eta: 0:02:03 lr: 0.000010 loss: 2.7359 (2.6759) grad_norm: 3.3196 (nan) time: 0.5036 [2021-03-27 10:48:26 swin_small_patch4_window7_224] INFO: Epoch: [299] [1020/1251] eta: 0:01:57 lr: 0.000010 loss: 2.9595 (2.6776) grad_norm: 3.4626 (nan) time: 0.5026 [2021-03-27 10:48:31 swin_small_patch4_window7_224] INFO: Epoch: [299] [1030/1251] eta: 0:01:52 lr: 0.000010 loss: 2.8874 (2.6784) grad_norm: 3.6952 (nan) time: 0.5107 [2021-03-27 10:48:36 swin_small_patch4_window7_224] INFO: Epoch: [299] [1040/1251] eta: 0:01:47 lr: 0.000010 loss: 2.7400 (2.6774) grad_norm: 3.5048 (nan) time: 0.5108 [2021-03-27 10:48:41 swin_small_patch4_window7_224] INFO: Epoch: [299] [1050/1251] eta: 0:01:42 lr: 0.000010 loss: 2.5118 (2.6765) grad_norm: 3.1689 (nan) time: 0.4996 [2021-03-27 10:48:46 swin_small_patch4_window7_224] INFO: Epoch: [299] [1060/1251] eta: 0:01:37 lr: 0.000010 loss: 2.5849 (2.6761) grad_norm: 3.1317 (nan) time: 0.4965 [2021-03-27 10:48:51 swin_small_patch4_window7_224] INFO: Epoch: [299] [1070/1251] eta: 0:01:32 lr: 0.000010 loss: 2.6960 (2.6755) grad_norm: 3.2966 (nan) time: 0.5045 [2021-03-27 10:48:56 swin_small_patch4_window7_224] INFO: Epoch: [299] [1080/1251] eta: 0:01:27 lr: 0.000010 loss: 2.6759 (2.6738) grad_norm: 3.2905 (nan) time: 0.5073 [2021-03-27 10:49:01 swin_small_patch4_window7_224] INFO: Epoch: [299] [1090/1251] eta: 0:01:22 lr: 0.000010 loss: 2.6759 (2.6749) grad_norm: 3.2574 (nan) time: 0.5028 [2021-03-27 10:49:06 swin_small_patch4_window7_224] INFO: Epoch: [299] [1100/1251] eta: 0:01:16 lr: 0.000010 loss: 2.8964 (2.6752) grad_norm: 3.3339 (nan) time: 0.4964 [2021-03-27 10:49:11 swin_small_patch4_window7_224] INFO: Epoch: [299] [1110/1251] eta: 0:01:11 lr: 0.000010 loss: 2.8878 (2.6754) grad_norm: 3.2468 (nan) time: 0.4954 [2021-03-27 10:49:16 swin_small_patch4_window7_224] INFO: Epoch: [299] [1120/1251] eta: 0:01:06 lr: 0.000010 loss: 2.6771 (2.6739) grad_norm: 3.2118 (nan) time: 0.5011 [2021-03-27 10:49:21 swin_small_patch4_window7_224] INFO: Epoch: [299] [1130/1251] eta: 0:01:01 lr: 0.000010 loss: 2.8248 (2.6744) grad_norm: 3.2118 (nan) time: 0.5005 [2021-03-27 10:49:26 swin_small_patch4_window7_224] INFO: Epoch: [299] [1140/1251] eta: 0:00:56 lr: 0.000010 loss: 2.8248 (2.6737) grad_norm: 3.3019 (nan) time: 0.4993 [2021-03-27 10:49:31 swin_small_patch4_window7_224] INFO: Epoch: [299] [1150/1251] eta: 0:00:51 lr: 0.000010 loss: 2.7677 (2.6757) grad_norm: 3.3019 (nan) time: 0.5005 [2021-03-27 10:49:36 swin_small_patch4_window7_224] INFO: Epoch: [299] [1160/1251] eta: 0:00:46 lr: 0.000010 loss: 2.8180 (2.6757) grad_norm: 3.2513 (nan) time: 0.5029 [2021-03-27 10:49:42 swin_small_patch4_window7_224] INFO: Epoch: [299] [1170/1251] eta: 0:00:41 lr: 0.000010 loss: 2.8458 (2.6775) grad_norm: 3.3095 (nan) time: 0.5039 [2021-03-27 10:49:47 swin_small_patch4_window7_224] INFO: Epoch: [299] [1180/1251] eta: 0:00:36 lr: 0.000010 loss: 2.9467 (2.6777) grad_norm: 3.2473 (nan) time: 0.5072 [2021-03-27 10:49:52 swin_small_patch4_window7_224] INFO: Epoch: [299] [1190/1251] eta: 0:00:31 lr: 0.000010 loss: 2.6036 (2.6749) grad_norm: 3.2458 (nan) time: 0.5092 [2021-03-27 10:49:57 swin_small_patch4_window7_224] INFO: Epoch: [299] [1200/1251] eta: 0:00:25 lr: 0.000010 loss: 2.3440 (2.6731) grad_norm: 3.2714 (nan) time: 0.4999 [2021-03-27 10:50:02 swin_small_patch4_window7_224] INFO: Epoch: [299] [1210/1251] eta: 0:00:20 lr: 0.000010 loss: 2.7049 (2.6739) grad_norm: 3.3890 (nan) time: 0.5005 [2021-03-27 10:50:07 swin_small_patch4_window7_224] INFO: Epoch: [299] [1220/1251] eta: 0:00:15 lr: 0.000010 loss: 2.8477 (2.6743) grad_norm: 3.6782 (nan) time: 0.5016 [2021-03-27 10:50:12 swin_small_patch4_window7_224] INFO: Epoch: [299] [1230/1251] eta: 0:00:10 lr: 0.000010 loss: 2.7806 (2.6755) grad_norm: 3.6970 (nan) time: 0.5080 [2021-03-27 10:50:17 swin_small_patch4_window7_224] INFO: Epoch: [299] [1240/1251] eta: 0:00:05 lr: 0.000010 loss: 2.7385 (2.6747) grad_norm: 3.5382 (nan) time: 0.5063 [2021-03-27 10:50:22 swin_small_patch4_window7_224] INFO: Epoch: [299] [1250/1251] eta: 0:00:00 lr: 0.000010 loss: 2.8104 (2.6768) grad_norm: 3.5199 (nan) time: 0.4916 [2021-03-27 10:51:23 swin_small_patch4_window7_224] INFO: Test: [ 0/49] eta: 0:01:10 loss: 1.0882 (1.0882) acc1: 73.4375 (73.4375) acc5: 92.1875 (92.1875) [2021-03-27 10:51:24 swin_small_patch4_window7_224] INFO: Test: [10/49] eta: 0:00:08 loss: 0.7896 (0.7912) acc1: 81.2500 (81.3920) acc5: 95.3125 (95.7386) [2021-03-27 10:51:25 swin_small_patch4_window7_224] INFO: Test: [20/49] eta: 0:00:04 loss: 0.7896 (0.7932) acc1: 81.2500 (81.5476) acc5: 95.3125 (95.6845) [2021-03-27 10:51:26 swin_small_patch4_window7_224] INFO: Test: [30/49] eta: 0:00:02 loss: 0.7787 (0.7760) acc1: 81.2500 (81.5524) acc5: 95.3125 (95.8165) [2021-03-27 10:51:27 swin_small_patch4_window7_224] INFO: Test: [40/49] eta: 0:00:01 loss: 0.6884 (0.7469) acc1: 82.8125 (82.2027) acc5: 96.8750 (96.2271) [2021-03-27 10:51:28 swin_small_patch4_window7_224] INFO: Test: [48/49] eta: 0:00:00 loss: 0.7544 (0.7520) acc1: 82.8125 (82.1120) acc5: 96.8750 (96.1280) [2021-03-27 10:51:42 swin_small_patch4_window7_224] INFO: * Acc@1 83.186 Acc@5 96.236 loss 0.734 [2021-03-27 10:51:42 swin_small_patch4_window7_224] INFO: Accuracy of the network on the 50000 test images: 83.2% [2021-03-27 10:51:42 swin_small_patch4_window7_224] INFO: Max accuracy: 83.19%